diff --git a/Documentation/DocBook/crypto-API.tmpl b/Documentation/DocBook/crypto-API.tmpl
index d55dc5a..fb2a152 100644
--- a/Documentation/DocBook/crypto-API.tmpl
+++ b/Documentation/DocBook/crypto-API.tmpl
@@ -440,8 +440,8 @@
      The type flag specifies the type of the cipher algorithm.
      The caller usually provides a 0 when the caller wants the
      default handling. Otherwise, the caller may provide the
-     following selections which match the the aforementioned
-     cipher types:
+     following selections which match the aforementioned cipher
+     types:
     </para>
 
     <itemizedlist>
diff --git a/Documentation/crypto/asymmetric-keys.txt b/Documentation/crypto/asymmetric-keys.txt
index 8c07e0e..2b7816d 100644
--- a/Documentation/crypto/asymmetric-keys.txt
+++ b/Documentation/crypto/asymmetric-keys.txt
@@ -76,7 +76,7 @@
 Looking in /proc/keys, the last 8 hex digits of the key fingerprint are
 displayed, along with the subtype:
 
-	1a39e171 I-----     1 perm 3f010000     0     0 asymmetri modsign.0: DSA 5acc2142 []
+	1a39e171 I-----     1 perm 3f010000     0     0 asymmetric modsign.0: DSA 5acc2142 []
 
 
 =========================
diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt b/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
index 07ccdaa..2654269 100644
--- a/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
+++ b/Documentation/devicetree/bindings/rng/brcm,bcm2835.txt
@@ -2,7 +2,8 @@
 
 Required properties:
 
-- compatible : should be "brcm,bcm2835-rng"
+- compatible : should be "brcm,bcm2835-rng"  or "brcm,bcm-nsp-rng" or
+  "brcm,bcm5301x-rng"
 - reg : Specifies base physical address and size of the registers.
 
 Example:
@@ -11,3 +12,8 @@
         compatible = "brcm,bcm2835-rng";
         reg = <0x7e104000 0x10>;
 };
+
+rng@18033000 {
+	compatible = "brcm,bcm-nsp-rng";
+	reg = <0x18033000 0x14>;
+};
diff --git a/MAINTAINERS b/MAINTAINERS
index 92a3f42..531c600 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3286,6 +3286,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6.git
 S:	Maintained
 F:	Documentation/crypto/
+F:	Documentation/devicetree/bindings/crypto/
 F:	Documentation/DocBook/crypto-API.tmpl
 F:	arch/*/crypto/
 F:	crypto/
@@ -5273,6 +5274,7 @@
 M:	Herbert Xu <herbert@gondor.apana.org.au>
 L:	linux-crypto@vger.kernel.org
 S:	Odd fixes
+F:	Documentation/devicetree/bindings/rng/
 F:	Documentation/hw_random.txt
 F:	drivers/char/hw_random/
 F:	include/linux/hw_random.h
@@ -9318,7 +9320,8 @@
 S:	Maintained
 
 QAT DRIVER
-M:	Tadeusz Struk <tadeusz.struk@intel.com>
+M:	Giovanni Cabiddu <giovanni.cabiddu@intel.com>
+M:	Salvatore Benedetto <salvatore.benedetto@intel.com>
 L:	qat-linux@intel.com
 S:	Supported
 F:	drivers/crypto/qat/
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index def9e78..1ed829e 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -206,6 +206,11 @@
 			brcm,nand-has-wp;
 		};
 
+		rng: rng@33000 {
+			compatible = "brcm,bcm-nsp-rng";
+			reg = <0x33000 0x14>;
+		};
+
 		ccbtimer0: timer@34000 {
 			compatible = "arm,sp804";
 			reg = <0x34000 0x1000>;
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 03a39fe..1568cb5 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -154,30 +154,23 @@
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
-	if (!may_use_simd()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_init(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return crypto_shash_init(desc);
-	}
+	desc->tfm = child;
+	desc->flags = req->base.flags;
+	return crypto_shash_init(desc);
 }
 
 static int ghash_async_update(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_update(cryptd_req);
@@ -190,12 +183,12 @@
 static int ghash_async_final(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_final(cryptd_req);
@@ -212,7 +205,8 @@
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_digest(cryptd_req);
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
index f895fc0..4084631 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
@@ -49,6 +49,10 @@
 
 / {
 	model = "LS1043A RDB Board";
+
+	aliases {
+		crypto = &crypto;
+	};
 };
 
 &i2c0 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index de0323b..6bd46c1 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -159,6 +159,49 @@
 			big-endian;
 		};
 
+		crypto: crypto@1700000 {
+			compatible = "fsl,sec-v5.4", "fsl,sec-v5.0",
+				     "fsl,sec-v4.0";
+			fsl,sec-era = <3>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x00 0x1700000 0x100000>;
+			reg = <0x00 0x1700000 0x0 0x100000>;
+			interrupts = <0 75 0x4>;
+
+			sec_jr0: jr@10000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x10000 0x10000>;
+				interrupts = <0 71 0x4>;
+			};
+
+			sec_jr1: jr@20000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x20000 0x10000>;
+				interrupts = <0 72 0x4>;
+			};
+
+			sec_jr2: jr@30000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x30000 0x10000>;
+				interrupts = <0 73 0x4>;
+			};
+
+			sec_jr3: jr@40000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x40000 0x10000>;
+				interrupts = <0 74 0x4>;
+			};
+		};
+
 		dcfg: dcfg@1ee0000 {
 			compatible = "fsl,ls1043a-dcfg", "syscon";
 			reg = <0x0 0x1ee0000 0x0 0x10000>;
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 44be1e0..9b6e408 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -174,13 +174,15 @@
 #define iounmap				__iounmap
 
 /*
- * io{read,write}{16,32}be() macros
+ * io{read,write}{16,32,64}be() macros
  */
 #define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
 #define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+#define ioread64be(p)		({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; })
 
 #define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
 #define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
+#define iowrite64be(v,p)	({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 9c221b6..7998c17 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -9,9 +9,11 @@
 obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
 obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
+obj-$(CONFIG_CRYPT_CRC32C_VPMSUM) += crc32c-vpmsum.o
 
 aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
 md5-ppc-y := md5-asm.o md5-glue.o
 sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
 sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
+crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/aes-spe-regs.h b/arch/powerpc/crypto/aes-spe-regs.h
index 30d217b..2cc3a2c 100644
--- a/arch/powerpc/crypto/aes-spe-regs.h
+++ b/arch/powerpc/crypto/aes-spe-regs.h
@@ -18,7 +18,7 @@
 #define rLN r7	/* length of data to be processed			*/
 #define rIP r8	/* potiner to IV (CBC/CTR/XTS modes)			*/
 #define rKT r9	/* pointer to tweak key (XTS mode)			*/
-#define rT0 r11	/* pointers to en-/decrpytion tables			*/
+#define rT0 r11	/* pointers to en-/decryption tables			*/
 #define rT1 r10
 #define rD0 r9	/* data 						*/
 #define rD1 r14
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
new file mode 100644
index 0000000..dc640b2
--- /dev/null
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -0,0 +1,1553 @@
+/*
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * We then use fixed point Barrett reduction to compute a mod n over GF(2)
+ * for n = CRC using POWER8 instructions. We use x = 32.
+ *
+ * http://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * 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/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+	.section	.rodata
+.balign 16
+
+.byteswap_constant:
+	/* byte reverse permute constant */
+	.octa 0x0F0E0D0C0B0A09080706050403020100
+
+#define MAX_SIZE	32768
+.constants:
+
+	/* Reduce 262144 kbits to 1024 bits */
+	/* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
+	.octa 0x00000000b6ca9e20000000009c37c408
+
+	/* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
+	.octa 0x00000000350249a800000001b51df26c
+
+	/* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
+	.octa 0x00000001862dac54000000000724b9d0
+
+	/* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
+	.octa 0x00000001d87fb48c00000001c00532fe
+
+	/* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
+	.octa 0x00000001f39b699e00000000f05a9362
+
+	/* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
+	.octa 0x0000000101da11b400000001e1007970
+
+	/* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
+	.octa 0x00000001cab571e000000000a57366ee
+
+	/* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
+	.octa 0x00000000c7020cfe0000000192011284
+
+	/* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
+	.octa 0x00000000cdaed1ae0000000162716d9a
+
+	/* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
+	.octa 0x00000001e804effc00000000cd97ecde
+
+	/* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
+	.octa 0x0000000077c3ea3a0000000058812bc0
+
+	/* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
+	.octa 0x0000000068df31b40000000088b8c12e
+
+	/* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
+	.octa 0x00000000b059b6c200000001230b234c
+
+	/* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
+	.octa 0x0000000145fb8ed800000001120b416e
+
+	/* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
+	.octa 0x00000000cbc0916800000001974aecb0
+
+	/* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
+	.octa 0x000000005ceeedc2000000008ee3f226
+
+	/* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
+	.octa 0x0000000047d74e8600000001089aba9a
+
+	/* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
+	.octa 0x00000001407e9e220000000065113872
+
+	/* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
+	.octa 0x00000001da967bda000000005c07ec10
+
+	/* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
+	.octa 0x000000006c8983680000000187590924
+
+	/* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
+	.octa 0x00000000f2d14c9800000000e35da7c6
+
+	/* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
+	.octa 0x00000001993c6ad4000000000415855a
+
+	/* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
+	.octa 0x000000014683d1ac0000000073617758
+
+	/* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
+	.octa 0x00000001a7c93e6c0000000176021d28
+
+	/* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
+	.octa 0x000000010211e90a00000001c358fd0a
+
+	/* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
+	.octa 0x000000001119403e00000001ff7a2c18
+
+	/* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
+	.octa 0x000000001c3261aa00000000f2d9f7e4
+
+	/* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
+	.octa 0x000000014e37a634000000016cf1f9c8
+
+	/* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
+	.octa 0x0000000073786c0c000000010af9279a
+
+	/* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
+	.octa 0x000000011dc037f80000000004f101e8
+
+	/* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
+	.octa 0x0000000031433dfc0000000070bcf184
+
+	/* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
+	.octa 0x000000009cde8348000000000a8de642
+
+	/* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
+	.octa 0x0000000038d3c2a60000000062ea130c
+
+	/* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
+	.octa 0x000000011b25f26000000001eb31cbb2
+
+	/* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
+	.octa 0x000000001629e6f00000000170783448
+
+	/* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
+	.octa 0x0000000160838b4c00000001a684b4c6
+
+	/* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
+	.octa 0x000000007a44011c00000000253ca5b4
+
+	/* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
+	.octa 0x00000000226f417a0000000057b4b1e2
+
+	/* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
+	.octa 0x0000000045eb2eb400000000b6bd084c
+
+	/* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
+	.octa 0x000000014459d70c0000000123c2d592
+
+	/* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
+	.octa 0x00000001d406ed8200000000159dafce
+
+	/* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
+	.octa 0x0000000160c8e1a80000000127e1a64e
+
+	/* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
+	.octa 0x0000000027ba80980000000056860754
+
+	/* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
+	.octa 0x000000006d92d01800000001e661aae8
+
+	/* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
+	.octa 0x000000012ed7e3f200000000f82c6166
+
+	/* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
+	.octa 0x000000002dc8778800000000c4f9c7ae
+
+	/* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
+	.octa 0x0000000018240bb80000000074203d20
+
+	/* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
+	.octa 0x000000001ad381580000000198173052
+
+	/* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
+	.octa 0x00000001396b78f200000001ce8aba54
+
+	/* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
+	.octa 0x000000011a68133400000001850d5d94
+
+	/* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
+	.octa 0x000000012104732e00000001d609239c
+
+	/* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
+	.octa 0x00000000a140d90c000000001595f048
+
+	/* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
+	.octa 0x00000001b7215eda0000000042ccee08
+
+	/* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
+	.octa 0x00000001aaf1df3c000000010a389d74
+
+	/* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
+	.octa 0x0000000029d15b8a000000012a840da6
+
+	/* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
+	.octa 0x00000000f1a96922000000001d181c0c
+
+	/* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
+	.octa 0x00000001ac80d03c0000000068b7d1f6
+
+	/* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
+	.octa 0x000000000f11d56a000000005b0f14fc
+
+	/* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
+	.octa 0x00000001f1c022a20000000179e9e730
+
+	/* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
+	.octa 0x0000000173d00ae200000001ce1368d6
+
+	/* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
+	.octa 0x00000001d4ffe4ac0000000112c3a84c
+
+	/* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
+	.octa 0x000000016edc5ae400000000de940fee
+
+	/* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
+	.octa 0x00000001f1a0214000000000fe896b7e
+
+	/* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
+	.octa 0x00000000ca0b28a000000001f797431c
+
+	/* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
+	.octa 0x00000001928e30a20000000053e989ba
+
+	/* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
+	.octa 0x0000000097b1b002000000003920cd16
+
+	/* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
+	.octa 0x00000000b15bf90600000001e6f579b8
+
+	/* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
+	.octa 0x00000000411c5d52000000007493cb0a
+
+	/* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
+	.octa 0x00000001c36f330000000001bdd376d8
+
+	/* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
+	.octa 0x00000001119227e0000000016badfee6
+
+	/* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
+	.octa 0x00000000114d47020000000071de5c58
+
+	/* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
+	.octa 0x00000000458b5b9800000000453f317c
+
+	/* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
+	.octa 0x000000012e31fb8e0000000121675cce
+
+	/* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
+	.octa 0x000000005cf619d800000001f409ee92
+
+	/* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
+	.octa 0x0000000063f4d8b200000000f36b9c88
+
+	/* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
+	.octa 0x000000004138dc8a0000000036b398f4
+
+	/* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
+	.octa 0x00000001d29ee8e000000001748f9adc
+
+	/* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
+	.octa 0x000000006a08ace800000001be94ec00
+
+	/* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
+	.octa 0x0000000127d4201000000000b74370d6
+
+	/* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
+	.octa 0x0000000019d76b6200000001174d0b98
+
+	/* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
+	.octa 0x00000001b1471f6e00000000befc06a4
+
+	/* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
+	.octa 0x00000001f64c19cc00000001ae125288
+
+	/* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
+	.octa 0x00000000003c0ea00000000095c19b34
+
+	/* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
+	.octa 0x000000014d73abf600000001a78496f2
+
+	/* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
+	.octa 0x00000001620eb84400000001ac5390a0
+
+	/* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
+	.octa 0x0000000147655048000000002a80ed6e
+
+	/* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
+	.octa 0x0000000067b5077e00000001fa9b0128
+
+	/* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
+	.octa 0x0000000010ffe20600000001ea94929e
+
+	/* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
+	.octa 0x000000000fee8f1e0000000125f4305c
+
+	/* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
+	.octa 0x00000001da26fbae00000001471e2002
+
+	/* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
+	.octa 0x00000001b3a8bd880000000132d2253a
+
+	/* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
+	.octa 0x00000000e8f3898e00000000f26b3592
+
+	/* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
+	.octa 0x00000000b0d0d28c00000000bc8b67b0
+
+	/* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
+	.octa 0x0000000030f2a798000000013a826ef2
+
+	/* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
+	.octa 0x000000000fba10020000000081482c84
+
+	/* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
+	.octa 0x00000000bdb9bd7200000000e77307c2
+
+	/* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
+	.octa 0x0000000075d3bf5a00000000d4a07ec8
+
+	/* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
+	.octa 0x00000000ef1f98a00000000017102100
+
+	/* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
+	.octa 0x00000000689c760200000000db406486
+
+	/* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
+	.octa 0x000000016d5fa5fe0000000192db7f88
+
+	/* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
+	.octa 0x00000001d0d2b9ca000000018bf67b1e
+
+	/* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
+	.octa 0x0000000041e7b470000000007c09163e
+
+	/* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
+	.octa 0x00000001cbb6495e000000000adac060
+
+	/* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
+	.octa 0x000000010052a0b000000000bd8316ae
+
+	/* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
+	.octa 0x00000001d8effb5c000000019f09ab54
+
+	/* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
+	.octa 0x00000001d969853c0000000125155542
+
+	/* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
+	.octa 0x00000000523ccce2000000018fdb5882
+
+	/* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
+	.octa 0x000000001e2436bc00000000e794b3f4
+
+	/* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
+	.octa 0x00000000ddd1c3a2000000016f9bb022
+
+	/* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
+	.octa 0x0000000019fcfe3800000000290c9978
+
+	/* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
+	.octa 0x00000001ce95db640000000083c0f350
+
+	/* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */
+	.octa 0x00000000af5828060000000173ea6628
+
+	/* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */
+	.octa 0x00000001006388f600000001c8b4e00a
+
+	/* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */
+	.octa 0x0000000179eca00a00000000de95d6aa
+
+	/* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */
+	.octa 0x0000000122410a6a000000010b7f7248
+
+	/* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */
+	.octa 0x000000004288e87c00000001326e3a06
+
+	/* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */
+	.octa 0x000000016c5490da00000000bb62c2e6
+
+	/* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */
+	.octa 0x00000000d1c71f6e0000000156a4b2c2
+
+	/* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */
+	.octa 0x00000001b4ce08a6000000011dfe763a
+
+	/* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */
+	.octa 0x00000001466ba60c000000007bcca8e2
+
+	/* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */
+	.octa 0x00000001f6c488a40000000186118faa
+
+	/* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */
+	.octa 0x000000013bfb06820000000111a65a88
+
+	/* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */
+	.octa 0x00000000690e9e54000000003565e1c4
+
+	/* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */
+	.octa 0x00000000281346b6000000012ed02a82
+
+	/* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */
+	.octa 0x000000015646402400000000c486ecfc
+
+	/* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */
+	.octa 0x000000016063a8dc0000000001b951b2
+
+	/* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */
+	.octa 0x0000000116a663620000000048143916
+
+	/* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */
+	.octa 0x000000017e8aa4d200000001dc2ae124
+
+	/* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */
+	.octa 0x00000001728eb10c00000001416c58d6
+
+	/* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */
+	.octa 0x00000001b08fd7fa00000000a479744a
+
+	/* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */
+	.octa 0x00000001092a16e80000000096ca3a26
+
+	/* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */
+	.octa 0x00000000a505637c00000000ff223d4e
+
+	/* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */
+	.octa 0x00000000d94869b2000000010e84da42
+
+	/* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */
+	.octa 0x00000001c8b203ae00000001b61ba3d0
+
+	/* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */
+	.octa 0x000000005704aea000000000680f2de8
+
+	/* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */
+	.octa 0x000000012e295fa2000000008772a9a8
+
+	/* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */
+	.octa 0x000000011d0908bc0000000155f295bc
+
+	/* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */
+	.octa 0x0000000193ed97ea00000000595f9282
+
+	/* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */
+	.octa 0x000000013a0f1c520000000164b1c25a
+
+	/* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */
+	.octa 0x000000010c2c40c000000000fbd67c50
+
+	/* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */
+	.octa 0x00000000ff6fac3e0000000096076268
+
+	/* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */
+	.octa 0x000000017b3609c000000001d288e4cc
+
+	/* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */
+	.octa 0x0000000088c8c92200000001eaac1bdc
+
+	/* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */
+	.octa 0x00000001751baae600000001f1ea39e2
+
+	/* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */
+	.octa 0x000000010795297200000001eb6506fc
+
+	/* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */
+	.octa 0x0000000162b00abe000000010f806ffe
+
+	/* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */
+	.octa 0x000000000d7b404c000000010408481e
+
+	/* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */
+	.octa 0x00000000763b13d40000000188260534
+
+	/* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */
+	.octa 0x00000000f6dc22d80000000058fc73e0
+
+	/* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */
+	.octa 0x000000007daae06000000000391c59b8
+
+	/* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */
+	.octa 0x000000013359ab7c000000018b638400
+
+	/* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */
+	.octa 0x000000008add438a000000011738f5c4
+
+	/* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */
+	.octa 0x00000001edbefdea000000008cf7c6da
+
+	/* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */
+	.octa 0x000000004104e0f800000001ef97fb16
+
+	/* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */
+	.octa 0x00000000b48a82220000000102130e20
+
+	/* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */
+	.octa 0x00000001bcb4684400000000db968898
+
+	/* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */
+	.octa 0x000000013293ce0a00000000b5047b5e
+
+	/* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */
+	.octa 0x00000001710d0844000000010b90fdb2
+
+	/* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */
+	.octa 0x0000000117907f6e000000004834a32e
+
+	/* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */
+	.octa 0x0000000087ddf93e0000000059c8f2b0
+
+	/* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */
+	.octa 0x000000005970e9b00000000122cec508
+
+	/* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */
+	.octa 0x0000000185b2b7d0000000000a330cda
+
+	/* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */
+	.octa 0x00000001dcee0efc000000014a47148c
+
+	/* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */
+	.octa 0x0000000030da27220000000042c61cb8
+
+	/* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */
+	.octa 0x000000012f925a180000000012fe6960
+
+	/* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */
+	.octa 0x00000000dd2e357c00000000dbda2c20
+
+	/* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */
+	.octa 0x00000000071c80de000000011122410c
+
+	/* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */
+	.octa 0x000000011513140a00000000977b2070
+
+	/* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */
+	.octa 0x00000001df876e8e000000014050438e
+
+	/* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */
+	.octa 0x000000015f81d6ce0000000147c840e8
+
+	/* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */
+	.octa 0x000000019dd94dbe00000001cc7c88ce
+
+	/* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */
+	.octa 0x00000001373d206e00000001476b35a4
+
+	/* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */
+	.octa 0x00000000668ccade000000013d52d508
+
+	/* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */
+	.octa 0x00000001b192d268000000008e4be32e
+
+	/* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */
+	.octa 0x00000000e30f3a7800000000024120fe
+
+	/* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */
+	.octa 0x000000010ef1f7bc00000000ddecddb4
+
+	/* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */
+	.octa 0x00000001f5ac738000000000d4d403bc
+
+	/* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */
+	.octa 0x000000011822ea7000000001734b89aa
+
+	/* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */
+	.octa 0x00000000c3a33848000000010e7a58d6
+
+	/* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */
+	.octa 0x00000001bd151c2400000001f9f04e9c
+
+	/* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */
+	.octa 0x0000000056002d7600000000b692225e
+
+	/* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */
+	.octa 0x000000014657c4f4000000019b8d3f3e
+
+	/* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */
+	.octa 0x0000000113742d7c00000001a874f11e
+
+	/* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */
+	.octa 0x000000019c5920ba000000010d5a4254
+
+	/* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */
+	.octa 0x000000005216d2d600000000bbb2f5d6
+
+	/* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */
+	.octa 0x0000000136f5ad8a0000000179cc0e36
+
+	/* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */
+	.octa 0x000000018b07beb600000001dca1da4a
+
+	/* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */
+	.octa 0x00000000db1e93b000000000feb1a192
+
+	/* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */
+	.octa 0x000000000b96fa3a00000000d1eeedd6
+
+	/* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */
+	.octa 0x00000001d9968af0000000008fad9bb4
+
+	/* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */
+	.octa 0x000000000e4a77a200000001884938e4
+
+	/* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */
+	.octa 0x00000000508c2ac800000001bc2e9bc0
+
+	/* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */
+	.octa 0x0000000021572a8000000001f9658a68
+
+	/* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */
+	.octa 0x00000001b859daf2000000001b9224fc
+
+	/* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */
+	.octa 0x000000016f7884740000000055b2fb84
+
+	/* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */
+	.octa 0x00000001b438810e000000018b090348
+
+	/* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */
+	.octa 0x0000000095ddc6f2000000011ccbd5ea
+
+	/* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */
+	.octa 0x00000001d977c20c0000000007ae47f8
+
+	/* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */
+	.octa 0x00000000ebedb99a0000000172acbec0
+
+	/* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */
+	.octa 0x00000001df9e9e9200000001c6e3ff20
+
+	/* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */
+	.octa 0x00000001a4a3f95200000000e1b38744
+
+	/* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */
+	.octa 0x00000000e2f5122000000000791585b2
+
+	/* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */
+	.octa 0x000000004aa01f3e00000000ac53b894
+
+	/* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */
+	.octa 0x00000000b3e90a5800000001ed5f2cf4
+
+	/* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */
+	.octa 0x000000000c9ca2aa00000001df48b2e0
+
+	/* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */
+	.octa 0x000000015168231600000000049c1c62
+
+	/* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */
+	.octa 0x0000000036fce78c000000017c460c12
+
+	/* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */
+	.octa 0x000000009037dc10000000015be4da7e
+
+	/* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */
+	.octa 0x00000000d3298582000000010f38f668
+
+	/* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */
+	.octa 0x00000001b42e8ad60000000039f40a00
+
+	/* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */
+	.octa 0x00000000142a983800000000bd4c10c4
+
+	/* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */
+	.octa 0x0000000109c7f1900000000042db1d98
+
+	/* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */
+	.octa 0x0000000056ff931000000001c905bae6
+
+	/* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */
+	.octa 0x00000001594513aa00000000069d40ea
+
+	/* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */
+	.octa 0x00000001e3b5b1e8000000008e4fbad0
+
+	/* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */
+	.octa 0x000000011dd5fc080000000047bedd46
+
+	/* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */
+	.octa 0x00000001675f0cc20000000026396bf8
+
+	/* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */
+	.octa 0x00000000d1c8dd4400000000379beb92
+
+	/* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */
+	.octa 0x0000000115ebd3d8000000000abae54a
+
+	/* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */
+	.octa 0x00000001ecbd0dac0000000007e6a128
+
+	/* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */
+	.octa 0x00000000cdf67af2000000000ade29d2
+
+	/* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */
+	.octa 0x000000004c01ff4c00000000f974c45c
+
+	/* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */
+	.octa 0x00000000f2d8657e00000000e77ac60a
+
+	/* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */
+	.octa 0x000000006bae74c40000000145895816
+
+	/* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */
+	.octa 0x0000000152af8aa00000000038e362be
+
+	/* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */
+	.octa 0x0000000004663802000000007f991a64
+
+	/* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */
+	.octa 0x00000001ab2f5afc00000000fa366d3a
+
+	/* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */
+	.octa 0x0000000074a4ebd400000001a2bb34f0
+
+	/* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */
+	.octa 0x00000001d7ab3a4c0000000028a9981e
+
+	/* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */
+	.octa 0x00000001a8da60c600000001dbc672be
+
+	/* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */
+	.octa 0x000000013cf6382000000000b04d77f6
+
+	/* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */
+	.octa 0x00000000bec12e1e0000000124400d96
+
+	/* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */
+	.octa 0x00000001c6368010000000014ca4b414
+
+	/* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */
+	.octa 0x00000001e6e78758000000012fe2c938
+
+	/* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */
+	.octa 0x000000008d7f2b3c00000001faed01e6
+
+	/* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */
+	.octa 0x000000016b4a156e000000007e80ecfe
+
+	/* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */
+	.octa 0x00000001c63cfeb60000000098daee94
+
+	/* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */
+	.octa 0x000000015f902670000000010a04edea
+
+	/* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */
+	.octa 0x00000001cd5de11e00000001c00b4524
+
+	/* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */
+	.octa 0x000000001acaec540000000170296550
+
+	/* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */
+	.octa 0x000000002bd0ca780000000181afaa48
+
+	/* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */
+	.octa 0x0000000032d63d5c0000000185a31ffa
+
+	/* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */
+	.octa 0x000000001c6d4e4c000000002469f608
+
+	/* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */
+	.octa 0x0000000106a60b92000000006980102a
+
+	/* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */
+	.octa 0x00000000d3855e120000000111ea9ca8
+
+	/* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */
+	.octa 0x00000000e312563600000001bd1d29ce
+
+	/* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */
+	.octa 0x000000009e8f7ea400000001b34b9580
+
+	/* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */
+	.octa 0x00000001c82e562c000000003076054e
+
+	/* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */
+	.octa 0x00000000ca9f09ce000000012a608ea4
+
+	/* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */
+	.octa 0x00000000c63764e600000000784d05fe
+
+	/* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */
+	.octa 0x0000000168d2e49e000000016ef0d82a
+
+	/* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */
+	.octa 0x00000000e986c1480000000075bda454
+
+	/* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */
+	.octa 0x00000000cfb65894000000003dc0a1c4
+
+	/* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */
+	.octa 0x0000000111cadee400000000e9a5d8be
+
+	/* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */
+	.octa 0x0000000171fb63ce00000001609bc4b4
+
+.short_constants:
+
+	/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros */
+	/* x^1952 mod p(x)`, x^1984 mod p(x)`, x^2016 mod p(x)`, x^2048 mod p(x)` */
+	.octa 0x7fec2963e5bf80485cf015c388e56f72
+
+	/* x^1824 mod p(x)`, x^1856 mod p(x)`, x^1888 mod p(x)`, x^1920 mod p(x)` */
+	.octa 0x38e888d4844752a9963a18920246e2e6
+
+	/* x^1696 mod p(x)`, x^1728 mod p(x)`, x^1760 mod p(x)`, x^1792 mod p(x)` */
+	.octa 0x42316c00730206ad419a441956993a31
+
+	/* x^1568 mod p(x)`, x^1600 mod p(x)`, x^1632 mod p(x)`, x^1664 mod p(x)` */
+	.octa 0x543d5c543e65ddf9924752ba2b830011
+
+	/* x^1440 mod p(x)`, x^1472 mod p(x)`, x^1504 mod p(x)`, x^1536 mod p(x)` */
+	.octa 0x78e87aaf56767c9255bd7f9518e4a304
+
+	/* x^1312 mod p(x)`, x^1344 mod p(x)`, x^1376 mod p(x)`, x^1408 mod p(x)` */
+	.octa 0x8f68fcec1903da7f6d76739fe0553f1e
+
+	/* x^1184 mod p(x)`, x^1216 mod p(x)`, x^1248 mod p(x)`, x^1280 mod p(x)` */
+	.octa 0x3f4840246791d588c133722b1fe0b5c3
+
+	/* x^1056 mod p(x)`, x^1088 mod p(x)`, x^1120 mod p(x)`, x^1152 mod p(x)` */
+	.octa 0x34c96751b04de25a64b67ee0e55ef1f3
+
+	/* x^928 mod p(x)`, x^960 mod p(x)`, x^992 mod p(x)`, x^1024 mod p(x)` */
+	.octa 0x156c8e180b4a395b069db049b8fdb1e7
+
+	/* x^800 mod p(x)`, x^832 mod p(x)`, x^864 mod p(x)`, x^896 mod p(x)` */
+	.octa 0xe0b99ccbe661f7bea11bfaf3c9e90b9e
+
+	/* x^672 mod p(x)`, x^704 mod p(x)`, x^736 mod p(x)`, x^768 mod p(x)` */
+	.octa 0x041d37768cd75659817cdc5119b29a35
+
+	/* x^544 mod p(x)`, x^576 mod p(x)`, x^608 mod p(x)`, x^640 mod p(x)` */
+	.octa 0x3a0777818cfaa9651ce9d94b36c41f1c
+
+	/* x^416 mod p(x)`, x^448 mod p(x)`, x^480 mod p(x)`, x^512 mod p(x)` */
+	.octa 0x0e148e8252377a554f256efcb82be955
+
+	/* x^288 mod p(x)`, x^320 mod p(x)`, x^352 mod p(x)`, x^384 mod p(x)` */
+	.octa 0x9c25531d19e65ddeec1631edb2dea967
+
+	/* x^160 mod p(x)`, x^192 mod p(x)`, x^224 mod p(x)`, x^256 mod p(x)` */
+	.octa 0x790606ff9957c0a65d27e147510ac59a
+
+	/* x^32 mod p(x)`, x^64 mod p(x)`, x^96 mod p(x)`, x^128 mod p(x)` */
+	.octa 0x82f63b786ea2d55ca66805eb18b8ea18
+
+
+.barrett_constants:
+	/* 33 bit reflected Barrett constant m - (4^32)/n */
+	.octa 0x000000000000000000000000dea713f1	/* x^64 div p(x)` */
+	/* 33 bit reflected Barrett constant n */
+	.octa 0x00000000000000000000000105ec76f1
+
+	.text
+
+#if defined(__BIG_ENDIAN__)
+#define BYTESWAP_DATA
+#else
+#undef BYTESWAP_DATA
+#endif
+
+#define off16		r25
+#define off32		r26
+#define off48		r27
+#define off64		r28
+#define off80		r29
+#define off96		r30
+#define off112		r31
+
+#define const1		v24
+#define const2		v25
+
+#define byteswap	v26
+#define	mask_32bit	v27
+#define	mask_64bit	v28
+#define zeroes		v29
+
+#ifdef BYTESWAP_DATA
+#define VPERM(A, B, C, D) vperm	A, B, C, D
+#else
+#define VPERM(A, B, C, D)
+#endif
+
+/* unsigned int __crc32c_vpmsum(unsigned int crc, void *p, unsigned long len) */
+FUNC_START(__crc32c_vpmsum)
+	std	r31,-8(r1)
+	std	r30,-16(r1)
+	std	r29,-24(r1)
+	std	r28,-32(r1)
+	std	r27,-40(r1)
+	std	r26,-48(r1)
+	std	r25,-56(r1)
+
+	li	off16,16
+	li	off32,32
+	li	off48,48
+	li	off64,64
+	li	off80,80
+	li	off96,96
+	li	off112,112
+	li	r0,0
+
+	/* Enough room for saving 10 non volatile VMX registers */
+	subi	r6,r1,56+10*16
+	subi	r7,r1,56+2*16
+
+	stvx	v20,0,r6
+	stvx	v21,off16,r6
+	stvx	v22,off32,r6
+	stvx	v23,off48,r6
+	stvx	v24,off64,r6
+	stvx	v25,off80,r6
+	stvx	v26,off96,r6
+	stvx	v27,off112,r6
+	stvx	v28,0,r7
+	stvx	v29,off16,r7
+
+	mr	r10,r3
+
+	vxor	zeroes,zeroes,zeroes
+	vspltisw v0,-1
+
+	vsldoi	mask_32bit,zeroes,v0,4
+	vsldoi	mask_64bit,zeroes,v0,8
+
+	/* Get the initial value into v8 */
+	vxor	v8,v8,v8
+	MTVRD(v8, R3)
+	vsldoi	v8,zeroes,v8,8	/* shift into bottom 32 bits */
+
+#ifdef BYTESWAP_DATA
+	addis	r3,r2,.byteswap_constant@toc@ha
+	addi	r3,r3,.byteswap_constant@toc@l
+
+	lvx	byteswap,0,r3
+	addi	r3,r3,16
+#endif
+
+	cmpdi	r5,256
+	blt	.Lshort
+
+	rldicr	r6,r5,0,56
+
+	/* Checksum in blocks of MAX_SIZE */
+1:	lis	r7,MAX_SIZE@h
+	ori	r7,r7,MAX_SIZE@l
+	mr	r9,r7
+	cmpd	r6,r7
+	bgt	2f
+	mr	r7,r6
+2:	subf	r6,r7,r6
+
+	/* our main loop does 128 bytes at a time */
+	srdi	r7,r7,7
+
+	/*
+	 * Work out the offset into the constants table to start at. Each
+	 * constant is 16 bytes, and it is used against 128 bytes of input
+	 * data - 128 / 16 = 8
+	 */
+	sldi	r8,r7,4
+	srdi	r9,r9,3
+	subf	r8,r8,r9
+
+	/* We reduce our final 128 bytes in a separate step */
+	addi	r7,r7,-1
+	mtctr	r7
+
+	addis	r3,r2,.constants@toc@ha
+	addi	r3,r3,.constants@toc@l
+
+	/* Find the start of our constants */
+	add	r3,r3,r8
+
+	/* zero v0-v7 which will contain our checksums */
+	vxor	v0,v0,v0
+	vxor	v1,v1,v1
+	vxor	v2,v2,v2
+	vxor	v3,v3,v3
+	vxor	v4,v4,v4
+	vxor	v5,v5,v5
+	vxor	v6,v6,v6
+	vxor	v7,v7,v7
+
+	lvx	const1,0,r3
+
+	/*
+	 * If we are looping back to consume more data we use the values
+	 * already in v16-v23.
+	 */
+	cmpdi	r0,1
+	beq	2f
+
+	/* First warm up pass */
+	lvx	v16,0,r4
+	lvx	v17,off16,r4
+	VPERM(v16,v16,v16,byteswap)
+	VPERM(v17,v17,v17,byteswap)
+	lvx	v18,off32,r4
+	lvx	v19,off48,r4
+	VPERM(v18,v18,v18,byteswap)
+	VPERM(v19,v19,v19,byteswap)
+	lvx	v20,off64,r4
+	lvx	v21,off80,r4
+	VPERM(v20,v20,v20,byteswap)
+	VPERM(v21,v21,v21,byteswap)
+	lvx	v22,off96,r4
+	lvx	v23,off112,r4
+	VPERM(v22,v22,v22,byteswap)
+	VPERM(v23,v23,v23,byteswap)
+	addi	r4,r4,8*16
+
+	/* xor in initial value */
+	vxor	v16,v16,v8
+
+2:	bdz	.Lfirst_warm_up_done
+
+	addi	r3,r3,16
+	lvx	const2,0,r3
+
+	/* Second warm up pass */
+	VPMSUMD(v8,v16,const1)
+	lvx	v16,0,r4
+	VPERM(v16,v16,v16,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v9,v17,const1)
+	lvx	v17,off16,r4
+	VPERM(v17,v17,v17,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v10,v18,const1)
+	lvx	v18,off32,r4
+	VPERM(v18,v18,v18,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v11,v19,const1)
+	lvx	v19,off48,r4
+	VPERM(v19,v19,v19,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v12,v20,const1)
+	lvx	v20,off64,r4
+	VPERM(v20,v20,v20,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v13,v21,const1)
+	lvx	v21,off80,r4
+	VPERM(v21,v21,v21,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v14,v22,const1)
+	lvx	v22,off96,r4
+	VPERM(v22,v22,v22,byteswap)
+	ori	r2,r2,0
+
+	VPMSUMD(v15,v23,const1)
+	lvx	v23,off112,r4
+	VPERM(v23,v23,v23,byteswap)
+
+	addi	r4,r4,8*16
+
+	bdz	.Lfirst_cool_down
+
+	/*
+	 * main loop. We modulo schedule it such that it takes three iterations
+	 * to complete - first iteration load, second iteration vpmsum, third
+	 * iteration xor.
+	 */
+	.balign	16
+4:	lvx	const1,0,r3
+	addi	r3,r3,16
+	ori	r2,r2,0
+
+	vxor	v0,v0,v8
+	VPMSUMD(v8,v16,const2)
+	lvx	v16,0,r4
+	VPERM(v16,v16,v16,byteswap)
+	ori	r2,r2,0
+
+	vxor	v1,v1,v9
+	VPMSUMD(v9,v17,const2)
+	lvx	v17,off16,r4
+	VPERM(v17,v17,v17,byteswap)
+	ori	r2,r2,0
+
+	vxor	v2,v2,v10
+	VPMSUMD(v10,v18,const2)
+	lvx	v18,off32,r4
+	VPERM(v18,v18,v18,byteswap)
+	ori	r2,r2,0
+
+	vxor	v3,v3,v11
+	VPMSUMD(v11,v19,const2)
+	lvx	v19,off48,r4
+	VPERM(v19,v19,v19,byteswap)
+	lvx	const2,0,r3
+	ori	r2,r2,0
+
+	vxor	v4,v4,v12
+	VPMSUMD(v12,v20,const1)
+	lvx	v20,off64,r4
+	VPERM(v20,v20,v20,byteswap)
+	ori	r2,r2,0
+
+	vxor	v5,v5,v13
+	VPMSUMD(v13,v21,const1)
+	lvx	v21,off80,r4
+	VPERM(v21,v21,v21,byteswap)
+	ori	r2,r2,0
+
+	vxor	v6,v6,v14
+	VPMSUMD(v14,v22,const1)
+	lvx	v22,off96,r4
+	VPERM(v22,v22,v22,byteswap)
+	ori	r2,r2,0
+
+	vxor	v7,v7,v15
+	VPMSUMD(v15,v23,const1)
+	lvx	v23,off112,r4
+	VPERM(v23,v23,v23,byteswap)
+
+	addi	r4,r4,8*16
+
+	bdnz	4b
+
+.Lfirst_cool_down:
+	/* First cool down pass */
+	lvx	const1,0,r3
+	addi	r3,r3,16
+
+	vxor	v0,v0,v8
+	VPMSUMD(v8,v16,const1)
+	ori	r2,r2,0
+
+	vxor	v1,v1,v9
+	VPMSUMD(v9,v17,const1)
+	ori	r2,r2,0
+
+	vxor	v2,v2,v10
+	VPMSUMD(v10,v18,const1)
+	ori	r2,r2,0
+
+	vxor	v3,v3,v11
+	VPMSUMD(v11,v19,const1)
+	ori	r2,r2,0
+
+	vxor	v4,v4,v12
+	VPMSUMD(v12,v20,const1)
+	ori	r2,r2,0
+
+	vxor	v5,v5,v13
+	VPMSUMD(v13,v21,const1)
+	ori	r2,r2,0
+
+	vxor	v6,v6,v14
+	VPMSUMD(v14,v22,const1)
+	ori	r2,r2,0
+
+	vxor	v7,v7,v15
+	VPMSUMD(v15,v23,const1)
+	ori	r2,r2,0
+
+.Lsecond_cool_down:
+	/* Second cool down pass */
+	vxor	v0,v0,v8
+	vxor	v1,v1,v9
+	vxor	v2,v2,v10
+	vxor	v3,v3,v11
+	vxor	v4,v4,v12
+	vxor	v5,v5,v13
+	vxor	v6,v6,v14
+	vxor	v7,v7,v15
+
+	/*
+	 * vpmsumd produces a 96 bit result in the least significant bits
+	 * of the register. Since we are bit reflected we have to shift it
+	 * left 32 bits so it occupies the least significant bits in the
+	 * bit reflected domain.
+	 */
+	vsldoi	v0,v0,zeroes,4
+	vsldoi	v1,v1,zeroes,4
+	vsldoi	v2,v2,zeroes,4
+	vsldoi	v3,v3,zeroes,4
+	vsldoi	v4,v4,zeroes,4
+	vsldoi	v5,v5,zeroes,4
+	vsldoi	v6,v6,zeroes,4
+	vsldoi	v7,v7,zeroes,4
+
+	/* xor with last 1024 bits */
+	lvx	v8,0,r4
+	lvx	v9,off16,r4
+	VPERM(v8,v8,v8,byteswap)
+	VPERM(v9,v9,v9,byteswap)
+	lvx	v10,off32,r4
+	lvx	v11,off48,r4
+	VPERM(v10,v10,v10,byteswap)
+	VPERM(v11,v11,v11,byteswap)
+	lvx	v12,off64,r4
+	lvx	v13,off80,r4
+	VPERM(v12,v12,v12,byteswap)
+	VPERM(v13,v13,v13,byteswap)
+	lvx	v14,off96,r4
+	lvx	v15,off112,r4
+	VPERM(v14,v14,v14,byteswap)
+	VPERM(v15,v15,v15,byteswap)
+
+	addi	r4,r4,8*16
+
+	vxor	v16,v0,v8
+	vxor	v17,v1,v9
+	vxor	v18,v2,v10
+	vxor	v19,v3,v11
+	vxor	v20,v4,v12
+	vxor	v21,v5,v13
+	vxor	v22,v6,v14
+	vxor	v23,v7,v15
+
+	li	r0,1
+	cmpdi	r6,0
+	addi	r6,r6,128
+	bne	1b
+
+	/* Work out how many bytes we have left */
+	andi.	r5,r5,127
+
+	/* Calculate where in the constant table we need to start */
+	subfic	r6,r5,128
+	add	r3,r3,r6
+
+	/* How many 16 byte chunks are in the tail */
+	srdi	r7,r5,4
+	mtctr	r7
+
+	/*
+	 * Reduce the previously calculated 1024 bits to 64 bits, shifting
+	 * 32 bits to include the trailing 32 bits of zeros
+	 */
+	lvx	v0,0,r3
+	lvx	v1,off16,r3
+	lvx	v2,off32,r3
+	lvx	v3,off48,r3
+	lvx	v4,off64,r3
+	lvx	v5,off80,r3
+	lvx	v6,off96,r3
+	lvx	v7,off112,r3
+	addi	r3,r3,8*16
+
+	VPMSUMW(v0,v16,v0)
+	VPMSUMW(v1,v17,v1)
+	VPMSUMW(v2,v18,v2)
+	VPMSUMW(v3,v19,v3)
+	VPMSUMW(v4,v20,v4)
+	VPMSUMW(v5,v21,v5)
+	VPMSUMW(v6,v22,v6)
+	VPMSUMW(v7,v23,v7)
+
+	/* Now reduce the tail (0 - 112 bytes) */
+	cmpdi	r7,0
+	beq	1f
+
+	lvx	v16,0,r4
+	lvx	v17,0,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off32,r4
+	lvx	v17,off32,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off64,r4
+	lvx	v17,off64,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+	bdz	1f
+
+	lvx	v16,off96,r4
+	lvx	v17,off96,r3
+	VPERM(v16,v16,v16,byteswap)
+	VPMSUMW(v16,v16,v17)
+	vxor	v0,v0,v16
+
+	/* Now xor all the parallel chunks together */
+1:	vxor	v0,v0,v1
+	vxor	v2,v2,v3
+	vxor	v4,v4,v5
+	vxor	v6,v6,v7
+
+	vxor	v0,v0,v2
+	vxor	v4,v4,v6
+
+	vxor	v0,v0,v4
+
+.Lbarrett_reduction:
+	/* Barrett constants */
+	addis	r3,r2,.barrett_constants@toc@ha
+	addi	r3,r3,.barrett_constants@toc@l
+
+	lvx	const1,0,r3
+	lvx	const2,off16,r3
+
+	vsldoi	v1,v0,v0,8
+	vxor	v0,v0,v1		/* xor two 64 bit results together */
+
+	/* shift left one bit */
+	vspltisb v1,1
+	vsl	v0,v0,v1
+
+	vand	v0,v0,mask_64bit
+
+	/*
+	 * The reflected version of Barrett reduction. Instead of bit
+	 * reflecting our data (which is expensive to do), we bit reflect our
+	 * constants and our algorithm, which means the intermediate data in
+	 * our vector registers goes from 0-63 instead of 63-0. We can reflect
+	 * the algorithm because we don't carry in mod 2 arithmetic.
+	 */
+	vand	v1,v0,mask_32bit	/* bottom 32 bits of a */
+	VPMSUMD(v1,v1,const1)		/* ma */
+	vand	v1,v1,mask_32bit	/* bottom 32bits of ma */
+	VPMSUMD(v1,v1,const2)		/* qn */
+	vxor	v0,v0,v1		/* a - qn, subtraction is xor in GF(2) */
+
+	/*
+	 * Since we are bit reflected, the result (ie the low 32 bits) is in
+	 * the high 32 bits. We just need to shift it left 4 bytes
+	 * V0 [ 0 1 X 3 ]
+	 * V0 [ 0 X 2 3 ]
+	 */
+	vsldoi	v0,v0,zeroes,4		/* shift result into top 64 bits of */
+
+	/* Get it into r3 */
+	MFVRD(R3, v0)
+
+.Lout:
+	subi	r6,r1,56+10*16
+	subi	r7,r1,56+2*16
+
+	lvx	v20,0,r6
+	lvx	v21,off16,r6
+	lvx	v22,off32,r6
+	lvx	v23,off48,r6
+	lvx	v24,off64,r6
+	lvx	v25,off80,r6
+	lvx	v26,off96,r6
+	lvx	v27,off112,r6
+	lvx	v28,0,r7
+	lvx	v29,off16,r7
+
+	ld	r31,-8(r1)
+	ld	r30,-16(r1)
+	ld	r29,-24(r1)
+	ld	r28,-32(r1)
+	ld	r27,-40(r1)
+	ld	r26,-48(r1)
+	ld	r25,-56(r1)
+
+	blr
+
+.Lfirst_warm_up_done:
+	lvx	const1,0,r3
+	addi	r3,r3,16
+
+	VPMSUMD(v8,v16,const1)
+	VPMSUMD(v9,v17,const1)
+	VPMSUMD(v10,v18,const1)
+	VPMSUMD(v11,v19,const1)
+	VPMSUMD(v12,v20,const1)
+	VPMSUMD(v13,v21,const1)
+	VPMSUMD(v14,v22,const1)
+	VPMSUMD(v15,v23,const1)
+
+	b	.Lsecond_cool_down
+
+.Lshort:
+	cmpdi	r5,0
+	beq	.Lzero
+
+	addis	r3,r2,.short_constants@toc@ha
+	addi	r3,r3,.short_constants@toc@l
+
+	/* Calculate where in the constant table we need to start */
+	subfic	r6,r5,256
+	add	r3,r3,r6
+
+	/* How many 16 byte chunks? */
+	srdi	r7,r5,4
+	mtctr	r7
+
+	vxor	v19,v19,v19
+	vxor	v20,v20,v20
+
+	lvx	v0,0,r4
+	lvx	v16,0,r3
+	VPERM(v0,v0,v16,byteswap)
+	vxor	v0,v0,v8	/* xor in initial value */
+	VPMSUMW(v0,v0,v16)
+	bdz	.Lv0
+
+	lvx	v1,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v1,v1,v17,byteswap)
+	VPMSUMW(v1,v1,v17)
+	bdz	.Lv1
+
+	lvx	v2,off32,r4
+	lvx	v16,off32,r3
+	VPERM(v2,v2,v16,byteswap)
+	VPMSUMW(v2,v2,v16)
+	bdz	.Lv2
+
+	lvx	v3,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v3,v3,v17,byteswap)
+	VPMSUMW(v3,v3,v17)
+	bdz	.Lv3
+
+	lvx	v4,off64,r4
+	lvx	v16,off64,r3
+	VPERM(v4,v4,v16,byteswap)
+	VPMSUMW(v4,v4,v16)
+	bdz	.Lv4
+
+	lvx	v5,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v5,v5,v17,byteswap)
+	VPMSUMW(v5,v5,v17)
+	bdz	.Lv5
+
+	lvx	v6,off96,r4
+	lvx	v16,off96,r3
+	VPERM(v6,v6,v16,byteswap)
+	VPMSUMW(v6,v6,v16)
+	bdz	.Lv6
+
+	lvx	v7,off112,r4
+	lvx	v17,off112,r3
+	VPERM(v7,v7,v17,byteswap)
+	VPMSUMW(v7,v7,v17)
+	bdz	.Lv7
+
+	addi	r3,r3,128
+	addi	r4,r4,128
+
+	lvx	v8,0,r4
+	lvx	v16,0,r3
+	VPERM(v8,v8,v16,byteswap)
+	VPMSUMW(v8,v8,v16)
+	bdz	.Lv8
+
+	lvx	v9,off16,r4
+	lvx	v17,off16,r3
+	VPERM(v9,v9,v17,byteswap)
+	VPMSUMW(v9,v9,v17)
+	bdz	.Lv9
+
+	lvx	v10,off32,r4
+	lvx	v16,off32,r3
+	VPERM(v10,v10,v16,byteswap)
+	VPMSUMW(v10,v10,v16)
+	bdz	.Lv10
+
+	lvx	v11,off48,r4
+	lvx	v17,off48,r3
+	VPERM(v11,v11,v17,byteswap)
+	VPMSUMW(v11,v11,v17)
+	bdz	.Lv11
+
+	lvx	v12,off64,r4
+	lvx	v16,off64,r3
+	VPERM(v12,v12,v16,byteswap)
+	VPMSUMW(v12,v12,v16)
+	bdz	.Lv12
+
+	lvx	v13,off80,r4
+	lvx	v17,off80,r3
+	VPERM(v13,v13,v17,byteswap)
+	VPMSUMW(v13,v13,v17)
+	bdz	.Lv13
+
+	lvx	v14,off96,r4
+	lvx	v16,off96,r3
+	VPERM(v14,v14,v16,byteswap)
+	VPMSUMW(v14,v14,v16)
+	bdz	.Lv14
+
+	lvx	v15,off112,r4
+	lvx	v17,off112,r3
+	VPERM(v15,v15,v17,byteswap)
+	VPMSUMW(v15,v15,v17)
+
+.Lv15:	vxor	v19,v19,v15
+.Lv14:	vxor	v20,v20,v14
+.Lv13:	vxor	v19,v19,v13
+.Lv12:	vxor	v20,v20,v12
+.Lv11:	vxor	v19,v19,v11
+.Lv10:	vxor	v20,v20,v10
+.Lv9:	vxor	v19,v19,v9
+.Lv8:	vxor	v20,v20,v8
+.Lv7:	vxor	v19,v19,v7
+.Lv6:	vxor	v20,v20,v6
+.Lv5:	vxor	v19,v19,v5
+.Lv4:	vxor	v20,v20,v4
+.Lv3:	vxor	v19,v19,v3
+.Lv2:	vxor	v20,v20,v2
+.Lv1:	vxor	v19,v19,v1
+.Lv0:	vxor	v20,v20,v0
+
+	vxor	v0,v19,v20
+
+	b	.Lbarrett_reduction
+
+.Lzero:
+	mr	r3,r10
+	b	.Lout
+
+FUNC_END(__crc32_vpmsum)
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
new file mode 100644
index 0000000..bfe3d37
--- /dev/null
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -0,0 +1,167 @@
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <asm/switch_to.h>
+
+#define CHKSUM_BLOCK_SIZE	1
+#define CHKSUM_DIGEST_SIZE	4
+
+#define VMX_ALIGN		16
+#define VMX_ALIGN_MASK		(VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT	512
+
+u32 __crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len);
+
+static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
+{
+	unsigned int prealign;
+	unsigned int tail;
+
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+		return __crc32c_le(crc, p, len);
+
+	if ((unsigned long)p & VMX_ALIGN_MASK) {
+		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+		crc = __crc32c_le(crc, p, prealign);
+		len -= prealign;
+		p += prealign;
+	}
+
+	if (len & ~VMX_ALIGN_MASK) {
+		pagefault_disable();
+		enable_kernel_altivec();
+		crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+		pagefault_enable();
+	}
+
+	tail = len & VMX_ALIGN_MASK;
+	if (tail) {
+		p += len & ~VMX_ALIGN_MASK;
+		crc = __crc32c_le(crc, p, tail);
+	}
+
+	return crc;
+}
+
+static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = 0;
+
+	return 0;
+}
+
+/*
+ * Setting the seed allows arbitrary accumulators and flexible XOR policy
+ * If your algorithm starts with ~0, then XOR with ~0 before you set
+ * the seed.
+ */
+static int crc32c_vpmsum_setkey(struct crypto_shash *hash, const u8 *key,
+			       unsigned int keylen)
+{
+	u32 *mctx = crypto_shash_ctx(hash);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	*mctx = le32_to_cpup((__le32 *)key);
+	return 0;
+}
+
+static int crc32c_vpmsum_init(struct shash_desc *desc)
+{
+	u32 *mctx = crypto_shash_ctx(desc->tfm);
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = *mctx;
+
+	return 0;
+}
+
+static int crc32c_vpmsum_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = crc32c_vpmsum(*crcp, data, len);
+
+	return 0;
+}
+
+static int __crc32c_vpmsum_finup(u32 *crcp, const u8 *data, unsigned int len,
+				u8 *out)
+{
+	*(__le32 *)out = ~cpu_to_le32(crc32c_vpmsum(*crcp, data, len));
+
+	return 0;
+}
+
+static int crc32c_vpmsum_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return __crc32c_vpmsum_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32c_vpmsum_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*(__le32 *)out = ~cpu_to_le32p(crcp);
+
+	return 0;
+}
+
+static int crc32c_vpmsum_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
+{
+	return __crc32c_vpmsum_finup(crypto_shash_ctx(desc->tfm), data, len,
+				     out);
+}
+
+static struct shash_alg alg = {
+	.setkey		= crc32c_vpmsum_setkey,
+	.init		= crc32c_vpmsum_init,
+	.update		= crc32c_vpmsum_update,
+	.final		= crc32c_vpmsum_final,
+	.finup		= crc32c_vpmsum_finup,
+	.digest		= crc32c_vpmsum_digest,
+	.descsize	= sizeof(u32),
+	.digestsize	= CHKSUM_DIGEST_SIZE,
+	.base		= {
+		.cra_name		= "crc32c",
+		.cra_driver_name	= "crc32c-vpmsum",
+		.cra_priority		= 200,
+		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(u32),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= crc32c_vpmsum_cra_init,
+	}
+};
+
+static int __init crc32c_vpmsum_mod_init(void)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crc32c_vpmsum_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crc32c_vpmsum_mod_init);
+module_exit(crc32c_vpmsum_mod_fini);
+
+MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
+MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-vpmsum");
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1d035c1..49cd876 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -174,6 +174,8 @@
 #define PPC_INST_MFSPR_DSCR_USER_MASK	0xfc1fffff
 #define PPC_INST_MTSPR_DSCR_USER	0x7c0303a6
 #define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1fffff
+#define PPC_INST_MFVSRD			0x7c000066
+#define PPC_INST_MTVSRD			0x7c000166
 #define PPC_INST_SLBFEE			0x7c0007a7
 
 #define PPC_INST_STRING			0x7c00042a
@@ -188,6 +190,8 @@
 #define PPC_INST_WAIT			0x7c00007c
 #define PPC_INST_TLBIVAX		0x7c000624
 #define PPC_INST_TLBSRX_DOT		0x7c0006a5
+#define PPC_INST_VPMSUMW		0x10000488
+#define PPC_INST_VPMSUMD		0x100004c8
 #define PPC_INST_XXLOR			0xf0000510
 #define PPC_INST_XXSWAPD		0xf0000250
 #define PPC_INST_XVCPSGNDP		0xf0000780
@@ -359,6 +363,14 @@
 					       VSX_XX1((s), a, b))
 #define LXVD2X(s, a, b)		stringify_in_c(.long PPC_INST_LXVD2X | \
 					       VSX_XX1((s), a, b))
+#define MFVRD(a, t)		stringify_in_c(.long PPC_INST_MFVSRD | \
+					       VSX_XX1((t)+32, a, R0))
+#define MTVRD(t, a)		stringify_in_c(.long PPC_INST_MTVSRD | \
+					       VSX_XX1((t)+32, a, R0))
+#define VPMSUMW(t, a, b)	stringify_in_c(.long PPC_INST_VPMSUMW | \
+					       VSX_XX3((t), a, b))
+#define VPMSUMD(t, a, b)	stringify_in_c(.long PPC_INST_VPMSUMD | \
+					       VSX_XX3((t), a, b))
 #define XXLOR(t, a, b)		stringify_in_c(.long PPC_INST_XXLOR | \
 					       VSX_XX3((t), a, b))
 #define XXSWAPD(t, a)		stringify_in_c(.long PPC_INST_XXSWAPD | \
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 2b31632..051af61 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -286,6 +286,9 @@
 
 #endif
 
+#define FUNC_START(name)	_GLOBAL(name)
+#define FUNC_END(name)
+
 /* 
  * LOAD_REG_IMMEDIATE(rn, expr)
  *   Loads the value of the constant expression 'expr' into register 'rn'
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 12e48d5..3963f0b 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -38,6 +38,18 @@
 EXPORT_SYMBOL(ioread16be);
 EXPORT_SYMBOL(ioread32);
 EXPORT_SYMBOL(ioread32be);
+#ifdef __powerpc64__
+u64 ioread64(void __iomem *addr)
+{
+	return readq(addr);
+}
+u64 ioread64be(void __iomem *addr)
+{
+	return readq_be(addr);
+}
+EXPORT_SYMBOL(ioread64);
+EXPORT_SYMBOL(ioread64be);
+#endif /* __powerpc64__ */
 
 void iowrite8(u8 val, void __iomem *addr)
 {
@@ -64,6 +76,18 @@
 EXPORT_SYMBOL(iowrite16be);
 EXPORT_SYMBOL(iowrite32);
 EXPORT_SYMBOL(iowrite32be);
+#ifdef __powerpc64__
+void iowrite64(u64 val, void __iomem *addr)
+{
+	writeq(val, addr);
+}
+void iowrite64be(u64 val, void __iomem *addr)
+{
+	writeq_be(val, addr);
+}
+EXPORT_SYMBOL(iowrite64);
+EXPORT_SYMBOL(iowrite64be);
+#endif /* __powerpc64__ */
 
 /*
  * These are the "repeat read/write" functions. Note the
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 7554a8b..2ea18b0 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -22,6 +22,7 @@
 
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
@@ -44,7 +45,7 @@
 	long dec;
 	int key_len;
 	union {
-		struct crypto_blkcipher *blk;
+		struct crypto_skcipher *blk;
 		struct crypto_cipher *cip;
 	} fallback;
 };
@@ -63,7 +64,7 @@
 	long enc;
 	long dec;
 	int key_len;
-	struct crypto_blkcipher *fallback;
+	struct crypto_skcipher *fallback;
 };
 
 /*
@@ -237,16 +238,16 @@
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 	unsigned int ret;
 
-	sctx->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	sctx->fallback.blk->base.crt_flags |= (tfm->crt_flags &
-			CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(sctx->fallback.blk, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(sctx->fallback.blk, tfm->crt_flags &
+						      CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_blkcipher_setkey(sctx->fallback.blk, key, len);
-	if (ret) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (sctx->fallback.blk->base.crt_flags &
-				CRYPTO_TFM_RES_MASK);
-	}
+	ret = crypto_skcipher_setkey(sctx->fallback.blk, key, len);
+
+	tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+	tfm->crt_flags |= crypto_skcipher_get_flags(sctx->fallback.blk) &
+			  CRYPTO_TFM_RES_MASK;
+
 	return ret;
 }
 
@@ -255,15 +256,17 @@
 		unsigned int nbytes)
 {
 	unsigned int ret;
-	struct crypto_blkcipher *tfm;
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
 
-	tfm = desc->tfm;
-	desc->tfm = sctx->fallback.blk;
+	skcipher_request_set_tfm(req, sctx->fallback.blk);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_decrypt_iv(desc, dst, src, nbytes);
+	ret = crypto_skcipher_decrypt(req);
 
-	desc->tfm = tfm;
+	skcipher_request_zero(req);
 	return ret;
 }
 
@@ -272,15 +275,15 @@
 		unsigned int nbytes)
 {
 	unsigned int ret;
-	struct crypto_blkcipher *tfm;
-	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, sctx->fallback.blk);
 
-	tfm = desc->tfm;
-	desc->tfm = sctx->fallback.blk;
+	skcipher_request_set_tfm(req, sctx->fallback.blk);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_encrypt_iv(desc, dst, src, nbytes);
-
-	desc->tfm = tfm;
+	ret = crypto_skcipher_encrypt(req);
 	return ret;
 }
 
@@ -370,8 +373,9 @@
 	const char *name = tfm->__crt_alg->cra_name;
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 
-	sctx->fallback.blk = crypto_alloc_blkcipher(name, 0,
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	sctx->fallback.blk = crypto_alloc_skcipher(name, 0,
+						   CRYPTO_ALG_ASYNC |
+						   CRYPTO_ALG_NEED_FALLBACK);
 
 	if (IS_ERR(sctx->fallback.blk)) {
 		pr_err("Allocating AES fallback algorithm %s failed\n",
@@ -386,8 +390,7 @@
 {
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_blkcipher(sctx->fallback.blk);
-	sctx->fallback.blk = NULL;
+	crypto_free_skcipher(sctx->fallback.blk);
 }
 
 static struct crypto_alg ecb_aes_alg = {
@@ -536,16 +539,16 @@
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 	unsigned int ret;
 
-	xts_ctx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	xts_ctx->fallback->base.crt_flags |= (tfm->crt_flags &
-			CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(xts_ctx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(xts_ctx->fallback, tfm->crt_flags &
+						     CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_blkcipher_setkey(xts_ctx->fallback, key, len);
-	if (ret) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (xts_ctx->fallback->base.crt_flags &
-				CRYPTO_TFM_RES_MASK);
-	}
+	ret = crypto_skcipher_setkey(xts_ctx->fallback, key, len);
+
+	tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+	tfm->crt_flags |= crypto_skcipher_get_flags(xts_ctx->fallback) &
+			  CRYPTO_TFM_RES_MASK;
+
 	return ret;
 }
 
@@ -553,16 +556,18 @@
 		struct scatterlist *dst, struct scatterlist *src,
 		unsigned int nbytes)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct crypto_blkcipher *tfm;
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
 	unsigned int ret;
 
-	tfm = desc->tfm;
-	desc->tfm = xts_ctx->fallback;
+	skcipher_request_set_tfm(req, xts_ctx->fallback);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_decrypt_iv(desc, dst, src, nbytes);
+	ret = crypto_skcipher_decrypt(req);
 
-	desc->tfm = tfm;
+	skcipher_request_zero(req);
 	return ret;
 }
 
@@ -570,16 +575,18 @@
 		struct scatterlist *dst, struct scatterlist *src,
 		unsigned int nbytes)
 {
-	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
-	struct crypto_blkcipher *tfm;
+	struct crypto_blkcipher *tfm = desc->tfm;
+	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(req, xts_ctx->fallback);
 	unsigned int ret;
 
-	tfm = desc->tfm;
-	desc->tfm = xts_ctx->fallback;
+	skcipher_request_set_tfm(req, xts_ctx->fallback);
+	skcipher_request_set_callback(req, desc->flags, NULL, NULL);
+	skcipher_request_set_crypt(req, src, dst, nbytes, desc->info);
 
-	ret = crypto_blkcipher_encrypt_iv(desc, dst, src, nbytes);
+	ret = crypto_skcipher_encrypt(req);
 
-	desc->tfm = tfm;
+	skcipher_request_zero(req);
 	return ret;
 }
 
@@ -700,8 +707,9 @@
 	const char *name = tfm->__crt_alg->cra_name;
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 
-	xts_ctx->fallback = crypto_alloc_blkcipher(name, 0,
-			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	xts_ctx->fallback = crypto_alloc_skcipher(name, 0,
+						  CRYPTO_ALG_ASYNC |
+						  CRYPTO_ALG_NEED_FALLBACK);
 
 	if (IS_ERR(xts_ctx->fallback)) {
 		pr_err("Allocating XTS fallback algorithm %s failed\n",
@@ -715,8 +723,7 @@
 {
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_blkcipher(xts_ctx->fallback);
-	xts_ctx->fallback = NULL;
+	crypto_free_skcipher(xts_ctx->fallback);
 }
 
 static struct crypto_alg xts_aes_alg = {
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index b9b912a..34b3fa2 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -49,7 +49,9 @@
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
-	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb/
+	obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb/
+	obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb/
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 5b7fa14..0ab5ee1 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -59,17 +59,6 @@
 	u8 nonce[4];
 };
 
-struct aesni_gcm_set_hash_subkey_result {
-	int err;
-	struct completion completion;
-};
-
-struct aesni_hash_subkey_req_data {
-	u8 iv[16];
-	struct aesni_gcm_set_hash_subkey_result result;
-	struct scatterlist sg;
-};
-
 struct aesni_lrw_ctx {
 	struct lrw_table_ctx lrw_table;
 	u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
@@ -809,71 +798,28 @@
 	cryptd_free_aead(*ctx);
 }
 
-static void
-rfc4106_set_hash_subkey_done(struct crypto_async_request *req, int err)
-{
-	struct aesni_gcm_set_hash_subkey_result *result = req->data;
-
-	if (err == -EINPROGRESS)
-		return;
-	result->err = err;
-	complete(&result->completion);
-}
-
 static int
 rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 {
-	struct crypto_ablkcipher *ctr_tfm;
-	struct ablkcipher_request *req;
-	int ret = -EINVAL;
-	struct aesni_hash_subkey_req_data *req_data;
+	struct crypto_cipher *tfm;
+	int ret;
 
-	ctr_tfm = crypto_alloc_ablkcipher("ctr(aes)", 0, 0);
-	if (IS_ERR(ctr_tfm))
-		return PTR_ERR(ctr_tfm);
+	tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
 
-	ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len);
+	ret = crypto_cipher_setkey(tfm, key, key_len);
 	if (ret)
-		goto out_free_ablkcipher;
-
-	ret = -ENOMEM;
-	req = ablkcipher_request_alloc(ctr_tfm, GFP_KERNEL);
-	if (!req)
-		goto out_free_ablkcipher;
-
-	req_data = kmalloc(sizeof(*req_data), GFP_KERNEL);
-	if (!req_data)
-		goto out_free_request;
-
-	memset(req_data->iv, 0, sizeof(req_data->iv));
+		goto out_free_cipher;
 
 	/* Clear the data in the hash sub key container to zero.*/
 	/* We want to cipher all zeros to create the hash sub key. */
 	memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE);
 
-	init_completion(&req_data->result.completion);
-	sg_init_one(&req_data->sg, hash_subkey, RFC4106_HASH_SUBKEY_SIZE);
-	ablkcipher_request_set_tfm(req, ctr_tfm);
-	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
-					CRYPTO_TFM_REQ_MAY_BACKLOG,
-					rfc4106_set_hash_subkey_done,
-					&req_data->result);
+	crypto_cipher_encrypt_one(tfm, hash_subkey, hash_subkey);
 
-	ablkcipher_request_set_crypt(req, &req_data->sg,
-		&req_data->sg, RFC4106_HASH_SUBKEY_SIZE, req_data->iv);
-
-	ret = crypto_ablkcipher_encrypt(req);
-	if (ret == -EINPROGRESS || ret == -EBUSY) {
-		ret = wait_for_completion_interruptible
-			(&req_data->result.completion);
-		if (!ret)
-			ret = req_data->result.err;
-	}
-	kfree(req_data);
-out_free_request:
-	ablkcipher_request_free(req);
-out_free_ablkcipher:
-	crypto_free_ablkcipher(ctr_tfm);
+out_free_cipher:
+	crypto_free_cipher(tfm);
 	return ret;
 }
 
@@ -1098,9 +1044,12 @@
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	aead_request_set_tfm(req, irq_fpu_usable() ?
-				  cryptd_aead_child(cryptd_tfm) :
-				  &cryptd_tfm->base);
+	tfm = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		tfm = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, tfm);
 
 	return crypto_aead_encrypt(req);
 }
@@ -1111,9 +1060,12 @@
 	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
 	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	aead_request_set_tfm(req, irq_fpu_usable() ?
-				  cryptd_aead_child(cryptd_tfm) :
-				  &cryptd_tfm->base);
+	tfm = &cryptd_tfm->base;
+	if (irq_fpu_usable() && (!in_atomic() ||
+				 !cryptd_aead_queued(cryptd_tfm)))
+		tfm = cryptd_aead_child(cryptd_tfm);
+
+	aead_request_set_tfm(req, tfm);
 
 	return crypto_aead_decrypt(req);
 }
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 2d5c2e0b..f910d1d 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -70,7 +70,7 @@
 	struct blkcipher_walk walk;
 	int err;
 
-	if (!may_use_simd())
+	if (nbytes <= CHACHA20_BLOCK_SIZE || !may_use_simd())
 		return crypto_chacha20_crypt(desc, dst, src, nbytes);
 
 	state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index a69321a..0420bab 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -168,30 +168,23 @@
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
-	if (!irq_fpu_usable()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_init(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return crypto_shash_init(desc);
-	}
+	desc->tfm = child;
+	desc->flags = req->base.flags;
+	return crypto_shash_init(desc);
 }
 
 static int ghash_async_update(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!irq_fpu_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_update(cryptd_req);
@@ -204,12 +197,12 @@
 static int ghash_async_final(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!irq_fpu_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_final(cryptd_req);
@@ -249,7 +242,8 @@
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable()) {
+	if (!irq_fpu_usable() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_digest(cryptd_req);
diff --git a/arch/x86/crypto/sha-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile
similarity index 100%
rename from arch/x86/crypto/sha-mb/Makefile
rename to arch/x86/crypto/sha1-mb/Makefile
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
similarity index 81%
rename from arch/x86/crypto/sha-mb/sha1_mb.c
rename to arch/x86/crypto/sha1-mb/sha1_mb.c
index 9c5af33..9e5b671 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb.c
@@ -67,7 +67,7 @@
 #include <asm/byteorder.h>
 #include <linux/hardirq.h>
 #include <asm/fpu/api.h>
-#include "sha_mb_ctx.h"
+#include "sha1_mb_ctx.h"
 
 #define FLUSH_INTERVAL 1000 /* in usec */
 
@@ -77,30 +77,34 @@
 	struct mcryptd_ahash *mcryptd_tfm;
 };
 
-static inline struct mcryptd_hash_request_ctx *cast_hash_to_mcryptd_ctx(struct sha1_hash_ctx *hash_ctx)
+static inline struct mcryptd_hash_request_ctx
+		*cast_hash_to_mcryptd_ctx(struct sha1_hash_ctx *hash_ctx)
 {
-	struct shash_desc *desc;
+	struct ahash_request *areq;
 
-	desc = container_of((void *) hash_ctx, struct shash_desc, __ctx);
-	return container_of(desc, struct mcryptd_hash_request_ctx, desc);
+	areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
+	return container_of(areq, struct mcryptd_hash_request_ctx, areq);
 }
 
-static inline struct ahash_request *cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+static inline struct ahash_request
+		*cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
 {
 	return container_of((void *) ctx, struct ahash_request, __ctx);
 }
 
 static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
-				struct shash_desc *desc)
+				struct ahash_request *areq)
 {
 	rctx->flag = HASH_UPDATE;
 }
 
 static asmlinkage void (*sha1_job_mgr_init)(struct sha1_mb_mgr *state);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)(struct sha1_mb_mgr *state,
-							  struct job_sha1 *job);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)(struct sha1_mb_mgr *state);
-static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)(struct sha1_mb_mgr *state);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)
+			(struct sha1_mb_mgr *state, struct job_sha1 *job);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)
+						(struct sha1_mb_mgr *state);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)
+						(struct sha1_mb_mgr *state);
 
 static inline void sha1_init_digest(uint32_t *digest)
 {
@@ -131,7 +135,8 @@
 	return i >> SHA1_LOG2_BLOCK_SIZE;
 }
 
-static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr, struct sha1_hash_ctx *ctx)
+static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr,
+						struct sha1_hash_ctx *ctx)
 {
 	while (ctx) {
 		if (ctx->status & HASH_CTX_STS_COMPLETE) {
@@ -177,8 +182,8 @@
 
 				ctx->job.buffer = (uint8_t *) buffer;
 				ctx->job.len = len;
-				ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr,
-										  &ctx->job);
+				ctx = (struct sha1_hash_ctx *)sha1_job_mgr_submit(&mgr->mgr,
+										&ctx->job);
 				continue;
 			}
 		}
@@ -191,13 +196,15 @@
 		if (ctx->status & HASH_CTX_STS_LAST) {
 
 			uint8_t *buf = ctx->partial_block_buffer;
-			uint32_t n_extra_blocks = sha1_pad(buf, ctx->total_length);
+			uint32_t n_extra_blocks =
+					sha1_pad(buf, ctx->total_length);
 
 			ctx->status = (HASH_CTX_STS_PROCESSING |
 				       HASH_CTX_STS_COMPLETE);
 			ctx->job.buffer = buf;
 			ctx->job.len = (uint32_t) n_extra_blocks;
-			ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
+			ctx = (struct sha1_hash_ctx *)
+				sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
 			continue;
 		}
 
@@ -208,14 +215,17 @@
 	return NULL;
 }
 
-static struct sha1_hash_ctx *sha1_ctx_mgr_get_comp_ctx(struct sha1_ctx_mgr *mgr)
+static struct sha1_hash_ctx
+			*sha1_ctx_mgr_get_comp_ctx(struct sha1_ctx_mgr *mgr)
 {
 	/*
 	 * If get_comp_job returns NULL, there are no jobs complete.
-	 * If get_comp_job returns a job, verify that it is safe to return to the user.
+	 * If get_comp_job returns a job, verify that it is safe to return to
+	 * the user.
 	 * If it is not ready, resubmit the job to finish processing.
 	 * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
-	 * Otherwise, all jobs currently being managed by the hash_ctx_mgr still need processing.
+	 * Otherwise, all jobs currently being managed by the hash_ctx_mgr
+	 * still need processing.
 	 */
 	struct sha1_hash_ctx *ctx;
 
@@ -235,7 +245,10 @@
 					  int flags)
 {
 	if (flags & (~HASH_ENTIRE)) {
-		/* User should not pass anything other than FIRST, UPDATE, or LAST */
+		/*
+		 * User should not pass anything other than FIRST, UPDATE, or
+		 * LAST
+		 */
 		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
 		return ctx;
 	}
@@ -264,14 +277,20 @@
 		ctx->partial_block_buffer_length = 0;
 	}
 
-	/* If we made it here, there were no errors during this call to submit */
+	/*
+	 * If we made it here, there were no errors during this call to
+	 * submit
+	 */
 	ctx->error = HASH_CTX_ERROR_NONE;
 
 	/* Store buffer ptr info from user */
 	ctx->incoming_buffer = buffer;
 	ctx->incoming_buffer_length = len;
 
-	/* Store the user's request flags and mark this ctx as currently being processed. */
+	/*
+	 * Store the user's request flags and mark this ctx as currently
+	 * being processed.
+	 */
 	ctx->status = (flags & HASH_LAST) ?
 			(HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
 			HASH_CTX_STS_PROCESSING;
@@ -285,9 +304,13 @@
 	 * Or if the user's buffer contains less than a whole block,
 	 * append as much as possible to the extra block.
 	 */
-	if ((ctx->partial_block_buffer_length) | (len < SHA1_BLOCK_SIZE)) {
-		/* Compute how many bytes to copy from user buffer into extra block */
-		uint32_t copy_len = SHA1_BLOCK_SIZE - ctx->partial_block_buffer_length;
+	if (ctx->partial_block_buffer_length || len < SHA1_BLOCK_SIZE) {
+		/*
+		 * Compute how many bytes to copy from user buffer into
+		 * extra block
+		 */
+		uint32_t copy_len = SHA1_BLOCK_SIZE -
+					ctx->partial_block_buffer_length;
 		if (len < copy_len)
 			copy_len = len;
 
@@ -297,20 +320,28 @@
 				buffer, copy_len);
 
 			ctx->partial_block_buffer_length += copy_len;
-			ctx->incoming_buffer = (const void *)((const char *)buffer + copy_len);
+			ctx->incoming_buffer = (const void *)
+					((const char *)buffer + copy_len);
 			ctx->incoming_buffer_length = len - copy_len;
 		}
 
-		/* The extra block should never contain more than 1 block here */
+		/*
+		 * The extra block should never contain more than 1 block
+		 * here
+		 */
 		assert(ctx->partial_block_buffer_length <= SHA1_BLOCK_SIZE);
 
-		/* If the extra block buffer contains exactly 1 block, it can be hashed. */
+		/*
+		 * If the extra block buffer contains exactly 1 block, it can
+		 * be hashed.
+		 */
 		if (ctx->partial_block_buffer_length >= SHA1_BLOCK_SIZE) {
 			ctx->partial_block_buffer_length = 0;
 
 			ctx->job.buffer = ctx->partial_block_buffer;
 			ctx->job.len = 1;
-			ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
+			ctx = (struct sha1_hash_ctx *)
+				sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
 		}
 	}
 
@@ -329,23 +360,24 @@
 			return NULL;
 
 		/*
-		 * If flush returned a job, resubmit the job to finish processing.
+		 * If flush returned a job, resubmit the job to finish
+		 * processing.
 		 */
 		ctx = sha1_ctx_mgr_resubmit(mgr, ctx);
 
 		/*
-		 * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
-		 * Otherwise, all jobs currently being managed by the sha1_ctx_mgr
-		 * still need processing. Loop.
+		 * If sha1_ctx_mgr_resubmit returned a job, it is ready to be
+		 * returned. Otherwise, all jobs currently being managed by the
+		 * sha1_ctx_mgr still need processing. Loop.
 		 */
 		if (ctx)
 			return ctx;
 	}
 }
 
-static int sha1_mb_init(struct shash_desc *desc)
+static int sha1_mb_init(struct ahash_request *areq)
 {
-	struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+	struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
 
 	hash_ctx_init(sctx);
 	sctx->job.result_digest[0] = SHA1_H0;
@@ -363,7 +395,7 @@
 static int sha1_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
 {
 	int	i;
-	struct	sha1_hash_ctx *sctx = shash_desc_ctx(&rctx->desc);
+	struct	sha1_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
 	__be32	*dst = (__be32 *) rctx->out;
 
 	for (i = 0; i < 5; ++i)
@@ -394,9 +426,11 @@
 				flag |= HASH_LAST;
 
 		}
-		sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(&rctx->desc);
+		sha_ctx = (struct sha1_hash_ctx *)
+						ahash_request_ctx(&rctx->areq);
 		kernel_fpu_begin();
-		sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, flag);
+		sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx,
+						rctx->walk.data, nbytes, flag);
 		if (!sha_ctx) {
 			if (flush)
 				sha_ctx = sha1_ctx_mgr_flush(cstate->mgr);
@@ -485,11 +519,10 @@
 	mcryptd_arm_flusher(cstate, delay);
 }
 
-static int sha1_mb_update(struct shash_desc *desc, const u8 *data,
-			  unsigned int len)
+static int sha1_mb_update(struct ahash_request *areq)
 {
 	struct mcryptd_hash_request_ctx *rctx =
-			container_of(desc, struct mcryptd_hash_request_ctx, desc);
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
 	struct mcryptd_alg_cstate *cstate =
 				this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
 
@@ -505,7 +538,7 @@
 	}
 
 	/* need to init context */
-	req_ctx_init(rctx, desc);
+	req_ctx_init(rctx, areq);
 
 	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
 
@@ -518,10 +551,11 @@
 		rctx->flag |= HASH_DONE;
 
 	/* submit */
-	sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+	sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
 	sha1_mb_add_list(rctx, cstate);
 	kernel_fpu_begin();
-	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, HASH_UPDATE);
+	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+							nbytes, HASH_UPDATE);
 	kernel_fpu_end();
 
 	/* check if anything is returned */
@@ -544,11 +578,10 @@
 	return ret;
 }
 
-static int sha1_mb_finup(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, u8 *out)
+static int sha1_mb_finup(struct ahash_request *areq)
 {
 	struct mcryptd_hash_request_ctx *rctx =
-			container_of(desc, struct mcryptd_hash_request_ctx, desc);
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
 	struct mcryptd_alg_cstate *cstate =
 				this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
 
@@ -563,7 +596,7 @@
 	}
 
 	/* need to init context */
-	req_ctx_init(rctx, desc);
+	req_ctx_init(rctx, areq);
 
 	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
 
@@ -576,15 +609,15 @@
 		rctx->flag |= HASH_DONE;
 		flag = HASH_LAST;
 	}
-	rctx->out = out;
 
 	/* submit */
 	rctx->flag |= HASH_FINAL;
-	sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+	sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
 	sha1_mb_add_list(rctx, cstate);
 
 	kernel_fpu_begin();
-	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, flag);
+	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+								nbytes, flag);
 	kernel_fpu_end();
 
 	/* check if anything is returned */
@@ -605,10 +638,10 @@
 	return ret;
 }
 
-static int sha1_mb_final(struct shash_desc *desc, u8 *out)
+static int sha1_mb_final(struct ahash_request *areq)
 {
 	struct mcryptd_hash_request_ctx *rctx =
-			container_of(desc, struct mcryptd_hash_request_ctx, desc);
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
 	struct mcryptd_alg_cstate *cstate =
 				this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
 
@@ -623,16 +656,16 @@
 	}
 
 	/* need to init context */
-	req_ctx_init(rctx, desc);
+	req_ctx_init(rctx, areq);
 
-	rctx->out = out;
 	rctx->flag |= HASH_DONE | HASH_FINAL;
 
-	sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+	sha_ctx = (struct sha1_hash_ctx *) ahash_request_ctx(areq);
 	/* flag HASH_FINAL and 0 data size */
 	sha1_mb_add_list(rctx, cstate);
 	kernel_fpu_begin();
-	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0, HASH_LAST);
+	sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
+								HASH_LAST);
 	kernel_fpu_end();
 
 	/* check if anything is returned */
@@ -654,48 +687,98 @@
 	return ret;
 }
 
-static int sha1_mb_export(struct shash_desc *desc, void *out)
+static int sha1_mb_export(struct ahash_request *areq, void *out)
 {
-	struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+	struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
 
 	memcpy(out, sctx, sizeof(*sctx));
 
 	return 0;
 }
 
-static int sha1_mb_import(struct shash_desc *desc, const void *in)
+static int sha1_mb_import(struct ahash_request *areq, const void *in)
 {
-	struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+	struct sha1_hash_ctx *sctx = ahash_request_ctx(areq);
 
 	memcpy(sctx, in, sizeof(*sctx));
 
 	return 0;
 }
 
+static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_ahash *mcryptd_tfm;
+	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mcryptd_hash_ctx *mctx;
 
-static struct shash_alg sha1_mb_shash_alg = {
-	.digestsize	=	SHA1_DIGEST_SIZE,
+	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb",
+						CRYPTO_ALG_INTERNAL,
+						CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(mcryptd_tfm))
+		return PTR_ERR(mcryptd_tfm);
+	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+	mctx->alg_state = &sha1_mb_alg_state;
+	ctx->mcryptd_tfm = mcryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+	return 0;
+}
+
+static void sha1_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static int sha1_mb_areq_init_tfm(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				sizeof(struct sha1_hash_ctx));
+
+	return 0;
+}
+
+static void sha1_mb_areq_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha1_mb_areq_alg = {
 	.init		=	sha1_mb_init,
 	.update		=	sha1_mb_update,
 	.final		=	sha1_mb_final,
 	.finup		=	sha1_mb_finup,
 	.export		=	sha1_mb_export,
 	.import		=	sha1_mb_import,
-	.descsize	=	sizeof(struct sha1_hash_ctx),
-	.statesize	=	sizeof(struct sha1_hash_ctx),
-	.base		=	{
-		.cra_name	 = "__sha1-mb",
-		.cra_driver_name = "__intel_sha1-mb",
-		.cra_priority	 = 100,
-		/*
-		 * use ASYNC flag as some buffers in multi-buffer
-		 * algo may not have completed before hashing thread sleep
-		 */
-		.cra_flags	 = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_ASYNC |
-				   CRYPTO_ALG_INTERNAL,
-		.cra_blocksize	 = SHA1_BLOCK_SIZE,
-		.cra_module	 = THIS_MODULE,
-		.cra_list	 = LIST_HEAD_INIT(sha1_mb_shash_alg.base.cra_list),
+	.halg		=	{
+		.digestsize	=	SHA1_DIGEST_SIZE,
+		.statesize	=	sizeof(struct sha1_hash_ctx),
+		.base		=	{
+			.cra_name	 = "__sha1-mb",
+			.cra_driver_name = "__intel_sha1-mb",
+			.cra_priority	 = 100,
+			/*
+			 * use ASYNC flag as some buffers in multi-buffer
+			 * algo may not have completed before hashing thread
+			 * sleep
+			 */
+			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_INTERNAL,
+			.cra_blocksize	= SHA1_BLOCK_SIZE,
+			.cra_module	= THIS_MODULE,
+			.cra_list	= LIST_HEAD_INIT
+					(sha1_mb_areq_alg.halg.base.cra_list),
+			.cra_init	= sha1_mb_areq_init_tfm,
+			.cra_exit	= sha1_mb_areq_exit_tfm,
+			.cra_ctxsize	= sizeof(struct sha1_hash_ctx),
+		}
 	}
 };
 
@@ -780,48 +863,22 @@
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
-	struct crypto_shash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
 	struct mcryptd_hash_request_ctx *rctx;
-	struct shash_desc *desc;
+	struct ahash_request *areq;
 
 	memcpy(mcryptd_req, req, sizeof(*req));
 	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
 	rctx = ahash_request_ctx(mcryptd_req);
-	desc = &rctx->desc;
-	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	areq = &rctx->areq;
+
+	ahash_request_set_tfm(areq, child);
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
+					rctx->complete, req);
 
 	return crypto_ahash_import(mcryptd_req, in);
 }
 
-static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
-{
-	struct mcryptd_ahash *mcryptd_tfm;
-	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct mcryptd_hash_ctx *mctx;
-
-	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb",
-					  CRYPTO_ALG_INTERNAL,
-					  CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(mcryptd_tfm))
-		return PTR_ERR(mcryptd_tfm);
-	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
-	mctx->alg_state = &sha1_mb_alg_state;
-	ctx->mcryptd_tfm = mcryptd_tfm;
-	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct ahash_request) +
-				 crypto_ahash_reqsize(&mcryptd_tfm->base));
-
-	return 0;
-}
-
-static void sha1_mb_async_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	mcryptd_free_ahash(ctx->mcryptd_tfm);
-}
-
 static struct ahash_alg sha1_mb_async_alg = {
 	.init           = sha1_mb_async_init,
 	.update         = sha1_mb_async_update,
@@ -866,7 +923,8 @@
 		if (time_before(cur_time, rctx->tag.expire))
 			break;
 		kernel_fpu_begin();
-		sha_ctx = (struct sha1_hash_ctx *) sha1_ctx_mgr_flush(cstate->mgr);
+		sha_ctx = (struct sha1_hash_ctx *)
+					sha1_ctx_mgr_flush(cstate->mgr);
 		kernel_fpu_end();
 		if (!sha_ctx) {
 			pr_err("sha1_mb error: nothing got flushed for non-empty list\n");
@@ -927,7 +985,7 @@
 	}
 	sha1_mb_alg_state.flusher = &sha1_mb_flusher;
 
-	err = crypto_register_shash(&sha1_mb_shash_alg);
+	err = crypto_register_ahash(&sha1_mb_areq_alg);
 	if (err)
 		goto err2;
 	err = crypto_register_ahash(&sha1_mb_async_alg);
@@ -937,7 +995,7 @@
 
 	return 0;
 err1:
-	crypto_unregister_shash(&sha1_mb_shash_alg);
+	crypto_unregister_ahash(&sha1_mb_areq_alg);
 err2:
 	for_each_possible_cpu(cpu) {
 		cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
@@ -953,7 +1011,7 @@
 	struct mcryptd_alg_cstate *cpu_state;
 
 	crypto_unregister_ahash(&sha1_mb_async_alg);
-	crypto_unregister_shash(&sha1_mb_shash_alg);
+	crypto_unregister_ahash(&sha1_mb_areq_alg);
 	for_each_possible_cpu(cpu) {
 		cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
 		kfree(cpu_state->mgr);
diff --git a/arch/x86/crypto/sha-mb/sha_mb_ctx.h b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
similarity index 99%
rename from arch/x86/crypto/sha-mb/sha_mb_ctx.h
rename to arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
index e36069d..98a35bc 100644
--- a/arch/x86/crypto/sha-mb/sha_mb_ctx.h
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_ctx.h
@@ -54,7 +54,7 @@
 #ifndef _SHA_MB_CTX_INTERNAL_H
 #define _SHA_MB_CTX_INTERNAL_H
 
-#include "sha_mb_mgr.h"
+#include "sha1_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
 #define HASH_FIRST           0x01
diff --git a/arch/x86/crypto/sha-mb/sha_mb_mgr.h b/arch/x86/crypto/sha1-mb/sha1_mb_mgr.h
similarity index 100%
rename from arch/x86/crypto/sha-mb/sha_mb_mgr.h
rename to arch/x86/crypto/sha1-mb/sha1_mb_mgr.h
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S
similarity index 100%
rename from arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S
rename to arch/x86/crypto/sha1-mb/sha1_mb_mgr_datastruct.S
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
similarity index 100%
rename from arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
rename to arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
similarity index 98%
rename from arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
rename to arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
index 822acb5..d2add0d 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_init_avx2.c
@@ -51,7 +51,7 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "sha_mb_mgr.h"
+#include "sha1_mb_mgr.h"
 
 void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
 {
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S
similarity index 100%
rename from arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
rename to arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S
diff --git a/arch/x86/crypto/sha-mb/sha1_x8_avx2.S b/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S
similarity index 100%
rename from arch/x86/crypto/sha-mb/sha1_x8_avx2.S
rename to arch/x86/crypto/sha1-mb/sha1_x8_avx2.S
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 1024e37..fc61739 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -374,3 +374,9 @@
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
 MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-ssse3");
+MODULE_ALIAS_CRYPTO("sha1-avx");
+MODULE_ALIAS_CRYPTO("sha1-avx2");
+#ifdef CONFIG_AS_SHA1_NI
+MODULE_ALIAS_CRYPTO("sha1-ni");
+#endif
diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile
new file mode 100644
index 0000000..41089e7
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/Makefile
@@ -0,0 +1,11 @@
+#
+# Arch-specific CryptoAPI modules.
+#
+
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+                                $(comma)4)$(comma)%ymm2,yes,no)
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb.o
+	sha256-mb-y := sha256_mb.o sha256_mb_mgr_flush_avx2.o \
+	     sha256_mb_mgr_init_avx2.o sha256_mb_mgr_submit_avx2.o sha256_x8_avx2.o
+endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
new file mode 100644
index 0000000..89fa85e
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -0,0 +1,1030 @@
+/*
+ * Multi buffer SHA256 algorithm Glue Code
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+#include <crypto/mcryptd.h>
+#include <crypto/crypto_wq.h>
+#include <asm/byteorder.h>
+#include <linux/hardirq.h>
+#include <asm/fpu/api.h>
+#include "sha256_mb_ctx.h"
+
+#define FLUSH_INTERVAL 1000 /* in usec */
+
+static struct mcryptd_alg_state sha256_mb_alg_state;
+
+struct sha256_mb_ctx {
+	struct mcryptd_ahash *mcryptd_tfm;
+};
+
+static inline struct mcryptd_hash_request_ctx
+		*cast_hash_to_mcryptd_ctx(struct sha256_hash_ctx *hash_ctx)
+{
+	struct ahash_request *areq;
+
+	areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
+	return container_of(areq, struct mcryptd_hash_request_ctx, areq);
+}
+
+static inline struct ahash_request
+		*cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+{
+	return container_of((void *) ctx, struct ahash_request, __ctx);
+}
+
+static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
+				struct ahash_request *areq)
+{
+	rctx->flag = HASH_UPDATE;
+}
+
+static asmlinkage void (*sha256_job_mgr_init)(struct sha256_mb_mgr *state);
+static asmlinkage struct job_sha256* (*sha256_job_mgr_submit)
+			(struct sha256_mb_mgr *state, struct job_sha256 *job);
+static asmlinkage struct job_sha256* (*sha256_job_mgr_flush)
+			(struct sha256_mb_mgr *state);
+static asmlinkage struct job_sha256* (*sha256_job_mgr_get_comp_job)
+			(struct sha256_mb_mgr *state);
+
+inline void sha256_init_digest(uint32_t *digest)
+{
+	static const uint32_t initial_digest[SHA256_DIGEST_LENGTH] = {
+				SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+				SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7};
+	memcpy(digest, initial_digest, sizeof(initial_digest));
+}
+
+inline uint32_t sha256_pad(uint8_t padblock[SHA256_BLOCK_SIZE * 2],
+			 uint32_t total_len)
+{
+	uint32_t i = total_len & (SHA256_BLOCK_SIZE - 1);
+
+	memset(&padblock[i], 0, SHA256_BLOCK_SIZE);
+	padblock[i] = 0x80;
+
+	i += ((SHA256_BLOCK_SIZE - 1) &
+	      (0 - (total_len + SHA256_PADLENGTHFIELD_SIZE + 1)))
+	     + 1 + SHA256_PADLENGTHFIELD_SIZE;
+
+#if SHA256_PADLENGTHFIELD_SIZE == 16
+	*((uint64_t *) &padblock[i - 16]) = 0;
+#endif
+
+	*((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
+
+	/* Number of extra blocks to hash */
+	return i >> SHA256_LOG2_BLOCK_SIZE;
+}
+
+static struct sha256_hash_ctx
+		*sha256_ctx_mgr_resubmit(struct sha256_ctx_mgr *mgr,
+					struct sha256_hash_ctx *ctx)
+{
+	while (ctx) {
+		if (ctx->status & HASH_CTX_STS_COMPLETE) {
+			/* Clear PROCESSING bit */
+			ctx->status = HASH_CTX_STS_COMPLETE;
+			return ctx;
+		}
+
+		/*
+		 * If the extra blocks are empty, begin hashing what remains
+		 * in the user's buffer.
+		 */
+		if (ctx->partial_block_buffer_length == 0 &&
+		    ctx->incoming_buffer_length) {
+
+			const void *buffer = ctx->incoming_buffer;
+			uint32_t len = ctx->incoming_buffer_length;
+			uint32_t copy_len;
+
+			/*
+			 * Only entire blocks can be hashed.
+			 * Copy remainder to extra blocks buffer.
+			 */
+			copy_len = len & (SHA256_BLOCK_SIZE-1);
+
+			if (copy_len) {
+				len -= copy_len;
+				memcpy(ctx->partial_block_buffer,
+				       ((const char *) buffer + len),
+				       copy_len);
+				ctx->partial_block_buffer_length = copy_len;
+			}
+
+			ctx->incoming_buffer_length = 0;
+
+			/* len should be a multiple of the block size now */
+			assert((len % SHA256_BLOCK_SIZE) == 0);
+
+			/* Set len to the number of blocks to be hashed */
+			len >>= SHA256_LOG2_BLOCK_SIZE;
+
+			if (len) {
+
+				ctx->job.buffer = (uint8_t *) buffer;
+				ctx->job.len = len;
+				ctx = (struct sha256_hash_ctx *)
+				sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
+				continue;
+			}
+		}
+
+		/*
+		 * If the extra blocks are not empty, then we are
+		 * either on the last block(s) or we need more
+		 * user input before continuing.
+		 */
+		if (ctx->status & HASH_CTX_STS_LAST) {
+
+			uint8_t *buf = ctx->partial_block_buffer;
+			uint32_t n_extra_blocks =
+				sha256_pad(buf, ctx->total_length);
+
+			ctx->status = (HASH_CTX_STS_PROCESSING |
+				       HASH_CTX_STS_COMPLETE);
+			ctx->job.buffer = buf;
+			ctx->job.len = (uint32_t) n_extra_blocks;
+			ctx = (struct sha256_hash_ctx *)
+				sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
+			continue;
+		}
+
+		ctx->status = HASH_CTX_STS_IDLE;
+		return ctx;
+	}
+
+	return NULL;
+}
+
+static struct sha256_hash_ctx
+		*sha256_ctx_mgr_get_comp_ctx(struct sha256_ctx_mgr *mgr)
+{
+	/*
+	 * If get_comp_job returns NULL, there are no jobs complete.
+	 * If get_comp_job returns a job, verify that it is safe to return to
+	 * the user. If it is not ready, resubmit the job to finish processing.
+	 * If sha256_ctx_mgr_resubmit returned a job, it is ready to be
+	 * returned. Otherwise, all jobs currently being managed by the
+	 * hash_ctx_mgr still need processing.
+	 */
+	struct sha256_hash_ctx *ctx;
+
+	ctx = (struct sha256_hash_ctx *) sha256_job_mgr_get_comp_job(&mgr->mgr);
+	return sha256_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static void sha256_ctx_mgr_init(struct sha256_ctx_mgr *mgr)
+{
+	sha256_job_mgr_init(&mgr->mgr);
+}
+
+static struct sha256_hash_ctx *sha256_ctx_mgr_submit(struct sha256_ctx_mgr *mgr,
+					  struct sha256_hash_ctx *ctx,
+					  const void *buffer,
+					  uint32_t len,
+					  int flags)
+{
+	if (flags & (~HASH_ENTIRE)) {
+		/* User should not pass anything other than FIRST, UPDATE
+		 * or LAST
+		 */
+		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
+		return ctx;
+	}
+
+	if (ctx->status & HASH_CTX_STS_PROCESSING) {
+		/* Cannot submit to a currently processing job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
+		return ctx;
+	}
+
+	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+		/* Cannot update a finished job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
+		return ctx;
+	}
+
+	if (flags & HASH_FIRST) {
+		/* Init digest */
+		sha256_init_digest(ctx->job.result_digest);
+
+		/* Reset byte counter */
+		ctx->total_length = 0;
+
+		/* Clear extra blocks */
+		ctx->partial_block_buffer_length = 0;
+	}
+
+	/* If we made it here, there was no error during this call to submit */
+	ctx->error = HASH_CTX_ERROR_NONE;
+
+	/* Store buffer ptr info from user */
+	ctx->incoming_buffer = buffer;
+	ctx->incoming_buffer_length = len;
+
+	/*
+	 * Store the user's request flags and mark this ctx as currently
+	 * being processed.
+	 */
+	ctx->status = (flags & HASH_LAST) ?
+			(HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
+			HASH_CTX_STS_PROCESSING;
+
+	/* Advance byte counter */
+	ctx->total_length += len;
+
+	/*
+	 * If there is anything currently buffered in the extra blocks,
+	 * append to it until it contains a whole block.
+	 * Or if the user's buffer contains less than a whole block,
+	 * append as much as possible to the extra block.
+	 */
+	if (ctx->partial_block_buffer_length || len < SHA256_BLOCK_SIZE) {
+		/*
+		 * Compute how many bytes to copy from user buffer into
+		 * extra block
+		 */
+		uint32_t copy_len = SHA256_BLOCK_SIZE -
+					ctx->partial_block_buffer_length;
+		if (len < copy_len)
+			copy_len = len;
+
+		if (copy_len) {
+			/* Copy and update relevant pointers and counters */
+			memcpy(
+		&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
+				buffer, copy_len);
+
+			ctx->partial_block_buffer_length += copy_len;
+			ctx->incoming_buffer = (const void *)
+					((const char *)buffer + copy_len);
+			ctx->incoming_buffer_length = len - copy_len;
+		}
+
+		/* The extra block should never contain more than 1 block */
+		assert(ctx->partial_block_buffer_length <= SHA256_BLOCK_SIZE);
+
+		/*
+		 * If the extra block buffer contains exactly 1 block,
+		 * it can be hashed.
+		 */
+		if (ctx->partial_block_buffer_length >= SHA256_BLOCK_SIZE) {
+			ctx->partial_block_buffer_length = 0;
+
+			ctx->job.buffer = ctx->partial_block_buffer;
+			ctx->job.len = 1;
+			ctx = (struct sha256_hash_ctx *)
+				sha256_job_mgr_submit(&mgr->mgr, &ctx->job);
+		}
+	}
+
+	return sha256_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static struct sha256_hash_ctx *sha256_ctx_mgr_flush(struct sha256_ctx_mgr *mgr)
+{
+	struct sha256_hash_ctx *ctx;
+
+	while (1) {
+		ctx = (struct sha256_hash_ctx *)
+					sha256_job_mgr_flush(&mgr->mgr);
+
+		/* If flush returned 0, there are no more jobs in flight. */
+		if (!ctx)
+			return NULL;
+
+		/*
+		 * If flush returned a job, resubmit the job to finish
+		 * processing.
+		 */
+		ctx = sha256_ctx_mgr_resubmit(mgr, ctx);
+
+		/*
+		 * If sha256_ctx_mgr_resubmit returned a job, it is ready to
+		 * be returned. Otherwise, all jobs currently being managed by
+		 * the sha256_ctx_mgr still need processing. Loop.
+		 */
+		if (ctx)
+			return ctx;
+	}
+}
+
+static int sha256_mb_init(struct ahash_request *areq)
+{
+	struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	hash_ctx_init(sctx);
+	sctx->job.result_digest[0] = SHA256_H0;
+	sctx->job.result_digest[1] = SHA256_H1;
+	sctx->job.result_digest[2] = SHA256_H2;
+	sctx->job.result_digest[3] = SHA256_H3;
+	sctx->job.result_digest[4] = SHA256_H4;
+	sctx->job.result_digest[5] = SHA256_H5;
+	sctx->job.result_digest[6] = SHA256_H6;
+	sctx->job.result_digest[7] = SHA256_H7;
+	sctx->total_length = 0;
+	sctx->partial_block_buffer_length = 0;
+	sctx->status = HASH_CTX_STS_IDLE;
+
+	return 0;
+}
+
+static int sha256_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
+{
+	int	i;
+	struct	sha256_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
+	__be32	*dst = (__be32 *) rctx->out;
+
+	for (i = 0; i < 8; ++i)
+		dst[i] = cpu_to_be32(sctx->job.result_digest[i]);
+
+	return 0;
+}
+
+static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
+			struct mcryptd_alg_cstate *cstate, bool flush)
+{
+	int	flag = HASH_UPDATE;
+	int	nbytes, err = 0;
+	struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
+	struct sha256_hash_ctx *sha_ctx;
+
+	/* more work ? */
+	while (!(rctx->flag & HASH_DONE)) {
+		nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
+		if (nbytes < 0) {
+			err = nbytes;
+			goto out;
+		}
+		/* check if the walk is done */
+		if (crypto_ahash_walk_last(&rctx->walk)) {
+			rctx->flag |= HASH_DONE;
+			if (rctx->flag & HASH_FINAL)
+				flag |= HASH_LAST;
+
+		}
+		sha_ctx = (struct sha256_hash_ctx *)
+						ahash_request_ctx(&rctx->areq);
+		kernel_fpu_begin();
+		sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx,
+						rctx->walk.data, nbytes, flag);
+		if (!sha_ctx) {
+			if (flush)
+				sha_ctx = sha256_ctx_mgr_flush(cstate->mgr);
+		}
+		kernel_fpu_end();
+		if (sha_ctx)
+			rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		else {
+			rctx = NULL;
+			goto out;
+		}
+	}
+
+	/* copy the results */
+	if (rctx->flag & HASH_FINAL)
+		sha256_mb_set_results(rctx);
+
+out:
+	*ret_rctx = rctx;
+	return err;
+}
+
+static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
+			    struct mcryptd_alg_cstate *cstate,
+			    int err)
+{
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha256_hash_ctx *sha_ctx;
+	struct mcryptd_hash_request_ctx *req_ctx;
+	int ret;
+
+	/* remove from work list */
+	spin_lock(&cstate->work_lock);
+	list_del(&rctx->waiter);
+	spin_unlock(&cstate->work_lock);
+
+	if (irqs_disabled())
+		rctx->complete(&req->base, err);
+	else {
+		local_bh_disable();
+		rctx->complete(&req->base, err);
+		local_bh_enable();
+	}
+
+	/* check to see if there are other jobs that are done */
+	sha_ctx = sha256_ctx_mgr_get_comp_ctx(cstate->mgr);
+	while (sha_ctx) {
+		req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		ret = sha_finish_walk(&req_ctx, cstate, false);
+		if (req_ctx) {
+			spin_lock(&cstate->work_lock);
+			list_del(&req_ctx->waiter);
+			spin_unlock(&cstate->work_lock);
+
+			req = cast_mcryptd_ctx_to_req(req_ctx);
+			if (irqs_disabled())
+				rctx->complete(&req->base, ret);
+			else {
+				local_bh_disable();
+				rctx->complete(&req->base, ret);
+				local_bh_enable();
+			}
+		}
+		sha_ctx = sha256_ctx_mgr_get_comp_ctx(cstate->mgr);
+	}
+
+	return 0;
+}
+
+static void sha256_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
+			     struct mcryptd_alg_cstate *cstate)
+{
+	unsigned long next_flush;
+	unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
+
+	/* initialize tag */
+	rctx->tag.arrival = jiffies;    /* tag the arrival time */
+	rctx->tag.seq_num = cstate->next_seq_num++;
+	next_flush = rctx->tag.arrival + delay;
+	rctx->tag.expire = next_flush;
+
+	spin_lock(&cstate->work_lock);
+	list_add_tail(&rctx->waiter, &cstate->work_list);
+	spin_unlock(&cstate->work_lock);
+
+	mcryptd_arm_flusher(cstate, delay);
+}
+
+static int sha256_mb_update(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha256_hash_ctx *sha_ctx;
+	int ret = 0, nbytes;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk))
+		rctx->flag |= HASH_DONE;
+
+	/* submit */
+	sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
+	sha256_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+							nbytes, HASH_UPDATE);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha256_mb_finup(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+		container_of(areq, struct mcryptd_hash_request_ctx, areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha256_hash_ctx *sha_ctx;
+	int ret = 0, flag = HASH_UPDATE, nbytes;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk)) {
+		rctx->flag |= HASH_DONE;
+		flag = HASH_LAST;
+	}
+
+	/* submit */
+	rctx->flag |= HASH_FINAL;
+	sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
+	sha256_mb_add_list(rctx, cstate);
+
+	kernel_fpu_begin();
+	sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+								nbytes, flag);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha256_mb_final(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+			areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha256_mb_alg_state.alg_cstate);
+
+	struct sha256_hash_ctx *sha_ctx;
+	int ret = 0;
+	u8 data;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	rctx->flag |= HASH_DONE | HASH_FINAL;
+
+	sha_ctx = (struct sha256_hash_ctx *) ahash_request_ctx(areq);
+	/* flag HASH_FINAL and 0 data size */
+	sha256_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha256_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
+								HASH_LAST);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha256_mb_export(struct ahash_request *areq, void *out)
+{
+	struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha256_mb_import(struct ahash_request *areq, const void *in)
+{
+	struct sha256_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha256_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_ahash *mcryptd_tfm;
+	struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mcryptd_hash_ctx *mctx;
+
+	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha256-mb",
+						CRYPTO_ALG_INTERNAL,
+						CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(mcryptd_tfm))
+		return PTR_ERR(mcryptd_tfm);
+	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+	mctx->alg_state = &sha256_mb_alg_state;
+	ctx->mcryptd_tfm = mcryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+	return 0;
+}
+
+static void sha256_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static int sha256_mb_areq_init_tfm(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				sizeof(struct sha256_hash_ctx));
+
+	return 0;
+}
+
+static void sha256_mb_areq_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha256_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha256_mb_areq_alg = {
+	.init		=	sha256_mb_init,
+	.update		=	sha256_mb_update,
+	.final		=	sha256_mb_final,
+	.finup		=	sha256_mb_finup,
+	.export		=	sha256_mb_export,
+	.import		=	sha256_mb_import,
+	.halg		=	{
+	.digestsize	=	SHA256_DIGEST_SIZE,
+	.statesize	=	sizeof(struct sha256_hash_ctx),
+		.base		=	{
+			.cra_name	 = "__sha256-mb",
+			.cra_driver_name = "__intel_sha256-mb",
+			.cra_priority	 = 100,
+			/*
+			 * use ASYNC flag as some buffers in multi-buffer
+			 * algo may not have completed before hashing thread
+			 * sleep
+			 */
+			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_INTERNAL,
+			.cra_blocksize	= SHA256_BLOCK_SIZE,
+			.cra_module	= THIS_MODULE,
+			.cra_list	= LIST_HEAD_INIT
+					(sha256_mb_areq_alg.halg.base.cra_list),
+			.cra_init	= sha256_mb_areq_init_tfm,
+			.cra_exit	= sha256_mb_areq_exit_tfm,
+			.cra_ctxsize	= sizeof(struct sha256_hash_ctx),
+		}
+	}
+};
+
+static int sha256_mb_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_init(mcryptd_req);
+}
+
+static int sha256_mb_async_update(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_update(mcryptd_req);
+}
+
+static int sha256_mb_async_finup(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_finup(mcryptd_req);
+}
+
+static int sha256_mb_async_final(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_final(mcryptd_req);
+}
+
+static int sha256_mb_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_digest(mcryptd_req);
+}
+
+static int sha256_mb_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_export(mcryptd_req, out);
+}
+
+static int sha256_mb_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha256_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+	struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct mcryptd_hash_request_ctx *rctx;
+	struct ahash_request *areq;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	rctx = ahash_request_ctx(mcryptd_req);
+	areq = &rctx->areq;
+
+	ahash_request_set_tfm(areq, child);
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
+					rctx->complete, req);
+
+	return crypto_ahash_import(mcryptd_req, in);
+}
+
+static struct ahash_alg sha256_mb_async_alg = {
+	.init           = sha256_mb_async_init,
+	.update         = sha256_mb_async_update,
+	.final          = sha256_mb_async_final,
+	.finup          = sha256_mb_async_finup,
+	.export         = sha256_mb_async_export,
+	.import         = sha256_mb_async_import,
+	.digest         = sha256_mb_async_digest,
+	.halg = {
+		.digestsize     = SHA256_DIGEST_SIZE,
+		.statesize      = sizeof(struct sha256_hash_ctx),
+		.base = {
+			.cra_name               = "sha256",
+			.cra_driver_name        = "sha256_mb",
+			.cra_priority           = 200,
+			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
+							CRYPTO_ALG_ASYNC,
+			.cra_blocksize          = SHA256_BLOCK_SIZE,
+			.cra_type               = &crypto_ahash_type,
+			.cra_module             = THIS_MODULE,
+			.cra_list               = LIST_HEAD_INIT
+				(sha256_mb_async_alg.halg.base.cra_list),
+			.cra_init               = sha256_mb_async_init_tfm,
+			.cra_exit               = sha256_mb_async_exit_tfm,
+			.cra_ctxsize		= sizeof(struct sha256_mb_ctx),
+			.cra_alignmask		= 0,
+		},
+	},
+};
+
+static unsigned long sha256_mb_flusher(struct mcryptd_alg_cstate *cstate)
+{
+	struct mcryptd_hash_request_ctx *rctx;
+	unsigned long cur_time;
+	unsigned long next_flush = 0;
+	struct sha256_hash_ctx *sha_ctx;
+
+
+	cur_time = jiffies;
+
+	while (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		if (time_before(cur_time, rctx->tag.expire))
+			break;
+		kernel_fpu_begin();
+		sha_ctx = (struct sha256_hash_ctx *)
+					sha256_ctx_mgr_flush(cstate->mgr);
+		kernel_fpu_end();
+		if (!sha_ctx) {
+			pr_err("sha256_mb error: nothing got"
+					" flushed for non-empty list\n");
+			break;
+		}
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		sha_finish_walk(&rctx, cstate, true);
+		sha_complete_job(rctx, cstate, 0);
+	}
+
+	if (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		/* get the hash context and then flush time */
+		next_flush = rctx->tag.expire;
+		mcryptd_arm_flusher(cstate, get_delay(next_flush));
+	}
+	return next_flush;
+}
+
+static int __init sha256_mb_mod_init(void)
+{
+
+	int cpu;
+	int err;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	/* check for dependent cpu features */
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_BMI2))
+		return -ENODEV;
+
+	/* initialize multibuffer structures */
+	sha256_mb_alg_state.alg_cstate = alloc_percpu
+						(struct mcryptd_alg_cstate);
+
+	sha256_job_mgr_init = sha256_mb_mgr_init_avx2;
+	sha256_job_mgr_submit = sha256_mb_mgr_submit_avx2;
+	sha256_job_mgr_flush = sha256_mb_mgr_flush_avx2;
+	sha256_job_mgr_get_comp_job = sha256_mb_mgr_get_comp_job_avx2;
+
+	if (!sha256_mb_alg_state.alg_cstate)
+		return -ENOMEM;
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
+		cpu_state->next_flush = 0;
+		cpu_state->next_seq_num = 0;
+		cpu_state->flusher_engaged = false;
+		INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
+		cpu_state->cpu = cpu;
+		cpu_state->alg_state = &sha256_mb_alg_state;
+		cpu_state->mgr = kzalloc(sizeof(struct sha256_ctx_mgr),
+					GFP_KERNEL);
+		if (!cpu_state->mgr)
+			goto err2;
+		sha256_ctx_mgr_init(cpu_state->mgr);
+		INIT_LIST_HEAD(&cpu_state->work_list);
+		spin_lock_init(&cpu_state->work_lock);
+	}
+	sha256_mb_alg_state.flusher = &sha256_mb_flusher;
+
+	err = crypto_register_ahash(&sha256_mb_areq_alg);
+	if (err)
+		goto err2;
+	err = crypto_register_ahash(&sha256_mb_async_alg);
+	if (err)
+		goto err1;
+
+
+	return 0;
+err1:
+	crypto_unregister_ahash(&sha256_mb_areq_alg);
+err2:
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha256_mb_alg_state.alg_cstate);
+	return -ENODEV;
+}
+
+static void __exit sha256_mb_mod_fini(void)
+{
+	int cpu;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	crypto_unregister_ahash(&sha256_mb_async_alg);
+	crypto_unregister_ahash(&sha256_mb_areq_alg);
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha256_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha256_mb_alg_state.alg_cstate);
+}
+
+module_init(sha256_mb_mod_init);
+module_exit(sha256_mb_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, multi buffer accelerated");
+
+MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/x86/crypto/sha-mb/sha_mb_ctx.h b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
similarity index 87%
copy from arch/x86/crypto/sha-mb/sha_mb_ctx.h
copy to arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
index e36069d..edd252b 100644
--- a/arch/x86/crypto/sha-mb/sha_mb_ctx.h
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_ctx.h
@@ -1,12 +1,12 @@
 /*
- * Header file for multi buffer SHA context
+ * Header file for multi buffer SHA256 context
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
  *
  * GPL LICENSE SUMMARY
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of version 2 of the GNU General Public License as
@@ -18,11 +18,11 @@
  *  General Public License for more details.
  *
  *  Contact Information:
- *	Tim Chen <tim.c.chen@linux.intel.com>
+ *	Megha Dey <megha.dey@linux.intel.com>
  *
  *  BSD LICENSE
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  Redistribution and use in source and binary forms, with or without
  *  modification, are permitted provided that the following conditions
@@ -54,7 +54,7 @@
 #ifndef _SHA_MB_CTX_INTERNAL_H
 #define _SHA_MB_CTX_INTERNAL_H
 
-#include "sha_mb_mgr.h"
+#include "sha256_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
 #define HASH_FIRST           0x01
@@ -94,10 +94,10 @@
 
 
 /* Hash Constants and Typedefs */
-#define SHA1_DIGEST_LENGTH          5
-#define SHA1_LOG2_BLOCK_SIZE        6
+#define SHA256_DIGEST_LENGTH        8
+#define SHA256_LOG2_BLOCK_SIZE        6
 
-#define SHA1_PADLENGTHFIELD_SIZE    8
+#define SHA256_PADLENGTHFIELD_SIZE    8
 
 #ifdef SHA_MB_DEBUG
 #define assert(expr) \
@@ -111,15 +111,15 @@
 #define assert(expr) do {} while (0)
 #endif
 
-struct sha1_ctx_mgr {
-	struct sha1_mb_mgr mgr;
+struct sha256_ctx_mgr {
+	struct sha256_mb_mgr mgr;
 };
 
-/* typedef struct sha1_ctx_mgr sha1_ctx_mgr; */
+/* typedef struct sha256_ctx_mgr sha256_ctx_mgr; */
 
-struct sha1_hash_ctx {
+struct sha256_hash_ctx {
 	/* Must be at struct offset 0 */
-	struct job_sha1       job;
+	struct job_sha256       job;
 	/* status flag */
 	int status;
 	/* error flag */
@@ -128,7 +128,7 @@
 	uint32_t	total_length;
 	const void	*incoming_buffer;
 	uint32_t	incoming_buffer_length;
-	uint8_t		partial_block_buffer[SHA1_BLOCK_SIZE * 2];
+	uint8_t		partial_block_buffer[SHA256_BLOCK_SIZE * 2];
 	uint32_t	partial_block_buffer_length;
 	void		*user_data;
 };
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
similarity index 61%
copy from arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
copy to arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
index 822acb5..b01ae40 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr.h
@@ -1,12 +1,12 @@
 /*
- * Initialization code for multi buffer SHA1 algorithm for AVX2
+ * Header file for multi buffer SHA256 algorithm manager
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
  *
  * GPL LICENSE SUMMARY
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of version 2 of the GNU General Public License as
@@ -18,11 +18,11 @@
  *  General Public License for more details.
  *
  *  Contact Information:
- *	Tim Chen <tim.c.chen@linux.intel.com>
+ *	Megha Dey <megha.dey@linux.intel.com>
  *
  *  BSD LICENSE
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  Redistribution and use in source and binary forms, with or without
  *  modification, are permitted provided that the following conditions
@@ -50,15 +50,59 @@
  *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
+#ifndef __SHA_MB_MGR_H
+#define __SHA_MB_MGR_H
 
-#include "sha_mb_mgr.h"
+#include <linux/types.h>
 
-void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
-{
-	unsigned int j;
-	state->unused_lanes = 0xF76543210ULL;
-	for (j = 0; j < 8; j++) {
-		state->lens[j] = 0xFFFFFFFF;
-		state->ldata[j].job_in_lane = NULL;
-	}
-}
+#define NUM_SHA256_DIGEST_WORDS 8
+
+enum job_sts {	STS_UNKNOWN = 0,
+		STS_BEING_PROCESSED = 1,
+		STS_COMPLETED = 2,
+		STS_INTERNAL_ERROR = 3,
+		STS_ERROR = 4
+};
+
+struct job_sha256 {
+	u8	*buffer;
+	u32	len;
+	u32	result_digest[NUM_SHA256_DIGEST_WORDS] __aligned(32);
+	enum	job_sts status;
+	void	*user_data;
+};
+
+/* SHA256 out-of-order scheduler */
+
+/* typedef uint32_t sha8_digest_array[8][8]; */
+
+struct sha256_args_x8 {
+	uint32_t	digest[8][8];
+	uint8_t		*data_ptr[8];
+};
+
+struct sha256_lane_data {
+	struct job_sha256 *job_in_lane;
+};
+
+struct sha256_mb_mgr {
+	struct sha256_args_x8 args;
+
+	uint32_t lens[8];
+
+	/* each byte is index (0...7) of unused lanes */
+	uint64_t unused_lanes;
+	/* byte 4 is set to FF as a flag */
+	struct sha256_lane_data ldata[8];
+};
+
+
+#define SHA256_MB_MGR_NUM_LANES_AVX2 8
+
+void sha256_mb_mgr_init_avx2(struct sha256_mb_mgr *state);
+struct job_sha256 *sha256_mb_mgr_submit_avx2(struct sha256_mb_mgr *state,
+					 struct job_sha256 *job);
+struct job_sha256 *sha256_mb_mgr_flush_avx2(struct sha256_mb_mgr *state);
+struct job_sha256 *sha256_mb_mgr_get_comp_job_avx2(struct sha256_mb_mgr *state);
+
+#endif
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S
new file mode 100644
index 0000000..5c377ba
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_datastruct.S
@@ -0,0 +1,304 @@
+/*
+ * Header file for multi buffer SHA256 algorithm data structure
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# Macros for defining data structures
+
+# Usage example
+
+#START_FIELDS	# JOB_AES
+###	name		size	align
+#FIELD	_plaintext,	8,	8	# pointer to plaintext
+#FIELD	_ciphertext,	8,	8	# pointer to ciphertext
+#FIELD	_IV,		16,	8	# IV
+#FIELD	_keys,		8,	8	# pointer to keys
+#FIELD	_len,		4,	4	# length in bytes
+#FIELD	_status,	4,	4	# status enumeration
+#FIELD	_user_data,	8,	8	# pointer to user data
+#UNION  _union,         size1,  align1, \
+#	                size2,  align2, \
+#	                size3,  align3, \
+#	                ...
+#END_FIELDS
+#%assign _JOB_AES_size	_FIELD_OFFSET
+#%assign _JOB_AES_align	_STRUCT_ALIGN
+
+#########################################################################
+
+# Alternate "struc-like" syntax:
+#	STRUCT job_aes2
+#	RES_Q	.plaintext,	1
+#	RES_Q	.ciphertext, 	1
+#	RES_DQ	.IV,		1
+#	RES_B	.nested,	_JOB_AES_SIZE, _JOB_AES_ALIGN
+#	RES_U	.union,		size1, align1, \
+#				size2, align2, \
+#				...
+#	ENDSTRUCT
+#	# Following only needed if nesting
+#	%assign job_aes2_size	_FIELD_OFFSET
+#	%assign job_aes2_align	_STRUCT_ALIGN
+#
+# RES_* macros take a name, a count and an optional alignment.
+# The count in in terms of the base size of the macro, and the
+# default alignment is the base size.
+# The macros are:
+# Macro    Base size
+# RES_B	    1
+# RES_W	    2
+# RES_D     4
+# RES_Q     8
+# RES_DQ   16
+# RES_Y    32
+# RES_Z    64
+#
+# RES_U defines a union. It's arguments are a name and two or more
+# pairs of "size, alignment"
+#
+# The two assigns are only needed if this structure is being nested
+# within another. Even if the assigns are not done, one can still use
+# STRUCT_NAME_size as the size of the structure.
+#
+# Note that for nesting, you still need to assign to STRUCT_NAME_size.
+#
+# The differences between this and using "struc" directly are that each
+# type is implicitly aligned to its natural length (although this can be
+# over-ridden with an explicit third parameter), and that the structure
+# is padded at the end to its overall alignment.
+#
+
+#########################################################################
+
+#ifndef _DATASTRUCT_ASM_
+#define _DATASTRUCT_ASM_
+
+#define SZ8			8*SHA256_DIGEST_WORD_SIZE
+#define ROUNDS			64*SZ8
+#define PTR_SZ                  8
+#define SHA256_DIGEST_WORD_SIZE 4
+#define MAX_SHA256_LANES        8
+#define SHA256_DIGEST_WORDS 8
+#define SHA256_DIGEST_ROW_SIZE  (MAX_SHA256_LANES * SHA256_DIGEST_WORD_SIZE)
+#define SHA256_DIGEST_SIZE      (SHA256_DIGEST_ROW_SIZE * SHA256_DIGEST_WORDS)
+#define SHA256_BLK_SZ           64
+
+# START_FIELDS
+.macro START_FIELDS
+ _FIELD_OFFSET = 0
+ _STRUCT_ALIGN = 0
+.endm
+
+# FIELD name size align
+.macro FIELD name size align
+ _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
+ \name	= _FIELD_OFFSET
+ _FIELD_OFFSET = _FIELD_OFFSET + (\size)
+.if (\align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = \align
+.endif
+.endm
+
+# END_FIELDS
+.macro END_FIELDS
+ _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
+.endm
+
+########################################################################
+
+.macro STRUCT p1
+START_FIELDS
+.struc \p1
+.endm
+
+.macro ENDSTRUCT
+ tmp = _FIELD_OFFSET
+ END_FIELDS
+ tmp = (_FIELD_OFFSET - %%tmp)
+.if (tmp > 0)
+	.lcomm	tmp
+.endif
+.endstruc
+.endm
+
+## RES_int name size align
+.macro RES_int p1 p2 p3
+ name = \p1
+ size = \p2
+ align = .\p3
+
+ _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
+.align align
+.lcomm name size
+ _FIELD_OFFSET = _FIELD_OFFSET + (size)
+.if (align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = align
+.endif
+.endm
+
+# macro RES_B name, size [, align]
+.macro RES_B _name, _size, _align=1
+RES_int _name _size _align
+.endm
+
+# macro RES_W name, size [, align]
+.macro RES_W _name, _size, _align=2
+RES_int _name 2*(_size) _align
+.endm
+
+# macro RES_D name, size [, align]
+.macro RES_D _name, _size, _align=4
+RES_int _name 4*(_size) _align
+.endm
+
+# macro RES_Q name, size [, align]
+.macro RES_Q _name, _size, _align=8
+RES_int _name 8*(_size) _align
+.endm
+
+# macro RES_DQ name, size [, align]
+.macro RES_DQ _name, _size, _align=16
+RES_int _name 16*(_size) _align
+.endm
+
+# macro RES_Y name, size [, align]
+.macro RES_Y _name, _size, _align=32
+RES_int _name 32*(_size) _align
+.endm
+
+# macro RES_Z name, size [, align]
+.macro RES_Z _name, _size, _align=64
+RES_int _name 64*(_size) _align
+.endm
+
+#endif
+
+
+########################################################################
+#### Define SHA256 Out Of Order Data Structures
+########################################################################
+
+START_FIELDS    # LANE_DATA
+###     name            size    align
+FIELD   _job_in_lane,   8,      8       # pointer to job object
+END_FIELDS
+
+ _LANE_DATA_size = _FIELD_OFFSET
+ _LANE_DATA_align = _STRUCT_ALIGN
+
+########################################################################
+
+START_FIELDS    # SHA256_ARGS_X4
+###     name            size    align
+FIELD   _digest,        4*8*8,  4       # transposed digest
+FIELD   _data_ptr,      8*8,    8       # array of pointers to data
+END_FIELDS
+
+ _SHA256_ARGS_X4_size  =  _FIELD_OFFSET
+ _SHA256_ARGS_X4_align = _STRUCT_ALIGN
+ _SHA256_ARGS_X8_size  =	_FIELD_OFFSET
+ _SHA256_ARGS_X8_align =	_STRUCT_ALIGN
+
+#######################################################################
+
+START_FIELDS    # MB_MGR
+###     name            size    align
+FIELD   _args,          _SHA256_ARGS_X4_size, _SHA256_ARGS_X4_align
+FIELD   _lens,          4*8,    8
+FIELD   _unused_lanes,  8,      8
+FIELD   _ldata,         _LANE_DATA_size*8, _LANE_DATA_align
+END_FIELDS
+
+ _MB_MGR_size  =  _FIELD_OFFSET
+ _MB_MGR_align =  _STRUCT_ALIGN
+
+_args_digest   =     _args + _digest
+_args_data_ptr =     _args + _data_ptr
+
+#######################################################################
+
+START_FIELDS    #STACK_FRAME
+###     name            size    align
+FIELD   _data,		16*SZ8,   1       # transposed digest
+FIELD   _digest,         8*SZ8,   1       # array of pointers to data
+FIELD   _ytmp,           4*SZ8,   1
+FIELD   _rsp,            8,       1
+END_FIELDS
+
+ _STACK_FRAME_size  =  _FIELD_OFFSET
+ _STACK_FRAME_align =  _STRUCT_ALIGN
+
+#######################################################################
+
+########################################################################
+#### Define constants
+########################################################################
+
+#define STS_UNKNOWN             0
+#define STS_BEING_PROCESSED     1
+#define STS_COMPLETED           2
+
+########################################################################
+#### Define JOB_SHA256 structure
+########################################################################
+
+START_FIELDS    # JOB_SHA256
+
+###     name                            size    align
+FIELD   _buffer,                        8,      8       # pointer to buffer
+FIELD   _len,                           8,      8       # length in bytes
+FIELD   _result_digest,                 8*4,    32      # Digest (output)
+FIELD   _status,                        4,      4
+FIELD   _user_data,                     8,      8
+END_FIELDS
+
+ _JOB_SHA256_size = _FIELD_OFFSET
+ _JOB_SHA256_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
new file mode 100644
index 0000000..b691da9
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -0,0 +1,304 @@
+/*
+ * Flush routine for SHA256 multibuffer
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha256_mb_mgr_datastruct.S"
+
+.extern sha256_x8_avx2
+
+#LINUX register definitions
+#define arg1	%rdi
+#define arg2	%rsi
+
+# Common register definitions
+#define state	arg1
+#define job	arg2
+#define len2	arg2
+
+# idx must be a register not clobberred by sha1_mult
+#define idx		%r8
+#define DWORD_idx	%r8d
+
+#define unused_lanes	%rbx
+#define lane_data	%rbx
+#define tmp2		%rbx
+#define tmp2_w		%ebx
+
+#define job_rax		%rax
+#define tmp1		%rax
+#define size_offset	%rax
+#define tmp		%rax
+#define start_offset	%rax
+
+#define tmp3		%arg1
+
+#define extra_blocks	%arg2
+#define p		%arg2
+
+.macro LABEL prefix n
+\prefix\n\():
+.endm
+
+.macro JNE_SKIP i
+jne     skip_\i
+.endm
+
+.altmacro
+.macro SET_OFFSET _offset
+offset = \_offset
+.endm
+.noaltmacro
+
+# JOB_SHA256* sha256_mb_mgr_flush_avx2(MB_MGR *state)
+# arg 1 : rcx : state
+ENTRY(sha256_mb_mgr_flush_avx2)
+	FRAME_BEGIN
+        push    %rbx
+
+	# If bit (32+3) is set, then all lanes are empty
+	mov	_unused_lanes(state), unused_lanes
+	bt	$32+3, unused_lanes
+	jc	return_null
+
+	# find a lane with a non-null job
+	xor	idx, idx
+	offset = (_ldata + 1 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	one(%rip), idx
+	offset = (_ldata + 2 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	two(%rip), idx
+	offset = (_ldata + 3 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	three(%rip), idx
+	offset = (_ldata + 4 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	four(%rip), idx
+	offset = (_ldata + 5 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	five(%rip), idx
+	offset = (_ldata + 6 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	six(%rip), idx
+	offset = (_ldata + 7 * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+	cmovne	seven(%rip), idx
+
+	# copy idx to empty lanes
+copy_lane_data:
+	offset =  (_args + _data_ptr)
+	mov	offset(state,idx,8), tmp
+
+	I = 0
+.rep 8
+	offset = (_ldata + I * _LANE_DATA_size + _job_in_lane)
+	cmpq	$0, offset(state)
+.altmacro
+	JNE_SKIP %I
+	offset =  (_args + _data_ptr + 8*I)
+	mov	tmp, offset(state)
+	offset =  (_lens + 4*I)
+	movl	$0xFFFFFFFF, offset(state)
+LABEL skip_ %I
+	I = (I+1)
+.noaltmacro
+.endr
+
+	# Find min length
+	vmovdqa _lens+0*16(state), %xmm0
+	vmovdqa _lens+1*16(state), %xmm1
+
+	vpminud %xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
+	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
+	vpminud %xmm3, %xmm2, %xmm2		# xmm2 has {x,x,E,F}
+	vpalignr $4, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,x,E}
+	vpminud %xmm3, %xmm2, %xmm2		# xmm2 has min val in low dword
+
+	vmovd	%xmm2, DWORD_idx
+	mov	idx, len2
+	and	$0xF, idx
+	shr	$4, len2
+	jz	len_is_0
+
+	vpand	clear_low_nibble(%rip), %xmm2, %xmm2
+	vpshufd	$0, %xmm2, %xmm2
+
+	vpsubd	%xmm2, %xmm0, %xmm0
+	vpsubd	%xmm2, %xmm1, %xmm1
+
+	vmovdqa	%xmm0, _lens+0*16(state)
+	vmovdqa	%xmm1, _lens+1*16(state)
+
+	# "state" and "args" are the same address, arg1
+	# len is arg2
+	call	sha256_x8_avx2
+	# state and idx are intact
+
+len_is_0:
+	# process completed job "idx"
+	imul	$_LANE_DATA_size, idx, lane_data
+	lea	_ldata(state, lane_data), lane_data
+
+	mov	_job_in_lane(lane_data), job_rax
+	movq	$0, _job_in_lane(lane_data)
+	movl	$STS_COMPLETED, _status(job_rax)
+	mov	_unused_lanes(state), unused_lanes
+	shl	$4, unused_lanes
+	or	idx, unused_lanes
+
+	mov	unused_lanes, _unused_lanes(state)
+	movl	$0xFFFFFFFF, _lens(state,idx,4)
+
+	vmovd	_args_digest(state , idx, 4) , %xmm0
+	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
+	vmovd	_args_digest+4*32(state, idx, 4), %xmm1
+	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
+
+	vmovdqu	%xmm0, _result_digest(job_rax)
+	offset =  (_result_digest + 1*16)
+	vmovdqu	%xmm1, offset(job_rax)
+
+return:
+	pop     %rbx
+	FRAME_END
+	ret
+
+return_null:
+	xor	job_rax, job_rax
+	jmp	return
+ENDPROC(sha256_mb_mgr_flush_avx2)
+
+##############################################################################
+
+.align 16
+ENTRY(sha256_mb_mgr_get_comp_job_avx2)
+	push	%rbx
+
+	## if bit 32+3 is set, then all lanes are empty
+	mov	_unused_lanes(state), unused_lanes
+	bt	$(32+3), unused_lanes
+	jc	.return_null
+
+	# Find min length
+	vmovdqa	_lens(state), %xmm0
+	vmovdqa	_lens+1*16(state), %xmm1
+
+	vpminud	%xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
+	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has {x,x,E,F}
+	vpalignr $4, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,x,E}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has min val in low dword
+
+	vmovd	%xmm2, DWORD_idx
+	test	$~0xF, idx
+	jnz	.return_null
+
+	# process completed job "idx"
+	imul	$_LANE_DATA_size, idx, lane_data
+	lea	_ldata(state, lane_data), lane_data
+
+	mov	_job_in_lane(lane_data), job_rax
+	movq	$0,  _job_in_lane(lane_data)
+	movl	$STS_COMPLETED, _status(job_rax)
+	mov	_unused_lanes(state), unused_lanes
+	shl	$4, unused_lanes
+	or	idx, unused_lanes
+	mov	unused_lanes, _unused_lanes(state)
+
+	movl	$0xFFFFFFFF, _lens(state,  idx, 4)
+
+	vmovd	_args_digest(state, idx, 4), %xmm0
+	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
+	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
+	movl	_args_digest+4*32(state, idx, 4), tmp2_w
+	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
+	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
+
+	vmovdqu	%xmm0, _result_digest(job_rax)
+	movl	tmp2_w, _result_digest+1*16(job_rax)
+
+	pop	%rbx
+
+	ret
+
+.return_null:
+	xor	job_rax, job_rax
+	pop	%rbx
+	ret
+ENDPROC(sha256_mb_mgr_get_comp_job_avx2)
+
+.data
+
+.align 16
+clear_low_nibble:
+.octa	0x000000000000000000000000FFFFFFF0
+one:
+.quad	1
+two:
+.quad	2
+three:
+.quad	3
+four:
+.quad	4
+five:
+.quad	5
+six:
+.quad	6
+seven:
+.quad  7
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
similarity index 89%
copy from arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
copy to arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
index 822acb5..b0c4983 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_init_avx2.c
@@ -1,12 +1,12 @@
 /*
- * Initialization code for multi buffer SHA1 algorithm for AVX2
+ * Initialization code for multi buffer SHA256 algorithm for AVX2
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
  *
  * GPL LICENSE SUMMARY
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of version 2 of the GNU General Public License as
@@ -18,11 +18,11 @@
  *  General Public License for more details.
  *
  *  Contact Information:
- *	Tim Chen <tim.c.chen@linux.intel.com>
+ *      Megha Dey <megha.dey@linux.intel.com>
  *
  *  BSD LICENSE
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  Redistribution and use in source and binary forms, with or without
  *  modification, are permitted provided that the following conditions
@@ -51,11 +51,12 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "sha_mb_mgr.h"
+#include "sha256_mb_mgr.h"
 
-void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
+void sha256_mb_mgr_init_avx2(struct sha256_mb_mgr *state)
 {
 	unsigned int j;
+
 	state->unused_lanes = 0xF76543210ULL;
 	for (j = 0; j < 8; j++) {
 		state->lens[j] = 0xFFFFFFFF;
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S
new file mode 100644
index 0000000..7ea670e
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S
@@ -0,0 +1,215 @@
+/*
+ * Buffer submit code for multi buffer SHA256 algorithm
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha256_mb_mgr_datastruct.S"
+
+.extern sha256_x8_avx2
+
+# LINUX register definitions
+arg1		= %rdi
+arg2		= %rsi
+size_offset	= %rcx
+tmp2		= %rcx
+extra_blocks	= %rdx
+
+# Common definitions
+#define state	arg1
+#define job	%rsi
+#define len2	arg2
+#define p2	arg2
+
+# idx must be a register not clobberred by sha1_x8_avx2
+idx		= %r8
+DWORD_idx	= %r8d
+last_len	= %r8
+
+p		= %r11
+start_offset	= %r11
+
+unused_lanes	= %rbx
+BYTE_unused_lanes = %bl
+
+job_rax		= %rax
+len		= %rax
+DWORD_len	= %eax
+
+lane		= %r12
+tmp3		= %r12
+
+tmp		= %r9
+DWORD_tmp	= %r9d
+
+lane_data	= %r10
+
+# JOB* sha256_mb_mgr_submit_avx2(MB_MGR *state, JOB_SHA256 *job)
+# arg 1 : rcx : state
+# arg 2 : rdx : job
+ENTRY(sha256_mb_mgr_submit_avx2)
+	FRAME_BEGIN
+	push	%rbx
+	push	%r12
+
+	mov	_unused_lanes(state), unused_lanes
+	mov	unused_lanes, lane
+	and	$0xF, lane
+	shr	$4, unused_lanes
+	imul	$_LANE_DATA_size, lane, lane_data
+	movl	$STS_BEING_PROCESSED, _status(job)
+	lea	_ldata(state, lane_data), lane_data
+	mov	unused_lanes, _unused_lanes(state)
+	movl	_len(job),  DWORD_len
+
+	mov	job, _job_in_lane(lane_data)
+	shl	$4, len
+	or	lane, len
+
+	movl	DWORD_len,  _lens(state , lane, 4)
+
+	# Load digest words from result_digest
+	vmovdqu	_result_digest(job), %xmm0
+	vmovdqu	_result_digest+1*16(job), %xmm1
+	vmovd	%xmm0, _args_digest(state, lane, 4)
+	vpextrd	$1, %xmm0, _args_digest+1*32(state , lane, 4)
+	vpextrd	$2, %xmm0, _args_digest+2*32(state , lane, 4)
+	vpextrd	$3, %xmm0, _args_digest+3*32(state , lane, 4)
+	vmovd	%xmm1, _args_digest+4*32(state , lane, 4)
+
+	vpextrd	$1, %xmm1, _args_digest+5*32(state , lane, 4)
+	vpextrd	$2, %xmm1, _args_digest+6*32(state , lane, 4)
+	vpextrd	$3, %xmm1, _args_digest+7*32(state , lane, 4)
+
+	mov	_buffer(job), p
+	mov	p, _args_data_ptr(state, lane, 8)
+
+	cmp	$0xF, unused_lanes
+	jne	return_null
+
+start_loop:
+	# Find min length
+	vmovdqa	_lens(state), %xmm0
+	vmovdqa	_lens+1*16(state), %xmm1
+
+	vpminud	%xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
+	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has {x,x,E,F}
+	vpalignr $4, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,x,E}
+	vpminud	%xmm3, %xmm2, %xmm2		# xmm2 has min val in low dword
+
+	vmovd	%xmm2, DWORD_idx
+	mov	idx, len2
+	and	$0xF, idx
+	shr	$4, len2
+	jz	len_is_0
+
+	vpand	clear_low_nibble(%rip), %xmm2, %xmm2
+	vpshufd	$0, %xmm2, %xmm2
+
+	vpsubd	%xmm2, %xmm0, %xmm0
+	vpsubd	%xmm2, %xmm1, %xmm1
+
+	vmovdqa	%xmm0, _lens + 0*16(state)
+	vmovdqa	%xmm1, _lens + 1*16(state)
+
+	# "state" and "args" are the same address, arg1
+	# len is arg2
+	call	sha256_x8_avx2
+
+	# state and idx are intact
+
+len_is_0:
+	# process completed job "idx"
+	imul	$_LANE_DATA_size, idx, lane_data
+	lea	_ldata(state, lane_data), lane_data
+
+	mov	_job_in_lane(lane_data), job_rax
+	mov	_unused_lanes(state), unused_lanes
+	movq	$0, _job_in_lane(lane_data)
+	movl	$STS_COMPLETED, _status(job_rax)
+	shl	$4, unused_lanes
+	or	idx, unused_lanes
+	mov	unused_lanes, _unused_lanes(state)
+
+	movl	$0xFFFFFFFF, _lens(state,idx,4)
+
+	vmovd	_args_digest(state, idx, 4), %xmm0
+	vpinsrd	$1, _args_digest+1*32(state , idx, 4), %xmm0, %xmm0
+	vpinsrd	$2, _args_digest+2*32(state , idx, 4), %xmm0, %xmm0
+	vpinsrd	$3, _args_digest+3*32(state , idx, 4), %xmm0, %xmm0
+	vmovd	_args_digest+4*32(state, idx, 4), %xmm1
+
+	vpinsrd	$1, _args_digest+5*32(state , idx, 4), %xmm1, %xmm1
+	vpinsrd	$2, _args_digest+6*32(state , idx, 4), %xmm1, %xmm1
+	vpinsrd	$3, _args_digest+7*32(state , idx, 4), %xmm1, %xmm1
+
+	vmovdqu	%xmm0, _result_digest(job_rax)
+	vmovdqu	%xmm1, _result_digest+1*16(job_rax)
+
+return:
+	pop     %r12
+        pop     %rbx
+        FRAME_END
+	ret
+
+return_null:
+	xor	job_rax, job_rax
+	jmp	return
+
+ENDPROC(sha256_mb_mgr_submit_avx2)
+
+.data
+
+.align 16
+clear_low_nibble:
+	.octa	0x000000000000000000000000FFFFFFF0
diff --git a/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S
new file mode 100644
index 0000000..aa21aea
--- /dev/null
+++ b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S
@@ -0,0 +1,593 @@
+/*
+ * Multi-buffer SHA256 algorithm hash compute routine
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include "sha256_mb_mgr_datastruct.S"
+
+## code to compute oct SHA256 using SSE-256
+## outer calling routine takes care of save and restore of XMM registers
+## Logic designed/laid out by JDG
+
+## Function clobbers: rax, rcx, rdx,   rbx, rsi, rdi, r9-r15; %ymm0-15
+## Linux clobbers:    rax rbx rcx rdx rsi            r9 r10 r11 r12 r13 r14 r15
+## Linux preserves:                       rdi rbp r8
+##
+## clobbers %ymm0-15
+
+arg1 = %rdi
+arg2 = %rsi
+reg3 = %rcx
+reg4 = %rdx
+
+# Common definitions
+STATE = arg1
+INP_SIZE = arg2
+
+IDX = %rax
+ROUND = %rbx
+TBL = reg3
+
+inp0 = %r9
+inp1 = %r10
+inp2 = %r11
+inp3 = %r12
+inp4 = %r13
+inp5 = %r14
+inp6 = %r15
+inp7 = reg4
+
+a = %ymm0
+b = %ymm1
+c = %ymm2
+d = %ymm3
+e = %ymm4
+f = %ymm5
+g = %ymm6
+h = %ymm7
+
+T1 = %ymm8
+
+a0 = %ymm12
+a1 = %ymm13
+a2 = %ymm14
+TMP = %ymm15
+TMP0 = %ymm6
+TMP1 = %ymm7
+
+TT0 = %ymm8
+TT1 = %ymm9
+TT2 = %ymm10
+TT3 = %ymm11
+TT4 = %ymm12
+TT5 = %ymm13
+TT6 = %ymm14
+TT7 = %ymm15
+
+# Define stack usage
+
+# Assume stack aligned to 32 bytes before call
+# Therefore FRAMESZ mod 32 must be 32-8 = 24
+
+#define FRAMESZ	0x388
+
+#define VMOVPS	vmovups
+
+# TRANSPOSE8 r0, r1, r2, r3, r4, r5, r6, r7, t0, t1
+# "transpose" data in {r0...r7} using temps {t0...t1}
+# Input looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
+# r0 = {a7 a6 a5 a4   a3 a2 a1 a0}
+# r1 = {b7 b6 b5 b4   b3 b2 b1 b0}
+# r2 = {c7 c6 c5 c4   c3 c2 c1 c0}
+# r3 = {d7 d6 d5 d4   d3 d2 d1 d0}
+# r4 = {e7 e6 e5 e4   e3 e2 e1 e0}
+# r5 = {f7 f6 f5 f4   f3 f2 f1 f0}
+# r6 = {g7 g6 g5 g4   g3 g2 g1 g0}
+# r7 = {h7 h6 h5 h4   h3 h2 h1 h0}
+#
+# Output looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
+# r0 = {h0 g0 f0 e0   d0 c0 b0 a0}
+# r1 = {h1 g1 f1 e1   d1 c1 b1 a1}
+# r2 = {h2 g2 f2 e2   d2 c2 b2 a2}
+# r3 = {h3 g3 f3 e3   d3 c3 b3 a3}
+# r4 = {h4 g4 f4 e4   d4 c4 b4 a4}
+# r5 = {h5 g5 f5 e5   d5 c5 b5 a5}
+# r6 = {h6 g6 f6 e6   d6 c6 b6 a6}
+# r7 = {h7 g7 f7 e7   d7 c7 b7 a7}
+#
+
+.macro TRANSPOSE8 r0 r1 r2 r3 r4 r5 r6 r7 t0 t1
+	# process top half (r0..r3) {a...d}
+	vshufps	$0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4   b1 b0 a1 a0}
+	vshufps	$0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6   b3 b2 a3 a2}
+	vshufps	$0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4   d1 d0 c1 c0}
+	vshufps	$0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6   d3 d2 c3 c2}
+	vshufps	$0xDD, \t1, \t0, \r3 # r3 = {d5 c5 b5 a5   d1 c1 b1 a1}
+	vshufps	$0x88, \r2, \r0, \r1 # r1 = {d6 c6 b6 a6   d2 c2 b2 a2}
+	vshufps	$0xDD, \r2, \r0, \r0 # r0 = {d7 c7 b7 a7   d3 c3 b3 a3}
+	vshufps	$0x88, \t1, \t0, \t0 # t0 = {d4 c4 b4 a4   d0 c0 b0 a0}
+
+	# use r2 in place of t0
+	# process bottom half (r4..r7) {e...h}
+	vshufps	$0x44, \r5, \r4, \r2 # r2 = {f5 f4 e5 e4   f1 f0 e1 e0}
+	vshufps	$0xEE, \r5, \r4, \r4 # r4 = {f7 f6 e7 e6   f3 f2 e3 e2}
+	vshufps	$0x44, \r7, \r6, \t1 # t1 = {h5 h4 g5 g4   h1 h0 g1 g0}
+	vshufps	$0xEE, \r7, \r6, \r6 # r6 = {h7 h6 g7 g6   h3 h2 g3 g2}
+	vshufps	$0xDD, \t1, \r2, \r7 # r7 = {h5 g5 f5 e5   h1 g1 f1 e1}
+	vshufps	$0x88, \r6, \r4, \r5 # r5 = {h6 g6 f6 e6   h2 g2 f2 e2}
+	vshufps	$0xDD, \r6, \r4, \r4 # r4 = {h7 g7 f7 e7   h3 g3 f3 e3}
+	vshufps	$0x88, \t1, \r2, \t1 # t1 = {h4 g4 f4 e4   h0 g0 f0 e0}
+
+	vperm2f128	$0x13, \r1, \r5, \r6  # h6...a6
+	vperm2f128	$0x02, \r1, \r5, \r2  # h2...a2
+	vperm2f128	$0x13, \r3, \r7, \r5  # h5...a5
+	vperm2f128	$0x02, \r3, \r7, \r1  # h1...a1
+	vperm2f128	$0x13, \r0, \r4, \r7  # h7...a7
+	vperm2f128	$0x02, \r0, \r4, \r3  # h3...a3
+	vperm2f128	$0x13, \t0, \t1, \r4  # h4...a4
+	vperm2f128	$0x02, \t0, \t1, \r0  # h0...a0
+
+.endm
+
+.macro ROTATE_ARGS
+TMP_ = h
+h = g
+g = f
+f = e
+e = d
+d = c
+c = b
+b = a
+a = TMP_
+.endm
+
+.macro _PRORD reg imm tmp
+	vpslld	$(32-\imm),\reg,\tmp
+	vpsrld	$\imm,\reg, \reg
+	vpor	\tmp,\reg, \reg
+.endm
+
+# PRORD_nd reg, imm, tmp, src
+.macro _PRORD_nd reg imm tmp src
+	vpslld	$(32-\imm), \src, \tmp
+	vpsrld	$\imm, \src, \reg
+	vpor	\tmp, \reg, \reg
+.endm
+
+# PRORD dst/src, amt
+.macro PRORD reg imm
+	_PRORD	\reg,\imm,TMP
+.endm
+
+# PRORD_nd dst, src, amt
+.macro PRORD_nd reg tmp imm
+	_PRORD_nd	\reg, \imm, TMP, \tmp
+.endm
+
+# arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_00_15 _T1 i
+	PRORD_nd	a0,e,5	# sig1: a0 = (e >> 5)
+
+	vpxor	g, f, a2	# ch: a2 = f^g
+	vpand	e,a2, a2	# ch: a2 = (f^g)&e
+	vpxor	g, a2, a2	# a2 = ch
+
+	PRORD_nd	a1,e,25	# sig1: a1 = (e >> 25)
+
+	vmovdqu	\_T1,(SZ8*(\i & 0xf))(%rsp)
+	vpaddd	(TBL,ROUND,1), \_T1, \_T1	# T1 = W + K
+	vpxor	e,a0, a0	# sig1: a0 = e ^ (e >> 5)
+	PRORD	a0, 6		# sig1: a0 = (e >> 6) ^ (e >> 11)
+	vpaddd	a2, h, h	# h = h + ch
+	PRORD_nd	a2,a,11	# sig0: a2 = (a >> 11)
+	vpaddd	\_T1,h, h 	# h = h + ch + W + K
+	vpxor	a1, a0, a0	# a0 = sigma1
+	PRORD_nd	a1,a,22	# sig0: a1 = (a >> 22)
+	vpxor	c, a, \_T1	# maj: T1 = a^c
+	add	$SZ8, ROUND	# ROUND++
+	vpand	b, \_T1, \_T1	# maj: T1 = (a^c)&b
+	vpaddd	a0, h, h
+	vpaddd	h, d, d
+	vpxor	a, a2, a2	# sig0: a2 = a ^ (a >> 11)
+	PRORD	a2,2		# sig0: a2 = (a >> 2) ^ (a >> 13)
+	vpxor	a1, a2, a2	# a2 = sig0
+	vpand	c, a, a1	# maj: a1 = a&c
+	vpor	\_T1, a1, a1 	# a1 = maj
+	vpaddd	a1, h, h	# h = h + ch + W + K + maj
+	vpaddd	a2, h, h	# h = h + ch + W + K + maj + sigma0
+	ROTATE_ARGS
+.endm
+
+# arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_16_XX _T1 i
+	vmovdqu	(SZ8*((\i-15)&0xf))(%rsp), \_T1
+	vmovdqu	(SZ8*((\i-2)&0xf))(%rsp), a1
+	vmovdqu	\_T1, a0
+	PRORD	\_T1,11
+	vmovdqu	a1, a2
+	PRORD	a1,2
+	vpxor	a0, \_T1, \_T1
+	PRORD	\_T1, 7
+	vpxor	a2, a1, a1
+	PRORD	a1, 17
+	vpsrld	$3, a0, a0
+	vpxor	a0, \_T1, \_T1
+	vpsrld	$10, a2, a2
+	vpxor	a2, a1, a1
+	vpaddd	(SZ8*((\i-16)&0xf))(%rsp), \_T1, \_T1
+	vpaddd	(SZ8*((\i-7)&0xf))(%rsp), a1, a1
+	vpaddd	a1, \_T1, \_T1
+
+	ROUND_00_15 \_T1,\i
+.endm
+
+# SHA256_ARGS:
+#   UINT128 digest[8];  // transposed digests
+#   UINT8  *data_ptr[4];
+
+# void sha256_x8_avx2(SHA256_ARGS *args, UINT64 bytes);
+# arg 1 : STATE : pointer to array of pointers to input data
+# arg 2 : INP_SIZE  : size of input in blocks
+	# general registers preserved in outer calling routine
+	# outer calling routine saves all the XMM registers
+	# save rsp, allocate 32-byte aligned for local variables
+ENTRY(sha256_x8_avx2)
+
+	# save callee-saved clobbered registers to comply with C function ABI
+	push    %r12
+	push    %r13
+	push    %r14
+	push    %r15
+
+	mov	%rsp, IDX
+	sub	$FRAMESZ, %rsp
+	and	$~0x1F, %rsp
+	mov	IDX, _rsp(%rsp)
+
+	# Load the pre-transposed incoming digest.
+	vmovdqu	0*SHA256_DIGEST_ROW_SIZE(STATE),a
+	vmovdqu	1*SHA256_DIGEST_ROW_SIZE(STATE),b
+	vmovdqu	2*SHA256_DIGEST_ROW_SIZE(STATE),c
+	vmovdqu	3*SHA256_DIGEST_ROW_SIZE(STATE),d
+	vmovdqu	4*SHA256_DIGEST_ROW_SIZE(STATE),e
+	vmovdqu	5*SHA256_DIGEST_ROW_SIZE(STATE),f
+	vmovdqu	6*SHA256_DIGEST_ROW_SIZE(STATE),g
+	vmovdqu	7*SHA256_DIGEST_ROW_SIZE(STATE),h
+
+	lea	K256_8(%rip),TBL
+
+	# load the address of each of the 4 message lanes
+	# getting ready to transpose input onto stack
+	mov	_args_data_ptr+0*PTR_SZ(STATE),inp0
+	mov	_args_data_ptr+1*PTR_SZ(STATE),inp1
+	mov	_args_data_ptr+2*PTR_SZ(STATE),inp2
+	mov	_args_data_ptr+3*PTR_SZ(STATE),inp3
+	mov	_args_data_ptr+4*PTR_SZ(STATE),inp4
+	mov	_args_data_ptr+5*PTR_SZ(STATE),inp5
+	mov	_args_data_ptr+6*PTR_SZ(STATE),inp6
+	mov	_args_data_ptr+7*PTR_SZ(STATE),inp7
+
+	xor	IDX, IDX
+lloop:
+	xor	ROUND, ROUND
+
+	# save old digest
+	vmovdqu	a, _digest(%rsp)
+	vmovdqu	b, _digest+1*SZ8(%rsp)
+	vmovdqu	c, _digest+2*SZ8(%rsp)
+	vmovdqu	d, _digest+3*SZ8(%rsp)
+	vmovdqu	e, _digest+4*SZ8(%rsp)
+	vmovdqu	f, _digest+5*SZ8(%rsp)
+	vmovdqu	g, _digest+6*SZ8(%rsp)
+	vmovdqu	h, _digest+7*SZ8(%rsp)
+	i = 0
+.rep 2
+	VMOVPS	i*32(inp0, IDX), TT0
+	VMOVPS	i*32(inp1, IDX), TT1
+	VMOVPS	i*32(inp2, IDX), TT2
+	VMOVPS	i*32(inp3, IDX), TT3
+	VMOVPS	i*32(inp4, IDX), TT4
+	VMOVPS	i*32(inp5, IDX), TT5
+	VMOVPS	i*32(inp6, IDX), TT6
+	VMOVPS	i*32(inp7, IDX), TT7
+	vmovdqu	g, _ytmp(%rsp)
+	vmovdqu	h, _ytmp+1*SZ8(%rsp)
+	TRANSPOSE8	TT0, TT1, TT2, TT3, TT4, TT5, TT6, TT7,   TMP0, TMP1
+	vmovdqu	PSHUFFLE_BYTE_FLIP_MASK(%rip), TMP1
+	vmovdqu	_ytmp(%rsp), g
+	vpshufb	TMP1, TT0, TT0
+	vpshufb	TMP1, TT1, TT1
+	vpshufb	TMP1, TT2, TT2
+	vpshufb	TMP1, TT3, TT3
+	vpshufb	TMP1, TT4, TT4
+	vpshufb	TMP1, TT5, TT5
+	vpshufb	TMP1, TT6, TT6
+	vpshufb	TMP1, TT7, TT7
+	vmovdqu	_ytmp+1*SZ8(%rsp), h
+	vmovdqu	TT4, _ytmp(%rsp)
+	vmovdqu	TT5, _ytmp+1*SZ8(%rsp)
+	vmovdqu	TT6, _ytmp+2*SZ8(%rsp)
+	vmovdqu	TT7, _ytmp+3*SZ8(%rsp)
+	ROUND_00_15	TT0,(i*8+0)
+	vmovdqu	_ytmp(%rsp), TT0
+	ROUND_00_15	TT1,(i*8+1)
+	vmovdqu	_ytmp+1*SZ8(%rsp), TT1
+	ROUND_00_15	TT2,(i*8+2)
+	vmovdqu	_ytmp+2*SZ8(%rsp), TT2
+	ROUND_00_15	TT3,(i*8+3)
+	vmovdqu	_ytmp+3*SZ8(%rsp), TT3
+	ROUND_00_15	TT0,(i*8+4)
+	ROUND_00_15	TT1,(i*8+5)
+	ROUND_00_15	TT2,(i*8+6)
+	ROUND_00_15	TT3,(i*8+7)
+	i = (i+1)
+.endr
+	add	$64, IDX
+	i = (i*8)
+
+	jmp	Lrounds_16_xx
+.align 16
+Lrounds_16_xx:
+.rep 16
+	ROUND_16_XX	T1, i
+	i = (i+1)
+.endr
+
+	cmp	$ROUNDS,ROUND
+	jb	Lrounds_16_xx
+
+	# add old digest
+	vpaddd	_digest+0*SZ8(%rsp), a, a
+	vpaddd	_digest+1*SZ8(%rsp), b, b
+	vpaddd	_digest+2*SZ8(%rsp), c, c
+	vpaddd	_digest+3*SZ8(%rsp), d, d
+	vpaddd	_digest+4*SZ8(%rsp), e, e
+	vpaddd	_digest+5*SZ8(%rsp), f, f
+	vpaddd	_digest+6*SZ8(%rsp), g, g
+	vpaddd	_digest+7*SZ8(%rsp), h, h
+
+	sub	$1, INP_SIZE  # unit is blocks
+	jne	lloop
+
+	# write back to memory (state object) the transposed digest
+	vmovdqu	a, 0*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	b, 1*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	c, 2*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	d, 3*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	e, 4*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	f, 5*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	g, 6*SHA256_DIGEST_ROW_SIZE(STATE)
+	vmovdqu	h, 7*SHA256_DIGEST_ROW_SIZE(STATE)
+
+	# update input pointers
+	add	IDX, inp0
+	mov	inp0, _args_data_ptr+0*8(STATE)
+	add	IDX, inp1
+	mov	inp1, _args_data_ptr+1*8(STATE)
+	add	IDX, inp2
+	mov	inp2, _args_data_ptr+2*8(STATE)
+	add	IDX, inp3
+	mov	inp3, _args_data_ptr+3*8(STATE)
+	add	IDX, inp4
+	mov	inp4, _args_data_ptr+4*8(STATE)
+	add	IDX, inp5
+	mov	inp5, _args_data_ptr+5*8(STATE)
+	add	IDX, inp6
+	mov	inp6, _args_data_ptr+6*8(STATE)
+	add	IDX, inp7
+	mov	inp7, _args_data_ptr+7*8(STATE)
+
+	# Postamble
+	mov	_rsp(%rsp), %rsp
+
+	# restore callee-saved clobbered registers
+	pop     %r15
+	pop     %r14
+	pop     %r13
+	pop     %r12
+
+	ret
+ENDPROC(sha256_x8_avx2)
+.data
+.align 64
+K256_8:
+	.octa	0x428a2f98428a2f98428a2f98428a2f98
+	.octa	0x428a2f98428a2f98428a2f98428a2f98
+	.octa	0x71374491713744917137449171374491
+	.octa	0x71374491713744917137449171374491
+	.octa	0xb5c0fbcfb5c0fbcfb5c0fbcfb5c0fbcf
+	.octa	0xb5c0fbcfb5c0fbcfb5c0fbcfb5c0fbcf
+	.octa	0xe9b5dba5e9b5dba5e9b5dba5e9b5dba5
+	.octa	0xe9b5dba5e9b5dba5e9b5dba5e9b5dba5
+	.octa	0x3956c25b3956c25b3956c25b3956c25b
+	.octa	0x3956c25b3956c25b3956c25b3956c25b
+	.octa	0x59f111f159f111f159f111f159f111f1
+	.octa	0x59f111f159f111f159f111f159f111f1
+	.octa	0x923f82a4923f82a4923f82a4923f82a4
+	.octa	0x923f82a4923f82a4923f82a4923f82a4
+	.octa	0xab1c5ed5ab1c5ed5ab1c5ed5ab1c5ed5
+	.octa	0xab1c5ed5ab1c5ed5ab1c5ed5ab1c5ed5
+	.octa	0xd807aa98d807aa98d807aa98d807aa98
+	.octa	0xd807aa98d807aa98d807aa98d807aa98
+	.octa	0x12835b0112835b0112835b0112835b01
+	.octa	0x12835b0112835b0112835b0112835b01
+	.octa	0x243185be243185be243185be243185be
+	.octa	0x243185be243185be243185be243185be
+	.octa	0x550c7dc3550c7dc3550c7dc3550c7dc3
+	.octa	0x550c7dc3550c7dc3550c7dc3550c7dc3
+	.octa	0x72be5d7472be5d7472be5d7472be5d74
+	.octa	0x72be5d7472be5d7472be5d7472be5d74
+	.octa	0x80deb1fe80deb1fe80deb1fe80deb1fe
+	.octa	0x80deb1fe80deb1fe80deb1fe80deb1fe
+	.octa	0x9bdc06a79bdc06a79bdc06a79bdc06a7
+	.octa	0x9bdc06a79bdc06a79bdc06a79bdc06a7
+	.octa	0xc19bf174c19bf174c19bf174c19bf174
+	.octa	0xc19bf174c19bf174c19bf174c19bf174
+	.octa	0xe49b69c1e49b69c1e49b69c1e49b69c1
+	.octa	0xe49b69c1e49b69c1e49b69c1e49b69c1
+	.octa	0xefbe4786efbe4786efbe4786efbe4786
+	.octa	0xefbe4786efbe4786efbe4786efbe4786
+	.octa	0x0fc19dc60fc19dc60fc19dc60fc19dc6
+	.octa	0x0fc19dc60fc19dc60fc19dc60fc19dc6
+	.octa	0x240ca1cc240ca1cc240ca1cc240ca1cc
+	.octa	0x240ca1cc240ca1cc240ca1cc240ca1cc
+	.octa	0x2de92c6f2de92c6f2de92c6f2de92c6f
+	.octa	0x2de92c6f2de92c6f2de92c6f2de92c6f
+	.octa	0x4a7484aa4a7484aa4a7484aa4a7484aa
+	.octa	0x4a7484aa4a7484aa4a7484aa4a7484aa
+	.octa	0x5cb0a9dc5cb0a9dc5cb0a9dc5cb0a9dc
+	.octa	0x5cb0a9dc5cb0a9dc5cb0a9dc5cb0a9dc
+	.octa	0x76f988da76f988da76f988da76f988da
+	.octa	0x76f988da76f988da76f988da76f988da
+	.octa	0x983e5152983e5152983e5152983e5152
+	.octa	0x983e5152983e5152983e5152983e5152
+	.octa	0xa831c66da831c66da831c66da831c66d
+	.octa	0xa831c66da831c66da831c66da831c66d
+	.octa	0xb00327c8b00327c8b00327c8b00327c8
+	.octa	0xb00327c8b00327c8b00327c8b00327c8
+	.octa	0xbf597fc7bf597fc7bf597fc7bf597fc7
+	.octa	0xbf597fc7bf597fc7bf597fc7bf597fc7
+	.octa	0xc6e00bf3c6e00bf3c6e00bf3c6e00bf3
+	.octa	0xc6e00bf3c6e00bf3c6e00bf3c6e00bf3
+	.octa	0xd5a79147d5a79147d5a79147d5a79147
+	.octa	0xd5a79147d5a79147d5a79147d5a79147
+	.octa	0x06ca635106ca635106ca635106ca6351
+	.octa	0x06ca635106ca635106ca635106ca6351
+	.octa	0x14292967142929671429296714292967
+	.octa	0x14292967142929671429296714292967
+	.octa	0x27b70a8527b70a8527b70a8527b70a85
+	.octa	0x27b70a8527b70a8527b70a8527b70a85
+	.octa	0x2e1b21382e1b21382e1b21382e1b2138
+	.octa	0x2e1b21382e1b21382e1b21382e1b2138
+	.octa	0x4d2c6dfc4d2c6dfc4d2c6dfc4d2c6dfc
+	.octa	0x4d2c6dfc4d2c6dfc4d2c6dfc4d2c6dfc
+	.octa	0x53380d1353380d1353380d1353380d13
+	.octa	0x53380d1353380d1353380d1353380d13
+	.octa	0x650a7354650a7354650a7354650a7354
+	.octa	0x650a7354650a7354650a7354650a7354
+	.octa	0x766a0abb766a0abb766a0abb766a0abb
+	.octa	0x766a0abb766a0abb766a0abb766a0abb
+	.octa	0x81c2c92e81c2c92e81c2c92e81c2c92e
+	.octa	0x81c2c92e81c2c92e81c2c92e81c2c92e
+	.octa	0x92722c8592722c8592722c8592722c85
+	.octa	0x92722c8592722c8592722c8592722c85
+	.octa	0xa2bfe8a1a2bfe8a1a2bfe8a1a2bfe8a1
+	.octa	0xa2bfe8a1a2bfe8a1a2bfe8a1a2bfe8a1
+	.octa	0xa81a664ba81a664ba81a664ba81a664b
+	.octa	0xa81a664ba81a664ba81a664ba81a664b
+	.octa	0xc24b8b70c24b8b70c24b8b70c24b8b70
+	.octa	0xc24b8b70c24b8b70c24b8b70c24b8b70
+	.octa	0xc76c51a3c76c51a3c76c51a3c76c51a3
+	.octa	0xc76c51a3c76c51a3c76c51a3c76c51a3
+	.octa	0xd192e819d192e819d192e819d192e819
+	.octa	0xd192e819d192e819d192e819d192e819
+	.octa	0xd6990624d6990624d6990624d6990624
+	.octa	0xd6990624d6990624d6990624d6990624
+	.octa	0xf40e3585f40e3585f40e3585f40e3585
+	.octa	0xf40e3585f40e3585f40e3585f40e3585
+	.octa	0x106aa070106aa070106aa070106aa070
+	.octa	0x106aa070106aa070106aa070106aa070
+	.octa	0x19a4c11619a4c11619a4c11619a4c116
+	.octa	0x19a4c11619a4c11619a4c11619a4c116
+	.octa	0x1e376c081e376c081e376c081e376c08
+	.octa	0x1e376c081e376c081e376c081e376c08
+	.octa	0x2748774c2748774c2748774c2748774c
+	.octa	0x2748774c2748774c2748774c2748774c
+	.octa	0x34b0bcb534b0bcb534b0bcb534b0bcb5
+	.octa	0x34b0bcb534b0bcb534b0bcb534b0bcb5
+	.octa	0x391c0cb3391c0cb3391c0cb3391c0cb3
+	.octa	0x391c0cb3391c0cb3391c0cb3391c0cb3
+	.octa	0x4ed8aa4a4ed8aa4a4ed8aa4a4ed8aa4a
+	.octa	0x4ed8aa4a4ed8aa4a4ed8aa4a4ed8aa4a
+	.octa	0x5b9cca4f5b9cca4f5b9cca4f5b9cca4f
+	.octa	0x5b9cca4f5b9cca4f5b9cca4f5b9cca4f
+	.octa	0x682e6ff3682e6ff3682e6ff3682e6ff3
+	.octa	0x682e6ff3682e6ff3682e6ff3682e6ff3
+	.octa	0x748f82ee748f82ee748f82ee748f82ee
+	.octa	0x748f82ee748f82ee748f82ee748f82ee
+	.octa	0x78a5636f78a5636f78a5636f78a5636f
+	.octa	0x78a5636f78a5636f78a5636f78a5636f
+	.octa	0x84c8781484c8781484c8781484c87814
+	.octa	0x84c8781484c8781484c8781484c87814
+	.octa	0x8cc702088cc702088cc702088cc70208
+	.octa	0x8cc702088cc702088cc702088cc70208
+	.octa	0x90befffa90befffa90befffa90befffa
+	.octa	0x90befffa90befffa90befffa90befffa
+	.octa	0xa4506ceba4506ceba4506ceba4506ceb
+	.octa	0xa4506ceba4506ceba4506ceba4506ceb
+	.octa	0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7
+	.octa	0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7
+	.octa	0xc67178f2c67178f2c67178f2c67178f2
+	.octa	0xc67178f2c67178f2c67178f2c67178f2
+PSHUFFLE_BYTE_FLIP_MASK:
+.octa 0x0c0d0e0f08090a0b0405060700010203
+.octa 0x0c0d0e0f08090a0b0405060700010203
+
+.align 64
+.global K256
+K256:
+	.int	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.int	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.int	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.int	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.int	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.int	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.int	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.int	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.int	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.int	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.int	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.int	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.int	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.int	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.int	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.int	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 3ae0f43..9e79baf0 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -427,4 +427,14 @@
 MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
 MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha256-ssse3");
+MODULE_ALIAS_CRYPTO("sha256-avx");
+MODULE_ALIAS_CRYPTO("sha256-avx2");
 MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha224-ssse3");
+MODULE_ALIAS_CRYPTO("sha224-avx");
+MODULE_ALIAS_CRYPTO("sha224-avx2");
+#ifdef CONFIG_AS_SHA256_NI
+MODULE_ALIAS_CRYPTO("sha256-ni");
+MODULE_ALIAS_CRYPTO("sha224-ni");
+#endif
diff --git a/arch/x86/crypto/sha512-mb/Makefile b/arch/x86/crypto/sha512-mb/Makefile
new file mode 100644
index 0000000..0a57e21
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/Makefile
@@ -0,0 +1,11 @@
+#
+# Arch-specific CryptoAPI modules.
+#
+
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+                                $(comma)4)$(comma)%ymm2,yes,no)
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb.o
+	sha512-mb-y := sha512_mb.o sha512_mb_mgr_flush_avx2.o \
+	     sha512_mb_mgr_init_avx2.o sha512_mb_mgr_submit_avx2.o sha512_x4_avx2.o
+endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
new file mode 100644
index 0000000..f4cf5b7
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -0,0 +1,1046 @@
+/*
+ * Multi buffer SHA512 algorithm Glue Code
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *	Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+#include <crypto/mcryptd.h>
+#include <crypto/crypto_wq.h>
+#include <asm/byteorder.h>
+#include <linux/hardirq.h>
+#include <asm/fpu/api.h>
+#include "sha512_mb_ctx.h"
+
+#define FLUSH_INTERVAL 1000 /* in usec */
+
+static struct mcryptd_alg_state sha512_mb_alg_state;
+
+struct sha512_mb_ctx {
+	struct mcryptd_ahash *mcryptd_tfm;
+};
+
+static inline struct mcryptd_hash_request_ctx
+		*cast_hash_to_mcryptd_ctx(struct sha512_hash_ctx *hash_ctx)
+{
+	struct ahash_request *areq;
+
+	areq = container_of((void *) hash_ctx, struct ahash_request, __ctx);
+	return container_of(areq, struct mcryptd_hash_request_ctx, areq);
+}
+
+static inline struct ahash_request
+		*cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+{
+	return container_of((void *) ctx, struct ahash_request, __ctx);
+}
+
+static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
+				struct ahash_request *areq)
+{
+	rctx->flag = HASH_UPDATE;
+}
+
+static asmlinkage void (*sha512_job_mgr_init)(struct sha512_mb_mgr *state);
+static asmlinkage struct job_sha512* (*sha512_job_mgr_submit)
+						(struct sha512_mb_mgr *state,
+						struct job_sha512 *job);
+static asmlinkage struct job_sha512* (*sha512_job_mgr_flush)
+						(struct sha512_mb_mgr *state);
+static asmlinkage struct job_sha512* (*sha512_job_mgr_get_comp_job)
+						(struct sha512_mb_mgr *state);
+
+inline void sha512_init_digest(uint64_t *digest)
+{
+	static const uint64_t initial_digest[SHA512_DIGEST_LENGTH] = {
+					SHA512_H0, SHA512_H1, SHA512_H2,
+					SHA512_H3, SHA512_H4, SHA512_H5,
+					SHA512_H6, SHA512_H7 };
+	memcpy(digest, initial_digest, sizeof(initial_digest));
+}
+
+inline uint32_t sha512_pad(uint8_t padblock[SHA512_BLOCK_SIZE * 2],
+			 uint32_t total_len)
+{
+	uint32_t i = total_len & (SHA512_BLOCK_SIZE - 1);
+
+	memset(&padblock[i], 0, SHA512_BLOCK_SIZE);
+	padblock[i] = 0x80;
+
+	i += ((SHA512_BLOCK_SIZE - 1) &
+	      (0 - (total_len + SHA512_PADLENGTHFIELD_SIZE + 1)))
+	     + 1 + SHA512_PADLENGTHFIELD_SIZE;
+
+#if SHA512_PADLENGTHFIELD_SIZE == 16
+	*((uint64_t *) &padblock[i - 16]) = 0;
+#endif
+
+	*((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
+
+	/* Number of extra blocks to hash */
+	return i >> SHA512_LOG2_BLOCK_SIZE;
+}
+
+static struct sha512_hash_ctx *sha512_ctx_mgr_resubmit
+		(struct sha512_ctx_mgr *mgr, struct sha512_hash_ctx *ctx)
+{
+	while (ctx) {
+		if (ctx->status & HASH_CTX_STS_COMPLETE) {
+			/* Clear PROCESSING bit */
+			ctx->status = HASH_CTX_STS_COMPLETE;
+			return ctx;
+		}
+
+		/*
+		 * If the extra blocks are empty, begin hashing what remains
+		 * in the user's buffer.
+		 */
+		if (ctx->partial_block_buffer_length == 0 &&
+		    ctx->incoming_buffer_length) {
+
+			const void *buffer = ctx->incoming_buffer;
+			uint32_t len = ctx->incoming_buffer_length;
+			uint32_t copy_len;
+
+			/*
+			 * Only entire blocks can be hashed.
+			 * Copy remainder to extra blocks buffer.
+			 */
+			copy_len = len & (SHA512_BLOCK_SIZE-1);
+
+			if (copy_len) {
+				len -= copy_len;
+				memcpy(ctx->partial_block_buffer,
+				       ((const char *) buffer + len),
+				       copy_len);
+				ctx->partial_block_buffer_length = copy_len;
+			}
+
+			ctx->incoming_buffer_length = 0;
+
+			/* len should be a multiple of the block size now */
+			assert((len % SHA512_BLOCK_SIZE) == 0);
+
+			/* Set len to the number of blocks to be hashed */
+			len >>= SHA512_LOG2_BLOCK_SIZE;
+
+			if (len) {
+
+				ctx->job.buffer = (uint8_t *) buffer;
+				ctx->job.len = len;
+				ctx = (struct sha512_hash_ctx *)
+					sha512_job_mgr_submit(&mgr->mgr,
+					&ctx->job);
+				continue;
+			}
+		}
+
+		/*
+		 * If the extra blocks are not empty, then we are
+		 * either on the last block(s) or we need more
+		 * user input before continuing.
+		 */
+		if (ctx->status & HASH_CTX_STS_LAST) {
+
+			uint8_t *buf = ctx->partial_block_buffer;
+			uint32_t n_extra_blocks =
+					sha512_pad(buf, ctx->total_length);
+
+			ctx->status = (HASH_CTX_STS_PROCESSING |
+				       HASH_CTX_STS_COMPLETE);
+			ctx->job.buffer = buf;
+			ctx->job.len = (uint32_t) n_extra_blocks;
+			ctx = (struct sha512_hash_ctx *)
+				sha512_job_mgr_submit(&mgr->mgr, &ctx->job);
+			continue;
+		}
+
+		if (ctx)
+			ctx->status = HASH_CTX_STS_IDLE;
+		return ctx;
+	}
+
+	return NULL;
+}
+
+static struct sha512_hash_ctx
+		*sha512_ctx_mgr_get_comp_ctx(struct sha512_ctx_mgr *mgr)
+{
+	/*
+	 * If get_comp_job returns NULL, there are no jobs complete.
+	 * If get_comp_job returns a job, verify that it is safe to return to
+	 * the user.
+	 * If it is not ready, resubmit the job to finish processing.
+	 * If sha512_ctx_mgr_resubmit returned a job, it is ready to be
+	 * returned.
+	 * Otherwise, all jobs currently being managed by the hash_ctx_mgr
+	 * still need processing.
+	 */
+	struct sha512_hash_ctx *ctx;
+
+	ctx = (struct sha512_hash_ctx *)
+				sha512_job_mgr_get_comp_job(&mgr->mgr);
+	return sha512_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static void sha512_ctx_mgr_init(struct sha512_ctx_mgr *mgr)
+{
+	sha512_job_mgr_init(&mgr->mgr);
+}
+
+static struct sha512_hash_ctx
+			*sha512_ctx_mgr_submit(struct sha512_ctx_mgr *mgr,
+					  struct sha512_hash_ctx *ctx,
+					  const void *buffer,
+					  uint32_t len,
+					  int flags)
+{
+	if (flags & (~HASH_ENTIRE)) {
+		/*
+		 * User should not pass anything other than FIRST, UPDATE, or
+		 * LAST
+		 */
+		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
+		return ctx;
+	}
+
+	if (ctx->status & HASH_CTX_STS_PROCESSING) {
+		/* Cannot submit to a currently processing job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
+		return ctx;
+	}
+
+	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+		/* Cannot update a finished job. */
+		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
+		return ctx;
+	}
+
+
+	if (flags & HASH_FIRST) {
+		/* Init digest */
+		sha512_init_digest(ctx->job.result_digest);
+
+		/* Reset byte counter */
+		ctx->total_length = 0;
+
+		/* Clear extra blocks */
+		ctx->partial_block_buffer_length = 0;
+	}
+
+	/*
+	 * If we made it here, there were no errors during this call to
+	 * submit
+	 */
+	ctx->error = HASH_CTX_ERROR_NONE;
+
+	/* Store buffer ptr info from user */
+	ctx->incoming_buffer = buffer;
+	ctx->incoming_buffer_length = len;
+
+	/*
+	 * Store the user's request flags and mark this ctx as currently being
+	 * processed.
+	 */
+	ctx->status = (flags & HASH_LAST) ?
+			(HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
+			HASH_CTX_STS_PROCESSING;
+
+	/* Advance byte counter */
+	ctx->total_length += len;
+
+	/*
+	 * If there is anything currently buffered in the extra blocks,
+	 * append to it until it contains a whole block.
+	 * Or if the user's buffer contains less than a whole block,
+	 * append as much as possible to the extra block.
+	 */
+	if (ctx->partial_block_buffer_length || len < SHA512_BLOCK_SIZE) {
+		/* Compute how many bytes to copy from user buffer into extra
+		 * block
+		 */
+		uint32_t copy_len = SHA512_BLOCK_SIZE -
+					ctx->partial_block_buffer_length;
+		if (len < copy_len)
+			copy_len = len;
+
+		if (copy_len) {
+			/* Copy and update relevant pointers and counters */
+			memcpy
+		(&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
+				buffer, copy_len);
+
+			ctx->partial_block_buffer_length += copy_len;
+			ctx->incoming_buffer = (const void *)
+					((const char *)buffer + copy_len);
+			ctx->incoming_buffer_length = len - copy_len;
+		}
+
+		/* The extra block should never contain more than 1 block
+		 * here
+		 */
+		assert(ctx->partial_block_buffer_length <= SHA512_BLOCK_SIZE);
+
+		/* If the extra block buffer contains exactly 1 block, it can
+		 * be hashed.
+		 */
+		if (ctx->partial_block_buffer_length >= SHA512_BLOCK_SIZE) {
+			ctx->partial_block_buffer_length = 0;
+
+			ctx->job.buffer = ctx->partial_block_buffer;
+			ctx->job.len = 1;
+			ctx = (struct sha512_hash_ctx *)
+				sha512_job_mgr_submit(&mgr->mgr, &ctx->job);
+		}
+	}
+
+	return sha512_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static struct sha512_hash_ctx *sha512_ctx_mgr_flush(struct sha512_ctx_mgr *mgr)
+{
+	struct sha512_hash_ctx *ctx;
+
+	while (1) {
+		ctx = (struct sha512_hash_ctx *)
+					sha512_job_mgr_flush(&mgr->mgr);
+
+		/* If flush returned 0, there are no more jobs in flight. */
+		if (!ctx)
+			return NULL;
+
+		/*
+		 * If flush returned a job, resubmit the job to finish
+		 * processing.
+		 */
+		ctx = sha512_ctx_mgr_resubmit(mgr, ctx);
+
+		/*
+		 * If sha512_ctx_mgr_resubmit returned a job, it is ready to
+		 * be returned. Otherwise, all jobs currently being managed by
+		 * the sha512_ctx_mgr still need processing. Loop.
+		 */
+		if (ctx)
+			return ctx;
+	}
+}
+
+static int sha512_mb_init(struct ahash_request *areq)
+{
+	struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	hash_ctx_init(sctx);
+	sctx->job.result_digest[0] = SHA512_H0;
+	sctx->job.result_digest[1] = SHA512_H1;
+	sctx->job.result_digest[2] = SHA512_H2;
+	sctx->job.result_digest[3] = SHA512_H3;
+	sctx->job.result_digest[4] = SHA512_H4;
+	sctx->job.result_digest[5] = SHA512_H5;
+	sctx->job.result_digest[6] = SHA512_H6;
+	sctx->job.result_digest[7] = SHA512_H7;
+	sctx->total_length = 0;
+	sctx->partial_block_buffer_length = 0;
+	sctx->status = HASH_CTX_STS_IDLE;
+
+	return 0;
+}
+
+static int sha512_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
+{
+	int	i;
+	struct	sha512_hash_ctx *sctx = ahash_request_ctx(&rctx->areq);
+	__be64	*dst = (__be64 *) rctx->out;
+
+	for (i = 0; i < 8; ++i)
+		dst[i] = cpu_to_be64(sctx->job.result_digest[i]);
+
+	return 0;
+}
+
+static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
+			struct mcryptd_alg_cstate *cstate, bool flush)
+{
+	int	flag = HASH_UPDATE;
+	int	nbytes, err = 0;
+	struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
+	struct sha512_hash_ctx *sha_ctx;
+
+	/* more work ? */
+	while (!(rctx->flag & HASH_DONE)) {
+		nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
+		if (nbytes < 0) {
+			err = nbytes;
+			goto out;
+		}
+		/* check if the walk is done */
+		if (crypto_ahash_walk_last(&rctx->walk)) {
+			rctx->flag |= HASH_DONE;
+			if (rctx->flag & HASH_FINAL)
+				flag |= HASH_LAST;
+
+		}
+		sha_ctx = (struct sha512_hash_ctx *)
+						ahash_request_ctx(&rctx->areq);
+		kernel_fpu_begin();
+		sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx,
+						rctx->walk.data, nbytes, flag);
+		if (!sha_ctx) {
+			if (flush)
+				sha_ctx = sha512_ctx_mgr_flush(cstate->mgr);
+		}
+		kernel_fpu_end();
+		if (sha_ctx)
+			rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		else {
+			rctx = NULL;
+			goto out;
+		}
+	}
+
+	/* copy the results */
+	if (rctx->flag & HASH_FINAL)
+		sha512_mb_set_results(rctx);
+
+out:
+	*ret_rctx = rctx;
+	return err;
+}
+
+static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
+			    struct mcryptd_alg_cstate *cstate,
+			    int err)
+{
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha512_hash_ctx *sha_ctx;
+	struct mcryptd_hash_request_ctx *req_ctx;
+	int ret;
+
+	/* remove from work list */
+	spin_lock(&cstate->work_lock);
+	list_del(&rctx->waiter);
+	spin_unlock(&cstate->work_lock);
+
+	if (irqs_disabled())
+		rctx->complete(&req->base, err);
+	else {
+		local_bh_disable();
+		rctx->complete(&req->base, err);
+		local_bh_enable();
+	}
+
+	/* check to see if there are other jobs that are done */
+	sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate->mgr);
+	while (sha_ctx) {
+		req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		ret = sha_finish_walk(&req_ctx, cstate, false);
+		if (req_ctx) {
+			spin_lock(&cstate->work_lock);
+			list_del(&req_ctx->waiter);
+			spin_unlock(&cstate->work_lock);
+
+			req = cast_mcryptd_ctx_to_req(req_ctx);
+			if (irqs_disabled())
+				rctx->complete(&req->base, ret);
+			else {
+				local_bh_disable();
+				rctx->complete(&req->base, ret);
+				local_bh_enable();
+			}
+		}
+		sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate->mgr);
+	}
+
+	return 0;
+}
+
+static void sha512_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
+			     struct mcryptd_alg_cstate *cstate)
+{
+	unsigned long next_flush;
+	unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
+
+	/* initialize tag */
+	rctx->tag.arrival = jiffies;    /* tag the arrival time */
+	rctx->tag.seq_num = cstate->next_seq_num++;
+	next_flush = rctx->tag.arrival + delay;
+	rctx->tag.expire = next_flush;
+
+	spin_lock(&cstate->work_lock);
+	list_add_tail(&rctx->waiter, &cstate->work_list);
+	spin_unlock(&cstate->work_lock);
+
+	mcryptd_arm_flusher(cstate, delay);
+}
+
+static int sha512_mb_update(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+									areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha512_hash_ctx *sha_ctx;
+	int ret = 0, nbytes;
+
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk))
+		rctx->flag |= HASH_DONE;
+
+	/* submit */
+	sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
+	sha512_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+							nbytes, HASH_UPDATE);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha512_mb_finup(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+									areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
+
+	struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+	struct sha512_hash_ctx *sha_ctx;
+	int ret = 0, flag = HASH_UPDATE, nbytes;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+	if (nbytes < 0) {
+		ret = nbytes;
+		goto done;
+	}
+
+	if (crypto_ahash_walk_last(&rctx->walk)) {
+		rctx->flag |= HASH_DONE;
+		flag = HASH_LAST;
+	}
+
+	/* submit */
+	rctx->flag |= HASH_FINAL;
+	sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
+	sha512_mb_add_list(rctx, cstate);
+
+	kernel_fpu_begin();
+	sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data,
+								nbytes, flag);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha512_mb_final(struct ahash_request *areq)
+{
+	struct mcryptd_hash_request_ctx *rctx =
+			container_of(areq, struct mcryptd_hash_request_ctx,
+									areq);
+	struct mcryptd_alg_cstate *cstate =
+				this_cpu_ptr(sha512_mb_alg_state.alg_cstate);
+
+	struct sha512_hash_ctx *sha_ctx;
+	int ret = 0;
+	u8 data;
+
+	/* sanity check */
+	if (rctx->tag.cpu != smp_processor_id()) {
+		pr_err("mcryptd error: cpu clash\n");
+		goto done;
+	}
+
+	/* need to init context */
+	req_ctx_init(rctx, areq);
+
+	rctx->flag |= HASH_DONE | HASH_FINAL;
+
+	sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq);
+	/* flag HASH_FINAL and 0 data size */
+	sha512_mb_add_list(rctx, cstate);
+	kernel_fpu_begin();
+	sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0,
+								HASH_LAST);
+	kernel_fpu_end();
+
+	/* check if anything is returned */
+	if (!sha_ctx)
+		return -EINPROGRESS;
+
+	if (sha_ctx->error) {
+		ret = sha_ctx->error;
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		goto done;
+	}
+
+	rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+	ret = sha_finish_walk(&rctx, cstate, false);
+	if (!rctx)
+		return -EINPROGRESS;
+done:
+	sha_complete_job(rctx, cstate, ret);
+	return ret;
+}
+
+static int sha512_mb_export(struct ahash_request *areq, void *out)
+{
+	struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_mb_import(struct ahash_request *areq, const void *in)
+{
+	struct sha512_hash_ctx *sctx = ahash_request_ctx(areq);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct mcryptd_ahash *mcryptd_tfm;
+	struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mcryptd_hash_ctx *mctx;
+
+	mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha512-mb",
+						CRYPTO_ALG_INTERNAL,
+						CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(mcryptd_tfm))
+		return PTR_ERR(mcryptd_tfm);
+	mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+	mctx->alg_state = &sha512_mb_alg_state;
+	ctx->mcryptd_tfm = mcryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+	return 0;
+}
+
+static void sha512_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static int sha512_mb_areq_init_tfm(struct crypto_tfm *tfm)
+{
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				sizeof(struct ahash_request) +
+				sizeof(struct sha512_hash_ctx));
+
+	return 0;
+}
+
+static void sha512_mb_areq_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct sha512_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha512_mb_areq_alg = {
+	.init		=	sha512_mb_init,
+	.update		=	sha512_mb_update,
+	.final		=	sha512_mb_final,
+	.finup		=	sha512_mb_finup,
+	.export		=	sha512_mb_export,
+	.import		=	sha512_mb_import,
+	.halg		=	{
+	.digestsize	=	SHA512_DIGEST_SIZE,
+	.statesize	=	sizeof(struct sha512_hash_ctx),
+	.base		=	{
+			.cra_name	 = "__sha512-mb",
+			.cra_driver_name = "__intel_sha512-mb",
+			.cra_priority	 = 100,
+			/*
+			 * use ASYNC flag as some buffers in multi-buffer
+			 * algo may not have completed before hashing thread
+			 * sleep
+			 */
+			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_INTERNAL,
+			.cra_blocksize	= SHA512_BLOCK_SIZE,
+			.cra_module	= THIS_MODULE,
+			.cra_list	= LIST_HEAD_INIT
+					(sha512_mb_areq_alg.halg.base.cra_list),
+			.cra_init	= sha512_mb_areq_init_tfm,
+			.cra_exit	= sha512_mb_areq_exit_tfm,
+			.cra_ctxsize	= sizeof(struct sha512_hash_ctx),
+		}
+	}
+};
+
+static int sha512_mb_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_init(mcryptd_req);
+}
+
+static int sha512_mb_async_update(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_update(mcryptd_req);
+}
+
+static int sha512_mb_async_finup(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_finup(mcryptd_req);
+}
+
+static int sha512_mb_async_final(struct ahash_request *req)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_final(mcryptd_req);
+}
+
+static int sha512_mb_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_digest(mcryptd_req);
+}
+
+static int sha512_mb_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_export(mcryptd_req, out);
+}
+
+static int sha512_mb_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha512_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+	struct crypto_ahash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct mcryptd_hash_request_ctx *rctx;
+	struct ahash_request *areq;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	rctx = ahash_request_ctx(mcryptd_req);
+
+	areq = &rctx->areq;
+
+	ahash_request_set_tfm(areq, child);
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_SLEEP,
+					rctx->complete, req);
+
+	return crypto_ahash_import(mcryptd_req, in);
+}
+
+static struct ahash_alg sha512_mb_async_alg = {
+	.init           = sha512_mb_async_init,
+	.update         = sha512_mb_async_update,
+	.final          = sha512_mb_async_final,
+	.finup          = sha512_mb_async_finup,
+	.digest         = sha512_mb_async_digest,
+	.export		= sha512_mb_async_export,
+	.import		= sha512_mb_async_import,
+	.halg = {
+		.digestsize     = SHA512_DIGEST_SIZE,
+		.statesize      = sizeof(struct sha512_hash_ctx),
+		.base = {
+			.cra_name               = "sha512",
+			.cra_driver_name        = "sha512_mb",
+			.cra_priority           = 200,
+			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
+							CRYPTO_ALG_ASYNC,
+			.cra_blocksize          = SHA512_BLOCK_SIZE,
+			.cra_type               = &crypto_ahash_type,
+			.cra_module             = THIS_MODULE,
+			.cra_list               = LIST_HEAD_INIT
+				(sha512_mb_async_alg.halg.base.cra_list),
+			.cra_init               = sha512_mb_async_init_tfm,
+			.cra_exit               = sha512_mb_async_exit_tfm,
+			.cra_ctxsize		= sizeof(struct sha512_mb_ctx),
+			.cra_alignmask		= 0,
+		},
+	},
+};
+
+static unsigned long sha512_mb_flusher(struct mcryptd_alg_cstate *cstate)
+{
+	struct mcryptd_hash_request_ctx *rctx;
+	unsigned long cur_time;
+	unsigned long next_flush = 0;
+	struct sha512_hash_ctx *sha_ctx;
+
+
+	cur_time = jiffies;
+
+	while (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		if time_before(cur_time, rctx->tag.expire)
+			break;
+		kernel_fpu_begin();
+		sha_ctx = (struct sha512_hash_ctx *)
+					sha512_ctx_mgr_flush(cstate->mgr);
+		kernel_fpu_end();
+		if (!sha_ctx) {
+			pr_err("sha512_mb error: nothing got flushed for"
+							" non-empty list\n");
+			break;
+		}
+		rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+		sha_finish_walk(&rctx, cstate, true);
+		sha_complete_job(rctx, cstate, 0);
+	}
+
+	if (!list_empty(&cstate->work_list)) {
+		rctx = list_entry(cstate->work_list.next,
+				struct mcryptd_hash_request_ctx, waiter);
+		/* get the hash context and then flush time */
+		next_flush = rctx->tag.expire;
+		mcryptd_arm_flusher(cstate, get_delay(next_flush));
+	}
+	return next_flush;
+}
+
+static int __init sha512_mb_mod_init(void)
+{
+
+	int cpu;
+	int err;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	/* check for dependent cpu features */
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_BMI2))
+		return -ENODEV;
+
+	/* initialize multibuffer structures */
+	sha512_mb_alg_state.alg_cstate =
+				alloc_percpu(struct mcryptd_alg_cstate);
+
+	sha512_job_mgr_init = sha512_mb_mgr_init_avx2;
+	sha512_job_mgr_submit = sha512_mb_mgr_submit_avx2;
+	sha512_job_mgr_flush = sha512_mb_mgr_flush_avx2;
+	sha512_job_mgr_get_comp_job = sha512_mb_mgr_get_comp_job_avx2;
+
+	if (!sha512_mb_alg_state.alg_cstate)
+		return -ENOMEM;
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
+		cpu_state->next_flush = 0;
+		cpu_state->next_seq_num = 0;
+		cpu_state->flusher_engaged = false;
+		INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
+		cpu_state->cpu = cpu;
+		cpu_state->alg_state = &sha512_mb_alg_state;
+		cpu_state->mgr = kzalloc(sizeof(struct sha512_ctx_mgr),
+								GFP_KERNEL);
+		if (!cpu_state->mgr)
+			goto err2;
+		sha512_ctx_mgr_init(cpu_state->mgr);
+		INIT_LIST_HEAD(&cpu_state->work_list);
+		spin_lock_init(&cpu_state->work_lock);
+	}
+	sha512_mb_alg_state.flusher = &sha512_mb_flusher;
+
+	err = crypto_register_ahash(&sha512_mb_areq_alg);
+	if (err)
+		goto err2;
+	err = crypto_register_ahash(&sha512_mb_async_alg);
+	if (err)
+		goto err1;
+
+
+	return 0;
+err1:
+	crypto_unregister_ahash(&sha512_mb_areq_alg);
+err2:
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha512_mb_alg_state.alg_cstate);
+	return -ENODEV;
+}
+
+static void __exit sha512_mb_mod_fini(void)
+{
+	int cpu;
+	struct mcryptd_alg_cstate *cpu_state;
+
+	crypto_unregister_ahash(&sha512_mb_async_alg);
+	crypto_unregister_ahash(&sha512_mb_areq_alg);
+	for_each_possible_cpu(cpu) {
+		cpu_state = per_cpu_ptr(sha512_mb_alg_state.alg_cstate, cpu);
+		kfree(cpu_state->mgr);
+	}
+	free_percpu(sha512_mb_alg_state.alg_cstate);
+}
+
+module_init(sha512_mb_mod_init);
+module_exit(sha512_mb_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, multi buffer accelerated");
+
+MODULE_ALIAS("sha512");
diff --git a/arch/x86/crypto/sha-mb/sha_mb_ctx.h b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
similarity index 81%
copy from arch/x86/crypto/sha-mb/sha_mb_ctx.h
copy to arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
index e36069d..9d4b2c8 100644
--- a/arch/x86/crypto/sha-mb/sha_mb_ctx.h
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_ctx.h
@@ -1,12 +1,12 @@
 /*
- * Header file for multi buffer SHA context
+ * Header file for multi buffer SHA512 context
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
  *
  * GPL LICENSE SUMMARY
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of version 2 of the GNU General Public License as
@@ -18,11 +18,11 @@
  *  General Public License for more details.
  *
  *  Contact Information:
- *	Tim Chen <tim.c.chen@linux.intel.com>
+ *      Megha Dey <megha.dey@linux.intel.com>
  *
  *  BSD LICENSE
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  Redistribution and use in source and binary forms, with or without
  *  modification, are permitted provided that the following conditions
@@ -54,14 +54,14 @@
 #ifndef _SHA_MB_CTX_INTERNAL_H
 #define _SHA_MB_CTX_INTERNAL_H
 
-#include "sha_mb_mgr.h"
+#include "sha512_mb_mgr.h"
 
 #define HASH_UPDATE          0x00
 #define HASH_FIRST           0x01
 #define HASH_LAST            0x02
 #define HASH_ENTIRE          0x03
-#define HASH_DONE	     0x04
-#define HASH_FINAL	     0x08
+#define HASH_DONE            0x04
+#define HASH_FINAL           0x08
 
 #define HASH_CTX_STS_IDLE       0x00
 #define HASH_CTX_STS_PROCESSING 0x01
@@ -73,13 +73,8 @@
 	HASH_CTX_ERROR_INVALID_FLAGS      = -1,
 	HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
 	HASH_CTX_ERROR_ALREADY_COMPLETED  = -3,
-
-#ifdef HASH_CTX_DEBUG
-	HASH_CTX_ERROR_DEBUG_DIGEST_MISMATCH = -4,
-#endif
 };
 
-
 #define hash_ctx_user_data(ctx)  ((ctx)->user_data)
 #define hash_ctx_digest(ctx)     ((ctx)->job.result_digest)
 #define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
@@ -92,12 +87,11 @@
 		(ctx)->status = HASH_CTX_STS_COMPLETE; \
 	} while (0)
 
-
 /* Hash Constants and Typedefs */
-#define SHA1_DIGEST_LENGTH          5
-#define SHA1_LOG2_BLOCK_SIZE        6
+#define SHA512_DIGEST_LENGTH          8
+#define SHA512_LOG2_BLOCK_SIZE        7
 
-#define SHA1_PADLENGTHFIELD_SIZE    8
+#define SHA512_PADLENGTHFIELD_SIZE    16
 
 #ifdef SHA_MB_DEBUG
 #define assert(expr) \
@@ -111,26 +105,26 @@
 #define assert(expr) do {} while (0)
 #endif
 
-struct sha1_ctx_mgr {
-	struct sha1_mb_mgr mgr;
+struct sha512_ctx_mgr {
+	struct sha512_mb_mgr mgr;
 };
 
-/* typedef struct sha1_ctx_mgr sha1_ctx_mgr; */
+/* typedef struct sha512_ctx_mgr sha512_ctx_mgr; */
 
-struct sha1_hash_ctx {
+struct sha512_hash_ctx {
 	/* Must be at struct offset 0 */
-	struct job_sha1       job;
+	struct job_sha512       job;
 	/* status flag */
 	int status;
 	/* error flag */
 	int error;
 
-	uint32_t	total_length;
-	const void	*incoming_buffer;
-	uint32_t	incoming_buffer_length;
-	uint8_t		partial_block_buffer[SHA1_BLOCK_SIZE * 2];
-	uint32_t	partial_block_buffer_length;
-	void		*user_data;
+	uint32_t        total_length;
+	const void      *incoming_buffer;
+	uint32_t        incoming_buffer_length;
+	uint8_t         partial_block_buffer[SHA512_BLOCK_SIZE * 2];
+	uint32_t        partial_block_buffer_length;
+	void            *user_data;
 };
 
 #endif
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
similarity index 62%
copy from arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
copy to arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
index 822acb5..178f17e 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr.h
@@ -1,12 +1,12 @@
 /*
- * Initialization code for multi buffer SHA1 algorithm for AVX2
+ * Header file for multi buffer SHA512 algorithm manager
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
  *
  * GPL LICENSE SUMMARY
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of version 2 of the GNU General Public License as
@@ -18,11 +18,11 @@
  *  General Public License for more details.
  *
  *  Contact Information:
- *	Tim Chen <tim.c.chen@linux.intel.com>
+ *      Megha Dey <megha.dey@linux.intel.com>
  *
  *  BSD LICENSE
  *
- *  Copyright(c) 2014 Intel Corporation.
+ *  Copyright(c) 2016 Intel Corporation.
  *
  *  Redistribution and use in source and binary forms, with or without
  *  modification, are permitted provided that the following conditions
@@ -51,14 +51,54 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include "sha_mb_mgr.h"
+#ifndef __SHA_MB_MGR_H
+#define __SHA_MB_MGR_H
 
-void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
-{
-	unsigned int j;
-	state->unused_lanes = 0xF76543210ULL;
-	for (j = 0; j < 8; j++) {
-		state->lens[j] = 0xFFFFFFFF;
-		state->ldata[j].job_in_lane = NULL;
-	}
-}
+#include <linux/types.h>
+
+#define NUM_SHA512_DIGEST_WORDS 8
+
+enum job_sts {STS_UNKNOWN = 0,
+	STS_BEING_PROCESSED = 1,
+	STS_COMPLETED =       2,
+	STS_INTERNAL_ERROR = 3,
+	STS_ERROR = 4
+};
+
+struct job_sha512 {
+	u8  *buffer;
+	u64  len;
+	u64  result_digest[NUM_SHA512_DIGEST_WORDS] __aligned(32);
+	enum job_sts status;
+	void   *user_data;
+};
+
+struct sha512_args_x4 {
+	uint64_t        digest[8][4];
+	uint8_t         *data_ptr[4];
+};
+
+struct sha512_lane_data {
+	struct job_sha512 *job_in_lane;
+};
+
+struct sha512_mb_mgr {
+	struct sha512_args_x4 args;
+
+	uint64_t lens[4];
+
+	/* each byte is index (0...7) of unused lanes */
+	uint64_t unused_lanes;
+	/* byte 4 is set to FF as a flag */
+	struct sha512_lane_data ldata[4];
+};
+
+#define SHA512_MB_MGR_NUM_LANES_AVX2 4
+
+void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state);
+struct job_sha512 *sha512_mb_mgr_submit_avx2(struct sha512_mb_mgr *state,
+						struct job_sha512 *job);
+struct job_sha512 *sha512_mb_mgr_flush_avx2(struct sha512_mb_mgr *state);
+struct job_sha512 *sha512_mb_mgr_get_comp_job_avx2(struct sha512_mb_mgr *state);
+
+#endif
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S
new file mode 100644
index 0000000..cf2636d
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_datastruct.S
@@ -0,0 +1,281 @@
+/*
+ * Header file for multi buffer SHA256 algorithm data structure
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of version 2 of the GNU General Public License as
+ *  published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  Contact Information:
+ *      Megha Dey <megha.dey@linux.intel.com>
+ *
+ *  BSD LICENSE
+ *
+ *  Copyright(c) 2016 Intel Corporation.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *    * Redistributions of source code must retain the above copyright
+ *      notice, this list of conditions and the following disclaimer.
+ *    * Redistributions in binary form must reproduce the above copyright
+ *      notice, this list of conditions and the following disclaimer in
+ *      the documentation and/or other materials provided with the
+ *      distribution.
+ *    * Neither the name of Intel Corporation nor the names of its
+ *      contributors may be used to endorse or promote products derived
+ *      from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# Macros for defining data structures
+
+# Usage example
+
+#START_FIELDS   # JOB_AES
+###     name            size    align
+#FIELD  _plaintext,     8,      8       # pointer to plaintext
+#FIELD  _ciphertext,    8,      8       # pointer to ciphertext
+#FIELD  _IV,            16,     8       # IV
+#FIELD  _keys,          8,      8       # pointer to keys
+#FIELD  _len,           4,      4       # length in bytes
+#FIELD  _status,        4,      4       # status enumeration
+#FIELD  _user_data,     8,      8       # pointer to user data
+#UNION  _union,         size1,  align1, \
+#                       size2,  align2, \
+#                       size3,  align3, \
+#                       ...
+#END_FIELDS
+#%assign _JOB_AES_size  _FIELD_OFFSET
+#%assign _JOB_AES_align _STRUCT_ALIGN
+
+#########################################################################
+
+# Alternate "struc-like" syntax:
+#       STRUCT job_aes2
+#       RES_Q   .plaintext,     1
+#       RES_Q   .ciphertext,    1
+#       RES_DQ  .IV,            1
+#       RES_B   .nested,        _JOB_AES_SIZE, _JOB_AES_ALIGN
+#       RES_U   .union,         size1, align1, \
+#                               size2, align2, \
+#                               ...
+#       ENDSTRUCT
+#       # Following only needed if nesting
+#       %assign job_aes2_size   _FIELD_OFFSET
+#       %assign job_aes2_align  _STRUCT_ALIGN
+#
+# RES_* macros take a name, a count and an optional alignment.
+# The count in in terms of the base size of the macro, and the
+# default alignment is the base size.
+# The macros are:
+# Macro    Base size
+# RES_B     1
+# RES_W     2
+# RES_D     4
+# RES_Q     8
+# RES_DQ   16
+# RES_Y    32
+# RES_Z    64
+#
+# RES_U defines a union. It's arguments are a name and two or more
+# pairs of "size, alignment"
+#
+# The two assigns are only needed if this structure is being nested
+# within another. Even if the assigns are not done, one can still use
+# STRUCT_NAME_size as the size of the structure.
+#
+# Note that for nesting, you still need to assign to STRUCT_NAME_size.
+#
+# The differences between this and using "struc" directly are that each
+# type is implicitly aligned to its natural length (although this can be
+# over-ridden with an explicit third parameter), and that the structure
+# is padded at the end to its overall alignment.
+#
+
+#########################################################################
+
+#ifndef _DATASTRUCT_ASM_
+#define _DATASTRUCT_ASM_
+
+#define PTR_SZ                  8
+#define SHA512_DIGEST_WORD_SIZE 8
+#define SHA512_MB_MGR_NUM_LANES_AVX2 4
+#define NUM_SHA512_DIGEST_WORDS 8
+#define SZ4                     4*SHA512_DIGEST_WORD_SIZE
+#define ROUNDS                  80*SZ4
+#define SHA512_DIGEST_ROW_SIZE  (SHA512_MB_MGR_NUM_LANES_AVX2 * 8)
+
+# START_FIELDS
+.macro START_FIELDS
+ _FIELD_OFFSET = 0
+ _STRUCT_ALIGN = 0
+.endm
+
+# FIELD name size align
+.macro FIELD name size align
+ _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
+ \name  = _FIELD_OFFSET
+ _FIELD_OFFSET = _FIELD_OFFSET + (\size)
+.if (\align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = \align
+.endif
+.endm
+
+# END_FIELDS
+.macro END_FIELDS
+ _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
+.endm
+
+.macro STRUCT p1
+START_FIELDS
+.struc \p1
+.endm
+
+.macro ENDSTRUCT
+ tmp = _FIELD_OFFSET
+ END_FIELDS
+ tmp = (_FIELD_OFFSET - ##tmp)
+.if (tmp > 0)
+        .lcomm  tmp
+.endm
+
+## RES_int name size align
+.macro RES_int p1 p2 p3
+ name = \p1
+ size = \p2
+ align = .\p3
+
+ _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
+.align align
+.lcomm name size
+ _FIELD_OFFSET = _FIELD_OFFSET + (size)
+.if (align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = align
+.endif
+.endm
+
+# macro RES_B name, size [, align]
+.macro RES_B _name, _size, _align=1
+RES_int _name _size _align
+.endm
+
+# macro RES_W name, size [, align]
+.macro RES_W _name, _size, _align=2
+RES_int _name 2*(_size) _align
+.endm
+
+# macro RES_D name, size [, align]
+.macro RES_D _name, _size, _align=4
+RES_int _name 4*(_size) _align
+.endm
+
+# macro RES_Q name, size [, align]
+.macro RES_Q _name, _size, _align=8
+RES_int _name 8*(_size) _align
+.endm
+
+# macro RES_DQ name, size [, align]
+.macro RES_DQ _name, _size, _align=16
+RES_int _name 16*(_size) _align
+.endm
+
+# macro RES_Y name, size [, align]
+.macro RES_Y _name, _size, _align=32
+RES_int _name 32*(_size) _align
+.endm
+
+# macro RES_Z name, size [, align]
+.macro RES_Z _name, _size, _align=64
+RES_int _name 64*(_size) _align
+.endm
+
+#endif
+
+###################################################################
+### Define SHA512 Out Of Order Data Structures
+###################################################################
+
+START_FIELDS    # LANE_DATA
+###     name            size    align
+FIELD   _job_in_lane,   8,      8       # pointer to job object
+END_FIELDS
+
+ _LANE_DATA_size = _FIELD_OFFSET
+ _LANE_DATA_align = _STRUCT_ALIGN
+
+####################################################################
+
+START_FIELDS    # SHA512_ARGS_X4
+###     name            size    align
+FIELD   _digest,        8*8*4,  4      # transposed digest
+FIELD   _data_ptr,      8*4,    8       # array of pointers to data
+END_FIELDS
+
+ _SHA512_ARGS_X4_size  =  _FIELD_OFFSET
+ _SHA512_ARGS_X4_align =  _STRUCT_ALIGN
+
+#####################################################################
+
+START_FIELDS    # MB_MGR
+###     name            size    align
+FIELD   _args,          _SHA512_ARGS_X4_size, _SHA512_ARGS_X4_align
+FIELD   _lens,          8*4,    8
+FIELD   _unused_lanes,  8,      8
+FIELD   _ldata,         _LANE_DATA_size*4, _LANE_DATA_align
+END_FIELDS
+
+ _MB_MGR_size  =  _FIELD_OFFSET
+ _MB_MGR_align =  _STRUCT_ALIGN
+
+_args_digest = _args + _digest
+_args_data_ptr = _args + _data_ptr
+
+#######################################################################
+
+#######################################################################
+#### Define constants
+#######################################################################
+
+#define STS_UNKNOWN             0
+#define STS_BEING_PROCESSED     1
+#define STS_COMPLETED           2
+
+#######################################################################
+#### Define JOB_SHA512 structure
+#######################################################################
+
+START_FIELDS    # JOB_SHA512
+###     name                            size    align
+FIELD   _buffer,                        8,      8       # pointer to buffer
+FIELD   _len,                           8,      8       # length in bytes
+FIELD   _result_digest,                 8*8,    32      # Digest (output)
+FIELD   _status,                        4,      4
+FIELD   _user_data,                     8,      8
+END_FIELDS
+
+ _JOB_SHA512_size = _FIELD_OFFSET
+ _JOB_SHA512_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S
new file mode 100644
index 0000000..3ddba19
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S
@@ -0,0 +1,291 @@
+/*
+ * Flush routine for SHA512 multibuffer
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha512_mb_mgr_datastruct.S"
+
+.extern sha512_x4_avx2
+
+# LINUX register definitions
+#define arg1    %rdi
+#define arg2    %rsi
+
+# idx needs to be other than arg1, arg2, rbx, r12
+#define idx     %rdx
+
+# Common definitions
+#define state   arg1
+#define job     arg2
+#define len2    arg2
+
+#define unused_lanes    %rbx
+#define lane_data       %rbx
+#define tmp2            %rbx
+
+#define job_rax         %rax
+#define tmp1            %rax
+#define size_offset     %rax
+#define tmp             %rax
+#define start_offset    %rax
+
+#define tmp3            arg1
+
+#define extra_blocks    arg2
+#define p               arg2
+
+#define tmp4            %r8
+#define lens0           %r8
+
+#define lens1           %r9
+#define lens2           %r10
+#define lens3           %r11
+
+.macro LABEL prefix n
+\prefix\n\():
+.endm
+
+.macro JNE_SKIP i
+jne     skip_\i
+.endm
+
+.altmacro
+.macro SET_OFFSET _offset
+offset = \_offset
+.endm
+.noaltmacro
+
+# JOB* sha512_mb_mgr_flush_avx2(MB_MGR *state)
+# arg 1 : rcx : state
+ENTRY(sha512_mb_mgr_flush_avx2)
+	FRAME_BEGIN
+	push	%rbx
+
+	# If bit (32+3) is set, then all lanes are empty
+	mov     _unused_lanes(state), unused_lanes
+        bt      $32+7, unused_lanes
+        jc      return_null
+
+        # find a lane with a non-null job
+	xor     idx, idx
+        offset = (_ldata + 1*_LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+        cmovne  one(%rip), idx
+        offset = (_ldata + 2*_LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+        cmovne  two(%rip), idx
+        offset = (_ldata + 3*_LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+        cmovne  three(%rip), idx
+
+        # copy idx to empty lanes
+copy_lane_data:
+	offset =  (_args + _data_ptr)
+        mov     offset(state,idx,8), tmp
+
+        I = 0
+.rep 4
+	offset =  (_ldata + I * _LANE_DATA_size + _job_in_lane)
+        cmpq    $0, offset(state)
+.altmacro
+        JNE_SKIP %I
+        offset =  (_args + _data_ptr + 8*I)
+        mov     tmp, offset(state)
+        offset =  (_lens + 8*I +4)
+        movl    $0xFFFFFFFF, offset(state)
+LABEL skip_ %I
+        I = (I+1)
+.noaltmacro
+.endr
+
+        # Find min length
+        mov     _lens + 0*8(state),lens0
+        mov     lens0,idx
+        mov     _lens + 1*8(state),lens1
+        cmp     idx,lens1
+        cmovb   lens1,idx
+        mov     _lens + 2*8(state),lens2
+        cmp     idx,lens2
+        cmovb   lens2,idx
+        mov     _lens + 3*8(state),lens3
+        cmp     idx,lens3
+        cmovb   lens3,idx
+        mov     idx,len2
+        and     $0xF,idx
+        and     $~0xFF,len2
+	jz      len_is_0
+
+        sub     len2, lens0
+        sub     len2, lens1
+        sub     len2, lens2
+        sub     len2, lens3
+        shr     $32,len2
+        mov     lens0, _lens + 0*8(state)
+        mov     lens1, _lens + 1*8(state)
+        mov     lens2, _lens + 2*8(state)
+        mov     lens3, _lens + 3*8(state)
+
+        # "state" and "args" are the same address, arg1
+        # len is arg2
+        call    sha512_x4_avx2
+        # state and idx are intact
+
+len_is_0:
+        # process completed job "idx"
+	imul    $_LANE_DATA_size, idx, lane_data
+        lea     _ldata(state, lane_data), lane_data
+
+        mov     _job_in_lane(lane_data), job_rax
+        movq    $0,  _job_in_lane(lane_data)
+        movl    $STS_COMPLETED, _status(job_rax)
+        mov     _unused_lanes(state), unused_lanes
+        shl     $8, unused_lanes
+        or      idx, unused_lanes
+        mov     unused_lanes, _unused_lanes(state)
+
+	movl    $0xFFFFFFFF, _lens+4(state,  idx, 8)
+
+	vmovq _args_digest+0*32(state, idx, 8), %xmm0
+        vpinsrq $1, _args_digest+1*32(state, idx, 8), %xmm0, %xmm0
+	vmovq _args_digest+2*32(state, idx, 8), %xmm1
+        vpinsrq $1, _args_digest+3*32(state, idx, 8), %xmm1, %xmm1
+	vmovq _args_digest+4*32(state, idx, 8), %xmm2
+        vpinsrq $1, _args_digest+5*32(state, idx, 8), %xmm2, %xmm2
+	vmovq _args_digest+6*32(state, idx, 8), %xmm3
+	vpinsrq $1, _args_digest+7*32(state, idx, 8), %xmm3, %xmm3
+
+	vmovdqu %xmm0, _result_digest(job_rax)
+	vmovdqu %xmm1, _result_digest+1*16(job_rax)
+	vmovdqu %xmm2, _result_digest+2*16(job_rax)
+	vmovdqu %xmm3, _result_digest+3*16(job_rax)
+
+return:
+	pop	%rbx
+	FRAME_END
+        ret
+
+return_null:
+        xor     job_rax, job_rax
+        jmp     return
+ENDPROC(sha512_mb_mgr_flush_avx2)
+.align 16
+
+ENTRY(sha512_mb_mgr_get_comp_job_avx2)
+        push    %rbx
+
+	mov     _unused_lanes(state), unused_lanes
+        bt      $(32+7), unused_lanes
+        jc      .return_null
+
+        # Find min length
+        mov     _lens(state),lens0
+        mov     lens0,idx
+        mov     _lens+1*8(state),lens1
+        cmp     idx,lens1
+        cmovb   lens1,idx
+        mov     _lens+2*8(state),lens2
+        cmp     idx,lens2
+        cmovb   lens2,idx
+        mov     _lens+3*8(state),lens3
+        cmp     idx,lens3
+        cmovb   lens3,idx
+        test    $~0xF,idx
+        jnz     .return_null
+        and     $0xF,idx
+
+        #process completed job "idx"
+	imul    $_LANE_DATA_size, idx, lane_data
+        lea     _ldata(state, lane_data), lane_data
+
+        mov     _job_in_lane(lane_data), job_rax
+        movq    $0,  _job_in_lane(lane_data)
+        movl    $STS_COMPLETED, _status(job_rax)
+        mov     _unused_lanes(state), unused_lanes
+        shl     $8, unused_lanes
+        or      idx, unused_lanes
+        mov     unused_lanes, _unused_lanes(state)
+
+        movl    $0xFFFFFFFF, _lens+4(state,  idx, 8)
+
+	vmovq   _args_digest(state, idx, 8), %xmm0
+        vpinsrq $1, _args_digest+1*32(state, idx, 8), %xmm0, %xmm0
+	vmovq    _args_digest+2*32(state, idx, 8), %xmm1
+        vpinsrq $1, _args_digest+3*32(state, idx, 8), %xmm1, %xmm1
+	vmovq    _args_digest+4*32(state, idx, 8), %xmm2
+        vpinsrq $1, _args_digest+5*32(state, idx, 8), %xmm2, %xmm2
+        vmovq    _args_digest+6*32(state, idx, 8), %xmm3
+        vpinsrq $1, _args_digest+7*32(state, idx, 8), %xmm3, %xmm3
+
+	vmovdqu %xmm0, _result_digest+0*16(job_rax)
+	vmovdqu %xmm1, _result_digest+1*16(job_rax)
+	vmovdqu %xmm2, _result_digest+2*16(job_rax)
+	vmovdqu %xmm3, _result_digest+3*16(job_rax)
+
+	pop     %rbx
+
+        ret
+
+.return_null:
+        xor     job_rax, job_rax
+	pop     %rbx
+        ret
+ENDPROC(sha512_mb_mgr_get_comp_job_avx2)
+.data
+
+.align 16
+one:
+.quad  1
+two:
+.quad  2
+three:
+.quad  3
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
new file mode 100644
index 0000000..36870b2
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
@@ -0,0 +1,67 @@
+/*
+ * Initialization code for multi buffer SHA256 algorithm for AVX2
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "sha512_mb_mgr.h"
+
+void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state)
+{
+	unsigned int j;
+
+	state->lens[0] = 0;
+	state->lens[1] = 1;
+	state->lens[2] = 2;
+	state->lens[3] = 3;
+	state->unused_lanes = 0xFF03020100;
+	for (j = 0; j < 4; j++)
+		state->ldata[j].job_in_lane = NULL;
+}
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S
new file mode 100644
index 0000000..815f07b
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S
@@ -0,0 +1,222 @@
+/*
+ * Buffer submit code for multi buffer SHA512 algorithm
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include <asm/frame.h>
+#include "sha512_mb_mgr_datastruct.S"
+
+.extern sha512_x4_avx2
+
+#define arg1    %rdi
+#define arg2    %rsi
+
+#define idx             %rdx
+#define last_len        %rdx
+
+#define size_offset     %rcx
+#define tmp2            %rcx
+
+# Common definitions
+#define state   arg1
+#define job     arg2
+#define len2    arg2
+#define p2      arg2
+
+#define p               %r11
+#define start_offset    %r11
+
+#define unused_lanes    %rbx
+
+#define job_rax         %rax
+#define len             %rax
+
+#define lane            %r12
+#define tmp3            %r12
+#define lens3           %r12
+
+#define extra_blocks    %r8
+#define lens0           %r8
+
+#define tmp             %r9
+#define lens1           %r9
+
+#define lane_data       %r10
+#define lens2           %r10
+
+#define DWORD_len %eax
+
+# JOB* sha512_mb_mgr_submit_avx2(MB_MGR *state, JOB *job)
+# arg 1 : rcx : state
+# arg 2 : rdx : job
+ENTRY(sha512_mb_mgr_submit_avx2)
+	FRAME_BEGIN
+	push	%rbx
+	push	%r12
+
+        mov     _unused_lanes(state), unused_lanes
+        movzb     %bl,lane
+        shr     $8, unused_lanes
+        imul    $_LANE_DATA_size, lane,lane_data
+        movl    $STS_BEING_PROCESSED, _status(job)
+	lea     _ldata(state, lane_data), lane_data
+        mov     unused_lanes, _unused_lanes(state)
+        movl    _len(job),  DWORD_len
+
+	mov     job, _job_in_lane(lane_data)
+        movl    DWORD_len,_lens+4(state , lane, 8)
+
+	# Load digest words from result_digest
+	vmovdqu	_result_digest+0*16(job), %xmm0
+	vmovdqu _result_digest+1*16(job), %xmm1
+	vmovdqu	_result_digest+2*16(job), %xmm2
+        vmovdqu	_result_digest+3*16(job), %xmm3
+
+	vmovq    %xmm0, _args_digest(state, lane, 8)
+	vpextrq  $1, %xmm0, _args_digest+1*32(state , lane, 8)
+	vmovq    %xmm1, _args_digest+2*32(state , lane, 8)
+	vpextrq  $1, %xmm1, _args_digest+3*32(state , lane, 8)
+	vmovq    %xmm2, _args_digest+4*32(state , lane, 8)
+	vpextrq  $1, %xmm2, _args_digest+5*32(state , lane, 8)
+	vmovq    %xmm3, _args_digest+6*32(state , lane, 8)
+	vpextrq  $1, %xmm3, _args_digest+7*32(state , lane, 8)
+
+	mov     _buffer(job), p
+	mov     p, _args_data_ptr(state, lane, 8)
+
+	cmp     $0xFF, unused_lanes
+	jne     return_null
+
+start_loop:
+
+	# Find min length
+	mov     _lens+0*8(state),lens0
+	mov     lens0,idx
+	mov     _lens+1*8(state),lens1
+	cmp     idx,lens1
+	cmovb   lens1, idx
+	mov     _lens+2*8(state),lens2
+	cmp     idx,lens2
+	cmovb   lens2,idx
+	mov     _lens+3*8(state),lens3
+	cmp     idx,lens3
+	cmovb   lens3,idx
+	mov     idx,len2
+	and     $0xF,idx
+	and     $~0xFF,len2
+	jz      len_is_0
+
+	sub     len2,lens0
+	sub     len2,lens1
+	sub     len2,lens2
+	sub     len2,lens3
+	shr     $32,len2
+	mov     lens0, _lens + 0*8(state)
+	mov     lens1, _lens + 1*8(state)
+	mov     lens2, _lens + 2*8(state)
+	mov     lens3, _lens + 3*8(state)
+
+	# "state" and "args" are the same address, arg1
+	# len is arg2
+	call    sha512_x4_avx2
+	# state and idx are intact
+
+len_is_0:
+
+	# process completed job "idx"
+	imul    $_LANE_DATA_size, idx, lane_data
+	lea     _ldata(state, lane_data), lane_data
+
+	mov     _job_in_lane(lane_data), job_rax
+	mov     _unused_lanes(state), unused_lanes
+	movq    $0, _job_in_lane(lane_data)
+	movl    $STS_COMPLETED, _status(job_rax)
+	shl     $8, unused_lanes
+	or      idx, unused_lanes
+	mov     unused_lanes, _unused_lanes(state)
+
+	movl	$0xFFFFFFFF,_lens+4(state,idx,8)
+	vmovq    _args_digest+0*32(state , idx, 8), %xmm0
+	vpinsrq  $1, _args_digest+1*32(state , idx, 8), %xmm0, %xmm0
+	vmovq    _args_digest+2*32(state , idx, 8), %xmm1
+	vpinsrq  $1, _args_digest+3*32(state , idx, 8), %xmm1, %xmm1
+	vmovq    _args_digest+4*32(state , idx, 8), %xmm2
+	vpinsrq  $1, _args_digest+5*32(state , idx, 8), %xmm2, %xmm2
+	vmovq    _args_digest+6*32(state , idx, 8), %xmm3
+	vpinsrq  $1, _args_digest+7*32(state , idx, 8), %xmm3, %xmm3
+
+	vmovdqu  %xmm0, _result_digest + 0*16(job_rax)
+	vmovdqu  %xmm1, _result_digest + 1*16(job_rax)
+	vmovdqu  %xmm2, _result_digest + 2*16(job_rax)
+	vmovdqu  %xmm3, _result_digest + 3*16(job_rax)
+
+return:
+	pop	%r12
+	pop	%rbx
+	FRAME_END
+	ret
+
+return_null:
+	xor     job_rax, job_rax
+	jmp     return
+ENDPROC(sha512_mb_mgr_submit_avx2)
+.data
+
+.align 16
+H0:     .int  0x6a09e667
+H1:     .int  0xbb67ae85
+H2:     .int  0x3c6ef372
+H3:     .int  0xa54ff53a
+H4:     .int  0x510e527f
+H5:     .int  0x9b05688c
+H6:     .int  0x1f83d9ab
+H7:     .int  0x5be0cd19
diff --git a/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S
new file mode 100644
index 0000000..31ab1ef
--- /dev/null
+++ b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S
@@ -0,0 +1,529 @@
+/*
+ * Multi-buffer SHA512 algorithm hash compute routine
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ *     Megha Dey <megha.dey@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# code to compute quad SHA512 using AVX2
+# use YMMs to tackle the larger digest size
+# outer calling routine takes care of save and restore of XMM registers
+# Logic designed/laid out by JDG
+
+# Function clobbers: rax, rcx, rdx, rbx, rsi, rdi, r9-r15; ymm0-15
+# Stack must be aligned to 32 bytes before call
+# Linux clobbers: rax rbx rcx rsi r8 r9 r10 r11 r12
+# Linux preserves: rcx rdx rdi rbp r13 r14 r15
+# clobbers ymm0-15
+
+#include <linux/linkage.h>
+#include "sha512_mb_mgr_datastruct.S"
+
+arg1 = %rdi
+arg2 = %rsi
+
+# Common definitions
+STATE = arg1
+INP_SIZE = arg2
+
+IDX = %rax
+ROUND = %rbx
+TBL = %r8
+
+inp0 = %r9
+inp1 = %r10
+inp2 = %r11
+inp3 = %r12
+
+a = %ymm0
+b = %ymm1
+c = %ymm2
+d = %ymm3
+e = %ymm4
+f = %ymm5
+g = %ymm6
+h = %ymm7
+
+a0 = %ymm8
+a1 = %ymm9
+a2 = %ymm10
+
+TT0 = %ymm14
+TT1 = %ymm13
+TT2 = %ymm12
+TT3 = %ymm11
+TT4 = %ymm10
+TT5 = %ymm9
+
+T1 = %ymm14
+TMP = %ymm15
+
+# Define stack usage
+STACK_SPACE1 = SZ4*16 + NUM_SHA512_DIGEST_WORDS*SZ4 + 24
+
+#define VMOVPD	vmovupd
+_digest = SZ4*16
+
+# transpose r0, r1, r2, r3, t0, t1
+# "transpose" data in {r0..r3} using temps {t0..t3}
+# Input looks like: {r0 r1 r2 r3}
+# r0 = {a7 a6 a5 a4 a3 a2 a1 a0}
+# r1 = {b7 b6 b5 b4 b3 b2 b1 b0}
+# r2 = {c7 c6 c5 c4 c3 c2 c1 c0}
+# r3 = {d7 d6 d5 d4 d3 d2 d1 d0}
+#
+# output looks like: {t0 r1 r0 r3}
+# t0 = {d1 d0 c1 c0 b1 b0 a1 a0}
+# r1 = {d3 d2 c3 c2 b3 b2 a3 a2}
+# r0 = {d5 d4 c5 c4 b5 b4 a5 a4}
+# r3 = {d7 d6 c7 c6 b7 b6 a7 a6}
+
+.macro TRANSPOSE r0 r1 r2 r3 t0 t1
+	vshufps  $0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4   b1 b0 a1 a0}
+        vshufps  $0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6   b3 b2 a3 a2}
+        vshufps  $0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4   d1 d0 c1 c0}
+        vshufps  $0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6   d3 d2 c3 c2}
+
+	vperm2f128      $0x20, \r2, \r0, \r1  # h6...a6
+        vperm2f128      $0x31, \r2, \r0, \r3  # h2...a2
+        vperm2f128      $0x31, \t1, \t0, \r0  # h5...a5
+        vperm2f128      $0x20, \t1, \t0, \t0  # h1...a1
+.endm
+
+.macro ROTATE_ARGS
+TMP_ = h
+h = g
+g = f
+f = e
+e = d
+d = c
+c = b
+b = a
+a = TMP_
+.endm
+
+# PRORQ reg, imm, tmp
+# packed-rotate-right-double
+# does a rotate by doing two shifts and an or
+.macro _PRORQ reg imm tmp
+	vpsllq	$(64-\imm),\reg,\tmp
+	vpsrlq	$\imm,\reg, \reg
+	vpor	\tmp,\reg, \reg
+.endm
+
+# non-destructive
+# PRORQ_nd reg, imm, tmp, src
+.macro _PRORQ_nd reg imm tmp src
+	vpsllq	$(64-\imm), \src, \tmp
+	vpsrlq	$\imm, \src, \reg
+	vpor	\tmp, \reg, \reg
+.endm
+
+# PRORQ dst/src, amt
+.macro PRORQ reg imm
+	_PRORQ	\reg, \imm, TMP
+.endm
+
+# PRORQ_nd dst, src, amt
+.macro PRORQ_nd reg tmp imm
+	_PRORQ_nd	\reg, \imm, TMP, \tmp
+.endm
+
+#; arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_00_15 _T1 i
+	PRORQ_nd a0, e, (18-14)	# sig1: a0 = (e >> 4)
+
+	vpxor   g, f, a2        # ch: a2 = f^g
+        vpand   e,a2, a2                # ch: a2 = (f^g)&e
+        vpxor   g, a2, a2               # a2 = ch
+
+        PRORQ_nd        a1,e,41         # sig1: a1 = (e >> 25)
+
+        offset = SZ4*(\i & 0xf)
+        vmovdqu \_T1,offset(%rsp)
+        vpaddq  (TBL,ROUND,1), \_T1, \_T1       # T1 = W + K
+        vpxor   e,a0, a0        # sig1: a0 = e ^ (e >> 5)
+        PRORQ   a0, 14           # sig1: a0 = (e >> 6) ^ (e >> 11)
+        vpaddq  a2, h, h        # h = h + ch
+        PRORQ_nd        a2,a,6  # sig0: a2 = (a >> 11)
+        vpaddq  \_T1,h, h       # h = h + ch + W + K
+        vpxor   a1, a0, a0      # a0 = sigma1
+	vmovdqu a,\_T1
+        PRORQ_nd        a1,a,39 # sig0: a1 = (a >> 22)
+        vpxor   c, \_T1, \_T1      # maj: T1 = a^c
+        add     $SZ4, ROUND     # ROUND++
+        vpand   b, \_T1, \_T1   # maj: T1 = (a^c)&b
+        vpaddq  a0, h, h
+        vpaddq  h, d, d
+        vpxor   a, a2, a2       # sig0: a2 = a ^ (a >> 11)
+        PRORQ   a2,28            # sig0: a2 = (a >> 2) ^ (a >> 13)
+        vpxor   a1, a2, a2      # a2 = sig0
+        vpand   c, a, a1        # maj: a1 = a&c
+        vpor    \_T1, a1, a1    # a1 = maj
+        vpaddq  a1, h, h        # h = h + ch + W + K + maj
+        vpaddq  a2, h, h        # h = h + ch + W + K + maj + sigma0
+        ROTATE_ARGS
+.endm
+
+
+#; arguments passed implicitly in preprocessor symbols i, a...h
+.macro ROUND_16_XX _T1 i
+	vmovdqu SZ4*((\i-15)&0xf)(%rsp), \_T1
+        vmovdqu SZ4*((\i-2)&0xf)(%rsp), a1
+        vmovdqu \_T1, a0
+        PRORQ   \_T1,7
+        vmovdqu a1, a2
+        PRORQ   a1,42
+        vpxor   a0, \_T1, \_T1
+        PRORQ   \_T1, 1
+        vpxor   a2, a1, a1
+        PRORQ   a1, 19
+        vpsrlq  $7, a0, a0
+        vpxor   a0, \_T1, \_T1
+        vpsrlq  $6, a2, a2
+        vpxor   a2, a1, a1
+        vpaddq  SZ4*((\i-16)&0xf)(%rsp), \_T1, \_T1
+        vpaddq  SZ4*((\i-7)&0xf)(%rsp), a1, a1
+        vpaddq  a1, \_T1, \_T1
+
+        ROUND_00_15 \_T1,\i
+.endm
+
+
+# void sha512_x4_avx2(void *STATE, const int INP_SIZE)
+# arg 1 : STATE    : pointer to input data
+# arg 2 : INP_SIZE : size of data in blocks (assumed >= 1)
+ENTRY(sha512_x4_avx2)
+	# general registers preserved in outer calling routine
+	# outer calling routine saves all the XMM registers
+	# save callee-saved clobbered registers to comply with C function ABI
+	push    %r12
+	push    %r13
+	push    %r14
+	push    %r15
+
+	sub     $STACK_SPACE1, %rsp
+
+        # Load the pre-transposed incoming digest.
+        vmovdqu 0*SHA512_DIGEST_ROW_SIZE(STATE),a
+        vmovdqu 1*SHA512_DIGEST_ROW_SIZE(STATE),b
+        vmovdqu 2*SHA512_DIGEST_ROW_SIZE(STATE),c
+        vmovdqu 3*SHA512_DIGEST_ROW_SIZE(STATE),d
+        vmovdqu 4*SHA512_DIGEST_ROW_SIZE(STATE),e
+        vmovdqu 5*SHA512_DIGEST_ROW_SIZE(STATE),f
+        vmovdqu 6*SHA512_DIGEST_ROW_SIZE(STATE),g
+        vmovdqu 7*SHA512_DIGEST_ROW_SIZE(STATE),h
+
+        lea     K512_4(%rip),TBL
+
+        # load the address of each of the 4 message lanes
+        # getting ready to transpose input onto stack
+        mov     _data_ptr+0*PTR_SZ(STATE),inp0
+        mov     _data_ptr+1*PTR_SZ(STATE),inp1
+        mov     _data_ptr+2*PTR_SZ(STATE),inp2
+        mov     _data_ptr+3*PTR_SZ(STATE),inp3
+
+        xor     IDX, IDX
+lloop:
+        xor     ROUND, ROUND
+
+	# save old digest
+        vmovdqu a, _digest(%rsp)
+        vmovdqu b, _digest+1*SZ4(%rsp)
+        vmovdqu c, _digest+2*SZ4(%rsp)
+        vmovdqu d, _digest+3*SZ4(%rsp)
+        vmovdqu e, _digest+4*SZ4(%rsp)
+        vmovdqu f, _digest+5*SZ4(%rsp)
+        vmovdqu g, _digest+6*SZ4(%rsp)
+        vmovdqu h, _digest+7*SZ4(%rsp)
+        i = 0
+.rep 4
+	vmovdqu PSHUFFLE_BYTE_FLIP_MASK(%rip), TMP
+        VMOVPD  i*32(inp0, IDX), TT2
+        VMOVPD  i*32(inp1, IDX), TT1
+        VMOVPD  i*32(inp2, IDX), TT4
+        VMOVPD  i*32(inp3, IDX), TT3
+	TRANSPOSE	TT2, TT1, TT4, TT3, TT0, TT5
+	vpshufb	TMP, TT0, TT0
+	vpshufb	TMP, TT1, TT1
+	vpshufb	TMP, TT2, TT2
+	vpshufb	TMP, TT3, TT3
+	ROUND_00_15	TT0,(i*4+0)
+	ROUND_00_15	TT1,(i*4+1)
+	ROUND_00_15	TT2,(i*4+2)
+	ROUND_00_15	TT3,(i*4+3)
+	i = (i+1)
+.endr
+        add     $128, IDX
+
+        i = (i*4)
+
+        jmp     Lrounds_16_xx
+.align 16
+Lrounds_16_xx:
+.rep 16
+        ROUND_16_XX     T1, i
+        i = (i+1)
+.endr
+        cmp     $0xa00,ROUND
+        jb      Lrounds_16_xx
+
+	# add old digest
+        vpaddq  _digest(%rsp), a, a
+        vpaddq  _digest+1*SZ4(%rsp), b, b
+        vpaddq  _digest+2*SZ4(%rsp), c, c
+        vpaddq  _digest+3*SZ4(%rsp), d, d
+        vpaddq  _digest+4*SZ4(%rsp), e, e
+        vpaddq  _digest+5*SZ4(%rsp), f, f
+        vpaddq  _digest+6*SZ4(%rsp), g, g
+        vpaddq  _digest+7*SZ4(%rsp), h, h
+
+        sub     $1, INP_SIZE  # unit is blocks
+        jne     lloop
+
+        # write back to memory (state object) the transposed digest
+        vmovdqu a, 0*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu b, 1*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu c, 2*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu d, 3*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu e, 4*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu f, 5*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu g, 6*SHA512_DIGEST_ROW_SIZE(STATE)
+        vmovdqu h, 7*SHA512_DIGEST_ROW_SIZE(STATE)
+
+	# update input data pointers
+	add     IDX, inp0
+        mov     inp0, _data_ptr+0*PTR_SZ(STATE)
+        add     IDX, inp1
+        mov     inp1, _data_ptr+1*PTR_SZ(STATE)
+        add     IDX, inp2
+        mov     inp2, _data_ptr+2*PTR_SZ(STATE)
+        add     IDX, inp3
+        mov     inp3, _data_ptr+3*PTR_SZ(STATE)
+
+	#;;;;;;;;;;;;;;;
+	#; Postamble
+	add $STACK_SPACE1, %rsp
+	# restore callee-saved clobbered registers
+
+	pop     %r15
+	pop     %r14
+	pop     %r13
+	pop     %r12
+
+	# outer calling routine restores XMM and other GP registers
+	ret
+ENDPROC(sha512_x4_avx2)
+
+.data
+.align 64
+K512_4:
+	.octa 0x428a2f98d728ae22428a2f98d728ae22,\
+		0x428a2f98d728ae22428a2f98d728ae22
+	.octa 0x7137449123ef65cd7137449123ef65cd,\
+		0x7137449123ef65cd7137449123ef65cd
+	.octa 0xb5c0fbcfec4d3b2fb5c0fbcfec4d3b2f,\
+		0xb5c0fbcfec4d3b2fb5c0fbcfec4d3b2f
+	.octa 0xe9b5dba58189dbbce9b5dba58189dbbc,\
+		0xe9b5dba58189dbbce9b5dba58189dbbc
+	.octa 0x3956c25bf348b5383956c25bf348b538,\
+		0x3956c25bf348b5383956c25bf348b538
+	.octa 0x59f111f1b605d01959f111f1b605d019,\
+		0x59f111f1b605d01959f111f1b605d019
+	.octa 0x923f82a4af194f9b923f82a4af194f9b,\
+		0x923f82a4af194f9b923f82a4af194f9b
+	.octa 0xab1c5ed5da6d8118ab1c5ed5da6d8118,\
+		0xab1c5ed5da6d8118ab1c5ed5da6d8118
+	.octa 0xd807aa98a3030242d807aa98a3030242,\
+		0xd807aa98a3030242d807aa98a3030242
+	.octa 0x12835b0145706fbe12835b0145706fbe,\
+		0x12835b0145706fbe12835b0145706fbe
+	.octa 0x243185be4ee4b28c243185be4ee4b28c,\
+		0x243185be4ee4b28c243185be4ee4b28c
+	.octa 0x550c7dc3d5ffb4e2550c7dc3d5ffb4e2,\
+		0x550c7dc3d5ffb4e2550c7dc3d5ffb4e2
+	.octa 0x72be5d74f27b896f72be5d74f27b896f,\
+		0x72be5d74f27b896f72be5d74f27b896f
+	.octa 0x80deb1fe3b1696b180deb1fe3b1696b1,\
+		0x80deb1fe3b1696b180deb1fe3b1696b1
+	.octa 0x9bdc06a725c712359bdc06a725c71235,\
+		0x9bdc06a725c712359bdc06a725c71235
+	.octa 0xc19bf174cf692694c19bf174cf692694,\
+		0xc19bf174cf692694c19bf174cf692694
+	.octa 0xe49b69c19ef14ad2e49b69c19ef14ad2,\
+		0xe49b69c19ef14ad2e49b69c19ef14ad2
+	.octa 0xefbe4786384f25e3efbe4786384f25e3,\
+		0xefbe4786384f25e3efbe4786384f25e3
+	.octa 0x0fc19dc68b8cd5b50fc19dc68b8cd5b5,\
+		0x0fc19dc68b8cd5b50fc19dc68b8cd5b5
+	.octa 0x240ca1cc77ac9c65240ca1cc77ac9c65,\
+		0x240ca1cc77ac9c65240ca1cc77ac9c65
+	.octa 0x2de92c6f592b02752de92c6f592b0275,\
+		0x2de92c6f592b02752de92c6f592b0275
+	.octa 0x4a7484aa6ea6e4834a7484aa6ea6e483,\
+		0x4a7484aa6ea6e4834a7484aa6ea6e483
+	.octa 0x5cb0a9dcbd41fbd45cb0a9dcbd41fbd4,\
+		0x5cb0a9dcbd41fbd45cb0a9dcbd41fbd4
+	.octa 0x76f988da831153b576f988da831153b5,\
+		0x76f988da831153b576f988da831153b5
+	.octa 0x983e5152ee66dfab983e5152ee66dfab,\
+		0x983e5152ee66dfab983e5152ee66dfab
+	.octa 0xa831c66d2db43210a831c66d2db43210,\
+		0xa831c66d2db43210a831c66d2db43210
+	.octa 0xb00327c898fb213fb00327c898fb213f,\
+		0xb00327c898fb213fb00327c898fb213f
+	.octa 0xbf597fc7beef0ee4bf597fc7beef0ee4,\
+		0xbf597fc7beef0ee4bf597fc7beef0ee4
+	.octa 0xc6e00bf33da88fc2c6e00bf33da88fc2,\
+		0xc6e00bf33da88fc2c6e00bf33da88fc2
+	.octa 0xd5a79147930aa725d5a79147930aa725,\
+		0xd5a79147930aa725d5a79147930aa725
+	.octa 0x06ca6351e003826f06ca6351e003826f,\
+		0x06ca6351e003826f06ca6351e003826f
+	.octa 0x142929670a0e6e70142929670a0e6e70,\
+		0x142929670a0e6e70142929670a0e6e70
+	.octa 0x27b70a8546d22ffc27b70a8546d22ffc,\
+		0x27b70a8546d22ffc27b70a8546d22ffc
+	.octa 0x2e1b21385c26c9262e1b21385c26c926,\
+		0x2e1b21385c26c9262e1b21385c26c926
+	.octa 0x4d2c6dfc5ac42aed4d2c6dfc5ac42aed,\
+		0x4d2c6dfc5ac42aed4d2c6dfc5ac42aed
+	.octa 0x53380d139d95b3df53380d139d95b3df,\
+		0x53380d139d95b3df53380d139d95b3df
+	.octa 0x650a73548baf63de650a73548baf63de,\
+		0x650a73548baf63de650a73548baf63de
+	.octa 0x766a0abb3c77b2a8766a0abb3c77b2a8,\
+		0x766a0abb3c77b2a8766a0abb3c77b2a8
+	.octa 0x81c2c92e47edaee681c2c92e47edaee6,\
+		0x81c2c92e47edaee681c2c92e47edaee6
+	.octa 0x92722c851482353b92722c851482353b,\
+		0x92722c851482353b92722c851482353b
+	.octa 0xa2bfe8a14cf10364a2bfe8a14cf10364,\
+		0xa2bfe8a14cf10364a2bfe8a14cf10364
+	.octa 0xa81a664bbc423001a81a664bbc423001,\
+		0xa81a664bbc423001a81a664bbc423001
+	.octa 0xc24b8b70d0f89791c24b8b70d0f89791,\
+		0xc24b8b70d0f89791c24b8b70d0f89791
+	.octa 0xc76c51a30654be30c76c51a30654be30,\
+		0xc76c51a30654be30c76c51a30654be30
+	.octa 0xd192e819d6ef5218d192e819d6ef5218,\
+		0xd192e819d6ef5218d192e819d6ef5218
+	.octa 0xd69906245565a910d69906245565a910,\
+		0xd69906245565a910d69906245565a910
+	.octa 0xf40e35855771202af40e35855771202a,\
+		0xf40e35855771202af40e35855771202a
+	.octa 0x106aa07032bbd1b8106aa07032bbd1b8,\
+		0x106aa07032bbd1b8106aa07032bbd1b8
+	.octa 0x19a4c116b8d2d0c819a4c116b8d2d0c8,\
+		0x19a4c116b8d2d0c819a4c116b8d2d0c8
+	.octa 0x1e376c085141ab531e376c085141ab53,\
+		0x1e376c085141ab531e376c085141ab53
+	.octa 0x2748774cdf8eeb992748774cdf8eeb99,\
+		0x2748774cdf8eeb992748774cdf8eeb99
+	.octa 0x34b0bcb5e19b48a834b0bcb5e19b48a8,\
+		0x34b0bcb5e19b48a834b0bcb5e19b48a8
+	.octa 0x391c0cb3c5c95a63391c0cb3c5c95a63,\
+		0x391c0cb3c5c95a63391c0cb3c5c95a63
+	.octa 0x4ed8aa4ae3418acb4ed8aa4ae3418acb,\
+		0x4ed8aa4ae3418acb4ed8aa4ae3418acb
+	.octa 0x5b9cca4f7763e3735b9cca4f7763e373,\
+		0x5b9cca4f7763e3735b9cca4f7763e373
+	.octa 0x682e6ff3d6b2b8a3682e6ff3d6b2b8a3,\
+		0x682e6ff3d6b2b8a3682e6ff3d6b2b8a3
+	.octa 0x748f82ee5defb2fc748f82ee5defb2fc,\
+		0x748f82ee5defb2fc748f82ee5defb2fc
+	.octa 0x78a5636f43172f6078a5636f43172f60,\
+		0x78a5636f43172f6078a5636f43172f60
+	.octa 0x84c87814a1f0ab7284c87814a1f0ab72,\
+		0x84c87814a1f0ab7284c87814a1f0ab72
+	.octa 0x8cc702081a6439ec8cc702081a6439ec,\
+		0x8cc702081a6439ec8cc702081a6439ec
+	.octa 0x90befffa23631e2890befffa23631e28,\
+		0x90befffa23631e2890befffa23631e28
+	.octa 0xa4506cebde82bde9a4506cebde82bde9,\
+		0xa4506cebde82bde9a4506cebde82bde9
+	.octa 0xbef9a3f7b2c67915bef9a3f7b2c67915,\
+		0xbef9a3f7b2c67915bef9a3f7b2c67915
+	.octa 0xc67178f2e372532bc67178f2e372532b,\
+		0xc67178f2e372532bc67178f2e372532b
+	.octa 0xca273eceea26619cca273eceea26619c,\
+		0xca273eceea26619cca273eceea26619c
+	.octa 0xd186b8c721c0c207d186b8c721c0c207,\
+		0xd186b8c721c0c207d186b8c721c0c207
+	.octa 0xeada7dd6cde0eb1eeada7dd6cde0eb1e,\
+		0xeada7dd6cde0eb1eeada7dd6cde0eb1e
+	.octa 0xf57d4f7fee6ed178f57d4f7fee6ed178,\
+		0xf57d4f7fee6ed178f57d4f7fee6ed178
+	.octa 0x06f067aa72176fba06f067aa72176fba,\
+		0x06f067aa72176fba06f067aa72176fba
+	.octa 0x0a637dc5a2c898a60a637dc5a2c898a6,\
+		0x0a637dc5a2c898a60a637dc5a2c898a6
+	.octa 0x113f9804bef90dae113f9804bef90dae,\
+		0x113f9804bef90dae113f9804bef90dae
+	.octa 0x1b710b35131c471b1b710b35131c471b,\
+		0x1b710b35131c471b1b710b35131c471b
+	.octa 0x28db77f523047d8428db77f523047d84,\
+		0x28db77f523047d8428db77f523047d84
+	.octa 0x32caab7b40c7249332caab7b40c72493,\
+		0x32caab7b40c7249332caab7b40c72493
+	.octa 0x3c9ebe0a15c9bebc3c9ebe0a15c9bebc,\
+		0x3c9ebe0a15c9bebc3c9ebe0a15c9bebc
+	.octa 0x431d67c49c100d4c431d67c49c100d4c,\
+		0x431d67c49c100d4c431d67c49c100d4c
+	.octa 0x4cc5d4becb3e42b64cc5d4becb3e42b6,\
+		0x4cc5d4becb3e42b64cc5d4becb3e42b6
+	.octa 0x597f299cfc657e2a597f299cfc657e2a,\
+		0x597f299cfc657e2a597f299cfc657e2a
+	.octa 0x5fcb6fab3ad6faec5fcb6fab3ad6faec,\
+		0x5fcb6fab3ad6faec5fcb6fab3ad6faec
+	.octa 0x6c44198c4a4758176c44198c4a475817,\
+		0x6c44198c4a4758176c44198c4a475817
+
+PSHUFFLE_BYTE_FLIP_MASK: .octa 0x08090a0b0c0d0e0f0001020304050607
+                         .octa 0x18191a1b1c1d1e1f1011121314151617
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 0b17c83..2b0e2a6 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -346,4 +346,10 @@
 MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
 
 MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha512-ssse3");
+MODULE_ALIAS_CRYPTO("sha512-avx");
+MODULE_ALIAS_CRYPTO("sha512-avx2");
 MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha384-ssse3");
+MODULE_ALIAS_CRYPTO("sha384-avx");
+MODULE_ALIAS_CRYPTO("sha384-avx2");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 1d33beb..a9377be 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -93,6 +93,15 @@
 	select CRYPTO_AKCIPHER2
 	select CRYPTO_ALGAPI
 
+config CRYPTO_KPP2
+	tristate
+	select CRYPTO_ALGAPI2
+
+config CRYPTO_KPP
+	tristate
+	select CRYPTO_ALGAPI
+	select CRYPTO_KPP2
+
 config CRYPTO_RSA
 	tristate "RSA algorithm"
 	select CRYPTO_AKCIPHER
@@ -102,6 +111,19 @@
 	help
 	  Generic implementation of the RSA public key algorithm.
 
+config CRYPTO_DH
+	tristate "Diffie-Hellman algorithm"
+	select CRYPTO_KPP
+	select MPILIB
+	help
+	  Generic implementation of the Diffie-Hellman algorithm.
+
+config CRYPTO_ECDH
+	tristate "ECDH algorithm"
+	select CRYTPO_KPP
+	help
+	  Generic implementation of the ECDH algorithm
+
 config CRYPTO_MANAGER
 	tristate "Cryptographic algorithm manager"
 	select CRYPTO_MANAGER2
@@ -115,6 +137,7 @@
 	select CRYPTO_HASH2
 	select CRYPTO_BLKCIPHER2
 	select CRYPTO_AKCIPHER2
+	select CRYPTO_KPP2
 
 config CRYPTO_USER
 	tristate "Userspace cryptographic algorithm configuration"
@@ -414,6 +437,17 @@
 	  gain performance compared with software implementation.
 	  Module will be crc32c-intel.
 
+config CRYPT_CRC32C_VPMSUM
+	tristate "CRC32c CRC algorithm (powerpc64)"
+	depends on PPC64
+	select CRYPTO_HASH
+	select CRC32
+	help
+	  CRC32c algorithm implemented using vector polynomial multiply-sum
+	  (vpmsum) instructions, introduced in POWER8. Enable on POWER8
+	  and newer processors for improved performance.
+
+
 config CRYPTO_CRC32C_SPARC64
 	tristate "CRC32c CRC algorithm (SPARC64)"
 	depends on SPARC64
@@ -681,6 +715,38 @@
 	  lanes remain unfilled, a flush operation will be initiated to
 	  process the crypto jobs, adding a slight latency.
 
+config CRYPTO_SHA256_MB
+	tristate "SHA256 digest algorithm (x86_64 Multi-Buffer, Experimental)"
+	depends on X86 && 64BIT
+	select CRYPTO_SHA256
+	select CRYPTO_HASH
+	select CRYPTO_MCRYPTD
+	help
+	  SHA-256 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
+	  using multi-buffer technique.  This algorithm computes on
+	  multiple data lanes concurrently with SIMD instructions for
+	  better throughput.  It should not be enabled by default but
+	  used when there is significant amount of work to keep the keep
+	  the data lanes filled to get performance benefit.  If the data
+	  lanes remain unfilled, a flush operation will be initiated to
+	  process the crypto jobs, adding a slight latency.
+
+config CRYPTO_SHA512_MB
+        tristate "SHA512 digest algorithm (x86_64 Multi-Buffer, Experimental)"
+        depends on X86 && 64BIT
+        select CRYPTO_SHA512
+        select CRYPTO_HASH
+        select CRYPTO_MCRYPTD
+        help
+          SHA-512 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
+          using multi-buffer technique.  This algorithm computes on
+          multiple data lanes concurrently with SIMD instructions for
+          better throughput.  It should not be enabled by default but
+          used when there is significant amount of work to keep the keep
+          the data lanes filled to get performance benefit.  If the data
+          lanes remain unfilled, a flush operation will be initiated to
+          process the crypto jobs, adding a slight latency.
+
 config CRYPTO_SHA256
 	tristate "SHA224 and SHA256 digest algorithm"
 	select CRYPTO_HASH
@@ -750,6 +816,16 @@
 	  SHA-512 secure hash standard (DFIPS 180-2) implemented
 	  using sparc64 crypto instructions, when available.
 
+config CRYPTO_SHA3
+	tristate "SHA3 digest algorithm"
+	select CRYPTO_HASH
+	help
+	  SHA-3 secure hash standard (DFIPS 202). It's based on
+	  cryptographic sponge function family called Keccak.
+
+	  References:
+	  http://keccak.noekeon.org/
+
 config CRYPTO_TGR192
 	tristate "Tiger digest algorithms"
 	select CRYPTO_HASH
@@ -1567,6 +1643,7 @@
 config CRYPTO_DRBG_CTR
 	bool "Enable CTR DRBG"
 	select CRYPTO_AES
+	depends on CRYPTO_CTR
 	help
 	  Enable the CTR DRBG variant as defined in NIST SP800-90A.
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 4f4ef7e..99cc64a 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -20,8 +20,6 @@
 crypto_blkcipher-y += blkcipher.o
 crypto_blkcipher-y += skcipher.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o
-obj-$(CONFIG_CRYPTO_BLKCIPHER2) += chainiv.o
-obj-$(CONFIG_CRYPTO_BLKCIPHER2) += eseqiv.o
 obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o
 obj-$(CONFIG_CRYPTO_ECHAINIV) += echainiv.o
 
@@ -30,6 +28,15 @@
 obj-$(CONFIG_CRYPTO_HASH2) += crypto_hash.o
 
 obj-$(CONFIG_CRYPTO_AKCIPHER2) += akcipher.o
+obj-$(CONFIG_CRYPTO_KPP2) += kpp.o
+
+dh_generic-y := dh.o
+dh_generic-y += dh_helper.o
+obj-$(CONFIG_CRYPTO_DH) += dh_generic.o
+ecdh_generic-y := ecc.o
+ecdh_generic-y += ecdh.o
+ecdh_generic-y += ecdh_helper.o
+obj-$(CONFIG_CRYPTO_ECDH) += ecdh_generic.o
 
 $(obj)/rsapubkey-asn1.o: $(obj)/rsapubkey-asn1.c $(obj)/rsapubkey-asn1.h
 $(obj)/rsaprivkey-asn1.o: $(obj)/rsaprivkey-asn1.c $(obj)/rsaprivkey-asn1.h
@@ -61,6 +68,7 @@
 obj-$(CONFIG_CRYPTO_SHA1) += sha1_generic.o
 obj-$(CONFIG_CRYPTO_SHA256) += sha256_generic.o
 obj-$(CONFIG_CRYPTO_SHA512) += sha512_generic.o
+obj-$(CONFIG_CRYPTO_SHA3) += sha3_generic.o
 obj-$(CONFIG_CRYPTO_WP512) += wp512.o
 obj-$(CONFIG_CRYPTO_TGR192) += tgr192.o
 obj-$(CONFIG_CRYPTO_GF128MUL) += gf128mul.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
index e1fcf53..1441f07 100644
--- a/crypto/ablk_helper.c
+++ b/crypto/ablk_helper.c
@@ -71,7 +71,8 @@
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ablkcipher_queued(ctx->cryptd_tfm))) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 
@@ -90,7 +91,8 @@
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ablkcipher_queued(ctx->cryptd_tfm))) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index e5b5721..d676fc5 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -14,11 +14,8 @@
  */
 
 #include <crypto/internal/skcipher.h>
-#include <linux/cpumask.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
-#include <linux/rtnetlink.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/cryptouser.h>
@@ -349,16 +346,6 @@
 	return alg->cra_ctxsize;
 }
 
-int skcipher_null_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	return crypto_ablkcipher_encrypt(&req->creq);
-}
-
-int skcipher_null_givdecrypt(struct skcipher_givcrypt_request *req)
-{
-	return crypto_ablkcipher_decrypt(&req->creq);
-}
-
 static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type,
 				      u32 mask)
 {
@@ -371,10 +358,6 @@
 	crt->setkey = setkey;
 	crt->encrypt = alg->encrypt;
 	crt->decrypt = alg->decrypt;
-	if (!alg->ivsize) {
-		crt->givencrypt = skcipher_null_givencrypt;
-		crt->givdecrypt = skcipher_null_givdecrypt;
-	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
 
@@ -436,11 +419,6 @@
 };
 EXPORT_SYMBOL_GPL(crypto_ablkcipher_type);
 
-static int no_givdecrypt(struct skcipher_givcrypt_request *req)
-{
-	return -ENOSYS;
-}
-
 static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 				      u32 mask)
 {
@@ -454,8 +432,6 @@
 		      alg->setkey : setkey;
 	crt->encrypt = alg->encrypt;
 	crt->decrypt = alg->decrypt;
-	crt->givencrypt = alg->givencrypt ?: no_givdecrypt;
-	crt->givdecrypt = alg->givdecrypt ?: no_givdecrypt;
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
 
@@ -516,202 +492,3 @@
 	.report = crypto_givcipher_report,
 };
 EXPORT_SYMBOL_GPL(crypto_givcipher_type);
-
-const char *crypto_default_geniv(const struct crypto_alg *alg)
-{
-	if (((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	     CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					 alg->cra_ablkcipher.ivsize) !=
-	    alg->cra_blocksize)
-		return "chainiv";
-
-	return "eseqiv";
-}
-
-static int crypto_givcipher_default(struct crypto_alg *alg, u32 type, u32 mask)
-{
-	struct rtattr *tb[3];
-	struct {
-		struct rtattr attr;
-		struct crypto_attr_type data;
-	} ptype;
-	struct {
-		struct rtattr attr;
-		struct crypto_attr_alg data;
-	} palg;
-	struct crypto_template *tmpl;
-	struct crypto_instance *inst;
-	struct crypto_alg *larval;
-	const char *geniv;
-	int err;
-
-	larval = crypto_larval_lookup(alg->cra_driver_name,
-				      (type & ~CRYPTO_ALG_TYPE_MASK) |
-				      CRYPTO_ALG_TYPE_GIVCIPHER,
-				      mask | CRYPTO_ALG_TYPE_MASK);
-	err = PTR_ERR(larval);
-	if (IS_ERR(larval))
-		goto out;
-
-	err = -EAGAIN;
-	if (!crypto_is_larval(larval))
-		goto drop_larval;
-
-	ptype.attr.rta_len = sizeof(ptype);
-	ptype.attr.rta_type = CRYPTOA_TYPE;
-	ptype.data.type = type | CRYPTO_ALG_GENIV;
-	/* GENIV tells the template that we're making a default geniv. */
-	ptype.data.mask = mask | CRYPTO_ALG_GENIV;
-	tb[0] = &ptype.attr;
-
-	palg.attr.rta_len = sizeof(palg);
-	palg.attr.rta_type = CRYPTOA_ALG;
-	/* Must use the exact name to locate ourselves. */
-	memcpy(palg.data.name, alg->cra_driver_name, CRYPTO_MAX_ALG_NAME);
-	tb[1] = &palg.attr;
-
-	tb[2] = NULL;
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER)
-		geniv = alg->cra_blkcipher.geniv;
-	else
-		geniv = alg->cra_ablkcipher.geniv;
-
-	if (!geniv)
-		geniv = crypto_default_geniv(alg);
-
-	tmpl = crypto_lookup_template(geniv);
-	err = -ENOENT;
-	if (!tmpl)
-		goto kill_larval;
-
-	if (tmpl->create) {
-		err = tmpl->create(tmpl, tb);
-		if (err)
-			goto put_tmpl;
-		goto ok;
-	}
-
-	inst = tmpl->alloc(tb);
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto put_tmpl;
-
-	err = crypto_register_instance(tmpl, inst);
-	if (err) {
-		tmpl->free(inst);
-		goto put_tmpl;
-	}
-
-ok:
-	/* Redo the lookup to use the instance we just registered. */
-	err = -EAGAIN;
-
-put_tmpl:
-	crypto_tmpl_put(tmpl);
-kill_larval:
-	crypto_larval_kill(larval);
-drop_larval:
-	crypto_mod_put(larval);
-out:
-	crypto_mod_put(alg);
-	return err;
-}
-
-struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask)
-{
-	struct crypto_alg *alg;
-
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return alg;
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_GIVCIPHER)
-		return alg;
-
-	if (!((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	      CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					  alg->cra_ablkcipher.ivsize))
-		return alg;
-
-	crypto_mod_put(alg);
-	alg = crypto_alg_mod_lookup(name, type | CRYPTO_ALG_TESTED,
-				    mask & ~CRYPTO_ALG_TESTED);
-	if (IS_ERR(alg))
-		return alg;
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_GIVCIPHER) {
-		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
-			crypto_mod_put(alg);
-			alg = ERR_PTR(-ENOENT);
-		}
-		return alg;
-	}
-
-	BUG_ON(!((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-		 CRYPTO_ALG_TYPE_BLKCIPHER ? alg->cra_blkcipher.ivsize :
-					     alg->cra_ablkcipher.ivsize));
-
-	return ERR_PTR(crypto_givcipher_default(alg, type, mask));
-}
-EXPORT_SYMBOL_GPL(crypto_lookup_skcipher);
-
-int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
-			 u32 type, u32 mask)
-{
-	struct crypto_alg *alg;
-	int err;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask);
-
-	alg = crypto_lookup_skcipher(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
-
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
-	return err;
-}
-EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
-
-struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name,
-						  u32 type, u32 mask)
-{
-	struct crypto_tfm *tfm;
-	int err;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask);
-
-	for (;;) {
-		struct crypto_alg *alg;
-
-		alg = crypto_lookup_skcipher(alg_name, type, mask);
-		if (IS_ERR(alg)) {
-			err = PTR_ERR(alg);
-			goto err;
-		}
-
-		tfm = __crypto_alloc_tfm(alg, type, mask);
-		if (!IS_ERR(tfm))
-			return __crypto_ablkcipher_cast(tfm);
-
-		crypto_mod_put(alg);
-		err = PTR_ERR(tfm);
-
-err:
-		if (err != -EAGAIN)
-			break;
-		if (fatal_signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
-
-	return ERR_PTR(err);
-}
-EXPORT_SYMBOL_GPL(crypto_alloc_ablkcipher);
diff --git a/crypto/aead.c b/crypto/aead.c
index 9b18a1e..3f5c5ff 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -294,9 +294,9 @@
 	if (err)
 		goto out;
 
-	ctx->null = crypto_get_default_null_skcipher();
-	err = PTR_ERR(ctx->null);
-	if (IS_ERR(ctx->null))
+	ctx->sknull = crypto_get_default_null_skcipher2();
+	err = PTR_ERR(ctx->sknull);
+	if (IS_ERR(ctx->sknull))
 		goto out;
 
 	child = crypto_spawn_aead(aead_instance_ctx(inst));
@@ -314,7 +314,7 @@
 	return err;
 
 drop_null:
-	crypto_put_default_null_skcipher();
+	crypto_put_default_null_skcipher2();
 	goto out;
 }
 EXPORT_SYMBOL_GPL(aead_init_geniv);
@@ -324,7 +324,7 @@
 	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher();
+	crypto_put_default_null_skcipher2();
 }
 EXPORT_SYMBOL_GPL(aead_exit_geniv);
 
@@ -346,9 +346,13 @@
 {
 	struct crypto_alg *base = &alg->base;
 
-	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
+	if (max3(alg->maxauthsize, alg->ivsize, alg->chunksize) >
+	    PAGE_SIZE / 8)
 		return -EINVAL;
 
+	if (!alg->chunksize)
+		alg->chunksize = base->cra_blocksize;
+
 	base->cra_type = &crypto_aead_type;
 	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
 	base->cra_flags |= CRYPTO_ALG_TYPE_AEAD;
diff --git a/crypto/ahash.c b/crypto/ahash.c
index 3887a98..2ce8bcb 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -461,10 +461,10 @@
 
 static unsigned int crypto_ahash_extsize(struct crypto_alg *alg)
 {
-	if (alg->cra_type == &crypto_ahash_type)
-		return alg->cra_ctxsize;
+	if (alg->cra_type != &crypto_ahash_type)
+		return sizeof(struct crypto_shash *);
 
-	return sizeof(struct crypto_shash *);
+	return crypto_alg_extsize(alg);
 }
 
 #ifdef CONFIG_NET
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 731255a..df939b5 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -811,6 +811,21 @@
 }
 EXPORT_SYMBOL_GPL(crypto_attr_u32);
 
+int crypto_inst_setname(struct crypto_instance *inst, const char *name,
+			struct crypto_alg *alg)
+{
+	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", name,
+		     alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
+		     name, alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_inst_setname);
+
 void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg,
 			     unsigned int head)
 {
@@ -825,13 +840,8 @@
 
 	inst = (void *)(p + head);
 
-	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", name,
-		     alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
-		goto err_free_inst;
-
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
-		     name, alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+	err = crypto_inst_setname(inst, name, alg);
+	if (err)
 		goto err_free_inst;
 
 	return p;
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 55a354d..a7e1ac7 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -32,8 +32,8 @@
 
 struct crypto_authenc_ctx {
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 };
 
 struct authenc_request_ctx {
@@ -83,7 +83,7 @@
 {
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
 	struct crypto_ahash *auth = ctx->auth;
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct crypto_skcipher *enc = ctx->enc;
 	struct crypto_authenc_keys keys;
 	int err = -EINVAL;
 
@@ -100,11 +100,11 @@
 	if (err)
 		goto out;
 
-	crypto_ablkcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(enc, crypto_aead_get_flags(authenc) &
-					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(enc, keys.enckey, keys.enckeylen);
-	crypto_aead_set_flags(authenc, crypto_ablkcipher_get_flags(enc) &
+	crypto_skcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(enc, crypto_aead_get_flags(authenc) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(enc, keys.enckey, keys.enckeylen);
+	crypto_aead_set_flags(authenc, crypto_skcipher_get_flags(enc) &
 				       CRYPTO_TFM_RES_MASK);
 
 out:
@@ -184,12 +184,15 @@
 {
 	struct crypto_aead *authenc = crypto_aead_reqtfm(req);
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
-	struct blkcipher_desc desc = {
-		.tfm = ctx->null,
-	};
+	SKCIPHER_REQUEST_ON_STACK(skreq, ctx->null);
 
-	return crypto_blkcipher_encrypt(&desc, req->dst, req->src,
-					req->assoclen);
+	skcipher_request_set_tfm(skreq, ctx->null);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      NULL, NULL);
+	skcipher_request_set_crypt(skreq, req->src, req->dst, req->assoclen,
+				   NULL);
+
+	return crypto_skcipher_encrypt(skreq);
 }
 
 static int crypto_authenc_encrypt(struct aead_request *req)
@@ -199,14 +202,13 @@
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
 	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct crypto_skcipher *enc = ctx->enc;
 	unsigned int cryptlen = req->cryptlen;
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail +
-						    ictx->reqoff);
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ictx->reqoff);
 	struct scatterlist *src, *dst;
 	int err;
 
-	sg_init_table(areq_ctx->src, 2);
 	src = scatterwalk_ffwd(areq_ctx->src, req->src, req->assoclen);
 	dst = src;
 
@@ -215,16 +217,15 @@
 		if (err)
 			return err;
 
-		sg_init_table(areq_ctx->dst, 2);
 		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, req->assoclen);
 	}
 
-	ablkcipher_request_set_tfm(abreq, enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					crypto_authenc_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, src, dst, cryptlen, req->iv);
+	skcipher_request_set_tfm(skreq, enc);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      crypto_authenc_encrypt_done, req);
+	skcipher_request_set_crypt(skreq, src, dst, cryptlen, req->iv);
 
-	err = crypto_ablkcipher_encrypt(abreq);
+	err = crypto_skcipher_encrypt(skreq);
 	if (err)
 		return err;
 
@@ -240,8 +241,8 @@
 	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct authenc_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct ahash_request *ahreq = (void *)(areq_ctx->tail + ictx->reqoff);
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail +
-						    ictx->reqoff);
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ictx->reqoff);
 	unsigned int authsize = crypto_aead_authsize(authenc);
 	u8 *ihash = ahreq->result + authsize;
 	struct scatterlist *src, *dst;
@@ -251,22 +252,19 @@
 	if (crypto_memneq(ihash, ahreq->result, authsize))
 		return -EBADMSG;
 
-	sg_init_table(areq_ctx->src, 2);
 	src = scatterwalk_ffwd(areq_ctx->src, req->src, req->assoclen);
 	dst = src;
 
-	if (req->src != req->dst) {
-		sg_init_table(areq_ctx->dst, 2);
+	if (req->src != req->dst)
 		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, req->assoclen);
-	}
 
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, src, dst,
-				     req->cryptlen - authsize, req->iv);
+	skcipher_request_set_tfm(skreq, ctx->enc);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      req->base.complete, req->base.data);
+	skcipher_request_set_crypt(skreq, src, dst,
+				   req->cryptlen - authsize, req->iv);
 
-	return crypto_ablkcipher_decrypt(abreq);
+	return crypto_skcipher_decrypt(skreq);
 }
 
 static void authenc_verify_ahash_done(struct crypto_async_request *areq,
@@ -318,20 +316,20 @@
 	struct authenc_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 	int err;
 
 	auth = crypto_spawn_ahash(&ictx->auth);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
-	enc = crypto_spawn_skcipher(&ictx->enc);
+	enc = crypto_spawn_skcipher2(&ictx->enc);
 	err = PTR_ERR(enc);
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
-	null = crypto_get_default_null_skcipher();
+	null = crypto_get_default_null_skcipher2();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_skcipher;
@@ -347,13 +345,13 @@
 		max_t(unsigned int,
 		      crypto_ahash_reqsize(auth) +
 		      sizeof(struct ahash_request),
-		      sizeof(struct ablkcipher_request) +
-		      crypto_ablkcipher_reqsize(enc)));
+		      sizeof(struct skcipher_request) +
+		      crypto_skcipher_reqsize(enc)));
 
 	return 0;
 
 err_free_skcipher:
-	crypto_free_ablkcipher(enc);
+	crypto_free_skcipher(enc);
 err_free_ahash:
 	crypto_free_ahash(auth);
 	return err;
@@ -364,8 +362,8 @@
 	struct crypto_authenc_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->auth);
-	crypto_free_ablkcipher(ctx->enc);
-	crypto_put_default_null_skcipher();
+	crypto_free_skcipher(ctx->enc);
+	crypto_put_default_null_skcipher2();
 }
 
 static void crypto_authenc_free(struct aead_instance *inst)
@@ -384,7 +382,7 @@
 	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
-	struct crypto_alg *enc;
+	struct skcipher_alg *enc;
 	struct authenc_instance_ctx *ctx;
 	const char *enc_name;
 	int err;
@@ -397,7 +395,8 @@
 		return -EINVAL;
 
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK);
+			      CRYPTO_ALG_TYPE_AHASH_MASK |
+			      crypto_requires_sync(algt->type, algt->mask));
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
@@ -421,37 +420,40 @@
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->enc, enc_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_auth;
 
-	enc = crypto_skcipher_spawn_alg(&ctx->enc);
+	enc = crypto_spawn_skcipher_alg(&ctx->enc);
 
 	ctx->reqoff = ALIGN(2 * auth->digestsize + auth_base->cra_alignmask,
 			    auth_base->cra_alignmask + 1);
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "authenc(%s,%s)", auth_base->cra_name, enc->cra_name) >=
+		     "authenc(%s,%s)", auth_base->cra_name,
+		     enc->base.cra_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "authenc(%s,%s)", auth_base->cra_driver_name,
-		     enc->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		     enc->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	inst->alg.base.cra_flags = enc->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = enc->cra_priority * 10 +
+	inst->alg.base.cra_flags = (auth_base->cra_flags |
+				    enc->base.cra_flags) & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = enc->base.cra_priority * 10 +
 				      auth_base->cra_priority;
-	inst->alg.base.cra_blocksize = enc->cra_blocksize;
+	inst->alg.base.cra_blocksize = enc->base.cra_blocksize;
 	inst->alg.base.cra_alignmask = auth_base->cra_alignmask |
-				       enc->cra_alignmask;
+				       enc->base.cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_authenc_ctx);
 
-	inst->alg.ivsize = enc->cra_ablkcipher.ivsize;
+	inst->alg.ivsize = crypto_skcipher_alg_ivsize(enc);
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(enc);
 	inst->alg.maxauthsize = auth->digestsize;
 
 	inst->alg.init = crypto_authenc_init_tfm;
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 0c04688..121010a 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -35,8 +35,8 @@
 struct crypto_authenc_esn_ctx {
 	unsigned int reqoff;
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 };
 
 struct authenc_esn_request_ctx {
@@ -65,7 +65,7 @@
 {
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
 	struct crypto_ahash *auth = ctx->auth;
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct crypto_skcipher *enc = ctx->enc;
 	struct crypto_authenc_keys keys;
 	int err = -EINVAL;
 
@@ -82,11 +82,11 @@
 	if (err)
 		goto out;
 
-	crypto_ablkcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(enc, crypto_aead_get_flags(authenc_esn) &
+	crypto_skcipher_clear_flags(enc, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(enc, crypto_aead_get_flags(authenc_esn) &
 					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(enc, keys.enckey, keys.enckeylen);
-	crypto_aead_set_flags(authenc_esn, crypto_ablkcipher_get_flags(enc) &
+	err = crypto_skcipher_setkey(enc, keys.enckey, keys.enckeylen);
+	crypto_aead_set_flags(authenc_esn, crypto_skcipher_get_flags(enc) &
 					   CRYPTO_TFM_RES_MASK);
 
 out:
@@ -182,11 +182,14 @@
 {
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct blkcipher_desc desc = {
-		.tfm = ctx->null,
-	};
+	SKCIPHER_REQUEST_ON_STACK(skreq, ctx->null);
 
-	return crypto_blkcipher_encrypt(&desc, req->dst, req->src, len);
+	skcipher_request_set_tfm(skreq, ctx->null);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      NULL, NULL);
+	skcipher_request_set_crypt(skreq, req->src, req->dst, len, NULL);
+
+	return crypto_skcipher_encrypt(skreq);
 }
 
 static int crypto_authenc_esn_encrypt(struct aead_request *req)
@@ -194,9 +197,9 @@
 	struct crypto_aead *authenc_esn = crypto_aead_reqtfm(req);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-						    + ctx->reqoff);
-	struct crypto_ablkcipher *enc = ctx->enc;
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ctx->reqoff);
+	struct crypto_skcipher *enc = ctx->enc;
 	unsigned int assoclen = req->assoclen;
 	unsigned int cryptlen = req->cryptlen;
 	struct scatterlist *src, *dst;
@@ -215,12 +218,12 @@
 		dst = scatterwalk_ffwd(areq_ctx->dst, req->dst, assoclen);
 	}
 
-	ablkcipher_request_set_tfm(abreq, enc);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					crypto_authenc_esn_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, src, dst, cryptlen, req->iv);
+	skcipher_request_set_tfm(skreq, enc);
+	skcipher_request_set_callback(skreq, aead_request_flags(req),
+				      crypto_authenc_esn_encrypt_done, req);
+	skcipher_request_set_crypt(skreq, src, dst, cryptlen, req->iv);
 
-	err = crypto_ablkcipher_encrypt(abreq);
+	err = crypto_skcipher_encrypt(skreq);
 	if (err)
 		return err;
 
@@ -234,8 +237,8 @@
 	unsigned int authsize = crypto_aead_authsize(authenc_esn);
 	struct authenc_esn_request_ctx *areq_ctx = aead_request_ctx(req);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(authenc_esn);
-	struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
-						    + ctx->reqoff);
+	struct skcipher_request *skreq = (void *)(areq_ctx->tail +
+						  ctx->reqoff);
 	struct crypto_ahash *auth = ctx->auth;
 	u8 *ohash = PTR_ALIGN((u8 *)areq_ctx->tail,
 			      crypto_ahash_alignmask(auth) + 1);
@@ -256,12 +259,12 @@
 	sg_init_table(areq_ctx->dst, 2);
 	dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen);
 
-	ablkcipher_request_set_tfm(abreq, ctx->enc);
-	ablkcipher_request_set_callback(abreq, flags,
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(abreq, dst, dst, cryptlen, req->iv);
+	skcipher_request_set_tfm(skreq, ctx->enc);
+	skcipher_request_set_callback(skreq, flags,
+				      req->base.complete, req->base.data);
+	skcipher_request_set_crypt(skreq, dst, dst, cryptlen, req->iv);
 
-	return crypto_ablkcipher_decrypt(abreq);
+	return crypto_skcipher_decrypt(skreq);
 }
 
 static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
@@ -331,20 +334,20 @@
 	struct authenc_esn_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ahash *auth;
-	struct crypto_ablkcipher *enc;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *enc;
+	struct crypto_skcipher *null;
 	int err;
 
 	auth = crypto_spawn_ahash(&ictx->auth);
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
-	enc = crypto_spawn_skcipher(&ictx->enc);
+	enc = crypto_spawn_skcipher2(&ictx->enc);
 	err = PTR_ERR(enc);
 	if (IS_ERR(enc))
 		goto err_free_ahash;
 
-	null = crypto_get_default_null_skcipher();
+	null = crypto_get_default_null_skcipher2();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_skcipher;
@@ -361,15 +364,15 @@
 		sizeof(struct authenc_esn_request_ctx) +
 		ctx->reqoff +
 		max_t(unsigned int,
-			crypto_ahash_reqsize(auth) +
-			sizeof(struct ahash_request),
-			sizeof(struct skcipher_givcrypt_request) +
-			crypto_ablkcipher_reqsize(enc)));
+		      crypto_ahash_reqsize(auth) +
+		      sizeof(struct ahash_request),
+		      sizeof(struct skcipher_request) +
+		      crypto_skcipher_reqsize(enc)));
 
 	return 0;
 
 err_free_skcipher:
-	crypto_free_ablkcipher(enc);
+	crypto_free_skcipher(enc);
 err_free_ahash:
 	crypto_free_ahash(auth);
 	return err;
@@ -380,8 +383,8 @@
 	struct crypto_authenc_esn_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->auth);
-	crypto_free_ablkcipher(ctx->enc);
-	crypto_put_default_null_skcipher();
+	crypto_free_skcipher(ctx->enc);
+	crypto_put_default_null_skcipher2();
 }
 
 static void crypto_authenc_esn_free(struct aead_instance *inst)
@@ -400,7 +403,7 @@
 	struct aead_instance *inst;
 	struct hash_alg_common *auth;
 	struct crypto_alg *auth_base;
-	struct crypto_alg *enc;
+	struct skcipher_alg *enc;
 	struct authenc_esn_instance_ctx *ctx;
 	const char *enc_name;
 	int err;
@@ -413,7 +416,8 @@
 		return -EINVAL;
 
 	auth = ahash_attr_alg(tb[1], CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK);
+			      CRYPTO_ALG_TYPE_AHASH_MASK |
+			      crypto_requires_sync(algt->type, algt->mask));
 	if (IS_ERR(auth))
 		return PTR_ERR(auth);
 
@@ -437,34 +441,36 @@
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ctx->enc, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->enc, enc_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->enc, enc_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_auth;
 
-	enc = crypto_skcipher_spawn_alg(&ctx->enc);
+	enc = crypto_spawn_skcipher_alg(&ctx->enc);
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
 		     "authencesn(%s,%s)", auth_base->cra_name,
-		     enc->cra_name) >= CRYPTO_MAX_ALG_NAME)
+		     enc->base.cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "authencesn(%s,%s)", auth_base->cra_driver_name,
-		     enc->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		     enc->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_enc;
 
-	inst->alg.base.cra_flags = enc->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = enc->cra_priority * 10 +
+	inst->alg.base.cra_flags = (auth_base->cra_flags |
+				    enc->base.cra_flags) & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = enc->base.cra_priority * 10 +
 				      auth_base->cra_priority;
-	inst->alg.base.cra_blocksize = enc->cra_blocksize;
+	inst->alg.base.cra_blocksize = enc->base.cra_blocksize;
 	inst->alg.base.cra_alignmask = auth_base->cra_alignmask |
-				       enc->cra_alignmask;
+				       enc->base.cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_authenc_esn_ctx);
 
-	inst->alg.ivsize = enc->cra_ablkcipher.ivsize;
+	inst->alg.ivsize = crypto_skcipher_alg_ivsize(enc);
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(enc);
 	inst->alg.maxauthsize = auth->digestsize;
 
 	inst->alg.init = crypto_authenc_esn_init_tfm;
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 8cc1622..3699995 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -21,7 +21,6 @@
 #include <linux/hardirq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/scatterlist.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -466,10 +465,6 @@
 	crt->setkey = async_setkey;
 	crt->encrypt = async_encrypt;
 	crt->decrypt = async_decrypt;
-	if (!alg->ivsize) {
-		crt->givencrypt = skcipher_null_givencrypt;
-		crt->givdecrypt = skcipher_null_givdecrypt;
-	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
 
@@ -560,185 +555,5 @@
 };
 EXPORT_SYMBOL_GPL(crypto_blkcipher_type);
 
-static int crypto_grab_nivcipher(struct crypto_skcipher_spawn *spawn,
-				const char *name, u32 type, u32 mask)
-{
-	struct crypto_alg *alg;
-	int err;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask)| CRYPTO_ALG_GENIV;
-
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
-
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
-	return err;
-}
-
-struct crypto_instance *skcipher_geniv_alloc(struct crypto_template *tmpl,
-					     struct rtattr **tb, u32 type,
-					     u32 mask)
-{
-	struct {
-		int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key,
-			      unsigned int keylen);
-		int (*encrypt)(struct ablkcipher_request *req);
-		int (*decrypt)(struct ablkcipher_request *req);
-
-		unsigned int min_keysize;
-		unsigned int max_keysize;
-		unsigned int ivsize;
-
-		const char *geniv;
-	} balg;
-	const char *name;
-	struct crypto_skcipher_spawn *spawn;
-	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
-	int err;
-
-	algt = crypto_get_attr_type(tb);
-	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	if ((algt->type ^ (CRYPTO_ALG_TYPE_GIVCIPHER | CRYPTO_ALG_GENIV)) &
-	    algt->mask)
-		return ERR_PTR(-EINVAL);
-
-	name = crypto_attr_alg_name(tb[1]);
-	if (IS_ERR(name))
-		return ERR_CAST(name);
-
-	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
-	if (!inst)
-		return ERR_PTR(-ENOMEM);
-
-	spawn = crypto_instance_ctx(inst);
-
-	/* Ignore async algorithms if necessary. */
-	mask |= crypto_requires_sync(algt->type, algt->mask);
-
-	crypto_set_skcipher_spawn(spawn, inst);
-	err = crypto_grab_nivcipher(spawn, name, type, mask);
-	if (err)
-		goto err_free_inst;
-
-	alg = crypto_skcipher_spawn_alg(spawn);
-
-	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
-	    CRYPTO_ALG_TYPE_BLKCIPHER) {
-		balg.ivsize = alg->cra_blkcipher.ivsize;
-		balg.min_keysize = alg->cra_blkcipher.min_keysize;
-		balg.max_keysize = alg->cra_blkcipher.max_keysize;
-
-		balg.setkey = async_setkey;
-		balg.encrypt = async_encrypt;
-		balg.decrypt = async_decrypt;
-
-		balg.geniv = alg->cra_blkcipher.geniv;
-	} else {
-		balg.ivsize = alg->cra_ablkcipher.ivsize;
-		balg.min_keysize = alg->cra_ablkcipher.min_keysize;
-		balg.max_keysize = alg->cra_ablkcipher.max_keysize;
-
-		balg.setkey = alg->cra_ablkcipher.setkey;
-		balg.encrypt = alg->cra_ablkcipher.encrypt;
-		balg.decrypt = alg->cra_ablkcipher.decrypt;
-
-		balg.geniv = alg->cra_ablkcipher.geniv;
-	}
-
-	err = -EINVAL;
-	if (!balg.ivsize)
-		goto err_drop_alg;
-
-	/*
-	 * This is only true if we're constructing an algorithm with its
-	 * default IV generator.  For the default generator we elide the
-	 * template name and double-check the IV generator.
-	 */
-	if (algt->mask & CRYPTO_ALG_GENIV) {
-		if (!balg.geniv)
-			balg.geniv = crypto_default_geniv(alg);
-		err = -EAGAIN;
-		if (strcmp(tmpl->name, balg.geniv))
-			goto err_drop_alg;
-
-		memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
-		memcpy(inst->alg.cra_driver_name, alg->cra_driver_name,
-		       CRYPTO_MAX_ALG_NAME);
-	} else {
-		err = -ENAMETOOLONG;
-		if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
-		if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_driver_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
-	}
-
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_GIVCIPHER | CRYPTO_ALG_GENIV;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_givcipher_type;
-
-	inst->alg.cra_ablkcipher.ivsize = balg.ivsize;
-	inst->alg.cra_ablkcipher.min_keysize = balg.min_keysize;
-	inst->alg.cra_ablkcipher.max_keysize = balg.max_keysize;
-	inst->alg.cra_ablkcipher.geniv = balg.geniv;
-
-	inst->alg.cra_ablkcipher.setkey = balg.setkey;
-	inst->alg.cra_ablkcipher.encrypt = balg.encrypt;
-	inst->alg.cra_ablkcipher.decrypt = balg.decrypt;
-
-out:
-	return inst;
-
-err_drop_alg:
-	crypto_drop_skcipher(spawn);
-err_free_inst:
-	kfree(inst);
-	inst = ERR_PTR(err);
-	goto out;
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_alloc);
-
-void skcipher_geniv_free(struct crypto_instance *inst)
-{
-	crypto_drop_skcipher(crypto_instance_ctx(inst));
-	kfree(inst);
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_free);
-
-int skcipher_geniv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_ablkcipher *cipher;
-
-	cipher = crypto_spawn_skcipher(crypto_instance_ctx(inst));
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	tfm->crt_ablkcipher.base = cipher;
-	tfm->crt_ablkcipher.reqsize += crypto_ablkcipher_reqsize(cipher);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_init);
-
-void skcipher_geniv_exit(struct crypto_tfm *tfm)
-{
-	crypto_free_ablkcipher(tfm->crt_ablkcipher.base);
-}
-EXPORT_SYMBOL_GPL(skcipher_geniv_exit);
-
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Generic block chaining cipher type");
diff --git a/crypto/ccm.c b/crypto/ccm.c
index cc31ea4..006d857 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -28,7 +28,7 @@
 
 struct crypto_ccm_ctx {
 	struct crypto_cipher *cipher;
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 };
 
 struct crypto_rfc4309_ctx {
@@ -50,7 +50,7 @@
 	u32 flags;
 	struct scatterlist src[3];
 	struct scatterlist dst[3];
-	struct ablkcipher_request abreq;
+	struct skcipher_request skreq;
 };
 
 static inline struct crypto_ccm_req_priv_ctx *crypto_ccm_reqctx(
@@ -83,15 +83,15 @@
 			     unsigned int keylen)
 {
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead);
-	struct crypto_ablkcipher *ctr = ctx->ctr;
+	struct crypto_skcipher *ctr = ctx->ctr;
 	struct crypto_cipher *tfm = ctx->cipher;
 	int err = 0;
 
-	crypto_ablkcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
-				    CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(ctr, key, keylen);
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
+	crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(ctr, key, keylen);
+	crypto_aead_set_flags(aead, crypto_skcipher_get_flags(ctr) &
 			      CRYPTO_TFM_RES_MASK);
 	if (err)
 		goto out;
@@ -347,7 +347,7 @@
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->abreq;
+	struct skcipher_request *skreq = &pctx->skreq;
 	struct scatterlist *dst;
 	unsigned int cryptlen = req->cryptlen;
 	u8 *odata = pctx->odata;
@@ -366,11 +366,11 @@
 	if (req->src != req->dst)
 		dst = pctx->dst;
 
-	ablkcipher_request_set_tfm(abreq, ctx->ctr);
-	ablkcipher_request_set_callback(abreq, pctx->flags,
-					crypto_ccm_encrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, pctx->src, dst, cryptlen + 16, iv);
-	err = crypto_ablkcipher_encrypt(abreq);
+	skcipher_request_set_tfm(skreq, ctx->ctr);
+	skcipher_request_set_callback(skreq, pctx->flags,
+				      crypto_ccm_encrypt_done, req);
+	skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv);
+	err = crypto_skcipher_encrypt(skreq);
 	if (err)
 		return err;
 
@@ -407,7 +407,7 @@
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_ccm_req_priv_ctx *pctx = crypto_ccm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->abreq;
+	struct skcipher_request *skreq = &pctx->skreq;
 	struct scatterlist *dst;
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int cryptlen = req->cryptlen;
@@ -429,11 +429,11 @@
 	if (req->src != req->dst)
 		dst = pctx->dst;
 
-	ablkcipher_request_set_tfm(abreq, ctx->ctr);
-	ablkcipher_request_set_callback(abreq, pctx->flags,
-					crypto_ccm_decrypt_done, req);
-	ablkcipher_request_set_crypt(abreq, pctx->src, dst, cryptlen + 16, iv);
-	err = crypto_ablkcipher_decrypt(abreq);
+	skcipher_request_set_tfm(skreq, ctx->ctr);
+	skcipher_request_set_callback(skreq, pctx->flags,
+				      crypto_ccm_decrypt_done, req);
+	skcipher_request_set_crypt(skreq, pctx->src, dst, cryptlen + 16, iv);
+	err = crypto_skcipher_decrypt(skreq);
 	if (err)
 		return err;
 
@@ -454,7 +454,7 @@
 	struct ccm_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_cipher *cipher;
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 	unsigned long align;
 	int err;
 
@@ -462,7 +462,7 @@
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	ctr = crypto_spawn_skcipher(&ictx->ctr);
+	ctr = crypto_spawn_skcipher2(&ictx->ctr);
 	err = PTR_ERR(ctr);
 	if (IS_ERR(ctr))
 		goto err_free_cipher;
@@ -475,7 +475,7 @@
 	crypto_aead_set_reqsize(
 		tfm,
 		align + sizeof(struct crypto_ccm_req_priv_ctx) +
-		crypto_ablkcipher_reqsize(ctr));
+		crypto_skcipher_reqsize(ctr));
 
 	return 0;
 
@@ -489,7 +489,7 @@
 	struct crypto_ccm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_cipher(ctx->cipher);
-	crypto_free_ablkcipher(ctx->ctr);
+	crypto_free_skcipher(ctx->ctr);
 }
 
 static void crypto_ccm_free(struct aead_instance *inst)
@@ -509,7 +509,7 @@
 {
 	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
-	struct crypto_alg *ctr;
+	struct skcipher_alg *ctr;
 	struct crypto_alg *cipher;
 	struct ccm_instance_ctx *ictx;
 	int err;
@@ -544,39 +544,40 @@
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ictx->ctr, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ictx->ctr, ctr_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ictx->ctr, ctr_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_cipher;
 
-	ctr = crypto_skcipher_spawn_alg(&ictx->ctr);
+	ctr = crypto_spawn_skcipher_alg(&ictx->ctr);
 
 	/* Not a stream cipher? */
 	err = -EINVAL;
-	if (ctr->cra_blocksize != 1)
+	if (ctr->base.cra_blocksize != 1)
 		goto err_drop_ctr;
 
 	/* We want the real thing! */
-	if (ctr->cra_ablkcipher.ivsize != 16)
+	if (crypto_skcipher_alg_ivsize(ctr) != 16)
 		goto err_drop_ctr;
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "ccm_base(%s,%s)", ctr->cra_driver_name,
+		     "ccm_base(%s,%s)", ctr->base.cra_driver_name,
 		     cipher->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_ctr;
 
 	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
 
-	inst->alg.base.cra_flags = ctr->cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_flags = ctr->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (cipher->cra_priority +
-				       ctr->cra_priority) / 2;
+				       ctr->base.cra_priority) / 2;
 	inst->alg.base.cra_blocksize = 1;
 	inst->alg.base.cra_alignmask = cipher->cra_alignmask |
-				       ctr->cra_alignmask |
+				       ctr->base.cra_alignmask |
 				       (__alignof__(u32) - 1);
 	inst->alg.ivsize = 16;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(ctr);
 	inst->alg.maxauthsize = 16;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_ccm_ctx);
 	inst->alg.init = crypto_ccm_init_tfm;
@@ -863,6 +864,7 @@
 	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
 	inst->alg.ivsize = 8;
+	inst->alg.chunksize = crypto_aead_alg_chunksize(alg);
 	inst->alg.maxauthsize = 16;
 
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4309_ctx);
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 7b6b935..e899ef5 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -31,7 +31,7 @@
 };
 
 struct chachapoly_ctx {
-	struct crypto_ablkcipher *chacha;
+	struct crypto_skcipher *chacha;
 	struct crypto_ahash *poly;
 	/* key bytes we use for the ChaCha20 IV */
 	unsigned int saltlen;
@@ -53,7 +53,7 @@
 struct chacha_req {
 	u8 iv[CHACHA20_IV_SIZE];
 	struct scatterlist src[1];
-	struct ablkcipher_request req; /* must be last member */
+	struct skcipher_request req; /* must be last member */
 };
 
 struct chachapoly_req_ctx {
@@ -144,12 +144,12 @@
 		dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);
 	}
 
-	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
-					chacha_decrypt_done, req);
-	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, src, dst,
-				     rctx->cryptlen, creq->iv);
-	err = crypto_ablkcipher_decrypt(&creq->req);
+	skcipher_request_set_callback(&creq->req, aead_request_flags(req),
+				      chacha_decrypt_done, req);
+	skcipher_request_set_tfm(&creq->req, ctx->chacha);
+	skcipher_request_set_crypt(&creq->req, src, dst,
+				   rctx->cryptlen, creq->iv);
+	err = crypto_skcipher_decrypt(&creq->req);
 	if (err)
 		return err;
 
@@ -393,13 +393,13 @@
 
 	chacha_iv(creq->iv, req, 0);
 
-	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
-					poly_genkey_done, req);
-	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, creq->src, creq->src,
-				     POLY1305_KEY_SIZE, creq->iv);
+	skcipher_request_set_callback(&creq->req, aead_request_flags(req),
+				      poly_genkey_done, req);
+	skcipher_request_set_tfm(&creq->req, ctx->chacha);
+	skcipher_request_set_crypt(&creq->req, creq->src, creq->src,
+				   POLY1305_KEY_SIZE, creq->iv);
 
-	err = crypto_ablkcipher_decrypt(&creq->req);
+	err = crypto_skcipher_decrypt(&creq->req);
 	if (err)
 		return err;
 
@@ -433,12 +433,12 @@
 		dst = scatterwalk_ffwd(rctx->dst, req->dst, req->assoclen);
 	}
 
-	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
-					chacha_encrypt_done, req);
-	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
-	ablkcipher_request_set_crypt(&creq->req, src, dst,
-				     req->cryptlen, creq->iv);
-	err = crypto_ablkcipher_encrypt(&creq->req);
+	skcipher_request_set_callback(&creq->req, aead_request_flags(req),
+				      chacha_encrypt_done, req);
+	skcipher_request_set_tfm(&creq->req, ctx->chacha);
+	skcipher_request_set_crypt(&creq->req, src, dst,
+				   req->cryptlen, creq->iv);
+	err = crypto_skcipher_encrypt(&creq->req);
 	if (err)
 		return err;
 
@@ -500,13 +500,13 @@
 	keylen -= ctx->saltlen;
 	memcpy(ctx->salt, key + keylen, ctx->saltlen);
 
-	crypto_ablkcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
-				    CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
+					       CRYPTO_TFM_REQ_MASK);
 
-	err = crypto_ablkcipher_setkey(ctx->chacha, key, keylen);
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctx->chacha) &
-			      CRYPTO_TFM_RES_MASK);
+	err = crypto_skcipher_setkey(ctx->chacha, key, keylen);
+	crypto_aead_set_flags(aead, crypto_skcipher_get_flags(ctx->chacha) &
+				    CRYPTO_TFM_RES_MASK);
 	return err;
 }
 
@@ -524,7 +524,7 @@
 	struct aead_instance *inst = aead_alg_instance(tfm);
 	struct chachapoly_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
-	struct crypto_ablkcipher *chacha;
+	struct crypto_skcipher *chacha;
 	struct crypto_ahash *poly;
 	unsigned long align;
 
@@ -532,7 +532,7 @@
 	if (IS_ERR(poly))
 		return PTR_ERR(poly);
 
-	chacha = crypto_spawn_skcipher(&ictx->chacha);
+	chacha = crypto_spawn_skcipher2(&ictx->chacha);
 	if (IS_ERR(chacha)) {
 		crypto_free_ahash(poly);
 		return PTR_ERR(chacha);
@@ -548,8 +548,8 @@
 		tfm,
 		align + offsetof(struct chachapoly_req_ctx, u) +
 		max(offsetof(struct chacha_req, req) +
-		    sizeof(struct ablkcipher_request) +
-		    crypto_ablkcipher_reqsize(chacha),
+		    sizeof(struct skcipher_request) +
+		    crypto_skcipher_reqsize(chacha),
 		    offsetof(struct poly_req, req) +
 		    sizeof(struct ahash_request) +
 		    crypto_ahash_reqsize(poly)));
@@ -562,7 +562,7 @@
 	struct chachapoly_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->poly);
-	crypto_free_ablkcipher(ctx->chacha);
+	crypto_free_skcipher(ctx->chacha);
 }
 
 static void chachapoly_free(struct aead_instance *inst)
@@ -579,7 +579,7 @@
 {
 	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
-	struct crypto_alg *chacha;
+	struct skcipher_alg *chacha;
 	struct crypto_alg *poly;
 	struct hash_alg_common *poly_hash;
 	struct chachapoly_instance_ctx *ctx;
@@ -605,7 +605,9 @@
 
 	poly = crypto_find_alg(poly_name, &crypto_ahash_type,
 			       CRYPTO_ALG_TYPE_HASH,
-			       CRYPTO_ALG_TYPE_AHASH_MASK);
+			       CRYPTO_ALG_TYPE_AHASH_MASK |
+			       crypto_requires_sync(algt->type,
+						    algt->mask));
 	if (IS_ERR(poly))
 		return PTR_ERR(poly);
 
@@ -623,20 +625,20 @@
 		goto err_free_inst;
 
 	crypto_set_skcipher_spawn(&ctx->chacha, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->chacha, chacha_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->chacha, chacha_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_poly;
 
-	chacha = crypto_skcipher_spawn_alg(&ctx->chacha);
+	chacha = crypto_spawn_skcipher_alg(&ctx->chacha);
 
 	err = -EINVAL;
 	/* Need 16-byte IV size, including Initial Block Counter value */
-	if (chacha->cra_ablkcipher.ivsize != CHACHA20_IV_SIZE)
+	if (crypto_skcipher_alg_ivsize(chacha) != CHACHA20_IV_SIZE)
 		goto out_drop_chacha;
 	/* Not a stream cipher? */
-	if (chacha->cra_blocksize != 1)
+	if (chacha->base.cra_blocksize != 1)
 		goto out_drop_chacha;
 
 	err = -ENAMETOOLONG;
@@ -645,20 +647,21 @@
 		     poly_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "%s(%s,%s)", name, chacha->cra_driver_name,
+		     "%s(%s,%s)", name, chacha->base.cra_driver_name,
 		     poly->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 
-	inst->alg.base.cra_flags = (chacha->cra_flags | poly->cra_flags) &
+	inst->alg.base.cra_flags = (chacha->base.cra_flags | poly->cra_flags) &
 				   CRYPTO_ALG_ASYNC;
-	inst->alg.base.cra_priority = (chacha->cra_priority +
+	inst->alg.base.cra_priority = (chacha->base.cra_priority +
 				       poly->cra_priority) / 2;
 	inst->alg.base.cra_blocksize = 1;
-	inst->alg.base.cra_alignmask = chacha->cra_alignmask |
+	inst->alg.base.cra_alignmask = chacha->base.cra_alignmask |
 				       poly->cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct chachapoly_ctx) +
 				     ctx->saltlen;
 	inst->alg.ivsize = ivsize;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(chacha);
 	inst->alg.maxauthsize = POLY1305_DIGEST_SIZE;
 	inst->alg.init = chachapoly_init;
 	inst->alg.exit = chachapoly_exit;
diff --git a/crypto/chainiv.c b/crypto/chainiv.c
deleted file mode 100644
index b434001..0000000
--- a/crypto/chainiv.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * chainiv: Chain IV Generator
- *
- * Generate IVs simply be using the last block of the previous encryption.
- * This is mainly useful for CBC with a synchronous algorithm.
- *
- * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/skcipher.h>
-#include <crypto/rng.h>
-#include <crypto/crypto_wq.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/workqueue.h>
-
-enum {
-	CHAINIV_STATE_INUSE = 0,
-};
-
-struct chainiv_ctx {
-	spinlock_t lock;
-	char iv[];
-};
-
-struct async_chainiv_ctx {
-	unsigned long state;
-
-	spinlock_t lock;
-	int err;
-
-	struct crypto_queue queue;
-	struct work_struct postponed;
-
-	char iv[];
-};
-
-static int chainiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	unsigned int ivsize;
-	int err;
-
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags &
-						~CRYPTO_TFM_REQ_MAY_SLEEP,
-					req->creq.base.complete,
-					req->creq.base.data);
-	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
-				     req->creq.nbytes, req->creq.info);
-
-	spin_lock_bh(&ctx->lock);
-
-	ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	memcpy(req->giv, ctx->iv, ivsize);
-	memcpy(subreq->info, ctx->iv, ivsize);
-
-	err = crypto_ablkcipher_encrypt(subreq);
-	if (err)
-		goto unlock;
-
-	memcpy(ctx->iv, subreq->info, ivsize);
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	return err;
-}
-
-static int chainiv_init_common(struct crypto_tfm *tfm, char iv[])
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	int err = 0;
-
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
-
-	if (iv) {
-		err = crypto_rng_get_bytes(crypto_default_rng, iv,
-					   crypto_ablkcipher_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: skcipher_geniv_init(tfm);
-}
-
-static int chainiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-	char *iv;
-
-	spin_lock_init(&ctx->lock);
-
-	iv = NULL;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt = chainiv_givencrypt;
-		iv = ctx->iv;
-	}
-
-	return chainiv_init_common(tfm, iv);
-}
-
-static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
-{
-	int queued;
-	int err = ctx->err;
-
-	if (!ctx->queue.qlen) {
-		smp_mb__before_atomic();
-		clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
-
-		if (!ctx->queue.qlen ||
-		    test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-			goto out;
-	}
-
-	queued = queue_work(kcrypto_wq, &ctx->postponed);
-	BUG_ON(!queued);
-
-out:
-	return err;
-}
-
-static int async_chainiv_postpone_request(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err;
-
-	spin_lock_bh(&ctx->lock);
-	err = skcipher_enqueue_givcrypt(&ctx->queue, req);
-	spin_unlock_bh(&ctx->lock);
-
-	if (test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-		return err;
-
-	ctx->err = err;
-	return async_chainiv_schedule_work(ctx);
-}
-
-static int async_chainiv_givencrypt_tail(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	unsigned int ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	memcpy(req->giv, ctx->iv, ivsize);
-	memcpy(subreq->info, ctx->iv, ivsize);
-
-	ctx->err = crypto_ablkcipher_encrypt(subreq);
-	if (ctx->err)
-		goto out;
-
-	memcpy(ctx->iv, subreq->info, ivsize);
-
-out:
-	return async_chainiv_schedule_work(ctx);
-}
-
-static int async_chainiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags,
-					req->creq.base.complete,
-					req->creq.base.data);
-	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
-				     req->creq.nbytes, req->creq.info);
-
-	if (test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-		goto postpone;
-
-	if (ctx->queue.qlen) {
-		clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
-		goto postpone;
-	}
-
-	return async_chainiv_givencrypt_tail(req);
-
-postpone:
-	return async_chainiv_postpone_request(req);
-}
-
-static void async_chainiv_do_postponed(struct work_struct *work)
-{
-	struct async_chainiv_ctx *ctx = container_of(work,
-						     struct async_chainiv_ctx,
-						     postponed);
-	struct skcipher_givcrypt_request *req;
-	struct ablkcipher_request *subreq;
-	int err;
-
-	/* Only handle one request at a time to avoid hogging keventd. */
-	spin_lock_bh(&ctx->lock);
-	req = skcipher_dequeue_givcrypt(&ctx->queue);
-	spin_unlock_bh(&ctx->lock);
-
-	if (!req) {
-		async_chainiv_schedule_work(ctx);
-		return;
-	}
-
-	subreq = skcipher_givcrypt_reqctx(req);
-	subreq->base.flags |= CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	err = async_chainiv_givencrypt_tail(req);
-
-	local_bh_disable();
-	skcipher_givcrypt_complete(req, err);
-	local_bh_enable();
-}
-
-static int async_chainiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct async_chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-	char *iv;
-
-	spin_lock_init(&ctx->lock);
-
-	crypto_init_queue(&ctx->queue, 100);
-	INIT_WORK(&ctx->postponed, async_chainiv_do_postponed);
-
-	iv = NULL;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt =
-			async_chainiv_givencrypt;
-		iv = ctx->iv;
-	}
-
-	return chainiv_init_common(tfm, iv);
-}
-
-static void async_chainiv_exit(struct crypto_tfm *tfm)
-{
-	struct async_chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	BUG_ON(test_bit(CHAINIV_STATE_INUSE, &ctx->state) || ctx->queue.qlen);
-
-	skcipher_geniv_exit(tfm);
-}
-
-static struct crypto_template chainiv_tmpl;
-
-static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
-{
-	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-
-	algt = crypto_get_attr_type(tb);
-	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	inst = skcipher_geniv_alloc(&chainiv_tmpl, tb, 0, 0);
-	if (IS_ERR(inst))
-		goto out;
-
-	inst->alg.cra_init = chainiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
-
-	inst->alg.cra_ctxsize = sizeof(struct chainiv_ctx);
-
-	if (!crypto_requires_sync(algt->type, algt->mask)) {
-		inst->alg.cra_flags |= CRYPTO_ALG_ASYNC;
-
-		inst->alg.cra_init = async_chainiv_init;
-		inst->alg.cra_exit = async_chainiv_exit;
-
-		inst->alg.cra_ctxsize = sizeof(struct async_chainiv_ctx);
-	}
-
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
-
-out:
-	return inst;
-}
-
-static struct crypto_template chainiv_tmpl = {
-	.name = "chainiv",
-	.alloc = chainiv_alloc,
-	.free = skcipher_geniv_free,
-	.module = THIS_MODULE,
-};
-
-static int __init chainiv_module_init(void)
-{
-	return crypto_register_template(&chainiv_tmpl);
-}
-
-static void chainiv_module_exit(void)
-{
-	crypto_unregister_template(&chainiv_tmpl);
-}
-
-module_init(chainiv_module_init);
-module_exit(chainiv_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Chain IV Generator");
-MODULE_ALIAS_CRYPTO("chainiv");
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 7921251..cf8037a 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -22,6 +22,7 @@
 #include <crypto/internal/aead.h>
 #include <crypto/cryptd.h>
 #include <crypto/crypto_wq.h>
+#include <linux/atomic.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -31,7 +32,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
-#define CRYPTD_MAX_CPU_QLEN 100
+#define CRYPTD_MAX_CPU_QLEN 1000
 
 struct cryptd_cpu_queue {
 	struct crypto_queue queue;
@@ -58,6 +59,7 @@
 };
 
 struct cryptd_blkcipher_ctx {
+	atomic_t refcnt;
 	struct crypto_blkcipher *child;
 };
 
@@ -66,6 +68,7 @@
 };
 
 struct cryptd_hash_ctx {
+	atomic_t refcnt;
 	struct crypto_shash *child;
 };
 
@@ -75,6 +78,7 @@
 };
 
 struct cryptd_aead_ctx {
+	atomic_t refcnt;
 	struct crypto_aead *child;
 };
 
@@ -118,11 +122,29 @@
 {
 	int cpu, err;
 	struct cryptd_cpu_queue *cpu_queue;
+	struct crypto_tfm *tfm;
+	atomic_t *refcnt;
+	bool may_backlog;
 
 	cpu = get_cpu();
 	cpu_queue = this_cpu_ptr(queue->cpu_queue);
 	err = crypto_enqueue_request(&cpu_queue->queue, request);
+
+	refcnt = crypto_tfm_ctx(request->tfm);
+	may_backlog = request->flags & CRYPTO_TFM_REQ_MAY_BACKLOG;
+
+	if (err == -EBUSY && !may_backlog)
+		goto out_put_cpu;
+
 	queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
+
+	if (!atomic_read(refcnt))
+		goto out_put_cpu;
+
+	tfm = request->tfm;
+	atomic_inc(refcnt);
+
+out_put_cpu:
 	put_cpu();
 
 	return err;
@@ -206,7 +228,10 @@
 						unsigned int len))
 {
 	struct cryptd_blkcipher_request_ctx *rctx;
+	struct cryptd_blkcipher_ctx *ctx;
+	struct crypto_ablkcipher *tfm;
 	struct blkcipher_desc desc;
+	int refcnt;
 
 	rctx = ablkcipher_request_ctx(req);
 
@@ -222,9 +247,16 @@
 	req->base.complete = rctx->complete;
 
 out:
+	tfm = crypto_ablkcipher_reqtfm(req);
+	ctx = crypto_ablkcipher_ctx(tfm);
+	refcnt = atomic_read(&ctx->refcnt);
+
 	local_bh_disable();
 	rctx->complete(&req->base, err);
 	local_bh_enable();
+
+	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ablkcipher(tfm);
 }
 
 static void cryptd_blkcipher_encrypt(struct crypto_async_request *req, int err)
@@ -456,6 +488,21 @@
 	return cryptd_enqueue_request(queue, &req->base);
 }
 
+static void cryptd_hash_complete(struct ahash_request *req, int err)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	int refcnt = atomic_read(&ctx->refcnt);
+
+	local_bh_disable();
+	rctx->complete(&req->base, err);
+	local_bh_enable();
+
+	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ahash(tfm);
+}
+
 static void cryptd_hash_init(struct crypto_async_request *req_async, int err)
 {
 	struct cryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
@@ -475,9 +522,7 @@
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_init_enqueue(struct ahash_request *req)
@@ -500,9 +545,7 @@
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_update_enqueue(struct ahash_request *req)
@@ -523,9 +566,7 @@
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_final_enqueue(struct ahash_request *req)
@@ -546,9 +587,7 @@
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_finup_enqueue(struct ahash_request *req)
@@ -575,9 +614,7 @@
 	req->base.complete = rctx->complete;
 
 out:
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
+	cryptd_hash_complete(req, err);
 }
 
 static int cryptd_hash_digest_enqueue(struct ahash_request *req)
@@ -688,7 +725,10 @@
 			int (*crypt)(struct aead_request *req))
 {
 	struct cryptd_aead_request_ctx *rctx;
+	struct cryptd_aead_ctx *ctx;
 	crypto_completion_t compl;
+	struct crypto_aead *tfm;
+	int refcnt;
 
 	rctx = aead_request_ctx(req);
 	compl = rctx->complete;
@@ -697,10 +737,18 @@
 		goto out;
 	aead_request_set_tfm(req, child);
 	err = crypt( req );
+
 out:
+	tfm = crypto_aead_reqtfm(req);
+	ctx = crypto_aead_ctx(tfm);
+	refcnt = atomic_read(&ctx->refcnt);
+
 	local_bh_disable();
 	compl(&req->base, err);
 	local_bh_enable();
+
+	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_aead(tfm);
 }
 
 static void cryptd_aead_encrypt(struct crypto_async_request *areq, int err)
@@ -883,6 +931,7 @@
 						  u32 type, u32 mask)
 {
 	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct cryptd_blkcipher_ctx *ctx;
 	struct crypto_tfm *tfm;
 
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
@@ -899,6 +948,9 @@
 		return ERR_PTR(-EINVAL);
 	}
 
+	ctx = crypto_tfm_ctx(tfm);
+	atomic_set(&ctx->refcnt, 1);
+
 	return __cryptd_ablkcipher_cast(__crypto_ablkcipher_cast(tfm));
 }
 EXPORT_SYMBOL_GPL(cryptd_alloc_ablkcipher);
@@ -910,9 +962,20 @@
 }
 EXPORT_SYMBOL_GPL(cryptd_ablkcipher_child);
 
+bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm)
+{
+	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
+
+	return atomic_read(&ctx->refcnt) - 1;
+}
+EXPORT_SYMBOL_GPL(cryptd_ablkcipher_queued);
+
 void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm)
 {
-	crypto_free_ablkcipher(&tfm->base);
+	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
+
+	if (atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ablkcipher(&tfm->base);
 }
 EXPORT_SYMBOL_GPL(cryptd_free_ablkcipher);
 
@@ -920,6 +983,7 @@
 					u32 type, u32 mask)
 {
 	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct cryptd_hash_ctx *ctx;
 	struct crypto_ahash *tfm;
 
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
@@ -933,6 +997,9 @@
 		return ERR_PTR(-EINVAL);
 	}
 
+	ctx = crypto_ahash_ctx(tfm);
+	atomic_set(&ctx->refcnt, 1);
+
 	return __cryptd_ahash_cast(tfm);
 }
 EXPORT_SYMBOL_GPL(cryptd_alloc_ahash);
@@ -952,9 +1019,20 @@
 }
 EXPORT_SYMBOL_GPL(cryptd_shash_desc);
 
+bool cryptd_ahash_queued(struct cryptd_ahash *tfm)
+{
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
+
+	return atomic_read(&ctx->refcnt) - 1;
+}
+EXPORT_SYMBOL_GPL(cryptd_ahash_queued);
+
 void cryptd_free_ahash(struct cryptd_ahash *tfm)
 {
-	crypto_free_ahash(&tfm->base);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
+
+	if (atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_ahash(&tfm->base);
 }
 EXPORT_SYMBOL_GPL(cryptd_free_ahash);
 
@@ -962,6 +1040,7 @@
 						  u32 type, u32 mask)
 {
 	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
+	struct cryptd_aead_ctx *ctx;
 	struct crypto_aead *tfm;
 
 	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
@@ -974,6 +1053,10 @@
 		crypto_free_aead(tfm);
 		return ERR_PTR(-EINVAL);
 	}
+
+	ctx = crypto_aead_ctx(tfm);
+	atomic_set(&ctx->refcnt, 1);
+
 	return __cryptd_aead_cast(tfm);
 }
 EXPORT_SYMBOL_GPL(cryptd_alloc_aead);
@@ -986,9 +1069,20 @@
 }
 EXPORT_SYMBOL_GPL(cryptd_aead_child);
 
+bool cryptd_aead_queued(struct cryptd_aead *tfm)
+{
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(&tfm->base);
+
+	return atomic_read(&ctx->refcnt) - 1;
+}
+EXPORT_SYMBOL_GPL(cryptd_aead_queued);
+
 void cryptd_free_aead(struct cryptd_aead *tfm)
 {
-	crypto_free_aead(&tfm->base);
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(&tfm->base);
+
+	if (atomic_dec_and_test(&ctx->refcnt))
+		crypto_free_aead(&tfm->base);
 }
 EXPORT_SYMBOL_GPL(cryptd_free_aead);
 
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index 941c9a4..20ff2c7 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -26,7 +26,7 @@
 #include <linux/string.h>
 
 static DEFINE_MUTEX(crypto_default_null_skcipher_lock);
-static struct crypto_blkcipher *crypto_default_null_skcipher;
+static struct crypto_skcipher *crypto_default_null_skcipher;
 static int crypto_default_null_skcipher_refcnt;
 
 static int null_compress(struct crypto_tfm *tfm, const u8 *src,
@@ -153,15 +153,16 @@
 MODULE_ALIAS_CRYPTO("digest_null");
 MODULE_ALIAS_CRYPTO("cipher_null");
 
-struct crypto_blkcipher *crypto_get_default_null_skcipher(void)
+struct crypto_skcipher *crypto_get_default_null_skcipher(void)
 {
-	struct crypto_blkcipher *tfm;
+	struct crypto_skcipher *tfm;
 
 	mutex_lock(&crypto_default_null_skcipher_lock);
 	tfm = crypto_default_null_skcipher;
 
 	if (!tfm) {
-		tfm = crypto_alloc_blkcipher("ecb(cipher_null)", 0, 0);
+		tfm = crypto_alloc_skcipher("ecb(cipher_null)",
+					    0, CRYPTO_ALG_ASYNC);
 		if (IS_ERR(tfm))
 			goto unlock;
 
@@ -181,7 +182,7 @@
 {
 	mutex_lock(&crypto_default_null_skcipher_lock);
 	if (!--crypto_default_null_skcipher_refcnt) {
-		crypto_free_blkcipher(crypto_default_null_skcipher);
+		crypto_free_skcipher(crypto_default_null_skcipher);
 		crypto_default_null_skcipher = NULL;
 	}
 	mutex_unlock(&crypto_default_null_skcipher_lock);
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 7097a33..1c57054 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -28,6 +28,7 @@
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/rng.h>
 #include <crypto/akcipher.h>
+#include <crypto/kpp.h>
 
 #include "internal.h"
 
@@ -126,6 +127,21 @@
 	return -EMSGSIZE;
 }
 
+static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_kpp rkpp;
+
+	strncpy(rkpp.type, "kpp", sizeof(rkpp.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_KPP,
+		    sizeof(struct crypto_report_kpp), &rkpp))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int crypto_report_one(struct crypto_alg *alg,
 			     struct crypto_user_alg *ualg, struct sk_buff *skb)
 {
@@ -176,6 +192,10 @@
 			goto nla_put_failure;
 
 		break;
+	case CRYPTO_ALG_TYPE_KPP:
+		if (crypto_report_kpp(skb, alg))
+			goto nla_put_failure;
+		break;
 	}
 
 out:
@@ -358,32 +378,6 @@
 	return err;
 }
 
-static struct crypto_alg *crypto_user_skcipher_alg(const char *name, u32 type,
-						   u32 mask)
-{
-	int err;
-	struct crypto_alg *alg;
-
-	type = crypto_skcipher_type(type);
-	mask = crypto_skcipher_mask(mask);
-
-	for (;;) {
-		alg = crypto_lookup_skcipher(name,  type, mask);
-		if (!IS_ERR(alg))
-			return alg;
-
-		err = PTR_ERR(alg);
-		if (err != -EAGAIN)
-			break;
-		if (fatal_signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
-
-	return ERR_PTR(err);
-}
-
 static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct nlattr **attrs)
 {
@@ -416,16 +410,7 @@
 	else
 		name = p->cru_name;
 
-	switch (p->cru_type & p->cru_mask & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_GIVCIPHER:
-	case CRYPTO_ALG_TYPE_BLKCIPHER:
-	case CRYPTO_ALG_TYPE_ABLKCIPHER:
-		alg = crypto_user_skcipher_alg(name, p->cru_type, p->cru_mask);
-		break;
-	default:
-		alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask);
-	}
-
+	alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask);
 	if (IS_ERR(alg))
 		return PTR_ERR(alg);
 
diff --git a/crypto/ctr.c b/crypto/ctr.c
index 2386f73..ff4d21e 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -26,13 +26,13 @@
 };
 
 struct crypto_rfc3686_ctx {
-	struct crypto_ablkcipher *child;
+	struct crypto_skcipher *child;
 	u8 nonce[CTR_RFC3686_NONCE_SIZE];
 };
 
 struct crypto_rfc3686_req_ctx {
 	u8 iv[CTR_RFC3686_BLOCK_SIZE];
-	struct ablkcipher_request subreq CRYPTO_MINALIGN_ATTR;
+	struct skcipher_request subreq CRYPTO_MINALIGN_ATTR;
 };
 
 static int crypto_ctr_setkey(struct crypto_tfm *parent, const u8 *key,
@@ -249,11 +249,11 @@
 	.module = THIS_MODULE,
 };
 
-static int crypto_rfc3686_setkey(struct crypto_ablkcipher *parent,
+static int crypto_rfc3686_setkey(struct crypto_skcipher *parent,
 				 const u8 *key, unsigned int keylen)
 {
-	struct crypto_rfc3686_ctx *ctx = crypto_ablkcipher_ctx(parent);
-	struct crypto_ablkcipher *child = ctx->child;
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(parent);
+	struct crypto_skcipher *child = ctx->child;
 	int err;
 
 	/* the nonce is stored in bytes at end of key */
@@ -265,173 +265,178 @@
 
 	keylen -= CTR_RFC3686_NONCE_SIZE;
 
-	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(parent) &
-				    CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(child, key, keylen);
-	crypto_ablkcipher_set_flags(parent, crypto_ablkcipher_get_flags(child) &
-				    CRYPTO_TFM_RES_MASK);
+	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
+					 CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(child, key, keylen);
+	crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
+					  CRYPTO_TFM_RES_MASK);
 
 	return err;
 }
 
-static int crypto_rfc3686_crypt(struct ablkcipher_request *req)
+static int crypto_rfc3686_crypt(struct skcipher_request *req)
 {
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct crypto_rfc3686_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct crypto_ablkcipher *child = ctx->child;
-	unsigned long align = crypto_ablkcipher_alignmask(tfm);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *child = ctx->child;
+	unsigned long align = crypto_skcipher_alignmask(tfm);
 	struct crypto_rfc3686_req_ctx *rctx =
-		(void *)PTR_ALIGN((u8 *)ablkcipher_request_ctx(req), align + 1);
-	struct ablkcipher_request *subreq = &rctx->subreq;
+		(void *)PTR_ALIGN((u8 *)skcipher_request_ctx(req), align + 1);
+	struct skcipher_request *subreq = &rctx->subreq;
 	u8 *iv = rctx->iv;
 
 	/* set up counter block */
 	memcpy(iv, ctx->nonce, CTR_RFC3686_NONCE_SIZE);
-	memcpy(iv + CTR_RFC3686_NONCE_SIZE, req->info, CTR_RFC3686_IV_SIZE);
+	memcpy(iv + CTR_RFC3686_NONCE_SIZE, req->iv, CTR_RFC3686_IV_SIZE);
 
 	/* initialize counter portion of counter block */
 	*(__be32 *)(iv + CTR_RFC3686_NONCE_SIZE + CTR_RFC3686_IV_SIZE) =
 		cpu_to_be32(1);
 
-	ablkcipher_request_set_tfm(subreq, child);
-	ablkcipher_request_set_callback(subreq, req->base.flags,
-					req->base.complete, req->base.data);
-	ablkcipher_request_set_crypt(subreq, req->src, req->dst, req->nbytes,
-				     iv);
+	skcipher_request_set_tfm(subreq, child);
+	skcipher_request_set_callback(subreq, req->base.flags,
+				      req->base.complete, req->base.data);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->cryptlen, iv);
 
-	return crypto_ablkcipher_encrypt(subreq);
+	return crypto_skcipher_encrypt(subreq);
 }
 
-static int crypto_rfc3686_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc3686_init_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_skcipher_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_rfc3686_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *cipher;
+	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *cipher;
 	unsigned long align;
+	unsigned int reqsize;
 
-	cipher = crypto_spawn_skcipher(spawn);
+	cipher = crypto_spawn_skcipher2(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
 
-	align = crypto_tfm_alg_alignmask(tfm);
+	align = crypto_skcipher_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_ablkcipher.reqsize = align +
-		sizeof(struct crypto_rfc3686_req_ctx) +
-		crypto_ablkcipher_reqsize(cipher);
+	reqsize = align + sizeof(struct crypto_rfc3686_req_ctx) +
+		  crypto_skcipher_reqsize(cipher);
+	crypto_skcipher_set_reqsize(tfm, reqsize);
 
 	return 0;
 }
 
-static void crypto_rfc3686_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc3686_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_rfc3686_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc3686_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	crypto_free_ablkcipher(ctx->child);
+	crypto_free_skcipher(ctx->child);
 }
 
-static struct crypto_instance *crypto_rfc3686_alloc(struct rtattr **tb)
+static void crypto_rfc3686_free(struct skcipher_instance *inst)
+{
+	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
+
+	crypto_drop_skcipher(spawn);
+	kfree(inst);
+}
+
+static int crypto_rfc3686_create(struct crypto_template *tmpl,
+				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	struct skcipher_instance *inst;
+	struct skcipher_alg *alg;
 	struct crypto_skcipher_spawn *spawn;
 	const char *cipher_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
-	if ((algt->type ^ CRYPTO_ALG_TYPE_BLKCIPHER) & algt->mask)
-		return ERR_PTR(-EINVAL);
+	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
+		return -EINVAL;
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
-		return ERR_CAST(cipher_name);
+		return PTR_ERR(cipher_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	spawn = crypto_instance_ctx(inst);
+	spawn = skcipher_instance_ctx(inst);
 
-	crypto_set_skcipher_spawn(spawn, inst);
-	err = crypto_grab_skcipher(spawn, cipher_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
+	err = crypto_grab_skcipher2(spawn, cipher_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_free_inst;
 
-	alg = crypto_skcipher_spawn_alg(spawn);
+	alg = crypto_spawn_skcipher_alg(spawn);
 
 	/* We only support 16-byte blocks. */
 	err = -EINVAL;
-	if (alg->cra_ablkcipher.ivsize != CTR_RFC3686_BLOCK_SIZE)
+	if (crypto_skcipher_alg_ivsize(alg) != CTR_RFC3686_BLOCK_SIZE)
 		goto err_drop_spawn;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
+	if (alg->base.cra_blocksize != 1)
 		goto err_drop_spawn;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "rfc3686(%s)",
-		     alg->cra_name) >= CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc3686(%s)", alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_spawn;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc3686(%s)", alg->cra_driver_name) >=
-			CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc3686(%s)", alg->base.cra_driver_name) >=
+	    CRYPTO_MAX_ALG_NAME)
 		goto err_drop_spawn;
 
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-			      (alg->cra_flags & CRYPTO_ALG_ASYNC);
-	inst->alg.cra_type = &crypto_ablkcipher_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
 
-	inst->alg.cra_ablkcipher.ivsize = CTR_RFC3686_IV_SIZE;
-	inst->alg.cra_ablkcipher.min_keysize =
-		alg->cra_ablkcipher.min_keysize + CTR_RFC3686_NONCE_SIZE;
-	inst->alg.cra_ablkcipher.max_keysize =
-		alg->cra_ablkcipher.max_keysize + CTR_RFC3686_NONCE_SIZE;
+	inst->alg.ivsize = CTR_RFC3686_IV_SIZE;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(alg);
+	inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg) +
+				CTR_RFC3686_NONCE_SIZE;
+	inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(alg) +
+				CTR_RFC3686_NONCE_SIZE;
 
-	inst->alg.cra_ablkcipher.geniv = "seqiv";
+	inst->alg.setkey = crypto_rfc3686_setkey;
+	inst->alg.encrypt = crypto_rfc3686_crypt;
+	inst->alg.decrypt = crypto_rfc3686_crypt;
 
-	inst->alg.cra_ablkcipher.setkey = crypto_rfc3686_setkey;
-	inst->alg.cra_ablkcipher.encrypt = crypto_rfc3686_crypt;
-	inst->alg.cra_ablkcipher.decrypt = crypto_rfc3686_crypt;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc3686_ctx);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc3686_ctx);
+	inst->alg.init = crypto_rfc3686_init_tfm;
+	inst->alg.exit = crypto_rfc3686_exit_tfm;
 
-	inst->alg.cra_init = crypto_rfc3686_init_tfm;
-	inst->alg.cra_exit = crypto_rfc3686_exit_tfm;
+	inst->free = crypto_rfc3686_free;
 
-	return inst;
+	err = skcipher_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_spawn;
+
+out:
+	return err;
 
 err_drop_spawn:
 	crypto_drop_skcipher(spawn);
 err_free_inst:
 	kfree(inst);
-	return ERR_PTR(err);
-}
-
-static void crypto_rfc3686_free(struct crypto_instance *inst)
-{
-	struct crypto_skcipher_spawn *spawn = crypto_instance_ctx(inst);
-
-	crypto_drop_skcipher(spawn);
-	kfree(inst);
+	goto out;
 }
 
 static struct crypto_template crypto_rfc3686_tmpl = {
 	.name = "rfc3686",
-	.alloc = crypto_rfc3686_alloc,
-	.free = crypto_rfc3686_free,
+	.create = crypto_rfc3686_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/cts.c b/crypto/cts.c
index e467ec0..5197618 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -40,7 +40,7 @@
  * rfc3962 includes errata information in its Appendix A.
  */
 
-#include <crypto/algapi.h>
+#include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -51,289 +51,364 @@
 #include <linux/slab.h>
 
 struct crypto_cts_ctx {
-	struct crypto_blkcipher *child;
+	struct crypto_skcipher *child;
 };
 
-static int crypto_cts_setkey(struct crypto_tfm *parent, const u8 *key,
+struct crypto_cts_reqctx {
+	struct scatterlist sg[2];
+	unsigned offset;
+	struct skcipher_request subreq;
+};
+
+static inline u8 *crypto_cts_reqctx_space(struct skcipher_request *req)
+{
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *child = ctx->child;
+
+	return PTR_ALIGN((u8 *)(rctx + 1) + crypto_skcipher_reqsize(child),
+			 crypto_skcipher_alignmask(tfm) + 1);
+}
+
+static int crypto_cts_setkey(struct crypto_skcipher *parent, const u8 *key,
 			     unsigned int keylen)
 {
-	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(parent);
-	struct crypto_blkcipher *child = ctx->child;
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(parent);
+	struct crypto_skcipher *child = ctx->child;
 	int err;
 
-	crypto_blkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_blkcipher_set_flags(child, crypto_tfm_get_flags(parent) &
-				       CRYPTO_TFM_REQ_MASK);
-	err = crypto_blkcipher_setkey(child, key, keylen);
-	crypto_tfm_set_flags(parent, crypto_blkcipher_get_flags(child) &
-				     CRYPTO_TFM_RES_MASK);
+	crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(parent) &
+					 CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(child, key, keylen);
+	crypto_skcipher_set_flags(parent, crypto_skcipher_get_flags(child) &
+					  CRYPTO_TFM_RES_MASK);
 	return err;
 }
 
-static int cts_cbc_encrypt(struct crypto_cts_ctx *ctx,
-			   struct blkcipher_desc *desc,
-			   struct scatterlist *dst,
-			   struct scatterlist *src,
-			   unsigned int offset,
-			   unsigned int nbytes)
+static void cts_cbc_crypt_done(struct crypto_async_request *areq, int err)
 {
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	u8 tmp[bsize], tmp2[bsize];
-	struct blkcipher_desc lcldesc;
-	struct scatterlist sgsrc[1], sgdst[1];
-	int lastn = nbytes - bsize;
-	u8 iv[bsize];
-	u8 s[bsize * 2], d[bsize * 2];
-	int err;
+	struct skcipher_request *req = areq->data;
 
-	if (lastn < 0)
-		return -EINVAL;
+	if (err == -EINPROGRESS)
+		return;
 
-	sg_init_table(sgsrc, 1);
-	sg_init_table(sgdst, 1);
-
-	memset(s, 0, sizeof(s));
-	scatterwalk_map_and_copy(s, src, offset, nbytes, 0);
-
-	memcpy(iv, desc->info, bsize);
-
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = iv;
-	lcldesc.flags = desc->flags;
-
-	sg_set_buf(&sgsrc[0], s, bsize);
-	sg_set_buf(&sgdst[0], tmp, bsize);
-	err = crypto_blkcipher_encrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
-
-	memcpy(d + bsize, tmp, lastn);
-
-	lcldesc.info = tmp;
-
-	sg_set_buf(&sgsrc[0], s + bsize, bsize);
-	sg_set_buf(&sgdst[0], tmp2, bsize);
-	err = crypto_blkcipher_encrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
-
-	memcpy(d, tmp2, bsize);
-
-	scatterwalk_map_and_copy(d, dst, offset, nbytes, 1);
-
-	memcpy(desc->info, tmp2, bsize);
-
-	return err;
+	skcipher_request_complete(req, err);
 }
 
-static int crypto_cts_encrypt(struct blkcipher_desc *desc,
-			      struct scatterlist *dst, struct scatterlist *src,
-			      unsigned int nbytes)
+static int cts_cbc_encrypt(struct skcipher_request *req)
 {
-	struct crypto_cts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	int tot_blocks = (nbytes + bsize - 1) / bsize;
-	int cbc_blocks = tot_blocks > 2 ? tot_blocks - 2 : 0;
-	struct blkcipher_desc lcldesc;
-	int err;
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	u8 d[bsize * 2] __attribute__ ((aligned(__alignof__(u32))));
+	struct scatterlist *sg;
+	unsigned int offset;
+	int lastn;
 
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = desc->info;
-	lcldesc.flags = desc->flags;
+	offset = rctx->offset;
+	lastn = req->cryptlen - offset;
 
-	if (tot_blocks == 1) {
-		err = crypto_blkcipher_encrypt_iv(&lcldesc, dst, src, bsize);
-	} else if (nbytes <= bsize * 2) {
-		err = cts_cbc_encrypt(ctx, desc, dst, src, 0, nbytes);
-	} else {
-		/* do normal function for tot_blocks - 2 */
-		err = crypto_blkcipher_encrypt_iv(&lcldesc, dst, src,
-							cbc_blocks * bsize);
-		if (err == 0) {
-			/* do cts for final two blocks */
-			err = cts_cbc_encrypt(ctx, desc, dst, src,
-						cbc_blocks * bsize,
-						nbytes - (cbc_blocks * bsize));
-		}
-	}
+	sg = scatterwalk_ffwd(rctx->sg, req->dst, offset - bsize);
+	scatterwalk_map_and_copy(d + bsize, sg, 0, bsize, 0);
 
-	return err;
+	memset(d, 0, bsize);
+	scatterwalk_map_and_copy(d, req->src, offset, lastn, 0);
+
+	scatterwalk_map_and_copy(d, sg, 0, bsize + lastn, 1);
+	memzero_explicit(d, sizeof(d));
+
+	skcipher_request_set_callback(subreq, req->base.flags &
+					      CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      cts_cbc_crypt_done, req);
+	skcipher_request_set_crypt(subreq, sg, sg, bsize, req->iv);
+	return crypto_skcipher_encrypt(subreq);
 }
 
-static int cts_cbc_decrypt(struct crypto_cts_ctx *ctx,
-			   struct blkcipher_desc *desc,
-			   struct scatterlist *dst,
-			   struct scatterlist *src,
-			   unsigned int offset,
-			   unsigned int nbytes)
+static void crypto_cts_encrypt_done(struct crypto_async_request *areq, int err)
 {
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	u8 tmp[bsize];
-	struct blkcipher_desc lcldesc;
-	struct scatterlist sgsrc[1], sgdst[1];
-	int lastn = nbytes - bsize;
-	u8 iv[bsize];
-	u8 s[bsize * 2], d[bsize * 2];
-	int err;
+	struct skcipher_request *req = areq->data;
 
-	if (lastn < 0)
-		return -EINVAL;
-
-	sg_init_table(sgsrc, 1);
-	sg_init_table(sgdst, 1);
-
-	scatterwalk_map_and_copy(s, src, offset, nbytes, 0);
-
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = iv;
-	lcldesc.flags = desc->flags;
-
-	/* 1. Decrypt Cn-1 (s) to create Dn (tmp)*/
-	memset(iv, 0, sizeof(iv));
-	sg_set_buf(&sgsrc[0], s, bsize);
-	sg_set_buf(&sgdst[0], tmp, bsize);
-	err = crypto_blkcipher_decrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
 	if (err)
-		return err;
-	/* 2. Pad Cn with zeros at the end to create C of length BB */
-	memset(iv, 0, sizeof(iv));
-	memcpy(iv, s + bsize, lastn);
-	/* 3. Exclusive-or Dn (tmp) with C (iv) to create Xn (tmp) */
-	crypto_xor(tmp, iv, bsize);
-	/* 4. Select the first Ln bytes of Xn (tmp) to create Pn */
-	memcpy(d + bsize, tmp, lastn);
+		goto out;
 
-	/* 5. Append the tail (BB - Ln) bytes of Xn (tmp) to Cn to create En */
-	memcpy(s + bsize + lastn, tmp + lastn, bsize - lastn);
-	/* 6. Decrypt En to create Pn-1 */
-	memzero_explicit(iv, sizeof(iv));
+	err = cts_cbc_encrypt(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
+		return;
 
-	sg_set_buf(&sgsrc[0], s + bsize, bsize);
-	sg_set_buf(&sgdst[0], d, bsize);
-	err = crypto_blkcipher_decrypt_iv(&lcldesc, sgdst, sgsrc, bsize);
-
-	/* XOR with previous block */
-	crypto_xor(d, desc->info, bsize);
-
-	scatterwalk_map_and_copy(d, dst, offset, nbytes, 1);
-
-	memcpy(desc->info, s, bsize);
-	return err;
+out:
+	skcipher_request_complete(req, err);
 }
 
-static int crypto_cts_decrypt(struct blkcipher_desc *desc,
-			      struct scatterlist *dst, struct scatterlist *src,
-			      unsigned int nbytes)
+static int crypto_cts_encrypt(struct skcipher_request *req)
 {
-	struct crypto_cts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	int bsize = crypto_blkcipher_blocksize(desc->tfm);
-	int tot_blocks = (nbytes + bsize - 1) / bsize;
-	int cbc_blocks = tot_blocks > 2 ? tot_blocks - 2 : 0;
-	struct blkcipher_desc lcldesc;
-	int err;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	unsigned int nbytes = req->cryptlen;
+	int cbc_blocks = (nbytes + bsize - 1) / bsize - 1;
+	unsigned int offset;
 
-	lcldesc.tfm = ctx->child;
-	lcldesc.info = desc->info;
-	lcldesc.flags = desc->flags;
+	skcipher_request_set_tfm(subreq, ctx->child);
 
-	if (tot_blocks == 1) {
-		err = crypto_blkcipher_decrypt_iv(&lcldesc, dst, src, bsize);
-	} else if (nbytes <= bsize * 2) {
-		err = cts_cbc_decrypt(ctx, desc, dst, src, 0, nbytes);
-	} else {
-		/* do normal function for tot_blocks - 2 */
-		err = crypto_blkcipher_decrypt_iv(&lcldesc, dst, src,
-							cbc_blocks * bsize);
-		if (err == 0) {
-			/* do cts for final two blocks */
-			err = cts_cbc_decrypt(ctx, desc, dst, src,
-						cbc_blocks * bsize,
-						nbytes - (cbc_blocks * bsize));
-		}
+	if (cbc_blocks <= 0) {
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      req->base.complete,
+					      req->base.data);
+		skcipher_request_set_crypt(subreq, req->src, req->dst, nbytes,
+					   req->iv);
+		return crypto_skcipher_encrypt(subreq);
 	}
-	return err;
+
+	offset = cbc_blocks * bsize;
+	rctx->offset = offset;
+
+	skcipher_request_set_callback(subreq, req->base.flags,
+				      crypto_cts_encrypt_done, req);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   offset, req->iv);
+
+	return crypto_skcipher_encrypt(subreq) ?:
+	       cts_cbc_encrypt(req);
 }
 
-static int crypto_cts_init_tfm(struct crypto_tfm *tfm)
+static int cts_cbc_decrypt(struct skcipher_request *req)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_blkcipher *cipher;
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	u8 d[bsize * 2] __attribute__ ((aligned(__alignof__(u32))));
+	struct scatterlist *sg;
+	unsigned int offset;
+	u8 *space;
+	int lastn;
 
-	cipher = crypto_spawn_blkcipher(spawn);
+	offset = rctx->offset;
+	lastn = req->cryptlen - offset;
+
+	sg = scatterwalk_ffwd(rctx->sg, req->dst, offset - bsize);
+
+	/* 1. Decrypt Cn-1 (s) to create Dn */
+	scatterwalk_map_and_copy(d + bsize, sg, 0, bsize, 0);
+	space = crypto_cts_reqctx_space(req);
+	crypto_xor(d + bsize, space, bsize);
+	/* 2. Pad Cn with zeros at the end to create C of length BB */
+	memset(d, 0, bsize);
+	scatterwalk_map_and_copy(d, req->src, offset, lastn, 0);
+	/* 3. Exclusive-or Dn with C to create Xn */
+	/* 4. Select the first Ln bytes of Xn to create Pn */
+	crypto_xor(d + bsize, d, lastn);
+
+	/* 5. Append the tail (BB - Ln) bytes of Xn to Cn to create En */
+	memcpy(d + lastn, d + bsize + lastn, bsize - lastn);
+	/* 6. Decrypt En to create Pn-1 */
+
+	scatterwalk_map_and_copy(d, sg, 0, bsize + lastn, 1);
+	memzero_explicit(d, sizeof(d));
+
+	skcipher_request_set_callback(subreq, req->base.flags &
+					      CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      cts_cbc_crypt_done, req);
+
+	skcipher_request_set_crypt(subreq, sg, sg, bsize, space);
+	return crypto_skcipher_decrypt(subreq);
+}
+
+static void crypto_cts_decrypt_done(struct crypto_async_request *areq, int err)
+{
+	struct skcipher_request *req = areq->data;
+
+	if (err)
+		goto out;
+
+	err = cts_cbc_decrypt(req);
+	if (err == -EINPROGRESS ||
+	    (err == -EBUSY && req->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG))
+		return;
+
+out:
+	skcipher_request_complete(req, err);
+}
+
+static int crypto_cts_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_cts_reqctx *rctx = skcipher_request_ctx(req);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_request *subreq = &rctx->subreq;
+	int bsize = crypto_skcipher_blocksize(tfm);
+	unsigned int nbytes = req->cryptlen;
+	int cbc_blocks = (nbytes + bsize - 1) / bsize - 1;
+	unsigned int offset;
+	u8 *space;
+
+	skcipher_request_set_tfm(subreq, ctx->child);
+
+	if (cbc_blocks <= 0) {
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      req->base.complete,
+					      req->base.data);
+		skcipher_request_set_crypt(subreq, req->src, req->dst, nbytes,
+					   req->iv);
+		return crypto_skcipher_decrypt(subreq);
+	}
+
+	skcipher_request_set_callback(subreq, req->base.flags,
+				      crypto_cts_decrypt_done, req);
+
+	space = crypto_cts_reqctx_space(req);
+
+	offset = cbc_blocks * bsize;
+	rctx->offset = offset;
+
+	if (cbc_blocks <= 1)
+		memcpy(space, req->iv, bsize);
+	else
+		scatterwalk_map_and_copy(space, req->src, offset - 2 * bsize,
+					 bsize, 0);
+
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   offset, req->iv);
+
+	return crypto_skcipher_decrypt(subreq) ?:
+	       cts_cbc_decrypt(req);
+}
+
+static int crypto_cts_init_tfm(struct crypto_skcipher *tfm)
+{
+	struct skcipher_instance *inst = skcipher_alg_instance(tfm);
+	struct crypto_skcipher_spawn *spawn = skcipher_instance_ctx(inst);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_skcipher *cipher;
+	unsigned reqsize;
+	unsigned bsize;
+	unsigned align;
+
+	cipher = crypto_spawn_skcipher2(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
+
+	align = crypto_skcipher_alignmask(tfm);
+	bsize = crypto_skcipher_blocksize(cipher);
+	reqsize = ALIGN(sizeof(struct crypto_cts_reqctx) +
+			crypto_skcipher_reqsize(cipher),
+			crypto_tfm_ctx_alignment()) +
+		  (align & ~(crypto_tfm_ctx_alignment() - 1)) + bsize;
+
+	crypto_skcipher_set_reqsize(tfm, reqsize);
+
 	return 0;
 }
 
-static void crypto_cts_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_cts_exit_tfm(struct crypto_skcipher *tfm)
 {
-	struct crypto_cts_ctx *ctx = crypto_tfm_ctx(tfm);
-	crypto_free_blkcipher(ctx->child);
+	struct crypto_cts_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_skcipher(ctx->child);
 }
 
-static struct crypto_instance *crypto_cts_alloc(struct rtattr **tb)
+static void crypto_cts_free(struct skcipher_instance *inst)
 {
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	crypto_drop_skcipher(skcipher_instance_ctx(inst));
+	kfree(inst);
+}
+
+static int crypto_cts_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct crypto_skcipher_spawn *spawn;
+	struct skcipher_instance *inst;
+	struct crypto_attr_type *algt;
+	struct skcipher_alg *alg;
+	const char *cipher_name;
 	int err;
 
-	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return PTR_ERR(algt);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask)
+		return -EINVAL;
+
+	cipher_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(cipher_name))
+		return PTR_ERR(cipher_name);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	spawn = skcipher_instance_ctx(inst);
+
+	crypto_set_skcipher_spawn(spawn, skcipher_crypto_instance(inst));
+	err = crypto_grab_skcipher2(spawn, cipher_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
-		return ERR_PTR(err);
+		goto err_free_inst;
 
-	alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_BLKCIPHER,
-				  CRYPTO_ALG_TYPE_MASK);
-	if (IS_ERR(alg))
-		return ERR_CAST(alg);
+	alg = crypto_spawn_skcipher_alg(spawn);
 
-	inst = ERR_PTR(-EINVAL);
-	if (!is_power_of_2(alg->cra_blocksize))
-		goto out_put_alg;
+	err = -EINVAL;
+	if (crypto_skcipher_alg_ivsize(alg) != alg->base.cra_blocksize)
+		goto err_drop_spawn;
 
-	if (strncmp(alg->cra_name, "cbc(", 4))
-		goto out_put_alg;
+	if (strncmp(alg->base.cra_name, "cbc(", 4))
+		goto err_drop_spawn;
 
-	inst = crypto_alloc_instance("cts", alg);
-	if (IS_ERR(inst))
-		goto out_put_alg;
+	err = crypto_inst_setname(skcipher_crypto_instance(inst), "cts",
+				  &alg->base);
+	if (err)
+		goto err_drop_spawn;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_blkcipher_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
 	/* We access the data as u32s when xoring. */
-	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
 
-	inst->alg.cra_blkcipher.ivsize = alg->cra_blocksize;
-	inst->alg.cra_blkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
-	inst->alg.cra_blkcipher.max_keysize = alg->cra_blkcipher.max_keysize;
+	inst->alg.ivsize = alg->base.cra_blocksize;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(alg);
+	inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(alg);
+	inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(alg);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_cts_ctx);
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_cts_ctx);
 
-	inst->alg.cra_init = crypto_cts_init_tfm;
-	inst->alg.cra_exit = crypto_cts_exit_tfm;
+	inst->alg.init = crypto_cts_init_tfm;
+	inst->alg.exit = crypto_cts_exit_tfm;
 
-	inst->alg.cra_blkcipher.setkey = crypto_cts_setkey;
-	inst->alg.cra_blkcipher.encrypt = crypto_cts_encrypt;
-	inst->alg.cra_blkcipher.decrypt = crypto_cts_decrypt;
+	inst->alg.setkey = crypto_cts_setkey;
+	inst->alg.encrypt = crypto_cts_encrypt;
+	inst->alg.decrypt = crypto_cts_decrypt;
 
-out_put_alg:
-	crypto_mod_put(alg);
-	return inst;
-}
+	inst->free = crypto_cts_free;
 
-static void crypto_cts_free(struct crypto_instance *inst)
-{
-	crypto_drop_spawn(crypto_instance_ctx(inst));
+	err = skcipher_register_instance(tmpl, inst);
+	if (err)
+		goto err_drop_spawn;
+
+out:
+	return err;
+
+err_drop_spawn:
+	crypto_drop_skcipher(spawn);
+err_free_inst:
 	kfree(inst);
+	goto out;
 }
 
 static struct crypto_template crypto_cts_tmpl = {
 	.name = "cts",
-	.alloc = crypto_cts_alloc,
-	.free = crypto_cts_free,
+	.create = crypto_cts_create,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/dh.c b/crypto/dh.c
new file mode 100644
index 0000000..9d19360
--- /dev/null
+++ b/crypto/dh.c
@@ -0,0 +1,189 @@
+/*  Diffie-Hellman Key Agreement Method [RFC2631]
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/kpp.h>
+#include <crypto/dh.h>
+#include <linux/mpi.h>
+
+struct dh_ctx {
+	MPI p;
+	MPI g;
+	MPI xa;
+};
+
+static inline void dh_clear_params(struct dh_ctx *ctx)
+{
+	mpi_free(ctx->p);
+	mpi_free(ctx->g);
+	ctx->p = NULL;
+	ctx->g = NULL;
+}
+
+static void dh_free_ctx(struct dh_ctx *ctx)
+{
+	dh_clear_params(ctx);
+	mpi_free(ctx->xa);
+	ctx->xa = NULL;
+}
+
+/*
+ * If base is g we compute the public key
+ *	ya = g^xa mod p; [RFC2631 sec 2.1.1]
+ * else if base if the counterpart public key we compute the shared secret
+ *	ZZ = yb^xa mod p; [RFC2631 sec 2.1.1]
+ */
+static int _compute_val(const struct dh_ctx *ctx, MPI base, MPI val)
+{
+	/* val = base^xa mod p */
+	return mpi_powm(val, base, ctx->xa, ctx->p);
+}
+
+static inline struct dh_ctx *dh_get_ctx(struct crypto_kpp *tfm)
+{
+	return kpp_tfm_ctx(tfm);
+}
+
+static int dh_check_params_length(unsigned int p_len)
+{
+	return (p_len < 1536) ? -EINVAL : 0;
+}
+
+static int dh_set_params(struct dh_ctx *ctx, struct dh *params)
+{
+	if (unlikely(!params->p || !params->g))
+		return -EINVAL;
+
+	if (dh_check_params_length(params->p_size << 3))
+		return -EINVAL;
+
+	ctx->p = mpi_read_raw_data(params->p, params->p_size);
+	if (!ctx->p)
+		return -EINVAL;
+
+	ctx->g = mpi_read_raw_data(params->g, params->g_size);
+	if (!ctx->g) {
+		mpi_free(ctx->p);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dh_set_secret(struct crypto_kpp *tfm, void *buf, unsigned int len)
+{
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+	struct dh params;
+
+	if (crypto_dh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	if (dh_set_params(ctx, &params) < 0)
+		return -EINVAL;
+
+	ctx->xa = mpi_read_raw_data(params.key, params.key_size);
+	if (!ctx->xa) {
+		dh_clear_params(ctx);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dh_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+	MPI base, val = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!val)
+		return -ENOMEM;
+
+	if (unlikely(!ctx->xa)) {
+		ret = -EINVAL;
+		goto err_free_val;
+	}
+
+	if (req->src) {
+		base = mpi_read_raw_from_sgl(req->src, req->src_len);
+		if (!base) {
+			ret = EINVAL;
+			goto err_free_val;
+		}
+	} else {
+		base = ctx->g;
+	}
+
+	ret = _compute_val(ctx, base, val);
+	if (ret)
+		goto err_free_base;
+
+	ret = mpi_write_to_sgl(val, req->dst, req->dst_len, &sign);
+	if (ret)
+		goto err_free_base;
+
+	if (sign < 0)
+		ret = -EBADMSG;
+err_free_base:
+	if (req->src)
+		mpi_free(base);
+err_free_val:
+	mpi_free(val);
+	return ret;
+}
+
+static int dh_max_size(struct crypto_kpp *tfm)
+{
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+
+	return mpi_get_size(ctx->p);
+}
+
+static void dh_exit_tfm(struct crypto_kpp *tfm)
+{
+	struct dh_ctx *ctx = dh_get_ctx(tfm);
+
+	dh_free_ctx(ctx);
+}
+
+static struct kpp_alg dh = {
+	.set_secret = dh_set_secret,
+	.generate_public_key = dh_compute_value,
+	.compute_shared_secret = dh_compute_value,
+	.max_size = dh_max_size,
+	.exit = dh_exit_tfm,
+	.base = {
+		.cra_name = "dh",
+		.cra_driver_name = "dh-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct dh_ctx),
+	},
+};
+
+static int dh_init(void)
+{
+	return crypto_register_kpp(&dh);
+}
+
+static void dh_exit(void)
+{
+	crypto_unregister_kpp(&dh);
+}
+
+module_init(dh_init);
+module_exit(dh_exit);
+MODULE_ALIAS_CRYPTO("dh");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("DH generic algorithm");
diff --git a/crypto/dh_helper.c b/crypto/dh_helper.c
new file mode 100644
index 0000000..02db76b
--- /dev/null
+++ b/crypto/dh_helper.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <crypto/dh.h>
+#include <crypto/kpp.h>
+
+#define DH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 3 * sizeof(int))
+
+static inline u8 *dh_pack_data(void *dst, const void *src, size_t size)
+{
+	memcpy(dst, src, size);
+	return dst + size;
+}
+
+static inline const u8 *dh_unpack_data(void *dst, const void *src, size_t size)
+{
+	memcpy(dst, src, size);
+	return src + size;
+}
+
+static inline int dh_data_size(const struct dh *p)
+{
+	return p->key_size + p->p_size + p->g_size;
+}
+
+int crypto_dh_key_len(const struct dh *p)
+{
+	return DH_KPP_SECRET_MIN_SIZE + dh_data_size(p);
+}
+EXPORT_SYMBOL_GPL(crypto_dh_key_len);
+
+int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params)
+{
+	u8 *ptr = buf;
+	struct kpp_secret secret = {
+		.type = CRYPTO_KPP_SECRET_TYPE_DH,
+		.len = len
+	};
+
+	if (unlikely(!buf))
+		return -EINVAL;
+
+	if (len != crypto_dh_key_len(params))
+		return -EINVAL;
+
+	ptr = dh_pack_data(ptr, &secret, sizeof(secret));
+	ptr = dh_pack_data(ptr, &params->key_size, sizeof(params->key_size));
+	ptr = dh_pack_data(ptr, &params->p_size, sizeof(params->p_size));
+	ptr = dh_pack_data(ptr, &params->g_size, sizeof(params->g_size));
+	ptr = dh_pack_data(ptr, params->key, params->key_size);
+	ptr = dh_pack_data(ptr, params->p, params->p_size);
+	dh_pack_data(ptr, params->g, params->g_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_dh_encode_key);
+
+int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params)
+{
+	const u8 *ptr = buf;
+	struct kpp_secret secret;
+
+	if (unlikely(!buf || len < DH_KPP_SECRET_MIN_SIZE))
+		return -EINVAL;
+
+	ptr = dh_unpack_data(&secret, ptr, sizeof(secret));
+	if (secret.type != CRYPTO_KPP_SECRET_TYPE_DH)
+		return -EINVAL;
+
+	ptr = dh_unpack_data(&params->key_size, ptr, sizeof(params->key_size));
+	ptr = dh_unpack_data(&params->p_size, ptr, sizeof(params->p_size));
+	ptr = dh_unpack_data(&params->g_size, ptr, sizeof(params->g_size));
+	if (secret.len != crypto_dh_key_len(params))
+		return -EINVAL;
+
+	/* Don't allocate memory. Set pointers to data within
+	 * the given buffer
+	 */
+	params->key = (void *)ptr;
+	params->p = (void *)(ptr + params->key_size);
+	params->g = (void *)(ptr + params->key_size + params->p_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_dh_decode_key);
diff --git a/crypto/drbg.c b/crypto/drbg.c
index 0a3538f..f752da3 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -252,10 +252,16 @@
 MODULE_ALIAS_CRYPTO("drbg_pr_ctr_aes128");
 MODULE_ALIAS_CRYPTO("drbg_nopr_ctr_aes128");
 
-static int drbg_kcapi_sym(struct drbg_state *drbg, const unsigned char *key,
-			  unsigned char *outval, const struct drbg_string *in);
+static void drbg_kcapi_symsetkey(struct drbg_state *drbg,
+				 const unsigned char *key);
+static int drbg_kcapi_sym(struct drbg_state *drbg, unsigned char *outval,
+			  const struct drbg_string *in);
 static int drbg_init_sym_kernel(struct drbg_state *drbg);
 static int drbg_fini_sym_kernel(struct drbg_state *drbg);
+static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
+			      u8 *inbuf, u32 inbuflen,
+			      u8 *outbuf, u32 outlen);
+#define DRBG_CTR_NULL_LEN 128
 
 /* BCC function for CTR DRBG as defined in 10.4.3 */
 static int drbg_ctr_bcc(struct drbg_state *drbg,
@@ -270,6 +276,7 @@
 	drbg_string_fill(&data, out, drbg_blocklen(drbg));
 
 	/* 10.4.3 step 2 / 4 */
+	drbg_kcapi_symsetkey(drbg, key);
 	list_for_each_entry(curr, in, list) {
 		const unsigned char *pos = curr->buf;
 		size_t len = curr->len;
@@ -278,7 +285,7 @@
 			/* 10.4.3 step 4.2 */
 			if (drbg_blocklen(drbg) == cnt) {
 				cnt = 0;
-				ret = drbg_kcapi_sym(drbg, key, out, &data);
+				ret = drbg_kcapi_sym(drbg, out, &data);
 				if (ret)
 					return ret;
 			}
@@ -290,7 +297,7 @@
 	}
 	/* 10.4.3 step 4.2 for last block */
 	if (cnt)
-		ret = drbg_kcapi_sym(drbg, key, out, &data);
+		ret = drbg_kcapi_sym(drbg, out, &data);
 
 	return ret;
 }
@@ -425,6 +432,7 @@
 	/* 10.4.2 step 12: overwriting of outval is implemented in next step */
 
 	/* 10.4.2 step 13 */
+	drbg_kcapi_symsetkey(drbg, temp);
 	while (generated_len < bytes_to_return) {
 		short blocklen = 0;
 		/*
@@ -432,7 +440,7 @@
 		 * implicit as the key is only drbg_blocklen in size based on
 		 * the implementation of the cipher function callback
 		 */
-		ret = drbg_kcapi_sym(drbg, temp, X, &cipherin);
+		ret = drbg_kcapi_sym(drbg, X, &cipherin);
 		if (ret)
 			goto out;
 		blocklen = (drbg_blocklen(drbg) <
@@ -476,13 +484,26 @@
 	unsigned char *temp = drbg->scratchpad;
 	unsigned char *df_data = drbg->scratchpad + drbg_statelen(drbg) +
 				 drbg_blocklen(drbg);
-	unsigned char *temp_p, *df_data_p; /* pointer to iterate over buffers */
-	unsigned int len = 0;
-	struct drbg_string cipherin;
 
 	if (3 > reseed)
 		memset(df_data, 0, drbg_statelen(drbg));
 
+	if (!reseed) {
+		/*
+		 * The DRBG uses the CTR mode of the underlying AES cipher. The
+		 * CTR mode increments the counter value after the AES operation
+		 * but SP800-90A requires that the counter is incremented before
+		 * the AES operation. Hence, we increment it at the time we set
+		 * it by one.
+		 */
+		crypto_inc(drbg->V, drbg_blocklen(drbg));
+
+		ret = crypto_skcipher_setkey(drbg->ctr_handle, drbg->C,
+					     drbg_keylen(drbg));
+		if (ret)
+			goto out;
+	}
+
 	/* 10.2.1.3.2 step 2 and 10.2.1.4.2 step 2 */
 	if (seed) {
 		ret = drbg_ctr_df(drbg, df_data, drbg_statelen(drbg), seed);
@@ -490,35 +511,20 @@
 			goto out;
 	}
 
-	drbg_string_fill(&cipherin, drbg->V, drbg_blocklen(drbg));
-	/*
-	 * 10.2.1.3.2 steps 2 and 3 are already covered as the allocation
-	 * zeroizes all memory during initialization
-	 */
-	while (len < (drbg_statelen(drbg))) {
-		/* 10.2.1.2 step 2.1 */
-		crypto_inc(drbg->V, drbg_blocklen(drbg));
-		/*
-		 * 10.2.1.2 step 2.2 */
-		ret = drbg_kcapi_sym(drbg, drbg->C, temp + len, &cipherin);
-		if (ret)
-			goto out;
-		/* 10.2.1.2 step 2.3 and 3 */
-		len += drbg_blocklen(drbg);
-	}
-
-	/* 10.2.1.2 step 4 */
-	temp_p = temp;
-	df_data_p = df_data;
-	for (len = 0; len < drbg_statelen(drbg); len++) {
-		*temp_p ^= *df_data_p;
-		df_data_p++; temp_p++;
-	}
+	ret = drbg_kcapi_sym_ctr(drbg, df_data, drbg_statelen(drbg),
+				 temp, drbg_statelen(drbg));
+	if (ret)
+		return ret;
 
 	/* 10.2.1.2 step 5 */
-	memcpy(drbg->C, temp, drbg_keylen(drbg));
+	ret = crypto_skcipher_setkey(drbg->ctr_handle, temp,
+				     drbg_keylen(drbg));
+	if (ret)
+		goto out;
 	/* 10.2.1.2 step 6 */
 	memcpy(drbg->V, temp + drbg_keylen(drbg), drbg_blocklen(drbg));
+	/* See above: increment counter by one to compensate timing of CTR op */
+	crypto_inc(drbg->V, drbg_blocklen(drbg));
 	ret = 0;
 
 out:
@@ -537,9 +543,8 @@
 			     unsigned char *buf, unsigned int buflen,
 			     struct list_head *addtl)
 {
-	int len = 0;
-	int ret = 0;
-	struct drbg_string data;
+	int ret;
+	int len = min_t(int, buflen, INT_MAX);
 
 	/* 10.2.1.5.2 step 2 */
 	if (addtl && !list_empty(addtl)) {
@@ -549,33 +554,16 @@
 	}
 
 	/* 10.2.1.5.2 step 4.1 */
-	crypto_inc(drbg->V, drbg_blocklen(drbg));
-	drbg_string_fill(&data, drbg->V, drbg_blocklen(drbg));
-	while (len < buflen) {
-		int outlen = 0;
-		/* 10.2.1.5.2 step 4.2 */
-		ret = drbg_kcapi_sym(drbg, drbg->C, drbg->scratchpad, &data);
-		if (ret) {
-			len = ret;
-			goto out;
-		}
-		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
-			  drbg_blocklen(drbg) : (buflen - len);
-		/* 10.2.1.5.2 step 4.3 */
-		memcpy(buf + len, drbg->scratchpad, outlen);
-		len += outlen;
-		/* 10.2.1.5.2 step 6 */
-		if (len < buflen)
-			crypto_inc(drbg->V, drbg_blocklen(drbg));
-	}
+	ret = drbg_kcapi_sym_ctr(drbg, drbg->ctr_null_value, DRBG_CTR_NULL_LEN,
+				 buf, len);
+	if (ret)
+		return ret;
 
 	/* 10.2.1.5.2 step 6 */
 	ret = drbg_ctr_update(drbg, NULL, 3);
 	if (ret)
 		len = ret;
 
-out:
-	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
 	return len;
 }
 
@@ -1145,11 +1133,11 @@
 	if (!drbg)
 		return;
 	kzfree(drbg->V);
-	drbg->V = NULL;
+	drbg->Vbuf = NULL;
 	kzfree(drbg->C);
-	drbg->C = NULL;
-	kzfree(drbg->scratchpad);
-	drbg->scratchpad = NULL;
+	drbg->Cbuf = NULL;
+	kzfree(drbg->scratchpadbuf);
+	drbg->scratchpadbuf = NULL;
 	drbg->reseed_ctr = 0;
 	drbg->d_ops = NULL;
 	drbg->core = NULL;
@@ -1185,12 +1173,18 @@
 		goto err;
 	}
 
-	drbg->V = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
-	if (!drbg->V)
+	ret = drbg->d_ops->crypto_init(drbg);
+	if (ret < 0)
 		goto err;
-	drbg->C = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
-	if (!drbg->C)
-		goto err;
+
+	drbg->Vbuf = kmalloc(drbg_statelen(drbg) + ret, GFP_KERNEL);
+	if (!drbg->Vbuf)
+		goto fini;
+	drbg->V = PTR_ALIGN(drbg->Vbuf, ret + 1);
+	drbg->Cbuf = kmalloc(drbg_statelen(drbg) + ret, GFP_KERNEL);
+	if (!drbg->Cbuf)
+		goto fini;
+	drbg->C = PTR_ALIGN(drbg->Cbuf, ret + 1);
 	/* scratchpad is only generated for CTR and Hash */
 	if (drbg->core->flags & DRBG_HMAC)
 		sb_size = 0;
@@ -1204,13 +1198,16 @@
 		sb_size = drbg_statelen(drbg) + drbg_blocklen(drbg);
 
 	if (0 < sb_size) {
-		drbg->scratchpad = kzalloc(sb_size, GFP_KERNEL);
-		if (!drbg->scratchpad)
-			goto err;
+		drbg->scratchpadbuf = kzalloc(sb_size + ret, GFP_KERNEL);
+		if (!drbg->scratchpadbuf)
+			goto fini;
+		drbg->scratchpad = PTR_ALIGN(drbg->scratchpadbuf, ret + 1);
 	}
 
 	return 0;
 
+fini:
+	drbg->d_ops->crypto_fini(drbg);
 err:
 	drbg_dealloc_state(drbg);
 	return ret;
@@ -1478,10 +1475,6 @@
 		if (ret)
 			goto unlock;
 
-		ret = -EFAULT;
-		if (drbg->d_ops->crypto_init(drbg))
-			goto err;
-
 		ret = drbg_prepare_hrng(drbg);
 		if (ret)
 			goto free_everything;
@@ -1505,8 +1498,6 @@
 	mutex_unlock(&drbg->drbg_mutex);
 	return ret;
 
-err:
-	drbg_dealloc_state(drbg);
 unlock:
 	mutex_unlock(&drbg->drbg_mutex);
 	return ret;
@@ -1591,7 +1582,8 @@
 	sdesc->shash.tfm = tfm;
 	sdesc->shash.flags = 0;
 	drbg->priv_data = sdesc;
-	return 0;
+
+	return crypto_shash_alignmask(tfm);
 }
 
 static int drbg_fini_hash_kernel(struct drbg_state *drbg)
@@ -1627,10 +1619,45 @@
 #endif /* (CONFIG_CRYPTO_DRBG_HASH || CONFIG_CRYPTO_DRBG_HMAC) */
 
 #ifdef CONFIG_CRYPTO_DRBG_CTR
+static int drbg_fini_sym_kernel(struct drbg_state *drbg)
+{
+	struct crypto_cipher *tfm =
+		(struct crypto_cipher *)drbg->priv_data;
+	if (tfm)
+		crypto_free_cipher(tfm);
+	drbg->priv_data = NULL;
+
+	if (drbg->ctr_handle)
+		crypto_free_skcipher(drbg->ctr_handle);
+	drbg->ctr_handle = NULL;
+
+	if (drbg->ctr_req)
+		skcipher_request_free(drbg->ctr_req);
+	drbg->ctr_req = NULL;
+
+	kfree(drbg->ctr_null_value_buf);
+	drbg->ctr_null_value = NULL;
+
+	return 0;
+}
+
+static void drbg_skcipher_cb(struct crypto_async_request *req, int error)
+{
+	struct drbg_state *drbg = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+	drbg->ctr_async_err = error;
+	complete(&drbg->ctr_completion);
+}
+
 static int drbg_init_sym_kernel(struct drbg_state *drbg)
 {
-	int ret = 0;
 	struct crypto_cipher *tfm;
+	struct crypto_skcipher *sk_tfm;
+	struct skcipher_request *req;
+	unsigned int alignmask;
+	char ctr_name[CRYPTO_MAX_ALG_NAME];
 
 	tfm = crypto_alloc_cipher(drbg->core->backend_cra_name, 0, 0);
 	if (IS_ERR(tfm)) {
@@ -1640,31 +1667,103 @@
 	}
 	BUG_ON(drbg_blocklen(drbg) != crypto_cipher_blocksize(tfm));
 	drbg->priv_data = tfm;
-	return ret;
+
+	if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)",
+	    drbg->core->backend_cra_name) >= CRYPTO_MAX_ALG_NAME) {
+		drbg_fini_sym_kernel(drbg);
+		return -EINVAL;
+	}
+	sk_tfm = crypto_alloc_skcipher(ctr_name, 0, 0);
+	if (IS_ERR(sk_tfm)) {
+		pr_info("DRBG: could not allocate CTR cipher TFM handle: %s\n",
+				ctr_name);
+		drbg_fini_sym_kernel(drbg);
+		return PTR_ERR(sk_tfm);
+	}
+	drbg->ctr_handle = sk_tfm;
+
+	req = skcipher_request_alloc(sk_tfm, GFP_KERNEL);
+	if (!req) {
+		pr_info("DRBG: could not allocate request queue\n");
+		drbg_fini_sym_kernel(drbg);
+		return -ENOMEM;
+	}
+	drbg->ctr_req = req;
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					drbg_skcipher_cb, drbg);
+
+	alignmask = crypto_skcipher_alignmask(sk_tfm);
+	drbg->ctr_null_value_buf = kzalloc(DRBG_CTR_NULL_LEN + alignmask,
+					   GFP_KERNEL);
+	if (!drbg->ctr_null_value_buf) {
+		drbg_fini_sym_kernel(drbg);
+		return -ENOMEM;
+	}
+	drbg->ctr_null_value = (u8 *)PTR_ALIGN(drbg->ctr_null_value_buf,
+					       alignmask + 1);
+
+	return alignmask;
 }
 
-static int drbg_fini_sym_kernel(struct drbg_state *drbg)
-{
-	struct crypto_cipher *tfm =
-		(struct crypto_cipher *)drbg->priv_data;
-	if (tfm)
-		crypto_free_cipher(tfm);
-	drbg->priv_data = NULL;
-	return 0;
-}
-
-static int drbg_kcapi_sym(struct drbg_state *drbg, const unsigned char *key,
-			  unsigned char *outval, const struct drbg_string *in)
+static void drbg_kcapi_symsetkey(struct drbg_state *drbg,
+				 const unsigned char *key)
 {
 	struct crypto_cipher *tfm =
 		(struct crypto_cipher *)drbg->priv_data;
 
 	crypto_cipher_setkey(tfm, key, (drbg_keylen(drbg)));
+}
+
+static int drbg_kcapi_sym(struct drbg_state *drbg, unsigned char *outval,
+			  const struct drbg_string *in)
+{
+	struct crypto_cipher *tfm =
+		(struct crypto_cipher *)drbg->priv_data;
+
 	/* there is only component in *in */
 	BUG_ON(in->len < drbg_blocklen(drbg));
 	crypto_cipher_encrypt_one(tfm, outval, in->buf);
 	return 0;
 }
+
+static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
+			      u8 *inbuf, u32 inlen,
+			      u8 *outbuf, u32 outlen)
+{
+	struct scatterlist sg_in;
+
+	sg_init_one(&sg_in, inbuf, inlen);
+
+	while (outlen) {
+		u32 cryptlen = min_t(u32, inlen, outlen);
+		struct scatterlist sg_out;
+		int ret;
+
+		sg_init_one(&sg_out, outbuf, cryptlen);
+		skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out,
+					   cryptlen, drbg->V);
+		ret = crypto_skcipher_encrypt(drbg->ctr_req);
+		switch (ret) {
+		case 0:
+			break;
+		case -EINPROGRESS:
+		case -EBUSY:
+			ret = wait_for_completion_interruptible(
+				&drbg->ctr_completion);
+			if (!ret && !drbg->ctr_async_err) {
+				reinit_completion(&drbg->ctr_completion);
+				break;
+			}
+		default:
+			return ret;
+		}
+		init_completion(&drbg->ctr_completion);
+
+		outlen -= cryptlen;
+	}
+
+	return 0;
+}
 #endif /* CONFIG_CRYPTO_DRBG_CTR */
 
 /***************************************************************
diff --git a/crypto/ecc.c b/crypto/ecc.c
new file mode 100644
index 0000000..414c78a
--- /dev/null
+++ b/crypto/ecc.c
@@ -0,0 +1,1018 @@
+/*
+ * Copyright (c) 2013, Kenneth MacKay
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *  * Redistributions of source code must retain the above copyright
+ *   notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/swab.h>
+#include <linux/fips.h>
+#include <crypto/ecdh.h>
+
+#include "ecc.h"
+#include "ecc_curve_defs.h"
+
+typedef struct {
+	u64 m_low;
+	u64 m_high;
+} uint128_t;
+
+static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
+{
+	switch (curve_id) {
+	/* In FIPS mode only allow P256 and higher */
+	case ECC_CURVE_NIST_P192:
+		return fips_enabled ? NULL : &nist_p192;
+	case ECC_CURVE_NIST_P256:
+		return &nist_p256;
+	default:
+		return NULL;
+	}
+}
+
+static u64 *ecc_alloc_digits_space(unsigned int ndigits)
+{
+	size_t len = ndigits * sizeof(u64);
+
+	if (!len)
+		return NULL;
+
+	return kmalloc(len, GFP_KERNEL);
+}
+
+static void ecc_free_digits_space(u64 *space)
+{
+	kzfree(space);
+}
+
+static struct ecc_point *ecc_alloc_point(unsigned int ndigits)
+{
+	struct ecc_point *p = kmalloc(sizeof(*p), GFP_KERNEL);
+
+	if (!p)
+		return NULL;
+
+	p->x = ecc_alloc_digits_space(ndigits);
+	if (!p->x)
+		goto err_alloc_x;
+
+	p->y = ecc_alloc_digits_space(ndigits);
+	if (!p->y)
+		goto err_alloc_y;
+
+	p->ndigits = ndigits;
+
+	return p;
+
+err_alloc_y:
+	ecc_free_digits_space(p->x);
+err_alloc_x:
+	kfree(p);
+	return NULL;
+}
+
+static void ecc_free_point(struct ecc_point *p)
+{
+	if (!p)
+		return;
+
+	kzfree(p->x);
+	kzfree(p->y);
+	kzfree(p);
+}
+
+static void vli_clear(u64 *vli, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		vli[i] = 0;
+}
+
+/* Returns true if vli == 0, false otherwise. */
+static bool vli_is_zero(const u64 *vli, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		if (vli[i])
+			return false;
+	}
+
+	return true;
+}
+
+/* Returns nonzero if bit bit of vli is set. */
+static u64 vli_test_bit(const u64 *vli, unsigned int bit)
+{
+	return (vli[bit / 64] & ((u64)1 << (bit % 64)));
+}
+
+/* Counts the number of 64-bit "digits" in vli. */
+static unsigned int vli_num_digits(const u64 *vli, unsigned int ndigits)
+{
+	int i;
+
+	/* Search from the end until we find a non-zero digit.
+	 * We do it in reverse because we expect that most digits will
+	 * be nonzero.
+	 */
+	for (i = ndigits - 1; i >= 0 && vli[i] == 0; i--);
+
+	return (i + 1);
+}
+
+/* Counts the number of bits required for vli. */
+static unsigned int vli_num_bits(const u64 *vli, unsigned int ndigits)
+{
+	unsigned int i, num_digits;
+	u64 digit;
+
+	num_digits = vli_num_digits(vli, ndigits);
+	if (num_digits == 0)
+		return 0;
+
+	digit = vli[num_digits - 1];
+	for (i = 0; digit; i++)
+		digit >>= 1;
+
+	return ((num_digits - 1) * 64 + i);
+}
+
+/* Sets dest = src. */
+static void vli_set(u64 *dest, const u64 *src, unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		dest[i] = src[i];
+}
+
+/* Returns sign of left - right. */
+static int vli_cmp(const u64 *left, const u64 *right, unsigned int ndigits)
+{
+	int i;
+
+	for (i = ndigits - 1; i >= 0; i--) {
+		if (left[i] > right[i])
+			return 1;
+		else if (left[i] < right[i])
+			return -1;
+	}
+
+	return 0;
+}
+
+/* Computes result = in << c, returning carry. Can modify in place
+ * (if result == in). 0 < shift < 64.
+ */
+static u64 vli_lshift(u64 *result, const u64 *in, unsigned int shift,
+		      unsigned int ndigits)
+{
+	u64 carry = 0;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 temp = in[i];
+
+		result[i] = (temp << shift) | carry;
+		carry = temp >> (64 - shift);
+	}
+
+	return carry;
+}
+
+/* Computes vli = vli >> 1. */
+static void vli_rshift1(u64 *vli, unsigned int ndigits)
+{
+	u64 *end = vli;
+	u64 carry = 0;
+
+	vli += ndigits;
+
+	while (vli-- > end) {
+		u64 temp = *vli;
+		*vli = (temp >> 1) | carry;
+		carry = temp << 63;
+	}
+}
+
+/* Computes result = left + right, returning carry. Can modify in place. */
+static u64 vli_add(u64 *result, const u64 *left, const u64 *right,
+		   unsigned int ndigits)
+{
+	u64 carry = 0;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 sum;
+
+		sum = left[i] + right[i] + carry;
+		if (sum != left[i])
+			carry = (sum < left[i]);
+
+		result[i] = sum;
+	}
+
+	return carry;
+}
+
+/* Computes result = left - right, returning borrow. Can modify in place. */
+static u64 vli_sub(u64 *result, const u64 *left, const u64 *right,
+		   unsigned int ndigits)
+{
+	u64 borrow = 0;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 diff;
+
+		diff = left[i] - right[i] - borrow;
+		if (diff != left[i])
+			borrow = (diff > left[i]);
+
+		result[i] = diff;
+	}
+
+	return borrow;
+}
+
+static uint128_t mul_64_64(u64 left, u64 right)
+{
+	u64 a0 = left & 0xffffffffull;
+	u64 a1 = left >> 32;
+	u64 b0 = right & 0xffffffffull;
+	u64 b1 = right >> 32;
+	u64 m0 = a0 * b0;
+	u64 m1 = a0 * b1;
+	u64 m2 = a1 * b0;
+	u64 m3 = a1 * b1;
+	uint128_t result;
+
+	m2 += (m0 >> 32);
+	m2 += m1;
+
+	/* Overflow */
+	if (m2 < m1)
+		m3 += 0x100000000ull;
+
+	result.m_low = (m0 & 0xffffffffull) | (m2 << 32);
+	result.m_high = m3 + (m2 >> 32);
+
+	return result;
+}
+
+static uint128_t add_128_128(uint128_t a, uint128_t b)
+{
+	uint128_t result;
+
+	result.m_low = a.m_low + b.m_low;
+	result.m_high = a.m_high + b.m_high + (result.m_low < a.m_low);
+
+	return result;
+}
+
+static void vli_mult(u64 *result, const u64 *left, const u64 *right,
+		     unsigned int ndigits)
+{
+	uint128_t r01 = { 0, 0 };
+	u64 r2 = 0;
+	unsigned int i, k;
+
+	/* Compute each digit of result in sequence, maintaining the
+	 * carries.
+	 */
+	for (k = 0; k < ndigits * 2 - 1; k++) {
+		unsigned int min;
+
+		if (k < ndigits)
+			min = 0;
+		else
+			min = (k + 1) - ndigits;
+
+		for (i = min; i <= k && i < ndigits; i++) {
+			uint128_t product;
+
+			product = mul_64_64(left[i], right[k - i]);
+
+			r01 = add_128_128(r01, product);
+			r2 += (r01.m_high < product.m_high);
+		}
+
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = r2;
+		r2 = 0;
+	}
+
+	result[ndigits * 2 - 1] = r01.m_low;
+}
+
+static void vli_square(u64 *result, const u64 *left, unsigned int ndigits)
+{
+	uint128_t r01 = { 0, 0 };
+	u64 r2 = 0;
+	int i, k;
+
+	for (k = 0; k < ndigits * 2 - 1; k++) {
+		unsigned int min;
+
+		if (k < ndigits)
+			min = 0;
+		else
+			min = (k + 1) - ndigits;
+
+		for (i = min; i <= k && i <= k - i; i++) {
+			uint128_t product;
+
+			product = mul_64_64(left[i], left[k - i]);
+
+			if (i < k - i) {
+				r2 += product.m_high >> 63;
+				product.m_high = (product.m_high << 1) |
+						 (product.m_low >> 63);
+				product.m_low <<= 1;
+			}
+
+			r01 = add_128_128(r01, product);
+			r2 += (r01.m_high < product.m_high);
+		}
+
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = r2;
+		r2 = 0;
+	}
+
+	result[ndigits * 2 - 1] = r01.m_low;
+}
+
+/* Computes result = (left + right) % mod.
+ * Assumes that left < mod and right < mod, result != mod.
+ */
+static void vli_mod_add(u64 *result, const u64 *left, const u64 *right,
+			const u64 *mod, unsigned int ndigits)
+{
+	u64 carry;
+
+	carry = vli_add(result, left, right, ndigits);
+
+	/* result > mod (result = mod + remainder), so subtract mod to
+	 * get remainder.
+	 */
+	if (carry || vli_cmp(result, mod, ndigits) >= 0)
+		vli_sub(result, result, mod, ndigits);
+}
+
+/* Computes result = (left - right) % mod.
+ * Assumes that left < mod and right < mod, result != mod.
+ */
+static void vli_mod_sub(u64 *result, const u64 *left, const u64 *right,
+			const u64 *mod, unsigned int ndigits)
+{
+	u64 borrow = vli_sub(result, left, right, ndigits);
+
+	/* In this case, p_result == -diff == (max int) - diff.
+	 * Since -x % d == d - x, we can get the correct result from
+	 * result + mod (with overflow).
+	 */
+	if (borrow)
+		vli_add(result, result, mod, ndigits);
+}
+
+/* Computes p_result = p_product % curve_p.
+ * See algorithm 5 and 6 from
+ * http://www.isys.uni-klu.ac.at/PDF/2001-0126-MT.pdf
+ */
+static void vli_mmod_fast_192(u64 *result, const u64 *product,
+			      const u64 *curve_prime, u64 *tmp)
+{
+	const unsigned int ndigits = 3;
+	int carry;
+
+	vli_set(result, product, ndigits);
+
+	vli_set(tmp, &product[3], ndigits);
+	carry = vli_add(result, result, tmp, ndigits);
+
+	tmp[0] = 0;
+	tmp[1] = product[3];
+	tmp[2] = product[4];
+	carry += vli_add(result, result, tmp, ndigits);
+
+	tmp[0] = tmp[1] = product[5];
+	tmp[2] = 0;
+	carry += vli_add(result, result, tmp, ndigits);
+
+	while (carry || vli_cmp(curve_prime, result, ndigits) != 1)
+		carry -= vli_sub(result, result, curve_prime, ndigits);
+}
+
+/* Computes result = product % curve_prime
+ * from http://www.nsa.gov/ia/_files/nist-routines.pdf
+ */
+static void vli_mmod_fast_256(u64 *result, const u64 *product,
+			      const u64 *curve_prime, u64 *tmp)
+{
+	int carry;
+	const unsigned int ndigits = 4;
+
+	/* t */
+	vli_set(result, product, ndigits);
+
+	/* s1 */
+	tmp[0] = 0;
+	tmp[1] = product[5] & 0xffffffff00000000ull;
+	tmp[2] = product[6];
+	tmp[3] = product[7];
+	carry = vli_lshift(tmp, tmp, 1, ndigits);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s2 */
+	tmp[1] = product[6] << 32;
+	tmp[2] = (product[6] >> 32) | (product[7] << 32);
+	tmp[3] = product[7] >> 32;
+	carry += vli_lshift(tmp, tmp, 1, ndigits);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s3 */
+	tmp[0] = product[4];
+	tmp[1] = product[5] & 0xffffffff;
+	tmp[2] = 0;
+	tmp[3] = product[7];
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s4 */
+	tmp[0] = (product[4] >> 32) | (product[5] << 32);
+	tmp[1] = (product[5] >> 32) | (product[6] & 0xffffffff00000000ull);
+	tmp[2] = product[7];
+	tmp[3] = (product[6] >> 32) | (product[4] << 32);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* d1 */
+	tmp[0] = (product[5] >> 32) | (product[6] << 32);
+	tmp[1] = (product[6] >> 32);
+	tmp[2] = 0;
+	tmp[3] = (product[4] & 0xffffffff) | (product[5] << 32);
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d2 */
+	tmp[0] = product[6];
+	tmp[1] = product[7];
+	tmp[2] = 0;
+	tmp[3] = (product[4] >> 32) | (product[5] & 0xffffffff00000000ull);
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d3 */
+	tmp[0] = (product[6] >> 32) | (product[7] << 32);
+	tmp[1] = (product[7] >> 32) | (product[4] << 32);
+	tmp[2] = (product[4] >> 32) | (product[5] << 32);
+	tmp[3] = (product[6] << 32);
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d4 */
+	tmp[0] = product[7];
+	tmp[1] = product[4] & 0xffffffff00000000ull;
+	tmp[2] = product[5];
+	tmp[3] = product[6] & 0xffffffff00000000ull;
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	if (carry < 0) {
+		do {
+			carry += vli_add(result, result, curve_prime, ndigits);
+		} while (carry < 0);
+	} else {
+		while (carry || vli_cmp(curve_prime, result, ndigits) != 1)
+			carry -= vli_sub(result, result, curve_prime, ndigits);
+	}
+}
+
+/* Computes result = product % curve_prime
+ *  from http://www.nsa.gov/ia/_files/nist-routines.pdf
+*/
+static bool vli_mmod_fast(u64 *result, u64 *product,
+			  const u64 *curve_prime, unsigned int ndigits)
+{
+	u64 tmp[2 * ndigits];
+
+	switch (ndigits) {
+	case 3:
+		vli_mmod_fast_192(result, product, curve_prime, tmp);
+		break;
+	case 4:
+		vli_mmod_fast_256(result, product, curve_prime, tmp);
+		break;
+	default:
+		pr_err("unsupports digits size!\n");
+		return false;
+	}
+
+	return true;
+}
+
+/* Computes result = (left * right) % curve_prime. */
+static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
+			      const u64 *curve_prime, unsigned int ndigits)
+{
+	u64 product[2 * ndigits];
+
+	vli_mult(product, left, right, ndigits);
+	vli_mmod_fast(result, product, curve_prime, ndigits);
+}
+
+/* Computes result = left^2 % curve_prime. */
+static void vli_mod_square_fast(u64 *result, const u64 *left,
+				const u64 *curve_prime, unsigned int ndigits)
+{
+	u64 product[2 * ndigits];
+
+	vli_square(product, left, ndigits);
+	vli_mmod_fast(result, product, curve_prime, ndigits);
+}
+
+#define EVEN(vli) (!(vli[0] & 1))
+/* Computes result = (1 / p_input) % mod. All VLIs are the same size.
+ * See "From Euclid's GCD to Montgomery Multiplication to the Great Divide"
+ * https://labs.oracle.com/techrep/2001/smli_tr-2001-95.pdf
+ */
+static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
+			unsigned int ndigits)
+{
+	u64 a[ndigits], b[ndigits];
+	u64 u[ndigits], v[ndigits];
+	u64 carry;
+	int cmp_result;
+
+	if (vli_is_zero(input, ndigits)) {
+		vli_clear(result, ndigits);
+		return;
+	}
+
+	vli_set(a, input, ndigits);
+	vli_set(b, mod, ndigits);
+	vli_clear(u, ndigits);
+	u[0] = 1;
+	vli_clear(v, ndigits);
+
+	while ((cmp_result = vli_cmp(a, b, ndigits)) != 0) {
+		carry = 0;
+
+		if (EVEN(a)) {
+			vli_rshift1(a, ndigits);
+
+			if (!EVEN(u))
+				carry = vli_add(u, u, mod, ndigits);
+
+			vli_rshift1(u, ndigits);
+			if (carry)
+				u[ndigits - 1] |= 0x8000000000000000ull;
+		} else if (EVEN(b)) {
+			vli_rshift1(b, ndigits);
+
+			if (!EVEN(v))
+				carry = vli_add(v, v, mod, ndigits);
+
+			vli_rshift1(v, ndigits);
+			if (carry)
+				v[ndigits - 1] |= 0x8000000000000000ull;
+		} else if (cmp_result > 0) {
+			vli_sub(a, a, b, ndigits);
+			vli_rshift1(a, ndigits);
+
+			if (vli_cmp(u, v, ndigits) < 0)
+				vli_add(u, u, mod, ndigits);
+
+			vli_sub(u, u, v, ndigits);
+			if (!EVEN(u))
+				carry = vli_add(u, u, mod, ndigits);
+
+			vli_rshift1(u, ndigits);
+			if (carry)
+				u[ndigits - 1] |= 0x8000000000000000ull;
+		} else {
+			vli_sub(b, b, a, ndigits);
+			vli_rshift1(b, ndigits);
+
+			if (vli_cmp(v, u, ndigits) < 0)
+				vli_add(v, v, mod, ndigits);
+
+			vli_sub(v, v, u, ndigits);
+			if (!EVEN(v))
+				carry = vli_add(v, v, mod, ndigits);
+
+			vli_rshift1(v, ndigits);
+			if (carry)
+				v[ndigits - 1] |= 0x8000000000000000ull;
+		}
+	}
+
+	vli_set(result, u, ndigits);
+}
+
+/* ------ Point operations ------ */
+
+/* Returns true if p_point is the point at infinity, false otherwise. */
+static bool ecc_point_is_zero(const struct ecc_point *point)
+{
+	return (vli_is_zero(point->x, point->ndigits) &&
+		vli_is_zero(point->y, point->ndigits));
+}
+
+/* Point multiplication algorithm using Montgomery's ladder with co-Z
+ * coordinates. From http://eprint.iacr.org/2011/338.pdf
+ */
+
+/* Double in place */
+static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
+				      u64 *curve_prime, unsigned int ndigits)
+{
+	/* t1 = x, t2 = y, t3 = z */
+	u64 t4[ndigits];
+	u64 t5[ndigits];
+
+	if (vli_is_zero(z1, ndigits))
+		return;
+
+	/* t4 = y1^2 */
+	vli_mod_square_fast(t4, y1, curve_prime, ndigits);
+	/* t5 = x1*y1^2 = A */
+	vli_mod_mult_fast(t5, x1, t4, curve_prime, ndigits);
+	/* t4 = y1^4 */
+	vli_mod_square_fast(t4, t4, curve_prime, ndigits);
+	/* t2 = y1*z1 = z3 */
+	vli_mod_mult_fast(y1, y1, z1, curve_prime, ndigits);
+	/* t3 = z1^2 */
+	vli_mod_square_fast(z1, z1, curve_prime, ndigits);
+
+	/* t1 = x1 + z1^2 */
+	vli_mod_add(x1, x1, z1, curve_prime, ndigits);
+	/* t3 = 2*z1^2 */
+	vli_mod_add(z1, z1, z1, curve_prime, ndigits);
+	/* t3 = x1 - z1^2 */
+	vli_mod_sub(z1, x1, z1, curve_prime, ndigits);
+	/* t1 = x1^2 - z1^4 */
+	vli_mod_mult_fast(x1, x1, z1, curve_prime, ndigits);
+
+	/* t3 = 2*(x1^2 - z1^4) */
+	vli_mod_add(z1, x1, x1, curve_prime, ndigits);
+	/* t1 = 3*(x1^2 - z1^4) */
+	vli_mod_add(x1, x1, z1, curve_prime, ndigits);
+	if (vli_test_bit(x1, 0)) {
+		u64 carry = vli_add(x1, x1, curve_prime, ndigits);
+
+		vli_rshift1(x1, ndigits);
+		x1[ndigits - 1] |= carry << 63;
+	} else {
+		vli_rshift1(x1, ndigits);
+	}
+	/* t1 = 3/2*(x1^2 - z1^4) = B */
+
+	/* t3 = B^2 */
+	vli_mod_square_fast(z1, x1, curve_prime, ndigits);
+	/* t3 = B^2 - A */
+	vli_mod_sub(z1, z1, t5, curve_prime, ndigits);
+	/* t3 = B^2 - 2A = x3 */
+	vli_mod_sub(z1, z1, t5, curve_prime, ndigits);
+	/* t5 = A - x3 */
+	vli_mod_sub(t5, t5, z1, curve_prime, ndigits);
+	/* t1 = B * (A - x3) */
+	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	/* t4 = B * (A - x3) - y1^4 = y3 */
+	vli_mod_sub(t4, x1, t4, curve_prime, ndigits);
+
+	vli_set(x1, z1, ndigits);
+	vli_set(z1, y1, ndigits);
+	vli_set(y1, t4, ndigits);
+}
+
+/* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */
+static void apply_z(u64 *x1, u64 *y1, u64 *z, u64 *curve_prime,
+		    unsigned int ndigits)
+{
+	u64 t1[ndigits];
+
+	vli_mod_square_fast(t1, z, curve_prime, ndigits);    /* z^2 */
+	vli_mod_mult_fast(x1, x1, t1, curve_prime, ndigits); /* x1 * z^2 */
+	vli_mod_mult_fast(t1, t1, z, curve_prime, ndigits);  /* z^3 */
+	vli_mod_mult_fast(y1, y1, t1, curve_prime, ndigits); /* y1 * z^3 */
+}
+
+/* P = (x1, y1) => 2P, (x2, y2) => P' */
+static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+				u64 *p_initial_z, u64 *curve_prime,
+				unsigned int ndigits)
+{
+	u64 z[ndigits];
+
+	vli_set(x2, x1, ndigits);
+	vli_set(y2, y1, ndigits);
+
+	vli_clear(z, ndigits);
+	z[0] = 1;
+
+	if (p_initial_z)
+		vli_set(z, p_initial_z, ndigits);
+
+	apply_z(x1, y1, z, curve_prime, ndigits);
+
+	ecc_point_double_jacobian(x1, y1, z, curve_prime, ndigits);
+
+	apply_z(x2, y2, z, curve_prime, ndigits);
+}
+
+/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
+ * Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3)
+ * or P => P', Q => P + Q
+ */
+static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
+		     unsigned int ndigits)
+{
+	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
+	u64 t5[ndigits];
+
+	/* t5 = x2 - x1 */
+	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
+	/* t5 = (x2 - x1)^2 = A */
+	vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+	/* t1 = x1*A = B */
+	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	/* t3 = x2*A = C */
+	vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+	/* t4 = y2 - y1 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+	/* t5 = (y2 - y1)^2 = D */
+	vli_mod_square_fast(t5, y2, curve_prime, ndigits);
+
+	/* t5 = D - B */
+	vli_mod_sub(t5, t5, x1, curve_prime, ndigits);
+	/* t5 = D - B - C = x3 */
+	vli_mod_sub(t5, t5, x2, curve_prime, ndigits);
+	/* t3 = C - B */
+	vli_mod_sub(x2, x2, x1, curve_prime, ndigits);
+	/* t2 = y1*(C - B) */
+	vli_mod_mult_fast(y1, y1, x2, curve_prime, ndigits);
+	/* t3 = B - x3 */
+	vli_mod_sub(x2, x1, t5, curve_prime, ndigits);
+	/* t4 = (y2 - y1)*(B - x3) */
+	vli_mod_mult_fast(y2, y2, x2, curve_prime, ndigits);
+	/* t4 = y3 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+
+	vli_set(x2, t5, ndigits);
+}
+
+/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
+ * Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3)
+ * or P => P - Q, Q => P + Q
+ */
+static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
+		       unsigned int ndigits)
+{
+	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
+	u64 t5[ndigits];
+	u64 t6[ndigits];
+	u64 t7[ndigits];
+
+	/* t5 = x2 - x1 */
+	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
+	/* t5 = (x2 - x1)^2 = A */
+	vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+	/* t1 = x1*A = B */
+	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	/* t3 = x2*A = C */
+	vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+	/* t4 = y2 + y1 */
+	vli_mod_add(t5, y2, y1, curve_prime, ndigits);
+	/* t4 = y2 - y1 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+
+	/* t6 = C - B */
+	vli_mod_sub(t6, x2, x1, curve_prime, ndigits);
+	/* t2 = y1 * (C - B) */
+	vli_mod_mult_fast(y1, y1, t6, curve_prime, ndigits);
+	/* t6 = B + C */
+	vli_mod_add(t6, x1, x2, curve_prime, ndigits);
+	/* t3 = (y2 - y1)^2 */
+	vli_mod_square_fast(x2, y2, curve_prime, ndigits);
+	/* t3 = x3 */
+	vli_mod_sub(x2, x2, t6, curve_prime, ndigits);
+
+	/* t7 = B - x3 */
+	vli_mod_sub(t7, x1, x2, curve_prime, ndigits);
+	/* t4 = (y2 - y1)*(B - x3) */
+	vli_mod_mult_fast(y2, y2, t7, curve_prime, ndigits);
+	/* t4 = y3 */
+	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
+
+	/* t7 = (y2 + y1)^2 = F */
+	vli_mod_square_fast(t7, t5, curve_prime, ndigits);
+	/* t7 = x3' */
+	vli_mod_sub(t7, t7, t6, curve_prime, ndigits);
+	/* t6 = x3' - B */
+	vli_mod_sub(t6, t7, x1, curve_prime, ndigits);
+	/* t6 = (y2 + y1)*(x3' - B) */
+	vli_mod_mult_fast(t6, t6, t5, curve_prime, ndigits);
+	/* t2 = y3' */
+	vli_mod_sub(y1, t6, y1, curve_prime, ndigits);
+
+	vli_set(x1, t7, ndigits);
+}
+
+static void ecc_point_mult(struct ecc_point *result,
+			   const struct ecc_point *point, const u64 *scalar,
+			   u64 *initial_z, u64 *curve_prime,
+			   unsigned int ndigits)
+{
+	/* R0 and R1 */
+	u64 rx[2][ndigits];
+	u64 ry[2][ndigits];
+	u64 z[ndigits];
+	int i, nb;
+	int num_bits = vli_num_bits(scalar, ndigits);
+
+	vli_set(rx[1], point->x, ndigits);
+	vli_set(ry[1], point->y, ndigits);
+
+	xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve_prime,
+			    ndigits);
+
+	for (i = num_bits - 2; i > 0; i--) {
+		nb = !vli_test_bit(scalar, i);
+		xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
+			   ndigits);
+		xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime,
+			 ndigits);
+	}
+
+	nb = !vli_test_bit(scalar, 0);
+	xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
+		   ndigits);
+
+	/* Find final 1/Z value. */
+	/* X1 - X0 */
+	vli_mod_sub(z, rx[1], rx[0], curve_prime, ndigits);
+	/* Yb * (X1 - X0) */
+	vli_mod_mult_fast(z, z, ry[1 - nb], curve_prime, ndigits);
+	/* xP * Yb * (X1 - X0) */
+	vli_mod_mult_fast(z, z, point->x, curve_prime, ndigits);
+
+	/* 1 / (xP * Yb * (X1 - X0)) */
+	vli_mod_inv(z, z, curve_prime, point->ndigits);
+
+	/* yP / (xP * Yb * (X1 - X0)) */
+	vli_mod_mult_fast(z, z, point->y, curve_prime, ndigits);
+	/* Xb * yP / (xP * Yb * (X1 - X0)) */
+	vli_mod_mult_fast(z, z, rx[1 - nb], curve_prime, ndigits);
+	/* End 1/Z calculation */
+
+	xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime, ndigits);
+
+	apply_z(rx[0], ry[0], z, curve_prime, ndigits);
+
+	vli_set(result->x, rx[0], ndigits);
+	vli_set(result->y, ry[0], ndigits);
+}
+
+static inline void ecc_swap_digits(const u64 *in, u64 *out,
+				   unsigned int ndigits)
+{
+	int i;
+
+	for (i = 0; i < ndigits; i++)
+		out[i] = __swab64(in[ndigits - 1 - i]);
+}
+
+int ecc_is_key_valid(unsigned int curve_id, unsigned int ndigits,
+		     const u8 *private_key, unsigned int private_key_len)
+{
+	int nbytes;
+	const struct ecc_curve *curve = ecc_get_curve(curve_id);
+
+	if (!private_key)
+		return -EINVAL;
+
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	if (private_key_len != nbytes)
+		return -EINVAL;
+
+	if (vli_is_zero((const u64 *)&private_key[0], ndigits))
+		return -EINVAL;
+
+	/* Make sure the private key is in the range [1, n-1]. */
+	if (vli_cmp(curve->n, (const u64 *)&private_key[0], ndigits) != 1)
+		return -EINVAL;
+
+	return 0;
+}
+
+int ecdh_make_pub_key(unsigned int curve_id, unsigned int ndigits,
+		      const u8 *private_key, unsigned int private_key_len,
+		      u8 *public_key, unsigned int public_key_len)
+{
+	int ret = 0;
+	struct ecc_point *pk;
+	u64 priv[ndigits];
+	unsigned int nbytes;
+	const struct ecc_curve *curve = ecc_get_curve(curve_id);
+
+	if (!private_key || !curve) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ecc_swap_digits((const u64 *)private_key, priv, ndigits);
+
+	pk = ecc_alloc_point(ndigits);
+	if (!pk) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ecc_point_mult(pk, &curve->g, priv, NULL, curve->p, ndigits);
+	if (ecc_point_is_zero(pk)) {
+		ret = -EAGAIN;
+		goto err_free_point;
+	}
+
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+	ecc_swap_digits(pk->x, (u64 *)public_key, ndigits);
+	ecc_swap_digits(pk->y, (u64 *)&public_key[nbytes], ndigits);
+
+err_free_point:
+	ecc_free_point(pk);
+out:
+	return ret;
+}
+
+int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
+		       const u8 *private_key, unsigned int private_key_len,
+		       const u8 *public_key, unsigned int public_key_len,
+		       u8 *secret, unsigned int secret_len)
+{
+	int ret = 0;
+	struct ecc_point *product, *pk;
+	u64 priv[ndigits];
+	u64 rand_z[ndigits];
+	unsigned int nbytes;
+	const struct ecc_curve *curve = ecc_get_curve(curve_id);
+
+	if (!private_key || !public_key || !curve) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nbytes = ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	get_random_bytes(rand_z, nbytes);
+
+	pk = ecc_alloc_point(ndigits);
+	if (!pk) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	product = ecc_alloc_point(ndigits);
+	if (!product) {
+		ret = -ENOMEM;
+		goto err_alloc_product;
+	}
+
+	ecc_swap_digits((const u64 *)public_key, pk->x, ndigits);
+	ecc_swap_digits((const u64 *)&public_key[nbytes], pk->y, ndigits);
+	ecc_swap_digits((const u64 *)private_key, priv, ndigits);
+
+	ecc_point_mult(product, pk, priv, rand_z, curve->p, ndigits);
+
+	ecc_swap_digits(product->x, (u64 *)secret, ndigits);
+
+	if (ecc_point_is_zero(product))
+		ret = -EFAULT;
+
+	ecc_free_point(product);
+err_alloc_product:
+	ecc_free_point(pk);
+out:
+	return ret;
+}
diff --git a/crypto/ecc.h b/crypto/ecc.h
new file mode 100644
index 0000000..663d598
--- /dev/null
+++ b/crypto/ecc.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (c) 2013, Kenneth MacKay
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *  * Redistributions of source code must retain the above copyright
+ *   notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _CRYPTO_ECC_H
+#define _CRYPTO_ECC_H
+
+#define ECC_MAX_DIGITS	4 /* 256 */
+
+#define ECC_DIGITS_TO_BYTES_SHIFT 3
+
+/**
+ * ecc_is_key_valid() - Validate a given ECDH private key
+ *
+ * @curve_id:		id representing the curve to use
+ * @ndigits:		curve number of digits
+ * @private_key:	private key to be used for the given curve
+ * @private_key_len:	private key len
+ *
+ * Returns 0 if the key is acceptable, a negative value otherwise
+ */
+int ecc_is_key_valid(unsigned int curve_id, unsigned int ndigits,
+		     const u8 *private_key, unsigned int private_key_len);
+
+/**
+ * ecdh_make_pub_key() - Compute an ECC public key
+ *
+ * @curve_id:		id representing the curve to use
+ * @private_key:	pregenerated private key for the given curve
+ * @private_key_len:	length of private_key
+ * @public_key:		buffer for storing the public key generated
+ * @public_key_len:	length of the public_key buffer
+ *
+ * Returns 0 if the public key was generated successfully, a negative value
+ * if an error occurred.
+ */
+int ecdh_make_pub_key(const unsigned int curve_id, unsigned int ndigits,
+		      const u8 *private_key, unsigned int private_key_len,
+		      u8 *public_key, unsigned int public_key_len);
+
+/**
+ * crypto_ecdh_shared_secret() - Compute a shared secret
+ *
+ * @curve_id:		id representing the curve to use
+ * @private_key:	private key of part A
+ * @private_key_len:	length of private_key
+ * @public_key:		public key of counterpart B
+ * @public_key_len:	length of public_key
+ * @secret:		buffer for storing the calculated shared secret
+ * @secret_len:		length of the secret buffer
+ *
+ * Note: It is recommended that you hash the result of crypto_ecdh_shared_secret
+ * before using it for symmetric encryption or HMAC.
+ *
+ * Returns 0 if the shared secret was generated successfully, a negative value
+ * if an error occurred.
+ */
+int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
+		       const u8 *private_key, unsigned int private_key_len,
+		       const u8 *public_key, unsigned int public_key_len,
+		       u8 *secret, unsigned int secret_len);
+#endif
diff --git a/crypto/ecc_curve_defs.h b/crypto/ecc_curve_defs.h
new file mode 100644
index 0000000..03ae5f7
--- /dev/null
+++ b/crypto/ecc_curve_defs.h
@@ -0,0 +1,57 @@
+#ifndef _CRYTO_ECC_CURVE_DEFS_H
+#define _CRYTO_ECC_CURVE_DEFS_H
+
+struct ecc_point {
+	u64 *x;
+	u64 *y;
+	u8 ndigits;
+};
+
+struct ecc_curve {
+	char *name;
+	struct ecc_point g;
+	u64 *p;
+	u64 *n;
+};
+
+/* NIST P-192 */
+static u64 nist_p192_g_x[] = { 0xF4FF0AFD82FF1012ull, 0x7CBF20EB43A18800ull,
+				0x188DA80EB03090F6ull };
+static u64 nist_p192_g_y[] = { 0x73F977A11E794811ull, 0x631011ED6B24CDD5ull,
+				0x07192B95FFC8DA78ull };
+static u64 nist_p192_p[] = { 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFEull,
+				0xFFFFFFFFFFFFFFFFull };
+static u64 nist_p192_n[] = { 0x146BC9B1B4D22831ull, 0xFFFFFFFF99DEF836ull,
+				0xFFFFFFFFFFFFFFFFull };
+static struct ecc_curve nist_p192 = {
+	.name = "nist_192",
+	.g = {
+		.x = nist_p192_g_x,
+		.y = nist_p192_g_y,
+		.ndigits = 3,
+	},
+	.p = nist_p192_p,
+	.n = nist_p192_n
+};
+
+/* NIST P-256 */
+static u64 nist_p256_g_x[] = { 0xF4A13945D898C296ull, 0x77037D812DEB33A0ull,
+				0xF8BCE6E563A440F2ull, 0x6B17D1F2E12C4247ull };
+static u64 nist_p256_g_y[] = { 0xCBB6406837BF51F5ull, 0x2BCE33576B315ECEull,
+				0x8EE7EB4A7C0F9E16ull, 0x4FE342E2FE1A7F9Bull };
+static u64 nist_p256_p[] = { 0xFFFFFFFFFFFFFFFFull, 0x00000000FFFFFFFFull,
+				0x0000000000000000ull, 0xFFFFFFFF00000001ull };
+static u64 nist_p256_n[] = { 0xF3B9CAC2FC632551ull, 0xBCE6FAADA7179E84ull,
+				0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFF00000000ull };
+static struct ecc_curve nist_p256 = {
+	.name = "nist_256",
+	.g = {
+		.x = nist_p256_g_x,
+		.y = nist_p256_g_y,
+		.ndigits = 4,
+	},
+	.p = nist_p256_p,
+	.n = nist_p256_n
+};
+
+#endif
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
new file mode 100644
index 0000000..3de2898
--- /dev/null
+++ b/crypto/ecdh.c
@@ -0,0 +1,151 @@
+/* ECDH key-agreement protocol
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvator Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/kpp.h>
+#include <crypto/ecdh.h>
+#include <linux/scatterlist.h>
+#include "ecc.h"
+
+struct ecdh_ctx {
+	unsigned int curve_id;
+	unsigned int ndigits;
+	u64 private_key[ECC_MAX_DIGITS];
+	u64 public_key[2 * ECC_MAX_DIGITS];
+	u64 shared_secret[ECC_MAX_DIGITS];
+};
+
+static inline struct ecdh_ctx *ecdh_get_ctx(struct crypto_kpp *tfm)
+{
+	return kpp_tfm_ctx(tfm);
+}
+
+static unsigned int ecdh_supported_curve(unsigned int curve_id)
+{
+	switch (curve_id) {
+	case ECC_CURVE_NIST_P192: return 3;
+	case ECC_CURVE_NIST_P256: return 4;
+	default: return 0;
+	}
+}
+
+static int ecdh_set_secret(struct crypto_kpp *tfm, void *buf, unsigned int len)
+{
+	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+	struct ecdh params;
+	unsigned int ndigits;
+
+	if (crypto_ecdh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	ndigits = ecdh_supported_curve(params.curve_id);
+	if (!ndigits)
+		return -EINVAL;
+
+	ctx->curve_id = params.curve_id;
+	ctx->ndigits = ndigits;
+
+	if (ecc_is_key_valid(ctx->curve_id, ctx->ndigits,
+			     (const u8 *)params.key, params.key_size) < 0)
+		return -EINVAL;
+
+	memcpy(ctx->private_key, params.key, params.key_size);
+
+	return 0;
+}
+
+static int ecdh_compute_value(struct kpp_request *req)
+{
+	int ret = 0;
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+	size_t copied, nbytes;
+	void *buf;
+
+	nbytes = ctx->ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	if (req->src) {
+		copied = sg_copy_to_buffer(req->src, 1, ctx->public_key,
+					   2 * nbytes);
+		if (copied != 2 * nbytes)
+			return -EINVAL;
+
+		ret = crypto_ecdh_shared_secret(ctx->curve_id, ctx->ndigits,
+					 (const u8 *)ctx->private_key, nbytes,
+					 (const u8 *)ctx->public_key, 2 * nbytes,
+					 (u8 *)ctx->shared_secret, nbytes);
+
+		buf = ctx->shared_secret;
+	} else {
+		ret = ecdh_make_pub_key(ctx->curve_id, ctx->ndigits,
+					(const u8 *)ctx->private_key, nbytes,
+					(u8 *)ctx->public_key,
+					sizeof(ctx->public_key));
+		buf = ctx->public_key;
+		/* Public part is a point thus it has both coordinates */
+		nbytes *= 2;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	copied = sg_copy_from_buffer(req->dst, 1, buf, nbytes);
+	if (copied != nbytes)
+		return -EINVAL;
+
+	return ret;
+}
+
+static int ecdh_max_size(struct crypto_kpp *tfm)
+{
+	struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+	int nbytes = ctx->ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+
+	/* Public key is made of two coordinates */
+	return 2 * nbytes;
+}
+
+static void no_exit_tfm(struct crypto_kpp *tfm)
+{
+	return;
+}
+
+static struct kpp_alg ecdh = {
+	.set_secret = ecdh_set_secret,
+	.generate_public_key = ecdh_compute_value,
+	.compute_shared_secret = ecdh_compute_value,
+	.max_size = ecdh_max_size,
+	.exit = no_exit_tfm,
+	.base = {
+		.cra_name = "ecdh",
+		.cra_driver_name = "ecdh-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct ecdh_ctx),
+	},
+};
+
+static int ecdh_init(void)
+{
+	return crypto_register_kpp(&ecdh);
+}
+
+static void ecdh_exit(void)
+{
+	crypto_unregister_kpp(&ecdh);
+}
+
+module_init(ecdh_init);
+module_exit(ecdh_exit);
+MODULE_ALIAS_CRYPTO("ecdh");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ECDH generic algorithm");
diff --git a/crypto/ecdh_helper.c b/crypto/ecdh_helper.c
new file mode 100644
index 0000000..3cd8a24
--- /dev/null
+++ b/crypto/ecdh_helper.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <crypto/ecdh.h>
+#include <crypto/kpp.h>
+
+#define ECDH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 2 * sizeof(short))
+
+static inline u8 *ecdh_pack_data(void *dst, const void *src, size_t sz)
+{
+	memcpy(dst, src, sz);
+	return dst + sz;
+}
+
+static inline const u8 *ecdh_unpack_data(void *dst, const void *src, size_t sz)
+{
+	memcpy(dst, src, sz);
+	return src + sz;
+}
+
+int crypto_ecdh_key_len(const struct ecdh *params)
+{
+	return ECDH_KPP_SECRET_MIN_SIZE + params->key_size;
+}
+EXPORT_SYMBOL_GPL(crypto_ecdh_key_len);
+
+int crypto_ecdh_encode_key(char *buf, unsigned int len,
+			   const struct ecdh *params)
+{
+	u8 *ptr = buf;
+	struct kpp_secret secret = {
+		.type = CRYPTO_KPP_SECRET_TYPE_ECDH,
+		.len = len
+	};
+
+	if (unlikely(!buf))
+		return -EINVAL;
+
+	if (len != crypto_ecdh_key_len(params))
+		return -EINVAL;
+
+	ptr = ecdh_pack_data(ptr, &secret, sizeof(secret));
+	ptr = ecdh_pack_data(ptr, &params->curve_id, sizeof(params->curve_id));
+	ptr = ecdh_pack_data(ptr, &params->key_size, sizeof(params->key_size));
+	ecdh_pack_data(ptr, params->key, params->key_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_ecdh_encode_key);
+
+int crypto_ecdh_decode_key(const char *buf, unsigned int len,
+			   struct ecdh *params)
+{
+	const u8 *ptr = buf;
+	struct kpp_secret secret;
+
+	if (unlikely(!buf || len < ECDH_KPP_SECRET_MIN_SIZE))
+		return -EINVAL;
+
+	ptr = ecdh_unpack_data(&secret, ptr, sizeof(secret));
+	if (secret.type != CRYPTO_KPP_SECRET_TYPE_ECDH)
+		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))
+		return -EINVAL;
+
+	/* Don't allocate memory. Set pointer to data
+	 * within the given buffer
+	 */
+	params->key = (void *)ptr;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_ecdh_decode_key);
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
index b96a8456..1b01fe9 100644
--- a/crypto/echainiv.c
+++ b/crypto/echainiv.c
@@ -20,6 +20,7 @@
 
 #include <crypto/internal/geniv.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -112,13 +113,16 @@
 	info = req->iv;
 
 	if (req->src != req->dst) {
-		struct blkcipher_desc desc = {
-			.tfm = ctx->null,
-		};
+		SKCIPHER_REQUEST_ON_STACK(nreq, ctx->sknull);
 
-		err = crypto_blkcipher_encrypt(
-			&desc, req->dst, req->src,
-			req->assoclen + req->cryptlen);
+		skcipher_request_set_tfm(nreq, ctx->sknull);
+		skcipher_request_set_callback(nreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(nreq, req->src, req->dst,
+					   req->assoclen + req->cryptlen,
+					   NULL);
+
+		err = crypto_skcipher_encrypt(nreq);
 		if (err)
 			return err;
 	}
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
deleted file mode 100644
index 16dda72..0000000
--- a/crypto/eseqiv.c
+++ /dev/null
@@ -1,242 +0,0 @@
-/*
- * eseqiv: Encrypted Sequence Number IV Generator
- *
- * This generator generates an IV based on a sequence number by xoring it
- * with a salt and then encrypting it with the same key as used to encrypt
- * the plain text.  This algorithm requires that the block size be equal
- * to the IV size.  It is mainly useful for CBC.
- *
- * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/skcipher.h>
-#include <crypto/rng.h>
-#include <crypto/scatterwalk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-
-struct eseqiv_request_ctx {
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
-	char tail[];
-};
-
-struct eseqiv_ctx {
-	spinlock_t lock;
-	unsigned int reqoff;
-	char salt[];
-};
-
-static void eseqiv_complete2(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct eseqiv_request_ctx *reqctx = skcipher_givcrypt_reqctx(req);
-
-	memcpy(req->giv, PTR_ALIGN((u8 *)reqctx->tail,
-			 crypto_ablkcipher_alignmask(geniv) + 1),
-	       crypto_ablkcipher_ivsize(geniv));
-}
-
-static void eseqiv_complete(struct crypto_async_request *base, int err)
-{
-	struct skcipher_givcrypt_request *req = base->data;
-
-	if (err)
-		goto out;
-
-	eseqiv_complete2(req);
-
-out:
-	skcipher_givcrypt_complete(req, err);
-}
-
-static int eseqiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct eseqiv_request_ctx *reqctx = skcipher_givcrypt_reqctx(req);
-	struct ablkcipher_request *subreq;
-	crypto_completion_t compl;
-	void *data;
-	struct scatterlist *osrc, *odst;
-	struct scatterlist *dst;
-	struct page *srcp;
-	struct page *dstp;
-	u8 *giv;
-	u8 *vsrc;
-	u8 *vdst;
-	__be64 seq;
-	unsigned int ivsize;
-	unsigned int len;
-	int err;
-
-	subreq = (void *)(reqctx->tail + ctx->reqoff);
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-
-	giv = req->giv;
-	compl = req->creq.base.complete;
-	data = req->creq.base.data;
-
-	osrc = req->creq.src;
-	odst = req->creq.dst;
-	srcp = sg_page(osrc);
-	dstp = sg_page(odst);
-	vsrc = PageHighMem(srcp) ? NULL : page_address(srcp) + osrc->offset;
-	vdst = PageHighMem(dstp) ? NULL : page_address(dstp) + odst->offset;
-
-	ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	if (vsrc != giv + ivsize && vdst != giv + ivsize) {
-		giv = PTR_ALIGN((u8 *)reqctx->tail,
-				crypto_ablkcipher_alignmask(geniv) + 1);
-		compl = eseqiv_complete;
-		data = req;
-	}
-
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags, compl,
-					data);
-
-	sg_init_table(reqctx->src, 2);
-	sg_set_buf(reqctx->src, giv, ivsize);
-	scatterwalk_crypto_chain(reqctx->src, osrc, vsrc == giv + ivsize, 2);
-
-	dst = reqctx->src;
-	if (osrc != odst) {
-		sg_init_table(reqctx->dst, 2);
-		sg_set_buf(reqctx->dst, giv, ivsize);
-		scatterwalk_crypto_chain(reqctx->dst, odst, vdst == giv + ivsize, 2);
-
-		dst = reqctx->dst;
-	}
-
-	ablkcipher_request_set_crypt(subreq, reqctx->src, dst,
-				     req->creq.nbytes + ivsize,
-				     req->creq.info);
-
-	memcpy(req->creq.info, ctx->salt, ivsize);
-
-	len = ivsize;
-	if (ivsize > sizeof(u64)) {
-		memset(req->giv, 0, ivsize - sizeof(u64));
-		len = sizeof(u64);
-	}
-	seq = cpu_to_be64(req->seq);
-	memcpy(req->giv + ivsize - len, &seq, len);
-
-	err = crypto_ablkcipher_encrypt(subreq);
-	if (err)
-		goto out;
-
-	if (giv != req->giv)
-		eseqiv_complete2(req);
-
-out:
-	return err;
-}
-
-static int eseqiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	unsigned long alignmask;
-	unsigned int reqsize;
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	alignmask = crypto_tfm_ctx_alignment() - 1;
-	reqsize = sizeof(struct eseqiv_request_ctx);
-
-	if (alignmask & reqsize) {
-		alignmask &= reqsize;
-		alignmask--;
-	}
-
-	alignmask = ~alignmask;
-	alignmask &= crypto_ablkcipher_alignmask(geniv);
-
-	reqsize += alignmask;
-	reqsize += crypto_ablkcipher_ivsize(geniv);
-	reqsize = ALIGN(reqsize, crypto_tfm_ctx_alignment());
-
-	ctx->reqoff = reqsize - sizeof(struct eseqiv_request_ctx);
-
-	tfm->crt_ablkcipher.reqsize = reqsize +
-				      sizeof(struct ablkcipher_request);
-
-	err = 0;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt = eseqiv_givencrypt;
-		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-					   crypto_ablkcipher_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: skcipher_geniv_init(tfm);
-}
-
-static struct crypto_template eseqiv_tmpl;
-
-static struct crypto_instance *eseqiv_alloc(struct rtattr **tb)
-{
-	struct crypto_instance *inst;
-	int err;
-
-	inst = skcipher_geniv_alloc(&eseqiv_tmpl, tb, 0, 0);
-	if (IS_ERR(inst))
-		goto out;
-
-	err = -EINVAL;
-	if (inst->alg.cra_ablkcipher.ivsize != inst->alg.cra_blocksize)
-		goto free_inst;
-
-	inst->alg.cra_init = eseqiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
-
-	inst->alg.cra_ctxsize = sizeof(struct eseqiv_ctx);
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
-
-out:
-	return inst;
-
-free_inst:
-	skcipher_geniv_free(inst);
-	inst = ERR_PTR(err);
-	goto out;
-}
-
-static struct crypto_template eseqiv_tmpl = {
-	.name = "eseqiv",
-	.alloc = eseqiv_alloc,
-	.free = skcipher_geniv_free,
-	.module = THIS_MODULE,
-};
-
-static int __init eseqiv_module_init(void)
-{
-	return crypto_register_template(&eseqiv_tmpl);
-}
-
-static void __exit eseqiv_module_exit(void)
-{
-	crypto_unregister_template(&eseqiv_tmpl);
-}
-
-module_init(eseqiv_module_init);
-module_exit(eseqiv_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator");
-MODULE_ALIAS_CRYPTO("eseqiv");
diff --git a/crypto/gcm.c b/crypto/gcm.c
index bec329b..70a892e8 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -29,7 +29,7 @@
 };
 
 struct crypto_gcm_ctx {
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 	struct crypto_ahash *ghash;
 };
 
@@ -50,7 +50,7 @@
 
 struct crypto_rfc4543_ctx {
 	struct crypto_aead *child;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *null;
 	u8 nonce[4];
 };
 
@@ -74,7 +74,7 @@
 	struct crypto_gcm_ghash_ctx ghash_ctx;
 	union {
 		struct ahash_request ahreq;
-		struct ablkcipher_request abreq;
+		struct skcipher_request skreq;
 	} u;
 };
 
@@ -114,7 +114,7 @@
 {
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_ahash *ghash = ctx->ghash;
-	struct crypto_ablkcipher *ctr = ctx->ctr;
+	struct crypto_skcipher *ctr = ctx->ctr;
 	struct {
 		be128 hash;
 		u8 iv[8];
@@ -122,35 +122,35 @@
 		struct crypto_gcm_setkey_result result;
 
 		struct scatterlist sg[1];
-		struct ablkcipher_request req;
+		struct skcipher_request req;
 	} *data;
 	int err;
 
-	crypto_ablkcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
-					 CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(ctr, key, keylen);
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
+	crypto_skcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_skcipher_setkey(ctr, key, keylen);
+	crypto_aead_set_flags(aead, crypto_skcipher_get_flags(ctr) &
 				    CRYPTO_TFM_RES_MASK);
 	if (err)
 		return err;
 
-	data = kzalloc(sizeof(*data) + crypto_ablkcipher_reqsize(ctr),
+	data = kzalloc(sizeof(*data) + crypto_skcipher_reqsize(ctr),
 		       GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
 	init_completion(&data->result.completion);
 	sg_init_one(data->sg, &data->hash, sizeof(data->hash));
-	ablkcipher_request_set_tfm(&data->req, ctr);
-	ablkcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP |
-						    CRYPTO_TFM_REQ_MAY_BACKLOG,
-					crypto_gcm_setkey_done,
-					&data->result);
-	ablkcipher_request_set_crypt(&data->req, data->sg, data->sg,
-				     sizeof(data->hash), data->iv);
+	skcipher_request_set_tfm(&data->req, ctr);
+	skcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+						  CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      crypto_gcm_setkey_done,
+				      &data->result);
+	skcipher_request_set_crypt(&data->req, data->sg, data->sg,
+				   sizeof(data->hash), data->iv);
 
-	err = crypto_ablkcipher_encrypt(&data->req);
+	err = crypto_skcipher_encrypt(&data->req);
 	if (err == -EINPROGRESS || err == -EBUSY) {
 		err = wait_for_completion_interruptible(
 			&data->result.completion);
@@ -223,13 +223,13 @@
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *ablk_req = &pctx->u.abreq;
+	struct skcipher_request *skreq = &pctx->u.skreq;
 	struct scatterlist *dst;
 
 	dst = req->src == req->dst ? pctx->src : pctx->dst;
 
-	ablkcipher_request_set_tfm(ablk_req, ctx->ctr);
-	ablkcipher_request_set_crypt(ablk_req, pctx->src, dst,
+	skcipher_request_set_tfm(skreq, ctx->ctr);
+	skcipher_request_set_crypt(skreq, pctx->src, dst,
 				     cryptlen + sizeof(pctx->auth_tag),
 				     pctx->iv);
 }
@@ -494,14 +494,14 @@
 static int crypto_gcm_encrypt(struct aead_request *req)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->u.abreq;
+	struct skcipher_request *skreq = &pctx->u.skreq;
 	u32 flags = aead_request_flags(req);
 
 	crypto_gcm_init_common(req);
 	crypto_gcm_init_crypt(req, req->cryptlen);
-	ablkcipher_request_set_callback(abreq, flags, gcm_encrypt_done, req);
+	skcipher_request_set_callback(skreq, flags, gcm_encrypt_done, req);
 
-	return crypto_ablkcipher_encrypt(abreq) ?:
+	return crypto_skcipher_encrypt(skreq) ?:
 	       gcm_encrypt_continue(req, flags);
 }
 
@@ -533,12 +533,12 @@
 static int gcm_dec_hash_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->u.abreq;
+	struct skcipher_request *skreq = &pctx->u.skreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
 	crypto_gcm_init_crypt(req, gctx->cryptlen);
-	ablkcipher_request_set_callback(abreq, flags, gcm_decrypt_done, req);
-	return crypto_ablkcipher_decrypt(abreq) ?: crypto_gcm_verify(req);
+	skcipher_request_set_callback(skreq, flags, gcm_decrypt_done, req);
+	return crypto_skcipher_decrypt(skreq) ?: crypto_gcm_verify(req);
 }
 
 static int crypto_gcm_decrypt(struct aead_request *req)
@@ -566,7 +566,7 @@
 	struct aead_instance *inst = aead_alg_instance(tfm);
 	struct gcm_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
-	struct crypto_ablkcipher *ctr;
+	struct crypto_skcipher *ctr;
 	struct crypto_ahash *ghash;
 	unsigned long align;
 	int err;
@@ -575,7 +575,7 @@
 	if (IS_ERR(ghash))
 		return PTR_ERR(ghash);
 
-	ctr = crypto_spawn_skcipher(&ictx->ctr);
+	ctr = crypto_spawn_skcipher2(&ictx->ctr);
 	err = PTR_ERR(ctr);
 	if (IS_ERR(ctr))
 		goto err_free_hash;
@@ -587,8 +587,8 @@
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
 	crypto_aead_set_reqsize(tfm,
 		align + offsetof(struct crypto_gcm_req_priv_ctx, u) +
-		max(sizeof(struct ablkcipher_request) +
-		    crypto_ablkcipher_reqsize(ctr),
+		max(sizeof(struct skcipher_request) +
+		    crypto_skcipher_reqsize(ctr),
 		    sizeof(struct ahash_request) +
 		    crypto_ahash_reqsize(ghash)));
 
@@ -604,7 +604,7 @@
 	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->ghash);
-	crypto_free_ablkcipher(ctx->ctr);
+	crypto_free_skcipher(ctx->ctr);
 }
 
 static void crypto_gcm_free(struct aead_instance *inst)
@@ -624,7 +624,7 @@
 {
 	struct crypto_attr_type *algt;
 	struct aead_instance *inst;
-	struct crypto_alg *ctr;
+	struct skcipher_alg *ctr;
 	struct crypto_alg *ghash_alg;
 	struct hash_alg_common *ghash;
 	struct gcm_instance_ctx *ctx;
@@ -639,7 +639,9 @@
 
 	ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
 				    CRYPTO_ALG_TYPE_HASH,
-				    CRYPTO_ALG_TYPE_AHASH_MASK);
+				    CRYPTO_ALG_TYPE_AHASH_MASK |
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (IS_ERR(ghash_alg))
 		return PTR_ERR(ghash_alg);
 
@@ -661,41 +663,42 @@
 		goto err_drop_ghash;
 
 	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
-	err = crypto_grab_skcipher(&ctx->ctr, ctr_name, 0,
-				   crypto_requires_sync(algt->type,
-							algt->mask));
+	err = crypto_grab_skcipher2(&ctx->ctr, ctr_name, 0,
+				    crypto_requires_sync(algt->type,
+							 algt->mask));
 	if (err)
 		goto err_drop_ghash;
 
-	ctr = crypto_skcipher_spawn_alg(&ctx->ctr);
+	ctr = crypto_spawn_skcipher_alg(&ctx->ctr);
 
 	/* We only support 16-byte blocks. */
-	if (ctr->cra_ablkcipher.ivsize != 16)
+	if (crypto_skcipher_alg_ivsize(ctr) != 16)
 		goto out_put_ctr;
 
 	/* Not a stream cipher? */
 	err = -EINVAL;
-	if (ctr->cra_blocksize != 1)
+	if (ctr->base.cra_blocksize != 1)
 		goto out_put_ctr;
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "gcm_base(%s,%s)", ctr->cra_driver_name,
+		     "gcm_base(%s,%s)", ctr->base.cra_driver_name,
 		     ghash_alg->cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
 	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
 
-	inst->alg.base.cra_flags = (ghash->base.cra_flags | ctr->cra_flags) &
-				   CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_flags = (ghash->base.cra_flags |
+				    ctr->base.cra_flags) & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (ghash->base.cra_priority +
-				       ctr->cra_priority) / 2;
+				       ctr->base.cra_priority) / 2;
 	inst->alg.base.cra_blocksize = 1;
 	inst->alg.base.cra_alignmask = ghash->base.cra_alignmask |
-				       ctr->cra_alignmask;
+				       ctr->base.cra_alignmask;
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_gcm_ctx);
 	inst->alg.ivsize = 12;
+	inst->alg.chunksize = crypto_skcipher_alg_chunksize(ctr);
 	inst->alg.maxauthsize = 16;
 	inst->alg.init = crypto_gcm_init_tfm;
 	inst->alg.exit = crypto_gcm_exit_tfm;
@@ -980,6 +983,7 @@
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4106_ctx);
 
 	inst->alg.ivsize = 8;
+	inst->alg.chunksize = crypto_aead_alg_chunksize(alg);
 	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
 	inst->alg.init = crypto_rfc4106_init_tfm;
@@ -1084,11 +1088,13 @@
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int nbytes = req->assoclen + req->cryptlen -
 			      (enc ? 0 : authsize);
-	struct blkcipher_desc desc = {
-		.tfm = ctx->null,
-	};
+	SKCIPHER_REQUEST_ON_STACK(nreq, ctx->null);
 
-	return crypto_blkcipher_encrypt(&desc, req->dst, req->src, nbytes);
+	skcipher_request_set_tfm(nreq, ctx->null);
+	skcipher_request_set_callback(nreq, req->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(nreq, req->src, req->dst, nbytes, NULL);
+
+	return crypto_skcipher_encrypt(nreq);
 }
 
 static int crypto_rfc4543_encrypt(struct aead_request *req)
@@ -1108,7 +1114,7 @@
 	struct crypto_aead_spawn *spawn = &ictx->aead;
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *null;
 	unsigned long align;
 	int err = 0;
 
@@ -1116,7 +1122,7 @@
 	if (IS_ERR(aead))
 		return PTR_ERR(aead);
 
-	null = crypto_get_default_null_skcipher();
+	null = crypto_get_default_null_skcipher2();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_aead;
@@ -1144,7 +1150,7 @@
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_put_default_null_skcipher();
+	crypto_put_default_null_skcipher2();
 }
 
 static void crypto_rfc4543_free(struct aead_instance *inst)
@@ -1219,6 +1225,7 @@
 	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
 
 	inst->alg.ivsize = 8;
+	inst->alg.chunksize = crypto_aead_alg_chunksize(alg);
 	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
 	inst->alg.init = crypto_rfc4543_init_tfm;
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index 597cedd..c4938497 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -87,24 +87,28 @@
 	memcpy(dest, src, n);
 }
 
+/*
+ * Obtain a high-resolution time stamp value. The time stamp is used to measure
+ * the execution time of a given code path and its variations. Hence, the time
+ * stamp must have a sufficiently high resolution.
+ *
+ * Note, if the function returns zero because a given architecture does not
+ * implement a high-resolution time stamp, the RNG code's runtime test
+ * will detect it and will not produce output.
+ */
 void jent_get_nstime(__u64 *out)
 {
-	struct timespec ts;
 	__u64 tmp = 0;
 
 	tmp = random_get_entropy();
 
 	/*
-	 * If random_get_entropy does not return a value (which is possible on,
-	 * for example, MIPS), invoke __getnstimeofday
+	 * If random_get_entropy does not return a value, i.e. it is not
+	 * implemented for a given architecture, use a clock source.
 	 * hoping that there are timers we can work with.
 	 */
-	if ((0 == tmp) &&
-	   (0 == __getnstimeofday(&ts))) {
-		tmp = ts.tv_sec;
-		tmp = tmp << 32;
-		tmp = tmp | ts.tv_nsec;
-	}
+	if (tmp == 0)
+		tmp = ktime_get_ns();
 
 	*out = tmp;
 }
diff --git a/crypto/kpp.c b/crypto/kpp.c
new file mode 100644
index 0000000..d36ce05
--- /dev/null
+++ b/crypto/kpp.c
@@ -0,0 +1,123 @@
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <linux/cryptouser.h>
+#include <net/netlink.h>
+#include <crypto/kpp.h>
+#include <crypto/internal/kpp.h>
+#include "internal.h"
+
+#ifdef CONFIG_NET
+static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_kpp rkpp;
+
+	strncpy(rkpp.type, "kpp", sizeof(rkpp.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_KPP,
+		    sizeof(struct crypto_report_kpp), &rkpp))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int crypto_kpp_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
+static void crypto_kpp_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+
+static void crypto_kpp_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	seq_puts(m, "type         : kpp\n");
+}
+
+static void crypto_kpp_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_kpp *kpp = __crypto_kpp_tfm(tfm);
+	struct kpp_alg *alg = crypto_kpp_alg(kpp);
+
+	alg->exit(kpp);
+}
+
+static int crypto_kpp_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_kpp *kpp = __crypto_kpp_tfm(tfm);
+	struct kpp_alg *alg = crypto_kpp_alg(kpp);
+
+	if (alg->exit)
+		kpp->base.exit = crypto_kpp_exit_tfm;
+
+	if (alg->init)
+		return alg->init(kpp);
+
+	return 0;
+}
+
+static const struct crypto_type crypto_kpp_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_kpp_init_tfm,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_kpp_show,
+#endif
+	.report = crypto_kpp_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_KPP,
+	.tfmsize = offsetof(struct crypto_kpp, base),
+};
+
+struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_kpp_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_kpp);
+
+static void kpp_prepare_alg(struct kpp_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	base->cra_type = &crypto_kpp_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_KPP;
+}
+
+int crypto_register_kpp(struct kpp_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	kpp_prepare_alg(alg);
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_kpp);
+
+void crypto_unregister_kpp(struct kpp_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_kpp);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Key-agreement Protocol Primitives");
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index c4eb9da..86fb59b 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -41,7 +41,7 @@
 static struct mcryptd_flush_list __percpu *mcryptd_flist;
 
 struct hashd_instance_ctx {
-	struct crypto_shash_spawn spawn;
+	struct crypto_ahash_spawn spawn;
 	struct mcryptd_queue *queue;
 };
 
@@ -272,18 +272,18 @@
 {
 	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
 	struct hashd_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_shash_spawn *spawn = &ictx->spawn;
+	struct crypto_ahash_spawn *spawn = &ictx->spawn;
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_shash *hash;
+	struct crypto_ahash *hash;
 
-	hash = crypto_spawn_shash(spawn);
+	hash = crypto_spawn_ahash(spawn);
 	if (IS_ERR(hash))
 		return PTR_ERR(hash);
 
 	ctx->child = hash;
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct mcryptd_hash_request_ctx) +
-				 crypto_shash_descsize(hash));
+				 crypto_ahash_reqsize(hash));
 	return 0;
 }
 
@@ -291,21 +291,21 @@
 {
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_shash(ctx->child);
+	crypto_free_ahash(ctx->child);
 }
 
 static int mcryptd_hash_setkey(struct crypto_ahash *parent,
 				   const u8 *key, unsigned int keylen)
 {
 	struct mcryptd_hash_ctx *ctx   = crypto_ahash_ctx(parent);
-	struct crypto_shash *child = ctx->child;
+	struct crypto_ahash *child = ctx->child;
 	int err;
 
-	crypto_shash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_shash_set_flags(child, crypto_ahash_get_flags(parent) &
+	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ahash_set_flags(child, crypto_ahash_get_flags(parent) &
 				      CRYPTO_TFM_REQ_MASK);
-	err = crypto_shash_setkey(child, key, keylen);
-	crypto_ahash_set_flags(parent, crypto_shash_get_flags(child) &
+	err = crypto_ahash_setkey(child, key, keylen);
+	crypto_ahash_set_flags(parent, crypto_ahash_get_flags(child) &
 				       CRYPTO_TFM_RES_MASK);
 	return err;
 }
@@ -331,20 +331,20 @@
 static void mcryptd_hash_init(struct crypto_async_request *req_async, int err)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
-	struct crypto_shash *child = ctx->child;
+	struct crypto_ahash *child = ctx->child;
 	struct ahash_request *req = ahash_request_cast(req_async);
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
-	struct shash_desc *desc = &rctx->desc;
+	struct ahash_request *desc = &rctx->areq;
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	ahash_request_set_tfm(desc, child);
+	ahash_request_set_callback(desc, CRYPTO_TFM_REQ_MAY_SLEEP,
+						rctx->complete, req_async);
 
-	err = crypto_shash_init(desc);
-
-	req->base.complete = rctx->complete;
+	rctx->out = req->result;
+	err = crypto_ahash_init(desc);
 
 out:
 	local_bh_disable();
@@ -365,7 +365,8 @@
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	err = shash_ahash_mcryptd_update(req, &rctx->desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_update(&rctx->areq);
 	if (err) {
 		req->base.complete = rctx->complete;
 		goto out;
@@ -391,7 +392,8 @@
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	err = shash_ahash_mcryptd_final(req, &rctx->desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_final(&rctx->areq);
 	if (err) {
 		req->base.complete = rctx->complete;
 		goto out;
@@ -416,8 +418,8 @@
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
-
-	err = shash_ahash_mcryptd_finup(req, &rctx->desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_finup(&rctx->areq);
 
 	if (err) {
 		req->base.complete = rctx->complete;
@@ -439,25 +441,21 @@
 static void mcryptd_hash_digest(struct crypto_async_request *req_async, int err)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_tfm_ctx(req_async->tfm);
-	struct crypto_shash *child = ctx->child;
+	struct crypto_ahash *child = ctx->child;
 	struct ahash_request *req = ahash_request_cast(req_async);
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
-	struct shash_desc *desc = &rctx->desc;
+	struct ahash_request *desc = &rctx->areq;
 
 	if (unlikely(err == -EINPROGRESS))
 		goto out;
 
-	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;  /* check this again */
+	ahash_request_set_tfm(desc, child);
+	ahash_request_set_callback(desc, CRYPTO_TFM_REQ_MAY_SLEEP,
+						rctx->complete, req_async);
 
-	err = shash_ahash_mcryptd_digest(req, desc);
+	rctx->out = req->result;
+	err = ahash_mcryptd_digest(desc);
 
-	if (err) {
-		req->base.complete = rctx->complete;
-		goto out;
-	}
-
-	return;
 out:
 	local_bh_disable();
 	rctx->complete(&req->base, err);
@@ -473,14 +471,14 @@
 {
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
 
-	return crypto_shash_export(&rctx->desc, out);
+	return crypto_ahash_export(&rctx->areq, out);
 }
 
 static int mcryptd_hash_import(struct ahash_request *req, const void *in)
 {
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
 
-	return crypto_shash_import(&rctx->desc, in);
+	return crypto_ahash_import(&rctx->areq, in);
 }
 
 static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
@@ -488,7 +486,7 @@
 {
 	struct hashd_instance_ctx *ctx;
 	struct ahash_instance *inst;
-	struct shash_alg *salg;
+	struct hash_alg_common *halg;
 	struct crypto_alg *alg;
 	u32 type = 0;
 	u32 mask = 0;
@@ -496,11 +494,11 @@
 
 	mcryptd_check_internal(tb, &type, &mask);
 
-	salg = shash_attr_alg(tb[1], type, mask);
-	if (IS_ERR(salg))
-		return PTR_ERR(salg);
+	halg = ahash_attr_alg(tb[1], type, mask);
+	if (IS_ERR(halg))
+		return PTR_ERR(halg);
 
-	alg = &salg->base;
+	alg = &halg->base;
 	pr_debug("crypto: mcryptd hash alg: %s\n", alg->cra_name);
 	inst = mcryptd_alloc_instance(alg, ahash_instance_headroom(),
 					sizeof(*ctx));
@@ -511,7 +509,7 @@
 	ctx = ahash_instance_ctx(inst);
 	ctx->queue = queue;
 
-	err = crypto_init_shash_spawn(&ctx->spawn, salg,
+	err = crypto_init_ahash_spawn(&ctx->spawn, halg,
 				      ahash_crypto_instance(inst));
 	if (err)
 		goto out_free_inst;
@@ -521,8 +519,8 @@
 		type |= CRYPTO_ALG_INTERNAL;
 	inst->alg.halg.base.cra_flags = type;
 
-	inst->alg.halg.digestsize = salg->digestsize;
-	inst->alg.halg.statesize = salg->statesize;
+	inst->alg.halg.digestsize = halg->digestsize;
+	inst->alg.halg.statesize = halg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm;
@@ -539,7 +537,7 @@
 
 	err = ahash_register_instance(tmpl, inst);
 	if (err) {
-		crypto_drop_shash(&ctx->spawn);
+		crypto_drop_ahash(&ctx->spawn);
 out_free_inst:
 		kfree(inst);
 	}
@@ -575,7 +573,7 @@
 
 	switch (inst->alg.cra_flags & CRYPTO_ALG_TYPE_MASK) {
 	case CRYPTO_ALG_TYPE_AHASH:
-		crypto_drop_shash(&hctx->spawn);
+		crypto_drop_ahash(&hctx->spawn);
 		kfree(ahash_instance(inst));
 		return;
 	default:
@@ -612,55 +610,38 @@
 }
 EXPORT_SYMBOL_GPL(mcryptd_alloc_ahash);
 
-int shash_ahash_mcryptd_digest(struct ahash_request *req,
-			       struct shash_desc *desc)
+int ahash_mcryptd_digest(struct ahash_request *desc)
 {
 	int err;
 
-	err = crypto_shash_init(desc) ?:
-	      shash_ahash_mcryptd_finup(req, desc);
+	err = crypto_ahash_init(desc) ?:
+	      ahash_mcryptd_finup(desc);
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_digest);
 
-int shash_ahash_mcryptd_update(struct ahash_request *req,
-			       struct shash_desc *desc)
+int ahash_mcryptd_update(struct ahash_request *desc)
 {
-	struct crypto_shash *tfm = desc->tfm;
-	struct shash_alg *shash = crypto_shash_alg(tfm);
-
 	/* alignment is to be done by multi-buffer crypto algorithm if needed */
 
-	return shash->update(desc, NULL, 0);
+	return crypto_ahash_update(desc);
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_update);
 
-int shash_ahash_mcryptd_finup(struct ahash_request *req,
-			      struct shash_desc *desc)
+int ahash_mcryptd_finup(struct ahash_request *desc)
 {
-	struct crypto_shash *tfm = desc->tfm;
-	struct shash_alg *shash = crypto_shash_alg(tfm);
-
 	/* alignment is to be done by multi-buffer crypto algorithm if needed */
 
-	return shash->finup(desc, NULL, 0, req->result);
+	return crypto_ahash_finup(desc);
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_finup);
 
-int shash_ahash_mcryptd_final(struct ahash_request *req,
-			      struct shash_desc *desc)
+int ahash_mcryptd_final(struct ahash_request *desc)
 {
-	struct crypto_shash *tfm = desc->tfm;
-	struct shash_alg *shash = crypto_shash_alg(tfm);
-
 	/* alignment is to be done by multi-buffer crypto algorithm if needed */
 
-	return shash->final(desc, req->result);
+	return crypto_ahash_final(desc);
 }
-EXPORT_SYMBOL_GPL(shash_ahash_mcryptd_final);
 
-struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
+struct crypto_ahash *mcryptd_ahash_child(struct mcryptd_ahash *tfm)
 {
 	struct mcryptd_hash_ctx *ctx = crypto_ahash_ctx(&tfm->base);
 
@@ -668,12 +649,12 @@
 }
 EXPORT_SYMBOL_GPL(mcryptd_ahash_child);
 
-struct shash_desc *mcryptd_shash_desc(struct ahash_request *req)
+struct ahash_request *mcryptd_ahash_desc(struct ahash_request *req)
 {
 	struct mcryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
-	return &rctx->desc;
+	return &rctx->areq;
 }
-EXPORT_SYMBOL_GPL(mcryptd_shash_desc);
+EXPORT_SYMBOL_GPL(mcryptd_ahash_desc);
 
 void mcryptd_free_ahash(struct mcryptd_ahash *tfm)
 {
@@ -681,7 +662,6 @@
 }
 EXPORT_SYMBOL_GPL(mcryptd_free_ahash);
 
-
 static int __init mcryptd_init(void)
 {
 	int err, cpu;
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index 8ba4266..877019a 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -92,19 +92,17 @@
 
 struct pkcs1pad_ctx {
 	struct crypto_akcipher *child;
-	const char *hash_name;
 	unsigned int key_size;
 };
 
 struct pkcs1pad_inst_ctx {
 	struct crypto_akcipher_spawn spawn;
-	const char *hash_name;
+	const struct rsa_asn1_template *digest_info;
 };
 
 struct pkcs1pad_request {
-	struct scatterlist in_sg[3], out_sg[2];
+	struct scatterlist in_sg[2], out_sg[1];
 	uint8_t *in_buf, *out_buf;
-
 	struct akcipher_request child_req;
 };
 
@@ -112,40 +110,48 @@
 		unsigned int keylen)
 {
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
-	int err, size;
+	int err;
+
+	ctx->key_size = 0;
 
 	err = crypto_akcipher_set_pub_key(ctx->child, key, keylen);
+	if (err)
+		return err;
 
-	if (!err) {
-		/* Find out new modulus size from rsa implementation */
-		size = crypto_akcipher_maxsize(ctx->child);
+	/* Find out new modulus size from rsa implementation */
+	err = crypto_akcipher_maxsize(ctx->child);
+	if (err < 0)
+		return err;
 
-		ctx->key_size = size > 0 ? size : 0;
-		if (size <= 0)
-			err = size;
-	}
+	if (err > PAGE_SIZE)
+		return -ENOTSUPP;
 
-	return err;
+	ctx->key_size = err;
+	return 0;
 }
 
 static int pkcs1pad_set_priv_key(struct crypto_akcipher *tfm, const void *key,
 		unsigned int keylen)
 {
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
-	int err, size;
+	int err;
+
+	ctx->key_size = 0;
 
 	err = crypto_akcipher_set_priv_key(ctx->child, key, keylen);
+	if (err)
+		return err;
 
-	if (!err) {
-		/* Find out new modulus size from rsa implementation */
-		size = crypto_akcipher_maxsize(ctx->child);
+	/* Find out new modulus size from rsa implementation */
+	err = crypto_akcipher_maxsize(ctx->child);
+	if (err < 0)
+		return err;
 
-		ctx->key_size = size > 0 ? size : 0;
-		if (size <= 0)
-			err = size;
-	}
+	if (err > PAGE_SIZE)
+		return -ENOTSUPP;
 
-	return err;
+	ctx->key_size = err;
+	return 0;
 }
 
 static int pkcs1pad_get_max_size(struct crypto_akcipher *tfm)
@@ -164,19 +170,10 @@
 static void pkcs1pad_sg_set_buf(struct scatterlist *sg, void *buf, size_t len,
 		struct scatterlist *next)
 {
-	int nsegs = next ? 1 : 0;
+	int nsegs = next ? 2 : 1;
 
-	if (offset_in_page(buf) + len <= PAGE_SIZE) {
-		nsegs += 1;
-		sg_init_table(sg, nsegs);
-		sg_set_buf(sg, buf, len);
-	} else {
-		nsegs += 2;
-		sg_init_table(sg, nsegs);
-		sg_set_buf(sg + 0, buf, PAGE_SIZE - offset_in_page(buf));
-		sg_set_buf(sg + 1, buf + PAGE_SIZE - offset_in_page(buf),
-				offset_in_page(buf) + len - PAGE_SIZE);
-	}
+	sg_init_table(sg, nsegs);
+	sg_set_buf(sg, buf, len);
 
 	if (next)
 		sg_chain(sg, nsegs, next);
@@ -187,37 +184,36 @@
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	size_t pad_len = ctx->key_size - req_ctx->child_req.dst_len;
-	size_t chunk_len, pad_left;
-	struct sg_mapping_iter miter;
+	unsigned int pad_len;
+	unsigned int len;
+	u8 *out_buf;
 
-	if (!err) {
-		if (pad_len) {
-			sg_miter_start(&miter, req->dst,
-					sg_nents_for_len(req->dst, pad_len),
-					SG_MITER_ATOMIC | SG_MITER_TO_SG);
+	if (err)
+		goto out;
 
-			pad_left = pad_len;
-			while (pad_left) {
-				sg_miter_next(&miter);
+	len = req_ctx->child_req.dst_len;
+	pad_len = ctx->key_size - len;
 
-				chunk_len = min(miter.length, pad_left);
-				memset(miter.addr, 0, chunk_len);
-				pad_left -= chunk_len;
-			}
+	/* Four billion to one */
+	if (likely(!pad_len))
+		goto out;
 
-			sg_miter_stop(&miter);
-		}
+	out_buf = kzalloc(ctx->key_size, GFP_ATOMIC);
+	err = -ENOMEM;
+	if (!out_buf)
+		goto out;
 
-		sg_pcopy_from_buffer(req->dst,
-				sg_nents_for_len(req->dst, ctx->key_size),
-				req_ctx->out_buf, req_ctx->child_req.dst_len,
-				pad_len);
-	}
+	sg_copy_to_buffer(req->dst, sg_nents_for_len(req->dst, len),
+			  out_buf + pad_len, len);
+	sg_copy_from_buffer(req->dst,
+			    sg_nents_for_len(req->dst, ctx->key_size),
+			    out_buf, ctx->key_size);
+	kzfree(out_buf);
+
+out:
 	req->dst_len = ctx->key_size;
 
 	kfree(req_ctx->in_buf);
-	kzfree(req_ctx->out_buf);
 
 	return err;
 }
@@ -257,21 +253,8 @@
 		return -EOVERFLOW;
 	}
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/*
-	 * Replace both input and output to add the padding in the input and
-	 * the potential missing leading zeros in the output.
-	 */
-	req_ctx->child_req.src = req_ctx->in_sg;
-	req_ctx->child_req.src_len = ctx->key_size - 1;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!req_ctx->in_buf)
 		return -ENOMEM;
 
@@ -284,9 +267,7 @@
 	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
 			ctx->key_size - 1 - req->src_len, req->src);
 
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf) {
 		kfree(req_ctx->in_buf);
 		return -ENOMEM;
@@ -299,6 +280,10 @@
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
 
+	/* Reuse output buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
+				   req->dst, ctx->key_size - 1, req->dst_len);
+
 	err = crypto_akcipher_encrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -380,18 +365,7 @@
 	if (!ctx->key_size || req->src_len != ctx->key_size)
 		return -EINVAL;
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/* Reuse input buffer, output to a new buffer */
-	req_ctx->child_req.src = req->src;
-	req_ctx->child_req.src_len = req->src_len;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size ;
-
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
@@ -402,6 +376,11 @@
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_decrypt_complete_cb, req);
 
+	/* Reuse input buffer, output to a new buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req->src,
+				   req_ctx->out_sg, req->src_len,
+				   ctx->key_size);
+
 	err = crypto_akcipher_decrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -416,20 +395,16 @@
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	const struct rsa_asn1_template *digest_info = NULL;
+	struct akcipher_instance *inst = akcipher_alg_instance(tfm);
+	struct pkcs1pad_inst_ctx *ictx = akcipher_instance_ctx(inst);
+	const struct rsa_asn1_template *digest_info = ictx->digest_info;
 	int err;
 	unsigned int ps_end, digest_size = 0;
 
 	if (!ctx->key_size)
 		return -EINVAL;
 
-	if (ctx->hash_name) {
-		digest_info = rsa_lookup_asn1(ctx->hash_name);
-		if (!digest_info)
-			return -EINVAL;
-
-		digest_size = digest_info->size;
-	}
+	digest_size = digest_info->size;
 
 	if (req->src_len + digest_size > ctx->key_size - 11)
 		return -EOVERFLOW;
@@ -439,21 +414,8 @@
 		return -EOVERFLOW;
 	}
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/*
-	 * Replace both input and output to add the padding in the input and
-	 * the potential missing leading zeros in the output.
-	 */
-	req_ctx->child_req.src = req_ctx->in_sg;
-	req_ctx->child_req.src_len = ctx->key_size - 1;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!req_ctx->in_buf)
 		return -ENOMEM;
 
@@ -462,29 +424,20 @@
 	memset(req_ctx->in_buf + 1, 0xff, ps_end - 1);
 	req_ctx->in_buf[ps_end] = 0x00;
 
-	if (digest_info) {
-		memcpy(req_ctx->in_buf + ps_end + 1, digest_info->data,
-		       digest_info->size);
-	}
+	memcpy(req_ctx->in_buf + ps_end + 1, digest_info->data,
+	       digest_info->size);
 
 	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
 			ctx->key_size - 1 - req->src_len, req->src);
 
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
-	if (!req_ctx->out_buf) {
-		kfree(req_ctx->in_buf);
-		return -ENOMEM;
-	}
-
-	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
-			ctx->key_size, NULL);
-
 	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
 
+	/* Reuse output buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
+				   req->dst, ctx->key_size - 1, req->dst_len);
+
 	err = crypto_akcipher_sign(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -499,56 +452,58 @@
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	const struct rsa_asn1_template *digest_info;
+	struct akcipher_instance *inst = akcipher_alg_instance(tfm);
+	struct pkcs1pad_inst_ctx *ictx = akcipher_instance_ctx(inst);
+	const struct rsa_asn1_template *digest_info = ictx->digest_info;
+	unsigned int dst_len;
 	unsigned int pos;
-
-	if (err == -EOVERFLOW)
-		/* Decrypted value had no leading 0 byte */
-		err = -EINVAL;
+	u8 *out_buf;
 
 	if (err)
 		goto done;
 
-	if (req_ctx->child_req.dst_len != ctx->key_size - 1) {
-		err = -EINVAL;
+	err = -EINVAL;
+	dst_len = req_ctx->child_req.dst_len;
+	if (dst_len < ctx->key_size - 1)
 		goto done;
+
+	out_buf = req_ctx->out_buf;
+	if (dst_len == ctx->key_size) {
+		if (out_buf[0] != 0x00)
+			/* Decrypted value had no leading 0 byte */
+			goto done;
+
+		dst_len--;
+		out_buf++;
 	}
 
 	err = -EBADMSG;
-	if (req_ctx->out_buf[0] != 0x01)
+	if (out_buf[0] != 0x01)
 		goto done;
 
-	for (pos = 1; pos < req_ctx->child_req.dst_len; pos++)
-		if (req_ctx->out_buf[pos] != 0xff)
+	for (pos = 1; pos < dst_len; pos++)
+		if (out_buf[pos] != 0xff)
 			break;
 
-	if (pos < 9 || pos == req_ctx->child_req.dst_len ||
-	    req_ctx->out_buf[pos] != 0x00)
+	if (pos < 9 || pos == dst_len || out_buf[pos] != 0x00)
 		goto done;
 	pos++;
 
-	if (ctx->hash_name) {
-		digest_info = rsa_lookup_asn1(ctx->hash_name);
-		if (!digest_info)
-			goto done;
+	if (memcmp(out_buf + pos, digest_info->data, digest_info->size))
+		goto done;
 
-		if (memcmp(req_ctx->out_buf + pos, digest_info->data,
-			   digest_info->size))
-			goto done;
-
-		pos += digest_info->size;
-	}
+	pos += digest_info->size;
 
 	err = 0;
 
-	if (req->dst_len < req_ctx->child_req.dst_len - pos)
+	if (req->dst_len < dst_len - pos)
 		err = -EOVERFLOW;
-	req->dst_len = req_ctx->child_req.dst_len - pos;
+	req->dst_len = dst_len - pos;
 
 	if (!err)
 		sg_copy_from_buffer(req->dst,
 				sg_nents_for_len(req->dst, req->dst_len),
-				req_ctx->out_buf + pos, req->dst_len);
+				out_buf + pos, req->dst_len);
 done:
 	kzfree(req_ctx->out_buf);
 
@@ -588,18 +543,7 @@
 	if (!ctx->key_size || req->src_len < ctx->key_size)
 		return -EINVAL;
 
-	if (ctx->key_size > PAGE_SIZE)
-		return -ENOTSUPP;
-
-	/* Reuse input buffer, output to a new buffer */
-	req_ctx->child_req.src = req->src;
-	req_ctx->child_req.src_len = req->src_len;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
-	req_ctx->out_buf = kmalloc(ctx->key_size,
-			(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-			GFP_KERNEL : GFP_ATOMIC);
+	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
@@ -610,6 +554,11 @@
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_verify_complete_cb, req);
 
+	/* Reuse input buffer, output to a new buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req->src,
+				   req_ctx->out_sg, req->src_len,
+				   ctx->key_size);
+
 	err = crypto_akcipher_verify(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -626,12 +575,11 @@
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct crypto_akcipher *child_tfm;
 
-	child_tfm = crypto_spawn_akcipher(akcipher_instance_ctx(inst));
+	child_tfm = crypto_spawn_akcipher(&ictx->spawn);
 	if (IS_ERR(child_tfm))
 		return PTR_ERR(child_tfm);
 
 	ctx->child = child_tfm;
-	ctx->hash_name = ictx->hash_name;
 	return 0;
 }
 
@@ -648,12 +596,12 @@
 	struct crypto_akcipher_spawn *spawn = &ctx->spawn;
 
 	crypto_drop_akcipher(spawn);
-	kfree(ctx->hash_name);
 	kfree(inst);
 }
 
 static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
+	const struct rsa_asn1_template *digest_info;
 	struct crypto_attr_type *algt;
 	struct akcipher_instance *inst;
 	struct pkcs1pad_inst_ctx *ctx;
@@ -676,7 +624,11 @@
 
 	hash_name = crypto_attr_alg_name(tb[2]);
 	if (IS_ERR(hash_name))
-		hash_name = NULL;
+		return PTR_ERR(hash_name);
+
+	digest_info = rsa_lookup_asn1(hash_name);
+	if (!digest_info)
+		return -EINVAL;
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
@@ -684,7 +636,7 @@
 
 	ctx = akcipher_instance_ctx(inst);
 	spawn = &ctx->spawn;
-	ctx->hash_name = hash_name ? kstrdup(hash_name, GFP_KERNEL) : NULL;
+	ctx->digest_info = digest_info;
 
 	crypto_set_spawn(&spawn->base, akcipher_crypto_instance(inst));
 	err = crypto_grab_akcipher(spawn, rsa_alg_name, 0,
@@ -696,27 +648,14 @@
 
 	err = -ENAMETOOLONG;
 
-	if (!hash_name) {
-		if (snprintf(inst->alg.base.cra_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)",
-			     rsa_alg->base.cra_name) >=
-					CRYPTO_MAX_ALG_NAME ||
-		    snprintf(inst->alg.base.cra_driver_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)",
-			     rsa_alg->base.cra_driver_name) >=
-					CRYPTO_MAX_ALG_NAME)
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "pkcs1pad(%s,%s)", rsa_alg->base.cra_name, hash_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "pkcs1pad(%s,%s)",
+		     rsa_alg->base.cra_driver_name, hash_name) >=
+	    CRYPTO_MAX_ALG_NAME)
 		goto out_drop_alg;
-	} else {
-		if (snprintf(inst->alg.base.cra_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s,%s)",
-			     rsa_alg->base.cra_name, hash_name) >=
-				CRYPTO_MAX_ALG_NAME ||
-		    snprintf(inst->alg.base.cra_driver_name,
-			     CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s,%s)",
-			     rsa_alg->base.cra_driver_name, hash_name) >=
-					CRYPTO_MAX_ALG_NAME)
-		goto out_free_hash;
-	}
 
 	inst->alg.base.cra_flags = rsa_alg->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = rsa_alg->base.cra_priority;
@@ -738,12 +677,10 @@
 
 	err = akcipher_register_instance(tmpl, inst);
 	if (err)
-		goto out_free_hash;
+		goto out_drop_alg;
 
 	return 0;
 
-out_free_hash:
-	kfree(ctx->hash_name);
 out_drop_alg:
 	crypto_drop_akcipher(spawn);
 out_free_inst:
diff --git a/crypto/rsa.c b/crypto/rsa.c
index 77d737f..4c280b6 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -10,16 +10,23 @@
  */
 
 #include <linux/module.h>
+#include <linux/mpi.h>
 #include <crypto/internal/rsa.h>
 #include <crypto/internal/akcipher.h>
 #include <crypto/akcipher.h>
 #include <crypto/algapi.h>
 
+struct rsa_mpi_key {
+	MPI n;
+	MPI e;
+	MPI d;
+};
+
 /*
  * RSAEP function [RFC3447 sec 5.1.1]
  * c = m^e mod n;
  */
-static int _rsa_enc(const struct rsa_key *key, MPI c, MPI m)
+static int _rsa_enc(const struct rsa_mpi_key *key, MPI c, MPI m)
 {
 	/* (1) Validate 0 <= m < n */
 	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
@@ -33,7 +40,7 @@
  * RSADP function [RFC3447 sec 5.1.2]
  * m = c^d mod n;
  */
-static int _rsa_dec(const struct rsa_key *key, MPI m, MPI c)
+static int _rsa_dec(const struct rsa_mpi_key *key, MPI m, MPI c)
 {
 	/* (1) Validate 0 <= c < n */
 	if (mpi_cmp_ui(c, 0) < 0 || mpi_cmp(c, key->n) >= 0)
@@ -47,7 +54,7 @@
  * RSASP1 function [RFC3447 sec 5.2.1]
  * s = m^d mod n
  */
-static int _rsa_sign(const struct rsa_key *key, MPI s, MPI m)
+static int _rsa_sign(const struct rsa_mpi_key *key, MPI s, MPI m)
 {
 	/* (1) Validate 0 <= m < n */
 	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
@@ -61,7 +68,7 @@
  * RSAVP1 function [RFC3447 sec 5.2.2]
  * m = s^e mod n;
  */
-static int _rsa_verify(const struct rsa_key *key, MPI m, MPI s)
+static int _rsa_verify(const struct rsa_mpi_key *key, MPI m, MPI s)
 {
 	/* (1) Validate 0 <= s < n */
 	if (mpi_cmp_ui(s, 0) < 0 || mpi_cmp(s, key->n) >= 0)
@@ -71,7 +78,7 @@
 	return mpi_powm(m, s, key->e, key->n);
 }
 
-static inline struct rsa_key *rsa_get_key(struct crypto_akcipher *tfm)
+static inline struct rsa_mpi_key *rsa_get_key(struct crypto_akcipher *tfm)
 {
 	return akcipher_tfm_ctx(tfm);
 }
@@ -79,7 +86,7 @@
 static int rsa_enc(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI m, c = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -101,7 +108,7 @@
 	if (ret)
 		goto err_free_m;
 
-	ret = mpi_write_to_sgl(c, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(c, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_m;
 
@@ -118,7 +125,7 @@
 static int rsa_dec(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI c, m = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -140,7 +147,7 @@
 	if (ret)
 		goto err_free_c;
 
-	ret = mpi_write_to_sgl(m, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(m, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_c;
 
@@ -156,7 +163,7 @@
 static int rsa_sign(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI m, s = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -178,7 +185,7 @@
 	if (ret)
 		goto err_free_m;
 
-	ret = mpi_write_to_sgl(s, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(s, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_m;
 
@@ -195,7 +202,7 @@
 static int rsa_verify(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_key *pkey = rsa_get_key(tfm);
+	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
 	MPI s, m = mpi_alloc(0);
 	int ret = 0;
 	int sign;
@@ -219,7 +226,7 @@
 	if (ret)
 		goto err_free_s;
 
-	ret = mpi_write_to_sgl(m, req->dst, &req->dst_len, &sign);
+	ret = mpi_write_to_sgl(m, req->dst, req->dst_len, &sign);
 	if (ret)
 		goto err_free_s;
 
@@ -233,6 +240,16 @@
 	return ret;
 }
 
+static void rsa_free_mpi_key(struct rsa_mpi_key *key)
+{
+	mpi_free(key->d);
+	mpi_free(key->e);
+	mpi_free(key->n);
+	key->d = NULL;
+	key->e = NULL;
+	key->n = NULL;
+}
+
 static int rsa_check_key_length(unsigned int len)
 {
 	switch (len) {
@@ -251,49 +268,87 @@
 static int rsa_set_pub_key(struct crypto_akcipher *tfm, const void *key,
 			   unsigned int keylen)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *mpi_key = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
 	int ret;
 
-	ret = rsa_parse_pub_key(pkey, key, keylen);
+	/* Free the old MPI key if any */
+	rsa_free_mpi_key(mpi_key);
+
+	ret = rsa_parse_pub_key(&raw_key, key, keylen);
 	if (ret)
 		return ret;
 
-	if (rsa_check_key_length(mpi_get_size(pkey->n) << 3)) {
-		rsa_free_key(pkey);
-		ret = -EINVAL;
+	mpi_key->e = mpi_read_raw_data(raw_key.e, raw_key.e_sz);
+	if (!mpi_key->e)
+		goto err;
+
+	mpi_key->n = mpi_read_raw_data(raw_key.n, raw_key.n_sz);
+	if (!mpi_key->n)
+		goto err;
+
+	if (rsa_check_key_length(mpi_get_size(mpi_key->n) << 3)) {
+		rsa_free_mpi_key(mpi_key);
+		return -EINVAL;
 	}
-	return ret;
+
+	return 0;
+
+err:
+	rsa_free_mpi_key(mpi_key);
+	return -ENOMEM;
 }
 
 static int rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key,
 			    unsigned int keylen)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *mpi_key = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
 	int ret;
 
-	ret = rsa_parse_priv_key(pkey, key, keylen);
+	/* Free the old MPI key if any */
+	rsa_free_mpi_key(mpi_key);
+
+	ret = rsa_parse_priv_key(&raw_key, key, keylen);
 	if (ret)
 		return ret;
 
-	if (rsa_check_key_length(mpi_get_size(pkey->n) << 3)) {
-		rsa_free_key(pkey);
-		ret = -EINVAL;
+	mpi_key->d = mpi_read_raw_data(raw_key.d, raw_key.d_sz);
+	if (!mpi_key->d)
+		goto err;
+
+	mpi_key->e = mpi_read_raw_data(raw_key.e, raw_key.e_sz);
+	if (!mpi_key->e)
+		goto err;
+
+	mpi_key->n = mpi_read_raw_data(raw_key.n, raw_key.n_sz);
+	if (!mpi_key->n)
+		goto err;
+
+	if (rsa_check_key_length(mpi_get_size(mpi_key->n) << 3)) {
+		rsa_free_mpi_key(mpi_key);
+		return -EINVAL;
 	}
-	return ret;
+
+	return 0;
+
+err:
+	rsa_free_mpi_key(mpi_key);
+	return -ENOMEM;
 }
 
 static int rsa_max_size(struct crypto_akcipher *tfm)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *pkey = akcipher_tfm_ctx(tfm);
 
 	return pkey->n ? mpi_get_size(pkey->n) : -EINVAL;
 }
 
 static void rsa_exit_tfm(struct crypto_akcipher *tfm)
 {
-	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+	struct rsa_mpi_key *pkey = akcipher_tfm_ctx(tfm);
 
-	rsa_free_key(pkey);
+	rsa_free_mpi_key(pkey);
 }
 
 static struct akcipher_alg rsa = {
@@ -310,7 +365,7 @@
 		.cra_driver_name = "rsa-generic",
 		.cra_priority = 100,
 		.cra_module = THIS_MODULE,
-		.cra_ctxsize = sizeof(struct rsa_key),
+		.cra_ctxsize = sizeof(struct rsa_mpi_key),
 	},
 };
 
diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c
index d226f48..4df6451 100644
--- a/crypto/rsa_helper.c
+++ b/crypto/rsa_helper.c
@@ -22,20 +22,29 @@
 	      const void *value, size_t vlen)
 {
 	struct rsa_key *key = context;
+	const u8 *ptr = value;
+	size_t n_sz = vlen;
 
-	key->n = mpi_read_raw_data(value, vlen);
-
-	if (!key->n)
-		return -ENOMEM;
-
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (mpi_get_size(key->n) != 256 &&
-			     mpi_get_size(key->n) != 384)) {
-		pr_err("RSA: key size not allowed in FIPS mode\n");
-		mpi_free(key->n);
-		key->n = NULL;
+	/* invalid key provided */
+	if (!value || !vlen)
 		return -EINVAL;
+
+	if (fips_enabled) {
+		while (!*ptr && n_sz) {
+			ptr++;
+			n_sz--;
+		}
+
+		/* In FIPS mode only allow key size 2K & 3K */
+		if (n_sz != 256 && n_sz != 384) {
+			pr_err("RSA: key size not allowed in FIPS mode\n");
+			return -EINVAL;
+		}
 	}
+
+	key->n = value;
+	key->n_sz = vlen;
+
 	return 0;
 }
 
@@ -44,10 +53,12 @@
 {
 	struct rsa_key *key = context;
 
-	key->e = mpi_read_raw_data(value, vlen);
+	/* invalid key provided */
+	if (!value || !key->n_sz || !vlen || vlen > key->n_sz)
+		return -EINVAL;
 
-	if (!key->e)
-		return -ENOMEM;
+	key->e = value;
+	key->e_sz = vlen;
 
 	return 0;
 }
@@ -57,46 +68,95 @@
 {
 	struct rsa_key *key = context;
 
-	key->d = mpi_read_raw_data(value, vlen);
-
-	if (!key->d)
-		return -ENOMEM;
-
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (mpi_get_size(key->d) != 256 &&
-			     mpi_get_size(key->d) != 384)) {
-		pr_err("RSA: key size not allowed in FIPS mode\n");
-		mpi_free(key->d);
-		key->d = NULL;
+	/* invalid key provided */
+	if (!value || !key->n_sz || !vlen || vlen > key->n_sz)
 		return -EINVAL;
-	}
+
+	key->d = value;
+	key->d_sz = vlen;
+
 	return 0;
 }
 
-static void free_mpis(struct rsa_key *key)
+int rsa_get_p(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
 {
-	mpi_free(key->n);
-	mpi_free(key->e);
-	mpi_free(key->d);
-	key->n = NULL;
-	key->e = NULL;
-	key->d = NULL;
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->p = value;
+	key->p_sz = vlen;
+
+	return 0;
+}
+
+int rsa_get_q(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->q = value;
+	key->q_sz = vlen;
+
+	return 0;
+}
+
+int rsa_get_dp(void *context, size_t hdrlen, unsigned char tag,
+	       const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->dp = value;
+	key->dp_sz = vlen;
+
+	return 0;
+}
+
+int rsa_get_dq(void *context, size_t hdrlen, unsigned char tag,
+	       const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->dq = value;
+	key->dq_sz = vlen;
+
+	return 0;
+}
+
+int rsa_get_qinv(void *context, size_t hdrlen, unsigned char tag,
+		 const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	/* invalid key provided */
+	if (!value || !vlen || vlen > key->n_sz)
+		return -EINVAL;
+
+	key->qinv = value;
+	key->qinv_sz = vlen;
+
+	return 0;
 }
 
 /**
- * rsa_free_key() - frees rsa key allocated by rsa_parse_key()
- *
- * @rsa_key:	struct rsa_key key representation
- */
-void rsa_free_key(struct rsa_key *key)
-{
-	free_mpis(key);
-}
-EXPORT_SYMBOL_GPL(rsa_free_key);
-
-/**
- * rsa_parse_pub_key() - extracts an rsa public key from BER encoded buffer
- *			 and stores it in the provided struct rsa_key
+ * rsa_parse_pub_key() - decodes the BER encoded buffer and stores in the
+ *                       provided struct rsa_key, pointers to the raw key as is,
+ *                       so that the caller can copy it or MPI parse it, etc.
  *
  * @rsa_key:	struct rsa_key key representation
  * @key:	key in BER format
@@ -107,23 +167,15 @@
 int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key,
 		      unsigned int key_len)
 {
-	int ret;
-
-	free_mpis(rsa_key);
-	ret = asn1_ber_decoder(&rsapubkey_decoder, rsa_key, key, key_len);
-	if (ret < 0)
-		goto error;
-
-	return 0;
-error:
-	free_mpis(rsa_key);
-	return ret;
+	return asn1_ber_decoder(&rsapubkey_decoder, rsa_key, key, key_len);
 }
 EXPORT_SYMBOL_GPL(rsa_parse_pub_key);
 
 /**
- * rsa_parse_pub_key() - extracts an rsa private key from BER encoded buffer
- *			 and stores it in the provided struct rsa_key
+ * rsa_parse_priv_key() - decodes the BER encoded buffer and stores in the
+ *                        provided struct rsa_key, pointers to the raw key
+ *                        as is, so that the caller can copy it or MPI parse it,
+ *                        etc.
  *
  * @rsa_key:	struct rsa_key key representation
  * @key:	key in BER format
@@ -134,16 +186,6 @@
 int rsa_parse_priv_key(struct rsa_key *rsa_key, const void *key,
 		       unsigned int key_len)
 {
-	int ret;
-
-	free_mpis(rsa_key);
-	ret = asn1_ber_decoder(&rsaprivkey_decoder, rsa_key, key, key_len);
-	if (ret < 0)
-		goto error;
-
-	return 0;
-error:
-	free_mpis(rsa_key);
-	return ret;
+	return asn1_ber_decoder(&rsaprivkey_decoder, rsa_key, key, key_len);
 }
 EXPORT_SYMBOL_GPL(rsa_parse_priv_key);
diff --git a/crypto/rsaprivkey.asn1 b/crypto/rsaprivkey.asn1
index 731aea5..4ce0675 100644
--- a/crypto/rsaprivkey.asn1
+++ b/crypto/rsaprivkey.asn1
@@ -3,9 +3,9 @@
 	n		INTEGER ({ rsa_get_n }),
 	e		INTEGER ({ rsa_get_e }),
 	d		INTEGER ({ rsa_get_d }),
-	prime1		INTEGER,
-	prime2		INTEGER,
-	exponent1	INTEGER,
-	exponent2	INTEGER,
-	coefficient	INTEGER
+	prime1		INTEGER ({ rsa_get_p }),
+	prime2		INTEGER ({ rsa_get_q }),
+	exponent1	INTEGER ({ rsa_get_dp }),
+	exponent2	INTEGER ({ rsa_get_dq }),
+	coefficient	INTEGER ({ rsa_get_qinv })
 }
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index ea5815c..52ce17a 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -18,8 +18,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/pagemap.h>
-#include <linux/highmem.h>
 #include <linux/scatterlist.h>
 
 static inline void memcpy_dir(void *buf, void *sgdata, size_t nbytes, int out)
@@ -30,53 +28,6 @@
 	memcpy(dst, src, nbytes);
 }
 
-void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg)
-{
-	walk->sg = sg;
-
-	BUG_ON(!sg->length);
-
-	walk->offset = sg->offset;
-}
-EXPORT_SYMBOL_GPL(scatterwalk_start);
-
-void *scatterwalk_map(struct scatter_walk *walk)
-{
-	return kmap_atomic(scatterwalk_page(walk)) +
-	       offset_in_page(walk->offset);
-}
-EXPORT_SYMBOL_GPL(scatterwalk_map);
-
-static void scatterwalk_pagedone(struct scatter_walk *walk, int out,
-				 unsigned int more)
-{
-	if (out) {
-		struct page *page;
-
-		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
-		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
-		 * PageSlab cannot be optimised away per se due to
-		 * use of volatile pointer.
-		 */
-		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
-			flush_dcache_page(page);
-	}
-
-	if (more) {
-		walk->offset += PAGE_SIZE - 1;
-		walk->offset &= PAGE_MASK;
-		if (walk->offset >= walk->sg->offset + walk->sg->length)
-			scatterwalk_start(walk, sg_next(walk->sg));
-	}
-}
-
-void scatterwalk_done(struct scatter_walk *walk, int out, int more)
-{
-	if (!(scatterwalk_pagelen(walk) & (PAGE_SIZE - 1)) || !more)
-		scatterwalk_pagedone(walk, out, more);
-}
-EXPORT_SYMBOL_GPL(scatterwalk_done);
-
 void scatterwalk_copychunks(void *buf, struct scatter_walk *walk,
 			    size_t nbytes, int out)
 {
@@ -87,9 +38,11 @@
 		if (len_this_page > nbytes)
 			len_this_page = nbytes;
 
-		vaddr = scatterwalk_map(walk);
-		memcpy_dir(buf, vaddr, len_this_page, out);
-		scatterwalk_unmap(vaddr);
+		if (out != 2) {
+			vaddr = scatterwalk_map(walk);
+			memcpy_dir(buf, vaddr, len_this_page, out);
+			scatterwalk_unmap(vaddr);
+		}
 
 		scatterwalk_advance(walk, len_this_page);
 
@@ -99,7 +52,7 @@
 		buf += len_this_page;
 		nbytes -= len_this_page;
 
-		scatterwalk_pagedone(walk, out, 1);
+		scatterwalk_pagedone(walk, out & 1, 1);
 	}
 }
 EXPORT_SYMBOL_GPL(scatterwalk_copychunks);
@@ -125,28 +78,6 @@
 }
 EXPORT_SYMBOL_GPL(scatterwalk_map_and_copy);
 
-int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes)
-{
-	int offset = 0, n = 0;
-
-	/* num_bytes is too small */
-	if (num_bytes < sg->length)
-		return -1;
-
-	do {
-		offset += sg->length;
-		n++;
-		sg = sg_next(sg);
-
-		/* num_bytes is too large */
-		if (unlikely(!sg && (num_bytes < offset)))
-			return -1;
-	} while (sg && (num_bytes > offset));
-
-	return n;
-}
-EXPORT_SYMBOL_GPL(scatterwalk_bytes_sglen);
-
 struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
 				     struct scatterlist *src,
 				     unsigned int len)
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index 15a749a..c704923 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -14,50 +14,17 @@
  */
 
 #include <crypto/internal/geniv.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/rng.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/string.h>
 
-struct seqiv_ctx {
-	spinlock_t lock;
-	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
-};
-
 static void seqiv_free(struct crypto_instance *inst);
 
-static void seqiv_complete2(struct skcipher_givcrypt_request *req, int err)
-{
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	struct crypto_ablkcipher *geniv;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	if (err)
-		goto out;
-
-	geniv = skcipher_givcrypt_reqtfm(req);
-	memcpy(req->creq.info, subreq->info, crypto_ablkcipher_ivsize(geniv));
-
-out:
-	kfree(subreq->info);
-}
-
-static void seqiv_complete(struct crypto_async_request *base, int err)
-{
-	struct skcipher_givcrypt_request *req = base->data;
-
-	seqiv_complete2(req, err);
-	skcipher_givcrypt_complete(req, err);
-}
-
 static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err)
 {
 	struct aead_request *subreq = aead_request_ctx(req);
@@ -85,65 +52,6 @@
 	aead_request_complete(req, err);
 }
 
-static void seqiv_geniv(struct seqiv_ctx *ctx, u8 *info, u64 seq,
-			unsigned int ivsize)
-{
-	unsigned int len = ivsize;
-
-	if (ivsize > sizeof(u64)) {
-		memset(info, 0, ivsize - sizeof(u64));
-		len = sizeof(u64);
-	}
-	seq = cpu_to_be64(seq);
-	memcpy(info + ivsize - len, &seq, len);
-	crypto_xor(info, ctx->salt, ivsize);
-}
-
-static int seqiv_givencrypt(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	crypto_completion_t compl;
-	void *data;
-	u8 *info;
-	unsigned int ivsize;
-	int err;
-
-	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
-
-	compl = req->creq.base.complete;
-	data = req->creq.base.data;
-	info = req->creq.info;
-
-	ivsize = crypto_ablkcipher_ivsize(geniv);
-
-	if (unlikely(!IS_ALIGNED((unsigned long)info,
-				 crypto_ablkcipher_alignmask(geniv) + 1))) {
-		info = kmalloc(ivsize, req->creq.base.flags &
-				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
-								  GFP_ATOMIC);
-		if (!info)
-			return -ENOMEM;
-
-		compl = seqiv_complete;
-		data = req;
-	}
-
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags, compl,
-					data);
-	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
-				     req->creq.nbytes, info);
-
-	seqiv_geniv(ctx, info, req->seq, ivsize);
-	memcpy(req->giv, info, ivsize);
-
-	err = crypto_ablkcipher_encrypt(subreq);
-	if (unlikely(info != req->creq.info))
-		seqiv_complete2(req, err);
-	return err;
-}
-
 static int seqiv_aead_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
@@ -165,12 +73,16 @@
 	info = req->iv;
 
 	if (req->src != req->dst) {
-		struct blkcipher_desc desc = {
-			.tfm = ctx->null,
-		};
+		SKCIPHER_REQUEST_ON_STACK(nreq, ctx->sknull);
 
-		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
-					       req->assoclen + req->cryptlen);
+		skcipher_request_set_tfm(nreq, ctx->sknull);
+		skcipher_request_set_callback(nreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(nreq, req->src, req->dst,
+					   req->assoclen + req->cryptlen,
+					   NULL);
+
+		err = crypto_skcipher_encrypt(nreq);
 		if (err)
 			return err;
 	}
@@ -229,62 +141,6 @@
 	return crypto_aead_decrypt(subreq);
 }
 
-static int seqiv_init(struct crypto_tfm *tfm)
-{
-	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
-	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err;
-
-	spin_lock_init(&ctx->lock);
-
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
-
-	err = 0;
-	if (!crypto_get_default_rng()) {
-		crypto_ablkcipher_crt(geniv)->givencrypt = seqiv_givencrypt;
-		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-					   crypto_ablkcipher_ivsize(geniv));
-		crypto_put_default_rng();
-	}
-
-	return err ?: skcipher_geniv_init(tfm);
-}
-
-static int seqiv_ablkcipher_create(struct crypto_template *tmpl,
-				   struct rtattr **tb)
-{
-	struct crypto_instance *inst;
-	int err;
-
-	inst = skcipher_geniv_alloc(tmpl, tb, 0, 0);
-
-	if (IS_ERR(inst))
-		return PTR_ERR(inst);
-
-	err = -EINVAL;
-	if (inst->alg.cra_ablkcipher.ivsize < sizeof(u64))
-		goto free_inst;
-
-	inst->alg.cra_init = seqiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
-
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
-	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
-
-	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
-
-	err = crypto_register_instance(tmpl, inst);
-	if (err)
-		goto free_inst;
-
-out:
-	return err;
-
-free_inst:
-	skcipher_geniv_free(inst);
-	goto out;
-}
-
 static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct aead_instance *inst;
@@ -330,26 +186,20 @@
 static int seqiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
 		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
-		err = seqiv_ablkcipher_create(tmpl, tb);
-	else
-		err = seqiv_aead_create(tmpl, tb);
+		return -EINVAL;
 
-	return err;
+	return seqiv_aead_create(tmpl, tb);
 }
 
 static void seqiv_free(struct crypto_instance *inst)
 {
-	if ((inst->alg.cra_flags ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
-		skcipher_geniv_free(inst);
-	else
-		aead_geniv_free(aead_instance(inst));
+	aead_geniv_free(aead_instance(inst));
 }
 
 static struct crypto_template seqiv_tmpl = {
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
new file mode 100644
index 0000000..6226439
--- /dev/null
+++ b/crypto/sha3_generic.c
@@ -0,0 +1,300 @@
+/*
+ * Cryptographic API.
+ *
+ * SHA-3, as specified in
+ * http://nvlpubs.nist.gov/nistpubs/FIPS/NIST.FIPS.202.pdf
+ *
+ * SHA-3 code by Jeff Garzik <jeff@garzik.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)•
+ * any later version.
+ *
+ */
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/sha3.h>
+#include <asm/byteorder.h>
+
+#define KECCAK_ROUNDS 24
+
+#define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y))))
+
+static const u64 keccakf_rndc[24] = {
+	0x0000000000000001, 0x0000000000008082, 0x800000000000808a,
+	0x8000000080008000, 0x000000000000808b, 0x0000000080000001,
+	0x8000000080008081, 0x8000000000008009, 0x000000000000008a,
+	0x0000000000000088, 0x0000000080008009, 0x000000008000000a,
+	0x000000008000808b, 0x800000000000008b, 0x8000000000008089,
+	0x8000000000008003, 0x8000000000008002, 0x8000000000000080,
+	0x000000000000800a, 0x800000008000000a, 0x8000000080008081,
+	0x8000000000008080, 0x0000000080000001, 0x8000000080008008
+};
+
+static const int keccakf_rotc[24] = {
+	1,  3,  6,  10, 15, 21, 28, 36, 45, 55, 2,  14,
+	27, 41, 56, 8,  25, 43, 62, 18, 39, 61, 20, 44
+};
+
+static const int keccakf_piln[24] = {
+	10, 7,  11, 17, 18, 3, 5,  16, 8,  21, 24, 4,
+	15, 23, 19, 13, 12, 2, 20, 14, 22, 9,  6,  1
+};
+
+/* update the state with given number of rounds */
+
+static void keccakf(u64 st[25])
+{
+	int i, j, round;
+	u64 t, bc[5];
+
+	for (round = 0; round < KECCAK_ROUNDS; round++) {
+
+		/* Theta */
+		for (i = 0; i < 5; i++)
+			bc[i] = st[i] ^ st[i + 5] ^ st[i + 10] ^ st[i + 15]
+				^ st[i + 20];
+
+		for (i = 0; i < 5; i++) {
+			t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1);
+			for (j = 0; j < 25; j += 5)
+				st[j + i] ^= t;
+		}
+
+		/* Rho Pi */
+		t = st[1];
+		for (i = 0; i < 24; i++) {
+			j = keccakf_piln[i];
+			bc[0] = st[j];
+			st[j] = ROTL64(t, keccakf_rotc[i]);
+			t = bc[0];
+		}
+
+		/* Chi */
+		for (j = 0; j < 25; j += 5) {
+			for (i = 0; i < 5; i++)
+				bc[i] = st[j + i];
+			for (i = 0; i < 5; i++)
+				st[j + i] ^= (~bc[(i + 1) % 5]) &
+					     bc[(i + 2) % 5];
+		}
+
+		/* Iota */
+		st[0] ^= keccakf_rndc[round];
+	}
+}
+
+static void sha3_init(struct sha3_state *sctx, unsigned int digest_sz)
+{
+	memset(sctx, 0, sizeof(*sctx));
+	sctx->md_len = digest_sz;
+	sctx->rsiz = 200 - 2 * digest_sz;
+	sctx->rsizw = sctx->rsiz / 8;
+}
+
+static int sha3_224_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_224_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_256_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_256_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_384_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_384_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_512_init(struct shash_desc *desc)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+
+	sha3_init(sctx, SHA3_512_DIGEST_SIZE);
+	return 0;
+}
+
+static int sha3_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int done;
+	const u8 *src;
+
+	done = 0;
+	src = data;
+
+	if ((sctx->partial + len) > (sctx->rsiz - 1)) {
+		if (sctx->partial) {
+			done = -sctx->partial;
+			memcpy(sctx->buf + sctx->partial, data,
+			       done + sctx->rsiz);
+			src = sctx->buf;
+		}
+
+		do {
+			unsigned int i;
+
+			for (i = 0; i < sctx->rsizw; i++)
+				sctx->st[i] ^= ((u64 *) src)[i];
+			keccakf(sctx->st);
+
+			done += sctx->rsiz;
+			src = data + done;
+		} while (done + (sctx->rsiz - 1) < len);
+
+		sctx->partial = 0;
+	}
+	memcpy(sctx->buf + sctx->partial, src, len - done);
+	sctx->partial += (len - done);
+
+	return 0;
+}
+
+static int sha3_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, inlen = sctx->partial;
+
+	sctx->buf[inlen++] = 0x06;
+	memset(sctx->buf + inlen, 0, sctx->rsiz - inlen);
+	sctx->buf[sctx->rsiz - 1] |= 0x80;
+
+	for (i = 0; i < sctx->rsizw; i++)
+		sctx->st[i] ^= ((u64 *) sctx->buf)[i];
+
+	keccakf(sctx->st);
+
+	for (i = 0; i < sctx->rsizw; i++)
+		sctx->st[i] = cpu_to_le64(sctx->st[i]);
+
+	memcpy(out, sctx->st, sctx->md_len);
+
+	memset(sctx, 0, sizeof(*sctx));
+	return 0;
+}
+
+static struct shash_alg sha3_224 = {
+	.digestsize	=	SHA3_224_DIGEST_SIZE,
+	.init		=	sha3_224_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-224",
+		.cra_driver_name =	"sha3-224-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_224_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static struct shash_alg sha3_256 = {
+	.digestsize	=	SHA3_256_DIGEST_SIZE,
+	.init		=	sha3_256_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-256",
+		.cra_driver_name =	"sha3-256-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_256_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static struct shash_alg sha3_384 = {
+	.digestsize	=	SHA3_384_DIGEST_SIZE,
+	.init		=	sha3_384_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-384",
+		.cra_driver_name =	"sha3-384-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_384_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static struct shash_alg sha3_512 = {
+	.digestsize	=	SHA3_512_DIGEST_SIZE,
+	.init		=	sha3_512_init,
+	.update		=	sha3_update,
+	.final		=	sha3_final,
+	.descsize	=	sizeof(struct sha3_state),
+	.base		=	{
+		.cra_name	=	"sha3-512",
+		.cra_driver_name =	"sha3-512-generic",
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA3_512_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+};
+
+static int __init sha3_generic_mod_init(void)
+{
+	int ret;
+
+	ret = crypto_register_shash(&sha3_224);
+	if (ret < 0)
+		goto err_out;
+	ret = crypto_register_shash(&sha3_256);
+	if (ret < 0)
+		goto err_out_224;
+	ret = crypto_register_shash(&sha3_384);
+	if (ret < 0)
+		goto err_out_256;
+	ret = crypto_register_shash(&sha3_512);
+	if (ret < 0)
+		goto err_out_384;
+
+	return 0;
+
+err_out_384:
+	crypto_unregister_shash(&sha3_384);
+err_out_256:
+	crypto_unregister_shash(&sha3_256);
+err_out_224:
+	crypto_unregister_shash(&sha3_224);
+err_out:
+	return ret;
+}
+
+static void __exit sha3_generic_mod_fini(void)
+{
+	crypto_unregister_shash(&sha3_224);
+	crypto_unregister_shash(&sha3_256);
+	crypto_unregister_shash(&sha3_384);
+	crypto_unregister_shash(&sha3_512);
+}
+
+module_init(sha3_generic_mod_init);
+module_exit(sha3_generic_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-3 Secure Hash Algorithm");
+
+MODULE_ALIAS_CRYPTO("sha3-224");
+MODULE_ALIAS_CRYPTO("sha3-224-generic");
+MODULE_ALIAS_CRYPTO("sha3-256");
+MODULE_ALIAS_CRYPTO("sha3-256-generic");
+MODULE_ALIAS_CRYPTO("sha3-384");
+MODULE_ALIAS_CRYPTO("sha3-384-generic");
+MODULE_ALIAS_CRYPTO("sha3-512");
+MODULE_ALIAS_CRYPTO("sha3-512-generic");
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 69230e9..f7d0018 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -16,7 +16,11 @@
 
 #include <crypto/internal/skcipher.h>
 #include <linux/bug.h>
+#include <linux/cryptouser.h>
 #include <linux/module.h>
+#include <linux/rtnetlink.h>
+#include <linux/seq_file.h>
+#include <net/netlink.h>
 
 #include "internal.h"
 
@@ -25,10 +29,11 @@
 	if (alg->cra_type == &crypto_blkcipher_type)
 		return sizeof(struct crypto_blkcipher *);
 
-	BUG_ON(alg->cra_type != &crypto_ablkcipher_type &&
-	       alg->cra_type != &crypto_givcipher_type);
+	if (alg->cra_type == &crypto_ablkcipher_type ||
+	    alg->cra_type == &crypto_givcipher_type)
+		return sizeof(struct crypto_ablkcipher *);
 
-	return sizeof(struct crypto_ablkcipher *);
+	return crypto_alg_extsize(alg);
 }
 
 static int skcipher_setkey_blkcipher(struct crypto_skcipher *tfm,
@@ -216,26 +221,118 @@
 	return 0;
 }
 
+static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(skcipher);
+
+	alg->exit(skcipher);
+}
+
 static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 {
+	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
+	struct skcipher_alg *alg = crypto_skcipher_alg(skcipher);
+
 	if (tfm->__crt_alg->cra_type == &crypto_blkcipher_type)
 		return crypto_init_skcipher_ops_blkcipher(tfm);
 
-	BUG_ON(tfm->__crt_alg->cra_type != &crypto_ablkcipher_type &&
-	       tfm->__crt_alg->cra_type != &crypto_givcipher_type);
+	if (tfm->__crt_alg->cra_type == &crypto_ablkcipher_type ||
+	    tfm->__crt_alg->cra_type == &crypto_givcipher_type)
+		return crypto_init_skcipher_ops_ablkcipher(tfm);
 
-	return crypto_init_skcipher_ops_ablkcipher(tfm);
+	skcipher->setkey = alg->setkey;
+	skcipher->encrypt = alg->encrypt;
+	skcipher->decrypt = alg->decrypt;
+	skcipher->ivsize = alg->ivsize;
+	skcipher->keysize = alg->max_keysize;
+
+	if (alg->exit)
+		skcipher->base.exit = crypto_skcipher_exit_tfm;
+
+	if (alg->init)
+		return alg->init(skcipher);
+
+	return 0;
 }
 
+static void crypto_skcipher_free_instance(struct crypto_instance *inst)
+{
+	struct skcipher_instance *skcipher =
+		container_of(inst, struct skcipher_instance, s.base);
+
+	skcipher->free(skcipher);
+}
+
+static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	struct skcipher_alg *skcipher = container_of(alg, struct skcipher_alg,
+						     base);
+
+	seq_printf(m, "type         : skcipher\n");
+	seq_printf(m, "async        : %s\n",
+		   alg->cra_flags & CRYPTO_ALG_ASYNC ?  "yes" : "no");
+	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
+	seq_printf(m, "min keysize  : %u\n", skcipher->min_keysize);
+	seq_printf(m, "max keysize  : %u\n", skcipher->max_keysize);
+	seq_printf(m, "ivsize       : %u\n", skcipher->ivsize);
+	seq_printf(m, "chunksize    : %u\n", skcipher->chunksize);
+}
+
+#ifdef CONFIG_NET
+static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_blkcipher rblkcipher;
+	struct skcipher_alg *skcipher = container_of(alg, struct skcipher_alg,
+						     base);
+
+	strncpy(rblkcipher.type, "skcipher", sizeof(rblkcipher.type));
+	strncpy(rblkcipher.geniv, "<none>", sizeof(rblkcipher.geniv));
+
+	rblkcipher.blocksize = alg->cra_blocksize;
+	rblkcipher.min_keysize = skcipher->min_keysize;
+	rblkcipher.max_keysize = skcipher->max_keysize;
+	rblkcipher.ivsize = skcipher->ivsize;
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER,
+		    sizeof(struct crypto_report_blkcipher), &rblkcipher))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int crypto_skcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
 static const struct crypto_type crypto_skcipher_type2 = {
 	.extsize = crypto_skcipher_extsize,
 	.init_tfm = crypto_skcipher_init_tfm,
+	.free = crypto_skcipher_free_instance,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_skcipher_show,
+#endif
+	.report = crypto_skcipher_report,
 	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
 	.maskset = CRYPTO_ALG_TYPE_BLKCIPHER_MASK,
-	.type = CRYPTO_ALG_TYPE_BLKCIPHER,
+	.type = CRYPTO_ALG_TYPE_SKCIPHER,
 	.tfmsize = offsetof(struct crypto_skcipher, base),
 };
 
+int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn,
+			  const char *name, u32 type, u32 mask)
+{
+	spawn->base.frontend = &crypto_skcipher_type2;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_grab_skcipher);
+
 struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name,
 					      u32 type, u32 mask)
 {
@@ -243,5 +340,90 @@
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_skcipher);
 
+int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_type_has_alg(alg_name, &crypto_skcipher_type2,
+				   type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_has_skcipher2);
+
+static int skcipher_prepare_alg(struct skcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	if (!alg->chunksize)
+		alg->chunksize = base->cra_blocksize;
+
+	base->cra_type = &crypto_skcipher_type2;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER;
+
+	return 0;
+}
+
+int crypto_register_skcipher(struct skcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+	int err;
+
+	err = skcipher_prepare_alg(alg);
+	if (err)
+		return err;
+
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_skcipher);
+
+void crypto_unregister_skcipher(struct skcipher_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_skcipher);
+
+int crypto_register_skciphers(struct skcipher_alg *algs, int count)
+{
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_skcipher(&algs[i]);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (--i; i >= 0; --i)
+		crypto_unregister_skcipher(&algs[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_register_skciphers);
+
+void crypto_unregister_skciphers(struct skcipher_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_skcipher(&algs[i]);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_skciphers);
+
+int skcipher_register_instance(struct crypto_template *tmpl,
+			   struct skcipher_instance *inst)
+{
+	int err;
+
+	err = skcipher_prepare_alg(&inst->alg);
+	if (err)
+		return err;
+
+	return crypto_register_instance(tmpl, skcipher_crypto_instance(inst));
+}
+EXPORT_SYMBOL_GPL(skcipher_register_instance);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Symmetric key cipher type");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 579dce0..ae22f05 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -24,6 +24,7 @@
 
 #include <crypto/aead.h>
 #include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/fips.h>
 #include <linux/init.h>
@@ -72,7 +73,8 @@
 	"cast6", "arc4", "michael_mic", "deflate", "crc32c", "tea", "xtea",
 	"khazad", "wp512", "wp384", "wp256", "tnepres", "xeta",  "fcrypt",
 	"camellia", "seed", "salsa20", "rmd128", "rmd160", "rmd256", "rmd320",
-	"lzo", "cts", "zlib", NULL
+	"lzo", "cts", "zlib", "sha3-224", "sha3-256", "sha3-384", "sha3-512",
+	NULL
 };
 
 struct tcrypt_result {
@@ -91,76 +93,6 @@
 	complete(&res->completion);
 }
 
-static int test_cipher_jiffies(struct blkcipher_desc *desc, int enc,
-			       struct scatterlist *sg, int blen, int secs)
-{
-	unsigned long start, end;
-	int bcount;
-	int ret;
-
-	for (start = jiffies, end = start + secs * HZ, bcount = 0;
-	     time_before(jiffies, end); bcount++) {
-		if (enc)
-			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
-		else
-			ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
-
-		if (ret)
-			return ret;
-	}
-
-	printk("%d operations in %d seconds (%ld bytes)\n",
-	       bcount, secs, (long)bcount * blen);
-	return 0;
-}
-
-static int test_cipher_cycles(struct blkcipher_desc *desc, int enc,
-			      struct scatterlist *sg, int blen)
-{
-	unsigned long cycles = 0;
-	int ret = 0;
-	int i;
-
-	local_irq_disable();
-
-	/* Warm-up run. */
-	for (i = 0; i < 4; i++) {
-		if (enc)
-			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
-		else
-			ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
-
-		if (ret)
-			goto out;
-	}
-
-	/* The real thing. */
-	for (i = 0; i < 8; i++) {
-		cycles_t start, end;
-
-		start = get_cycles();
-		if (enc)
-			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
-		else
-			ret = crypto_blkcipher_decrypt(desc, sg, sg, blen);
-		end = get_cycles();
-
-		if (ret)
-			goto out;
-
-		cycles += end - start;
-	}
-
-out:
-	local_irq_enable();
-
-	if (ret == 0)
-		printk("1 operation in %lu cycles (%d bytes)\n",
-		       (cycles + 4) / 8, blen);
-
-	return ret;
-}
-
 static inline int do_one_aead_op(struct aead_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
@@ -454,106 +386,6 @@
 	return;
 }
 
-static void test_cipher_speed(const char *algo, int enc, unsigned int secs,
-			      struct cipher_speed_template *template,
-			      unsigned int tcount, u8 *keysize)
-{
-	unsigned int ret, i, j, iv_len;
-	const char *key;
-	char iv[128];
-	struct crypto_blkcipher *tfm;
-	struct blkcipher_desc desc;
-	const char *e;
-	u32 *b_size;
-
-	if (enc == ENCRYPT)
-	        e = "encryption";
-	else
-		e = "decryption";
-
-	tfm = crypto_alloc_blkcipher(algo, 0, CRYPTO_ALG_ASYNC);
-
-	if (IS_ERR(tfm)) {
-		printk("failed to load transform for %s: %ld\n", algo,
-		       PTR_ERR(tfm));
-		return;
-	}
-	desc.tfm = tfm;
-	desc.flags = 0;
-
-	printk(KERN_INFO "\ntesting speed of %s (%s) %s\n", algo,
-			get_driver_name(crypto_blkcipher, tfm), e);
-
-	i = 0;
-	do {
-
-		b_size = block_sizes;
-		do {
-			struct scatterlist sg[TVMEMSIZE];
-
-			if ((*keysize + *b_size) > TVMEMSIZE * PAGE_SIZE) {
-				printk("template (%u) too big for "
-				       "tvmem (%lu)\n", *keysize + *b_size,
-				       TVMEMSIZE * PAGE_SIZE);
-				goto out;
-			}
-
-			printk("test %u (%d bit key, %d byte blocks): ", i,
-					*keysize * 8, *b_size);
-
-			memset(tvmem[0], 0xff, PAGE_SIZE);
-
-			/* set key, plain text and IV */
-			key = tvmem[0];
-			for (j = 0; j < tcount; j++) {
-				if (template[j].klen == *keysize) {
-					key = template[j].key;
-					break;
-				}
-			}
-
-			ret = crypto_blkcipher_setkey(tfm, key, *keysize);
-			if (ret) {
-				printk("setkey() failed flags=%x\n",
-						crypto_blkcipher_get_flags(tfm));
-				goto out;
-			}
-
-			sg_init_table(sg, TVMEMSIZE);
-			sg_set_buf(sg, tvmem[0] + *keysize,
-				   PAGE_SIZE - *keysize);
-			for (j = 1; j < TVMEMSIZE; j++) {
-				sg_set_buf(sg + j, tvmem[j], PAGE_SIZE);
-				memset (tvmem[j], 0xff, PAGE_SIZE);
-			}
-
-			iv_len = crypto_blkcipher_ivsize(tfm);
-			if (iv_len) {
-				memset(&iv, 0xff, iv_len);
-				crypto_blkcipher_set_iv(tfm, iv, iv_len);
-			}
-
-			if (secs)
-				ret = test_cipher_jiffies(&desc, enc, sg,
-							  *b_size, secs);
-			else
-				ret = test_cipher_cycles(&desc, enc, sg,
-							 *b_size);
-
-			if (ret) {
-				printk("%s() failed flags=%x\n", e, desc.flags);
-				break;
-			}
-			b_size++;
-			i++;
-		} while (*b_size);
-		keysize++;
-	} while (*keysize);
-
-out:
-	crypto_free_blkcipher(tfm);
-}
-
 static void test_hash_sg_init(struct scatterlist *sg)
 {
 	int i;
@@ -577,6 +409,127 @@
 	return ret;
 }
 
+struct test_mb_ahash_data {
+	struct scatterlist sg[TVMEMSIZE];
+	char result[64];
+	struct ahash_request *req;
+	struct tcrypt_result tresult;
+	char *xbuf[XBUFSIZE];
+};
+
+static void test_mb_ahash_speed(const char *algo, unsigned int sec,
+				struct hash_speed *speed)
+{
+	struct test_mb_ahash_data *data;
+	struct crypto_ahash *tfm;
+	unsigned long start, end;
+	unsigned long cycles;
+	unsigned int i, j, k;
+	int ret;
+
+	data = kzalloc(sizeof(*data) * 8, GFP_KERNEL);
+	if (!data)
+		return;
+
+	tfm = crypto_alloc_ahash(algo, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_err("failed to load transform for %s: %ld\n",
+			algo, PTR_ERR(tfm));
+		goto free_data;
+	}
+
+	for (i = 0; i < 8; ++i) {
+		if (testmgr_alloc_buf(data[i].xbuf))
+			goto out;
+
+		init_completion(&data[i].tresult.completion);
+
+		data[i].req = ahash_request_alloc(tfm, GFP_KERNEL);
+		if (!data[i].req) {
+			pr_err("alg: hash: Failed to allocate request for %s\n",
+			       algo);
+			goto out;
+		}
+
+		ahash_request_set_callback(data[i].req, 0,
+					   tcrypt_complete, &data[i].tresult);
+		test_hash_sg_init(data[i].sg);
+	}
+
+	pr_info("\ntesting speed of multibuffer %s (%s)\n", algo,
+		get_driver_name(crypto_ahash, tfm));
+
+	for (i = 0; speed[i].blen != 0; i++) {
+		/* For some reason this only tests digests. */
+		if (speed[i].blen != speed[i].plen)
+			continue;
+
+		if (speed[i].blen > TVMEMSIZE * PAGE_SIZE) {
+			pr_err("template (%u) too big for tvmem (%lu)\n",
+			       speed[i].blen, TVMEMSIZE * PAGE_SIZE);
+			goto out;
+		}
+
+		if (speed[i].klen)
+			crypto_ahash_setkey(tfm, tvmem[0], speed[i].klen);
+
+		for (k = 0; k < 8; k++)
+			ahash_request_set_crypt(data[k].req, data[k].sg,
+						data[k].result, speed[i].blen);
+
+		pr_info("test%3u "
+			"(%5u byte blocks,%5u bytes per update,%4u updates): ",
+			i, speed[i].blen, speed[i].plen,
+			speed[i].blen / speed[i].plen);
+
+		start = get_cycles();
+
+		for (k = 0; k < 8; k++) {
+			ret = crypto_ahash_digest(data[k].req);
+			if (ret == -EINPROGRESS) {
+				ret = 0;
+				continue;
+			}
+
+			if (ret)
+				break;
+
+			complete(&data[k].tresult.completion);
+			data[k].tresult.err = 0;
+		}
+
+		for (j = 0; j < k; j++) {
+			struct tcrypt_result *tr = &data[j].tresult;
+
+			wait_for_completion(&tr->completion);
+			if (tr->err)
+				ret = tr->err;
+		}
+
+		end = get_cycles();
+		cycles = end - start;
+		pr_cont("%6lu cycles/operation, %4lu cycles/byte\n",
+			cycles, cycles / (8 * speed[i].blen));
+
+		if (ret) {
+			pr_err("At least one hashing failed ret=%d\n", ret);
+			break;
+		}
+	}
+
+out:
+	for (k = 0; k < 8; ++k)
+		ahash_request_free(data[k].req);
+
+	for (k = 0; k < 8; ++k)
+		testmgr_free_buf(data[k].xbuf);
+
+	crypto_free_ahash(tfm);
+
+free_data:
+	kfree(data);
+}
+
 static int test_ahash_jiffies_digest(struct ahash_request *req, int blen,
 				     char *out, int secs)
 {
@@ -812,7 +765,7 @@
 	return test_ahash_speed_common(algo, secs, speed, CRYPTO_ALG_ASYNC);
 }
 
-static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
+static inline int do_one_acipher_op(struct skcipher_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
 		struct tcrypt_result *tr = req->base.data;
@@ -825,7 +778,7 @@
 	return ret;
 }
 
-static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
+static int test_acipher_jiffies(struct skcipher_request *req, int enc,
 				int blen, int secs)
 {
 	unsigned long start, end;
@@ -836,10 +789,10 @@
 	     time_before(jiffies, end); bcount++) {
 		if (enc)
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_encrypt(req));
+						crypto_skcipher_encrypt(req));
 		else
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_decrypt(req));
+						crypto_skcipher_decrypt(req));
 
 		if (ret)
 			return ret;
@@ -850,7 +803,7 @@
 	return 0;
 }
 
-static int test_acipher_cycles(struct ablkcipher_request *req, int enc,
+static int test_acipher_cycles(struct skcipher_request *req, int enc,
 			       int blen)
 {
 	unsigned long cycles = 0;
@@ -861,10 +814,10 @@
 	for (i = 0; i < 4; i++) {
 		if (enc)
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_encrypt(req));
+						crypto_skcipher_encrypt(req));
 		else
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_decrypt(req));
+						crypto_skcipher_decrypt(req));
 
 		if (ret)
 			goto out;
@@ -877,10 +830,10 @@
 		start = get_cycles();
 		if (enc)
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_encrypt(req));
+						crypto_skcipher_encrypt(req));
 		else
 			ret = do_one_acipher_op(req,
-						crypto_ablkcipher_decrypt(req));
+						crypto_skcipher_decrypt(req));
 		end = get_cycles();
 
 		if (ret)
@@ -897,16 +850,16 @@
 	return ret;
 }
 
-static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
-			       struct cipher_speed_template *template,
-			       unsigned int tcount, u8 *keysize)
+static void test_skcipher_speed(const char *algo, int enc, unsigned int secs,
+				struct cipher_speed_template *template,
+				unsigned int tcount, u8 *keysize, bool async)
 {
 	unsigned int ret, i, j, k, iv_len;
 	struct tcrypt_result tresult;
 	const char *key;
 	char iv[128];
-	struct ablkcipher_request *req;
-	struct crypto_ablkcipher *tfm;
+	struct skcipher_request *req;
+	struct crypto_skcipher *tfm;
 	const char *e;
 	u32 *b_size;
 
@@ -917,7 +870,7 @@
 
 	init_completion(&tresult.completion);
 
-	tfm = crypto_alloc_ablkcipher(algo, 0, 0);
+	tfm = crypto_alloc_skcipher(algo, 0, async ? 0 : CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm)) {
 		pr_err("failed to load transform for %s: %ld\n", algo,
@@ -926,17 +879,17 @@
 	}
 
 	pr_info("\ntesting speed of async %s (%s) %s\n", algo,
-			get_driver_name(crypto_ablkcipher, tfm), e);
+			get_driver_name(crypto_skcipher, tfm), e);
 
-	req = ablkcipher_request_alloc(tfm, GFP_KERNEL);
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
 	if (!req) {
 		pr_err("tcrypt: skcipher: Failed to allocate request for %s\n",
 		       algo);
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					tcrypt_complete, &tresult);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      tcrypt_complete, &tresult);
 
 	i = 0;
 	do {
@@ -966,12 +919,12 @@
 				}
 			}
 
-			crypto_ablkcipher_clear_flags(tfm, ~0);
+			crypto_skcipher_clear_flags(tfm, ~0);
 
-			ret = crypto_ablkcipher_setkey(tfm, key, *keysize);
+			ret = crypto_skcipher_setkey(tfm, key, *keysize);
 			if (ret) {
 				pr_err("setkey() failed flags=%x\n",
-					crypto_ablkcipher_get_flags(tfm));
+					crypto_skcipher_get_flags(tfm));
 				goto out_free_req;
 			}
 
@@ -995,11 +948,11 @@
 				sg_set_buf(sg, tvmem[0] + *keysize, *b_size);
 			}
 
-			iv_len = crypto_ablkcipher_ivsize(tfm);
+			iv_len = crypto_skcipher_ivsize(tfm);
 			if (iv_len)
 				memset(&iv, 0xff, iv_len);
 
-			ablkcipher_request_set_crypt(req, sg, sg, *b_size, iv);
+			skcipher_request_set_crypt(req, sg, sg, *b_size, iv);
 
 			if (secs)
 				ret = test_acipher_jiffies(req, enc,
@@ -1010,7 +963,7 @@
 
 			if (ret) {
 				pr_err("%s() failed flags=%x\n", e,
-					crypto_ablkcipher_get_flags(tfm));
+				       crypto_skcipher_get_flags(tfm));
 				break;
 			}
 			b_size++;
@@ -1020,9 +973,25 @@
 	} while (*keysize);
 
 out_free_req:
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 out:
-	crypto_free_ablkcipher(tfm);
+	crypto_free_skcipher(tfm);
+}
+
+static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
+			       struct cipher_speed_template *template,
+			       unsigned int tcount, u8 *keysize)
+{
+	return test_skcipher_speed(algo, enc, secs, template, tcount, keysize,
+				   true);
+}
+
+static void test_cipher_speed(const char *algo, int enc, unsigned int secs,
+			      struct cipher_speed_template *template,
+			      unsigned int tcount, u8 *keysize)
+{
+	return test_skcipher_speed(algo, enc, secs, template, tcount, keysize,
+				   false);
 }
 
 static void test_available(void)
@@ -1284,6 +1253,22 @@
 		ret += tcrypt_test("crct10dif");
 		break;
 
+	case 48:
+		ret += tcrypt_test("sha3-224");
+		break;
+
+	case 49:
+		ret += tcrypt_test("sha3-256");
+		break;
+
+	case 50:
+		ret += tcrypt_test("sha3-384");
+		break;
+
+	case 51:
+		ret += tcrypt_test("sha3-512");
+		break;
+
 	case 100:
 		ret += tcrypt_test("hmac(md5)");
 		break;
@@ -1328,6 +1313,22 @@
 		ret += tcrypt_test("hmac(crc32)");
 		break;
 
+	case 111:
+		ret += tcrypt_test("hmac(sha3-224)");
+		break;
+
+	case 112:
+		ret += tcrypt_test("hmac(sha3-256)");
+		break;
+
+	case 113:
+		ret += tcrypt_test("hmac(sha3-384)");
+		break;
+
+	case 114:
+		ret += tcrypt_test("hmac(sha3-512)");
+		break;
+
 	case 150:
 		ret += tcrypt_test("ansi_cprng");
 		break;
@@ -1406,6 +1407,10 @@
 				speed_template_32_48_64);
 		test_cipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
 				speed_template_32_48_64);
+		test_cipher_speed("cts(cbc(aes))", ENCRYPT, sec, NULL, 0,
+				speed_template_16_24_32);
+		test_cipher_speed("cts(cbc(aes))", DECRYPT, sec, NULL, 0,
+				speed_template_16_24_32);
 		test_cipher_speed("ctr(aes)", ENCRYPT, sec, NULL, 0,
 				speed_template_16_24_32);
 		test_cipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
@@ -1691,6 +1696,22 @@
 		test_hash_speed("poly1305", sec, poly1305_speed_template);
 		if (mode > 300 && mode < 400) break;
 
+	case 322:
+		test_hash_speed("sha3-224", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
+	case 323:
+		test_hash_speed("sha3-256", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
+	case 324:
+		test_hash_speed("sha3-384", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
+	case 325:
+		test_hash_speed("sha3-512", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
 	case 399:
 		break;
 
@@ -1770,6 +1791,35 @@
 		test_ahash_speed("rmd320", sec, generic_hash_speed_template);
 		if (mode > 400 && mode < 500) break;
 
+	case 418:
+		test_ahash_speed("sha3-224", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 419:
+		test_ahash_speed("sha3-256", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 420:
+		test_ahash_speed("sha3-384", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+
+	case 421:
+		test_ahash_speed("sha3-512", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 422:
+		test_mb_ahash_speed("sha1", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 423:
+		test_mb_ahash_speed("sha256", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
+	case 424:
+		test_mb_ahash_speed("sha512", sec, generic_hash_speed_template);
+		if (mode > 400 && mode < 500) break;
+
 	case 499:
 		break;
 
@@ -1790,6 +1840,10 @@
 				   speed_template_32_48_64);
 		test_acipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
 				   speed_template_32_48_64);
+		test_acipher_speed("cts(cbc(aes))", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("cts(cbc(aes))", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
 		test_acipher_speed("ctr(aes)", ENCRYPT, sec, NULL, 0,
 				   speed_template_16_24_32);
 		test_acipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index c727fb0..5c9d5a5 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -32,6 +32,7 @@
 #include <crypto/rng.h>
 #include <crypto/drbg.h>
 #include <crypto/akcipher.h>
+#include <crypto/kpp.h>
 
 #include "internal.h"
 
@@ -120,6 +121,11 @@
 	unsigned int count;
 };
 
+struct kpp_test_suite {
+	struct kpp_testvec *vecs;
+	unsigned int count;
+};
+
 struct alg_test_desc {
 	const char *alg;
 	int (*test)(const struct alg_test_desc *desc, const char *driver,
@@ -134,6 +140,7 @@
 		struct cprng_test_suite cprng;
 		struct drbg_test_suite drbg;
 		struct akcipher_test_suite akcipher;
+		struct kpp_test_suite kpp;
 	} suite;
 };
 
@@ -1777,8 +1784,135 @@
 
 }
 
-static int do_test_rsa(struct crypto_akcipher *tfm,
-		       struct akcipher_testvec *vecs)
+static int do_test_kpp(struct crypto_kpp *tfm, struct kpp_testvec *vec,
+		       const char *alg)
+{
+	struct kpp_request *req;
+	void *input_buf = NULL;
+	void *output_buf = NULL;
+	struct tcrypt_result result;
+	unsigned int out_len_max;
+	int err = -ENOMEM;
+	struct scatterlist src, dst;
+
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		return err;
+
+	init_completion(&result.completion);
+
+	err = crypto_kpp_set_secret(tfm, vec->secret, vec->secret_size);
+	if (err < 0)
+		goto free_req;
+
+	out_len_max = crypto_kpp_maxsize(tfm);
+	output_buf = kzalloc(out_len_max, GFP_KERNEL);
+	if (!output_buf) {
+		err = -ENOMEM;
+		goto free_req;
+	}
+
+	/* Use appropriate parameter as base */
+	kpp_request_set_input(req, NULL, 0);
+	sg_init_one(&dst, output_buf, out_len_max);
+	kpp_request_set_output(req, &dst, out_len_max);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				 tcrypt_complete, &result);
+
+	/* Compute public key */
+	err = wait_async_op(&result, crypto_kpp_generate_public_key(req));
+	if (err) {
+		pr_err("alg: %s: generate public key test failed. err %d\n",
+		       alg, err);
+		goto free_output;
+	}
+	/* Verify calculated public key */
+	if (memcmp(vec->expected_a_public, sg_virt(req->dst),
+		   vec->expected_a_public_size)) {
+		pr_err("alg: %s: generate public key test failed. Invalid output\n",
+		       alg);
+		err = -EINVAL;
+		goto free_output;
+	}
+
+	/* Calculate shared secret key by using counter part (b) public key. */
+	input_buf = kzalloc(vec->b_public_size, GFP_KERNEL);
+	if (!input_buf) {
+		err = -ENOMEM;
+		goto free_output;
+	}
+
+	memcpy(input_buf, vec->b_public, vec->b_public_size);
+	sg_init_one(&src, input_buf, vec->b_public_size);
+	sg_init_one(&dst, output_buf, out_len_max);
+	kpp_request_set_input(req, &src, vec->b_public_size);
+	kpp_request_set_output(req, &dst, out_len_max);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				 tcrypt_complete, &result);
+	err = wait_async_op(&result, crypto_kpp_compute_shared_secret(req));
+	if (err) {
+		pr_err("alg: %s: compute shard secret test failed. err %d\n",
+		       alg, err);
+		goto free_all;
+	}
+	/*
+	 * verify shared secret from which the user will derive
+	 * secret key by executing whatever hash it has chosen
+	 */
+	if (memcmp(vec->expected_ss, sg_virt(req->dst),
+		   vec->expected_ss_size)) {
+		pr_err("alg: %s: compute shared secret test failed. Invalid output\n",
+		       alg);
+		err = -EINVAL;
+	}
+
+free_all:
+	kfree(input_buf);
+free_output:
+	kfree(output_buf);
+free_req:
+	kpp_request_free(req);
+	return err;
+}
+
+static int test_kpp(struct crypto_kpp *tfm, const char *alg,
+		    struct kpp_testvec *vecs, unsigned int tcount)
+{
+	int ret, i;
+
+	for (i = 0; i < tcount; i++) {
+		ret = do_test_kpp(tfm, vecs++, alg);
+		if (ret) {
+			pr_err("alg: %s: test failed on vector %d, err=%d\n",
+			       alg, i + 1, ret);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static int alg_test_kpp(const struct alg_test_desc *desc, const char *driver,
+			u32 type, u32 mask)
+{
+	struct crypto_kpp *tfm;
+	int err = 0;
+
+	tfm = crypto_alloc_kpp(driver, type | CRYPTO_ALG_INTERNAL, mask);
+	if (IS_ERR(tfm)) {
+		pr_err("alg: kpp: Failed to load tfm for %s: %ld\n",
+		       driver, PTR_ERR(tfm));
+		return PTR_ERR(tfm);
+	}
+	if (desc->suite.kpp.vecs)
+		err = test_kpp(tfm, desc->alg, desc->suite.kpp.vecs,
+			       desc->suite.kpp.count);
+
+	crypto_free_kpp(tfm);
+	return err;
+}
+
+static int test_akcipher_one(struct crypto_akcipher *tfm,
+			     struct akcipher_testvec *vecs)
 {
 	char *xbuf[XBUFSIZE];
 	struct akcipher_request *req;
@@ -1807,6 +1941,7 @@
 	if (err)
 		goto free_req;
 
+	err = -ENOMEM;
 	out_len_max = crypto_akcipher_maxsize(tfm);
 	outbuf_enc = kzalloc(out_len_max, GFP_KERNEL);
 	if (!outbuf_enc)
@@ -1829,17 +1964,18 @@
 	/* Run RSA encrypt - c = m^e mod n;*/
 	err = wait_async_op(&result, crypto_akcipher_encrypt(req));
 	if (err) {
-		pr_err("alg: rsa: encrypt test failed. err %d\n", err);
+		pr_err("alg: akcipher: encrypt test failed. err %d\n", err);
 		goto free_all;
 	}
 	if (req->dst_len != vecs->c_size) {
-		pr_err("alg: rsa: encrypt test failed. Invalid output len\n");
+		pr_err("alg: akcipher: encrypt test failed. Invalid output len\n");
 		err = -EINVAL;
 		goto free_all;
 	}
 	/* verify that encrypted message is equal to expected */
 	if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) {
-		pr_err("alg: rsa: encrypt test failed. Invalid output\n");
+		pr_err("alg: akcipher: encrypt test failed. Invalid output\n");
+		hexdump(outbuf_enc, vecs->c_size);
 		err = -EINVAL;
 		goto free_all;
 	}
@@ -1867,18 +2003,22 @@
 	/* Run RSA decrypt - m = c^d mod n;*/
 	err = wait_async_op(&result, crypto_akcipher_decrypt(req));
 	if (err) {
-		pr_err("alg: rsa: decrypt test failed. err %d\n", err);
+		pr_err("alg: akcipher: decrypt test failed. err %d\n", err);
 		goto free_all;
 	}
 	out_len = req->dst_len;
-	if (out_len != vecs->m_size) {
-		pr_err("alg: rsa: decrypt test failed. Invalid output len\n");
+	if (out_len < vecs->m_size) {
+		pr_err("alg: akcipher: decrypt test failed. "
+		       "Invalid output len %u\n", out_len);
 		err = -EINVAL;
 		goto free_all;
 	}
 	/* verify that decrypted message is equal to the original msg */
-	if (memcmp(vecs->m, outbuf_dec, vecs->m_size)) {
-		pr_err("alg: rsa: decrypt test failed. Invalid output\n");
+	if (memchr_inv(outbuf_dec, 0, out_len - vecs->m_size) ||
+	    memcmp(vecs->m, outbuf_dec + out_len - vecs->m_size,
+		   vecs->m_size)) {
+		pr_err("alg: akcipher: decrypt test failed. Invalid output\n");
+		hexdump(outbuf_dec, out_len);
 		err = -EINVAL;
 	}
 free_all:
@@ -1891,28 +2031,22 @@
 	return err;
 }
 
-static int test_rsa(struct crypto_akcipher *tfm, struct akcipher_testvec *vecs,
-		    unsigned int tcount)
-{
-	int ret, i;
-
-	for (i = 0; i < tcount; i++) {
-		ret = do_test_rsa(tfm, vecs++);
-		if (ret) {
-			pr_err("alg: rsa: test failed on vector %d, err=%d\n",
-			       i + 1, ret);
-			return ret;
-		}
-	}
-	return 0;
-}
-
 static int test_akcipher(struct crypto_akcipher *tfm, const char *alg,
 			 struct akcipher_testvec *vecs, unsigned int tcount)
 {
-	if (strncmp(alg, "rsa", 3) == 0)
-		return test_rsa(tfm, vecs, tcount);
+	const char *algo =
+		crypto_tfm_alg_driver_name(crypto_akcipher_tfm(tfm));
+	int ret, i;
 
+	for (i = 0; i < tcount; i++) {
+		ret = test_akcipher_one(tfm, vecs++);
+		if (!ret)
+			continue;
+
+		pr_err("alg: akcipher: test %d failed for %s, err=%d\n",
+		       i + 1, algo, ret);
+		return ret;
+	}
 	return 0;
 }
 
@@ -2729,6 +2863,16 @@
 			}
 		}
 	}, {
+		.alg = "dh",
+		.test = alg_test_kpp,
+		.fips_allowed = 1,
+		.suite = {
+			.kpp = {
+				.vecs = dh_tv_template,
+				.count = DH_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "digest_null",
 		.test = alg_test_null,
 	}, {
@@ -3157,6 +3301,16 @@
 			}
 		}
 	}, {
+		.alg = "ecdh",
+		.test = alg_test_kpp,
+		.fips_allowed = 1,
+		.suite = {
+			.kpp = {
+				.vecs = ecdh_tv_template,
+				.count = ECDH_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "gcm(aes)",
 		.test = alg_test_aead,
 		.fips_allowed = 1,
@@ -3249,6 +3403,46 @@
 			}
 		}
 	}, {
+		.alg = "hmac(sha3-224)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_224_tv_template,
+				.count = HMAC_SHA3_224_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "hmac(sha3-256)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_256_tv_template,
+				.count = HMAC_SHA3_256_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "hmac(sha3-384)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_384_tv_template,
+				.count = HMAC_SHA3_384_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "hmac(sha3-512)",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = hmac_sha3_512_tv_template,
+				.count = HMAC_SHA3_512_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "hmac(sha384)",
 		.test = alg_test_hash,
 		.fips_allowed = 1,
@@ -3659,6 +3853,46 @@
 			}
 		}
 	}, {
+		.alg = "sha3-224",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_224_tv_template,
+				.count = SHA3_224_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "sha3-256",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_256_tv_template,
+				.count = SHA3_256_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "sha3-384",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_384_tv_template,
+				.count = SHA3_384_TEST_VECTORS
+			}
+		}
+	}, {
+		.alg = "sha3-512",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = sha3_512_tv_template,
+				.count = SHA3_512_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "sha384",
 		.test = alg_test_hash,
 		.fips_allowed = 1,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 487ec88..acb6bbf 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -133,6 +133,17 @@
 	bool public_key_vec;
 };
 
+struct kpp_testvec {
+	unsigned char *secret;
+	unsigned char *b_public;
+	unsigned char *expected_a_public;
+	unsigned char *expected_ss;
+	unsigned short secret_size;
+	unsigned short b_public_size;
+	unsigned short expected_a_public_size;
+	unsigned short expected_ss_size;
+};
+
 static char zeroed_string[48];
 
 /*
@@ -141,7 +152,7 @@
 #ifdef CONFIG_CRYPTO_FIPS
 #define RSA_TEST_VECTORS	2
 #else
-#define RSA_TEST_VECTORS	4
+#define RSA_TEST_VECTORS	5
 #endif
 static struct akcipher_testvec rsa_tv_template[] = {
 	{
@@ -327,6 +338,516 @@
 	.m_size = 8,
 	.c_size = 256,
 	.public_key_vec = true,
+	}, {
+	.key =
+	"\x30\x82\x09\x29" /* sequence of 2345 bytes */
+	"\x02\x01\x00" /* version integer of 1 byte */
+	"\x02\x82\x02\x01" /* modulus - integer of 513 bytes */
+	"\x00\xC3\x8B\x55\x7B\x73\x4D\xFF\xE9\x9B\xC6\xDC\x67\x3C\xB4\x8E"
+	"\xA0\x86\xED\xF2\xB9\x50\x5C\x54\x5C\xBA\xE4\xA1\xB2\xA7\xAE\x2F"
+	"\x1B\x7D\xF1\xFB\xAC\x79\xC5\xDF\x1A\x00\xC9\xB2\xC1\x61\x25\x33"
+	"\xE6\x9C\xE9\xCF\xD6\x27\xC4\x4E\x44\x30\x44\x5E\x08\xA1\x87\x52"
+	"\xCC\x6B\x97\x70\x8C\xBC\xA5\x06\x31\x0C\xD4\x2F\xD5\x7D\x26\x24"
+	"\xA2\xE2\xAC\x78\xF4\x53\x14\xCE\xF7\x19\x2E\xD7\xF7\xE6\x0C\xB9"
+	"\x56\x7F\x0B\xF1\xB1\xE2\x43\x70\xBD\x86\x1D\xA1\xCC\x2B\x19\x08"
+	"\x76\xEF\x91\xAC\xBF\x20\x24\x0D\x38\xC0\x89\xB8\x9A\x70\xB3\x64"
+	"\xD9\x8F\x80\x41\x10\x5B\x9F\xB1\xCB\x76\x43\x00\x21\x25\x36\xD4"
+	"\x19\xFC\x55\x95\x10\xE4\x26\x74\x98\x2C\xD9\xBD\x0B\x2B\x04\xC2"
+	"\xAC\x82\x38\xB4\xDD\x4C\x04\x7E\x51\x36\x40\x1E\x0B\xC4\x7C\x25"
+	"\xDD\x4B\xB2\xE7\x20\x0A\x57\xF9\xB4\x94\xC3\x08\x33\x22\x6F\x8B"
+	"\x48\xDB\x03\x68\x5A\x5B\xBA\xAE\xF3\xAD\xCF\xC3\x6D\xBA\xF1\x28"
+	"\x67\x7E\x6C\x79\x07\xDE\xFC\xED\xE7\x96\xE3\x6C\xE0\x2C\x87\xF8"
+	"\x02\x01\x28\x38\x43\x21\x53\x84\x69\x75\x78\x15\x7E\xEE\xD2\x1B"
+	"\xB9\x23\x40\xA8\x86\x1E\x38\x83\xB2\x73\x1D\x53\xFB\x9E\x2A\x8A"
+	"\xB2\x75\x35\x01\xC3\xC3\xC4\x94\xE8\x84\x86\x64\x81\xF4\x42\xAA"
+	"\x3C\x0E\xD6\x4F\xBC\x0A\x09\x2D\xE7\x1B\xD4\x10\xA8\x54\xEA\x89"
+	"\x84\x8A\xCB\xF7\x5A\x3C\xCA\x76\x08\x29\x62\xB4\x6A\x22\xDF\x14"
+	"\x95\x71\xFD\xB6\x86\x39\xB8\x8B\xF8\x91\x7F\x38\xAA\x14\xCD\xE5"
+	"\xF5\x1D\xC2\x6D\x53\x69\x52\x84\x7F\xA3\x1A\x5E\x26\x04\x83\x06"
+	"\x73\x52\x56\xCF\x76\x26\xC9\xDD\x75\xD7\xFC\xF4\x69\xD8\x7B\x55"
+	"\xB7\x68\x13\x53\xB9\xE7\x89\xC3\xE8\xD6\x6E\xA7\x6D\xEA\x81\xFD"
+	"\xC4\xB7\x05\x5A\xB7\x41\x0A\x23\x8E\x03\x8A\x1C\xAE\xD3\x1E\xCE"
+	"\xE3\x5E\xFC\x19\x4A\xEE\x61\x9B\x8E\xE5\xE5\xDD\x85\xF9\x41\xEC"
+	"\x14\x53\x92\xF7\xDD\x06\x85\x02\x91\xE3\xEB\x6C\x43\x03\xB1\x36"
+	"\x7B\x89\x5A\xA8\xEB\xFC\xD5\xA8\x35\xDC\x81\xD9\x5C\xBD\xCA\xDC"
+	"\x9B\x98\x0B\x06\x5D\x0C\x5B\xEE\xF3\xD5\xCC\x57\xC9\x71\x2F\x90"
+	"\x3B\x3C\xF0\x8E\x4E\x35\x48\xAE\x63\x74\xA9\xFC\x72\x75\x8E\x34"
+	"\xA8\xF2\x1F\xEA\xDF\x3A\x37\x2D\xE5\x39\x39\xF8\x57\x58\x3C\x04"
+	"\xFE\x87\x06\x98\xBC\x7B\xD3\x21\x36\x60\x25\x54\xA7\x3D\xFA\x91"
+	"\xCC\xA8\x0B\x92\x8E\xB4\xF7\x06\xFF\x1E\x95\xCB\x07\x76\x97\x3B"
+	"\x9D"
+	"\x02\x03\x01\x00\x01" /* public key integer of 3 bytes */
+	"\x02\x82\x02\x00" /* private key integer of 512 bytes */
+	"\x74\xA9\xE0\x6A\x32\xB4\xCA\x85\xD9\x86\x9F\x60\x88\x7B\x40\xCC"
+	"\xCD\x33\x91\xA8\xB6\x25\x1F\xBF\xE3\x51\x1C\x97\xB6\x2A\xD9\xB8"
+	"\x11\x40\x19\xE3\x21\x13\xC8\xB3\x7E\xDC\xD7\x65\x40\x4C\x2D\xD6"
+	"\xDC\xAF\x32\x6C\x96\x75\x2C\x2C\xCA\x8F\x3F\x7A\xEE\xC4\x09\xC6"
+	"\x24\x3A\xC9\xCF\x6D\x8D\x17\x50\x94\x52\xD3\xE7\x0F\x2F\x7E\x94"
+	"\x1F\xA0\xBE\xD9\x25\xE8\x38\x42\x7C\x27\xD2\x79\xF8\x2A\x87\x38"
+	"\xEF\xBB\x74\x8B\xA8\x6E\x8C\x08\xC6\xC7\x4F\x0C\xBC\x79\xC6\xEF"
+	"\x0E\xA7\x5E\xE4\xF8\x8C\x09\xC7\x5E\x37\xCC\x87\x77\xCD\xCF\xD1"
+	"\x6D\x28\x1B\xA9\x62\xC0\xB8\x16\xA7\x8B\xF9\xBB\xCC\xB4\x15\x7F"
+	"\x1B\x69\x03\xF2\x7B\xEB\xE5\x8C\x14\xD6\x23\x4F\x52\x6F\x18\xA6"
+	"\x4B\x5B\x01\xAD\x35\xF9\x48\x53\xB3\x86\x35\x66\xD7\xE7\x29\xC0"
+	"\x09\xB5\xC6\xE6\xFA\xC4\xDA\x19\xBE\xD7\x4D\x41\x14\xBE\x6F\xDF"
+	"\x1B\xAB\xC0\xCA\x88\x07\xAC\xF1\x7D\x35\x83\x67\x28\x2D\x50\xE9"
+	"\xCE\x27\x71\x5E\x1C\xCF\xD2\x30\x65\x79\x72\x2F\x9C\xE1\xD2\x39"
+	"\x7F\xEF\x3B\x01\xF2\x14\x1D\xDF\xBD\x51\xD3\xA1\x53\x62\xCF\x5F"
+	"\x79\x84\xCE\x06\x96\x69\x29\x49\x82\x1C\x71\x4A\xA1\x66\xC8\x2F"
+	"\xFD\x7B\x96\x7B\xFC\xC4\x26\x58\xC4\xFC\x7C\xAF\xB5\xE8\x95\x83"
+	"\x87\xCB\x46\xDE\x97\xA7\xB3\xA2\x54\x5B\xD7\xAF\xAB\xEB\xC8\xF3"
+	"\x55\x9D\x48\x2B\x30\x9C\xDC\x26\x4B\xC2\x89\x45\x13\xB2\x01\x9A"
+	"\xA4\x65\xC3\xEC\x24\x2D\x26\x97\xEB\x80\x8A\x9D\x03\xBC\x59\x66"
+	"\x9E\xE2\xBB\xBB\x63\x19\x64\x93\x11\x7B\x25\x65\x30\xCD\x5B\x4B"
+	"\x2C\xFF\xDC\x2D\x30\x87\x1F\x3C\x88\x07\xD0\xFC\x48\xCC\x05\x8A"
+	"\xA2\xC8\x39\x3E\xD5\x51\xBC\x0A\xBE\x6D\xA8\xA0\xF6\x88\x06\x79"
+	"\x13\xFF\x1B\x45\xDA\x54\xC9\x24\x25\x8A\x75\x0A\x26\xD1\x69\x81"
+	"\x14\x14\xD1\x79\x7D\x8E\x76\xF2\xE0\xEB\xDD\x0F\xDE\xC2\xEC\x80"
+	"\xD7\xDC\x16\x99\x92\xBE\xCB\x40\x0C\xCE\x7C\x3B\x46\xA2\x5B\x5D"
+	"\x0C\x45\xEB\xE1\x00\xDE\x72\x50\xB1\xA6\x0B\x76\xC5\x8D\xFC\x82"
+	"\x38\x6D\x99\x14\x1D\x1A\x4A\xD3\x7C\x53\xB8\x12\x46\xA2\x30\x38"
+	"\x82\xF4\x96\x6E\x8C\xCE\x47\x0D\xAF\x0A\x3B\x45\xB7\x43\x95\x43"
+	"\x9E\x02\x2C\x44\x07\x6D\x1F\x3C\x66\x89\x09\xB6\x1F\x06\x30\xCC"
+	"\xAD\xCE\x7D\x9A\xDE\x3E\xFB\x6C\xE4\x58\x43\xD2\x4F\xA5\x9E\x5E"
+	"\xA7\x7B\xAE\x3A\xF6\x7E\xD9\xDB\xD3\xF5\xC5\x41\xAF\xE6\x9C\x91"
+	"\x02\x82\x01\x01" /* prime1 - integer of 257 bytes */
+	"\x00\xE0\xA6\x6C\xF0\xA2\xF8\x81\x85\x36\x43\xD0\x13\x0B\x33\x8B"
+	"\x8F\x78\x3D\xAC\xC7\x5E\x46\x6A\x7F\x05\xAE\x3E\x26\x0A\xA6\xD0"
+	"\x51\xF3\xC8\x61\xF5\x77\x22\x48\x10\x87\x4C\xD5\xA4\xD5\xAE\x2D"
+	"\x4E\x7A\xFE\x1C\x31\xE7\x6B\xFF\xA4\x69\x20\xF9\x2A\x0B\x99\xBE"
+	"\x7C\x32\x68\xAD\xB0\xC6\x94\x81\x41\x75\xDC\x06\x78\x0A\xB4\xCF"
+	"\xCD\x1B\x2D\x31\xE4\x7B\xEA\xA8\x35\x99\x75\x57\xC6\x0E\xF6\x78"
+	"\x4F\xA0\x92\x4A\x00\x1B\xE7\x96\xF2\x5B\xFD\x2C\x0A\x0A\x13\x81"
+	"\xAF\xCB\x59\x87\x31\xD9\x83\x65\xF2\x22\x48\xD0\x03\x67\x39\xF6"
+	"\xFF\xA8\x36\x07\x3A\x68\xE3\x7B\xA9\x64\xFD\x9C\xF7\xB1\x3D\xBF"
+	"\x26\x5C\xCC\x7A\xFC\xA2\x8F\x51\xD1\xE1\xE2\x3C\xEC\x06\x75\x7C"
+	"\x34\xF9\xA9\x33\x70\x11\xAD\x5A\xDC\x5F\xCF\x50\xF6\x23\x2F\x39"
+	"\xAC\x92\x48\x53\x4D\x01\x96\x3C\xD8\xDC\x1F\x23\x23\x78\x80\x34"
+	"\x54\x14\x76\x8B\xB6\xBB\xFB\x88\x78\x31\x59\x28\xD2\xB1\x75\x17"
+	"\x88\x04\x4A\x78\x62\x18\x2E\xF5\xFB\x9B\xEF\x15\xD8\x16\x47\xC6"
+	"\x42\xB1\x02\xDA\x9E\xE3\x84\x90\xB4\x2D\xC3\xCE\x13\xC9\x12\x7D"
+	"\x3E\xCD\x39\x39\xC9\xAD\xA1\x1A\xE6\xD5\xAD\x5A\x09\x4D\x1B\x0C"
+	"\xAB"
+	"\x02\x82\x01\x01" /* prime 2 - integer of 257 bytes */
+	"\x00\xDE\xD5\x1B\xF6\xCD\x83\xB1\xC6\x47\x7E\xB9\xC0\x6B\xA9\xB8"
+	"\x02\xF3\xAE\x40\x5D\xFC\xD3\xE5\x4E\xF1\xE3\x39\x04\x52\x84\x89"
+	"\x40\x37\xBB\xC2\xCD\x7F\x71\x77\x17\xDF\x6A\x4C\x31\x24\x7F\xB9"
+	"\x7E\x7F\xC8\x43\x4A\x3C\xEB\x8D\x1B\x7F\x21\x51\x67\x45\x8F\xA0"
+	"\x36\x29\x3A\x18\x45\xA5\x32\xEC\x74\x88\x3C\x98\x5D\x67\x3B\xD7"
+	"\x51\x1F\xE9\xAE\x09\x01\xDE\xDE\x7C\xFB\x60\xD1\xA5\x6C\xE9\x6A"
+	"\x93\x04\x02\x3A\xBB\x67\x02\xB9\xFD\x23\xF0\x02\x2B\x49\x85\xC9"
+	"\x5B\xE7\x4B\xDF\xA3\xF4\xEE\x59\x4C\x45\xEF\x8B\xC1\x6B\xDE\xDE"
+	"\xBC\x1A\xFC\xD2\x76\x3F\x33\x74\xA9\x8E\xA3\x7E\x0C\xC6\xCE\x70"
+	"\xA1\x5B\xA6\x77\xEA\x76\xEB\x18\xCE\xB9\xD7\x78\x8D\xAE\x06\xBB"
+	"\xD3\x1F\x16\x0D\x05\xAB\x4F\xC6\x52\xC8\x6B\x36\x51\x7D\x1D\x27"
+	"\xAF\x88\x9A\x6F\xCC\x25\x2E\x74\x06\x72\xCE\x9E\xDB\xE0\x9D\x30"
+	"\xEF\x55\xA5\x58\x21\xA7\x42\x12\x2C\x2C\x23\x87\xC1\x0F\xE8\x51"
+	"\xDA\x53\xDA\xFC\x05\x36\xDF\x08\x0E\x08\x36\xBE\x5C\x86\x9E\xCA"
+	"\x68\x90\x33\x12\x0B\x14\x82\xAB\x90\x1A\xD4\x49\x32\x9C\xBD\xAA"
+	"\xAB\x4E\x38\xF1\xEE\xED\x3D\x3F\xE8\xBD\x48\x56\xA6\x64\xEE\xC8"
+	"\xD7"
+	"\x02\x82\x01\x01" /* exponent 1 - integer of 257 bytes */
+	"\x00\x96\x5E\x6F\x8F\x06\xD6\xE6\x03\x1F\x96\x76\x81\x38\xBF\x30"
+	"\xCC\x40\x84\xAF\xD0\xE7\x06\xA5\x24\x0E\xCE\x59\xA5\x26\xFE\x0F"
+	"\x74\xBB\x83\xC6\x26\x02\xAF\x3C\xA3\x6B\x9C\xFF\x68\x0C\xEB\x40"
+	"\x42\x46\xCB\x2E\x5E\x2C\xF4\x3A\x32\x77\x77\xED\xAF\xBA\x02\x17"
+	"\xE1\x93\xF0\x43\x4A\x8F\x31\x39\xEF\x72\x0F\x6B\x79\x10\x59\x84"
+	"\xBA\x5A\x55\x7F\x0E\xDB\xEE\xEE\xD6\xA9\xB8\x44\x9F\x3A\xC6\xB9"
+	"\x33\x3B\x5C\x90\x11\xD0\x9B\xCC\x8A\xBF\x0E\x10\x5B\x4B\xF1\x50"
+	"\x9E\x35\xB3\xE0\x6D\x7A\x95\x9C\x38\x5D\xC0\x75\x13\xC2\x15\xA7"
+	"\x81\xEA\xBA\xF7\x4D\x9E\x85\x9D\xF1\x7D\xBA\xD0\x45\x6F\x2A\xD0"
+	"\x76\xC2\x28\xD0\xAD\xA7\xB5\xDC\xE3\x6A\x99\xFF\x83\x50\xB3\x75"
+	"\x07\x14\x91\xAF\xEF\x74\xB5\x9F\x9A\xE0\xBA\xA9\x0B\x87\xF3\x85"
+	"\x5C\x40\xB2\x0E\xA7\xFD\xC6\xED\x45\x8E\xD9\x7C\xB0\xB2\x68\xC6"
+	"\x1D\xFD\x70\x78\x06\x41\x7F\x95\x12\x36\x9D\xE2\x58\x5D\x15\xEE"
+	"\x41\x49\xF5\xFA\xEC\x56\x19\xA0\xE6\xE0\xB2\x40\xE1\xD9\xD0\x03"
+	"\x22\x02\xCF\xD1\x3C\x07\x38\x65\x8F\x65\x0E\xAA\x32\xCE\x25\x05"
+	"\x16\x73\x51\xB9\x9F\x88\x0B\xCD\x30\xF3\x97\xCC\x2B\x6B\xA4\x0E"
+	"\x6F"
+	"\x02\x82\x01\x00" /* exponent 2 - integer of 256 bytes */
+	"\x2A\x5F\x3F\xB8\x08\x90\x58\x47\xA9\xE4\xB1\x11\xA3\xE7\x5B\xF4"
+	"\x43\xBE\x08\xC3\x56\x86\x3C\x7E\x6C\x84\x96\x9C\xF9\xCB\xF6\x05"
+	"\x5E\x13\xB8\x11\x37\x80\xAD\xF2\xBE\x2B\x0A\x5D\xF5\xE0\xCB\xB7"
+	"\x00\x39\x66\x82\x41\x5F\x51\x2F\xBF\x56\xE8\x91\xC8\xAA\x6C\xFE"
+	"\x9F\x8C\x4A\x7D\x43\xD2\x91\x1F\xFF\x9F\xF6\x21\x1C\xB6\x46\x55"
+	"\x48\xCA\x38\xAB\xC1\xCD\x4D\x65\x5A\xAF\xA8\x6D\xDA\x6D\xF0\x34"
+	"\x10\x79\x14\x0D\xFA\xA2\x8C\x17\x54\xB4\x18\xD5\x7E\x5F\x90\x50"
+	"\x87\x84\xE7\xFB\xD7\x61\x53\x5D\xAB\x96\xC7\x6E\x7A\x42\xA0\xFC"
+	"\x07\xED\xB7\x5F\x80\xD9\x19\xFF\xFB\xFD\x9E\xC4\x73\x31\x62\x3D"
+	"\x6C\x9E\x15\x03\x62\xA5\x85\xCC\x19\x8E\x9D\x7F\xE3\x6D\xA8\x5D"
+	"\x96\xF5\xAC\x78\x3D\x81\x27\xE7\x29\xF1\x29\x1D\x09\xBB\x77\x86"
+	"\x6B\x65\x62\x88\xE1\x31\x1A\x22\xF7\xC5\xCE\x73\x65\x1C\xBE\xE7"
+	"\x63\xD3\xD3\x14\x63\x27\xAF\x28\xF3\x23\xB6\x76\xC1\xBD\x9D\x82"
+	"\xF4\x9B\x19\x7D\x2C\x57\xF0\xC2\x2A\x51\xAE\x95\x0D\x8C\x38\x54"
+	"\xF5\xC6\xA0\x51\xB7\x0E\xB9\xEC\xE7\x0D\x22\xF6\x1A\xD3\xFE\x16"
+	"\x21\x03\xB7\x0D\x85\xD3\x35\xC9\xDD\xE4\x59\x85\xBE\x7F\xA1\x75"
+	"\x02\x82\x01\x01" /* coefficient - integer of 257 bytes */
+	"\x00\xB9\x48\xD2\x54\x2F\x19\x54\x64\xAE\x62\x80\x61\x89\x80\xB4"
+	"\x48\x0B\x8D\x7E\x1B\x0F\x50\x08\x82\x3F\xED\x75\x84\xB7\x13\xE4"
+	"\xF8\x8D\xA8\xBB\x54\x21\x4C\x5A\x54\x07\x16\x4B\xB4\xA4\x9E\x30"
+	"\xBF\x7A\x30\x1B\x39\x60\xA3\x21\x53\xFB\xB0\xDC\x0F\x7C\x2C\xFB"
+	"\xAA\x95\x7D\x51\x39\x28\x33\x1F\x25\x31\x53\xF5\xD2\x64\x2B\xF2"
+	"\x1E\xB3\xC0\x6A\x0B\xC9\xA4\x42\x64\x5C\xFB\x15\xA3\xE8\x4C\x3A"
+	"\x9C\x3C\xBE\xA3\x39\x83\x23\xE3\x6D\x18\xCC\xC2\xDC\x63\x8D\xBA"
+	"\x98\xE0\xE0\x31\x4A\x2B\x37\x9C\x4D\x6B\xF3\x9F\x51\xE4\x43\x5C"
+	"\x83\x5F\xBF\x5C\xFE\x92\x45\x01\xAF\xF5\xC2\xF4\xB7\x56\x93\xA5"
+	"\xF4\xAA\x67\x3C\x48\x37\xBD\x9A\x3C\xFE\xA5\x9A\xB0\xD1\x6B\x85"
+	"\xDD\x81\xD4\xFA\xAD\x31\x83\xA8\x22\x9B\xFD\xB4\x61\xDC\x7A\x51"
+	"\x59\x62\x10\x1B\x7E\x44\xA3\xFE\x90\x51\x5A\x3E\x02\x87\xAD\xFA"
+	"\xDD\x0B\x1F\x3D\x35\xAF\xEE\x13\x85\x51\xA7\x42\xC0\xEE\x9E\x20"
+	"\xE9\xD0\x29\xB2\xE4\x21\xE4\x6D\x62\xB9\xF4\x48\x4A\xD8\x46\x8E"
+	"\x61\xA6\x2C\x5D\xDF\x8F\x97\x2B\x3A\x75\x1D\x83\x17\x6F\xC6\xB0"
+	"\xDE\xFC\x14\x25\x06\x5A\x60\xBB\xB8\x21\x89\xD1\xEF\x57\xF1\x71"
+	"\x3D",
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\x5c\xce\x9c\xd7\x9a\x9e\xa1\xfe\x7a\x82\x3c\x68\x27\x98\xe3\x5d"
+	"\xd5\xd7\x07\x29\xf5\xfb\xc3\x1a\x7f\x63\x1e\x62\x31\x3b\x19\x87"
+	"\x79\x4f\xec\x7b\xf3\xcb\xea\x9b\x95\x52\x3a\x40\xe5\x87\x7b\x72"
+	"\xd1\x72\xc9\xfb\x54\x63\xd8\xc9\xd7\x2c\xfc\x7b\xc3\x14\x1e\xbc"
+	"\x18\xb4\x34\xa1\xbf\x14\xb1\x37\x31\x6e\xf0\x1b\x35\x19\x54\x07"
+	"\xf7\x99\xec\x3e\x63\xe2\xcd\x61\x28\x65\xc3\xcd\xb1\x38\x36\xa5"
+	"\xb2\xd7\xb0\xdc\x1f\xf5\xef\x19\xc7\x53\x32\x2d\x1c\x26\xda\xe4"
+	"\x0d\xd6\x90\x7e\x28\xd8\xdc\xe4\x61\x05\xd2\x25\x90\x01\xd3\x96"
+	"\x6d\xa6\xcf\x58\x20\xbb\x03\xf4\x01\xbc\x79\xb9\x18\xd8\xb8\xba"
+	"\xbd\x93\xfc\xf2\x62\x5d\x8c\x66\x1e\x0e\x84\x59\x93\xdd\xe2\x93"
+	"\xa2\x62\x7d\x08\x82\x7a\xdd\xfc\xb8\xbc\xc5\x4f\x9c\x4e\xbf\xb4"
+	"\xfc\xf4\xc5\x01\xe8\x00\x70\x4d\x28\x26\xcc\x2e\xfe\x0e\x58\x41"
+	"\x8b\xec\xaf\x7c\x4b\x54\xd0\xa0\x64\xf9\x32\xf4\x2e\x47\x65\x0a"
+	"\x67\x88\x39\x3a\xdb\xb2\xdb\x7b\xb5\xf6\x17\xa8\xd9\xc6\x5e\x28"
+	"\x13\x82\x8a\x99\xdb\x60\x08\xa5\x23\x37\xfa\x88\x90\x31\xc8\x9d"
+	"\x8f\xec\xfb\x85\x9f\xb1\xce\xa6\x24\x50\x46\x44\x47\xcb\x65\xd1"
+	"\xdf\xc0\xb1\x6c\x90\x1f\x99\x8e\x4d\xd5\x9e\x31\x07\x66\x87\xdf"
+	"\x01\xaa\x56\x3c\x71\xe0\x2b\x6f\x67\x3b\x23\xed\xc2\xbd\x03\x30"
+	"\x79\x76\x02\x10\x10\x98\x85\x8a\xff\xfd\x0b\xda\xa5\xd9\x32\x48"
+	"\x02\xa0\x0b\xb9\x2a\x8a\x18\xca\xc6\x8f\x3f\xbb\x16\xb2\xaa\x98"
+	"\x27\xe3\x60\x43\xed\x15\x70\xd4\x57\x15\xfe\x19\xd4\x9b\x13\x78"
+	"\x8a\xf7\x21\xf1\xa2\xa2\x2d\xb3\x09\xcf\x44\x91\x6e\x08\x3a\x30"
+	"\x81\x3e\x90\x93\x8a\x67\x33\x00\x59\x54\x9a\x25\xd3\x49\x8e\x9f"
+	"\xc1\x4b\xe5\x86\xf3\x50\x4c\xbc\xc5\xd3\xf5\x3a\x54\xe1\x36\x3f"
+	"\xe2\x5a\xb4\x37\xc0\xeb\x70\x35\xec\xf6\xb7\xe8\x44\x3b\x7b\xf3"
+	"\xf1\xf2\x1e\xdb\x60\x7d\xd5\xbe\xf0\x71\x34\x90\x4c\xcb\xd4\x35"
+	"\x51\xc7\xdd\xd8\xc9\x81\xf5\x5d\x57\x46\x2c\xb1\x7b\x9b\xaa\xcb"
+	"\xd1\x22\x25\x49\x44\xa3\xd4\x6b\x29\x7b\xd8\xb2\x07\x93\xbf\x3d"
+	"\x52\x49\x84\x79\xef\xb8\xe5\xc4\xad\xca\xa8\xc6\xf6\xa6\x76\x70"
+	"\x5b\x0b\xe5\x83\xc6\x0e\xef\x55\xf2\xe7\xff\x04\xea\xe6\x13\xbe"
+	"\x40\xe1\x40\x45\x48\x66\x75\x31\xae\x35\x64\x91\x11\x6f\xda\xee"
+	"\x26\x86\x45\x6f\x0b\xd5\x9f\x03\xb1\x65\x5b\xdb\xa4\xe4\xf9\x45",
+	.key_len = 2349,
+	.m_size = 8,
+	.c_size = 512,
+	}
+};
+
+#define DH_TEST_VECTORS 2
+
+struct kpp_testvec dh_tv_template[] = {
+	{
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x01\x00" /* type */
+	"\x11\x02" /* len */
+	"\x00\x01\x00\x00" /* key_size */
+	"\x00\x01\x00\x00" /* p_size */
+	"\x01\x00\x00\x00" /* g_size */
+#else
+	"\x00\x01" /* type */
+	"\x02\x11" /* len */
+	"\x00\x00\x01\x00" /* key_size */
+	"\x00\x00\x01\x00" /* p_size */
+	"\x00\x00\x00\x01" /* g_size */
+#endif
+	/* xa */
+	"\x44\xc1\x48\x36\xa7\x2b\x6f\x4e\x43\x03\x68\xad\x31\x00\xda\xf3"
+	"\x2a\x01\xa8\x32\x63\x5f\x89\x32\x1f\xdf\x4c\xa1\x6a\xbc\x10\x15"
+	"\x90\x35\xc9\x26\x41\xdf\x7b\xaa\x56\x56\x3d\x85\x44\xb5\xc0\x8e"
+	"\x37\x83\x06\x50\xb3\x5f\x0e\x28\x2c\xd5\x46\x15\xe3\xda\x7d\x74"
+	"\x87\x13\x91\x4f\xd4\x2d\xf6\xc7\x5e\x14\x2c\x11\xc2\x26\xb4\x3a"
+	"\xe3\xb2\x36\x20\x11\x3b\x22\xf2\x06\x65\x66\xe2\x57\x58\xf8\x22"
+	"\x1a\x94\xbd\x2b\x0e\x8c\x55\xad\x61\x23\x45\x2b\x19\x1e\x63\x3a"
+	"\x13\x61\xe3\xa0\x79\x70\x3e\x6d\x98\x32\xbc\x7f\x82\xc3\x11\xd8"
+	"\xeb\x53\xb5\xfc\xb5\xd5\x3c\x4a\xea\x92\x3e\x01\xce\x15\x65\xd4"
+	"\xaa\x85\xc1\x11\x90\x83\x31\x6e\xfe\xe7\x7f\x7d\xed\xab\xf9\x29"
+	"\xf8\xc7\xf1\x68\xc6\xb7\xe4\x1f\x2f\x28\xa0\xc9\x1a\x50\x64\x29"
+	"\x4b\x01\x6d\x1a\xda\x46\x63\x21\x07\x40\x8c\x8e\x4c\x6f\xb5\xe5"
+	"\x12\xf3\xc2\x1b\x48\x27\x5e\x27\x01\xb1\xaa\xed\x68\x9b\x83\x18"
+	"\x8f\xb1\xeb\x1f\x04\xd1\x3c\x79\xed\x4b\xf7\x0a\x33\xdc\xe0\xc6"
+	"\xd8\x02\x51\x59\x00\x74\x30\x07\x4c\x2d\xac\xe4\x13\xf1\x80\xf0"
+	"\xce\xfa\xff\xa9\xce\x29\x46\xdd\x9d\xad\xd1\xc3\xc6\x58\x1a\x63"
+	/* p */
+	"\xb9\x36\x3a\xf1\x82\x1f\x60\xd3\x22\x47\xb8\xbc\x2d\x22\x6b\x81"
+	"\x7f\xe8\x20\x06\x09\x23\x73\x49\x9a\x59\x8b\x35\x25\xf8\x31\xbc"
+	"\x7d\xa8\x1c\x9d\x56\x0d\x1a\xf7\x4b\x4f\x96\xa4\x35\x77\x6a\x89"
+	"\xab\x42\x00\x49\x21\x71\xed\x28\x16\x1d\x87\x5a\x10\xa7\x9c\x64"
+	"\x94\xd4\x87\x3d\x28\xef\x44\xfe\x4b\xe2\xb4\x15\x8c\x82\xa6\xf3"
+	"\x50\x5f\xa8\xe8\xa2\x60\xe7\x00\x86\x78\x05\xd4\x78\x19\xa1\x98"
+	"\x62\x4e\x4a\x00\x78\x56\x96\xe6\xcf\xd7\x10\x1b\x74\x5d\xd0\x26"
+	"\x61\xdb\x6b\x32\x09\x51\xd8\xa5\xfd\x54\x16\x71\x01\xb3\x39\xe6"
+	"\x4e\x69\xb1\xd7\x06\x8f\xd6\x1e\xdc\x72\x25\x26\x74\xc8\x41\x06"
+	"\x5c\xd1\x26\x5c\xb0\x2f\xf9\x59\x13\xc1\x2a\x0f\x78\xea\x7b\xf7"
+	"\xbd\x59\xa0\x90\x1d\xfc\x33\x5b\x4c\xbf\x05\x9c\x3a\x3f\x69\xa2"
+	"\x45\x61\x4e\x10\x6a\xb3\x17\xc5\x68\x30\xfb\x07\x5f\x34\xc6\xfb"
+	"\x73\x07\x3c\x70\xf6\xae\xe7\x72\x84\xc3\x18\x81\x8f\xe8\x11\x1f"
+	"\x3d\x83\x83\x01\x2a\x14\x73\xbf\x32\x32\x2e\xc9\x4d\xdb\x2a\xca"
+	"\xee\x71\xf9\xda\xad\xe8\x82\x0b\x4d\x0c\x1f\xb6\x1d\xef\x00\x67"
+	"\x74\x3d\x95\xe0\xb7\xc4\x30\x8a\x24\x87\x12\x47\x27\x70\x0d\x73"
+	/* g */
+	"\x02",
+	.b_public =
+	"\x2a\x67\x5c\xfd\x63\x5d\xc0\x97\x0a\x8b\xa2\x1f\xf8\x8a\xcb\x54"
+	"\xca\x2f\xd3\x49\x3f\x01\x8e\x87\xfe\xcc\x94\xa0\x3e\xd4\x26\x79"
+	"\x9a\x94\x3c\x11\x81\x58\x5c\x60\x3d\xf5\x98\x90\x89\x64\x62\x1f"
+	"\xbd\x05\x6d\x2b\xcd\x84\x40\x9b\x4a\x1f\xe0\x19\xf1\xca\x20\xb3"
+	"\x4e\xa0\x4f\x15\xcc\xa5\xfe\xa5\xb4\xf5\x0b\x18\x7a\x5a\x37\xaa"
+	"\x58\x00\x19\x7f\xe2\xa3\xd9\x1c\x44\x57\xcc\xde\x2e\xc1\x38\xea"
+	"\xeb\xe3\x90\x40\xc4\x6c\xf7\xcd\xe9\x22\x50\x71\xf5\x7c\xdb\x37"
+	"\x0e\x80\xc3\xed\x7e\xb1\x2b\x2f\xbe\x71\xa6\x11\xa5\x9d\xf5\x39"
+	"\xf1\xa2\xe5\x85\xbc\x25\x91\x4e\x84\x8d\x26\x9f\x4f\xe6\x0f\xa6"
+	"\x2b\x6b\xf9\x0d\xaf\x6f\xbb\xfa\x2d\x79\x15\x31\x57\xae\x19\x60"
+	"\x22\x0a\xf5\xfd\x98\x0e\xbf\x5d\x49\x75\x58\x37\xbc\x7f\xf5\x21"
+	"\x56\x1e\xd5\xb3\x50\x0b\xca\x96\xf3\xd1\x3f\xb3\x70\xa8\x6d\x63"
+	"\x48\xfb\x3d\xd7\x29\x91\x45\xb5\x48\xcd\xb6\x78\x30\xf2\x3f\x1e"
+	"\xd6\x22\xd6\x35\x9b\xf9\x1f\x85\xae\xab\x4b\xd7\xe0\xc7\x86\x67"
+	"\x3f\x05\x7f\xa6\x0d\x2f\x0d\xbf\x53\x5f\x4d\x2c\x6d\x5e\x57\x40"
+	"\x30\x3a\x23\x98\xf9\xb4\x32\xf5\x32\x83\xdd\x0b\xae\x33\x97\x2f",
+	.expected_a_public =
+	"\x5c\x24\xdf\xeb\x5b\x4b\xf8\xc5\xef\x39\x48\x82\xe0\x1e\x62\xee"
+	"\x8a\xae\xdf\x93\x6c\x2b\x16\x95\x92\x16\x3f\x16\x7b\x75\x03\x85"
+	"\xd9\xf1\x69\xc2\x14\x87\x45\xfc\xa4\x19\xf6\xf0\xa4\xf3\xec\xd4"
+	"\x6c\x5c\x03\x3b\x94\xc2\x2f\x92\xe4\xce\xb3\xe4\x72\xe8\x17\xe6"
+	"\x23\x7e\x00\x01\x09\x59\x13\xbf\xc1\x2f\x99\xa9\x07\xaa\x02\x23"
+	"\x4a\xca\x39\x4f\xbc\xec\x0f\x27\x4f\x19\x93\x6c\xb9\x30\x52\xfd"
+	"\x2b\x9d\x86\xf1\x06\x1e\xb6\x56\x27\x4a\xc9\x8a\xa7\x8a\x48\x5e"
+	"\xb5\x60\xcb\xdf\xff\x03\x26\x10\xbf\x90\x8f\x46\x60\xeb\x9b\x9a"
+	"\xd6\x6f\x44\x91\x03\x92\x18\x2c\x96\x5e\x40\x19\xfb\xf4\x4f\x3a"
+	"\x02\x7b\xaf\xcc\x22\x20\x79\xb9\xf8\x9f\x8f\x85\x6b\xec\x44\xbb"
+	"\xe6\xa8\x8e\xb1\xe8\x2c\xee\x64\xee\xf8\xbd\x00\xf3\xe2\x2b\x93"
+	"\xcd\xe7\xc4\xdf\xc9\x19\x46\xfe\xb6\x07\x73\xc1\x8a\x64\x79\x26"
+	"\xe7\x30\xad\x2a\xdf\xe6\x8f\x59\xf5\x81\xbf\x4a\x29\x91\xe7\xb7"
+	"\xcf\x48\x13\x27\x75\x79\x40\xd9\xd6\x32\x52\x4e\x6a\x86\xae\x6f"
+	"\xc2\xbf\xec\x1f\xc2\x69\xb2\xb6\x59\xe5\xa5\x17\xa4\x77\xb7\x62"
+	"\x46\xde\xe8\xd2\x89\x78\x9a\xef\xa3\xb5\x8f\x26\xec\x80\xda\x39",
+	.expected_ss =
+	"\x8f\xf3\xac\xa2\xea\x22\x11\x5c\x45\x65\x1a\x77\x75\x2e\xcf\x46"
+	"\x23\x14\x1e\x67\x53\x4d\x35\xb0\x38\x1d\x4e\xb9\x41\x9a\x21\x24"
+	"\x6e\x9f\x40\xfe\x90\x51\xb1\x06\xa4\x7b\x87\x17\x2f\xe7\x5e\x22"
+	"\xf0\x7b\x54\x84\x0a\xac\x0a\x90\xd2\xd7\xe8\x7f\xe7\xe3\x30\x75"
+	"\x01\x1f\x24\x75\x56\xbe\xcc\x8d\x1e\x68\x0c\x41\x72\xd3\xfa\xbb"
+	"\xe5\x9c\x60\xc7\x28\x77\x0c\xbe\x89\xab\x08\xd6\x21\xe7\x2e\x1a"
+	"\x58\x7a\xca\x4f\x22\xf3\x2b\x30\xfd\xf4\x98\xc1\xa3\xf8\xf6\xcc"
+	"\xa9\xe4\xdb\x5b\xee\xd5\x5c\x6f\x62\x4c\xd1\x1a\x02\x2a\x23\xe4"
+	"\xb5\x57\xf3\xf9\xec\x04\x83\x54\xfe\x08\x5e\x35\xac\xfb\xa8\x09"
+	"\x82\x32\x60\x11\xb2\x16\x62\x6b\xdf\xda\xde\x9c\xcb\x63\x44\x6c"
+	"\x59\x26\x6a\x8f\xb0\x24\xcb\xa6\x72\x48\x1e\xeb\xe0\xe1\x09\x44"
+	"\xdd\xee\x66\x6d\x84\xcf\xa5\xc1\xb8\x36\x74\xd3\x15\x96\xc3\xe4"
+	"\xc6\x5a\x4d\x23\x97\x0c\x5c\xcb\xa9\xf5\x29\xc2\x0e\xff\x93\x82"
+	"\xd3\x34\x49\xad\x64\xa6\xb1\xc0\x59\x28\x75\x60\xa7\x8a\xb0\x11"
+	"\x56\x89\x42\x74\x11\xf5\xf6\x5e\x6f\x16\x54\x6a\xb1\x76\x4d\x50"
+	"\x8a\x68\xc1\x5b\x82\xb9\x0d\x00\x32\x50\xed\x88\x87\x48\x92\x17",
+	.secret_size = 529,
+	.b_public_size = 256,
+	.expected_a_public_size = 256,
+	.expected_ss_size = 256,
+	},
+	{
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x01\x00" /* type */
+	"\x11\x02" /* len */
+	"\x00\x01\x00\x00" /* key_size */
+	"\x00\x01\x00\x00" /* p_size */
+	"\x01\x00\x00\x00" /* g_size */
+#else
+	"\x00\x01" /* type */
+	"\x02\x11" /* len */
+	"\x00\x00\x01\x00" /* key_size */
+	"\x00\x00\x01\x00" /* p_size */
+	"\x00\x00\x00\x01" /* g_size */
+#endif
+	/* xa */
+	"\x4d\x75\xa8\x6e\xba\x23\x3a\x0c\x63\x56\xc8\xc9\x5a\xa7\xd6\x0e"
+	"\xed\xae\x40\x78\x87\x47\x5f\xe0\xa7\x7b\xba\x84\x88\x67\x4e\xe5"
+	"\x3c\xcc\x5c\x6a\xe7\x4a\x20\xec\xbe\xcb\xf5\x52\x62\x9f\x37\x80"
+	"\x0c\x72\x7b\x83\x66\xa4\xf6\x7f\x95\x97\x1c\x6a\x5c\x7e\xf1\x67"
+	"\x37\xb3\x93\x39\x3d\x0b\x55\x35\xd9\xe5\x22\x04\x9f\xf8\xc1\x04"
+	"\xce\x13\xa5\xac\xe1\x75\x05\xd1\x2b\x53\xa2\x84\xef\xb1\x18\xf4"
+	"\x66\xdd\xea\xe6\x24\x69\x5a\x49\xe0\x7a\xd8\xdf\x1b\xb7\xf1\x6d"
+	"\x9b\x50\x2c\xc8\x1c\x1c\xa3\xb4\x37\xfb\x66\x3f\x67\x71\x73\xa9"
+	"\xff\x5f\xd9\xa2\x25\x6e\x25\x1b\x26\x54\xbf\x0c\xc6\xdb\xea\x0a"
+	"\x52\x6c\x16\x7c\x27\x68\x15\x71\x58\x73\x9d\xe6\xc2\x80\xaa\x97"
+	"\x31\x66\xfb\xa6\xfb\xfd\xd0\x9c\x1d\xbe\x81\x48\xf5\x9a\x32\xf1"
+	"\x69\x62\x18\x78\xae\x72\x36\xe6\x94\x27\xd1\xff\x18\x4f\x28\x6a"
+	"\x16\xbd\x6a\x60\xee\xe5\xf9\x6d\x16\xe4\xb8\xa6\x41\x9b\x23\x7e"
+	"\xf7\x9d\xd1\x1d\x03\x15\x66\x3a\xcf\xb6\x2c\x13\x96\x2c\x52\x21"
+	"\xe4\x2d\x48\x7a\x8a\x5d\xb2\x88\xed\x98\x61\x79\x8b\x6a\x1e\x5f"
+	"\xd0\x8a\x2d\x99\x5a\x2b\x0f\xbc\xef\x53\x8f\x32\xc1\xa2\x99\x26"
+	/* p */
+	"\xb9\x36\x3a\xf1\x82\x1f\x60\xd3\x22\x47\xb8\xbc\x2d\x22\x6b\x81"
+	"\x7f\xe8\x20\x06\x09\x23\x73\x49\x9a\x59\x8b\x35\x25\xf8\x31\xbc"
+	"\x7d\xa8\x1c\x9d\x56\x0d\x1a\xf7\x4b\x4f\x96\xa4\x35\x77\x6a\x89"
+	"\xab\x42\x00\x49\x21\x71\xed\x28\x16\x1d\x87\x5a\x10\xa7\x9c\x64"
+	"\x94\xd4\x87\x3d\x28\xef\x44\xfe\x4b\xe2\xb4\x15\x8c\x82\xa6\xf3"
+	"\x50\x5f\xa8\xe8\xa2\x60\xe7\x00\x86\x78\x05\xd4\x78\x19\xa1\x98"
+	"\x62\x4e\x4a\x00\x78\x56\x96\xe6\xcf\xd7\x10\x1b\x74\x5d\xd0\x26"
+	"\x61\xdb\x6b\x32\x09\x51\xd8\xa5\xfd\x54\x16\x71\x01\xb3\x39\xe6"
+	"\x4e\x69\xb1\xd7\x06\x8f\xd6\x1e\xdc\x72\x25\x26\x74\xc8\x41\x06"
+	"\x5c\xd1\x26\x5c\xb0\x2f\xf9\x59\x13\xc1\x2a\x0f\x78\xea\x7b\xf7"
+	"\xbd\x59\xa0\x90\x1d\xfc\x33\x5b\x4c\xbf\x05\x9c\x3a\x3f\x69\xa2"
+	"\x45\x61\x4e\x10\x6a\xb3\x17\xc5\x68\x30\xfb\x07\x5f\x34\xc6\xfb"
+	"\x73\x07\x3c\x70\xf6\xae\xe7\x72\x84\xc3\x18\x81\x8f\xe8\x11\x1f"
+	"\x3d\x83\x83\x01\x2a\x14\x73\xbf\x32\x32\x2e\xc9\x4d\xdb\x2a\xca"
+	"\xee\x71\xf9\xda\xad\xe8\x82\x0b\x4d\x0c\x1f\xb6\x1d\xef\x00\x67"
+	"\x74\x3d\x95\xe0\xb7\xc4\x30\x8a\x24\x87\x12\x47\x27\x70\x0d\x73"
+	/* g */
+	"\x02",
+	.b_public =
+	"\x99\x4d\xd9\x01\x84\x8e\x4a\x5b\xb8\xa5\x64\x8c\x6c\x00\x5c\x0e"
+	"\x1e\x1b\xee\x5d\x9f\x53\xe3\x16\x70\x01\xed\xbf\x4f\x14\x36\x6e"
+	"\xe4\x43\x45\x43\x49\xcc\xb1\xb0\x2a\xc0\x6f\x22\x55\x42\x17\x94"
+	"\x18\x83\xd7\x2a\x5c\x51\x54\xf8\x4e\x7c\x10\xda\x76\x68\x57\x77"
+	"\x1e\x62\x03\x30\x04\x7b\x4c\x39\x9c\x54\x01\x54\xec\xef\xb3\x55"
+	"\xa4\xc0\x24\x6d\x3d\xbd\xcc\x46\x5b\x00\x96\xc7\xea\x93\xd1\x3f"
+	"\xf2\x6a\x72\xe3\xf2\xc1\x92\x24\x5b\xda\x48\x70\x2c\xa9\x59\x97"
+	"\x19\xb1\xd6\x54\xb3\x9c\x2e\xb0\x63\x07\x9b\x5e\xac\xb5\xf2\xb1"
+	"\x5b\xf8\xf3\xd7\x2d\x37\x9b\x68\x6c\xf8\x90\x07\xbc\x37\x9a\xa5"
+	"\xe2\x91\x12\x25\x47\x77\xe3\x3d\xb2\x95\x69\x44\x0b\x91\x1e\xaf"
+	"\x7c\x8c\x7c\x34\x41\x6a\xab\x60\x6e\xc6\x52\xec\x7e\x94\x0a\x37"
+	"\xec\x98\x90\xdf\x3f\x02\xbd\x23\x52\xdd\xd9\xe5\x31\x80\x74\x25"
+	"\xb6\xd2\xd3\xcc\xd5\xcc\x6d\xf9\x7e\x4d\x78\xab\x77\x51\xfa\x77"
+	"\x19\x94\x49\x8c\x05\xd4\x75\xed\xd2\xb3\x64\x57\xe0\x52\x99\xc0"
+	"\x83\xe3\xbb\x5e\x2b\xf1\xd2\xc0\xb1\x37\x36\x0b\x7c\xb5\x63\x96"
+	"\x8e\xde\x04\x23\x11\x95\x62\x11\x9a\xce\x6f\x63\xc8\xd5\xd1\x8f",
+	.expected_a_public =
+	"\x90\x89\xe4\x82\xd6\x0a\xcf\x1a\xae\xce\x1b\x66\xa7\x19\x71\x18"
+	"\x8f\x95\x4b\x5b\x80\x45\x4a\x5a\x43\x99\x4d\x37\xcf\xa3\xa7\x28"
+	"\x9c\xc7\x73\xf1\xb2\x17\xf6\x99\xe3\x6b\x56\xcb\x3e\x35\x60\x7d"
+	"\x65\xc7\x84\x6b\x3e\x60\xee\xcd\xd2\x70\xe7\xc9\x32\x1c\xf0\xb4"
+	"\xf9\x52\xd9\x88\x75\xfd\x40\x2c\xa7\xbe\x19\x1c\x0a\xae\x93\xe1"
+	"\x71\xc7\xcd\x4f\x33\x5c\x10\x7d\x39\x56\xfc\x73\x84\xb2\x67\xc3"
+	"\x77\x26\x20\x97\x2b\xf8\x13\x43\x93\x9c\x9a\xa4\x08\xc7\x34\x83"
+	"\xe6\x98\x61\xe7\x16\x30\x2c\xb1\xdb\x2a\xb2\xcc\xc3\x02\xa5\x3c"
+	"\x71\x50\x14\x83\xc7\xbb\xa4\xbe\x98\x1b\xfe\xcb\x43\xe9\x97\x62"
+	"\xd6\xf0\x8c\xcb\x1c\xba\x1e\xa8\xa6\xa6\x50\xfc\x85\x7d\x47\xbf"
+	"\xf4\x3e\x23\xd3\x5f\xb2\x71\x3e\x40\x94\xaa\x87\x83\x2c\x6c\x8e"
+	"\x60\xfd\xdd\xf7\xf4\x76\x03\xd3\x1d\xec\x18\x51\xa3\xf2\x44\x1a"
+	"\x3f\xb4\x7c\x18\x0d\x68\x65\x92\x54\x0d\x2d\x81\x16\xf1\x84\x66"
+	"\x89\x92\xd0\x1a\x5e\x1f\x42\x46\x5b\xe5\x83\x86\x80\xd9\xcd\x3a"
+	"\x5a\x2f\xb9\x59\x9b\xe4\x43\x84\x64\xf3\x09\x1a\x0a\xa2\x64\x0f"
+	"\x77\x4e\x8d\x8b\xe6\x88\xd1\xfc\xaf\x8f\xdf\x1d\xbc\x31\xb3\xbd",
+	.expected_ss =
+	"\x34\xc3\x35\x14\x88\x46\x26\x23\x97\xbb\xdd\x28\x5c\x94\xf6\x47"
+	"\xca\xb3\x19\xaf\xca\x44\x9b\xc2\x7d\x89\xfd\x96\x14\xfd\x6d\x58"
+	"\xd8\xc4\x6b\x61\x2a\x0d\xf2\x36\x45\xc8\xe4\xa4\xed\x81\x53\x81"
+	"\x66\x1e\xe0\x5a\xb1\x78\x2d\x0b\x5c\xb4\xd1\xfc\x90\xc6\x9c\xdb"
+	"\x5a\x30\x0b\x14\x7d\xbe\xb3\x7d\xb1\xb2\x76\x3c\x6c\xef\x74\x6b"
+	"\xe7\x1f\x64\x0c\xab\x65\xe1\x76\x5c\x3d\x83\xb5\x8a\xfb\xaf\x0f"
+	"\xf2\x06\x14\x8f\xa0\xf6\xc1\x89\x78\xf2\xba\x72\x73\x3c\xf7\x76"
+	"\x21\x67\xbc\x24\x31\xb8\x09\x65\x0f\x0c\x02\x32\x4a\x98\x14\xfc"
+	"\x72\x2c\x25\x60\x68\x5f\x2f\x30\x1e\x5b\xf0\x3b\xd1\xa2\x87\xa0"
+	"\x54\xdf\xdb\xc0\xee\x0a\x0f\x47\xc9\x90\x20\x2c\xf9\xe3\x52\xad"
+	"\x27\x65\x8d\x54\x8d\xa8\xa1\xf3\xed\x15\xd4\x94\x28\x90\x31\x93"
+	"\x1b\xc0\x51\xbb\x43\x5d\x76\x3b\x1d\x2a\x71\x50\xea\x5d\x48\x94"
+	"\x7f\x6f\xf1\x48\xdb\x30\xe5\xae\x64\x79\xd9\x7a\xdb\xc6\xff\xd8"
+	"\x5e\x5a\x64\xbd\xf6\x85\x04\xe8\x28\x6a\xac\xef\xce\x19\x8e\x9a"
+	"\xfe\x75\xc0\x27\x69\xe3\xb3\x7b\x21\xa7\xb1\x16\xa4\x85\x23\xee"
+	"\xb0\x1b\x04\x6e\xbd\xab\x16\xde\xfd\x86\x6b\xa9\x95\xd7\x0b\xfd",
+	.secret_size = 529,
+	.b_public_size = 256,
+	.expected_a_public_size = 256,
+	.expected_ss_size = 256,
+	}
+};
+
+#ifdef CONFIG_CRYPTO_FIPS
+#define ECDH_TEST_VECTORS 1
+#else
+#define ECDH_TEST_VECTORS 2
+#endif
+struct kpp_testvec ecdh_tv_template[] = {
+	{
+#ifndef CONFIG_CRYPTO_FIPS
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x02\x00" /* type */
+	"\x20\x00" /* len */
+	"\x01\x00" /* curve_id */
+	"\x18\x00" /* key_size */
+#else
+	"\x00\x02" /* type */
+	"\x00\x20" /* len */
+	"\x00\x01" /* curve_id */
+	"\x00\x18" /* key_size */
+#endif
+	"\xb5\x05\xb1\x71\x1e\xbf\x8c\xda"
+	"\x4e\x19\x1e\x62\x1f\x23\x23\x31"
+	"\x36\x1e\xd3\x84\x2f\xcc\x21\x72",
+	.b_public =
+	"\xc3\xba\x67\x4b\x71\xec\xd0\x76"
+	"\x7a\x99\x75\x64\x36\x13\x9a\x94"
+	"\x5d\x8b\xdc\x60\x90\x91\xfd\x3f"
+	"\xb0\x1f\x8a\x0a\x68\xc6\x88\x6e"
+	"\x83\x87\xdd\x67\x09\xf8\x8d\x96"
+	"\x07\xd6\xbd\x1c\xe6\x8d\x9d\x67",
+	.expected_a_public =
+	"\x1a\x04\xdb\xa5\xe1\xdd\x4e\x79"
+	"\xa3\xe6\xef\x0e\x5c\x80\x49\x85"
+	"\xfa\x78\xb4\xef\x49\xbd\x4c\x7c"
+	"\x22\x90\x21\x02\xf9\x1b\x81\x5d"
+	"\x0c\x8a\xa8\x98\xd6\x27\x69\x88"
+	"\x5e\xbc\x94\xd8\x15\x9e\x21\xce",
+	.expected_ss =
+	"\xf4\x57\xcc\x4f\x1f\x4e\x31\xcc"
+	"\xe3\x40\x60\xc8\x06\x93\xc6\x2e"
+	"\x99\x80\x81\x28\xaf\xc5\x51\x74",
+	.secret_size = 32,
+	.b_public_size = 48,
+	.expected_a_public_size = 48,
+	.expected_ss_size = 24
+	}, {
+#endif
+	.secret =
+#ifdef __LITTLE_ENDIAN
+	"\x02\x00" /* type */
+	"\x28\x00" /* len */
+	"\x02\x00" /* curve_id */
+	"\x20\x00" /* key_size */
+#else
+	"\x00\x02" /* type */
+	"\x00\x28" /* len */
+	"\x00\x02" /* curve_id */
+	"\x00\x20" /* key_size */
+#endif
+	"\x24\xd1\x21\xeb\xe5\xcf\x2d\x83"
+	"\xf6\x62\x1b\x6e\x43\x84\x3a\xa3"
+	"\x8b\xe0\x86\xc3\x20\x19\xda\x92"
+	"\x50\x53\x03\xe1\xc0\xea\xb8\x82",
+	.expected_a_public =
+	"\x1a\x7f\xeb\x52\x00\xbd\x3c\x31"
+	"\x7d\xb6\x70\xc1\x86\xa6\xc7\xc4"
+	"\x3b\xc5\x5f\x6c\x6f\x58\x3c\xf5"
+	"\xb6\x63\x82\x77\x33\x24\xa1\x5f"
+	"\x6a\xca\x43\x6f\xf7\x7e\xff\x02"
+	"\x37\x08\xcc\x40\x5e\x7a\xfd\x6a"
+	"\x6a\x02\x6e\x41\x87\x68\x38\x77"
+	"\xfa\xa9\x44\x43\x2d\xef\x09\xdf",
+	.expected_ss =
+	"\xea\x17\x6f\x7e\x6e\x57\x26\x38"
+	"\x8b\xfb\x41\xeb\xba\xc8\x6d\xa5"
+	"\xa8\x72\xd1\xff\xc9\x47\x3d\xaa"
+	"\x58\x43\x9f\x34\x0f\x8c\xf3\xc9",
+	.b_public =
+	"\xcc\xb4\xda\x74\xb1\x47\x3f\xea"
+	"\x6c\x70\x9e\x38\x2d\xc7\xaa\xb7"
+	"\x29\xb2\x47\x03\x19\xab\xdd\x34"
+	"\xbd\xa8\x2c\x93\xe1\xa4\x74\xd9"
+	"\x64\x63\xf7\x70\x20\x2f\xa4\xe6"
+	"\x9f\x4a\x38\xcc\xc0\x2c\x49\x2f"
+	"\xb1\x32\xbb\xaf\x22\x61\xda\xcb"
+	"\x6f\xdb\xa9\xaa\xfc\x77\x81\xf3",
+	.secret_size = 40,
+	.b_public_size = 64,
+	.expected_a_public_size = 64,
+	.expected_ss_size = 32
 	}
 };
 
@@ -376,6 +897,131 @@
 	},
 };
 
+#define SHA3_224_TEST_VECTORS	3
+static struct hash_testvec sha3_224_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\x6b\x4e\x03\x42\x36\x67\xdb\xb7"
+				"\x3b\x6e\x15\x45\x4f\x0e\xb1\xab"
+				"\xd4\x59\x7f\x9a\x1b\x07\x8e\x3f"
+				"\x5b\x5a\x6b\xc7",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x9e\x86\xff\x69\x55\x7c\xa9\x5f"
+				"\x40\x5f\x08\x12\x69\x68\x5b\x38"
+				"\xe3\xa8\x19\xb3\x09\xee\x94\x2f"
+				"\x48\x2b\x6a\x8b",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+				"jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x8a\x24\x10\x8b\x15\x4a\xda\x21"
+				"\xc9\xfd\x55\x74\x49\x44\x79\xba"
+				"\x5c\x7e\x7a\xb7\x6e\xf2\x64\xea"
+				"\xd0\xfc\xce\x33",
+	},
+};
+
+#define SHA3_256_TEST_VECTORS	3
+static struct hash_testvec sha3_256_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\xa7\xff\xc6\xf8\xbf\x1e\xd7\x66"
+				"\x51\xc1\x47\x56\xa0\x61\xd6\x62"
+				"\xf5\x80\xff\x4d\xe4\x3b\x49\xfa"
+				"\x82\xd8\x0a\x4b\x80\xf8\x43\x4a",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x80\x08\x4b\xf2\xfb\xa0\x24\x75"
+				"\x72\x6f\xeb\x2c\xab\x2d\x82\x15"
+				"\xea\xb1\x4b\xc6\xbd\xd8\xbf\xb2"
+				"\xc8\x15\x12\x57\x03\x2e\xcd\x8b",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+			     "jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x41\xc0\xdb\xa2\xa9\xd6\x24\x08"
+				"\x49\x10\x03\x76\xa8\x23\x5e\x2c"
+				"\x82\xe1\xb9\x99\x8a\x99\x9e\x21"
+				"\xdb\x32\xdd\x97\x49\x6d\x33\x76",
+	},
+};
+
+
+#define SHA3_384_TEST_VECTORS	3
+static struct hash_testvec sha3_384_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\x0c\x63\xa7\x5b\x84\x5e\x4f\x7d"
+				"\x01\x10\x7d\x85\x2e\x4c\x24\x85"
+				"\xc5\x1a\x50\xaa\xaa\x94\xfc\x61"
+				"\x99\x5e\x71\xbb\xee\x98\x3a\x2a"
+				"\xc3\x71\x38\x31\x26\x4a\xdb\x47"
+				"\xfb\x6b\xd1\xe0\x58\xd5\xf0\x04",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x18\x15\xf7\x74\xf3\x20\x49\x1b"
+				"\x48\x56\x9e\xfe\xc7\x94\xd2\x49"
+				"\xee\xb5\x9a\xae\x46\xd2\x2b\xf7"
+				"\x7d\xaf\xe2\x5c\x5e\xdc\x28\xd7"
+				"\xea\x44\xf9\x3e\xe1\x23\x4a\xa8"
+				"\x8f\x61\xc9\x19\x12\xa4\xcc\xd9",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+			     "jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x99\x1c\x66\x57\x55\xeb\x3a\x4b"
+				"\x6b\xbd\xfb\x75\xc7\x8a\x49\x2e"
+				"\x8c\x56\xa2\x2c\x5c\x4d\x7e\x42"
+				"\x9b\xfd\xbc\x32\xb9\xd4\xad\x5a"
+				"\xa0\x4a\x1f\x07\x6e\x62\xfe\xa1"
+				"\x9e\xef\x51\xac\xd0\x65\x7c\x22",
+	},
+};
+
+
+#define SHA3_512_TEST_VECTORS	3
+static struct hash_testvec sha3_512_tv_template[] = {
+	{
+		.plaintext = "",
+		.digest	= "\xa6\x9f\x73\xcc\xa2\x3a\x9a\xc5"
+				"\xc8\xb5\x67\xdc\x18\x5a\x75\x6e"
+				"\x97\xc9\x82\x16\x4f\xe2\x58\x59"
+				"\xe0\xd1\xdc\xc1\x47\x5c\x80\xa6"
+				"\x15\xb2\x12\x3a\xf1\xf5\xf9\x4c"
+				"\x11\xe3\xe9\x40\x2c\x3a\xc5\x58"
+				"\xf5\x00\x19\x9d\x95\xb6\xd3\xe3"
+				"\x01\x75\x85\x86\x28\x1d\xcd\x26",
+	}, {
+		.plaintext = "a",
+		.psize	= 1,
+		.digest	= "\x69\x7f\x2d\x85\x61\x72\xcb\x83"
+				"\x09\xd6\xb8\xb9\x7d\xac\x4d\xe3"
+				"\x44\xb5\x49\xd4\xde\xe6\x1e\xdf"
+				"\xb4\x96\x2d\x86\x98\xb7\xfa\x80"
+				"\x3f\x4f\x93\xff\x24\x39\x35\x86"
+				"\xe2\x8b\x5b\x95\x7a\xc3\xd1\xd3"
+				"\x69\x42\x0c\xe5\x33\x32\x71\x2f"
+				"\x99\x7b\xd3\x36\xd0\x9a\xb0\x2a",
+	}, {
+		.plaintext = "abcdbcdecdefdefgefghfghighijhijkijkl"
+			     "jklmklmnlmnomnopnopq",
+		.psize	= 56,
+		.digest	= "\x04\xa3\x71\xe8\x4e\xcf\xb5\xb8"
+				"\xb7\x7c\xb4\x86\x10\xfc\xa8\x18"
+				"\x2d\xd4\x57\xce\x6f\x32\x6a\x0f"
+				"\xd3\xd7\xec\x2f\x1e\x91\x63\x6d"
+				"\xee\x69\x1f\xbe\x0c\x98\x53\x02"
+				"\xba\x1b\x0d\x8d\xc7\x8c\x08\x63"
+				"\x46\xb5\x33\xb4\x9c\x03\x0d\x99"
+				"\xa2\x7d\xaf\x11\x39\xd6\xe7\x5e",
+	},
+};
+
+
 /*
  * MD5 test vectors from RFC1321
  */
@@ -3246,6 +3892,394 @@
 	},
 };
 
+#define HMAC_SHA3_224_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_224_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\x3b\x16\x54\x6b\xbc\x7b\xe2\x70"
+			  "\x6a\x03\x1d\xca\xfd\x56\x37\x3d"
+			  "\x98\x84\x36\x76\x41\xd8\xc5\x9a"
+			  "\xf3\xc8\x60\xf7",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\x7f\xdb\x8d\xd8\x8b\xd2\xf6\x0d"
+			  "\x1b\x79\x86\x34\xad\x38\x68\x11"
+			  "\xc2\xcf\xc8\x5b\xfa\xf5\xd5\x2b"
+			  "\xba\xce\x5e\x66",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\xb4\xa1\xf0\x4c\x00\x28\x7a\x9b"
+			  "\x7f\x60\x75\xb3\x13\xd2\x79\xb8"
+			  "\x33\xbc\x8f\x75\x12\x43\x52\xd0"
+			  "\x5f\xb9\x99\x5f",
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x05\xd8\xcd\x6d\x00\xfa\xea\x8d"
+			  "\x1e\xb6\x8a\xde\x28\x73\x0b\xbd"
+			  "\x3c\xba\xb6\x92\x9f\x0a\x08\x6b"
+			  "\x29\xcd\x62\xa0",
+	},
+};
+
+#define HMAC_SHA3_256_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_256_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\xba\x85\x19\x23\x10\xdf\xfa\x96"
+			  "\xe2\xa3\xa4\x0e\x69\x77\x43\x51"
+			  "\x14\x0b\xb7\x18\x5e\x12\x02\xcd"
+			  "\xcc\x91\x75\x89\xf9\x5e\x16\xbb",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\xc7\xd4\x07\x2e\x78\x88\x77\xae"
+			  "\x35\x96\xbb\xb0\xda\x73\xb8\x87"
+			  "\xc9\x17\x1f\x93\x09\x5b\x29\x4a"
+			  "\xe8\x57\xfb\xe2\x64\x5e\x1b\xa5",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\xed\x73\xa3\x74\xb9\x6c\x00\x52"
+			  "\x35\xf9\x48\x03\x2f\x09\x67\x4a"
+			  "\x58\xc0\xce\x55\x5c\xfc\x1f\x22"
+			  "\x3b\x02\x35\x65\x60\x31\x2c\x3b",
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x65\xc5\xb0\x6d\x4c\x3d\xe3\x2a"
+			  "\x7a\xef\x87\x63\x26\x1e\x49\xad"
+			  "\xb6\xe2\x29\x3e\xc8\xe7\xc6\x1e"
+			  "\x8d\xe6\x17\x01\xfc\x63\xe1\x23",
+	},
+};
+
+#define HMAC_SHA3_384_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_384_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\x68\xd2\xdc\xf7\xfd\x4d\xdd\x0a"
+			  "\x22\x40\xc8\xa4\x37\x30\x5f\x61"
+			  "\xfb\x73\x34\xcf\xb5\xd0\x22\x6e"
+			  "\x1b\xc2\x7d\xc1\x0a\x2e\x72\x3a"
+			  "\x20\xd3\x70\xb4\x77\x43\x13\x0e"
+			  "\x26\xac\x7e\x3d\x53\x28\x86\xbd",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\xf1\x10\x1f\x8c\xbf\x97\x66\xfd"
+			  "\x67\x64\xd2\xed\x61\x90\x3f\x21"
+			  "\xca\x9b\x18\xf5\x7c\xf3\xe1\xa2"
+			  "\x3c\xa1\x35\x08\xa9\x32\x43\xce"
+			  "\x48\xc0\x45\xdc\x00\x7f\x26\xa2"
+			  "\x1b\x3f\x5e\x0e\x9d\xf4\xc2\x0a",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\x0f\xc1\x95\x13\xbf\x6b\xd8\x78"
+			  "\x03\x70\x16\x70\x6a\x0e\x57\xbc"
+			  "\x52\x81\x39\x83\x6b\x9a\x42\xc3"
+			  "\xd4\x19\xe4\x98\xe0\xe1\xfb\x96"
+			  "\x16\xfd\x66\x91\x38\xd3\x3a\x11"
+			  "\x05\xe0\x7c\x72\xb6\x95\x3b\xcc",
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x02\x6f\xdf\x6b\x50\x74\x1e\x37"
+			  "\x38\x99\xc9\xf7\xd5\x40\x6d\x4e"
+			  "\xb0\x9f\xc6\x66\x56\x36\xfc\x1a"
+			  "\x53\x00\x29\xdd\xf5\xcf\x3c\xa5"
+			  "\xa9\x00\xed\xce\x01\xf5\xf6\x1e"
+			  "\x2f\x40\x8c\xdf\x2f\xd3\xe7\xe8",
+	},
+};
+
+#define HMAC_SHA3_512_TEST_VECTORS	4
+
+static struct hash_testvec hmac_sha3_512_tv_template[] = {
+	{
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b",
+		.ksize	= 20,
+		.plaintext = "Hi There",
+		.psize	= 8,
+		.digest	= "\xeb\x3f\xbd\x4b\x2e\xaa\xb8\xf5"
+			  "\xc5\x04\xbd\x3a\x41\x46\x5a\xac"
+			  "\xec\x15\x77\x0a\x7c\xab\xac\x53"
+			  "\x1e\x48\x2f\x86\x0b\x5e\xc7\xba"
+			  "\x47\xcc\xb2\xc6\xf2\xaf\xce\x8f"
+			  "\x88\xd2\x2b\x6d\xc6\x13\x80\xf2"
+			  "\x3a\x66\x8f\xd3\x88\x8b\xb8\x05"
+			  "\x37\xc0\xa0\xb8\x64\x07\x68\x9e",
+	}, {
+		.key	= "Jefe",
+		.ksize	= 4,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\x5a\x4b\xfe\xab\x61\x66\x42\x7c"
+			  "\x7a\x36\x47\xb7\x47\x29\x2b\x83"
+			  "\x84\x53\x7c\xdb\x89\xaf\xb3\xbf"
+			  "\x56\x65\xe4\xc5\xe7\x09\x35\x0b"
+			  "\x28\x7b\xae\xc9\x21\xfd\x7c\xa0"
+			  "\xee\x7a\x0c\x31\xd0\x22\xa9\x5e"
+			  "\x1f\xc9\x2b\xa9\xd7\x7d\xf8\x83"
+			  "\x96\x02\x75\xbe\xb4\xe6\x20\x24",
+		.np	= 4,
+		.tap	= { 7, 7, 7, 7 }
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext = "Test Using Large"
+			   "r Than Block-Siz"
+			   "e Key - Hash Key"
+			   " First",
+		.psize	= 54,
+		.digest = "\x00\xf7\x51\xa9\xe5\x06\x95\xb0"
+			  "\x90\xed\x69\x11\xa4\xb6\x55\x24"
+			  "\x95\x1c\xdc\x15\xa7\x3a\x5d\x58"
+			  "\xbb\x55\x21\x5e\xa2\xcd\x83\x9a"
+			  "\xc7\x9d\x2b\x44\xa3\x9b\xaf\xab"
+			  "\x27\xe8\x3f\xde\x9e\x11\xf6\x34"
+			  "\x0b\x11\xd9\x91\xb1\xb9\x1b\xf2"
+			  "\xee\xe7\xfc\x87\x24\x26\xc3\xa4",
+	}, {
+		.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"
+			  "\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	= 131,
+		.plaintext =
+			  "This is a test u"
+			  "sing a larger th"
+			  "an block-size ke"
+			  "y and a larger t"
+			  "han block-size d"
+			  "ata. The key nee"
+			  "ds to be hashed "
+			  "before being use"
+			  "d by the HMAC al"
+			  "gorithm.",
+		.psize	= 152,
+		.digest	= "\x38\xa4\x56\xa0\x04\xbd\x10\xd3"
+			  "\x2c\x9a\xb8\x33\x66\x84\x11\x28"
+			  "\x62\xc3\xdb\x61\xad\xcc\xa3\x18"
+			  "\x29\x35\x5e\xaf\x46\xfd\x5c\x73"
+			  "\xd0\x6a\x1f\x0d\x13\xfe\xc9\xa6"
+			  "\x52\xfb\x38\x11\xb5\x77\xb1\xb1"
+			  "\xd1\xb9\x78\x9f\x97\xae\x5b\x83"
+			  "\xc6\xf4\x4d\xfc\xf1\xd6\x7e\xba",
+	},
+};
+
 /*
  * Poly1305 test vectors from RFC7539 A.3.
  */
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index ac51149..56ad5a5 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -90,7 +90,7 @@
 
 config HW_RANDOM_BCM2835
 	tristate "Broadcom BCM2835 Random Number Generator support"
-	depends on ARCH_BCM2835
+	depends on ARCH_BCM2835 || ARCH_BCM_NSP || ARCH_BCM_5301X
 	default HW_RANDOM
 	---help---
 	  This driver provides kernel-side support for the Random Number
@@ -396,6 +396,20 @@
 
 	  If unsure, say Y.
 
+config HW_RANDOM_MESON
+	tristate "Amlogic Meson Random Number Generator support"
+	depends on HW_RANDOM
+	depends on ARCH_MESON || COMPILE_TEST
+	default y
+	---help---
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on Amlogic Meson SoCs.
+
+	  To compile this driver as a module, choose M here. the
+	  module will be called meson-rng.
+
+	  If unsure, say Y.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 63022b4..04bb0b0 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -34,3 +34,4 @@
 obj-$(CONFIG_HW_RANDOM_XGENE) += xgene-rng.o
 obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
 obj-$(CONFIG_HW_RANDOM_PIC32) += pic32-rng.o
+obj-$(CONFIG_HW_RANDOM_MESON) += meson-rng.o
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index 7192ec2..af21492 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -19,6 +19,7 @@
 #define RNG_CTRL	0x0
 #define RNG_STATUS	0x4
 #define RNG_DATA	0x8
+#define RNG_INT_MASK	0x10
 
 /* enable rng */
 #define RNG_RBGEN	0x1
@@ -26,10 +27,24 @@
 /* the initial numbers generated are "less random" so will be discarded */
 #define RNG_WARMUP_COUNT 0x40000
 
+#define RNG_INT_OFF	0x1
+
+static void __init nsp_rng_init(void __iomem *base)
+{
+	u32 val;
+
+	/* mask the interrupt */
+	val = readl(base + RNG_INT_MASK);
+	val |= RNG_INT_OFF;
+	writel(val, base + RNG_INT_MASK);
+}
+
 static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max,
 			       bool wait)
 {
 	void __iomem *rng_base = (void __iomem *)rng->priv;
+	u32 max_words = max / sizeof(u32);
+	u32 num_words, count;
 
 	while ((__raw_readl(rng_base + RNG_STATUS) >> 24) == 0) {
 		if (!wait)
@@ -37,8 +52,14 @@
 		cpu_relax();
 	}
 
-	*(u32 *)buf = __raw_readl(rng_base + RNG_DATA);
-	return sizeof(u32);
+	num_words = readl(rng_base + RNG_STATUS) >> 24;
+	if (num_words > max_words)
+		num_words = max_words;
+
+	for (count = 0; count < num_words; count++)
+		((u32 *)buf)[count] = readl(rng_base + RNG_DATA);
+
+	return num_words * sizeof(u32);
 }
 
 static struct hwrng bcm2835_rng_ops = {
@@ -46,10 +67,19 @@
 	.read	= bcm2835_rng_read,
 };
 
+static const struct of_device_id bcm2835_rng_of_match[] = {
+	{ .compatible = "brcm,bcm2835-rng"},
+	{ .compatible = "brcm,bcm-nsp-rng", .data = nsp_rng_init},
+	{ .compatible = "brcm,bcm5301x-rng", .data = nsp_rng_init},
+	{},
+};
+
 static int bcm2835_rng_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
+	void (*rng_setup)(void __iomem *base);
+	const struct of_device_id *rng_id;
 	void __iomem *rng_base;
 	int err;
 
@@ -61,6 +91,15 @@
 	}
 	bcm2835_rng_ops.priv = (unsigned long)rng_base;
 
+	rng_id = of_match_node(bcm2835_rng_of_match, np);
+	if (!rng_id)
+		return -EINVAL;
+
+	/* Check for rng init function, execute it */
+	rng_setup = rng_id->data;
+	if (rng_setup)
+		rng_setup(rng_base);
+
 	/* set warm-up count & enable */
 	__raw_writel(RNG_WARMUP_COUNT, rng_base + RNG_STATUS);
 	__raw_writel(RNG_RBGEN, rng_base + RNG_CTRL);
@@ -90,10 +129,6 @@
 	return 0;
 }
 
-static const struct of_device_id bcm2835_rng_of_match[] = {
-	{ .compatible = "brcm,bcm2835-rng", },
-	{},
-};
 MODULE_DEVICE_TABLE(of, bcm2835_rng_of_match);
 
 static struct platform_driver bcm2835_rng_driver = {
diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c
index ed44561..23d3585 100644
--- a/drivers/char/hw_random/exynos-rng.c
+++ b/drivers/char/hw_random/exynos-rng.c
@@ -45,12 +45,12 @@
 
 static u32 exynos_rng_readl(struct exynos_rng *rng, u32 offset)
 {
-	return	__raw_readl(rng->mem + offset);
+	return	readl_relaxed(rng->mem + offset);
 }
 
 static void exynos_rng_writel(struct exynos_rng *rng, u32 val, u32 offset)
 {
-	__raw_writel(val, rng->mem + offset);
+	writel_relaxed(val, rng->mem + offset);
 }
 
 static int exynos_rng_configure(struct exynos_rng *exynos_rng)
diff --git a/drivers/char/hw_random/meson-rng.c b/drivers/char/hw_random/meson-rng.c
new file mode 100644
index 0000000..0cfd81b
--- /dev/null
+++ b/drivers/char/hw_random/meson-rng.c
@@ -0,0 +1,131 @@
+/*
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2014 Amlogic, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * BSD LICENSE
+ *
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2014 Amlogic, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/hw_random.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/of.h>
+
+#define RNG_DATA 0x00
+
+struct meson_rng_data {
+	void __iomem *base;
+	struct platform_device *pdev;
+	struct hwrng rng;
+};
+
+static int meson_rng_read(struct hwrng *rng, void *buf, size_t max, bool wait)
+{
+	struct meson_rng_data *data =
+			container_of(rng, struct meson_rng_data, rng);
+
+	if (max < sizeof(u32))
+		return 0;
+
+	*(u32 *)buf = readl_relaxed(data->base + RNG_DATA);
+
+	return sizeof(u32);
+}
+
+static int meson_rng_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct meson_rng_data *data;
+	struct resource *res;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->base))
+		return PTR_ERR(data->base);
+
+	data->rng.name = pdev->name;
+	data->rng.read = meson_rng_read;
+
+	platform_set_drvdata(pdev, data);
+
+	return devm_hwrng_register(dev, &data->rng);
+}
+
+static const struct of_device_id meson_rng_of_match[] = {
+	{ .compatible = "amlogic,meson-rng", },
+	{},
+};
+
+static struct platform_driver meson_rng_driver = {
+	.probe	= meson_rng_probe,
+	.driver	= {
+		.name = "meson-rng",
+		.of_match_table = meson_rng_of_match,
+	},
+};
+
+module_platform_driver(meson_rng_driver);
+
+MODULE_ALIAS("platform:meson-rng");
+MODULE_DESCRIPTION("Meson H/W Random Number Generator driver");
+MODULE_AUTHOR("Lawrence Mok <lawrence.mok@amlogic.com>");
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 8a1432e..01d4be2 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -384,7 +384,12 @@
 	}
 
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
+		goto err_ioremap;
+	}
 
 	ret = (dev->of_node) ? of_get_omap_rng_device_details(priv, pdev) :
 				get_omap_rng_device_details(priv);
@@ -435,8 +440,15 @@
 static int __maybe_unused omap_rng_resume(struct device *dev)
 {
 	struct omap_rng_dev *priv = dev_get_drvdata(dev);
+	int ret;
 
-	pm_runtime_get_sync(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret) {
+		dev_err(dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
 	priv->pdata->init(priv);
 
 	return 0;
diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c
index 92a8106..63d84e6 100644
--- a/drivers/char/hw_random/stm32-rng.c
+++ b/drivers/char/hw_random/stm32-rng.c
@@ -69,8 +69,12 @@
 		}
 
 		/* If error detected or data not ready... */
-		if (sr != RNG_SR_DRDY)
+		if (sr != RNG_SR_DRDY) {
+			if (WARN_ONCE(sr & (RNG_SR_SEIS | RNG_SR_CEIS),
+					"bad RNG status - %x\n", sr))
+				writel_relaxed(0, priv->base + RNG_SR);
 			break;
+		}
 
 		*(u32 *)data = readl_relaxed(priv->base + RNG_DR);
 
@@ -79,10 +83,6 @@
 		max -= sizeof(u32);
 	}
 
-	if (WARN_ONCE(sr & (RNG_SR_SEIS | RNG_SR_CEIS),
-		      "bad RNG status - %x\n", sr))
-		writel_relaxed(0, priv->base + RNG_SR);
-
 	pm_runtime_mark_last_busy((struct device *) priv->rng.priv);
 	pm_runtime_put_sync_autosuspend((struct device *) priv->rng.priv);
 
diff --git a/drivers/crypto/bfin_crc.c b/drivers/crypto/bfin_crc.c
index 95b7396..10db7df 100644
--- a/drivers/crypto/bfin_crc.c
+++ b/drivers/crypto/bfin_crc.c
@@ -588,11 +588,6 @@
 	crypto_init_queue(&crc->queue, CRC_CCRYPTO_QUEUE_LENGTH);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res == NULL) {
-		dev_err(&pdev->dev, "Cannot get IORESOURCE_MEM\n");
-		return -ENOENT;
-	}
-
 	crc->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR((void *)crc->regs)) {
 		dev_err(&pdev->dev, "Cannot map CRC IO\n");
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index 5652a53..64bf302 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -1,6 +1,6 @@
 config CRYPTO_DEV_FSL_CAAM
 	tristate "Freescale CAAM-Multicore driver backend"
-	depends on FSL_SOC || ARCH_MXC
+	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
 	help
 	  Enables the driver module for Freescale's Cryptographic Accelerator
 	  and Assurance Module (CAAM), also known as the SEC version 4 (SEC4).
@@ -99,6 +99,18 @@
 	  To compile this as a module, choose M here: the module
 	  will be called caamhash.
 
+config CRYPTO_DEV_FSL_CAAM_PKC_API
+        tristate "Register public key cryptography implementations with Crypto API"
+        depends on CRYPTO_DEV_FSL_CAAM && CRYPTO_DEV_FSL_CAAM_JR
+        default y
+        select CRYPTO_RSA
+        help
+          Selecting this will allow SEC Public key support for RSA.
+          Supported cryptographic primitives: encryption, decryption,
+          signature and verification.
+          To compile this as a module, choose M here: the module
+          will be called caam_pkc.
+
 config CRYPTO_DEV_FSL_CAAM_RNG_API
 	tristate "Register caam device for hwrng API"
 	depends on CRYPTO_DEV_FSL_CAAM && CRYPTO_DEV_FSL_CAAM_JR
@@ -116,10 +128,6 @@
 	def_bool SOC_IMX6 || SOC_IMX7D
 	depends on CRYPTO_DEV_FSL_CAAM
 
-config CRYPTO_DEV_FSL_CAAM_LE
-	def_bool CRYPTO_DEV_FSL_CAAM_IMX || SOC_LS1021A
-	depends on CRYPTO_DEV_FSL_CAAM
-
 config CRYPTO_DEV_FSL_CAAM_DEBUG
 	bool "Enable debug output in CAAM driver"
 	depends on CRYPTO_DEV_FSL_CAAM
diff --git a/drivers/crypto/caam/Makefile b/drivers/crypto/caam/Makefile
index 550758a..08bf551 100644
--- a/drivers/crypto/caam/Makefile
+++ b/drivers/crypto/caam/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the CAAM backend and dependent components
 #
 ifeq ($(CONFIG_CRYPTO_DEV_FSL_CAAM_DEBUG), y)
-	EXTRA_CFLAGS := -DDEBUG
+	ccflags-y := -DDEBUG
 endif
 
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM) += caam.o
@@ -10,6 +10,8 @@
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_CRYPTO_API) += caamalg.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_AHASH_API) += caamhash.o
 obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_RNG_API) += caamrng.o
+obj-$(CONFIG_CRYPTO_DEV_FSL_CAAM_PKC_API) += caam_pkc.o
 
 caam-objs := ctrl.o
 caam_jr-objs := jr.o key_gen.o error.o
+caam_pkc-y := caampkc.o pkc_desc.o
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 5845d4a..f1ecc8d 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -847,7 +847,7 @@
 							 *next_buflen, 0);
 		} else {
 			(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
-							SEC4_SG_LEN_FIN;
+				cpu_to_caam32(SEC4_SG_LEN_FIN);
 		}
 
 		state->current_buf = !state->current_buf;
@@ -949,7 +949,8 @@
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
 						last_buflen);
-	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |= SEC4_SG_LEN_FIN;
+	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
+		cpu_to_caam32(SEC4_SG_LEN_FIN);
 
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
new file mode 100644
index 0000000..851015e
--- /dev/null
+++ b/drivers/crypto/caam/caampkc.c
@@ -0,0 +1,607 @@
+/*
+ * caam - Freescale FSL CAAM support for Public Key Cryptography
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
+ * all the desired key parameters, input and output pointers.
+ */
+#include "compat.h"
+#include "regs.h"
+#include "intern.h"
+#include "jr.h"
+#include "error.h"
+#include "desc_constr.h"
+#include "sg_sw_sec4.h"
+#include "caampkc.h"
+
+#define DESC_RSA_PUB_LEN	(2 * CAAM_CMD_SZ + sizeof(struct rsa_pub_pdb))
+#define DESC_RSA_PRIV_F1_LEN	(2 * CAAM_CMD_SZ + \
+				 sizeof(struct rsa_priv_f1_pdb))
+
+static void rsa_io_unmap(struct device *dev, struct rsa_edesc *edesc,
+			 struct akcipher_request *req)
+{
+	dma_unmap_sg(dev, req->dst, edesc->dst_nents, DMA_FROM_DEVICE);
+	dma_unmap_sg(dev, req->src, edesc->src_nents, DMA_TO_DEVICE);
+
+	if (edesc->sec4_sg_bytes)
+		dma_unmap_single(dev, edesc->sec4_sg_dma, edesc->sec4_sg_bytes,
+				 DMA_TO_DEVICE);
+}
+
+static void rsa_pub_unmap(struct device *dev, struct rsa_edesc *edesc,
+			  struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct rsa_pub_pdb *pdb = &edesc->pdb.pub;
+
+	dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+	dma_unmap_single(dev, pdb->e_dma, key->e_sz, DMA_TO_DEVICE);
+}
+
+static void rsa_priv_f1_unmap(struct device *dev, struct rsa_edesc *edesc,
+			      struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct rsa_priv_f1_pdb *pdb = &edesc->pdb.priv_f1;
+
+	dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+	dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE);
+}
+
+/* RSA Job Completion handler */
+static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context)
+{
+	struct akcipher_request *req = context;
+	struct rsa_edesc *edesc;
+
+	if (err)
+		caam_jr_strstatus(dev, err);
+
+	edesc = container_of(desc, struct rsa_edesc, hw_desc[0]);
+
+	rsa_pub_unmap(dev, edesc, req);
+	rsa_io_unmap(dev, edesc, req);
+	kfree(edesc);
+
+	akcipher_request_complete(req, err);
+}
+
+static void rsa_priv_f1_done(struct device *dev, u32 *desc, u32 err,
+			     void *context)
+{
+	struct akcipher_request *req = context;
+	struct rsa_edesc *edesc;
+
+	if (err)
+		caam_jr_strstatus(dev, err);
+
+	edesc = container_of(desc, struct rsa_edesc, hw_desc[0]);
+
+	rsa_priv_f1_unmap(dev, edesc, req);
+	rsa_io_unmap(dev, edesc, req);
+	kfree(edesc);
+
+	akcipher_request_complete(req, err);
+}
+
+static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
+					 size_t desclen)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct device *dev = ctx->dev;
+	struct rsa_edesc *edesc;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	int sgc;
+	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
+	int src_nents, dst_nents;
+
+	src_nents = sg_nents_for_len(req->src, req->src_len);
+	dst_nents = sg_nents_for_len(req->dst, req->dst_len);
+
+	if (src_nents > 1)
+		sec4_sg_len = src_nents;
+	if (dst_nents > 1)
+		sec4_sg_len += dst_nents;
+
+	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc, hw desc commands and link tables */
+	edesc = kzalloc(sizeof(*edesc) + desclen + sec4_sg_bytes,
+			GFP_DMA | flags);
+	if (!edesc)
+		return ERR_PTR(-ENOMEM);
+
+	sgc = dma_map_sg(dev, req->src, src_nents, DMA_TO_DEVICE);
+	if (unlikely(!sgc)) {
+		dev_err(dev, "unable to map source\n");
+		goto src_fail;
+	}
+
+	sgc = dma_map_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
+	if (unlikely(!sgc)) {
+		dev_err(dev, "unable to map destination\n");
+		goto dst_fail;
+	}
+
+	edesc->sec4_sg = (void *)edesc + sizeof(*edesc) + desclen;
+
+	sec4_sg_index = 0;
+	if (src_nents > 1) {
+		sg_to_sec4_sg_last(req->src, src_nents, edesc->sec4_sg, 0);
+		sec4_sg_index += src_nents;
+	}
+	if (dst_nents > 1)
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+				   edesc->sec4_sg + sec4_sg_index, 0);
+
+	/* Save nents for later use in Job Descriptor */
+	edesc->src_nents = src_nents;
+	edesc->dst_nents = dst_nents;
+
+	if (!sec4_sg_bytes)
+		return edesc;
+
+	edesc->sec4_sg_dma = dma_map_single(dev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, edesc->sec4_sg_dma)) {
+		dev_err(dev, "unable to map S/G table\n");
+		goto sec4_sg_fail;
+	}
+
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+
+	return edesc;
+
+sec4_sg_fail:
+	dma_unmap_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
+dst_fail:
+	dma_unmap_sg(dev, req->src, src_nents, DMA_TO_DEVICE);
+src_fail:
+	kfree(edesc);
+	return ERR_PTR(-ENOMEM);
+}
+
+static int set_rsa_pub_pdb(struct akcipher_request *req,
+			   struct rsa_edesc *edesc)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *dev = ctx->dev;
+	struct rsa_pub_pdb *pdb = &edesc->pdb.pub;
+	int sec4_sg_index = 0;
+
+	pdb->n_dma = dma_map_single(dev, key->n, key->n_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->n_dma)) {
+		dev_err(dev, "Unable to map RSA modulus memory\n");
+		return -ENOMEM;
+	}
+
+	pdb->e_dma = dma_map_single(dev, key->e, key->e_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->e_dma)) {
+		dev_err(dev, "Unable to map RSA public exponent memory\n");
+		dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	if (edesc->src_nents > 1) {
+		pdb->sgf |= RSA_PDB_SGF_F;
+		pdb->f_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->src_nents;
+	} else {
+		pdb->f_dma = sg_dma_address(req->src);
+	}
+
+	if (edesc->dst_nents > 1) {
+		pdb->sgf |= RSA_PDB_SGF_G;
+		pdb->g_dma = edesc->sec4_sg_dma +
+			     sec4_sg_index * sizeof(struct sec4_sg_entry);
+	} else {
+		pdb->g_dma = sg_dma_address(req->dst);
+	}
+
+	pdb->sgf |= (key->e_sz << RSA_PDB_E_SHIFT) | key->n_sz;
+	pdb->f_len = req->src_len;
+
+	return 0;
+}
+
+static int set_rsa_priv_f1_pdb(struct akcipher_request *req,
+			       struct rsa_edesc *edesc)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *dev = ctx->dev;
+	struct rsa_priv_f1_pdb *pdb = &edesc->pdb.priv_f1;
+	int sec4_sg_index = 0;
+
+	pdb->n_dma = dma_map_single(dev, key->n, key->n_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->n_dma)) {
+		dev_err(dev, "Unable to map modulus memory\n");
+		return -ENOMEM;
+	}
+
+	pdb->d_dma = dma_map_single(dev, key->d, key->d_sz, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, pdb->d_dma)) {
+		dev_err(dev, "Unable to map RSA private exponent memory\n");
+		dma_unmap_single(dev, pdb->n_dma, key->n_sz, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	if (edesc->src_nents > 1) {
+		pdb->sgf |= RSA_PRIV_PDB_SGF_G;
+		pdb->g_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->src_nents;
+	} else {
+		pdb->g_dma = sg_dma_address(req->src);
+	}
+
+	if (edesc->dst_nents > 1) {
+		pdb->sgf |= RSA_PRIV_PDB_SGF_F;
+		pdb->f_dma = edesc->sec4_sg_dma +
+			     sec4_sg_index * sizeof(struct sec4_sg_entry);
+	} else {
+		pdb->f_dma = sg_dma_address(req->dst);
+	}
+
+	pdb->sgf |= (key->d_sz << RSA_PDB_D_SHIFT) | key->n_sz;
+
+	return 0;
+}
+
+static int caam_rsa_enc(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *jrdev = ctx->dev;
+	struct rsa_edesc *edesc;
+	int ret;
+
+	if (unlikely(!key->n || !key->e))
+		return -EINVAL;
+
+	if (req->dst_len < key->n_sz) {
+		req->dst_len = key->n_sz;
+		dev_err(jrdev, "Output buffer length less than parameter n\n");
+		return -EOVERFLOW;
+	}
+
+	/* Allocate extended descriptor */
+	edesc = rsa_edesc_alloc(req, DESC_RSA_PUB_LEN);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Set RSA Encrypt Protocol Data Block */
+	ret = set_rsa_pub_pdb(req, edesc);
+	if (ret)
+		goto init_fail;
+
+	/* Initialize Job Descriptor */
+	init_rsa_pub_desc(edesc->hw_desc, &edesc->pdb.pub);
+
+	ret = caam_jr_enqueue(jrdev, edesc->hw_desc, rsa_pub_done, req);
+	if (!ret)
+		return -EINPROGRESS;
+
+	rsa_pub_unmap(jrdev, edesc, req);
+
+init_fail:
+	rsa_io_unmap(jrdev, edesc, req);
+	kfree(edesc);
+	return ret;
+}
+
+static int caam_rsa_dec(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+	struct device *jrdev = ctx->dev;
+	struct rsa_edesc *edesc;
+	int ret;
+
+	if (unlikely(!key->n || !key->d))
+		return -EINVAL;
+
+	if (req->dst_len < key->n_sz) {
+		req->dst_len = key->n_sz;
+		dev_err(jrdev, "Output buffer length less than parameter n\n");
+		return -EOVERFLOW;
+	}
+
+	/* Allocate extended descriptor */
+	edesc = rsa_edesc_alloc(req, DESC_RSA_PRIV_F1_LEN);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Set RSA Decrypt Protocol Data Block - Private Key Form #1 */
+	ret = set_rsa_priv_f1_pdb(req, edesc);
+	if (ret)
+		goto init_fail;
+
+	/* Initialize Job Descriptor */
+	init_rsa_priv_f1_desc(edesc->hw_desc, &edesc->pdb.priv_f1);
+
+	ret = caam_jr_enqueue(jrdev, edesc->hw_desc, rsa_priv_f1_done, req);
+	if (!ret)
+		return -EINPROGRESS;
+
+	rsa_priv_f1_unmap(jrdev, edesc, req);
+
+init_fail:
+	rsa_io_unmap(jrdev, edesc, req);
+	kfree(edesc);
+	return ret;
+}
+
+static void caam_rsa_free_key(struct caam_rsa_key *key)
+{
+	kzfree(key->d);
+	kfree(key->e);
+	kfree(key->n);
+	key->d = NULL;
+	key->e = NULL;
+	key->n = NULL;
+	key->d_sz = 0;
+	key->e_sz = 0;
+	key->n_sz = 0;
+}
+
+/**
+ * caam_read_raw_data - Read a raw byte stream as a positive integer.
+ * The function skips buffer's leading zeros, copies the remained data
+ * to a buffer allocated in the GFP_DMA | GFP_KERNEL zone and returns
+ * the address of the new buffer.
+ *
+ * @buf   : The data to read
+ * @nbytes: The amount of data to read
+ */
+static inline u8 *caam_read_raw_data(const u8 *buf, size_t *nbytes)
+{
+	u8 *val;
+
+	while (!*buf && *nbytes) {
+		buf++;
+		(*nbytes)--;
+	}
+
+	val = kzalloc(*nbytes, GFP_DMA | GFP_KERNEL);
+	if (!val)
+		return NULL;
+
+	memcpy(val, buf, *nbytes);
+
+	return val;
+}
+
+static int caam_rsa_check_key_length(unsigned int len)
+{
+	if (len > 4096)
+		return -EINVAL;
+	return 0;
+}
+
+static int caam_rsa_set_pub_key(struct crypto_akcipher *tfm, const void *key,
+				unsigned int keylen)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
+	struct caam_rsa_key *rsa_key = &ctx->key;
+	int ret;
+
+	/* Free the old RSA key if any */
+	caam_rsa_free_key(rsa_key);
+
+	ret = rsa_parse_pub_key(&raw_key, key, keylen);
+	if (ret)
+		return ret;
+
+	/* Copy key in DMA zone */
+	rsa_key->e = kzalloc(raw_key.e_sz, GFP_DMA | GFP_KERNEL);
+	if (!rsa_key->e)
+		goto err;
+
+	/*
+	 * Skip leading zeros and copy the positive integer to a buffer
+	 * allocated in the GFP_DMA | GFP_KERNEL zone. The decryption descriptor
+	 * expects a positive integer for the RSA modulus and uses its length as
+	 * decryption output length.
+	 */
+	rsa_key->n = caam_read_raw_data(raw_key.n, &raw_key.n_sz);
+	if (!rsa_key->n)
+		goto err;
+
+	if (caam_rsa_check_key_length(raw_key.n_sz << 3)) {
+		caam_rsa_free_key(rsa_key);
+		return -EINVAL;
+	}
+
+	rsa_key->e_sz = raw_key.e_sz;
+	rsa_key->n_sz = raw_key.n_sz;
+
+	memcpy(rsa_key->e, raw_key.e, raw_key.e_sz);
+
+	return 0;
+err:
+	caam_rsa_free_key(rsa_key);
+	return -ENOMEM;
+}
+
+static int caam_rsa_set_priv_key(struct crypto_akcipher *tfm, const void *key,
+				 unsigned int keylen)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct rsa_key raw_key = {0};
+	struct caam_rsa_key *rsa_key = &ctx->key;
+	int ret;
+
+	/* Free the old RSA key if any */
+	caam_rsa_free_key(rsa_key);
+
+	ret = rsa_parse_priv_key(&raw_key, key, keylen);
+	if (ret)
+		return ret;
+
+	/* Copy key in DMA zone */
+	rsa_key->d = kzalloc(raw_key.d_sz, GFP_DMA | GFP_KERNEL);
+	if (!rsa_key->d)
+		goto err;
+
+	rsa_key->e = kzalloc(raw_key.e_sz, GFP_DMA | GFP_KERNEL);
+	if (!rsa_key->e)
+		goto err;
+
+	/*
+	 * Skip leading zeros and copy the positive integer to a buffer
+	 * allocated in the GFP_DMA | GFP_KERNEL zone. The decryption descriptor
+	 * expects a positive integer for the RSA modulus and uses its length as
+	 * decryption output length.
+	 */
+	rsa_key->n = caam_read_raw_data(raw_key.n, &raw_key.n_sz);
+	if (!rsa_key->n)
+		goto err;
+
+	if (caam_rsa_check_key_length(raw_key.n_sz << 3)) {
+		caam_rsa_free_key(rsa_key);
+		return -EINVAL;
+	}
+
+	rsa_key->d_sz = raw_key.d_sz;
+	rsa_key->e_sz = raw_key.e_sz;
+	rsa_key->n_sz = raw_key.n_sz;
+
+	memcpy(rsa_key->d, raw_key.d, raw_key.d_sz);
+	memcpy(rsa_key->e, raw_key.e, raw_key.e_sz);
+
+	return 0;
+
+err:
+	caam_rsa_free_key(rsa_key);
+	return -ENOMEM;
+}
+
+static int caam_rsa_max_size(struct crypto_akcipher *tfm)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+
+	return (key->n) ? key->n_sz : -EINVAL;
+}
+
+/* Per session pkc's driver context creation function */
+static int caam_rsa_init_tfm(struct crypto_akcipher *tfm)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	ctx->dev = caam_jr_alloc();
+
+	if (IS_ERR(ctx->dev)) {
+		dev_err(ctx->dev, "Job Ring Device allocation for transform failed\n");
+		return PTR_ERR(ctx->dev);
+	}
+
+	return 0;
+}
+
+/* Per session pkc's driver context cleanup function */
+static void caam_rsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct caam_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct caam_rsa_key *key = &ctx->key;
+
+	caam_rsa_free_key(key);
+	caam_jr_free(ctx->dev);
+}
+
+static struct akcipher_alg caam_rsa = {
+	.encrypt = caam_rsa_enc,
+	.decrypt = caam_rsa_dec,
+	.sign = caam_rsa_dec,
+	.verify = caam_rsa_enc,
+	.set_pub_key = caam_rsa_set_pub_key,
+	.set_priv_key = caam_rsa_set_priv_key,
+	.max_size = caam_rsa_max_size,
+	.init = caam_rsa_init_tfm,
+	.exit = caam_rsa_exit_tfm,
+	.base = {
+		.cra_name = "rsa",
+		.cra_driver_name = "rsa-caam",
+		.cra_priority = 3000,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct caam_rsa_ctx),
+	},
+};
+
+/* Public Key Cryptography module initialization handler */
+static int __init caam_pkc_init(void)
+{
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	struct caam_drv_private *priv;
+	u32 cha_inst, pk_inst;
+	int err;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node) {
+		dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec4.0");
+		if (!dev_node)
+			return -ENODEV;
+	}
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev) {
+		of_node_put(dev_node);
+		return -ENODEV;
+	}
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	/*
+	 * If priv is NULL, it's probably because the caam driver wasn't
+	 * properly initialized (e.g. RNG4 init failed). Thus, bail out here.
+	 */
+	if (!priv)
+		return -ENODEV;
+
+	/* Determine public key hardware accelerator presence. */
+	cha_inst = rd_reg32(&priv->ctrl->perfmon.cha_num_ls);
+	pk_inst = (cha_inst & CHA_ID_LS_PK_MASK) >> CHA_ID_LS_PK_SHIFT;
+
+	/* Do not register algorithms if PKHA is not present. */
+	if (!pk_inst)
+		return -ENODEV;
+
+	err = crypto_register_akcipher(&caam_rsa);
+	if (err)
+		dev_warn(ctrldev, "%s alg registration failed\n",
+			 caam_rsa.base.cra_driver_name);
+	else
+		dev_info(ctrldev, "caam pkc algorithms registered in /proc/crypto\n");
+
+	return err;
+}
+
+static void __exit caam_pkc_exit(void)
+{
+	crypto_unregister_akcipher(&caam_rsa);
+}
+
+module_init(caam_pkc_init);
+module_exit(caam_pkc_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("FSL CAAM support for PKC functions of crypto API");
+MODULE_AUTHOR("Freescale Semiconductor");
diff --git a/drivers/crypto/caam/caampkc.h b/drivers/crypto/caam/caampkc.h
new file mode 100644
index 0000000..f595d15
--- /dev/null
+++ b/drivers/crypto/caam/caampkc.h
@@ -0,0 +1,70 @@
+/*
+ * caam - Freescale FSL CAAM support for Public Key Cryptography descriptors
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
+ * all the desired key parameters, input and output pointers.
+ */
+
+#ifndef _PKC_DESC_H_
+#define _PKC_DESC_H_
+#include "compat.h"
+#include "pdb.h"
+
+/**
+ * caam_rsa_key - CAAM RSA key structure. Keys are allocated in DMA zone.
+ * @n           : RSA modulus raw byte stream
+ * @e           : RSA public exponent raw byte stream
+ * @d           : RSA private exponent raw byte stream
+ * @n_sz        : length in bytes of RSA modulus n
+ * @e_sz        : length in bytes of RSA public exponent
+ * @d_sz        : length in bytes of RSA private exponent
+ */
+struct caam_rsa_key {
+	u8 *n;
+	u8 *e;
+	u8 *d;
+	size_t n_sz;
+	size_t e_sz;
+	size_t d_sz;
+};
+
+/**
+ * caam_rsa_ctx - per session context.
+ * @key         : RSA key in DMA zone
+ * @dev         : device structure
+ */
+struct caam_rsa_ctx {
+	struct caam_rsa_key key;
+	struct device *dev;
+};
+
+/**
+ * rsa_edesc - s/w-extended rsa descriptor
+ * @src_nents     : number of segments in input scatterlist
+ * @dst_nents     : number of segments in output scatterlist
+ * @sec4_sg_bytes : length of h/w link table
+ * @sec4_sg_dma   : dma address of h/w link table
+ * @sec4_sg       : pointer to h/w link table
+ * @pdb           : specific RSA Protocol Data Block (PDB)
+ * @hw_desc       : descriptor followed by link tables if any
+ */
+struct rsa_edesc {
+	int src_nents;
+	int dst_nents;
+	int sec4_sg_bytes;
+	dma_addr_t sec4_sg_dma;
+	struct sec4_sg_entry *sec4_sg;
+	union {
+		struct rsa_pub_pdb pub;
+		struct rsa_priv_f1_pdb priv_f1;
+	} pdb;
+	u32 hw_desc[];
+};
+
+/* Descriptor construction primitives. */
+void init_rsa_pub_desc(u32 *desc, struct rsa_pub_pdb *pdb);
+void init_rsa_priv_f1_desc(u32 *desc, struct rsa_priv_f1_pdb *pdb);
+
+#endif
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index b6955ec..7149cd2 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -35,8 +35,11 @@
 #include <crypto/md5.h>
 #include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
+#include <crypto/akcipher.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/rsa.h>
+#include <crypto/internal/akcipher.h>
 
 #endif /* !defined(CAAM_COMPAT_H) */
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 5ad5f30..0ec112e 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -15,6 +15,9 @@
 #include "desc_constr.h"
 #include "error.h"
 
+bool caam_little_end;
+EXPORT_SYMBOL(caam_little_end);
+
 /*
  * i.MX targets tend to have clock control subsystems that can
  * enable/disable clocking to our device.
@@ -106,7 +109,7 @@
 
 
 	if (ctrlpriv->virt_en == 1) {
-		setbits32(&ctrl->deco_rsr, DECORSR_JR0);
+		clrsetbits_32(&ctrl->deco_rsr, 0, DECORSR_JR0);
 
 		while (!(rd_reg32(&ctrl->deco_rsr) & DECORSR_VALID) &&
 		       --timeout)
@@ -115,7 +118,7 @@
 		timeout = 100000;
 	}
 
-	setbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+	clrsetbits_32(&ctrl->deco_rq, 0, DECORR_RQD0ENABLE);
 
 	while (!(rd_reg32(&ctrl->deco_rq) & DECORR_DEN0) &&
 								 --timeout)
@@ -123,12 +126,12 @@
 
 	if (!timeout) {
 		dev_err(ctrldev, "failed to acquire DECO 0\n");
-		clrbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+		clrsetbits_32(&ctrl->deco_rq, DECORR_RQD0ENABLE, 0);
 		return -ENODEV;
 	}
 
 	for (i = 0; i < desc_len(desc); i++)
-		wr_reg32(&deco->descbuf[i], *(desc + i));
+		wr_reg32(&deco->descbuf[i], caam32_to_cpu(*(desc + i)));
 
 	flags = DECO_JQCR_WHL;
 	/*
@@ -139,7 +142,7 @@
 		flags |= DECO_JQCR_FOUR;
 
 	/* Instruct the DECO to execute it */
-	setbits32(&deco->jr_ctl_hi, flags);
+	clrsetbits_32(&deco->jr_ctl_hi, 0, flags);
 
 	timeout = 10000000;
 	do {
@@ -158,10 +161,10 @@
 		  DECO_OP_STATUS_HI_ERR_MASK;
 
 	if (ctrlpriv->virt_en == 1)
-		clrbits32(&ctrl->deco_rsr, DECORSR_JR0);
+		clrsetbits_32(&ctrl->deco_rsr, DECORSR_JR0, 0);
 
 	/* Mark the DECO as free */
-	clrbits32(&ctrl->deco_rq, DECORR_RQD0ENABLE);
+	clrsetbits_32(&ctrl->deco_rq, DECORR_RQD0ENABLE, 0);
 
 	if (!timeout)
 		return -EAGAIN;
@@ -349,7 +352,7 @@
 	r4tst = &ctrl->r4tst[0];
 
 	/* put RNG4 into program mode */
-	setbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+	clrsetbits_32(&r4tst->rtmctl, 0, RTMCTL_PRGM);
 
 	/*
 	 * Performance-wise, it does not make sense to
@@ -363,7 +366,7 @@
 	      >> RTSDCTL_ENT_DLY_SHIFT;
 	if (ent_delay <= val) {
 		/* put RNG4 into run mode */
-		clrbits32(&r4tst->rtmctl, RTMCTL_PRGM);
+		clrsetbits_32(&r4tst->rtmctl, RTMCTL_PRGM, 0);
 		return;
 	}
 
@@ -381,9 +384,9 @@
 	 * select raw sampling in both entropy shifter
 	 * and statistical checker
 	 */
-	setbits32(&val, RTMCTL_SAMP_MODE_RAW_ES_SC);
+	clrsetbits_32(&val, 0, RTMCTL_SAMP_MODE_RAW_ES_SC);
 	/* put RNG4 into run mode */
-	clrbits32(&val, RTMCTL_PRGM);
+	clrsetbits_32(&val, RTMCTL_PRGM, 0);
 	/* write back the control register */
 	wr_reg32(&r4tst->rtmctl, val);
 }
@@ -406,6 +409,23 @@
 }
 EXPORT_SYMBOL(caam_get_era);
 
+#ifdef CONFIG_DEBUG_FS
+static int caam_debugfs_u64_get(void *data, u64 *val)
+{
+	*val = caam64_to_cpu(*(u64 *)data);
+	return 0;
+}
+
+static int caam_debugfs_u32_get(void *data, u64 *val)
+{
+	*val = caam32_to_cpu(*(u32 *)data);
+	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");
+#endif
+
 /* Probe routine for CAAM top (controller) level */
 static int caam_probe(struct platform_device *pdev)
 {
@@ -504,6 +524,10 @@
 		ret = -ENOMEM;
 		goto disable_caam_emi_slow;
 	}
+
+	caam_little_end = !(bool)(rd_reg32(&ctrl->perfmon.status) &
+				  (CSTA_PLEND | CSTA_ALT_PLEND));
+
 	/* Finding the page size for using the CTPR_MS register */
 	comp_params = rd_reg32(&ctrl->perfmon.comp_parms_ms);
 	pg_size = (comp_params & CTPR_MS_PG_SZ_MASK) >> CTPR_MS_PG_SZ_SHIFT;
@@ -559,9 +583,9 @@
 	}
 
 	if (ctrlpriv->virt_en == 1)
-		setbits32(&ctrl->jrstart, JRSTART_JR0_START |
-			  JRSTART_JR1_START | JRSTART_JR2_START |
-			  JRSTART_JR3_START);
+		clrsetbits_32(&ctrl->jrstart, 0, JRSTART_JR0_START |
+			      JRSTART_JR1_START | JRSTART_JR2_START |
+			      JRSTART_JR3_START);
 
 	if (sizeof(dma_addr_t) == sizeof(u64))
 		if (of_device_is_compatible(nprop, "fsl,sec-v5.0"))
@@ -693,7 +717,7 @@
 		ctrlpriv->rng4_sh_init = ~ctrlpriv->rng4_sh_init & RDSTA_IFMASK;
 
 		/* Enable RDB bit so that RNG works faster */
-		setbits32(&ctrl->scfgr, SCFGR_RDBENABLE);
+		clrsetbits_32(&ctrl->scfgr, 0, SCFGR_RDBENABLE);
 	}
 
 	/* NOTE: RTIC detection ought to go here, around Si time */
@@ -719,48 +743,59 @@
 	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
 
 	/* Controller-level - performance monitor counters */
+
 	ctrlpriv->ctl_rq_dequeued =
-		debugfs_create_u64("rq_dequeued",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->req_dequeued);
+		debugfs_create_file("rq_dequeued",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->req_dequeued,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_enc_req =
-		debugfs_create_u64("ob_rq_encrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_enc_req);
+		debugfs_create_file("ob_rq_encrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_enc_req,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_dec_req =
-		debugfs_create_u64("ib_rq_decrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_dec_req);
+		debugfs_create_file("ib_rq_decrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_dec_req,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_enc_bytes =
-		debugfs_create_u64("ob_bytes_encrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_enc_bytes);
+		debugfs_create_file("ob_bytes_encrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_enc_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ob_prot_bytes =
-		debugfs_create_u64("ob_bytes_protected",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ob_prot_bytes);
+		debugfs_create_file("ob_bytes_protected",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ob_prot_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_dec_bytes =
-		debugfs_create_u64("ib_bytes_decrypted",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_dec_bytes);
+		debugfs_create_file("ib_bytes_decrypted",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_dec_bytes,
+				    &caam_fops_u64_ro);
 	ctrlpriv->ctl_ib_valid_bytes =
-		debugfs_create_u64("ib_bytes_validated",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->ib_valid_bytes);
+		debugfs_create_file("ib_bytes_validated",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->ib_valid_bytes,
+				    &caam_fops_u64_ro);
 
 	/* Controller level - global status values */
 	ctrlpriv->ctl_faultaddr =
-		debugfs_create_u64("fault_addr",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->faultaddr);
+		debugfs_create_file("fault_addr",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->faultaddr,
+				    &caam_fops_u32_ro);
 	ctrlpriv->ctl_faultdetail =
-		debugfs_create_u32("fault_detail",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->faultdetail);
+		debugfs_create_file("fault_detail",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->faultdetail,
+				    &caam_fops_u32_ro);
 	ctrlpriv->ctl_faultstatus =
-		debugfs_create_u32("fault_status",
-				   S_IRUSR | S_IRGRP | S_IROTH,
-				   ctrlpriv->ctl, &perfmon->status);
+		debugfs_create_file("fault_status",
+				    S_IRUSR | S_IRGRP | S_IROTH,
+				    ctrlpriv->ctl, &perfmon->status,
+				    &caam_fops_u32_ro);
 
 	/* Internal covering keys (useful in non-secure mode only) */
 	ctrlpriv->ctl_kek_wrap.data = &ctrlpriv->ctrl->kek[0];
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index 1e93c6a..26427c1 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -20,19 +20,18 @@
 #define SEC4_SG_BPID_MASK	0x000000ff
 #define SEC4_SG_BPID_SHIFT	16
 #define SEC4_SG_LEN_MASK	0x3fffffff	/* Excludes EXT and FINAL */
-#define SEC4_SG_OFFS_MASK	0x00001fff
+#define SEC4_SG_OFFSET_MASK	0x00001fff
 
 struct sec4_sg_entry {
-#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+#if !defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) && \
+	defined(CONFIG_CRYPTO_DEV_FSL_CAAM_IMX)
 	u32 rsvd1;
 	dma_addr_t ptr;
 #else
 	u64 ptr;
 #endif /* CONFIG_CRYPTO_DEV_FSL_CAAM_IMX */
 	u32 len;
-	u8 rsvd2;
-	u8 buf_pool_id;
-	u16 offset;
+	u32 bpid_offset;
 };
 
 /* Max size of any CAAM descriptor in 32-bit words, inclusive of header */
@@ -454,6 +453,8 @@
 #define OP_PCLID_PUBLICKEYPAIR	(0x14 << OP_PCLID_SHIFT)
 #define OP_PCLID_DSASIGN	(0x15 << OP_PCLID_SHIFT)
 #define OP_PCLID_DSAVERIFY	(0x16 << OP_PCLID_SHIFT)
+#define OP_PCLID_RSAENC_PUBKEY  (0x18 << OP_PCLID_SHIFT)
+#define OP_PCLID_RSADEC_PRVKEY  (0x19 << OP_PCLID_SHIFT)
 
 /* Assuming OP_TYPE = OP_TYPE_DECAP_PROTOCOL/ENCAP_PROTOCOL */
 #define OP_PCLID_IPSEC		(0x01 << OP_PCLID_SHIFT)
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index 98d07de..d3869b9 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -5,6 +5,7 @@
  */
 
 #include "desc.h"
+#include "regs.h"
 
 #define IMMEDIATE (1 << 23)
 #define CAAM_CMD_SZ sizeof(u32)
@@ -30,9 +31,11 @@
 			       LDST_SRCDST_WORD_DECOCTRL | \
 			       (LDOFF_ENABLE_AUTO_NFIFO << LDST_OFFSET_SHIFT))
 
+extern bool caam_little_end;
+
 static inline int desc_len(u32 *desc)
 {
-	return *desc & HDR_DESCLEN_MASK;
+	return caam32_to_cpu(*desc) & HDR_DESCLEN_MASK;
 }
 
 static inline int desc_bytes(void *desc)
@@ -52,7 +55,7 @@
 
 static inline void init_desc(u32 *desc, u32 options)
 {
-	*desc = (options | HDR_ONE) + 1;
+	*desc = cpu_to_caam32((options | HDR_ONE) + 1);
 }
 
 static inline void init_sh_desc(u32 *desc, u32 options)
@@ -74,13 +77,21 @@
 	init_desc(desc, CMD_DESC_HDR | options);
 }
 
+static inline void init_job_desc_pdb(u32 *desc, u32 options, size_t pdb_bytes)
+{
+	u32 pdb_len = (pdb_bytes + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ;
+
+	init_job_desc(desc, (((pdb_len + 1) << HDR_START_IDX_SHIFT)) | options);
+}
+
 static inline void append_ptr(u32 *desc, dma_addr_t ptr)
 {
 	dma_addr_t *offset = (dma_addr_t *)desc_end(desc);
 
-	*offset = ptr;
+	*offset = cpu_to_caam_dma(ptr);
 
-	(*desc) += CAAM_PTR_SZ / CAAM_CMD_SZ;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) +
+				CAAM_PTR_SZ / CAAM_CMD_SZ);
 }
 
 static inline void init_job_desc_shared(u32 *desc, dma_addr_t ptr, int len,
@@ -99,16 +110,17 @@
 	if (len) /* avoid sparse warning: memcpy with byte count of 0 */
 		memcpy(offset, data, len);
 
-	(*desc) += (len + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) +
+				(len + CAAM_CMD_SZ - 1) / CAAM_CMD_SZ);
 }
 
 static inline void append_cmd(u32 *desc, u32 command)
 {
 	u32 *cmd = desc_end(desc);
 
-	*cmd = command;
+	*cmd = cpu_to_caam32(command);
 
-	(*desc)++;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) + 1);
 }
 
 #define append_u32 append_cmd
@@ -117,16 +129,22 @@
 {
 	u32 *offset = desc_end(desc);
 
-	*offset = upper_32_bits(data);
-	*(++offset) = lower_32_bits(data);
+	/* Only 32-bit alignment is guaranteed in descriptor buffer */
+	if (caam_little_end) {
+		*offset = cpu_to_caam32(lower_32_bits(data));
+		*(++offset) = cpu_to_caam32(upper_32_bits(data));
+	} else {
+		*offset = cpu_to_caam32(upper_32_bits(data));
+		*(++offset) = cpu_to_caam32(lower_32_bits(data));
+	}
 
-	(*desc) += 2;
+	(*desc) = cpu_to_caam32(caam32_to_cpu(*desc) + 2);
 }
 
 /* Write command without affecting header, and return pointer to next word */
 static inline u32 *write_cmd(u32 *desc, u32 command)
 {
-	*desc = command;
+	*desc = cpu_to_caam32(command);
 
 	return desc + 1;
 }
@@ -168,14 +186,17 @@
 
 static inline void set_jump_tgt_here(u32 *desc, u32 *jump_cmd)
 {
-	*jump_cmd = *jump_cmd | (desc_len(desc) - (jump_cmd - desc));
+	*jump_cmd = cpu_to_caam32(caam32_to_cpu(*jump_cmd) |
+				  (desc_len(desc) - (jump_cmd - desc)));
 }
 
 static inline void set_move_tgt_here(u32 *desc, u32 *move_cmd)
 {
-	*move_cmd &= ~MOVE_OFFSET_MASK;
-	*move_cmd = *move_cmd | ((desc_len(desc) << (MOVE_OFFSET_SHIFT + 2)) &
-				 MOVE_OFFSET_MASK);
+	u32 val = caam32_to_cpu(*move_cmd);
+
+	val &= ~MOVE_OFFSET_MASK;
+	val |= (desc_len(desc) << (MOVE_OFFSET_SHIFT + 2)) & MOVE_OFFSET_MASK;
+	*move_cmd = cpu_to_caam32(val);
 }
 
 #define APPEND_CMD(cmd, op) \
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 5ef4be2..a81f551 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -31,7 +31,7 @@
 	 * mask interrupts since we are going to poll
 	 * for reset completion status
 	 */
-	setbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JRCFG_IMSK);
 
 	/* initiate flush (required prior to reset) */
 	wr_reg32(&jrp->rregs->jrcommand, JRCR_RESET);
@@ -57,7 +57,7 @@
 	}
 
 	/* unmask interrupts */
-	clrbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, JRCFG_IMSK, 0);
 
 	return 0;
 }
@@ -147,7 +147,7 @@
 	}
 
 	/* mask valid interrupts */
-	setbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JRCFG_IMSK);
 
 	/* Have valid interrupt at this point, just ACK and trigger */
 	wr_reg32(&jrp->rregs->jrintstatus, irqstate);
@@ -182,7 +182,7 @@
 			sw_idx = (tail + i) & (JOBR_DEPTH - 1);
 
 			if (jrp->outring[hw_idx].desc ==
-			    jrp->entinfo[sw_idx].desc_addr_dma)
+			    caam_dma_to_cpu(jrp->entinfo[sw_idx].desc_addr_dma))
 				break; /* found */
 		}
 		/* we should never fail to find a matching descriptor */
@@ -200,7 +200,7 @@
 		usercall = jrp->entinfo[sw_idx].callbk;
 		userarg = jrp->entinfo[sw_idx].cbkarg;
 		userdesc = jrp->entinfo[sw_idx].desc_addr_virt;
-		userstatus = jrp->outring[hw_idx].jrstatus;
+		userstatus = caam32_to_cpu(jrp->outring[hw_idx].jrstatus);
 
 		/*
 		 * Make sure all information from the job has been obtained
@@ -236,7 +236,7 @@
 	}
 
 	/* reenable / unmask IRQs */
-	clrbits32(&jrp->rregs->rconfig_lo, JRCFG_IMSK);
+	clrsetbits_32(&jrp->rregs->rconfig_lo, JRCFG_IMSK, 0);
 }
 
 /**
@@ -330,7 +330,7 @@
 	int head, tail, desc_size;
 	dma_addr_t desc_dma;
 
-	desc_size = (*desc & HDR_JD_LENGTH_MASK) * sizeof(u32);
+	desc_size = (caam32_to_cpu(*desc) & HDR_JD_LENGTH_MASK) * sizeof(u32);
 	desc_dma = dma_map_single(dev, desc, desc_size, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, desc_dma)) {
 		dev_err(dev, "caam_jr_enqueue(): can't map jobdesc\n");
@@ -356,7 +356,7 @@
 	head_entry->cbkarg = areq;
 	head_entry->desc_addr_dma = desc_dma;
 
-	jrp->inpring[jrp->inp_ring_write_index] = desc_dma;
+	jrp->inpring[jrp->inp_ring_write_index] = cpu_to_caam_dma(desc_dma);
 
 	/*
 	 * Guarantee that the descriptor's DMA address has been written to
@@ -444,9 +444,9 @@
 	spin_lock_init(&jrp->outlock);
 
 	/* Select interrupt coalescing parameters */
-	setbits32(&jrp->rregs->rconfig_lo, JOBR_INTC |
-		  (JOBR_INTC_COUNT_THLD << JRCFG_ICDCT_SHIFT) |
-		  (JOBR_INTC_TIME_THLD << JRCFG_ICTT_SHIFT));
+	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JOBR_INTC |
+		      (JOBR_INTC_COUNT_THLD << JRCFG_ICDCT_SHIFT) |
+		      (JOBR_INTC_TIME_THLD << JRCFG_ICTT_SHIFT));
 
 	return 0;
 
diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h
index 3a87c0c..aaa00dd 100644
--- a/drivers/crypto/caam/pdb.h
+++ b/drivers/crypto/caam/pdb.h
@@ -1,18 +1,19 @@
 /*
  * CAAM Protocol Data Block (PDB) definition header file
  *
- * Copyright 2008-2012 Freescale Semiconductor, Inc.
+ * Copyright 2008-2016 Freescale Semiconductor, Inc.
  *
  */
 
 #ifndef CAAM_PDB_H
 #define CAAM_PDB_H
+#include "compat.h"
 
 /*
  * PDB- IPSec ESP Header Modification Options
  */
-#define PDBHMO_ESP_DECAP_SHIFT	12
-#define PDBHMO_ESP_ENCAP_SHIFT	4
+#define PDBHMO_ESP_DECAP_SHIFT	28
+#define PDBHMO_ESP_ENCAP_SHIFT	28
 /*
  * Encap and Decap - Decrement TTL (Hop Limit) - Based on the value of the
  * Options Byte IP version (IPvsn) field:
@@ -32,12 +33,23 @@
  */
 #define PDBHMO_ESP_DFBIT		(0x04 << PDBHMO_ESP_ENCAP_SHIFT)
 
+#define PDBNH_ESP_ENCAP_SHIFT		16
+#define PDBNH_ESP_ENCAP_MASK		(0xff << PDBNH_ESP_ENCAP_SHIFT)
+
+#define PDBHDRLEN_ESP_DECAP_SHIFT	16
+#define PDBHDRLEN_MASK			(0x0fff << PDBHDRLEN_ESP_DECAP_SHIFT)
+
+#define PDB_NH_OFFSET_SHIFT		8
+#define PDB_NH_OFFSET_MASK		(0xff << PDB_NH_OFFSET_SHIFT)
+
 /*
  * PDB - IPSec ESP Encap/Decap Options
  */
 #define PDBOPTS_ESP_ARSNONE	0x00 /* no antireplay window */
 #define PDBOPTS_ESP_ARS32	0x40 /* 32-entry antireplay window */
+#define PDBOPTS_ESP_ARS128	0x80 /* 128-entry antireplay window */
 #define PDBOPTS_ESP_ARS64	0xc0 /* 64-entry antireplay window */
+#define PDBOPTS_ESP_ARS_MASK	0xc0 /* antireplay window mask */
 #define PDBOPTS_ESP_IVSRC	0x20 /* IV comes from internal random gen */
 #define PDBOPTS_ESP_ESN		0x10 /* extended sequence included */
 #define PDBOPTS_ESP_OUTFMT	0x08 /* output only decapsulation (decap) */
@@ -54,35 +66,73 @@
 /*
  * General IPSec encap/decap PDB definitions
  */
+
+/**
+ * ipsec_encap_cbc - PDB part for IPsec CBC encapsulation
+ * @iv: 16-byte array initialization vector
+ */
 struct ipsec_encap_cbc {
-	u32 iv[4];
+	u8 iv[16];
 };
 
+/**
+ * ipsec_encap_ctr - PDB part for IPsec CTR encapsulation
+ * @ctr_nonce: 4-byte array nonce
+ * @ctr_initial: initial count constant
+ * @iv: initialization vector
+ */
 struct ipsec_encap_ctr {
-	u32 ctr_nonce;
+	u8 ctr_nonce[4];
 	u32 ctr_initial;
-	u32 iv[2];
+	u64 iv;
 };
 
+/**
+ * ipsec_encap_ccm - PDB part for IPsec CCM encapsulation
+ * @salt: 3-byte array salt (lower 24 bits)
+ * @ccm_opt: CCM algorithm options - MSB-LSB description:
+ *  b0_flags (8b) - CCM B0; use 0x5B for 8-byte ICV, 0x6B for 12-byte ICV,
+ *    0x7B for 16-byte ICV (cf. RFC4309, RFC3610)
+ *  ctr_flags (8b) - counter flags; constant equal to 0x3
+ *  ctr_initial (16b) - initial count constant
+ * @iv: initialization vector
+ */
 struct ipsec_encap_ccm {
-	u32 salt; /* lower 24 bits */
-	u8 b0_flags;
-	u8 ctr_flags;
-	u16 ctr_initial;
-	u32 iv[2];
+	u8 salt[4];
+	u32 ccm_opt;
+	u64 iv;
 };
 
+/**
+ * ipsec_encap_gcm - PDB part for IPsec GCM encapsulation
+ * @salt: 3-byte array salt (lower 24 bits)
+ * @rsvd: reserved, do not use
+ * @iv: initialization vector
+ */
 struct ipsec_encap_gcm {
-	u32 salt; /* lower 24 bits */
+	u8 salt[4];
 	u32 rsvd1;
-	u32 iv[2];
+	u64 iv;
 };
 
+/**
+ * ipsec_encap_pdb - PDB for IPsec encapsulation
+ * @options: MSB-LSB description
+ *  hmo (header manipulation options) - 4b
+ *  reserved - 4b
+ *  next header - 8b
+ *  next header offset - 8b
+ *  option flags (depend on selected algorithm) - 8b
+ * @seq_num_ext_hi: (optional) IPsec Extended Sequence Number (ESN)
+ * @seq_num: IPsec sequence number
+ * @spi: IPsec SPI (Security Parameters Index)
+ * @ip_hdr_len: optional IP Header length (in bytes)
+ *  reserved - 16b
+ *  Opt. IP Hdr Len - 16b
+ * @ip_hdr: optional IP Header content
+ */
 struct ipsec_encap_pdb {
-	u8 hmo_rsvd;
-	u8 ip_nh;
-	u8 ip_nh_offset;
-	u8 options;
+	u32 options;
 	u32 seq_num_ext_hi;
 	u32 seq_num;
 	union {
@@ -92,36 +142,65 @@
 		struct ipsec_encap_gcm gcm;
 	};
 	u32 spi;
-	u16 rsvd1;
-	u16 ip_hdr_len;
-	u32 ip_hdr[0]; /* optional IP Header content */
+	u32 ip_hdr_len;
+	u32 ip_hdr[0];
 };
 
+/**
+ * ipsec_decap_cbc - PDB part for IPsec CBC decapsulation
+ * @rsvd: reserved, do not use
+ */
 struct ipsec_decap_cbc {
 	u32 rsvd[2];
 };
 
+/**
+ * ipsec_decap_ctr - PDB part for IPsec CTR decapsulation
+ * @ctr_nonce: 4-byte array nonce
+ * @ctr_initial: initial count constant
+ */
 struct ipsec_decap_ctr {
-	u32 salt;
+	u8 ctr_nonce[4];
 	u32 ctr_initial;
 };
 
+/**
+ * ipsec_decap_ccm - PDB part for IPsec CCM decapsulation
+ * @salt: 3-byte salt (lower 24 bits)
+ * @ccm_opt: CCM algorithm options - MSB-LSB description:
+ *  b0_flags (8b) - CCM B0; use 0x5B for 8-byte ICV, 0x6B for 12-byte ICV,
+ *    0x7B for 16-byte ICV (cf. RFC4309, RFC3610)
+ *  ctr_flags (8b) - counter flags; constant equal to 0x3
+ *  ctr_initial (16b) - initial count constant
+ */
 struct ipsec_decap_ccm {
-	u32 salt;
-	u8 iv_flags;
-	u8 ctr_flags;
-	u16 ctr_initial;
+	u8 salt[4];
+	u32 ccm_opt;
 };
 
+/**
+ * ipsec_decap_gcm - PDB part for IPsec GCN decapsulation
+ * @salt: 4-byte salt
+ * @rsvd: reserved, do not use
+ */
 struct ipsec_decap_gcm {
-	u32 salt;
+	u8 salt[4];
 	u32 resvd;
 };
 
+/**
+ * ipsec_decap_pdb - PDB for IPsec decapsulation
+ * @options: MSB-LSB description
+ *  hmo (header manipulation options) - 4b
+ *  IP header length - 12b
+ *  next header offset - 8b
+ *  option flags (depend on selected algorithm) - 8b
+ * @seq_num_ext_hi: (optional) IPsec Extended Sequence Number (ESN)
+ * @seq_num: IPsec sequence number
+ * @anti_replay: Anti-replay window; size depends on ARS (option flags)
+ */
 struct ipsec_decap_pdb {
-	u16 hmo_ip_hdr_len;
-	u8 ip_nh_offset;
-	u8 options;
+	u32 options;
 	union {
 		struct ipsec_decap_cbc cbc;
 		struct ipsec_decap_ctr ctr;
@@ -130,8 +209,7 @@
 	};
 	u32 seq_num_ext_hi;
 	u32 seq_num;
-	u32 anti_replay[2];
-	u32 end_index[0];
+	__be32 anti_replay[4];
 };
 
 /*
@@ -399,4 +477,52 @@
 	u8 *ab; /* only used if ECC processing */
 };
 
+/* RSA Protocol Data Block */
+#define RSA_PDB_SGF_SHIFT       28
+#define RSA_PDB_E_SHIFT         12
+#define RSA_PDB_E_MASK          (0xFFF << RSA_PDB_E_SHIFT)
+#define RSA_PDB_D_SHIFT         12
+#define RSA_PDB_D_MASK          (0xFFF << RSA_PDB_D_SHIFT)
+
+#define RSA_PDB_SGF_F           (0x8 << RSA_PDB_SGF_SHIFT)
+#define RSA_PDB_SGF_G           (0x4 << RSA_PDB_SGF_SHIFT)
+#define RSA_PRIV_PDB_SGF_F      (0x4 << RSA_PDB_SGF_SHIFT)
+#define RSA_PRIV_PDB_SGF_G      (0x8 << RSA_PDB_SGF_SHIFT)
+
+#define RSA_PRIV_KEY_FRM_1      0
+
+/**
+ * RSA Encrypt Protocol Data Block
+ * @sgf: scatter-gather field
+ * @f_dma: dma address of input data
+ * @g_dma: dma address of encrypted output data
+ * @n_dma: dma address of RSA modulus
+ * @e_dma: dma address of RSA public exponent
+ * @f_len: length in octets of the input data
+ */
+struct rsa_pub_pdb {
+	u32		sgf;
+	dma_addr_t	f_dma;
+	dma_addr_t	g_dma;
+	dma_addr_t	n_dma;
+	dma_addr_t	e_dma;
+	u32		f_len;
+} __packed;
+
+/**
+ * RSA Decrypt PDB - Private Key Form #1
+ * @sgf: scatter-gather field
+ * @g_dma: dma address of encrypted input data
+ * @f_dma: dma address of output data
+ * @n_dma: dma address of RSA modulus
+ * @d_dma: dma address of RSA private exponent
+ */
+struct rsa_priv_f1_pdb {
+	u32		sgf;
+	dma_addr_t	g_dma;
+	dma_addr_t	f_dma;
+	dma_addr_t	n_dma;
+	dma_addr_t	d_dma;
+} __packed;
+
 #endif
diff --git a/drivers/crypto/caam/pkc_desc.c b/drivers/crypto/caam/pkc_desc.c
new file mode 100644
index 0000000..4e4183e
--- /dev/null
+++ b/drivers/crypto/caam/pkc_desc.c
@@ -0,0 +1,36 @@
+/*
+ * caam - Freescale FSL CAAM support for Public Key Cryptography descriptors
+ *
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * There is no Shared Descriptor for PKC so that the Job Descriptor must carry
+ * all the desired key parameters, input and output pointers.
+ */
+#include "caampkc.h"
+#include "desc_constr.h"
+
+/* Descriptor for RSA Public operation */
+void init_rsa_pub_desc(u32 *desc, struct rsa_pub_pdb *pdb)
+{
+	init_job_desc_pdb(desc, 0, sizeof(*pdb));
+	append_cmd(desc, pdb->sgf);
+	append_ptr(desc, pdb->f_dma);
+	append_ptr(desc, pdb->g_dma);
+	append_ptr(desc, pdb->n_dma);
+	append_ptr(desc, pdb->e_dma);
+	append_cmd(desc, pdb->f_len);
+	append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSAENC_PUBKEY);
+}
+
+/* Descriptor for RSA Private operation - Private Key Form #1 */
+void init_rsa_priv_f1_desc(u32 *desc, struct rsa_priv_f1_pdb *pdb)
+{
+	init_job_desc_pdb(desc, 0, sizeof(*pdb));
+	append_cmd(desc, pdb->sgf);
+	append_ptr(desc, pdb->g_dma);
+	append_ptr(desc, pdb->f_dma);
+	append_ptr(desc, pdb->n_dma);
+	append_ptr(desc, pdb->d_dma);
+	append_operation(desc, OP_TYPE_UNI_PROTOCOL | OP_PCLID_RSADEC_PRVKEY |
+			 RSA_PRIV_KEY_FRM_1);
+}
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 0ba9c40..b3c5016 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -8,6 +8,7 @@
 #define REGS_H
 
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include <linux/io.h>
 
 /*
@@ -65,46 +66,56 @@
  *
  */
 
-#ifdef CONFIG_ARM
-/* These are common macros for Power, put here for ARM */
-#define setbits32(_addr, _v) writel((readl(_addr) | (_v)), (_addr))
-#define clrbits32(_addr, _v) writel((readl(_addr) & ~(_v)), (_addr))
+extern bool caam_little_end;
 
-#define out_arch(type, endian, a, v)	__raw_write##type(cpu_to_##endian(v), a)
-#define in_arch(type, endian, a)	endian##_to_cpu(__raw_read##type(a))
+#define caam_to_cpu(len)				\
+static inline u##len caam##len ## _to_cpu(u##len val)	\
+{							\
+	if (caam_little_end)				\
+		return le##len ## _to_cpu(val);		\
+	else						\
+		return be##len ## _to_cpu(val);		\
+}
 
-#define out_le32(a, v)	out_arch(l, le32, a, v)
-#define in_le32(a)	in_arch(l, le32, a)
+#define cpu_to_caam(len)				\
+static inline u##len cpu_to_caam##len(u##len val)	\
+{							\
+	if (caam_little_end)				\
+		return cpu_to_le##len(val);		\
+	else						\
+		return cpu_to_be##len(val);		\
+}
 
-#define out_be32(a, v)	out_arch(l, be32, a, v)
-#define in_be32(a)	in_arch(l, be32, a)
+caam_to_cpu(16)
+caam_to_cpu(32)
+caam_to_cpu(64)
+cpu_to_caam(16)
+cpu_to_caam(32)
+cpu_to_caam(64)
 
-#define clrsetbits(type, addr, clear, set) \
-	out_##type((addr), (in_##type(addr) & ~(clear)) | (set))
+static inline void wr_reg32(void __iomem *reg, u32 data)
+{
+	if (caam_little_end)
+		iowrite32(data, reg);
+	else
+		iowrite32be(data, reg);
+}
 
-#define clrsetbits_be32(addr, clear, set) clrsetbits(be32, addr, clear, set)
-#define clrsetbits_le32(addr, clear, set) clrsetbits(le32, addr, clear, set)
-#endif
+static inline u32 rd_reg32(void __iomem *reg)
+{
+	if (caam_little_end)
+		return ioread32(reg);
 
-#ifdef __BIG_ENDIAN
-#define wr_reg32(reg, data) out_be32(reg, data)
-#define rd_reg32(reg) in_be32(reg)
-#define clrsetbits_32(addr, clear, set) clrsetbits_be32(addr, clear, set)
-#ifdef CONFIG_64BIT
-#define wr_reg64(reg, data) out_be64(reg, data)
-#define rd_reg64(reg) in_be64(reg)
-#endif
-#else
-#ifdef __LITTLE_ENDIAN
-#define wr_reg32(reg, data) __raw_writel(data, reg)
-#define rd_reg32(reg) __raw_readl(reg)
-#define clrsetbits_32(addr, clear, set) clrsetbits_le32(addr, clear, set)
-#ifdef CONFIG_64BIT
-#define wr_reg64(reg, data) __raw_writeq(data, reg)
-#define rd_reg64(reg) __raw_readq(reg)
-#endif
-#endif
-#endif
+	return ioread32be(reg);
+}
+
+static inline void clrsetbits_32(void __iomem *reg, u32 clear, u32 set)
+{
+	if (caam_little_end)
+		iowrite32((ioread32(reg) & ~clear) | set, reg);
+	else
+		iowrite32be((ioread32be(reg) & ~clear) | set, reg);
+}
 
 /*
  * The only users of these wr/rd_reg64 functions is the Job Ring (JR).
@@ -123,29 +134,67 @@
  *    base + 0x0000 : least-significant 32 bits
  *    base + 0x0004 : most-significant 32 bits
  */
+#ifdef CONFIG_64BIT
+static inline void wr_reg64(void __iomem *reg, u64 data)
+{
+	if (caam_little_end)
+		iowrite64(data, reg);
+	else
+		iowrite64be(data, reg);
+}
 
-#ifndef CONFIG_64BIT
-#if !defined(CONFIG_CRYPTO_DEV_FSL_CAAM_LE) || \
-	defined(CONFIG_CRYPTO_DEV_FSL_CAAM_IMX)
-#define REG64_MS32(reg) ((u32 __iomem *)(reg))
-#define REG64_LS32(reg) ((u32 __iomem *)(reg) + 1)
+static inline u64 rd_reg64(void __iomem *reg)
+{
+	if (caam_little_end)
+		return ioread64(reg);
+	else
+		return ioread64be(reg);
+}
+
+#else /* CONFIG_64BIT */
+static inline void wr_reg64(void __iomem *reg, u64 data)
+{
+#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+	if (caam_little_end) {
+		wr_reg32((u32 __iomem *)(reg) + 1, data >> 32);
+		wr_reg32((u32 __iomem *)(reg), data);
+	} else
+#endif
+	{
+		wr_reg32((u32 __iomem *)(reg), data >> 32);
+		wr_reg32((u32 __iomem *)(reg) + 1, data);
+	}
+}
+
+static inline u64 rd_reg64(void __iomem *reg)
+{
+#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
+	if (caam_little_end)
+		return ((u64)rd_reg32((u32 __iomem *)(reg) + 1) << 32 |
+			(u64)rd_reg32((u32 __iomem *)(reg)));
+	else
+#endif
+		return ((u64)rd_reg32((u32 __iomem *)(reg)) << 32 |
+			(u64)rd_reg32((u32 __iomem *)(reg) + 1));
+}
+#endif /* CONFIG_64BIT  */
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+#ifdef CONFIG_SOC_IMX7D
+#define cpu_to_caam_dma(value) \
+		(((u64)cpu_to_caam32(lower_32_bits(value)) << 32) | \
+		  (u64)cpu_to_caam32(upper_32_bits(value)))
+#define caam_dma_to_cpu(value) \
+		(((u64)caam32_to_cpu(lower_32_bits(value)) << 32) | \
+		  (u64)caam32_to_cpu(upper_32_bits(value)))
 #else
-#define REG64_MS32(reg) ((u32 __iomem *)(reg) + 1)
-#define REG64_LS32(reg) ((u32 __iomem *)(reg))
-#endif
-
-static inline void wr_reg64(u64 __iomem *reg, u64 data)
-{
-	wr_reg32(REG64_MS32(reg), data >> 32);
-	wr_reg32(REG64_LS32(reg), data);
-}
-
-static inline u64 rd_reg64(u64 __iomem *reg)
-{
-	return ((u64)rd_reg32(REG64_MS32(reg)) << 32 |
-		(u64)rd_reg32(REG64_LS32(reg)));
-}
-#endif
+#define cpu_to_caam_dma(value) cpu_to_caam64(value)
+#define caam_dma_to_cpu(value) caam64_to_cpu(value)
+#endif /* CONFIG_SOC_IMX7D */
+#else
+#define cpu_to_caam_dma(value) cpu_to_caam32(value)
+#define caam_dma_to_cpu(value) caam32_to_cpu(value)
+#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT  */
 
 /*
  * jr_outentry
@@ -249,6 +298,8 @@
 	u32 faultliodn;	/* FALR - Fault Address LIODN	*/
 	u32 faultdetail;	/* FADR - Fault Addr Detail	*/
 	u32 rsvd2;
+#define CSTA_PLEND		BIT(10)
+#define CSTA_ALT_PLEND		BIT(18)
 	u32 status;		/* CSTA - CAAM Status */
 	u64 rsvd3;
 
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index 12ec661..19dc64f 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -5,18 +5,19 @@
  *
  */
 
+#include "regs.h"
+
 struct sec4_sg_entry;
 
 /*
  * convert single dma address to h/w link table format
  */
 static inline void dma_to_sec4_sg_one(struct sec4_sg_entry *sec4_sg_ptr,
-				      dma_addr_t dma, u32 len, u32 offset)
+				      dma_addr_t dma, u32 len, u16 offset)
 {
-	sec4_sg_ptr->ptr = dma;
-	sec4_sg_ptr->len = len;
-	sec4_sg_ptr->buf_pool_id = 0;
-	sec4_sg_ptr->offset = offset;
+	sec4_sg_ptr->ptr = cpu_to_caam_dma(dma);
+	sec4_sg_ptr->len = cpu_to_caam32(len);
+	sec4_sg_ptr->bpid_offset = cpu_to_caam32(offset & SEC4_SG_OFFSET_MASK);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "sec4_sg_ptr@: ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, sec4_sg_ptr,
@@ -30,7 +31,7 @@
  */
 static inline struct sec4_sg_entry *
 sg_to_sec4_sg(struct scatterlist *sg, int sg_count,
-	      struct sec4_sg_entry *sec4_sg_ptr, u32 offset)
+	      struct sec4_sg_entry *sec4_sg_ptr, u16 offset)
 {
 	while (sg_count) {
 		dma_to_sec4_sg_one(sec4_sg_ptr, sg_dma_address(sg),
@@ -48,10 +49,10 @@
  */
 static inline void sg_to_sec4_sg_last(struct scatterlist *sg, int sg_count,
 				      struct sec4_sg_entry *sec4_sg_ptr,
-				      u32 offset)
+				      u16 offset)
 {
 	sec4_sg_ptr = sg_to_sec4_sg(sg, sg_count, sec4_sg_ptr, offset);
-	sec4_sg_ptr->len |= SEC4_SG_LEN_FIN;
+	sec4_sg_ptr->len |= cpu_to_caam32(SEC4_SG_LEN_FIN);
 }
 
 static inline struct sec4_sg_entry *sg_to_sec4_sg_len(
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
index 0d0d452..58a4244 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c
@@ -14,9 +14,8 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
 #include <crypto/aes.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 
 #include "ccp-crypto.h"
@@ -110,15 +109,12 @@
 	ctx->u.aes.key_len = key_len / 2;
 	sg_init_one(&ctx->u.aes.key_sg, ctx->u.aes.key, key_len);
 
-	return crypto_ablkcipher_setkey(ctx->u.aes.tfm_ablkcipher, key,
-					key_len);
+	return crypto_skcipher_setkey(ctx->u.aes.tfm_skcipher, key, key_len);
 }
 
 static int ccp_aes_xts_crypt(struct ablkcipher_request *req,
 			     unsigned int encrypt)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
 	struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req);
 	unsigned int unit;
@@ -146,14 +142,19 @@
 
 	if ((unit_size == CCP_XTS_AES_UNIT_SIZE__LAST) ||
 	    (ctx->u.aes.key_len != AES_KEYSIZE_128)) {
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->u.aes.tfm_skcipher);
+
 		/* Use the fallback to process the request for any
 		 * unsupported unit sizes or key sizes
 		 */
-		ablkcipher_request_set_tfm(req, ctx->u.aes.tfm_ablkcipher);
-		ret = (encrypt) ? crypto_ablkcipher_encrypt(req) :
-				  crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
-
+		skcipher_request_set_tfm(subreq, ctx->u.aes.tfm_skcipher);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		ret = encrypt ? crypto_skcipher_encrypt(subreq) :
+				crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return ret;
 	}
 
@@ -192,23 +193,21 @@
 static int ccp_aes_xts_cra_init(struct crypto_tfm *tfm)
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *fallback_tfm;
+	struct crypto_skcipher *fallback_tfm;
 
 	ctx->complete = ccp_aes_xts_complete;
 	ctx->u.aes.key_len = 0;
 
-	fallback_tfm = crypto_alloc_ablkcipher(crypto_tfm_alg_name(tfm), 0,
-					       CRYPTO_ALG_ASYNC |
-					       CRYPTO_ALG_NEED_FALLBACK);
+	fallback_tfm = crypto_alloc_skcipher("xts(aes)", 0,
+					     CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(fallback_tfm)) {
-		pr_warn("could not load fallback driver %s\n",
-			crypto_tfm_alg_name(tfm));
+		pr_warn("could not load fallback driver xts(aes)\n");
 		return PTR_ERR(fallback_tfm);
 	}
-	ctx->u.aes.tfm_ablkcipher = fallback_tfm;
+	ctx->u.aes.tfm_skcipher = fallback_tfm;
 
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx) +
-				      fallback_tfm->base.crt_ablkcipher.reqsize;
+	tfm->crt_ablkcipher.reqsize = sizeof(struct ccp_aes_req_ctx);
 
 	return 0;
 }
@@ -217,9 +216,7 @@
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (ctx->u.aes.tfm_ablkcipher)
-		crypto_free_ablkcipher(ctx->u.aes.tfm_ablkcipher);
-	ctx->u.aes.tfm_ablkcipher = NULL;
+	crypto_free_skcipher(ctx->u.aes.tfm_skcipher);
 }
 
 static int ccp_register_aes_xts_alg(struct list_head *head,
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index a326ec2..8335b32 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -17,7 +17,6 @@
 #include <linux/wait.h>
 #include <linux/pci.h>
 #include <linux/ccp.h>
-#include <linux/crypto.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
 #include <crypto/ctr.h>
@@ -69,7 +68,7 @@
 /***** AES related defines *****/
 struct ccp_aes_ctx {
 	/* Fallback cipher for XTS with unsupported unit sizes */
-	struct crypto_ablkcipher *tfm_ablkcipher;
+	struct crypto_skcipher *tfm_skcipher;
 
 	/* Cipher used to generate CMAC K1/K2 keys */
 	struct crypto_cipher *tfm_cipher;
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index e8ef9fd..e373cc6 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -31,22 +31,42 @@
 
 #include "cesa.h"
 
+/* Limit of the crypto queue before reaching the backlog */
+#define CESA_CRYPTO_DEFAULT_MAX_QLEN 128
+
 static int allhwsupport = !IS_ENABLED(CONFIG_CRYPTO_DEV_MV_CESA);
 module_param_named(allhwsupport, allhwsupport, int, 0444);
 MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if overlaps with the mv_cesa driver)");
 
 struct mv_cesa_dev *cesa_dev;
 
-static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
+struct crypto_async_request *
+mv_cesa_dequeue_req_locked(struct mv_cesa_engine *engine,
+			   struct crypto_async_request **backlog)
 {
-	struct crypto_async_request *req, *backlog;
+	struct crypto_async_request *req;
+
+	*backlog = crypto_get_backlog(&engine->queue);
+	req = crypto_dequeue_request(&engine->queue);
+
+	if (!req)
+		return NULL;
+
+	return req;
+}
+
+static void mv_cesa_rearm_engine(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req = NULL, *backlog = NULL;
 	struct mv_cesa_ctx *ctx;
 
-	spin_lock_bh(&cesa_dev->lock);
-	backlog = crypto_get_backlog(&cesa_dev->queue);
-	req = crypto_dequeue_request(&cesa_dev->queue);
-	engine->req = req;
-	spin_unlock_bh(&cesa_dev->lock);
+
+	spin_lock_bh(&engine->lock);
+	if (!engine->req) {
+		req = mv_cesa_dequeue_req_locked(engine, &backlog);
+		engine->req = req;
+	}
+	spin_unlock_bh(&engine->lock);
 
 	if (!req)
 		return;
@@ -55,8 +75,47 @@
 		backlog->complete(backlog, -EINPROGRESS);
 
 	ctx = crypto_tfm_ctx(req->tfm);
-	ctx->ops->prepare(req, engine);
 	ctx->ops->step(req);
+
+	return;
+}
+
+static int mv_cesa_std_process(struct mv_cesa_engine *engine, u32 status)
+{
+	struct crypto_async_request *req;
+	struct mv_cesa_ctx *ctx;
+	int res;
+
+	req = engine->req;
+	ctx = crypto_tfm_ctx(req->tfm);
+	res = ctx->ops->process(req, status);
+
+	if (res == 0) {
+		ctx->ops->complete(req);
+		mv_cesa_engine_enqueue_complete_request(engine, req);
+	} else if (res == -EINPROGRESS) {
+		ctx->ops->step(req);
+	}
+
+	return res;
+}
+
+static int mv_cesa_int_process(struct mv_cesa_engine *engine, u32 status)
+{
+	if (engine->chain.first && engine->chain.last)
+		return mv_cesa_tdma_process(engine, status);
+
+	return mv_cesa_std_process(engine, status);
+}
+
+static inline void
+mv_cesa_complete_req(struct mv_cesa_ctx *ctx, struct crypto_async_request *req,
+		     int res)
+{
+	ctx->ops->cleanup(req);
+	local_bh_disable();
+	req->complete(req, res);
+	local_bh_enable();
 }
 
 static irqreturn_t mv_cesa_int(int irq, void *priv)
@@ -83,49 +142,54 @@
 		writel(~status, engine->regs + CESA_SA_FPGA_INT_STATUS);
 		writel(~status, engine->regs + CESA_SA_INT_STATUS);
 
+		/* Process fetched requests */
+		res = mv_cesa_int_process(engine, status & mask);
 		ret = IRQ_HANDLED;
+
 		spin_lock_bh(&engine->lock);
 		req = engine->req;
+		if (res != -EINPROGRESS)
+			engine->req = NULL;
 		spin_unlock_bh(&engine->lock);
-		if (req) {
-			ctx = crypto_tfm_ctx(req->tfm);
-			res = ctx->ops->process(req, status & mask);
-			if (res != -EINPROGRESS) {
-				spin_lock_bh(&engine->lock);
-				engine->req = NULL;
-				mv_cesa_dequeue_req_unlocked(engine);
-				spin_unlock_bh(&engine->lock);
-				ctx->ops->cleanup(req);
-				local_bh_disable();
-				req->complete(req, res);
-				local_bh_enable();
-			} else {
-				ctx->ops->step(req);
-			}
+
+		ctx = crypto_tfm_ctx(req->tfm);
+
+		if (res && res != -EINPROGRESS)
+			mv_cesa_complete_req(ctx, req, res);
+
+		/* Launch the next pending request */
+		mv_cesa_rearm_engine(engine);
+
+		/* Iterate over the complete queue */
+		while (true) {
+			req = mv_cesa_engine_dequeue_complete_request(engine);
+			if (!req)
+				break;
+
+			mv_cesa_complete_req(ctx, req, 0);
 		}
 	}
 
 	return ret;
 }
 
-int mv_cesa_queue_req(struct crypto_async_request *req)
+int mv_cesa_queue_req(struct crypto_async_request *req,
+		      struct mv_cesa_req *creq)
 {
 	int ret;
-	int i;
+	struct mv_cesa_engine *engine = creq->engine;
 
-	spin_lock_bh(&cesa_dev->lock);
-	ret = crypto_enqueue_request(&cesa_dev->queue, req);
-	spin_unlock_bh(&cesa_dev->lock);
+	spin_lock_bh(&engine->lock);
+	if (mv_cesa_req_get_type(creq) == CESA_DMA_REQ)
+		mv_cesa_tdma_chain(engine, creq);
+
+	ret = crypto_enqueue_request(&engine->queue, req);
+	spin_unlock_bh(&engine->lock);
 
 	if (ret != -EINPROGRESS)
 		return ret;
 
-	for (i = 0; i < cesa_dev->caps->nengines; i++) {
-		spin_lock_bh(&cesa_dev->engines[i].lock);
-		if (!cesa_dev->engines[i].req)
-			mv_cesa_dequeue_req_unlocked(&cesa_dev->engines[i]);
-		spin_unlock_bh(&cesa_dev->engines[i].lock);
-	}
+	mv_cesa_rearm_engine(engine);
 
 	return -EINPROGRESS;
 }
@@ -309,6 +373,10 @@
 	if (!dma->padding_pool)
 		return -ENOMEM;
 
+	dma->iv_pool = dmam_pool_create("cesa_iv", dev, 16, 1, 0);
+	if (!dma->iv_pool)
+		return -ENOMEM;
+
 	cesa->dma = dma;
 
 	return 0;
@@ -416,7 +484,7 @@
 		return -ENOMEM;
 
 	spin_lock_init(&cesa->lock);
-	crypto_init_queue(&cesa->queue, 50);
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
 	cesa->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(cesa->regs))
@@ -489,6 +557,10 @@
 						engine);
 		if (ret)
 			goto err_cleanup;
+
+		crypto_init_queue(&engine->queue, CESA_CRYPTO_DEFAULT_MAX_QLEN);
+		atomic_set(&engine->load, 0);
+		INIT_LIST_HEAD(&engine->complete_queue);
 	}
 
 	cesa_dev = cesa;
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index 74071e4..e423d33 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -271,10 +271,13 @@
 /* TDMA descriptor flags */
 #define CESA_TDMA_DST_IN_SRAM			BIT(31)
 #define CESA_TDMA_SRC_IN_SRAM			BIT(30)
-#define CESA_TDMA_TYPE_MSK			GENMASK(29, 0)
+#define CESA_TDMA_END_OF_REQ			BIT(29)
+#define CESA_TDMA_BREAK_CHAIN			BIT(28)
+#define CESA_TDMA_TYPE_MSK			GENMASK(27, 0)
 #define CESA_TDMA_DUMMY				0
 #define CESA_TDMA_DATA				1
 #define CESA_TDMA_OP				2
+#define CESA_TDMA_IV				3
 
 /**
  * struct mv_cesa_tdma_desc - TDMA descriptor
@@ -390,6 +393,7 @@
 	struct dma_pool *op_pool;
 	struct dma_pool *cache_pool;
 	struct dma_pool *padding_pool;
+	struct dma_pool *iv_pool;
 };
 
 /**
@@ -398,7 +402,6 @@
  * @regs:	device registers
  * @sram_size:	usable SRAM size
  * @lock:	device lock
- * @queue:	crypto request queue
  * @engines:	array of engines
  * @dma:	dma pools
  *
@@ -410,7 +413,6 @@
 	struct device *dev;
 	unsigned int sram_size;
 	spinlock_t lock;
-	struct crypto_queue queue;
 	struct mv_cesa_engine *engines;
 	struct mv_cesa_dev_dma *dma;
 };
@@ -429,6 +431,11 @@
  * @int_mask:		interrupt mask cache
  * @pool:		memory pool pointing to the memory region reserved in
  *			SRAM
+ * @queue:		fifo of the pending crypto requests
+ * @load:		engine load counter, useful for load balancing
+ * @chain:		list of the current tdma descriptors being processed
+ * 			by this engine.
+ * @complete_queue:	fifo of the processed requests by the engine
  *
  * Structure storing CESA engine information.
  */
@@ -444,23 +451,27 @@
 	size_t max_req_len;
 	u32 int_mask;
 	struct gen_pool *pool;
+	struct crypto_queue queue;
+	atomic_t load;
+	struct mv_cesa_tdma_chain chain;
+	struct list_head complete_queue;
 };
 
 /**
  * struct mv_cesa_req_ops - CESA request operations
- * @prepare:	prepare a request to be executed on the specified engine
  * @process:	process a request chunk result (should return 0 if the
  *		operation, -EINPROGRESS if it needs more steps or an error
  *		code)
  * @step:	launch the crypto operation on the next chunk
  * @cleanup:	cleanup the crypto request (release associated data)
+ * @complete:	complete the request, i.e copy result or context from sram when
+ * 		needed.
  */
 struct mv_cesa_req_ops {
-	void (*prepare)(struct crypto_async_request *req,
-			struct mv_cesa_engine *engine);
 	int (*process)(struct crypto_async_request *req, u32 status);
 	void (*step)(struct crypto_async_request *req);
 	void (*cleanup)(struct crypto_async_request *req);
+	void (*complete)(struct crypto_async_request *req);
 };
 
 /**
@@ -507,21 +518,11 @@
 
 /**
  * struct mv_cesa_req - CESA request
- * @type:	request type
  * @engine:	engine associated with this request
+ * @chain:	list of tdma descriptors associated  with this request
  */
 struct mv_cesa_req {
-	enum mv_cesa_req_type type;
 	struct mv_cesa_engine *engine;
-};
-
-/**
- * struct mv_cesa_tdma_req - CESA TDMA request
- * @base:	base information
- * @chain:	TDMA chain
- */
-struct mv_cesa_tdma_req {
-	struct mv_cesa_req base;
 	struct mv_cesa_tdma_chain chain;
 };
 
@@ -538,13 +539,11 @@
 
 /**
  * struct mv_cesa_ablkcipher_std_req - cipher standard request
- * @base:	base information
  * @op:		operation context
  * @offset:	current operation offset
  * @size:	size of the crypto operation
  */
 struct mv_cesa_ablkcipher_std_req {
-	struct mv_cesa_req base;
 	struct mv_cesa_op_ctx op;
 	unsigned int offset;
 	unsigned int size;
@@ -558,34 +557,27 @@
  * @dst_nents:	number of entries in the dest sg list
  */
 struct mv_cesa_ablkcipher_req {
-	union {
-		struct mv_cesa_req base;
-		struct mv_cesa_tdma_req dma;
-		struct mv_cesa_ablkcipher_std_req std;
-	} req;
+	struct mv_cesa_req base;
+	struct mv_cesa_ablkcipher_std_req std;
 	int src_nents;
 	int dst_nents;
 };
 
 /**
  * struct mv_cesa_ahash_std_req - standard hash request
- * @base:	base information
  * @offset:	current operation offset
  */
 struct mv_cesa_ahash_std_req {
-	struct mv_cesa_req base;
 	unsigned int offset;
 };
 
 /**
  * struct mv_cesa_ahash_dma_req - DMA hash request
- * @base:		base information
  * @padding:		padding buffer
  * @padding_dma:	DMA address of the padding buffer
  * @cache_dma:		DMA address of the cache buffer
  */
 struct mv_cesa_ahash_dma_req {
-	struct mv_cesa_tdma_req base;
 	u8 *padding;
 	dma_addr_t padding_dma;
 	u8 *cache;
@@ -604,8 +596,8 @@
  * @state:		hash state
  */
 struct mv_cesa_ahash_req {
+	struct mv_cesa_req base;
 	union {
-		struct mv_cesa_req base;
 		struct mv_cesa_ahash_dma_req dma;
 		struct mv_cesa_ahash_std_req std;
 	} req;
@@ -623,6 +615,35 @@
 
 extern struct mv_cesa_dev *cesa_dev;
 
+
+static inline void
+mv_cesa_engine_enqueue_complete_request(struct mv_cesa_engine *engine,
+					struct crypto_async_request *req)
+{
+	list_add_tail(&req->list, &engine->complete_queue);
+}
+
+static inline struct crypto_async_request *
+mv_cesa_engine_dequeue_complete_request(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req;
+
+	req = list_first_entry_or_null(&engine->complete_queue,
+				       struct crypto_async_request,
+				       list);
+	if (req)
+		list_del(&req->list);
+
+	return req;
+}
+
+
+static inline enum mv_cesa_req_type
+mv_cesa_req_get_type(struct mv_cesa_req *req)
+{
+	return req->chain.first ? CESA_DMA_REQ : CESA_STD_REQ;
+}
+
 static inline void mv_cesa_update_op_cfg(struct mv_cesa_op_ctx *op,
 					 u32 cfg, u32 mask)
 {
@@ -695,7 +716,32 @@
 		CESA_SA_DESC_CFG_FIRST_FRAG;
 }
 
-int mv_cesa_queue_req(struct crypto_async_request *req);
+int mv_cesa_queue_req(struct crypto_async_request *req,
+		      struct mv_cesa_req *creq);
+
+struct crypto_async_request *
+mv_cesa_dequeue_req_locked(struct mv_cesa_engine *engine,
+			   struct crypto_async_request **backlog);
+
+static inline struct mv_cesa_engine *mv_cesa_select_engine(int weight)
+{
+	int i;
+	u32 min_load = U32_MAX;
+	struct mv_cesa_engine *selected = NULL;
+
+	for (i = 0; i < cesa_dev->caps->nengines; i++) {
+		struct mv_cesa_engine *engine = cesa_dev->engines + i;
+		u32 load = atomic_read(&engine->load);
+		if (load < min_load) {
+			min_load = load;
+			selected = engine;
+		}
+	}
+
+	atomic_add(weight, &selected->load);
+
+	return selected;
+}
 
 /*
  * Helper function that indicates whether a crypto request needs to be
@@ -765,9 +811,9 @@
 	return iter->op_len;
 }
 
-void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq);
+void mv_cesa_dma_step(struct mv_cesa_req *dreq);
 
-static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
+static inline int mv_cesa_dma_process(struct mv_cesa_req *dreq,
 				      u32 status)
 {
 	if (!(status & CESA_SA_INT_ACC0_IDMA_DONE))
@@ -779,10 +825,13 @@
 	return 0;
 }
 
-void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 			 struct mv_cesa_engine *engine);
+void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq);
+void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
+			struct mv_cesa_req *dreq);
+int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status);
 
-void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq);
 
 static inline void
 mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
@@ -790,6 +839,9 @@
 	memset(chain, 0, sizeof(*chain));
 }
 
+int mv_cesa_dma_add_iv_op(struct mv_cesa_tdma_chain *chain, dma_addr_t src,
+			  u32 size, u32 flags, gfp_t gfp_flags);
+
 struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
 					const struct mv_cesa_op_ctx *op_templ,
 					bool skip_ctx,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index dcf1fce..48df03a 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -70,25 +70,28 @@
 		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
 			     DMA_BIDIRECTIONAL);
 	}
-	mv_cesa_dma_cleanup(&creq->req.dma);
+	mv_cesa_dma_cleanup(&creq->base);
 }
 
 static inline void mv_cesa_ablkcipher_cleanup(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ablkcipher_dma_cleanup(req);
 }
 
 static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t  len = min_t(size_t, req->nbytes - sreq->offset,
 			    CESA_SA_SRAM_PAYLOAD_SIZE);
 
+	mv_cesa_adjust_op(engine, &sreq->op);
+	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);
@@ -106,6 +109,8 @@
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
@@ -113,8 +118,8 @@
 					  u32 status)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	size_t len;
 
 	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
@@ -133,21 +138,19 @@
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_req *basereq = &creq->base;
+	unsigned int ivsize;
 	int ret;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_dma_process(&creq->req.dma, status);
-	else
-		ret = mv_cesa_ablkcipher_std_process(ablkreq, status);
+	if (mv_cesa_req_get_type(basereq) == CESA_STD_REQ)
+		return mv_cesa_ablkcipher_std_process(ablkreq, status);
 
+	ret = mv_cesa_dma_process(basereq, status);
 	if (ret)
 		return ret;
 
-	memcpy_fromio(ablkreq->info,
-		      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
-		      crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq)));
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+	memcpy_fromio(ablkreq->info, basereq->chain.last->data, ivsize);
 
 	return 0;
 }
@@ -157,8 +160,8 @@
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->req.dma);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->base);
 	else
 		mv_cesa_ablkcipher_std_step(ablkreq);
 }
@@ -167,22 +170,19 @@
 mv_cesa_ablkcipher_dma_prepare(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+	mv_cesa_dma_prepare(basereq, basereq->engine);
 }
 
 static inline void
 mv_cesa_ablkcipher_std_prepare(struct ablkcipher_request *req)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
 
 	sreq->size = 0;
 	sreq->offset = 0;
-	mv_cesa_adjust_op(engine, &sreq->op);
-	memcpy_toio(engine->sram, &sreq->op, sizeof(sreq->op));
 }
 
 static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
@@ -190,9 +190,9 @@
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-	creq->req.base.engine = engine;
+	creq->base.engine = engine;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ablkcipher_dma_prepare(ablkreq);
 	else
 		mv_cesa_ablkcipher_std_prepare(ablkreq);
@@ -206,11 +206,34 @@
 	mv_cesa_ablkcipher_cleanup(ablkreq);
 }
 
+static void
+mv_cesa_ablkcipher_complete(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+	struct mv_cesa_engine *engine = creq->base.engine;
+	unsigned int ivsize;
+
+	atomic_sub(ablkreq->nbytes, &engine->load);
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq));
+
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ) {
+		struct mv_cesa_req *basereq;
+
+		basereq = &creq->base;
+		memcpy(ablkreq->info, basereq->chain.last->data, ivsize);
+	} else {
+		memcpy_fromio(ablkreq->info,
+			      engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
+			      ivsize);
+	}
+}
+
 static const struct mv_cesa_req_ops mv_cesa_ablkcipher_req_ops = {
 	.step = mv_cesa_ablkcipher_step,
 	.process = mv_cesa_ablkcipher_process,
-	.prepare = mv_cesa_ablkcipher_prepare,
 	.cleanup = mv_cesa_ablkcipher_req_cleanup,
+	.complete = mv_cesa_ablkcipher_complete,
 };
 
 static int mv_cesa_ablkcipher_cra_init(struct crypto_tfm *tfm)
@@ -295,15 +318,15 @@
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		      GFP_KERNEL : GFP_ATOMIC;
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ablkcipher_dma_iter iter;
 	struct mv_cesa_tdma_chain chain;
 	bool skip_ctx = false;
 	int ret;
+	unsigned int ivsize;
 
-	dreq->base.type = CESA_DMA_REQ;
-	dreq->chain.first = NULL;
-	dreq->chain.last = NULL;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	if (req->src != req->dst) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
@@ -358,12 +381,21 @@
 
 	} while (mv_cesa_ablkcipher_req_iter_next_op(&iter));
 
-	dreq->chain = chain;
+	/* Add output data for IV */
+	ivsize = crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(req));
+	ret = mv_cesa_dma_add_iv_op(&chain, CESA_SA_CRYPT_IV_SRAM_OFFSET,
+				    ivsize, CESA_TDMA_SRC_IN_SRAM, flags);
+
+	if (ret)
+		goto err_free_tdma;
+
+	basereq->chain = chain;
+	basereq->chain.last->flags |= CESA_TDMA_END_OF_REQ;
 
 	return 0;
 
 err_free_tdma:
-	mv_cesa_dma_cleanup(dreq);
+	mv_cesa_dma_cleanup(basereq);
 	if (req->dst != req->src)
 		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
 			     DMA_FROM_DEVICE);
@@ -380,11 +412,13 @@
 				const struct mv_cesa_op_ctx *op_templ)
 {
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
-	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->std;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	sreq->base.type = CESA_STD_REQ;
 	sreq->op = *op_templ;
 	sreq->skip_ctx = false;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	return 0;
 }
@@ -414,7 +448,6 @@
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_OP_CRYPT_ONLY,
 			      CESA_SA_DESC_CFG_OP_MSK);
 
-	/* TODO: add a threshold for DMA usage */
 	if (cesa_dev->caps->has_tdma)
 		ret = mv_cesa_ablkcipher_dma_req_init(req, tmpl);
 	else
@@ -423,26 +456,39 @@
 	return ret;
 }
 
+static int mv_cesa_ablkcipher_queue_req(struct ablkcipher_request *req,
+					struct mv_cesa_op_ctx *tmpl)
+{
+	int ret;
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_engine *engine;
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	engine = mv_cesa_select_engine(req->nbytes);
+	mv_cesa_ablkcipher_prepare(&req->base, engine);
+
+	ret = mv_cesa_queue_req(&req->base, &creq->base);
+
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
 static int mv_cesa_des_op(struct ablkcipher_request *req,
 			  struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret;
 
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK);
 
 	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_des_encrypt(struct ablkcipher_request *req)
@@ -547,22 +593,13 @@
 			   struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_des3_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret;
 
 	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_3DES,
 			      CESA_SA_DESC_CFG_CRYPTM_MSK);
 
 	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_des3_ede_encrypt(struct ablkcipher_request *req)
@@ -673,7 +710,7 @@
 			  struct mv_cesa_op_ctx *tmpl)
 {
 	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	int ret, i;
+	int i;
 	u32 *key;
 	u32 cfg;
 
@@ -696,15 +733,7 @@
 			      CESA_SA_DESC_CFG_CRYPTM_MSK |
 			      CESA_SA_DESC_CFG_AES_LEN_MSK);
 
-	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
-	if (ret)
-		return ret;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ablkcipher_cleanup(req);
-
-	return ret;
+	return mv_cesa_ablkcipher_queue_req(req, tmpl);
 }
 
 static int mv_cesa_ecb_aes_encrypt(struct ablkcipher_request *req)
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 7a5058d..c35912b 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -103,14 +103,14 @@
 
 	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
 	mv_cesa_ahash_dma_free_cache(&creq->req.dma);
-	mv_cesa_dma_cleanup(&creq->req.dma.base);
+	mv_cesa_dma_cleanup(&creq->base);
 }
 
 static inline void mv_cesa_ahash_cleanup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_cleanup(req);
 }
 
@@ -118,7 +118,7 @@
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_last_cleanup(req);
 }
 
@@ -157,11 +157,23 @@
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_engine *engine = creq->base.engine;
 	struct mv_cesa_op_ctx *op;
 	unsigned int new_cache_ptr = 0;
 	u32 frag_mode;
 	size_t  len;
+	unsigned int digsize;
+	int i;
+
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
+	for (i = 0; i < digsize / 4; i++)
+		writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i));
+
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
 
 	if (creq->cache_ptr)
 		memcpy_toio(engine->sram + CESA_SA_DATA_SRAM_OFFSET,
@@ -237,6 +249,8 @@
 
 	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
 	writel_relaxed(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
@@ -254,20 +268,17 @@
 static inline void mv_cesa_ahash_dma_prepare(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
-	struct mv_cesa_tdma_req *dreq = &creq->req.dma.base;
+	struct mv_cesa_req *basereq = &creq->base;
 
-	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+	mv_cesa_dma_prepare(basereq, basereq->engine);
 }
 
 static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
-	struct mv_cesa_engine *engine = sreq->base.engine;
 
 	sreq->offset = 0;
-	mv_cesa_adjust_op(engine, &creq->op_tmpl);
-	memcpy_toio(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
 }
 
 static void mv_cesa_ahash_step(struct crypto_async_request *req)
@@ -275,8 +286,8 @@
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
 
-	if (creq->req.base.type == CESA_DMA_REQ)
-		mv_cesa_dma_step(&creq->req.dma.base);
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->base);
 	else
 		mv_cesa_ahash_std_step(ahashreq);
 }
@@ -285,17 +296,20 @@
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
-	struct mv_cesa_engine *engine = creq->req.base.engine;
+
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
+		return mv_cesa_dma_process(&creq->base, status);
+
+	return mv_cesa_ahash_std_process(ahashreq, status);
+}
+
+static void mv_cesa_ahash_complete(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	struct mv_cesa_engine *engine = creq->base.engine;
 	unsigned int digsize;
-	int ret, i;
-
-	if (creq->req.base.type == CESA_DMA_REQ)
-		ret = mv_cesa_dma_process(&creq->req.dma.base, status);
-	else
-		ret = mv_cesa_ahash_std_process(ahashreq, status);
-
-	if (ret == -EINPROGRESS)
-		return ret;
+	int i;
 
 	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
 	for (i = 0; i < digsize / 4; i++)
@@ -325,7 +339,7 @@
 		}
 	}
 
-	return ret;
+	atomic_sub(ahashreq->nbytes, &engine->load);
 }
 
 static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
@@ -333,19 +347,13 @@
 {
 	struct ahash_request *ahashreq = ahash_request_cast(req);
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
-	unsigned int digsize;
-	int i;
 
-	creq->req.base.engine = engine;
+	creq->base.engine = engine;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (mv_cesa_req_get_type(&creq->base) == CESA_DMA_REQ)
 		mv_cesa_ahash_dma_prepare(ahashreq);
 	else
 		mv_cesa_ahash_std_prepare(ahashreq);
-
-	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
-	for (i = 0; i < digsize / 4; i++)
-		writel_relaxed(creq->state[i], engine->regs + CESA_IVDIG(i));
 }
 
 static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
@@ -362,8 +370,8 @@
 static const struct mv_cesa_req_ops mv_cesa_ahash_req_ops = {
 	.step = mv_cesa_ahash_step,
 	.process = mv_cesa_ahash_process,
-	.prepare = mv_cesa_ahash_prepare,
 	.cleanup = mv_cesa_ahash_req_cleanup,
+	.complete = mv_cesa_ahash_complete,
 };
 
 static int mv_cesa_ahash_init(struct ahash_request *req,
@@ -553,15 +561,14 @@
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
 		      GFP_KERNEL : GFP_ATOMIC;
-	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
-	struct mv_cesa_tdma_req *dreq = &ahashdreq->base;
+	struct mv_cesa_req *basereq = &creq->base;
 	struct mv_cesa_ahash_dma_iter iter;
 	struct mv_cesa_op_ctx *op = NULL;
 	unsigned int frag_len;
 	int ret;
 
-	dreq->chain.first = NULL;
-	dreq->chain.last = NULL;
+	basereq->chain.first = NULL;
+	basereq->chain.last = NULL;
 
 	if (creq->src_nents) {
 		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
@@ -572,14 +579,14 @@
 		}
 	}
 
-	mv_cesa_tdma_desc_iter_init(&dreq->chain);
+	mv_cesa_tdma_desc_iter_init(&basereq->chain);
 	mv_cesa_ahash_req_iter_init(&iter, req);
 
 	/*
 	 * Add the cache (left-over data from a previous block) first.
 	 * This will never overflow the SRAM size.
 	 */
-	ret = mv_cesa_ahash_dma_add_cache(&dreq->chain, &iter, creq, flags);
+	ret = mv_cesa_ahash_dma_add_cache(&basereq->chain, &iter, creq, flags);
 	if (ret)
 		goto err_free_tdma;
 
@@ -590,7 +597,7 @@
 		 * data. We intentionally do not add the final op block.
 		 */
 		while (true) {
-			ret = mv_cesa_dma_add_op_transfers(&dreq->chain,
+			ret = mv_cesa_dma_add_op_transfers(&basereq->chain,
 							   &iter.base,
 							   &iter.src, flags);
 			if (ret)
@@ -601,7 +608,7 @@
 			if (!mv_cesa_ahash_req_iter_next_op(&iter))
 				break;
 
-			op = mv_cesa_dma_add_frag(&dreq->chain, &creq->op_tmpl,
+			op = mv_cesa_dma_add_frag(&basereq->chain, &creq->op_tmpl,
 						  frag_len, flags);
 			if (IS_ERR(op)) {
 				ret = PTR_ERR(op);
@@ -619,10 +626,10 @@
 	 * operation, which depends whether this is the final request.
 	 */
 	if (creq->last_req)
-		op = mv_cesa_ahash_dma_last_req(&dreq->chain, &iter, creq,
+		op = mv_cesa_ahash_dma_last_req(&basereq->chain, &iter, creq,
 						frag_len, flags);
 	else if (frag_len)
-		op = mv_cesa_dma_add_frag(&dreq->chain, &creq->op_tmpl,
+		op = mv_cesa_dma_add_frag(&basereq->chain, &creq->op_tmpl,
 					  frag_len, flags);
 
 	if (IS_ERR(op)) {
@@ -632,7 +639,7 @@
 
 	if (op) {
 		/* Add dummy desc to wait for crypto operation end */
-		ret = mv_cesa_dma_add_dummy_end(&dreq->chain, flags);
+		ret = mv_cesa_dma_add_dummy_end(&basereq->chain, flags);
 		if (ret)
 			goto err_free_tdma;
 	}
@@ -643,10 +650,13 @@
 	else
 		creq->cache_ptr = 0;
 
+	basereq->chain.last->flags |= (CESA_TDMA_END_OF_REQ |
+				       CESA_TDMA_BREAK_CHAIN);
+
 	return 0;
 
 err_free_tdma:
-	mv_cesa_dma_cleanup(dreq);
+	mv_cesa_dma_cleanup(basereq);
 	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
 
 err:
@@ -660,11 +670,6 @@
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	int ret;
 
-	if (cesa_dev->caps->has_tdma)
-		creq->req.base.type = CESA_DMA_REQ;
-	else
-		creq->req.base.type = CESA_STD_REQ;
-
 	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
 	if (creq->src_nents < 0) {
 		dev_err(cesa_dev->dev, "Invalid number of src SG");
@@ -678,81 +683,68 @@
 	if (*cached)
 		return 0;
 
-	if (creq->req.base.type == CESA_DMA_REQ)
+	if (cesa_dev->caps->has_tdma)
 		ret = mv_cesa_ahash_dma_req_init(req);
 
 	return ret;
 }
 
+static int mv_cesa_ahash_queue_req(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_engine *engine;
+	bool cached = false;
+	int ret;
+
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	engine = mv_cesa_select_engine(req->nbytes);
+	mv_cesa_ahash_prepare(&req->base, engine);
+
+	ret = mv_cesa_queue_req(&req->base, &creq->base);
+
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
+		mv_cesa_ahash_cleanup(req);
+
+	return ret;
+}
+
 static int mv_cesa_ahash_update(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
-	bool cached = false;
-	int ret;
 
 	creq->len += req->nbytes;
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
 
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_final(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
-	bool cached = false;
-	int ret;
 
 	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
 	creq->last_req = true;
 	req->nbytes = 0;
 
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
-
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_finup(struct ahash_request *req)
 {
 	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
 	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
-	bool cached = false;
-	int ret;
 
 	creq->len += req->nbytes;
 	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
 	creq->last_req = true;
 
-	ret = mv_cesa_ahash_req_init(req, &cached);
-	if (ret)
-		return ret;
-
-	if (cached)
-		return 0;
-
-	ret = mv_cesa_queue_req(&req->base);
-	if (mv_cesa_req_needs_cleanup(&req->base, ret))
-		mv_cesa_ahash_cleanup(req);
-
-	return ret;
+	return mv_cesa_ahash_queue_req(req);
 }
 
 static int mv_cesa_ahash_export(struct ahash_request *req, void *hash,
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
index 0ad8f1e..86a065b 100644
--- a/drivers/crypto/marvell/tdma.c
+++ b/drivers/crypto/marvell/tdma.c
@@ -37,9 +37,9 @@
 	return true;
 }
 
-void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
+void mv_cesa_dma_step(struct mv_cesa_req *dreq)
 {
-	struct mv_cesa_engine *engine = dreq->base.engine;
+	struct mv_cesa_engine *engine = dreq->engine;
 
 	writel_relaxed(0, engine->regs + CESA_SA_CFG);
 
@@ -53,19 +53,25 @@
 		       engine->regs + CESA_SA_CFG);
 	writel_relaxed(dreq->chain.first->cur_dma,
 		       engine->regs + CESA_TDMA_NEXT_ADDR);
+	BUG_ON(readl(engine->regs + CESA_SA_CMD) &
+	       CESA_SA_CMD_EN_CESA_SA_ACCL0);
 	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
 }
 
-void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
+void mv_cesa_dma_cleanup(struct mv_cesa_req *dreq)
 {
 	struct mv_cesa_tdma_desc *tdma;
 
 	for (tdma = dreq->chain.first; tdma;) {
 		struct mv_cesa_tdma_desc *old_tdma = tdma;
+		u32 type = tdma->flags & CESA_TDMA_TYPE_MSK;
 
-		if (tdma->flags & CESA_TDMA_OP)
+		if (type == CESA_TDMA_OP)
 			dma_pool_free(cesa_dev->dma->op_pool, tdma->op,
 				      le32_to_cpu(tdma->src));
+		else if (type == CESA_TDMA_IV)
+			dma_pool_free(cesa_dev->dma->iv_pool, tdma->data,
+				      le32_to_cpu(tdma->dst));
 
 		tdma = tdma->next;
 		dma_pool_free(cesa_dev->dma->tdma_desc_pool, old_tdma,
@@ -76,7 +82,7 @@
 	dreq->chain.last = NULL;
 }
 
-void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+void mv_cesa_dma_prepare(struct mv_cesa_req *dreq,
 			 struct mv_cesa_engine *engine)
 {
 	struct mv_cesa_tdma_desc *tdma;
@@ -88,11 +94,97 @@
 		if (tdma->flags & CESA_TDMA_SRC_IN_SRAM)
 			tdma->src = cpu_to_le32(tdma->src + engine->sram_dma);
 
-		if (tdma->flags & CESA_TDMA_OP)
+		if ((tdma->flags & CESA_TDMA_TYPE_MSK) == CESA_TDMA_OP)
 			mv_cesa_adjust_op(engine, tdma->op);
 	}
 }
 
+void mv_cesa_tdma_chain(struct mv_cesa_engine *engine,
+			struct mv_cesa_req *dreq)
+{
+	if (engine->chain.first == NULL && engine->chain.last == NULL) {
+		engine->chain.first = dreq->chain.first;
+		engine->chain.last  = dreq->chain.last;
+	} else {
+		struct mv_cesa_tdma_desc *last;
+
+		last = engine->chain.last;
+		last->next = dreq->chain.first;
+		engine->chain.last = dreq->chain.last;
+
+		if (!(last->flags & CESA_TDMA_BREAK_CHAIN))
+			last->next_dma = dreq->chain.first->cur_dma;
+	}
+}
+
+int mv_cesa_tdma_process(struct mv_cesa_engine *engine, u32 status)
+{
+	struct crypto_async_request *req = NULL;
+	struct mv_cesa_tdma_desc *tdma = NULL, *next = NULL;
+	dma_addr_t tdma_cur;
+	int res = 0;
+
+	tdma_cur = readl(engine->regs + CESA_TDMA_CUR);
+
+	for (tdma = engine->chain.first; tdma; tdma = next) {
+		spin_lock_bh(&engine->lock);
+		next = tdma->next;
+		spin_unlock_bh(&engine->lock);
+
+		if (tdma->flags & CESA_TDMA_END_OF_REQ) {
+			struct crypto_async_request *backlog = NULL;
+			struct mv_cesa_ctx *ctx;
+			u32 current_status;
+
+			spin_lock_bh(&engine->lock);
+			/*
+			 * if req is NULL, this means we're processing the
+			 * request in engine->req.
+			 */
+			if (!req)
+				req = engine->req;
+			else
+				req = mv_cesa_dequeue_req_locked(engine,
+								 &backlog);
+
+			/* Re-chaining to the next request */
+			engine->chain.first = tdma->next;
+			tdma->next = NULL;
+
+			/* If this is the last request, clear the chain */
+			if (engine->chain.first == NULL)
+				engine->chain.last  = NULL;
+			spin_unlock_bh(&engine->lock);
+
+			ctx = crypto_tfm_ctx(req->tfm);
+			current_status = (tdma->cur_dma == tdma_cur) ?
+					  status : CESA_SA_INT_ACC0_IDMA_DONE;
+			res = ctx->ops->process(req, current_status);
+			ctx->ops->complete(req);
+
+			if (res == 0)
+				mv_cesa_engine_enqueue_complete_request(engine,
+									req);
+
+			if (backlog)
+				backlog->complete(backlog, -EINPROGRESS);
+		}
+
+		if (res || tdma->cur_dma == tdma_cur)
+			break;
+	}
+
+	/* Save the last request in error to engine->req, so that the core
+	 * knows which request was fautly */
+	if (res) {
+		spin_lock_bh(&engine->lock);
+		engine->req = req;
+		spin_unlock_bh(&engine->lock);
+	}
+
+	return res;
+}
+
 static struct mv_cesa_tdma_desc *
 mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
 {
@@ -117,6 +209,32 @@
 	return new_tdma;
 }
 
+int mv_cesa_dma_add_iv_op(struct mv_cesa_tdma_chain *chain, dma_addr_t src,
+			  u32 size, u32 flags, gfp_t gfp_flags)
+{
+
+	struct mv_cesa_tdma_desc *tdma;
+	u8 *iv;
+	dma_addr_t dma_handle;
+
+	tdma = mv_cesa_dma_add_desc(chain, gfp_flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	iv = dma_pool_alloc(cesa_dev->dma->iv_pool, gfp_flags, &dma_handle);
+	if (!iv)
+		return -ENOMEM;
+
+	tdma->byte_cnt = cpu_to_le32(size | BIT(31));
+	tdma->src = src;
+	tdma->dst = cpu_to_le32(dma_handle);
+	tdma->data = iv;
+
+	flags &= (CESA_TDMA_DST_IN_SRAM | CESA_TDMA_SRC_IN_SRAM);
+	tdma->flags = flags | CESA_TDMA_IV;
+	return 0;
+}
+
 struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
 					const struct mv_cesa_op_ctx *op_templ,
 					bool skip_ctx,
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index 59ed54e..625ee50 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -11,7 +11,6 @@
  * http://www.gnu.org/copyleft/gpl.html
  */
 
-#include <linux/crypto.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -25,6 +24,7 @@
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 
 #define DCP_MAX_CHANS	4
 #define DCP_BUF_SZ	PAGE_SIZE
@@ -84,7 +84,7 @@
 	unsigned int			hot:1;
 
 	/* Crypto-specific context */
-	struct crypto_ablkcipher	*fallback;
+	struct crypto_skcipher		*fallback;
 	unsigned int			key_len;
 	uint8_t				key[AES_KEYSIZE_128];
 };
@@ -374,20 +374,22 @@
 
 static int mxs_dcp_block_fallback(struct ablkcipher_request *req, int enc)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
-	struct dcp_async_ctx *ctx = crypto_ablkcipher_ctx(
-		crypto_ablkcipher_reqtfm(req));
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct dcp_async_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
 	int ret;
 
-	ablkcipher_request_set_tfm(req, ctx->fallback);
+	skcipher_request_set_tfm(subreq, ctx->fallback);
+	skcipher_request_set_callback(subreq, req->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->nbytes, req->info);
 
 	if (enc)
-		ret = crypto_ablkcipher_encrypt(req);
+		ret = crypto_skcipher_encrypt(subreq);
 	else
-		ret = crypto_ablkcipher_decrypt(req);
+		ret = crypto_skcipher_decrypt(subreq);
 
-	ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+	skcipher_request_zero(subreq);
 
 	return ret;
 }
@@ -453,28 +455,22 @@
 		return 0;
 	}
 
-	/* Check if the key size is supported by kernel at all. */
-	if (len != AES_KEYSIZE_192 && len != AES_KEYSIZE_256) {
-		tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
-
 	/*
 	 * If the requested AES key size is not supported by the hardware,
 	 * but is supported by in-kernel software implementation, we use
 	 * software fallback.
 	 */
-	actx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	actx->fallback->base.crt_flags |=
-		tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK;
+	crypto_skcipher_clear_flags(actx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(actx->fallback,
+				  tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_ablkcipher_setkey(actx->fallback, key, len);
+	ret = crypto_skcipher_setkey(actx->fallback, key, len);
 	if (!ret)
 		return 0;
 
 	tfm->base.crt_flags &= ~CRYPTO_TFM_RES_MASK;
-	tfm->base.crt_flags |=
-		actx->fallback->base.crt_flags & CRYPTO_TFM_RES_MASK;
+	tfm->base.crt_flags |= crypto_skcipher_get_flags(actx->fallback) &
+			       CRYPTO_TFM_RES_MASK;
 
 	return ret;
 }
@@ -484,9 +480,9 @@
 	const char *name = crypto_tfm_alg_name(tfm);
 	const uint32_t flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK;
 	struct dcp_async_ctx *actx = crypto_tfm_ctx(tfm);
-	struct crypto_ablkcipher *blk;
+	struct crypto_skcipher *blk;
 
-	blk = crypto_alloc_ablkcipher(name, 0, flags);
+	blk = crypto_alloc_skcipher(name, 0, flags);
 	if (IS_ERR(blk))
 		return PTR_ERR(blk);
 
@@ -499,8 +495,7 @@
 {
 	struct dcp_async_ctx *actx = crypto_tfm_ctx(tfm);
 
-	crypto_free_ablkcipher(actx->fallback);
-	actx->fallback = NULL;
+	crypto_free_skcipher(actx->fallback);
 }
 
 /*
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 0794f1c..42f0f22 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -392,7 +392,7 @@
 		     ((bytes_so_far + sizeof(struct msc_triplet)) <= lenp) &&
 		     i < msc->triplets;
 		     i++) {
-			if (msc->fc > NX_MAX_FC || msc->mode > NX_MAX_MODE) {
+			if (msc->fc >= NX_MAX_FC || msc->mode >= NX_MAX_MODE) {
 				dev_err(dev, "unknown function code/mode "
 					"combo: %d/%d (ignored)\n", msc->fc,
 					msc->mode);
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index ce174d3..4ab53a60 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -528,8 +528,6 @@
 
 	omap_aes_dma_stop(dd);
 
-	dmaengine_terminate_all(dd->dma_lch_in);
-	dmaengine_terminate_all(dd->dma_lch_out);
 
 	return 0;
 }
@@ -580,10 +578,12 @@
 	sg_init_table(&dd->in_sgl, 1);
 	sg_set_buf(&dd->in_sgl, buf_in, total);
 	dd->in_sg = &dd->in_sgl;
+	dd->in_sg_len = 1;
 
 	sg_init_table(&dd->out_sgl, 1);
 	sg_set_buf(&dd->out_sgl, buf_out, total);
 	dd->out_sg = &dd->out_sgl;
+	dd->out_sg_len = 1;
 
 	return 0;
 }
@@ -604,7 +604,6 @@
 			crypto_ablkcipher_reqtfm(req));
 	struct omap_aes_dev *dd = omap_aes_find_dev(ctx);
 	struct omap_aes_reqctx *rctx;
-	int len;
 
 	if (!dd)
 		return -ENODEV;
@@ -616,6 +615,14 @@
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 
+	dd->in_sg_len = sg_nents_for_len(dd->in_sg, dd->total);
+	if (dd->in_sg_len < 0)
+		return dd->in_sg_len;
+
+	dd->out_sg_len = sg_nents_for_len(dd->out_sg, dd->total);
+	if (dd->out_sg_len < 0)
+		return dd->out_sg_len;
+
 	if (omap_aes_check_aligned(dd->in_sg, dd->total) ||
 	    omap_aes_check_aligned(dd->out_sg, dd->total)) {
 		if (omap_aes_copy_sgs(dd))
@@ -625,11 +632,6 @@
 		dd->sgs_copied = 0;
 	}
 
-	len = ALIGN(dd->total, AES_BLOCK_SIZE);
-	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, len);
-	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, len);
-	BUG_ON(dd->in_sg_len < 0 || dd->out_sg_len < 0);
-
 	rctx = ablkcipher_request_ctx(req);
 	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
@@ -1185,17 +1187,19 @@
 	spin_unlock(&list_lock);
 
 	for (i = 0; i < dd->pdata->algs_info_size; i++) {
-		for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
-			algp = &dd->pdata->algs_info[i].algs_list[j];
+		if (!dd->pdata->algs_info[i].registered) {
+			for (j = 0; j < dd->pdata->algs_info[i].size; j++) {
+				algp = &dd->pdata->algs_info[i].algs_list[j];
 
-			pr_debug("reg alg: %s\n", algp->cra_name);
-			INIT_LIST_HEAD(&algp->cra_list);
+				pr_debug("reg alg: %s\n", algp->cra_name);
+				INIT_LIST_HEAD(&algp->cra_list);
 
-			err = crypto_register_alg(algp);
-			if (err)
-				goto err_algs;
+				err = crypto_register_alg(algp);
+				if (err)
+					goto err_algs;
 
-			dd->pdata->algs_info[i].registered++;
+				dd->pdata->algs_info[i].registered++;
+			}
 		}
 	}
 
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index 3eedb03..5691434 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -560,10 +560,12 @@
 	sg_init_table(&dd->in_sgl, 1);
 	sg_set_buf(&dd->in_sgl, buf_in, dd->total);
 	dd->in_sg = &dd->in_sgl;
+	dd->in_sg_len = 1;
 
 	sg_init_table(&dd->out_sgl, 1);
 	sg_set_buf(&dd->out_sgl, buf_out, dd->total);
 	dd->out_sg = &dd->out_sgl;
+	dd->out_sg_len = 1;
 
 	return 0;
 }
@@ -595,6 +597,14 @@
 	dd->in_sg = req->src;
 	dd->out_sg = req->dst;
 
+	dd->in_sg_len = sg_nents_for_len(dd->in_sg, dd->total);
+	if (dd->in_sg_len < 0)
+		return dd->in_sg_len;
+
+	dd->out_sg_len = sg_nents_for_len(dd->out_sg, dd->total);
+	if (dd->out_sg_len < 0)
+		return dd->out_sg_len;
+
 	if (omap_des_copy_needed(dd->in_sg) ||
 	    omap_des_copy_needed(dd->out_sg)) {
 		if (omap_des_copy_sgs(dd))
@@ -604,10 +614,6 @@
 		dd->sgs_copied = 0;
 	}
 
-	dd->in_sg_len = scatterwalk_bytes_sglen(dd->in_sg, dd->total);
-	dd->out_sg_len = scatterwalk_bytes_sglen(dd->out_sg, dd->total);
-	BUG_ON(dd->in_sg_len < 0 || dd->out_sg_len < 0);
-
 	rctx = ablkcipher_request_ctx(req);
 	ctx = crypto_ablkcipher_ctx(crypto_ablkcipher_reqtfm(req));
 	rctx->mode &= FLAGS_MODE_MASK;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 63464e8..7fe4eef 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -100,6 +100,8 @@
 
 #define DEFAULT_TIMEOUT_INTERVAL	HZ
 
+#define DEFAULT_AUTOSUSPEND_DELAY	1000
+
 /* mostly device flags */
 #define FLAGS_BUSY		0
 #define FLAGS_FINAL		1
@@ -173,7 +175,7 @@
 	struct omap_sham_hmac_ctx base[0];
 };
 
-#define OMAP_SHAM_QUEUE_LENGTH	1
+#define OMAP_SHAM_QUEUE_LENGTH	10
 
 struct omap_sham_algs_info {
 	struct ahash_alg	*algs_list;
@@ -813,7 +815,6 @@
 {
 	struct omap_sham_reqctx *ctx = ahash_request_ctx(dd->req);
 
-	dmaengine_terminate_all(dd->dma_lch);
 
 	if (ctx->flags & BIT(FLAGS_SG)) {
 		dma_unmap_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE);
@@ -999,7 +1000,8 @@
 	dd->flags &= ~(BIT(FLAGS_BUSY) | BIT(FLAGS_FINAL) | BIT(FLAGS_CPU) |
 			BIT(FLAGS_DMA_READY) | BIT(FLAGS_OUTPUT_READY));
 
-	pm_runtime_put(dd->dev);
+	pm_runtime_mark_last_busy(dd->dev);
+	pm_runtime_put_autosuspend(dd->dev);
 
 	if (req->base.complete)
 		req->base.complete(&req->base, err);
@@ -1093,7 +1095,7 @@
 	ctx->offset = 0;
 
 	if (ctx->flags & BIT(FLAGS_FINUP)) {
-		if ((ctx->digcnt + ctx->bufcnt + ctx->total) < 9) {
+		if ((ctx->digcnt + ctx->bufcnt + ctx->total) < 240) {
 			/*
 			* OMAP HW accel works only with buffers >= 9
 			* will switch to bypass in final()
@@ -1149,9 +1151,13 @@
 	if (ctx->flags & BIT(FLAGS_ERROR))
 		return 0; /* uncompleted hash is not needed */
 
-	/* OMAP HW accel works only with buffers >= 9 */
-	/* HMAC is always >= 9 because ipad == block size */
-	if ((ctx->digcnt + ctx->bufcnt) < 9)
+	/*
+	 * OMAP HW accel works only with buffers >= 9.
+	 * HMAC is always >= 9 because ipad == block size.
+	 * If buffersize is less than 240, we use fallback SW encoding,
+	 * as using DMA + HW in this case doesn't provide any benefit.
+	 */
+	if ((ctx->digcnt + ctx->bufcnt) < 240)
 		return omap_sham_final_shash(req);
 	else if (ctx->bufcnt)
 		return omap_sham_enqueue(req, OP_FINAL);
@@ -1328,7 +1334,7 @@
 	.halg.base	= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "omap-sha1",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1351,7 +1357,7 @@
 	.halg.base	= {
 		.cra_name		= "md5",
 		.cra_driver_name	= "omap-md5",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1375,7 +1381,7 @@
 	.halg.base	= {
 		.cra_name		= "hmac(sha1)",
 		.cra_driver_name	= "omap-hmac-sha1",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1400,7 +1406,7 @@
 	.halg.base	= {
 		.cra_name		= "hmac(md5)",
 		.cra_driver_name	= "omap-hmac-md5",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
@@ -1428,7 +1434,7 @@
 	.halg.base	= {
 		.cra_name		= "sha224",
 		.cra_driver_name	= "omap-sha224",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1450,7 +1456,7 @@
 	.halg.base	= {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "omap-sha256",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1473,7 +1479,7 @@
 	.halg.base	= {
 		.cra_name		= "hmac(sha224)",
 		.cra_driver_name	= "omap-hmac-sha224",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1497,7 +1503,7 @@
 	.halg.base	= {
 		.cra_name		= "hmac(sha256)",
 		.cra_driver_name	= "omap-hmac-sha256",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1523,7 +1529,7 @@
 	.halg.base	= {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "omap-sha384",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1545,7 +1551,7 @@
 	.halg.base	= {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "omap-sha512",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1568,7 +1574,7 @@
 	.halg.base	= {
 		.cra_name		= "hmac(sha384)",
 		.cra_driver_name	= "omap-hmac-sha384",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1592,7 +1598,7 @@
 	.halg.base	= {
 		.cra_name		= "hmac(sha512)",
 		.cra_driver_name	= "omap-hmac-sha512",
-		.cra_priority		= 100,
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
@@ -1946,6 +1952,9 @@
 
 	dd->flags |= dd->pdata->flags;
 
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY);
+
 	pm_runtime_enable(dev);
 	pm_runtime_irq_safe(dev);
 
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 3b1c7ec..4757609 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -171,7 +171,7 @@
 	 * The fallback cipher. If the operation can't be done in hardware,
 	 * fallback to a software version.
 	 */
-	struct crypto_ablkcipher	*sw_cipher;
+	struct crypto_skcipher		*sw_cipher;
 };
 
 /* AEAD cipher context. */
@@ -789,33 +789,35 @@
 	 * request for any other size (192 bits) then we need to do a software
 	 * fallback.
 	 */
-	if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256 &&
-	    ctx->sw_cipher) {
+	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.
 		 */
-		ctx->sw_cipher->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-		ctx->sw_cipher->base.crt_flags |=
-			cipher->base.crt_flags & CRYPTO_TFM_REQ_MASK;
+		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_ablkcipher_setkey(ctx->sw_cipher, key, len);
+		err = crypto_skcipher_setkey(ctx->sw_cipher, key, len);
+
+		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+		tfm->crt_flags |=
+			crypto_skcipher_get_flags(ctx->sw_cipher) &
+			CRYPTO_TFM_RES_MASK;
+
 		if (err)
 			goto sw_setkey_failed;
-	} else if (len != AES_KEYSIZE_128 && len != AES_KEYSIZE_256 &&
-		   !ctx->sw_cipher)
-		err = -EINVAL;
+	}
 
 	memcpy(ctx->key, key, len);
 	ctx->key_len = len;
 
 sw_setkey_failed:
-	if (err && ctx->sw_cipher) {
-		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |=
-			ctx->sw_cipher->base.crt_flags & CRYPTO_TFM_RES_MASK;
-	}
-
 	return err;
 }
 
@@ -910,20 +912,21 @@
 	struct crypto_tfm *old_tfm =
 	    crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(old_tfm);
+	SKCIPHER_REQUEST_ON_STACK(subreq, ctx->sw_cipher);
 	int err;
 
-	if (!ctx->sw_cipher)
-		return -EINVAL;
-
 	/*
 	 * Change the request to use the software fallback transform, and once
 	 * the ciphering has completed, put the old transform back into the
 	 * request.
 	 */
-	ablkcipher_request_set_tfm(req, ctx->sw_cipher);
-	err = is_encrypt ? crypto_ablkcipher_encrypt(req) :
-		crypto_ablkcipher_decrypt(req);
-	ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(old_tfm));
+	skcipher_request_set_tfm(subreq, ctx->sw_cipher);
+	skcipher_request_set_callback(subreq, req->base.flags, NULL, NULL);
+	skcipher_request_set_crypt(subreq, req->src, req->dst,
+				   req->nbytes, req->info);
+	err = is_encrypt ? crypto_skcipher_encrypt(subreq) :
+			   crypto_skcipher_decrypt(subreq);
+	skcipher_request_zero(subreq);
 
 	return err;
 }
@@ -1015,12 +1018,13 @@
 	ctx->generic.flags = spacc_alg->type;
 	ctx->generic.engine = engine;
 	if (alg->cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
-		ctx->sw_cipher = crypto_alloc_ablkcipher(alg->cra_name, 0,
-				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+		ctx->sw_cipher = crypto_alloc_skcipher(
+			alg->cra_name, 0, CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_NEED_FALLBACK);
 		if (IS_ERR(ctx->sw_cipher)) {
 			dev_warn(engine->dev, "failed to allocate fallback for %s\n",
 				 alg->cra_name);
-			ctx->sw_cipher = NULL;
+			return PTR_ERR(ctx->sw_cipher);
 		}
 	}
 	ctx->generic.key_offs = spacc_alg->key_offs;
@@ -1035,9 +1039,7 @@
 {
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (ctx->sw_cipher)
-		crypto_free_ablkcipher(ctx->sw_cipher);
-	ctx->sw_cipher = NULL;
+	crypto_free_skcipher(ctx->sw_cipher);
 }
 
 static int spacc_ablk_encrypt(struct ablkcipher_request *req)
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 85b44e5..ce3cae4 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -4,12 +4,13 @@
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AKCIPHER
+	select CRYPTO_DH
 	select CRYPTO_HMAC
+	select CRYPTO_RSA
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
 	select FW_LOADER
-	select ASN1
 
 config CRYPTO_DEV_QAT_DH895xCC
 	tristate "Support for Intel(R) DH895xCC"
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 c5bd5a9..6bc68bc 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
+++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c
@@ -229,6 +229,7 @@
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
 	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->reset_device = adf_reset_flr;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
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 879e04c..618cec3 100644
--- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
+++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c
@@ -239,6 +239,7 @@
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
 	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->reset_device = adf_reset_flr;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
index 5fc3dbb..92fb6ff 100644
--- a/drivers/crypto/qat/qat_common/Makefile
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -1,12 +1,3 @@
-$(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \
-			     $(obj)/qat_rsapubkey-asn1.h
-$(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \
-			      $(obj)/qat_rsaprivkey-asn1.h
-$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h
-
-clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h
-clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h
-
 obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o
 intel_qat-objs := adf_cfg.o \
 	adf_isr.o \
@@ -20,8 +11,6 @@
 	adf_hw_arbiter.o \
 	qat_crypto.o \
 	qat_algs.o \
-	qat_rsapubkey-asn1.o \
-	qat_rsaprivkey-asn1.o \
 	qat_asym_algs.o \
 	qat_uclo.o \
 	qat_hal.o
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index 5a07208..e882253 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -176,6 +176,7 @@
 	void (*disable_iov)(struct adf_accel_dev *accel_dev);
 	void (*enable_ints)(struct adf_accel_dev *accel_dev);
 	int (*enable_vf2pf_comms)(struct adf_accel_dev *accel_dev);
+	void (*reset_device)(struct adf_accel_dev *accel_dev);
 	const char *fw_name;
 	const char *fw_mmp_name;
 	uint32_t fuses;
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index b40d9c8..2839fcc 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -82,18 +82,12 @@
 	struct work_struct reset_work;
 };
 
-void adf_dev_restore(struct adf_accel_dev *accel_dev)
+void adf_reset_sbr(struct adf_accel_dev *accel_dev)
 {
 	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
 	struct pci_dev *parent = pdev->bus->self;
 	uint16_t bridge_ctl = 0;
 
-	if (accel_dev->is_vf)
-		return;
-
-	dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
-		 accel_dev->accel_id);
-
 	if (!parent)
 		parent = pdev;
 
@@ -101,6 +95,8 @@
 		dev_info(&GET_DEV(accel_dev),
 			 "Transaction still in progress. Proceeding\n");
 
+	dev_info(&GET_DEV(accel_dev), "Secondary bus reset\n");
+
 	pci_read_config_word(parent, PCI_BRIDGE_CONTROL, &bridge_ctl);
 	bridge_ctl |= PCI_BRIDGE_CTL_BUS_RESET;
 	pci_write_config_word(parent, PCI_BRIDGE_CONTROL, bridge_ctl);
@@ -108,8 +104,40 @@
 	bridge_ctl &= ~PCI_BRIDGE_CTL_BUS_RESET;
 	pci_write_config_word(parent, PCI_BRIDGE_CONTROL, bridge_ctl);
 	msleep(100);
-	pci_restore_state(pdev);
-	pci_save_state(pdev);
+}
+EXPORT_SYMBOL_GPL(adf_reset_sbr);
+
+void adf_reset_flr(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	u16 control = 0;
+	int pos = 0;
+
+	dev_info(&GET_DEV(accel_dev), "Function level reset\n");
+	pos = pci_pcie_cap(pdev);
+	if (!pos) {
+		dev_err(&GET_DEV(accel_dev), "Restart device failed\n");
+		return;
+	}
+	pci_read_config_word(pdev, pos + PCI_EXP_DEVCTL, &control);
+	control |= PCI_EXP_DEVCTL_BCR_FLR;
+	pci_write_config_word(pdev, pos + PCI_EXP_DEVCTL, control);
+	msleep(100);
+}
+EXPORT_SYMBOL_GPL(adf_reset_flr);
+
+void adf_dev_restore(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+
+	if (hw_device->reset_device) {
+		dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
+			 accel_dev->accel_id);
+		hw_device->reset_device(accel_dev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
+	}
 }
 
 static void adf_device_reset_worker(struct work_struct *work)
@@ -243,7 +271,8 @@
 
 int adf_init_aer(void)
 {
-	device_reset_wq = create_workqueue("qat_device_reset_wq");
+	device_reset_wq = alloc_workqueue("qat_device_reset_wq",
+					  WQ_MEM_RECLAIM, 0);
 	return !device_reset_wq ? -EFAULT : 0;
 }
 
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 75faa39..980e074 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -141,6 +141,8 @@
 
 int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf);
 void adf_disable_aer(struct adf_accel_dev *accel_dev);
+void adf_reset_sbr(struct adf_accel_dev *accel_dev);
+void adf_reset_flr(struct adf_accel_dev *accel_dev);
 void adf_dev_restore(struct adf_accel_dev *accel_dev);
 int adf_init_aer(void);
 void adf_exit_aer(void);
diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c
index 4a526e2..9320ae1 100644
--- a/drivers/crypto/qat/qat_common/adf_sriov.c
+++ b/drivers/crypto/qat/qat_common/adf_sriov.c
@@ -292,7 +292,7 @@
 int __init adf_init_pf_wq(void)
 {
 	/* Workqueue for PF2VF responses */
-	pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq");
+	pf2vf_resp_wq = alloc_workqueue("qat_pf2vf_resp_wq", WQ_MEM_RECLAIM, 0);
 
 	return !pf2vf_resp_wq ? -ENOMEM : 0;
 }
diff --git a/drivers/crypto/qat/qat_common/adf_vf_isr.c b/drivers/crypto/qat/qat_common/adf_vf_isr.c
index aa689ca..bf99e11 100644
--- a/drivers/crypto/qat/qat_common/adf_vf_isr.c
+++ b/drivers/crypto/qat/qat_common/adf_vf_isr.c
@@ -321,7 +321,7 @@
 
 int __init adf_init_vf_wq(void)
 {
-	adf_vf_stop_wq = create_workqueue("adf_vf_stop_wq");
+	adf_vf_stop_wq = alloc_workqueue("adf_vf_stop_wq", WQ_MEM_RECLAIM, 0);
 
 	return !adf_vf_stop_wq ? -EFAULT : 0;
 }
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 1e8852a8..769148d 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -947,13 +947,13 @@
 	return 0;
 
 out_free_all:
-	memset(ctx->dec_cd, 0, sizeof(*ctx->enc_cd));
-	dma_free_coherent(dev, sizeof(*ctx->enc_cd),
+	memset(ctx->dec_cd, 0, sizeof(*ctx->dec_cd));
+	dma_free_coherent(dev, sizeof(*ctx->dec_cd),
 			  ctx->dec_cd, ctx->dec_cd_paddr);
 	ctx->dec_cd = NULL;
 out_free_enc:
-	memset(ctx->enc_cd, 0, sizeof(*ctx->dec_cd));
-	dma_free_coherent(dev, sizeof(*ctx->dec_cd),
+	memset(ctx->enc_cd, 0, sizeof(*ctx->enc_cd));
+	dma_free_coherent(dev, sizeof(*ctx->enc_cd),
 			  ctx->enc_cd, ctx->enc_cd_paddr);
 	ctx->enc_cd = NULL;
 	return -ENOMEM;
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 05f49d4..0d35dca 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -49,11 +49,12 @@
 #include <crypto/internal/rsa.h>
 #include <crypto/internal/akcipher.h>
 #include <crypto/akcipher.h>
+#include <crypto/kpp.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/dh.h>
 #include <linux/dma-mapping.h>
 #include <linux/fips.h>
 #include <crypto/scatterwalk.h>
-#include "qat_rsapubkey-asn1.h"
-#include "qat_rsaprivkey-asn1.h"
 #include "icp_qat_fw_pke.h"
 #include "adf_accel_devices.h"
 #include "adf_transport.h"
@@ -75,6 +76,14 @@
 			dma_addr_t d;
 			dma_addr_t n;
 		} dec;
+		struct {
+			dma_addr_t c;
+			dma_addr_t p;
+			dma_addr_t q;
+			dma_addr_t dp;
+			dma_addr_t dq;
+			dma_addr_t qinv;
+		} dec_crt;
 		u64 in_tab[8];
 	};
 } __packed __aligned(64);
@@ -95,71 +104,480 @@
 	char *n;
 	char *e;
 	char *d;
+	char *p;
+	char *q;
+	char *dp;
+	char *dq;
+	char *qinv;
 	dma_addr_t dma_n;
 	dma_addr_t dma_e;
 	dma_addr_t dma_d;
+	dma_addr_t dma_p;
+	dma_addr_t dma_q;
+	dma_addr_t dma_dp;
+	dma_addr_t dma_dq;
+	dma_addr_t dma_qinv;
 	unsigned int key_sz;
+	bool crt_mode;
 	struct qat_crypto_instance *inst;
 } __packed __aligned(64);
 
-struct qat_rsa_request {
-	struct qat_rsa_input_params in;
-	struct qat_rsa_output_params out;
+struct qat_dh_input_params {
+	union {
+		struct {
+			dma_addr_t b;
+			dma_addr_t xa;
+			dma_addr_t p;
+		} in;
+		struct {
+			dma_addr_t xa;
+			dma_addr_t p;
+		} in_g2;
+		u64 in_tab[8];
+	};
+} __packed __aligned(64);
+
+struct qat_dh_output_params {
+	union {
+		dma_addr_t r;
+		u64 out_tab[8];
+	};
+} __packed __aligned(64);
+
+struct qat_dh_ctx {
+	char *g;
+	char *xa;
+	char *p;
+	dma_addr_t dma_g;
+	dma_addr_t dma_xa;
+	dma_addr_t dma_p;
+	unsigned int p_size;
+	bool g2;
+	struct qat_crypto_instance *inst;
+} __packed __aligned(64);
+
+struct qat_asym_request {
+	union {
+		struct qat_rsa_input_params rsa;
+		struct qat_dh_input_params dh;
+	} in;
+	union {
+		struct qat_rsa_output_params rsa;
+		struct qat_dh_output_params dh;
+	} out;
 	dma_addr_t phy_in;
 	dma_addr_t phy_out;
 	char *src_align;
 	char *dst_align;
 	struct icp_qat_fw_pke_request req;
-	struct qat_rsa_ctx *ctx;
+	union {
+		struct qat_rsa_ctx *rsa;
+		struct qat_dh_ctx *dh;
+	} ctx;
+	union {
+		struct akcipher_request *rsa;
+		struct kpp_request *dh;
+	} areq;
 	int err;
+	void (*cb)(struct icp_qat_fw_pke_resp *resp);
 } __aligned(64);
 
+static void qat_dh_cb(struct icp_qat_fw_pke_resp *resp)
+{
+	struct qat_asym_request *req = (void *)(__force long)resp->opaque;
+	struct kpp_request *areq = req->areq.dh;
+	struct device *dev = &GET_DEV(req->ctx.dh->inst->accel_dev);
+	int err = ICP_QAT_FW_PKE_RESP_PKE_STAT_GET(
+				resp->pke_resp_hdr.comn_resp_flags);
+
+	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
+
+	if (areq->src) {
+		if (req->src_align)
+			dma_free_coherent(dev, req->ctx.dh->p_size,
+					  req->src_align, req->in.dh.in.b);
+		else
+			dma_unmap_single(dev, req->in.dh.in.b,
+					 req->ctx.dh->p_size, DMA_TO_DEVICE);
+	}
+
+	areq->dst_len = req->ctx.dh->p_size;
+	if (req->dst_align) {
+		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
+					 areq->dst_len, 1);
+
+		dma_free_coherent(dev, req->ctx.dh->p_size, req->dst_align,
+				  req->out.dh.r);
+	} else {
+		dma_unmap_single(dev, req->out.dh.r, req->ctx.dh->p_size,
+				 DMA_FROM_DEVICE);
+	}
+
+	dma_unmap_single(dev, req->phy_in, sizeof(struct qat_dh_input_params),
+			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, req->phy_out,
+			 sizeof(struct qat_dh_output_params),
+			 DMA_TO_DEVICE);
+
+	kpp_request_complete(areq, err);
+}
+
+#define PKE_DH_1536 0x390c1a49
+#define PKE_DH_G2_1536 0x2e0b1a3e
+#define PKE_DH_2048 0x4d0c1a60
+#define PKE_DH_G2_2048 0x3e0b1a55
+#define PKE_DH_3072 0x510c1a77
+#define PKE_DH_G2_3072 0x3a0b1a6c
+#define PKE_DH_4096 0x690c1a8e
+#define PKE_DH_G2_4096 0x4a0b1a83
+
+static unsigned long qat_dh_fn_id(unsigned int len, bool g2)
+{
+	unsigned int bitslen = len << 3;
+
+	switch (bitslen) {
+	case 1536:
+		return g2 ? PKE_DH_G2_1536 : PKE_DH_1536;
+	case 2048:
+		return g2 ? PKE_DH_G2_2048 : PKE_DH_2048;
+	case 3072:
+		return g2 ? PKE_DH_G2_3072 : PKE_DH_3072;
+	case 4096:
+		return g2 ? PKE_DH_G2_4096 : PKE_DH_4096;
+	default:
+		return 0;
+	};
+}
+
+static inline struct qat_dh_ctx *qat_dh_get_params(struct crypto_kpp *tfm)
+{
+	return kpp_tfm_ctx(tfm);
+}
+
+static int qat_dh_compute_value(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	struct qat_asym_request *qat_req =
+			PTR_ALIGN(kpp_request_ctx(req), 64);
+	struct icp_qat_fw_pke_request *msg = &qat_req->req;
+	int ret, ctr = 0;
+	int n_input_params = 0;
+
+	if (unlikely(!ctx->xa))
+		return -EINVAL;
+
+	if (req->dst_len < ctx->p_size) {
+		req->dst_len = ctx->p_size;
+		return -EOVERFLOW;
+	}
+	memset(msg, '\0', sizeof(*msg));
+	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
+					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
+
+	msg->pke_hdr.cd_pars.func_id = qat_dh_fn_id(ctx->p_size,
+						    !req->src && ctx->g2);
+	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
+		return -EINVAL;
+
+	qat_req->cb = qat_dh_cb;
+	qat_req->ctx.dh = ctx;
+	qat_req->areq.dh = req;
+	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
+	msg->pke_hdr.comn_req_flags =
+		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
+					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
+
+	/*
+	 * If no source is provided use g as base
+	 */
+	if (req->src) {
+		qat_req->in.dh.in.xa = ctx->dma_xa;
+		qat_req->in.dh.in.p = ctx->dma_p;
+		n_input_params = 3;
+	} else {
+		if (ctx->g2) {
+			qat_req->in.dh.in_g2.xa = ctx->dma_xa;
+			qat_req->in.dh.in_g2.p = ctx->dma_p;
+			n_input_params = 2;
+		} else {
+			qat_req->in.dh.in.b = ctx->dma_g;
+			qat_req->in.dh.in.xa = ctx->dma_xa;
+			qat_req->in.dh.in.p = ctx->dma_p;
+			n_input_params = 3;
+		}
+	}
+
+	ret = -ENOMEM;
+	if (req->src) {
+		/*
+		 * src can be of any size in valid range, but HW expects it to
+		 * be the same as modulo p so in case it is different we need
+		 * to allocate a new buf and copy src data.
+		 * In other case we just need to map the user provided buffer.
+		 * Also need to make sure that it is in contiguous buffer.
+		 */
+		if (sg_is_last(req->src) && req->src_len == ctx->p_size) {
+			qat_req->src_align = NULL;
+			qat_req->in.dh.in.b = dma_map_single(dev,
+							     sg_virt(req->src),
+							     req->src_len,
+							     DMA_TO_DEVICE);
+			if (unlikely(dma_mapping_error(dev,
+						       qat_req->in.dh.in.b)))
+				return ret;
+
+		} else {
+			int shift = ctx->p_size - req->src_len;
+
+			qat_req->src_align = dma_zalloc_coherent(dev,
+								 ctx->p_size,
+								 &qat_req->in.dh.in.b,
+								 GFP_KERNEL);
+			if (unlikely(!qat_req->src_align))
+				return ret;
+
+			scatterwalk_map_and_copy(qat_req->src_align + shift,
+						 req->src, 0, req->src_len, 0);
+		}
+	}
+	/*
+	 * dst can be of any size in valid range, but HW expects it to be the
+	 * same as modulo m so in case it is different we need to allocate a
+	 * new buf and copy src data.
+	 * In other case we just need to map the user provided buffer.
+	 * Also need to make sure that it is in contiguous buffer.
+	 */
+	if (sg_is_last(req->dst) && req->dst_len == ctx->p_size) {
+		qat_req->dst_align = NULL;
+		qat_req->out.dh.r = dma_map_single(dev, sg_virt(req->dst),
+						   req->dst_len,
+						   DMA_FROM_DEVICE);
+
+		if (unlikely(dma_mapping_error(dev, qat_req->out.dh.r)))
+			goto unmap_src;
+
+	} else {
+		qat_req->dst_align = dma_zalloc_coherent(dev, ctx->p_size,
+							 &qat_req->out.dh.r,
+							 GFP_KERNEL);
+		if (unlikely(!qat_req->dst_align))
+			goto unmap_src;
+	}
+
+	qat_req->in.dh.in_tab[n_input_params] = 0;
+	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),
+					 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),
+					  DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
+		goto unmap_in_params;
+
+	msg->pke_mid.src_data_addr = qat_req->phy_in;
+	msg->pke_mid.dest_data_addr = qat_req->phy_out;
+	msg->pke_mid.opaque = (uint64_t)(__force long)qat_req;
+	msg->input_param_count = n_input_params;
+	msg->output_param_count = 1;
+
+	do {
+		ret = adf_send_message(ctx->inst->pke_tx, (uint32_t *)msg);
+	} while (ret == -EBUSY && ctr++ < 100);
+
+	if (!ret)
+		return -EINPROGRESS;
+
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_dh_output_params),
+				 DMA_TO_DEVICE);
+unmap_in_params:
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_dh_input_params),
+				 DMA_TO_DEVICE);
+unmap_dst:
+	if (qat_req->dst_align)
+		dma_free_coherent(dev, ctx->p_size, qat_req->dst_align,
+				  qat_req->out.dh.r);
+	else
+		if (!dma_mapping_error(dev, qat_req->out.dh.r))
+			dma_unmap_single(dev, qat_req->out.dh.r, ctx->p_size,
+					 DMA_FROM_DEVICE);
+unmap_src:
+	if (req->src) {
+		if (qat_req->src_align)
+			dma_free_coherent(dev, ctx->p_size, qat_req->src_align,
+					  qat_req->in.dh.in.b);
+		else
+			if (!dma_mapping_error(dev, qat_req->in.dh.in.b))
+				dma_unmap_single(dev, qat_req->in.dh.in.b,
+						 ctx->p_size,
+						 DMA_TO_DEVICE);
+	}
+	return ret;
+}
+
+static int qat_dh_check_params_length(unsigned int p_len)
+{
+	switch (p_len) {
+	case 1536:
+	case 2048:
+	case 3072:
+	case 4096:
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int qat_dh_set_params(struct qat_dh_ctx *ctx, struct dh *params)
+{
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+
+	if (unlikely(!params->p || !params->g))
+		return -EINVAL;
+
+	if (qat_dh_check_params_length(params->p_size << 3))
+		return -EINVAL;
+
+	ctx->p_size = params->p_size;
+	ctx->p = dma_zalloc_coherent(dev, ctx->p_size, &ctx->dma_p, GFP_KERNEL);
+	if (!ctx->p)
+		return -ENOMEM;
+	memcpy(ctx->p, params->p, ctx->p_size);
+
+	/* If g equals 2 don't copy it */
+	if (params->g_size == 1 && *(char *)params->g == 0x02) {
+		ctx->g2 = true;
+		return 0;
+	}
+
+	ctx->g = dma_zalloc_coherent(dev, ctx->p_size, &ctx->dma_g, GFP_KERNEL);
+	if (!ctx->g) {
+		dma_free_coherent(dev, ctx->p_size, ctx->p, ctx->dma_p);
+		ctx->p = NULL;
+		return -ENOMEM;
+	}
+	memcpy(ctx->g + (ctx->p_size - params->g_size), params->g,
+	       params->g_size);
+
+	return 0;
+}
+
+static void qat_dh_clear_ctx(struct device *dev, struct qat_dh_ctx *ctx)
+{
+	if (ctx->g) {
+		dma_free_coherent(dev, ctx->p_size, ctx->g, ctx->dma_g);
+		ctx->g = NULL;
+	}
+	if (ctx->xa) {
+		dma_free_coherent(dev, ctx->p_size, ctx->xa, ctx->dma_xa);
+		ctx->xa = NULL;
+	}
+	if (ctx->p) {
+		dma_free_coherent(dev, ctx->p_size, ctx->p, ctx->dma_p);
+		ctx->p = NULL;
+	}
+	ctx->p_size = 0;
+	ctx->g2 = false;
+}
+
+static int qat_dh_set_secret(struct crypto_kpp *tfm, void *buf,
+			     unsigned int len)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+	struct dh params;
+	int ret;
+
+	if (crypto_dh_decode_key(buf, len, &params) < 0)
+		return -EINVAL;
+
+	/* Free old secret if any */
+	qat_dh_clear_ctx(dev, ctx);
+
+	ret = qat_dh_set_params(ctx, &params);
+	if (ret < 0)
+		return ret;
+
+	ctx->xa = dma_zalloc_coherent(dev, ctx->p_size, &ctx->dma_xa,
+				      GFP_KERNEL);
+	if (!ctx->xa) {
+		qat_dh_clear_ctx(dev, ctx);
+		return -ENOMEM;
+	}
+	memcpy(ctx->xa + (ctx->p_size - params.key_size), params.key,
+	       params.key_size);
+
+	return 0;
+}
+
+static int qat_dh_max_size(struct crypto_kpp *tfm)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+
+	return ctx->p ? ctx->p_size : -EINVAL;
+}
+
+static int qat_dh_init_tfm(struct crypto_kpp *tfm)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst =
+			qat_crypto_get_instance_node(get_current_node());
+
+	if (!inst)
+		return -EINVAL;
+
+	ctx->p_size = 0;
+	ctx->g2 = false;
+	ctx->inst = inst;
+	return 0;
+}
+
+static void qat_dh_exit_tfm(struct crypto_kpp *tfm)
+{
+	struct qat_dh_ctx *ctx = kpp_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+
+	qat_dh_clear_ctx(dev, ctx);
+	qat_crypto_put_instance(ctx->inst);
+}
+
 static void qat_rsa_cb(struct icp_qat_fw_pke_resp *resp)
 {
-	struct akcipher_request *areq = (void *)(__force long)resp->opaque;
-	struct qat_rsa_request *req = PTR_ALIGN(akcipher_request_ctx(areq), 64);
-	struct device *dev = &GET_DEV(req->ctx->inst->accel_dev);
+	struct qat_asym_request *req = (void *)(__force long)resp->opaque;
+	struct akcipher_request *areq = req->areq.rsa;
+	struct device *dev = &GET_DEV(req->ctx.rsa->inst->accel_dev);
 	int err = ICP_QAT_FW_PKE_RESP_PKE_STAT_GET(
 				resp->pke_resp_hdr.comn_resp_flags);
 
 	err = (err == ICP_QAT_FW_COMN_STATUS_FLAG_OK) ? 0 : -EINVAL;
 
 	if (req->src_align)
-		dma_free_coherent(dev, req->ctx->key_sz, req->src_align,
-				  req->in.enc.m);
+		dma_free_coherent(dev, req->ctx.rsa->key_sz, req->src_align,
+				  req->in.rsa.enc.m);
 	else
-		dma_unmap_single(dev, req->in.enc.m, req->ctx->key_sz,
+		dma_unmap_single(dev, req->in.rsa.enc.m, req->ctx.rsa->key_sz,
 				 DMA_TO_DEVICE);
 
-	areq->dst_len = req->ctx->key_sz;
+	areq->dst_len = req->ctx.rsa->key_sz;
 	if (req->dst_align) {
-		char *ptr = req->dst_align;
-
-		while (!(*ptr) && areq->dst_len) {
-			areq->dst_len--;
-			ptr++;
-		}
-
-		if (areq->dst_len != req->ctx->key_sz)
-			memmove(req->dst_align, ptr, areq->dst_len);
-
 		scatterwalk_map_and_copy(req->dst_align, areq->dst, 0,
 					 areq->dst_len, 1);
 
-		dma_free_coherent(dev, req->ctx->key_sz, req->dst_align,
-				  req->out.enc.c);
+		dma_free_coherent(dev, req->ctx.rsa->key_sz, req->dst_align,
+				  req->out.rsa.enc.c);
 	} else {
-		char *ptr = sg_virt(areq->dst);
-
-		while (!(*ptr) && areq->dst_len) {
-			areq->dst_len--;
-			ptr++;
-		}
-
-		if (sg_virt(areq->dst) != ptr && areq->dst_len)
-			memmove(sg_virt(areq->dst), ptr, areq->dst_len);
-
-		dma_unmap_single(dev, req->out.enc.c, req->ctx->key_sz,
+		dma_unmap_single(dev, req->out.rsa.enc.c, req->ctx.rsa->key_sz,
 				 DMA_FROM_DEVICE);
 	}
 
@@ -175,8 +593,9 @@
 void qat_alg_asym_callback(void *_resp)
 {
 	struct icp_qat_fw_pke_resp *resp = _resp;
+	struct qat_asym_request *areq = (void *)(__force long)resp->opaque;
 
-	qat_rsa_cb(resp);
+	areq->cb(resp);
 }
 
 #define PKE_RSA_EP_512 0x1c161b21
@@ -237,13 +656,42 @@
 	};
 }
 
+#define PKE_RSA_DP2_512 0x1c131b57
+#define PKE_RSA_DP2_1024 0x26131c2d
+#define PKE_RSA_DP2_1536 0x45111d12
+#define PKE_RSA_DP2_2048 0x59121dfa
+#define PKE_RSA_DP2_3072 0x81121ed9
+#define PKE_RSA_DP2_4096 0xb1111fb2
+
+static unsigned long qat_rsa_dec_fn_id_crt(unsigned int len)
+{
+	unsigned int bitslen = len << 3;
+
+	switch (bitslen) {
+	case 512:
+		return PKE_RSA_DP2_512;
+	case 1024:
+		return PKE_RSA_DP2_1024;
+	case 1536:
+		return PKE_RSA_DP2_1536;
+	case 2048:
+		return PKE_RSA_DP2_2048;
+	case 3072:
+		return PKE_RSA_DP2_3072;
+	case 4096:
+		return PKE_RSA_DP2_4096;
+	default:
+		return 0;
+	};
+}
+
 static int qat_rsa_enc(struct akcipher_request *req)
 {
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
-	struct qat_rsa_request *qat_req =
+	struct qat_asym_request *qat_req =
 			PTR_ALIGN(akcipher_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
 	int ret, ctr = 0;
@@ -262,14 +710,16 @@
 	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
 		return -EINVAL;
 
-	qat_req->ctx = ctx;
+	qat_req->cb = qat_rsa_cb;
+	qat_req->ctx.rsa = ctx;
+	qat_req->areq.rsa = req;
 	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
 	msg->pke_hdr.comn_req_flags =
 		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
 					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
 
-	qat_req->in.enc.e = ctx->dma_e;
-	qat_req->in.enc.n = ctx->dma_n;
+	qat_req->in.rsa.enc.e = ctx->dma_e;
+	qat_req->in.rsa.enc.n = ctx->dma_n;
 	ret = -ENOMEM;
 
 	/*
@@ -281,16 +731,16 @@
 	 */
 	if (sg_is_last(req->src) && req->src_len == ctx->key_sz) {
 		qat_req->src_align = NULL;
-		qat_req->in.enc.m = dma_map_single(dev, sg_virt(req->src),
+		qat_req->in.rsa.enc.m = dma_map_single(dev, sg_virt(req->src),
 						   req->src_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(dev, qat_req->in.enc.m)))
+		if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.enc.m)))
 			return ret;
 
 	} else {
 		int shift = ctx->key_sz - req->src_len;
 
 		qat_req->src_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->in.enc.m,
+							 &qat_req->in.rsa.enc.m,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->src_align))
 			return ret;
@@ -300,30 +750,30 @@
 	}
 	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
 		qat_req->dst_align = NULL;
-		qat_req->out.enc.c = dma_map_single(dev, sg_virt(req->dst),
-						    req->dst_len,
-						    DMA_FROM_DEVICE);
+		qat_req->out.rsa.enc.c = dma_map_single(dev, sg_virt(req->dst),
+							req->dst_len,
+							DMA_FROM_DEVICE);
 
-		if (unlikely(dma_mapping_error(dev, qat_req->out.enc.c)))
+		if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.enc.c)))
 			goto unmap_src;
 
 	} else {
 		qat_req->dst_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->out.enc.c,
+							 &qat_req->out.rsa.enc.c,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
 
 	}
-	qat_req->in.in_tab[3] = 0;
-	qat_req->out.out_tab[1] = 0;
-	qat_req->phy_in = dma_map_single(dev, &qat_req->in.enc.m,
+	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),
 					 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.enc.c,
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.enc.c,
 					  sizeof(struct qat_rsa_output_params),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
@@ -331,7 +781,7 @@
 
 	msg->pke_mid.src_data_addr = qat_req->phy_in;
 	msg->pke_mid.dest_data_addr = qat_req->phy_out;
-	msg->pke_mid.opaque = (uint64_t)(__force long)req;
+	msg->pke_mid.opaque = (uint64_t)(__force long)qat_req;
 	msg->input_param_count = 3;
 	msg->output_param_count = 1;
 	do {
@@ -353,19 +803,19 @@
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
-				  qat_req->out.enc.c);
+				  qat_req->out.rsa.enc.c);
 	else
-		if (!dma_mapping_error(dev, qat_req->out.enc.c))
-			dma_unmap_single(dev, qat_req->out.enc.c, ctx->key_sz,
-					 DMA_FROM_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->out.rsa.enc.c))
+			dma_unmap_single(dev, qat_req->out.rsa.enc.c,
+					 ctx->key_sz, DMA_FROM_DEVICE);
 unmap_src:
 	if (qat_req->src_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.enc.m);
+				  qat_req->in.rsa.enc.m);
 	else
-		if (!dma_mapping_error(dev, qat_req->in.enc.m))
-			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
-					 DMA_TO_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->in.rsa.enc.m))
+			dma_unmap_single(dev, qat_req->in.rsa.enc.m,
+					 ctx->key_sz, DMA_TO_DEVICE);
 	return ret;
 }
 
@@ -375,7 +825,7 @@
 	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
-	struct qat_rsa_request *qat_req =
+	struct qat_asym_request *qat_req =
 			PTR_ALIGN(akcipher_request_ctx(req), 64);
 	struct icp_qat_fw_pke_request *msg = &qat_req->req;
 	int ret, ctr = 0;
@@ -390,18 +840,30 @@
 	memset(msg, '\0', sizeof(*msg));
 	ICP_QAT_FW_PKE_HDR_VALID_FLAG_SET(msg->pke_hdr,
 					  ICP_QAT_FW_COMN_REQ_FLAG_SET);
-	msg->pke_hdr.cd_pars.func_id = qat_rsa_dec_fn_id(ctx->key_sz);
+	msg->pke_hdr.cd_pars.func_id = ctx->crt_mode ?
+		qat_rsa_dec_fn_id_crt(ctx->key_sz) :
+		qat_rsa_dec_fn_id(ctx->key_sz);
 	if (unlikely(!msg->pke_hdr.cd_pars.func_id))
 		return -EINVAL;
 
-	qat_req->ctx = ctx;
+	qat_req->cb = qat_rsa_cb;
+	qat_req->ctx.rsa = ctx;
+	qat_req->areq.rsa = req;
 	msg->pke_hdr.service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_PKE;
 	msg->pke_hdr.comn_req_flags =
 		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_PTR_TYPE_FLAT,
 					    QAT_COMN_CD_FLD_TYPE_64BIT_ADR);
 
-	qat_req->in.dec.d = ctx->dma_d;
-	qat_req->in.dec.n = ctx->dma_n;
+	if (ctx->crt_mode) {
+		qat_req->in.rsa.dec_crt.p = ctx->dma_p;
+		qat_req->in.rsa.dec_crt.q = ctx->dma_q;
+		qat_req->in.rsa.dec_crt.dp = ctx->dma_dp;
+		qat_req->in.rsa.dec_crt.dq = ctx->dma_dq;
+		qat_req->in.rsa.dec_crt.qinv = ctx->dma_qinv;
+	} else {
+		qat_req->in.rsa.dec.d = ctx->dma_d;
+		qat_req->in.rsa.dec.n = ctx->dma_n;
+	}
 	ret = -ENOMEM;
 
 	/*
@@ -413,16 +875,16 @@
 	 */
 	if (sg_is_last(req->src) && req->src_len == ctx->key_sz) {
 		qat_req->src_align = NULL;
-		qat_req->in.dec.c = dma_map_single(dev, sg_virt(req->src),
+		qat_req->in.rsa.dec.c = dma_map_single(dev, sg_virt(req->src),
 						   req->dst_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(dev, qat_req->in.dec.c)))
+		if (unlikely(dma_mapping_error(dev, qat_req->in.rsa.dec.c)))
 			return ret;
 
 	} else {
 		int shift = ctx->key_sz - req->src_len;
 
 		qat_req->src_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->in.dec.c,
+							 &qat_req->in.rsa.dec.c,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->src_align))
 			return ret;
@@ -432,31 +894,34 @@
 	}
 	if (sg_is_last(req->dst) && req->dst_len == ctx->key_sz) {
 		qat_req->dst_align = NULL;
-		qat_req->out.dec.m = dma_map_single(dev, sg_virt(req->dst),
+		qat_req->out.rsa.dec.m = dma_map_single(dev, sg_virt(req->dst),
 						    req->dst_len,
 						    DMA_FROM_DEVICE);
 
-		if (unlikely(dma_mapping_error(dev, qat_req->out.dec.m)))
+		if (unlikely(dma_mapping_error(dev, qat_req->out.rsa.dec.m)))
 			goto unmap_src;
 
 	} else {
 		qat_req->dst_align = dma_zalloc_coherent(dev, ctx->key_sz,
-							 &qat_req->out.dec.m,
+							 &qat_req->out.rsa.dec.m,
 							 GFP_KERNEL);
 		if (unlikely(!qat_req->dst_align))
 			goto unmap_src;
 
 	}
 
-	qat_req->in.in_tab[3] = 0;
-	qat_req->out.out_tab[1] = 0;
-	qat_req->phy_in = dma_map_single(dev, &qat_req->in.dec.c,
+	if (ctx->crt_mode)
+		qat_req->in.rsa.in_tab[6] = 0;
+	else
+		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),
 					 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.dec.m,
+	qat_req->phy_out = dma_map_single(dev, &qat_req->out.rsa.dec.m,
 					  sizeof(struct qat_rsa_output_params),
 					  DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, qat_req->phy_out)))
@@ -464,8 +929,12 @@
 
 	msg->pke_mid.src_data_addr = qat_req->phy_in;
 	msg->pke_mid.dest_data_addr = qat_req->phy_out;
-	msg->pke_mid.opaque = (uint64_t)(__force long)req;
-	msg->input_param_count = 3;
+	msg->pke_mid.opaque = (uint64_t)(__force long)qat_req;
+	if (ctx->crt_mode)
+		msg->input_param_count = 6;
+	else
+		msg->input_param_count = 3;
+
 	msg->output_param_count = 1;
 	do {
 		ret = adf_send_message(ctx->inst->pke_tx, (uint32_t *)msg);
@@ -486,26 +955,24 @@
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
-				  qat_req->out.dec.m);
+				  qat_req->out.rsa.dec.m);
 	else
-		if (!dma_mapping_error(dev, qat_req->out.dec.m))
-			dma_unmap_single(dev, qat_req->out.dec.m, ctx->key_sz,
-					 DMA_FROM_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->out.rsa.dec.m))
+			dma_unmap_single(dev, qat_req->out.rsa.dec.m,
+					 ctx->key_sz, DMA_FROM_DEVICE);
 unmap_src:
 	if (qat_req->src_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.dec.c);
+				  qat_req->in.rsa.dec.c);
 	else
-		if (!dma_mapping_error(dev, qat_req->in.dec.c))
-			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
-					 DMA_TO_DEVICE);
+		if (!dma_mapping_error(dev, qat_req->in.rsa.dec.c))
+			dma_unmap_single(dev, qat_req->in.rsa.dec.c,
+					 ctx->key_sz, DMA_TO_DEVICE);
 	return ret;
 }
 
-int qat_rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
-		  const void *value, size_t vlen)
+int qat_rsa_set_n(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 {
-	struct qat_rsa_ctx *ctx = context;
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
 	const char *ptr = value;
@@ -518,11 +985,6 @@
 
 	ctx->key_sz = vlen;
 	ret = -EINVAL;
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (ctx->key_sz != 256 && ctx->key_sz != 384)) {
-		pr_err("QAT: RSA: key size not allowed in FIPS mode\n");
-		goto err;
-	}
 	/* invalid key size provided */
 	if (!qat_rsa_enc_fn_id(ctx->key_sz))
 		goto err;
@@ -540,10 +1002,8 @@
 	return ret;
 }
 
-int qat_rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
-		  const void *value, size_t vlen)
+int qat_rsa_set_e(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 {
-	struct qat_rsa_ctx *ctx = context;
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
 	const char *ptr = value;
@@ -559,18 +1019,15 @@
 	}
 
 	ctx->e = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_e, GFP_KERNEL);
-	if (!ctx->e) {
-		ctx->e = NULL;
+	if (!ctx->e)
 		return -ENOMEM;
-	}
+
 	memcpy(ctx->e + (ctx->key_sz - vlen), ptr, vlen);
 	return 0;
 }
 
-int qat_rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
-		  const void *value, size_t vlen)
+int qat_rsa_set_d(struct qat_rsa_ctx *ctx, const char *value, size_t vlen)
 {
-	struct qat_rsa_ctx *ctx = context;
 	struct qat_crypto_instance *inst = ctx->inst;
 	struct device *dev = &GET_DEV(inst->accel_dev);
 	const char *ptr = value;
@@ -585,12 +1042,6 @@
 	if (!ctx->key_sz || !vlen || vlen > ctx->key_sz)
 		goto err;
 
-	/* In FIPS mode only allow key size 2K & 3K */
-	if (fips_enabled && (vlen != 256 && vlen != 384)) {
-		pr_err("QAT: RSA: key size not allowed in FIPS mode\n");
-		goto err;
-	}
-
 	ret = -ENOMEM;
 	ctx->d = dma_zalloc_coherent(dev, ctx->key_sz, &ctx->dma_d, GFP_KERNEL);
 	if (!ctx->d)
@@ -603,12 +1054,106 @@
 	return ret;
 }
 
-static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
-			  unsigned int keylen, bool private)
+static void qat_rsa_drop_leading_zeros(const char **ptr, unsigned int *len)
 {
-	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
-	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
-	int ret;
+	while (!**ptr && *len) {
+		(*ptr)++;
+		(*len)--;
+	}
+}
+
+static void qat_rsa_setkey_crt(struct qat_rsa_ctx *ctx, struct rsa_key *rsa_key)
+{
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	const char *ptr;
+	unsigned int len;
+	unsigned int half_key_sz = ctx->key_sz / 2;
+
+	/* p */
+	ptr = rsa_key->p;
+	len = rsa_key->p_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto err;
+	ctx->p = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_p, GFP_KERNEL);
+	if (!ctx->p)
+		goto err;
+	memcpy(ctx->p + (half_key_sz - len), ptr, len);
+
+	/* q */
+	ptr = rsa_key->q;
+	len = rsa_key->q_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_p;
+	ctx->q = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_q, GFP_KERNEL);
+	if (!ctx->q)
+		goto free_p;
+	memcpy(ctx->q + (half_key_sz - len), ptr, len);
+
+	/* dp */
+	ptr = rsa_key->dp;
+	len = rsa_key->dp_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_q;
+	ctx->dp = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_dp,
+				      GFP_KERNEL);
+	if (!ctx->dp)
+		goto free_q;
+	memcpy(ctx->dp + (half_key_sz - len), ptr, len);
+
+	/* dq */
+	ptr = rsa_key->dq;
+	len = rsa_key->dq_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_dp;
+	ctx->dq = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_dq,
+				      GFP_KERNEL);
+	if (!ctx->dq)
+		goto free_dp;
+	memcpy(ctx->dq + (half_key_sz - len), ptr, len);
+
+	/* qinv */
+	ptr = rsa_key->qinv;
+	len = rsa_key->qinv_sz;
+	qat_rsa_drop_leading_zeros(&ptr, &len);
+	if (!len)
+		goto free_dq;
+	ctx->qinv = dma_zalloc_coherent(dev, half_key_sz, &ctx->dma_qinv,
+					GFP_KERNEL);
+	if (!ctx->qinv)
+		goto free_dq;
+	memcpy(ctx->qinv + (half_key_sz - len), ptr, len);
+
+	ctx->crt_mode = true;
+	return;
+
+free_dq:
+	memset(ctx->dq, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->dq, ctx->dma_dq);
+	ctx->dq = NULL;
+free_dp:
+	memset(ctx->dp, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->dp, ctx->dma_dp);
+	ctx->dp = NULL;
+free_q:
+	memset(ctx->q, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->q, ctx->dma_q);
+	ctx->q = NULL;
+free_p:
+	memset(ctx->p, '\0', half_key_sz);
+	dma_free_coherent(dev, half_key_sz, ctx->p, ctx->dma_p);
+	ctx->p = NULL;
+err:
+	ctx->crt_mode = false;
+}
+
+static void qat_rsa_clear_ctx(struct device *dev, struct qat_rsa_ctx *ctx)
+{
+	unsigned int half_key_sz = ctx->key_sz / 2;
 
 	/* Free the old key if any */
 	if (ctx->n)
@@ -619,20 +1164,69 @@
 		memset(ctx->d, '\0', ctx->key_sz);
 		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
 	}
+	if (ctx->p) {
+		memset(ctx->p, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->p, ctx->dma_p);
+	}
+	if (ctx->q) {
+		memset(ctx->q, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->q, ctx->dma_q);
+	}
+	if (ctx->dp) {
+		memset(ctx->dp, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->dp, ctx->dma_dp);
+	}
+	if (ctx->dq) {
+		memset(ctx->dq, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->dq, ctx->dma_dq);
+	}
+	if (ctx->qinv) {
+		memset(ctx->qinv, '\0', half_key_sz);
+		dma_free_coherent(dev, half_key_sz, ctx->qinv, ctx->dma_qinv);
+	}
 
 	ctx->n = NULL;
 	ctx->e = NULL;
 	ctx->d = NULL;
+	ctx->p = NULL;
+	ctx->q = NULL;
+	ctx->dp = NULL;
+	ctx->dq = NULL;
+	ctx->qinv = NULL;
+	ctx->crt_mode = false;
+	ctx->key_sz = 0;
+}
+
+static int qat_rsa_setkey(struct crypto_akcipher *tfm, const void *key,
+			  unsigned int keylen, bool private)
+{
+	struct qat_rsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	struct device *dev = &GET_DEV(ctx->inst->accel_dev);
+	struct rsa_key rsa_key;
+	int ret;
+
+	qat_rsa_clear_ctx(dev, ctx);
 
 	if (private)
-		ret = asn1_ber_decoder(&qat_rsaprivkey_decoder, ctx, key,
-				       keylen);
+		ret = rsa_parse_priv_key(&rsa_key, key, keylen);
 	else
-		ret = asn1_ber_decoder(&qat_rsapubkey_decoder, ctx, key,
-				       keylen);
+		ret = rsa_parse_pub_key(&rsa_key, key, keylen);
 	if (ret < 0)
 		goto free;
 
+	ret = qat_rsa_set_n(ctx, rsa_key.n, rsa_key.n_sz);
+	if (ret < 0)
+		goto free;
+	ret = qat_rsa_set_e(ctx, rsa_key.e, rsa_key.e_sz);
+	if (ret < 0)
+		goto free;
+	if (private) {
+		ret = qat_rsa_set_d(ctx, rsa_key.d, rsa_key.d_sz);
+		if (ret < 0)
+			goto free;
+		qat_rsa_setkey_crt(ctx, &rsa_key);
+	}
+
 	if (!ctx->n || !ctx->e) {
 		/* invalid key provided */
 		ret = -EINVAL;
@@ -646,20 +1240,7 @@
 
 	return 0;
 free:
-	if (ctx->d) {
-		memset(ctx->d, '\0', ctx->key_sz);
-		dma_free_coherent(dev, ctx->key_sz, ctx->d, ctx->dma_d);
-		ctx->d = NULL;
-	}
-	if (ctx->e) {
-		dma_free_coherent(dev, ctx->key_sz, ctx->e, ctx->dma_e);
-		ctx->e = NULL;
-	}
-	if (ctx->n) {
-		dma_free_coherent(dev, ctx->key_sz, ctx->n, ctx->dma_n);
-		ctx->n = NULL;
-		ctx->key_sz = 0;
-	}
+	qat_rsa_clear_ctx(dev, ctx);
 	return ret;
 }
 
@@ -725,7 +1306,7 @@
 	.max_size = qat_rsa_max_size,
 	.init = qat_rsa_init_tfm,
 	.exit = qat_rsa_exit_tfm,
-	.reqsize = sizeof(struct qat_rsa_request) + 64,
+	.reqsize = sizeof(struct qat_asym_request) + 64,
 	.base = {
 		.cra_name = "rsa",
 		.cra_driver_name = "qat-rsa",
@@ -735,6 +1316,23 @@
 	},
 };
 
+static struct kpp_alg dh = {
+	.set_secret = qat_dh_set_secret,
+	.generate_public_key = qat_dh_compute_value,
+	.compute_shared_secret = qat_dh_compute_value,
+	.max_size = qat_dh_max_size,
+	.init = qat_dh_init_tfm,
+	.exit = qat_dh_exit_tfm,
+	.reqsize = sizeof(struct qat_asym_request) + 64,
+	.base = {
+		.cra_name = "dh",
+		.cra_driver_name = "qat-dh",
+		.cra_priority = 1000,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct qat_dh_ctx),
+	},
+};
+
 int qat_asym_algs_register(void)
 {
 	int ret = 0;
@@ -743,7 +1341,11 @@
 	if (++active_devs == 1) {
 		rsa.base.cra_flags = 0;
 		ret = crypto_register_akcipher(&rsa);
+		if (ret)
+			goto unlock;
+		ret = crypto_register_kpp(&dh);
 	}
+unlock:
 	mutex_unlock(&algs_lock);
 	return ret;
 }
@@ -751,7 +1353,9 @@
 void qat_asym_algs_unregister(void)
 {
 	mutex_lock(&algs_lock);
-	if (--active_devs == 0)
+	if (--active_devs == 0) {
 		crypto_unregister_akcipher(&rsa);
+		crypto_unregister_kpp(&dh);
+	}
 	mutex_unlock(&algs_lock);
 }
diff --git a/drivers/crypto/qat/qat_common/qat_rsaprivkey.asn1 b/drivers/crypto/qat/qat_common/qat_rsaprivkey.asn1
deleted file mode 100644
index f0066ad..0000000
--- a/drivers/crypto/qat/qat_common/qat_rsaprivkey.asn1
+++ /dev/null
@@ -1,11 +0,0 @@
-RsaPrivKey ::= SEQUENCE {
-	version		INTEGER,
-	n		INTEGER ({ qat_rsa_get_n }),
-	e		INTEGER ({ qat_rsa_get_e }),
-	d		INTEGER ({ qat_rsa_get_d }),
-	prime1		INTEGER,
-	prime2		INTEGER,
-	exponent1	INTEGER,
-	exponent2	INTEGER,
-	coefficient	INTEGER
-}
diff --git a/drivers/crypto/qat/qat_common/qat_rsapubkey.asn1 b/drivers/crypto/qat/qat_common/qat_rsapubkey.asn1
deleted file mode 100644
index bd667b3..0000000
--- a/drivers/crypto/qat/qat_common/qat_rsapubkey.asn1
+++ /dev/null
@@ -1,4 +0,0 @@
-RsaPubKey ::= SEQUENCE {
-	n INTEGER ({ qat_rsa_get_n }),
-	e INTEGER ({ qat_rsa_get_e })
-}
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 6e1d5e1..1dfcab3 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -252,6 +252,7 @@
 	hw_data->get_arb_mapping = adf_get_arbiter_mapping;
 	hw_data->enable_ints = adf_enable_ints;
 	hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
+	hw_data->reset_device = adf_reset_sbr;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
 }
 
diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/ablkcipher.c
index dbcbbe2..b04b42f 100644
--- a/drivers/crypto/qce/ablkcipher.c
+++ b/drivers/crypto/qce/ablkcipher.c
@@ -15,8 +15,8 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <crypto/aes.h>
-#include <crypto/algapi.h>
 #include <crypto/des.h>
+#include <crypto/internal/skcipher.h>
 
 #include "cipher.h"
 
@@ -189,7 +189,7 @@
 	memcpy(ctx->enc_key, key, keylen);
 	return 0;
 fallback:
-	ret = crypto_ablkcipher_setkey(ctx->fallback, key, keylen);
+	ret = crypto_skcipher_setkey(ctx->fallback, key, keylen);
 	if (!ret)
 		ctx->enc_keylen = keylen;
 	return ret;
@@ -212,10 +212,16 @@
 
 	if (IS_AES(rctx->flags) && ctx->enc_keylen != AES_KEYSIZE_128 &&
 	    ctx->enc_keylen != AES_KEYSIZE_256) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		ret = encrypt ? crypto_ablkcipher_encrypt(req) :
-				crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		ret = encrypt ? crypto_skcipher_encrypt(subreq) :
+				crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return ret;
 	}
 
@@ -239,10 +245,9 @@
 	memset(ctx, 0, sizeof(*ctx));
 	tfm->crt_ablkcipher.reqsize = sizeof(struct qce_cipher_reqctx);
 
-	ctx->fallback = crypto_alloc_ablkcipher(crypto_tfm_alg_name(tfm),
-						CRYPTO_ALG_TYPE_ABLKCIPHER,
-						CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_NEED_FALLBACK);
+	ctx->fallback = crypto_alloc_skcipher(crypto_tfm_alg_name(tfm), 0,
+					      CRYPTO_ALG_ASYNC |
+					      CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(ctx->fallback))
 		return PTR_ERR(ctx->fallback);
 
@@ -253,7 +258,7 @@
 {
 	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	crypto_free_ablkcipher(ctx->fallback);
+	crypto_free_skcipher(ctx->fallback);
 }
 
 struct qce_ablkcipher_def {
diff --git a/drivers/crypto/qce/cipher.h b/drivers/crypto/qce/cipher.h
index 5c6a5f8..2b0278b 100644
--- a/drivers/crypto/qce/cipher.h
+++ b/drivers/crypto/qce/cipher.h
@@ -22,7 +22,7 @@
 struct qce_cipher_ctx {
 	u8 enc_key[QCE_MAX_KEY_SIZE];
 	unsigned int enc_keylen;
-	struct crypto_ablkcipher *fallback;
+	struct crypto_skcipher *fallback;
 };
 
 /**
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 2b3a0cf..dce1af0 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -155,43 +155,43 @@
  * expansion of its usage.
  */
 struct samsung_aes_variant {
-	unsigned int		    aes_offset;
+	unsigned int			aes_offset;
 };
 
 struct s5p_aes_reqctx {
-	unsigned long mode;
+	unsigned long			mode;
 };
 
 struct s5p_aes_ctx {
-	struct s5p_aes_dev         *dev;
+	struct s5p_aes_dev		*dev;
 
-	uint8_t                     aes_key[AES_MAX_KEY_SIZE];
-	uint8_t                     nonce[CTR_RFC3686_NONCE_SIZE];
-	int                         keylen;
+	uint8_t				aes_key[AES_MAX_KEY_SIZE];
+	uint8_t				nonce[CTR_RFC3686_NONCE_SIZE];
+	int				keylen;
 };
 
 struct s5p_aes_dev {
-	struct device              *dev;
-	struct clk                 *clk;
-	void __iomem               *ioaddr;
-	void __iomem               *aes_ioaddr;
-	int                         irq_fc;
+	struct device			*dev;
+	struct clk			*clk;
+	void __iomem			*ioaddr;
+	void __iomem			*aes_ioaddr;
+	int				irq_fc;
 
-	struct ablkcipher_request  *req;
-	struct s5p_aes_ctx         *ctx;
-	struct scatterlist         *sg_src;
-	struct scatterlist         *sg_dst;
+	struct ablkcipher_request	*req;
+	struct s5p_aes_ctx		*ctx;
+	struct scatterlist		*sg_src;
+	struct scatterlist		*sg_dst;
 
 	/* In case of unaligned access: */
-	struct scatterlist         *sg_src_cpy;
-	struct scatterlist         *sg_dst_cpy;
+	struct scatterlist		*sg_src_cpy;
+	struct scatterlist		*sg_dst_cpy;
 
-	struct tasklet_struct       tasklet;
-	struct crypto_queue         queue;
-	bool                        busy;
-	spinlock_t                  lock;
+	struct tasklet_struct		tasklet;
+	struct crypto_queue		queue;
+	bool				busy;
+	spinlock_t			lock;
 
-	struct samsung_aes_variant *variant;
+	struct samsung_aes_variant	*variant;
 };
 
 static struct s5p_aes_dev *s5p_dev;
@@ -421,11 +421,11 @@
 static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 {
 	struct platform_device *pdev = dev_id;
-	struct s5p_aes_dev     *dev  = platform_get_drvdata(pdev);
-	uint32_t                status;
-	unsigned long           flags;
-	bool			set_dma_tx = false;
-	bool			set_dma_rx = false;
+	struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
+	bool set_dma_tx = false;
+	bool set_dma_rx = false;
+	unsigned long flags;
+	uint32_t status;
 
 	spin_lock_irqsave(&dev->lock, flags);
 
@@ -538,10 +538,10 @@
 
 static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 {
-	struct ablkcipher_request  *req = dev->req;
-	uint32_t                    aes_control;
-	int                         err;
-	unsigned long               flags;
+	struct ablkcipher_request *req = dev->req;
+	uint32_t aes_control;
+	unsigned long flags;
+	int err;
 
 	aes_control = SSS_AES_KEY_CHANGE_MODE;
 	if (mode & FLAGS_AES_DECRYPT)
@@ -653,10 +653,10 @@
 
 static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 {
-	struct crypto_ablkcipher   *tfm    = crypto_ablkcipher_reqtfm(req);
-	struct s5p_aes_ctx         *ctx    = crypto_ablkcipher_ctx(tfm);
-	struct s5p_aes_reqctx      *reqctx = ablkcipher_request_ctx(req);
-	struct s5p_aes_dev         *dev    = ctx->dev;
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct s5p_aes_reqctx *reqctx = ablkcipher_request_ctx(req);
+	struct s5p_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct s5p_aes_dev *dev = ctx->dev;
 
 	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
 		dev_err(dev->dev, "request size is not exact amount of AES blocks\n");
@@ -671,7 +671,7 @@
 static int s5p_aes_setkey(struct crypto_ablkcipher *cipher,
 			  const uint8_t *key, unsigned int keylen)
 {
-	struct crypto_tfm  *tfm = crypto_ablkcipher_tfm(cipher);
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
 	struct s5p_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (keylen != AES_KEYSIZE_128 &&
@@ -763,11 +763,11 @@
 
 static int s5p_aes_probe(struct platform_device *pdev)
 {
-	int                 i, j, err = -ENODEV;
-	struct s5p_aes_dev *pdata;
-	struct device      *dev = &pdev->dev;
-	struct resource    *res;
+	struct device *dev = &pdev->dev;
+	int i, j, err = -ENODEV;
 	struct samsung_aes_variant *variant;
+	struct s5p_aes_dev *pdata;
+	struct resource *res;
 
 	if (s5p_dev)
 		return -EEXIST;
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index c3f3d89..0c49956 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -14,10 +14,9 @@
  * Based on omap-aes.c and tegra-aes.c
  */
 
-#include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/hash.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/sha.h>
 
@@ -150,10 +149,7 @@
 	/* AES-specific context */
 	int keylen;
 	u8 key[AES_KEYSIZE_128];
-	struct crypto_ablkcipher *fallback;
-
-	/* SHA-specific context */
-	struct crypto_shash *shash_fallback;
+	struct crypto_skcipher *fallback;
 };
 
 struct sahara_aes_reqctx {
@@ -620,25 +616,21 @@
 		return 0;
 	}
 
-	if (keylen != AES_KEYSIZE_128 &&
-	    keylen != AES_KEYSIZE_192 && keylen != AES_KEYSIZE_256)
+	if (keylen != AES_KEYSIZE_192 && keylen != AES_KEYSIZE_256)
 		return -EINVAL;
 
 	/*
 	 * The requested key size is not supported by HW, do a fallback.
 	 */
-	ctx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	ctx->fallback->base.crt_flags |=
-		(tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_clear_flags(ctx->fallback, CRYPTO_TFM_REQ_MASK);
+	crypto_skcipher_set_flags(ctx->fallback, tfm->base.crt_flags &
+						 CRYPTO_TFM_REQ_MASK);
 
-	ret = crypto_ablkcipher_setkey(ctx->fallback, key, keylen);
-	if (ret) {
-		struct crypto_tfm *tfm_aux = crypto_ablkcipher_tfm(tfm);
+	ret = crypto_skcipher_setkey(ctx->fallback, key, keylen);
 
-		tfm_aux->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm_aux->crt_flags |=
-			(ctx->fallback->base.crt_flags & CRYPTO_TFM_RES_MASK);
-	}
+	tfm->base.crt_flags &= ~CRYPTO_TFM_RES_MASK;
+	tfm->base.crt_flags |= crypto_skcipher_get_flags(ctx->fallback) &
+			       CRYPTO_TFM_RES_MASK;
 	return ret;
 }
 
@@ -670,16 +662,20 @@
 
 static int sahara_aes_ecb_encrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_encrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_encrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -688,16 +684,20 @@
 
 static int sahara_aes_ecb_decrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -706,16 +706,20 @@
 
 static int sahara_aes_cbc_encrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_encrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_encrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -724,16 +728,20 @@
 
 static int sahara_aes_cbc_decrypt(struct ablkcipher_request *req)
 {
-	struct crypto_tfm *tfm =
-		crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
 	struct sahara_ctx *ctx = crypto_ablkcipher_ctx(
 		crypto_ablkcipher_reqtfm(req));
 	int err;
 
 	if (unlikely(ctx->keylen != AES_KEYSIZE_128)) {
-		ablkcipher_request_set_tfm(req, ctx->fallback);
-		err = crypto_ablkcipher_decrypt(req);
-		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
+
+		skcipher_request_set_tfm(subreq, ctx->fallback);
+		skcipher_request_set_callback(subreq, req->base.flags,
+					      NULL, NULL);
+		skcipher_request_set_crypt(subreq, req->src, req->dst,
+					   req->nbytes, req->info);
+		err = crypto_skcipher_decrypt(subreq);
+		skcipher_request_zero(subreq);
 		return err;
 	}
 
@@ -745,8 +753,9 @@
 	const char *name = crypto_tfm_alg_name(tfm);
 	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	ctx->fallback = crypto_alloc_ablkcipher(name, 0,
-				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+	ctx->fallback = crypto_alloc_skcipher(name, 0,
+					      CRYPTO_ALG_ASYNC |
+					      CRYPTO_ALG_NEED_FALLBACK);
 	if (IS_ERR(ctx->fallback)) {
 		pr_err("Error allocating fallback algo %s\n", name);
 		return PTR_ERR(ctx->fallback);
@@ -761,9 +770,7 @@
 {
 	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (ctx->fallback)
-		crypto_free_ablkcipher(ctx->fallback);
-	ctx->fallback = NULL;
+	crypto_free_skcipher(ctx->fallback);
 }
 
 static u32 sahara_sha_init_hdr(struct sahara_dev *dev,
@@ -1180,15 +1187,6 @@
 
 static int sahara_sha_cra_init(struct crypto_tfm *tfm)
 {
-	const char *name = crypto_tfm_alg_name(tfm);
-	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	ctx->shash_fallback = crypto_alloc_shash(name, 0,
-					CRYPTO_ALG_NEED_FALLBACK);
-	if (IS_ERR(ctx->shash_fallback)) {
-		pr_err("Error allocating fallback algo %s\n", name);
-		return PTR_ERR(ctx->shash_fallback);
-	}
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
 				 sizeof(struct sahara_sha_reqctx) +
 				 SHA_BUFFER_LEN + SHA256_BLOCK_SIZE);
@@ -1196,14 +1194,6 @@
 	return 0;
 }
 
-static void sahara_sha_cra_exit(struct crypto_tfm *tfm)
-{
-	struct sahara_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_shash(ctx->shash_fallback);
-	ctx->shash_fallback = NULL;
-}
-
 static struct crypto_alg aes_algs[] = {
 {
 	.cra_name		= "ecb(aes)",
@@ -1272,7 +1262,6 @@
 		.cra_alignmask		= 0,
 		.cra_module		= THIS_MODULE,
 		.cra_init		= sahara_sha_cra_init,
-		.cra_exit		= sahara_sha_cra_exit,
 	}
 },
 };
@@ -1300,7 +1289,6 @@
 		.cra_alignmask		= 0,
 		.cra_module		= THIS_MODULE,
 		.cra_init		= sahara_sha_cra_init,
-		.cra_exit		= sahara_sha_cra_exit,
 	}
 },
 };
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index b7ee8d3..0418a2f 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -91,10 +91,17 @@
 		return be16_to_cpu(ptr->len);
 }
 
-static void to_talitos_ptr_extent_clear(struct talitos_ptr *ptr, bool is_sec1)
+static void to_talitos_ptr_ext_set(struct talitos_ptr *ptr, u8 val,
+				   bool is_sec1)
 {
 	if (!is_sec1)
-		ptr->j_extent = 0;
+		ptr->j_extent = val;
+}
+
+static void to_talitos_ptr_ext_or(struct talitos_ptr *ptr, u8 val, bool is_sec1)
+{
+	if (!is_sec1)
+		ptr->j_extent |= val;
 }
 
 /*
@@ -111,7 +118,7 @@
 
 	to_talitos_ptr_len(ptr, len, is_sec1);
 	to_talitos_ptr(ptr, dma_addr, is_sec1);
-	to_talitos_ptr_extent_clear(ptr, is_sec1);
+	to_talitos_ptr_ext_set(ptr, 0, is_sec1);
 }
 
 /*
@@ -804,6 +811,11 @@
  * crypto alg
  */
 #define TALITOS_CRA_PRIORITY		3000
+/*
+ * Defines a priority for doing AEAD with descriptors type
+ * HMAC_SNOOP_NO_AFEA (HSNA) instead of type IPSEC_ESP
+ */
+#define TALITOS_CRA_PRIORITY_AEAD_HSNA	(TALITOS_CRA_PRIORITY - 1)
 #define TALITOS_MAX_KEY_SIZE		96
 #define TALITOS_MAX_IV_LENGTH		16 /* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
 
@@ -904,35 +916,59 @@
 static void talitos_sg_unmap(struct device *dev,
 			     struct talitos_edesc *edesc,
 			     struct scatterlist *src,
-			     struct scatterlist *dst)
+			     struct scatterlist *dst,
+			     unsigned int len, unsigned int offset)
 {
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 	unsigned int src_nents = edesc->src_nents ? : 1;
 	unsigned int dst_nents = edesc->dst_nents ? : 1;
 
+	if (is_sec1 && dst && dst_nents > 1) {
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl + offset,
+					   len, DMA_FROM_DEVICE);
+		sg_pcopy_from_buffer(dst, dst_nents, edesc->buf + offset, len,
+				     offset);
+	}
 	if (src != dst) {
-		dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
+		if (src_nents == 1 || !is_sec1)
+			dma_unmap_sg(dev, src, src_nents, DMA_TO_DEVICE);
 
-		if (dst) {
+		if (dst && (dst_nents == 1 || !is_sec1))
 			dma_unmap_sg(dev, dst, dst_nents, DMA_FROM_DEVICE);
-		}
-	} else
+	} else if (src_nents == 1 || !is_sec1) {
 		dma_unmap_sg(dev, src, src_nents, DMA_BIDIRECTIONAL);
+	}
 }
 
 static void ipsec_esp_unmap(struct device *dev,
 			    struct talitos_edesc *edesc,
 			    struct aead_request *areq)
 {
-	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[6], DMA_FROM_DEVICE);
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct talitos_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+
+	if (edesc->desc.hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[6],
+					 DMA_FROM_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[3], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[0], DMA_TO_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, areq->src, areq->dst);
+	talitos_sg_unmap(dev, edesc, areq->src, areq->dst, areq->cryptlen,
+			 areq->assoclen);
 
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
+
+	if (!(edesc->desc.hdr & DESC_HDR_TYPE_IPSEC_ESP)) {
+		unsigned int dst_nents = edesc->dst_nents ? : 1;
+
+		sg_pcopy_to_buffer(areq->dst, dst_nents, ctx->iv, ivsize,
+				   areq->assoclen + areq->cryptlen - ivsize);
+	}
 }
 
 /*
@@ -942,6 +978,8 @@
 				   struct talitos_desc *desc, void *context,
 				   int err)
 {
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 	struct aead_request *areq = context;
 	struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
 	unsigned int authsize = crypto_aead_authsize(authenc);
@@ -955,8 +993,11 @@
 
 	/* copy the generated ICV to dst */
 	if (edesc->icv_ool) {
-		icvdata = &edesc->link_tbl[edesc->src_nents +
-					   edesc->dst_nents + 2];
+		if (is_sec1)
+			icvdata = edesc->buf + areq->assoclen + areq->cryptlen;
+		else
+			icvdata = &edesc->link_tbl[edesc->src_nents +
+						   edesc->dst_nents + 2];
 		sg = sg_last(areq->dst, edesc->dst_nents);
 		memcpy((char *)sg_virt(sg) + sg->length - authsize,
 		       icvdata, authsize);
@@ -977,6 +1018,8 @@
 	struct talitos_edesc *edesc;
 	struct scatterlist *sg;
 	char *oicv, *icv;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	edesc = container_of(desc, struct talitos_edesc, desc);
 
@@ -988,7 +1031,12 @@
 		icv = (char *)sg_virt(sg) + sg->length - authsize;
 
 		if (edesc->dma_len) {
-			oicv = (char *)&edesc->link_tbl[edesc->src_nents +
+			if (is_sec1)
+				oicv = (char *)&edesc->dma_link_tbl +
+					       req->assoclen + req->cryptlen;
+			else
+				oicv = (char *)
+				       &edesc->link_tbl[edesc->src_nents +
 							edesc->dst_nents + 2];
 			if (edesc->icv_ool)
 				icv = oicv + authsize;
@@ -1050,8 +1098,8 @@
 
 		to_talitos_ptr(link_tbl_ptr + count,
 			       sg_dma_address(sg) + offset, 0);
-		link_tbl_ptr[count].len = cpu_to_be16(len);
-		link_tbl_ptr[count].j_extent = 0;
+		to_talitos_ptr_len(link_tbl_ptr + count, len, 0);
+		to_talitos_ptr_ext_set(link_tbl_ptr + count, 0, 0);
 		count++;
 		cryptlen -= len;
 		offset = 0;
@@ -1062,17 +1110,43 @@
 
 	/* tag end of link table */
 	if (count > 0)
-		link_tbl_ptr[count - 1].j_extent = DESC_PTR_LNKTBL_RETURN;
+		to_talitos_ptr_ext_set(link_tbl_ptr + count - 1,
+				       DESC_PTR_LNKTBL_RETURN, 0);
 
 	return count;
 }
 
-static inline int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
-				 int cryptlen,
-				 struct talitos_ptr *link_tbl_ptr)
+int talitos_sg_map(struct device *dev, struct scatterlist *src,
+		   unsigned int len, struct talitos_edesc *edesc,
+		   struct talitos_ptr *ptr,
+		   int sg_count, unsigned int offset, int tbl_off)
 {
-	return sg_to_link_tbl_offset(sg, sg_count, 0, cryptlen,
-				     link_tbl_ptr);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	to_talitos_ptr_len(ptr, len, is_sec1);
+	to_talitos_ptr_ext_set(ptr, 0, is_sec1);
+
+	if (sg_count == 1) {
+		to_talitos_ptr(ptr, sg_dma_address(src) + offset, is_sec1);
+		return sg_count;
+	}
+	if (is_sec1) {
+		to_talitos_ptr(ptr, edesc->dma_link_tbl + offset, is_sec1);
+		return sg_count;
+	}
+	sg_count = sg_to_link_tbl_offset(src, sg_count, offset, len,
+					 &edesc->link_tbl[tbl_off]);
+	if (sg_count == 1) {
+		/* 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), is_sec1);
+	to_talitos_ptr_ext_or(ptr, DESC_PTR_LNKTBL_JUMP, is_sec1);
+
+	return sg_count;
 }
 
 /*
@@ -1093,42 +1167,52 @@
 	int tbl_off = 0;
 	int sg_count, ret;
 	int sg_link_tbl_len;
+	bool sync_needed = false;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/* hmac key */
 	map_single_talitos_ptr(dev, &desc->ptr[0], ctx->authkeylen, &ctx->key,
 			       DMA_TO_DEVICE);
 
-	sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1,
-			      (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
-							   : DMA_TO_DEVICE);
+	sg_count = edesc->src_nents ?: 1;
+	if (is_sec1 && sg_count > 1)
+		sg_copy_to_buffer(areq->src, sg_count, edesc->buf,
+				  areq->assoclen + cryptlen);
+	else
+		sg_count = dma_map_sg(dev, areq->src, sg_count,
+				      (areq->src == areq->dst) ?
+				      DMA_BIDIRECTIONAL : DMA_TO_DEVICE);
+
 	/* hmac data */
-	desc->ptr[1].len = cpu_to_be16(areq->assoclen);
-	if (sg_count > 1 &&
-	    (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0,
-					 areq->assoclen,
-					 &edesc->link_tbl[tbl_off])) > 1) {
-		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
-			       sizeof(struct talitos_ptr), 0);
-		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
+	ret = talitos_sg_map(dev, areq->src, areq->assoclen, edesc,
+			     &desc->ptr[1], sg_count, 0, tbl_off);
 
-		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-					   edesc->dma_len, DMA_BIDIRECTIONAL);
-
+	if (ret > 1) {
 		tbl_off += ret;
-	} else {
-		to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0);
-		desc->ptr[1].j_extent = 0;
+		sync_needed = true;
 	}
 
 	/* cipher iv */
-	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, 0);
-	desc->ptr[2].len = cpu_to_be16(ivsize);
-	desc->ptr[2].j_extent = 0;
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP) {
+		to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, is_sec1);
+		to_talitos_ptr_len(&desc->ptr[2], ivsize, is_sec1);
+		to_talitos_ptr_ext_set(&desc->ptr[2], 0, is_sec1);
+	} else {
+		to_talitos_ptr(&desc->ptr[3], edesc->iv_dma, is_sec1);
+		to_talitos_ptr_len(&desc->ptr[3], ivsize, is_sec1);
+		to_talitos_ptr_ext_set(&desc->ptr[3], 0, is_sec1);
+	}
 
 	/* cipher key */
-	map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
-			       (char *)&ctx->key + ctx->authkeylen,
-			       DMA_TO_DEVICE);
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
+				       (char *)&ctx->key + ctx->authkeylen,
+				       DMA_TO_DEVICE);
+	else
+		map_single_talitos_ptr(dev, &desc->ptr[2], ctx->enckeylen,
+				       (char *)&ctx->key + ctx->authkeylen,
+				       DMA_TO_DEVICE);
 
 	/*
 	 * cipher in
@@ -1136,78 +1220,82 @@
 	 * extent is bytes of HMAC postpended to ciphertext,
 	 * typically 12 for ipsec
 	 */
-	desc->ptr[4].len = cpu_to_be16(cryptlen);
-	desc->ptr[4].j_extent = authsize;
+	to_talitos_ptr_len(&desc->ptr[4], cryptlen, is_sec1);
+	to_talitos_ptr_ext_set(&desc->ptr[4], 0, is_sec1);
 
 	sg_link_tbl_len = cryptlen;
-	if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
-		sg_link_tbl_len += authsize;
 
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) +
-			       areq->assoclen, 0);
-	} else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count,
-						areq->assoclen, sg_link_tbl_len,
-						&edesc->link_tbl[tbl_off])) >
-		   1) {
-		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
-					      tbl_off *
-					      sizeof(struct talitos_ptr), 0);
-		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-					   edesc->dma_len,
-					   DMA_BIDIRECTIONAL);
-		tbl_off += ret;
-	} else {
-		copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0);
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP) {
+		to_talitos_ptr_ext_set(&desc->ptr[4], authsize, is_sec1);
+
+		if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV)
+			sg_link_tbl_len += authsize;
+	}
+
+	sg_count = talitos_sg_map(dev, areq->src, cryptlen, edesc,
+				  &desc->ptr[4], sg_count, areq->assoclen,
+				  tbl_off);
+
+	if (sg_count > 1) {
+		tbl_off += sg_count;
+		sync_needed = true;
 	}
 
 	/* cipher out */
-	desc->ptr[5].len = cpu_to_be16(cryptlen);
-	desc->ptr[5].j_extent = authsize;
+	if (areq->src != areq->dst) {
+		sg_count = edesc->dst_nents ? : 1;
+		if (!is_sec1 || sg_count == 1)
+			dma_map_sg(dev, areq->dst, sg_count, DMA_FROM_DEVICE);
+	}
 
-	if (areq->src != areq->dst)
-		sg_count = dma_map_sg(dev, areq->dst, edesc->dst_nents ? : 1,
-				      DMA_FROM_DEVICE);
+	sg_count = talitos_sg_map(dev, areq->dst, cryptlen, edesc,
+				  &desc->ptr[5], sg_count, areq->assoclen,
+				  tbl_off);
 
-	edesc->icv_ool = false;
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		to_talitos_ptr_ext_or(&desc->ptr[5], authsize, is_sec1);
 
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) +
-			       areq->assoclen, 0);
-	} else if ((sg_count =
-			sg_to_link_tbl_offset(areq->dst, sg_count,
-					      areq->assoclen, cryptlen,
-					      &edesc->link_tbl[tbl_off])) > 1) {
-		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
-
-		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
-			       tbl_off * sizeof(struct talitos_ptr), 0);
-
-		/* Add an entry to the link table for ICV data */
-		tbl_ptr += sg_count - 1;
-		tbl_ptr->j_extent = 0;
-		tbl_ptr++;
-		tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
-		tbl_ptr->len = cpu_to_be16(authsize);
-
-		/* icv data follows link tables */
-		to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl +
-					(edesc->src_nents + edesc->dst_nents +
-					 2) * sizeof(struct talitos_ptr) +
-					authsize, 0);
-		desc->ptr[5].j_extent |= DESC_PTR_LNKTBL_JUMP;
-		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
-					   edesc->dma_len, DMA_BIDIRECTIONAL);
-
+	if (sg_count > 1) {
 		edesc->icv_ool = true;
+		sync_needed = true;
+
+		if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP) {
+			struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
+			int offset = (edesc->src_nents + edesc->dst_nents + 2) *
+				     sizeof(struct talitos_ptr) + authsize;
+
+			/* Add an entry to the link table for ICV data */
+			tbl_ptr += sg_count - 1;
+			to_talitos_ptr_ext_set(tbl_ptr, 0, is_sec1);
+			tbl_ptr++;
+			to_talitos_ptr_ext_set(tbl_ptr, DESC_PTR_LNKTBL_RETURN,
+					       is_sec1);
+			to_talitos_ptr_len(tbl_ptr, authsize, is_sec1);
+
+			/* icv data follows link tables */
+			to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl + offset,
+				       is_sec1);
+		}
 	} else {
-		copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0);
+		edesc->icv_ool = false;
+	}
+
+	/* ICV data */
+	if (!(desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)) {
+		to_talitos_ptr_len(&desc->ptr[6], authsize, is_sec1);
+		to_talitos_ptr(&desc->ptr[6], edesc->dma_link_tbl +
+			       areq->assoclen + cryptlen, is_sec1);
 	}
 
 	/* iv out */
-	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
-			       DMA_FROM_DEVICE);
+	if (desc->hdr & DESC_HDR_TYPE_IPSEC_ESP)
+		map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
+				       DMA_FROM_DEVICE);
+
+	if (sync_needed)
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len,
+					   DMA_BIDIRECTIONAL);
 
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
@@ -1233,7 +1321,7 @@
 						 bool encrypt)
 {
 	struct talitos_edesc *edesc;
-	int src_nents, dst_nents, alloc_len, dma_len;
+	int src_nents, dst_nents, alloc_len, dma_len, src_len, dst_len;
 	dma_addr_t iv_dma = 0;
 	gfp_t flags = cryptoflags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		      GFP_ATOMIC;
@@ -1251,8 +1339,8 @@
 		iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE);
 
 	if (!dst || dst == src) {
-		src_nents = sg_nents_for_len(src,
-					     assoclen + cryptlen + authsize);
+		src_len = assoclen + cryptlen + authsize;
+		src_nents = sg_nents_for_len(src, src_len);
 		if (src_nents < 0) {
 			dev_err(dev, "Invalid number of src SG.\n");
 			err = ERR_PTR(-EINVAL);
@@ -1260,17 +1348,18 @@
 		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
 		dst_nents = dst ? src_nents : 0;
+		dst_len = 0;
 	} else { /* dst && dst != src*/
-		src_nents = sg_nents_for_len(src, assoclen + cryptlen +
-						 (encrypt ? 0 : authsize));
+		src_len = assoclen + cryptlen + (encrypt ? 0 : authsize);
+		src_nents = sg_nents_for_len(src, src_len);
 		if (src_nents < 0) {
 			dev_err(dev, "Invalid number of src SG.\n");
 			err = ERR_PTR(-EINVAL);
 			goto error_sg;
 		}
 		src_nents = (src_nents == 1) ? 0 : src_nents;
-		dst_nents = sg_nents_for_len(dst, assoclen + cryptlen +
-						 (encrypt ? authsize : 0));
+		dst_len = assoclen + cryptlen + (encrypt ? authsize : 0);
+		dst_nents = sg_nents_for_len(dst, dst_len);
 		if (dst_nents < 0) {
 			dev_err(dev, "Invalid number of dst SG.\n");
 			err = ERR_PTR(-EINVAL);
@@ -1287,8 +1376,8 @@
 	alloc_len = sizeof(struct talitos_edesc);
 	if (src_nents || dst_nents) {
 		if (is_sec1)
-			dma_len = (src_nents ? cryptlen : 0) +
-				  (dst_nents ? cryptlen : 0);
+			dma_len = (src_nents ? src_len : 0) +
+				  (dst_nents ? dst_len : 0);
 		else
 			dma_len = (src_nents + dst_nents + 2) *
 				  sizeof(struct talitos_ptr) + authsize * 2;
@@ -1412,40 +1501,13 @@
 	return 0;
 }
 
-static void unmap_sg_talitos_ptr(struct device *dev, struct scatterlist *src,
-				 struct scatterlist *dst, unsigned int len,
-				 struct talitos_edesc *edesc)
-{
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
-
-	if (is_sec1) {
-		if (!edesc->src_nents) {
-			dma_unmap_sg(dev, src, 1,
-				     dst != src ? DMA_TO_DEVICE
-						: DMA_BIDIRECTIONAL);
-		}
-		if (dst && edesc->dst_nents) {
-			dma_sync_single_for_device(dev,
-						   edesc->dma_link_tbl + len,
-						   len, DMA_FROM_DEVICE);
-			sg_copy_from_buffer(dst, edesc->dst_nents ? : 1,
-					    edesc->buf + len, len);
-		} else if (dst && dst != src) {
-			dma_unmap_sg(dev, dst, 1, DMA_FROM_DEVICE);
-		}
-	} else {
-		talitos_sg_unmap(dev, edesc, src, dst);
-	}
-}
-
 static void common_nonsnoop_unmap(struct device *dev,
 				  struct talitos_edesc *edesc,
 				  struct ablkcipher_request *areq)
 {
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
-	unmap_sg_talitos_ptr(dev, areq->src, areq->dst, areq->nbytes, edesc);
+	talitos_sg_unmap(dev, edesc, areq->src, areq->dst, areq->nbytes, 0);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1], DMA_TO_DEVICE);
 
@@ -1470,100 +1532,6 @@
 	areq->base.complete(&areq->base, err);
 }
 
-int map_sg_in_talitos_ptr(struct device *dev, struct scatterlist *src,
-			  unsigned int len, struct talitos_edesc *edesc,
-			  enum dma_data_direction dir, struct talitos_ptr *ptr)
-{
-	int sg_count;
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
-
-	to_talitos_ptr_len(ptr, len, is_sec1);
-
-	if (is_sec1) {
-		sg_count = edesc->src_nents ? : 1;
-
-		if (sg_count == 1) {
-			dma_map_sg(dev, src, 1, dir);
-			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
-		} else {
-			sg_copy_to_buffer(src, sg_count, edesc->buf, len);
-			to_talitos_ptr(ptr, edesc->dma_link_tbl, is_sec1);
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   len, DMA_TO_DEVICE);
-		}
-	} else {
-		to_talitos_ptr_extent_clear(ptr, is_sec1);
-
-		sg_count = dma_map_sg(dev, src, edesc->src_nents ? : 1, dir);
-
-		if (sg_count == 1) {
-			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
-		} else {
-			sg_count = sg_to_link_tbl(src, sg_count, len,
-						  &edesc->link_tbl[0]);
-			if (sg_count > 1) {
-				to_talitos_ptr(ptr, edesc->dma_link_tbl, 0);
-				ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
-				dma_sync_single_for_device(dev,
-							   edesc->dma_link_tbl,
-							   edesc->dma_len,
-							   DMA_BIDIRECTIONAL);
-			} else {
-				/* Only one segment now, so no link tbl needed*/
-				to_talitos_ptr(ptr, sg_dma_address(src),
-					       is_sec1);
-			}
-		}
-	}
-	return sg_count;
-}
-
-void map_sg_out_talitos_ptr(struct device *dev, struct scatterlist *dst,
-			    unsigned int len, struct talitos_edesc *edesc,
-			    enum dma_data_direction dir,
-			    struct talitos_ptr *ptr, int sg_count)
-{
-	struct talitos_private *priv = dev_get_drvdata(dev);
-	bool is_sec1 = has_ftr_sec1(priv);
-
-	if (dir != DMA_NONE)
-		sg_count = dma_map_sg(dev, dst, edesc->dst_nents ? : 1, dir);
-
-	to_talitos_ptr_len(ptr, len, is_sec1);
-
-	if (is_sec1) {
-		if (sg_count == 1) {
-			if (dir != DMA_NONE)
-				dma_map_sg(dev, dst, 1, dir);
-			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
-		} else {
-			to_talitos_ptr(ptr, edesc->dma_link_tbl + len, is_sec1);
-			dma_sync_single_for_device(dev,
-						   edesc->dma_link_tbl + len,
-						   len, DMA_FROM_DEVICE);
-		}
-	} else {
-		to_talitos_ptr_extent_clear(ptr, is_sec1);
-
-		if (sg_count == 1) {
-			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
-		} else {
-			struct talitos_ptr *link_tbl_ptr =
-				&edesc->link_tbl[edesc->src_nents + 1];
-
-			to_talitos_ptr(ptr, edesc->dma_link_tbl +
-					    (edesc->src_nents + 1) *
-					     sizeof(struct talitos_ptr), 0);
-			ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
-			sg_to_link_tbl(dst, sg_count, len, link_tbl_ptr);
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		}
-	}
-}
-
 static int common_nonsnoop(struct talitos_edesc *edesc,
 			   struct ablkcipher_request *areq,
 			   void (*callback) (struct device *dev,
@@ -1577,6 +1545,7 @@
 	unsigned int cryptlen = areq->nbytes;
 	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
 	int sg_count, ret;
+	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
 
@@ -1586,25 +1555,39 @@
 	/* cipher iv */
 	to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, is_sec1);
 	to_talitos_ptr_len(&desc->ptr[1], ivsize, is_sec1);
-	to_talitos_ptr_extent_clear(&desc->ptr[1], is_sec1);
+	to_talitos_ptr_ext_set(&desc->ptr[1], 0, is_sec1);
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[2], ctx->keylen,
 			       (char *)&ctx->key, DMA_TO_DEVICE);
 
+	sg_count = edesc->src_nents ?: 1;
+	if (is_sec1 && sg_count > 1)
+		sg_copy_to_buffer(areq->src, sg_count, edesc->buf,
+				  cryptlen);
+	else
+		sg_count = dma_map_sg(dev, areq->src, sg_count,
+				      (areq->src == areq->dst) ?
+				      DMA_BIDIRECTIONAL : DMA_TO_DEVICE);
 	/*
 	 * cipher in
 	 */
-	sg_count = map_sg_in_talitos_ptr(dev, areq->src, cryptlen, edesc,
-					 (areq->src == areq->dst) ?
-					  DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
-					  &desc->ptr[3]);
+	sg_count = talitos_sg_map(dev, areq->src, cryptlen, edesc,
+				  &desc->ptr[3], sg_count, 0, 0);
+	if (sg_count > 1)
+		sync_needed = true;
 
 	/* cipher out */
-	map_sg_out_talitos_ptr(dev, areq->dst, cryptlen, edesc,
-			       (areq->src == areq->dst) ? DMA_NONE
-							: DMA_FROM_DEVICE,
-			       &desc->ptr[4], sg_count);
+	if (areq->src != areq->dst) {
+		sg_count = edesc->dst_nents ? : 1;
+		if (!is_sec1 || sg_count == 1)
+			dma_map_sg(dev, areq->dst, sg_count, DMA_FROM_DEVICE);
+	}
+
+	ret = talitos_sg_map(dev, areq->dst, cryptlen, edesc, &desc->ptr[4],
+			     sg_count, 0, (edesc->src_nents + 1));
+	if (ret > 1)
+		sync_needed = true;
 
 	/* iv out */
 	map_single_talitos_ptr(dev, &desc->ptr[5], ivsize, ctx->iv,
@@ -1613,6 +1596,10 @@
 	/* last DWORD empty */
 	desc->ptr[6] = zero_entry;
 
+	if (sync_needed)
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len, DMA_BIDIRECTIONAL);
+
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
 		common_nonsnoop_unmap(dev, edesc, areq);
@@ -1676,7 +1663,7 @@
 
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
-	unmap_sg_talitos_ptr(dev, req_ctx->psrc, NULL, 0, edesc);
+	talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL, 0, 0);
 
 	/* When using hashctx-in, must unmap it. */
 	if (from_talitos_ptr_len(&edesc->desc.ptr[1], is_sec1))
@@ -1747,8 +1734,10 @@
 	struct device *dev = ctx->dev;
 	struct talitos_desc *desc = &edesc->desc;
 	int ret;
+	bool sync_needed = false;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
+	int sg_count;
 
 	/* first DWORD empty */
 	desc->ptr[0] = zero_entry;
@@ -1773,11 +1762,19 @@
 	else
 		desc->ptr[2] = zero_entry;
 
+	sg_count = edesc->src_nents ?: 1;
+	if (is_sec1 && sg_count > 1)
+		sg_copy_to_buffer(areq->src, sg_count, edesc->buf, length);
+	else
+		sg_count = dma_map_sg(dev, req_ctx->psrc, sg_count,
+				      DMA_TO_DEVICE);
 	/*
 	 * data in
 	 */
-	map_sg_in_talitos_ptr(dev, req_ctx->psrc, length, edesc,
-			      DMA_TO_DEVICE, &desc->ptr[3]);
+	sg_count = talitos_sg_map(dev, req_ctx->psrc, length, edesc,
+				  &desc->ptr[3], sg_count, 0, 0);
+	if (sg_count > 1)
+		sync_needed = true;
 
 	/* fifth DWORD empty */
 	desc->ptr[4] = zero_entry;
@@ -1798,6 +1795,10 @@
 	if (is_sec1 && from_talitos_ptr_len(&desc->ptr[3], true) == 0)
 		talitos_handle_buggy_hash(ctx, edesc, &desc->ptr[3]);
 
+	if (sync_needed)
+		dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+					   edesc->dma_len, DMA_BIDIRECTIONAL);
+
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
 		common_nonsnoop_hash_unmap(dev, edesc, areq);
@@ -2124,6 +2125,7 @@
 
 struct talitos_alg_template {
 	u32 type;
+	u32 priority;
 	union {
 		struct crypto_alg crypto;
 		struct ahash_alg hash;
@@ -2155,6 +2157,27 @@
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha1),"
@@ -2176,6 +2199,29 @@
 		                     DESC_HDR_MODE1_MDEU_PAD |
 		                     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
 	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha1),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha1-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA1_HMAC,
+	},
 	{       .type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
@@ -2196,6 +2242,27 @@
 				     DESC_HDR_MODE1_MDEU_PAD |
 				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
 	},
+	{       .type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
+	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
@@ -2219,6 +2286,29 @@
 		                     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha224),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha224-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA224_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA224_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha256),cbc(aes))",
@@ -2239,6 +2329,27 @@
 		                     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha256),"
@@ -2261,6 +2372,29 @@
 		                     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(sha256),"
+					    "cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-sha256-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_SHA256_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(sha384),cbc(aes))",
@@ -2365,6 +2499,27 @@
 		                     DESC_HDR_MODE1_MDEU_MD5_HMAC,
 	},
 	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(aes))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-aes-talitos",
+				.cra_blocksize = AES_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_AESU |
+				     DESC_HDR_MODE0_AESU_CBC |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_MD5_HMAC,
+	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
 		.alg.aead = {
 			.base = {
 				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
@@ -2385,6 +2540,28 @@
 		                     DESC_HDR_MODE1_MDEU_PAD |
 		                     DESC_HDR_MODE1_MDEU_MD5_HMAC,
 	},
+	{	.type = CRYPTO_ALG_TYPE_AEAD,
+		.priority = TALITOS_CRA_PRIORITY_AEAD_HSNA,
+		.alg.aead = {
+			.base = {
+				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
+				.cra_driver_name = "authenc-hmac-md5-"
+						   "cbc-3des-talitos",
+				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+				.cra_flags = CRYPTO_ALG_ASYNC,
+			},
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+		},
+		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
+				     DESC_HDR_SEL0_DEU |
+				     DESC_HDR_MODE0_DEU_CBC |
+				     DESC_HDR_MODE0_DEU_3DES |
+				     DESC_HDR_SEL1_MDEUA |
+				     DESC_HDR_MODE1_MDEU_INIT |
+				     DESC_HDR_MODE1_MDEU_PAD |
+				     DESC_HDR_MODE1_MDEU_MD5_HMAC,
+	},
 	/* ABLKCIPHER algorithms. */
 	{	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.alg.crypto = {
@@ -2901,7 +3078,10 @@
 	}
 
 	alg->cra_module = THIS_MODULE;
-	alg->cra_priority = TALITOS_CRA_PRIORITY;
+	if (t_alg->algt.priority)
+		alg->cra_priority = t_alg->algt.priority;
+	else
+		alg->cra_priority = TALITOS_CRA_PRIORITY;
 	alg->cra_alignmask = 0;
 	alg->cra_ctxsize = sizeof(struct talitos_ctx);
 	alg->cra_flags |= CRYPTO_ALG_KERN_DRIVER_ONLY;
diff --git a/drivers/crypto/ux500/cryp/Makefile b/drivers/crypto/ux500/cryp/Makefile
index e5d362a..b497ae3 100644
--- a/drivers/crypto/ux500/cryp/Makefile
+++ b/drivers/crypto/ux500/cryp/Makefile
@@ -4,9 +4,9 @@
 # * License terms: GNU General Public License (GPL) version 2  */
 
 ifdef CONFIG_CRYPTO_DEV_UX500_DEBUG
-CFLAGS_cryp_core.o := -DDEBUG -O0
-CFLAGS_cryp.o := -DDEBUG -O0
-CFLAGS_cryp_irq.o := -DDEBUG -O0
+CFLAGS_cryp_core.o := -DDEBUG
+CFLAGS_cryp.o := -DDEBUG
+CFLAGS_cryp_irq.o := -DDEBUG
 endif
 
 obj-$(CONFIG_CRYPTO_DEV_UX500_CRYP) += ux500_cryp.o
diff --git a/drivers/crypto/ux500/hash/Makefile b/drivers/crypto/ux500/hash/Makefile
index b2f90d9..784d9c0 100644
--- a/drivers/crypto/ux500/hash/Makefile
+++ b/drivers/crypto/ux500/hash/Makefile
@@ -4,7 +4,7 @@
 # License terms: GNU General Public License (GPL) version 2
 #
 ifdef CONFIG_CRYPTO_DEV_UX500_DEBUG
-CFLAGS_hash_core.o := -DDEBUG -O0
+CFLAGS_hash_core.o := -DDEBUG
 endif
 
 obj-$(CONFIG_CRYPTO_DEV_UX500_HASH) += ux500_hash.o
diff --git a/drivers/crypto/vmx/.gitignore b/drivers/crypto/vmx/.gitignore
new file mode 100644
index 0000000..af4a7ce
--- /dev/null
+++ b/drivers/crypto/vmx/.gitignore
@@ -0,0 +1,2 @@
+aesp8-ppc.S
+ghashp8-ppc.S
diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile
index d28ab96..de6e241 100644
--- a/drivers/crypto/vmx/Makefile
+++ b/drivers/crypto/vmx/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o
-vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o ghash.o
+vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o
 
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 TARGET := linux-ppc64le
diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c
new file mode 100644
index 0000000..cfb2541
--- /dev/null
+++ b/drivers/crypto/vmx/aes_xts.c
@@ -0,0 +1,190 @@
+/**
+ * AES XTS routines supporting VMX In-core instructions on Power 8
+ *
+ * Copyright (C) 2015 International Business Machines Inc.
+ *
+ * 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 Foundations; version 2 only.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY of FITNESS FOR A PARTICUPAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Author: Leonidas S. Barbosa <leosilva@linux.vnet.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/crypto.h>
+#include <linux/delay.h>
+#include <linux/hardirq.h>
+#include <asm/switch_to.h>
+#include <crypto/aes.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/xts.h>
+
+#include "aesp8-ppc.h"
+
+struct p8_aes_xts_ctx {
+	struct crypto_blkcipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
+	struct aes_key tweak_key;
+};
+
+static int p8_aes_xts_init(struct crypto_tfm *tfm)
+{
+	const char *alg;
+	struct crypto_blkcipher *fallback;
+	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback =
+		crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+			"Failed to allocate transformation for '%s': %ld\n",
+			alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+		crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_blkcipher_set_flags(
+		fallback,
+		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+	ctx->fallback = fallback;
+
+	return 0;
+}
+
+static void p8_aes_xts_exit(struct crypto_tfm *tfm)
+{
+	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (ctx->fallback) {
+		crypto_free_blkcipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
+}
+
+static int p8_aes_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
+			     unsigned int keylen)
+{
+	int ret;
+	struct p8_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ret = xts_check_key(tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_vsx();
+	ret = aes_p8_set_encrypt_key(key + keylen/2, (keylen/2) * 8, &ctx->tweak_key);
+	ret += aes_p8_set_encrypt_key(key, (keylen/2) * 8, &ctx->enc_key);
+	ret += aes_p8_set_decrypt_key(key, (keylen/2) * 8, &ctx->dec_key);
+	disable_kernel_vsx();
+	pagefault_enable();
+	preempt_enable();
+
+	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	return ret;
+}
+
+static int p8_aes_xts_crypt(struct blkcipher_desc *desc,
+			    struct scatterlist *dst,
+			    struct scatterlist *src,
+			    unsigned int nbytes, int enc)
+{
+	int ret;
+	u8 tweak[AES_BLOCK_SIZE];
+	u8 *iv;
+	struct blkcipher_walk walk;
+	struct p8_aes_xts_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = enc ? crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes) :
+                            crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_vsx();
+
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+
+		iv = (u8 *)walk.iv;
+		ret = blkcipher_walk_virt(desc, &walk);
+		memset(tweak, 0, AES_BLOCK_SIZE);
+		aes_p8_encrypt(iv, tweak, &ctx->tweak_key);
+
+		while ((nbytes = walk.nbytes)) {
+			if (enc)
+				aes_p8_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
+						nbytes & AES_BLOCK_MASK, &ctx->enc_key, NULL, tweak);
+			else
+				aes_p8_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
+						nbytes & AES_BLOCK_MASK, &ctx->dec_key, NULL, tweak);
+
+			nbytes &= AES_BLOCK_SIZE - 1;
+			ret = blkcipher_walk_done(desc, &walk, nbytes);
+		}
+
+		disable_kernel_vsx();
+		pagefault_enable();
+		preempt_enable();
+	}
+	return ret;
+}
+
+static int p8_aes_xts_encrypt(struct blkcipher_desc *desc,
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
+{
+	return p8_aes_xts_crypt(desc, dst, src, nbytes, 1);
+}
+
+static int p8_aes_xts_decrypt(struct blkcipher_desc *desc,
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
+{
+	return p8_aes_xts_crypt(desc, dst, src, nbytes, 0);
+}
+
+struct crypto_alg p8_aes_xts_alg = {
+	.cra_name = "xts(aes)",
+	.cra_driver_name = "p8_aes_xts",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 2000,
+	.cra_type = &crypto_blkcipher_type,
+	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_xts_ctx),
+	.cra_init = p8_aes_xts_init,
+	.cra_exit = p8_aes_xts_exit,
+	.cra_blkcipher = {
+			.ivsize = AES_BLOCK_SIZE,
+			.min_keysize = 2 * AES_MIN_KEY_SIZE,
+			.max_keysize = 2 * AES_MAX_KEY_SIZE,
+			.setkey	 = p8_aes_xts_setkey,
+			.encrypt = p8_aes_xts_encrypt,
+			.decrypt = p8_aes_xts_decrypt,
+	}
+};
diff --git a/drivers/crypto/vmx/aesp8-ppc.h b/drivers/crypto/vmx/aesp8-ppc.h
index 4cd34ee..01972e1 100644
--- a/drivers/crypto/vmx/aesp8-ppc.h
+++ b/drivers/crypto/vmx/aesp8-ppc.h
@@ -19,3 +19,7 @@
 void aes_p8_ctr32_encrypt_blocks(const u8 *in, u8 *out,
 				 size_t len, const struct aes_key *key,
 				 const u8 *iv);
+void aes_p8_xts_encrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
+void aes_p8_xts_decrypt(const u8 *in, u8 *out, size_t len,
+			const struct aes_key *key1, const struct aes_key *key2, u8 *iv);
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index 2280539..0b4a293 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (the "License").  You may not use
+# this file except in compliance with the License.  You can obtain a copy
+# in the file LICENSE in the source distribution or at
+# https://www.openssl.org/source/license.html
+
 #
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@@ -20,6 +27,19 @@
 # instructions are interleaved. It's reckoned that eventual
 # misalignment penalties at page boundaries are in average lower
 # than additional overhead in pure AltiVec approach.
+#
+# May 2016
+#
+# Add XTS subroutine, 9x on little- and 12x improvement on big-endian
+# systems were measured.
+#
+######################################################################
+# Current large-block performance in cycles per byte processed with
+# 128-bit key (less is better).
+#
+#		CBC en-/decrypt	CTR	XTS
+# POWER8[le]	3.96/0.72	0.74	1.1
+# POWER8[be]	3.75/0.65	0.66	1.0
 
 $flavour = shift;
 
@@ -1875,6 +1895,1845 @@
 ___
 }}	}}}
 
+#########################################################################
+{{{	# XTS procedures						#
+# int aes_p8_xts_[en|de]crypt(const char *inp, char *out, size_t len,	#
+#                             const AES_KEY *key1, const AES_KEY *key2,	#
+#                             [const] unsigned char iv[16]);		#
+# If $key2 is NULL, then a "tweak chaining" mode is engaged, in which	#
+# input tweak value is assumed to be encrypted already, and last tweak	#
+# value, one suitable for consecutive call on same chunk of data, is	#
+# written back to original buffer. In addition, in "tweak chaining"	#
+# mode only complete input blocks are processed.			#
+
+my ($inp,$out,$len,$key1,$key2,$ivp,$rounds,$idx) =	map("r$_",(3..10));
+my ($rndkey0,$rndkey1,$inout) =				map("v$_",(0..2));
+my ($output,$inptail,$inpperm,$leperm,$keyperm) =	map("v$_",(3..7));
+my ($tweak,$seven,$eighty7,$tmp,$tweak1) =		map("v$_",(8..12));
+my $taillen = $key2;
+
+   ($inp,$idx) = ($idx,$inp);				# reassign
+
+$code.=<<___;
+.globl	.${prefix}_xts_encrypt
+	mr		$inp,r3				# reassign
+	li		r3,-1
+	${UCMP}i	$len,16
+	bltlr-
+
+	lis		r0,0xfff0
+	mfspr		r12,256				# save vrsave
+	li		r11,0
+	mtspr		256,r0
+
+	vspltisb	$seven,0x07			# 0x070707..07
+	le?lvsl		$leperm,r11,r11
+	le?vspltisb	$tmp,0x0f
+	le?vxor		$leperm,$leperm,$seven
+
+	li		$idx,15
+	lvx		$tweak,0,$ivp			# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$tweak,$tweak,$inptail,$inpperm
+
+	neg		r11,$inp
+	lvsr		$inpperm,0,r11			# prepare for unaligned load
+	lvx		$inout,0,$inp
+	addi		$inp,$inp,15			# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	${UCMP}i	$key2,0				# key2==NULL?
+	beq		Lxts_enc_no_key2
+
+	?lvsl		$keyperm,0,$key2		# prepare for unaligned key
+	lwz		$rounds,240($key2)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	lvx		$rndkey0,0,$key2
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Ltweak_xts_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	bdnz		Ltweak_xts_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$tweak,$tweak,$rndkey0
+
+	li		$ivp,0				# don't chain the tweak
+	b		Lxts_enc
+
+Lxts_enc_no_key2:
+	li		$idx,-16
+	and		$len,$len,$idx			# in "tweak chaining"
+							# mode only complete
+							# blocks are processed
+Lxts_enc:
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+
+	?lvsl		$keyperm,0,$key1		# prepare for unaligned key
+	lwz		$rounds,240($key1)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	vslb		$eighty7,$seven,$seven		# 0x808080..80
+	vor		$eighty7,$eighty7,$seven	# 0x878787..87
+	vspltisb	$tmp,1				# 0x010101..01
+	vsldoi		$eighty7,$eighty7,$tmp,15	# 0x870101..01
+
+	${UCMP}i	$len,96
+	bge		_aesp8_xts_encrypt6x
+
+	andi.		$taillen,$len,15
+	subic		r0,$len,32
+	subi		$taillen,$taillen,16
+	subfe		r0,r0,r0
+	and		r0,r0,$taillen
+	add		$inp,$inp,r0
+
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	mtctr		$rounds
+	b		Loop_xts_enc
+
+.align	5
+Loop_xts_enc:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_enc
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak
+	vcipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+	addi		$out,$out,16
+
+	subic.		$len,$len,16
+	beq		Lxts_enc_done
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+
+	subic		r0,$len,32
+	subfe		r0,r0,r0
+	and		r0,r0,$taillen
+	add		$inp,$inp,r0
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$output,$output,$rndkey0	# just in case $len<16
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	mtctr		$rounds
+	${UCMP}i	$len,16
+	bge		Loop_xts_enc
+
+	vxor		$output,$output,$tweak
+	lvsr		$inpperm,0,$len			# $inpperm is no longer needed
+	vxor		$inptail,$inptail,$inptail	# $inptail is no longer needed
+	vspltisb	$tmp,-1
+	vperm		$inptail,$inptail,$tmp,$inpperm
+	vsel		$inout,$inout,$output,$inptail
+
+	subi		r11,$out,17
+	subi		$out,$out,16
+	mtctr		$len
+	li		$len,16
+Loop_xts_enc_steal:
+	lbzu		r0,1(r11)
+	stb		r0,16(r11)
+	bdnz		Loop_xts_enc_steal
+
+	mtctr		$rounds
+	b		Loop_xts_enc			# one more time...
+
+Lxts_enc_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_enc_ret
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_enc_ret:
+	mtspr		256,r12				# restore vrsave
+	li		r3,0
+	blr
+	.long		0
+	.byte		0,12,0x04,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_xts_encrypt,.-.${prefix}_xts_encrypt
+
+.globl	.${prefix}_xts_decrypt
+	mr		$inp,r3				# reassign
+	li		r3,-1
+	${UCMP}i	$len,16
+	bltlr-
+
+	lis		r0,0xfff8
+	mfspr		r12,256				# save vrsave
+	li		r11,0
+	mtspr		256,r0
+
+	andi.		r0,$len,15
+	neg		r0,r0
+	andi.		r0,r0,16
+	sub		$len,$len,r0
+
+	vspltisb	$seven,0x07			# 0x070707..07
+	le?lvsl		$leperm,r11,r11
+	le?vspltisb	$tmp,0x0f
+	le?vxor		$leperm,$leperm,$seven
+
+	li		$idx,15
+	lvx		$tweak,0,$ivp			# load [unaligned] iv
+	lvsl		$inpperm,0,$ivp
+	lvx		$inptail,$idx,$ivp
+	le?vxor		$inpperm,$inpperm,$tmp
+	vperm		$tweak,$tweak,$inptail,$inpperm
+
+	neg		r11,$inp
+	lvsr		$inpperm,0,r11			# prepare for unaligned load
+	lvx		$inout,0,$inp
+	addi		$inp,$inp,15			# 15 is not typo
+	le?vxor		$inpperm,$inpperm,$tmp
+
+	${UCMP}i	$key2,0				# key2==NULL?
+	beq		Lxts_dec_no_key2
+
+	?lvsl		$keyperm,0,$key2		# prepare for unaligned key
+	lwz		$rounds,240($key2)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	lvx		$rndkey0,0,$key2
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+Ltweak_xts_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipher		$tweak,$tweak,$rndkey0
+	lvx		$rndkey0,$idx,$key2
+	addi		$idx,$idx,16
+	bdnz		Ltweak_xts_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vcipher		$tweak,$tweak,$rndkey1
+	lvx		$rndkey1,$idx,$key2
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vcipherlast	$tweak,$tweak,$rndkey0
+
+	li		$ivp,0				# don't chain the tweak
+	b		Lxts_dec
+
+Lxts_dec_no_key2:
+	neg		$idx,$len
+	andi.		$idx,$idx,15
+	add		$len,$len,$idx			# in "tweak chaining"
+							# mode only complete
+							# blocks are processed
+Lxts_dec:
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+
+	?lvsl		$keyperm,0,$key1		# prepare for unaligned key
+	lwz		$rounds,240($key1)
+	srwi		$rounds,$rounds,1
+	subi		$rounds,$rounds,1
+	li		$idx,16
+
+	vslb		$eighty7,$seven,$seven		# 0x808080..80
+	vor		$eighty7,$eighty7,$seven	# 0x878787..87
+	vspltisb	$tmp,1				# 0x010101..01
+	vsldoi		$eighty7,$eighty7,$tmp,15	# 0x870101..01
+
+	${UCMP}i	$len,96
+	bge		_aesp8_xts_decrypt6x
+
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	mtctr		$rounds
+
+	${UCMP}i	$len,16
+	blt		Ltail_xts_dec
+	be?b		Loop_xts_dec
+
+.align	5
+Loop_xts_dec:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_dec
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak
+	vncipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+	addi		$out,$out,16
+
+	subic.		$len,$len,16
+	beq		Lxts_dec_done
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$inout,$inout,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	mtctr		$rounds
+	${UCMP}i	$len,16
+	bge		Loop_xts_dec
+
+Ltail_xts_dec:
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak1,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak1,$tweak1,$tmp
+
+	subi		$inp,$inp,16
+	add		$inp,$inp,$len
+
+	vxor		$inout,$inout,$tweak		# :-(
+	vxor		$inout,$inout,$tweak1		# :-)
+
+Loop_xts_dec_short:
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vncipher	$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+	bdnz		Loop_xts_dec_short
+
+	?vperm		$rndkey1,$rndkey1,$rndkey0,$keyperm
+	vncipher	$inout,$inout,$rndkey1
+	lvx		$rndkey1,$idx,$key1
+	li		$idx,16
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+	vxor		$rndkey0,$rndkey0,$tweak1
+	vncipherlast	$output,$inout,$rndkey0
+
+	le?vperm	$tmp,$output,$output,$leperm
+	be?nop
+	le?stvx_u	$tmp,0,$out
+	be?stvx_u	$output,0,$out
+
+	vmr		$inout,$inptail
+	lvx		$inptail,0,$inp
+	#addi		$inp,$inp,16
+	lvx		$rndkey0,0,$key1
+	lvx		$rndkey1,$idx,$key1
+	addi		$idx,$idx,16
+	vperm		$inout,$inout,$inptail,$inpperm
+	?vperm		$rndkey0,$rndkey0,$rndkey1,$keyperm
+
+	lvsr		$inpperm,0,$len			# $inpperm is no longer needed
+	vxor		$inptail,$inptail,$inptail	# $inptail is no longer needed
+	vspltisb	$tmp,-1
+	vperm		$inptail,$inptail,$tmp,$inpperm
+	vsel		$inout,$inout,$output,$inptail
+
+	vxor		$rndkey0,$rndkey0,$tweak
+	vxor		$inout,$inout,$rndkey0
+	lvx		$rndkey0,$idx,$key1
+	addi		$idx,$idx,16
+
+	subi		r11,$out,1
+	mtctr		$len
+	li		$len,16
+Loop_xts_dec_steal:
+	lbzu		r0,1(r11)
+	stb		r0,16(r11)
+	bdnz		Loop_xts_dec_steal
+
+	mtctr		$rounds
+	b		Loop_xts_dec			# one more time...
+
+Lxts_dec_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_dec_ret
+
+	vsrab		$tmp,$tweak,$seven		# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	vxor		$tweak,$tweak,$tmp
+
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_dec_ret:
+	mtspr		256,r12				# restore vrsave
+	li		r3,0
+	blr
+	.long		0
+	.byte		0,12,0x04,0,0x80,6,6,0
+	.long		0
+.size	.${prefix}_xts_decrypt,.-.${prefix}_xts_decrypt
+___
+#########################################################################
+{{	# Optimized XTS procedures					#
+my $key_=$key2;
+my ($x00,$x10,$x20,$x30,$x40,$x50,$x60,$x70)=map("r$_",(0,3,26..31));
+    $x00=0 if ($flavour =~ /osx/);
+my ($in0,  $in1,  $in2,  $in3,  $in4,  $in5 )=map("v$_",(0..5));
+my ($out0, $out1, $out2, $out3, $out4, $out5)=map("v$_",(7,12..16));
+my ($twk0, $twk1, $twk2, $twk3, $twk4, $twk5)=map("v$_",(17..22));
+my $rndkey0="v23";	# v24-v25 rotating buffer for first found keys
+			# v26-v31 last 6 round keys
+my ($keyperm)=($out0);	# aliases with "caller", redundant assignment
+my $taillen=$x70;
+
+$code.=<<___;
+.align	5
+_aesp8_xts_encrypt6x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	mflr		r11
+	li		r7,`$FRAME+8*16+15`
+	li		r3,`$FRAME+8*16+31`
+	$PUSH		r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+	stvx		v20,r7,$sp		# ABI says so
+	addi		r7,r7,32
+	stvx		v21,r3,$sp
+	addi		r3,r3,32
+	stvx		v22,r7,$sp
+	addi		r7,r7,32
+	stvx		v23,r3,$sp
+	addi		r3,r3,32
+	stvx		v24,r7,$sp
+	addi		r7,r7,32
+	stvx		v25,r3,$sp
+	addi		r3,r3,32
+	stvx		v26,r7,$sp
+	addi		r7,r7,32
+	stvx		v27,r3,$sp
+	addi		r3,r3,32
+	stvx		v28,r7,$sp
+	addi		r7,r7,32
+	stvx		v29,r3,$sp
+	addi		r3,r3,32
+	stvx		v30,r7,$sp
+	stvx		v31,r3,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key1	# load key schedule
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	lvx		v31,$x00,$key1
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_xts_enc_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key1
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_xts_enc_key
+
+	lvx		v26,$x10,$key1
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key1
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key1
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key1
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key1
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key1
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$twk5,$x70,$key1	# borrow $twk5
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$twk5,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	 vperm		$in0,$inout,$inptail,$inpperm
+	 subi		$inp,$inp,31		# undo "caller"
+	vxor		$twk0,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out0,$in0,$twk0
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in1,$x10,$inp
+	vxor		$twk1,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in1,$in1,$in1,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out1,$in1,$twk1
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in2,$x20,$inp
+	 andi.		$taillen,$len,15
+	vxor		$twk2,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in2,$in2,$in2,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out2,$in2,$twk2
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in3,$x30,$inp
+	 sub		$len,$len,$taillen
+	vxor		$twk3,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in3,$in3,$in3,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out3,$in3,$twk3
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in4,$x40,$inp
+	 subi		$len,$len,0x60
+	vxor		$twk4,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in4,$in4,$in4,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out4,$in4,$twk4
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	vxor		$twk5,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in5,$in5,$in5,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out5,$in5,$twk5
+	vxor		$tweak,$tweak,$tmp
+
+	vxor		v31,v31,$rndkey0
+	mtctr		$rounds
+	b		Loop_xts_enc6x
+
+.align	5
+Loop_xts_enc6x:
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	vcipher		$out5,$out5,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_enc6x
+
+	subic		$len,$len,96		# $len-=96
+	 vxor		$in0,$twk0,v31		# xor with last round key
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk0,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out4,$out4,v24
+	vcipher		$out5,$out5,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	 vxor		$in1,$twk1,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk1,$tweak,$rndkey0
+	vcipher		$out4,$out4,v25
+	vcipher		$out5,$out5,v25
+
+	and		r0,r0,$len
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out0,$out0,v26
+	vcipher		$out1,$out1,v26
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out4,$out4,v26
+	vcipher		$out5,$out5,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in5 are loaded
+						# with last "words"
+	 vxor		$in2,$twk2,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk2,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vcipher		$out0,$out0,v27
+	vcipher		$out1,$out1,v27
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out4,$out4,v27
+	vcipher		$out5,$out5,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out0,$out0,v28
+	vcipher		$out1,$out1,v28
+	 vxor		$in3,$twk3,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk3,$tweak,$rndkey0
+	vcipher		$out2,$out2,v28
+	vcipher		$out3,$out3,v28
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipher		$out4,$out4,v28
+	vcipher		$out5,$out5,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vand		$tmp,$tmp,$eighty7
+
+	vcipher		$out0,$out0,v29
+	vcipher		$out1,$out1,v29
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out2,$out2,v29
+	vcipher		$out3,$out3,v29
+	 vxor		$in4,$twk4,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk4,$tweak,$rndkey0
+	vcipher		$out4,$out4,v29
+	vcipher		$out5,$out5,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+
+	vcipher		$out0,$out0,v30
+	vcipher		$out1,$out1,v30
+	 vand		$tmp,$tmp,$eighty7
+	vcipher		$out2,$out2,v30
+	vcipher		$out3,$out3,v30
+	 vxor		$tweak,$tweak,$tmp
+	vcipher		$out4,$out4,v30
+	vcipher		$out5,$out5,v30
+	 vxor		$in5,$twk5,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk5,$tweak,$rndkey0
+
+	vcipherlast	$out0,$out0,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vcipherlast	$out1,$out1,$in1
+	 lvx_u		$in1,$x10,$inp
+	vcipherlast	$out2,$out2,$in2
+	 le?vperm	$in0,$in0,$in0,$leperm
+	 lvx_u		$in2,$x20,$inp
+	 vand		$tmp,$tmp,$eighty7
+	vcipherlast	$out3,$out3,$in3
+	 le?vperm	$in1,$in1,$in1,$leperm
+	 lvx_u		$in3,$x30,$inp
+	vcipherlast	$out4,$out4,$in4
+	 le?vperm	$in2,$in2,$in2,$leperm
+	 lvx_u		$in4,$x40,$inp
+	 vxor		$tweak,$tweak,$tmp
+	vcipherlast	$tmp,$out5,$in5		# last block might be needed
+						# in stealing mode
+	 le?vperm	$in3,$in3,$in3,$leperm
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	 le?vperm	$in4,$in4,$in4,$leperm
+	 le?vperm	$in5,$in5,$in5,$leperm
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	 vxor		$out0,$in0,$twk0
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	 vxor		$out1,$in1,$twk1
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$twk2
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$twk3
+	le?vperm	$out5,$tmp,$tmp,$leperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$twk4
+	le?stvx_u	$out5,$x50,$out
+	be?stvx_u	$tmp, $x50,$out
+	 vxor		$out5,$in5,$twk5
+	addi		$out,$out,0x60
+
+	mtctr		$rounds
+	beq		Loop_xts_enc6x		# did $len-=96 borrow?
+
+	addic.		$len,$len,0x60
+	beq		Lxts_enc6x_zero
+	cmpwi		$len,0x20
+	blt		Lxts_enc6x_one
+	nop
+	beq		Lxts_enc6x_two
+	cmpwi		$len,0x40
+	blt		Lxts_enc6x_three
+	nop
+	beq		Lxts_enc6x_four
+
+Lxts_enc6x_five:
+	vxor		$out0,$in1,$twk0
+	vxor		$out1,$in2,$twk1
+	vxor		$out2,$in3,$twk2
+	vxor		$out3,$in4,$twk3
+	vxor		$out4,$in5,$twk4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk5		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	vxor		$tmp,$out4,$twk5	# last block prep for stealing
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_four:
+	vxor		$out0,$in2,$twk0
+	vxor		$out1,$in3,$twk1
+	vxor		$out2,$in4,$twk2
+	vxor		$out3,$in5,$twk3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk4		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	vxor		$tmp,$out3,$twk4	# last block prep for stealing
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_three:
+	vxor		$out0,$in3,$twk0
+	vxor		$out1,$in4,$twk1
+	vxor		$out2,$in5,$twk2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk3		# unused tweak
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$tmp,$out2,$twk3	# last block prep for stealing
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_two:
+	vxor		$out0,$in4,$twk0
+	vxor		$out1,$in5,$twk1
+	vxor		$out2,$out2,$out2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_enc5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk2		# unused tweak
+	vxor		$tmp,$out1,$twk2	# last block prep for stealing
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_one:
+	vxor		$out0,$in5,$twk0
+	nop
+Loop_xts_enc1x:
+	vcipher		$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_enc1x
+
+	add		$inp,$inp,$taillen
+	cmpwi		$taillen,0
+	vcipher		$out0,$out0,v24
+
+	subi		$inp,$inp,16
+	vcipher		$out0,$out0,v25
+
+	lvsr		$inpperm,0,$taillen
+	vcipher		$out0,$out0,v26
+
+	lvx_u		$in0,0,$inp
+	vcipher		$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vcipher		$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk0,$twk0,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vcipher		$out0,$out0,v30
+
+	vperm		$in0,$in0,$in0,$inpperm
+	vcipherlast	$out0,$out0,$twk0
+
+	vmr		$twk0,$twk1		# unused tweak
+	vxor		$tmp,$out0,$twk1	# last block prep for stealing
+	le?vperm	$out0,$out0,$out0,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	addi		$out,$out,0x10
+	bne		Lxts_enc6x_steal
+	b		Lxts_enc6x_done
+
+.align	4
+Lxts_enc6x_zero:
+	cmpwi		$taillen,0
+	beq		Lxts_enc6x_done
+
+	add		$inp,$inp,$taillen
+	subi		$inp,$inp,16
+	lvx_u		$in0,0,$inp
+	lvsr		$inpperm,0,$taillen	# $in5 is no more
+	le?vperm	$in0,$in0,$in0,$leperm
+	vperm		$in0,$in0,$in0,$inpperm
+	vxor		$tmp,$tmp,$twk0
+Lxts_enc6x_steal:
+	vxor		$in0,$in0,$twk0
+	vxor		$out0,$out0,$out0
+	vspltisb	$out1,-1
+	vperm		$out0,$out0,$out1,$inpperm
+	vsel		$out0,$in0,$tmp,$out0	# $tmp is last block, remember?
+
+	subi		r30,$out,17
+	subi		$out,$out,16
+	mtctr		$taillen
+Loop_xts_enc6x_steal:
+	lbzu		r0,1(r30)
+	stb		r0,16(r30)
+	bdnz		Loop_xts_enc6x_steal
+
+	li		$taillen,0
+	mtctr		$rounds
+	b		Loop_xts_enc1x		# one more time...
+
+.align	4
+Lxts_enc6x_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_enc6x_ret
+
+	vxor		$tweak,$twk0,$rndkey0
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_enc6x_ret:
+	mtlr		r11
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$seven,r10,$sp		# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x04,1,0x80,6,6,0
+	.long		0
+
+.align	5
+_aesp8_xts_enc5x:
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		_aesp8_xts_enc5x
+
+	add		$inp,$inp,$taillen
+	cmpwi		$taillen,0
+	vcipher		$out0,$out0,v24
+	vcipher		$out1,$out1,v24
+	vcipher		$out2,$out2,v24
+	vcipher		$out3,$out3,v24
+	vcipher		$out4,$out4,v24
+
+	subi		$inp,$inp,16
+	vcipher		$out0,$out0,v25
+	vcipher		$out1,$out1,v25
+	vcipher		$out2,$out2,v25
+	vcipher		$out3,$out3,v25
+	vcipher		$out4,$out4,v25
+	 vxor		$twk0,$twk0,v31
+
+	vcipher		$out0,$out0,v26
+	lvsr		$inpperm,r0,$taillen	# $in5 is no more
+	vcipher		$out1,$out1,v26
+	vcipher		$out2,$out2,v26
+	vcipher		$out3,$out3,v26
+	vcipher		$out4,$out4,v26
+	 vxor		$in1,$twk1,v31
+
+	vcipher		$out0,$out0,v27
+	lvx_u		$in0,0,$inp
+	vcipher		$out1,$out1,v27
+	vcipher		$out2,$out2,v27
+	vcipher		$out3,$out3,v27
+	vcipher		$out4,$out4,v27
+	 vxor		$in2,$twk2,v31
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vcipher		$out0,$out0,v28
+	vcipher		$out1,$out1,v28
+	vcipher		$out2,$out2,v28
+	vcipher		$out3,$out3,v28
+	vcipher		$out4,$out4,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vxor		$in3,$twk3,v31
+
+	vcipher		$out0,$out0,v29
+	le?vperm	$in0,$in0,$in0,$leperm
+	vcipher		$out1,$out1,v29
+	vcipher		$out2,$out2,v29
+	vcipher		$out3,$out3,v29
+	vcipher		$out4,$out4,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$in4,$twk4,v31
+
+	vcipher		$out0,$out0,v30
+	vperm		$in0,$in0,$in0,$inpperm
+	vcipher		$out1,$out1,v30
+	vcipher		$out2,$out2,v30
+	vcipher		$out3,$out3,v30
+	vcipher		$out4,$out4,v30
+
+	vcipherlast	$out0,$out0,$twk0
+	vcipherlast	$out1,$out1,$in1
+	vcipherlast	$out2,$out2,$in2
+	vcipherlast	$out3,$out3,$in3
+	vcipherlast	$out4,$out4,$in4
+	blr
+        .long   	0
+        .byte   	0,12,0x14,0,0,0,0,0
+
+.align	5
+_aesp8_xts_decrypt6x:
+	$STU		$sp,-`($FRAME+21*16+6*$SIZE_T)`($sp)
+	mflr		r11
+	li		r7,`$FRAME+8*16+15`
+	li		r3,`$FRAME+8*16+31`
+	$PUSH		r11,`$FRAME+21*16+6*$SIZE_T+$LRSAVE`($sp)
+	stvx		v20,r7,$sp		# ABI says so
+	addi		r7,r7,32
+	stvx		v21,r3,$sp
+	addi		r3,r3,32
+	stvx		v22,r7,$sp
+	addi		r7,r7,32
+	stvx		v23,r3,$sp
+	addi		r3,r3,32
+	stvx		v24,r7,$sp
+	addi		r7,r7,32
+	stvx		v25,r3,$sp
+	addi		r3,r3,32
+	stvx		v26,r7,$sp
+	addi		r7,r7,32
+	stvx		v27,r3,$sp
+	addi		r3,r3,32
+	stvx		v28,r7,$sp
+	addi		r7,r7,32
+	stvx		v29,r3,$sp
+	addi		r3,r3,32
+	stvx		v30,r7,$sp
+	stvx		v31,r3,$sp
+	li		r0,-1
+	stw		$vrsave,`$FRAME+21*16-4`($sp)	# save vrsave
+	li		$x10,0x10
+	$PUSH		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	li		$x20,0x20
+	$PUSH		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	li		$x30,0x30
+	$PUSH		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	li		$x40,0x40
+	$PUSH		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	li		$x50,0x50
+	$PUSH		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	li		$x60,0x60
+	$PUSH		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	li		$x70,0x70
+	mtspr		256,r0
+
+	subi		$rounds,$rounds,3	# -4 in total
+
+	lvx		$rndkey0,$x00,$key1	# load key schedule
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	lvx		v31,$x00,$key1
+	?vperm		$rndkey0,$rndkey0,v30,$keyperm
+	addi		$key_,$sp,$FRAME+15
+	mtctr		$rounds
+
+Load_xts_dec_key:
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v30,$x10,$key1
+	addi		$key1,$key1,0x20
+	stvx		v24,$x00,$key_		# off-load round[1]
+	?vperm		v25,v31,v30,$keyperm
+	lvx		v31,$x00,$key1
+	stvx		v25,$x10,$key_		# off-load round[2]
+	addi		$key_,$key_,0x20
+	bdnz		Load_xts_dec_key
+
+	lvx		v26,$x10,$key1
+	?vperm		v24,v30,v31,$keyperm
+	lvx		v27,$x20,$key1
+	stvx		v24,$x00,$key_		# off-load round[3]
+	?vperm		v25,v31,v26,$keyperm
+	lvx		v28,$x30,$key1
+	stvx		v25,$x10,$key_		# off-load round[4]
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	?vperm		v26,v26,v27,$keyperm
+	lvx		v29,$x40,$key1
+	?vperm		v27,v27,v28,$keyperm
+	lvx		v30,$x50,$key1
+	?vperm		v28,v28,v29,$keyperm
+	lvx		v31,$x60,$key1
+	?vperm		v29,v29,v30,$keyperm
+	lvx		$twk5,$x70,$key1	# borrow $twk5
+	?vperm		v30,v30,v31,$keyperm
+	lvx		v24,$x00,$key_		# pre-load round[1]
+	?vperm		v31,v31,$twk5,$keyperm
+	lvx		v25,$x10,$key_		# pre-load round[2]
+
+	 vperm		$in0,$inout,$inptail,$inpperm
+	 subi		$inp,$inp,31		# undo "caller"
+	vxor		$twk0,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out0,$in0,$twk0
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in1,$x10,$inp
+	vxor		$twk1,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in1,$in1,$in1,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out1,$in1,$twk1
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in2,$x20,$inp
+	 andi.		$taillen,$len,15
+	vxor		$twk2,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in2,$in2,$in2,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out2,$in2,$twk2
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in3,$x30,$inp
+	 sub		$len,$len,$taillen
+	vxor		$twk3,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in3,$in3,$in3,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out3,$in3,$twk3
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in4,$x40,$inp
+	 subi		$len,$len,0x60
+	vxor		$twk4,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in4,$in4,$in4,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out4,$in4,$twk4
+	vxor		$tweak,$tweak,$tmp
+
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	vxor		$twk5,$tweak,$rndkey0
+	vsrab		$tmp,$tweak,$seven	# next tweak value
+	vaddubm		$tweak,$tweak,$tweak
+	vsldoi		$tmp,$tmp,$tmp,15
+	 le?vperm	$in5,$in5,$in5,$leperm
+	vand		$tmp,$tmp,$eighty7
+	 vxor		$out5,$in5,$twk5
+	vxor		$tweak,$tweak,$tmp
+
+	vxor		v31,v31,$rndkey0
+	mtctr		$rounds
+	b		Loop_xts_dec6x
+
+.align	5
+Loop_xts_dec6x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_dec6x
+
+	subic		$len,$len,96		# $len-=96
+	 vxor		$in0,$twk0,v31		# xor with last round key
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk0,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out4,$out4,v24
+	vncipher	$out5,$out5,v24
+
+	subfe.		r0,r0,r0		# borrow?-1:0
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	 vxor		$in1,$twk1,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk1,$tweak,$rndkey0
+	vncipher	$out4,$out4,v25
+	vncipher	$out5,$out5,v25
+
+	and		r0,r0,$len
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out4,$out4,v26
+	vncipher	$out5,$out5,v26
+
+	add		$inp,$inp,r0		# $inp is adjusted in such
+						# way that at exit from the
+						# loop inX-in5 are loaded
+						# with last "words"
+	 vxor		$in2,$twk2,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk2,$tweak,$rndkey0
+	 vaddubm	$tweak,$tweak,$tweak
+	vncipher	$out0,$out0,v27
+	vncipher	$out1,$out1,v27
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out4,$out4,v27
+	vncipher	$out5,$out5,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	 vxor		$in3,$twk3,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk3,$tweak,$rndkey0
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipher	$out4,$out4,v28
+	vncipher	$out5,$out5,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vand		$tmp,$tmp,$eighty7
+
+	vncipher	$out0,$out0,v29
+	vncipher	$out1,$out1,v29
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	 vxor		$in4,$twk4,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk4,$tweak,$rndkey0
+	vncipher	$out4,$out4,v29
+	vncipher	$out5,$out5,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+
+	vncipher	$out0,$out0,v30
+	vncipher	$out1,$out1,v30
+	 vand		$tmp,$tmp,$eighty7
+	vncipher	$out2,$out2,v30
+	vncipher	$out3,$out3,v30
+	 vxor		$tweak,$tweak,$tmp
+	vncipher	$out4,$out4,v30
+	vncipher	$out5,$out5,v30
+	 vxor		$in5,$twk5,v31
+	 vsrab		$tmp,$tweak,$seven	# next tweak value
+	 vxor		$twk5,$tweak,$rndkey0
+
+	vncipherlast	$out0,$out0,$in0
+	 lvx_u		$in0,$x00,$inp		# load next input block
+	 vaddubm	$tweak,$tweak,$tweak
+	 vsldoi		$tmp,$tmp,$tmp,15
+	vncipherlast	$out1,$out1,$in1
+	 lvx_u		$in1,$x10,$inp
+	vncipherlast	$out2,$out2,$in2
+	 le?vperm	$in0,$in0,$in0,$leperm
+	 lvx_u		$in2,$x20,$inp
+	 vand		$tmp,$tmp,$eighty7
+	vncipherlast	$out3,$out3,$in3
+	 le?vperm	$in1,$in1,$in1,$leperm
+	 lvx_u		$in3,$x30,$inp
+	vncipherlast	$out4,$out4,$in4
+	 le?vperm	$in2,$in2,$in2,$leperm
+	 lvx_u		$in4,$x40,$inp
+	 vxor		$tweak,$tweak,$tmp
+	vncipherlast	$out5,$out5,$in5
+	 le?vperm	$in3,$in3,$in3,$leperm
+	 lvx_u		$in5,$x50,$inp
+	 addi		$inp,$inp,0x60
+	 le?vperm	$in4,$in4,$in4,$leperm
+	 le?vperm	$in5,$in5,$in5,$leperm
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	 vxor		$out0,$in0,$twk0
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	 vxor		$out1,$in1,$twk1
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	 vxor		$out2,$in2,$twk2
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	 vxor		$out3,$in3,$twk3
+	le?vperm	$out5,$out5,$out5,$leperm
+	stvx_u		$out4,$x40,$out
+	 vxor		$out4,$in4,$twk4
+	stvx_u		$out5,$x50,$out
+	 vxor		$out5,$in5,$twk5
+	addi		$out,$out,0x60
+
+	mtctr		$rounds
+	beq		Loop_xts_dec6x		# did $len-=96 borrow?
+
+	addic.		$len,$len,0x60
+	beq		Lxts_dec6x_zero
+	cmpwi		$len,0x20
+	blt		Lxts_dec6x_one
+	nop
+	beq		Lxts_dec6x_two
+	cmpwi		$len,0x40
+	blt		Lxts_dec6x_three
+	nop
+	beq		Lxts_dec6x_four
+
+Lxts_dec6x_five:
+	vxor		$out0,$in1,$twk0
+	vxor		$out1,$in2,$twk1
+	vxor		$out2,$in3,$twk2
+	vxor		$out3,$in4,$twk3
+	vxor		$out4,$in5,$twk4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk5		# unused tweak
+	vxor		$twk1,$tweak,$rndkey0
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk1
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	le?vperm	$out4,$out4,$out4,$leperm
+	stvx_u		$out3,$x30,$out
+	stvx_u		$out4,$x40,$out
+	addi		$out,$out,0x50
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_four:
+	vxor		$out0,$in2,$twk0
+	vxor		$out1,$in3,$twk1
+	vxor		$out2,$in4,$twk2
+	vxor		$out3,$in5,$twk3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk4		# unused tweak
+	vmr		$twk1,$twk5
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk5
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	le?vperm	$out3,$out3,$out3,$leperm
+	stvx_u		$out2,$x20,$out
+	stvx_u		$out3,$x30,$out
+	addi		$out,$out,0x40
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_three:
+	vxor		$out0,$in3,$twk0
+	vxor		$out1,$in4,$twk1
+	vxor		$out2,$in5,$twk2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk3		# unused tweak
+	vmr		$twk1,$twk4
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk4
+	le?vperm	$out2,$out2,$out2,$leperm
+	stvx_u		$out1,$x10,$out
+	stvx_u		$out2,$x20,$out
+	addi		$out,$out,0x30
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_two:
+	vxor		$out0,$in4,$twk0
+	vxor		$out1,$in5,$twk1
+	vxor		$out2,$out2,$out2
+	vxor		$out3,$out3,$out3
+	vxor		$out4,$out4,$out4
+
+	bl		_aesp8_xts_dec5x
+
+	le?vperm	$out0,$out0,$out0,$leperm
+	vmr		$twk0,$twk2		# unused tweak
+	vmr		$twk1,$twk3
+	le?vperm	$out1,$out1,$out1,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	vxor		$out0,$in0,$twk3
+	stvx_u		$out1,$x10,$out
+	addi		$out,$out,0x20
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_one:
+	vxor		$out0,$in5,$twk0
+	nop
+Loop_xts_dec1x:
+	vncipher	$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Loop_xts_dec1x
+
+	subi		r0,$taillen,1
+	vncipher	$out0,$out0,v24
+
+	andi.		r0,r0,16
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+
+	sub		$inp,$inp,r0
+	vncipher	$out0,$out0,v26
+
+	lvx_u		$in0,0,$inp
+	vncipher	$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk0,$twk0,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out0,$out0,v30
+
+	mtctr		$rounds
+	vncipherlast	$out0,$out0,$twk0
+
+	vmr		$twk0,$twk1		# unused tweak
+	vmr		$twk1,$twk2
+	le?vperm	$out0,$out0,$out0,$leperm
+	stvx_u		$out0,$x00,$out		# store output
+	addi		$out,$out,0x10
+	vxor		$out0,$in0,$twk2
+	bne		Lxts_dec6x_steal
+	b		Lxts_dec6x_done
+
+.align	4
+Lxts_dec6x_zero:
+	cmpwi		$taillen,0
+	beq		Lxts_dec6x_done
+
+	lvx_u		$in0,0,$inp
+	le?vperm	$in0,$in0,$in0,$leperm
+	vxor		$out0,$in0,$twk1
+Lxts_dec6x_steal:
+	vncipher	$out0,$out0,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		Lxts_dec6x_steal
+
+	add		$inp,$inp,$taillen
+	vncipher	$out0,$out0,v24
+
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+
+	lvx_u		$in0,0,$inp
+	vncipher	$out0,$out0,v26
+
+	lvsr		$inpperm,0,$taillen	# $in5 is no more
+	vncipher	$out0,$out0,v27
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+
+	vncipher	$out0,$out0,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$twk1,$twk1,v31
+
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out0,$out0,v30
+
+	vperm		$in0,$in0,$in0,$inpperm
+	vncipherlast	$tmp,$out0,$twk1
+
+	le?vperm	$out0,$tmp,$tmp,$leperm
+	le?stvx_u	$out0,0,$out
+	be?stvx_u	$tmp,0,$out
+
+	vxor		$out0,$out0,$out0
+	vspltisb	$out1,-1
+	vperm		$out0,$out0,$out1,$inpperm
+	vsel		$out0,$in0,$tmp,$out0
+	vxor		$out0,$out0,$twk0
+
+	subi		r30,$out,1
+	mtctr		$taillen
+Loop_xts_dec6x_steal:
+	lbzu		r0,1(r30)
+	stb		r0,16(r30)
+	bdnz		Loop_xts_dec6x_steal
+
+	li		$taillen,0
+	mtctr		$rounds
+	b		Loop_xts_dec1x		# one more time...
+
+.align	4
+Lxts_dec6x_done:
+	${UCMP}i	$ivp,0
+	beq		Lxts_dec6x_ret
+
+	vxor		$tweak,$twk0,$rndkey0
+	le?vperm	$tweak,$tweak,$tweak,$leperm
+	stvx_u		$tweak,0,$ivp
+
+Lxts_dec6x_ret:
+	mtlr		r11
+	li		r10,`$FRAME+15`
+	li		r11,`$FRAME+31`
+	stvx		$seven,r10,$sp		# wipe copies of round keys
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+	stvx		$seven,r10,$sp
+	addi		r10,r10,32
+	stvx		$seven,r11,$sp
+	addi		r11,r11,32
+
+	mtspr		256,$vrsave
+	lvx		v20,r10,$sp		# ABI says so
+	addi		r10,r10,32
+	lvx		v21,r11,$sp
+	addi		r11,r11,32
+	lvx		v22,r10,$sp
+	addi		r10,r10,32
+	lvx		v23,r11,$sp
+	addi		r11,r11,32
+	lvx		v24,r10,$sp
+	addi		r10,r10,32
+	lvx		v25,r11,$sp
+	addi		r11,r11,32
+	lvx		v26,r10,$sp
+	addi		r10,r10,32
+	lvx		v27,r11,$sp
+	addi		r11,r11,32
+	lvx		v28,r10,$sp
+	addi		r10,r10,32
+	lvx		v29,r11,$sp
+	addi		r11,r11,32
+	lvx		v30,r10,$sp
+	lvx		v31,r11,$sp
+	$POP		r26,`$FRAME+21*16+0*$SIZE_T`($sp)
+	$POP		r27,`$FRAME+21*16+1*$SIZE_T`($sp)
+	$POP		r28,`$FRAME+21*16+2*$SIZE_T`($sp)
+	$POP		r29,`$FRAME+21*16+3*$SIZE_T`($sp)
+	$POP		r30,`$FRAME+21*16+4*$SIZE_T`($sp)
+	$POP		r31,`$FRAME+21*16+5*$SIZE_T`($sp)
+	addi		$sp,$sp,`$FRAME+21*16+6*$SIZE_T`
+	blr
+	.long		0
+	.byte		0,12,0x04,1,0x80,6,6,0
+	.long		0
+
+.align	5
+_aesp8_xts_dec5x:
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+	lvx		v24,$x20,$key_		# round[3]
+	addi		$key_,$key_,0x20
+
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	lvx		v25,$x10,$key_		# round[4]
+	bdnz		_aesp8_xts_dec5x
+
+	subi		r0,$taillen,1
+	vncipher	$out0,$out0,v24
+	vncipher	$out1,$out1,v24
+	vncipher	$out2,$out2,v24
+	vncipher	$out3,$out3,v24
+	vncipher	$out4,$out4,v24
+
+	andi.		r0,r0,16
+	cmpwi		$taillen,0
+	vncipher	$out0,$out0,v25
+	vncipher	$out1,$out1,v25
+	vncipher	$out2,$out2,v25
+	vncipher	$out3,$out3,v25
+	vncipher	$out4,$out4,v25
+	 vxor		$twk0,$twk0,v31
+
+	sub		$inp,$inp,r0
+	vncipher	$out0,$out0,v26
+	vncipher	$out1,$out1,v26
+	vncipher	$out2,$out2,v26
+	vncipher	$out3,$out3,v26
+	vncipher	$out4,$out4,v26
+	 vxor		$in1,$twk1,v31
+
+	vncipher	$out0,$out0,v27
+	lvx_u		$in0,0,$inp
+	vncipher	$out1,$out1,v27
+	vncipher	$out2,$out2,v27
+	vncipher	$out3,$out3,v27
+	vncipher	$out4,$out4,v27
+	 vxor		$in2,$twk2,v31
+
+	addi		$key_,$sp,$FRAME+15	# rewind $key_
+	vncipher	$out0,$out0,v28
+	vncipher	$out1,$out1,v28
+	vncipher	$out2,$out2,v28
+	vncipher	$out3,$out3,v28
+	vncipher	$out4,$out4,v28
+	lvx		v24,$x00,$key_		# re-pre-load round[1]
+	 vxor		$in3,$twk3,v31
+
+	vncipher	$out0,$out0,v29
+	le?vperm	$in0,$in0,$in0,$leperm
+	vncipher	$out1,$out1,v29
+	vncipher	$out2,$out2,v29
+	vncipher	$out3,$out3,v29
+	vncipher	$out4,$out4,v29
+	lvx		v25,$x10,$key_		# re-pre-load round[2]
+	 vxor		$in4,$twk4,v31
+
+	vncipher	$out0,$out0,v30
+	vncipher	$out1,$out1,v30
+	vncipher	$out2,$out2,v30
+	vncipher	$out3,$out3,v30
+	vncipher	$out4,$out4,v30
+
+	vncipherlast	$out0,$out0,$twk0
+	vncipherlast	$out1,$out1,$in1
+	vncipherlast	$out2,$out2,$in2
+	vncipherlast	$out3,$out3,$in3
+	vncipherlast	$out4,$out4,$in4
+	mtctr		$rounds
+	blr
+        .long   	0
+        .byte   	0,12,0x14,0,0,0,0,0
+___
+}}	}}}
+
 my $consts=1;
 foreach(split("\n",$code)) {
         s/\`([^\`]*)\`/eval($1)/geo;
@@ -1898,7 +3757,7 @@
 	    if ($flavour =~ /le$/o) {
 		SWITCH: for($conv)  {
 		    /\?inv/ && do   { @bytes=map($_^0xf,@bytes); last; };
-		    /\?rev/ && do   { @bytes=reverse(@bytes);    last; }; 
+		    /\?rev/ && do   { @bytes=reverse(@bytes);    last; };
 		}
 	    }
 
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index e163d57..f688c32 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -31,10 +31,12 @@
 extern struct crypto_alg p8_aes_alg;
 extern struct crypto_alg p8_aes_cbc_alg;
 extern struct crypto_alg p8_aes_ctr_alg;
+extern struct crypto_alg p8_aes_xts_alg;
 static struct crypto_alg *algs[] = {
 	&p8_aes_alg,
 	&p8_aes_cbc_alg,
 	&p8_aes_ctr_alg,
+	&p8_aes_xts_alg,
 	NULL,
 };
 
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index e9e5ae5..6e70597 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -260,11 +260,12 @@
 	tristate "ChaosKey random number generator driver support"
 	depends on HW_RANDOM
 	help
-	  Say Y here if you want to connect an AltusMetrum ChaosKey to
-	  your computer's USB port. The ChaosKey is a hardware random
-	  number generator which hooks into the kernel entropy pool to
-	  ensure a large supply of entropy for /dev/random and
-	  /dev/urandom and also provides direct access via /dev/chaoskeyX
+	  Say Y here if you want to connect an AltusMetrum ChaosKey or
+	  Araneus Alea I to your computer's USB port. These devices
+	  are hardware random number generators which hook into the
+	  kernel entropy pool to ensure a large supply of entropy for
+	  /dev/random and /dev/urandom and also provides direct access
+	  via /dev/chaoskeyX
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called chaoskey.
diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c
index 76350e4..6ddd08a 100644
--- a/drivers/usb/misc/chaoskey.c
+++ b/drivers/usb/misc/chaoskey.c
@@ -55,9 +55,13 @@
 #define CHAOSKEY_VENDOR_ID	0x1d50	/* OpenMoko */
 #define CHAOSKEY_PRODUCT_ID	0x60c6	/* ChaosKey */
 
+#define ALEA_VENDOR_ID		0x12d8	/* Araneus */
+#define ALEA_PRODUCT_ID		0x0001	/* Alea I */
+
 #define CHAOSKEY_BUF_LEN	64	/* max size of USB full speed packet */
 
-#define NAK_TIMEOUT (HZ)		/* stall/wait timeout for device */
+#define NAK_TIMEOUT (HZ)		/* normal stall/wait timeout */
+#define ALEA_FIRST_TIMEOUT (HZ*3)	/* first stall/wait timeout for Alea */
 
 #ifdef CONFIG_USB_DYNAMIC_MINORS
 #define USB_CHAOSKEY_MINOR_BASE 0
@@ -69,6 +73,7 @@
 
 static const struct usb_device_id chaoskey_table[] = {
 	{ USB_DEVICE(CHAOSKEY_VENDOR_ID, CHAOSKEY_PRODUCT_ID) },
+	{ USB_DEVICE(ALEA_VENDOR_ID, ALEA_PRODUCT_ID) },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, chaoskey_table);
@@ -84,6 +89,7 @@
 	int open;			/* open count */
 	bool present;			/* device not disconnected */
 	bool reading;			/* ongoing IO */
+	bool reads_started;		/* track first read for Alea */
 	int size;			/* size of buf */
 	int valid;			/* bytes of buf read */
 	int used;			/* bytes of buf consumed */
@@ -188,6 +194,9 @@
 
 	dev->in_ep = in_ep;
 
+	if (udev->descriptor.idVendor != ALEA_VENDOR_ID)
+		dev->reads_started = 1;
+
 	dev->size = size;
 	dev->present = 1;
 
@@ -357,6 +366,7 @@
 {
 	DEFINE_WAIT(wait);
 	int result;
+	bool started;
 
 	usb_dbg(dev->interface, "fill");
 
@@ -389,10 +399,17 @@
 		goto out;
 	}
 
+	/* The first read on the Alea takes a little under 2 seconds.
+	 * Reads after the first read take only a few microseconds
+	 * though.  Presumably the entropy-generating circuit needs
+	 * time to ramp up.  So, we wait longer on the first read.
+	 */
+	started = dev->reads_started;
+	dev->reads_started = true;
 	result = wait_event_interruptible_timeout(
 		dev->wait_q,
 		!dev->reading,
-		NAK_TIMEOUT);
+		(started ? NAK_TIMEOUT : ALEA_FIRST_TIMEOUT) );
 
 	if (result < 0)
 		goto out;
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 002b81f..7ef015e 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -585,6 +585,16 @@
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64
+#define ioread64 ioread64
+static inline u64 ioread64(const volatile void __iomem *addr)
+{
+	return readq(addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite8
 #define iowrite8 iowrite8
 static inline void iowrite8(u8 value, volatile void __iomem *addr)
@@ -609,11 +619,21 @@
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef iowrite64
+#define iowrite64 iowrite64
+static inline void iowrite64(u64 value, volatile void __iomem *addr)
+{
+	writeq(value, addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef ioread16be
 #define ioread16be ioread16be
 static inline u16 ioread16be(const volatile void __iomem *addr)
 {
-	return __be16_to_cpu(__raw_readw(addr));
+	return swab16(readw(addr));
 }
 #endif
 
@@ -621,15 +641,25 @@
 #define ioread32be ioread32be
 static inline u32 ioread32be(const volatile void __iomem *addr)
 {
-	return __be32_to_cpu(__raw_readl(addr));
+	return swab32(readl(addr));
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64be
+#define ioread64be ioread64be
+static inline u64 ioread64be(const volatile void __iomem *addr)
+{
+	return swab64(readq(addr));
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite16be
 #define iowrite16be iowrite16be
 static inline void iowrite16be(u16 value, void volatile __iomem *addr)
 {
-	__raw_writew(__cpu_to_be16(value), addr);
+	writew(swab16(value), addr);
 }
 #endif
 
@@ -637,10 +667,20 @@
 #define iowrite32be iowrite32be
 static inline void iowrite32be(u32 value, volatile void __iomem *addr)
 {
-	__raw_writel(__cpu_to_be32(value), addr);
+	writel(swab32(value), addr);
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef iowrite64be
+#define iowrite64be iowrite64be
+static inline void iowrite64be(u64 value, volatile void __iomem *addr)
+{
+	writeq(swab64(value), addr);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef ioread8_rep
 #define ioread8_rep ioread8_rep
 static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer,
@@ -668,6 +708,17 @@
 }
 #endif
 
+#ifdef CONFIG_64BIT
+#ifndef ioread64_rep
+#define ioread64_rep ioread64_rep
+static inline void ioread64_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsq(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_64BIT */
+
 #ifndef iowrite8_rep
 #define iowrite8_rep iowrite8_rep
 static inline void iowrite8_rep(volatile void __iomem *addr,
@@ -697,6 +748,18 @@
 	writesl(addr, buffer, count);
 }
 #endif
+
+#ifdef CONFIG_64BIT
+#ifndef iowrite64_rep
+#define iowrite64_rep iowrite64_rep
+static inline void iowrite64_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesq(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_64BIT */
 #endif /* CONFIG_GENERIC_IOMAP */
 
 #ifdef __KERNEL__
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index d8f8622..650fede 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -30,12 +30,20 @@
 extern unsigned int ioread16be(void __iomem *);
 extern unsigned int ioread32(void __iomem *);
 extern unsigned int ioread32be(void __iomem *);
+#ifdef CONFIG_64BIT
+extern u64 ioread64(void __iomem *);
+extern u64 ioread64be(void __iomem *);
+#endif
 
 extern void iowrite8(u8, void __iomem *);
 extern void iowrite16(u16, void __iomem *);
 extern void iowrite16be(u16, void __iomem *);
 extern void iowrite32(u32, void __iomem *);
 extern void iowrite32be(u32, void __iomem *);
+#ifdef CONFIG_64BIT
+extern void iowrite64(u64, void __iomem *);
+extern void iowrite64be(u64, void __iomem *);
+#endif
 
 /*
  * "string" versions of the above. Note that they
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 75174f8..12f8432 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -112,11 +112,12 @@
  *		 supplied during the decryption operation. This function is also
  *		 responsible for checking the authentication tag size for
  *		 validity.
- * @setkey: see struct ablkcipher_alg
- * @encrypt: see struct ablkcipher_alg
- * @decrypt: see struct ablkcipher_alg
- * @geniv: see struct ablkcipher_alg
- * @ivsize: see struct ablkcipher_alg
+ * @setkey: see struct skcipher_alg
+ * @encrypt: see struct skcipher_alg
+ * @decrypt: see struct skcipher_alg
+ * @geniv: see struct skcipher_alg
+ * @ivsize: see struct skcipher_alg
+ * @chunksize: see struct skcipher_alg
  * @init: Initialize the cryptographic transformation object. This function
  *	  is used to initialize the cryptographic transformation object.
  *	  This function is called only once at the instantiation time, right
@@ -145,6 +146,7 @@
 
 	unsigned int ivsize;
 	unsigned int maxauthsize;
+	unsigned int chunksize;
 
 	struct crypto_alg base;
 };
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index eeafd21..8637cdf 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -244,6 +244,8 @@
 }
 
 int crypto_attr_u32(struct rtattr *rta, u32 *num);
+int crypto_inst_setname(struct crypto_instance *inst, const char *name,
+			struct crypto_alg *alg);
 void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg,
 			     unsigned int head);
 struct crypto_instance *crypto_alloc_instance(const char *name,
@@ -440,8 +442,10 @@
 
 static inline void crypto_yield(u32 flags)
 {
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PREEMPT_VOLUNTARY)
 	if (flags & CRYPTO_TFM_REQ_MAY_SLEEP)
 		cond_resched();
+#endif
 }
 
 #endif	/* _CRYPTO_ALGAPI_H */
diff --git a/include/crypto/cryptd.h b/include/crypto/cryptd.h
index 1547f54..bc792d5 100644
--- a/include/crypto/cryptd.h
+++ b/include/crypto/cryptd.h
@@ -31,6 +31,7 @@
 struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name,
 						  u32 type, u32 mask);
 struct crypto_blkcipher *cryptd_ablkcipher_child(struct cryptd_ablkcipher *tfm);
+bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm);
 void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm);
 
 struct cryptd_ahash {
@@ -48,6 +49,8 @@
 					u32 type, u32 mask);
 struct crypto_shash *cryptd_ahash_child(struct cryptd_ahash *tfm);
 struct shash_desc *cryptd_shash_desc(struct ahash_request *req);
+/* Must be called without moving CPUs. */
+bool cryptd_ahash_queued(struct cryptd_ahash *tfm);
 void cryptd_free_ahash(struct cryptd_ahash *tfm);
 
 struct cryptd_aead {
@@ -64,6 +67,8 @@
 					  u32 type, u32 mask);
 
 struct crypto_aead *cryptd_aead_child(struct cryptd_aead *tfm);
+/* Must be called without moving CPUs. */
+bool cryptd_aead_queued(struct cryptd_aead *tfm);
 
 void cryptd_free_aead(struct cryptd_aead *tfm);
 
diff --git a/include/crypto/dh.h b/include/crypto/dh.h
new file mode 100644
index 0000000..5102a8f
--- /dev/null
+++ b/include/crypto/dh.h
@@ -0,0 +1,29 @@
+/*
+ * Diffie-Hellman secret to be used with kpp API along with helper functions
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_DH_
+#define _CRYPTO_DH_
+
+struct dh {
+	void *key;
+	void *p;
+	void *g;
+	unsigned int key_size;
+	unsigned int p_size;
+	unsigned int g_size;
+};
+
+int crypto_dh_key_len(const struct dh *params);
+int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params);
+int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params);
+
+#endif
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index d961b2b..61580b1 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -43,6 +43,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 #include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
 #include <linux/slab.h>
@@ -107,14 +108,25 @@
 struct drbg_state {
 	struct mutex drbg_mutex;	/* lock around DRBG */
 	unsigned char *V;	/* internal state 10.1.1.1 1a) */
+	unsigned char *Vbuf;
 	/* hash: static value 10.1.1.1 1b) hmac / ctr: key */
 	unsigned char *C;
+	unsigned char *Cbuf;
 	/* Number of RNG requests since last reseed -- 10.1.1.1 1c) */
 	size_t reseed_ctr;
 	size_t reseed_threshold;
 	 /* some memory the DRBG can use for its operation */
 	unsigned char *scratchpad;
+	unsigned char *scratchpadbuf;
 	void *priv_data;	/* Cipher handle */
+
+	struct crypto_skcipher *ctr_handle;	/* CTR mode cipher handle */
+	struct skcipher_request *ctr_req;	/* CTR mode request handle */
+	__u8 *ctr_null_value_buf;		/* CTR mode unaligned buffer */
+	__u8 *ctr_null_value;			/* CTR mode aligned zero buf */
+	struct completion ctr_completion;	/* CTR mode async handler */
+	int ctr_async_err;			/* CTR mode async error */
+
 	bool seeded;		/* DRBG fully seeded? */
 	bool pr;		/* Prediction resistance enabled? */
 	struct work_struct seed_work;	/* asynchronous seeding support */
diff --git a/include/crypto/ecdh.h b/include/crypto/ecdh.h
new file mode 100644
index 0000000..84bad54
--- /dev/null
+++ b/include/crypto/ecdh.h
@@ -0,0 +1,30 @@
+/*
+ * ECDH params to be used with kpp API
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_ECDH_
+#define _CRYPTO_ECDH_
+
+/* Curves IDs */
+#define ECC_CURVE_NIST_P192	0x0001
+#define ECC_CURVE_NIST_P256	0x0002
+
+struct ecdh {
+	unsigned short curve_id;
+	char *key;
+	unsigned short key_size;
+};
+
+int crypto_ecdh_key_len(const struct ecdh *params);
+int crypto_ecdh_encode_key(char *buf, unsigned int len, const struct ecdh *p);
+int crypto_ecdh_decode_key(const char *buf, unsigned int len, struct ecdh *p);
+
+#endif
diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h
index da38649..6ad8e31 100644
--- a/include/crypto/internal/aead.h
+++ b/include/crypto/internal/aead.h
@@ -159,6 +159,27 @@
 	return req ? container_of(req, struct aead_request, base) : NULL;
 }
 
+static inline unsigned int crypto_aead_alg_chunksize(struct aead_alg *alg)
+{
+	return alg->chunksize;
+}
+
+/**
+ * crypto_aead_chunksize() - obtain chunk size
+ * @tfm: cipher handle
+ *
+ * The block size is set to one for ciphers such as CCM.  However,
+ * you still need to provide incremental updates in multiples of
+ * the underlying block size as the IV does not have sub-block
+ * granularity.  This is known in this API as the chunk size.
+ *
+ * Return: chunk size in bytes
+ */
+static inline unsigned int crypto_aead_chunksize(struct crypto_aead *tfm)
+{
+	return crypto_aead_alg_chunksize(crypto_aead_alg(tfm));
+}
+
 int crypto_register_aead(struct aead_alg *alg);
 void crypto_unregister_aead(struct aead_alg *alg);
 int crypto_register_aeads(struct aead_alg *algs, int count);
diff --git a/include/crypto/internal/geniv.h b/include/crypto/internal/geniv.h
index 5933363..2bcfb93 100644
--- a/include/crypto/internal/geniv.h
+++ b/include/crypto/internal/geniv.h
@@ -20,7 +20,7 @@
 struct aead_geniv_ctx {
 	spinlock_t lock;
 	struct crypto_aead *child;
-	struct crypto_blkcipher *null;
+	struct crypto_skcipher *sknull;
 	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
 };
 
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 49dae16..1d4f365 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -114,14 +114,10 @@
 int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc);
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc);
 
-int shash_ahash_mcryptd_update(struct ahash_request *req,
-			       struct shash_desc *desc);
-int shash_ahash_mcryptd_final(struct ahash_request *req,
-			      struct shash_desc *desc);
-int shash_ahash_mcryptd_finup(struct ahash_request *req,
-			      struct shash_desc *desc);
-int shash_ahash_mcryptd_digest(struct ahash_request *req,
-			       struct shash_desc *desc);
+int ahash_mcryptd_update(struct ahash_request *desc);
+int ahash_mcryptd_final(struct ahash_request *desc);
+int ahash_mcryptd_finup(struct ahash_request *desc);
+int ahash_mcryptd_digest(struct ahash_request *desc);
 
 int crypto_init_shash_ops_async(struct crypto_tfm *tfm);
 
diff --git a/include/crypto/internal/kpp.h b/include/crypto/internal/kpp.h
new file mode 100644
index 0000000..ad3acf3
--- /dev/null
+++ b/include/crypto/internal/kpp.h
@@ -0,0 +1,64 @@
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#ifndef _CRYPTO_KPP_INT_H
+#define _CRYPTO_KPP_INT_H
+#include <crypto/kpp.h>
+#include <crypto/algapi.h>
+
+/*
+ * Transform internal helpers.
+ */
+static inline void *kpp_request_ctx(struct kpp_request *req)
+{
+	return req->__ctx;
+}
+
+static inline void *kpp_tfm_ctx(struct crypto_kpp *tfm)
+{
+	return tfm->base.__crt_ctx;
+}
+
+static inline void kpp_request_complete(struct kpp_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
+static inline const char *kpp_alg_name(struct crypto_kpp *tfm)
+{
+	return crypto_kpp_tfm(tfm)->__crt_alg->cra_name;
+}
+
+/**
+ * crypto_register_kpp() -- Register key-agreement protocol primitives algorithm
+ *
+ * Function registers an implementation of a key-agreement protocol primitive
+ * algorithm
+ *
+ * @alg:	algorithm definition
+ *
+ * Return: zero on success; error code in case of error
+ */
+int crypto_register_kpp(struct kpp_alg *alg);
+
+/**
+ * crypto_unregister_kpp() -- Unregister key-agreement protocol primitive
+ * algorithm
+ *
+ * Function unregisters an implementation of a key-agreement protocol primitive
+ * algorithm
+ *
+ * @alg:	algorithm definition
+ */
+void crypto_unregister_kpp(struct kpp_alg *alg);
+
+#endif
diff --git a/include/crypto/internal/rsa.h b/include/crypto/internal/rsa.h
index c7585bd..9e8f159 100644
--- a/include/crypto/internal/rsa.h
+++ b/include/crypto/internal/rsa.h
@@ -12,12 +12,44 @@
  */
 #ifndef _RSA_HELPER_
 #define _RSA_HELPER_
-#include <linux/mpi.h>
+#include <linux/types.h>
 
+/**
+ * rsa_key - RSA key structure
+ * @n           : RSA modulus raw byte stream
+ * @e           : RSA public exponent raw byte stream
+ * @d           : RSA private exponent raw byte stream
+ * @p           : RSA prime factor p of n raw byte stream
+ * @q           : RSA prime factor q of n raw byte stream
+ * @dp          : RSA exponent d mod (p - 1) raw byte stream
+ * @dq          : RSA exponent d mod (q - 1) raw byte stream
+ * @qinv        : RSA CRT coefficient q^(-1) mod p raw byte stream
+ * @n_sz        : length in bytes of RSA modulus n
+ * @e_sz        : length in bytes of RSA public exponent
+ * @d_sz        : length in bytes of RSA private exponent
+ * @p_sz        : length in bytes of p field
+ * @q_sz        : length in bytes of q field
+ * @dp_sz       : length in bytes of dp field
+ * @dq_sz       : length in bytes of dq field
+ * @qinv_sz     : length in bytes of qinv field
+ */
 struct rsa_key {
-	MPI n;
-	MPI e;
-	MPI d;
+	const u8 *n;
+	const u8 *e;
+	const u8 *d;
+	const u8 *p;
+	const u8 *q;
+	const u8 *dp;
+	const u8 *dq;
+	const u8 *qinv;
+	size_t n_sz;
+	size_t e_sz;
+	size_t d_sz;
+	size_t p_sz;
+	size_t q_sz;
+	size_t dp_sz;
+	size_t dq_sz;
+	size_t qinv_sz;
 };
 
 int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key,
@@ -26,7 +58,5 @@
 int rsa_parse_priv_key(struct rsa_key *rsa_key, const void *key,
 		       unsigned int key_len);
 
-void rsa_free_key(struct rsa_key *rsa_key);
-
 extern struct crypto_template rsa_pkcs1pad_tmpl;
 #endif
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index 2cf7a61..a21a95e 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -19,12 +19,46 @@
 
 struct rtattr;
 
+struct skcipher_instance {
+	void (*free)(struct skcipher_instance *inst);
+	union {
+		struct {
+			char head[offsetof(struct skcipher_alg, base)];
+			struct crypto_instance base;
+		} s;
+		struct skcipher_alg alg;
+	};
+};
+
 struct crypto_skcipher_spawn {
 	struct crypto_spawn base;
 };
 
 extern const struct crypto_type crypto_givcipher_type;
 
+static inline struct crypto_instance *skcipher_crypto_instance(
+	struct skcipher_instance *inst)
+{
+	return &inst->s.base;
+}
+
+static inline struct skcipher_instance *skcipher_alg_instance(
+	struct crypto_skcipher *skcipher)
+{
+	return container_of(crypto_skcipher_alg(skcipher),
+			    struct skcipher_instance, alg);
+}
+
+static inline void *skcipher_instance_ctx(struct skcipher_instance *inst)
+{
+	return crypto_instance_ctx(skcipher_crypto_instance(inst));
+}
+
+static inline void skcipher_request_complete(struct skcipher_request *req, int err)
+{
+	req->base.complete(&req->base, err);
+}
+
 static inline void crypto_set_skcipher_spawn(
 	struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst)
 {
@@ -34,6 +68,12 @@
 int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name,
 			 u32 type, u32 mask);
 
+static inline int crypto_grab_skcipher2(struct crypto_skcipher_spawn *spawn,
+					const char *name, u32 type, u32 mask)
+{
+	return crypto_grab_skcipher(spawn, name, type, mask);
+}
+
 struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask);
 
 static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn)
@@ -41,54 +81,42 @@
 	crypto_drop_spawn(&spawn->base);
 }
 
-static inline struct crypto_alg *crypto_skcipher_spawn_alg(
+static inline struct skcipher_alg *crypto_skcipher_spawn_alg(
 	struct crypto_skcipher_spawn *spawn)
 {
-	return spawn->base.alg;
+	return container_of(spawn->base.alg, struct skcipher_alg, base);
 }
 
-static inline struct crypto_ablkcipher *crypto_spawn_skcipher(
+static inline struct skcipher_alg *crypto_spawn_skcipher_alg(
 	struct crypto_skcipher_spawn *spawn)
 {
-	return __crypto_ablkcipher_cast(
-		crypto_spawn_tfm(&spawn->base, crypto_skcipher_type(0),
-				 crypto_skcipher_mask(0)));
+	return crypto_skcipher_spawn_alg(spawn);
 }
 
-int skcipher_null_givencrypt(struct skcipher_givcrypt_request *req);
-int skcipher_null_givdecrypt(struct skcipher_givcrypt_request *req);
-const char *crypto_default_geniv(const struct crypto_alg *alg);
-
-struct crypto_instance *skcipher_geniv_alloc(struct crypto_template *tmpl,
-					     struct rtattr **tb, u32 type,
-					     u32 mask);
-void skcipher_geniv_free(struct crypto_instance *inst);
-int skcipher_geniv_init(struct crypto_tfm *tfm);
-void skcipher_geniv_exit(struct crypto_tfm *tfm);
-
-static inline struct crypto_ablkcipher *skcipher_geniv_cipher(
-	struct crypto_ablkcipher *geniv)
+static inline struct crypto_skcipher *crypto_spawn_skcipher(
+	struct crypto_skcipher_spawn *spawn)
 {
-	return crypto_ablkcipher_crt(geniv)->base;
+	return crypto_spawn_tfm2(&spawn->base);
 }
 
-static inline int skcipher_enqueue_givcrypt(
-	struct crypto_queue *queue, struct skcipher_givcrypt_request *request)
+static inline struct crypto_skcipher *crypto_spawn_skcipher2(
+	struct crypto_skcipher_spawn *spawn)
 {
-	return ablkcipher_enqueue_request(queue, &request->creq);
+	return crypto_spawn_skcipher(spawn);
 }
 
-static inline struct skcipher_givcrypt_request *skcipher_dequeue_givcrypt(
-	struct crypto_queue *queue)
+static inline void crypto_skcipher_set_reqsize(
+	struct crypto_skcipher *skcipher, unsigned int reqsize)
 {
-	return skcipher_givcrypt_cast(crypto_dequeue_request(queue));
+	skcipher->reqsize = reqsize;
 }
 
-static inline void *skcipher_givcrypt_reqctx(
-	struct skcipher_givcrypt_request *req)
-{
-	return ablkcipher_request_ctx(&req->creq);
-}
+int crypto_register_skcipher(struct skcipher_alg *alg);
+void crypto_unregister_skcipher(struct skcipher_alg *alg);
+int crypto_register_skciphers(struct skcipher_alg *algs, int count);
+void crypto_unregister_skciphers(struct skcipher_alg *algs, int count);
+int skcipher_register_instance(struct crypto_template *tmpl,
+			       struct skcipher_instance *inst);
 
 static inline void ablkcipher_request_complete(struct ablkcipher_request *req,
 					       int err)
@@ -96,12 +124,6 @@
 	req->base.complete(&req->base, err);
 }
 
-static inline void skcipher_givcrypt_complete(
-	struct skcipher_givcrypt_request *req, int err)
-{
-	ablkcipher_request_complete(&req->creq, err);
-}
-
 static inline u32 ablkcipher_request_flags(struct ablkcipher_request *req)
 {
 	return req->base.flags;
@@ -122,5 +144,31 @@
 	return req->base.flags;
 }
 
+static inline unsigned int crypto_skcipher_alg_min_keysize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blkcipher.min_keysize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_ablkcipher.min_keysize;
+
+	return alg->min_keysize;
+}
+
+static inline unsigned int crypto_skcipher_alg_max_keysize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blkcipher.max_keysize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_ablkcipher.max_keysize;
+
+	return alg->max_keysize;
+}
+
 #endif	/* _CRYPTO_INTERNAL_SKCIPHER_H */
 
diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h
new file mode 100644
index 0000000..30791f7
--- /dev/null
+++ b/include/crypto/kpp.h
@@ -0,0 +1,330 @@
+/*
+ * Key-agreement Protocol Primitives (KPP)
+ *
+ * Copyright (c) 2016, Intel Corporation
+ * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _CRYPTO_KPP_
+#define _CRYPTO_KPP_
+#include <linux/crypto.h>
+
+/**
+ * struct kpp_request
+ *
+ * @base:	Common attributes for async crypto requests
+ * @src:	Source data
+ * @dst:	Destination data
+ * @src_len:	Size of the input buffer
+ * @dst_len:	Size of the output buffer. It needs to be at least
+ *		as big as the expected result depending	on the operation
+ *		After operation it will be updated with the actual size of the
+ *		result. In case of error where the dst sgl size was insufficient,
+ *		it will be updated to the size required for the operation.
+ * @__ctx:	Start of private context data
+ */
+struct kpp_request {
+	struct crypto_async_request base;
+	struct scatterlist *src;
+	struct scatterlist *dst;
+	unsigned int src_len;
+	unsigned int dst_len;
+	void *__ctx[] CRYPTO_MINALIGN_ATTR;
+};
+
+/**
+ * struct crypto_kpp - user-instantiated object which encapsulate
+ * algorithms and core processing logic
+ *
+ * @base:	Common crypto API algorithm data structure
+ */
+struct crypto_kpp {
+	struct crypto_tfm base;
+};
+
+/**
+ * struct kpp_alg - generic key-agreement protocol primitives
+ *
+ * @set_secret:		Function invokes the protocol specific function to
+ *			store the secret private key along with parameters.
+ *			The implementation knows how to decode thie buffer
+ * @generate_public_key: Function generate the public key to be sent to the
+ *			counterpart. In case of error, where output is not big
+ *			enough req->dst_len will be updated to the size
+ *			required
+ * @compute_shared_secret: Function compute the shared secret as defined by
+ *			the algorithm. The result is given back to the user.
+ *			In case of error, where output is not big enough,
+ *			req->dst_len will be updated to the size required
+ * @max_size:		Function returns the size of the output buffer
+ * @init:		Initialize the object. This is called only once at
+ *			instantiation time. In case the cryptographic hardware
+ *			needs to be initialized. Software fallback should be
+ *			put in place here.
+ * @exit:		Undo everything @init did.
+ *
+ * @reqsize:		Request context size required by algorithm
+ *			implementation
+ * @base		Common crypto API algorithm data structure
+ */
+struct kpp_alg {
+	int (*set_secret)(struct crypto_kpp *tfm, void *buffer,
+			  unsigned int len);
+	int (*generate_public_key)(struct kpp_request *req);
+	int (*compute_shared_secret)(struct kpp_request *req);
+
+	int (*max_size)(struct crypto_kpp *tfm);
+
+	int (*init)(struct crypto_kpp *tfm);
+	void (*exit)(struct crypto_kpp *tfm);
+
+	unsigned int reqsize;
+	struct crypto_alg base;
+};
+
+/**
+ * DOC: Generic Key-agreement Protocol Primitevs API
+ *
+ * The KPP API is used with the algorithm type
+ * CRYPTO_ALG_TYPE_KPP (listed as type "kpp" in /proc/crypto)
+ */
+
+/**
+ * crypto_alloc_kpp() - allocate KPP tfm handle
+ * @alg_name: is the name of the kpp algorithm (e.g. "dh", "ecdh")
+ * @type: specifies the type of the algorithm
+ * @mask: specifies the mask for the algorithm
+ *
+ * Allocate a handle for kpp algorithm. The returned struct crypto_kpp
+ * is requeried for any following API invocation
+ *
+ * Return: allocated handle in case of success; IS_ERR() is true in case of
+ *	   an error, PTR_ERR() returns the error code.
+ */
+struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask);
+
+static inline struct crypto_tfm *crypto_kpp_tfm(struct crypto_kpp *tfm)
+{
+	return &tfm->base;
+}
+
+static inline struct kpp_alg *__crypto_kpp_alg(struct crypto_alg *alg)
+{
+	return container_of(alg, struct kpp_alg, base);
+}
+
+static inline struct crypto_kpp *__crypto_kpp_tfm(struct crypto_tfm *tfm)
+{
+	return container_of(tfm, struct crypto_kpp, base);
+}
+
+static inline struct kpp_alg *crypto_kpp_alg(struct crypto_kpp *tfm)
+{
+	return __crypto_kpp_alg(crypto_kpp_tfm(tfm)->__crt_alg);
+}
+
+static inline unsigned int crypto_kpp_reqsize(struct crypto_kpp *tfm)
+{
+	return crypto_kpp_alg(tfm)->reqsize;
+}
+
+static inline void kpp_request_set_tfm(struct kpp_request *req,
+				       struct crypto_kpp *tfm)
+{
+	req->base.tfm = crypto_kpp_tfm(tfm);
+}
+
+static inline struct crypto_kpp *crypto_kpp_reqtfm(struct kpp_request *req)
+{
+	return __crypto_kpp_tfm(req->base.tfm);
+}
+
+/**
+ * crypto_free_kpp() - free KPP tfm handle
+ *
+ * @tfm: KPP tfm handle allocated with crypto_alloc_kpp()
+ */
+static inline void crypto_free_kpp(struct crypto_kpp *tfm)
+{
+	crypto_destroy_tfm(tfm, crypto_kpp_tfm(tfm));
+}
+
+/**
+ * kpp_request_alloc() - allocates kpp request
+ *
+ * @tfm:	KPP tfm handle allocated with crypto_alloc_kpp()
+ * @gfp:	allocation flags
+ *
+ * Return: allocated handle in case of success or NULL in case of an error.
+ */
+static inline struct kpp_request *kpp_request_alloc(struct crypto_kpp *tfm,
+						    gfp_t gfp)
+{
+	struct kpp_request *req;
+
+	req = kmalloc(sizeof(*req) + crypto_kpp_reqsize(tfm), gfp);
+	if (likely(req))
+		kpp_request_set_tfm(req, tfm);
+
+	return req;
+}
+
+/**
+ * kpp_request_free() - zeroize and free kpp request
+ *
+ * @req:	request to free
+ */
+static inline void kpp_request_free(struct kpp_request *req)
+{
+	kzfree(req);
+}
+
+/**
+ * kpp_request_set_callback() - Sets an asynchronous callback.
+ *
+ * Callback will be called when an asynchronous operation on a given
+ * request is finished.
+ *
+ * @req:	request that the callback will be set for
+ * @flgs:	specify for instance if the operation may backlog
+ * @cmpl:	callback which will be called
+ * @data:	private data used by the caller
+ */
+static inline void kpp_request_set_callback(struct kpp_request *req,
+					    u32 flgs,
+					    crypto_completion_t cmpl,
+					    void *data)
+{
+	req->base.complete = cmpl;
+	req->base.data = data;
+	req->base.flags = flgs;
+}
+
+/**
+ * kpp_request_set_input() - Sets input buffer
+ *
+ * Sets parameters required by generate_public_key
+ *
+ * @req:	kpp request
+ * @input:	ptr to input scatter list
+ * @input_len:	size of the input scatter list
+ */
+static inline void kpp_request_set_input(struct kpp_request *req,
+					 struct scatterlist *input,
+					 unsigned int input_len)
+{
+	req->src = input;
+	req->src_len = input_len;
+}
+
+/**
+ * kpp_request_set_output() - Sets output buffer
+ *
+ * Sets parameters required by kpp operation
+ *
+ * @req:	kpp request
+ * @output:	ptr to output scatter list
+ * @output_len:	size of the output scatter list
+ */
+static inline void kpp_request_set_output(struct kpp_request *req,
+					  struct scatterlist *output,
+					  unsigned int output_len)
+{
+	req->dst = output;
+	req->dst_len = output_len;
+}
+
+enum {
+	CRYPTO_KPP_SECRET_TYPE_UNKNOWN,
+	CRYPTO_KPP_SECRET_TYPE_DH,
+	CRYPTO_KPP_SECRET_TYPE_ECDH,
+};
+
+/**
+ * struct kpp_secret - small header for packing secret buffer
+ *
+ * @type:	define type of secret. Each kpp type will define its own
+ * @len:	specify the len of the secret, include the header, that
+ *		follows the struct
+ */
+struct kpp_secret {
+	unsigned short type;
+	unsigned short len;
+};
+
+/**
+ * crypto_kpp_set_secret() - Invoke kpp operation
+ *
+ * Function invokes the specific kpp operation for a given alg.
+ *
+ * @tfm:	tfm handle
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, void *buffer,
+					unsigned int len)
+{
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->set_secret(tfm, buffer, len);
+}
+
+/**
+ * crypto_kpp_generate_public_key() - Invoke kpp operation
+ *
+ * Function invokes the specific kpp operation for generating the public part
+ * for a given kpp algorithm
+ *
+ * @req:	kpp key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_kpp_generate_public_key(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->generate_public_key(req);
+}
+
+/**
+ * crypto_kpp_compute_shared_secret() - Invoke kpp operation
+ *
+ * Function invokes the specific kpp operation for computing the shared secret
+ * for a given kpp algorithm.
+ *
+ * @req:	kpp key request
+ *
+ * Return: zero on success; error code in case of error
+ */
+static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req)
+{
+	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->compute_shared_secret(req);
+}
+
+/**
+ * crypto_kpp_maxsize() - Get len for output buffer
+ *
+ * Function returns the output buffer size required
+ *
+ * @tfm:	KPP tfm handle allocated with crypto_alloc_kpp()
+ *
+ * Return: minimum len for output buffer or error code if key hasn't been set
+ */
+static inline int crypto_kpp_maxsize(struct crypto_kpp *tfm)
+{
+	struct kpp_alg *alg = crypto_kpp_alg(tfm);
+
+	return alg->max_size(tfm);
+}
+
+#endif
diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h
index c23ee1f..4a53c0d 100644
--- a/include/crypto/mcryptd.h
+++ b/include/crypto/mcryptd.h
@@ -39,7 +39,7 @@
 };
 
 struct mcryptd_hash_ctx {
-	struct crypto_shash *child;
+	struct crypto_ahash *child;
 	struct mcryptd_alg_state *alg_state;
 };
 
@@ -59,13 +59,13 @@
 	struct crypto_hash_walk walk;
 	u8 *out;
 	int flag;
-	struct shash_desc desc;
+	struct ahash_request areq;
 };
 
 struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name,
 					u32 type, u32 mask);
-struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm);
-struct shash_desc *mcryptd_shash_desc(struct ahash_request *req);
+struct crypto_ahash *mcryptd_ahash_child(struct mcryptd_ahash *tfm);
+struct ahash_request *mcryptd_ahash_desc(struct ahash_request *req);
 void mcryptd_free_ahash(struct mcryptd_ahash *tfm);
 void mcryptd_flusher(struct work_struct *work);
 
diff --git a/include/crypto/null.h b/include/crypto/null.h
index 06dc30d..3f0c59fb 100644
--- a/include/crypto/null.h
+++ b/include/crypto/null.h
@@ -8,7 +8,17 @@
 #define NULL_DIGEST_SIZE	0
 #define NULL_IV_SIZE		0
 
-struct crypto_blkcipher *crypto_get_default_null_skcipher(void);
+struct crypto_skcipher *crypto_get_default_null_skcipher(void);
 void crypto_put_default_null_skcipher(void);
 
+static inline struct crypto_skcipher *crypto_get_default_null_skcipher2(void)
+{
+	return crypto_get_default_null_skcipher();
+}
+
+static inline void crypto_put_default_null_skcipher2(void)
+{
+	crypto_put_default_null_skcipher();
+}
+
 #endif
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 35f99b6..880e6be 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -16,14 +16,10 @@
 #ifndef _CRYPTO_SCATTERWALK_H
 #define _CRYPTO_SCATTERWALK_H
 
-#include <asm/kmap_types.h>
 #include <crypto/algapi.h>
-#include <linux/hardirq.h>
 #include <linux/highmem.h>
 #include <linux/kernel.h>
-#include <linux/mm.h>
 #include <linux/scatterlist.h>
-#include <linux/sched.h>
 
 static inline void scatterwalk_crypto_chain(struct scatterlist *head,
 					    struct scatterlist *sg,
@@ -83,17 +79,53 @@
 	kunmap_atomic(vaddr);
 }
 
-void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg);
+static inline void scatterwalk_start(struct scatter_walk *walk,
+				     struct scatterlist *sg)
+{
+	walk->sg = sg;
+	walk->offset = sg->offset;
+}
+
+static inline void *scatterwalk_map(struct scatter_walk *walk)
+{
+	return kmap_atomic(scatterwalk_page(walk)) +
+	       offset_in_page(walk->offset);
+}
+
+static inline void scatterwalk_pagedone(struct scatter_walk *walk, int out,
+					unsigned int more)
+{
+	if (out) {
+		struct page *page;
+
+		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
+		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
+		 * PageSlab cannot be optimised away per se due to
+		 * use of volatile pointer.
+		 */
+		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
+			flush_dcache_page(page);
+	}
+
+	if (more && walk->offset >= walk->sg->offset + walk->sg->length)
+		scatterwalk_start(walk, sg_next(walk->sg));
+}
+
+static inline void scatterwalk_done(struct scatter_walk *walk, int out,
+				    int more)
+{
+	if (!more || walk->offset >= walk->sg->offset + walk->sg->length ||
+	    !(walk->offset & (PAGE_SIZE - 1)))
+		scatterwalk_pagedone(walk, out, more);
+}
+
 void scatterwalk_copychunks(void *buf, struct scatter_walk *walk,
 			    size_t nbytes, int out);
 void *scatterwalk_map(struct scatter_walk *walk);
-void scatterwalk_done(struct scatter_walk *walk, int out, int more);
 
 void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 			      unsigned int start, unsigned int nbytes, int out);
 
-int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes);
-
 struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
 				     struct scatterlist *src,
 				     unsigned int len);
diff --git a/include/crypto/sha3.h b/include/crypto/sha3.h
new file mode 100644
index 0000000..f4c9f68
--- /dev/null
+++ b/include/crypto/sha3.h
@@ -0,0 +1,29 @@
+/*
+ * Common values for SHA-3 algorithms
+ */
+#ifndef __CRYPTO_SHA3_H__
+#define __CRYPTO_SHA3_H__
+
+#define SHA3_224_DIGEST_SIZE	(224 / 8)
+#define SHA3_224_BLOCK_SIZE	(200 - 2 * SHA3_224_DIGEST_SIZE)
+
+#define SHA3_256_DIGEST_SIZE	(256 / 8)
+#define SHA3_256_BLOCK_SIZE	(200 - 2 * SHA3_256_DIGEST_SIZE)
+
+#define SHA3_384_DIGEST_SIZE	(384 / 8)
+#define SHA3_384_BLOCK_SIZE	(200 - 2 * SHA3_384_DIGEST_SIZE)
+
+#define SHA3_512_DIGEST_SIZE	(512 / 8)
+#define SHA3_512_BLOCK_SIZE	(200 - 2 * SHA3_512_DIGEST_SIZE)
+
+struct sha3_state {
+	u64		st[25];
+	unsigned int	md_len;
+	unsigned int	rsiz;
+	unsigned int	rsizw;
+
+	unsigned int	partial;
+	u8		buf[SHA3_224_BLOCK_SIZE];
+};
+
+#endif
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 0f987f5..cc4d98a 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -65,87 +65,81 @@
 	struct crypto_tfm base;
 };
 
+/**
+ * struct skcipher_alg - symmetric key cipher definition
+ * @min_keysize: Minimum key size supported by the transformation. This is the
+ *		 smallest key length supported by this transformation algorithm.
+ *		 This must be set to one of the pre-defined values as this is
+ *		 not hardware specific. Possible values for this field can be
+ *		 found via git grep "_MIN_KEY_SIZE" include/crypto/
+ * @max_keysize: Maximum key size supported by the transformation. This is the
+ *		 largest key length supported by this transformation algorithm.
+ *		 This must be set to one of the pre-defined values as this is
+ *		 not hardware specific. Possible values for this field can be
+ *		 found via git grep "_MAX_KEY_SIZE" include/crypto/
+ * @setkey: Set key for the transformation. This function is used to either
+ *	    program a supplied key into the hardware or store the key in the
+ *	    transformation context for programming it later. Note that this
+ *	    function does modify the transformation context. This function can
+ *	    be called multiple times during the existence of the transformation
+ *	    object, so one must make sure the key is properly reprogrammed into
+ *	    the hardware. This function is also responsible for checking the key
+ *	    length for validity. In case a software fallback was put in place in
+ *	    the @cra_init call, this function might need to use the fallback if
+ *	    the algorithm doesn't support all of the key sizes.
+ * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt
+ *	     the supplied scatterlist containing the blocks of data. The crypto
+ *	     API consumer is responsible for aligning the entries of the
+ *	     scatterlist properly and making sure the chunks are correctly
+ *	     sized. In case a software fallback was put in place in the
+ *	     @cra_init call, this function might need to use the fallback if
+ *	     the algorithm doesn't support all of the key sizes. In case the
+ *	     key was stored in transformation context, the key might need to be
+ *	     re-programmed into the hardware in this function. This function
+ *	     shall not modify the transformation context, as this function may
+ *	     be called in parallel with the same transformation object.
+ * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt
+ *	     and the conditions are exactly the same.
+ * @init: Initialize the cryptographic transformation object. This function
+ *	  is used to initialize the cryptographic transformation object.
+ *	  This function is called only once at the instantiation time, right
+ *	  after the transformation context was allocated. In case the
+ *	  cryptographic hardware has some special requirements which need to
+ *	  be handled by software, this function shall check for the precise
+ *	  requirement of the transformation and put any software fallbacks
+ *	  in place.
+ * @exit: Deinitialize the cryptographic transformation object. This is a
+ *	  counterpart to @init, used to remove various changes set in
+ *	  @init.
+ * @ivsize: IV size applicable for transformation. The consumer must provide an
+ *	    IV of exactly that size to perform the encrypt or decrypt operation.
+ * @chunksize: Equal to the block size except for stream ciphers such as
+ *	       CTR where it is set to the underlying block size.
+ * @base: Definition of a generic crypto algorithm.
+ *
+ * All fields except @ivsize are mandatory and must be filled.
+ */
+struct skcipher_alg {
+	int (*setkey)(struct crypto_skcipher *tfm, const u8 *key,
+	              unsigned int keylen);
+	int (*encrypt)(struct skcipher_request *req);
+	int (*decrypt)(struct skcipher_request *req);
+	int (*init)(struct crypto_skcipher *tfm);
+	void (*exit)(struct crypto_skcipher *tfm);
+
+	unsigned int min_keysize;
+	unsigned int max_keysize;
+	unsigned int ivsize;
+	unsigned int chunksize;
+
+	struct crypto_alg base;
+};
+
 #define SKCIPHER_REQUEST_ON_STACK(name, tfm) \
 	char __##name##_desc[sizeof(struct skcipher_request) + \
 		crypto_skcipher_reqsize(tfm)] CRYPTO_MINALIGN_ATTR; \
 	struct skcipher_request *name = (void *)__##name##_desc
 
-static inline struct crypto_ablkcipher *skcipher_givcrypt_reqtfm(
-	struct skcipher_givcrypt_request *req)
-{
-	return crypto_ablkcipher_reqtfm(&req->creq);
-}
-
-static inline int crypto_skcipher_givencrypt(
-	struct skcipher_givcrypt_request *req)
-{
-	struct ablkcipher_tfm *crt =
-		crypto_ablkcipher_crt(skcipher_givcrypt_reqtfm(req));
-	return crt->givencrypt(req);
-};
-
-static inline int crypto_skcipher_givdecrypt(
-	struct skcipher_givcrypt_request *req)
-{
-	struct ablkcipher_tfm *crt =
-		crypto_ablkcipher_crt(skcipher_givcrypt_reqtfm(req));
-	return crt->givdecrypt(req);
-};
-
-static inline void skcipher_givcrypt_set_tfm(
-	struct skcipher_givcrypt_request *req, struct crypto_ablkcipher *tfm)
-{
-	req->creq.base.tfm = crypto_ablkcipher_tfm(tfm);
-}
-
-static inline struct skcipher_givcrypt_request *skcipher_givcrypt_cast(
-	struct crypto_async_request *req)
-{
-	return container_of(ablkcipher_request_cast(req),
-			    struct skcipher_givcrypt_request, creq);
-}
-
-static inline struct skcipher_givcrypt_request *skcipher_givcrypt_alloc(
-	struct crypto_ablkcipher *tfm, gfp_t gfp)
-{
-	struct skcipher_givcrypt_request *req;
-
-	req = kmalloc(sizeof(struct skcipher_givcrypt_request) +
-		      crypto_ablkcipher_reqsize(tfm), gfp);
-
-	if (likely(req))
-		skcipher_givcrypt_set_tfm(req, tfm);
-
-	return req;
-}
-
-static inline void skcipher_givcrypt_free(struct skcipher_givcrypt_request *req)
-{
-	kfree(req);
-}
-
-static inline void skcipher_givcrypt_set_callback(
-	struct skcipher_givcrypt_request *req, u32 flags,
-	crypto_completion_t compl, void *data)
-{
-	ablkcipher_request_set_callback(&req->creq, flags, compl, data);
-}
-
-static inline void skcipher_givcrypt_set_crypt(
-	struct skcipher_givcrypt_request *req,
-	struct scatterlist *src, struct scatterlist *dst,
-	unsigned int nbytes, void *iv)
-{
-	ablkcipher_request_set_crypt(&req->creq, src, dst, nbytes, iv);
-}
-
-static inline void skcipher_givcrypt_set_giv(
-	struct skcipher_givcrypt_request *req, u8 *giv, u64 seq)
-{
-	req->giv = giv;
-	req->seq = seq;
-}
-
 /**
  * DOC: Symmetric Key Cipher API
  *
@@ -231,12 +225,43 @@
 			      crypto_skcipher_mask(mask));
 }
 
+/**
+ * crypto_has_skcipher2() - Search for the availability of an skcipher.
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      skcipher
+ * @type: specifies the type of the skcipher
+ * @mask: specifies the mask for the skcipher
+ *
+ * Return: true when the skcipher is known to the kernel crypto API; false
+ *	   otherwise
+ */
+int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask);
+
 static inline const char *crypto_skcipher_driver_name(
 	struct crypto_skcipher *tfm)
 {
 	return crypto_tfm_alg_driver_name(crypto_skcipher_tfm(tfm));
 }
 
+static inline struct skcipher_alg *crypto_skcipher_alg(
+	struct crypto_skcipher *tfm)
+{
+	return container_of(crypto_skcipher_tfm(tfm)->__crt_alg,
+			    struct skcipher_alg, base);
+}
+
+static inline unsigned int crypto_skcipher_alg_ivsize(struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blkcipher.ivsize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_ablkcipher.ivsize;
+
+	return alg->ivsize;
+}
+
 /**
  * crypto_skcipher_ivsize() - obtain IV size
  * @tfm: cipher handle
@@ -251,6 +276,36 @@
 	return tfm->ivsize;
 }
 
+static inline unsigned int crypto_skcipher_alg_chunksize(
+	struct skcipher_alg *alg)
+{
+	if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) ==
+	    CRYPTO_ALG_TYPE_BLKCIPHER)
+		return alg->base.cra_blocksize;
+
+	if (alg->base.cra_ablkcipher.encrypt)
+		return alg->base.cra_blocksize;
+
+	return alg->chunksize;
+}
+
+/**
+ * crypto_skcipher_chunksize() - obtain chunk size
+ * @tfm: cipher handle
+ *
+ * The block size is set to one for ciphers such as CTR.  However,
+ * you still need to provide incremental updates in multiples of
+ * the underlying block size as the IV does not have sub-block
+ * granularity.  This is known in this API as the chunk size.
+ *
+ * Return: chunk size in bytes
+ */
+static inline unsigned int crypto_skcipher_chunksize(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm));
+}
+
 /**
  * crypto_skcipher_blocksize() - obtain block size of cipher
  * @tfm: cipher handle
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 6e28c89..7cee555 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -47,16 +47,18 @@
 #define CRYPTO_ALG_TYPE_AEAD		0x00000003
 #define CRYPTO_ALG_TYPE_BLKCIPHER	0x00000004
 #define CRYPTO_ALG_TYPE_ABLKCIPHER	0x00000005
+#define CRYPTO_ALG_TYPE_SKCIPHER	0x00000005
 #define CRYPTO_ALG_TYPE_GIVCIPHER	0x00000006
-#define CRYPTO_ALG_TYPE_DIGEST		0x00000008
-#define CRYPTO_ALG_TYPE_HASH		0x00000008
-#define CRYPTO_ALG_TYPE_SHASH		0x00000009
-#define CRYPTO_ALG_TYPE_AHASH		0x0000000a
+#define CRYPTO_ALG_TYPE_KPP		0x00000008
 #define CRYPTO_ALG_TYPE_RNG		0x0000000c
 #define CRYPTO_ALG_TYPE_AKCIPHER	0x0000000d
+#define CRYPTO_ALG_TYPE_DIGEST		0x0000000e
+#define CRYPTO_ALG_TYPE_HASH		0x0000000e
+#define CRYPTO_ALG_TYPE_SHASH		0x0000000e
+#define CRYPTO_ALG_TYPE_AHASH		0x0000000f
 
 #define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
-#define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000c
+#define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000e
 #define CRYPTO_ALG_TYPE_BLKCIPHER_MASK	0x0000000c
 
 #define CRYPTO_ALG_LARVAL		0x00000010
@@ -486,8 +488,6 @@
 	              unsigned int keylen);
 	int (*encrypt)(struct ablkcipher_request *req);
 	int (*decrypt)(struct ablkcipher_request *req);
-	int (*givencrypt)(struct skcipher_givcrypt_request *req);
-	int (*givdecrypt)(struct skcipher_givcrypt_request *req);
 
 	struct crypto_ablkcipher *base;
 
@@ -712,23 +712,6 @@
  * state information is unused by the kernel crypto API.
  */
 
-/**
- * crypto_alloc_ablkcipher() - allocate asynchronous block cipher handle
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      ablkcipher cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Allocate a cipher handle for an ablkcipher. The returned struct
- * crypto_ablkcipher is the cipher handle that is required for any subsequent
- * API invocation for that ablkcipher.
- *
- * Return: allocated cipher handle in case of success; IS_ERR() is true in case
- *	   of an error, PTR_ERR() returns the error code.
- */
-struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name,
-						  u32 type, u32 mask);
-
 static inline struct crypto_tfm *crypto_ablkcipher_tfm(
 	struct crypto_ablkcipher *tfm)
 {
diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 3a5abe9..1cc5ffb 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -80,8 +80,7 @@
 int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 		    int *sign);
 void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign);
-int mpi_set_buffer(MPI a, const void *buffer, unsigned nbytes, int sign);
-int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned *nbytes,
+int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes,
 		     int *sign);
 
 #define log_mpidump g10_log_mpidump
diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h
index 2e67bb6..79b5ded 100644
--- a/include/uapi/linux/cryptouser.h
+++ b/include/uapi/linux/cryptouser.h
@@ -45,6 +45,7 @@
 	CRYPTOCFGA_REPORT_RNG,		/* struct crypto_report_rng */
 	CRYPTOCFGA_REPORT_CIPHER,	/* struct crypto_report_cipher */
 	CRYPTOCFGA_REPORT_AKCIPHER,	/* struct crypto_report_akcipher */
+	CRYPTOCFGA_REPORT_KPP,		/* struct crypto_report_kpp */
 	__CRYPTOCFGA_MAX
 
 #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1)
@@ -107,5 +108,9 @@
 	char type[CRYPTO_MAX_NAME];
 };
 
+struct crypto_report_kpp {
+	char type[CRYPTO_MAX_NAME];
+};
+
 #define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \
 			       sizeof(struct crypto_report_blkcipher))
diff --git a/lib/digsig.c b/lib/digsig.c
index 07be6c1..55b8b2f 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -104,21 +104,25 @@
 	datap = pkh->mpi;
 	endp = ukp->data + ukp->datalen;
 
-	err = -ENOMEM;
-
 	for (i = 0; i < pkh->nmpi; i++) {
 		unsigned int remaining = endp - datap;
 		pkey[i] = mpi_read_from_buffer(datap, &remaining);
-		if (!pkey[i])
+		if (IS_ERR(pkey[i])) {
+			err = PTR_ERR(pkey[i]);
 			goto err;
+		}
 		datap += remaining;
 	}
 
 	mblen = mpi_get_nbits(pkey[0]);
 	mlen = DIV_ROUND_UP(mblen, 8);
 
-	if (mlen == 0)
+	if (mlen == 0) {
+		err = -EINVAL;
 		goto err;
+	}
+
+	err = -ENOMEM;
 
 	out1 = kzalloc(mlen, GFP_KERNEL);
 	if (!out1)
@@ -126,8 +130,10 @@
 
 	nret = siglen;
 	in = mpi_read_from_buffer(sig, &nret);
-	if (!in)
+	if (IS_ERR(in)) {
+		err = PTR_ERR(in);
 		goto err;
+	}
 
 	res = mpi_alloc(mpi_get_nlimbs(in) * 2);
 	if (!res)
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 747606f..c6272ae 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -21,6 +21,7 @@
 #include <linux/bitops.h>
 #include <linux/count_zeros.h>
 #include <linux/byteorder/generic.h>
+#include <linux/scatterlist.h>
 #include <linux/string.h>
 #include "mpi-internal.h"
 
@@ -50,9 +51,7 @@
 		return NULL;
 	}
 	if (nbytes > 0)
-		nbits -= count_leading_zeros(buffer[0]);
-	else
-		nbits = 0;
+		nbits -= count_leading_zeros(buffer[0]) - (BITS_PER_LONG - 8);
 
 	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
 	val = mpi_alloc(nlimbs);
@@ -82,50 +81,30 @@
 MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread)
 {
 	const uint8_t *buffer = xbuffer;
-	int i, j;
-	unsigned nbits, nbytes, nlimbs, nread = 0;
-	mpi_limb_t a;
-	MPI val = NULL;
+	unsigned int nbits, nbytes;
+	MPI val;
 
 	if (*ret_nread < 2)
-		goto leave;
+		return ERR_PTR(-EINVAL);
 	nbits = buffer[0] << 8 | buffer[1];
 
 	if (nbits > MAX_EXTERN_MPI_BITS) {
 		pr_info("MPI: mpi too large (%u bits)\n", nbits);
-		goto leave;
+		return ERR_PTR(-EINVAL);
 	}
-	buffer += 2;
-	nread = 2;
 
 	nbytes = DIV_ROUND_UP(nbits, 8);
-	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
-	val = mpi_alloc(nlimbs);
-	if (!val)
-		return NULL;
-	i = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
-	i %= BYTES_PER_MPI_LIMB;
-	val->nbits = nbits;
-	j = val->nlimbs = nlimbs;
-	val->sign = 0;
-	for (; j > 0; j--) {
-		a = 0;
-		for (; i < BYTES_PER_MPI_LIMB; i++) {
-			if (++nread > *ret_nread) {
-				printk
-				    ("MPI: mpi larger than buffer nread=%d ret_nread=%d\n",
-				     nread, *ret_nread);
-				goto leave;
-			}
-			a <<= 8;
-			a |= *buffer++;
-		}
-		i = 0;
-		val->d[j - 1] = a;
+	if (nbytes + 2 > *ret_nread) {
+		pr_info("MPI: mpi larger than buffer nbytes=%u ret_nread=%u\n",
+				nbytes, *ret_nread);
+		return ERR_PTR(-EINVAL);
 	}
 
-leave:
-	*ret_nread = nread;
+	val = mpi_read_raw_data(buffer + 2, nbytes);
+	if (!val)
+		return ERR_PTR(-ENOMEM);
+
+	*ret_nread = nbytes + 2;
 	return val;
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
@@ -250,82 +229,6 @@
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);
 
-/****************
- * Use BUFFER to update MPI.
- */
-int mpi_set_buffer(MPI a, const void *xbuffer, unsigned nbytes, int sign)
-{
-	const uint8_t *buffer = xbuffer, *p;
-	mpi_limb_t alimb;
-	int nlimbs;
-	int i;
-
-	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
-	if (RESIZE_IF_NEEDED(a, nlimbs) < 0)
-		return -ENOMEM;
-	a->sign = sign;
-
-	for (i = 0, p = buffer + nbytes - 1; p >= buffer + BYTES_PER_MPI_LIMB;) {
-#if BYTES_PER_MPI_LIMB == 4
-		alimb = (mpi_limb_t) *p--;
-		alimb |= (mpi_limb_t) *p-- << 8;
-		alimb |= (mpi_limb_t) *p-- << 16;
-		alimb |= (mpi_limb_t) *p-- << 24;
-#elif BYTES_PER_MPI_LIMB == 8
-		alimb = (mpi_limb_t) *p--;
-		alimb |= (mpi_limb_t) *p-- << 8;
-		alimb |= (mpi_limb_t) *p-- << 16;
-		alimb |= (mpi_limb_t) *p-- << 24;
-		alimb |= (mpi_limb_t) *p-- << 32;
-		alimb |= (mpi_limb_t) *p-- << 40;
-		alimb |= (mpi_limb_t) *p-- << 48;
-		alimb |= (mpi_limb_t) *p-- << 56;
-#else
-#error please implement for this limb size.
-#endif
-		a->d[i++] = alimb;
-	}
-	if (p >= buffer) {
-#if BYTES_PER_MPI_LIMB == 4
-		alimb = *p--;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 8;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 16;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 24;
-#elif BYTES_PER_MPI_LIMB == 8
-		alimb = (mpi_limb_t) *p--;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 8;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 16;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 24;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 32;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 40;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 48;
-		if (p >= buffer)
-			alimb |= (mpi_limb_t) *p-- << 56;
-#else
-#error please implement for this limb size.
-#endif
-		a->d[i++] = alimb;
-	}
-	a->nlimbs = i;
-
-	if (i != nlimbs) {
-		pr_emerg("MPI: mpi_set_buffer: Assertion failed (%d != %d)", i,
-		       nlimbs);
-		BUG();
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mpi_set_buffer);
-
 /**
  * mpi_write_to_sgl() - Funnction exports MPI to an sgl (msb first)
  *
@@ -335,16 +238,13 @@
  * @a:		a multi precision integer
  * @sgl:	scatterlist to write to. Needs to be at least
  *		mpi_get_size(a) long.
- * @nbytes:	in/out param - it has the be set to the maximum number of
- *		bytes that can be written to sgl. This has to be at least
- *		the size of the integer a. On return it receives the actual
- *		length of the data written on success or the data that would
- *		be written if buffer was too small.
+ * @nbytes:	the number of bytes to write.  Leading bytes will be
+ *		filled with zero.
  * @sign:	if not NULL, it will be set to the sign of a.
  *
  * Return:	0 on success or error code in case of error
  */
-int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
+int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned nbytes,
 		     int *sign)
 {
 	u8 *p, *p2;
@@ -356,55 +256,60 @@
 #error please implement for this limb size.
 #endif
 	unsigned int n = mpi_get_size(a);
-	int i, x, y = 0, lzeros, buf_len;
-
-	if (!nbytes)
-		return -EINVAL;
+	struct sg_mapping_iter miter;
+	int i, x, buf_len;
+	int nents;
 
 	if (sign)
 		*sign = a->sign;
 
-	lzeros = count_lzeros(a);
-
-	if (*nbytes < n - lzeros) {
-		*nbytes = n - lzeros;
+	if (nbytes < n)
 		return -EOVERFLOW;
+
+	nents = sg_nents_for_len(sgl, nbytes);
+	if (nents < 0)
+		return -EINVAL;
+
+	sg_miter_start(&miter, sgl, nents, SG_MITER_ATOMIC | SG_MITER_TO_SG);
+	sg_miter_next(&miter);
+	buf_len = miter.length;
+	p2 = miter.addr;
+
+	while (nbytes > n) {
+		i = min_t(unsigned, nbytes - n, buf_len);
+		memset(p2, 0, i);
+		p2 += i;
+		nbytes -= i;
+
+		buf_len -= i;
+		if (!buf_len) {
+			sg_miter_next(&miter);
+			buf_len = miter.length;
+			p2 = miter.addr;
+		}
 	}
 
-	*nbytes = n - lzeros;
-	buf_len = sgl->length;
-	p2 = sg_virt(sgl);
-
-	for (i = a->nlimbs - 1 - lzeros / BYTES_PER_MPI_LIMB,
-			lzeros %= BYTES_PER_MPI_LIMB;
-		i >= 0; i--) {
+	for (i = a->nlimbs - 1; i >= 0; i--) {
 #if BYTES_PER_MPI_LIMB == 4
-		alimb = cpu_to_be32(a->d[i]);
+		alimb = a->d[i] ? cpu_to_be32(a->d[i]) : 0;
 #elif BYTES_PER_MPI_LIMB == 8
-		alimb = cpu_to_be64(a->d[i]);
+		alimb = a->d[i] ? cpu_to_be64(a->d[i]) : 0;
 #else
 #error please implement for this limb size.
 #endif
-		if (lzeros) {
-			y = lzeros;
-			lzeros = 0;
-		}
+		p = (u8 *)&alimb;
 
-		p = (u8 *)&alimb + y;
-
-		for (x = 0; x < sizeof(alimb) - y; x++) {
-			if (!buf_len) {
-				sgl = sg_next(sgl);
-				if (!sgl)
-					return -EINVAL;
-				buf_len = sgl->length;
-				p2 = sg_virt(sgl);
-			}
+		for (x = 0; x < sizeof(alimb); x++) {
 			*p2++ = *p++;
-			buf_len--;
+			if (!--buf_len) {
+				sg_miter_next(&miter);
+				buf_len = miter.length;
+				p2 = miter.addr;
+			}
 		}
-		y = 0;
 	}
+
+	sg_miter_stop(&miter);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mpi_write_to_sgl);
@@ -424,19 +329,23 @@
  */
 MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 {
-	struct scatterlist *sg;
-	int x, i, j, z, lzeros, ents;
+	struct sg_mapping_iter miter;
 	unsigned int nbits, nlimbs;
+	int x, j, z, lzeros, ents;
+	unsigned int len;
+	const u8 *buff;
 	mpi_limb_t a;
 	MPI val = NULL;
 
+	ents = sg_nents_for_len(sgl, nbytes);
+	if (ents < 0)
+		return NULL;
+
+	sg_miter_start(&miter, sgl, ents, SG_MITER_ATOMIC | SG_MITER_FROM_SG);
+
 	lzeros = 0;
-	ents = sg_nents(sgl);
-
-	for_each_sg(sgl, sg, ents, i) {
-		const u8 *buff = sg_virt(sg);
-		int len = sg->length;
-
+	len = 0;
+	while (nbytes > 0) {
 		while (len && !*buff) {
 			lzeros++;
 			len--;
@@ -446,12 +355,14 @@
 		if (len && *buff)
 			break;
 
-		ents--;
+		sg_miter_next(&miter);
+		buff = miter.addr;
+		len = miter.length;
+
 		nbytes -= lzeros;
 		lzeros = 0;
 	}
 
-	sgl = sg;
 	nbytes -= lzeros;
 	nbits = nbytes * 8;
 	if (nbits > MAX_EXTERN_MPI_BITS) {
@@ -460,8 +371,7 @@
 	}
 
 	if (nbytes > 0)
-		nbits -= count_leading_zeros(*(u8 *)(sg_virt(sgl) + lzeros)) -
-			(BITS_PER_LONG - 8);
+		nbits -= count_leading_zeros(*buff) - (BITS_PER_LONG - 8);
 
 	nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB);
 	val = mpi_alloc(nlimbs);
@@ -480,21 +390,24 @@
 	z = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
 	z %= BYTES_PER_MPI_LIMB;
 
-	for_each_sg(sgl, sg, ents, i) {
-		const u8 *buffer = sg_virt(sg) + lzeros;
-		int len = sg->length - lzeros;
-
+	for (;;) {
 		for (x = 0; x < len; x++) {
 			a <<= 8;
-			a |= *buffer++;
+			a |= *buff++;
 			if (((z + x + 1) % BYTES_PER_MPI_LIMB) == 0) {
 				val->d[j--] = a;
 				a = 0;
 			}
 		}
 		z += x;
-		lzeros = 0;
+
+		if (!sg_miter_next(&miter))
+			break;
+
+		buff = miter.addr;
+		len = miter.length;
 	}
+
 	return val;
 }
 EXPORT_SYMBOL_GPL(mpi_read_raw_from_sgl);
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 9e443fc..c0b3030 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -18,6 +18,7 @@
 #include <keys/user-type.h>
 #include <keys/big_key-type.h>
 #include <crypto/rng.h>
+#include <crypto/skcipher.h>
 
 /*
  * Layout of key payload words.
@@ -74,7 +75,7 @@
  * Crypto algorithms for big_key data encryption
  */
 static struct crypto_rng *big_key_rng;
-static struct crypto_blkcipher *big_key_blkcipher;
+static struct crypto_skcipher *big_key_skcipher;
 
 /*
  * Generate random key to encrypt big_key data
@@ -91,22 +92,26 @@
 {
 	int ret = -EINVAL;
 	struct scatterlist sgio;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher);
 
-	if (crypto_blkcipher_setkey(big_key_blkcipher, key, ENC_KEY_SIZE)) {
+	if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) {
 		ret = -EAGAIN;
 		goto error;
 	}
 
-	desc.flags = 0;
-	desc.tfm = big_key_blkcipher;
+	skcipher_request_set_tfm(req, big_key_skcipher);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
 
 	sg_init_one(&sgio, data, datalen);
+	skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL);
 
 	if (op == BIG_KEY_ENC)
-		ret = crypto_blkcipher_encrypt(&desc, &sgio, &sgio, datalen);
+		ret = crypto_skcipher_encrypt(req);
 	else
-		ret = crypto_blkcipher_decrypt(&desc, &sgio, &sgio, datalen);
+		ret = crypto_skcipher_decrypt(req);
+
+	skcipher_request_zero(req);
 
 error:
 	return ret;
@@ -140,7 +145,7 @@
 		 *
 		 * File content is stored encrypted with randomly generated key.
 		 */
-		size_t enclen = ALIGN(datalen, crypto_blkcipher_blocksize(big_key_blkcipher));
+		size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
 
 		/* prepare aligned data to encrypt */
 		data = kmalloc(enclen, GFP_KERNEL);
@@ -288,7 +293,7 @@
 		struct file *file;
 		u8 *data;
 		u8 *enckey = (u8 *)key->payload.data[big_key_data];
-		size_t enclen = ALIGN(datalen, crypto_blkcipher_blocksize(big_key_blkcipher));
+		size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
 
 		data = kmalloc(enclen, GFP_KERNEL);
 		if (!data)
@@ -359,9 +364,10 @@
 		goto error;
 
 	/* init block cipher */
-	big_key_blkcipher = crypto_alloc_blkcipher(big_key_alg_name, 0, 0);
-	if (IS_ERR(big_key_blkcipher)) {
-		big_key_blkcipher = NULL;
+	big_key_skcipher = crypto_alloc_skcipher(big_key_alg_name,
+						 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(big_key_skcipher)) {
+		big_key_skcipher = NULL;
 		ret = -EFAULT;
 		goto error;
 	}