20 files changed, 1952 insertions, 752 deletions

diff --git a/arch/arm/boot/dts/stm32746g-eval.dts b/arch/arm/boot/dts/stm32746g-eval.dts
index aa03fac1ec55..0dc18a0f0940 100644
--- a/arch/arm/boot/dts/stm32746g-eval.dts
+++ b/arch/arm/boot/dts/stm32746g-eval.dts
@@ -89,6 +89,10 @@
 	clock-frequency = <25000000>;
 };
 
+&crc {
+	status = "okay";
+};
+
 &usart1 {
 	pinctrl-0 = <&usart1_pins_a>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/stm32f746.dtsi b/arch/arm/boot/dts/stm32f746.dtsi
index f321ffe87144..755fb923c07b 100644
--- a/arch/arm/boot/dts/stm32f746.dtsi
+++ b/arch/arm/boot/dts/stm32f746.dtsi
@@ -289,6 +289,13 @@
 			};
 		};
 
+		crc: crc@40023000 {
+			compatible = "st,stm32f7-crc";
+			reg = <0x40023000 0x400>;
+			clocks = <&rcc 0 12>;
+			status = "disabled";
+		};
+
 		rcc: rcc@40023800 {
 			#clock-cells = <2>;
 			compatible = "st,stm32f42xx-rcc", "st,stm32-rcc";
diff --git a/arch/arm/configs/stm32_defconfig b/arch/arm/configs/stm32_defconfig
index a9d8e3c9b487..03437f8f9ad1 100644
--- a/arch/arm/configs/stm32_defconfig
+++ b/arch/arm/configs/stm32_defconfig
@@ -75,5 +75,7 @@ CONFIG_MAGIC_SYSRQ=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_BUGVERBOSE is not set
 # CONFIG_FTRACE is not set
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_DEV_STM32=y
 CONFIG_CRC_ITU_T=y
 CONFIG_CRC7=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index a8fce93137fb..b9adedcc5b2e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -73,7 +73,7 @@ config CRYPTO_AES_ARM_BS
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_SIMD
-	select CRYPTO_AES_ARM
+	select CRYPTO_AES
 	help
 	  Use a faster and more secure NEON based implementation of AES in CBC,
 	  CTR and XTS modes
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index 2920b96dbd36..c76377961444 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -42,9 +42,6 @@ asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
 asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]);
 
-asmlinkage void __aes_arm_encrypt(const u32 rk[], int rounds, const u8 in[],
-				  u8 out[]);
-
 struct aesbs_ctx {
 	int	rounds;
 	u8	rk[13 * (8 * AES_BLOCK_SIZE) + 32] __aligned(AES_BLOCK_SIZE);
@@ -52,12 +49,12 @@ struct aesbs_ctx {
 
 struct aesbs_cbc_ctx {
 	struct aesbs_ctx	key;
-	u32			enc[AES_MAX_KEYLENGTH_U32];
+	struct crypto_cipher	*enc_tfm;
 };
 
 struct aesbs_xts_ctx {
 	struct aesbs_ctx	key;
-	u32			twkey[AES_MAX_KEYLENGTH_U32];
+	struct crypto_cipher	*tweak_tfm;
 };
 
 static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
@@ -132,20 +129,18 @@ static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 
 	ctx->key.rounds = 6 + key_len / 4;
 
-	memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc));
-
 	kernel_neon_begin();
 	aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
 	kernel_neon_end();
 
-	return 0;
+	return crypto_cipher_setkey(ctx->enc_tfm, in_key, key_len);
 }
 
 static void cbc_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
 {
 	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	__aes_arm_encrypt(ctx->enc, ctx->key.rounds, src, dst);
+	crypto_cipher_encrypt_one(ctx->enc_tfm, dst, src);
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
@@ -181,6 +176,23 @@ static int cbc_decrypt(struct skcipher_request *req)
 	return err;
 }
 
+static int cbc_init(struct crypto_tfm *tfm)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->enc_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(ctx->enc_tfm))
+		return PTR_ERR(ctx->enc_tfm);
+	return 0;
+}
+
+static void cbc_exit(struct crypto_tfm *tfm)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_cipher(ctx->enc_tfm);
+}
+
 static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -228,7 +240,6 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_aes_ctx rk;
 	int err;
 
 	err = xts_verify_key(tfm, in_key, key_len);
@@ -236,15 +247,30 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 		return err;
 
 	key_len /= 2;
-	err = crypto_aes_expand_key(&rk, in_key + key_len, key_len);
+	err = crypto_cipher_setkey(ctx->tweak_tfm, in_key + key_len, key_len);
 	if (err)
 		return err;
 
-	memcpy(ctx->twkey, rk.key_enc, sizeof(ctx->twkey));
-
 	return aesbs_setkey(tfm, in_key, key_len);
 }
 
+static int xts_init(struct crypto_tfm *tfm)
+{
+	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->tweak_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(ctx->tweak_tfm))
+		return PTR_ERR(ctx->tweak_tfm);
+	return 0;
+}
+
+static void xts_exit(struct crypto_tfm *tfm)
+{
+	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_cipher(ctx->tweak_tfm);
+}
+
 static int __xts_crypt(struct skcipher_request *req,
 		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]))
@@ -256,7 +282,7 @@ static int __xts_crypt(struct skcipher_request *req,
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	__aes_arm_encrypt(ctx->twkey, ctx->key.rounds, walk.iv, walk.iv);
+	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 
 	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
@@ -309,6 +335,8 @@ static struct skcipher_alg aes_algs[] = { {
 	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_init		= cbc_init,
+	.base.cra_exit		= cbc_exit,
 
 	.min_keysize		= AES_MIN_KEY_SIZE,
 	.max_keysize		= AES_MAX_KEY_SIZE,
@@ -342,6 +370,8 @@ static struct skcipher_alg aes_algs[] = { {
 	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+	.base.cra_init		= xts_init,
+	.base.cra_exit		= xts_exit,
 
 	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
 	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
@@ -402,5 +432,5 @@ unregister_simds:
 	return err;
 }
 
-module_init(aes_init);
+late_initcall(aes_init);
 module_exit(aes_exit);
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 5d995f7724af..620495a43363 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -380,7 +380,7 @@
 			#size-cells = <2>;
 			ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>;
 
-			rng {
+			hwrng: rng {
 				compatible = "amlogic,meson-rng";
 				reg = <0x0 0x0 0x0 0x4>;
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 04b3324bc132..a375cb21cc8b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -524,3 +524,8 @@
 &vpu {
 	compatible = "amlogic,meson-gxbb-vpu", "amlogic,meson-gx-vpu";
 };
+
+&hwrng {
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
+};
diff --git a/arch/metag/kernel/stacktrace.c b/arch/metag/kernel/stacktrace.c
index 91ffc4b75c33..09d67b7f51ca 100644
--- a/arch/metag/kernel/stacktrace.c
+++ b/arch/metag/kernel/stacktrace.c
@@ -31,8 +31,6 @@ static void tbi_boing_init(void)
 }
 #endif
 
-#define ALIGN_DOWN(addr, size)  ((addr)&(~((size)-1)))
-
 /*
  * Unwind the current stack frame and store the new register values in the
  * structure passed as argument. Unwinding is equivalent to a function return,
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 87f40454bad3..67eca3af9fc7 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -10,6 +10,8 @@ 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_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
+obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.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
@@ -17,3 +19,4 @@ 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
+crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
new file mode 100644
index 000000000000..0153a9c6f4af
--- /dev/null
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -0,0 +1,137 @@
+/*
+ * CRC vpmsum tester
+ * Copyright 2017 Daniel Axtens, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/crc-t10dif.h>
+#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 <linux/cpufeature.h>
+#include <asm/switch_to.h>
+
+static unsigned long iterations = 10000;
+
+#define MAX_CRC_LENGTH 65535
+
+
+static int __init crc_test_init(void)
+{
+	u16 crc16 = 0, verify16 = 0;
+	u32 crc32 = 0, verify32 = 0;
+	__le32 verify32le = 0;
+	unsigned char *data;
+	unsigned long i;
+	int ret;
+
+	struct crypto_shash *crct10dif_tfm;
+	struct crypto_shash *crc32c_tfm;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	data = kmalloc(MAX_CRC_LENGTH, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
+
+	if (IS_ERR(crct10dif_tfm)) {
+		pr_err("Error allocating crc-t10dif\n");
+		goto free_buf;
+	}
+
+	crc32c_tfm = crypto_alloc_shash("crc32c", 0, 0);
+
+	if (IS_ERR(crc32c_tfm)) {
+		pr_err("Error allocating crc32c\n");
+		goto free_16;
+	}
+
+	do {
+		SHASH_DESC_ON_STACK(crct10dif_shash, crct10dif_tfm);
+		SHASH_DESC_ON_STACK(crc32c_shash, crc32c_tfm);
+
+		crct10dif_shash->tfm = crct10dif_tfm;
+		ret = crypto_shash_init(crct10dif_shash);
+
+		if (ret) {
+			pr_err("Error initing crc-t10dif\n");
+			goto free_32;
+		}
+
+
+		crc32c_shash->tfm = crc32c_tfm;
+		ret = crypto_shash_init(crc32c_shash);
+
+		if (ret) {
+			pr_err("Error initing crc32c\n");
+			goto free_32;
+		}
+
+		pr_info("crc-vpmsum_test begins, %lu iterations\n", iterations);
+		for (i=0; i<iterations; i++) {
+			size_t len, offset;
+
+			get_random_bytes(data, MAX_CRC_LENGTH);
+			get_random_bytes(&len, sizeof(len));
+			get_random_bytes(&offset, sizeof(offset));
+
+			len %= MAX_CRC_LENGTH;
+			offset &= 15;
+			if (len <= offset)
+				continue;
+			len -= offset;
+
+			crypto_shash_update(crct10dif_shash, data+offset, len);
+			crypto_shash_final(crct10dif_shash, (u8 *)(&crc16));
+			verify16 = crc_t10dif_generic(verify16, data+offset, len);
+
+
+			if (crc16 != verify16) {
+				pr_err("FAILURE in CRC16: got 0x%04x expected 0x%04x (len %lu)\n",
+				       crc16, verify16, len);
+				break;
+			}
+
+			crypto_shash_update(crc32c_shash, data+offset, len);
+			crypto_shash_final(crc32c_shash, (u8 *)(&crc32));
+			verify32 = le32_to_cpu(verify32le);
+		        verify32le = ~cpu_to_le32(__crc32c_le(~verify32, data+offset, len));
+			if (crc32 != (u32)verify32le) {
+				pr_err("FAILURE in CRC32: got 0x%08x expected 0x%08x (len %lu)\n",
+				       crc32, verify32, len);
+				break;
+			}
+		}
+		pr_info("crc-vpmsum_test done, completed %lu iterations\n", i);
+	} while (0);
+
+free_32:
+	crypto_free_shash(crc32c_tfm);
+
+free_16:
+	crypto_free_shash(crct10dif_tfm);
+
+free_buf:
+	kfree(data);
+
+	return 0;
+}
+
+static void __exit crc_test_exit(void) {}
+
+module_init(crc_test_init);
+module_exit(crc_test_exit);
+module_param(iterations, long, 0400);
+
+MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
+MODULE_DESCRIPTION("Vector polynomial multiply-sum CRC tester");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S
new file mode 100644
index 000000000000..aadb59c96a27
--- /dev/null
+++ b/arch/powerpc/crypto/crc32-vpmsum_core.S
@@ -0,0 +1,755 @@
+/*
+ * Core of the accelerated CRC algorithm.
+ * In your file, define the constants and CRC_FUNCTION_NAME
+ * Then include this file.
+ *
+ * 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>
+
+#define MAX_SIZE	32768
+
+	.text
+
+#if defined(__BIG_ENDIAN__) && defined(REFLECT)
+#define BYTESWAP_DATA
+#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT)
+#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 CRC_FUNCTION_NAME(unsigned int crc, void *p, unsigned long len) */
+FUNC_START(CRC_FUNCTION_NAME)
+	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)
+#ifdef REFLECT
+	vsldoi	v8,zeroes,v8,8	/* shift into bottom 32 bits */
+#else
+	vsldoi	v8,v8,zeroes,4	/* shift into top 32 bits */
+#endif
+
+#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
+
+#ifdef REFLECT
+	/*
+	 * 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
+#endif
+
+	/* 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 */
+
+#ifdef REFLECT
+	/* shift left one bit */
+	vspltisb v1,1
+	vsl	v0,v0,v1
+#endif
+
+	vand	v0,v0,mask_64bit
+#ifndef REFLECT
+	/*
+	 * Now for the Barrett reduction algorithm. The idea is to calculate q,
+	 * the multiple of our polynomial that we need to subtract. By
+	 * doing the computation 2x bits higher (ie 64 bits) and shifting the
+	 * result back down 2x bits, we round down to the nearest multiple.
+	 */
+	VPMSUMD(v1,v0,const1)	/* ma */
+	vsldoi	v1,zeroes,v1,8	/* q = floor(ma/(2^64)) */
+	VPMSUMD(v1,v1,const2)	/* qn */
+	vxor	v0,v0,v1	/* a - qn, subtraction is xor in GF(2) */
+
+	/*
+	 * Get the result into r3. We need to shift it left 8 bytes:
+	 * V0 [ 0 1 2 X ]
+	 * V0 [ 0 X 2 3 ]
+	 */
+	vsldoi	v0,v0,zeroes,8	/* shift result into top 64 bits */
+#else
+	/*
+	 * 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 */
+#endif
+
+	/* 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