kernel-alx/patches-4.9/0285-4.9.186-all-fixes.patch

diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
index ee3723beb701..33b38716b77f 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
@@ -4,6 +4,7 @@ Required properties:
  - compatible: Should be one of the following:
    - "microchip,mcp2510" for MCP2510.
    - "microchip,mcp2515" for MCP2515.
+   - "microchip,mcp25625" for MCP25625.
  - reg: SPI chip select.
  - clocks: The clock feeding the CAN controller.
  - interrupt-parent: The parent interrupt controller.
diff --git a/Makefile b/Makefile
index c80dad45334e..1ab22a85118f 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 185
+SUBLEVEL = 186
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 61fd1ce63c56..6bb9f8ea9291 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -185,11 +185,6 @@ static void *__init unw_hdr_alloc_early(unsigned long sz)
 				       MAX_DMA_ADDRESS);
 }
 
-static void *unw_hdr_alloc(unsigned long sz)
-{
-	return kmalloc(sz, GFP_KERNEL);
-}
-
 static void init_unwind_table(struct unwind_table *table, const char *name,
 			      const void *core_start, unsigned long core_size,
 			      const void *init_start, unsigned long init_size,
@@ -370,6 +365,10 @@ ret_err:
 }
 
 #ifdef CONFIG_MODULES
+static void *unw_hdr_alloc(unsigned long sz)
+{
+	return kmalloc(sz, GFP_KERNEL);
+}
 
 static struct unwind_table *last_table;
 
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index 7839300fe46b..200d9082caa4 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -332,7 +332,7 @@
 			pwm1: pwm@02080000 {
 				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
 				reg = <0x02080000 0x4000>;
-				interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_PWM1>,
 					 <&clks IMX6UL_CLK_PWM1>;
 				clock-names = "ipg", "per";
@@ -343,7 +343,7 @@
 			pwm2: pwm@02084000 {
 				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
 				reg = <0x02084000 0x4000>;
-				interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_PWM2>,
 					 <&clks IMX6UL_CLK_PWM2>;
 				clock-names = "ipg", "per";
@@ -354,7 +354,7 @@
 			pwm3: pwm@02088000 {
 				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
 				reg = <0x02088000 0x4000>;
-				interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_PWM3>,
 					 <&clks IMX6UL_CLK_PWM3>;
 				clock-names = "ipg", "per";
@@ -365,7 +365,7 @@
 			pwm4: pwm@0208c000 {
 				compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm";
 				reg = <0x0208c000 0x4000>;
-				interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6UL_CLK_PWM4>,
 					 <&clks IMX6UL_CLK_PWM4>;
 				clock-names = "ipg", "per";
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 8e4539f69fdc..3bdf0d588238 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -1479,6 +1479,8 @@ static __init void da850_evm_init(void)
 	if (ret)
 		pr_warn("%s: dsp/rproc registration failed: %d\n",
 			__func__, ret);
+
+	regulator_has_full_constraints();
 }
 
 #ifdef CONFIG_SERIAL_8250_CONSOLE
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 9a22d40602aa..24779504f489 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -706,6 +706,9 @@ static struct platform_device da8xx_lcdc_device = {
 	.id		= 0,
 	.num_resources	= ARRAY_SIZE(da8xx_lcdc_resources),
 	.resource	= da8xx_lcdc_resources,
+	.dev		= {
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+	}
 };
 
 int __init da8xx_register_lcdc(struct da8xx_lcdc_platform_data *pdata)
diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c
index 718981bb80cd..0aec48c1736b 100644
--- a/arch/arm/mach-omap2/prm3xxx.c
+++ b/arch/arm/mach-omap2/prm3xxx.c
@@ -433,7 +433,7 @@ static void omap3_prm_reconfigure_io_chain(void)
  * registers, and omap3xxx_prm_reconfigure_io_chain() must be called.
  * No return value.
  */
-static void __init omap3xxx_prm_enable_io_wakeup(void)
+static void omap3xxx_prm_enable_io_wakeup(void)
 {
 	if (prm_features & PRM_HAS_IO_WAKEUP)
 		omap2_prm_set_mod_reg_bits(OMAP3430_EN_IO_MASK, WKUP_MOD,
diff --git a/arch/arm64/crypto/sha256-core.S b/arch/arm64/crypto/sha256-core.S
deleted file mode 100644
index 3ce82cc860bc..000000000000
--- a/arch/arm64/crypto/sha256-core.S
+++ /dev/null
@@ -1,2061 +0,0 @@
-// 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
-// project. The module is, however, dual licensed under OpenSSL and
-// CRYPTOGAMS licenses depending on where you obtain it. For further
-// details see http://www.openssl.org/~appro/cryptogams/.
-//
-// Permission to use under GPLv2 terms is granted.
-// ====================================================================
-//
-// SHA256/512 for ARMv8.
-//
-// Performance in cycles per processed byte and improvement coefficient
-// over code generated with "default" compiler:
-//
-//		SHA256-hw	SHA256(*)	SHA512
-// Apple A7	1.97		10.5 (+33%)	6.73 (-1%(**))
-// Cortex-A53	2.38		15.5 (+115%)	10.0 (+150%(***))
-// Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
-// Denver	2.01		10.5 (+26%)	6.70 (+8%)
-// X-Gene			20.0 (+100%)	12.8 (+300%(***))
-// Mongoose	2.36		13.0 (+50%)	8.36 (+33%)
-//
-// (*)	Software SHA256 results are of lesser relevance, presented
-//	mostly for informational purposes.
-// (**)	The result is a trade-off: it's possible to improve it by
-//	10% (or by 1 cycle per round), but at the cost of 20% loss
-//	on Cortex-A53 (or by 4 cycles per round).
-// (***)	Super-impressive coefficients over gcc-generated code are
-//	indication of some compiler "pathology", most notably code
-//	generated with -mgeneral-regs-only is significanty faster
-//	and the gap is only 40-90%.
-//
-// October 2016.
-//
-// Originally it was reckoned that it makes no sense to implement NEON
-// version of SHA256 for 64-bit processors. This is because performance
-// improvement on most wide-spread Cortex-A5x processors was observed
-// to be marginal, same on Cortex-A53 and ~10% on A57. But then it was
-// observed that 32-bit NEON SHA256 performs significantly better than
-// 64-bit scalar version on *some* of the more recent processors. As
-// result 64-bit NEON version of SHA256 was added to provide best
-// all-round performance. For example it executes ~30% faster on X-Gene
-// and Mongoose. [For reference, NEON version of SHA512 is bound to
-// deliver much less improvement, likely *negative* on Cortex-A5x.
-// Which is why NEON support is limited to SHA256.]
-
-#ifndef	__KERNEL__
-# include "arm_arch.h"
-#endif
-
-.text
-
-.extern	OPENSSL_armcap_P
-.globl	sha256_block_data_order
-.type	sha256_block_data_order,%function
-.align	6
-sha256_block_data_order:
-#ifndef	__KERNEL__
-# ifdef	__ILP32__
-	ldrsw	x16,.LOPENSSL_armcap_P
-# else
-	ldr	x16,.LOPENSSL_armcap_P
-# endif
-	adr	x17,.LOPENSSL_armcap_P
-	add	x16,x16,x17
-	ldr	w16,[x16]
-	tst	w16,#ARMV8_SHA256
-	b.ne	.Lv8_entry
-	tst	w16,#ARMV7_NEON
-	b.ne	.Lneon_entry
-#endif
-	stp	x29,x30,[sp,#-128]!
-	add	x29,sp,#0
-
-	stp	x19,x20,[sp,#16]
-	stp	x21,x22,[sp,#32]
-	stp	x23,x24,[sp,#48]
-	stp	x25,x26,[sp,#64]
-	stp	x27,x28,[sp,#80]
-	sub	sp,sp,#4*4
-
-	ldp	w20,w21,[x0]				// load context
-	ldp	w22,w23,[x0,#2*4]
-	ldp	w24,w25,[x0,#4*4]
-	add	x2,x1,x2,lsl#6	// end of input
-	ldp	w26,w27,[x0,#6*4]
-	adr	x30,.LK256
-	stp	x0,x2,[x29,#96]
-
-.Loop:
-	ldp	w3,w4,[x1],#2*4
-	ldr	w19,[x30],#4			// *K++
-	eor	w28,w21,w22				// magic seed
-	str	x1,[x29,#112]
-#ifndef	__AARCH64EB__
-	rev	w3,w3			// 0
-#endif
-	ror	w16,w24,#6
-	add	w27,w27,w19			// h+=K[i]
-	eor	w6,w24,w24,ror#14
-	and	w17,w25,w24
-	bic	w19,w26,w24
-	add	w27,w27,w3			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w20,w21			// a^b, b^c in next round
-	eor	w16,w16,w6,ror#11	// Sigma1(e)
-	ror	w6,w20,#2
-	add	w27,w27,w17			// h+=Ch(e,f,g)
-	eor	w17,w20,w20,ror#9
-	add	w27,w27,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w23,w23,w27			// d+=h
-	eor	w28,w28,w21			// Maj(a,b,c)
-	eor	w17,w6,w17,ror#13	// Sigma0(a)
-	add	w27,w27,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w27,w27,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w4,w4			// 1
-#endif
-	ldp	w5,w6,[x1],#2*4
-	add	w27,w27,w17			// h+=Sigma0(a)
-	ror	w16,w23,#6
-	add	w26,w26,w28			// h+=K[i]
-	eor	w7,w23,w23,ror#14
-	and	w17,w24,w23
-	bic	w28,w25,w23
-	add	w26,w26,w4			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w27,w20			// a^b, b^c in next round
-	eor	w16,w16,w7,ror#11	// Sigma1(e)
-	ror	w7,w27,#2
-	add	w26,w26,w17			// h+=Ch(e,f,g)
-	eor	w17,w27,w27,ror#9
-	add	w26,w26,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w22,w22,w26			// d+=h
-	eor	w19,w19,w20			// Maj(a,b,c)
-	eor	w17,w7,w17,ror#13	// Sigma0(a)
-	add	w26,w26,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w26,w26,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w5,w5			// 2
-#endif
-	add	w26,w26,w17			// h+=Sigma0(a)
-	ror	w16,w22,#6
-	add	w25,w25,w19			// h+=K[i]
-	eor	w8,w22,w22,ror#14
-	and	w17,w23,w22
-	bic	w19,w24,w22
-	add	w25,w25,w5			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w26,w27			// a^b, b^c in next round
-	eor	w16,w16,w8,ror#11	// Sigma1(e)
-	ror	w8,w26,#2
-	add	w25,w25,w17			// h+=Ch(e,f,g)
-	eor	w17,w26,w26,ror#9
-	add	w25,w25,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w21,w21,w25			// d+=h
-	eor	w28,w28,w27			// Maj(a,b,c)
-	eor	w17,w8,w17,ror#13	// Sigma0(a)
-	add	w25,w25,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w25,w25,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w6,w6			// 3
-#endif
-	ldp	w7,w8,[x1],#2*4
-	add	w25,w25,w17			// h+=Sigma0(a)
-	ror	w16,w21,#6
-	add	w24,w24,w28			// h+=K[i]
-	eor	w9,w21,w21,ror#14
-	and	w17,w22,w21
-	bic	w28,w23,w21
-	add	w24,w24,w6			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w25,w26			// a^b, b^c in next round
-	eor	w16,w16,w9,ror#11	// Sigma1(e)
-	ror	w9,w25,#2
-	add	w24,w24,w17			// h+=Ch(e,f,g)
-	eor	w17,w25,w25,ror#9
-	add	w24,w24,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w20,w20,w24			// d+=h
-	eor	w19,w19,w26			// Maj(a,b,c)
-	eor	w17,w9,w17,ror#13	// Sigma0(a)
-	add	w24,w24,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w24,w24,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w7,w7			// 4
-#endif
-	add	w24,w24,w17			// h+=Sigma0(a)
-	ror	w16,w20,#6
-	add	w23,w23,w19			// h+=K[i]
-	eor	w10,w20,w20,ror#14
-	and	w17,w21,w20
-	bic	w19,w22,w20
-	add	w23,w23,w7			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w24,w25			// a^b, b^c in next round
-	eor	w16,w16,w10,ror#11	// Sigma1(e)
-	ror	w10,w24,#2
-	add	w23,w23,w17			// h+=Ch(e,f,g)
-	eor	w17,w24,w24,ror#9
-	add	w23,w23,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w27,w27,w23			// d+=h
-	eor	w28,w28,w25			// Maj(a,b,c)
-	eor	w17,w10,w17,ror#13	// Sigma0(a)
-	add	w23,w23,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w23,w23,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w8,w8			// 5
-#endif
-	ldp	w9,w10,[x1],#2*4
-	add	w23,w23,w17			// h+=Sigma0(a)
-	ror	w16,w27,#6
-	add	w22,w22,w28			// h+=K[i]
-	eor	w11,w27,w27,ror#14
-	and	w17,w20,w27
-	bic	w28,w21,w27
-	add	w22,w22,w8			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w23,w24			// a^b, b^c in next round
-	eor	w16,w16,w11,ror#11	// Sigma1(e)
-	ror	w11,w23,#2
-	add	w22,w22,w17			// h+=Ch(e,f,g)
-	eor	w17,w23,w23,ror#9
-	add	w22,w22,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w26,w26,w22			// d+=h
-	eor	w19,w19,w24			// Maj(a,b,c)
-	eor	w17,w11,w17,ror#13	// Sigma0(a)
-	add	w22,w22,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w22,w22,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w9,w9			// 6
-#endif
-	add	w22,w22,w17			// h+=Sigma0(a)
-	ror	w16,w26,#6
-	add	w21,w21,w19			// h+=K[i]
-	eor	w12,w26,w26,ror#14
-	and	w17,w27,w26
-	bic	w19,w20,w26
-	add	w21,w21,w9			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w22,w23			// a^b, b^c in next round
-	eor	w16,w16,w12,ror#11	// Sigma1(e)
-	ror	w12,w22,#2
-	add	w21,w21,w17			// h+=Ch(e,f,g)
-	eor	w17,w22,w22,ror#9
-	add	w21,w21,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w25,w25,w21			// d+=h
-	eor	w28,w28,w23			// Maj(a,b,c)
-	eor	w17,w12,w17,ror#13	// Sigma0(a)
-	add	w21,w21,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w21,w21,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w10,w10			// 7
-#endif
-	ldp	w11,w12,[x1],#2*4
-	add	w21,w21,w17			// h+=Sigma0(a)
-	ror	w16,w25,#6
-	add	w20,w20,w28			// h+=K[i]
-	eor	w13,w25,w25,ror#14
-	and	w17,w26,w25
-	bic	w28,w27,w25
-	add	w20,w20,w10			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w21,w22			// a^b, b^c in next round
-	eor	w16,w16,w13,ror#11	// Sigma1(e)
-	ror	w13,w21,#2
-	add	w20,w20,w17			// h+=Ch(e,f,g)
-	eor	w17,w21,w21,ror#9
-	add	w20,w20,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w24,w24,w20			// d+=h
-	eor	w19,w19,w22			// Maj(a,b,c)
-	eor	w17,w13,w17,ror#13	// Sigma0(a)
-	add	w20,w20,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w20,w20,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w11,w11			// 8
-#endif
-	add	w20,w20,w17			// h+=Sigma0(a)
-	ror	w16,w24,#6
-	add	w27,w27,w19			// h+=K[i]
-	eor	w14,w24,w24,ror#14
-	and	w17,w25,w24
-	bic	w19,w26,w24
-	add	w27,w27,w11			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w20,w21			// a^b, b^c in next round
-	eor	w16,w16,w14,ror#11	// Sigma1(e)
-	ror	w14,w20,#2
-	add	w27,w27,w17			// h+=Ch(e,f,g)
-	eor	w17,w20,w20,ror#9
-	add	w27,w27,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w23,w23,w27			// d+=h
-	eor	w28,w28,w21			// Maj(a,b,c)
-	eor	w17,w14,w17,ror#13	// Sigma0(a)
-	add	w27,w27,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w27,w27,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w12,w12			// 9
-#endif
-	ldp	w13,w14,[x1],#2*4
-	add	w27,w27,w17			// h+=Sigma0(a)
-	ror	w16,w23,#6
-	add	w26,w26,w28			// h+=K[i]
-	eor	w15,w23,w23,ror#14
-	and	w17,w24,w23
-	bic	w28,w25,w23
-	add	w26,w26,w12			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w27,w20			// a^b, b^c in next round
-	eor	w16,w16,w15,ror#11	// Sigma1(e)
-	ror	w15,w27,#2
-	add	w26,w26,w17			// h+=Ch(e,f,g)
-	eor	w17,w27,w27,ror#9
-	add	w26,w26,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w22,w22,w26			// d+=h
-	eor	w19,w19,w20			// Maj(a,b,c)
-	eor	w17,w15,w17,ror#13	// Sigma0(a)
-	add	w26,w26,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w26,w26,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w13,w13			// 10
-#endif
-	add	w26,w26,w17			// h+=Sigma0(a)
-	ror	w16,w22,#6
-	add	w25,w25,w19			// h+=K[i]
-	eor	w0,w22,w22,ror#14
-	and	w17,w23,w22
-	bic	w19,w24,w22
-	add	w25,w25,w13			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w26,w27			// a^b, b^c in next round
-	eor	w16,w16,w0,ror#11	// Sigma1(e)
-	ror	w0,w26,#2
-	add	w25,w25,w17			// h+=Ch(e,f,g)
-	eor	w17,w26,w26,ror#9
-	add	w25,w25,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w21,w21,w25			// d+=h
-	eor	w28,w28,w27			// Maj(a,b,c)
-	eor	w17,w0,w17,ror#13	// Sigma0(a)
-	add	w25,w25,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w25,w25,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w14,w14			// 11
-#endif
-	ldp	w15,w0,[x1],#2*4
-	add	w25,w25,w17			// h+=Sigma0(a)
-	str	w6,[sp,#12]
-	ror	w16,w21,#6
-	add	w24,w24,w28			// h+=K[i]
-	eor	w6,w21,w21,ror#14
-	and	w17,w22,w21
-	bic	w28,w23,w21
-	add	w24,w24,w14			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w25,w26			// a^b, b^c in next round
-	eor	w16,w16,w6,ror#11	// Sigma1(e)
-	ror	w6,w25,#2
-	add	w24,w24,w17			// h+=Ch(e,f,g)
-	eor	w17,w25,w25,ror#9
-	add	w24,w24,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w20,w20,w24			// d+=h
-	eor	w19,w19,w26			// Maj(a,b,c)
-	eor	w17,w6,w17,ror#13	// Sigma0(a)
-	add	w24,w24,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w24,w24,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w15,w15			// 12
-#endif
-	add	w24,w24,w17			// h+=Sigma0(a)
-	str	w7,[sp,#0]
-	ror	w16,w20,#6
-	add	w23,w23,w19			// h+=K[i]
-	eor	w7,w20,w20,ror#14
-	and	w17,w21,w20
-	bic	w19,w22,w20
-	add	w23,w23,w15			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w24,w25			// a^b, b^c in next round
-	eor	w16,w16,w7,ror#11	// Sigma1(e)
-	ror	w7,w24,#2
-	add	w23,w23,w17			// h+=Ch(e,f,g)
-	eor	w17,w24,w24,ror#9
-	add	w23,w23,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w27,w27,w23			// d+=h
-	eor	w28,w28,w25			// Maj(a,b,c)
-	eor	w17,w7,w17,ror#13	// Sigma0(a)
-	add	w23,w23,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w23,w23,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w0,w0			// 13
-#endif
-	ldp	w1,w2,[x1]
-	add	w23,w23,w17			// h+=Sigma0(a)
-	str	w8,[sp,#4]
-	ror	w16,w27,#6
-	add	w22,w22,w28			// h+=K[i]
-	eor	w8,w27,w27,ror#14
-	and	w17,w20,w27
-	bic	w28,w21,w27
-	add	w22,w22,w0			// h+=X[i]
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w23,w24			// a^b, b^c in next round
-	eor	w16,w16,w8,ror#11	// Sigma1(e)
-	ror	w8,w23,#2
-	add	w22,w22,w17			// h+=Ch(e,f,g)
-	eor	w17,w23,w23,ror#9
-	add	w22,w22,w16			// h+=Sigma1(e)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	add	w26,w26,w22			// d+=h
-	eor	w19,w19,w24			// Maj(a,b,c)
-	eor	w17,w8,w17,ror#13	// Sigma0(a)
-	add	w22,w22,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	//add	w22,w22,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w1,w1			// 14
-#endif
-	ldr	w6,[sp,#12]
-	add	w22,w22,w17			// h+=Sigma0(a)
-	str	w9,[sp,#8]
-	ror	w16,w26,#6
-	add	w21,w21,w19			// h+=K[i]
-	eor	w9,w26,w26,ror#14
-	and	w17,w27,w26
-	bic	w19,w20,w26
-	add	w21,w21,w1			// h+=X[i]
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w22,w23			// a^b, b^c in next round
-	eor	w16,w16,w9,ror#11	// Sigma1(e)
-	ror	w9,w22,#2
-	add	w21,w21,w17			// h+=Ch(e,f,g)
-	eor	w17,w22,w22,ror#9
-	add	w21,w21,w16			// h+=Sigma1(e)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	add	w25,w25,w21			// d+=h
-	eor	w28,w28,w23			// Maj(a,b,c)
-	eor	w17,w9,w17,ror#13	// Sigma0(a)
-	add	w21,w21,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	//add	w21,w21,w17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	w2,w2			// 15
-#endif
-	ldr	w7,[sp,#0]
-	add	w21,w21,w17			// h+=Sigma0(a)
-	str	w10,[sp,#12]
-	ror	w16,w25,#6
-	add	w20,w20,w28			// h+=K[i]
-	ror	w9,w4,#7
-	and	w17,w26,w25
-	ror	w8,w1,#17
-	bic	w28,w27,w25
-	ror	w10,w21,#2
-	add	w20,w20,w2			// h+=X[i]
-	eor	w16,w16,w25,ror#11
-	eor	w9,w9,w4,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w21,w22			// a^b, b^c in next round
-	eor	w16,w16,w25,ror#25	// Sigma1(e)
-	eor	w10,w10,w21,ror#13
-	add	w20,w20,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w8,w8,w1,ror#19
-	eor	w9,w9,w4,lsr#3	// sigma0(X[i+1])
-	add	w20,w20,w16			// h+=Sigma1(e)
-	eor	w19,w19,w22			// Maj(a,b,c)
-	eor	w17,w10,w21,ror#22	// Sigma0(a)
-	eor	w8,w8,w1,lsr#10	// sigma1(X[i+14])
-	add	w3,w3,w12
-	add	w24,w24,w20			// d+=h
-	add	w20,w20,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w3,w3,w9
-	add	w20,w20,w17			// h+=Sigma0(a)
-	add	w3,w3,w8
-.Loop_16_xx:
-	ldr	w8,[sp,#4]
-	str	w11,[sp,#0]
-	ror	w16,w24,#6
-	add	w27,w27,w19			// h+=K[i]
-	ror	w10,w5,#7
-	and	w17,w25,w24
-	ror	w9,w2,#17
-	bic	w19,w26,w24
-	ror	w11,w20,#2
-	add	w27,w27,w3			// h+=X[i]
-	eor	w16,w16,w24,ror#11
-	eor	w10,w10,w5,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w20,w21			// a^b, b^c in next round
-	eor	w16,w16,w24,ror#25	// Sigma1(e)
-	eor	w11,w11,w20,ror#13
-	add	w27,w27,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w9,w9,w2,ror#19
-	eor	w10,w10,w5,lsr#3	// sigma0(X[i+1])
-	add	w27,w27,w16			// h+=Sigma1(e)
-	eor	w28,w28,w21			// Maj(a,b,c)
-	eor	w17,w11,w20,ror#22	// Sigma0(a)
-	eor	w9,w9,w2,lsr#10	// sigma1(X[i+14])
-	add	w4,w4,w13
-	add	w23,w23,w27			// d+=h
-	add	w27,w27,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w4,w4,w10
-	add	w27,w27,w17			// h+=Sigma0(a)
-	add	w4,w4,w9
-	ldr	w9,[sp,#8]
-	str	w12,[sp,#4]
-	ror	w16,w23,#6
-	add	w26,w26,w28			// h+=K[i]
-	ror	w11,w6,#7
-	and	w17,w24,w23
-	ror	w10,w3,#17
-	bic	w28,w25,w23
-	ror	w12,w27,#2
-	add	w26,w26,w4			// h+=X[i]
-	eor	w16,w16,w23,ror#11
-	eor	w11,w11,w6,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w27,w20			// a^b, b^c in next round
-	eor	w16,w16,w23,ror#25	// Sigma1(e)
-	eor	w12,w12,w27,ror#13
-	add	w26,w26,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w10,w10,w3,ror#19
-	eor	w11,w11,w6,lsr#3	// sigma0(X[i+1])
-	add	w26,w26,w16			// h+=Sigma1(e)
-	eor	w19,w19,w20			// Maj(a,b,c)
-	eor	w17,w12,w27,ror#22	// Sigma0(a)
-	eor	w10,w10,w3,lsr#10	// sigma1(X[i+14])
-	add	w5,w5,w14
-	add	w22,w22,w26			// d+=h
-	add	w26,w26,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w5,w5,w11
-	add	w26,w26,w17			// h+=Sigma0(a)
-	add	w5,w5,w10
-	ldr	w10,[sp,#12]
-	str	w13,[sp,#8]
-	ror	w16,w22,#6
-	add	w25,w25,w19			// h+=K[i]
-	ror	w12,w7,#7
-	and	w17,w23,w22
-	ror	w11,w4,#17
-	bic	w19,w24,w22
-	ror	w13,w26,#2
-	add	w25,w25,w5			// h+=X[i]
-	eor	w16,w16,w22,ror#11
-	eor	w12,w12,w7,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w26,w27			// a^b, b^c in next round
-	eor	w16,w16,w22,ror#25	// Sigma1(e)
-	eor	w13,w13,w26,ror#13
-	add	w25,w25,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w11,w11,w4,ror#19
-	eor	w12,w12,w7,lsr#3	// sigma0(X[i+1])
-	add	w25,w25,w16			// h+=Sigma1(e)
-	eor	w28,w28,w27			// Maj(a,b,c)
-	eor	w17,w13,w26,ror#22	// Sigma0(a)
-	eor	w11,w11,w4,lsr#10	// sigma1(X[i+14])
-	add	w6,w6,w15
-	add	w21,w21,w25			// d+=h
-	add	w25,w25,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w6,w6,w12
-	add	w25,w25,w17			// h+=Sigma0(a)
-	add	w6,w6,w11
-	ldr	w11,[sp,#0]
-	str	w14,[sp,#12]
-	ror	w16,w21,#6
-	add	w24,w24,w28			// h+=K[i]
-	ror	w13,w8,#7
-	and	w17,w22,w21
-	ror	w12,w5,#17
-	bic	w28,w23,w21
-	ror	w14,w25,#2
-	add	w24,w24,w6			// h+=X[i]
-	eor	w16,w16,w21,ror#11
-	eor	w13,w13,w8,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w25,w26			// a^b, b^c in next round
-	eor	w16,w16,w21,ror#25	// Sigma1(e)
-	eor	w14,w14,w25,ror#13
-	add	w24,w24,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w12,w12,w5,ror#19
-	eor	w13,w13,w8,lsr#3	// sigma0(X[i+1])
-	add	w24,w24,w16			// h+=Sigma1(e)
-	eor	w19,w19,w26			// Maj(a,b,c)
-	eor	w17,w14,w25,ror#22	// Sigma0(a)
-	eor	w12,w12,w5,lsr#10	// sigma1(X[i+14])
-	add	w7,w7,w0
-	add	w20,w20,w24			// d+=h
-	add	w24,w24,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w7,w7,w13
-	add	w24,w24,w17			// h+=Sigma0(a)
-	add	w7,w7,w12
-	ldr	w12,[sp,#4]
-	str	w15,[sp,#0]
-	ror	w16,w20,#6
-	add	w23,w23,w19			// h+=K[i]
-	ror	w14,w9,#7
-	and	w17,w21,w20
-	ror	w13,w6,#17
-	bic	w19,w22,w20
-	ror	w15,w24,#2
-	add	w23,w23,w7			// h+=X[i]
-	eor	w16,w16,w20,ror#11
-	eor	w14,w14,w9,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w24,w25			// a^b, b^c in next round
-	eor	w16,w16,w20,ror#25	// Sigma1(e)
-	eor	w15,w15,w24,ror#13
-	add	w23,w23,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w13,w13,w6,ror#19
-	eor	w14,w14,w9,lsr#3	// sigma0(X[i+1])
-	add	w23,w23,w16			// h+=Sigma1(e)
-	eor	w28,w28,w25			// Maj(a,b,c)
-	eor	w17,w15,w24,ror#22	// Sigma0(a)
-	eor	w13,w13,w6,lsr#10	// sigma1(X[i+14])
-	add	w8,w8,w1
-	add	w27,w27,w23			// d+=h
-	add	w23,w23,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w8,w8,w14
-	add	w23,w23,w17			// h+=Sigma0(a)
-	add	w8,w8,w13
-	ldr	w13,[sp,#8]
-	str	w0,[sp,#4]
-	ror	w16,w27,#6
-	add	w22,w22,w28			// h+=K[i]
-	ror	w15,w10,#7
-	and	w17,w20,w27
-	ror	w14,w7,#17
-	bic	w28,w21,w27
-	ror	w0,w23,#2
-	add	w22,w22,w8			// h+=X[i]
-	eor	w16,w16,w27,ror#11
-	eor	w15,w15,w10,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w23,w24			// a^b, b^c in next round
-	eor	w16,w16,w27,ror#25	// Sigma1(e)
-	eor	w0,w0,w23,ror#13
-	add	w22,w22,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w14,w14,w7,ror#19
-	eor	w15,w15,w10,lsr#3	// sigma0(X[i+1])
-	add	w22,w22,w16			// h+=Sigma1(e)
-	eor	w19,w19,w24			// Maj(a,b,c)
-	eor	w17,w0,w23,ror#22	// Sigma0(a)
-	eor	w14,w14,w7,lsr#10	// sigma1(X[i+14])
-	add	w9,w9,w2
-	add	w26,w26,w22			// d+=h
-	add	w22,w22,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w9,w9,w15
-	add	w22,w22,w17			// h+=Sigma0(a)
-	add	w9,w9,w14
-	ldr	w14,[sp,#12]
-	str	w1,[sp,#8]
-	ror	w16,w26,#6
-	add	w21,w21,w19			// h+=K[i]
-	ror	w0,w11,#7
-	and	w17,w27,w26
-	ror	w15,w8,#17
-	bic	w19,w20,w26
-	ror	w1,w22,#2
-	add	w21,w21,w9			// h+=X[i]
-	eor	w16,w16,w26,ror#11
-	eor	w0,w0,w11,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w22,w23			// a^b, b^c in next round
-	eor	w16,w16,w26,ror#25	// Sigma1(e)
-	eor	w1,w1,w22,ror#13
-	add	w21,w21,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w15,w15,w8,ror#19
-	eor	w0,w0,w11,lsr#3	// sigma0(X[i+1])
-	add	w21,w21,w16			// h+=Sigma1(e)
-	eor	w28,w28,w23			// Maj(a,b,c)
-	eor	w17,w1,w22,ror#22	// Sigma0(a)
-	eor	w15,w15,w8,lsr#10	// sigma1(X[i+14])
-	add	w10,w10,w3
-	add	w25,w25,w21			// d+=h
-	add	w21,w21,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w10,w10,w0
-	add	w21,w21,w17			// h+=Sigma0(a)
-	add	w10,w10,w15
-	ldr	w15,[sp,#0]
-	str	w2,[sp,#12]
-	ror	w16,w25,#6
-	add	w20,w20,w28			// h+=K[i]
-	ror	w1,w12,#7
-	and	w17,w26,w25
-	ror	w0,w9,#17
-	bic	w28,w27,w25
-	ror	w2,w21,#2
-	add	w20,w20,w10			// h+=X[i]
-	eor	w16,w16,w25,ror#11
-	eor	w1,w1,w12,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w21,w22			// a^b, b^c in next round
-	eor	w16,w16,w25,ror#25	// Sigma1(e)
-	eor	w2,w2,w21,ror#13
-	add	w20,w20,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w0,w0,w9,ror#19
-	eor	w1,w1,w12,lsr#3	// sigma0(X[i+1])
-	add	w20,w20,w16			// h+=Sigma1(e)
-	eor	w19,w19,w22			// Maj(a,b,c)
-	eor	w17,w2,w21,ror#22	// Sigma0(a)
-	eor	w0,w0,w9,lsr#10	// sigma1(X[i+14])
-	add	w11,w11,w4
-	add	w24,w24,w20			// d+=h
-	add	w20,w20,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w11,w11,w1
-	add	w20,w20,w17			// h+=Sigma0(a)
-	add	w11,w11,w0
-	ldr	w0,[sp,#4]
-	str	w3,[sp,#0]
-	ror	w16,w24,#6
-	add	w27,w27,w19			// h+=K[i]
-	ror	w2,w13,#7
-	and	w17,w25,w24
-	ror	w1,w10,#17
-	bic	w19,w26,w24
-	ror	w3,w20,#2
-	add	w27,w27,w11			// h+=X[i]
-	eor	w16,w16,w24,ror#11
-	eor	w2,w2,w13,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w20,w21			// a^b, b^c in next round
-	eor	w16,w16,w24,ror#25	// Sigma1(e)
-	eor	w3,w3,w20,ror#13
-	add	w27,w27,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w1,w1,w10,ror#19
-	eor	w2,w2,w13,lsr#3	// sigma0(X[i+1])
-	add	w27,w27,w16			// h+=Sigma1(e)
-	eor	w28,w28,w21			// Maj(a,b,c)
-	eor	w17,w3,w20,ror#22	// Sigma0(a)
-	eor	w1,w1,w10,lsr#10	// sigma1(X[i+14])
-	add	w12,w12,w5
-	add	w23,w23,w27			// d+=h
-	add	w27,w27,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w12,w12,w2
-	add	w27,w27,w17			// h+=Sigma0(a)
-	add	w12,w12,w1
-	ldr	w1,[sp,#8]
-	str	w4,[sp,#4]
-	ror	w16,w23,#6
-	add	w26,w26,w28			// h+=K[i]
-	ror	w3,w14,#7
-	and	w17,w24,w23
-	ror	w2,w11,#17
-	bic	w28,w25,w23
-	ror	w4,w27,#2
-	add	w26,w26,w12			// h+=X[i]
-	eor	w16,w16,w23,ror#11
-	eor	w3,w3,w14,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w27,w20			// a^b, b^c in next round
-	eor	w16,w16,w23,ror#25	// Sigma1(e)
-	eor	w4,w4,w27,ror#13
-	add	w26,w26,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w2,w2,w11,ror#19
-	eor	w3,w3,w14,lsr#3	// sigma0(X[i+1])
-	add	w26,w26,w16			// h+=Sigma1(e)
-	eor	w19,w19,w20			// Maj(a,b,c)
-	eor	w17,w4,w27,ror#22	// Sigma0(a)
-	eor	w2,w2,w11,lsr#10	// sigma1(X[i+14])
-	add	w13,w13,w6
-	add	w22,w22,w26			// d+=h
-	add	w26,w26,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w13,w13,w3
-	add	w26,w26,w17			// h+=Sigma0(a)
-	add	w13,w13,w2
-	ldr	w2,[sp,#12]
-	str	w5,[sp,#8]
-	ror	w16,w22,#6
-	add	w25,w25,w19			// h+=K[i]
-	ror	w4,w15,#7
-	and	w17,w23,w22
-	ror	w3,w12,#17
-	bic	w19,w24,w22
-	ror	w5,w26,#2
-	add	w25,w25,w13			// h+=X[i]
-	eor	w16,w16,w22,ror#11
-	eor	w4,w4,w15,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w26,w27			// a^b, b^c in next round
-	eor	w16,w16,w22,ror#25	// Sigma1(e)
-	eor	w5,w5,w26,ror#13
-	add	w25,w25,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w3,w3,w12,ror#19
-	eor	w4,w4,w15,lsr#3	// sigma0(X[i+1])
-	add	w25,w25,w16			// h+=Sigma1(e)
-	eor	w28,w28,w27			// Maj(a,b,c)
-	eor	w17,w5,w26,ror#22	// Sigma0(a)
-	eor	w3,w3,w12,lsr#10	// sigma1(X[i+14])
-	add	w14,w14,w7
-	add	w21,w21,w25			// d+=h
-	add	w25,w25,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w14,w14,w4
-	add	w25,w25,w17			// h+=Sigma0(a)
-	add	w14,w14,w3
-	ldr	w3,[sp,#0]
-	str	w6,[sp,#12]
-	ror	w16,w21,#6
-	add	w24,w24,w28			// h+=K[i]
-	ror	w5,w0,#7
-	and	w17,w22,w21
-	ror	w4,w13,#17
-	bic	w28,w23,w21
-	ror	w6,w25,#2
-	add	w24,w24,w14			// h+=X[i]
-	eor	w16,w16,w21,ror#11
-	eor	w5,w5,w0,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w25,w26			// a^b, b^c in next round
-	eor	w16,w16,w21,ror#25	// Sigma1(e)
-	eor	w6,w6,w25,ror#13
-	add	w24,w24,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w4,w4,w13,ror#19
-	eor	w5,w5,w0,lsr#3	// sigma0(X[i+1])
-	add	w24,w24,w16			// h+=Sigma1(e)
-	eor	w19,w19,w26			// Maj(a,b,c)
-	eor	w17,w6,w25,ror#22	// Sigma0(a)
-	eor	w4,w4,w13,lsr#10	// sigma1(X[i+14])
-	add	w15,w15,w8
-	add	w20,w20,w24			// d+=h
-	add	w24,w24,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w15,w15,w5
-	add	w24,w24,w17			// h+=Sigma0(a)
-	add	w15,w15,w4
-	ldr	w4,[sp,#4]
-	str	w7,[sp,#0]
-	ror	w16,w20,#6
-	add	w23,w23,w19			// h+=K[i]
-	ror	w6,w1,#7
-	and	w17,w21,w20
-	ror	w5,w14,#17
-	bic	w19,w22,w20
-	ror	w7,w24,#2
-	add	w23,w23,w15			// h+=X[i]
-	eor	w16,w16,w20,ror#11
-	eor	w6,w6,w1,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w24,w25			// a^b, b^c in next round
-	eor	w16,w16,w20,ror#25	// Sigma1(e)
-	eor	w7,w7,w24,ror#13
-	add	w23,w23,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w5,w5,w14,ror#19
-	eor	w6,w6,w1,lsr#3	// sigma0(X[i+1])
-	add	w23,w23,w16			// h+=Sigma1(e)
-	eor	w28,w28,w25			// Maj(a,b,c)
-	eor	w17,w7,w24,ror#22	// Sigma0(a)
-	eor	w5,w5,w14,lsr#10	// sigma1(X[i+14])
-	add	w0,w0,w9
-	add	w27,w27,w23			// d+=h
-	add	w23,w23,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w0,w0,w6
-	add	w23,w23,w17			// h+=Sigma0(a)
-	add	w0,w0,w5
-	ldr	w5,[sp,#8]
-	str	w8,[sp,#4]
-	ror	w16,w27,#6
-	add	w22,w22,w28			// h+=K[i]
-	ror	w7,w2,#7
-	and	w17,w20,w27
-	ror	w6,w15,#17
-	bic	w28,w21,w27
-	ror	w8,w23,#2
-	add	w22,w22,w0			// h+=X[i]
-	eor	w16,w16,w27,ror#11
-	eor	w7,w7,w2,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w23,w24			// a^b, b^c in next round
-	eor	w16,w16,w27,ror#25	// Sigma1(e)
-	eor	w8,w8,w23,ror#13
-	add	w22,w22,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w6,w6,w15,ror#19
-	eor	w7,w7,w2,lsr#3	// sigma0(X[i+1])
-	add	w22,w22,w16			// h+=Sigma1(e)
-	eor	w19,w19,w24			// Maj(a,b,c)
-	eor	w17,w8,w23,ror#22	// Sigma0(a)
-	eor	w6,w6,w15,lsr#10	// sigma1(X[i+14])
-	add	w1,w1,w10
-	add	w26,w26,w22			// d+=h
-	add	w22,w22,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w1,w1,w7
-	add	w22,w22,w17			// h+=Sigma0(a)
-	add	w1,w1,w6
-	ldr	w6,[sp,#12]
-	str	w9,[sp,#8]
-	ror	w16,w26,#6
-	add	w21,w21,w19			// h+=K[i]
-	ror	w8,w3,#7
-	and	w17,w27,w26
-	ror	w7,w0,#17
-	bic	w19,w20,w26
-	ror	w9,w22,#2
-	add	w21,w21,w1			// h+=X[i]
-	eor	w16,w16,w26,ror#11
-	eor	w8,w8,w3,ror#18
-	orr	w17,w17,w19			// Ch(e,f,g)
-	eor	w19,w22,w23			// a^b, b^c in next round
-	eor	w16,w16,w26,ror#25	// Sigma1(e)
-	eor	w9,w9,w22,ror#13
-	add	w21,w21,w17			// h+=Ch(e,f,g)
-	and	w28,w28,w19			// (b^c)&=(a^b)
-	eor	w7,w7,w0,ror#19
-	eor	w8,w8,w3,lsr#3	// sigma0(X[i+1])
-	add	w21,w21,w16			// h+=Sigma1(e)
-	eor	w28,w28,w23			// Maj(a,b,c)
-	eor	w17,w9,w22,ror#22	// Sigma0(a)
-	eor	w7,w7,w0,lsr#10	// sigma1(X[i+14])
-	add	w2,w2,w11
-	add	w25,w25,w21			// d+=h
-	add	w21,w21,w28			// h+=Maj(a,b,c)
-	ldr	w28,[x30],#4		// *K++, w19 in next round
-	add	w2,w2,w8
-	add	w21,w21,w17			// h+=Sigma0(a)
-	add	w2,w2,w7
-	ldr	w7,[sp,#0]
-	str	w10,[sp,#12]
-	ror	w16,w25,#6
-	add	w20,w20,w28			// h+=K[i]
-	ror	w9,w4,#7
-	and	w17,w26,w25
-	ror	w8,w1,#17
-	bic	w28,w27,w25
-	ror	w10,w21,#2
-	add	w20,w20,w2			// h+=X[i]
-	eor	w16,w16,w25,ror#11
-	eor	w9,w9,w4,ror#18
-	orr	w17,w17,w28			// Ch(e,f,g)
-	eor	w28,w21,w22			// a^b, b^c in next round
-	eor	w16,w16,w25,ror#25	// Sigma1(e)
-	eor	w10,w10,w21,ror#13
-	add	w20,w20,w17			// h+=Ch(e,f,g)
-	and	w19,w19,w28			// (b^c)&=(a^b)
-	eor	w8,w8,w1,ror#19
-	eor	w9,w9,w4,lsr#3	// sigma0(X[i+1])
-	add	w20,w20,w16			// h+=Sigma1(e)
-	eor	w19,w19,w22			// Maj(a,b,c)
-	eor	w17,w10,w21,ror#22	// Sigma0(a)
-	eor	w8,w8,w1,lsr#10	// sigma1(X[i+14])
-	add	w3,w3,w12
-	add	w24,w24,w20			// d+=h
-	add	w20,w20,w19			// h+=Maj(a,b,c)
-	ldr	w19,[x30],#4		// *K++, w28 in next round
-	add	w3,w3,w9
-	add	w20,w20,w17			// h+=Sigma0(a)
-	add	w3,w3,w8
-	cbnz	w19,.Loop_16_xx
-
-	ldp	x0,x2,[x29,#96]
-	ldr	x1,[x29,#112]
-	sub	x30,x30,#260		// rewind
-
-	ldp	w3,w4,[x0]
-	ldp	w5,w6,[x0,#2*4]
-	add	x1,x1,#14*4			// advance input pointer
-	ldp	w7,w8,[x0,#4*4]
-	add	w20,w20,w3
-	ldp	w9,w10,[x0,#6*4]
-	add	w21,w21,w4
-	add	w22,w22,w5
-	add	w23,w23,w6
-	stp	w20,w21,[x0]
-	add	w24,w24,w7
-	add	w25,w25,w8
-	stp	w22,w23,[x0,#2*4]
-	add	w26,w26,w9
-	add	w27,w27,w10
-	cmp	x1,x2
-	stp	w24,w25,[x0,#4*4]
-	stp	w26,w27,[x0,#6*4]
-	b.ne	.Loop
-
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#4*4
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#128
-	ret
-.size	sha256_block_data_order,.-sha256_block_data_order
-
-.align	6
-.type	.LK256,%object
-.LK256:
-	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
-	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
-	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
-	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
-	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
-	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
-	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
-	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
-	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
-	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
-	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
-	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
-	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
-	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
-	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
-	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-	.long	0	//terminator
-.size	.LK256,.-.LK256
-#ifndef	__KERNEL__
-.align	3
-.LOPENSSL_armcap_P:
-# ifdef	__ILP32__
-	.long	OPENSSL_armcap_P-.
-# else
-	.quad	OPENSSL_armcap_P-.
-# endif
-#endif
-.asciz	"SHA256 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>"
-.align	2
-#ifndef	__KERNEL__
-.type	sha256_block_armv8,%function
-.align	6
-sha256_block_armv8:
-.Lv8_entry:
-	stp		x29,x30,[sp,#-16]!
-	add		x29,sp,#0
-
-	ld1		{v0.4s,v1.4s},[x0]
-	adr		x3,.LK256
-
-.Loop_hw:
-	ld1		{v4.16b-v7.16b},[x1],#64
-	sub		x2,x2,#1
-	ld1		{v16.4s},[x3],#16
-	rev32		v4.16b,v4.16b
-	rev32		v5.16b,v5.16b
-	rev32		v6.16b,v6.16b
-	rev32		v7.16b,v7.16b
-	orr		v18.16b,v0.16b,v0.16b		// offload
-	orr		v19.16b,v1.16b,v1.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v4.4s
-	.inst	0x5e2828a4	//sha256su0 v4.16b,v5.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-	.inst	0x5e0760c4	//sha256su1 v4.16b,v6.16b,v7.16b
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v5.4s
-	.inst	0x5e2828c5	//sha256su0 v5.16b,v6.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-	.inst	0x5e0460e5	//sha256su1 v5.16b,v7.16b,v4.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v6.4s
-	.inst	0x5e2828e6	//sha256su0 v6.16b,v7.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-	.inst	0x5e056086	//sha256su1 v6.16b,v4.16b,v5.16b
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v7.4s
-	.inst	0x5e282887	//sha256su0 v7.16b,v4.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-	.inst	0x5e0660a7	//sha256su1 v7.16b,v5.16b,v6.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v4.4s
-	.inst	0x5e2828a4	//sha256su0 v4.16b,v5.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-	.inst	0x5e0760c4	//sha256su1 v4.16b,v6.16b,v7.16b
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v5.4s
-	.inst	0x5e2828c5	//sha256su0 v5.16b,v6.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-	.inst	0x5e0460e5	//sha256su1 v5.16b,v7.16b,v4.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v6.4s
-	.inst	0x5e2828e6	//sha256su0 v6.16b,v7.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-	.inst	0x5e056086	//sha256su1 v6.16b,v4.16b,v5.16b
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v7.4s
-	.inst	0x5e282887	//sha256su0 v7.16b,v4.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-	.inst	0x5e0660a7	//sha256su1 v7.16b,v5.16b,v6.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v4.4s
-	.inst	0x5e2828a4	//sha256su0 v4.16b,v5.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-	.inst	0x5e0760c4	//sha256su1 v4.16b,v6.16b,v7.16b
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v5.4s
-	.inst	0x5e2828c5	//sha256su0 v5.16b,v6.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-	.inst	0x5e0460e5	//sha256su1 v5.16b,v7.16b,v4.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v6.4s
-	.inst	0x5e2828e6	//sha256su0 v6.16b,v7.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-	.inst	0x5e056086	//sha256su1 v6.16b,v4.16b,v5.16b
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v7.4s
-	.inst	0x5e282887	//sha256su0 v7.16b,v4.16b
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-	.inst	0x5e0660a7	//sha256su1 v7.16b,v5.16b,v6.16b
-	ld1		{v17.4s},[x3],#16
-	add		v16.4s,v16.4s,v4.4s
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-
-	ld1		{v16.4s},[x3],#16
-	add		v17.4s,v17.4s,v5.4s
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-
-	ld1		{v17.4s},[x3]
-	add		v16.4s,v16.4s,v6.4s
-	sub		x3,x3,#64*4-16	// rewind
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
-	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
-
-	add		v17.4s,v17.4s,v7.4s
-	orr		v2.16b,v0.16b,v0.16b
-	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
-	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
-
-	add		v0.4s,v0.4s,v18.4s
-	add		v1.4s,v1.4s,v19.4s
-
-	cbnz		x2,.Loop_hw
-
-	st1		{v0.4s,v1.4s},[x0]
-
-	ldr		x29,[sp],#16
-	ret
-.size	sha256_block_armv8,.-sha256_block_armv8
-#endif
-#ifdef	__KERNEL__
-.globl	sha256_block_neon
-#endif
-.type	sha256_block_neon,%function
-.align	4
-sha256_block_neon:
-.Lneon_entry:
-	stp	x29, x30, [sp, #-16]!
-	mov	x29, sp
-	sub	sp,sp,#16*4
-
-	adr	x16,.LK256
-	add	x2,x1,x2,lsl#6	// len to point at the end of inp
-
-	ld1	{v0.16b},[x1], #16
-	ld1	{v1.16b},[x1], #16
-	ld1	{v2.16b},[x1], #16
-	ld1	{v3.16b},[x1], #16
-	ld1	{v4.4s},[x16], #16
-	ld1	{v5.4s},[x16], #16
-	ld1	{v6.4s},[x16], #16
-	ld1	{v7.4s},[x16], #16
-	rev32	v0.16b,v0.16b		// yes, even on
-	rev32	v1.16b,v1.16b		// big-endian
-	rev32	v2.16b,v2.16b
-	rev32	v3.16b,v3.16b
-	mov	x17,sp
-	add	v4.4s,v4.4s,v0.4s
-	add	v5.4s,v5.4s,v1.4s
-	add	v6.4s,v6.4s,v2.4s
-	st1	{v4.4s-v5.4s},[x17], #32
-	add	v7.4s,v7.4s,v3.4s
-	st1	{v6.4s-v7.4s},[x17]
-	sub	x17,x17,#32
-
-	ldp	w3,w4,[x0]
-	ldp	w5,w6,[x0,#8]
-	ldp	w7,w8,[x0,#16]
-	ldp	w9,w10,[x0,#24]
-	ldr	w12,[sp,#0]
-	mov	w13,wzr
-	eor	w14,w4,w5
-	mov	w15,wzr
-	b	.L_00_48
-
-.align	4
-.L_00_48:
-	ext	v4.16b,v0.16b,v1.16b,#4
-	add	w10,w10,w12
-	add	w3,w3,w15
-	and	w12,w8,w7
-	bic	w15,w9,w7
-	ext	v7.16b,v2.16b,v3.16b,#4
-	eor	w11,w7,w7,ror#5
-	add	w3,w3,w13
-	mov	d19,v3.d[1]
-	orr	w12,w12,w15
-	eor	w11,w11,w7,ror#19
-	ushr	v6.4s,v4.4s,#7
-	eor	w15,w3,w3,ror#11
-	ushr	v5.4s,v4.4s,#3
-	add	w10,w10,w12
-	add	v0.4s,v0.4s,v7.4s
-	ror	w11,w11,#6
-	sli	v6.4s,v4.4s,#25
-	eor	w13,w3,w4
-	eor	w15,w15,w3,ror#20
-	ushr	v7.4s,v4.4s,#18
-	add	w10,w10,w11
-	ldr	w12,[sp,#4]
-	and	w14,w14,w13
-	eor	v5.16b,v5.16b,v6.16b
-	ror	w15,w15,#2
-	add	w6,w6,w10
-	sli	v7.4s,v4.4s,#14
-	eor	w14,w14,w4
-	ushr	v16.4s,v19.4s,#17
-	add	w9,w9,w12
-	add	w10,w10,w15
-	and	w12,w7,w6
-	eor	v5.16b,v5.16b,v7.16b
-	bic	w15,w8,w6
-	eor	w11,w6,w6,ror#5
-	sli	v16.4s,v19.4s,#15
-	add	w10,w10,w14
-	orr	w12,w12,w15
-	ushr	v17.4s,v19.4s,#10
-	eor	w11,w11,w6,ror#19
-	eor	w15,w10,w10,ror#11
-	ushr	v7.4s,v19.4s,#19
-	add	w9,w9,w12
-	ror	w11,w11,#6
-	add	v0.4s,v0.4s,v5.4s
-	eor	w14,w10,w3
-	eor	w15,w15,w10,ror#20
-	sli	v7.4s,v19.4s,#13
-	add	w9,w9,w11
-	ldr	w12,[sp,#8]
-	and	w13,w13,w14
-	eor	v17.16b,v17.16b,v16.16b
-	ror	w15,w15,#2
-	add	w5,w5,w9
-	eor	w13,w13,w3
-	eor	v17.16b,v17.16b,v7.16b
-	add	w8,w8,w12
-	add	w9,w9,w15
-	and	w12,w6,w5
-	add	v0.4s,v0.4s,v17.4s
-	bic	w15,w7,w5
-	eor	w11,w5,w5,ror#5
-	add	w9,w9,w13
-	ushr	v18.4s,v0.4s,#17
-	orr	w12,w12,w15
-	ushr	v19.4s,v0.4s,#10
-	eor	w11,w11,w5,ror#19
-	eor	w15,w9,w9,ror#11
-	sli	v18.4s,v0.4s,#15
-	add	w8,w8,w12
-	ushr	v17.4s,v0.4s,#19
-	ror	w11,w11,#6
-	eor	w13,w9,w10
-	eor	v19.16b,v19.16b,v18.16b
-	eor	w15,w15,w9,ror#20
-	add	w8,w8,w11
-	sli	v17.4s,v0.4s,#13
-	ldr	w12,[sp,#12]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	ld1	{v4.4s},[x16], #16
-	add	w4,w4,w8
-	eor	v19.16b,v19.16b,v17.16b
-	eor	w14,w14,w10
-	eor	v17.16b,v17.16b,v17.16b
-	add	w7,w7,w12
-	add	w8,w8,w15
-	and	w12,w5,w4
-	mov	v17.d[1],v19.d[0]
-	bic	w15,w6,w4
-	eor	w11,w4,w4,ror#5
-	add	w8,w8,w14
-	add	v0.4s,v0.4s,v17.4s
-	orr	w12,w12,w15
-	eor	w11,w11,w4,ror#19
-	eor	w15,w8,w8,ror#11
-	add	v4.4s,v4.4s,v0.4s
-	add	w7,w7,w12
-	ror	w11,w11,#6
-	eor	w14,w8,w9
-	eor	w15,w15,w8,ror#20
-	add	w7,w7,w11
-	ldr	w12,[sp,#16]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w3,w3,w7
-	eor	w13,w13,w9
-	st1	{v4.4s},[x17], #16
-	ext	v4.16b,v1.16b,v2.16b,#4
-	add	w6,w6,w12
-	add	w7,w7,w15
-	and	w12,w4,w3
-	bic	w15,w5,w3
-	ext	v7.16b,v3.16b,v0.16b,#4
-	eor	w11,w3,w3,ror#5
-	add	w7,w7,w13
-	mov	d19,v0.d[1]
-	orr	w12,w12,w15
-	eor	w11,w11,w3,ror#19
-	ushr	v6.4s,v4.4s,#7
-	eor	w15,w7,w7,ror#11
-	ushr	v5.4s,v4.4s,#3
-	add	w6,w6,w12
-	add	v1.4s,v1.4s,v7.4s
-	ror	w11,w11,#6
-	sli	v6.4s,v4.4s,#25
-	eor	w13,w7,w8
-	eor	w15,w15,w7,ror#20
-	ushr	v7.4s,v4.4s,#18
-	add	w6,w6,w11
-	ldr	w12,[sp,#20]
-	and	w14,w14,w13
-	eor	v5.16b,v5.16b,v6.16b
-	ror	w15,w15,#2
-	add	w10,w10,w6
-	sli	v7.4s,v4.4s,#14
-	eor	w14,w14,w8
-	ushr	v16.4s,v19.4s,#17
-	add	w5,w5,w12
-	add	w6,w6,w15
-	and	w12,w3,w10
-	eor	v5.16b,v5.16b,v7.16b
-	bic	w15,w4,w10
-	eor	w11,w10,w10,ror#5
-	sli	v16.4s,v19.4s,#15
-	add	w6,w6,w14
-	orr	w12,w12,w15
-	ushr	v17.4s,v19.4s,#10
-	eor	w11,w11,w10,ror#19
-	eor	w15,w6,w6,ror#11
-	ushr	v7.4s,v19.4s,#19
-	add	w5,w5,w12
-	ror	w11,w11,#6
-	add	v1.4s,v1.4s,v5.4s
-	eor	w14,w6,w7
-	eor	w15,w15,w6,ror#20
-	sli	v7.4s,v19.4s,#13
-	add	w5,w5,w11
-	ldr	w12,[sp,#24]
-	and	w13,w13,w14
-	eor	v17.16b,v17.16b,v16.16b
-	ror	w15,w15,#2
-	add	w9,w9,w5
-	eor	w13,w13,w7
-	eor	v17.16b,v17.16b,v7.16b
-	add	w4,w4,w12
-	add	w5,w5,w15
-	and	w12,w10,w9
-	add	v1.4s,v1.4s,v17.4s
-	bic	w15,w3,w9
-	eor	w11,w9,w9,ror#5
-	add	w5,w5,w13
-	ushr	v18.4s,v1.4s,#17
-	orr	w12,w12,w15
-	ushr	v19.4s,v1.4s,#10
-	eor	w11,w11,w9,ror#19
-	eor	w15,w5,w5,ror#11
-	sli	v18.4s,v1.4s,#15
-	add	w4,w4,w12
-	ushr	v17.4s,v1.4s,#19
-	ror	w11,w11,#6
-	eor	w13,w5,w6
-	eor	v19.16b,v19.16b,v18.16b
-	eor	w15,w15,w5,ror#20
-	add	w4,w4,w11
-	sli	v17.4s,v1.4s,#13
-	ldr	w12,[sp,#28]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	ld1	{v4.4s},[x16], #16
-	add	w8,w8,w4
-	eor	v19.16b,v19.16b,v17.16b
-	eor	w14,w14,w6
-	eor	v17.16b,v17.16b,v17.16b
-	add	w3,w3,w12
-	add	w4,w4,w15
-	and	w12,w9,w8
-	mov	v17.d[1],v19.d[0]
-	bic	w15,w10,w8
-	eor	w11,w8,w8,ror#5
-	add	w4,w4,w14
-	add	v1.4s,v1.4s,v17.4s
-	orr	w12,w12,w15
-	eor	w11,w11,w8,ror#19
-	eor	w15,w4,w4,ror#11
-	add	v4.4s,v4.4s,v1.4s
-	add	w3,w3,w12
-	ror	w11,w11,#6
-	eor	w14,w4,w5
-	eor	w15,w15,w4,ror#20
-	add	w3,w3,w11
-	ldr	w12,[sp,#32]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w7,w7,w3
-	eor	w13,w13,w5
-	st1	{v4.4s},[x17], #16
-	ext	v4.16b,v2.16b,v3.16b,#4
-	add	w10,w10,w12
-	add	w3,w3,w15
-	and	w12,w8,w7
-	bic	w15,w9,w7
-	ext	v7.16b,v0.16b,v1.16b,#4
-	eor	w11,w7,w7,ror#5
-	add	w3,w3,w13
-	mov	d19,v1.d[1]
-	orr	w12,w12,w15
-	eor	w11,w11,w7,ror#19
-	ushr	v6.4s,v4.4s,#7
-	eor	w15,w3,w3,ror#11
-	ushr	v5.4s,v4.4s,#3
-	add	w10,w10,w12
-	add	v2.4s,v2.4s,v7.4s
-	ror	w11,w11,#6
-	sli	v6.4s,v4.4s,#25
-	eor	w13,w3,w4
-	eor	w15,w15,w3,ror#20
-	ushr	v7.4s,v4.4s,#18
-	add	w10,w10,w11
-	ldr	w12,[sp,#36]
-	and	w14,w14,w13
-	eor	v5.16b,v5.16b,v6.16b
-	ror	w15,w15,#2
-	add	w6,w6,w10
-	sli	v7.4s,v4.4s,#14
-	eor	w14,w14,w4
-	ushr	v16.4s,v19.4s,#17
-	add	w9,w9,w12
-	add	w10,w10,w15
-	and	w12,w7,w6
-	eor	v5.16b,v5.16b,v7.16b
-	bic	w15,w8,w6
-	eor	w11,w6,w6,ror#5
-	sli	v16.4s,v19.4s,#15
-	add	w10,w10,w14
-	orr	w12,w12,w15
-	ushr	v17.4s,v19.4s,#10
-	eor	w11,w11,w6,ror#19
-	eor	w15,w10,w10,ror#11
-	ushr	v7.4s,v19.4s,#19
-	add	w9,w9,w12
-	ror	w11,w11,#6
-	add	v2.4s,v2.4s,v5.4s
-	eor	w14,w10,w3
-	eor	w15,w15,w10,ror#20
-	sli	v7.4s,v19.4s,#13
-	add	w9,w9,w11
-	ldr	w12,[sp,#40]
-	and	w13,w13,w14
-	eor	v17.16b,v17.16b,v16.16b
-	ror	w15,w15,#2
-	add	w5,w5,w9
-	eor	w13,w13,w3
-	eor	v17.16b,v17.16b,v7.16b
-	add	w8,w8,w12
-	add	w9,w9,w15
-	and	w12,w6,w5
-	add	v2.4s,v2.4s,v17.4s
-	bic	w15,w7,w5
-	eor	w11,w5,w5,ror#5
-	add	w9,w9,w13
-	ushr	v18.4s,v2.4s,#17
-	orr	w12,w12,w15
-	ushr	v19.4s,v2.4s,#10
-	eor	w11,w11,w5,ror#19
-	eor	w15,w9,w9,ror#11
-	sli	v18.4s,v2.4s,#15
-	add	w8,w8,w12
-	ushr	v17.4s,v2.4s,#19
-	ror	w11,w11,#6
-	eor	w13,w9,w10
-	eor	v19.16b,v19.16b,v18.16b
-	eor	w15,w15,w9,ror#20
-	add	w8,w8,w11
-	sli	v17.4s,v2.4s,#13
-	ldr	w12,[sp,#44]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	ld1	{v4.4s},[x16], #16
-	add	w4,w4,w8
-	eor	v19.16b,v19.16b,v17.16b
-	eor	w14,w14,w10
-	eor	v17.16b,v17.16b,v17.16b
-	add	w7,w7,w12
-	add	w8,w8,w15
-	and	w12,w5,w4
-	mov	v17.d[1],v19.d[0]
-	bic	w15,w6,w4
-	eor	w11,w4,w4,ror#5
-	add	w8,w8,w14
-	add	v2.4s,v2.4s,v17.4s
-	orr	w12,w12,w15
-	eor	w11,w11,w4,ror#19
-	eor	w15,w8,w8,ror#11
-	add	v4.4s,v4.4s,v2.4s
-	add	w7,w7,w12
-	ror	w11,w11,#6
-	eor	w14,w8,w9
-	eor	w15,w15,w8,ror#20
-	add	w7,w7,w11
-	ldr	w12,[sp,#48]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w3,w3,w7
-	eor	w13,w13,w9
-	st1	{v4.4s},[x17], #16
-	ext	v4.16b,v3.16b,v0.16b,#4
-	add	w6,w6,w12
-	add	w7,w7,w15
-	and	w12,w4,w3
-	bic	w15,w5,w3
-	ext	v7.16b,v1.16b,v2.16b,#4
-	eor	w11,w3,w3,ror#5
-	add	w7,w7,w13
-	mov	d19,v2.d[1]
-	orr	w12,w12,w15
-	eor	w11,w11,w3,ror#19
-	ushr	v6.4s,v4.4s,#7
-	eor	w15,w7,w7,ror#11
-	ushr	v5.4s,v4.4s,#3
-	add	w6,w6,w12
-	add	v3.4s,v3.4s,v7.4s
-	ror	w11,w11,#6
-	sli	v6.4s,v4.4s,#25
-	eor	w13,w7,w8
-	eor	w15,w15,w7,ror#20
-	ushr	v7.4s,v4.4s,#18
-	add	w6,w6,w11
-	ldr	w12,[sp,#52]
-	and	w14,w14,w13
-	eor	v5.16b,v5.16b,v6.16b
-	ror	w15,w15,#2
-	add	w10,w10,w6
-	sli	v7.4s,v4.4s,#14
-	eor	w14,w14,w8
-	ushr	v16.4s,v19.4s,#17
-	add	w5,w5,w12
-	add	w6,w6,w15
-	and	w12,w3,w10
-	eor	v5.16b,v5.16b,v7.16b
-	bic	w15,w4,w10
-	eor	w11,w10,w10,ror#5
-	sli	v16.4s,v19.4s,#15
-	add	w6,w6,w14
-	orr	w12,w12,w15
-	ushr	v17.4s,v19.4s,#10
-	eor	w11,w11,w10,ror#19
-	eor	w15,w6,w6,ror#11
-	ushr	v7.4s,v19.4s,#19
-	add	w5,w5,w12
-	ror	w11,w11,#6
-	add	v3.4s,v3.4s,v5.4s
-	eor	w14,w6,w7
-	eor	w15,w15,w6,ror#20
-	sli	v7.4s,v19.4s,#13
-	add	w5,w5,w11
-	ldr	w12,[sp,#56]
-	and	w13,w13,w14
-	eor	v17.16b,v17.16b,v16.16b
-	ror	w15,w15,#2
-	add	w9,w9,w5
-	eor	w13,w13,w7
-	eor	v17.16b,v17.16b,v7.16b
-	add	w4,w4,w12
-	add	w5,w5,w15
-	and	w12,w10,w9
-	add	v3.4s,v3.4s,v17.4s
-	bic	w15,w3,w9
-	eor	w11,w9,w9,ror#5
-	add	w5,w5,w13
-	ushr	v18.4s,v3.4s,#17
-	orr	w12,w12,w15
-	ushr	v19.4s,v3.4s,#10
-	eor	w11,w11,w9,ror#19
-	eor	w15,w5,w5,ror#11
-	sli	v18.4s,v3.4s,#15
-	add	w4,w4,w12
-	ushr	v17.4s,v3.4s,#19
-	ror	w11,w11,#6
-	eor	w13,w5,w6
-	eor	v19.16b,v19.16b,v18.16b
-	eor	w15,w15,w5,ror#20
-	add	w4,w4,w11
-	sli	v17.4s,v3.4s,#13
-	ldr	w12,[sp,#60]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	ld1	{v4.4s},[x16], #16
-	add	w8,w8,w4
-	eor	v19.16b,v19.16b,v17.16b
-	eor	w14,w14,w6
-	eor	v17.16b,v17.16b,v17.16b
-	add	w3,w3,w12
-	add	w4,w4,w15
-	and	w12,w9,w8
-	mov	v17.d[1],v19.d[0]
-	bic	w15,w10,w8
-	eor	w11,w8,w8,ror#5
-	add	w4,w4,w14
-	add	v3.4s,v3.4s,v17.4s
-	orr	w12,w12,w15
-	eor	w11,w11,w8,ror#19
-	eor	w15,w4,w4,ror#11
-	add	v4.4s,v4.4s,v3.4s
-	add	w3,w3,w12
-	ror	w11,w11,#6
-	eor	w14,w4,w5
-	eor	w15,w15,w4,ror#20
-	add	w3,w3,w11
-	ldr	w12,[x16]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w7,w7,w3
-	eor	w13,w13,w5
-	st1	{v4.4s},[x17], #16
-	cmp	w12,#0				// check for K256 terminator
-	ldr	w12,[sp,#0]
-	sub	x17,x17,#64
-	bne	.L_00_48
-
-	sub	x16,x16,#256		// rewind x16
-	cmp	x1,x2
-	mov	x17, #64
-	csel	x17, x17, xzr, eq
-	sub	x1,x1,x17			// avoid SEGV
-	mov	x17,sp
-	add	w10,w10,w12
-	add	w3,w3,w15
-	and	w12,w8,w7
-	ld1	{v0.16b},[x1],#16
-	bic	w15,w9,w7
-	eor	w11,w7,w7,ror#5
-	ld1	{v4.4s},[x16],#16
-	add	w3,w3,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w7,ror#19
-	eor	w15,w3,w3,ror#11
-	rev32	v0.16b,v0.16b
-	add	w10,w10,w12
-	ror	w11,w11,#6
-	eor	w13,w3,w4
-	eor	w15,w15,w3,ror#20
-	add	v4.4s,v4.4s,v0.4s
-	add	w10,w10,w11
-	ldr	w12,[sp,#4]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w6,w6,w10
-	eor	w14,w14,w4
-	add	w9,w9,w12
-	add	w10,w10,w15
-	and	w12,w7,w6
-	bic	w15,w8,w6
-	eor	w11,w6,w6,ror#5
-	add	w10,w10,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w6,ror#19
-	eor	w15,w10,w10,ror#11
-	add	w9,w9,w12
-	ror	w11,w11,#6
-	eor	w14,w10,w3
-	eor	w15,w15,w10,ror#20
-	add	w9,w9,w11
-	ldr	w12,[sp,#8]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w5,w5,w9
-	eor	w13,w13,w3
-	add	w8,w8,w12
-	add	w9,w9,w15
-	and	w12,w6,w5
-	bic	w15,w7,w5
-	eor	w11,w5,w5,ror#5
-	add	w9,w9,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w5,ror#19
-	eor	w15,w9,w9,ror#11
-	add	w8,w8,w12
-	ror	w11,w11,#6
-	eor	w13,w9,w10
-	eor	w15,w15,w9,ror#20
-	add	w8,w8,w11
-	ldr	w12,[sp,#12]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w4,w4,w8
-	eor	w14,w14,w10
-	add	w7,w7,w12
-	add	w8,w8,w15
-	and	w12,w5,w4
-	bic	w15,w6,w4
-	eor	w11,w4,w4,ror#5
-	add	w8,w8,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w4,ror#19
-	eor	w15,w8,w8,ror#11
-	add	w7,w7,w12
-	ror	w11,w11,#6
-	eor	w14,w8,w9
-	eor	w15,w15,w8,ror#20
-	add	w7,w7,w11
-	ldr	w12,[sp,#16]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w3,w3,w7
-	eor	w13,w13,w9
-	st1	{v4.4s},[x17], #16
-	add	w6,w6,w12
-	add	w7,w7,w15
-	and	w12,w4,w3
-	ld1	{v1.16b},[x1],#16
-	bic	w15,w5,w3
-	eor	w11,w3,w3,ror#5
-	ld1	{v4.4s},[x16],#16
-	add	w7,w7,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w3,ror#19
-	eor	w15,w7,w7,ror#11
-	rev32	v1.16b,v1.16b
-	add	w6,w6,w12
-	ror	w11,w11,#6
-	eor	w13,w7,w8
-	eor	w15,w15,w7,ror#20
-	add	v4.4s,v4.4s,v1.4s
-	add	w6,w6,w11
-	ldr	w12,[sp,#20]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w10,w10,w6
-	eor	w14,w14,w8
-	add	w5,w5,w12
-	add	w6,w6,w15
-	and	w12,w3,w10
-	bic	w15,w4,w10
-	eor	w11,w10,w10,ror#5
-	add	w6,w6,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w10,ror#19
-	eor	w15,w6,w6,ror#11
-	add	w5,w5,w12
-	ror	w11,w11,#6
-	eor	w14,w6,w7
-	eor	w15,w15,w6,ror#20
-	add	w5,w5,w11
-	ldr	w12,[sp,#24]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w9,w9,w5
-	eor	w13,w13,w7
-	add	w4,w4,w12
-	add	w5,w5,w15
-	and	w12,w10,w9
-	bic	w15,w3,w9
-	eor	w11,w9,w9,ror#5
-	add	w5,w5,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w9,ror#19
-	eor	w15,w5,w5,ror#11
-	add	w4,w4,w12
-	ror	w11,w11,#6
-	eor	w13,w5,w6
-	eor	w15,w15,w5,ror#20
-	add	w4,w4,w11
-	ldr	w12,[sp,#28]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w8,w8,w4
-	eor	w14,w14,w6
-	add	w3,w3,w12
-	add	w4,w4,w15
-	and	w12,w9,w8
-	bic	w15,w10,w8
-	eor	w11,w8,w8,ror#5
-	add	w4,w4,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w8,ror#19
-	eor	w15,w4,w4,ror#11
-	add	w3,w3,w12
-	ror	w11,w11,#6
-	eor	w14,w4,w5
-	eor	w15,w15,w4,ror#20
-	add	w3,w3,w11
-	ldr	w12,[sp,#32]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w7,w7,w3
-	eor	w13,w13,w5
-	st1	{v4.4s},[x17], #16
-	add	w10,w10,w12
-	add	w3,w3,w15
-	and	w12,w8,w7
-	ld1	{v2.16b},[x1],#16
-	bic	w15,w9,w7
-	eor	w11,w7,w7,ror#5
-	ld1	{v4.4s},[x16],#16
-	add	w3,w3,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w7,ror#19
-	eor	w15,w3,w3,ror#11
-	rev32	v2.16b,v2.16b
-	add	w10,w10,w12
-	ror	w11,w11,#6
-	eor	w13,w3,w4
-	eor	w15,w15,w3,ror#20
-	add	v4.4s,v4.4s,v2.4s
-	add	w10,w10,w11
-	ldr	w12,[sp,#36]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w6,w6,w10
-	eor	w14,w14,w4
-	add	w9,w9,w12
-	add	w10,w10,w15
-	and	w12,w7,w6
-	bic	w15,w8,w6
-	eor	w11,w6,w6,ror#5
-	add	w10,w10,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w6,ror#19
-	eor	w15,w10,w10,ror#11
-	add	w9,w9,w12
-	ror	w11,w11,#6
-	eor	w14,w10,w3
-	eor	w15,w15,w10,ror#20
-	add	w9,w9,w11
-	ldr	w12,[sp,#40]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w5,w5,w9
-	eor	w13,w13,w3
-	add	w8,w8,w12
-	add	w9,w9,w15
-	and	w12,w6,w5
-	bic	w15,w7,w5
-	eor	w11,w5,w5,ror#5
-	add	w9,w9,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w5,ror#19
-	eor	w15,w9,w9,ror#11
-	add	w8,w8,w12
-	ror	w11,w11,#6
-	eor	w13,w9,w10
-	eor	w15,w15,w9,ror#20
-	add	w8,w8,w11
-	ldr	w12,[sp,#44]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w4,w4,w8
-	eor	w14,w14,w10
-	add	w7,w7,w12
-	add	w8,w8,w15
-	and	w12,w5,w4
-	bic	w15,w6,w4
-	eor	w11,w4,w4,ror#5
-	add	w8,w8,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w4,ror#19
-	eor	w15,w8,w8,ror#11
-	add	w7,w7,w12
-	ror	w11,w11,#6
-	eor	w14,w8,w9
-	eor	w15,w15,w8,ror#20
-	add	w7,w7,w11
-	ldr	w12,[sp,#48]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w3,w3,w7
-	eor	w13,w13,w9
-	st1	{v4.4s},[x17], #16
-	add	w6,w6,w12
-	add	w7,w7,w15
-	and	w12,w4,w3
-	ld1	{v3.16b},[x1],#16
-	bic	w15,w5,w3
-	eor	w11,w3,w3,ror#5
-	ld1	{v4.4s},[x16],#16
-	add	w7,w7,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w3,ror#19
-	eor	w15,w7,w7,ror#11
-	rev32	v3.16b,v3.16b
-	add	w6,w6,w12
-	ror	w11,w11,#6
-	eor	w13,w7,w8
-	eor	w15,w15,w7,ror#20
-	add	v4.4s,v4.4s,v3.4s
-	add	w6,w6,w11
-	ldr	w12,[sp,#52]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w10,w10,w6
-	eor	w14,w14,w8
-	add	w5,w5,w12
-	add	w6,w6,w15
-	and	w12,w3,w10
-	bic	w15,w4,w10
-	eor	w11,w10,w10,ror#5
-	add	w6,w6,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w10,ror#19
-	eor	w15,w6,w6,ror#11
-	add	w5,w5,w12
-	ror	w11,w11,#6
-	eor	w14,w6,w7
-	eor	w15,w15,w6,ror#20
-	add	w5,w5,w11
-	ldr	w12,[sp,#56]
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w9,w9,w5
-	eor	w13,w13,w7
-	add	w4,w4,w12
-	add	w5,w5,w15
-	and	w12,w10,w9
-	bic	w15,w3,w9
-	eor	w11,w9,w9,ror#5
-	add	w5,w5,w13
-	orr	w12,w12,w15
-	eor	w11,w11,w9,ror#19
-	eor	w15,w5,w5,ror#11
-	add	w4,w4,w12
-	ror	w11,w11,#6
-	eor	w13,w5,w6
-	eor	w15,w15,w5,ror#20
-	add	w4,w4,w11
-	ldr	w12,[sp,#60]
-	and	w14,w14,w13
-	ror	w15,w15,#2
-	add	w8,w8,w4
-	eor	w14,w14,w6
-	add	w3,w3,w12
-	add	w4,w4,w15
-	and	w12,w9,w8
-	bic	w15,w10,w8
-	eor	w11,w8,w8,ror#5
-	add	w4,w4,w14
-	orr	w12,w12,w15
-	eor	w11,w11,w8,ror#19
-	eor	w15,w4,w4,ror#11
-	add	w3,w3,w12
-	ror	w11,w11,#6
-	eor	w14,w4,w5
-	eor	w15,w15,w4,ror#20
-	add	w3,w3,w11
-	and	w13,w13,w14
-	ror	w15,w15,#2
-	add	w7,w7,w3
-	eor	w13,w13,w5
-	st1	{v4.4s},[x17], #16
-	add	w3,w3,w15			// h+=Sigma0(a) from the past
-	ldp	w11,w12,[x0,#0]
-	add	w3,w3,w13			// h+=Maj(a,b,c) from the past
-	ldp	w13,w14,[x0,#8]
-	add	w3,w3,w11			// accumulate
-	add	w4,w4,w12
-	ldp	w11,w12,[x0,#16]
-	add	w5,w5,w13
-	add	w6,w6,w14
-	ldp	w13,w14,[x0,#24]
-	add	w7,w7,w11
-	add	w8,w8,w12
-	 ldr	w12,[sp,#0]
-	stp	w3,w4,[x0,#0]
-	add	w9,w9,w13
-	 mov	w13,wzr
-	stp	w5,w6,[x0,#8]
-	add	w10,w10,w14
-	stp	w7,w8,[x0,#16]
-	 eor	w14,w4,w5
-	stp	w9,w10,[x0,#24]
-	 mov	w15,wzr
-	 mov	x17,sp
-	b.ne	.L_00_48
-
-	ldr	x29,[x29]
-	add	sp,sp,#16*4+16
-	ret
-.size	sha256_block_neon,.-sha256_block_neon
-#ifndef	__KERNEL__
-.comm	OPENSSL_armcap_P,4,4
-#endif
diff --git a/arch/arm64/crypto/sha512-core.S b/arch/arm64/crypto/sha512-core.S
deleted file mode 100644
index bd0f59f06c9d..000000000000
--- a/arch/arm64/crypto/sha512-core.S
+++ /dev/null
@@ -1,1085 +0,0 @@
-// 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
-// project. The module is, however, dual licensed under OpenSSL and
-// CRYPTOGAMS licenses depending on where you obtain it. For further
-// details see http://www.openssl.org/~appro/cryptogams/.
-//
-// Permission to use under GPLv2 terms is granted.
-// ====================================================================
-//
-// SHA256/512 for ARMv8.
-//
-// Performance in cycles per processed byte and improvement coefficient
-// over code generated with "default" compiler:
-//
-//		SHA256-hw	SHA256(*)	SHA512
-// Apple A7	1.97		10.5 (+33%)	6.73 (-1%(**))
-// Cortex-A53	2.38		15.5 (+115%)	10.0 (+150%(***))
-// Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
-// Denver	2.01		10.5 (+26%)	6.70 (+8%)
-// X-Gene			20.0 (+100%)	12.8 (+300%(***))
-// Mongoose	2.36		13.0 (+50%)	8.36 (+33%)
-//
-// (*)	Software SHA256 results are of lesser relevance, presented
-//	mostly for informational purposes.
-// (**)	The result is a trade-off: it's possible to improve it by
-//	10% (or by 1 cycle per round), but at the cost of 20% loss
-//	on Cortex-A53 (or by 4 cycles per round).
-// (***)	Super-impressive coefficients over gcc-generated code are
-//	indication of some compiler "pathology", most notably code
-//	generated with -mgeneral-regs-only is significanty faster
-//	and the gap is only 40-90%.
-//
-// October 2016.
-//
-// Originally it was reckoned that it makes no sense to implement NEON
-// version of SHA256 for 64-bit processors. This is because performance
-// improvement on most wide-spread Cortex-A5x processors was observed
-// to be marginal, same on Cortex-A53 and ~10% on A57. But then it was
-// observed that 32-bit NEON SHA256 performs significantly better than
-// 64-bit scalar version on *some* of the more recent processors. As
-// result 64-bit NEON version of SHA256 was added to provide best
-// all-round performance. For example it executes ~30% faster on X-Gene
-// and Mongoose. [For reference, NEON version of SHA512 is bound to
-// deliver much less improvement, likely *negative* on Cortex-A5x.
-// Which is why NEON support is limited to SHA256.]
-
-#ifndef	__KERNEL__
-# include "arm_arch.h"
-#endif
-
-.text
-
-.extern	OPENSSL_armcap_P
-.globl	sha512_block_data_order
-.type	sha512_block_data_order,%function
-.align	6
-sha512_block_data_order:
-	stp	x29,x30,[sp,#-128]!
-	add	x29,sp,#0
-
-	stp	x19,x20,[sp,#16]
-	stp	x21,x22,[sp,#32]
-	stp	x23,x24,[sp,#48]
-	stp	x25,x26,[sp,#64]
-	stp	x27,x28,[sp,#80]
-	sub	sp,sp,#4*8
-
-	ldp	x20,x21,[x0]				// load context
-	ldp	x22,x23,[x0,#2*8]
-	ldp	x24,x25,[x0,#4*8]
-	add	x2,x1,x2,lsl#7	// end of input
-	ldp	x26,x27,[x0,#6*8]
-	adr	x30,.LK512
-	stp	x0,x2,[x29,#96]
-
-.Loop:
-	ldp	x3,x4,[x1],#2*8
-	ldr	x19,[x30],#8			// *K++
-	eor	x28,x21,x22				// magic seed
-	str	x1,[x29,#112]
-#ifndef	__AARCH64EB__
-	rev	x3,x3			// 0
-#endif
-	ror	x16,x24,#14
-	add	x27,x27,x19			// h+=K[i]
-	eor	x6,x24,x24,ror#23
-	and	x17,x25,x24
-	bic	x19,x26,x24
-	add	x27,x27,x3			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x20,x21			// a^b, b^c in next round
-	eor	x16,x16,x6,ror#18	// Sigma1(e)
-	ror	x6,x20,#28
-	add	x27,x27,x17			// h+=Ch(e,f,g)
-	eor	x17,x20,x20,ror#5
-	add	x27,x27,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x23,x23,x27			// d+=h
-	eor	x28,x28,x21			// Maj(a,b,c)
-	eor	x17,x6,x17,ror#34	// Sigma0(a)
-	add	x27,x27,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x27,x27,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x4,x4			// 1
-#endif
-	ldp	x5,x6,[x1],#2*8
-	add	x27,x27,x17			// h+=Sigma0(a)
-	ror	x16,x23,#14
-	add	x26,x26,x28			// h+=K[i]
-	eor	x7,x23,x23,ror#23
-	and	x17,x24,x23
-	bic	x28,x25,x23
-	add	x26,x26,x4			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x27,x20			// a^b, b^c in next round
-	eor	x16,x16,x7,ror#18	// Sigma1(e)
-	ror	x7,x27,#28
-	add	x26,x26,x17			// h+=Ch(e,f,g)
-	eor	x17,x27,x27,ror#5
-	add	x26,x26,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x22,x22,x26			// d+=h
-	eor	x19,x19,x20			// Maj(a,b,c)
-	eor	x17,x7,x17,ror#34	// Sigma0(a)
-	add	x26,x26,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x26,x26,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x5,x5			// 2
-#endif
-	add	x26,x26,x17			// h+=Sigma0(a)
-	ror	x16,x22,#14
-	add	x25,x25,x19			// h+=K[i]
-	eor	x8,x22,x22,ror#23
-	and	x17,x23,x22
-	bic	x19,x24,x22
-	add	x25,x25,x5			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x26,x27			// a^b, b^c in next round
-	eor	x16,x16,x8,ror#18	// Sigma1(e)
-	ror	x8,x26,#28
-	add	x25,x25,x17			// h+=Ch(e,f,g)
-	eor	x17,x26,x26,ror#5
-	add	x25,x25,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x21,x21,x25			// d+=h
-	eor	x28,x28,x27			// Maj(a,b,c)
-	eor	x17,x8,x17,ror#34	// Sigma0(a)
-	add	x25,x25,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x25,x25,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x6,x6			// 3
-#endif
-	ldp	x7,x8,[x1],#2*8
-	add	x25,x25,x17			// h+=Sigma0(a)
-	ror	x16,x21,#14
-	add	x24,x24,x28			// h+=K[i]
-	eor	x9,x21,x21,ror#23
-	and	x17,x22,x21
-	bic	x28,x23,x21
-	add	x24,x24,x6			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x25,x26			// a^b, b^c in next round
-	eor	x16,x16,x9,ror#18	// Sigma1(e)
-	ror	x9,x25,#28
-	add	x24,x24,x17			// h+=Ch(e,f,g)
-	eor	x17,x25,x25,ror#5
-	add	x24,x24,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x20,x20,x24			// d+=h
-	eor	x19,x19,x26			// Maj(a,b,c)
-	eor	x17,x9,x17,ror#34	// Sigma0(a)
-	add	x24,x24,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x24,x24,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x7,x7			// 4
-#endif
-	add	x24,x24,x17			// h+=Sigma0(a)
-	ror	x16,x20,#14
-	add	x23,x23,x19			// h+=K[i]
-	eor	x10,x20,x20,ror#23
-	and	x17,x21,x20
-	bic	x19,x22,x20
-	add	x23,x23,x7			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x24,x25			// a^b, b^c in next round
-	eor	x16,x16,x10,ror#18	// Sigma1(e)
-	ror	x10,x24,#28
-	add	x23,x23,x17			// h+=Ch(e,f,g)
-	eor	x17,x24,x24,ror#5
-	add	x23,x23,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x27,x27,x23			// d+=h
-	eor	x28,x28,x25			// Maj(a,b,c)
-	eor	x17,x10,x17,ror#34	// Sigma0(a)
-	add	x23,x23,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x23,x23,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x8,x8			// 5
-#endif
-	ldp	x9,x10,[x1],#2*8
-	add	x23,x23,x17			// h+=Sigma0(a)
-	ror	x16,x27,#14
-	add	x22,x22,x28			// h+=K[i]
-	eor	x11,x27,x27,ror#23
-	and	x17,x20,x27
-	bic	x28,x21,x27
-	add	x22,x22,x8			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x23,x24			// a^b, b^c in next round
-	eor	x16,x16,x11,ror#18	// Sigma1(e)
-	ror	x11,x23,#28
-	add	x22,x22,x17			// h+=Ch(e,f,g)
-	eor	x17,x23,x23,ror#5
-	add	x22,x22,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x26,x26,x22			// d+=h
-	eor	x19,x19,x24			// Maj(a,b,c)
-	eor	x17,x11,x17,ror#34	// Sigma0(a)
-	add	x22,x22,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x22,x22,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x9,x9			// 6
-#endif
-	add	x22,x22,x17			// h+=Sigma0(a)
-	ror	x16,x26,#14
-	add	x21,x21,x19			// h+=K[i]
-	eor	x12,x26,x26,ror#23
-	and	x17,x27,x26
-	bic	x19,x20,x26
-	add	x21,x21,x9			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x22,x23			// a^b, b^c in next round
-	eor	x16,x16,x12,ror#18	// Sigma1(e)
-	ror	x12,x22,#28
-	add	x21,x21,x17			// h+=Ch(e,f,g)
-	eor	x17,x22,x22,ror#5
-	add	x21,x21,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x25,x25,x21			// d+=h
-	eor	x28,x28,x23			// Maj(a,b,c)
-	eor	x17,x12,x17,ror#34	// Sigma0(a)
-	add	x21,x21,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x21,x21,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x10,x10			// 7
-#endif
-	ldp	x11,x12,[x1],#2*8
-	add	x21,x21,x17			// h+=Sigma0(a)
-	ror	x16,x25,#14
-	add	x20,x20,x28			// h+=K[i]
-	eor	x13,x25,x25,ror#23
-	and	x17,x26,x25
-	bic	x28,x27,x25
-	add	x20,x20,x10			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x21,x22			// a^b, b^c in next round
-	eor	x16,x16,x13,ror#18	// Sigma1(e)
-	ror	x13,x21,#28
-	add	x20,x20,x17			// h+=Ch(e,f,g)
-	eor	x17,x21,x21,ror#5
-	add	x20,x20,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x24,x24,x20			// d+=h
-	eor	x19,x19,x22			// Maj(a,b,c)
-	eor	x17,x13,x17,ror#34	// Sigma0(a)
-	add	x20,x20,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x20,x20,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x11,x11			// 8
-#endif
-	add	x20,x20,x17			// h+=Sigma0(a)
-	ror	x16,x24,#14
-	add	x27,x27,x19			// h+=K[i]
-	eor	x14,x24,x24,ror#23
-	and	x17,x25,x24
-	bic	x19,x26,x24
-	add	x27,x27,x11			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x20,x21			// a^b, b^c in next round
-	eor	x16,x16,x14,ror#18	// Sigma1(e)
-	ror	x14,x20,#28
-	add	x27,x27,x17			// h+=Ch(e,f,g)
-	eor	x17,x20,x20,ror#5
-	add	x27,x27,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x23,x23,x27			// d+=h
-	eor	x28,x28,x21			// Maj(a,b,c)
-	eor	x17,x14,x17,ror#34	// Sigma0(a)
-	add	x27,x27,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x27,x27,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x12,x12			// 9
-#endif
-	ldp	x13,x14,[x1],#2*8
-	add	x27,x27,x17			// h+=Sigma0(a)
-	ror	x16,x23,#14
-	add	x26,x26,x28			// h+=K[i]
-	eor	x15,x23,x23,ror#23
-	and	x17,x24,x23
-	bic	x28,x25,x23
-	add	x26,x26,x12			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x27,x20			// a^b, b^c in next round
-	eor	x16,x16,x15,ror#18	// Sigma1(e)
-	ror	x15,x27,#28
-	add	x26,x26,x17			// h+=Ch(e,f,g)
-	eor	x17,x27,x27,ror#5
-	add	x26,x26,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x22,x22,x26			// d+=h
-	eor	x19,x19,x20			// Maj(a,b,c)
-	eor	x17,x15,x17,ror#34	// Sigma0(a)
-	add	x26,x26,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x26,x26,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x13,x13			// 10
-#endif
-	add	x26,x26,x17			// h+=Sigma0(a)
-	ror	x16,x22,#14
-	add	x25,x25,x19			// h+=K[i]
-	eor	x0,x22,x22,ror#23
-	and	x17,x23,x22
-	bic	x19,x24,x22
-	add	x25,x25,x13			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x26,x27			// a^b, b^c in next round
-	eor	x16,x16,x0,ror#18	// Sigma1(e)
-	ror	x0,x26,#28
-	add	x25,x25,x17			// h+=Ch(e,f,g)
-	eor	x17,x26,x26,ror#5
-	add	x25,x25,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x21,x21,x25			// d+=h
-	eor	x28,x28,x27			// Maj(a,b,c)
-	eor	x17,x0,x17,ror#34	// Sigma0(a)
-	add	x25,x25,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x25,x25,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x14,x14			// 11
-#endif
-	ldp	x15,x0,[x1],#2*8
-	add	x25,x25,x17			// h+=Sigma0(a)
-	str	x6,[sp,#24]
-	ror	x16,x21,#14
-	add	x24,x24,x28			// h+=K[i]
-	eor	x6,x21,x21,ror#23
-	and	x17,x22,x21
-	bic	x28,x23,x21
-	add	x24,x24,x14			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x25,x26			// a^b, b^c in next round
-	eor	x16,x16,x6,ror#18	// Sigma1(e)
-	ror	x6,x25,#28
-	add	x24,x24,x17			// h+=Ch(e,f,g)
-	eor	x17,x25,x25,ror#5
-	add	x24,x24,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x20,x20,x24			// d+=h
-	eor	x19,x19,x26			// Maj(a,b,c)
-	eor	x17,x6,x17,ror#34	// Sigma0(a)
-	add	x24,x24,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x24,x24,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x15,x15			// 12
-#endif
-	add	x24,x24,x17			// h+=Sigma0(a)
-	str	x7,[sp,#0]
-	ror	x16,x20,#14
-	add	x23,x23,x19			// h+=K[i]
-	eor	x7,x20,x20,ror#23
-	and	x17,x21,x20
-	bic	x19,x22,x20
-	add	x23,x23,x15			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x24,x25			// a^b, b^c in next round
-	eor	x16,x16,x7,ror#18	// Sigma1(e)
-	ror	x7,x24,#28
-	add	x23,x23,x17			// h+=Ch(e,f,g)
-	eor	x17,x24,x24,ror#5
-	add	x23,x23,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x27,x27,x23			// d+=h
-	eor	x28,x28,x25			// Maj(a,b,c)
-	eor	x17,x7,x17,ror#34	// Sigma0(a)
-	add	x23,x23,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x23,x23,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x0,x0			// 13
-#endif
-	ldp	x1,x2,[x1]
-	add	x23,x23,x17			// h+=Sigma0(a)
-	str	x8,[sp,#8]
-	ror	x16,x27,#14
-	add	x22,x22,x28			// h+=K[i]
-	eor	x8,x27,x27,ror#23
-	and	x17,x20,x27
-	bic	x28,x21,x27
-	add	x22,x22,x0			// h+=X[i]
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x23,x24			// a^b, b^c in next round
-	eor	x16,x16,x8,ror#18	// Sigma1(e)
-	ror	x8,x23,#28
-	add	x22,x22,x17			// h+=Ch(e,f,g)
-	eor	x17,x23,x23,ror#5
-	add	x22,x22,x16			// h+=Sigma1(e)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	add	x26,x26,x22			// d+=h
-	eor	x19,x19,x24			// Maj(a,b,c)
-	eor	x17,x8,x17,ror#34	// Sigma0(a)
-	add	x22,x22,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	//add	x22,x22,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x1,x1			// 14
-#endif
-	ldr	x6,[sp,#24]
-	add	x22,x22,x17			// h+=Sigma0(a)
-	str	x9,[sp,#16]
-	ror	x16,x26,#14
-	add	x21,x21,x19			// h+=K[i]
-	eor	x9,x26,x26,ror#23
-	and	x17,x27,x26
-	bic	x19,x20,x26
-	add	x21,x21,x1			// h+=X[i]
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x22,x23			// a^b, b^c in next round
-	eor	x16,x16,x9,ror#18	// Sigma1(e)
-	ror	x9,x22,#28
-	add	x21,x21,x17			// h+=Ch(e,f,g)
-	eor	x17,x22,x22,ror#5
-	add	x21,x21,x16			// h+=Sigma1(e)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	add	x25,x25,x21			// d+=h
-	eor	x28,x28,x23			// Maj(a,b,c)
-	eor	x17,x9,x17,ror#34	// Sigma0(a)
-	add	x21,x21,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	//add	x21,x21,x17			// h+=Sigma0(a)
-#ifndef	__AARCH64EB__
-	rev	x2,x2			// 15
-#endif
-	ldr	x7,[sp,#0]
-	add	x21,x21,x17			// h+=Sigma0(a)
-	str	x10,[sp,#24]
-	ror	x16,x25,#14
-	add	x20,x20,x28			// h+=K[i]
-	ror	x9,x4,#1
-	and	x17,x26,x25
-	ror	x8,x1,#19
-	bic	x28,x27,x25
-	ror	x10,x21,#28
-	add	x20,x20,x2			// h+=X[i]
-	eor	x16,x16,x25,ror#18
-	eor	x9,x9,x4,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x21,x22			// a^b, b^c in next round
-	eor	x16,x16,x25,ror#41	// Sigma1(e)
-	eor	x10,x10,x21,ror#34
-	add	x20,x20,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x8,x8,x1,ror#61
-	eor	x9,x9,x4,lsr#7	// sigma0(X[i+1])
-	add	x20,x20,x16			// h+=Sigma1(e)
-	eor	x19,x19,x22			// Maj(a,b,c)
-	eor	x17,x10,x21,ror#39	// Sigma0(a)
-	eor	x8,x8,x1,lsr#6	// sigma1(X[i+14])
-	add	x3,x3,x12
-	add	x24,x24,x20			// d+=h
-	add	x20,x20,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x3,x3,x9
-	add	x20,x20,x17			// h+=Sigma0(a)
-	add	x3,x3,x8
-.Loop_16_xx:
-	ldr	x8,[sp,#8]
-	str	x11,[sp,#0]
-	ror	x16,x24,#14
-	add	x27,x27,x19			// h+=K[i]
-	ror	x10,x5,#1
-	and	x17,x25,x24
-	ror	x9,x2,#19
-	bic	x19,x26,x24
-	ror	x11,x20,#28
-	add	x27,x27,x3			// h+=X[i]
-	eor	x16,x16,x24,ror#18
-	eor	x10,x10,x5,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x20,x21			// a^b, b^c in next round
-	eor	x16,x16,x24,ror#41	// Sigma1(e)
-	eor	x11,x11,x20,ror#34
-	add	x27,x27,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x9,x9,x2,ror#61
-	eor	x10,x10,x5,lsr#7	// sigma0(X[i+1])
-	add	x27,x27,x16			// h+=Sigma1(e)
-	eor	x28,x28,x21			// Maj(a,b,c)
-	eor	x17,x11,x20,ror#39	// Sigma0(a)
-	eor	x9,x9,x2,lsr#6	// sigma1(X[i+14])
-	add	x4,x4,x13
-	add	x23,x23,x27			// d+=h
-	add	x27,x27,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x4,x4,x10
-	add	x27,x27,x17			// h+=Sigma0(a)
-	add	x4,x4,x9
-	ldr	x9,[sp,#16]
-	str	x12,[sp,#8]
-	ror	x16,x23,#14
-	add	x26,x26,x28			// h+=K[i]
-	ror	x11,x6,#1
-	and	x17,x24,x23
-	ror	x10,x3,#19
-	bic	x28,x25,x23
-	ror	x12,x27,#28
-	add	x26,x26,x4			// h+=X[i]
-	eor	x16,x16,x23,ror#18
-	eor	x11,x11,x6,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x27,x20			// a^b, b^c in next round
-	eor	x16,x16,x23,ror#41	// Sigma1(e)
-	eor	x12,x12,x27,ror#34
-	add	x26,x26,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x10,x10,x3,ror#61
-	eor	x11,x11,x6,lsr#7	// sigma0(X[i+1])
-	add	x26,x26,x16			// h+=Sigma1(e)
-	eor	x19,x19,x20			// Maj(a,b,c)
-	eor	x17,x12,x27,ror#39	// Sigma0(a)
-	eor	x10,x10,x3,lsr#6	// sigma1(X[i+14])
-	add	x5,x5,x14
-	add	x22,x22,x26			// d+=h
-	add	x26,x26,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x5,x5,x11
-	add	x26,x26,x17			// h+=Sigma0(a)
-	add	x5,x5,x10
-	ldr	x10,[sp,#24]
-	str	x13,[sp,#16]
-	ror	x16,x22,#14
-	add	x25,x25,x19			// h+=K[i]
-	ror	x12,x7,#1
-	and	x17,x23,x22
-	ror	x11,x4,#19
-	bic	x19,x24,x22
-	ror	x13,x26,#28
-	add	x25,x25,x5			// h+=X[i]
-	eor	x16,x16,x22,ror#18
-	eor	x12,x12,x7,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x26,x27			// a^b, b^c in next round
-	eor	x16,x16,x22,ror#41	// Sigma1(e)
-	eor	x13,x13,x26,ror#34
-	add	x25,x25,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x11,x11,x4,ror#61
-	eor	x12,x12,x7,lsr#7	// sigma0(X[i+1])
-	add	x25,x25,x16			// h+=Sigma1(e)
-	eor	x28,x28,x27			// Maj(a,b,c)
-	eor	x17,x13,x26,ror#39	// Sigma0(a)
-	eor	x11,x11,x4,lsr#6	// sigma1(X[i+14])
-	add	x6,x6,x15
-	add	x21,x21,x25			// d+=h
-	add	x25,x25,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x6,x6,x12
-	add	x25,x25,x17			// h+=Sigma0(a)
-	add	x6,x6,x11
-	ldr	x11,[sp,#0]
-	str	x14,[sp,#24]
-	ror	x16,x21,#14
-	add	x24,x24,x28			// h+=K[i]
-	ror	x13,x8,#1
-	and	x17,x22,x21
-	ror	x12,x5,#19
-	bic	x28,x23,x21
-	ror	x14,x25,#28
-	add	x24,x24,x6			// h+=X[i]
-	eor	x16,x16,x21,ror#18
-	eor	x13,x13,x8,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x25,x26			// a^b, b^c in next round
-	eor	x16,x16,x21,ror#41	// Sigma1(e)
-	eor	x14,x14,x25,ror#34
-	add	x24,x24,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x12,x12,x5,ror#61
-	eor	x13,x13,x8,lsr#7	// sigma0(X[i+1])
-	add	x24,x24,x16			// h+=Sigma1(e)
-	eor	x19,x19,x26			// Maj(a,b,c)
-	eor	x17,x14,x25,ror#39	// Sigma0(a)
-	eor	x12,x12,x5,lsr#6	// sigma1(X[i+14])
-	add	x7,x7,x0
-	add	x20,x20,x24			// d+=h
-	add	x24,x24,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x7,x7,x13
-	add	x24,x24,x17			// h+=Sigma0(a)
-	add	x7,x7,x12
-	ldr	x12,[sp,#8]
-	str	x15,[sp,#0]
-	ror	x16,x20,#14
-	add	x23,x23,x19			// h+=K[i]
-	ror	x14,x9,#1
-	and	x17,x21,x20
-	ror	x13,x6,#19
-	bic	x19,x22,x20
-	ror	x15,x24,#28
-	add	x23,x23,x7			// h+=X[i]
-	eor	x16,x16,x20,ror#18
-	eor	x14,x14,x9,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x24,x25			// a^b, b^c in next round
-	eor	x16,x16,x20,ror#41	// Sigma1(e)
-	eor	x15,x15,x24,ror#34
-	add	x23,x23,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x13,x13,x6,ror#61
-	eor	x14,x14,x9,lsr#7	// sigma0(X[i+1])
-	add	x23,x23,x16			// h+=Sigma1(e)
-	eor	x28,x28,x25			// Maj(a,b,c)
-	eor	x17,x15,x24,ror#39	// Sigma0(a)
-	eor	x13,x13,x6,lsr#6	// sigma1(X[i+14])
-	add	x8,x8,x1
-	add	x27,x27,x23			// d+=h
-	add	x23,x23,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x8,x8,x14
-	add	x23,x23,x17			// h+=Sigma0(a)
-	add	x8,x8,x13
-	ldr	x13,[sp,#16]
-	str	x0,[sp,#8]
-	ror	x16,x27,#14
-	add	x22,x22,x28			// h+=K[i]
-	ror	x15,x10,#1
-	and	x17,x20,x27
-	ror	x14,x7,#19
-	bic	x28,x21,x27
-	ror	x0,x23,#28
-	add	x22,x22,x8			// h+=X[i]
-	eor	x16,x16,x27,ror#18
-	eor	x15,x15,x10,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x23,x24			// a^b, b^c in next round
-	eor	x16,x16,x27,ror#41	// Sigma1(e)
-	eor	x0,x0,x23,ror#34
-	add	x22,x22,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x14,x14,x7,ror#61
-	eor	x15,x15,x10,lsr#7	// sigma0(X[i+1])
-	add	x22,x22,x16			// h+=Sigma1(e)
-	eor	x19,x19,x24			// Maj(a,b,c)
-	eor	x17,x0,x23,ror#39	// Sigma0(a)
-	eor	x14,x14,x7,lsr#6	// sigma1(X[i+14])
-	add	x9,x9,x2
-	add	x26,x26,x22			// d+=h
-	add	x22,x22,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x9,x9,x15
-	add	x22,x22,x17			// h+=Sigma0(a)
-	add	x9,x9,x14
-	ldr	x14,[sp,#24]
-	str	x1,[sp,#16]
-	ror	x16,x26,#14
-	add	x21,x21,x19			// h+=K[i]
-	ror	x0,x11,#1
-	and	x17,x27,x26
-	ror	x15,x8,#19
-	bic	x19,x20,x26
-	ror	x1,x22,#28
-	add	x21,x21,x9			// h+=X[i]
-	eor	x16,x16,x26,ror#18
-	eor	x0,x0,x11,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x22,x23			// a^b, b^c in next round
-	eor	x16,x16,x26,ror#41	// Sigma1(e)
-	eor	x1,x1,x22,ror#34
-	add	x21,x21,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x15,x15,x8,ror#61
-	eor	x0,x0,x11,lsr#7	// sigma0(X[i+1])
-	add	x21,x21,x16			// h+=Sigma1(e)
-	eor	x28,x28,x23			// Maj(a,b,c)
-	eor	x17,x1,x22,ror#39	// Sigma0(a)
-	eor	x15,x15,x8,lsr#6	// sigma1(X[i+14])
-	add	x10,x10,x3
-	add	x25,x25,x21			// d+=h
-	add	x21,x21,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x10,x10,x0
-	add	x21,x21,x17			// h+=Sigma0(a)
-	add	x10,x10,x15
-	ldr	x15,[sp,#0]
-	str	x2,[sp,#24]
-	ror	x16,x25,#14
-	add	x20,x20,x28			// h+=K[i]
-	ror	x1,x12,#1
-	and	x17,x26,x25
-	ror	x0,x9,#19
-	bic	x28,x27,x25
-	ror	x2,x21,#28
-	add	x20,x20,x10			// h+=X[i]
-	eor	x16,x16,x25,ror#18
-	eor	x1,x1,x12,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x21,x22			// a^b, b^c in next round
-	eor	x16,x16,x25,ror#41	// Sigma1(e)
-	eor	x2,x2,x21,ror#34
-	add	x20,x20,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x0,x0,x9,ror#61
-	eor	x1,x1,x12,lsr#7	// sigma0(X[i+1])
-	add	x20,x20,x16			// h+=Sigma1(e)
-	eor	x19,x19,x22			// Maj(a,b,c)
-	eor	x17,x2,x21,ror#39	// Sigma0(a)
-	eor	x0,x0,x9,lsr#6	// sigma1(X[i+14])
-	add	x11,x11,x4
-	add	x24,x24,x20			// d+=h
-	add	x20,x20,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x11,x11,x1
-	add	x20,x20,x17			// h+=Sigma0(a)
-	add	x11,x11,x0
-	ldr	x0,[sp,#8]
-	str	x3,[sp,#0]
-	ror	x16,x24,#14
-	add	x27,x27,x19			// h+=K[i]
-	ror	x2,x13,#1
-	and	x17,x25,x24
-	ror	x1,x10,#19
-	bic	x19,x26,x24
-	ror	x3,x20,#28
-	add	x27,x27,x11			// h+=X[i]
-	eor	x16,x16,x24,ror#18
-	eor	x2,x2,x13,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x20,x21			// a^b, b^c in next round
-	eor	x16,x16,x24,ror#41	// Sigma1(e)
-	eor	x3,x3,x20,ror#34
-	add	x27,x27,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x1,x1,x10,ror#61
-	eor	x2,x2,x13,lsr#7	// sigma0(X[i+1])
-	add	x27,x27,x16			// h+=Sigma1(e)
-	eor	x28,x28,x21			// Maj(a,b,c)
-	eor	x17,x3,x20,ror#39	// Sigma0(a)
-	eor	x1,x1,x10,lsr#6	// sigma1(X[i+14])
-	add	x12,x12,x5
-	add	x23,x23,x27			// d+=h
-	add	x27,x27,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x12,x12,x2
-	add	x27,x27,x17			// h+=Sigma0(a)
-	add	x12,x12,x1
-	ldr	x1,[sp,#16]
-	str	x4,[sp,#8]
-	ror	x16,x23,#14
-	add	x26,x26,x28			// h+=K[i]
-	ror	x3,x14,#1
-	and	x17,x24,x23
-	ror	x2,x11,#19
-	bic	x28,x25,x23
-	ror	x4,x27,#28
-	add	x26,x26,x12			// h+=X[i]
-	eor	x16,x16,x23,ror#18
-	eor	x3,x3,x14,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x27,x20			// a^b, b^c in next round
-	eor	x16,x16,x23,ror#41	// Sigma1(e)
-	eor	x4,x4,x27,ror#34
-	add	x26,x26,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x2,x2,x11,ror#61
-	eor	x3,x3,x14,lsr#7	// sigma0(X[i+1])
-	add	x26,x26,x16			// h+=Sigma1(e)
-	eor	x19,x19,x20			// Maj(a,b,c)
-	eor	x17,x4,x27,ror#39	// Sigma0(a)
-	eor	x2,x2,x11,lsr#6	// sigma1(X[i+14])
-	add	x13,x13,x6
-	add	x22,x22,x26			// d+=h
-	add	x26,x26,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x13,x13,x3
-	add	x26,x26,x17			// h+=Sigma0(a)
-	add	x13,x13,x2
-	ldr	x2,[sp,#24]
-	str	x5,[sp,#16]
-	ror	x16,x22,#14
-	add	x25,x25,x19			// h+=K[i]
-	ror	x4,x15,#1
-	and	x17,x23,x22
-	ror	x3,x12,#19
-	bic	x19,x24,x22
-	ror	x5,x26,#28
-	add	x25,x25,x13			// h+=X[i]
-	eor	x16,x16,x22,ror#18
-	eor	x4,x4,x15,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x26,x27			// a^b, b^c in next round
-	eor	x16,x16,x22,ror#41	// Sigma1(e)
-	eor	x5,x5,x26,ror#34
-	add	x25,x25,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x3,x3,x12,ror#61
-	eor	x4,x4,x15,lsr#7	// sigma0(X[i+1])
-	add	x25,x25,x16			// h+=Sigma1(e)
-	eor	x28,x28,x27			// Maj(a,b,c)
-	eor	x17,x5,x26,ror#39	// Sigma0(a)
-	eor	x3,x3,x12,lsr#6	// sigma1(X[i+14])
-	add	x14,x14,x7
-	add	x21,x21,x25			// d+=h
-	add	x25,x25,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x14,x14,x4
-	add	x25,x25,x17			// h+=Sigma0(a)
-	add	x14,x14,x3
-	ldr	x3,[sp,#0]
-	str	x6,[sp,#24]
-	ror	x16,x21,#14
-	add	x24,x24,x28			// h+=K[i]
-	ror	x5,x0,#1
-	and	x17,x22,x21
-	ror	x4,x13,#19
-	bic	x28,x23,x21
-	ror	x6,x25,#28
-	add	x24,x24,x14			// h+=X[i]
-	eor	x16,x16,x21,ror#18
-	eor	x5,x5,x0,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x25,x26			// a^b, b^c in next round
-	eor	x16,x16,x21,ror#41	// Sigma1(e)
-	eor	x6,x6,x25,ror#34
-	add	x24,x24,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x4,x4,x13,ror#61
-	eor	x5,x5,x0,lsr#7	// sigma0(X[i+1])
-	add	x24,x24,x16			// h+=Sigma1(e)
-	eor	x19,x19,x26			// Maj(a,b,c)
-	eor	x17,x6,x25,ror#39	// Sigma0(a)
-	eor	x4,x4,x13,lsr#6	// sigma1(X[i+14])
-	add	x15,x15,x8
-	add	x20,x20,x24			// d+=h
-	add	x24,x24,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x15,x15,x5
-	add	x24,x24,x17			// h+=Sigma0(a)
-	add	x15,x15,x4
-	ldr	x4,[sp,#8]
-	str	x7,[sp,#0]
-	ror	x16,x20,#14
-	add	x23,x23,x19			// h+=K[i]
-	ror	x6,x1,#1
-	and	x17,x21,x20
-	ror	x5,x14,#19
-	bic	x19,x22,x20
-	ror	x7,x24,#28
-	add	x23,x23,x15			// h+=X[i]
-	eor	x16,x16,x20,ror#18
-	eor	x6,x6,x1,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x24,x25			// a^b, b^c in next round
-	eor	x16,x16,x20,ror#41	// Sigma1(e)
-	eor	x7,x7,x24,ror#34
-	add	x23,x23,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x5,x5,x14,ror#61
-	eor	x6,x6,x1,lsr#7	// sigma0(X[i+1])
-	add	x23,x23,x16			// h+=Sigma1(e)
-	eor	x28,x28,x25			// Maj(a,b,c)
-	eor	x17,x7,x24,ror#39	// Sigma0(a)
-	eor	x5,x5,x14,lsr#6	// sigma1(X[i+14])
-	add	x0,x0,x9
-	add	x27,x27,x23			// d+=h
-	add	x23,x23,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x0,x0,x6
-	add	x23,x23,x17			// h+=Sigma0(a)
-	add	x0,x0,x5
-	ldr	x5,[sp,#16]
-	str	x8,[sp,#8]
-	ror	x16,x27,#14
-	add	x22,x22,x28			// h+=K[i]
-	ror	x7,x2,#1
-	and	x17,x20,x27
-	ror	x6,x15,#19
-	bic	x28,x21,x27
-	ror	x8,x23,#28
-	add	x22,x22,x0			// h+=X[i]
-	eor	x16,x16,x27,ror#18
-	eor	x7,x7,x2,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x23,x24			// a^b, b^c in next round
-	eor	x16,x16,x27,ror#41	// Sigma1(e)
-	eor	x8,x8,x23,ror#34
-	add	x22,x22,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x6,x6,x15,ror#61
-	eor	x7,x7,x2,lsr#7	// sigma0(X[i+1])
-	add	x22,x22,x16			// h+=Sigma1(e)
-	eor	x19,x19,x24			// Maj(a,b,c)
-	eor	x17,x8,x23,ror#39	// Sigma0(a)
-	eor	x6,x6,x15,lsr#6	// sigma1(X[i+14])
-	add	x1,x1,x10
-	add	x26,x26,x22			// d+=h
-	add	x22,x22,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x1,x1,x7
-	add	x22,x22,x17			// h+=Sigma0(a)
-	add	x1,x1,x6
-	ldr	x6,[sp,#24]
-	str	x9,[sp,#16]
-	ror	x16,x26,#14
-	add	x21,x21,x19			// h+=K[i]
-	ror	x8,x3,#1
-	and	x17,x27,x26
-	ror	x7,x0,#19
-	bic	x19,x20,x26
-	ror	x9,x22,#28
-	add	x21,x21,x1			// h+=X[i]
-	eor	x16,x16,x26,ror#18
-	eor	x8,x8,x3,ror#8
-	orr	x17,x17,x19			// Ch(e,f,g)
-	eor	x19,x22,x23			// a^b, b^c in next round
-	eor	x16,x16,x26,ror#41	// Sigma1(e)
-	eor	x9,x9,x22,ror#34
-	add	x21,x21,x17			// h+=Ch(e,f,g)
-	and	x28,x28,x19			// (b^c)&=(a^b)
-	eor	x7,x7,x0,ror#61
-	eor	x8,x8,x3,lsr#7	// sigma0(X[i+1])
-	add	x21,x21,x16			// h+=Sigma1(e)
-	eor	x28,x28,x23			// Maj(a,b,c)
-	eor	x17,x9,x22,ror#39	// Sigma0(a)
-	eor	x7,x7,x0,lsr#6	// sigma1(X[i+14])
-	add	x2,x2,x11
-	add	x25,x25,x21			// d+=h
-	add	x21,x21,x28			// h+=Maj(a,b,c)
-	ldr	x28,[x30],#8		// *K++, x19 in next round
-	add	x2,x2,x8
-	add	x21,x21,x17			// h+=Sigma0(a)
-	add	x2,x2,x7
-	ldr	x7,[sp,#0]
-	str	x10,[sp,#24]
-	ror	x16,x25,#14
-	add	x20,x20,x28			// h+=K[i]
-	ror	x9,x4,#1
-	and	x17,x26,x25
-	ror	x8,x1,#19
-	bic	x28,x27,x25
-	ror	x10,x21,#28
-	add	x20,x20,x2			// h+=X[i]
-	eor	x16,x16,x25,ror#18
-	eor	x9,x9,x4,ror#8
-	orr	x17,x17,x28			// Ch(e,f,g)
-	eor	x28,x21,x22			// a^b, b^c in next round
-	eor	x16,x16,x25,ror#41	// Sigma1(e)
-	eor	x10,x10,x21,ror#34
-	add	x20,x20,x17			// h+=Ch(e,f,g)
-	and	x19,x19,x28			// (b^c)&=(a^b)
-	eor	x8,x8,x1,ror#61
-	eor	x9,x9,x4,lsr#7	// sigma0(X[i+1])
-	add	x20,x20,x16			// h+=Sigma1(e)
-	eor	x19,x19,x22			// Maj(a,b,c)
-	eor	x17,x10,x21,ror#39	// Sigma0(a)
-	eor	x8,x8,x1,lsr#6	// sigma1(X[i+14])
-	add	x3,x3,x12
-	add	x24,x24,x20			// d+=h
-	add	x20,x20,x19			// h+=Maj(a,b,c)
-	ldr	x19,[x30],#8		// *K++, x28 in next round
-	add	x3,x3,x9
-	add	x20,x20,x17			// h+=Sigma0(a)
-	add	x3,x3,x8
-	cbnz	x19,.Loop_16_xx
-
-	ldp	x0,x2,[x29,#96]
-	ldr	x1,[x29,#112]
-	sub	x30,x30,#648		// rewind
-
-	ldp	x3,x4,[x0]
-	ldp	x5,x6,[x0,#2*8]
-	add	x1,x1,#14*8			// advance input pointer
-	ldp	x7,x8,[x0,#4*8]
-	add	x20,x20,x3
-	ldp	x9,x10,[x0,#6*8]
-	add	x21,x21,x4
-	add	x22,x22,x5
-	add	x23,x23,x6
-	stp	x20,x21,[x0]
-	add	x24,x24,x7
-	add	x25,x25,x8
-	stp	x22,x23,[x0,#2*8]
-	add	x26,x26,x9
-	add	x27,x27,x10
-	cmp	x1,x2
-	stp	x24,x25,[x0,#4*8]
-	stp	x26,x27,[x0,#6*8]
-	b.ne	.Loop
-
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#4*8
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#128
-	ret
-.size	sha512_block_data_order,.-sha512_block_data_order
-
-.align	6
-.type	.LK512,%object
-.LK512:
-	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
-	.quad	0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
-	.quad	0x3956c25bf348b538,0x59f111f1b605d019
-	.quad	0x923f82a4af194f9b,0xab1c5ed5da6d8118
-	.quad	0xd807aa98a3030242,0x12835b0145706fbe
-	.quad	0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
-	.quad	0x72be5d74f27b896f,0x80deb1fe3b1696b1
-	.quad	0x9bdc06a725c71235,0xc19bf174cf692694
-	.quad	0xe49b69c19ef14ad2,0xefbe4786384f25e3
-	.quad	0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
-	.quad	0x2de92c6f592b0275,0x4a7484aa6ea6e483
-	.quad	0x5cb0a9dcbd41fbd4,0x76f988da831153b5
-	.quad	0x983e5152ee66dfab,0xa831c66d2db43210
-	.quad	0xb00327c898fb213f,0xbf597fc7beef0ee4
-	.quad	0xc6e00bf33da88fc2,0xd5a79147930aa725
-	.quad	0x06ca6351e003826f,0x142929670a0e6e70
-	.quad	0x27b70a8546d22ffc,0x2e1b21385c26c926
-	.quad	0x4d2c6dfc5ac42aed,0x53380d139d95b3df
-	.quad	0x650a73548baf63de,0x766a0abb3c77b2a8
-	.quad	0x81c2c92e47edaee6,0x92722c851482353b
-	.quad	0xa2bfe8a14cf10364,0xa81a664bbc423001
-	.quad	0xc24b8b70d0f89791,0xc76c51a30654be30
-	.quad	0xd192e819d6ef5218,0xd69906245565a910
-	.quad	0xf40e35855771202a,0x106aa07032bbd1b8
-	.quad	0x19a4c116b8d2d0c8,0x1e376c085141ab53
-	.quad	0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
-	.quad	0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
-	.quad	0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
-	.quad	0x748f82ee5defb2fc,0x78a5636f43172f60
-	.quad	0x84c87814a1f0ab72,0x8cc702081a6439ec
-	.quad	0x90befffa23631e28,0xa4506cebde82bde9
-	.quad	0xbef9a3f7b2c67915,0xc67178f2e372532b
-	.quad	0xca273eceea26619c,0xd186b8c721c0c207
-	.quad	0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
-	.quad	0x06f067aa72176fba,0x0a637dc5a2c898a6
-	.quad	0x113f9804bef90dae,0x1b710b35131c471b
-	.quad	0x28db77f523047d84,0x32caab7b40c72493
-	.quad	0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
-	.quad	0x4cc5d4becb3e42b6,0x597f299cfc657e2a
-	.quad	0x5fcb6fab3ad6faec,0x6c44198c4a475817
-	.quad	0	// terminator
-.size	.LK512,.-.LK512
-#ifndef	__KERNEL__
-.align	3
-.LOPENSSL_armcap_P:
-# ifdef	__ILP32__
-	.long	OPENSSL_armcap_P-.
-# else
-	.quad	OPENSSL_armcap_P-.
-# endif
-#endif
-.asciz	"SHA512 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>"
-.align	2
-#ifndef	__KERNEL__
-.comm	OPENSSL_armcap_P,4,4
-#endif
diff --git a/arch/mips/include/uapi/asm/sgidefs.h b/arch/mips/include/uapi/asm/sgidefs.h
index 876442fcfb32..5be81f8fd479 100644
--- a/arch/mips/include/uapi/asm/sgidefs.h
+++ b/arch/mips/include/uapi/asm/sgidefs.h
@@ -10,14 +10,6 @@
 #ifndef __ASM_SGIDEFS_H
 #define __ASM_SGIDEFS_H
 
-/*
- * Using a Linux compiler for building Linux seems logic but not to
- * everybody.
- */
-#ifndef __linux__
-#error Use a Linux compiler or give up.
-#endif
-
 /*
  * Definitions for the ISA levels
  *
diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h
index 5811e7849a2e..1df70a73dc5c 100644
--- a/arch/s390/include/asm/facility.h
+++ b/arch/s390/include/asm/facility.h
@@ -61,6 +61,18 @@ static inline int test_facility(unsigned long nr)
 	return __test_facility(nr, &S390_lowcore.stfle_fac_list);
 }
 
+static inline unsigned long __stfle_asm(u64 *stfle_fac_list, int size)
+{
+	register unsigned long reg0 asm("0") = size - 1;
+
+	asm volatile(
+		".insn s,0xb2b00000,0(%1)" /* stfle */
+		: "+d" (reg0)
+		: "a" (stfle_fac_list)
+		: "memory", "cc");
+	return reg0;
+}
+
 /**
  * stfle - Store facility list extended
  * @stfle_fac_list: array where facility list can be stored
@@ -78,13 +90,8 @@ static inline void stfle(u64 *stfle_fac_list, int size)
 	memcpy(stfle_fac_list, &S390_lowcore.stfl_fac_list, 4);
 	if (S390_lowcore.stfl_fac_list & 0x01000000) {
 		/* More facility bits available with stfle */
-		register unsigned long reg0 asm("0") = size - 1;
-
-		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
-			     : "+d" (reg0)
-			     : "a" (stfle_fac_list)
-			     : "memory", "cc");
-		nr = (reg0 + 1) * 8; /* # bytes stored by stfle */
+		nr = __stfle_asm(stfle_fac_list, size);
+		nr = min_t(unsigned long, (nr + 1) * 8, size * 8);
 	}
 	memset((char *) stfle_fac_list + nr, 0, size * 8 - nr);
 	preempt_enable();
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e497d374412a..8d20fb09722c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -23,6 +23,7 @@
 #include <linux/rcupdate.h>
 #include <linux/export.h>
 #include <linux/context_tracking.h>
+#include <linux/nospec.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -650,9 +651,11 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 {
 	struct thread_struct *thread = &tsk->thread;
 	unsigned long val = 0;
+	int index = n;
 
 	if (n < HBP_NUM) {
-		struct perf_event *bp = thread->ptrace_bps[n];
+		struct perf_event *bp = thread->ptrace_bps[index];
+		index = array_index_nospec(index, HBP_NUM);
 
 		if (bp)
 			val = bp->hw.info.address;
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9692a5e9fdab..b95693a73f12 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -4,6 +4,7 @@
 #include <linux/user.h>
 #include <linux/regset.h>
 #include <linux/syscalls.h>
+#include <linux/nospec.h>
 
 #include <asm/uaccess.h>
 #include <asm/desc.h>
@@ -219,6 +220,7 @@ int do_get_thread_area(struct task_struct *p, int idx,
 		       struct user_desc __user *u_info)
 {
 	struct user_desc info;
+	int index;
 
 	if (idx == -1 && get_user(idx, &u_info->entry_number))
 		return -EFAULT;
@@ -226,8 +228,11 @@ int do_get_thread_area(struct task_struct *p, int idx,
 	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
 		return -EINVAL;
 
-	fill_user_desc(&info, idx,
-		       &p->thread.tls_array[idx - GDT_ENTRY_TLS_MIN]);
+	index = idx - GDT_ENTRY_TLS_MIN;
+	index = array_index_nospec(index,
+			GDT_ENTRY_TLS_MAX - GDT_ENTRY_TLS_MIN + 1);
+
+	fill_user_desc(&info, idx, &p->thread.tls_array[index]);
 
 	if (copy_to_user(u_info, &info, sizeof(info)))
 		return -EFAULT;
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 463033b4db1d..5a24a484ecc7 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -2185,7 +2185,7 @@ static struct talitos_alg_template driver_algs[] = {
 			.base = {
 				.cra_name = "authenc(hmac(sha1),cbc(aes))",
 				.cra_driver_name = "authenc-hmac-sha1-"
-						   "cbc-aes-talitos",
+						   "cbc-aes-talitos-hsna",
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2229,7 +2229,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "authenc(hmac(sha1),"
 					    "cbc(des3_ede))",
 				.cra_driver_name = "authenc-hmac-sha1-"
-						   "cbc-3des-talitos",
+						   "cbc-3des-talitos-hsna",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2271,7 +2271,7 @@ static struct talitos_alg_template driver_algs[] = {
 			.base = {
 				.cra_name = "authenc(hmac(sha224),cbc(aes))",
 				.cra_driver_name = "authenc-hmac-sha224-"
-						   "cbc-aes-talitos",
+						   "cbc-aes-talitos-hsna",
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2315,7 +2315,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "authenc(hmac(sha224),"
 					    "cbc(des3_ede))",
 				.cra_driver_name = "authenc-hmac-sha224-"
-						   "cbc-3des-talitos",
+						   "cbc-3des-talitos-hsna",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2357,7 +2357,7 @@ static struct talitos_alg_template driver_algs[] = {
 			.base = {
 				.cra_name = "authenc(hmac(sha256),cbc(aes))",
 				.cra_driver_name = "authenc-hmac-sha256-"
-						   "cbc-aes-talitos",
+						   "cbc-aes-talitos-hsna",
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2401,7 +2401,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "authenc(hmac(sha256),"
 					    "cbc(des3_ede))",
 				.cra_driver_name = "authenc-hmac-sha256-"
-						   "cbc-3des-talitos",
+						   "cbc-3des-talitos-hsna",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2527,7 +2527,7 @@ static struct talitos_alg_template driver_algs[] = {
 			.base = {
 				.cra_name = "authenc(hmac(md5),cbc(aes))",
 				.cra_driver_name = "authenc-hmac-md5-"
-						   "cbc-aes-talitos",
+						   "cbc-aes-talitos-hsna",
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
@@ -2569,7 +2569,7 @@ static struct talitos_alg_template driver_algs[] = {
 			.base = {
 				.cra_name = "authenc(hmac(md5),cbc(des3_ede))",
 				.cra_driver_name = "authenc-hmac-md5-"
-						   "cbc-3des-talitos",
+						   "cbc-3des-talitos-hsna",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 				.cra_flags = CRYPTO_ALG_ASYNC,
 			},
diff --git a/drivers/input/keyboard/imx_keypad.c b/drivers/input/keyboard/imx_keypad.c
index 2165f3dd328b..842c0235471d 100644
--- a/drivers/input/keyboard/imx_keypad.c
+++ b/drivers/input/keyboard/imx_keypad.c
@@ -530,11 +530,12 @@ static int imx_keypad_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused imx_kbd_suspend(struct device *dev)
+static int __maybe_unused imx_kbd_noirq_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct imx_keypad *kbd = platform_get_drvdata(pdev);
 	struct input_dev *input_dev = kbd->input_dev;
+	unsigned short reg_val = readw(kbd->mmio_base + KPSR);
 
 	/* imx kbd can wake up system even clock is disabled */
 	mutex_lock(&input_dev->mutex);
@@ -544,13 +545,20 @@ static int __maybe_unused imx_kbd_suspend(struct device *dev)
 
 	mutex_unlock(&input_dev->mutex);
 
-	if (device_may_wakeup(&pdev->dev))
+	if (device_may_wakeup(&pdev->dev)) {
+		if (reg_val & KBD_STAT_KPKD)
+			reg_val |= KBD_STAT_KRIE;
+		if (reg_val & KBD_STAT_KPKR)
+			reg_val |= KBD_STAT_KDIE;
+		writew(reg_val, kbd->mmio_base + KPSR);
+
 		enable_irq_wake(kbd->irq);
+	}
 
 	return 0;
 }
 
-static int __maybe_unused imx_kbd_resume(struct device *dev)
+static int __maybe_unused imx_kbd_noirq_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct imx_keypad *kbd = platform_get_drvdata(pdev);
@@ -574,7 +582,9 @@ err_clk:
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(imx_kbd_pm_ops, imx_kbd_suspend, imx_kbd_resume);
+static const struct dev_pm_ops imx_kbd_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_kbd_noirq_suspend, imx_kbd_noirq_resume)
+};
 
 static struct platform_driver imx_keypad_driver = {
 	.driver		= {
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 38edf8f5bf8a..15be3ee6cc50 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1187,6 +1187,8 @@ static const char * const middle_button_pnp_ids[] = {
 	"LEN2132", /* ThinkPad P52 */
 	"LEN2133", /* ThinkPad P72 w/ NFC */
 	"LEN2134", /* ThinkPad P72 */
+	"LEN0407",
+	"LEN0408",
 	NULL
 };
 
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 0aba34a7b3b3..727f9e571955 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -218,8 +218,8 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
 		BUG();
 	}
 
-	DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str,
-		block);
+	DMERR_LIMIT("%s: %s block %llu is corrupted", v->data_dev->name,
+		    type_str, block);
 
 	if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS)
 		DMERR("%s: reached maximum errors", v->data_dev->name);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 21698eb671d7..765a16dab2e5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7296,9 +7296,9 @@ static void status_unused(struct seq_file *seq)
 static int status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
-	unsigned long dt, db;
-	sector_t rt;
-	int scale;
+	unsigned long dt, db = 0;
+	sector_t rt, curr_mark_cnt, resync_mark_cnt;
+	int scale, recovery_active;
 	unsigned int per_milli;
 
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
@@ -7368,22 +7368,30 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 	 * db: blocks written from mark until now
 	 * rt: remaining time
 	 *
-	 * rt is a sector_t, so could be 32bit or 64bit.
-	 * So we divide before multiply in case it is 32bit and close
-	 * to the limit.
-	 * We scale the divisor (db) by 32 to avoid losing precision
-	 * near the end of resync when the number of remaining sectors
-	 * is close to 'db'.
-	 * We then divide rt by 32 after multiplying by db to compensate.
-	 * The '+1' avoids division by zero if db is very small.
+	 * rt is a sector_t, which is always 64bit now. We are keeping
+	 * the original algorithm, but it is not really necessary.
+	 *
+	 * Original algorithm:
+	 *   So we divide before multiply in case it is 32bit and close
+	 *   to the limit.
+	 *   We scale the divisor (db) by 32 to avoid losing precision
+	 *   near the end of resync when the number of remaining sectors
+	 *   is close to 'db'.
+	 *   We then divide rt by 32 after multiplying by db to compensate.
+	 *   The '+1' avoids division by zero if db is very small.
 	 */
 	dt = ((jiffies - mddev->resync_mark) / HZ);
 	if (!dt) dt++;
-	db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active))
-		- mddev->resync_mark_cnt;
+
+	curr_mark_cnt = mddev->curr_mark_cnt;
+	recovery_active = atomic_read(&mddev->recovery_active);
+	resync_mark_cnt = mddev->resync_mark_cnt;
+
+	if (curr_mark_cnt >= (recovery_active + resync_mark_cnt))
+		db = curr_mark_cnt - (recovery_active + resync_mark_cnt);
 
 	rt = max_sectors - resync;    /* number of remaining sectors */
-	sector_div(rt, db/32+1);
+	rt = div64_u64(rt, db/32+1);
 	rt *= dt;
 	rt >>= 5;
 
diff --git a/drivers/misc/vmw_vmci/vmci_context.c b/drivers/misc/vmw_vmci/vmci_context.c
index f866a4baecb5..b9da2c6cc981 100644
--- a/drivers/misc/vmw_vmci/vmci_context.c
+++ b/drivers/misc/vmw_vmci/vmci_context.c
@@ -28,6 +28,9 @@
 #include "vmci_driver.h"
 #include "vmci_event.h"
 
+/* Use a wide upper bound for the maximum contexts. */
+#define VMCI_MAX_CONTEXTS 2000
+
 /*
  * List of current VMCI contexts.  Contexts can be added by
  * vmci_ctx_create() and removed via vmci_ctx_destroy().
@@ -124,19 +127,22 @@ struct vmci_ctx *vmci_ctx_create(u32 cid, u32 priv_flags,
 	/* Initialize host-specific VMCI context. */
 	init_waitqueue_head(&context->host_context.wait_queue);
 
-	context->queue_pair_array = vmci_handle_arr_create(0);
+	context->queue_pair_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_QP_COUNT);
 	if (!context->queue_pair_array) {
 		error = -ENOMEM;
 		goto err_free_ctx;
 	}
 
-	context->doorbell_array = vmci_handle_arr_create(0);
+	context->doorbell_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT);
 	if (!context->doorbell_array) {
 		error = -ENOMEM;
 		goto err_free_qp_array;
 	}
 
-	context->pending_doorbell_array = vmci_handle_arr_create(0);
+	context->pending_doorbell_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT);
 	if (!context->pending_doorbell_array) {
 		error = -ENOMEM;
 		goto err_free_db_array;
@@ -211,7 +217,7 @@ static int ctx_fire_notification(u32 context_id, u32 priv_flags)
 	 * We create an array to hold the subscribers we find when
 	 * scanning through all contexts.
 	 */
-	subscriber_array = vmci_handle_arr_create(0);
+	subscriber_array = vmci_handle_arr_create(0, VMCI_MAX_CONTEXTS);
 	if (subscriber_array == NULL)
 		return VMCI_ERROR_NO_MEM;
 
@@ -630,20 +636,26 @@ int vmci_ctx_add_notification(u32 context_id, u32 remote_cid)
 
 	spin_lock(&context->lock);
 
-	list_for_each_entry(n, &context->notifier_list, node) {
-		if (vmci_handle_is_equal(n->handle, notifier->handle)) {
-			exists = true;
-			break;
+	if (context->n_notifiers < VMCI_MAX_CONTEXTS) {
+		list_for_each_entry(n, &context->notifier_list, node) {
+			if (vmci_handle_is_equal(n->handle, notifier->handle)) {
+				exists = true;
+				break;
+			}
 		}
-	}
 
-	if (exists) {
-		kfree(notifier);
-		result = VMCI_ERROR_ALREADY_EXISTS;
+		if (exists) {
+			kfree(notifier);
+			result = VMCI_ERROR_ALREADY_EXISTS;
+		} else {
+			list_add_tail_rcu(&notifier->node,
+					  &context->notifier_list);
+			context->n_notifiers++;
+			result = VMCI_SUCCESS;
+		}
 	} else {
-		list_add_tail_rcu(&notifier->node, &context->notifier_list);
-		context->n_notifiers++;
-		result = VMCI_SUCCESS;
+		kfree(notifier);
+		result = VMCI_ERROR_NO_MEM;
 	}
 
 	spin_unlock(&context->lock);
@@ -728,8 +740,7 @@ static int vmci_ctx_get_chkpt_doorbells(struct vmci_ctx *context,
 					u32 *buf_size, void **pbuf)
 {
 	struct dbell_cpt_state *dbells;
-	size_t n_doorbells;
-	int i;
+	u32 i, n_doorbells;
 
 	n_doorbells = vmci_handle_arr_get_size(context->doorbell_array);
 	if (n_doorbells > 0) {
@@ -867,7 +878,8 @@ int vmci_ctx_rcv_notifications_get(u32 context_id,
 	spin_lock(&context->lock);
 
 	*db_handle_array = context->pending_doorbell_array;
-	context->pending_doorbell_array = vmci_handle_arr_create(0);
+	context->pending_doorbell_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT);
 	if (!context->pending_doorbell_array) {
 		context->pending_doorbell_array = *db_handle_array;
 		*db_handle_array = NULL;
@@ -949,12 +961,11 @@ int vmci_ctx_dbell_create(u32 context_id, struct vmci_handle handle)
 		return VMCI_ERROR_NOT_FOUND;
 
 	spin_lock(&context->lock);
-	if (!vmci_handle_arr_has_entry(context->doorbell_array, handle)) {
-		vmci_handle_arr_append_entry(&context->doorbell_array, handle);
-		result = VMCI_SUCCESS;
-	} else {
+	if (!vmci_handle_arr_has_entry(context->doorbell_array, handle))
+		result = vmci_handle_arr_append_entry(&context->doorbell_array,
+						      handle);
+	else
 		result = VMCI_ERROR_DUPLICATE_ENTRY;
-	}
 
 	spin_unlock(&context->lock);
 	vmci_ctx_put(context);
@@ -1090,15 +1101,16 @@ int vmci_ctx_notify_dbell(u32 src_cid,
 			if (!vmci_handle_arr_has_entry(
 					dst_context->pending_doorbell_array,
 					handle)) {
-				vmci_handle_arr_append_entry(
+				result = vmci_handle_arr_append_entry(
 					&dst_context->pending_doorbell_array,
 					handle);
-
-				ctx_signal_notify(dst_context);
-				wake_up(&dst_context->host_context.wait_queue);
-
+				if (result == VMCI_SUCCESS) {
+					ctx_signal_notify(dst_context);
+					wake_up(&dst_context->host_context.wait_queue);
+				}
+			} else {
+				result = VMCI_SUCCESS;
 			}
-			result = VMCI_SUCCESS;
 		}
 		spin_unlock(&dst_context->lock);
 	}
@@ -1125,13 +1137,11 @@ int vmci_ctx_qp_create(struct vmci_ctx *context, struct vmci_handle handle)
 	if (context == NULL || vmci_handle_is_invalid(handle))
 		return VMCI_ERROR_INVALID_ARGS;
 
-	if (!vmci_handle_arr_has_entry(context->queue_pair_array, handle)) {
-		vmci_handle_arr_append_entry(&context->queue_pair_array,
-					     handle);
-		result = VMCI_SUCCESS;
-	} else {
+	if (!vmci_handle_arr_has_entry(context->queue_pair_array, handle))
+		result = vmci_handle_arr_append_entry(
+			&context->queue_pair_array, handle);
+	else
 		result = VMCI_ERROR_DUPLICATE_ENTRY;
-	}
 
 	return result;
 }
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.c b/drivers/misc/vmw_vmci/vmci_handle_array.c
index 344973a0fb0a..917e18a8af95 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.c
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.c
@@ -16,24 +16,29 @@
 #include <linux/slab.h>
 #include "vmci_handle_array.h"
 
-static size_t handle_arr_calc_size(size_t capacity)
+static size_t handle_arr_calc_size(u32 capacity)
 {
-	return sizeof(struct vmci_handle_arr) +
+	return VMCI_HANDLE_ARRAY_HEADER_SIZE +
 	    capacity * sizeof(struct vmci_handle);
 }
 
-struct vmci_handle_arr *vmci_handle_arr_create(size_t capacity)
+struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity)
 {
 	struct vmci_handle_arr *array;
 
+	if (max_capacity == 0 || capacity > max_capacity)
+		return NULL;
+
 	if (capacity == 0)
-		capacity = VMCI_HANDLE_ARRAY_DEFAULT_SIZE;
+		capacity = min((u32)VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY,
+			       max_capacity);
 
 	array = kmalloc(handle_arr_calc_size(capacity), GFP_ATOMIC);
 	if (!array)
 		return NULL;
 
 	array->capacity = capacity;
+	array->max_capacity = max_capacity;
 	array->size = 0;
 
 	return array;
@@ -44,27 +49,34 @@ void vmci_handle_arr_destroy(struct vmci_handle_arr *array)
 	kfree(array);
 }
 
-void vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
-				  struct vmci_handle handle)
+int vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
+				 struct vmci_handle handle)
 {
 	struct vmci_handle_arr *array = *array_ptr;
 
 	if (unlikely(array->size >= array->capacity)) {
 		/* reallocate. */
 		struct vmci_handle_arr *new_array;
-		size_t new_capacity = array->capacity * VMCI_ARR_CAP_MULT;
-		size_t new_size = handle_arr_calc_size(new_capacity);
+		u32 capacity_bump = min(array->max_capacity - array->capacity,
+					array->capacity);
+		size_t new_size = handle_arr_calc_size(array->capacity +
+						       capacity_bump);
+
+		if (array->size >= array->max_capacity)
+			return VMCI_ERROR_NO_MEM;
 
 		new_array = krealloc(array, new_size, GFP_ATOMIC);
 		if (!new_array)
-			return;
+			return VMCI_ERROR_NO_MEM;
 
-		new_array->capacity = new_capacity;
+		new_array->capacity += capacity_bump;
 		*array_ptr = array = new_array;
 	}
 
 	array->entries[array->size] = handle;
 	array->size++;
+
+	return VMCI_SUCCESS;
 }
 
 /*
@@ -74,7 +86,7 @@ struct vmci_handle vmci_handle_arr_remove_entry(struct vmci_handle_arr *array,
 						struct vmci_handle entry_handle)
 {
 	struct vmci_handle handle = VMCI_INVALID_HANDLE;
-	size_t i;
+	u32 i;
 
 	for (i = 0; i < array->size; i++) {
 		if (vmci_handle_is_equal(array->entries[i], entry_handle)) {
@@ -109,7 +121,7 @@ struct vmci_handle vmci_handle_arr_remove_tail(struct vmci_handle_arr *array)
  * Handle at given index, VMCI_INVALID_HANDLE if invalid index.
  */
 struct vmci_handle
-vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, size_t index)
+vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, u32 index)
 {
 	if (unlikely(index >= array->size))
 		return VMCI_INVALID_HANDLE;
@@ -120,7 +132,7 @@ vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, size_t index)
 bool vmci_handle_arr_has_entry(const struct vmci_handle_arr *array,
 			       struct vmci_handle entry_handle)
 {
-	size_t i;
+	u32 i;
 
 	for (i = 0; i < array->size; i++)
 		if (vmci_handle_is_equal(array->entries[i], entry_handle))
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.h b/drivers/misc/vmw_vmci/vmci_handle_array.h
index b5f3a7f98cf1..0fc58597820e 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.h
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.h
@@ -17,32 +17,41 @@
 #define _VMCI_HANDLE_ARRAY_H_
 
 #include <linux/vmw_vmci_defs.h>
+#include <linux/limits.h>
 #include <linux/types.h>
 
-#define VMCI_HANDLE_ARRAY_DEFAULT_SIZE 4
-#define VMCI_ARR_CAP_MULT 2	/* Array capacity multiplier */
-
 struct vmci_handle_arr {
-	size_t capacity;
-	size_t size;
+	u32 capacity;
+	u32 max_capacity;
+	u32 size;
+	u32 pad;
 	struct vmci_handle entries[];
 };
 
-struct vmci_handle_arr *vmci_handle_arr_create(size_t capacity);
+#define VMCI_HANDLE_ARRAY_HEADER_SIZE				\
+	offsetof(struct vmci_handle_arr, entries)
+/* Select a default capacity that results in a 64 byte sized array */
+#define VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY			6
+/* Make sure that the max array size can be expressed by a u32 */
+#define VMCI_HANDLE_ARRAY_MAX_CAPACITY				\
+	((U32_MAX - VMCI_HANDLE_ARRAY_HEADER_SIZE - 1) /	\
+	sizeof(struct vmci_handle))
+
+struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity);
 void vmci_handle_arr_destroy(struct vmci_handle_arr *array);
-void vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
-				  struct vmci_handle handle);
+int vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
+				 struct vmci_handle handle);
 struct vmci_handle vmci_handle_arr_remove_entry(struct vmci_handle_arr *array,
 						struct vmci_handle
 						entry_handle);
 struct vmci_handle vmci_handle_arr_remove_tail(struct vmci_handle_arr *array);
 struct vmci_handle
-vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, size_t index);
+vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, u32 index);
 bool vmci_handle_arr_has_entry(const struct vmci_handle_arr *array,
 			       struct vmci_handle entry_handle);
 struct vmci_handle *vmci_handle_arr_get_handles(struct vmci_handle_arr *array);
 
-static inline size_t vmci_handle_arr_get_size(
+static inline u32 vmci_handle_arr_get_size(
 	const struct vmci_handle_arr *array)
 {
 	return array->size;
diff --git a/drivers/net/can/spi/Kconfig b/drivers/net/can/spi/Kconfig
index 148cae5871a6..249d2db7d600 100644
--- a/drivers/net/can/spi/Kconfig
+++ b/drivers/net/can/spi/Kconfig
@@ -2,9 +2,10 @@ menu "CAN SPI interfaces"
 	depends on SPI
 
 config CAN_MCP251X
-	tristate "Microchip MCP251x SPI CAN controllers"
+	tristate "Microchip MCP251x and MCP25625 SPI CAN controllers"
 	depends on HAS_DMA
 	---help---
-	  Driver for the Microchip MCP251x SPI CAN controllers.
+	  Driver for the Microchip MCP251x and MCP25625 SPI CAN
+	  controllers.
 
 endmenu
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index f3f05fea8e1f..d8c448beab24 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1,5 +1,5 @@
 /*
- * CAN bus driver for Microchip 251x CAN Controller with SPI Interface
+ * CAN bus driver for Microchip 251x/25625 CAN Controller with SPI Interface
  *
  * MCP2510 support and bug fixes by Christian Pellegrin
  * <chripell@evolware.org>
@@ -41,7 +41,7 @@
  * static struct spi_board_info spi_board_info[] = {
  *         {
  *                 .modalias = "mcp2510",
- *			// or "mcp2515" depending on your controller
+ *			// "mcp2515" or "mcp25625" depending on your controller
  *                 .platform_data = &mcp251x_info,
  *                 .irq = IRQ_EINT13,
  *                 .max_speed_hz = 2*1000*1000,
@@ -238,6 +238,7 @@ static const struct can_bittiming_const mcp251x_bittiming_const = {
 enum mcp251x_model {
 	CAN_MCP251X_MCP2510	= 0x2510,
 	CAN_MCP251X_MCP2515	= 0x2515,
+	CAN_MCP251X_MCP25625	= 0x25625,
 };
 
 struct mcp251x_priv {
@@ -280,7 +281,6 @@ static inline int mcp251x_is_##_model(struct spi_device *spi) \
 }
 
 MCP251X_IS(2510);
-MCP251X_IS(2515);
 
 static void mcp251x_clean(struct net_device *net)
 {
@@ -640,7 +640,7 @@ static int mcp251x_hw_reset(struct spi_device *spi)
 
 	/* Wait for oscillator startup timer after reset */
 	mdelay(MCP251X_OST_DELAY_MS);
-	
+
 	reg = mcp251x_read_reg(spi, CANSTAT);
 	if ((reg & CANCTRL_REQOP_MASK) != CANCTRL_REQOP_CONF)
 		return -ENODEV;
@@ -821,9 +821,8 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 		/* receive buffer 0 */
 		if (intf & CANINTF_RX0IF) {
 			mcp251x_hw_rx(spi, 0);
-			/*
-			 * Free one buffer ASAP
-			 * (The MCP2515 does this automatically.)
+			/* Free one buffer ASAP
+			 * (The MCP2515/25625 does this automatically.)
 			 */
 			if (mcp251x_is_2510(spi))
 				mcp251x_write_bits(spi, CANINTF, CANINTF_RX0IF, 0x00);
@@ -832,7 +831,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 		/* receive buffer 1 */
 		if (intf & CANINTF_RX1IF) {
 			mcp251x_hw_rx(spi, 1);
-			/* the MCP2515 does this automatically */
+			/* The MCP2515/25625 does this automatically. */
 			if (mcp251x_is_2510(spi))
 				clear_intf |= CANINTF_RX1IF;
 		}
@@ -1007,6 +1006,10 @@ static const struct of_device_id mcp251x_of_match[] = {
 		.compatible	= "microchip,mcp2515",
 		.data		= (void *)CAN_MCP251X_MCP2515,
 	},
+	{
+		.compatible	= "microchip,mcp25625",
+		.data		= (void *)CAN_MCP251X_MCP25625,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mcp251x_of_match);
@@ -1020,6 +1023,10 @@ static const struct spi_device_id mcp251x_id_table[] = {
 		.name		= "mcp2515",
 		.driver_data	= (kernel_ulong_t)CAN_MCP251X_MCP2515,
 	},
+	{
+		.name		= "mcp25625",
+		.driver_data	= (kernel_ulong_t)CAN_MCP251X_MCP25625,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(spi, mcp251x_id_table);
@@ -1260,5 +1267,5 @@ module_spi_driver(mcp251x_can_driver);
 
 MODULE_AUTHOR("Chris Elston <celston@katalix.com>, "
 	      "Christian Pellegrin <chripell@evolware.org>");
-MODULE_DESCRIPTION("Microchip 251x CAN driver");
+MODULE_DESCRIPTION("Microchip 251x/25625 CAN driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 8aecd8ef6542..15a0850e6bde 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1562,7 +1562,8 @@ static int bnx2x_get_module_info(struct net_device *dev,
 	}
 
 	if (!sff8472_comp ||
-	    (diag_type & SFP_EEPROM_DIAG_ADDR_CHANGE_REQ)) {
+	    (diag_type & SFP_EEPROM_DIAG_ADDR_CHANGE_REQ) ||
+	    !(diag_type & SFP_EEPROM_DDM_IMPLEMENTED)) {
 		modinfo->type = ETH_MODULE_SFF_8079;
 		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
 	} else {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
index b7d251108c19..7115f5025664 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
@@ -62,6 +62,7 @@
 #define SFP_EEPROM_DIAG_TYPE_ADDR		0x5c
 #define SFP_EEPROM_DIAG_TYPE_SIZE		1
 #define SFP_EEPROM_DIAG_ADDR_CHANGE_REQ		(1<<2)
+#define SFP_EEPROM_DDM_IMPLEMENTED		(1<<6)
 #define SFP_EEPROM_SFF_8472_COMP_ADDR		0x5e
 #define SFP_EEPROM_SFF_8472_COMP_SIZE		1
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 345818193de9..56db37d92937 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -898,7 +898,7 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
 			 u64 *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	int status;
+	int status, cnt;
 	u8 link_status = 0;
 
 	if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) {
@@ -909,6 +909,9 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
 
 	memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM);
 
+	/* check link status before offline tests */
+	link_status = netif_carrier_ok(netdev);
+
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
 		if (be_loopback_test(adapter, BE_MAC_LOOPBACK, &data[0]) != 0)
 			test->flags |= ETH_TEST_FL_FAILED;
@@ -929,13 +932,26 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
 		test->flags |= ETH_TEST_FL_FAILED;
 	}
 
-	status = be_cmd_link_status_query(adapter, NULL, &link_status, 0);
-	if (status) {
-		test->flags |= ETH_TEST_FL_FAILED;
-		data[4] = -1;
-	} else if (!link_status) {
+	/* link status was down prior to test */
+	if (!link_status) {
 		test->flags |= ETH_TEST_FL_FAILED;
 		data[4] = 1;
+		return;
+	}
+
+	for (cnt = 10; cnt; cnt--) {
+		status = be_cmd_link_status_query(adapter, NULL, &link_status,
+						  0);
+		if (status) {
+			test->flags |= ETH_TEST_FL_FAILED;
+			data[4] = -1;
+			break;
+		}
+
+		if (link_status)
+			break;
+
+		msleep_interruptible(500);
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 8bbedfc9c48f..a0f97c5ab6ef 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -4212,7 +4212,7 @@ void e1000e_up(struct e1000_adapter *adapter)
 		e1000_configure_msix(adapter);
 	e1000_irq_enable(adapter);
 
-	netif_start_queue(adapter->netdev);
+	/* Tx queue started by watchdog timer when link is up */
 
 	e1000e_trigger_lsc(adapter);
 }
@@ -4588,6 +4588,7 @@ int e1000e_open(struct net_device *netdev)
 	pm_runtime_get_sync(&pdev->dev);
 
 	netif_carrier_off(netdev);
+	netif_stop_queue(netdev);
 
 	/* allocate transmit descriptors */
 	err = e1000e_setup_tx_resources(adapter->tx_ring);
@@ -4648,7 +4649,6 @@ int e1000e_open(struct net_device *netdev)
 	e1000_irq_enable(adapter);
 
 	adapter->tx_hang_recheck = false;
-	netif_start_queue(netdev);
 
 	hw->mac.get_link_status = true;
 	pm_runtime_put(&pdev->dev);
@@ -5271,6 +5271,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			if (phy->ops.cfg_on_link_up)
 				phy->ops.cfg_on_link_up(hw);
 
+			netif_wake_queue(netdev);
 			netif_carrier_on(netdev);
 
 			if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -5284,6 +5285,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* Link status message must follow this format */
 			pr_info("%s NIC Link is Down\n", adapter->netdev->name);
 			netif_carrier_off(netdev);
+			netif_stop_queue(netdev);
 			if (!test_bit(__E1000_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
 					  round_jiffies(jiffies + 2 * HZ));
@@ -5291,13 +5293,8 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* 8000ES2LAN requires a Rx packet buffer work-around
 			 * on link down event; reset the controller to flush
 			 * the Rx packet buffer.
-			 *
-			 * If the link is lost the controller stops DMA, but
-			 * if there is queued Tx work it cannot be done.  So
-			 * reset the controller to flush the Tx packet buffers.
 			 */
-			if ((adapter->flags & FLAG_RX_NEEDS_RESTART) ||
-			    e1000_desc_unused(tx_ring) + 1 < tx_ring->count)
+			if (adapter->flags & FLAG_RX_NEEDS_RESTART)
 				adapter->flags |= FLAG_RESTART_NOW;
 			else
 				pm_schedule_suspend(netdev->dev.parent,
@@ -5320,6 +5317,14 @@ link_up:
 	adapter->gotc_old = adapter->stats.gotc;
 	spin_unlock(&adapter->stats64_lock);
 
+	/* If the link is lost the controller stops DMA, but
+	 * if there is queued Tx work it cannot be done.  So
+	 * reset the controller to flush the Tx packet buffers.
+	 */
+	if (!netif_carrier_ok(netdev) &&
+	    (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
+		adapter->flags |= FLAG_RESTART_NOW;
+
 	/* If reset is necessary, do it outside of interrupt context. */
 	if (adapter->flags & FLAG_RESTART_NOW) {
 		schedule_work(&adapter->reset_task);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index a01e6c0d0cd1..b2a745b579fd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -935,7 +935,7 @@ static inline void mlxsw_reg_spaft_pack(char *payload, u8 local_port,
 	MLXSW_REG_ZERO(spaft, payload);
 	mlxsw_reg_spaft_local_port_set(payload, local_port);
 	mlxsw_reg_spaft_allow_untagged_set(payload, allow_untagged);
-	mlxsw_reg_spaft_allow_prio_tagged_set(payload, true);
+	mlxsw_reg_spaft_allow_prio_tagged_set(payload, allow_untagged);
 	mlxsw_reg_spaft_allow_tagged_set(payload, true);
 }
 
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 6f85276376e8..ae9b983e8e5c 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -1058,7 +1058,7 @@ sis900_open(struct net_device *net_dev)
 	sis900_set_mode(sis_priv, HW_SPEED_10_MBPS, FDX_CAPABLE_HALF_SELECTED);
 
 	/* Enable all known interrupts by setting the interrupt mask. */
-	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE);
+	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE | TxDESC);
 	sw32(cr, RxENA | sr32(cr));
 	sw32(ier, IE);
 
@@ -1581,7 +1581,7 @@ static void sis900_tx_timeout(struct net_device *net_dev)
 	sw32(txdp, sis_priv->tx_ring_dma);
 
 	/* Enable all known interrupts by setting the interrupt mask. */
-	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE);
+	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE | TxDESC);
 }
 
 /**
@@ -1621,7 +1621,7 @@ sis900_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 			spin_unlock_irqrestore(&sis_priv->lock, flags);
 			return NETDEV_TX_OK;
 	}
-	sis_priv->tx_ring[entry].cmdsts = (OWN | skb->len);
+	sis_priv->tx_ring[entry].cmdsts = (OWN | INTR | skb->len);
 	sw32(cr, TxENA | sr32(cr));
 
 	sis_priv->cur_tx ++;
@@ -1677,7 +1677,7 @@ static irqreturn_t sis900_interrupt(int irq, void *dev_instance)
 	do {
 		status = sr32(isr);
 
-		if ((status & (HIBERR|TxURN|TxERR|TxIDLE|RxORN|RxERR|RxOK)) == 0)
+		if ((status & (HIBERR|TxURN|TxERR|TxIDLE|TxDESC|RxORN|RxERR|RxOK)) == 0)
 			/* nothing intresting happened */
 			break;
 		handled = 1;
@@ -1687,7 +1687,7 @@ static irqreturn_t sis900_interrupt(int irq, void *dev_instance)
 			/* Rx interrupt */
 			sis900_rx(net_dev);
 
-		if (status & (TxURN | TxERR | TxIDLE))
+		if (status & (TxURN | TxERR | TxIDLE | TxDESC))
 			/* Tx interrupt */
 			sis900_finish_xmit(net_dev);
 
@@ -1899,8 +1899,8 @@ static void sis900_finish_xmit (struct net_device *net_dev)
 
 		if (tx_status & OWN) {
 			/* The packet is not transmitted yet (owned by hardware) !
-			 * Note: the interrupt is generated only when Tx Machine
-			 * is idle, so this is an almost impossible case */
+			 * Note: this is an almost impossible condition
+			 * in case of TxDESC ('descriptor interrupt') */
 			break;
 		}
 
@@ -2476,7 +2476,7 @@ static int sis900_resume(struct pci_dev *pci_dev)
 	sis900_set_mode(sis_priv, HW_SPEED_10_MBPS, FDX_CAPABLE_HALF_SELECTED);
 
 	/* Enable all known interrupts by setting the interrupt mask. */
-	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE);
+	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE | TxDESC);
 	sw32(cr, RxENA | sr32(cr));
 	sw32(ier, IE);
 
diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c
index f60f7660b451..92f52a73ec0e 100644
--- a/drivers/net/ppp/ppp_mppe.c
+++ b/drivers/net/ppp/ppp_mppe.c
@@ -63,6 +63,7 @@ MODULE_AUTHOR("Frank Cusack <fcusack@fcusack.com>");
 MODULE_DESCRIPTION("Point-to-Point Protocol Microsoft Point-to-Point Encryption support");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("ppp-compress-" __stringify(CI_MPPE));
+MODULE_SOFTDEP("pre: arc4");
 MODULE_VERSION("1.0.2");
 
 static unsigned int
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index 99ab20334d21..37c3cbe0ff2b 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -128,6 +128,8 @@ static struct usb_device_id carl9170_usb_ids[] = {
 };
 MODULE_DEVICE_TABLE(usb, carl9170_usb_ids);
 
+static struct usb_driver carl9170_driver;
+
 static void carl9170_usb_submit_data_urb(struct ar9170 *ar)
 {
 	struct urb *urb;
@@ -966,32 +968,28 @@ err_out:
 
 static void carl9170_usb_firmware_failed(struct ar9170 *ar)
 {
-	struct device *parent = ar->udev->dev.parent;
-	struct usb_device *udev;
-
-	/*
-	 * Store a copy of the usb_device pointer locally.
-	 * This is because device_release_driver initiates
-	 * carl9170_usb_disconnect, which in turn frees our
-	 * driver context (ar).
+	/* Store a copies of the usb_interface and usb_device pointer locally.
+	 * This is because release_driver initiates carl9170_usb_disconnect,
+	 * which in turn frees our driver context (ar).
 	 */
-	udev = ar->udev;
+	struct usb_interface *intf = ar->intf;
+	struct usb_device *udev = ar->udev;
 
 	complete(&ar->fw_load_wait);
+	/* at this point 'ar' could be already freed. Don't use it anymore */
+	ar = NULL;
 
 	/* unbind anything failed */
-	if (parent)
-		device_lock(parent);
-
-	device_release_driver(&udev->dev);
-	if (parent)
-		device_unlock(parent);
+	usb_lock_device(udev);
+	usb_driver_release_interface(&carl9170_driver, intf);
+	usb_unlock_device(udev);
 
-	usb_put_dev(udev);
+	usb_put_intf(intf);
 }
 
 static void carl9170_usb_firmware_finish(struct ar9170 *ar)
 {
+	struct usb_interface *intf = ar->intf;
 	int err;
 
 	err = carl9170_parse_firmware(ar);
@@ -1009,7 +1007,7 @@ static void carl9170_usb_firmware_finish(struct ar9170 *ar)
 		goto err_unrx;
 
 	complete(&ar->fw_load_wait);
-	usb_put_dev(ar->udev);
+	usb_put_intf(intf);
 	return;
 
 err_unrx:
@@ -1052,7 +1050,6 @@ static int carl9170_usb_probe(struct usb_interface *intf,
 		return PTR_ERR(ar);
 
 	udev = interface_to_usbdev(intf);
-	usb_get_dev(udev);
 	ar->udev = udev;
 	ar->intf = intf;
 	ar->features = id->driver_info;
@@ -1094,15 +1091,14 @@ static int carl9170_usb_probe(struct usb_interface *intf,
 	atomic_set(&ar->rx_anch_urbs, 0);
 	atomic_set(&ar->rx_pool_urbs, 0);
 
-	usb_get_dev(ar->udev);
+	usb_get_intf(intf);
 
 	carl9170_set_state(ar, CARL9170_STOPPED);
 
 	err = request_firmware_nowait(THIS_MODULE, 1, CARL9170FW_NAME,
 		&ar->udev->dev, GFP_KERNEL, ar, carl9170_usb_firmware_step2);
 	if (err) {
-		usb_put_dev(udev);
-		usb_put_dev(udev);
+		usb_put_intf(intf);
 		carl9170_free(ar);
 	}
 	return err;
@@ -1131,7 +1127,6 @@ static void carl9170_usb_disconnect(struct usb_interface *intf)
 
 	carl9170_release_firmware(ar);
 	carl9170_free(ar);
-	usb_put_dev(udev);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/net/wireless/intersil/p54/p54usb.c b/drivers/net/wireless/intersil/p54/p54usb.c
index 043bd1c23c19..4a197a32d78c 100644
--- a/drivers/net/wireless/intersil/p54/p54usb.c
+++ b/drivers/net/wireless/intersil/p54/p54usb.c
@@ -33,6 +33,8 @@ MODULE_ALIAS("prism54usb");
 MODULE_FIRMWARE("isl3886usb");
 MODULE_FIRMWARE("isl3887usb");
 
+static struct usb_driver p54u_driver;
+
 /*
  * Note:
  *
@@ -921,9 +923,9 @@ static void p54u_load_firmware_cb(const struct firmware *firmware,
 {
 	struct p54u_priv *priv = context;
 	struct usb_device *udev = priv->udev;
+	struct usb_interface *intf = priv->intf;
 	int err;
 
-	complete(&priv->fw_wait_load);
 	if (firmware) {
 		priv->fw = firmware;
 		err = p54u_start_ops(priv);
@@ -932,26 +934,22 @@ static void p54u_load_firmware_cb(const struct firmware *firmware,
 		dev_err(&udev->dev, "Firmware not found.\n");
 	}
 
-	if (err) {
-		struct device *parent = priv->udev->dev.parent;
-
-		dev_err(&udev->dev, "failed to initialize device (%d)\n", err);
-
-		if (parent)
-			device_lock(parent);
+	complete(&priv->fw_wait_load);
+	/*
+	 * At this point p54u_disconnect may have already freed
+	 * the "priv" context. Do not use it anymore!
+	 */
+	priv = NULL;
 
-		device_release_driver(&udev->dev);
-		/*
-		 * At this point p54u_disconnect has already freed
-		 * the "priv" context. Do not use it anymore!
-		 */
-		priv = NULL;
+	if (err) {
+		dev_err(&intf->dev, "failed to initialize device (%d)\n", err);
 
-		if (parent)
-			device_unlock(parent);
+		usb_lock_device(udev);
+		usb_driver_release_interface(&p54u_driver, intf);
+		usb_unlock_device(udev);
 	}
 
-	usb_put_dev(udev);
+	usb_put_intf(intf);
 }
 
 static int p54u_load_firmware(struct ieee80211_hw *dev,
@@ -972,14 +970,14 @@ static int p54u_load_firmware(struct ieee80211_hw *dev,
 	dev_info(&priv->udev->dev, "Loading firmware file %s\n",
 	       p54u_fwlist[i].fw);
 
-	usb_get_dev(udev);
+	usb_get_intf(intf);
 	err = request_firmware_nowait(THIS_MODULE, 1, p54u_fwlist[i].fw,
 				      device, GFP_KERNEL, priv,
 				      p54u_load_firmware_cb);
 	if (err) {
 		dev_err(&priv->udev->dev, "(p54usb) cannot load firmware %s "
 					  "(%d)!\n", p54u_fwlist[i].fw, err);
-		usb_put_dev(udev);
+		usb_put_intf(intf);
 	}
 
 	return err;
@@ -1011,8 +1009,6 @@ static int p54u_probe(struct usb_interface *intf,
 	skb_queue_head_init(&priv->rx_queue);
 	init_usb_anchor(&priv->submitted);
 
-	usb_get_dev(udev);
-
 	/* really lazy and simple way of figuring out if we're a 3887 */
 	/* TODO: should just stick the identification in the device table */
 	i = intf->altsetting->desc.bNumEndpoints;
@@ -1053,10 +1049,8 @@ static int p54u_probe(struct usb_interface *intf,
 		priv->upload_fw = p54u_upload_firmware_net2280;
 	}
 	err = p54u_load_firmware(dev, intf);
-	if (err) {
-		usb_put_dev(udev);
+	if (err)
 		p54_free_common(dev);
-	}
 	return err;
 }
 
@@ -1072,7 +1066,6 @@ static void p54u_disconnect(struct usb_interface *intf)
 	wait_for_completion(&priv->fw_wait_load);
 	p54_unregister_common(dev);
 
-	usb_put_dev(interface_to_usbdev(intf));
 	release_firmware(priv->fw);
 	p54_free_common(dev);
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 4b1894b4757f..395d6ece2cac 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -1719,9 +1719,10 @@ struct mwifiex_ie_types_wmm_queue_status {
 struct ieee_types_vendor_header {
 	u8 element_id;
 	u8 len;
-	u8 oui[4];	/* 0~2: oui, 3: oui_type */
-	u8 oui_subtype;
-	u8 version;
+	struct {
+		u8 oui[3];
+		u8 oui_type;
+	} __packed oui;
 } __packed;
 
 struct ieee_types_wmm_parameter {
@@ -1735,6 +1736,9 @@ struct ieee_types_wmm_parameter {
 	 *   Version     [1]
 	 */
 	struct ieee_types_vendor_header vend_hdr;
+	u8 oui_subtype;
+	u8 version;
+
 	u8 qos_info_bitmap;
 	u8 reserved;
 	struct ieee_types_wmm_ac_parameters ac_params[IEEE80211_NUM_ACS];
@@ -1752,6 +1756,8 @@ struct ieee_types_wmm_info {
 	 *   Version     [1]
 	 */
 	struct ieee_types_vendor_header vend_hdr;
+	u8 oui_subtype;
+	u8 version;
 
 	u8 qos_info_bitmap;
 } __packed;
diff --git a/drivers/net/wireless/marvell/mwifiex/ie.c b/drivers/net/wireless/marvell/mwifiex/ie.c
index c488c3068abc..0f977dc556ca 100644
--- a/drivers/net/wireless/marvell/mwifiex/ie.c
+++ b/drivers/net/wireless/marvell/mwifiex/ie.c
@@ -328,6 +328,8 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 	struct ieee80211_vendor_ie *vendorhdr;
 	u16 gen_idx = MWIFIEX_AUTO_IDX_MASK, ie_len = 0;
 	int left_len, parsed_len = 0;
+	unsigned int token_len;
+	int err = 0;
 
 	if (!info->tail || !info->tail_len)
 		return 0;
@@ -343,6 +345,12 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 	 */
 	while (left_len > sizeof(struct ieee_types_header)) {
 		hdr = (void *)(info->tail + parsed_len);
+		token_len = hdr->len + sizeof(struct ieee_types_header);
+		if (token_len > left_len) {
+			err = -EINVAL;
+			goto out;
+		}
+
 		switch (hdr->element_id) {
 		case WLAN_EID_SSID:
 		case WLAN_EID_SUPP_RATES:
@@ -356,13 +364,16 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 		case WLAN_EID_VENDOR_SPECIFIC:
 			break;
 		default:
-			memcpy(gen_ie->ie_buffer + ie_len, hdr,
-			       hdr->len + sizeof(struct ieee_types_header));
-			ie_len += hdr->len + sizeof(struct ieee_types_header);
+			if (ie_len + token_len > IEEE_MAX_IE_SIZE) {
+				err = -EINVAL;
+				goto out;
+			}
+			memcpy(gen_ie->ie_buffer + ie_len, hdr, token_len);
+			ie_len += token_len;
 			break;
 		}
-		left_len -= hdr->len + sizeof(struct ieee_types_header);
-		parsed_len += hdr->len + sizeof(struct ieee_types_header);
+		left_len -= token_len;
+		parsed_len += token_len;
 	}
 
 	/* parse only WPA vendor IE from tail, WMM IE is configured by
@@ -372,15 +383,17 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 						    WLAN_OUI_TYPE_MICROSOFT_WPA,
 						    info->tail, info->tail_len);
 	if (vendorhdr) {
-		memcpy(gen_ie->ie_buffer + ie_len, vendorhdr,
-		       vendorhdr->len + sizeof(struct ieee_types_header));
-		ie_len += vendorhdr->len + sizeof(struct ieee_types_header);
+		token_len = vendorhdr->len + sizeof(struct ieee_types_header);
+		if (ie_len + token_len > IEEE_MAX_IE_SIZE) {
+			err = -EINVAL;
+			goto out;
+		}
+		memcpy(gen_ie->ie_buffer + ie_len, vendorhdr, token_len);
+		ie_len += token_len;
 	}
 
-	if (!ie_len) {
-		kfree(gen_ie);
-		return 0;
-	}
+	if (!ie_len)
+		goto out;
 
 	gen_ie->ie_index = cpu_to_le16(gen_idx);
 	gen_ie->mgmt_subtype_mask = cpu_to_le16(MGMT_MASK_BEACON |
@@ -390,13 +403,15 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 
 	if (mwifiex_update_uap_custom_ie(priv, gen_ie, &gen_idx, NULL, NULL,
 					 NULL, NULL)) {
-		kfree(gen_ie);
-		return -1;
+		err = -EINVAL;
+		goto out;
 	}
 
 	priv->gen_idx = gen_idx;
+
+ out:
 	kfree(gen_ie);
-	return 0;
+	return err;
 }
 
 /* This function parses different IEs-head & tail IEs, beacon IEs,
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 78d59a67f7e1..97847eee2dfb 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1236,6 +1236,8 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 		}
 		switch (element_id) {
 		case WLAN_EID_SSID:
+			if (element_len > IEEE80211_MAX_SSID_LEN)
+				return -EINVAL;
 			bss_entry->ssid.ssid_len = element_len;
 			memcpy(bss_entry->ssid.ssid, (current_ptr + 2),
 			       element_len);
@@ -1245,6 +1247,8 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			break;
 
 		case WLAN_EID_SUPP_RATES:
+			if (element_len > MWIFIEX_SUPPORTED_RATES)
+				return -EINVAL;
 			memcpy(bss_entry->data_rates, current_ptr + 2,
 			       element_len);
 			memcpy(bss_entry->supported_rates, current_ptr + 2,
@@ -1254,6 +1258,8 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			break;
 
 		case WLAN_EID_FH_PARAMS:
+			if (element_len + 2 < sizeof(*fh_param_set))
+				return -EINVAL;
 			fh_param_set =
 				(struct ieee_types_fh_param_set *) current_ptr;
 			memcpy(&bss_entry->phy_param_set.fh_param_set,
@@ -1262,6 +1268,8 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			break;
 
 		case WLAN_EID_DS_PARAMS:
+			if (element_len + 2 < sizeof(*ds_param_set))
+				return -EINVAL;
 			ds_param_set =
 				(struct ieee_types_ds_param_set *) current_ptr;
 
@@ -1273,6 +1281,8 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			break;
 
 		case WLAN_EID_CF_PARAMS:
+			if (element_len + 2 < sizeof(*cf_param_set))
+				return -EINVAL;
 			cf_param_set =
 				(struct ieee_types_cf_param_set *) current_ptr;
 			memcpy(&bss_entry->ss_param_set.cf_param_set,
@@ -1281,6 +1291,8 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			break;
 
 		case WLAN_EID_IBSS_PARAMS:
+			if (element_len + 2 < sizeof(*ibss_param_set))
+				return -EINVAL;
 			ibss_param_set =
 				(struct ieee_types_ibss_param_set *)
 				current_ptr;
@@ -1290,10 +1302,14 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			break;
 
 		case WLAN_EID_ERP_INFO:
+			if (!element_len)
+				return -EINVAL;
 			bss_entry->erp_flags = *(current_ptr + 2);
 			break;
 
 		case WLAN_EID_PWR_CONSTRAINT:
+			if (!element_len)
+				return -EINVAL;
 			bss_entry->local_constraint = *(current_ptr + 2);
 			bss_entry->sensed_11h = true;
 			break;
@@ -1336,15 +1352,22 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			vendor_ie = (struct ieee_types_vendor_specific *)
 					current_ptr;
 
-			if (!memcmp
-			    (vendor_ie->vend_hdr.oui, wpa_oui,
-			     sizeof(wpa_oui))) {
+			/* 802.11 requires at least 3-byte OUI. */
+			if (element_len < sizeof(vendor_ie->vend_hdr.oui.oui))
+				return -EINVAL;
+
+			/* Not long enough for a match? Skip it. */
+			if (element_len < sizeof(wpa_oui))
+				break;
+
+			if (!memcmp(&vendor_ie->vend_hdr.oui, wpa_oui,
+				    sizeof(wpa_oui))) {
 				bss_entry->bcn_wpa_ie =
 					(struct ieee_types_vendor_specific *)
 					current_ptr;
 				bss_entry->wpa_offset = (u16)
 					(current_ptr - bss_entry->beacon_buf);
-			} else if (!memcmp(vendor_ie->vend_hdr.oui, wmm_oui,
+			} else if (!memcmp(&vendor_ie->vend_hdr.oui, wmm_oui,
 				    sizeof(wmm_oui))) {
 				if (total_ie_len ==
 				    sizeof(struct ieee_types_wmm_parameter) ||
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 1532ac9cee0b..7f9645703d96 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -1374,7 +1374,7 @@ mwifiex_set_gen_ie_helper(struct mwifiex_private *priv, u8 *ie_data_ptr,
 			/* Test to see if it is a WPA IE, if not, then it is a
 			 * gen IE
 			 */
-			if (!memcmp(pvendor_ie->oui, wpa_oui,
+			if (!memcmp(&pvendor_ie->oui, wpa_oui,
 				    sizeof(wpa_oui))) {
 				find_wpa_ie = 1;
 				break;
@@ -1383,7 +1383,7 @@ mwifiex_set_gen_ie_helper(struct mwifiex_private *priv, u8 *ie_data_ptr,
 			/* Test to see if it is a WPS IE, if so, enable
 			 * wps session flag
 			 */
-			if (!memcmp(pvendor_ie->oui, wps_oui,
+			if (!memcmp(&pvendor_ie->oui, wps_oui,
 				    sizeof(wps_oui))) {
 				priv->wps.session_enable = true;
 				mwifiex_dbg(priv->adapter, MSG,
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index dea2fe671dfe..9843560e784f 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -240,7 +240,7 @@ mwifiex_wmm_setup_queue_priorities(struct mwifiex_private *priv,
 	mwifiex_dbg(priv->adapter, INFO,
 		    "info: WMM Parameter IE: version=%d,\t"
 		    "qos_info Parameter Set Count=%d, Reserved=%#x\n",
-		    wmm_ie->vend_hdr.version, wmm_ie->qos_info_bitmap &
+		    wmm_ie->version, wmm_ie->qos_info_bitmap &
 		    IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK,
 		    wmm_ie->reserved);
 
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index 35286907c636..d0090c5c88e7 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -150,6 +150,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues)
 			return -ENOMEM;
 		}
 		irq_ptr_qs[i] = q;
+		INIT_LIST_HEAD(&q->entry);
 	}
 	return 0;
 }
@@ -178,6 +179,7 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr,
 	q->mask = 1 << (31 - i);
 	q->nr = i;
 	q->handler = handler;
+	INIT_LIST_HEAD(&q->entry);
 }
 
 static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 30e9fbbff051..debe69adfc70 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -80,7 +80,6 @@ void tiqdio_add_input_queues(struct qdio_irq *irq_ptr)
 	mutex_lock(&tiq_list_lock);
 	list_add_rcu(&irq_ptr->input_qs[0]->entry, &tiq_list);
 	mutex_unlock(&tiq_list_lock);
-	xchg(irq_ptr->dsci, 1 << 7);
 }
 
 void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
@@ -88,14 +87,14 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
 	struct qdio_q *q;
 
 	q = irq_ptr->input_qs[0];
-	/* if establish triggered an error */
-	if (!q || !q->entry.prev || !q->entry.next)
+	if (!q)
 		return;
 
 	mutex_lock(&tiq_list_lock);
 	list_del_rcu(&q->entry);
 	mutex_unlock(&tiq_list_lock);
 	synchronize_rcu();
+	INIT_LIST_HEAD(&q->entry);
 }
 
 static inline int has_multiple_inq_on_dsci(struct qdio_irq *irq_ptr)
diff --git a/drivers/staging/comedi/drivers/amplc_pci230.c b/drivers/staging/comedi/drivers/amplc_pci230.c
index 42945de31fe2..d23aa5d8e62a 100644
--- a/drivers/staging/comedi/drivers/amplc_pci230.c
+++ b/drivers/staging/comedi/drivers/amplc_pci230.c
@@ -2337,7 +2337,8 @@ static irqreturn_t pci230_interrupt(int irq, void *d)
 	devpriv->intr_running = false;
 	spin_unlock_irqrestore(&devpriv->isr_spinlock, irqflags);
 
-	comedi_handle_events(dev, s_ao);
+	if (s_ao)
+		comedi_handle_events(dev, s_ao);
 	comedi_handle_events(dev, s_ai);
 
 	return IRQ_HANDLED;
diff --git a/drivers/staging/comedi/drivers/dt282x.c b/drivers/staging/comedi/drivers/dt282x.c
index d5295bbdd28c..37133d54dda1 100644
--- a/drivers/staging/comedi/drivers/dt282x.c
+++ b/drivers/staging/comedi/drivers/dt282x.c
@@ -566,7 +566,8 @@ static irqreturn_t dt282x_interrupt(int irq, void *d)
 	}
 #endif
 	comedi_handle_events(dev, s);
-	comedi_handle_events(dev, s_ao);
+	if (s_ao)
+		comedi_handle_events(dev, s_ao);
 
 	return IRQ_RETVAL(handled);
 }
diff --git a/drivers/staging/iio/cdc/ad7150.c b/drivers/staging/iio/cdc/ad7150.c
index 50a5b0c2cc7b..7ab95efcf1dc 100644
--- a/drivers/staging/iio/cdc/ad7150.c
+++ b/drivers/staging/iio/cdc/ad7150.c
@@ -6,6 +6,7 @@
  * Licensed under the GPL-2 or later.
  */
 
+#include <linux/bitfield.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -129,7 +130,7 @@ static int ad7150_read_event_config(struct iio_dev *indio_dev,
 {
 	int ret;
 	u8 threshtype;
-	bool adaptive;
+	bool thrfixed;
 	struct ad7150_chip_info *chip = iio_priv(indio_dev);
 
 	ret = i2c_smbus_read_byte_data(chip->client, AD7150_CFG);
@@ -137,21 +138,23 @@ static int ad7150_read_event_config(struct iio_dev *indio_dev,
 		return ret;
 
 	threshtype = (ret >> 5) & 0x03;
-	adaptive = !!(ret & 0x80);
+
+	/*check if threshold mode is fixed or adaptive*/
+	thrfixed = FIELD_GET(AD7150_CFG_FIX, ret);
 
 	switch (type) {
 	case IIO_EV_TYPE_MAG_ADAPTIVE:
 		if (dir == IIO_EV_DIR_RISING)
-			return adaptive && (threshtype == 0x1);
-		return adaptive && (threshtype == 0x0);
+			return !thrfixed && (threshtype == 0x1);
+		return !thrfixed && (threshtype == 0x0);
 	case IIO_EV_TYPE_THRESH_ADAPTIVE:
 		if (dir == IIO_EV_DIR_RISING)
-			return adaptive && (threshtype == 0x3);
-		return adaptive && (threshtype == 0x2);
+			return !thrfixed && (threshtype == 0x3);
+		return !thrfixed && (threshtype == 0x2);
 	case IIO_EV_TYPE_THRESH:
 		if (dir == IIO_EV_DIR_RISING)
-			return !adaptive && (threshtype == 0x1);
-		return !adaptive && (threshtype == 0x0);
+			return thrfixed && (threshtype == 0x1);
+		return thrfixed && (threshtype == 0x0);
 	default:
 		break;
 	}
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 5b54439a8a9b..84474f06dbcf 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -1814,8 +1814,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 
 	status = serial_port_in(port, UART_LSR);
 
-	if (status & (UART_LSR_DR | UART_LSR_BI) &&
-	    iir & UART_IIR_RDI) {
+	if (status & (UART_LSR_DR | UART_LSR_BI)) {
 		if (!up->dma || handle_rx_dma(up, iir))
 			status = serial8250_rx_chars(up, status);
 	}
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 5d1bd13a56c1..d5fbc2352029 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -198,11 +198,12 @@ rx_submit(struct eth_dev *dev, struct usb_request *req, gfp_t gfp_flags)
 		out = dev->port_usb->out_ep;
 	else
 		out = NULL;
-	spin_unlock_irqrestore(&dev->lock, flags);
 
 	if (!out)
+	{
+		spin_unlock_irqrestore(&dev->lock, flags);
 		return -ENOTCONN;
-
+	}
 
 	/* Padding up to RX_EXTRA handles minor disagreements with host.
 	 * Normally we use the USB "terminate on short read" convention;
@@ -223,6 +224,7 @@ rx_submit(struct eth_dev *dev, struct usb_request *req, gfp_t gfp_flags)
 
 	if (dev->port_usb->is_fixed)
 		size = max_t(size_t, size, dev->port_usb->fixed_out_len);
+	spin_unlock_irqrestore(&dev->lock, flags);
 
 	skb = alloc_skb(size + NET_IP_ALIGN, gfp_flags);
 	if (skb == NULL) {
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index 968ade5a35f5..696560529e6a 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -821,9 +821,8 @@ static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map)
 }
 
 static void usbhsf_dma_complete(void *arg);
-static void xfer_work(struct work_struct *work)
+static void usbhsf_dma_xfer_preparing(struct usbhs_pkt *pkt)
 {
-	struct usbhs_pkt *pkt = container_of(work, struct usbhs_pkt, work);
 	struct usbhs_pipe *pipe = pkt->pipe;
 	struct usbhs_fifo *fifo;
 	struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
@@ -831,12 +830,10 @@ static void xfer_work(struct work_struct *work)
 	struct dma_chan *chan;
 	struct device *dev = usbhs_priv_to_dev(priv);
 	enum dma_transfer_direction dir;
-	unsigned long flags;
 
-	usbhs_lock(priv, flags);
 	fifo = usbhs_pipe_to_fifo(pipe);
 	if (!fifo)
-		goto xfer_work_end;
+		return;
 
 	chan = usbhsf_dma_chan_get(fifo, pkt);
 	dir = usbhs_pipe_is_dir_in(pipe) ? DMA_DEV_TO_MEM : DMA_MEM_TO_DEV;
@@ -845,7 +842,7 @@ static void xfer_work(struct work_struct *work)
 					pkt->trans, dir,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc)
-		goto xfer_work_end;
+		return;
 
 	desc->callback		= usbhsf_dma_complete;
 	desc->callback_param	= pipe;
@@ -853,7 +850,7 @@ static void xfer_work(struct work_struct *work)
 	pkt->cookie = dmaengine_submit(desc);
 	if (pkt->cookie < 0) {
 		dev_err(dev, "Failed to submit dma descriptor\n");
-		goto xfer_work_end;
+		return;
 	}
 
 	dev_dbg(dev, "  %s %d (%d/ %d)\n",
@@ -864,8 +861,17 @@ static void xfer_work(struct work_struct *work)
 	dma_async_issue_pending(chan);
 	usbhsf_dma_start(pipe, fifo);
 	usbhs_pipe_enable(pipe);
+}
+
+static void xfer_work(struct work_struct *work)
+{
+	struct usbhs_pkt *pkt = container_of(work, struct usbhs_pkt, work);
+	struct usbhs_pipe *pipe = pkt->pipe;
+	struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
+	unsigned long flags;
 
-xfer_work_end:
+	usbhs_lock(priv, flags);
+	usbhsf_dma_xfer_preparing(pkt);
 	usbhs_unlock(priv, flags);
 }
 
@@ -918,8 +924,13 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done)
 	pkt->trans = len;
 
 	usbhsf_tx_irq_ctrl(pipe, 0);
-	INIT_WORK(&pkt->work, xfer_work);
-	schedule_work(&pkt->work);
+	/* FIXME: Workaound for usb dmac that driver can be used in atomic */
+	if (usbhs_get_dparam(priv, has_usb_dmac)) {
+		usbhsf_dma_xfer_preparing(pkt);
+	} else {
+		INIT_WORK(&pkt->work, xfer_work);
+		schedule_work(&pkt->work);
+	}
 
 	return 0;
 
@@ -1025,8 +1036,7 @@ static int usbhsf_dma_prepare_pop_with_usb_dmac(struct usbhs_pkt *pkt,
 
 	pkt->trans = pkt->length;
 
-	INIT_WORK(&pkt->work, xfer_work);
-	schedule_work(&pkt->work);
+	usbhsf_dma_xfer_preparing(pkt);
 
 	return 0;
 
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index f54931aa7528..63ff1a4f2e41 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1024,6 +1024,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) },
 	/* EZPrototypes devices */
 	{ USB_DEVICE(EZPROTOTYPES_VID, HJELMSLUND_USB485_ISO_PID) },
+	{ USB_DEVICE_INTERFACE_NUMBER(UNJO_VID, UNJO_ISODEBUG_V1_PID, 1) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 15d220eaf6e6..ed6b36674c15 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1542,3 +1542,9 @@
 #define CHETCO_SEASMART_DISPLAY_PID	0xA5AD /* SeaSmart NMEA2000 Display */
 #define CHETCO_SEASMART_LITE_PID	0xA5AE /* SeaSmart Lite USB Adapter */
 #define CHETCO_SEASMART_ANALOG_PID	0xA5AF /* SeaSmart Analog Adapter */
+
+/*
+ * Unjo AB
+ */
+#define UNJO_VID			0x22B7
+#define UNJO_ISODEBUG_V1_PID		0x150D
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 1effe74ec638..d7b31fdce94d 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1338,6 +1338,7 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0414, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0417, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_INTERFACE_CLASS(ZTE_VENDOR_ID, 0x0601, 0xff) },	/* GosunCn ZTE WeLink ME3630 (RNDIS mode) */
 	{ USB_DEVICE_INTERFACE_CLASS(ZTE_VENDOR_ID, 0x0602, 0xff) },	/* GosunCn ZTE WeLink ME3630 (MBIM mode) */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1008, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(4) },
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index c160d2d0e18d..57a97b38a2fa 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -114,6 +114,8 @@ int fscrypt_process_policy(struct file *filp,
 	if (!inode_has_encryption_context(inode)) {
 		if (!S_ISDIR(inode->i_mode))
 			ret = -ENOTDIR;
+		else if (IS_DEADDIR(inode))
+			ret = -ENOENT;
 		else if (!inode->i_sb->s_cop->empty_dir)
 			ret = -EOPNOTSUPP;
 		else if (!inode->i_sb->s_cop->empty_dir(inode))
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index fd817022cb9b..9e66d85021fc 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -478,13 +478,15 @@ static struct buffer_head *udf_getblk(struct inode *inode, long block,
 	return NULL;
 }
 
-/* Extend the file by 'blocks' blocks, return the number of extents added */
+/* Extend the file with new blocks totaling 'new_block_bytes',
+ * return the number of extents added
+ */
 static int udf_do_extend_file(struct inode *inode,
 			      struct extent_position *last_pos,
 			      struct kernel_long_ad *last_ext,
-			      sector_t blocks)
+			      loff_t new_block_bytes)
 {
-	sector_t add;
+	uint32_t add;
 	int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
 	struct super_block *sb = inode->i_sb;
 	struct kernel_lb_addr prealloc_loc = {};
@@ -494,7 +496,7 @@ static int udf_do_extend_file(struct inode *inode,
 
 	/* The previous extent is fake and we should not extend by anything
 	 * - there's nothing to do... */
-	if (!blocks && fake)
+	if (!new_block_bytes && fake)
 		return 0;
 
 	iinfo = UDF_I(inode);
@@ -525,13 +527,12 @@ static int udf_do_extend_file(struct inode *inode,
 	/* Can we merge with the previous extent? */
 	if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) ==
 					EXT_NOT_RECORDED_NOT_ALLOCATED) {
-		add = ((1 << 30) - sb->s_blocksize -
-			(last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) >>
-			sb->s_blocksize_bits;
-		if (add > blocks)
-			add = blocks;
-		blocks -= add;
-		last_ext->extLength += add << sb->s_blocksize_bits;
+		add = (1 << 30) - sb->s_blocksize -
+			(last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
+		if (add > new_block_bytes)
+			add = new_block_bytes;
+		new_block_bytes -= add;
+		last_ext->extLength += add;
 	}
 
 	if (fake) {
@@ -552,28 +553,27 @@ static int udf_do_extend_file(struct inode *inode,
 	}
 
 	/* Managed to do everything necessary? */
-	if (!blocks)
+	if (!new_block_bytes)
 		goto out;
 
 	/* All further extents will be NOT_RECORDED_NOT_ALLOCATED */
 	last_ext->extLocation.logicalBlockNum = 0;
 	last_ext->extLocation.partitionReferenceNum = 0;
-	add = (1 << (30-sb->s_blocksize_bits)) - 1;
-	last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
-				(add << sb->s_blocksize_bits);
+	add = (1 << 30) - sb->s_blocksize;
+	last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | add;
 
 	/* Create enough extents to cover the whole hole */
-	while (blocks > add) {
-		blocks -= add;
+	while (new_block_bytes > add) {
+		new_block_bytes -= add;
 		err = udf_add_aext(inode, last_pos, &last_ext->extLocation,
 				   last_ext->extLength, 1);
 		if (err)
 			return err;
 		count++;
 	}
-	if (blocks) {
+	if (new_block_bytes) {
 		last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
-			(blocks << sb->s_blocksize_bits);
+			new_block_bytes;
 		err = udf_add_aext(inode, last_pos, &last_ext->extLocation,
 				   last_ext->extLength, 1);
 		if (err)
@@ -604,6 +604,24 @@ out:
 	return count;
 }
 
+/* Extend the final block of the file to final_block_len bytes */
+static void udf_do_extend_final_block(struct inode *inode,
+				      struct extent_position *last_pos,
+				      struct kernel_long_ad *last_ext,
+				      uint32_t final_block_len)
+{
+	struct super_block *sb = inode->i_sb;
+	uint32_t added_bytes;
+
+	added_bytes = final_block_len -
+		      (last_ext->extLength & (sb->s_blocksize - 1));
+	last_ext->extLength += added_bytes;
+	UDF_I(inode)->i_lenExtents += added_bytes;
+
+	udf_write_aext(inode, last_pos, &last_ext->extLocation,
+			last_ext->extLength, 1);
+}
+
 static int udf_extend_file(struct inode *inode, loff_t newsize)
 {
 
@@ -613,10 +631,12 @@ static int udf_extend_file(struct inode *inode, loff_t newsize)
 	int8_t etype;
 	struct super_block *sb = inode->i_sb;
 	sector_t first_block = newsize >> sb->s_blocksize_bits, offset;
+	unsigned long partial_final_block;
 	int adsize;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 	struct kernel_long_ad extent;
-	int err;
+	int err = 0;
+	int within_final_block;
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
 		adsize = sizeof(struct short_ad);
@@ -626,18 +646,8 @@ static int udf_extend_file(struct inode *inode, loff_t newsize)
 		BUG();
 
 	etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset);
+	within_final_block = (etype != -1);
 
-	/* File has extent covering the new size (could happen when extending
-	 * inside a block)? */
-	if (etype != -1)
-		return 0;
-	if (newsize & (sb->s_blocksize - 1))
-		offset++;
-	/* Extended file just to the boundary of the last file block? */
-	if (offset == 0)
-		return 0;
-
-	/* Truncate is extending the file by 'offset' blocks */
 	if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) ||
 	    (epos.bh && epos.offset == sizeof(struct allocExtDesc))) {
 		/* File has no extents at all or has empty last
@@ -651,7 +661,22 @@ static int udf_extend_file(struct inode *inode, loff_t newsize)
 				      &extent.extLength, 0);
 		extent.extLength |= etype << 30;
 	}
-	err = udf_do_extend_file(inode, &epos, &extent, offset);
+
+	partial_final_block = newsize & (sb->s_blocksize - 1);
+
+	/* File has extent covering the new size (could happen when extending
+	 * inside a block)?
+	 */
+	if (within_final_block) {
+		/* Extending file within the last file block */
+		udf_do_extend_final_block(inode, &epos, &extent,
+					  partial_final_block);
+	} else {
+		loff_t add = ((loff_t)offset << sb->s_blocksize_bits) |
+			     partial_final_block;
+		err = udf_do_extend_file(inode, &epos, &extent, add);
+	}
+
 	if (err < 0)
 		goto out;
 	err = 0;
@@ -756,6 +781,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 	/* Are we beyond EOF? */
 	if (etype == -1) {
 		int ret;
+		loff_t hole_len;
 		isBeyondEOF = true;
 		if (count) {
 			if (c)
@@ -771,7 +797,8 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 			startnum = (offset > 0);
 		}
 		/* Create extents for the hole between EOF and offset */
-		ret = udf_do_extend_file(inode, &prev_epos, laarr, offset);
+		hole_len = (loff_t)offset << inode->i_blkbits;
+		ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len);
 		if (ret < 0) {
 			brelse(prev_epos.bh);
 			brelse(cur_epos.bh);
diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h
index 1bd31a38c51e..ce13d4677f1d 100644
--- a/include/linux/vmw_vmci_defs.h
+++ b/include/linux/vmw_vmci_defs.h
@@ -75,9 +75,18 @@ enum {
 
 /*
  * A single VMCI device has an upper limit of 128MB on the amount of
- * memory that can be used for queue pairs.
+ * memory that can be used for queue pairs. Since each queue pair
+ * consists of at least two pages, the memory limit also dictates the
+ * number of queue pairs a guest can create.
  */
 #define VMCI_MAX_GUEST_QP_MEMORY (128 * 1024 * 1024)
+#define VMCI_MAX_GUEST_QP_COUNT  (VMCI_MAX_GUEST_QP_MEMORY / PAGE_SIZE / 2)
+
+/*
+ * There can be at most PAGE_SIZE doorbells since there is one doorbell
+ * per byte in the doorbell bitmap page.
+ */
+#define VMCI_MAX_GUEST_DOORBELL_COUNT PAGE_SIZE
 
 /*
  * Queues with pre-mapped data pages must be small, so that we don't pin
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 1b1cf33cbfb0..2b6abd046087 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -149,9 +149,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 	pkt_len = skb->len - skb_inner_network_offset(skb);
 	err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
-	if (unlikely(net_xmit_eval(err)))
-		pkt_len = -1;
-	iptunnel_xmit_stats(dev, pkt_len);
+
+	if (dev) {
+		if (unlikely(net_xmit_eval(err)))
+			pkt_len = -1;
+		iptunnel_xmit_stats(dev, pkt_len);
+	}
 }
 #endif
 #endif
diff --git a/include/uapi/linux/nilfs2_ondisk.h b/include/uapi/linux/nilfs2_ondisk.h
index 2a8a3addb675..f9b6b5be7ddf 100644
--- a/include/uapi/linux/nilfs2_ondisk.h
+++ b/include/uapi/linux/nilfs2_ondisk.h
@@ -28,7 +28,7 @@
 
 #include <linux/types.h>
 #include <linux/magic.h>
-
+#include <asm/byteorder.h>
 
 #define NILFS_INODE_BMAP_SIZE	7
 
@@ -532,19 +532,19 @@ enum {
 static inline void							\
 nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp)		\
 {									\
-	cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) |		\
-				   (1UL << NILFS_CHECKPOINT_##flag));	\
+	cp->cp_flags = __cpu_to_le32(__le32_to_cpu(cp->cp_flags) |	\
+				     (1UL << NILFS_CHECKPOINT_##flag));	\
 }									\
 static inline void							\
 nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp)		\
 {									\
-	cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) &		\
+	cp->cp_flags = __cpu_to_le32(__le32_to_cpu(cp->cp_flags) &	\
 				   ~(1UL << NILFS_CHECKPOINT_##flag));	\
 }									\
 static inline int							\
 nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp)		\
 {									\
-	return !!(le32_to_cpu(cp->cp_flags) &				\
+	return !!(__le32_to_cpu(cp->cp_flags) &				\
 		  (1UL << NILFS_CHECKPOINT_##flag));			\
 }
 
@@ -594,20 +594,20 @@ enum {
 static inline void							\
 nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su)		\
 {									\
-	su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) |		\
+	su->su_flags = __cpu_to_le32(__le32_to_cpu(su->su_flags) |	\
 				   (1UL << NILFS_SEGMENT_USAGE_##flag));\
 }									\
 static inline void							\
 nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su)	\
 {									\
 	su->su_flags =							\
-		cpu_to_le32(le32_to_cpu(su->su_flags) &			\
+		__cpu_to_le32(__le32_to_cpu(su->su_flags) &		\
 			    ~(1UL << NILFS_SEGMENT_USAGE_##flag));      \
 }									\
 static inline int							\
 nilfs_segment_usage_##name(const struct nilfs_segment_usage *su)	\
 {									\
-	return !!(le32_to_cpu(su->su_flags) &				\
+	return !!(__le32_to_cpu(su->su_flags) &				\
 		  (1UL << NILFS_SEGMENT_USAGE_##flag));			\
 }
 
@@ -618,15 +618,15 @@ NILFS_SEGMENT_USAGE_FNS(ERROR, error)
 static inline void
 nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su)
 {
-	su->su_lastmod = cpu_to_le64(0);
-	su->su_nblocks = cpu_to_le32(0);
-	su->su_flags = cpu_to_le32(0);
+	su->su_lastmod = __cpu_to_le64(0);
+	su->su_nblocks = __cpu_to_le32(0);
+	su->su_flags = __cpu_to_le32(0);
 }
 
 static inline int
 nilfs_segment_usage_clean(const struct nilfs_segment_usage *su)
 {
-	return !le32_to_cpu(su->su_flags);
+	return !__le32_to_cpu(su->su_flags);
 }
 
 /**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7929526e96e2..93d7333c64d8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5492,7 +5492,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
-	} else if (current->mm) {
+	} else if (!(current->flags & PF_KTHREAD)) {
 		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 1e1fa99b3243..0b53d1907e4a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -264,8 +264,14 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 
 	prev = fq->q.fragments_tail;
 	err = inet_frag_queue_insert(&fq->q, skb, offset, end);
-	if (err)
+	if (err) {
+		if (err == IPFRAG_DUP) {
+			/* No error for duplicates, pretend they got queued. */
+			kfree_skb(skb);
+			return -EINPROGRESS;
+		}
 		goto insert_error;
+	}
 
 	if (dev)
 		fq->iif = dev->ifindex;
@@ -292,15 +298,17 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 		skb->_skb_refdst = 0UL;
 		err = nf_ct_frag6_reasm(fq, skb, prev, dev);
 		skb->_skb_refdst = orefdst;
-		return err;
+
+		/* After queue has assumed skb ownership, only 0 or
+		 * -EINPROGRESS must be returned.
+		 */
+		return err ? -EINPROGRESS : 0;
 	}
 
 	skb_dst_drop(skb);
 	return -EINPROGRESS;
 
 insert_error:
-	if (err == IPFRAG_DUP)
-		goto err;
 	inet_frag_kill(&fq->q);
 err:
 	skb_dst_drop(skb);
@@ -480,12 +488,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 		ret = 0;
 	}
 
-	/* after queue has assumed skb ownership, only 0 or -EINPROGRESS
-	 * must be returned.
-	 */
-	if (ret)
-		ret = -EINPROGRESS;
-
 	spin_unlock_bh(&fq->q.lock);
 	inet_frag_put(&fq->q);
 	return ret;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 8a690ebd7374..6708de10a3e5 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1403,7 +1403,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata)
 	rcu_read_lock();
 	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 
-	if (WARN_ON(!chanctx_conf)) {
+	if (WARN_ON_ONCE(!chanctx_conf)) {
 		rcu_read_unlock();
 		return NULL;
 	}
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index b2a27263d6ff..5c347d3a92c9 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -885,6 +885,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata)
 
 	/* flush STAs and mpaths on this iface */
 	sta_info_flush(sdata);
+	ieee80211_free_keys(sdata, true);
 	mesh_path_flush_by_iface(sdata);
 
 	/* stop the beacon */
@@ -1135,7 +1136,8 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
 	ifmsh->chsw_ttl = 0;
 
 	/* Remove the CSA and MCSP elements from the beacon */
-	tmp_csa_settings = rcu_dereference(ifmsh->csa);
+	tmp_csa_settings = rcu_dereference_protected(ifmsh->csa,
+					    lockdep_is_held(&sdata->wdev.mtx));
 	RCU_INIT_POINTER(ifmsh->csa, NULL);
 	if (tmp_csa_settings)
 		kfree_rcu(tmp_csa_settings, rcu_head);
@@ -1157,6 +1159,8 @@ int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	struct mesh_csa_settings *tmp_csa_settings;
 	int ret = 0;
 
+	lockdep_assert_held(&sdata->wdev.mtx);
+
 	tmp_csa_settings = kmalloc(sizeof(*tmp_csa_settings),
 				   GFP_ATOMIC);
 	if (!tmp_csa_settings)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 244eac1bd648..de18a463ac96 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2718,6 +2718,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt,
 	xprt = xprt_iter_xprt(&clnt->cl_xpi);
 	if (xps == NULL || xprt == NULL) {
 		rcu_read_unlock();
+		xprt_switch_put(xps);
 		return -EAGAIN;
 	}
 	resvport = xprt->resvport;
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 97913e109b14..99e5a2f63e76 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -369,7 +369,7 @@ void read_trace_pipe(void)
 		static char buf[4096];
 		ssize_t sz;
 
-		sz = read(trace_fd, buf, sizeof(buf));
+		sz = read(trace_fd, buf, sizeof(buf) - 1);
 		if (sz > 0) {
 			buf[sz] = 0;
 			puts(buf);
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 1ebbf233de9a..6d64b2cb02ab 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -1466,6 +1466,7 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev)
 	mutex_unlock(&its->its_lock);
 
 	kfree(its);
+	kfree(kvm_dev);/* alloc by kvm_ioctl_create_device, free by .destroy */
 }
 
 static int vgic_its_has_attr(struct kvm_device *dev,