Adding upstream version 6.6.15.upstream/6.6.15

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

27 files changed, 4763 insertions, 0 deletions

diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
new file mode 100644
index 0000000000..29490be254
--- /dev/null
+++ b/arch/arm64/lib/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0
+lib-y		:= clear_user.o delay.o copy_from_user.o		\
+		   copy_to_user.o copy_page.o				\
+		   clear_page.o csum.o insn.o memchr.o memcpy.o		\
+		   memset.o memcmp.o strcmp.o strncmp.o strlen.o	\
+		   strnlen.o strchr.o strrchr.o tishift.o
+
+ifeq ($(CONFIG_KERNEL_MODE_NEON), y)
+obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
+CFLAGS_REMOVE_xor-neon.o	+= -mgeneral-regs-only
+CFLAGS_xor-neon.o		+= -ffreestanding
+# Enable <arm_neon.h>
+CFLAGS_xor-neon.o		+= -isystem $(shell $(CC) -print-file-name=include)
+endif
+
+lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
+
+obj-$(CONFIG_CRC32) += crc32.o
+
+obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+
+obj-$(CONFIG_ARM64_MTE) += mte.o
+
+obj-$(CONFIG_KASAN_SW_TAGS) += kasan_sw_tags.o
diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S
new file mode 100644
index 0000000000..ebde40e7fa
--- /dev/null
+++ b/arch/arm64/lib/clear_page.S
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#include <linux/linkage.h>
+#include <linux/const.h>
+#include <asm/assembler.h>
+#include <asm/page.h>
+
+/*
+ * Clear page @dest
+ *
+ * Parameters:
+ *	x0 - dest
+ */
+SYM_FUNC_START(__pi_clear_page)
+	mrs	x1, dczid_el0
+	tbnz	x1, #4, 2f	/* Branch if DC ZVA is prohibited */
+	and	w1, w1, #0xf
+	mov	x2, #4
+	lsl	x1, x2, x1
+
+1:	dc	zva, x0
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+
+2:	stnp	xzr, xzr, [x0]
+	stnp	xzr, xzr, [x0, #16]
+	stnp	xzr, xzr, [x0, #32]
+	stnp	xzr, xzr, [x0, #48]
+	add	x0, x0, #64
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	2b
+	ret
+SYM_FUNC_END(__pi_clear_page)
+SYM_FUNC_ALIAS(clear_page, __pi_clear_page)
+EXPORT_SYMBOL(clear_page)
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
new file mode 100644
index 0000000000..a5a5f5b97b
--- /dev/null
+++ b/arch/arm64/lib/clear_user.S
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Arm Ltd.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-uaccess.h>
+
+	.text
+
+/* Prototype: int __arch_clear_user(void *addr, size_t sz)
+ * Purpose  : clear some user memory
+ * Params   : addr - user memory address to clear
+ *          : sz   - number of bytes to clear
+ * Returns  : number of bytes NOT cleared
+ *
+ * Alignment fixed up by hardware.
+ */
+
+	.p2align 4
+	// Alignment is for the loop, but since the prologue (including BTI)
+	// is also 16 bytes we can keep any padding outside the function
+SYM_FUNC_START(__arch_clear_user)
+	add	x2, x0, x1
+	subs	x1, x1, #8
+	b.mi	2f
+1:
+USER(9f, sttr	xzr, [x0])
+	add	x0, x0, #8
+	subs	x1, x1, #8
+	b.hi	1b
+USER(9f, sttr	xzr, [x2, #-8])
+	mov	x0, #0
+	ret
+
+2:	tbz	x1, #2, 3f
+USER(9f, sttr	wzr, [x0])
+USER(8f, sttr	wzr, [x2, #-4])
+	mov	x0, #0
+	ret
+
+3:	tbz	x1, #1, 4f
+USER(9f, sttrh	wzr, [x0])
+4:	tbz	x1, #0, 5f
+USER(7f, sttrb	wzr, [x2, #-1])
+5:	mov	x0, #0
+	ret
+
+	// Exception fixups
+7:	sub	x0, x2, #5	// Adjust for faulting on the final byte...
+8:	add	x0, x0, #4	// ...or the second word of the 4-7 byte case
+9:	sub	x0, x2, x0
+	ret
+SYM_FUNC_END(__arch_clear_user)
+EXPORT_SYMBOL(__arch_clear_user)
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
new file mode 100644
index 0000000000..34e3179075
--- /dev/null
+++ b/arch/arm64/lib/copy_from_user.S
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+/*
+ * Copy from user space to a kernel buffer (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - to
+ *	x1 - from
+ *	x2 - n
+ * Returns:
+ *	x0 - bytes not copied
+ */
+
+	.macro ldrb1 reg, ptr, val
+	user_ldst 9998f, ldtrb, \reg, \ptr, \val
+	.endm
+
+	.macro strb1 reg, ptr, val
+	strb \reg, [\ptr], \val
+	.endm
+
+	.macro ldrh1 reg, ptr, val
+	user_ldst 9997f, ldtrh, \reg, \ptr, \val
+	.endm
+
+	.macro strh1 reg, ptr, val
+	strh \reg, [\ptr], \val
+	.endm
+
+	.macro ldr1 reg, ptr, val
+	user_ldst 9997f, ldtr, \reg, \ptr, \val
+	.endm
+
+	.macro str1 reg, ptr, val
+	str \reg, [\ptr], \val
+	.endm
+
+	.macro ldp1 reg1, reg2, ptr, val
+	user_ldp 9997f, \reg1, \reg2, \ptr, \val
+	.endm
+
+	.macro stp1 reg1, reg2, ptr, val
+	stp \reg1, \reg2, [\ptr], \val
+	.endm
+
+end	.req	x5
+srcin	.req	x15
+SYM_FUNC_START(__arch_copy_from_user)
+	add	end, x0, x2
+	mov	srcin, x1
+#include "copy_template.S"
+	mov	x0, #0				// Nothing to copy
+	ret
+
+	// Exception fixups
+9997:	cmp	dst, dstin
+	b.ne	9998f
+	// Before being absolutely sure we couldn't copy anything, try harder
+USER(9998f, ldtrb tmp1w, [srcin])
+	strb	tmp1w, [dst], #1
+9998:	sub	x0, end, dst			// bytes not copied
+	ret
+SYM_FUNC_END(__arch_copy_from_user)
+EXPORT_SYMBOL(__arch_copy_from_user)
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
new file mode 100644
index 0000000000..c336d2ffde
--- /dev/null
+++ b/arch/arm64/lib/copy_page.S
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#include <linux/linkage.h>
+#include <linux/const.h>
+#include <asm/assembler.h>
+#include <asm/page.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
+
+/*
+ * Copy a page from src to dest (both are page aligned)
+ *
+ * Parameters:
+ *	x0 - dest
+ *	x1 - src
+ */
+SYM_FUNC_START(__pi_copy_page)
+alternative_if ARM64_HAS_NO_HW_PREFETCH
+	// Prefetch three cache lines ahead.
+	prfm	pldl1strm, [x1, #128]
+	prfm	pldl1strm, [x1, #256]
+	prfm	pldl1strm, [x1, #384]
+alternative_else_nop_endif
+
+	ldp	x2, x3, [x1]
+	ldp	x4, x5, [x1, #16]
+	ldp	x6, x7, [x1, #32]
+	ldp	x8, x9, [x1, #48]
+	ldp	x10, x11, [x1, #64]
+	ldp	x12, x13, [x1, #80]
+	ldp	x14, x15, [x1, #96]
+	ldp	x16, x17, [x1, #112]
+
+	add	x0, x0, #256
+	add	x1, x1, #128
+1:
+	tst	x0, #(PAGE_SIZE - 1)
+
+alternative_if ARM64_HAS_NO_HW_PREFETCH
+	prfm	pldl1strm, [x1, #384]
+alternative_else_nop_endif
+
+	stnp	x2, x3, [x0, #-256]
+	ldp	x2, x3, [x1]
+	stnp	x4, x5, [x0, #16 - 256]
+	ldp	x4, x5, [x1, #16]
+	stnp	x6, x7, [x0, #32 - 256]
+	ldp	x6, x7, [x1, #32]
+	stnp	x8, x9, [x0, #48 - 256]
+	ldp	x8, x9, [x1, #48]
+	stnp	x10, x11, [x0, #64 - 256]
+	ldp	x10, x11, [x1, #64]
+	stnp	x12, x13, [x0, #80 - 256]
+	ldp	x12, x13, [x1, #80]
+	stnp	x14, x15, [x0, #96 - 256]
+	ldp	x14, x15, [x1, #96]
+	stnp	x16, x17, [x0, #112 - 256]
+	ldp	x16, x17, [x1, #112]
+
+	add	x0, x0, #128
+	add	x1, x1, #128
+
+	b.ne	1b
+
+	stnp	x2, x3, [x0, #-256]
+	stnp	x4, x5, [x0, #16 - 256]
+	stnp	x6, x7, [x0, #32 - 256]
+	stnp	x8, x9, [x0, #48 - 256]
+	stnp	x10, x11, [x0, #64 - 256]
+	stnp	x12, x13, [x0, #80 - 256]
+	stnp	x14, x15, [x0, #96 - 256]
+	stnp	x16, x17, [x0, #112 - 256]
+
+	ret
+SYM_FUNC_END(__pi_copy_page)
+SYM_FUNC_ALIAS(copy_page, __pi_copy_page)
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/arm64/lib/copy_template.S b/arch/arm64/lib/copy_template.S
new file mode 100644
index 0000000000..488df234c4
--- /dev/null
+++ b/arch/arm64/lib/copy_template.S
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ */
+
+
+/*
+ * Copy a buffer from src to dest (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - dest
+ *	x1 - src
+ *	x2 - n
+ * Returns:
+ *	x0 - dest
+ */
+dstin	.req	x0
+src	.req	x1
+count	.req	x2
+tmp1	.req	x3
+tmp1w	.req	w3
+tmp2	.req	x4
+tmp2w	.req	w4
+dst	.req	x6
+
+A_l	.req	x7
+A_h	.req	x8
+B_l	.req	x9
+B_h	.req	x10
+C_l	.req	x11
+C_h	.req	x12
+D_l	.req	x13
+D_h	.req	x14
+
+	mov	dst, dstin
+	cmp	count, #16
+	/*When memory length is less than 16, the accessed are not aligned.*/
+	b.lo	.Ltiny15
+
+	neg	tmp2, src
+	ands	tmp2, tmp2, #15/* Bytes to reach alignment. */
+	b.eq	.LSrcAligned
+	sub	count, count, tmp2
+	/*
+	* Copy the leading memory data from src to dst in an increasing
+	* address order.By this way,the risk of overwriting the source
+	* memory data is eliminated when the distance between src and
+	* dst is less than 16. The memory accesses here are alignment.
+	*/
+	tbz	tmp2, #0, 1f
+	ldrb1	tmp1w, src, #1
+	strb1	tmp1w, dst, #1
+1:
+	tbz	tmp2, #1, 2f
+	ldrh1	tmp1w, src, #2
+	strh1	tmp1w, dst, #2
+2:
+	tbz	tmp2, #2, 3f
+	ldr1	tmp1w, src, #4
+	str1	tmp1w, dst, #4
+3:
+	tbz	tmp2, #3, .LSrcAligned
+	ldr1	tmp1, src, #8
+	str1	tmp1, dst, #8
+
+.LSrcAligned:
+	cmp	count, #64
+	b.ge	.Lcpy_over64
+	/*
+	* Deal with small copies quickly by dropping straight into the
+	* exit block.
+	*/
+.Ltail63:
+	/*
+	* Copy up to 48 bytes of data. At this point we only need the
+	* bottom 6 bits of count to be accurate.
+	*/
+	ands	tmp1, count, #0x30
+	b.eq	.Ltiny15
+	cmp	tmp1w, #0x20
+	b.eq	1f
+	b.lt	2f
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+1:
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+2:
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+.Ltiny15:
+	/*
+	* Prefer to break one ldp/stp into several load/store to access
+	* memory in an increasing address order,rather than to load/store 16
+	* bytes from (src-16) to (dst-16) and to backward the src to aligned
+	* address,which way is used in original cortex memcpy. If keeping
+	* the original memcpy process here, memmove need to satisfy the
+	* precondition that src address is at least 16 bytes bigger than dst
+	* address,otherwise some source data will be overwritten when memove
+	* call memcpy directly. To make memmove simpler and decouple the
+	* memcpy's dependency on memmove, withdrew the original process.
+	*/
+	tbz	count, #3, 1f
+	ldr1	tmp1, src, #8
+	str1	tmp1, dst, #8
+1:
+	tbz	count, #2, 2f
+	ldr1	tmp1w, src, #4
+	str1	tmp1w, dst, #4
+2:
+	tbz	count, #1, 3f
+	ldrh1	tmp1w, src, #2
+	strh1	tmp1w, dst, #2
+3:
+	tbz	count, #0, .Lexitfunc
+	ldrb1	tmp1w, src, #1
+	strb1	tmp1w, dst, #1
+
+	b	.Lexitfunc
+
+.Lcpy_over64:
+	subs	count, count, #128
+	b.ge	.Lcpy_body_large
+	/*
+	* Less than 128 bytes to copy, so handle 64 here and then jump
+	* to the tail.
+	*/
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+	ldp1	B_l, B_h, src, #16
+	ldp1	C_l, C_h, src, #16
+	stp1	B_l, B_h, dst, #16
+	stp1	C_l, C_h, dst, #16
+	ldp1	D_l, D_h, src, #16
+	stp1	D_l, D_h, dst, #16
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+	b	.Lexitfunc
+
+	/*
+	* Critical loop.  Start at a new cache line boundary.  Assuming
+	* 64 bytes per line this ensures the entire loop is in one line.
+	*/
+	.p2align	L1_CACHE_SHIFT
+.Lcpy_body_large:
+	/* pre-get 64 bytes data. */
+	ldp1	A_l, A_h, src, #16
+	ldp1	B_l, B_h, src, #16
+	ldp1	C_l, C_h, src, #16
+	ldp1	D_l, D_h, src, #16
+1:
+	/*
+	* interlace the load of next 64 bytes data block with store of the last
+	* loaded 64 bytes data.
+	*/
+	stp1	A_l, A_h, dst, #16
+	ldp1	A_l, A_h, src, #16
+	stp1	B_l, B_h, dst, #16
+	ldp1	B_l, B_h, src, #16
+	stp1	C_l, C_h, dst, #16
+	ldp1	C_l, C_h, src, #16
+	stp1	D_l, D_h, dst, #16
+	ldp1	D_l, D_h, src, #16
+	subs	count, count, #64
+	b.ge	1b
+	stp1	A_l, A_h, dst, #16
+	stp1	B_l, B_h, dst, #16
+	stp1	C_l, C_h, dst, #16
+	stp1	D_l, D_h, dst, #16
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+.Lexitfunc:
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
new file mode 100644
index 0000000000..8022317726
--- /dev/null
+++ b/arch/arm64/lib/copy_to_user.S
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+/*
+ * Copy to user space from a kernel buffer (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - to
+ *	x1 - from
+ *	x2 - n
+ * Returns:
+ *	x0 - bytes not copied
+ */
+	.macro ldrb1 reg, ptr, val
+	ldrb  \reg, [\ptr], \val
+	.endm
+
+	.macro strb1 reg, ptr, val
+	user_ldst 9998f, sttrb, \reg, \ptr, \val
+	.endm
+
+	.macro ldrh1 reg, ptr, val
+	ldrh  \reg, [\ptr], \val
+	.endm
+
+	.macro strh1 reg, ptr, val
+	user_ldst 9997f, sttrh, \reg, \ptr, \val
+	.endm
+
+	.macro ldr1 reg, ptr, val
+	ldr \reg, [\ptr], \val
+	.endm
+
+	.macro str1 reg, ptr, val
+	user_ldst 9997f, sttr, \reg, \ptr, \val
+	.endm
+
+	.macro ldp1 reg1, reg2, ptr, val
+	ldp \reg1, \reg2, [\ptr], \val
+	.endm
+
+	.macro stp1 reg1, reg2, ptr, val
+	user_stp 9997f, \reg1, \reg2, \ptr, \val
+	.endm
+
+end	.req	x5
+srcin	.req	x15
+SYM_FUNC_START(__arch_copy_to_user)
+	add	end, x0, x2
+	mov	srcin, x1
+#include "copy_template.S"
+	mov	x0, #0
+	ret
+
+	// Exception fixups
+9997:	cmp	dst, dstin
+	b.ne	9998f
+	// Before being absolutely sure we couldn't copy anything, try harder
+	ldrb	tmp1w, [srcin]
+USER(9998f, sttrb tmp1w, [dst])
+	add	dst, dst, #1
+9998:	sub	x0, end, dst			// bytes not copied
+	ret
+SYM_FUNC_END(__arch_copy_to_user)
+EXPORT_SYMBOL(__arch_copy_to_user)
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
new file mode 100644
index 0000000000..8340dccff4
--- /dev/null
+++ b/arch/arm64/lib/crc32.S
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Accelerated CRC32(C) using AArch64 CRC instructions
+ *
+ * Copyright (C) 2016 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative.h>
+#include <asm/assembler.h>
+
+	.arch		armv8-a+crc
+
+	.macro		byteorder, reg, be
+	.if		\be
+CPU_LE( rev		\reg, \reg	)
+	.else
+CPU_BE( rev		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		byteorder16, reg, be
+	.if		\be
+CPU_LE( rev16		\reg, \reg	)
+	.else
+CPU_BE( rev16		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		bitorder, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	.endif
+	.endm
+
+	.macro		bitorder16, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #16
+	.endif
+	.endm
+
+	.macro		bitorder8, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #24
+	.endif
+	.endm
+
+	.macro		__crc32, c, be=0
+	bitorder	w0, \be
+	cmp		x2, #16
+	b.lt		8f			// less than 16 bytes
+
+	and		x7, x2, #0x1f
+	and		x2, x2, #~0x1f
+	cbz		x7, 32f			// multiple of 32 bytes
+
+	and		x8, x7, #0xf
+	ldp		x3, x4, [x1]
+	add		x8, x8, x1
+	add		x1, x1, x7
+	ldp		x5, x6, [x8]
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
+
+	tst		x7, #8
+	crc32\c\()x	w8, w0, x3
+	csel		x3, x3, x4, eq
+	csel		w0, w0, w8, eq
+	tst		x7, #4
+	lsr		x4, x3, #32
+	crc32\c\()w	w8, w0, w3
+	csel		x3, x3, x4, eq
+	csel		w0, w0, w8, eq
+	tst		x7, #2
+	lsr		w4, w3, #16
+	crc32\c\()h	w8, w0, w3
+	csel		w3, w3, w4, eq
+	csel		w0, w0, w8, eq
+	tst		x7, #1
+	crc32\c\()b	w8, w0, w3
+	csel		w0, w0, w8, eq
+	tst		x7, #16
+	crc32\c\()x	w8, w0, x5
+	crc32\c\()x	w8, w8, x6
+	csel		w0, w0, w8, eq
+	cbz		x2, 0f
+
+32:	ldp		x3, x4, [x1], #32
+	sub		x2, x2, #32
+	ldp		x5, x6, [x1, #-16]
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
+	crc32\c\()x	w0, w0, x3
+	crc32\c\()x	w0, w0, x4
+	crc32\c\()x	w0, w0, x5
+	crc32\c\()x	w0, w0, x6
+	cbnz		x2, 32b
+0:	bitorder	w0, \be
+	ret
+
+8:	tbz		x2, #3, 4f
+	ldr		x3, [x1], #8
+	byteorder	x3, \be
+	bitorder	x3, \be
+	crc32\c\()x	w0, w0, x3
+4:	tbz		x2, #2, 2f
+	ldr		w3, [x1], #4
+	byteorder	w3, \be
+	bitorder	w3, \be
+	crc32\c\()w	w0, w0, w3
+2:	tbz		x2, #1, 1f
+	ldrh		w3, [x1], #2
+	byteorder16	w3, \be
+	bitorder16	w3, \be
+	crc32\c\()h	w0, w0, w3
+1:	tbz		x2, #0, 0f
+	ldrb		w3, [x1]
+	bitorder8	w3, \be
+	crc32\c\()b	w0, w0, w3
+0:	bitorder	w0, \be
+	ret
+	.endm
+
+	.align		5
+SYM_FUNC_START(crc32_le)
+alternative_if_not ARM64_HAS_CRC32
+	b		crc32_le_base
+alternative_else_nop_endif
+	__crc32
+SYM_FUNC_END(crc32_le)
+
+	.align		5
+SYM_FUNC_START(__crc32c_le)
+alternative_if_not ARM64_HAS_CRC32
+	b		__crc32c_le_base
+alternative_else_nop_endif
+	__crc32		c
+SYM_FUNC_END(__crc32c_le)
+
+	.align		5
+SYM_FUNC_START(crc32_be)
+alternative_if_not ARM64_HAS_CRC32
+	b		crc32_be_base
+alternative_else_nop_endif
+	__crc32		be=1
+SYM_FUNC_END(crc32_be)
diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
new file mode 100644
index 0000000000..2432683e48
--- /dev/null
+++ b/arch/arm64/lib/csum.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 Arm Ltd.
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <net/checksum.h>
+
+/* Looks dumb, but generates nice-ish code */
+static u64 accumulate(u64 sum, u64 data)
+{
+	__uint128_t tmp = (__uint128_t)sum + data;
+	return tmp + (tmp >> 64);
+}
+
+/*
+ * We over-read the buffer and this makes KASAN unhappy. Instead, disable
+ * instrumentation and call kasan explicitly.
+ */
+unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift, sum;
+	const u64 *ptr;
+	u64 data, sum64 = 0;
+
+	if (unlikely(len <= 0))
+		return 0;
+
+	offset = (unsigned long)buff & 7;
+	/*
+	 * This is to all intents and purposes safe, since rounding down cannot
+	 * result in a different page or cache line being accessed, and @buff
+	 * should absolutely not be pointing to anything read-sensitive. We do,
+	 * however, have to be careful not to piss off KASAN, which means using
+	 * unchecked reads to accommodate the head and tail, for which we'll
+	 * compensate with an explicit check up-front.
+	 */
+	kasan_check_read(buff, len);
+	ptr = (u64 *)(buff - offset);
+	len = len + offset - 8;
+
+	/*
+	 * Head: zero out any excess leading bytes. Shifting back by the same
+	 * amount should be at least as fast as any other way of handling the
+	 * odd/even alignment, and means we can ignore it until the very end.
+	 */
+	shift = offset * 8;
+	data = *ptr++;
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+
+	/*
+	 * Body: straightforward aligned loads from here on (the paired loads
+	 * underlying the quadword type still only need dword alignment). The
+	 * main loop strictly excludes the tail, so the second loop will always
+	 * run at least once.
+	 */
+	while (unlikely(len > 64)) {
+		__uint128_t tmp1, tmp2, tmp3, tmp4;
+
+		tmp1 = *(__uint128_t *)ptr;
+		tmp2 = *(__uint128_t *)(ptr + 2);
+		tmp3 = *(__uint128_t *)(ptr + 4);
+		tmp4 = *(__uint128_t *)(ptr + 6);
+
+		len -= 64;
+		ptr += 8;
+
+		/* This is the "don't dump the carry flag into a GPR" idiom */
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp2 += (tmp2 >> 64) | (tmp2 << 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp4 += (tmp4 >> 64) | (tmp4 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | sum64;
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		sum64 = tmp1 >> 64;
+	}
+	while (len > 8) {
+		__uint128_t tmp;
+
+		sum64 = accumulate(sum64, data);
+		tmp = *(__uint128_t *)ptr;
+
+		len -= 16;
+		ptr += 2;
+
+#ifdef __LITTLE_ENDIAN
+		data = tmp >> 64;
+		sum64 = accumulate(sum64, tmp);
+#else
+		data = tmp;
+		sum64 = accumulate(sum64, tmp >> 64);
+#endif
+	}
+	if (len > 0) {
+		sum64 = accumulate(sum64, data);
+		data = *ptr;
+		len -= 8;
+	}
+	/*
+	 * Tail: zero any over-read bytes similarly to the head, again
+	 * preserving odd/even alignment.
+	 */
+	shift = len * -8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	sum64 = accumulate(sum64, data);
+
+	/* Finally, folding */
+	sum64 += (sum64 >> 32) | (sum64 << 32);
+	sum = sum64 >> 32;
+	sum += (sum >> 16) | (sum << 16);
+	if (offset & 1)
+		return (u16)swab32(sum);
+
+	return sum >> 16;
+}
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum csum)
+{
+	__uint128_t src, dst;
+	u64 sum = (__force u64)csum;
+
+	src = *(const __uint128_t *)saddr->s6_addr;
+	dst = *(const __uint128_t *)daddr->s6_addr;
+
+	sum += (__force u32)htonl(len);
+#ifdef __LITTLE_ENDIAN
+	sum += (u32)proto << 24;
+#else
+	sum += proto;
+#endif
+	src += (src >> 64) | (src << 64);
+	dst += (dst >> 64) | (dst << 64);
+
+	sum = accumulate(sum, src >> 64);
+	sum = accumulate(sum, dst >> 64);
+
+	sum += ((sum >> 32) | (sum << 32));
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
new file mode 100644
index 0000000000..5b7890139b
--- /dev/null
+++ b/arch/arm64/lib/delay.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Delay loops based on the OpenRISC implementation.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/timex.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#define USECS_TO_CYCLES(time_usecs)			\
+	xloops_to_cycles((time_usecs) * 0x10C7UL)
+
+static inline unsigned long xloops_to_cycles(unsigned long xloops)
+{
+	return (xloops * loops_per_jiffy * HZ) >> 32;
+}
+
+void __delay(unsigned long cycles)
+{
+	cycles_t start = get_cycles();
+
+	if (cpus_have_const_cap(ARM64_HAS_WFXT)) {
+		u64 end = start + cycles;
+
+		/*
+		 * Start with WFIT. If an interrupt makes us resume
+		 * early, use a WFET loop to complete the delay.
+		 */
+		wfit(end);
+		while ((get_cycles() - start) < cycles)
+			wfet(end);
+	} else 	if (arch_timer_evtstrm_available()) {
+		const cycles_t timer_evt_period =
+			USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US);
+
+		while ((get_cycles() - start + timer_evt_period) < cycles)
+			wfe();
+	}
+
+	while ((get_cycles() - start) < cycles)
+		cpu_relax();
+}
+EXPORT_SYMBOL(__delay);
+
+inline void __const_udelay(unsigned long xloops)
+{
+	__delay(xloops_to_cycles(xloops));
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/arm64/lib/error-inject.c b/arch/arm64/lib/error-inject.c
new file mode 100644
index 0000000000..ed15021da3
--- /dev/null
+++ b/arch/arm64/lib/error-inject.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+
+void override_function_with_return(struct pt_regs *regs)
+{
+	/*
+	 * 'regs' represents the state on entry of a predefined function in
+	 * the kernel/module and which is captured on a kprobe.
+	 *
+	 * When kprobe returns back from exception it will override the end
+	 * of probed function and directly return to the predefined
+	 * function's caller.
+	 */
+	instruction_pointer_set(regs, procedure_link_pointer(regs));
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c
new file mode 100644
index 0000000000..a635ab83fe
--- /dev/null
+++ b/arch/arm64/lib/insn.c
@@ -0,0 +1,1517 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
+ */
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/printk.h>
+#include <linux/sizes.h>
+#include <linux/types.h>
+
+#include <asm/debug-monitors.h>
+#include <asm/errno.h>
+#include <asm/insn.h>
+#include <asm/kprobes.h>
+
+#define AARCH64_INSN_SF_BIT	BIT(31)
+#define AARCH64_INSN_N_BIT	BIT(22)
+#define AARCH64_INSN_LSL_12	BIT(22)
+
+static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type,
+						u32 *maskp, int *shiftp)
+{
+	u32 mask;
+	int shift;
+
+	switch (type) {
+	case AARCH64_INSN_IMM_26:
+		mask = BIT(26) - 1;
+		shift = 0;
+		break;
+	case AARCH64_INSN_IMM_19:
+		mask = BIT(19) - 1;
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_16:
+		mask = BIT(16) - 1;
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_14:
+		mask = BIT(14) - 1;
+		shift = 5;
+		break;
+	case AARCH64_INSN_IMM_12:
+		mask = BIT(12) - 1;
+		shift = 10;
+		break;
+	case AARCH64_INSN_IMM_9:
+		mask = BIT(9) - 1;
+		shift = 12;
+		break;
+	case AARCH64_INSN_IMM_7:
+		mask = BIT(7) - 1;
+		shift = 15;
+		break;
+	case AARCH64_INSN_IMM_6:
+	case AARCH64_INSN_IMM_S:
+		mask = BIT(6) - 1;
+		shift = 10;
+		break;
+	case AARCH64_INSN_IMM_R:
+		mask = BIT(6) - 1;
+		shift = 16;
+		break;
+	case AARCH64_INSN_IMM_N:
+		mask = 1;
+		shift = 22;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*maskp = mask;
+	*shiftp = shift;
+
+	return 0;
+}
+
+#define ADR_IMM_HILOSPLIT	2
+#define ADR_IMM_SIZE		SZ_2M
+#define ADR_IMM_LOMASK		((1 << ADR_IMM_HILOSPLIT) - 1)
+#define ADR_IMM_HIMASK		((ADR_IMM_SIZE >> ADR_IMM_HILOSPLIT) - 1)
+#define ADR_IMM_LOSHIFT		29
+#define ADR_IMM_HISHIFT		5
+
+u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn)
+{
+	u32 immlo, immhi, mask;
+	int shift;
+
+	switch (type) {
+	case AARCH64_INSN_IMM_ADR:
+		shift = 0;
+		immlo = (insn >> ADR_IMM_LOSHIFT) & ADR_IMM_LOMASK;
+		immhi = (insn >> ADR_IMM_HISHIFT) & ADR_IMM_HIMASK;
+		insn = (immhi << ADR_IMM_HILOSPLIT) | immlo;
+		mask = ADR_IMM_SIZE - 1;
+		break;
+	default:
+		if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) {
+			pr_err("%s: unknown immediate encoding %d\n", __func__,
+			       type);
+			return 0;
+		}
+	}
+
+	return (insn >> shift) & mask;
+}
+
+u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
+				  u32 insn, u64 imm)
+{
+	u32 immlo, immhi, mask;
+	int shift;
+
+	if (insn == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
+
+	switch (type) {
+	case AARCH64_INSN_IMM_ADR:
+		shift = 0;
+		immlo = (imm & ADR_IMM_LOMASK) << ADR_IMM_LOSHIFT;
+		imm >>= ADR_IMM_HILOSPLIT;
+		immhi = (imm & ADR_IMM_HIMASK) << ADR_IMM_HISHIFT;
+		imm = immlo | immhi;
+		mask = ((ADR_IMM_LOMASK << ADR_IMM_LOSHIFT) |
+			(ADR_IMM_HIMASK << ADR_IMM_HISHIFT));
+		break;
+	default:
+		if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) {
+			pr_err("%s: unknown immediate encoding %d\n", __func__,
+			       type);
+			return AARCH64_BREAK_FAULT;
+		}
+	}
+
+	/* Update the immediate field. */
+	insn &= ~(mask << shift);
+	insn |= (imm & mask) << shift;
+
+	return insn;
+}
+
+u32 aarch64_insn_decode_register(enum aarch64_insn_register_type type,
+					u32 insn)
+{
+	int shift;
+
+	switch (type) {
+	case AARCH64_INSN_REGTYPE_RT:
+	case AARCH64_INSN_REGTYPE_RD:
+		shift = 0;
+		break;
+	case AARCH64_INSN_REGTYPE_RN:
+		shift = 5;
+		break;
+	case AARCH64_INSN_REGTYPE_RT2:
+	case AARCH64_INSN_REGTYPE_RA:
+		shift = 10;
+		break;
+	case AARCH64_INSN_REGTYPE_RM:
+		shift = 16;
+		break;
+	default:
+		pr_err("%s: unknown register type encoding %d\n", __func__,
+		       type);
+		return 0;
+	}
+
+	return (insn >> shift) & GENMASK(4, 0);
+}
+
+static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type,
+					u32 insn,
+					enum aarch64_insn_register reg)
+{
+	int shift;
+
+	if (insn == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
+
+	if (reg < AARCH64_INSN_REG_0 || reg > AARCH64_INSN_REG_SP) {
+		pr_err("%s: unknown register encoding %d\n", __func__, reg);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (type) {
+	case AARCH64_INSN_REGTYPE_RT:
+	case AARCH64_INSN_REGTYPE_RD:
+		shift = 0;
+		break;
+	case AARCH64_INSN_REGTYPE_RN:
+		shift = 5;
+		break;
+	case AARCH64_INSN_REGTYPE_RT2:
+	case AARCH64_INSN_REGTYPE_RA:
+		shift = 10;
+		break;
+	case AARCH64_INSN_REGTYPE_RM:
+	case AARCH64_INSN_REGTYPE_RS:
+		shift = 16;
+		break;
+	default:
+		pr_err("%s: unknown register type encoding %d\n", __func__,
+		       type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn &= ~(GENMASK(4, 0) << shift);
+	insn |= reg << shift;
+
+	return insn;
+}
+
+static const u32 aarch64_insn_ldst_size[] = {
+	[AARCH64_INSN_SIZE_8] = 0,
+	[AARCH64_INSN_SIZE_16] = 1,
+	[AARCH64_INSN_SIZE_32] = 2,
+	[AARCH64_INSN_SIZE_64] = 3,
+};
+
+static u32 aarch64_insn_encode_ldst_size(enum aarch64_insn_size_type type,
+					 u32 insn)
+{
+	u32 size;
+
+	if (type < AARCH64_INSN_SIZE_8 || type > AARCH64_INSN_SIZE_64) {
+		pr_err("%s: unknown size encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	size = aarch64_insn_ldst_size[type];
+	insn &= ~GENMASK(31, 30);
+	insn |= size << 30;
+
+	return insn;
+}
+
+static inline long label_imm_common(unsigned long pc, unsigned long addr,
+				     long range)
+{
+	long offset;
+
+	if ((pc & 0x3) || (addr & 0x3)) {
+		pr_err("%s: A64 instructions must be word aligned\n", __func__);
+		return range;
+	}
+
+	offset = ((long)addr - (long)pc);
+
+	if (offset < -range || offset >= range) {
+		pr_err("%s: offset out of range\n", __func__);
+		return range;
+	}
+
+	return offset;
+}
+
+u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+					  enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+	long offset;
+
+	/*
+	 * B/BL support [-128M, 128M) offset
+	 * ARM64 virtual address arrangement guarantees all kernel and module
+	 * texts are within +/-128M.
+	 */
+	offset = label_imm_common(pc, addr, SZ_128M);
+	if (offset >= SZ_128M)
+		return AARCH64_BREAK_FAULT;
+
+	switch (type) {
+	case AARCH64_INSN_BRANCH_LINK:
+		insn = aarch64_insn_get_bl_value();
+		break;
+	case AARCH64_INSN_BRANCH_NOLINK:
+		insn = aarch64_insn_get_b_value();
+		break;
+	default:
+		pr_err("%s: unknown branch encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+					     offset >> 2);
+}
+
+u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_register reg,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+	long offset;
+
+	offset = label_imm_common(pc, addr, SZ_1M);
+	if (offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
+
+	switch (type) {
+	case AARCH64_INSN_BRANCH_COMP_ZERO:
+		insn = aarch64_insn_get_cbz_value();
+		break;
+	case AARCH64_INSN_BRANCH_COMP_NONZERO:
+		insn = aarch64_insn_get_cbnz_value();
+		break;
+	default:
+		pr_err("%s: unknown branch encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+					     offset >> 2);
+}
+
+u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_condition cond)
+{
+	u32 insn;
+	long offset;
+
+	offset = label_imm_common(pc, addr, SZ_1M);
+
+	insn = aarch64_insn_get_bcond_value();
+
+	if (cond < AARCH64_INSN_COND_EQ || cond > AARCH64_INSN_COND_AL) {
+		pr_err("%s: unknown condition encoding %d\n", __func__, cond);
+		return AARCH64_BREAK_FAULT;
+	}
+	insn |= cond;
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+					     offset >> 2);
+}
+
+u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
+				enum aarch64_insn_branch_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_BRANCH_NOLINK:
+		insn = aarch64_insn_get_br_value();
+		break;
+	case AARCH64_INSN_BRANCH_LINK:
+		insn = aarch64_insn_get_blr_value();
+		break;
+	case AARCH64_INSN_BRANCH_RETURN:
+		insn = aarch64_insn_get_ret_value();
+		break;
+	default:
+		pr_err("%s: unknown branch encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, reg);
+}
+
+u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
+				    enum aarch64_insn_register base,
+				    enum aarch64_insn_register offset,
+				    enum aarch64_insn_size_type size,
+				    enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_REG_OFFSET:
+		insn = aarch64_insn_get_ldr_reg_value();
+		break;
+	case AARCH64_INSN_LDST_SIGNED_LOAD_REG_OFFSET:
+		insn = aarch64_insn_get_signed_ldr_reg_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_REG_OFFSET:
+		insn = aarch64_insn_get_str_reg_value();
+		break;
+	default:
+		pr_err("%s: unknown load/store encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn,
+					    offset);
+}
+
+u32 aarch64_insn_gen_load_store_imm(enum aarch64_insn_register reg,
+				    enum aarch64_insn_register base,
+				    unsigned int imm,
+				    enum aarch64_insn_size_type size,
+				    enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+	u32 shift;
+
+	if (size < AARCH64_INSN_SIZE_8 || size > AARCH64_INSN_SIZE_64) {
+		pr_err("%s: unknown size encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	shift = aarch64_insn_ldst_size[size];
+	if (imm & ~(BIT(12 + shift) - BIT(shift))) {
+		pr_err("%s: invalid imm: %d\n", __func__, imm);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	imm >>= shift;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_IMM_OFFSET:
+		insn = aarch64_insn_get_ldr_imm_value();
+		break;
+	case AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET:
+		insn = aarch64_insn_get_signed_load_imm_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_IMM_OFFSET:
+		insn = aarch64_insn_get_str_imm_value();
+		break;
+	default:
+		pr_err("%s: unknown load/store encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, imm);
+}
+
+u32 aarch64_insn_gen_load_literal(unsigned long pc, unsigned long addr,
+				  enum aarch64_insn_register reg,
+				  bool is64bit)
+{
+	u32 insn;
+	long offset;
+
+	offset = label_imm_common(pc, addr, SZ_1M);
+	if (offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
+
+	insn = aarch64_insn_get_ldr_lit_value();
+
+	if (is64bit)
+		insn |= BIT(30);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+					     offset >> 2);
+}
+
+u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
+				     enum aarch64_insn_register reg2,
+				     enum aarch64_insn_register base,
+				     int offset,
+				     enum aarch64_insn_variant variant,
+				     enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+	int shift;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX:
+		insn = aarch64_insn_get_ldp_pre_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX:
+		insn = aarch64_insn_get_stp_pre_value();
+		break;
+	case AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX:
+		insn = aarch64_insn_get_ldp_post_value();
+		break;
+	case AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX:
+		insn = aarch64_insn_get_stp_post_value();
+		break;
+	default:
+		pr_err("%s: unknown load/store encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if ((offset & 0x3) || (offset < -256) || (offset > 252)) {
+			pr_err("%s: offset must be multiples of 4 in the range of [-256, 252] %d\n",
+			       __func__, offset);
+			return AARCH64_BREAK_FAULT;
+		}
+		shift = 2;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		if ((offset & 0x7) || (offset < -512) || (offset > 504)) {
+			pr_err("%s: offset must be multiples of 8 in the range of [-512, 504] %d\n",
+			       __func__, offset);
+			return AARCH64_BREAK_FAULT;
+		}
+		shift = 3;
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg1);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn,
+					    reg2);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_7, insn,
+					     offset >> shift);
+}
+
+u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
+				   enum aarch64_insn_register base,
+				   enum aarch64_insn_register state,
+				   enum aarch64_insn_size_type size,
+				   enum aarch64_insn_ldst_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LDST_LOAD_EX:
+	case AARCH64_INSN_LDST_LOAD_ACQ_EX:
+		insn = aarch64_insn_get_load_ex_value();
+		if (type == AARCH64_INSN_LDST_LOAD_ACQ_EX)
+			insn |= BIT(15);
+		break;
+	case AARCH64_INSN_LDST_STORE_EX:
+	case AARCH64_INSN_LDST_STORE_REL_EX:
+		insn = aarch64_insn_get_store_ex_value();
+		if (type == AARCH64_INSN_LDST_STORE_REL_EX)
+			insn |= BIT(15);
+		break;
+	default:
+		pr_err("%s: unknown load/store exclusive encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    reg);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    base);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn,
+					    AARCH64_INSN_REG_ZR);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+					    state);
+}
+
+#ifdef CONFIG_ARM64_LSE_ATOMICS
+static u32 aarch64_insn_encode_ldst_order(enum aarch64_insn_mem_order_type type,
+					  u32 insn)
+{
+	u32 order;
+
+	switch (type) {
+	case AARCH64_INSN_MEM_ORDER_NONE:
+		order = 0;
+		break;
+	case AARCH64_INSN_MEM_ORDER_ACQ:
+		order = 2;
+		break;
+	case AARCH64_INSN_MEM_ORDER_REL:
+		order = 1;
+		break;
+	case AARCH64_INSN_MEM_ORDER_ACQREL:
+		order = 3;
+		break;
+	default:
+		pr_err("%s: unknown mem order %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn &= ~GENMASK(23, 22);
+	insn |= order << 22;
+
+	return insn;
+}
+
+u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result,
+				  enum aarch64_insn_register address,
+				  enum aarch64_insn_register value,
+				  enum aarch64_insn_size_type size,
+				  enum aarch64_insn_mem_atomic_op op,
+				  enum aarch64_insn_mem_order_type order)
+{
+	u32 insn;
+
+	switch (op) {
+	case AARCH64_INSN_MEM_ATOMIC_ADD:
+		insn = aarch64_insn_get_ldadd_value();
+		break;
+	case AARCH64_INSN_MEM_ATOMIC_CLR:
+		insn = aarch64_insn_get_ldclr_value();
+		break;
+	case AARCH64_INSN_MEM_ATOMIC_EOR:
+		insn = aarch64_insn_get_ldeor_value();
+		break;
+	case AARCH64_INSN_MEM_ATOMIC_SET:
+		insn = aarch64_insn_get_ldset_value();
+		break;
+	case AARCH64_INSN_MEM_ATOMIC_SWP:
+		insn = aarch64_insn_get_swp_value();
+		break;
+	default:
+		pr_err("%s: unimplemented mem atomic op %d\n", __func__, op);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (size) {
+	case AARCH64_INSN_SIZE_32:
+	case AARCH64_INSN_SIZE_64:
+		break;
+	default:
+		pr_err("%s: unimplemented size encoding %d\n", __func__, size);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_ldst_order(order, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    result);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    address);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+					    value);
+}
+
+static u32 aarch64_insn_encode_cas_order(enum aarch64_insn_mem_order_type type,
+					 u32 insn)
+{
+	u32 order;
+
+	switch (type) {
+	case AARCH64_INSN_MEM_ORDER_NONE:
+		order = 0;
+		break;
+	case AARCH64_INSN_MEM_ORDER_ACQ:
+		order = BIT(22);
+		break;
+	case AARCH64_INSN_MEM_ORDER_REL:
+		order = BIT(15);
+		break;
+	case AARCH64_INSN_MEM_ORDER_ACQREL:
+		order = BIT(15) | BIT(22);
+		break;
+	default:
+		pr_err("%s: unknown mem order %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn &= ~(BIT(15) | BIT(22));
+	insn |= order;
+
+	return insn;
+}
+
+u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
+			 enum aarch64_insn_register address,
+			 enum aarch64_insn_register value,
+			 enum aarch64_insn_size_type size,
+			 enum aarch64_insn_mem_order_type order)
+{
+	u32 insn;
+
+	switch (size) {
+	case AARCH64_INSN_SIZE_32:
+	case AARCH64_INSN_SIZE_64:
+		break;
+	default:
+		pr_err("%s: unimplemented size encoding %d\n", __func__, size);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_get_cas_value();
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_cas_order(order, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    result);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    address);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+					    value);
+}
+#endif
+
+u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
+				 enum aarch64_insn_register src,
+				 int imm, enum aarch64_insn_variant variant,
+				 enum aarch64_insn_adsb_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_ADSB_ADD:
+		insn = aarch64_insn_get_add_imm_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB:
+		insn = aarch64_insn_get_sub_imm_value();
+		break;
+	case AARCH64_INSN_ADSB_ADD_SETFLAGS:
+		insn = aarch64_insn_get_adds_imm_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB_SETFLAGS:
+		insn = aarch64_insn_get_subs_imm_value();
+		break;
+	default:
+		pr_err("%s: unknown add/sub encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	/* We can't encode more than a 24bit value (12bit + 12bit shift) */
+	if (imm & ~(BIT(24) - 1))
+		goto out;
+
+	/* If we have something in the top 12 bits... */
+	if (imm & ~(SZ_4K - 1)) {
+		/* ... and in the low 12 bits -> error */
+		if (imm & (SZ_4K - 1))
+			goto out;
+
+		imm >>= 12;
+		insn |= AARCH64_INSN_LSL_12;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, imm);
+
+out:
+	pr_err("%s: invalid immediate encoding %d\n", __func__, imm);
+	return AARCH64_BREAK_FAULT;
+}
+
+u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      int immr, int imms,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_bitfield_type type)
+{
+	u32 insn;
+	u32 mask;
+
+	switch (type) {
+	case AARCH64_INSN_BITFIELD_MOVE:
+		insn = aarch64_insn_get_bfm_value();
+		break;
+	case AARCH64_INSN_BITFIELD_MOVE_UNSIGNED:
+		insn = aarch64_insn_get_ubfm_value();
+		break;
+	case AARCH64_INSN_BITFIELD_MOVE_SIGNED:
+		insn = aarch64_insn_get_sbfm_value();
+		break;
+	default:
+		pr_err("%s: unknown bitfield encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		mask = GENMASK(4, 0);
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT | AARCH64_INSN_N_BIT;
+		mask = GENMASK(5, 0);
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	if (immr & ~mask) {
+		pr_err("%s: invalid immr encoding %d\n", __func__, immr);
+		return AARCH64_BREAK_FAULT;
+	}
+	if (imms & ~mask) {
+		pr_err("%s: invalid imms encoding %d\n", __func__, imms);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms);
+}
+
+u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst,
+			      int imm, int shift,
+			      enum aarch64_insn_variant variant,
+			      enum aarch64_insn_movewide_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_MOVEWIDE_ZERO:
+		insn = aarch64_insn_get_movz_value();
+		break;
+	case AARCH64_INSN_MOVEWIDE_KEEP:
+		insn = aarch64_insn_get_movk_value();
+		break;
+	case AARCH64_INSN_MOVEWIDE_INVERSE:
+		insn = aarch64_insn_get_movn_value();
+		break;
+	default:
+		pr_err("%s: unknown movewide encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	if (imm & ~(SZ_64K - 1)) {
+		pr_err("%s: invalid immediate encoding %d\n", __func__, imm);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (shift != 0 && shift != 16) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		if (shift != 0 && shift != 16 && shift != 32 && shift != 48) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn |= (shift >> 4) << 21;
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm);
+}
+
+u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_adsb_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_ADSB_ADD:
+		insn = aarch64_insn_get_add_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB:
+		insn = aarch64_insn_get_sub_value();
+		break;
+	case AARCH64_INSN_ADSB_ADD_SETFLAGS:
+		insn = aarch64_insn_get_adds_value();
+		break;
+	case AARCH64_INSN_ADSB_SUB_SETFLAGS:
+		insn = aarch64_insn_get_subs_value();
+		break;
+	default:
+		pr_err("%s: unknown add/sub encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (shift & ~(SZ_32 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		if (shift & ~(SZ_64 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
+}
+
+u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data1_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_DATA1_REVERSE_16:
+		insn = aarch64_insn_get_rev16_value();
+		break;
+	case AARCH64_INSN_DATA1_REVERSE_32:
+		insn = aarch64_insn_get_rev32_value();
+		break;
+	case AARCH64_INSN_DATA1_REVERSE_64:
+		if (variant != AARCH64_INSN_VARIANT_64BIT) {
+			pr_err("%s: invalid variant for reverse64 %d\n",
+			       __func__, variant);
+			return AARCH64_BREAK_FAULT;
+		}
+		insn = aarch64_insn_get_rev64_value();
+		break;
+	default:
+		pr_err("%s: unknown data1 encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+}
+
+u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data2_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_DATA2_UDIV:
+		insn = aarch64_insn_get_udiv_value();
+		break;
+	case AARCH64_INSN_DATA2_SDIV:
+		insn = aarch64_insn_get_sdiv_value();
+		break;
+	case AARCH64_INSN_DATA2_LSLV:
+		insn = aarch64_insn_get_lslv_value();
+		break;
+	case AARCH64_INSN_DATA2_LSRV:
+		insn = aarch64_insn_get_lsrv_value();
+		break;
+	case AARCH64_INSN_DATA2_ASRV:
+		insn = aarch64_insn_get_asrv_value();
+		break;
+	case AARCH64_INSN_DATA2_RORV:
+		insn = aarch64_insn_get_rorv_value();
+		break;
+	default:
+		pr_err("%s: unknown data2 encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg);
+}
+
+u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst,
+			   enum aarch64_insn_register src,
+			   enum aarch64_insn_register reg1,
+			   enum aarch64_insn_register reg2,
+			   enum aarch64_insn_variant variant,
+			   enum aarch64_insn_data3_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_DATA3_MADD:
+		insn = aarch64_insn_get_madd_value();
+		break;
+	case AARCH64_INSN_DATA3_MSUB:
+		insn = aarch64_insn_get_msub_value();
+		break;
+	default:
+		pr_err("%s: unknown data3 encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RA, insn, src);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    reg1);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn,
+					    reg2);
+}
+
+u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
+					 enum aarch64_insn_register src,
+					 enum aarch64_insn_register reg,
+					 int shift,
+					 enum aarch64_insn_variant variant,
+					 enum aarch64_insn_logic_type type)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LOGIC_AND:
+		insn = aarch64_insn_get_and_value();
+		break;
+	case AARCH64_INSN_LOGIC_BIC:
+		insn = aarch64_insn_get_bic_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORR:
+		insn = aarch64_insn_get_orr_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORN:
+		insn = aarch64_insn_get_orn_value();
+		break;
+	case AARCH64_INSN_LOGIC_EOR:
+		insn = aarch64_insn_get_eor_value();
+		break;
+	case AARCH64_INSN_LOGIC_EON:
+		insn = aarch64_insn_get_eon_value();
+		break;
+	case AARCH64_INSN_LOGIC_AND_SETFLAGS:
+		insn = aarch64_insn_get_ands_value();
+		break;
+	case AARCH64_INSN_LOGIC_BIC_SETFLAGS:
+		insn = aarch64_insn_get_bics_value();
+		break;
+	default:
+		pr_err("%s: unknown logical encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (shift & ~(SZ_32 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		if (shift & ~(SZ_64 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, src);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
+}
+
+/*
+ * MOV (register) is architecturally an alias of ORR (shifted register) where
+ * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m>
+ */
+u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant)
+{
+	return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR,
+						    src, 0, variant,
+						    AARCH64_INSN_LOGIC_ORR);
+}
+
+u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr,
+			 enum aarch64_insn_register reg,
+			 enum aarch64_insn_adr_type type)
+{
+	u32 insn;
+	s32 offset;
+
+	switch (type) {
+	case AARCH64_INSN_ADR_TYPE_ADR:
+		insn = aarch64_insn_get_adr_value();
+		offset = addr - pc;
+		break;
+	case AARCH64_INSN_ADR_TYPE_ADRP:
+		insn = aarch64_insn_get_adrp_value();
+		offset = (addr - ALIGN_DOWN(pc, SZ_4K)) >> 12;
+		break;
+	default:
+		pr_err("%s: unknown adr encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	if (offset < -SZ_1M || offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, reg);
+
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn, offset);
+}
+
+/*
+ * Decode the imm field of a branch, and return the byte offset as a
+ * signed value (so it can be used when computing a new branch
+ * target).
+ */
+s32 aarch64_get_branch_offset(u32 insn)
+{
+	s32 imm;
+
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
+		return (imm << 6) >> 4;
+	}
+
+	if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+	    aarch64_insn_is_bcond(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_19, insn);
+		return (imm << 13) >> 11;
+	}
+
+	if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_14, insn);
+		return (imm << 18) >> 16;
+	}
+
+	/* Unhandled instruction */
+	BUG();
+}
+
+/*
+ * Encode the displacement of a branch in the imm field and return the
+ * updated instruction.
+ */
+u32 aarch64_set_branch_offset(u32 insn, s32 offset)
+{
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+						     offset >> 2);
+
+	if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+	    aarch64_insn_is_bcond(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+						     offset >> 2);
+
+	if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_14, insn,
+						     offset >> 2);
+
+	/* Unhandled instruction */
+	BUG();
+}
+
+s32 aarch64_insn_adrp_get_offset(u32 insn)
+{
+	BUG_ON(!aarch64_insn_is_adrp(insn));
+	return aarch64_insn_decode_immediate(AARCH64_INSN_IMM_ADR, insn) << 12;
+}
+
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset)
+{
+	BUG_ON(!aarch64_insn_is_adrp(insn));
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn,
+						offset >> 12);
+}
+
+/*
+ * Extract the Op/CR data from a msr/mrs instruction.
+ */
+u32 aarch64_insn_extract_system_reg(u32 insn)
+{
+	return (insn & 0x1FFFE0) >> 5;
+}
+
+bool aarch32_insn_is_wide(u32 insn)
+{
+	return insn >= 0xe800;
+}
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+u32 aarch32_insn_extract_reg_num(u32 insn, int offset)
+{
+	return (insn & (0xf << offset)) >> offset;
+}
+
+#define OPC2_MASK	0x7
+#define OPC2_OFFSET	5
+u32 aarch32_insn_mcr_extract_opc2(u32 insn)
+{
+	return (insn & (OPC2_MASK << OPC2_OFFSET)) >> OPC2_OFFSET;
+}
+
+#define CRM_MASK	0xf
+u32 aarch32_insn_mcr_extract_crm(u32 insn)
+{
+	return insn & CRM_MASK;
+}
+
+static bool range_of_ones(u64 val)
+{
+	/* Doesn't handle full ones or full zeroes */
+	u64 sval = val >> __ffs64(val);
+
+	/* One of Sean Eron Anderson's bithack tricks */
+	return ((sval + 1) & (sval)) == 0;
+}
+
+static u32 aarch64_encode_immediate(u64 imm,
+				    enum aarch64_insn_variant variant,
+				    u32 insn)
+{
+	unsigned int immr, imms, n, ones, ror, esz, tmp;
+	u64 mask;
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		esz = 32;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		insn |= AARCH64_INSN_SF_BIT;
+		esz = 64;
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	mask = GENMASK(esz - 1, 0);
+
+	/* Can't encode full zeroes, full ones, or value wider than the mask */
+	if (!imm || imm == mask || imm & ~mask)
+		return AARCH64_BREAK_FAULT;
+
+	/*
+	 * Inverse of Replicate(). Try to spot a repeating pattern
+	 * with a pow2 stride.
+	 */
+	for (tmp = esz / 2; tmp >= 2; tmp /= 2) {
+		u64 emask = BIT(tmp) - 1;
+
+		if ((imm & emask) != ((imm >> tmp) & emask))
+			break;
+
+		esz = tmp;
+		mask = emask;
+	}
+
+	/* N is only set if we're encoding a 64bit value */
+	n = esz == 64;
+
+	/* Trim imm to the element size */
+	imm &= mask;
+
+	/* That's how many ones we need to encode */
+	ones = hweight64(imm);
+
+	/*
+	 * imms is set to (ones - 1), prefixed with a string of ones
+	 * and a zero if they fit. Cap it to 6 bits.
+	 */
+	imms  = ones - 1;
+	imms |= 0xf << ffs(esz);
+	imms &= BIT(6) - 1;
+
+	/* Compute the rotation */
+	if (range_of_ones(imm)) {
+		/*
+		 * Pattern: 0..01..10..0
+		 *
+		 * Compute how many rotate we need to align it right
+		 */
+		ror = __ffs64(imm);
+	} else {
+		/*
+		 * Pattern: 0..01..10..01..1
+		 *
+		 * Fill the unused top bits with ones, and check if
+		 * the result is a valid immediate (all ones with a
+		 * contiguous ranges of zeroes).
+		 */
+		imm |= ~mask;
+		if (!range_of_ones(~imm))
+			return AARCH64_BREAK_FAULT;
+
+		/*
+		 * Compute the rotation to get a continuous set of
+		 * ones, with the first bit set at position 0
+		 */
+		ror = fls64(~imm);
+	}
+
+	/*
+	 * immr is the number of bits we need to rotate back to the
+	 * original set of ones. Note that this is relative to the
+	 * element size...
+	 */
+	immr = (esz - ror) % esz;
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, n);
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_R, insn, immr);
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, imms);
+}
+
+u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type,
+				       enum aarch64_insn_variant variant,
+				       enum aarch64_insn_register Rn,
+				       enum aarch64_insn_register Rd,
+				       u64 imm)
+{
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_LOGIC_AND:
+		insn = aarch64_insn_get_and_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_ORR:
+		insn = aarch64_insn_get_orr_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_EOR:
+		insn = aarch64_insn_get_eor_imm_value();
+		break;
+	case AARCH64_INSN_LOGIC_AND_SETFLAGS:
+		insn = aarch64_insn_get_ands_imm_value();
+		break;
+	default:
+		pr_err("%s: unknown logical encoding %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn);
+	return aarch64_encode_immediate(imm, variant, insn);
+}
+
+u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
+			  enum aarch64_insn_register Rm,
+			  enum aarch64_insn_register Rn,
+			  enum aarch64_insn_register Rd,
+			  u8 lsb)
+{
+	u32 insn;
+
+	insn = aarch64_insn_get_extr_value();
+
+	switch (variant) {
+	case AARCH64_INSN_VARIANT_32BIT:
+		if (lsb > 31)
+			return AARCH64_BREAK_FAULT;
+		break;
+	case AARCH64_INSN_VARIANT_64BIT:
+		if (lsb > 63)
+			return AARCH64_BREAK_FAULT;
+		insn |= AARCH64_INSN_SF_BIT;
+		insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_N, insn, 1);
+		break;
+	default:
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_S, insn, lsb);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, Rd);
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, Rn);
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm);
+}
+
+u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
+{
+	u32 opt;
+	u32 insn;
+
+	switch (type) {
+	case AARCH64_INSN_MB_SY:
+		opt = 0xf;
+		break;
+	case AARCH64_INSN_MB_ST:
+		opt = 0xe;
+		break;
+	case AARCH64_INSN_MB_LD:
+		opt = 0xd;
+		break;
+	case AARCH64_INSN_MB_ISH:
+		opt = 0xb;
+		break;
+	case AARCH64_INSN_MB_ISHST:
+		opt = 0xa;
+		break;
+	case AARCH64_INSN_MB_ISHLD:
+		opt = 0x9;
+		break;
+	case AARCH64_INSN_MB_NSH:
+		opt = 0x7;
+		break;
+	case AARCH64_INSN_MB_NSHST:
+		opt = 0x6;
+		break;
+	case AARCH64_INSN_MB_NSHLD:
+		opt = 0x5;
+		break;
+	default:
+		pr_err("%s: unknown dmb type %d\n", __func__, type);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_get_dmb_value();
+	insn &= ~GENMASK(11, 8);
+	insn |= (opt << 8);
+
+	return insn;
+}
diff --git a/arch/arm64/lib/kasan_sw_tags.S b/arch/arm64/lib/kasan_sw_tags.S
new file mode 100644
index 0000000000..20784ce75d
--- /dev/null
+++ b/arch/arm64/lib/kasan_sw_tags.S
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Google LLC
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Report a tag mismatch detected by tag-based KASAN.
+ *
+ * A compiler-generated thunk calls this with a non-AAPCS calling
+ * convention. Upon entry to this function, registers are as follows:
+ *
+ * x0:         fault address (see below for restore)
+ * x1:         fault description (see below for restore)
+ * x2 to x15:  callee-saved
+ * x16 to x17: safe to clobber
+ * x18 to x30: callee-saved
+ * sp:         pre-decremented by 256 bytes (see below for restore)
+ *
+ * The caller has decremented the SP by 256 bytes, and created a
+ * structure on the stack as follows:
+ *
+ * sp + 0..15:    x0 and x1 to be restored
+ * sp + 16..231:  free for use
+ * sp + 232..247: x29 and x30 (same as in GPRs)
+ * sp + 248..255: free for use
+ *
+ * Note that this is not a struct pt_regs.
+ *
+ * To call a regular AAPCS function we must save x2 to x15 (which we can
+ * store in the gaps), and create a frame record (for which we can use
+ * x29 and x30 spilled by the caller as those match the GPRs).
+ *
+ * The caller expects x0 and x1 to be restored from the structure, and
+ * for the structure to be removed from the stack (i.e. the SP must be
+ * incremented by 256 prior to return).
+ */
+SYM_CODE_START(__hwasan_tag_mismatch)
+	bti	c
+	add	x29, sp, #232
+	stp	x2, x3, [sp, #8 * 2]
+	stp	x4, x5, [sp, #8 * 4]
+	stp	x6, x7, [sp, #8 * 6]
+	stp	x8, x9, [sp, #8 * 8]
+	stp	x10, x11, [sp, #8 * 10]
+	stp	x12, x13, [sp, #8 * 12]
+	stp	x14, x15, [sp, #8 * 14]
+#ifndef CONFIG_SHADOW_CALL_STACK
+	str	x18, [sp, #8 * 18]
+#endif
+
+	mov	x2, x30
+	bl	kasan_tag_mismatch
+
+	ldp	x0, x1, [sp]
+	ldp	x2, x3, [sp, #8 * 2]
+	ldp	x4, x5, [sp, #8 * 4]
+	ldp	x6, x7, [sp, #8 * 6]
+	ldp	x8, x9, [sp, #8 * 8]
+	ldp	x10, x11, [sp, #8 * 10]
+	ldp	x12, x13, [sp, #8 * 12]
+	ldp	x14, x15, [sp, #8 * 14]
+#ifndef CONFIG_SHADOW_CALL_STACK
+	ldr	x18, [sp, #8 * 18]
+#endif
+	ldp	x29, x30, [sp, #8 * 29]
+
+	/* remove the structure from the stack */
+	add	sp, sp, #256
+	ret
+SYM_CODE_END(__hwasan_tag_mismatch)
+EXPORT_SYMBOL(__hwasan_tag_mismatch)
diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S
new file mode 100644
index 0000000000..37a9f2a4f7
--- /dev/null
+++ b/arch/arm64/lib/memchr.S
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Arm Ltd.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Find a character in an area of memory.
+ *
+ * Parameters:
+ *	x0 - buf
+ *	x1 - c
+ *	x2 - n
+ * Returns:
+ *	x0 - address of first occurrence of 'c' or 0
+ */
+
+#define L(label) .L ## label
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+
+#define srcin		x0
+#define chrin		w1
+#define cntin		x2
+
+#define result		x0
+
+#define wordcnt		x3
+#define rep01		x4
+#define repchr		x5
+#define cur_word	x6
+#define cur_byte	w6
+#define tmp		x7
+#define tmp2		x8
+
+	.p2align 4
+	nop
+SYM_FUNC_START(__pi_memchr)
+	and	chrin, chrin, #0xff
+	lsr	wordcnt, cntin, #3
+	cbz	wordcnt, L(byte_loop)
+	mov	rep01, #REP8_01
+	mul	repchr, x1, rep01
+	and	cntin, cntin, #7
+L(word_loop):
+	ldr	cur_word, [srcin], #8
+	sub	wordcnt, wordcnt, #1
+	eor	cur_word, cur_word, repchr
+	sub	tmp, cur_word, rep01
+	orr	tmp2, cur_word, #REP8_7f
+	bics	tmp, tmp, tmp2
+	b.ne	L(found_word)
+	cbnz	wordcnt, L(word_loop)
+L(byte_loop):
+	cbz	cntin, L(not_found)
+	ldrb	cur_byte, [srcin], #1
+	sub	cntin, cntin, #1
+	cmp	cur_byte, chrin
+	b.ne	L(byte_loop)
+	sub	srcin, srcin, #1
+	ret
+L(found_word):
+CPU_LE(	rev	tmp, tmp)
+	clz	tmp, tmp
+	sub	tmp, tmp, #64
+	add	result, srcin, tmp, asr #3
+	ret
+L(not_found):
+	mov	result, #0
+	ret
+SYM_FUNC_END(__pi_memchr)
+SYM_FUNC_ALIAS_WEAK(memchr, __pi_memchr)
+EXPORT_SYMBOL_NOKASAN(memchr)
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
new file mode 100644
index 0000000000..a5ccf2c55f
--- /dev/null
+++ b/arch/arm64/lib/memcmp.S
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2013-2021, Arm Limited.
+ *
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/e823e3abf5f89ecb/string/aarch64/memcmp.S
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64, unaligned accesses.
+ */
+
+#define L(label) .L ## label
+
+/* Parameters and result.  */
+#define src1		x0
+#define src2		x1
+#define limit		x2
+#define result		w0
+
+/* Internal variables.  */
+#define data1		x3
+#define data1w		w3
+#define data1h		x4
+#define data2		x5
+#define data2w		w5
+#define data2h		x6
+#define tmp1		x7
+#define tmp2		x8
+
+SYM_FUNC_START(__pi_memcmp)
+	subs	limit, limit, 8
+	b.lo	L(less8)
+
+	ldr	data1, [src1], 8
+	ldr	data2, [src2], 8
+	cmp	data1, data2
+	b.ne	L(return)
+
+	subs	limit, limit, 8
+	b.gt	L(more16)
+
+	ldr	data1, [src1, limit]
+	ldr	data2, [src2, limit]
+	b	L(return)
+
+L(more16):
+	ldr	data1, [src1], 8
+	ldr	data2, [src2], 8
+	cmp	data1, data2
+	bne	L(return)
+
+	/* Jump directly to comparing the last 16 bytes for 32 byte (or less)
+	   strings.  */
+	subs	limit, limit, 16
+	b.ls	L(last_bytes)
+
+	/* We overlap loads between 0-32 bytes at either side of SRC1 when we
+	   try to align, so limit it only to strings larger than 128 bytes.  */
+	cmp	limit, 96
+	b.ls	L(loop16)
+
+	/* Align src1 and adjust src2 with bytes not yet done.  */
+	and	tmp1, src1, 15
+	add	limit, limit, tmp1
+	sub	src1, src1, tmp1
+	sub	src2, src2, tmp1
+
+	/* Loop performing 16 bytes per iteration using aligned src1.
+	   Limit is pre-decremented by 16 and must be larger than zero.
+	   Exit if <= 16 bytes left to do or if the data is not equal.  */
+	.p2align 4
+L(loop16):
+	ldp	data1, data1h, [src1], 16
+	ldp	data2, data2h, [src2], 16
+	subs	limit, limit, 16
+	ccmp	data1, data2, 0, hi
+	ccmp	data1h, data2h, 0, eq
+	b.eq	L(loop16)
+
+	cmp	data1, data2
+	bne	L(return)
+	mov	data1, data1h
+	mov	data2, data2h
+	cmp	data1, data2
+	bne	L(return)
+
+	/* Compare last 1-16 bytes using unaligned access.  */
+L(last_bytes):
+	add	src1, src1, limit
+	add	src2, src2, limit
+	ldp	data1, data1h, [src1]
+	ldp	data2, data2h, [src2]
+	cmp	data1, data2
+	bne	L(return)
+	mov	data1, data1h
+	mov	data2, data2h
+	cmp	data1, data2
+
+	/* Compare data bytes and set return value to 0, -1 or 1.  */
+L(return):
+#ifndef __AARCH64EB__
+	rev	data1, data1
+	rev	data2, data2
+#endif
+	cmp	data1, data2
+L(ret_eq):
+	cset	result, ne
+	cneg	result, result, lo
+	ret
+
+	.p2align 4
+	/* Compare up to 8 bytes.  Limit is [-8..-1].  */
+L(less8):
+	adds	limit, limit, 4
+	b.lo	L(less4)
+	ldr	data1w, [src1], 4
+	ldr	data2w, [src2], 4
+	cmp	data1w, data2w
+	b.ne	L(return)
+	sub	limit, limit, 4
+L(less4):
+	adds	limit, limit, 4
+	beq	L(ret_eq)
+L(byte_loop):
+	ldrb	data1w, [src1], 1
+	ldrb	data2w, [src2], 1
+	subs	limit, limit, 1
+	ccmp	data1w, data2w, 0, ne	/* NZCV = 0b0000.  */
+	b.eq	L(byte_loop)
+	sub	result, data1w, data2w
+	ret
+SYM_FUNC_END(__pi_memcmp)
+SYM_FUNC_ALIAS_WEAK(memcmp, __pi_memcmp)
+EXPORT_SYMBOL_NOKASAN(memcmp)
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
new file mode 100644
index 0000000000..4ab48d49c4
--- /dev/null
+++ b/arch/arm64/lib/memcpy.S
@@ -0,0 +1,253 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2012-2021, Arm Limited.
+ *
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/afd6244a1f8d9229/string/aarch64/memcpy.S
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64, unaligned accesses.
+ *
+ */
+
+#define L(label) .L ## label
+
+#define dstin	x0
+#define src	x1
+#define count	x2
+#define dst	x3
+#define srcend	x4
+#define dstend	x5
+#define A_l	x6
+#define A_lw	w6
+#define A_h	x7
+#define B_l	x8
+#define B_lw	w8
+#define B_h	x9
+#define C_l	x10
+#define C_lw	w10
+#define C_h	x11
+#define D_l	x12
+#define D_h	x13
+#define E_l	x14
+#define E_h	x15
+#define F_l	x16
+#define F_h	x17
+#define G_l	count
+#define G_h	dst
+#define H_l	src
+#define H_h	srcend
+#define tmp1	x14
+
+/* This implementation handles overlaps and supports both memcpy and memmove
+   from a single entry point.  It uses unaligned accesses and branchless
+   sequences to keep the code small, simple and improve performance.
+
+   Copies are split into 3 main cases: small copies of up to 32 bytes, medium
+   copies of up to 128 bytes, and large copies.  The overhead of the overlap
+   check is negligible since it is only required for large copies.
+
+   Large copies use a software pipelined loop processing 64 bytes per iteration.
+   The destination pointer is 16-byte aligned to minimize unaligned accesses.
+   The loop tail is handled by always copying 64 bytes from the end.
+*/
+
+SYM_FUNC_START(__pi_memcpy)
+	add	srcend, src, count
+	add	dstend, dstin, count
+	cmp	count, 128
+	b.hi	L(copy_long)
+	cmp	count, 32
+	b.hi	L(copy32_128)
+
+	/* Small copies: 0..32 bytes.  */
+	cmp	count, 16
+	b.lo	L(copy16)
+	ldp	A_l, A_h, [src]
+	ldp	D_l, D_h, [srcend, -16]
+	stp	A_l, A_h, [dstin]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	/* Copy 8-15 bytes.  */
+L(copy16):
+	tbz	count, 3, L(copy8)
+	ldr	A_l, [src]
+	ldr	A_h, [srcend, -8]
+	str	A_l, [dstin]
+	str	A_h, [dstend, -8]
+	ret
+
+	.p2align 3
+	/* Copy 4-7 bytes.  */
+L(copy8):
+	tbz	count, 2, L(copy4)
+	ldr	A_lw, [src]
+	ldr	B_lw, [srcend, -4]
+	str	A_lw, [dstin]
+	str	B_lw, [dstend, -4]
+	ret
+
+	/* Copy 0..3 bytes using a branchless sequence.  */
+L(copy4):
+	cbz	count, L(copy0)
+	lsr	tmp1, count, 1
+	ldrb	A_lw, [src]
+	ldrb	C_lw, [srcend, -1]
+	ldrb	B_lw, [src, tmp1]
+	strb	A_lw, [dstin]
+	strb	B_lw, [dstin, tmp1]
+	strb	C_lw, [dstend, -1]
+L(copy0):
+	ret
+
+	.p2align 4
+	/* Medium copies: 33..128 bytes.  */
+L(copy32_128):
+	ldp	A_l, A_h, [src]
+	ldp	B_l, B_h, [src, 16]
+	ldp	C_l, C_h, [srcend, -32]
+	ldp	D_l, D_h, [srcend, -16]
+	cmp	count, 64
+	b.hi	L(copy128)
+	stp	A_l, A_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	.p2align 4
+	/* Copy 65..128 bytes.  */
+L(copy128):
+	ldp	E_l, E_h, [src, 32]
+	ldp	F_l, F_h, [src, 48]
+	cmp	count, 96
+	b.ls	L(copy96)
+	ldp	G_l, G_h, [srcend, -64]
+	ldp	H_l, H_h, [srcend, -48]
+	stp	G_l, G_h, [dstend, -64]
+	stp	H_l, H_h, [dstend, -48]
+L(copy96):
+	stp	A_l, A_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	E_l, E_h, [dstin, 32]
+	stp	F_l, F_h, [dstin, 48]
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	.p2align 4
+	/* Copy more than 128 bytes.  */
+L(copy_long):
+	/* Use backwards copy if there is an overlap.  */
+	sub	tmp1, dstin, src
+	cbz	tmp1, L(copy0)
+	cmp	tmp1, count
+	b.lo	L(copy_long_backwards)
+
+	/* Copy 16 bytes and then align dst to 16-byte alignment.  */
+
+	ldp	D_l, D_h, [src]
+	and	tmp1, dstin, 15
+	bic	dst, dstin, 15
+	sub	src, src, tmp1
+	add	count, count, tmp1	/* Count is now 16 too large.  */
+	ldp	A_l, A_h, [src, 16]
+	stp	D_l, D_h, [dstin]
+	ldp	B_l, B_h, [src, 32]
+	ldp	C_l, C_h, [src, 48]
+	ldp	D_l, D_h, [src, 64]!
+	subs	count, count, 128 + 16	/* Test and readjust count.  */
+	b.ls	L(copy64_from_end)
+
+L(loop64):
+	stp	A_l, A_h, [dst, 16]
+	ldp	A_l, A_h, [src, 16]
+	stp	B_l, B_h, [dst, 32]
+	ldp	B_l, B_h, [src, 32]
+	stp	C_l, C_h, [dst, 48]
+	ldp	C_l, C_h, [src, 48]
+	stp	D_l, D_h, [dst, 64]!
+	ldp	D_l, D_h, [src, 64]!
+	subs	count, count, 64
+	b.hi	L(loop64)
+
+	/* Write the last iteration and copy 64 bytes from the end.  */
+L(copy64_from_end):
+	ldp	E_l, E_h, [srcend, -64]
+	stp	A_l, A_h, [dst, 16]
+	ldp	A_l, A_h, [srcend, -48]
+	stp	B_l, B_h, [dst, 32]
+	ldp	B_l, B_h, [srcend, -32]
+	stp	C_l, C_h, [dst, 48]
+	ldp	C_l, C_h, [srcend, -16]
+	stp	D_l, D_h, [dst, 64]
+	stp	E_l, E_h, [dstend, -64]
+	stp	A_l, A_h, [dstend, -48]
+	stp	B_l, B_h, [dstend, -32]
+	stp	C_l, C_h, [dstend, -16]
+	ret
+
+	.p2align 4
+
+	/* Large backwards copy for overlapping copies.
+	   Copy 16 bytes and then align dst to 16-byte alignment.  */
+L(copy_long_backwards):
+	ldp	D_l, D_h, [srcend, -16]
+	and	tmp1, dstend, 15
+	sub	srcend, srcend, tmp1
+	sub	count, count, tmp1
+	ldp	A_l, A_h, [srcend, -16]
+	stp	D_l, D_h, [dstend, -16]
+	ldp	B_l, B_h, [srcend, -32]
+	ldp	C_l, C_h, [srcend, -48]
+	ldp	D_l, D_h, [srcend, -64]!
+	sub	dstend, dstend, tmp1
+	subs	count, count, 128
+	b.ls	L(copy64_from_start)
+
+L(loop64_backwards):
+	stp	A_l, A_h, [dstend, -16]
+	ldp	A_l, A_h, [srcend, -16]
+	stp	B_l, B_h, [dstend, -32]
+	ldp	B_l, B_h, [srcend, -32]
+	stp	C_l, C_h, [dstend, -48]
+	ldp	C_l, C_h, [srcend, -48]
+	stp	D_l, D_h, [dstend, -64]!
+	ldp	D_l, D_h, [srcend, -64]!
+	subs	count, count, 64
+	b.hi	L(loop64_backwards)
+
+	/* Write the last iteration and copy 64 bytes from the start.  */
+L(copy64_from_start):
+	ldp	G_l, G_h, [src, 48]
+	stp	A_l, A_h, [dstend, -16]
+	ldp	A_l, A_h, [src, 32]
+	stp	B_l, B_h, [dstend, -32]
+	ldp	B_l, B_h, [src, 16]
+	stp	C_l, C_h, [dstend, -48]
+	ldp	C_l, C_h, [src]
+	stp	D_l, D_h, [dstend, -64]
+	stp	G_l, G_h, [dstin, 48]
+	stp	A_l, A_h, [dstin, 32]
+	stp	B_l, B_h, [dstin, 16]
+	stp	C_l, C_h, [dstin]
+	ret
+SYM_FUNC_END(__pi_memcpy)
+
+SYM_FUNC_ALIAS(__memcpy, __pi_memcpy)
+EXPORT_SYMBOL(__memcpy)
+SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy)
+EXPORT_SYMBOL(memcpy)
+
+SYM_FUNC_ALIAS(__pi_memmove, __pi_memcpy)
+
+SYM_FUNC_ALIAS(__memmove, __pi_memmove)
+EXPORT_SYMBOL(__memmove)
+SYM_FUNC_ALIAS_WEAK(memmove, __memmove)
+EXPORT_SYMBOL(memmove)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
new file mode 100644
index 0000000000..a5aebe82ad
--- /dev/null
+++ b/arch/arm64/lib/memset.S
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+/*
+ * Fill in the buffer with character c (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - buf
+ *	x1 - c
+ *	x2 - n
+ * Returns:
+ *	x0 - buf
+ */
+
+dstin		.req	x0
+val		.req	w1
+count		.req	x2
+tmp1		.req	x3
+tmp1w		.req	w3
+tmp2		.req	x4
+tmp2w		.req	w4
+zva_len_x	.req	x5
+zva_len		.req	w5
+zva_bits_x	.req	x6
+
+A_l		.req	x7
+A_lw		.req	w7
+dst		.req	x8
+tmp3w		.req	w9
+tmp3		.req	x9
+
+SYM_FUNC_START(__pi_memset)
+	mov	dst, dstin	/* Preserve return value.  */
+	and	A_lw, val, #255
+	orr	A_lw, A_lw, A_lw, lsl #8
+	orr	A_lw, A_lw, A_lw, lsl #16
+	orr	A_l, A_l, A_l, lsl #32
+
+	cmp	count, #15
+	b.hi	.Lover16_proc
+	/*All store maybe are non-aligned..*/
+	tbz	count, #3, 1f
+	str	A_l, [dst], #8
+1:
+	tbz	count, #2, 2f
+	str	A_lw, [dst], #4
+2:
+	tbz	count, #1, 3f
+	strh	A_lw, [dst], #2
+3:
+	tbz	count, #0, 4f
+	strb	A_lw, [dst]
+4:
+	ret
+
+.Lover16_proc:
+	/*Whether  the start address is aligned with 16.*/
+	neg	tmp2, dst
+	ands	tmp2, tmp2, #15
+	b.eq	.Laligned
+/*
+* The count is not less than 16, we can use stp to store the start 16 bytes,
+* then adjust the dst aligned with 16.This process will make the current
+* memory address at alignment boundary.
+*/
+	stp	A_l, A_l, [dst] /*non-aligned store..*/
+	/*make the dst aligned..*/
+	sub	count, count, tmp2
+	add	dst, dst, tmp2
+
+.Laligned:
+	cbz	A_l, .Lzero_mem
+
+.Ltail_maybe_long:
+	cmp	count, #64
+	b.ge	.Lnot_short
+.Ltail63:
+	ands	tmp1, count, #0x30
+	b.eq	3f
+	cmp	tmp1w, #0x20
+	b.eq	1f
+	b.lt	2f
+	stp	A_l, A_l, [dst], #16
+1:
+	stp	A_l, A_l, [dst], #16
+2:
+	stp	A_l, A_l, [dst], #16
+/*
+* The last store length is less than 16,use stp to write last 16 bytes.
+* It will lead some bytes written twice and the access is non-aligned.
+*/
+3:
+	ands	count, count, #15
+	cbz	count, 4f
+	add	dst, dst, count
+	stp	A_l, A_l, [dst, #-16]	/* Repeat some/all of last store. */
+4:
+	ret
+
+	/*
+	* Critical loop. Start at a new cache line boundary. Assuming
+	* 64 bytes per line, this ensures the entire loop is in one line.
+	*/
+	.p2align	L1_CACHE_SHIFT
+.Lnot_short:
+	sub	dst, dst, #16/* Pre-bias.  */
+	sub	count, count, #64
+1:
+	stp	A_l, A_l, [dst, #16]
+	stp	A_l, A_l, [dst, #32]
+	stp	A_l, A_l, [dst, #48]
+	stp	A_l, A_l, [dst, #64]!
+	subs	count, count, #64
+	b.ge	1b
+	tst	count, #0x3f
+	add	dst, dst, #16
+	b.ne	.Ltail63
+.Lexitfunc:
+	ret
+
+	/*
+	* For zeroing memory, check to see if we can use the ZVA feature to
+	* zero entire 'cache' lines.
+	*/
+.Lzero_mem:
+	cmp	count, #63
+	b.le	.Ltail63
+	/*
+	* For zeroing small amounts of memory, it's not worth setting up
+	* the line-clear code.
+	*/
+	cmp	count, #128
+	b.lt	.Lnot_short /*count is at least  128 bytes*/
+
+	mrs	tmp1, dczid_el0
+	tbnz	tmp1, #4, .Lnot_short
+	mov	tmp3w, #4
+	and	zva_len, tmp1w, #15	/* Safety: other bits reserved.  */
+	lsl	zva_len, tmp3w, zva_len
+
+	ands	tmp3w, zva_len, #63
+	/*
+	* ensure the zva_len is not less than 64.
+	* It is not meaningful to use ZVA if the block size is less than 64.
+	*/
+	b.ne	.Lnot_short
+.Lzero_by_line:
+	/*
+	* Compute how far we need to go to become suitably aligned. We're
+	* already at quad-word alignment.
+	*/
+	cmp	count, zva_len_x
+	b.lt	.Lnot_short		/* Not enough to reach alignment.  */
+	sub	zva_bits_x, zva_len_x, #1
+	neg	tmp2, dst
+	ands	tmp2, tmp2, zva_bits_x
+	b.eq	2f			/* Already aligned.  */
+	/* Not aligned, check that there's enough to copy after alignment.*/
+	sub	tmp1, count, tmp2
+	/*
+	* grantee the remain length to be ZVA is bigger than 64,
+	* avoid to make the 2f's process over mem range.*/
+	cmp	tmp1, #64
+	ccmp	tmp1, zva_len_x, #8, ge	/* NZCV=0b1000 */
+	b.lt	.Lnot_short
+	/*
+	* We know that there's at least 64 bytes to zero and that it's safe
+	* to overrun by 64 bytes.
+	*/
+	mov	count, tmp1
+1:
+	stp	A_l, A_l, [dst]
+	stp	A_l, A_l, [dst, #16]
+	stp	A_l, A_l, [dst, #32]
+	subs	tmp2, tmp2, #64
+	stp	A_l, A_l, [dst, #48]
+	add	dst, dst, #64
+	b.ge	1b
+	/* We've overrun a bit, so adjust dst downwards.*/
+	add	dst, dst, tmp2
+2:
+	sub	count, count, zva_len_x
+3:
+	dc	zva, dst
+	add	dst, dst, zva_len_x
+	subs	count, count, zva_len_x
+	b.ge	3b
+	ands	count, count, zva_bits_x
+	b.ne	.Ltail_maybe_long
+	ret
+SYM_FUNC_END(__pi_memset)
+
+SYM_FUNC_ALIAS(__memset, __pi_memset)
+EXPORT_SYMBOL(__memset)
+
+SYM_FUNC_ALIAS_WEAK(memset, __pi_memset)
+EXPORT_SYMBOL(memset)
diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
new file mode 100644
index 0000000000..5018ac03b6
--- /dev/null
+++ b/arch/arm64/lib/mte.S
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#include <linux/linkage.h>
+
+#include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/mte.h>
+#include <asm/page.h>
+#include <asm/sysreg.h>
+
+	.arch	armv8.5-a+memtag
+
+/*
+ * multitag_transfer_size - set \reg to the block size that is accessed by the
+ * LDGM/STGM instructions.
+ */
+	.macro	multitag_transfer_size, reg, tmp
+	mrs_s	\reg, SYS_GMID_EL1
+	ubfx	\reg, \reg, #GMID_EL1_BS_SHIFT, #GMID_EL1_BS_WIDTH
+	mov	\tmp, #4
+	lsl	\reg, \tmp, \reg
+	.endm
+
+/*
+ * Clear the tags in a page
+ *   x0 - address of the page to be cleared
+ */
+SYM_FUNC_START(mte_clear_page_tags)
+	multitag_transfer_size x1, x2
+1:	stgm	xzr, [x0]
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_clear_page_tags)
+
+/*
+ * Zero the page and tags at the same time
+ *
+ * Parameters:
+ *	x0 - address to the beginning of the page
+ */
+SYM_FUNC_START(mte_zero_clear_page_tags)
+	and	x0, x0, #(1 << MTE_TAG_SHIFT) - 1	// clear the tag
+	mrs	x1, dczid_el0
+	tbnz	x1, #4, 2f	// Branch if DC GZVA is prohibited
+	and	w1, w1, #0xf
+	mov	x2, #4
+	lsl	x1, x2, x1
+
+1:	dc	gzva, x0
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+
+2:	stz2g	x0, [x0], #(MTE_GRANULE_SIZE * 2)
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	2b
+	ret
+SYM_FUNC_END(mte_zero_clear_page_tags)
+
+/*
+ * Copy the tags from the source page to the destination one
+ *   x0 - address of the destination page
+ *   x1 - address of the source page
+ */
+SYM_FUNC_START(mte_copy_page_tags)
+	mov	x2, x0
+	mov	x3, x1
+	multitag_transfer_size x5, x6
+1:	ldgm	x4, [x3]
+	stgm	x4, [x2]
+	add	x2, x2, x5
+	add	x3, x3, x5
+	tst	x2, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_copy_page_tags)
+
+/*
+ * Read tags from a user buffer (one tag per byte) and set the corresponding
+ * tags at the given kernel address. Used by PTRACE_POKEMTETAGS.
+ *   x0 - kernel address (to)
+ *   x1 - user buffer (from)
+ *   x2 - number of tags/bytes (n)
+ * Returns:
+ *   x0 - number of tags read/set
+ */
+SYM_FUNC_START(mte_copy_tags_from_user)
+	mov	x3, x1
+	cbz	x2, 2f
+1:
+USER(2f, ldtrb	w4, [x1])
+	lsl	x4, x4, #MTE_TAG_SHIFT
+	stg	x4, [x0], #MTE_GRANULE_SIZE
+	add	x1, x1, #1
+	subs	x2, x2, #1
+	b.ne	1b
+
+	// exception handling and function return
+2:	sub	x0, x1, x3		// update the number of tags set
+	ret
+SYM_FUNC_END(mte_copy_tags_from_user)
+
+/*
+ * Get the tags from a kernel address range and write the tag values to the
+ * given user buffer (one tag per byte). Used by PTRACE_PEEKMTETAGS.
+ *   x0 - user buffer (to)
+ *   x1 - kernel address (from)
+ *   x2 - number of tags/bytes (n)
+ * Returns:
+ *   x0 - number of tags read/set
+ */
+SYM_FUNC_START(mte_copy_tags_to_user)
+	mov	x3, x0
+	cbz	x2, 2f
+1:
+	ldg	x4, [x1]
+	ubfx	x4, x4, #MTE_TAG_SHIFT, #MTE_TAG_SIZE
+USER(2f, sttrb	w4, [x0])
+	add	x0, x0, #1
+	add	x1, x1, #MTE_GRANULE_SIZE
+	subs	x2, x2, #1
+	b.ne	1b
+
+	// exception handling and function return
+2:	sub	x0, x0, x3		// update the number of tags copied
+	ret
+SYM_FUNC_END(mte_copy_tags_to_user)
+
+/*
+ * Save the tags in a page
+ *   x0 - page address
+ *   x1 - tag storage, MTE_PAGE_TAG_STORAGE bytes
+ */
+SYM_FUNC_START(mte_save_page_tags)
+	multitag_transfer_size x7, x5
+1:
+	mov	x2, #0
+2:
+	ldgm	x5, [x0]
+	orr	x2, x2, x5
+	add	x0, x0, x7
+	tst	x0, #0xFF		// 16 tag values fit in a register,
+	b.ne	2b			// which is 16*16=256 bytes
+
+	str	x2, [x1], #8
+
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	ret
+SYM_FUNC_END(mte_save_page_tags)
+
+/*
+ * Restore the tags in a page
+ *   x0 - page address
+ *   x1 - tag storage, MTE_PAGE_TAG_STORAGE bytes
+ */
+SYM_FUNC_START(mte_restore_page_tags)
+	multitag_transfer_size x7, x5
+1:
+	ldr	x2, [x1], #8
+2:
+	stgm	x2, [x0]
+	add	x0, x0, x7
+	tst	x0, #0xFF
+	b.ne	2b
+
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	ret
+SYM_FUNC_END(mte_restore_page_tags)
diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S
new file mode 100644
index 0000000000..94ee67a6b2
--- /dev/null
+++ b/arch/arm64/lib/strchr.S
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/lib/strchr.S
+ *
+ * Copyright (C) 1995-2000 Russell King
+ * Copyright (C) 2013 ARM Ltd.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Find the first occurrence of a character in a string.
+ *
+ * Parameters:
+ *	x0 - str
+ *	x1 - c
+ * Returns:
+ *	x0 - address of first occurrence of 'c' or 0
+ */
+SYM_FUNC_START(__pi_strchr)
+	and	w1, w1, #0xff
+1:	ldrb	w2, [x0], #1
+	cmp	w2, w1
+	ccmp	w2, wzr, #4, ne
+	b.ne	1b
+	sub	x0, x0, #1
+	cmp	w2, w1
+	csel	x0, x0, xzr, eq
+	ret
+SYM_FUNC_END(__pi_strchr)
+
+SYM_FUNC_ALIAS_WEAK(strchr, __pi_strchr)
+EXPORT_SYMBOL_NOKASAN(strchr)
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
new file mode 100644
index 0000000000..9b89b45336
--- /dev/null
+++ b/arch/arm64/lib/strcmp.S
@@ -0,0 +1,190 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2012-2022, Arm Limited.
+ *
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/189dfefe37d54c5b/string/aarch64/strcmp.S
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64.
+ * MTE compatible.
+ */
+
+#define L(label) .L ## label
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+
+#define src1		x0
+#define src2		x1
+#define result		x0
+
+#define data1		x2
+#define data1w		w2
+#define data2		x3
+#define data2w		w3
+#define has_nul		x4
+#define diff		x5
+#define off1		x5
+#define syndrome	x6
+#define tmp		x6
+#define data3		x7
+#define zeroones	x8
+#define shift		x9
+#define off2		x10
+
+/* On big-endian early bytes are at MSB and on little-endian LSB.
+   LS_FW means shifting towards early bytes.  */
+#ifdef __AARCH64EB__
+# define LS_FW lsl
+#else
+# define LS_FW lsr
+#endif
+
+/* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+   (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+   can be done in parallel across the entire word.
+   Since carry propagation makes 0x1 bytes before a NUL byte appear
+   NUL too in big-endian, byte-reverse the data before the NUL check.  */
+
+
+SYM_FUNC_START(__pi_strcmp)
+	sub	off2, src2, src1
+	mov	zeroones, REP8_01
+	and	tmp, src1, 7
+	tst	off2, 7
+	b.ne	L(misaligned8)
+	cbnz	tmp, L(mutual_align)
+
+	.p2align 4
+
+L(loop_aligned):
+	ldr	data2, [src1, off2]
+	ldr	data1, [src1], 8
+L(start_realigned):
+#ifdef __AARCH64EB__
+	rev	tmp, data1
+	sub	has_nul, tmp, zeroones
+	orr	tmp, tmp, REP8_7f
+#else
+	sub	has_nul, data1, zeroones
+	orr	tmp, data1, REP8_7f
+#endif
+	bics	has_nul, has_nul, tmp	/* Non-zero if NUL terminator.  */
+	ccmp	data1, data2, 0, eq
+	b.eq	L(loop_aligned)
+#ifdef __AARCH64EB__
+	rev	has_nul, has_nul
+#endif
+	eor	diff, data1, data2
+	orr	syndrome, diff, has_nul
+L(end):
+#ifndef __AARCH64EB__
+	rev	syndrome, syndrome
+	rev	data1, data1
+	rev	data2, data2
+#endif
+	clz	shift, syndrome
+	/* The most-significant-non-zero bit of the syndrome marks either the
+	   first bit that is different, or the top bit of the first zero byte.
+	   Shifting left now will bring the critical information into the
+	   top bits.  */
+	lsl	data1, data1, shift
+	lsl	data2, data2, shift
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
+	lsr	data1, data1, 56
+	sub	result, data1, data2, lsr 56
+	ret
+
+	.p2align 4
+
+L(mutual_align):
+	/* Sources are mutually aligned, but are not currently at an
+	   alignment boundary.  Round down the addresses and then mask off
+	   the bytes that precede the start point.  */
+	bic	src1, src1, 7
+	ldr	data2, [src1, off2]
+	ldr	data1, [src1], 8
+	neg	shift, src2, lsl 3	/* Bits to alignment -64.  */
+	mov	tmp, -1
+	LS_FW	tmp, tmp, shift
+	orr	data1, data1, tmp
+	orr	data2, data2, tmp
+	b	L(start_realigned)
+
+L(misaligned8):
+	/* Align SRC1 to 8 bytes and then compare 8 bytes at a time, always
+	   checking to make sure that we don't access beyond the end of SRC2.  */
+	cbz	tmp, L(src1_aligned)
+L(do_misaligned):
+	ldrb	data1w, [src1], 1
+	ldrb	data2w, [src2], 1
+	cmp	data1w, 0
+	ccmp	data1w, data2w, 0, ne	/* NZCV = 0b0000.  */
+	b.ne	L(done)
+	tst	src1, 7
+	b.ne	L(do_misaligned)
+
+L(src1_aligned):
+	neg	shift, src2, lsl 3
+	bic	src2, src2, 7
+	ldr	data3, [src2], 8
+#ifdef __AARCH64EB__
+	rev	data3, data3
+#endif
+	lsr	tmp, zeroones, shift
+	orr	data3, data3, tmp
+	sub	has_nul, data3, zeroones
+	orr	tmp, data3, REP8_7f
+	bics	has_nul, has_nul, tmp
+	b.ne	L(tail)
+
+	sub	off1, src2, src1
+
+	.p2align 4
+
+L(loop_unaligned):
+	ldr	data3, [src1, off1]
+	ldr	data2, [src1, off2]
+#ifdef __AARCH64EB__
+	rev	data3, data3
+#endif
+	sub	has_nul, data3, zeroones
+	orr	tmp, data3, REP8_7f
+	ldr	data1, [src1], 8
+	bics	has_nul, has_nul, tmp
+	ccmp	data1, data2, 0, eq
+	b.eq	L(loop_unaligned)
+
+	lsl	tmp, has_nul, shift
+#ifdef __AARCH64EB__
+	rev	tmp, tmp
+#endif
+	eor	diff, data1, data2
+	orr	syndrome, diff, tmp
+	cbnz	syndrome, L(end)
+L(tail):
+	ldr	data1, [src1]
+	neg	shift, shift
+	lsr	data2, data3, shift
+	lsr	has_nul, has_nul, shift
+#ifdef __AARCH64EB__
+	rev     data2, data2
+	rev	has_nul, has_nul
+#endif
+	eor	diff, data1, data2
+	orr	syndrome, diff, has_nul
+	b	L(end)
+
+L(done):
+	sub	result, data1, data2
+	ret
+SYM_FUNC_END(__pi_strcmp)
+SYM_FUNC_ALIAS_WEAK(strcmp, __pi_strcmp)
+EXPORT_SYMBOL_NOKASAN(strcmp)
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
new file mode 100644
index 0000000000..4919fe81ae
--- /dev/null
+++ b/arch/arm64/lib/strlen.S
@@ -0,0 +1,213 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2013-2021, Arm Limited.
+ *
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/98e4d6a5c13c8e54/string/aarch64/strlen.S
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/mte-def.h>
+
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64, unaligned accesses, min page size 4k.
+ */
+
+#define L(label) .L ## label
+
+/* Arguments and results.  */
+#define srcin		x0
+#define len		x0
+
+/* Locals and temporaries.  */
+#define src		x1
+#define data1		x2
+#define data2		x3
+#define has_nul1	x4
+#define has_nul2	x5
+#define tmp1		x4
+#define tmp2		x5
+#define tmp3		x6
+#define tmp4		x7
+#define zeroones	x8
+
+	/* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+	   (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+	   can be done in parallel across the entire word. A faster check
+	   (X - 1) & 0x80 is zero for non-NUL ASCII characters, but gives
+	   false hits for characters 129..255.	*/
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+#define REP8_80 0x8080808080808080
+
+/*
+ * When KASAN_HW_TAGS is in use, memory is checked at MTE_GRANULE_SIZE
+ * (16-byte) granularity, and we must ensure that no access straddles this
+ * alignment boundary.
+ */
+#ifdef CONFIG_KASAN_HW_TAGS
+#define MIN_PAGE_SIZE MTE_GRANULE_SIZE
+#else
+#define MIN_PAGE_SIZE 4096
+#endif
+
+	/* Since strings are short on average, we check the first 16 bytes
+	   of the string for a NUL character.  In order to do an unaligned ldp
+	   safely we have to do a page cross check first.  If there is a NUL
+	   byte we calculate the length from the 2 8-byte words using
+	   conditional select to reduce branch mispredictions (it is unlikely
+	   strlen will be repeatedly called on strings with the same length).
+
+	   If the string is longer than 16 bytes, we align src so don't need
+	   further page cross checks, and process 32 bytes per iteration
+	   using the fast NUL check.  If we encounter non-ASCII characters,
+	   fallback to a second loop using the full NUL check.
+
+	   If the page cross check fails, we read 16 bytes from an aligned
+	   address, remove any characters before the string, and continue
+	   in the main loop using aligned loads.  Since strings crossing a
+	   page in the first 16 bytes are rare (probability of
+	   16/MIN_PAGE_SIZE ~= 0.4%), this case does not need to be optimized.
+
+	   AArch64 systems have a minimum page size of 4k.  We don't bother
+	   checking for larger page sizes - the cost of setting up the correct
+	   page size is just not worth the extra gain from a small reduction in
+	   the cases taking the slow path.  Note that we only care about
+	   whether the first fetch, which may be misaligned, crosses a page
+	   boundary.  */
+
+SYM_FUNC_START(__pi_strlen)
+	and	tmp1, srcin, MIN_PAGE_SIZE - 1
+	mov	zeroones, REP8_01
+	cmp	tmp1, MIN_PAGE_SIZE - 16
+	b.gt	L(page_cross)
+	ldp	data1, data2, [srcin]
+#ifdef __AARCH64EB__
+	/* For big-endian, carry propagation (if the final byte in the
+	   string is 0x01) means we cannot use has_nul1/2 directly.
+	   Since we expect strings to be small and early-exit,
+	   byte-swap the data now so has_null1/2 will be correct.  */
+	rev	data1, data1
+	rev	data2, data2
+#endif
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	sub	tmp3, data2, zeroones
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	beq	L(main_loop_entry)
+
+	/* Enter with C = has_nul1 == 0.  */
+	csel	has_nul1, has_nul1, has_nul2, cc
+	mov	len, 8
+	rev	has_nul1, has_nul1
+	clz	tmp1, has_nul1
+	csel	len, xzr, len, cc
+	add	len, len, tmp1, lsr 3
+	ret
+
+	/* The inner loop processes 32 bytes per iteration and uses the fast
+	   NUL check.  If we encounter non-ASCII characters, use a second
+	   loop with the accurate NUL check.  */
+	.p2align 4
+L(main_loop_entry):
+	bic	src, srcin, 15
+	sub	src, src, 16
+L(main_loop):
+	ldp	data1, data2, [src, 32]!
+L(page_cross_entry):
+	sub	tmp1, data1, zeroones
+	sub	tmp3, data2, zeroones
+	orr	tmp2, tmp1, tmp3
+	tst	tmp2, zeroones, lsl 7
+	bne	1f
+	ldp	data1, data2, [src, 16]
+	sub	tmp1, data1, zeroones
+	sub	tmp3, data2, zeroones
+	orr	tmp2, tmp1, tmp3
+	tst	tmp2, zeroones, lsl 7
+	beq	L(main_loop)
+	add	src, src, 16
+1:
+	/* The fast check failed, so do the slower, accurate NUL check.	 */
+	orr	tmp2, data1, REP8_7f
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	beq	L(nonascii_loop)
+
+	/* Enter with C = has_nul1 == 0.  */
+L(tail):
+#ifdef __AARCH64EB__
+	/* For big-endian, carry propagation (if the final byte in the
+	   string is 0x01) means we cannot use has_nul1/2 directly.  The
+	   easiest way to get the correct byte is to byte-swap the data
+	   and calculate the syndrome a second time.  */
+	csel	data1, data1, data2, cc
+	rev	data1, data1
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	bic	has_nul1, tmp1, tmp2
+#else
+	csel	has_nul1, has_nul1, has_nul2, cc
+#endif
+	sub	len, src, srcin
+	rev	has_nul1, has_nul1
+	add	tmp2, len, 8
+	clz	tmp1, has_nul1
+	csel	len, len, tmp2, cc
+	add	len, len, tmp1, lsr 3
+	ret
+
+L(nonascii_loop):
+	ldp	data1, data2, [src, 16]!
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	sub	tmp3, data2, zeroones
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	bne	L(tail)
+	ldp	data1, data2, [src, 16]!
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, REP8_7f
+	sub	tmp3, data2, zeroones
+	orr	tmp4, data2, REP8_7f
+	bics	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	ccmp	has_nul2, 0, 0, eq
+	beq	L(nonascii_loop)
+	b	L(tail)
+
+	/* Load 16 bytes from [srcin & ~15] and force the bytes that precede
+	   srcin to 0x7f, so we ignore any NUL bytes before the string.
+	   Then continue in the aligned loop.  */
+L(page_cross):
+	bic	src, srcin, 15
+	ldp	data1, data2, [src]
+	lsl	tmp1, srcin, 3
+	mov	tmp4, -1
+#ifdef __AARCH64EB__
+	/* Big-endian.	Early bytes are at MSB.	 */
+	lsr	tmp1, tmp4, tmp1	/* Shift (tmp1 & 63).  */
+#else
+	/* Little-endian.  Early bytes are at LSB.  */
+	lsl	tmp1, tmp4, tmp1	/* Shift (tmp1 & 63).  */
+#endif
+	orr	tmp1, tmp1, REP8_80
+	orn	data1, data1, tmp1
+	orn	tmp2, data2, tmp1
+	tst	srcin, 8
+	csel	data1, data1, tmp4, eq
+	csel	data2, data2, tmp2, eq
+	b	L(page_cross_entry)
+SYM_FUNC_END(__pi_strlen)
+SYM_FUNC_ALIAS_WEAK(strlen, __pi_strlen)
+EXPORT_SYMBOL_NOKASAN(strlen)
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
new file mode 100644
index 0000000000..fe7bbc0b42
--- /dev/null
+++ b/arch/arm64/lib/strncmp.S
@@ -0,0 +1,310 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2013-2022, Arm Limited.
+ *
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/189dfefe37d54c5b/string/aarch64/strncmp.S
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64.
+ * MTE compatible.
+ */
+
+#define L(label) .L ## label
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+
+/* Parameters and result.  */
+#define src1		x0
+#define src2		x1
+#define limit		x2
+#define result		x0
+
+/* Internal variables.  */
+#define data1		x3
+#define data1w		w3
+#define data2		x4
+#define data2w		w4
+#define has_nul		x5
+#define diff		x6
+#define syndrome	x7
+#define tmp1		x8
+#define tmp2		x9
+#define tmp3		x10
+#define zeroones	x11
+#define pos		x12
+#define mask		x13
+#define endloop		x14
+#define count		mask
+#define offset		pos
+#define neg_offset	x15
+
+/* Define endian dependent shift operations.
+   On big-endian early bytes are at MSB and on little-endian LSB.
+   LS_FW means shifting towards early bytes.
+   LS_BK means shifting towards later bytes.
+   */
+#ifdef __AARCH64EB__
+#define LS_FW lsl
+#define LS_BK lsr
+#else
+#define LS_FW lsr
+#define LS_BK lsl
+#endif
+
+SYM_FUNC_START(__pi_strncmp)
+	cbz	limit, L(ret0)
+	eor	tmp1, src1, src2
+	mov	zeroones, #REP8_01
+	tst	tmp1, #7
+	and	count, src1, #7
+	b.ne	L(misaligned8)
+	cbnz	count, L(mutual_align)
+
+	/* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+	   (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+	   can be done in parallel across the entire word.  */
+	.p2align 4
+L(loop_aligned):
+	ldr	data1, [src1], #8
+	ldr	data2, [src2], #8
+L(start_realigned):
+	subs	limit, limit, #8
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, #REP8_7f
+	eor	diff, data1, data2	/* Non-zero if differences found.  */
+	csinv	endloop, diff, xzr, hi	/* Last Dword or differences.  */
+	bics	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
+	ccmp	endloop, #0, #0, eq
+	b.eq	L(loop_aligned)
+	/* End of main loop */
+
+L(full_check):
+#ifndef __AARCH64EB__
+	orr	syndrome, diff, has_nul
+	add	limit, limit, 8	/* Rewind limit to before last subs. */
+L(syndrome_check):
+	/* Limit was reached. Check if the NUL byte or the difference
+	   is before the limit. */
+	rev	syndrome, syndrome
+	rev	data1, data1
+	clz	pos, syndrome
+	rev	data2, data2
+	lsl	data1, data1, pos
+	cmp	limit, pos, lsr #3
+	lsl	data2, data2, pos
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
+	lsr	data1, data1, #56
+	sub	result, data1, data2, lsr #56
+	csel result, result, xzr, hi
+	ret
+#else
+	/* Not reached the limit, must have found the end or a diff.  */
+	tbz	limit, #63, L(not_limit)
+	add	tmp1, limit, 8
+	cbz	limit, L(not_limit)
+
+	lsl	limit, tmp1, #3	/* Bits -> bytes.  */
+	mov	mask, #~0
+	lsr	mask, mask, limit
+	bic	data1, data1, mask
+	bic	data2, data2, mask
+
+	/* Make sure that the NUL byte is marked in the syndrome.  */
+	orr	has_nul, has_nul, mask
+
+L(not_limit):
+	/* For big-endian we cannot use the trick with the syndrome value
+	   as carry-propagation can corrupt the upper bits if the trailing
+	   bytes in the string contain 0x01.  */
+	/* However, if there is no NUL byte in the dword, we can generate
+	   the result directly.  We can't just subtract the bytes as the
+	   MSB might be significant.  */
+	cbnz	has_nul, 1f
+	cmp	data1, data2
+	cset	result, ne
+	cneg	result, result, lo
+	ret
+1:
+	/* Re-compute the NUL-byte detection, using a byte-reversed value.  */
+	rev	tmp3, data1
+	sub	tmp1, tmp3, zeroones
+	orr	tmp2, tmp3, #REP8_7f
+	bic	has_nul, tmp1, tmp2
+	rev	has_nul, has_nul
+	orr	syndrome, diff, has_nul
+	clz	pos, syndrome
+	/* The most-significant-non-zero bit of the syndrome marks either the
+	   first bit that is different, or the top bit of the first zero byte.
+	   Shifting left now will bring the critical information into the
+	   top bits.  */
+L(end_quick):
+	lsl	data1, data1, pos
+	lsl	data2, data2, pos
+	/* But we need to zero-extend (char is unsigned) the value and then
+	   perform a signed 32-bit subtraction.  */
+	lsr	data1, data1, #56
+	sub	result, data1, data2, lsr #56
+	ret
+#endif
+
+L(mutual_align):
+	/* Sources are mutually aligned, but are not currently at an
+	   alignment boundary.  Round down the addresses and then mask off
+	   the bytes that precede the start point.
+	   We also need to adjust the limit calculations, but without
+	   overflowing if the limit is near ULONG_MAX.  */
+	bic	src1, src1, #7
+	bic	src2, src2, #7
+	ldr	data1, [src1], #8
+	neg	tmp3, count, lsl #3	/* 64 - bits(bytes beyond align). */
+	ldr	data2, [src2], #8
+	mov	tmp2, #~0
+	LS_FW	tmp2, tmp2, tmp3	/* Shift (count & 63).  */
+	/* Adjust the limit and ensure it doesn't overflow.  */
+	adds	limit, limit, count
+	csinv	limit, limit, xzr, lo
+	orr	data1, data1, tmp2
+	orr	data2, data2, tmp2
+	b	L(start_realigned)
+
+	.p2align 4
+	/* Don't bother with dwords for up to 16 bytes.  */
+L(misaligned8):
+	cmp	limit, #16
+	b.hs	L(try_misaligned_words)
+
+L(byte_loop):
+	/* Perhaps we can do better than this.  */
+	ldrb	data1w, [src1], #1
+	ldrb	data2w, [src2], #1
+	subs	limit, limit, #1
+	ccmp	data1w, #1, #0, hi	/* NZCV = 0b0000.  */
+	ccmp	data1w, data2w, #0, cs	/* NZCV = 0b0000.  */
+	b.eq	L(byte_loop)
+L(done):
+	sub	result, data1, data2
+	ret
+	/* Align the SRC1 to a dword by doing a bytewise compare and then do
+	   the dword loop.  */
+L(try_misaligned_words):
+	cbz	count, L(src1_aligned)
+
+	neg	count, count
+	and	count, count, #7
+	sub	limit, limit, count
+
+L(page_end_loop):
+	ldrb	data1w, [src1], #1
+	ldrb	data2w, [src2], #1
+	cmp	data1w, #1
+	ccmp	data1w, data2w, #0, cs	/* NZCV = 0b0000.  */
+	b.ne	L(done)
+	subs	count, count, #1
+	b.hi	L(page_end_loop)
+
+	/* The following diagram explains the comparison of misaligned strings.
+	   The bytes are shown in natural order. For little-endian, it is
+	   reversed in the registers. The "x" bytes are before the string.
+	   The "|" separates data that is loaded at one time.
+	   src1     | a a a a a a a a | b b b c c c c c | . . .
+	   src2     | x x x x x a a a   a a a a a b b b | c c c c c . . .
+
+	   After shifting in each step, the data looks like this:
+	                STEP_A              STEP_B              STEP_C
+	   data1    a a a a a a a a     b b b c c c c c     b b b c c c c c
+	   data2    a a a a a a a a     b b b 0 0 0 0 0     0 0 0 c c c c c
+
+	   The bytes with "0" are eliminated from the syndrome via mask.
+
+	   Align SRC2 down to 16 bytes. This way we can read 16 bytes at a
+	   time from SRC2. The comparison happens in 3 steps. After each step
+	   the loop can exit, or read from SRC1 or SRC2. */
+L(src1_aligned):
+	/* Calculate offset from 8 byte alignment to string start in bits. No
+	   need to mask offset since shifts are ignoring upper bits. */
+	lsl	offset, src2, #3
+	bic	src2, src2, #0xf
+	mov	mask, -1
+	neg	neg_offset, offset
+	ldr	data1, [src1], #8
+	ldp	tmp1, tmp2, [src2], #16
+	LS_BK	mask, mask, neg_offset
+	and	neg_offset, neg_offset, #63	/* Need actual value for cmp later. */
+	/* Skip the first compare if data in tmp1 is irrelevant. */
+	tbnz	offset, 6, L(misaligned_mid_loop)
+
+L(loop_misaligned):
+	/* STEP_A: Compare full 8 bytes when there is enough data from SRC2.*/
+	LS_FW	data2, tmp1, offset
+	LS_BK	tmp1, tmp2, neg_offset
+	subs	limit, limit, #8
+	orr	data2, data2, tmp1	/* 8 bytes from SRC2 combined from two regs.*/
+	sub	has_nul, data1, zeroones
+	eor	diff, data1, data2	/* Non-zero if differences found.  */
+	orr	tmp3, data1, #REP8_7f
+	csinv	endloop, diff, xzr, hi	/* If limit, set to all ones. */
+	bic	has_nul, has_nul, tmp3	/* Non-zero if NUL byte found in SRC1. */
+	orr	tmp3, endloop, has_nul
+	cbnz	tmp3, L(full_check)
+
+	ldr	data1, [src1], #8
+L(misaligned_mid_loop):
+	/* STEP_B: Compare first part of data1 to second part of tmp2. */
+	LS_FW	data2, tmp2, offset
+#ifdef __AARCH64EB__
+	/* For big-endian we do a byte reverse to avoid carry-propagation
+	problem described above. This way we can reuse the has_nul in the
+	next step and also use syndrome value trick at the end. */
+	rev	tmp3, data1
+	#define data1_fixed tmp3
+#else
+	#define data1_fixed data1
+#endif
+	sub	has_nul, data1_fixed, zeroones
+	orr	tmp3, data1_fixed, #REP8_7f
+	eor	diff, data2, data1	/* Non-zero if differences found.  */
+	bic	has_nul, has_nul, tmp3	/* Non-zero if NUL terminator.  */
+#ifdef __AARCH64EB__
+	rev	has_nul, has_nul
+#endif
+	cmp	limit, neg_offset, lsr #3
+	orr	syndrome, diff, has_nul
+	bic	syndrome, syndrome, mask	/* Ignore later bytes. */
+	csinv	tmp3, syndrome, xzr, hi	/* If limit, set to all ones. */
+	cbnz	tmp3, L(syndrome_check)
+
+	/* STEP_C: Compare second part of data1 to first part of tmp1. */
+	ldp	tmp1, tmp2, [src2], #16
+	cmp	limit, #8
+	LS_BK	data2, tmp1, neg_offset
+	eor	diff, data2, data1	/* Non-zero if differences found.  */
+	orr	syndrome, diff, has_nul
+	and	syndrome, syndrome, mask	/* Ignore earlier bytes. */
+	csinv	tmp3, syndrome, xzr, hi	/* If limit, set to all ones. */
+	cbnz	tmp3, L(syndrome_check)
+
+	ldr	data1, [src1], #8
+	sub	limit, limit, #8
+	b	L(loop_misaligned)
+
+#ifdef	__AARCH64EB__
+L(syndrome_check):
+	clz	pos, syndrome
+	cmp	pos, limit, lsl #3
+	b.lo	L(end_quick)
+#endif
+
+L(ret0):
+	mov	result, #0
+	ret
+SYM_FUNC_END(__pi_strncmp)
+SYM_FUNC_ALIAS_WEAK(strncmp, __pi_strncmp)
+EXPORT_SYMBOL_NOKASAN(strncmp)
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
new file mode 100644
index 0000000000..d5ac0e10a0
--- /dev/null
+++ b/arch/arm64/lib/strnlen.S
@@ -0,0 +1,162 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * determine the length of a fixed-size string
+ *
+ * Parameters:
+ *	x0 - const string pointer
+ *	x1 - maximal string length
+ * Returns:
+ *	x0 - the return length of specific string
+ */
+
+/* Arguments and results.  */
+srcin		.req	x0
+len		.req	x0
+limit		.req	x1
+
+/* Locals and temporaries.  */
+src		.req	x2
+data1		.req	x3
+data2		.req	x4
+data2a		.req	x5
+has_nul1	.req	x6
+has_nul2	.req	x7
+tmp1		.req	x8
+tmp2		.req	x9
+tmp3		.req	x10
+tmp4		.req	x11
+zeroones	.req	x12
+pos		.req	x13
+limit_wd	.req	x14
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+#define REP8_80 0x8080808080808080
+
+SYM_FUNC_START(__pi_strnlen)
+	cbz	limit, .Lhit_limit
+	mov	zeroones, #REP8_01
+	bic	src, srcin, #15
+	ands	tmp1, srcin, #15
+	b.ne	.Lmisaligned
+	/* Calculate the number of full and partial words -1.  */
+	sub	limit_wd, limit, #1 /* Limit != 0, so no underflow.  */
+	lsr	limit_wd, limit_wd, #4  /* Convert to Qwords.  */
+
+	/*
+	* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+	* (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+	* can be done in parallel across the entire word.
+	*/
+	/*
+	* The inner loop deals with two Dwords at a time.  This has a
+	* slightly higher start-up cost, but we should win quite quickly,
+	* especially on cores with a high number of issue slots per
+	* cycle, as we get much better parallelism out of the operations.
+	*/
+.Lloop:
+	ldp	data1, data2, [src], #16
+.Lrealigned:
+	sub	tmp1, data1, zeroones
+	orr	tmp2, data1, #REP8_7f
+	sub	tmp3, data2, zeroones
+	orr	tmp4, data2, #REP8_7f
+	bic	has_nul1, tmp1, tmp2
+	bic	has_nul2, tmp3, tmp4
+	subs	limit_wd, limit_wd, #1
+	orr	tmp1, has_nul1, has_nul2
+	ccmp	tmp1, #0, #0, pl    /* NZCV = 0000  */
+	b.eq	.Lloop
+
+	cbz	tmp1, .Lhit_limit   /* No null in final Qword.  */
+
+	/*
+	* We know there's a null in the final Qword. The easiest thing
+	* to do now is work out the length of the string and return
+	* MIN (len, limit).
+	*/
+	sub	len, src, srcin
+	cbz	has_nul1, .Lnul_in_data2
+CPU_BE( mov	data2, data1 )	/*perpare data to re-calculate the syndrome*/
+
+	sub	len, len, #8
+	mov	has_nul2, has_nul1
+.Lnul_in_data2:
+	/*
+	* For big-endian, carry propagation (if the final byte in the
+	* string is 0x01) means we cannot use has_nul directly.  The
+	* easiest way to get the correct byte is to byte-swap the data
+	* and calculate the syndrome a second time.
+	*/
+CPU_BE( rev	data2, data2 )
+CPU_BE( sub	tmp1, data2, zeroones )
+CPU_BE( orr	tmp2, data2, #REP8_7f )
+CPU_BE( bic	has_nul2, tmp1, tmp2 )
+
+	sub	len, len, #8
+	rev	has_nul2, has_nul2
+	clz	pos, has_nul2
+	add	len, len, pos, lsr #3       /* Bits to bytes.  */
+	cmp	len, limit
+	csel	len, len, limit, ls     /* Return the lower value.  */
+	ret
+
+.Lmisaligned:
+	/*
+	* Deal with a partial first word.
+	* We're doing two things in parallel here;
+	* 1) Calculate the number of words (but avoiding overflow if
+	* limit is near ULONG_MAX) - to do this we need to work out
+	* limit + tmp1 - 1 as a 65-bit value before shifting it;
+	* 2) Load and mask the initial data words - we force the bytes
+	* before the ones we are interested in to 0xff - this ensures
+	* early bytes will not hit any zero detection.
+	*/
+	ldp	data1, data2, [src], #16
+
+	sub	limit_wd, limit, #1
+	and	tmp3, limit_wd, #15
+	lsr	limit_wd, limit_wd, #4
+
+	add	tmp3, tmp3, tmp1
+	add	limit_wd, limit_wd, tmp3, lsr #4
+
+	neg	tmp4, tmp1
+	lsl	tmp4, tmp4, #3  /* Bytes beyond alignment -> bits.  */
+
+	mov	tmp2, #~0
+	/* Big-endian.  Early bytes are at MSB.  */
+CPU_BE( lsl	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
+	/* Little-endian.  Early bytes are at LSB.  */
+CPU_LE( lsr	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
+
+	cmp	tmp1, #8
+
+	orr	data1, data1, tmp2
+	orr	data2a, data2, tmp2
+
+	csinv	data1, data1, xzr, le
+	csel	data2, data2, data2a, le
+	b	.Lrealigned
+
+.Lhit_limit:
+	mov	len, limit
+	ret
+SYM_FUNC_END(__pi_strnlen)
+
+SYM_FUNC_ALIAS_WEAK(strnlen, __pi_strnlen)
+EXPORT_SYMBOL_NOKASAN(strnlen)
diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S
new file mode 100644
index 0000000000..a5123cf0ce
--- /dev/null
+++ b/arch/arm64/lib/strrchr.S
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/lib/strrchr.S
+ *
+ * Copyright (C) 1995-2000 Russell King
+ * Copyright (C) 2013 ARM Ltd.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Find the last occurrence of a character in a string.
+ *
+ * Parameters:
+ *	x0 - str
+ *	x1 - c
+ * Returns:
+ *	x0 - address of last occurrence of 'c' or 0
+ */
+SYM_FUNC_START(__pi_strrchr)
+	mov	x3, #0
+	and	w1, w1, #0xff
+1:	ldrb	w2, [x0], #1
+	cbz	w2, 2f
+	cmp	w2, w1
+	b.ne	1b
+	sub	x3, x0, #1
+	b	1b
+2:	mov	x0, x3
+	ret
+SYM_FUNC_END(__pi_strrchr)
+SYM_FUNC_ALIAS_WEAK(strrchr, __pi_strrchr)
+EXPORT_SYMBOL_NOKASAN(strrchr)
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
new file mode 100644
index 0000000000..a88613834f
--- /dev/null
+++ b/arch/arm64/lib/tishift.S
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+ *
+ * Copyright (C) 2017-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+
+SYM_FUNC_START(__ashlti3)
+	cbz	x2, 1f
+	mov	x3, #64
+	sub	x3, x3, x2
+	cmp	x3, #0
+	b.le	2f
+	lsl	x1, x1, x2
+	lsr	x3, x0, x3
+	lsl	x2, x0, x2
+	orr	x1, x1, x3
+	mov	x0, x2
+1:
+	ret
+2:
+	neg	w1, w3
+	mov	x2, #0
+	lsl	x1, x0, x1
+	mov	x0, x2
+	ret
+SYM_FUNC_END(__ashlti3)
+EXPORT_SYMBOL(__ashlti3)
+
+SYM_FUNC_START(__ashrti3)
+	cbz	x2, 1f
+	mov	x3, #64
+	sub	x3, x3, x2
+	cmp	x3, #0
+	b.le	2f
+	lsr	x0, x0, x2
+	lsl	x3, x1, x3
+	asr	x2, x1, x2
+	orr	x0, x0, x3
+	mov	x1, x2
+1:
+	ret
+2:
+	neg	w0, w3
+	asr	x2, x1, #63
+	asr	x0, x1, x0
+	mov	x1, x2
+	ret
+SYM_FUNC_END(__ashrti3)
+EXPORT_SYMBOL(__ashrti3)
+
+SYM_FUNC_START(__lshrti3)
+	cbz	x2, 1f
+	mov	x3, #64
+	sub	x3, x3, x2
+	cmp	x3, #0
+	b.le	2f
+	lsr	x0, x0, x2
+	lsl	x3, x1, x3
+	lsr	x2, x1, x2
+	orr	x0, x0, x3
+	mov	x1, x2
+1:
+	ret
+2:
+	neg	w0, w3
+	mov	x2, #0
+	lsr	x0, x1, x0
+	mov	x1, x2
+	ret
+SYM_FUNC_END(__lshrti3)
+EXPORT_SYMBOL(__lshrti3)
diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c
new file mode 100644
index 0000000000..7510d1a231
--- /dev/null
+++ b/arch/arm64/lib/uaccess_flushcache.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 ARM Ltd.
+ */
+
+#include <linux/uaccess.h>
+#include <asm/barrier.h>
+#include <asm/cacheflush.h>
+
+void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+{
+	/*
+	 * We assume this should not be called with @dst pointing to
+	 * non-cacheable memory, such that we don't need an explicit
+	 * barrier to order the cache maintenance against the memcpy.
+	 */
+	memcpy(dst, src, cnt);
+	dcache_clean_pop((unsigned long)dst, (unsigned long)dst + cnt);
+}
+EXPORT_SYMBOL_GPL(memcpy_flushcache);
+
+unsigned long __copy_user_flushcache(void *to, const void __user *from,
+				     unsigned long n)
+{
+	unsigned long rc;
+
+	rc = raw_copy_from_user(to, from, n);
+
+	/* See above */
+	dcache_clean_pop((unsigned long)to, (unsigned long)to + n - rc);
+	return rc;
+}
diff --git a/arch/arm64/lib/xor-neon.c b/arch/arm64/lib/xor-neon.c
new file mode 100644
index 0000000000..f9a53b7f98
--- /dev/null
+++ b/arch/arm64/lib/xor-neon.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * arch/arm64/lib/xor-neon.c
+ *
+ * Authors: Jackie Liu <liuyun01@kylinos.cn>
+ * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
+ */
+
+#include <linux/raid/xor.h>
+#include <linux/module.h>
+#include <asm/neon-intrinsics.h>
+
+static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_neon_4(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_neon_5(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4,
+	const unsigned long * __restrict p5)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+	uint64_t *dp5 = (uint64_t *)p5;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));
+
+		/* p1 ^= p5 */
+		v0 = veorq_u64(v0, vld1q_u64(dp5 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp5 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp5 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp5 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+		dp5 += 8;
+	} while (--lines > 0);
+}
+
+struct xor_block_template xor_block_inner_neon __ro_after_init = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_arm64_neon_2,
+	.do_3	= xor_arm64_neon_3,
+	.do_4	= xor_arm64_neon_4,
+	.do_5	= xor_arm64_neon_5,
+};
+EXPORT_SYMBOL(xor_block_inner_neon);
+
+static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
+{
+	uint64x2_t res;
+
+	asm(ARM64_ASM_PREAMBLE ".arch_extension sha3\n"
+	    "eor3 %0.16b, %1.16b, %2.16b, %3.16b"
+	    : "=w"(res) : "w"(p), "w"(q), "w"(r));
+	return res;
+}
+
+static void xor_arm64_eor3_3(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_eor3_4(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 + 0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 + 2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 + 4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_eor3_5(unsigned long bytes,
+	unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4,
+	const unsigned long * __restrict p5)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+	uint64_t *dp5 = (uint64_t *)p5;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* p1 ^= p4 ^ p5 */
+		v0 = eor3(v0, vld1q_u64(dp4 + 0), vld1q_u64(dp5 + 0));
+		v1 = eor3(v1, vld1q_u64(dp4 + 2), vld1q_u64(dp5 + 2));
+		v2 = eor3(v2, vld1q_u64(dp4 + 4), vld1q_u64(dp5 + 4));
+		v3 = eor3(v3, vld1q_u64(dp4 + 6), vld1q_u64(dp5 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+		dp5 += 8;
+	} while (--lines > 0);
+}
+
+static int __init xor_neon_init(void)
+{
+	if (IS_ENABLED(CONFIG_AS_HAS_SHA3) && cpu_have_named_feature(SHA3)) {
+		xor_block_inner_neon.do_3 = xor_arm64_eor3_3;
+		xor_block_inner_neon.do_4 = xor_arm64_eor3_4;
+		xor_block_inner_neon.do_5 = xor_arm64_eor3_5;
+	}
+	return 0;
+}
+module_init(xor_neon_init);
+
+static void __exit xor_neon_exit(void)
+{
+}
+module_exit(xor_neon_exit);
+
+MODULE_AUTHOR("Jackie Liu <liuyun01@kylinos.cn>");
+MODULE_DESCRIPTION("ARMv8 XOR Extensions");
+MODULE_LICENSE("GPL");