Adding upstream version 6.1.76.upstream/6.1.76

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

192 files changed, 25351 insertions, 0 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
new file mode 100644
index 000000000..5c8ee5a54
--- /dev/null
+++ b/arch/arm64/include/asm/Kbuild
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+generic-y += early_ioremap.h
+generic-y += mcs_spinlock.h
+generic-y += qrwlock.h
+generic-y += qspinlock.h
+generic-y += parport.h
+generic-y += user.h
+
+generated-y += cpucaps.h
+generated-y += sysreg-defs.h
diff --git a/arch/arm64/include/asm/acenv.h b/arch/arm64/include/asm/acenv.h
new file mode 100644
index 000000000..f1f810dc9
--- /dev/null
+++ b/arch/arm64/include/asm/acenv.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ARM64 specific ACPICA environments and implementation
+ *
+ * Copyright (C) 2014, Linaro Ltd.
+ *   Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *   Author: Graeme Gregory <graeme.gregory@linaro.org>
+ */
+
+#ifndef _ASM_ACENV_H
+#define _ASM_ACENV_H
+
+/* It is required unconditionally by ACPI core, update it when needed. */
+
+#endif /* _ASM_ACENV_H */
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
new file mode 100644
index 000000000..bd68e1b7f
--- /dev/null
+++ b/arch/arm64/include/asm/acpi.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Copyright (C) 2013-2014, Linaro Ltd.
+ *	Author: Al Stone <al.stone@linaro.org>
+ *	Author: Graeme Gregory <graeme.gregory@linaro.org>
+ *	Author: Hanjun Guo <hanjun.guo@linaro.org>
+ */
+
+#ifndef _ASM_ACPI_H
+#define _ASM_ACPI_H
+
+#include <linux/efi.h>
+#include <linux/memblock.h>
+#include <linux/psci.h>
+#include <linux/stddef.h>
+
+#include <asm/cputype.h>
+#include <asm/io.h>
+#include <asm/ptrace.h>
+#include <asm/smp_plat.h>
+#include <asm/tlbflush.h>
+
+/* Macros for consistency checks of the GICC subtable of MADT */
+
+/*
+ * MADT GICC minimum length refers to the MADT GICC structure table length as
+ * defined in the earliest ACPI version supported on arm64, ie ACPI 5.1.
+ *
+ * The efficiency_class member was added to the
+ * struct acpi_madt_generic_interrupt to represent the MADT GICC structure
+ * "Processor Power Efficiency Class" field, added in ACPI 6.0 whose offset
+ * is therefore used to delimit the MADT GICC structure minimum length
+ * appropriately.
+ */
+#define ACPI_MADT_GICC_MIN_LENGTH   offsetof(  \
+	struct acpi_madt_generic_interrupt, efficiency_class)
+
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \
+	(unsigned long)(entry) + (entry)->header.length > (end))
+
+#define ACPI_MADT_GICC_SPE  (offsetof(struct acpi_madt_generic_interrupt, \
+	spe_interrupt) + sizeof(u16))
+
+/* Basic configuration for ACPI */
+#ifdef	CONFIG_ACPI
+pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
+
+/* ACPI table mapping after acpi_permanent_mmap is set */
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
+#define acpi_os_ioremap acpi_os_ioremap
+
+typedef u64 phys_cpuid_t;
+#define PHYS_CPUID_INVALID INVALID_HWID
+
+#define acpi_strict 1	/* No out-of-spec workarounds on ARM64 */
+extern int acpi_disabled;
+extern int acpi_noirq;
+extern int acpi_pci_disabled;
+
+static inline void disable_acpi(void)
+{
+	acpi_disabled = 1;
+	acpi_pci_disabled = 1;
+	acpi_noirq = 1;
+}
+
+static inline void enable_acpi(void)
+{
+	acpi_disabled = 0;
+	acpi_pci_disabled = 0;
+	acpi_noirq = 0;
+}
+
+/*
+ * The ACPI processor driver for ACPI core code needs this macro
+ * to find out this cpu was already mapped (mapping from CPU hardware
+ * ID to CPU logical ID) or not.
+ */
+#define cpu_physical_id(cpu) cpu_logical_map(cpu)
+
+/*
+ * It's used from ACPI core in kdump to boot UP system with SMP kernel,
+ * with this check the ACPI core will not override the CPU index
+ * obtained from GICC with 0 and not print some error message as well.
+ * Since MADT must provide at least one GICC structure for GIC
+ * initialization, CPU will be always available in MADT on ARM64.
+ */
+static inline bool acpi_has_cpu_in_madt(void)
+{
+	return true;
+}
+
+struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu);
+static inline u32 get_acpi_id_for_cpu(unsigned int cpu)
+{
+	return	acpi_cpu_get_madt_gicc(cpu)->uid;
+}
+
+static inline void arch_fix_phys_package_id(int num, u32 slot) { }
+void __init acpi_init_cpus(void);
+int apei_claim_sea(struct pt_regs *regs);
+#else
+static inline void acpi_init_cpus(void) { }
+static inline int apei_claim_sea(struct pt_regs *regs) { return -ENOENT; }
+#endif /* CONFIG_ACPI */
+
+#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
+bool acpi_parking_protocol_valid(int cpu);
+void __init
+acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor);
+#else
+static inline bool acpi_parking_protocol_valid(int cpu) { return false; }
+static inline void
+acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor)
+{}
+#endif
+
+static inline const char *acpi_get_enable_method(int cpu)
+{
+	if (acpi_psci_present())
+		return "psci";
+
+	if (acpi_parking_protocol_valid(cpu))
+		return "parking-protocol";
+
+	return NULL;
+}
+
+#ifdef	CONFIG_ACPI_APEI
+/*
+ * acpi_disable_cmcff is used in drivers/acpi/apei/hest.c for disabling
+ * IA-32 Architecture Corrected Machine Check (CMC) Firmware-First mode
+ * with a kernel command line parameter "acpi=nocmcoff". But we don't
+ * have this IA-32 specific feature on ARM64, this definition is only
+ * for compatibility.
+ */
+#define acpi_disable_cmcff 1
+static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
+{
+	return __acpi_get_mem_attribute(addr);
+}
+#endif /* CONFIG_ACPI_APEI */
+
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+int acpi_numa_get_nid(unsigned int cpu);
+void acpi_map_cpus_to_nodes(void);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
+static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+static inline void acpi_map_cpus_to_nodes(void) { }
+#endif /* CONFIG_ACPI_NUMA */
+
+#define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE
+
+#endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
new file mode 100644
index 000000000..3622e9f4f
--- /dev/null
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -0,0 +1,264 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ALTERNATIVE_MACROS_H
+#define __ASM_ALTERNATIVE_MACROS_H
+
+#include <linux/const.h>
+#include <vdso/bits.h>
+
+#include <asm/cpucaps.h>
+#include <asm/insn-def.h>
+
+/*
+ * Binutils 2.27.0 can't handle a 'UL' suffix on constants, so for the assembly
+ * macros below we must use we must use `(1 << ARM64_CB_SHIFT)`.
+ */
+#define ARM64_CB_SHIFT	15
+#define ARM64_CB_BIT	BIT(ARM64_CB_SHIFT)
+
+#if ARM64_NCAPS >= ARM64_CB_BIT
+#error "cpucaps have overflown ARM64_CB_BIT"
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+#define ALTINSTR_ENTRY(feature)					              \
+	" .word 661b - .\n"				/* label           */ \
+	" .word 663f - .\n"				/* new instruction */ \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+#define ALTINSTR_ENTRY_CB(feature, cb)					      \
+	" .word 661b - .\n"				/* label           */ \
+	" .word " __stringify(cb) "- .\n"		/* callback */	      \
+	" .hword " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte 662b-661b\n"				/* source len      */ \
+	" .byte 664f-663f\n"				/* replacement len */
+
+/*
+ * alternative assembly primitive:
+ *
+ * If any of these .org directive fail, it means that insn1 and insn2
+ * don't have the same length. This used to be written as
+ *
+ * .if ((664b-663b) != (662b-661b))
+ * 	.error "Alternatives instruction length mismatch"
+ * .endif
+ *
+ * but most assemblers die if insn1 or insn2 have a .inst. This should
+ * be fixed in a binutils release posterior to 2.25.51.0.2 (anything
+ * containing commit 4e4d08cf7399b606 or c1baaddf8861).
+ *
+ * Alternatives with callbacks do not generate replacement instructions.
+ */
+#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled)	\
+	".if "__stringify(cfg_enabled)" == 1\n"				\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature)						\
+	".popsection\n"							\
+	".subsection 1\n"						\
+	"663:\n\t"							\
+	newinstr "\n"							\
+	"664:\n\t"							\
+	".org	. - (664b-663b) + (662b-661b)\n\t"			\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
+	".endif\n"
+
+#define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
+	".if "__stringify(cfg_enabled)" == 1\n"				\
+	"661:\n\t"							\
+	oldinstr "\n"							\
+	"662:\n"							\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY_CB(feature, cb)					\
+	".popsection\n"							\
+	"663:\n\t"							\
+	"664:\n\t"							\
+	".endif\n"
+
+#define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...)	\
+	__ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg))
+
+#define ALTERNATIVE_CB(oldinstr, feature, cb) \
+	__ALTERNATIVE_CFG_CB(oldinstr, (1 << ARM64_CB_SHIFT) | (feature), 1, cb)
+#else
+
+#include <asm/assembler.h>
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+	.word \orig_offset - .
+	.word \alt_offset - .
+	.hword (\feature)
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+.macro alternative_insn insn1, insn2, cap, enable = 1
+	.if \enable
+661:	\insn1
+662:	.pushsection .altinstructions, "a"
+	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+	.popsection
+	.subsection 1
+663:	\insn2
+664:	.org	. - (664b-663b) + (662b-661b)
+	.org	. - (662b-661b) + (664b-663b)
+	.previous
+	.endif
+.endm
+
+/*
+ * Alternative sequences
+ *
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
+ *
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ *    sequence.
+ *
+ * 2. Not contain a branch target that is used outside of the
+ *    alternative sequence it is defined in (branches into an
+ *    alternative sequence are not fixed up).
+ */
+
+/*
+ * Begin an alternative code sequence.
+ */
+.macro alternative_if_not cap
+	.set .Lasm_alt_mode, 0
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
+	.popsection
+661:
+.endm
+
+.macro alternative_if cap
+	.set .Lasm_alt_mode, 1
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+	.popsection
+	.subsection 1
+	.align 2	/* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
+.macro alternative_cb cap, cb
+	.set .Lasm_alt_mode, 0
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 661f, \cb, (1 << ARM64_CB_SHIFT) | \cap, 662f-661f, 0
+	.popsection
+661:
+.endm
+
+/*
+ * Provide the other half of the alternative code sequence.
+ */
+.macro alternative_else
+662:
+	.if .Lasm_alt_mode==0
+	.subsection 1
+	.else
+	.previous
+	.endif
+663:
+.endm
+
+/*
+ * Complete an alternative code sequence.
+ */
+.macro alternative_endif
+664:
+	.org	. - (664b-663b) + (662b-661b)
+	.org	. - (662b-661b) + (664b-663b)
+	.if .Lasm_alt_mode==0
+	.previous
+	.endif
+.endm
+
+/*
+ * Callback-based alternative epilogue
+ */
+.macro alternative_cb_end
+662:
+.endm
+
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+	nops	(662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
+#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
+	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
+
+#endif  /*  __ASSEMBLY__  */
+
+/*
+ * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature));
+ *
+ * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature, CONFIG_FOO));
+ * N.B. If CONFIG_FOO is specified, but not selected, the whole block
+ *      will be omitted, including oldinstr.
+ */
+#define ALTERNATIVE(oldinstr, newinstr, ...)   \
+	_ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+static __always_inline bool
+alternative_has_feature_likely(unsigned long feature)
+{
+	compiletime_assert(feature < ARM64_NCAPS,
+			   "feature must be < ARM64_NCAPS");
+
+	asm_volatile_goto(
+	ALTERNATIVE_CB("b	%l[l_no]", %[feature], alt_cb_patch_nops)
+	:
+	: [feature] "i" (feature)
+	:
+	: l_no);
+
+	return true;
+l_no:
+	return false;
+}
+
+static __always_inline bool
+alternative_has_feature_unlikely(unsigned long feature)
+{
+	compiletime_assert(feature < ARM64_NCAPS,
+			   "feature must be < ARM64_NCAPS");
+
+	asm_volatile_goto(
+	ALTERNATIVE("nop", "b	%l[l_yes]", %[feature])
+	:
+	: [feature] "i" (feature)
+	:
+	: l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_ALTERNATIVE_MACROS_H */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
new file mode 100644
index 000000000..a38b92e11
--- /dev/null
+++ b/arch/arm64/include/asm/alternative.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ALTERNATIVE_H
+#define __ASM_ALTERNATIVE_H
+
+#include <asm/alternative-macros.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+struct alt_instr {
+	s32 orig_offset;	/* offset to original instruction */
+	s32 alt_offset;		/* offset to replacement instruction */
+	u16 cpufeature;		/* cpufeature bit set for replacement */
+	u8  orig_len;		/* size of original instruction(s) */
+	u8  alt_len;		/* size of new instruction(s), <= orig_len */
+};
+
+typedef void (*alternative_cb_t)(struct alt_instr *alt,
+				 __le32 *origptr, __le32 *updptr, int nr_inst);
+
+void __init apply_boot_alternatives(void);
+void __init apply_alternatives_all(void);
+bool alternative_is_applied(u16 cpufeature);
+
+#ifdef CONFIG_MODULES
+void apply_alternatives_module(void *start, size_t length);
+#else
+static inline void apply_alternatives_module(void *start, size_t length) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_ALTERNATIVE_H */
diff --git a/arch/arm64/include/asm/apple_m1_pmu.h b/arch/arm64/include/asm/apple_m1_pmu.h
new file mode 100644
index 000000000..99483b19b
--- /dev/null
+++ b/arch/arm64/include/asm/apple_m1_pmu.h
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __ASM_APPLE_M1_PMU_h
+#define __ASM_APPLE_M1_PMU_h
+
+#include <linux/bits.h>
+#include <asm/sysreg.h>
+
+/* Counters */
+#define SYS_IMP_APL_PMC0_EL1	sys_reg(3, 2, 15, 0, 0)
+#define SYS_IMP_APL_PMC1_EL1	sys_reg(3, 2, 15, 1, 0)
+#define SYS_IMP_APL_PMC2_EL1	sys_reg(3, 2, 15, 2, 0)
+#define SYS_IMP_APL_PMC3_EL1	sys_reg(3, 2, 15, 3, 0)
+#define SYS_IMP_APL_PMC4_EL1	sys_reg(3, 2, 15, 4, 0)
+#define SYS_IMP_APL_PMC5_EL1	sys_reg(3, 2, 15, 5, 0)
+#define SYS_IMP_APL_PMC6_EL1	sys_reg(3, 2, 15, 6, 0)
+#define SYS_IMP_APL_PMC7_EL1	sys_reg(3, 2, 15, 7, 0)
+#define SYS_IMP_APL_PMC8_EL1	sys_reg(3, 2, 15, 9, 0)
+#define SYS_IMP_APL_PMC9_EL1	sys_reg(3, 2, 15, 10, 0)
+
+/* Core PMC control register */
+#define SYS_IMP_APL_PMCR0_EL1	sys_reg(3, 1, 15, 0, 0)
+#define PMCR0_CNT_ENABLE_0_7	GENMASK(7, 0)
+#define PMCR0_IMODE		GENMASK(10, 8)
+#define PMCR0_IMODE_OFF		0
+#define PMCR0_IMODE_PMI		1
+#define PMCR0_IMODE_AIC		2
+#define PMCR0_IMODE_HALT	3
+#define PMCR0_IMODE_FIQ		4
+#define PMCR0_IACT		BIT(11)
+#define PMCR0_PMI_ENABLE_0_7	GENMASK(19, 12)
+#define PMCR0_STOP_CNT_ON_PMI	BIT(20)
+#define PMCR0_CNT_GLOB_L2C_EVT	BIT(21)
+#define PMCR0_DEFER_PMI_TO_ERET	BIT(22)
+#define PMCR0_ALLOW_CNT_EN_EL0	BIT(30)
+#define PMCR0_CNT_ENABLE_8_9	GENMASK(33, 32)
+#define PMCR0_PMI_ENABLE_8_9	GENMASK(45, 44)
+
+#define SYS_IMP_APL_PMCR1_EL1	sys_reg(3, 1, 15, 1, 0)
+#define PMCR1_COUNT_A64_EL0_0_7	GENMASK(15, 8)
+#define PMCR1_COUNT_A64_EL1_0_7	GENMASK(23, 16)
+#define PMCR1_COUNT_A64_EL0_8_9	GENMASK(41, 40)
+#define PMCR1_COUNT_A64_EL1_8_9	GENMASK(49, 48)
+
+#define SYS_IMP_APL_PMCR2_EL1	sys_reg(3, 1, 15, 2, 0)
+#define SYS_IMP_APL_PMCR3_EL1	sys_reg(3, 1, 15, 3, 0)
+#define SYS_IMP_APL_PMCR4_EL1	sys_reg(3, 1, 15, 4, 0)
+
+#define SYS_IMP_APL_PMESR0_EL1	sys_reg(3, 1, 15, 5, 0)
+#define PMESR0_EVT_CNT_2	GENMASK(7, 0)
+#define PMESR0_EVT_CNT_3	GENMASK(15, 8)
+#define PMESR0_EVT_CNT_4	GENMASK(23, 16)
+#define PMESR0_EVT_CNT_5	GENMASK(31, 24)
+
+#define SYS_IMP_APL_PMESR1_EL1	sys_reg(3, 1, 15, 6, 0)
+#define PMESR1_EVT_CNT_6	GENMASK(7, 0)
+#define PMESR1_EVT_CNT_7	GENMASK(15, 8)
+#define PMESR1_EVT_CNT_8	GENMASK(23, 16)
+#define PMESR1_EVT_CNT_9	GENMASK(31, 24)
+
+#define SYS_IMP_APL_PMSR_EL1	sys_reg(3, 1, 15, 13, 0)
+#define PMSR_OVERFLOW		GENMASK(9, 0)
+
+#endif /* __ASM_APPLE_M1_PMU_h */
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
new file mode 100644
index 000000000..48d4473e8
--- /dev/null
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/arch_gicv3.h
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ */
+#ifndef __ASM_ARCH_GICV3_H
+#define __ASM_ARCH_GICV3_H
+
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/irqchip/arm-gic-common.h>
+#include <linux/stringify.h>
+#include <asm/barrier.h>
+#include <asm/cacheflush.h>
+
+#define read_gicreg(r)			read_sysreg_s(SYS_ ## r)
+#define write_gicreg(v, r)		write_sysreg_s(v, SYS_ ## r)
+
+/*
+ * Low-level accessors
+ *
+ * These system registers are 32 bits, but we make sure that the compiler
+ * sets the GP register's most significant bits to 0 with an explicit cast.
+ */
+
+static __always_inline void gic_write_dir(u32 irq)
+{
+	write_sysreg_s(irq, SYS_ICC_DIR_EL1);
+	isb();
+}
+
+static inline u64 gic_read_iar_common(void)
+{
+	u64 irqstat;
+
+	irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
+	dsb(sy);
+	return irqstat;
+}
+
+/*
+ * Cavium ThunderX erratum 23154
+ *
+ * The gicv3 of ThunderX requires a modified version for reading the
+ * IAR status to ensure data synchronization (access to icc_iar1_el1
+ * is not sync'ed before and after).
+ *
+ * Erratum 38545
+ *
+ * When a IAR register read races with a GIC interrupt RELEASE event,
+ * GIC-CPU interface could wrongly return a valid INTID to the CPU
+ * for an interrupt that is already released(non activated) instead of 0x3ff.
+ *
+ * To workaround this, return a valid interrupt ID only if there is a change
+ * in the active priority list after the IAR read.
+ *
+ * Common function used for both the workarounds since,
+ * 1. On Thunderx 88xx 1.x both erratas are applicable.
+ * 2. Having extra nops doesn't add any side effects for Silicons where
+ *    erratum 23154 is not applicable.
+ */
+static inline u64 gic_read_iar_cavium_thunderx(void)
+{
+	u64 irqstat, apr;
+
+	apr = read_sysreg_s(SYS_ICC_AP1R0_EL1);
+	nops(8);
+	irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
+	nops(4);
+	mb();
+
+	/* Max priority groups implemented is only 32 */
+	if (likely(apr != read_sysreg_s(SYS_ICC_AP1R0_EL1)))
+		return irqstat;
+
+	return 0x3ff;
+}
+
+static inline void gic_write_ctlr(u32 val)
+{
+	write_sysreg_s(val, SYS_ICC_CTLR_EL1);
+	isb();
+}
+
+static inline u32 gic_read_ctlr(void)
+{
+	return read_sysreg_s(SYS_ICC_CTLR_EL1);
+}
+
+static inline void gic_write_grpen1(u32 val)
+{
+	write_sysreg_s(val, SYS_ICC_IGRPEN1_EL1);
+	isb();
+}
+
+static inline void gic_write_sgi1r(u64 val)
+{
+	write_sysreg_s(val, SYS_ICC_SGI1R_EL1);
+}
+
+static inline u32 gic_read_sre(void)
+{
+	return read_sysreg_s(SYS_ICC_SRE_EL1);
+}
+
+static inline void gic_write_sre(u32 val)
+{
+	write_sysreg_s(val, SYS_ICC_SRE_EL1);
+	isb();
+}
+
+static inline void gic_write_bpr1(u32 val)
+{
+	write_sysreg_s(val, SYS_ICC_BPR1_EL1);
+}
+
+static inline u32 gic_read_pmr(void)
+{
+	return read_sysreg_s(SYS_ICC_PMR_EL1);
+}
+
+static __always_inline void gic_write_pmr(u32 val)
+{
+	write_sysreg_s(val, SYS_ICC_PMR_EL1);
+}
+
+static inline u32 gic_read_rpr(void)
+{
+	return read_sysreg_s(SYS_ICC_RPR_EL1);
+}
+
+#define gic_read_typer(c)		readq_relaxed(c)
+#define gic_write_irouter(v, c)		writeq_relaxed(v, c)
+#define gic_read_lpir(c)		readq_relaxed(c)
+#define gic_write_lpir(v, c)		writeq_relaxed(v, c)
+
+#define gic_flush_dcache_to_poc(a,l)	\
+	dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
+
+#define gits_read_baser(c)		readq_relaxed(c)
+#define gits_write_baser(v, c)		writeq_relaxed(v, c)
+
+#define gits_read_cbaser(c)		readq_relaxed(c)
+#define gits_write_cbaser(v, c)		writeq_relaxed(v, c)
+
+#define gits_write_cwriter(v, c)	writeq_relaxed(v, c)
+
+#define gicr_read_propbaser(c)		readq_relaxed(c)
+#define gicr_write_propbaser(v, c)	writeq_relaxed(v, c)
+
+#define gicr_write_pendbaser(v, c)	writeq_relaxed(v, c)
+#define gicr_read_pendbaser(c)		readq_relaxed(c)
+
+#define gicr_write_vpropbaser(v, c)	writeq_relaxed(v, c)
+#define gicr_read_vpropbaser(c)		readq_relaxed(c)
+
+#define gicr_write_vpendbaser(v, c)	writeq_relaxed(v, c)
+#define gicr_read_vpendbaser(c)		readq_relaxed(c)
+
+static inline bool gic_prio_masking_enabled(void)
+{
+	return system_uses_irq_prio_masking();
+}
+
+static inline void gic_pmr_mask_irqs(void)
+{
+	BUILD_BUG_ON(GICD_INT_DEF_PRI < (__GIC_PRIO_IRQOFF |
+					 GIC_PRIO_PSR_I_SET));
+	BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON);
+	/*
+	 * Need to make sure IRQON allows IRQs when SCR_EL3.FIQ is cleared
+	 * and non-secure PMR accesses are not subject to the shifts that
+	 * are applied to IRQ priorities
+	 */
+	BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) >= GIC_PRIO_IRQON);
+	/*
+	 * Same situation as above, but now we make sure that we can mask
+	 * regular interrupts.
+	 */
+	BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) < (__GIC_PRIO_IRQOFF_NS |
+							 GIC_PRIO_PSR_I_SET));
+	gic_write_pmr(GIC_PRIO_IRQOFF);
+}
+
+static inline void gic_arch_enable_irqs(void)
+{
+	asm volatile ("msr daifclr, #3" : : : "memory");
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
new file mode 100644
index 000000000..af1fafbe7
--- /dev/null
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -0,0 +1,235 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/arch_timer.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+#ifndef __ASM_ARCH_TIMER_H
+#define __ASM_ARCH_TIMER_H
+
+#include <asm/barrier.h>
+#include <asm/hwcap.h>
+#include <asm/sysreg.h>
+
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/smp.h>
+#include <linux/types.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
+#define has_erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h);					\
+	})
+
+#define erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h) ? ({ isb(); __wa->h;}) : arch_timer_##h; \
+	})
+
+#else
+#define has_erratum_handler(h)			   false
+#define erratum_handler(h)			   (arch_timer_##h)
+#endif
+
+enum arch_timer_erratum_match_type {
+	ate_match_dt,
+	ate_match_local_cap_id,
+	ate_match_acpi_oem_info,
+};
+
+struct clock_event_device;
+
+struct arch_timer_erratum_workaround {
+	enum arch_timer_erratum_match_type match_type;
+	const void *id;
+	const char *desc;
+	u64 (*read_cntpct_el0)(void);
+	u64 (*read_cntvct_el0)(void);
+	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
+	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
+	bool disable_compat_vdso;
+};
+
+DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
+		timer_unstable_counter_workaround);
+
+static inline notrace u64 arch_timer_read_cntpct_el0(void)
+{
+	u64 cnt;
+
+	asm volatile(ALTERNATIVE("isb\n mrs %0, cntpct_el0",
+				 "nop\n" __mrs_s("%0", SYS_CNTPCTSS_EL0),
+				 ARM64_HAS_ECV)
+		     : "=r" (cnt));
+
+	return cnt;
+}
+
+static inline notrace u64 arch_timer_read_cntvct_el0(void)
+{
+	u64 cnt;
+
+	asm volatile(ALTERNATIVE("isb\n mrs %0, cntvct_el0",
+				 "nop\n" __mrs_s("%0", SYS_CNTVCTSS_EL0),
+				 ARM64_HAS_ECV)
+		     : "=r" (cnt));
+
+	return cnt;
+}
+
+#define arch_timer_reg_read_stable(reg)					\
+	({								\
+		u64 _val;						\
+									\
+		preempt_disable_notrace();				\
+		_val = erratum_handler(read_ ## reg)();			\
+		preempt_enable_notrace();				\
+									\
+		_val;							\
+	})
+
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code.
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u64 val)
+{
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			write_sysreg(val, cntp_ctl_el0);
+			isb();
+			break;
+		case ARCH_TIMER_REG_CVAL:
+			write_sysreg(val, cntp_cval_el0);
+			break;
+		default:
+			BUILD_BUG();
+		}
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			write_sysreg(val, cntv_ctl_el0);
+			isb();
+			break;
+		case ARCH_TIMER_REG_CVAL:
+			write_sysreg(val, cntv_cval_el0);
+			break;
+		default:
+			BUILD_BUG();
+		}
+	} else {
+		BUILD_BUG();
+	}
+}
+
+static __always_inline
+u64 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
+{
+	if (access == ARCH_TIMER_PHYS_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			return read_sysreg(cntp_ctl_el0);
+		default:
+			BUILD_BUG();
+		}
+	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
+		switch (reg) {
+		case ARCH_TIMER_REG_CTRL:
+			return read_sysreg(cntv_ctl_el0);
+		default:
+			BUILD_BUG();
+		}
+	}
+
+	BUILD_BUG();
+	unreachable();
+}
+
+static inline u32 arch_timer_get_cntfrq(void)
+{
+	return read_sysreg(cntfrq_el0);
+}
+
+static inline u32 arch_timer_get_cntkctl(void)
+{
+	return read_sysreg(cntkctl_el1);
+}
+
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
+	write_sysreg(cntkctl, cntkctl_el1);
+	isb();
+}
+
+static __always_inline u64 __arch_counter_get_cntpct_stable(void)
+{
+	u64 cnt;
+
+	cnt = arch_timer_reg_read_stable(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static __always_inline u64 __arch_counter_get_cntpct(void)
+{
+	u64 cnt;
+
+	asm volatile(ALTERNATIVE("isb\n mrs %0, cntpct_el0",
+				 "nop\n" __mrs_s("%0", SYS_CNTPCTSS_EL0),
+				 ARM64_HAS_ECV)
+		     : "=r" (cnt));
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static __always_inline u64 __arch_counter_get_cntvct_stable(void)
+{
+	u64 cnt;
+
+	cnt = arch_timer_reg_read_stable(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static __always_inline u64 __arch_counter_get_cntvct(void)
+{
+	u64 cnt;
+
+	asm volatile(ALTERNATIVE("isb\n mrs %0, cntvct_el0",
+				 "nop\n" __mrs_s("%0", SYS_CNTVCTSS_EL0),
+				 ARM64_HAS_ECV)
+		     : "=r" (cnt));
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static inline int arch_timer_arch_init(void)
+{
+	return 0;
+}
+
+static inline void arch_timer_set_evtstrm_feature(void)
+{
+	cpu_set_named_feature(EVTSTRM);
+#ifdef CONFIG_COMPAT
+	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
+#endif
+}
+
+static inline bool arch_timer_have_evtstrm_feature(void)
+{
+	return cpu_have_named_feature(EVTSTRM);
+}
+#endif
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h
new file mode 100644
index 000000000..109e2a445
--- /dev/null
+++ b/arch/arm64/include/asm/archrandom.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARCHRANDOM_H
+#define _ASM_ARCHRANDOM_H
+
+#include <linux/arm-smccc.h>
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <asm/cpufeature.h>
+
+#define ARM_SMCCC_TRNG_MIN_VERSION	0x10000UL
+
+extern bool smccc_trng_available;
+
+static inline bool __init smccc_probe_trng(void)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_VERSION, &res);
+	if ((s32)res.a0 < 0)
+		return false;
+
+	return res.a0 >= ARM_SMCCC_TRNG_MIN_VERSION;
+}
+
+static inline bool __arm64_rndr(unsigned long *v)
+{
+	bool ok;
+
+	/*
+	 * Reads of RNDR set PSTATE.NZCV to 0b0000 on success,
+	 * and set PSTATE.NZCV to 0b0100 otherwise.
+	 */
+	asm volatile(
+		__mrs_s("%0", SYS_RNDR_EL0) "\n"
+	"	cset %w1, ne\n"
+	: "=r" (*v), "=r" (ok)
+	:
+	: "cc");
+
+	return ok;
+}
+
+static inline bool __arm64_rndrrs(unsigned long *v)
+{
+	bool ok;
+
+	/*
+	 * Reads of RNDRRS set PSTATE.NZCV to 0b0000 on success,
+	 * and set PSTATE.NZCV to 0b0100 otherwise.
+	 */
+	asm volatile(
+		__mrs_s("%0", SYS_RNDRRS_EL0) "\n"
+	"	cset %w1, ne\n"
+	: "=r" (*v), "=r" (ok)
+	:
+	: "cc");
+
+	return ok;
+}
+
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
+{
+	/*
+	 * Only support the generic interface after we have detected
+	 * the system wide capability, avoiding complexity with the
+	 * cpufeature code and with potential scheduling between CPUs
+	 * with and without the feature.
+	 */
+	if (max_longs && cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndr(v))
+		return 1;
+	return 0;
+}
+
+static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+	if (!max_longs)
+		return 0;
+
+	/*
+	 * We prefer the SMCCC call, since its semantics (return actual
+	 * hardware backed entropy) is closer to the idea behind this
+	 * function here than what even the RNDRSS register provides
+	 * (the output of a pseudo RNG freshly seeded by a TRNG).
+	 */
+	if (smccc_trng_available) {
+		struct arm_smccc_res res;
+
+		max_longs = min_t(size_t, 3, max_longs);
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, max_longs * 64, &res);
+		if ((int)res.a0 >= 0) {
+			switch (max_longs) {
+			case 3:
+				*v++ = res.a1;
+				fallthrough;
+			case 2:
+				*v++ = res.a2;
+				fallthrough;
+			case 1:
+				*v++ = res.a3;
+				break;
+			}
+			return max_longs;
+		}
+	}
+
+	/*
+	 * RNDRRS is not backed by an entropy source but by a DRBG that is
+	 * reseeded after each invocation. This is not a 100% fit but good
+	 * enough to implement this API if no other entropy source exists.
+	 */
+	if (cpus_have_const_cap(ARM64_HAS_RNG) && __arm64_rndrrs(v))
+		return 1;
+
+	return 0;
+}
+
+static inline bool __init __early_cpu_has_rndr(void)
+{
+	/* Open code as we run prior to the first call to cpufeature. */
+	unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1);
+	return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf;
+}
+
+static inline size_t __init __must_check
+arch_get_random_seed_longs_early(unsigned long *v, size_t max_longs)
+{
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (!max_longs)
+		return 0;
+
+	if (smccc_trng_available) {
+		struct arm_smccc_res res;
+
+		max_longs = min_t(size_t, 3, max_longs);
+		arm_smccc_1_1_invoke(ARM_SMCCC_TRNG_RND64, max_longs * 64, &res);
+		if ((int)res.a0 >= 0) {
+			switch (max_longs) {
+			case 3:
+				*v++ = res.a1;
+				fallthrough;
+			case 2:
+				*v++ = res.a2;
+				fallthrough;
+			case 1:
+				*v++ = res.a3;
+				break;
+			}
+			return max_longs;
+		}
+	}
+
+	if (__early_cpu_has_rndr() && __arm64_rndr(v))
+		return 1;
+
+	return 0;
+}
+#define arch_get_random_seed_longs_early arch_get_random_seed_longs_early
+
+#endif /* _ASM_ARCHRANDOM_H */
diff --git a/arch/arm64/include/asm/arm-cci.h b/arch/arm64/include/asm/arm-cci.h
new file mode 100644
index 000000000..6d4abbd0c
--- /dev/null
+++ b/arch/arm64/include/asm/arm-cci.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/arm-cci.h
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ */
+
+#ifndef __ASM_ARM_CCI_H
+#define __ASM_ARM_CCI_H
+
+static inline bool platform_has_secure_cci_access(void)
+{
+	return false;
+}
+
+#endif
diff --git a/arch/arm64/include/asm/arm_dsu_pmu.h b/arch/arm64/include/asm/arm_dsu_pmu.h
new file mode 100644
index 000000000..16cdedd5f
--- /dev/null
+++ b/arch/arm64/include/asm/arm_dsu_pmu.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU Low level register access routines.
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Author: Suzuki K Poulose <suzuki.poulose@arm.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <asm/sysreg.h>
+
+
+#define CLUSTERPMCR_EL1			sys_reg(3, 0, 15, 5, 0)
+#define CLUSTERPMCNTENSET_EL1		sys_reg(3, 0, 15, 5, 1)
+#define CLUSTERPMCNTENCLR_EL1		sys_reg(3, 0, 15, 5, 2)
+#define CLUSTERPMOVSSET_EL1		sys_reg(3, 0, 15, 5, 3)
+#define CLUSTERPMOVSCLR_EL1		sys_reg(3, 0, 15, 5, 4)
+#define CLUSTERPMSELR_EL1		sys_reg(3, 0, 15, 5, 5)
+#define CLUSTERPMINTENSET_EL1		sys_reg(3, 0, 15, 5, 6)
+#define CLUSTERPMINTENCLR_EL1		sys_reg(3, 0, 15, 5, 7)
+#define CLUSTERPMCCNTR_EL1		sys_reg(3, 0, 15, 6, 0)
+#define CLUSTERPMXEVTYPER_EL1		sys_reg(3, 0, 15, 6, 1)
+#define CLUSTERPMXEVCNTR_EL1		sys_reg(3, 0, 15, 6, 2)
+#define CLUSTERPMMDCR_EL1		sys_reg(3, 0, 15, 6, 3)
+#define CLUSTERPMCEID0_EL1		sys_reg(3, 0, 15, 6, 4)
+#define CLUSTERPMCEID1_EL1		sys_reg(3, 0, 15, 6, 5)
+
+static inline u32 __dsu_pmu_read_pmcr(void)
+{
+	return read_sysreg_s(CLUSTERPMCR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmcr(u32 val)
+{
+	write_sysreg_s(val, CLUSTERPMCR_EL1);
+	isb();
+}
+
+static inline u32 __dsu_pmu_get_reset_overflow(void)
+{
+	u32 val = read_sysreg_s(CLUSTERPMOVSCLR_EL1);
+	/* Clear the bit */
+	write_sysreg_s(val, CLUSTERPMOVSCLR_EL1);
+	isb();
+	return val;
+}
+
+static inline void __dsu_pmu_select_counter(int counter)
+{
+	write_sysreg_s(counter, CLUSTERPMSELR_EL1);
+	isb();
+}
+
+static inline u64 __dsu_pmu_read_counter(int counter)
+{
+	__dsu_pmu_select_counter(counter);
+	return read_sysreg_s(CLUSTERPMXEVCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_counter(int counter, u64 val)
+{
+	__dsu_pmu_select_counter(counter);
+	write_sysreg_s(val, CLUSTERPMXEVCNTR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_set_event(int counter, u32 event)
+{
+	__dsu_pmu_select_counter(counter);
+	write_sysreg_s(event, CLUSTERPMXEVTYPER_EL1);
+	isb();
+}
+
+static inline u64 __dsu_pmu_read_pmccntr(void)
+{
+	return read_sysreg_s(CLUSTERPMCCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmccntr(u64 val)
+{
+	write_sysreg_s(val, CLUSTERPMCCNTR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_disable_counter(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMCNTENCLR_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_enable_counter(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMCNTENSET_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_enable(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMINTENSET_EL1);
+	isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_disable(int counter)
+{
+	write_sysreg_s(BIT(counter), CLUSTERPMINTENCLR_EL1);
+	isb();
+}
+
+
+static inline u32 __dsu_pmu_read_pmceid(int n)
+{
+	switch (n) {
+	case 0:
+		return read_sysreg_s(CLUSTERPMCEID0_EL1);
+	case 1:
+		return read_sysreg_s(CLUSTERPMCEID1_EL1);
+	default:
+		BUILD_BUG();
+		return 0;
+	}
+}
diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h
new file mode 100644
index 000000000..c762038ba
--- /dev/null
+++ b/arch/arm64/include/asm/asm-bug.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_ASM_BUG_H
+/*
+ * Copyright (C) 2017  ARM Limited
+ */
+#define __ASM_ASM_BUG_H
+
+#include <asm/brk-imm.h>
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
+#define __BUGVERBOSE_LOCATION(file, line)			\
+		.pushsection .rodata.str,"aMS",@progbits,1;	\
+	14472:	.string file;					\
+		.popsection;					\
+								\
+		.long 14472b - .;				\
+		.short line;
+#else
+#define _BUGVERBOSE_LOCATION(file, line)
+#endif
+
+#ifdef CONFIG_GENERIC_BUG
+
+#define __BUG_ENTRY(flags) 				\
+		.pushsection __bug_table,"aw";		\
+		.align 2;				\
+	14470:	.long 14471f - .;			\
+_BUGVERBOSE_LOCATION(__FILE__, __LINE__)		\
+		.short flags; 				\
+		.popsection;				\
+	14471:
+#else
+#define __BUG_ENTRY(flags)
+#endif
+
+#define ASM_BUG_FLAGS(flags)				\
+	__BUG_ENTRY(flags)				\
+	brk	BUG_BRK_IMM
+
+#define ASM_BUG()	ASM_BUG_FLAGS(0)
+
+#endif /* __ASM_ASM_BUG_H */
diff --git a/arch/arm64/include/asm/asm-extable.h b/arch/arm64/include/asm/asm-extable.h
new file mode 100644
index 000000000..980d1dd8e
--- /dev/null
+++ b/arch/arm64/include/asm/asm-extable.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_ASM_EXTABLE_H
+#define __ASM_ASM_EXTABLE_H
+
+#include <linux/bits.h>
+#include <asm/gpr-num.h>
+
+#define EX_TYPE_NONE			0
+#define EX_TYPE_BPF			1
+#define EX_TYPE_UACCESS_ERR_ZERO	2
+#define EX_TYPE_KACCESS_ERR_ZERO	3
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	4
+
+/* Data fields for EX_TYPE_UACCESS_ERR_ZERO */
+#define EX_DATA_REG_ERR_SHIFT	0
+#define EX_DATA_REG_ERR		GENMASK(4, 0)
+#define EX_DATA_REG_ZERO_SHIFT	5
+#define EX_DATA_REG_ZERO	GENMASK(9, 5)
+
+/* Data fields for EX_TYPE_LOAD_UNALIGNED_ZEROPAD */
+#define EX_DATA_REG_DATA_SHIFT	0
+#define EX_DATA_REG_DATA	GENMASK(4, 0)
+#define EX_DATA_REG_ADDR_SHIFT	5
+#define EX_DATA_REG_ADDR	GENMASK(9, 5)
+
+#ifdef __ASSEMBLY__
+
+#define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
+	.pushsection	__ex_table, "a";		\
+	.align		2;				\
+	.long		((insn) - .);			\
+	.long		((fixup) - .);			\
+	.short		(type);				\
+	.short		(data);				\
+	.popsection;
+
+#define EX_DATA_REG(reg, gpr)	\
+	(.L__gpr_num_##gpr << EX_DATA_REG_##reg##_SHIFT)
+
+#define _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)		\
+	__ASM_EXTABLE_RAW(insn, fixup, 					\
+			  EX_TYPE_UACCESS_ERR_ZERO,			\
+			  (						\
+			    EX_DATA_REG(ERR, err) |			\
+			    EX_DATA_REG(ZERO, zero)			\
+			  ))
+
+#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
+	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, wzr)
+
+#define _ASM_EXTABLE_UACCESS(insn, fixup)				\
+	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, wzr, wzr)
+
+/*
+ * Create an exception table entry for uaccess `insn`, which will branch to `fixup`
+ * when an unhandled fault is taken.
+ */
+	.macro          _asm_extable_uaccess, insn, fixup
+	_ASM_EXTABLE_UACCESS(\insn, \fixup)
+	.endm
+
+/*
+ * Create an exception table entry for `insn` if `fixup` is provided. Otherwise
+ * do nothing.
+ */
+	.macro		_cond_uaccess_extable, insn, fixup
+	.ifnc			\fixup,
+	_asm_extable_uaccess	\insn, \fixup
+	.endif
+	.endm
+
+#else /* __ASSEMBLY__ */
+
+#include <linux/stringify.h>
+
+#define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
+	".pushsection	__ex_table, \"a\"\n"		\
+	".align		2\n"				\
+	".long		((" insn ") - .)\n"		\
+	".long		((" fixup ") - .)\n"		\
+	".short		(" type ")\n"			\
+	".short		(" data ")\n"			\
+	".popsection\n"
+
+#define EX_DATA_REG(reg, gpr)						\
+	"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
+
+#define _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)		\
+	__DEFINE_ASM_GPR_NUMS						\
+	__ASM_EXTABLE_RAW(#insn, #fixup, 				\
+			  __stringify(EX_TYPE_UACCESS_ERR_ZERO),	\
+			  "("						\
+			    EX_DATA_REG(ERR, err) " | "			\
+			    EX_DATA_REG(ZERO, zero)			\
+			  ")")
+
+#define _ASM_EXTABLE_KACCESS_ERR_ZERO(insn, fixup, err, zero)		\
+	__DEFINE_ASM_GPR_NUMS						\
+	__ASM_EXTABLE_RAW(#insn, #fixup, 				\
+			  __stringify(EX_TYPE_KACCESS_ERR_ZERO),	\
+			  "("						\
+			    EX_DATA_REG(ERR, err) " | "			\
+			    EX_DATA_REG(ZERO, zero)			\
+			  ")")
+
+#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
+	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, wzr)
+
+#define _ASM_EXTABLE_UACCESS(insn, fixup)				\
+	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, wzr, wzr)
+
+#define _ASM_EXTABLE_KACCESS_ERR(insn, fixup, err)			\
+	_ASM_EXTABLE_KACCESS_ERR_ZERO(insn, fixup, err, wzr)
+
+#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr)		\
+	__DEFINE_ASM_GPR_NUMS							\
+	__ASM_EXTABLE_RAW(#insn, #fixup,					\
+			  __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD),		\
+			  "("							\
+			    EX_DATA_REG(DATA, data) " | "			\
+			    EX_DATA_REG(ADDR, addr)				\
+			  ")")
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_ASM_EXTABLE_H */
diff --git a/arch/arm64/include/asm/asm-offsets.h b/arch/arm64/include/asm/asm-offsets.h
new file mode 100644
index 000000000..d370ee36a
--- /dev/null
+++ b/arch/arm64/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/arm64/include/asm/asm-prototypes.h b/arch/arm64/include/asm/asm-prototypes.h
new file mode 100644
index 000000000..ec1d9655f
--- /dev/null
+++ b/arch/arm64/include/asm/asm-prototypes.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_PROTOTYPES_H
+#define __ASM_PROTOTYPES_H
+/*
+ * CONFIG_MODVERSIONS requires a C declaration to generate the appropriate CRC
+ * for each symbol. Since commit:
+ *
+ *   4efca4ed05cbdfd1 ("kbuild: modversions for EXPORT_SYMBOL() for asm")
+ *
+ * ... kbuild will automatically pick these up from <asm/asm-prototypes.h> and
+ * feed this to genksyms when building assembly files.
+ */
+#include <linux/arm-smccc.h>
+
+#include <asm/ftrace.h>
+#include <asm/page.h>
+#include <asm/string.h>
+#include <asm/uaccess.h>
+
+#include <asm-generic/asm-prototypes.h>
+
+long long __ashlti3(long long a, int b);
+long long __ashrti3(long long a, int b);
+long long __lshrti3(long long a, int b);
+
+/*
+ * This function uses a custom calling convention and cannot be called from C so
+ * this prototype is not entirely accurate.
+ */
+void __hwasan_tag_mismatch(unsigned long addr, unsigned long access_info);
+
+#endif /* __ASM_PROTOTYPES_H */
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
new file mode 100644
index 000000000..75b211c98
--- /dev/null
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ASM_UACCESS_H
+#define __ASM_ASM_UACCESS_H
+
+#include <asm/alternative-macros.h>
+#include <asm/asm-extable.h>
+#include <asm/assembler.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/mmu.h>
+#include <asm/sysreg.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
+	mrs	\tmp1, ttbr1_el1			// swapper_pg_dir
+	bic	\tmp1, \tmp1, #TTBR_ASID_MASK
+	sub	\tmp1, \tmp1, #RESERVED_SWAPPER_OFFSET	// reserved_pg_dir
+	msr	ttbr0_el1, \tmp1			// set reserved TTBR0_EL1
+	isb
+	add	\tmp1, \tmp1, #RESERVED_SWAPPER_OFFSET
+	msr	ttbr1_el1, \tmp1		// set reserved ASID
+	isb
+	.endm
+
+	.macro	__uaccess_ttbr0_enable, tmp1, tmp2
+	get_current_task \tmp1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	mrs	\tmp2, ttbr1_el1
+	extr    \tmp2, \tmp2, \tmp1, #48
+	ror     \tmp2, \tmp2, #16
+	msr	ttbr1_el1, \tmp2		// set the active ASID
+	isb
+	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
+	isb
+	.endm
+
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_disable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp3		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1, \tmp2
+	restore_irq \tmp3
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1, tmp2
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2, tmp3
+	.endm
+#endif
+
+#define USER(l, x...)				\
+9999:	x;					\
+	_asm_extable_uaccess	9999b, l
+
+/*
+ * Generate the assembly for LDTR/STTR with exception table entries.
+ * This is complicated as there is no post-increment or pair versions of the
+ * unprivileged instructions, and USER() only works for single instructions.
+ */
+	.macro user_ldp l, reg1, reg2, addr, post_inc
+8888:		ldtr	\reg1, [\addr];
+8889:		ldtr	\reg2, [\addr, #8];
+		add	\addr, \addr, \post_inc;
+
+		_asm_extable_uaccess	8888b, \l;
+		_asm_extable_uaccess	8889b, \l;
+	.endm
+
+	.macro user_stp l, reg1, reg2, addr, post_inc
+8888:		sttr	\reg1, [\addr];
+8889:		sttr	\reg2, [\addr, #8];
+		add	\addr, \addr, \post_inc;
+
+		_asm_extable_uaccess	8888b,\l;
+		_asm_extable_uaccess	8889b,\l;
+	.endm
+
+	.macro user_ldst l, inst, reg, addr, post_inc
+8888:		\inst		\reg, [\addr];
+		add		\addr, \addr, \post_inc;
+
+		_asm_extable_uaccess	8888b, \l;
+	.endm
+#endif
diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
new file mode 100644
index 000000000..13ecc7985
--- /dev/null
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ASM_POINTER_AUTH_H
+#define __ASM_ASM_POINTER_AUTH_H
+
+#include <asm/alternative.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+
+	.macro __ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+	mov	\tmp1, #THREAD_KEYS_KERNEL
+	add	\tmp1, \tsk, \tmp1
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_KERNEL_KEY_APIA]
+	msr_s	SYS_APIAKEYLO_EL1, \tmp2
+	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	__ptrauth_keys_install_kernel_nosync \tsk, \tmp1, \tmp2, \tmp3
+alternative_else_nop_endif
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	__ptrauth_keys_install_kernel_nosync \tsk, \tmp1, \tmp2, \tmp3
+	isb
+alternative_else_nop_endif
+	.endm
+
+#else /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
+	.macro __ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, tmp1, tmp2, tmp3
+	.endm
+
+#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+/*
+ * thread.keys_user.ap* as offset exceeds the #imm offset range
+ * so use the base value of ldp as thread.keys_user and offset as
+ * thread.keys_user.ap*.
+ */
+	.macro __ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+	mov	\tmp1, #THREAD_KEYS_USER
+	add	\tmp1, \tsk, \tmp1
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
+	msr_s	SYS_APIAKEYLO_EL1, \tmp2
+	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	.endm
+
+	.macro __ptrauth_keys_init_cpu tsk, tmp1, tmp2, tmp3
+	mrs	\tmp1, id_aa64isar1_el1
+	ubfx	\tmp1, \tmp1, #ID_AA64ISAR1_EL1_APA_SHIFT, #8
+	mrs_s	\tmp2, SYS_ID_AA64ISAR2_EL1
+	ubfx	\tmp2, \tmp2, #ID_AA64ISAR2_EL1_APA3_SHIFT, #4
+	orr	\tmp1, \tmp1, \tmp2
+	cbz	\tmp1, .Lno_addr_auth\@
+	mov_q	\tmp1, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+			SCTLR_ELx_ENDA | SCTLR_ELx_ENDB)
+	mrs	\tmp2, sctlr_el1
+	orr	\tmp2, \tmp2, \tmp1
+	msr	sctlr_el1, \tmp2
+	__ptrauth_keys_install_kernel_nosync \tsk, \tmp1, \tmp2, \tmp3
+	isb
+.Lno_addr_auth\@:
+	.endm
+
+	.macro ptrauth_keys_init_cpu tsk, tmp1, tmp2, tmp3
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.Lno_addr_auth\@
+alternative_else_nop_endif
+	__ptrauth_keys_init_cpu \tsk, \tmp1, \tmp2, \tmp3
+.Lno_addr_auth\@:
+	.endm
+
+#else /* !CONFIG_ARM64_PTR_AUTH */
+
+	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+	.endm
+
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#endif /* __ASM_ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
new file mode 100644
index 000000000..e5957a53b
--- /dev/null
+++ b/arch/arm64/include/asm/assembler.h
@@ -0,0 +1,924 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/assembler.h, arch/arm/mm/proc-macros.S
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASSEMBLY__
+#error "Only include this from assembly code"
+#endif
+
+#ifndef __ASM_ASSEMBLER_H
+#define __ASM_ASSEMBLER_H
+
+#include <asm-generic/export.h>
+
+#include <asm/alternative.h>
+#include <asm/asm-bug.h>
+#include <asm/asm-extable.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
+#include <asm/cputype.h>
+#include <asm/debug-monitors.h>
+#include <asm/page.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/ptrace.h>
+#include <asm/thread_info.h>
+
+	/*
+	 * Provide a wxN alias for each wN register so what we can paste a xN
+	 * reference after a 'w' to obtain the 32-bit version.
+	 */
+	.irp	n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+	wx\n	.req	w\n
+	.endr
+
+	.macro save_and_disable_daif, flags
+	mrs	\flags, daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro disable_daif
+	msr	daifset, #0xf
+	.endm
+
+	.macro enable_daif
+	msr	daifclr, #0xf
+	.endm
+
+	.macro	restore_daif, flags:req
+	msr	daif, \flags
+	.endm
+
+	/* IRQ/FIQ are the lowest priority flags, unconditionally unmask the rest. */
+	.macro enable_da
+	msr	daifclr, #(8 | 4)
+	.endm
+
+/*
+ * Save/restore interrupts.
+ */
+	.macro	save_and_disable_irq, flags
+	mrs	\flags, daif
+	msr	daifset, #3
+	.endm
+
+	.macro	restore_irq, flags
+	msr	daif, \flags
+	.endm
+
+	.macro	enable_dbg
+	msr	daifclr, #8
+	.endm
+
+	.macro	disable_step_tsk, flgs, tmp
+	tbz	\flgs, #TIF_SINGLESTEP, 9990f
+	mrs	\tmp, mdscr_el1
+	bic	\tmp, \tmp, #DBG_MDSCR_SS
+	msr	mdscr_el1, \tmp
+	isb	// Synchronise with enable_dbg
+9990:
+	.endm
+
+	/* call with daif masked */
+	.macro	enable_step_tsk, flgs, tmp
+	tbz	\flgs, #TIF_SINGLESTEP, 9990f
+	mrs	\tmp, mdscr_el1
+	orr	\tmp, \tmp, #DBG_MDSCR_SS
+	msr	mdscr_el1, \tmp
+9990:
+	.endm
+
+/*
+ * RAS Error Synchronization barrier
+ */
+	.macro  esb
+#ifdef CONFIG_ARM64_RAS_EXTN
+	hint    #16
+#else
+	nop
+#endif
+	.endm
+
+/*
+ * Value prediction barrier
+ */
+	.macro	csdb
+	hint	#20
+	.endm
+
+/*
+ * Clear Branch History instruction
+ */
+	.macro clearbhb
+	hint	#22
+	.endm
+
+/*
+ * Speculation barrier
+ */
+	.macro	sb
+alternative_if_not ARM64_HAS_SB
+	dsb	nsh
+	isb
+alternative_else
+	SB_BARRIER_INSN
+	nop
+alternative_endif
+	.endm
+
+/*
+ * NOP sequence
+ */
+	.macro	nops, num
+	.rept	\num
+	nop
+	.endr
+	.endm
+
+/*
+ * Register aliases.
+ */
+lr	.req	x30		// link register
+
+/*
+ * Vector entry
+ */
+	 .macro	ventry	label
+	.align	7
+	b	\label
+	.endm
+
+/*
+ * Select code when configured for BE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_BE(code...) code
+#else
+#define CPU_BE(code...)
+#endif
+
+/*
+ * Select code when configured for LE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+/*
+ * Define a macro that constructs a 64-bit value by concatenating two
+ * 32-bit registers. Note that on big endian systems the order of the
+ * registers is swapped.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+	.macro	regs_to_64, rd, lbits, hbits
+#else
+	.macro	regs_to_64, rd, hbits, lbits
+#endif
+	orr	\rd, \lbits, \hbits, lsl #32
+	.endm
+
+/*
+ * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
+ * <symbol> is within the range +/- 4 GB of the PC.
+ */
+	/*
+	 * @dst: destination register (64 bit wide)
+	 * @sym: name of the symbol
+	 */
+	.macro	adr_l, dst, sym
+	adrp	\dst, \sym
+	add	\dst, \dst, :lo12:\sym
+	.endm
+
+	/*
+	 * @dst: destination register (32 or 64 bit wide)
+	 * @sym: name of the symbol
+	 * @tmp: optional 64-bit scratch register to be used if <dst> is a
+	 *       32-bit wide register, in which case it cannot be used to hold
+	 *       the address
+	 */
+	.macro	ldr_l, dst, sym, tmp=
+	.ifb	\tmp
+	adrp	\dst, \sym
+	ldr	\dst, [\dst, :lo12:\sym]
+	.else
+	adrp	\tmp, \sym
+	ldr	\dst, [\tmp, :lo12:\sym]
+	.endif
+	.endm
+
+	/*
+	 * @src: source register (32 or 64 bit wide)
+	 * @sym: name of the symbol
+	 * @tmp: mandatory 64-bit scratch register to calculate the address
+	 *       while <src> needs to be preserved.
+	 */
+	.macro	str_l, src, sym, tmp
+	adrp	\tmp, \sym
+	str	\src, [\tmp, :lo12:\sym]
+	.endm
+
+	/*
+	 * @dst: destination register
+	 */
+#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__)
+	.macro	get_this_cpu_offset, dst
+	mrs	\dst, tpidr_el2
+	.endm
+#else
+	.macro	get_this_cpu_offset, dst
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+	mrs	\dst, tpidr_el1
+alternative_else
+	mrs	\dst, tpidr_el2
+alternative_endif
+	.endm
+
+	.macro	set_this_cpu_offset, src
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+	msr	tpidr_el1, \src
+alternative_else
+	msr	tpidr_el2, \src
+alternative_endif
+	.endm
+#endif
+
+	/*
+	 * @dst: Result of per_cpu(sym, smp_processor_id()) (can be SP)
+	 * @sym: The name of the per-cpu variable
+	 * @tmp: scratch register
+	 */
+	.macro adr_this_cpu, dst, sym, tmp
+	adrp	\tmp, \sym
+	add	\dst, \tmp, #:lo12:\sym
+	get_this_cpu_offset \tmp
+	add	\dst, \dst, \tmp
+	.endm
+
+	/*
+	 * @dst: Result of READ_ONCE(per_cpu(sym, smp_processor_id()))
+	 * @sym: The name of the per-cpu variable
+	 * @tmp: scratch register
+	 */
+	.macro ldr_this_cpu dst, sym, tmp
+	adr_l	\dst, \sym
+	get_this_cpu_offset \tmp
+	ldr	\dst, [\dst, \tmp]
+	.endm
+
+/*
+ * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
+ */
+	.macro	vma_vm_mm, rd, rn
+	ldr	\rd, [\rn, #VMA_VM_MM]
+	.endm
+
+/*
+ * read_ctr - read CTR_EL0. If the system has mismatched register fields,
+ * provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val
+ */
+	.macro	read_ctr, reg
+#ifndef __KVM_NVHE_HYPERVISOR__
+alternative_if_not ARM64_MISMATCHED_CACHE_TYPE
+	mrs	\reg, ctr_el0			// read CTR
+	nop
+alternative_else
+	ldr_l	\reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL
+alternative_endif
+#else
+alternative_if_not ARM64_KVM_PROTECTED_MODE
+	ASM_BUG()
+alternative_else_nop_endif
+alternative_cb ARM64_ALWAYS_SYSTEM, kvm_compute_final_ctr_el0
+	movz	\reg, #0
+	movk	\reg, #0, lsl #16
+	movk	\reg, #0, lsl #32
+	movk	\reg, #0, lsl #48
+alternative_cb_end
+#endif
+	.endm
+
+
+/*
+ * raw_dcache_line_size - get the minimum D-cache line size on this CPU
+ * from the CTR register.
+ */
+	.macro	raw_dcache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * dcache_line_size - get the safe D-cache line size across all CPUs
+ */
+	.macro	dcache_line_size, reg, tmp
+	read_ctr	\tmp
+	ubfm		\tmp, \tmp, #16, #19	// cache line size encoding
+	mov		\reg, #4		// bytes per word
+	lsl		\reg, \reg, \tmp	// actual cache line size
+	.endm
+
+/*
+ * raw_icache_line_size - get the minimum I-cache line size on this CPU
+ * from the CTR register.
+ */
+	.macro	raw_icache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	and	\tmp, \tmp, #0xf		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * icache_line_size - get the safe I-cache line size across all CPUs
+ */
+	.macro	icache_line_size, reg, tmp
+	read_ctr	\tmp
+	and		\tmp, \tmp, #0xf	// cache line size encoding
+	mov		\reg, #4		// bytes per word
+	lsl		\reg, \reg, \tmp	// actual cache line size
+	.endm
+
+/*
+ * tcr_set_t0sz - update TCR.T0SZ so that we can load the ID map
+ */
+	.macro	tcr_set_t0sz, valreg, t0sz
+	bfi	\valreg, \t0sz, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
+	.endm
+
+/*
+ * tcr_set_t1sz - update TCR.T1SZ
+ */
+	.macro	tcr_set_t1sz, valreg, t1sz
+	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
+	.endm
+
+/*
+ * idmap_get_t0sz - get the T0SZ value needed to cover the ID map
+ *
+ * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
+ * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
+ * this number conveniently equals the number of leading zeroes in
+ * the physical address of _end.
+ */
+	.macro	idmap_get_t0sz, reg
+	adrp	\reg, _end
+	orr	\reg, \reg, #(1 << VA_BITS_MIN) - 1
+	clz	\reg, \reg
+	.endm
+
+/*
+ * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
+ * ID_AA64MMFR0_EL1.PARange value
+ *
+ *	tcr:		register with the TCR_ELx value to be updated
+ *	pos:		IPS or PS bitfield position
+ *	tmp{0,1}:	temporary registers
+ */
+	.macro	tcr_compute_pa_size, tcr, pos, tmp0, tmp1
+	mrs	\tmp0, ID_AA64MMFR0_EL1
+	// Narrow PARange to fit the PS field in TCR_ELx
+	ubfx	\tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3
+	mov	\tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX
+	cmp	\tmp0, \tmp1
+	csel	\tmp0, \tmp1, \tmp0, hi
+	bfi	\tcr, \tmp0, \pos, #3
+	.endm
+
+	.macro __dcache_op_workaround_clean_cache, op, addr
+alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
+	dc	\op, \addr
+alternative_else
+	dc	civac, \addr
+alternative_endif
+	.endm
+
+/*
+ * Macro to perform a data cache maintenance for the interval
+ * [start, end) with dcache line size explicitly provided.
+ *
+ * 	op:		operation passed to dc instruction
+ * 	domain:		domain used in dsb instruciton
+ * 	start:          starting virtual address of the region
+ * 	end:            end virtual address of the region
+ *	linesz:		dcache line size
+ * 	fixup:		optional label to branch to on user fault
+ * 	Corrupts:       start, end, tmp
+ */
+	.macro dcache_by_myline_op op, domain, start, end, linesz, tmp, fixup
+	sub	\tmp, \linesz, #1
+	bic	\start, \start, \tmp
+.Ldcache_op\@:
+	.ifc	\op, cvau
+	__dcache_op_workaround_clean_cache \op, \start
+	.else
+	.ifc	\op, cvac
+	__dcache_op_workaround_clean_cache \op, \start
+	.else
+	.ifc	\op, cvap
+	sys	3, c7, c12, 1, \start	// dc cvap
+	.else
+	.ifc	\op, cvadp
+	sys	3, c7, c13, 1, \start	// dc cvadp
+	.else
+	dc	\op, \start
+	.endif
+	.endif
+	.endif
+	.endif
+	add	\start, \start, \linesz
+	cmp	\start, \end
+	b.lo	.Ldcache_op\@
+	dsb	\domain
+
+	_cond_uaccess_extable .Ldcache_op\@, \fixup
+	.endm
+
+/*
+ * Macro to perform a data cache maintenance for the interval
+ * [start, end)
+ *
+ * 	op:		operation passed to dc instruction
+ * 	domain:		domain used in dsb instruciton
+ * 	start:          starting virtual address of the region
+ * 	end:            end virtual address of the region
+ * 	fixup:		optional label to branch to on user fault
+ * 	Corrupts:       start, end, tmp1, tmp2
+ */
+	.macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup
+	dcache_line_size \tmp1, \tmp2
+	dcache_by_myline_op \op, \domain, \start, \end, \tmp1, \tmp2, \fixup
+	.endm
+
+/*
+ * Macro to perform an instruction cache maintenance for the interval
+ * [start, end)
+ *
+ * 	start, end:	virtual addresses describing the region
+ *	fixup:		optional label to branch to on user fault
+ * 	Corrupts:	tmp1, tmp2
+ */
+	.macro invalidate_icache_by_line start, end, tmp1, tmp2, fixup
+	icache_line_size \tmp1, \tmp2
+	sub	\tmp2, \tmp1, #1
+	bic	\tmp2, \start, \tmp2
+.Licache_op\@:
+	ic	ivau, \tmp2			// invalidate I line PoU
+	add	\tmp2, \tmp2, \tmp1
+	cmp	\tmp2, \end
+	b.lo	.Licache_op\@
+	dsb	ish
+	isb
+
+	_cond_uaccess_extable .Licache_op\@, \fixup
+	.endm
+
+/*
+ * load_ttbr1 - install @pgtbl as a TTBR1 page table
+ * pgtbl preserved
+ * tmp1/tmp2 clobbered, either may overlap with pgtbl
+ */
+	.macro		load_ttbr1, pgtbl, tmp1, tmp2
+	phys_to_ttbr	\tmp1, \pgtbl
+	offset_ttbr1 	\tmp1, \tmp2
+	msr		ttbr1_el1, \tmp1
+	isb
+	.endm
+
+/*
+ * To prevent the possibility of old and new partial table walks being visible
+ * in the tlb, switch the ttbr to a zero page when we invalidate the old
+ * records. D4.7.1 'General TLB maintenance requirements' in ARM DDI 0487A.i
+ * Even switching to our copied tables will cause a changed output address at
+ * each stage of the walk.
+ */
+	.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2
+	phys_to_ttbr \tmp, \zero_page
+	msr	ttbr1_el1, \tmp
+	isb
+	tlbi	vmalle1
+	dsb	nsh
+	load_ttbr1 \page_table, \tmp, \tmp2
+	.endm
+
+/*
+ * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
+ */
+	.macro	reset_pmuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64dfr0_el1
+	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	\tmpreg, #1			// Skip if no PMU present
+	b.lt	9000f
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+9000:
+	.endm
+
+/*
+ * reset_amuserenr_el0 - reset AMUSERENR_EL0 if AMUv1 present
+ */
+	.macro	reset_amuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64pfr0_el1	// Check ID_AA64PFR0_EL1
+	ubfx	\tmpreg, \tmpreg, #ID_AA64PFR0_EL1_AMU_SHIFT, #4
+	cbz	\tmpreg, .Lskip_\@		// Skip if no AMU present
+	msr_s	SYS_AMUSERENR_EL0, xzr		// Disable AMU access from EL0
+.Lskip_\@:
+	.endm
+/*
+ * copy_page - copy src to dest using temp registers t1-t8
+ */
+	.macro copy_page dest:req src:req t1:req t2:req t3:req t4:req t5:req t6:req t7:req t8:req
+9998:	ldp	\t1, \t2, [\src]
+	ldp	\t3, \t4, [\src, #16]
+	ldp	\t5, \t6, [\src, #32]
+	ldp	\t7, \t8, [\src, #48]
+	add	\src, \src, #64
+	stnp	\t1, \t2, [\dest]
+	stnp	\t3, \t4, [\dest, #16]
+	stnp	\t5, \t6, [\dest, #32]
+	stnp	\t7, \t8, [\dest, #48]
+	add	\dest, \dest, #64
+	tst	\src, #(PAGE_SIZE - 1)
+	b.ne	9998b
+	.endm
+
+/*
+ * Annotate a function as being unsuitable for kprobes.
+ */
+#ifdef CONFIG_KPROBES
+#define NOKPROBE(x)				\
+	.pushsection "_kprobe_blacklist", "aw";	\
+	.quad	x;				\
+	.popsection;
+#else
+#define NOKPROBE(x)
+#endif
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+#define EXPORT_SYMBOL_NOKASAN(name)
+#else
+#define EXPORT_SYMBOL_NOKASAN(name)	EXPORT_SYMBOL(name)
+#endif
+
+	/*
+	 * Emit a 64-bit absolute little endian symbol reference in a way that
+	 * ensures that it will be resolved at build time, even when building a
+	 * PIE binary. This requires cooperation from the linker script, which
+	 * must emit the lo32/hi32 halves individually.
+	 */
+	.macro	le64sym, sym
+	.long	\sym\()_lo32
+	.long	\sym\()_hi32
+	.endm
+
+	/*
+	 * mov_q - move an immediate constant into a 64-bit register using
+	 *         between 2 and 4 movz/movk instructions (depending on the
+	 *         magnitude and sign of the operand)
+	 */
+	.macro	mov_q, reg, val
+	.if (((\val) >> 31) == 0 || ((\val) >> 31) == 0x1ffffffff)
+	movz	\reg, :abs_g1_s:\val
+	.else
+	.if (((\val) >> 47) == 0 || ((\val) >> 47) == 0x1ffff)
+	movz	\reg, :abs_g2_s:\val
+	.else
+	movz	\reg, :abs_g3:\val
+	movk	\reg, :abs_g2_nc:\val
+	.endif
+	movk	\reg, :abs_g1_nc:\val
+	.endif
+	movk	\reg, :abs_g0_nc:\val
+	.endm
+
+/*
+ * Return the current task_struct.
+ */
+	.macro	get_current_task, rd
+	mrs	\rd, sp_el0
+	.endm
+
+/*
+ * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD.
+ * orr is used as it can cover the immediate value (and is idempotent).
+ * In future this may be nop'ed out when dealing with 52-bit kernel VAs.
+ * 	ttbr: Value of ttbr to set, modified.
+ */
+	.macro	offset_ttbr1, ttbr, tmp
+#ifdef CONFIG_ARM64_VA_BITS_52
+	mrs_s	\tmp, SYS_ID_AA64MMFR2_EL1
+	and	\tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT)
+	cbnz	\tmp, .Lskipoffs_\@
+	orr	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
+.Lskipoffs_\@ :
+#endif
+	.endm
+
+/*
+ * Perform the reverse of offset_ttbr1.
+ * bic is used as it can cover the immediate value and, in future, won't need
+ * to be nop'ed out when dealing with 52-bit kernel VAs.
+ */
+	.macro	restore_ttbr1, ttbr
+#ifdef CONFIG_ARM64_VA_BITS_52
+	bic	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
+#endif
+	.endm
+
+/*
+ * Arrange a physical address in a TTBR register, taking care of 52-bit
+ * addresses.
+ *
+ * 	phys:	physical address, preserved
+ * 	ttbr:	returns the TTBR value
+ */
+	.macro	phys_to_ttbr, ttbr, phys
+#ifdef CONFIG_ARM64_PA_BITS_52
+	orr	\ttbr, \phys, \phys, lsr #46
+	and	\ttbr, \ttbr, #TTBR_BADDR_MASK_52
+#else
+	mov	\ttbr, \phys
+#endif
+	.endm
+
+	.macro	phys_to_pte, pte, phys
+#ifdef CONFIG_ARM64_PA_BITS_52
+	/*
+	 * We assume \phys is 64K aligned and this is guaranteed by only
+	 * supporting this configuration with 64K pages.
+	 */
+	orr	\pte, \phys, \phys, lsr #36
+	and	\pte, \pte, #PTE_ADDR_MASK
+#else
+	mov	\pte, \phys
+#endif
+	.endm
+
+	.macro	pte_to_phys, phys, pte
+#ifdef CONFIG_ARM64_PA_BITS_52
+	ubfiz	\phys, \pte, #(48 - 16 - 12), #16
+	bfxil	\phys, \pte, #16, #32
+	lsl	\phys, \phys, #16
+#else
+	and	\phys, \pte, #PTE_ADDR_MASK
+#endif
+	.endm
+
+/*
+ * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU.
+ */
+	.macro	tcr_clear_errata_bits, tcr, tmp1, tmp2
+#ifdef CONFIG_FUJITSU_ERRATUM_010001
+	mrs	\tmp1, midr_el1
+
+	mov_q	\tmp2, MIDR_FUJITSU_ERRATUM_010001_MASK
+	and	\tmp1, \tmp1, \tmp2
+	mov_q	\tmp2, MIDR_FUJITSU_ERRATUM_010001
+	cmp	\tmp1, \tmp2
+	b.ne	10f
+
+	mov_q	\tmp2, TCR_CLEAR_FUJITSU_ERRATUM_010001
+	bic	\tcr, \tcr, \tmp2
+10:
+#endif /* CONFIG_FUJITSU_ERRATUM_010001 */
+	.endm
+
+/**
+ * Errata workaround prior to disable MMU. Insert an ISB immediately prior
+ * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0.
+ */
+	.macro pre_disable_mmu_workaround
+#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041
+	isb
+#endif
+	.endm
+
+	/*
+	 * frame_push - Push @regcount callee saved registers to the stack,
+	 *              starting at x19, as well as x29/x30, and set x29 to
+	 *              the new value of sp. Add @extra bytes of stack space
+	 *              for locals.
+	 */
+	.macro		frame_push, regcount:req, extra
+	__frame		st, \regcount, \extra
+	.endm
+
+	/*
+	 * frame_pop  - Pop the callee saved registers from the stack that were
+	 *              pushed in the most recent call to frame_push, as well
+	 *              as x29/x30 and any extra stack space that may have been
+	 *              allocated.
+	 */
+	.macro		frame_pop
+	__frame		ld
+	.endm
+
+	.macro		__frame_regs, reg1, reg2, op, num
+	.if		.Lframe_regcount == \num
+	\op\()r		\reg1, [sp, #(\num + 1) * 8]
+	.elseif		.Lframe_regcount > \num
+	\op\()p		\reg1, \reg2, [sp, #(\num + 1) * 8]
+	.endif
+	.endm
+
+	.macro		__frame, op, regcount, extra=0
+	.ifc		\op, st
+	.if		(\regcount) < 0 || (\regcount) > 10
+	.error		"regcount should be in the range [0 ... 10]"
+	.endif
+	.if		((\extra) % 16) != 0
+	.error		"extra should be a multiple of 16 bytes"
+	.endif
+	.ifdef		.Lframe_regcount
+	.if		.Lframe_regcount != -1
+	.error		"frame_push/frame_pop may not be nested"
+	.endif
+	.endif
+	.set		.Lframe_regcount, \regcount
+	.set		.Lframe_extra, \extra
+	.set		.Lframe_local_offset, ((\regcount + 3) / 2) * 16
+	stp		x29, x30, [sp, #-.Lframe_local_offset - .Lframe_extra]!
+	mov		x29, sp
+	.endif
+
+	__frame_regs	x19, x20, \op, 1
+	__frame_regs	x21, x22, \op, 3
+	__frame_regs	x23, x24, \op, 5
+	__frame_regs	x25, x26, \op, 7
+	__frame_regs	x27, x28, \op, 9
+
+	.ifc		\op, ld
+	.if		.Lframe_regcount == -1
+	.error		"frame_push/frame_pop may not be nested"
+	.endif
+	ldp		x29, x30, [sp], #.Lframe_local_offset + .Lframe_extra
+	.set		.Lframe_regcount, -1
+	.endif
+	.endm
+
+/*
+ * Set SCTLR_ELx to the @reg value, and invalidate the local icache
+ * in the process. This is called when setting the MMU on.
+ */
+.macro set_sctlr, sreg, reg
+	msr	\sreg, \reg
+	isb
+	/*
+	 * Invalidate the local I-cache so that any instructions fetched
+	 * speculatively from the PoC are discarded, since they may have
+	 * been dynamically patched at the PoU.
+	 */
+	ic	iallu
+	dsb	nsh
+	isb
+.endm
+
+.macro set_sctlr_el1, reg
+	set_sctlr sctlr_el1, \reg
+.endm
+
+.macro set_sctlr_el2, reg
+	set_sctlr sctlr_el2, \reg
+.endm
+
+	/*
+	 * Check whether preempt/bh-disabled asm code should yield as soon as
+	 * it is able. This is the case if we are currently running in task
+	 * context, and either a softirq is pending, or the TIF_NEED_RESCHED
+	 * flag is set and re-enabling preemption a single time would result in
+	 * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
+	 * stored negated in the top word of the thread_info::preempt_count
+	 * field)
+	 */
+	.macro		cond_yield, lbl:req, tmp:req, tmp2:req
+	get_current_task \tmp
+	ldr		\tmp, [\tmp, #TSK_TI_PREEMPT]
+	/*
+	 * If we are serving a softirq, there is no point in yielding: the
+	 * softirq will not be preempted no matter what we do, so we should
+	 * run to completion as quickly as we can.
+	 */
+	tbnz		\tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
+#ifdef CONFIG_PREEMPTION
+	sub		\tmp, \tmp, #PREEMPT_DISABLE_OFFSET
+	cbz		\tmp, \lbl
+#endif
+	adr_l		\tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
+	get_this_cpu_offset	\tmp2
+	ldr		w\tmp, [\tmp, \tmp2]
+	cbnz		w\tmp, \lbl	// yield on pending softirq in task context
+.Lnoyield_\@:
+	.endm
+
+/*
+ * Branch Target Identifier (BTI)
+ */
+	.macro  bti, targets
+	.equ	.L__bti_targets_c, 34
+	.equ	.L__bti_targets_j, 36
+	.equ	.L__bti_targets_jc,38
+	hint	#.L__bti_targets_\targets
+	.endm
+
+/*
+ * This macro emits a program property note section identifying
+ * architecture features which require special handling, mainly for
+ * use in assembly files included in the VDSO.
+ */
+
+#define NT_GNU_PROPERTY_TYPE_0  5
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND      0xc0000000
+
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI      (1U << 0)
+#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC      (1U << 1)
+
+#ifdef CONFIG_ARM64_BTI_KERNEL
+#define GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT		\
+		((GNU_PROPERTY_AARCH64_FEATURE_1_BTI |	\
+		  GNU_PROPERTY_AARCH64_FEATURE_1_PAC))
+#endif
+
+#ifdef GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT
+.macro emit_aarch64_feature_1_and, feat=GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT
+	.pushsection .note.gnu.property, "a"
+	.align  3
+	.long   2f - 1f
+	.long   6f - 3f
+	.long   NT_GNU_PROPERTY_TYPE_0
+1:      .string "GNU"
+2:
+	.align  3
+3:      .long   GNU_PROPERTY_AARCH64_FEATURE_1_AND
+	.long   5f - 4f
+4:
+	/*
+	 * This is described with an array of char in the Linux API
+	 * spec but the text and all other usage (including binutils,
+	 * clang and GCC) treat this as a 32 bit value so no swizzling
+	 * is required for big endian.
+	 */
+	.long   \feat
+5:
+	.align  3
+6:
+	.popsection
+.endm
+
+#else
+.macro emit_aarch64_feature_1_and, feat=0
+.endm
+
+#endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */
+
+	.macro __mitigate_spectre_bhb_loop      tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_loop_iter
+	mov	\tmp, #32		// Patched to correct the immediate
+alternative_cb_end
+.Lspectre_bhb_loop\@:
+	b	. + 4
+	subs	\tmp, \tmp, #1
+	b.ne	.Lspectre_bhb_loop\@
+	sb
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	.macro mitigate_spectre_bhb_loop	tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_loop_mitigation_enable
+	b	.L_spectre_bhb_loop_done\@	// Patched to NOP
+alternative_cb_end
+	__mitigate_spectre_bhb_loop	\tmp
+.L_spectre_bhb_loop_done\@:
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	/* Save/restores x0-x3 to the stack */
+	.macro __mitigate_spectre_bhb_fw
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	stp	x0, x1, [sp, #-16]!
+	stp	x2, x3, [sp, #-16]!
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_3
+alternative_cb ARM64_ALWAYS_SYSTEM, smccc_patch_fw_mitigation_conduit
+	nop					// Patched to SMC/HVC #0
+alternative_cb_end
+	ldp	x2, x3, [sp], #16
+	ldp	x0, x1, [sp], #16
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	.macro mitigate_spectre_bhb_clear_insn
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_clearbhb
+	/* Patched to NOP when not supported */
+	clearbhb
+	isb
+alternative_cb_end
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+#endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
new file mode 100644
index 000000000..c9979273d
--- /dev/null
+++ b/arch/arm64/include/asm/atomic.h
@@ -0,0 +1,226 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_ATOMIC_H
+#define __ASM_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+#include <asm/cmpxchg.h>
+#include <asm/lse.h>
+
+#define ATOMIC_OP(op)							\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
+{									\
+	__lse_ll_sc_body(op, i, v);					\
+}
+
+ATOMIC_OP(atomic_andnot)
+ATOMIC_OP(atomic_or)
+ATOMIC_OP(atomic_xor)
+ATOMIC_OP(atomic_add)
+ATOMIC_OP(atomic_and)
+ATOMIC_OP(atomic_sub)
+
+#undef ATOMIC_OP
+
+#define ATOMIC_FETCH_OP(name, op)					\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
+{									\
+	return __lse_ll_sc_body(op##name, i, v);			\
+}
+
+#define ATOMIC_FETCH_OPS(op)						\
+	ATOMIC_FETCH_OP(_relaxed, op)					\
+	ATOMIC_FETCH_OP(_acquire, op)					\
+	ATOMIC_FETCH_OP(_release, op)					\
+	ATOMIC_FETCH_OP(        , op)
+
+ATOMIC_FETCH_OPS(atomic_fetch_andnot)
+ATOMIC_FETCH_OPS(atomic_fetch_or)
+ATOMIC_FETCH_OPS(atomic_fetch_xor)
+ATOMIC_FETCH_OPS(atomic_fetch_add)
+ATOMIC_FETCH_OPS(atomic_fetch_and)
+ATOMIC_FETCH_OPS(atomic_fetch_sub)
+ATOMIC_FETCH_OPS(atomic_add_return)
+ATOMIC_FETCH_OPS(atomic_sub_return)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_FETCH_OPS
+
+#define ATOMIC64_OP(op)							\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
+{									\
+	__lse_ll_sc_body(op, i, v);					\
+}
+
+ATOMIC64_OP(atomic64_andnot)
+ATOMIC64_OP(atomic64_or)
+ATOMIC64_OP(atomic64_xor)
+ATOMIC64_OP(atomic64_add)
+ATOMIC64_OP(atomic64_and)
+ATOMIC64_OP(atomic64_sub)
+
+#undef ATOMIC64_OP
+
+#define ATOMIC64_FETCH_OP(name, op)					\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
+{									\
+	return __lse_ll_sc_body(op##name, i, v);			\
+}
+
+#define ATOMIC64_FETCH_OPS(op)						\
+	ATOMIC64_FETCH_OP(_relaxed, op)					\
+	ATOMIC64_FETCH_OP(_acquire, op)					\
+	ATOMIC64_FETCH_OP(_release, op)					\
+	ATOMIC64_FETCH_OP(        , op)
+
+ATOMIC64_FETCH_OPS(atomic64_fetch_andnot)
+ATOMIC64_FETCH_OPS(atomic64_fetch_or)
+ATOMIC64_FETCH_OPS(atomic64_fetch_xor)
+ATOMIC64_FETCH_OPS(atomic64_fetch_add)
+ATOMIC64_FETCH_OPS(atomic64_fetch_and)
+ATOMIC64_FETCH_OPS(atomic64_fetch_sub)
+ATOMIC64_FETCH_OPS(atomic64_add_return)
+ATOMIC64_FETCH_OPS(atomic64_sub_return)
+
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_FETCH_OPS
+
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+{
+	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
+}
+
+#define arch_atomic_read(v)			__READ_ONCE((v)->counter)
+#define arch_atomic_set(v, i)			__WRITE_ONCE(((v)->counter), (i))
+
+#define arch_atomic_add_return_relaxed		arch_atomic_add_return_relaxed
+#define arch_atomic_add_return_acquire		arch_atomic_add_return_acquire
+#define arch_atomic_add_return_release		arch_atomic_add_return_release
+#define arch_atomic_add_return			arch_atomic_add_return
+
+#define arch_atomic_sub_return_relaxed		arch_atomic_sub_return_relaxed
+#define arch_atomic_sub_return_acquire		arch_atomic_sub_return_acquire
+#define arch_atomic_sub_return_release		arch_atomic_sub_return_release
+#define arch_atomic_sub_return			arch_atomic_sub_return
+
+#define arch_atomic_fetch_add_relaxed		arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_add_acquire		arch_atomic_fetch_add_acquire
+#define arch_atomic_fetch_add_release		arch_atomic_fetch_add_release
+#define arch_atomic_fetch_add			arch_atomic_fetch_add
+
+#define arch_atomic_fetch_sub_relaxed		arch_atomic_fetch_sub_relaxed
+#define arch_atomic_fetch_sub_acquire		arch_atomic_fetch_sub_acquire
+#define arch_atomic_fetch_sub_release		arch_atomic_fetch_sub_release
+#define arch_atomic_fetch_sub			arch_atomic_fetch_sub
+
+#define arch_atomic_fetch_and_relaxed		arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_and_acquire		arch_atomic_fetch_and_acquire
+#define arch_atomic_fetch_and_release		arch_atomic_fetch_and_release
+#define arch_atomic_fetch_and			arch_atomic_fetch_and
+
+#define arch_atomic_fetch_andnot_relaxed	arch_atomic_fetch_andnot_relaxed
+#define arch_atomic_fetch_andnot_acquire	arch_atomic_fetch_andnot_acquire
+#define arch_atomic_fetch_andnot_release	arch_atomic_fetch_andnot_release
+#define arch_atomic_fetch_andnot		arch_atomic_fetch_andnot
+
+#define arch_atomic_fetch_or_relaxed		arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_or_acquire		arch_atomic_fetch_or_acquire
+#define arch_atomic_fetch_or_release		arch_atomic_fetch_or_release
+#define arch_atomic_fetch_or			arch_atomic_fetch_or
+
+#define arch_atomic_fetch_xor_relaxed		arch_atomic_fetch_xor_relaxed
+#define arch_atomic_fetch_xor_acquire		arch_atomic_fetch_xor_acquire
+#define arch_atomic_fetch_xor_release		arch_atomic_fetch_xor_release
+#define arch_atomic_fetch_xor			arch_atomic_fetch_xor
+
+#define arch_atomic_xchg_relaxed(v, new) \
+	arch_xchg_relaxed(&((v)->counter), (new))
+#define arch_atomic_xchg_acquire(v, new) \
+	arch_xchg_acquire(&((v)->counter), (new))
+#define arch_atomic_xchg_release(v, new) \
+	arch_xchg_release(&((v)->counter), (new))
+#define arch_atomic_xchg(v, new) \
+	arch_xchg(&((v)->counter), (new))
+
+#define arch_atomic_cmpxchg_relaxed(v, old, new) \
+	arch_cmpxchg_relaxed(&((v)->counter), (old), (new))
+#define arch_atomic_cmpxchg_acquire(v, old, new) \
+	arch_cmpxchg_acquire(&((v)->counter), (old), (new))
+#define arch_atomic_cmpxchg_release(v, old, new) \
+	arch_cmpxchg_release(&((v)->counter), (old), (new))
+#define arch_atomic_cmpxchg(v, old, new) \
+	arch_cmpxchg(&((v)->counter), (old), (new))
+
+#define arch_atomic_andnot			arch_atomic_andnot
+
+/*
+ * 64-bit arch_atomic operations.
+ */
+#define ATOMIC64_INIT				ATOMIC_INIT
+#define arch_atomic64_read			arch_atomic_read
+#define arch_atomic64_set			arch_atomic_set
+
+#define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
+#define arch_atomic64_add_return_acquire	arch_atomic64_add_return_acquire
+#define arch_atomic64_add_return_release	arch_atomic64_add_return_release
+#define arch_atomic64_add_return		arch_atomic64_add_return
+
+#define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+#define arch_atomic64_sub_return_acquire	arch_atomic64_sub_return_acquire
+#define arch_atomic64_sub_return_release	arch_atomic64_sub_return_release
+#define arch_atomic64_sub_return		arch_atomic64_sub_return
+
+#define arch_atomic64_fetch_add_relaxed		arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_add_acquire		arch_atomic64_fetch_add_acquire
+#define arch_atomic64_fetch_add_release		arch_atomic64_fetch_add_release
+#define arch_atomic64_fetch_add			arch_atomic64_fetch_add
+
+#define arch_atomic64_fetch_sub_relaxed		arch_atomic64_fetch_sub_relaxed
+#define arch_atomic64_fetch_sub_acquire		arch_atomic64_fetch_sub_acquire
+#define arch_atomic64_fetch_sub_release		arch_atomic64_fetch_sub_release
+#define arch_atomic64_fetch_sub			arch_atomic64_fetch_sub
+
+#define arch_atomic64_fetch_and_relaxed		arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_and_acquire		arch_atomic64_fetch_and_acquire
+#define arch_atomic64_fetch_and_release		arch_atomic64_fetch_and_release
+#define arch_atomic64_fetch_and			arch_atomic64_fetch_and
+
+#define arch_atomic64_fetch_andnot_relaxed	arch_atomic64_fetch_andnot_relaxed
+#define arch_atomic64_fetch_andnot_acquire	arch_atomic64_fetch_andnot_acquire
+#define arch_atomic64_fetch_andnot_release	arch_atomic64_fetch_andnot_release
+#define arch_atomic64_fetch_andnot		arch_atomic64_fetch_andnot
+
+#define arch_atomic64_fetch_or_relaxed		arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_or_acquire		arch_atomic64_fetch_or_acquire
+#define arch_atomic64_fetch_or_release		arch_atomic64_fetch_or_release
+#define arch_atomic64_fetch_or			arch_atomic64_fetch_or
+
+#define arch_atomic64_fetch_xor_relaxed		arch_atomic64_fetch_xor_relaxed
+#define arch_atomic64_fetch_xor_acquire		arch_atomic64_fetch_xor_acquire
+#define arch_atomic64_fetch_xor_release		arch_atomic64_fetch_xor_release
+#define arch_atomic64_fetch_xor			arch_atomic64_fetch_xor
+
+#define arch_atomic64_xchg_relaxed		arch_atomic_xchg_relaxed
+#define arch_atomic64_xchg_acquire		arch_atomic_xchg_acquire
+#define arch_atomic64_xchg_release		arch_atomic_xchg_release
+#define arch_atomic64_xchg			arch_atomic_xchg
+
+#define arch_atomic64_cmpxchg_relaxed		arch_atomic_cmpxchg_relaxed
+#define arch_atomic64_cmpxchg_acquire		arch_atomic_cmpxchg_acquire
+#define arch_atomic64_cmpxchg_release		arch_atomic_cmpxchg_release
+#define arch_atomic64_cmpxchg			arch_atomic_cmpxchg
+
+#define arch_atomic64_andnot			arch_atomic64_andnot
+
+#define arch_atomic64_dec_if_positive		arch_atomic64_dec_if_positive
+
+#endif /* __ASM_ATOMIC_H */
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
new file mode 100644
index 000000000..cbb3d9611
--- /dev/null
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ASM_ATOMIC_LL_SC_H
+#define __ASM_ATOMIC_LL_SC_H
+
+#include <linux/stringify.h>
+
+#ifndef CONFIG_CC_HAS_K_CONSTRAINT
+#define K
+#endif
+
+/*
+ * AArch64 UP and SMP safe atomic ops.  We use load exclusive and
+ * store exclusive to ensure that these are atomic.  We may loop
+ * to ensure that the update happens.
+ */
+
+#define ATOMIC_OP(op, asm_op, constraint)				\
+static __always_inline void						\
+__ll_sc_atomic_##op(int i, atomic_t *v)					\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "\n"				\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxr	%w0, %2\n"					\
+	"	" #asm_op "	%w0, %w0, %w3\n"			\
+	"	stxr	%w1, %w0, %2\n"					\
+	"	cbnz	%w1, 1b\n"					\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: __stringify(constraint) "r" (i));				\
+}
+
+#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
+static __always_inline int						\
+__ll_sc_atomic_##op##_return##name(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "_return" #name "\n"		\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ld" #acq "xr	%w0, %2\n"				\
+	"	" #asm_op "	%w0, %w0, %w3\n"			\
+	"	st" #rel "xr	%w1, %w0, %2\n"				\
+	"	cbnz	%w1, 1b\n"					\
+	"	" #mb							\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: __stringify(constraint) "r" (i)				\
+	: cl);								\
+									\
+	return result;							\
+}
+
+#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \
+static __always_inline int						\
+__ll_sc_atomic_fetch_##op##name(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int val, result;						\
+									\
+	asm volatile("// atomic_fetch_" #op #name "\n"			\
+	"	prfm	pstl1strm, %3\n"				\
+	"1:	ld" #acq "xr	%w0, %3\n"				\
+	"	" #asm_op "	%w1, %w0, %w4\n"			\
+	"	st" #rel "xr	%w2, %w1, %3\n"				\
+	"	cbnz	%w2, 1b\n"					\
+	"	" #mb							\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
+	: __stringify(constraint) "r" (i)				\
+	: cl);								\
+									\
+	return result;							\
+}
+
+#define ATOMIC_OPS(...)							\
+	ATOMIC_OP(__VA_ARGS__)						\
+	ATOMIC_OP_RETURN(        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_OP_RETURN(_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_OP_RETURN(_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_OP_RETURN(_release,        ,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
+
+ATOMIC_OPS(add, add, I)
+ATOMIC_OPS(sub, sub, J)
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(...)							\
+	ATOMIC_OP(__VA_ARGS__)						\
+	ATOMIC_FETCH_OP (        , dmb ish,  , l, "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_FETCH_OP (_release,        ,  , l, "memory", __VA_ARGS__)
+
+ATOMIC_OPS(and, and, K)
+ATOMIC_OPS(or, orr, K)
+ATOMIC_OPS(xor, eor, K)
+/*
+ * GAS converts the mysterious and undocumented BIC (immediate) alias to
+ * an AND (immediate) instruction with the immediate inverted. We don't
+ * have a constraint for this, so fall back to register.
+ */
+ATOMIC_OPS(andnot, bic, )
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#define ATOMIC64_OP(op, asm_op, constraint)				\
+static __always_inline void						\
+__ll_sc_atomic64_##op(s64 i, atomic64_t *v)				\
+{									\
+	s64 result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "\n"				\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxr	%0, %2\n"					\
+	"	" #asm_op "	%0, %0, %3\n"				\
+	"	stxr	%w1, %0, %2\n"					\
+	"	cbnz	%w1, 1b"					\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: __stringify(constraint) "r" (i));				\
+}
+
+#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\
+static __always_inline long						\
+__ll_sc_atomic64_##op##_return##name(s64 i, atomic64_t *v)		\
+{									\
+	s64 result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "_return" #name "\n"		\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ld" #acq "xr	%0, %2\n"				\
+	"	" #asm_op "	%0, %0, %3\n"				\
+	"	st" #rel "xr	%w1, %0, %2\n"				\
+	"	cbnz	%w1, 1b\n"					\
+	"	" #mb							\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: __stringify(constraint) "r" (i)				\
+	: cl);								\
+									\
+	return result;							\
+}
+
+#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\
+static __always_inline long						\
+__ll_sc_atomic64_fetch_##op##name(s64 i, atomic64_t *v)			\
+{									\
+	s64 result, val;						\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_fetch_" #op #name "\n"		\
+	"	prfm	pstl1strm, %3\n"				\
+	"1:	ld" #acq "xr	%0, %3\n"				\
+	"	" #asm_op "	%1, %0, %4\n"				\
+	"	st" #rel "xr	%w2, %1, %3\n"				\
+	"	cbnz	%w2, 1b\n"					\
+	"	" #mb							\
+	: "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter)	\
+	: __stringify(constraint) "r" (i)				\
+	: cl);								\
+									\
+	return result;							\
+}
+
+#define ATOMIC64_OPS(...)						\
+	ATOMIC64_OP(__VA_ARGS__)					\
+	ATOMIC64_OP_RETURN(, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_OP_RETURN(_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_OP_RETURN(_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_OP_RETURN(_release,,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
+
+ATOMIC64_OPS(add, add, I)
+ATOMIC64_OPS(sub, sub, J)
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(...)						\
+	ATOMIC64_OP(__VA_ARGS__)					\
+	ATOMIC64_FETCH_OP (, dmb ish,  , l, "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_FETCH_OP (_release,,  , l, "memory", __VA_ARGS__)
+
+ATOMIC64_OPS(and, and, L)
+ATOMIC64_OPS(or, orr, L)
+ATOMIC64_OPS(xor, eor, L)
+/*
+ * GAS converts the mysterious and undocumented BIC (immediate) alias to
+ * an AND (immediate) instruction with the immediate inverted. We don't
+ * have a constraint for this, so fall back to register.
+ */
+ATOMIC64_OPS(andnot, bic, )
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+static __always_inline s64
+__ll_sc_atomic64_dec_if_positive(atomic64_t *v)
+{
+	s64 result;
+	unsigned long tmp;
+
+	asm volatile("// atomic64_dec_if_positive\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	subs	%0, %0, #1\n"
+	"	b.lt	2f\n"
+	"	stlxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	"	dmb	ish\n"
+	"2:"
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
+	:
+	: "cc", "memory");
+
+	return result;
+}
+
+#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint)	\
+static __always_inline u##sz						\
+__ll_sc__cmpxchg_case_##name##sz(volatile void *ptr,			\
+					 unsigned long old,		\
+					 u##sz new)			\
+{									\
+	unsigned long tmp;						\
+	u##sz oldval;							\
+									\
+	/*								\
+	 * Sub-word sizes require explicit casting so that the compare  \
+	 * part of the cmpxchg doesn't end up interpreting non-zero	\
+	 * upper bits of the register containing "old".			\
+	 */								\
+	if (sz < 32)							\
+		old = (u##sz)old;					\
+									\
+	asm volatile(							\
+	"	prfm	pstl1strm, %[v]\n"				\
+	"1:	ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n"		\
+	"	eor	%" #w "[tmp], %" #w "[oldval], %" #w "[old]\n"	\
+	"	cbnz	%" #w "[tmp], 2f\n"				\
+	"	st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n"	\
+	"	cbnz	%w[tmp], 1b\n"					\
+	"	" #mb "\n"						\
+	"2:"								\
+	: [tmp] "=&r" (tmp), [oldval] "=&r" (oldval),			\
+	  [v] "+Q" (*(u##sz *)ptr)					\
+	: [old] __stringify(constraint) "r" (old), [new] "r" (new)	\
+	: cl);								\
+									\
+	return oldval;							\
+}
+
+/*
+ * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly
+ * handle the 'K' constraint for the value 4294967295 - thus we use no
+ * constraint for 32 bit operations.
+ */
+__CMPXCHG_CASE(w, b,     ,  8,        ,  ,  ,         , K)
+__CMPXCHG_CASE(w, h,     , 16,        ,  ,  ,         , K)
+__CMPXCHG_CASE(w,  ,     , 32,        ,  ,  ,         , K)
+__CMPXCHG_CASE( ,  ,     , 64,        ,  ,  ,         , L)
+__CMPXCHG_CASE(w, b, acq_,  8,        , a,  , "memory", K)
+__CMPXCHG_CASE(w, h, acq_, 16,        , a,  , "memory", K)
+__CMPXCHG_CASE(w,  , acq_, 32,        , a,  , "memory", K)
+__CMPXCHG_CASE( ,  , acq_, 64,        , a,  , "memory", L)
+__CMPXCHG_CASE(w, b, rel_,  8,        ,  , l, "memory", K)
+__CMPXCHG_CASE(w, h, rel_, 16,        ,  , l, "memory", K)
+__CMPXCHG_CASE(w,  , rel_, 32,        ,  , l, "memory", K)
+__CMPXCHG_CASE( ,  , rel_, 64,        ,  , l, "memory", L)
+__CMPXCHG_CASE(w, b,  mb_,  8, dmb ish,  , l, "memory", K)
+__CMPXCHG_CASE(w, h,  mb_, 16, dmb ish,  , l, "memory", K)
+__CMPXCHG_CASE(w,  ,  mb_, 32, dmb ish,  , l, "memory", K)
+__CMPXCHG_CASE( ,  ,  mb_, 64, dmb ish,  , l, "memory", L)
+
+#undef __CMPXCHG_CASE
+
+#define __CMPXCHG_DBL(name, mb, rel, cl)				\
+static __always_inline long						\
+__ll_sc__cmpxchg_double##name(unsigned long old1,			\
+				      unsigned long old2,		\
+				      unsigned long new1,		\
+				      unsigned long new2,		\
+				      volatile void *ptr)		\
+{									\
+	unsigned long tmp, ret;						\
+									\
+	asm volatile("// __cmpxchg_double" #name "\n"			\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ldxp	%0, %1, %2\n"					\
+	"	eor	%0, %0, %3\n"					\
+	"	eor	%1, %1, %4\n"					\
+	"	orr	%1, %0, %1\n"					\
+	"	cbnz	%1, 2f\n"					\
+	"	st" #rel "xp	%w0, %5, %6, %2\n"			\
+	"	cbnz	%w0, 1b\n"					\
+	"	" #mb "\n"						\
+	"2:"								\
+	: "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr)		\
+	: "r" (old1), "r" (old2), "r" (new1), "r" (new2)		\
+	: cl);								\
+									\
+	return ret;							\
+}
+
+__CMPXCHG_DBL(   ,        ,  ,         )
+__CMPXCHG_DBL(_mb, dmb ish, l, "memory")
+
+#undef __CMPXCHG_DBL
+#undef K
+
+#endif	/* __ASM_ATOMIC_LL_SC_H */
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
new file mode 100644
index 000000000..a94d6dacc
--- /dev/null
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -0,0 +1,327 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/atomic.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2002 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ASM_ATOMIC_LSE_H
+#define __ASM_ATOMIC_LSE_H
+
+#define ATOMIC_OP(op, asm_op)						\
+static __always_inline void						\
+__lse_atomic_##op(int i, atomic_t *v)					\
+{									\
+	asm volatile(							\
+	__LSE_PREAMBLE							\
+	"	" #asm_op "	%w[i], %[v]\n"				\
+	: [v] "+Q" (v->counter)						\
+	: [i] "r" (i));							\
+}
+
+ATOMIC_OP(andnot, stclr)
+ATOMIC_OP(or, stset)
+ATOMIC_OP(xor, steor)
+ATOMIC_OP(add, stadd)
+
+static __always_inline void __lse_atomic_sub(int i, atomic_t *v)
+{
+	__lse_atomic_add(-i, v);
+}
+
+#undef ATOMIC_OP
+
+#define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...)			\
+static __always_inline int						\
+__lse_atomic_fetch_##op##name(int i, atomic_t *v)			\
+{									\
+	int old;							\
+									\
+	asm volatile(							\
+	__LSE_PREAMBLE							\
+	"	" #asm_op #mb "	%w[i], %w[old], %[v]"			\
+	: [v] "+Q" (v->counter),					\
+	  [old] "=r" (old)						\
+	: [i] "r" (i)							\
+	: cl);								\
+									\
+	return old;							\
+}
+
+#define ATOMIC_FETCH_OPS(op, asm_op)					\
+	ATOMIC_FETCH_OP(_relaxed,   , op, asm_op)			\
+	ATOMIC_FETCH_OP(_acquire,  a, op, asm_op, "memory")		\
+	ATOMIC_FETCH_OP(_release,  l, op, asm_op, "memory")		\
+	ATOMIC_FETCH_OP(        , al, op, asm_op, "memory")
+
+ATOMIC_FETCH_OPS(andnot, ldclr)
+ATOMIC_FETCH_OPS(or, ldset)
+ATOMIC_FETCH_OPS(xor, ldeor)
+ATOMIC_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_FETCH_OPS
+
+#define ATOMIC_FETCH_OP_SUB(name)					\
+static __always_inline int						\
+__lse_atomic_fetch_sub##name(int i, atomic_t *v)			\
+{									\
+	return __lse_atomic_fetch_add##name(-i, v);			\
+}
+
+ATOMIC_FETCH_OP_SUB(_relaxed)
+ATOMIC_FETCH_OP_SUB(_acquire)
+ATOMIC_FETCH_OP_SUB(_release)
+ATOMIC_FETCH_OP_SUB(        )
+
+#undef ATOMIC_FETCH_OP_SUB
+
+#define ATOMIC_OP_ADD_SUB_RETURN(name)					\
+static __always_inline int						\
+__lse_atomic_add_return##name(int i, atomic_t *v)			\
+{									\
+	return __lse_atomic_fetch_add##name(i, v) + i;			\
+}									\
+									\
+static __always_inline int						\
+__lse_atomic_sub_return##name(int i, atomic_t *v)			\
+{									\
+	return __lse_atomic_fetch_sub(i, v) - i;			\
+}
+
+ATOMIC_OP_ADD_SUB_RETURN(_relaxed)
+ATOMIC_OP_ADD_SUB_RETURN(_acquire)
+ATOMIC_OP_ADD_SUB_RETURN(_release)
+ATOMIC_OP_ADD_SUB_RETURN(        )
+
+#undef ATOMIC_OP_ADD_SUB_RETURN
+
+static __always_inline void __lse_atomic_and(int i, atomic_t *v)
+{
+	return __lse_atomic_andnot(~i, v);
+}
+
+#define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
+static __always_inline int						\
+__lse_atomic_fetch_and##name(int i, atomic_t *v)			\
+{									\
+	return __lse_atomic_fetch_andnot##name(~i, v);			\
+}
+
+ATOMIC_FETCH_OP_AND(_relaxed,   )
+ATOMIC_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC_FETCH_OP_AND(        , al, "memory")
+
+#undef ATOMIC_FETCH_OP_AND
+
+#define ATOMIC64_OP(op, asm_op)						\
+static __always_inline void						\
+__lse_atomic64_##op(s64 i, atomic64_t *v)				\
+{									\
+	asm volatile(							\
+	__LSE_PREAMBLE							\
+	"	" #asm_op "	%[i], %[v]\n"				\
+	: [v] "+Q" (v->counter)						\
+	: [i] "r" (i));							\
+}
+
+ATOMIC64_OP(andnot, stclr)
+ATOMIC64_OP(or, stset)
+ATOMIC64_OP(xor, steor)
+ATOMIC64_OP(add, stadd)
+
+static __always_inline void __lse_atomic64_sub(s64 i, atomic64_t *v)
+{
+	__lse_atomic64_add(-i, v);
+}
+
+#undef ATOMIC64_OP
+
+#define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
+static __always_inline long						\
+__lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)			\
+{									\
+	s64 old;							\
+									\
+	asm volatile(							\
+	__LSE_PREAMBLE							\
+	"	" #asm_op #mb "	%[i], %[old], %[v]"			\
+	: [v] "+Q" (v->counter),					\
+	  [old] "=r" (old)						\
+	: [i] "r" (i) 							\
+	: cl);								\
+									\
+	return old;							\
+}
+
+#define ATOMIC64_FETCH_OPS(op, asm_op)					\
+	ATOMIC64_FETCH_OP(_relaxed,   , op, asm_op)			\
+	ATOMIC64_FETCH_OP(_acquire,  a, op, asm_op, "memory")		\
+	ATOMIC64_FETCH_OP(_release,  l, op, asm_op, "memory")		\
+	ATOMIC64_FETCH_OP(        , al, op, asm_op, "memory")
+
+ATOMIC64_FETCH_OPS(andnot, ldclr)
+ATOMIC64_FETCH_OPS(or, ldset)
+ATOMIC64_FETCH_OPS(xor, ldeor)
+ATOMIC64_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_FETCH_OPS
+
+#define ATOMIC64_FETCH_OP_SUB(name)					\
+static __always_inline long						\
+__lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v)			\
+{									\
+	return __lse_atomic64_fetch_add##name(-i, v);			\
+}
+
+ATOMIC64_FETCH_OP_SUB(_relaxed)
+ATOMIC64_FETCH_OP_SUB(_acquire)
+ATOMIC64_FETCH_OP_SUB(_release)
+ATOMIC64_FETCH_OP_SUB(        )
+
+#undef ATOMIC64_FETCH_OP_SUB
+
+#define ATOMIC64_OP_ADD_SUB_RETURN(name)				\
+static __always_inline long						\
+__lse_atomic64_add_return##name(s64 i, atomic64_t *v)			\
+{									\
+	return __lse_atomic64_fetch_add##name(i, v) + i;		\
+}									\
+									\
+static __always_inline long						\
+__lse_atomic64_sub_return##name(s64 i, atomic64_t *v)			\
+{									\
+	return __lse_atomic64_fetch_sub##name(i, v) - i;		\
+}
+
+ATOMIC64_OP_ADD_SUB_RETURN(_relaxed)
+ATOMIC64_OP_ADD_SUB_RETURN(_acquire)
+ATOMIC64_OP_ADD_SUB_RETURN(_release)
+ATOMIC64_OP_ADD_SUB_RETURN(        )
+
+#undef ATOMIC64_OP_ADD_SUB_RETURN
+
+static __always_inline void __lse_atomic64_and(s64 i, atomic64_t *v)
+{
+	return __lse_atomic64_andnot(~i, v);
+}
+
+#define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
+static __always_inline long						\
+__lse_atomic64_fetch_and##name(s64 i, atomic64_t *v)			\
+{									\
+	return __lse_atomic64_fetch_andnot##name(~i, v);		\
+}
+
+ATOMIC64_FETCH_OP_AND(_relaxed,   )
+ATOMIC64_FETCH_OP_AND(_acquire,  a, "memory")
+ATOMIC64_FETCH_OP_AND(_release,  l, "memory")
+ATOMIC64_FETCH_OP_AND(        , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_AND
+
+static __always_inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v)
+{
+	unsigned long tmp;
+
+	asm volatile(
+	__LSE_PREAMBLE
+	"1:	ldr	%x[tmp], %[v]\n"
+	"	subs	%[ret], %x[tmp], #1\n"
+	"	b.lt	2f\n"
+	"	casal	%x[tmp], %[ret], %[v]\n"
+	"	sub	%x[tmp], %x[tmp], #1\n"
+	"	sub	%x[tmp], %x[tmp], %[ret]\n"
+	"	cbnz	%x[tmp], 1b\n"
+	"2:"
+	: [ret] "+&r" (v), [v] "+Q" (v->counter), [tmp] "=&r" (tmp)
+	:
+	: "cc", "memory");
+
+	return (long)v;
+}
+
+#define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...)			\
+static __always_inline u##sz						\
+__lse__cmpxchg_case_##name##sz(volatile void *ptr,			\
+					      u##sz old,		\
+					      u##sz new)		\
+{									\
+	register unsigned long x0 asm ("x0") = (unsigned long)ptr;	\
+	register u##sz x1 asm ("x1") = old;				\
+	register u##sz x2 asm ("x2") = new;				\
+	unsigned long tmp;						\
+									\
+	asm volatile(							\
+	__LSE_PREAMBLE							\
+	"	mov	%" #w "[tmp], %" #w "[old]\n"			\
+	"	cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n"	\
+	"	mov	%" #w "[ret], %" #w "[tmp]"			\
+	: [ret] "+r" (x0), [v] "+Q" (*(u##sz *)ptr),			\
+	  [tmp] "=&r" (tmp)						\
+	: [old] "r" (x1), [new] "r" (x2)				\
+	: cl);								\
+									\
+	return x0;							\
+}
+
+__CMPXCHG_CASE(w, b,     ,  8,   )
+__CMPXCHG_CASE(w, h,     , 16,   )
+__CMPXCHG_CASE(w,  ,     , 32,   )
+__CMPXCHG_CASE(x,  ,     , 64,   )
+__CMPXCHG_CASE(w, b, acq_,  8,  a, "memory")
+__CMPXCHG_CASE(w, h, acq_, 16,  a, "memory")
+__CMPXCHG_CASE(w,  , acq_, 32,  a, "memory")
+__CMPXCHG_CASE(x,  , acq_, 64,  a, "memory")
+__CMPXCHG_CASE(w, b, rel_,  8,  l, "memory")
+__CMPXCHG_CASE(w, h, rel_, 16,  l, "memory")
+__CMPXCHG_CASE(w,  , rel_, 32,  l, "memory")
+__CMPXCHG_CASE(x,  , rel_, 64,  l, "memory")
+__CMPXCHG_CASE(w, b,  mb_,  8, al, "memory")
+__CMPXCHG_CASE(w, h,  mb_, 16, al, "memory")
+__CMPXCHG_CASE(w,  ,  mb_, 32, al, "memory")
+__CMPXCHG_CASE(x,  ,  mb_, 64, al, "memory")
+
+#undef __CMPXCHG_CASE
+
+#define __CMPXCHG_DBL(name, mb, cl...)					\
+static __always_inline long						\
+__lse__cmpxchg_double##name(unsigned long old1,				\
+					 unsigned long old2,		\
+					 unsigned long new1,		\
+					 unsigned long new2,		\
+					 volatile void *ptr)		\
+{									\
+	unsigned long oldval1 = old1;					\
+	unsigned long oldval2 = old2;					\
+	register unsigned long x0 asm ("x0") = old1;			\
+	register unsigned long x1 asm ("x1") = old2;			\
+	register unsigned long x2 asm ("x2") = new1;			\
+	register unsigned long x3 asm ("x3") = new2;			\
+	register unsigned long x4 asm ("x4") = (unsigned long)ptr;	\
+									\
+	asm volatile(							\
+	__LSE_PREAMBLE							\
+	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
+	"	eor	%[old1], %[old1], %[oldval1]\n"			\
+	"	eor	%[old2], %[old2], %[oldval2]\n"			\
+	"	orr	%[old1], %[old1], %[old2]"			\
+	: [old1] "+&r" (x0), [old2] "+&r" (x1),				\
+	  [v] "+Q" (*(__uint128_t *)ptr)				\
+	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
+	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
+	: cl);								\
+									\
+	return x0;							\
+}
+
+__CMPXCHG_DBL(   ,   )
+__CMPXCHG_DBL(_mb, al, "memory")
+
+#undef __CMPXCHG_DBL
+
+#endif	/* __ASM_ATOMIC_LSE_H */
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
new file mode 100644
index 000000000..2cfc4245d
--- /dev/null
+++ b/arch/arm64/include/asm/barrier.h
@@ -0,0 +1,216 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/barrier.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/kasan-checks.h>
+
+#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
+#define nops(n)		asm volatile(__nops(n))
+
+#define sev()		asm volatile("sev" : : : "memory")
+#define wfe()		asm volatile("wfe" : : : "memory")
+#define wfet(val)	asm volatile("msr s0_3_c1_c0_0, %0"	\
+				     : : "r" (val) : "memory")
+#define wfi()		asm volatile("wfi" : : : "memory")
+#define wfit(val)	asm volatile("msr s0_3_c1_c0_1, %0"	\
+				     : : "r" (val) : "memory")
+
+#define isb()		asm volatile("isb" : : : "memory")
+#define dmb(opt)	asm volatile("dmb " #opt : : : "memory")
+#define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
+
+#define psb_csync()	asm volatile("hint #17" : : : "memory")
+#define __tsb_csync()	asm volatile("hint #18" : : : "memory")
+#define csdb()		asm volatile("hint #20" : : : "memory")
+
+/*
+ * Data Gathering Hint:
+ * This instruction prevents merging memory accesses with Normal-NC or
+ * Device-GRE attributes before the hint instruction with any memory accesses
+ * appearing after the hint instruction.
+ */
+#define dgh()		asm volatile("hint #6" : : : "memory")
+
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+#define pmr_sync()						\
+	do {							\
+		extern struct static_key_false gic_pmr_sync;	\
+								\
+		if (static_branch_unlikely(&gic_pmr_sync))	\
+			dsb(sy);				\
+	} while(0)
+#else
+#define pmr_sync()	do {} while (0)
+#endif
+
+#define __mb()		dsb(sy)
+#define __rmb()		dsb(ld)
+#define __wmb()		dsb(st)
+
+#define __dma_mb()	dmb(osh)
+#define __dma_rmb()	dmb(oshld)
+#define __dma_wmb()	dmb(oshst)
+
+#define io_stop_wc()	dgh()
+
+#define tsb_csync()								\
+	do {									\
+		/*								\
+		 * CPUs affected by Arm Erratum 2054223 or 2067961 needs	\
+		 * another TSB to ensure the trace is flushed. The barriers	\
+		 * don't have to be strictly back to back, as long as the	\
+		 * CPU is in trace prohibited state.				\
+		 */								\
+		if (cpus_have_final_cap(ARM64_WORKAROUND_TSB_FLUSH_FAILURE))	\
+			__tsb_csync();						\
+		__tsb_csync();							\
+	} while (0)
+
+/*
+ * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
+ * and 0 otherwise.
+ */
+#define array_index_mask_nospec array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long idx,
+						    unsigned long sz)
+{
+	unsigned long mask;
+
+	asm volatile(
+	"	cmp	%1, %2\n"
+	"	sbc	%0, xzr, xzr\n"
+	: "=r" (mask)
+	: "r" (idx), "Ir" (sz)
+	: "cc");
+
+	csdb();
+	return mask;
+}
+
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * https://lore.kernel.org/r/alpine.DEB.2.21.1902081950260.1662@nanos.tec.linutronix.de/
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
+#define __smp_mb()	dmb(ish)
+#define __smp_rmb()	dmb(ishld)
+#define __smp_wmb()	dmb(ishst)
+
+#define __smp_store_release(p, v)					\
+do {									\
+	typeof(p) __p = (p);						\
+	union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u =	\
+		{ .__val = (__force __unqual_scalar_typeof(*p)) (v) };	\
+	compiletime_assert_atomic_type(*p);				\
+	kasan_check_write(__p, sizeof(*p));				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*__p)				\
+				: "r" (*(__u8 *)__u.__c)		\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*__p)				\
+				: "r" (*(__u16 *)__u.__c)		\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*__p)				\
+				: "r" (*(__u32 *)__u.__c)		\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*__p)				\
+				: "r" (*(__u64 *)__u.__c)		\
+				: "memory");				\
+		break;							\
+	}								\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u;	\
+	typeof(p) __p = (p);						\
+	compiletime_assert_atomic_type(*p);				\
+	kasan_check_read(__p, sizeof(*p));				\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*__p) : "memory");			\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*__p) : "memory");			\
+		break;							\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*__p) : "memory");			\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*__p) : "memory");			\
+		break;							\
+	}								\
+	(typeof(*p))__u.__val;						\
+})
+
+#define smp_cond_load_relaxed(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	__unqual_scalar_typeof(*ptr) VAL;				\
+	for (;;) {							\
+		VAL = READ_ONCE(*__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	(typeof(*ptr))VAL;						\
+})
+
+#define smp_cond_load_acquire(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	__unqual_scalar_typeof(*ptr) VAL;				\
+	for (;;) {							\
+		VAL = smp_load_acquire(__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	(typeof(*ptr))VAL;						\
+})
+
+#include <asm-generic/barrier.h>
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* __ASM_BARRIER_H */
diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
new file mode 100644
index 000000000..9b3c78713
--- /dev/null
+++ b/arch/arm64/include/asm/bitops.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_BITOPS_H
+#define __ASM_BITOPS_H
+
+#include <linux/compiler.h>
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/builtin-ffs.h>
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-fls.h>
+
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/fls64.h>
+
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/hweight.h>
+
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/non-atomic.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
+
+#endif /* __ASM_BITOPS_H */
diff --git a/arch/arm64/include/asm/bitrev.h b/arch/arm64/include/asm/bitrev.h
new file mode 100644
index 000000000..6faf9fba8
--- /dev/null
+++ b/arch/arm64/include/asm/bitrev.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BITREV_H
+#define __ASM_BITREV_H
+static __always_inline __attribute_const__ u32 __arch_bitrev32(u32 x)
+{
+	__asm__ ("rbit %w0, %w1" : "=r" (x) : "r" (x));
+	return x;
+}
+
+static __always_inline __attribute_const__ u16 __arch_bitrev16(u16 x)
+{
+	return __arch_bitrev32((u32)x) >> 16;
+}
+
+static __always_inline __attribute_const__ u8 __arch_bitrev8(u8 x)
+{
+	return __arch_bitrev32((u32)x) >> 24;
+}
+
+#endif
diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h
new file mode 100644
index 000000000..3e7943fd1
--- /dev/null
+++ b/arch/arm64/include/asm/boot.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_BOOT_H
+#define __ASM_BOOT_H
+
+#include <linux/sizes.h>
+
+/*
+ * arm64 requires the DTB to be 8 byte aligned and
+ * not exceed 2MB in size.
+ */
+#define MIN_FDT_ALIGN		8
+#define MAX_FDT_SIZE		SZ_2M
+
+/*
+ * arm64 requires the kernel image to placed at a 2 MB aligned base address
+ */
+#define MIN_KIMG_ALIGN		SZ_2M
+
+#endif
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
new file mode 100644
index 000000000..6e000113e
--- /dev/null
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ASM_BRK_IMM_H
+#define __ASM_BRK_IMM_H
+
+/*
+ * #imm16 values used for BRK instruction generation
+ * 0x004: for installing kprobes
+ * 0x005: for installing uprobes
+ * 0x006: for kprobe software single-step
+ * Allowed values for kgdb are 0x400 - 0x7ff
+ * 0x100: for triggering a fault on purpose (reserved)
+ * 0x400: for dynamic BRK instruction
+ * 0x401: for compile time BRK instruction
+ * 0x800: kernel-mode BUG() and WARN() traps
+ * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
+ * 0x8xxx: Control-Flow Integrity traps
+ */
+#define KPROBES_BRK_IMM			0x004
+#define UPROBES_BRK_IMM			0x005
+#define KPROBES_BRK_SS_IMM		0x006
+#define FAULT_BRK_IMM			0x100
+#define KGDB_DYN_DBG_BRK_IMM		0x400
+#define KGDB_COMPILED_DBG_BRK_IMM	0x401
+#define BUG_BRK_IMM			0x800
+#define KASAN_BRK_IMM			0x900
+#define KASAN_BRK_MASK			0x0ff
+
+#define CFI_BRK_IMM_TARGET		GENMASK(4, 0)
+#define CFI_BRK_IMM_TYPE		GENMASK(9, 5)
+#define CFI_BRK_IMM_BASE		0x8000
+#define CFI_BRK_IMM_MASK		(CFI_BRK_IMM_TARGET | CFI_BRK_IMM_TYPE)
+
+#endif
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
new file mode 100644
index 000000000..28be048db
--- /dev/null
+++ b/arch/arm64/include/asm/bug.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015  ARM Limited
+ * Author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#ifndef _ARCH_ARM64_ASM_BUG_H
+#define _ARCH_ARM64_ASM_BUG_H
+
+#include <linux/stringify.h>
+
+#include <asm/asm-bug.h>
+
+#define __BUG_FLAGS(flags)				\
+	asm volatile (__stringify(ASM_BUG_FLAGS(flags)));
+
+#define BUG() do {					\
+	__BUG_FLAGS(0);					\
+	unreachable();					\
+} while (0)
+
+#define __WARN_FLAGS(flags) __BUG_FLAGS(BUGFLAG_WARNING|(flags))
+
+#define HAVE_ARCH_BUG
+
+#include <asm-generic/bug.h>
+
+#endif /* ! _ARCH_ARM64_ASM_BUG_H */
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
new file mode 100644
index 000000000..c0b178d1b
--- /dev/null
+++ b/arch/arm64/include/asm/cache.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_CACHE_H
+#define __ASM_CACHE_H
+
+#define L1_CACHE_SHIFT		(6)
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#define CLIDR_LOUU_SHIFT	27
+#define CLIDR_LOC_SHIFT		24
+#define CLIDR_LOUIS_SHIFT	21
+
+#define CLIDR_LOUU(clidr)	(((clidr) >> CLIDR_LOUU_SHIFT) & 0x7)
+#define CLIDR_LOC(clidr)	(((clidr) >> CLIDR_LOC_SHIFT) & 0x7)
+#define CLIDR_LOUIS(clidr)	(((clidr) >> CLIDR_LOUIS_SHIFT) & 0x7)
+
+/*
+ * Memory returned by kmalloc() may be used for DMA, so we must make
+ * sure that all such allocations are cache aligned. Otherwise,
+ * unrelated code may cause parts of the buffer to be read into the
+ * cache before the transfer is done, causing old data to be seen by
+ * the CPU.
+ */
+#define ARCH_DMA_MINALIGN	(128)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitops.h>
+#include <linux/kasan-enabled.h>
+
+#include <asm/cputype.h>
+#include <asm/mte-def.h>
+#include <asm/sysreg.h>
+
+#ifdef CONFIG_KASAN_SW_TAGS
+#define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
+#elif defined(CONFIG_KASAN_HW_TAGS)
+static inline unsigned int arch_slab_minalign(void)
+{
+	return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE :
+					 __alignof__(unsigned long long);
+}
+#define arch_slab_minalign() arch_slab_minalign()
+#endif
+
+#define CTR_L1IP(ctr)		SYS_FIELD_GET(CTR_EL0, L1Ip, ctr)
+
+#define ICACHEF_ALIASING	0
+#define ICACHEF_VPIPT		1
+extern unsigned long __icache_flags;
+
+/*
+ * Whilst the D-side always behaves as PIPT on AArch64, aliasing is
+ * permitted in the I-cache.
+ */
+static inline int icache_is_aliasing(void)
+{
+	return test_bit(ICACHEF_ALIASING, &__icache_flags);
+}
+
+static __always_inline int icache_is_vpipt(void)
+{
+	return test_bit(ICACHEF_VPIPT, &__icache_flags);
+}
+
+static inline u32 cache_type_cwg(void)
+{
+	return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype());
+}
+
+#define __read_mostly __section(".data..read_mostly")
+
+static inline int cache_line_size_of_cpu(void)
+{
+	u32 cwg = cache_type_cwg();
+
+	return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
+}
+
+int cache_line_size(void);
+
+/*
+ * Read the effective value of CTR_EL0.
+ *
+ * According to ARM ARM for ARMv8-A (ARM DDI 0487C.a),
+ * section D10.2.33 "CTR_EL0, Cache Type Register" :
+ *
+ * CTR_EL0.IDC reports the data cache clean requirements for
+ * instruction to data coherence.
+ *
+ *  0 - dcache clean to PoU is required unless :
+ *     (CLIDR_EL1.LoC == 0) || (CLIDR_EL1.LoUIS == 0 && CLIDR_EL1.LoUU == 0)
+ *  1 - dcache clean to PoU is not required for i-to-d coherence.
+ *
+ * This routine provides the CTR_EL0 with the IDC field updated to the
+ * effective state.
+ */
+static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
+{
+	u32 ctr = read_cpuid_cachetype();
+
+	if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) {
+		u64 clidr = read_sysreg(clidr_el1);
+
+		if (CLIDR_LOC(clidr) == 0 ||
+		    (CLIDR_LOUIS(clidr) == 0 && CLIDR_LOUU(clidr) == 0))
+			ctr |= BIT(CTR_EL0_IDC_SHIFT);
+	}
+
+	return ctr;
+}
+
+#endif	/* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
new file mode 100644
index 000000000..37185e978
--- /dev/null
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/cacheflush.h
+ *
+ * Copyright (C) 1999-2002 Russell King.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_CACHEFLUSH_H
+#define __ASM_CACHEFLUSH_H
+
+#include <linux/kgdb.h>
+#include <linux/mm.h>
+
+/*
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
+ */
+#define PG_dcache_clean PG_arch_1
+
+/*
+ *	MM Cache Management
+ *	===================
+ *
+ *	The arch/arm64/mm/cache.S implements these methods.
+ *
+ *	Start addresses are inclusive and end addresses are exclusive; start
+ *	addresses should be rounded down, end addresses up.
+ *
+ *	See Documentation/core-api/cachetlb.rst for more information. Please note that
+ *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
+ *	VIPT I-cache.
+ *
+ *	All functions below apply to the interval [start, end)
+ *		- start  - virtual start address (inclusive)
+ *		- end    - virtual end address (exclusive)
+ *
+ *	caches_clean_inval_pou(start, end)
+ *
+ *		Ensure coherency between the I-cache and the D-cache region to
+ *		the Point of Unification.
+ *
+ *	caches_clean_inval_user_pou(start, end)
+ *
+ *		Ensure coherency between the I-cache and the D-cache region to
+ *		the Point of Unification.
+ *		Use only if the region might access user memory.
+ *
+ *	icache_inval_pou(start, end)
+ *
+ *		Invalidate I-cache region to the Point of Unification.
+ *
+ *	dcache_clean_inval_poc(start, end)
+ *
+ *		Clean and invalidate D-cache region to the Point of Coherency.
+ *
+ *	dcache_inval_poc(start, end)
+ *
+ *		Invalidate D-cache region to the Point of Coherency.
+ *
+ *	dcache_clean_poc(start, end)
+ *
+ *		Clean D-cache region to the Point of Coherency.
+ *
+ *	dcache_clean_pop(start, end)
+ *
+ *		Clean D-cache region to the Point of Persistence.
+ *
+ *	dcache_clean_pou(start, end)
+ *
+ *		Clean D-cache region to the Point of Unification.
+ */
+extern void caches_clean_inval_pou(unsigned long start, unsigned long end);
+extern void icache_inval_pou(unsigned long start, unsigned long end);
+extern void dcache_clean_inval_poc(unsigned long start, unsigned long end);
+extern void dcache_inval_poc(unsigned long start, unsigned long end);
+extern void dcache_clean_poc(unsigned long start, unsigned long end);
+extern void dcache_clean_pop(unsigned long start, unsigned long end);
+extern void dcache_clean_pou(unsigned long start, unsigned long end);
+extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end);
+extern void sync_icache_aliases(unsigned long start, unsigned long end);
+
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+	caches_clean_inval_pou(start, end);
+
+	/*
+	 * IPI all online CPUs so that they undergo a context synchronization
+	 * event and are forced to refetch the new instructions.
+	 */
+
+	/*
+	 * KGDB performs cache maintenance with interrupts disabled, so we
+	 * will deadlock trying to IPI the secondary CPUs. In theory, we can
+	 * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that
+	 * just means that KGDB will elide the maintenance altogether! As it
+	 * turns out, KGDB uses IPIs to round-up the secondary CPUs during
+	 * the patching operation, so we don't need extra IPIs here anyway.
+	 * In which case, add a KGDB-specific bodge and return early.
+	 */
+	if (in_dbg_master())
+		return;
+
+	kick_all_cpus_sync();
+}
+#define flush_icache_range flush_icache_range
+
+/*
+ * Copy user data from/to a page which is mapped into a different
+ * processes address space.  Really, we want to allow our "user
+ * space" model to handle this.
+ */
+extern void copy_to_user_page(struct vm_area_struct *, struct page *,
+	unsigned long, void *, const void *, unsigned long);
+#define copy_to_user_page copy_to_user_page
+
+/*
+ * flush_dcache_page is used when the kernel has written to the page
+ * cache page at virtual address page->virtual.
+ *
+ * If this page isn't mapped (ie, page_mapping == NULL), or it might
+ * have userspace mappings, then we _must_ always clean + invalidate
+ * the dcache entries associated with the kernel mapping.
+ *
+ * Otherwise we can defer the operation, and clean the cache when we are
+ * about to change to user space.  This is the same method as used on SPARC64.
+ * See update_mmu_cache for the user space part.
+ */
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+extern void flush_dcache_page(struct page *);
+
+static __always_inline void icache_inval_all_pou(void)
+{
+	if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+		return;
+
+	asm("ic	ialluis");
+	dsb(ish);
+}
+
+#include <asm-generic/cacheflush.h>
+
+#endif /* __ASM_CACHEFLUSH_H */
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
new file mode 100644
index 000000000..dc52b7336
--- /dev/null
+++ b/arch/arm64/include/asm/checksum.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 ARM Ltd.
+ */
+#ifndef __ASM_CHECKSUM_H
+#define __ASM_CHECKSUM_H
+
+#include <linux/in6.h>
+
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum sum);
+
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+	sum += (sum >> 16) | (sum << 16);
+	return ~(__force __sum16)(sum >> 16);
+}
+#define csum_fold csum_fold
+
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	__uint128_t tmp;
+	u64 sum;
+	int n = ihl; /* we want it signed */
+
+	tmp = *(const __uint128_t *)iph;
+	iph += 16;
+	n -= 4;
+	tmp += ((tmp >> 64) | (tmp << 64));
+	sum = tmp >> 64;
+	do {
+		sum += *(const u32 *)iph;
+		iph += 4;
+	} while (--n > 0);
+
+	sum += ((sum >> 32) | (sum << 32));
+	return csum_fold((__force __wsum)(sum >> 32));
+}
+#define ip_fast_csum ip_fast_csum
+
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
+#include <asm-generic/checksum.h>
+
+#endif	/* __ASM_CHECKSUM_H */
diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h
new file mode 100644
index 000000000..482185566
--- /dev/null
+++ b/arch/arm64/include/asm/clocksource.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
new file mode 100644
index 000000000..497acf134
--- /dev/null
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/cmpxchg.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_CMPXCHG_H
+#define __ASM_CMPXCHG_H
+
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+
+#include <asm/barrier.h>
+#include <asm/lse.h>
+
+/*
+ * We need separate acquire parameters for ll/sc and lse, since the full
+ * barrier case is generated as release+dmb for the former and
+ * acquire+release for the latter.
+ */
+#define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl)	\
+static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr)		\
+{										\
+	u##sz ret;								\
+	unsigned long tmp;							\
+										\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(					\
+	/* LL/SC */								\
+	"	prfm	pstl1strm, %2\n"					\
+	"1:	ld" #acq "xr" #sfx "\t%" #w "0, %2\n"				\
+	"	st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n"			\
+	"	cbnz	%w1, 1b\n"						\
+	"	" #mb,								\
+	/* LSE atomics */							\
+	"	swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n"		\
+		__nops(3)							\
+	"	" #nop_lse)							\
+	: "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr)			\
+	: "r" (x)								\
+	: cl);									\
+										\
+	return ret;								\
+}
+
+__XCHG_CASE(w, b,     ,  8,        ,    ,  ,  ,  ,         )
+__XCHG_CASE(w, h,     , 16,        ,    ,  ,  ,  ,         )
+__XCHG_CASE(w,  ,     , 32,        ,    ,  ,  ,  ,         )
+__XCHG_CASE( ,  ,     , 64,        ,    ,  ,  ,  ,         )
+__XCHG_CASE(w, b, acq_,  8,        ,    , a, a,  , "memory")
+__XCHG_CASE(w, h, acq_, 16,        ,    , a, a,  , "memory")
+__XCHG_CASE(w,  , acq_, 32,        ,    , a, a,  , "memory")
+__XCHG_CASE( ,  , acq_, 64,        ,    , a, a,  , "memory")
+__XCHG_CASE(w, b, rel_,  8,        ,    ,  ,  , l, "memory")
+__XCHG_CASE(w, h, rel_, 16,        ,    ,  ,  , l, "memory")
+__XCHG_CASE(w,  , rel_, 32,        ,    ,  ,  , l, "memory")
+__XCHG_CASE( ,  , rel_, 64,        ,    ,  ,  , l, "memory")
+__XCHG_CASE(w, b,  mb_,  8, dmb ish, nop,  , a, l, "memory")
+__XCHG_CASE(w, h,  mb_, 16, dmb ish, nop,  , a, l, "memory")
+__XCHG_CASE(w,  ,  mb_, 32, dmb ish, nop,  , a, l, "memory")
+__XCHG_CASE( ,  ,  mb_, 64, dmb ish, nop,  , a, l, "memory")
+
+#undef __XCHG_CASE
+
+#define __XCHG_GEN(sfx)							\
+static __always_inline  unsigned long __xchg##sfx(unsigned long x,	\
+					volatile void *ptr,		\
+					int size)			\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __xchg_case##sfx##_8(x, ptr);			\
+	case 2:								\
+		return __xchg_case##sfx##_16(x, ptr);			\
+	case 4:								\
+		return __xchg_case##sfx##_32(x, ptr);			\
+	case 8:								\
+		return __xchg_case##sfx##_64(x, ptr);			\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
+}
+
+__XCHG_GEN()
+__XCHG_GEN(_acq)
+__XCHG_GEN(_rel)
+__XCHG_GEN(_mb)
+
+#undef __XCHG_GEN
+
+#define __xchg_wrapper(sfx, ptr, x)					\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret;								\
+})
+
+/* xchg */
+#define arch_xchg_relaxed(...)	__xchg_wrapper(    , __VA_ARGS__)
+#define arch_xchg_acquire(...)	__xchg_wrapper(_acq, __VA_ARGS__)
+#define arch_xchg_release(...)	__xchg_wrapper(_rel, __VA_ARGS__)
+#define arch_xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
+
+#define __CMPXCHG_CASE(name, sz)			\
+static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr,	\
+					      u##sz old,		\
+					      u##sz new)		\
+{									\
+	return __lse_ll_sc_body(_cmpxchg_case_##name##sz,		\
+				ptr, old, new);				\
+}
+
+__CMPXCHG_CASE(    ,  8)
+__CMPXCHG_CASE(    , 16)
+__CMPXCHG_CASE(    , 32)
+__CMPXCHG_CASE(    , 64)
+__CMPXCHG_CASE(acq_,  8)
+__CMPXCHG_CASE(acq_, 16)
+__CMPXCHG_CASE(acq_, 32)
+__CMPXCHG_CASE(acq_, 64)
+__CMPXCHG_CASE(rel_,  8)
+__CMPXCHG_CASE(rel_, 16)
+__CMPXCHG_CASE(rel_, 32)
+__CMPXCHG_CASE(rel_, 64)
+__CMPXCHG_CASE(mb_,  8)
+__CMPXCHG_CASE(mb_, 16)
+__CMPXCHG_CASE(mb_, 32)
+__CMPXCHG_CASE(mb_, 64)
+
+#undef __CMPXCHG_CASE
+
+#define __CMPXCHG_DBL(name)						\
+static inline long __cmpxchg_double##name(unsigned long old1,		\
+					 unsigned long old2,		\
+					 unsigned long new1,		\
+					 unsigned long new2,		\
+					 volatile void *ptr)		\
+{									\
+	return __lse_ll_sc_body(_cmpxchg_double##name, 			\
+				old1, old2, new1, new2, ptr);		\
+}
+
+__CMPXCHG_DBL(   )
+__CMPXCHG_DBL(_mb)
+
+#undef __CMPXCHG_DBL
+
+#define __CMPXCHG_GEN(sfx)						\
+static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr,	\
+					   unsigned long old,		\
+					   unsigned long new,		\
+					   int size)			\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __cmpxchg_case##sfx##_8(ptr, old, new);		\
+	case 2:								\
+		return __cmpxchg_case##sfx##_16(ptr, old, new);		\
+	case 4:								\
+		return __cmpxchg_case##sfx##_32(ptr, old, new);		\
+	case 8:								\
+		return __cmpxchg_case##sfx##_64(ptr, old, new);		\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
+}
+
+__CMPXCHG_GEN()
+__CMPXCHG_GEN(_acq)
+__CMPXCHG_GEN(_rel)
+__CMPXCHG_GEN(_mb)
+
+#undef __CMPXCHG_GEN
+
+#define __cmpxchg_wrapper(sfx, ptr, o, n)				\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__ret = (__typeof__(*(ptr)))					\
+		__cmpxchg##sfx((ptr), (unsigned long)(o),		\
+				(unsigned long)(n), sizeof(*(ptr)));	\
+	__ret;								\
+})
+
+/* cmpxchg */
+#define arch_cmpxchg_relaxed(...)	__cmpxchg_wrapper(    , __VA_ARGS__)
+#define arch_cmpxchg_acquire(...)	__cmpxchg_wrapper(_acq, __VA_ARGS__)
+#define arch_cmpxchg_release(...)	__cmpxchg_wrapper(_rel, __VA_ARGS__)
+#define arch_cmpxchg(...)		__cmpxchg_wrapper( _mb, __VA_ARGS__)
+#define arch_cmpxchg_local		arch_cmpxchg_relaxed
+
+/* cmpxchg64 */
+#define arch_cmpxchg64_relaxed		arch_cmpxchg_relaxed
+#define arch_cmpxchg64_acquire		arch_cmpxchg_acquire
+#define arch_cmpxchg64_release		arch_cmpxchg_release
+#define arch_cmpxchg64			arch_cmpxchg
+#define arch_cmpxchg64_local		arch_cmpxchg_local
+
+/* cmpxchg_double */
+#define system_has_cmpxchg_double()     1
+
+#define __cmpxchg_double_check(ptr1, ptr2)					\
+({										\
+	if (sizeof(*(ptr1)) != 8)						\
+		BUILD_BUG();							\
+	VM_BUG_ON((unsigned long *)(ptr2) - (unsigned long *)(ptr1) != 1);	\
+})
+
+#define arch_cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2)				\
+({										\
+	int __ret;								\
+	__cmpxchg_double_check(ptr1, ptr2);					\
+	__ret = !__cmpxchg_double_mb((unsigned long)(o1), (unsigned long)(o2),	\
+				     (unsigned long)(n1), (unsigned long)(n2),	\
+				     ptr1);					\
+	__ret;									\
+})
+
+#define arch_cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2)			\
+({										\
+	int __ret;								\
+	__cmpxchg_double_check(ptr1, ptr2);					\
+	__ret = !__cmpxchg_double((unsigned long)(o1), (unsigned long)(o2),	\
+				  (unsigned long)(n1), (unsigned long)(n2),	\
+				  ptr1);					\
+	__ret;									\
+})
+
+#define __CMPWAIT_CASE(w, sfx, sz)					\
+static inline void __cmpwait_case_##sz(volatile void *ptr,		\
+				       unsigned long val)		\
+{									\
+	unsigned long tmp;						\
+									\
+	asm volatile(							\
+	"	sevl\n"							\
+	"	wfe\n"							\
+	"	ldxr" #sfx "\t%" #w "[tmp], %[v]\n"			\
+	"	eor	%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
+	"	cbnz	%" #w "[tmp], 1f\n"				\
+	"	wfe\n"							\
+	"1:"								\
+	: [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr)			\
+	: [val] "r" (val));						\
+}
+
+__CMPWAIT_CASE(w, b, 8);
+__CMPWAIT_CASE(w, h, 16);
+__CMPWAIT_CASE(w,  , 32);
+__CMPWAIT_CASE( ,  , 64);
+
+#undef __CMPWAIT_CASE
+
+#define __CMPWAIT_GEN(sfx)						\
+static __always_inline void __cmpwait##sfx(volatile void *ptr,		\
+				  unsigned long val,			\
+				  int size)				\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __cmpwait_case##sfx##_8(ptr, (u8)val);		\
+	case 2:								\
+		return __cmpwait_case##sfx##_16(ptr, (u16)val);		\
+	case 4:								\
+		return __cmpwait_case##sfx##_32(ptr, val);		\
+	case 8:								\
+		return __cmpwait_case##sfx##_64(ptr, val);		\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
+}
+
+__CMPWAIT_GEN()
+
+#undef __CMPWAIT_GEN
+
+#define __cmpwait_relaxed(ptr, val) \
+	__cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr)))
+
+#endif	/* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
new file mode 100644
index 000000000..9f362274a
--- /dev/null
+++ b/arch/arm64/include/asm/compat.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_COMPAT_H
+#define __ASM_COMPAT_H
+
+#define compat_mode_t compat_mode_t
+typedef u16		compat_mode_t;
+
+#define __compat_uid_t	__compat_uid_t
+typedef u16		__compat_uid_t;
+typedef u16		__compat_gid_t;
+
+#define compat_ipc_pid_t compat_ipc_pid_t
+typedef u16		compat_ipc_pid_t;
+
+#define compat_statfs	compat_statfs
+
+#include <asm-generic/compat.h>
+
+#ifdef CONFIG_COMPAT
+
+/*
+ * Architecture specific compatibility types
+ */
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#ifdef __AARCH64EB__
+#define COMPAT_UTS_MACHINE	"armv8b\0\0"
+#else
+#define COMPAT_UTS_MACHINE	"armv8l\0\0"
+#endif
+
+typedef u16		__compat_uid16_t;
+typedef u16		__compat_gid16_t;
+typedef s32		compat_nlink_t;
+
+struct compat_stat {
+#ifdef __AARCH64EB__
+	short		st_dev;
+	short		__pad1;
+#else
+	compat_dev_t	st_dev;
+#endif
+	compat_ino_t	st_ino;
+	compat_mode_t	st_mode;
+	compat_ushort_t	st_nlink;
+	__compat_uid16_t	st_uid;
+	__compat_gid16_t	st_gid;
+#ifdef __AARCH64EB__
+	short		st_rdev;
+	short		__pad2;
+#else
+	compat_dev_t	st_rdev;
+#endif
+	compat_off_t	st_size;
+	compat_off_t	st_blksize;
+	compat_off_t	st_blocks;
+	old_time32_t	st_atime;
+	compat_ulong_t	st_atime_nsec;
+	old_time32_t	st_mtime;
+	compat_ulong_t	st_mtime_nsec;
+	old_time32_t	st_ctime;
+	compat_ulong_t	st_ctime_nsec;
+	compat_ulong_t	__unused4[2];
+};
+
+struct compat_statfs {
+	int		f_type;
+	int		f_bsize;
+	int		f_blocks;
+	int		f_bfree;
+	int		f_bavail;
+	int		f_files;
+	int		f_ffree;
+	compat_fsid_t	f_fsid;
+	int		f_namelen;	/* SunOS ignores this field. */
+	int		f_frsize;
+	int		f_flags;
+	int		f_spare[4];
+};
+
+#define COMPAT_RLIM_INFINITY		0xffffffff
+
+#define COMPAT_OFF_T_MAX	0x7fffffff
+
+#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
+#define COMPAT_MINSIGSTKSZ	2048
+
+static inline int is_compat_task(void)
+{
+	return test_thread_flag(TIF_32BIT);
+}
+
+static inline int is_compat_thread(struct thread_info *thread)
+{
+	return test_ti_thread_flag(thread, TIF_32BIT);
+}
+
+#else /* !CONFIG_COMPAT */
+
+static inline int is_compat_thread(struct thread_info *thread)
+{
+	return 0;
+}
+
+#endif /* CONFIG_COMPAT */
+#endif /* __ASM_COMPAT_H */
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
new file mode 100644
index 000000000..6fb2e6bcc
--- /dev/null
+++ b/arch/arm64/include/asm/compiler.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_COMPILER_H
+#define __ASM_COMPILER_H
+
+#ifdef ARM64_ASM_ARCH
+#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n"
+#else
+#define ARM64_ASM_PREAMBLE
+#endif
+
+/*
+ * The EL0/EL1 pointer bits used by a pointer authentication code.
+ * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
+ */
+#define ptrauth_user_pac_mask()		GENMASK_ULL(54, vabits_actual)
+#define ptrauth_kernel_pac_mask()	GENMASK_ULL(63, vabits_actual)
+
+/* Valid for EL0 TTBR0 and EL1 TTBR1 instruction pointers */
+#define ptrauth_clear_pac(ptr)						\
+	((ptr & BIT_ULL(55)) ? (ptr | ptrauth_kernel_pac_mask()) :	\
+			       (ptr & ~ptrauth_user_pac_mask()))
+
+#define __builtin_return_address(val)					\
+	(void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
+
+#endif /* __ASM_COMPILER_H */
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
new file mode 100644
index 000000000..fd7a92219
--- /dev/null
+++ b/arch/arm64/include/asm/cpu.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+  * Copyright (C) 2014 ARM Ltd.
+ */
+#ifndef __ASM_CPU_H
+#define __ASM_CPU_H
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+
+/*
+ * Records attributes of an individual CPU.
+ */
+struct cpuinfo_32bit {
+	u32		reg_id_dfr0;
+	u32		reg_id_dfr1;
+	u32		reg_id_isar0;
+	u32		reg_id_isar1;
+	u32		reg_id_isar2;
+	u32		reg_id_isar3;
+	u32		reg_id_isar4;
+	u32		reg_id_isar5;
+	u32		reg_id_isar6;
+	u32		reg_id_mmfr0;
+	u32		reg_id_mmfr1;
+	u32		reg_id_mmfr2;
+	u32		reg_id_mmfr3;
+	u32		reg_id_mmfr4;
+	u32		reg_id_mmfr5;
+	u32		reg_id_pfr0;
+	u32		reg_id_pfr1;
+	u32		reg_id_pfr2;
+
+	u32		reg_mvfr0;
+	u32		reg_mvfr1;
+	u32		reg_mvfr2;
+};
+
+struct cpuinfo_arm64 {
+	struct cpu	cpu;
+	struct kobject	kobj;
+	u64		reg_ctr;
+	u64		reg_cntfrq;
+	u64		reg_dczid;
+	u64		reg_midr;
+	u64		reg_revidr;
+	u64		reg_gmid;
+	u64		reg_smidr;
+
+	u64		reg_id_aa64dfr0;
+	u64		reg_id_aa64dfr1;
+	u64		reg_id_aa64isar0;
+	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64isar2;
+	u64		reg_id_aa64mmfr0;
+	u64		reg_id_aa64mmfr1;
+	u64		reg_id_aa64mmfr2;
+	u64		reg_id_aa64pfr0;
+	u64		reg_id_aa64pfr1;
+	u64		reg_id_aa64zfr0;
+	u64		reg_id_aa64smfr0;
+
+	struct cpuinfo_32bit	aarch32;
+
+	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
+	u64		reg_zcr;
+
+	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
+	u64		reg_smcr;
+};
+
+DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
+
+void cpuinfo_store_cpu(void);
+void __init cpuinfo_store_boot_cpu(void);
+
+void __init init_cpu_features(struct cpuinfo_arm64 *info);
+void update_cpu_features(int cpu, struct cpuinfo_arm64 *info,
+				 struct cpuinfo_arm64 *boot);
+
+#endif /* __ASM_CPU_H */
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
new file mode 100644
index 000000000..a444c8915
--- /dev/null
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/threads.h>
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name:	Name of the property as appears in a devicetree cpu node's
+ *		enable-method property. On systems booting with ACPI, @name
+ *		identifies the struct cpu_operations entry corresponding to
+ *		the boot protocol specified in the ACPI MADT table.
+ * @cpu_init:	Reads any data necessary for a specific enable-method for a
+ *		proposed logical id.
+ * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
+ *		mechanism for doing so, tests whether it is possible to boot
+ *		the given CPU.
+ * @cpu_boot:	Boots a cpu into the kernel.
+ * @cpu_postboot: Optionally, perform any post-boot cleanup or necessary
+ *		synchronisation. Called from the cpu being booted.
+ * @cpu_can_disable: Determines whether a CPU can be disabled based on
+ *		mechanism-specific information.
+ * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific
+ * 		reason, which will cause the hot unplug to be aborted. Called
+ * 		from the cpu to be killed.
+ * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
+ *		cpu being killed.
+ * @cpu_kill:  Ensures a cpu has left the kernel. Called from another cpu.
+ */
+struct cpu_operations {
+	const char	*name;
+	int		(*cpu_init)(unsigned int);
+	int		(*cpu_prepare)(unsigned int);
+	int		(*cpu_boot)(unsigned int);
+	void		(*cpu_postboot)(void);
+#ifdef CONFIG_HOTPLUG_CPU
+	bool		(*cpu_can_disable)(unsigned int cpu);
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_die)(unsigned int cpu);
+	int		(*cpu_kill)(unsigned int cpu);
+#endif
+};
+
+int __init init_cpu_ops(int cpu);
+extern const struct cpu_operations *get_cpu_ops(int cpu);
+
+static inline void __init init_bootcpu_ops(void)
+{
+	init_cpu_ops(0);
+}
+
+#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 000000000..a0badda3a
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,926 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/alternative-macros.h>
+#include <asm/cpucaps.h>
+#include <asm/cputype.h>
+#include <asm/hwcap.h>
+#include <asm/sysreg.h>
+
+#define MAX_CPU_FEATURES	128
+#define cpu_feature(x)		KERNEL_HWCAP_ ## x
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bug.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+
+/*
+ * CPU feature register tracking
+ *
+ * The safe value of a CPUID feature field is dependent on the implications
+ * of the values assigned to it by the architecture. Based on the relationship
+ * between the values, the features are classified into 3 types - LOWER_SAFE,
+ * HIGHER_SAFE and EXACT.
+ *
+ * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest
+ * for HIGHER_SAFE. It is expected that all CPUs have the same value for
+ * a field when EXACT is specified, failing which, the safe value specified
+ * in the table is chosen.
+ */
+
+enum ftr_type {
+	FTR_EXACT,			/* Use a predefined safe value */
+	FTR_LOWER_SAFE,			/* Smaller value is safe */
+	FTR_HIGHER_SAFE,		/* Bigger value is safe */
+	FTR_HIGHER_OR_ZERO_SAFE,	/* Bigger value is safe, but 0 is biggest */
+};
+
+#define FTR_STRICT	true	/* SANITY check strict matching required */
+#define FTR_NONSTRICT	false	/* SANITY check ignored */
+
+#define FTR_SIGNED	true	/* Value should be treated as signed */
+#define FTR_UNSIGNED	false	/* Value should be treated as unsigned */
+
+#define FTR_VISIBLE	true	/* Feature visible to the user space */
+#define FTR_HIDDEN	false	/* Feature is hidden from the user */
+
+#define FTR_VISIBLE_IF_IS_ENABLED(config)		\
+	(IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN)
+
+struct arm64_ftr_bits {
+	bool		sign;	/* Value is signed ? */
+	bool		visible;
+	bool		strict;	/* CPU Sanity check: strict matching required ? */
+	enum ftr_type	type;
+	u8		shift;
+	u8		width;
+	s64		safe_val; /* safe value for FTR_EXACT features */
+};
+
+/*
+ * Describe the early feature override to the core override code:
+ *
+ * @val			Values that are to be merged into the final
+ *			sanitised value of the register. Only the bitfields
+ *			set to 1 in @mask are valid
+ * @mask		Mask of the features that are overridden by @val
+ *
+ * A @mask field set to full-1 indicates that the corresponding field
+ * in @val is a valid override.
+ *
+ * A @mask field set to full-0 with the corresponding @val field set
+ * to full-0 denotes that this field has no override
+ *
+ * A @mask field set to full-0 with the corresponding @val field set
+ * to full-1 denotes thath this field has an invalid override.
+ */
+struct arm64_ftr_override {
+	u64		val;
+	u64		mask;
+};
+
+/*
+ * @arm64_ftr_reg - Feature register
+ * @strict_mask		Bits which should match across all CPUs for sanity.
+ * @sys_val		Safe value across the CPUs (system view)
+ */
+struct arm64_ftr_reg {
+	const char			*name;
+	u64				strict_mask;
+	u64				user_mask;
+	u64				sys_val;
+	u64				user_val;
+	struct arm64_ftr_override	*override;
+	const struct arm64_ftr_bits	*ftr_bits;
+};
+
+extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
+
+/*
+ * CPU capabilities:
+ *
+ * We use arm64_cpu_capabilities to represent system features, errata work
+ * arounds (both used internally by kernel and tracked in cpu_hwcaps) and
+ * ELF HWCAPs (which are exposed to user).
+ *
+ * To support systems with heterogeneous CPUs, we need to make sure that we
+ * detect the capabilities correctly on the system and take appropriate
+ * measures to ensure there are no incompatibilities.
+ *
+ * This comment tries to explain how we treat the capabilities.
+ * Each capability has the following list of attributes :
+ *
+ * 1) Scope of Detection : The system detects a given capability by
+ *    performing some checks at runtime. This could be, e.g, checking the
+ *    value of a field in CPU ID feature register or checking the cpu
+ *    model. The capability provides a call back ( @matches() ) to
+ *    perform the check. Scope defines how the checks should be performed.
+ *    There are three cases:
+ *
+ *     a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one
+ *        matches. This implies, we have to run the check on all the
+ *        booting CPUs, until the system decides that state of the
+ *        capability is finalised. (See section 2 below)
+ *		Or
+ *     b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs
+ *        matches. This implies, we run the check only once, when the
+ *        system decides to finalise the state of the capability. If the
+ *        capability relies on a field in one of the CPU ID feature
+ *        registers, we use the sanitised value of the register from the
+ *        CPU feature infrastructure to make the decision.
+ *		Or
+ *     c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the
+ *        feature. This category is for features that are "finalised"
+ *        (or used) by the kernel very early even before the SMP cpus
+ *        are brought up.
+ *
+ *    The process of detection is usually denoted by "update" capability
+ *    state in the code.
+ *
+ * 2) Finalise the state : The kernel should finalise the state of a
+ *    capability at some point during its execution and take necessary
+ *    actions if any. Usually, this is done, after all the boot-time
+ *    enabled CPUs are brought up by the kernel, so that it can make
+ *    better decision based on the available set of CPUs. However, there
+ *    are some special cases, where the action is taken during the early
+ *    boot by the primary boot CPU. (e.g, running the kernel at EL2 with
+ *    Virtualisation Host Extensions). The kernel usually disallows any
+ *    changes to the state of a capability once it finalises the capability
+ *    and takes any action, as it may be impossible to execute the actions
+ *    safely. A CPU brought up after a capability is "finalised" is
+ *    referred to as "Late CPU" w.r.t the capability. e.g, all secondary
+ *    CPUs are treated "late CPUs" for capabilities determined by the boot
+ *    CPU.
+ *
+ *    At the moment there are two passes of finalising the capabilities.
+ *      a) Boot CPU scope capabilities - Finalised by primary boot CPU via
+ *         setup_boot_cpu_capabilities().
+ *      b) Everything except (a) - Run via setup_system_capabilities().
+ *
+ * 3) Verification: When a CPU is brought online (e.g, by user or by the
+ *    kernel), the kernel should make sure that it is safe to use the CPU,
+ *    by verifying that the CPU is compliant with the state of the
+ *    capabilities finalised already. This happens via :
+ *
+ *	secondary_start_kernel()-> check_local_cpu_capabilities()
+ *
+ *    As explained in (2) above, capabilities could be finalised at
+ *    different points in the execution. Each newly booted CPU is verified
+ *    against the capabilities that have been finalised by the time it
+ *    boots.
+ *
+ *	a) SCOPE_BOOT_CPU : All CPUs are verified against the capability
+ *	except for the primary boot CPU.
+ *
+ *	b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the
+ *	user after the kernel boot are verified against the capability.
+ *
+ *    If there is a conflict, the kernel takes an action, based on the
+ *    severity (e.g, a CPU could be prevented from booting or cause a
+ *    kernel panic). The CPU is allowed to "affect" the state of the
+ *    capability, if it has not been finalised already. See section 5
+ *    for more details on conflicts.
+ *
+ * 4) Action: As mentioned in (2), the kernel can take an action for each
+ *    detected capability, on all CPUs on the system. Appropriate actions
+ *    include, turning on an architectural feature, modifying the control
+ *    registers (e.g, SCTLR, TCR etc.) or patching the kernel via
+ *    alternatives. The kernel patching is batched and performed at later
+ *    point. The actions are always initiated only after the capability
+ *    is finalised. This is usally denoted by "enabling" the capability.
+ *    The actions are initiated as follows :
+ *	a) Action is triggered on all online CPUs, after the capability is
+ *	finalised, invoked within the stop_machine() context from
+ *	enable_cpu_capabilitie().
+ *
+ *	b) Any late CPU, brought up after (1), the action is triggered via:
+ *
+ *	  check_local_cpu_capabilities() -> verify_local_cpu_capabilities()
+ *
+ * 5) Conflicts: Based on the state of the capability on a late CPU vs.
+ *    the system state, we could have the following combinations :
+ *
+ *		x-----------------------------x
+ *		| Type  | System   | Late CPU |
+ *		|-----------------------------|
+ *		|  a    |   y      |    n     |
+ *		|-----------------------------|
+ *		|  b    |   n      |    y     |
+ *		x-----------------------------x
+ *
+ *     Two separate flag bits are defined to indicate whether each kind of
+ *     conflict can be allowed:
+ *		ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed
+ *		ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed
+ *
+ *     Case (a) is not permitted for a capability that the system requires
+ *     all CPUs to have in order for the capability to be enabled. This is
+ *     typical for capabilities that represent enhanced functionality.
+ *
+ *     Case (b) is not permitted for a capability that must be enabled
+ *     during boot if any CPU in the system requires it in order to run
+ *     safely. This is typical for erratum work arounds that cannot be
+ *     enabled after the corresponding capability is finalised.
+ *
+ *     In some non-typical cases either both (a) and (b), or neither,
+ *     should be permitted. This can be described by including neither
+ *     or both flags in the capability's type field.
+ *
+ *     In case of a conflict, the CPU is prevented from booting. If the
+ *     ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability,
+ *     then a kernel panic is triggered.
+ */
+
+
+/*
+ * Decide how the capability is detected.
+ * On any local CPU vs System wide vs the primary boot CPU
+ */
+#define ARM64_CPUCAP_SCOPE_LOCAL_CPU		((u16)BIT(0))
+#define ARM64_CPUCAP_SCOPE_SYSTEM		((u16)BIT(1))
+/*
+ * The capabilitiy is detected on the Boot CPU and is used by kernel
+ * during early boot. i.e, the capability should be "detected" and
+ * "enabled" as early as possibly on all booting CPUs.
+ */
+#define ARM64_CPUCAP_SCOPE_BOOT_CPU		((u16)BIT(2))
+#define ARM64_CPUCAP_SCOPE_MASK			\
+	(ARM64_CPUCAP_SCOPE_SYSTEM	|	\
+	 ARM64_CPUCAP_SCOPE_LOCAL_CPU	|	\
+	 ARM64_CPUCAP_SCOPE_BOOT_CPU)
+
+#define SCOPE_SYSTEM				ARM64_CPUCAP_SCOPE_SYSTEM
+#define SCOPE_LOCAL_CPU				ARM64_CPUCAP_SCOPE_LOCAL_CPU
+#define SCOPE_BOOT_CPU				ARM64_CPUCAP_SCOPE_BOOT_CPU
+#define SCOPE_ALL				ARM64_CPUCAP_SCOPE_MASK
+
+/*
+ * Is it permitted for a late CPU to have this capability when system
+ * hasn't already enabled it ?
+ */
+#define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU	((u16)BIT(4))
+/* Is it safe for a late CPU to miss this capability when system has it */
+#define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU	((u16)BIT(5))
+/* Panic when a conflict is detected */
+#define ARM64_CPUCAP_PANIC_ON_CONFLICT		((u16)BIT(6))
+
+/*
+ * CPU errata workarounds that need to be enabled at boot time if one or
+ * more CPUs in the system requires it. When one of these capabilities
+ * has been enabled, it is safe to allow any CPU to boot that doesn't
+ * require the workaround. However, it is not safe if a "late" CPU
+ * requires a workaround and the system hasn't enabled it already.
+ */
+#define ARM64_CPUCAP_LOCAL_CPU_ERRATUM		\
+	(ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU)
+/*
+ * CPU feature detected at boot time based on system-wide value of a
+ * feature. It is safe for a late CPU to have this feature even though
+ * the system hasn't enabled it, although the feature will not be used
+ * by Linux in this case. If the system has enabled this feature already,
+ * then every late CPU must have it.
+ */
+#define ARM64_CPUCAP_SYSTEM_FEATURE	\
+	(ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
+/*
+ * CPU feature detected at boot time based on feature of one or more CPUs.
+ * All possible conflicts for a late CPU are ignored.
+ * NOTE: this means that a late CPU with the feature will *not* cause the
+ * capability to be advertised by cpus_have_*cap()!
+ */
+#define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE		\
+	(ARM64_CPUCAP_SCOPE_LOCAL_CPU		|	\
+	 ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU	|	\
+	 ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
+
+/*
+ * CPU feature detected at boot time, on one or more CPUs. A late CPU
+ * is not allowed to have the capability when the system doesn't have it.
+ * It is Ok for a late CPU to miss the feature.
+ */
+#define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE	\
+	(ARM64_CPUCAP_SCOPE_LOCAL_CPU		|	\
+	 ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU)
+
+/*
+ * CPU feature used early in the boot based on the boot CPU. All secondary
+ * CPUs must match the state of the capability as detected by the boot CPU. In
+ * case of a conflict, a kernel panic is triggered.
+ */
+#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE		\
+	(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT)
+
+/*
+ * CPU feature used early in the boot based on the boot CPU. It is safe for a
+ * late CPU to have this feature even though the boot CPU hasn't enabled it,
+ * although the feature will not be used by Linux in this case. If the boot CPU
+ * has enabled this feature already, then every late CPU must have it.
+ */
+#define ARM64_CPUCAP_BOOT_CPU_FEATURE                  \
+	(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
+
+struct arm64_cpu_capabilities {
+	const char *desc;
+	u16 capability;
+	u16 type;
+	bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
+	/*
+	 * Take the appropriate actions to configure this capability
+	 * for this CPU. If the capability is detected by the kernel
+	 * this will be called on all the CPUs in the system,
+	 * including the hotplugged CPUs, regardless of whether the
+	 * capability is available on that specific CPU. This is
+	 * useful for some capabilities (e.g, working around CPU
+	 * errata), where all the CPUs must take some action (e.g,
+	 * changing system control/configuration). Thus, if an action
+	 * is required only if the CPU has the capability, then the
+	 * routine must check it before taking any action.
+	 */
+	void (*cpu_enable)(const struct arm64_cpu_capabilities *cap);
+	union {
+		struct {	/* To be used for erratum handling only */
+			struct midr_range midr_range;
+			const struct arm64_midr_revidr {
+				u32 midr_rv;		/* revision/variant */
+				u32 revidr_mask;
+			} * const fixed_revs;
+		};
+
+		const struct midr_range *midr_range_list;
+		struct {	/* Feature register checking */
+			u32 sys_reg;
+			u8 field_pos;
+			u8 field_width;
+			u8 min_field_value;
+			u8 hwcap_type;
+			bool sign;
+			unsigned long hwcap;
+		};
+	};
+
+	/*
+	 * An optional list of "matches/cpu_enable" pair for the same
+	 * "capability" of the same "type" as described by the parent.
+	 * Only matches(), cpu_enable() and fields relevant to these
+	 * methods are significant in the list. The cpu_enable is
+	 * invoked only if the corresponding entry "matches()".
+	 * However, if a cpu_enable() method is associated
+	 * with multiple matches(), care should be taken that either
+	 * the match criteria are mutually exclusive, or that the
+	 * method is robust against being called multiple times.
+	 */
+	const struct arm64_cpu_capabilities *match_list;
+};
+
+static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
+{
+	return cap->type & ARM64_CPUCAP_SCOPE_MASK;
+}
+
+/*
+ * Generic helper for handling capabilities with multiple (match,enable) pairs
+ * of call backs, sharing the same capability bit.
+ * Iterate over each entry to see if at least one matches.
+ */
+static inline bool
+cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry,
+			       int scope)
+{
+	const struct arm64_cpu_capabilities *caps;
+
+	for (caps = entry->match_list; caps->matches; caps++)
+		if (caps->matches(caps, scope))
+			return true;
+
+	return false;
+}
+
+static __always_inline bool is_vhe_hyp_code(void)
+{
+	/* Only defined for code run in VHE hyp context */
+	return __is_defined(__KVM_VHE_HYPERVISOR__);
+}
+
+static __always_inline bool is_nvhe_hyp_code(void)
+{
+	/* Only defined for code run in NVHE hyp context */
+	return __is_defined(__KVM_NVHE_HYPERVISOR__);
+}
+
+static __always_inline bool is_hyp_code(void)
+{
+	return is_vhe_hyp_code() || is_nvhe_hyp_code();
+}
+
+extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+
+extern DECLARE_BITMAP(boot_capabilities, ARM64_NCAPS);
+
+#define for_each_available_cap(cap)		\
+	for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS)
+
+bool this_cpu_has_cap(unsigned int cap);
+void cpu_set_feature(unsigned int num);
+bool cpu_have_feature(unsigned int num);
+unsigned long cpu_get_elf_hwcap(void);
+unsigned long cpu_get_elf_hwcap2(void);
+
+#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
+#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
+
+static __always_inline bool system_capabilities_finalized(void)
+{
+	return alternative_has_feature_likely(ARM64_ALWAYS_SYSTEM);
+}
+
+/*
+ * Test for a capability with a runtime check.
+ *
+ * Before the capability is detected, this returns false.
+ */
+static __always_inline bool cpus_have_cap(unsigned int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return arch_test_bit(num, cpu_hwcaps);
+}
+
+/*
+ * Test for a capability without a runtime check.
+ *
+ * Before capabilities are finalized, this returns false.
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool __cpus_have_const_cap(int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return alternative_has_feature_unlikely(num);
+}
+
+/*
+ * Test for a capability without a runtime check.
+ *
+ * Before capabilities are finalized, this will BUG().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool cpus_have_final_cap(int num)
+{
+	if (system_capabilities_finalized())
+		return __cpus_have_const_cap(num);
+	else
+		BUG();
+}
+
+/*
+ * Test for a capability, possibly with a runtime check for non-hyp code.
+ *
+ * For hyp code, this behaves the same as cpus_have_final_cap().
+ *
+ * For non-hyp code:
+ * Before capabilities are finalized, this behaves as cpus_have_cap().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool cpus_have_const_cap(int num)
+{
+	if (is_hyp_code())
+		return cpus_have_final_cap(num);
+	else if (system_capabilities_finalized())
+		return __cpus_have_const_cap(num);
+	else
+		return cpus_have_cap(num);
+}
+
+static inline void cpus_set_cap(unsigned int num)
+{
+	if (num >= ARM64_NCAPS) {
+		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
+			num, ARM64_NCAPS);
+	} else {
+		__set_bit(num, cpu_hwcaps);
+	}
+}
+
+static inline int __attribute_const__
+cpuid_feature_extract_signed_field_width(u64 features, int field, int width)
+{
+	return (s64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static inline int __attribute_const__
+cpuid_feature_extract_signed_field(u64 features, int field)
+{
+	return cpuid_feature_extract_signed_field_width(features, field, 4);
+}
+
+static __always_inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
+{
+	return (u64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static __always_inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field(u64 features, int field)
+{
+	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
+}
+
+/*
+ * Fields that identify the version of the Performance Monitors Extension do
+ * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825,
+ * "Alternative ID scheme used for the Performance Monitors Extension version".
+ */
+static inline u64 __attribute_const__
+cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap)
+{
+	u64 val = cpuid_feature_extract_unsigned_field(features, field);
+	u64 mask = GENMASK_ULL(field + 3, field);
+
+	/* Treat IMPLEMENTATION DEFINED functionality as unimplemented */
+	if (val == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		val = 0;
+
+	if (val > cap) {
+		features &= ~mask;
+		features |= (cap << field) & mask;
+	}
+
+	return features;
+}
+
+static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
+{
+	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
+}
+
+static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg)
+{
+	return (reg->user_val | (reg->sys_val & reg->user_mask));
+}
+
+static inline int __attribute_const__
+cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign)
+{
+	if (WARN_ON_ONCE(!width))
+		width = 4;
+	return (sign) ?
+		cpuid_feature_extract_signed_field_width(features, field, width) :
+		cpuid_feature_extract_unsigned_field_width(features, field, width);
+}
+
+static inline int __attribute_const__
+cpuid_feature_extract_field(u64 features, int field, bool sign)
+{
+	return cpuid_feature_extract_field_width(features, field, 4, sign);
+}
+
+static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
+{
+	return (s64)cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width, ftrp->sign);
+}
+
+static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
+{
+	return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT) == 0x1 ||
+		cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT) == 0x1;
+}
+
+static inline bool id_aa64pfr0_32bit_el1(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL1_SHIFT);
+
+	return val == ID_AA64PFR0_EL1_ELx_32BIT_64BIT;
+}
+
+static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL0_SHIFT);
+
+	return val == ID_AA64PFR0_EL1_ELx_32BIT_64BIT;
+}
+
+static inline bool id_aa64pfr0_sve(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SVE_SHIFT);
+
+	return val > 0;
+}
+
+static inline bool id_aa64pfr1_sme(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_SME_SHIFT);
+
+	return val > 0;
+}
+
+static inline bool id_aa64pfr1_mte(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT);
+
+	return val >= ID_AA64PFR1_EL1_MTE_MTE2;
+}
+
+void __init setup_cpu_features(void);
+void check_local_cpu_capabilities(void);
+
+u64 read_sanitised_ftr_reg(u32 id);
+u64 __read_sysreg_by_encoding(u32 sys_id);
+
+static inline bool cpu_supports_mixed_endian_el0(void)
+{
+	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
+}
+
+
+static inline bool supports_csv2p3(int scope)
+{
+	u64 pfr0;
+	u8 csv2_val;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
+	else
+		pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	csv2_val = cpuid_feature_extract_unsigned_field(pfr0,
+							ID_AA64PFR0_EL1_CSV2_SHIFT);
+	return csv2_val == 3;
+}
+
+static inline bool supports_clearbhb(int scope)
+{
+	u64 isar2;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
+	else
+		isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
+
+	return cpuid_feature_extract_unsigned_field(isar2,
+						    ID_AA64ISAR2_EL1_CLRBHB_SHIFT);
+}
+
+const struct cpumask *system_32bit_el0_cpumask(void);
+DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
+
+static inline bool system_supports_32bit_el0(void)
+{
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	return static_branch_unlikely(&arm64_mismatched_32bit_el0) ||
+	       id_aa64pfr0_32bit_el0(pfr0);
+}
+
+static inline bool system_supports_4kb_granule(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_EL1_TGRAN4_SHIFT);
+
+	return (val >= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN) &&
+	       (val <= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX);
+}
+
+static inline bool system_supports_64kb_granule(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_EL1_TGRAN64_SHIFT);
+
+	return (val >= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN) &&
+	       (val <= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX);
+}
+
+static inline bool system_supports_16kb_granule(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_EL1_TGRAN16_SHIFT);
+
+	return (val >= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN) &&
+	       (val <= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX);
+}
+
+static inline bool system_supports_mixed_endian_el0(void)
+{
+	return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1));
+}
+
+static inline bool system_supports_mixed_endian(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_EL1_BIGEND_SHIFT);
+
+	return val == 0x1;
+}
+
+static __always_inline bool system_supports_fpsimd(void)
+{
+	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
+}
+
+static inline bool system_uses_hw_pan(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_PAN) &&
+		cpus_have_const_cap(ARM64_HAS_PAN);
+}
+
+static inline bool system_uses_ttbr0_pan(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
+		!system_uses_hw_pan();
+}
+
+static __always_inline bool system_supports_sve(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SVE) &&
+		cpus_have_const_cap(ARM64_SVE);
+}
+
+static __always_inline bool system_supports_sme(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME);
+}
+
+static __always_inline bool system_supports_fa64(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME_FA64);
+}
+
+static __always_inline bool system_supports_tpidr2(void)
+{
+	return system_supports_sme();
+}
+
+static __always_inline bool system_supports_cnp(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_CNP) &&
+		cpus_have_const_cap(ARM64_HAS_CNP);
+}
+
+static inline bool system_supports_address_auth(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
+		cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH);
+}
+
+static inline bool system_supports_generic_auth(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
+		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
+}
+
+static inline bool system_has_full_ptr_auth(void)
+{
+	return system_supports_address_auth() && system_supports_generic_auth();
+}
+
+static __always_inline bool system_uses_irq_prio_masking(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
+	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
+}
+
+static inline bool system_supports_mte(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_MTE) &&
+		cpus_have_const_cap(ARM64_MTE);
+}
+
+static inline bool system_has_prio_mask_debugging(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) &&
+	       system_uses_irq_prio_masking();
+}
+
+static inline bool system_supports_bti(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
+}
+
+static inline bool system_supports_tlb_range(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
+		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+}
+
+extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
+
+static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
+{
+	switch (parange) {
+	case ID_AA64MMFR0_EL1_PARANGE_32: return 32;
+	case ID_AA64MMFR0_EL1_PARANGE_36: return 36;
+	case ID_AA64MMFR0_EL1_PARANGE_40: return 40;
+	case ID_AA64MMFR0_EL1_PARANGE_42: return 42;
+	case ID_AA64MMFR0_EL1_PARANGE_44: return 44;
+	case ID_AA64MMFR0_EL1_PARANGE_48: return 48;
+	case ID_AA64MMFR0_EL1_PARANGE_52: return 52;
+	/*
+	 * A future PE could use a value unknown to the kernel.
+	 * However, by the "D10.1.4 Principles of the ID scheme
+	 * for fields in ID registers", ARM DDI 0487C.a, any new
+	 * value is guaranteed to be higher than what we know already.
+	 * As a safe limit, we return the limit supported by the kernel.
+	 */
+	default: return CONFIG_ARM64_PA_BITS;
+	}
+}
+
+/* Check whether hardware update of the Access flag is supported */
+static inline bool cpu_has_hw_af(void)
+{
+	u64 mmfr1;
+
+	if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM))
+		return false;
+
+	/*
+	 * Use cached version to avoid emulated msr operation on KVM
+	 * guests.
+	 */
+	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+	return cpuid_feature_extract_unsigned_field(mmfr1,
+						ID_AA64MMFR1_EL1_HAFDBS_SHIFT);
+}
+
+static inline bool cpu_has_pan(void)
+{
+	u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
+	return cpuid_feature_extract_unsigned_field(mmfr1,
+						    ID_AA64MMFR1_EL1_PAN_SHIFT);
+}
+
+#ifdef CONFIG_ARM64_AMU_EXTN
+/* Check whether the cpu supports the Activity Monitors Unit (AMU) */
+extern bool cpu_has_amu_feat(int cpu);
+#else
+static inline bool cpu_has_amu_feat(int cpu)
+{
+	return false;
+}
+#endif
+
+/* Get a cpu that supports the Activity Monitors Unit (AMU) */
+extern int get_cpu_with_amu_feat(void);
+
+static inline unsigned int get_vmid_bits(u64 mmfr1)
+{
+	int vmid_bits;
+
+	vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1,
+						ID_AA64MMFR1_EL1_VMIDBits_SHIFT);
+	if (vmid_bits == ID_AA64MMFR1_EL1_VMIDBits_16)
+		return 16;
+
+	/*
+	 * Return the default here even if any reserved
+	 * value is fetched from the system register.
+	 */
+	return 8;
+}
+
+struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id);
+
+extern struct arm64_ftr_override id_aa64mmfr1_override;
+extern struct arm64_ftr_override id_aa64pfr0_override;
+extern struct arm64_ftr_override id_aa64pfr1_override;
+extern struct arm64_ftr_override id_aa64zfr0_override;
+extern struct arm64_ftr_override id_aa64smfr0_override;
+extern struct arm64_ftr_override id_aa64isar1_override;
+extern struct arm64_ftr_override id_aa64isar2_override;
+
+u32 get_kvm_ipa_limit(void);
+void dump_cpu_features(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
new file mode 100644
index 000000000..2047713e0
--- /dev/null
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_CPUIDLE_H
+#define __ASM_CPUIDLE_H
+
+#include <asm/proc-fns.h>
+
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+#include <asm/arch_gicv3.h>
+
+struct arm_cpuidle_irq_context {
+	unsigned long pmr;
+	unsigned long daif_bits;
+};
+
+#define arm_cpuidle_save_irq_context(__c)				\
+	do {								\
+		struct arm_cpuidle_irq_context *c = __c;		\
+		if (system_uses_irq_prio_masking()) {			\
+			c->daif_bits = read_sysreg(daif);		\
+			write_sysreg(c->daif_bits | PSR_I_BIT | PSR_F_BIT, \
+				     daif);				\
+			c->pmr = gic_read_pmr();			\
+			gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); \
+		}							\
+	} while (0)
+
+#define arm_cpuidle_restore_irq_context(__c)				\
+	do {								\
+		struct arm_cpuidle_irq_context *c = __c;		\
+		if (system_uses_irq_prio_masking()) {			\
+			gic_write_pmr(c->pmr);				\
+			write_sysreg(c->daif_bits, daif);		\
+		}							\
+	} while (0)
+#else
+struct arm_cpuidle_irq_context { };
+
+#define arm_cpuidle_save_irq_context(c)		(void)c
+#define arm_cpuidle_restore_irq_context(c)	(void)c
+#endif
+#endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
new file mode 100644
index 000000000..7dce9c0aa
--- /dev/null
+++ b/arch/arm64/include/asm/cputype.h
@@ -0,0 +1,275 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_CPUTYPE_H
+#define __ASM_CPUTYPE_H
+
+#define INVALID_HWID		ULONG_MAX
+
+#define MPIDR_UP_BITMASK	(0x1 << 30)
+#define MPIDR_MT_BITMASK	(0x1 << 24)
+#define MPIDR_HWID_BITMASK	UL(0xff00ffffff)
+
+#define MPIDR_LEVEL_BITS_SHIFT	3
+#define MPIDR_LEVEL_BITS	(1 << MPIDR_LEVEL_BITS_SHIFT)
+#define MPIDR_LEVEL_MASK	((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_LEVEL_SHIFT(level) \
+	(((1 << level) >> 1) << MPIDR_LEVEL_BITS_SHIFT)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+	((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
+
+#define MIDR_REVISION_MASK	0xf
+#define MIDR_REVISION(midr)	((midr) & MIDR_REVISION_MASK)
+#define MIDR_PARTNUM_SHIFT	4
+#define MIDR_PARTNUM_MASK	(0xfff << MIDR_PARTNUM_SHIFT)
+#define MIDR_PARTNUM(midr)	\
+	(((midr) & MIDR_PARTNUM_MASK) >> MIDR_PARTNUM_SHIFT)
+#define MIDR_ARCHITECTURE_SHIFT	16
+#define MIDR_ARCHITECTURE_MASK	(0xf << MIDR_ARCHITECTURE_SHIFT)
+#define MIDR_ARCHITECTURE(midr)	\
+	(((midr) & MIDR_ARCHITECTURE_MASK) >> MIDR_ARCHITECTURE_SHIFT)
+#define MIDR_VARIANT_SHIFT	20
+#define MIDR_VARIANT_MASK	(0xf << MIDR_VARIANT_SHIFT)
+#define MIDR_VARIANT(midr)	\
+	(((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT)
+#define MIDR_IMPLEMENTOR_SHIFT	24
+#define MIDR_IMPLEMENTOR_MASK	(0xffU << MIDR_IMPLEMENTOR_SHIFT)
+#define MIDR_IMPLEMENTOR(midr)	\
+	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
+
+#define MIDR_CPU_MODEL(imp, partnum) \
+	((_AT(u32, imp)		<< MIDR_IMPLEMENTOR_SHIFT) | \
+	(0xf			<< MIDR_ARCHITECTURE_SHIFT) | \
+	((partnum)		<< MIDR_PARTNUM_SHIFT))
+
+#define MIDR_CPU_VAR_REV(var, rev) \
+	(((var)	<< MIDR_VARIANT_SHIFT) | (rev))
+
+#define MIDR_CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \
+			     MIDR_ARCHITECTURE_MASK)
+
+#define ARM_CPU_IMP_ARM			0x41
+#define ARM_CPU_IMP_APM			0x50
+#define ARM_CPU_IMP_CAVIUM		0x43
+#define ARM_CPU_IMP_BRCM		0x42
+#define ARM_CPU_IMP_QCOM		0x51
+#define ARM_CPU_IMP_NVIDIA		0x4E
+#define ARM_CPU_IMP_FUJITSU		0x46
+#define ARM_CPU_IMP_HISI		0x48
+#define ARM_CPU_IMP_APPLE		0x61
+#define ARM_CPU_IMP_AMPERE		0xC0
+
+#define ARM_CPU_PART_AEM_V8		0xD0F
+#define ARM_CPU_PART_FOUNDATION		0xD00
+#define ARM_CPU_PART_CORTEX_A57		0xD07
+#define ARM_CPU_PART_CORTEX_A72		0xD08
+#define ARM_CPU_PART_CORTEX_A53		0xD03
+#define ARM_CPU_PART_CORTEX_A73		0xD09
+#define ARM_CPU_PART_CORTEX_A75		0xD0A
+#define ARM_CPU_PART_CORTEX_A35		0xD04
+#define ARM_CPU_PART_CORTEX_A55		0xD05
+#define ARM_CPU_PART_CORTEX_A76		0xD0B
+#define ARM_CPU_PART_NEOVERSE_N1	0xD0C
+#define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_NEOVERSE_V1	0xD40
+#define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_A78AE	0xD42
+#define ARM_CPU_PART_CORTEX_X1		0xD44
+#define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_A520	0xD80
+#define ARM_CPU_PART_CORTEX_A710	0xD47
+#define ARM_CPU_PART_CORTEX_X2		0xD48
+#define ARM_CPU_PART_NEOVERSE_N2	0xD49
+#define ARM_CPU_PART_CORTEX_A78C	0xD4B
+
+#define APM_CPU_PART_XGENE		0x000
+#define APM_CPU_VAR_POTENZA		0x00
+
+#define CAVIUM_CPU_PART_THUNDERX	0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
+#define CAVIUM_CPU_PART_THUNDERX_83XX	0x0A3
+#define CAVIUM_CPU_PART_THUNDERX2	0x0AF
+/* OcteonTx2 series */
+#define CAVIUM_CPU_PART_OCTX2_98XX	0x0B1
+#define CAVIUM_CPU_PART_OCTX2_96XX	0x0B2
+#define CAVIUM_CPU_PART_OCTX2_95XX	0x0B3
+#define CAVIUM_CPU_PART_OCTX2_95XXN	0x0B4
+#define CAVIUM_CPU_PART_OCTX2_95XXMM	0x0B5
+#define CAVIUM_CPU_PART_OCTX2_95XXO	0x0B6
+
+#define BRCM_CPU_PART_BRAHMA_B53	0x100
+#define BRCM_CPU_PART_VULCAN		0x516
+
+#define QCOM_CPU_PART_FALKOR_V1		0x800
+#define QCOM_CPU_PART_FALKOR		0xC00
+#define QCOM_CPU_PART_KRYO		0x200
+#define QCOM_CPU_PART_KRYO_2XX_GOLD	0x800
+#define QCOM_CPU_PART_KRYO_2XX_SILVER	0x801
+#define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
+#define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
+#define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
+
+#define NVIDIA_CPU_PART_DENVER		0x003
+#define NVIDIA_CPU_PART_CARMEL		0x004
+
+#define FUJITSU_CPU_PART_A64FX		0x001
+
+#define HISI_CPU_PART_TSV110		0xD01
+
+#define APPLE_CPU_PART_M1_ICESTORM	0x022
+#define APPLE_CPU_PART_M1_FIRESTORM	0x023
+#define APPLE_CPU_PART_M1_ICESTORM_PRO	0x024
+#define APPLE_CPU_PART_M1_FIRESTORM_PRO	0x025
+#define APPLE_CPU_PART_M1_ICESTORM_MAX	0x028
+#define APPLE_CPU_PART_M1_FIRESTORM_MAX	0x029
+
+#define AMPERE_CPU_PART_AMPERE1		0xAC3
+
+#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
+#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
+#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
+#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
+#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
+#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
+#define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
+#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
+#define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
+#define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
+#define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
+#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
+#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
+#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
+#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
+#define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
+#define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
+#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
+#define MIDR_OCTX2_98XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_98XX)
+#define MIDR_OCTX2_96XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_96XX)
+#define MIDR_OCTX2_95XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XX)
+#define MIDR_OCTX2_95XXN MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXN)
+#define MIDR_OCTX2_95XXMM MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXMM)
+#define MIDR_OCTX2_95XXO MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_OCTX2_95XXO)
+#define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2)
+#define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53)
+#define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN)
+#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
+#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
+#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
+#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
+#define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
+#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
+#define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
+#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
+#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
+#define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
+#define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
+#define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
+#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
+#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
+#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
+#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+
+/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
+#define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
+#define MIDR_FUJITSU_ERRATUM_010001_MASK	(~MIDR_CPU_VAR_REV(1, 0))
+#define TCR_CLEAR_FUJITSU_ERRATUM_010001	(TCR_NFD1 | TCR_NFD0)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/sysreg.h>
+
+#define read_cpuid(reg)			read_sysreg_s(SYS_ ## reg)
+
+/*
+ * Represent a range of MIDR values for a given CPU model and a
+ * range of variant/revision values.
+ *
+ * @model	- CPU model as defined by MIDR_CPU_MODEL
+ * @rv_min	- Minimum value for the revision/variant as defined by
+ *		  MIDR_CPU_VAR_REV
+ * @rv_max	- Maximum value for the variant/revision for the range.
+ */
+struct midr_range {
+	u32 model;
+	u32 rv_min;
+	u32 rv_max;
+};
+
+#define MIDR_RANGE(m, v_min, r_min, v_max, r_max)		\
+	{							\
+		.model = m,					\
+		.rv_min = MIDR_CPU_VAR_REV(v_min, r_min),	\
+		.rv_max = MIDR_CPU_VAR_REV(v_max, r_max),	\
+	}
+
+#define MIDR_REV_RANGE(m, v, r_min, r_max) MIDR_RANGE(m, v, r_min, v, r_max)
+#define MIDR_REV(m, v, r) MIDR_RANGE(m, v, r, v, r)
+#define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf)
+
+static inline bool midr_is_cpu_model_range(u32 midr, u32 model, u32 rv_min,
+					   u32 rv_max)
+{
+	u32 _model = midr & MIDR_CPU_MODEL_MASK;
+	u32 rv = midr & (MIDR_REVISION_MASK | MIDR_VARIANT_MASK);
+
+	return _model == model && rv >= rv_min && rv <= rv_max;
+}
+
+static inline bool is_midr_in_range(u32 midr, struct midr_range const *range)
+{
+	return midr_is_cpu_model_range(midr, range->model,
+				       range->rv_min, range->rv_max);
+}
+
+static inline bool
+is_midr_in_range_list(u32 midr, struct midr_range const *ranges)
+{
+	while (ranges->model)
+		if (is_midr_in_range(midr, ranges++))
+			return true;
+	return false;
+}
+
+/*
+ * The CPU ID never changes at run time, so we might as well tell the
+ * compiler that it's constant.  Use this function to read the CPU ID
+ * rather than directly reading processor_id or read_cpuid() directly.
+ */
+static inline u32 __attribute_const__ read_cpuid_id(void)
+{
+	return read_cpuid(MIDR_EL1);
+}
+
+static inline u64 __attribute_const__ read_cpuid_mpidr(void)
+{
+	return read_cpuid(MPIDR_EL1);
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
+{
+	return MIDR_IMPLEMENTOR(read_cpuid_id());
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
+{
+	return MIDR_PARTNUM(read_cpuid_id());
+}
+
+static inline u32 __attribute_const__ read_cpuid_cachetype(void)
+{
+	return read_cpuid(CTR_EL0);
+}
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
new file mode 100644
index 000000000..54ceae087
--- /dev/null
+++ b/arch/arm64/include/asm/current.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+/*
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
+ */
+static __always_inline struct task_struct *get_current(void)
+{
+	unsigned long sp_el0;
+
+	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
+
+	return (struct task_struct *)sp_el0;
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
+
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
new file mode 100644
index 000000000..55f57dfa8
--- /dev/null
+++ b/arch/arm64/include/asm/daifflags.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 ARM Ltd.
+ */
+#ifndef __ASM_DAIFFLAGS_H
+#define __ASM_DAIFFLAGS_H
+
+#include <linux/irqflags.h>
+
+#include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/ptrace.h>
+
+#define DAIF_PROCCTX		0
+#define DAIF_PROCCTX_NOIRQ	(PSR_I_BIT | PSR_F_BIT)
+#define DAIF_ERRCTX		(PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+#define DAIF_MASK		(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+
+
+/* mask/save/unmask/restore all exceptions, including interrupts. */
+static inline void local_daif_mask(void)
+{
+	WARN_ON(system_has_prio_mask_debugging() &&
+		(read_sysreg_s(SYS_ICC_PMR_EL1) == (GIC_PRIO_IRQOFF |
+						    GIC_PRIO_PSR_I_SET)));
+
+	asm volatile(
+		"msr	daifset, #0xf		// local_daif_mask\n"
+		:
+		:
+		: "memory");
+
+	/* Don't really care for a dsb here, we don't intend to enable IRQs */
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+
+	trace_hardirqs_off();
+}
+
+static inline unsigned long local_daif_save_flags(void)
+{
+	unsigned long flags;
+
+	flags = read_sysreg(daif);
+
+	if (system_uses_irq_prio_masking()) {
+		/* If IRQs are masked with PMR, reflect it in the flags */
+		if (read_sysreg_s(SYS_ICC_PMR_EL1) != GIC_PRIO_IRQON)
+			flags |= PSR_I_BIT | PSR_F_BIT;
+	}
+
+	return flags;
+}
+
+static inline unsigned long local_daif_save(void)
+{
+	unsigned long flags;
+
+	flags = local_daif_save_flags();
+
+	local_daif_mask();
+
+	return flags;
+}
+
+static inline void local_daif_restore(unsigned long flags)
+{
+	bool irq_disabled = flags & PSR_I_BIT;
+
+	WARN_ON(system_has_prio_mask_debugging() &&
+		(read_sysreg(daif) & (PSR_I_BIT | PSR_F_BIT)) != (PSR_I_BIT | PSR_F_BIT));
+
+	if (!irq_disabled) {
+		trace_hardirqs_on();
+
+		if (system_uses_irq_prio_masking()) {
+			gic_write_pmr(GIC_PRIO_IRQON);
+			pmr_sync();
+		}
+	} else if (system_uses_irq_prio_masking()) {
+		u64 pmr;
+
+		if (!(flags & PSR_A_BIT)) {
+			/*
+			 * If interrupts are disabled but we can take
+			 * asynchronous errors, we can take NMIs
+			 */
+			flags &= ~(PSR_I_BIT | PSR_F_BIT);
+			pmr = GIC_PRIO_IRQOFF;
+		} else {
+			pmr = GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET;
+		}
+
+		/*
+		 * There has been concern that the write to daif
+		 * might be reordered before this write to PMR.
+		 * From the ARM ARM DDI 0487D.a, section D1.7.1
+		 * "Accessing PSTATE fields":
+		 *   Writes to the PSTATE fields have side-effects on
+		 *   various aspects of the PE operation. All of these
+		 *   side-effects are guaranteed:
+		 *     - Not to be visible to earlier instructions in
+		 *       the execution stream.
+		 *     - To be visible to later instructions in the
+		 *       execution stream
+		 *
+		 * Also, writes to PMR are self-synchronizing, so no
+		 * interrupts with a lower priority than PMR is signaled
+		 * to the PE after the write.
+		 *
+		 * So we don't need additional synchronization here.
+		 */
+		gic_write_pmr(pmr);
+	}
+
+	write_sysreg(flags, daif);
+
+	if (irq_disabled)
+		trace_hardirqs_off();
+}
+
+/*
+ * Called by synchronous exception handlers to restore the DAIF bits that were
+ * modified by taking an exception.
+ */
+static inline void local_daif_inherit(struct pt_regs *regs)
+{
+	unsigned long flags = regs->pstate & DAIF_MASK;
+
+	if (interrupts_enabled(regs))
+		trace_hardirqs_on();
+
+	if (system_uses_irq_prio_masking())
+		gic_write_pmr(regs->pmr_save);
+
+	/*
+	 * We can't use local_daif_restore(regs->pstate) here as
+	 * system_has_prio_mask_debugging() won't restore the I bit if it can
+	 * use the pmr instead.
+	 */
+	write_sysreg(flags, daif);
+}
+#endif
diff --git a/arch/arm64/include/asm/dcc.h b/arch/arm64/include/asm/dcc.h
new file mode 100644
index 000000000..ebd9fb472
--- /dev/null
+++ b/arch/arm64/include/asm/dcc.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2014-2015 The Linux Foundation. All rights reserved.
+ *
+ * A call to __dcc_getchar() or __dcc_putchar() is typically followed by
+ * a call to __dcc_getstatus().  We want to make sure that the CPU does
+ * not speculative read the DCC status before executing the read or write
+ * instruction.  That's what the ISBs are for.
+ *
+ * The 'volatile' ensures that the compiler does not cache the status bits,
+ * and instead reads the DCC register every time.
+ */
+#ifndef __ASM_DCC_H
+#define __ASM_DCC_H
+
+#include <asm/barrier.h>
+#include <asm/sysreg.h>
+
+static inline u32 __dcc_getstatus(void)
+{
+	return read_sysreg(mdccsr_el0);
+}
+
+static inline char __dcc_getchar(void)
+{
+	char c = read_sysreg(dbgdtrrx_el0);
+	isb();
+
+	return c;
+}
+
+static inline void __dcc_putchar(char c)
+{
+	/*
+	 * The typecast is to make absolutely certain that 'c' is
+	 * zero-extended.
+	 */
+	write_sysreg((unsigned char)c, dbgdtrtx_el0);
+	isb();
+}
+
+#endif
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
new file mode 100644
index 000000000..13d437bcb
--- /dev/null
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_DEBUG_MONITORS_H
+#define __ASM_DEBUG_MONITORS_H
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <asm/brk-imm.h>
+#include <asm/esr.h>
+#include <asm/insn.h>
+#include <asm/ptrace.h>
+
+/* Low-level stepping controls. */
+#define DBG_MDSCR_SS		(1 << 0)
+#define DBG_SPSR_SS		(1 << 21)
+
+/* MDSCR_EL1 enabling bits */
+#define DBG_MDSCR_KDE		(1 << 13)
+#define DBG_MDSCR_MDE		(1 << 15)
+#define DBG_MDSCR_MASK		~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
+
+#define	DBG_ESR_EVT(x)		(((x) >> 27) & 0x7)
+
+/* AArch64 */
+#define DBG_ESR_EVT_HWBP	0x0
+#define DBG_ESR_EVT_HWSS	0x1
+#define DBG_ESR_EVT_HWWP	0x2
+#define DBG_ESR_EVT_BRK		0x6
+
+/*
+ * Break point instruction encoding
+ */
+#define BREAK_INSTR_SIZE		AARCH64_INSN_SIZE
+
+#define AARCH64_BREAK_KGDB_DYN_DBG	\
+	(AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5))
+
+#define CACHE_FLUSH_IS_SAFE		1
+
+/* kprobes BRK opcodes with ESR encoding  */
+#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
+#define BRK64_OPCODE_KPROBES_SS	(AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5))
+/* uprobes BRK opcodes with ESR encoding  */
+#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
+
+/* AArch32 */
+#define DBG_ESR_EVT_BKPT	0x4
+#define DBG_ESR_EVT_VECC	0x5
+
+#define AARCH32_BREAK_ARM	0x07f001f0
+#define AARCH32_BREAK_THUMB	0xde01
+#define AARCH32_BREAK_THUMB2_LO	0xf7f0
+#define AARCH32_BREAK_THUMB2_HI	0xa000
+
+#ifndef __ASSEMBLY__
+struct task_struct;
+
+#define DBG_ARCH_ID_RESERVED	0	/* In case of ptrace ABI updates. */
+
+#define DBG_HOOK_HANDLED	0
+#define DBG_HOOK_ERROR		1
+
+struct step_hook {
+	struct list_head node;
+	int (*fn)(struct pt_regs *regs, unsigned long esr);
+};
+
+void register_user_step_hook(struct step_hook *hook);
+void unregister_user_step_hook(struct step_hook *hook);
+
+void register_kernel_step_hook(struct step_hook *hook);
+void unregister_kernel_step_hook(struct step_hook *hook);
+
+struct break_hook {
+	struct list_head node;
+	int (*fn)(struct pt_regs *regs, unsigned long esr);
+	u16 imm;
+	u16 mask; /* These bits are ignored when comparing with imm */
+};
+
+void register_user_break_hook(struct break_hook *hook);
+void unregister_user_break_hook(struct break_hook *hook);
+
+void register_kernel_break_hook(struct break_hook *hook);
+void unregister_kernel_break_hook(struct break_hook *hook);
+
+u8 debug_monitors_arch(void);
+
+enum dbg_active_el {
+	DBG_ACTIVE_EL0 = 0,
+	DBG_ACTIVE_EL1,
+};
+
+void enable_debug_monitors(enum dbg_active_el el);
+void disable_debug_monitors(enum dbg_active_el el);
+
+void user_rewind_single_step(struct task_struct *task);
+void user_fastforward_single_step(struct task_struct *task);
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task);
+
+void kernel_enable_single_step(struct pt_regs *regs);
+void kernel_disable_single_step(void);
+int kernel_active_single_step(void);
+void kernel_rewind_single_step(struct pt_regs *regs);
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int reinstall_suspended_bps(struct pt_regs *regs);
+#else
+static inline int reinstall_suspended_bps(struct pt_regs *regs)
+{
+	return -ENODEV;
+}
+#endif
+
+int aarch32_break_handler(struct pt_regs *regs);
+
+void debug_traps_init(void);
+
+#endif	/* __ASSEMBLY */
+#endif	/* __ASM_DEBUG_MONITORS_H */
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
new file mode 100644
index 000000000..996498751
--- /dev/null
+++ b/arch/arm64/include/asm/device.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_DEVICE_H
+#define __ASM_DEVICE_H
+
+struct dev_archdata {
+};
+
+struct pdev_archdata {
+};
+
+#endif
diff --git a/arch/arm64/include/asm/dmi.h b/arch/arm64/include/asm/dmi.h
new file mode 100644
index 000000000..69d37d87b
--- /dev/null
+++ b/arch/arm64/include/asm/dmi.h
@@ -0,0 +1,31 @@
+/*
+ * arch/arm64/include/asm/dmi.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ * Written by: Yi Li (yi.li@linaro.org)
+ *
+ * based on arch/ia64/include/asm/dmi.h
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef __ASM_DMI_H
+#define __ASM_DMI_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+
+/*
+ * According to section 2.3.6 of the UEFI spec, the firmware should not
+ * request a virtual mapping for configuration tables such as SMBIOS.
+ * This means we have to map them before use.
+ */
+#define dmi_early_remap(x, l)		ioremap_cache(x, l)
+#define dmi_early_unmap(x, l)		iounmap(x)
+#define dmi_remap(x, l)			ioremap_cache(x, l)
+#define dmi_unmap(x)			iounmap(x)
+#define dmi_alloc(l)			kzalloc(l, GFP_KERNEL)
+
+#endif
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
new file mode 100644
index 000000000..62c846be2
--- /dev/null
+++ b/arch/arm64/include/asm/efi.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_EFI_H
+#define _ASM_EFI_H
+
+#include <asm/boot.h>
+#include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
+#include <asm/io.h>
+#include <asm/memory.h>
+#include <asm/mmu_context.h>
+#include <asm/neon.h>
+#include <asm/ptrace.h>
+#include <asm/tlbflush.h>
+
+#ifdef CONFIG_EFI
+extern void efi_init(void);
+
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg);
+#else
+#define efi_init()
+
+static inline
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
+{
+	return false;
+}
+#endif
+
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
+
+#define arch_efi_call_virt_setup()					\
+({									\
+	efi_virtmap_load();						\
+	__efi_fpsimd_begin();						\
+	raw_spin_lock(&efi_rt_lock);					\
+})
+
+#undef arch_efi_call_virt
+#define arch_efi_call_virt(p, f, args...)				\
+	__efi_rt_asm_wrapper((p)->f, #f, args)
+
+#define arch_efi_call_virt_teardown()					\
+({									\
+	raw_spin_unlock(&efi_rt_lock);					\
+	__efi_fpsimd_end();						\
+	efi_virtmap_unload();						\
+})
+
+extern raw_spinlock_t efi_rt_lock;
+extern u64 *efi_rt_stack_top;
+efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
+
+/*
+ * efi_rt_stack_top[-1] contains the value the stack pointer had before
+ * switching to the EFI runtime stack.
+ */
+#define current_in_efi()						\
+	(!preemptible() && efi_rt_stack_top != NULL &&			\
+	 on_task_stack(current, READ_ONCE(efi_rt_stack_top[-1]), 1))
+
+#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+
+/*
+ * Even when Linux uses IRQ priorities for IRQ disabling, EFI does not.
+ * And EFI shouldn't really play around with priority masking as it is not aware
+ * which priorities the OS has assigned to its interrupts.
+ */
+#define arch_efi_save_flags(state_flags)		\
+	((void)((state_flags) = read_sysreg(daif)))
+
+#define arch_efi_restore_flags(state_flags)	write_sysreg(state_flags, daif)
+
+
+/* arch specific definitions used by the stub code */
+
+/*
+ * In some configurations (e.g. VMAP_STACK && 64K pages), stacks built into the
+ * kernel need greater alignment than we require the segments to be padded to.
+ */
+#define EFI_KIMG_ALIGN	\
+	(SEGMENT_ALIGN > THREAD_ALIGN ? SEGMENT_ALIGN : THREAD_ALIGN)
+
+/*
+ * On arm64, we have to ensure that the initrd ends up in the linear region,
+ * which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is
+ * guaranteed to cover the kernel Image.
+ *
+ * Since the EFI stub is part of the kernel Image, we can relax the
+ * usual requirements in Documentation/arm64/booting.rst, which still
+ * apply to other bootloaders, and are required for some kernel
+ * configurations.
+ */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
+{
+	return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1));
+}
+
+#define alloc_screen_info(x...)		&screen_info
+
+static inline void free_screen_info(struct screen_info *si)
+{
+}
+
+#define EFI_ALLOC_ALIGN		SZ_64K
+
+/*
+ * On ARM systems, virtually remapped UEFI runtime services are set up in two
+ * distinct stages:
+ * - The stub retrieves the final version of the memory map from UEFI, populates
+ *   the virt_addr fields and calls the SetVirtualAddressMap() [SVAM] runtime
+ *   service to communicate the new mapping to the firmware (Note that the new
+ *   mapping is not live at this time)
+ * - During an early initcall(), the EFI system table is permanently remapped
+ *   and the virtual remapping of the UEFI Runtime Services regions is loaded
+ *   into a private set of page tables. If this all succeeds, the Runtime
+ *   Services are enabled and the EFI_RUNTIME_SERVICES bit set.
+ */
+
+static inline void efi_set_pgd(struct mm_struct *mm)
+{
+	__switch_mm(mm);
+
+	if (system_uses_ttbr0_pan()) {
+		if (mm != current->active_mm) {
+			/*
+			 * Update the current thread's saved ttbr0 since it is
+			 * restored as part of a return from exception. Enable
+			 * access to the valid TTBR0_EL1 and invoke the errata
+			 * workaround directly since there is no return from
+			 * exception when invoking the EFI run-time services.
+			 */
+			update_saved_ttbr0(current, mm);
+			uaccess_ttbr0_enable();
+			post_ttbr_update_workaround();
+		} else {
+			/*
+			 * Defer the switch to the current thread's TTBR0_EL1
+			 * until uaccess_enable(). Restore the current
+			 * thread's saved ttbr0 corresponding to its active_mm
+			 */
+			uaccess_ttbr0_disable();
+			update_saved_ttbr0(current, current->active_mm);
+		}
+	}
+}
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
+static inline void efi_capsule_flush_cache_range(void *addr, int size)
+{
+	dcache_clean_inval_poc((unsigned long)addr, (unsigned long)addr + size);
+}
+
+#endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
new file mode 100644
index 000000000..668569adf
--- /dev/null
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM_KVM_INIT_H__
+#define __ARM_KVM_INIT_H__
+
+#ifndef __ASSEMBLY__
+#error Assembly-only header
+#endif
+
+#include <asm/kvm_arm.h>
+#include <asm/ptrace.h>
+#include <asm/sysreg.h>
+#include <linux/irqchip/arm-gic-v3.h>
+
+.macro __init_el2_sctlr
+	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
+	msr	sctlr_el2, x0
+	isb
+.endm
+
+/*
+ * Allow Non-secure EL1 and EL0 to access physical timer and counter.
+ * This is not necessary for VHE, since the host kernel runs in EL2,
+ * and EL0 accesses are configured in the later stage of boot process.
+ * Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout
+ * as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined
+ * to access CNTHCTL_EL2. This allows the kernel designed to run at EL1
+ * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
+ * EL2.
+ */
+.macro __init_el2_timers
+	mov	x0, #3				// Enable EL1 physical timers
+	msr	cnthctl_el2, x0
+	msr	cntvoff_el2, xzr		// Clear virtual offset
+.endm
+
+.macro __init_el2_debug
+	mrs	x1, id_aa64dfr0_el1
+	sbfx	x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x0, #1
+	b.lt	.Lskip_pmu_\@			// Skip if no PMU present
+	mrs	x0, pmcr_el0			// Disable debug access traps
+	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
+.Lskip_pmu_\@:
+	csel	x2, xzr, x0, lt			// all PMU counters from EL1
+
+	/* Statistical profiling */
+	ubfx	x0, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4
+	cbz	x0, .Lskip_spe_\@		// Skip if SPE not present
+
+	mrs_s	x0, SYS_PMBIDR_EL1              // If SPE available at EL2,
+	and	x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
+	cbnz	x0, .Lskip_spe_el2_\@		// then permit sampling of physical
+	mov	x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
+		      1 << SYS_PMSCR_EL2_PA_SHIFT)
+	msr_s	SYS_PMSCR_EL2, x0		// addresses and physical counter
+.Lskip_spe_el2_\@:
+	mov	x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
+	orr	x2, x2, x0			// If we don't have VHE, then
+						// use EL1&0 translation.
+
+.Lskip_spe_\@:
+	/* Trace buffer */
+	ubfx	x0, x1, #ID_AA64DFR0_EL1_TraceBuffer_SHIFT, #4
+	cbz	x0, .Lskip_trace_\@		// Skip if TraceBuffer is not present
+
+	mrs_s	x0, SYS_TRBIDR_EL1
+	and	x0, x0, TRBIDR_PROG
+	cbnz	x0, .Lskip_trace_\@		// If TRBE is available at EL2
+
+	mov	x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT)
+	orr	x2, x2, x0			// allow the EL1&0 translation
+						// to own it.
+
+.Lskip_trace_\@:
+	msr	mdcr_el2, x2			// Configure debug traps
+.endm
+
+/* LORegions */
+.macro __init_el2_lor
+	mrs	x1, id_aa64mmfr1_el1
+	ubfx	x0, x1, #ID_AA64MMFR1_EL1_LO_SHIFT, 4
+	cbz	x0, .Lskip_lor_\@
+	msr_s	SYS_LORC_EL1, xzr
+.Lskip_lor_\@:
+.endm
+
+/* Stage-2 translation */
+.macro __init_el2_stage2
+	msr	vttbr_el2, xzr
+.endm
+
+/* GICv3 system register access */
+.macro __init_el2_gicv3
+	mrs	x0, id_aa64pfr0_el1
+	ubfx	x0, x0, #ID_AA64PFR0_EL1_GIC_SHIFT, #4
+	cbz	x0, .Lskip_gicv3_\@
+
+	mrs_s	x0, SYS_ICC_SRE_EL2
+	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
+	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
+	msr_s	SYS_ICC_SRE_EL2, x0
+	isb					// Make sure SRE is now set
+	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
+	tbz	x0, #0, .Lskip_gicv3_\@		// and check that it sticks
+	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICH_HCR_EL2 to defaults
+.Lskip_gicv3_\@:
+.endm
+
+.macro __init_el2_hstr
+	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
+.endm
+
+/* Virtual CPU ID registers */
+.macro __init_el2_nvhe_idregs
+	mrs	x0, midr_el1
+	mrs	x1, mpidr_el1
+	msr	vpidr_el2, x0
+	msr	vmpidr_el2, x1
+.endm
+
+/* Coprocessor traps */
+.macro __init_el2_nvhe_cptr
+	mov	x0, #0x33ff
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+.endm
+
+/* Disable any fine grained traps */
+.macro __init_el2_fgt
+	mrs	x1, id_aa64mmfr0_el1
+	ubfx	x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4
+	cbz	x1, .Lskip_fgt_\@
+
+	mov	x0, xzr
+	mrs	x1, id_aa64dfr0_el1
+	ubfx	x1, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4
+	cmp	x1, #3
+	b.lt	.Lset_debug_fgt_\@
+	/* Disable PMSNEVFR_EL1 read and write traps */
+	orr	x0, x0, #(1 << 62)
+
+.Lset_debug_fgt_\@:
+	msr_s	SYS_HDFGRTR_EL2, x0
+	msr_s	SYS_HDFGWTR_EL2, x0
+
+	mov	x0, xzr
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4
+	cbz	x1, .Lset_fgt_\@
+
+	/* Disable nVHE traps of TPIDR2 and SMPRI */
+	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
+	orr	x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
+
+.Lset_fgt_\@:
+	msr_s	SYS_HFGRTR_EL2, x0
+	msr_s	SYS_HFGWTR_EL2, x0
+	msr_s	SYS_HFGITR_EL2, xzr
+
+	mrs	x1, id_aa64pfr0_el1		// AMU traps UNDEF without AMU
+	ubfx	x1, x1, #ID_AA64PFR0_EL1_AMU_SHIFT, #4
+	cbz	x1, .Lskip_fgt_\@
+
+	msr_s	SYS_HAFGRTR_EL2, xzr
+.Lskip_fgt_\@:
+.endm
+
+.macro __init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
+.endm
+
+/**
+ * Initialize EL2 registers to sane values. This should be called early on all
+ * cores that were booted in EL2. Note that everything gets initialised as
+ * if VHE was not evailable. The kernel context will be upgraded to VHE
+ * if possible later on in the boot process
+ *
+ * Regs: x0, x1 and x2 are clobbered.
+ */
+.macro init_el2_state
+	__init_el2_sctlr
+	__init_el2_timers
+	__init_el2_debug
+	__init_el2_lor
+	__init_el2_stage2
+	__init_el2_gicv3
+	__init_el2_hstr
+	__init_el2_nvhe_idregs
+	__init_el2_nvhe_cptr
+	__init_el2_fgt
+	__init_el2_nvhe_prepare_eret
+.endm
+
+#endif /* __ARM_KVM_INIT_H__ */
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
new file mode 100644
index 000000000..97932fbf9
--- /dev/null
+++ b/arch/arm64/include/asm/elf.h
@@ -0,0 +1,298 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_ELF_H
+#define __ASM_ELF_H
+
+#include <asm/hwcap.h>
+
+/*
+ * ELF register definitions..
+ */
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+/*
+ * AArch64 static relocation types.
+ */
+
+/* Miscellaneous. */
+#define R_ARM_NONE			0
+#define R_AARCH64_NONE			256
+
+/* Data. */
+#define R_AARCH64_ABS64			257
+#define R_AARCH64_ABS32			258
+#define R_AARCH64_ABS16			259
+#define R_AARCH64_PREL64		260
+#define R_AARCH64_PREL32		261
+#define R_AARCH64_PREL16		262
+
+/* Instructions. */
+#define R_AARCH64_MOVW_UABS_G0		263
+#define R_AARCH64_MOVW_UABS_G0_NC	264
+#define R_AARCH64_MOVW_UABS_G1		265
+#define R_AARCH64_MOVW_UABS_G1_NC	266
+#define R_AARCH64_MOVW_UABS_G2		267
+#define R_AARCH64_MOVW_UABS_G2_NC	268
+#define R_AARCH64_MOVW_UABS_G3		269
+
+#define R_AARCH64_MOVW_SABS_G0		270
+#define R_AARCH64_MOVW_SABS_G1		271
+#define R_AARCH64_MOVW_SABS_G2		272
+
+#define R_AARCH64_LD_PREL_LO19		273
+#define R_AARCH64_ADR_PREL_LO21		274
+#define R_AARCH64_ADR_PREL_PG_HI21	275
+#define R_AARCH64_ADR_PREL_PG_HI21_NC	276
+#define R_AARCH64_ADD_ABS_LO12_NC	277
+#define R_AARCH64_LDST8_ABS_LO12_NC	278
+
+#define R_AARCH64_TSTBR14		279
+#define R_AARCH64_CONDBR19		280
+#define R_AARCH64_JUMP26		282
+#define R_AARCH64_CALL26		283
+#define R_AARCH64_LDST16_ABS_LO12_NC	284
+#define R_AARCH64_LDST32_ABS_LO12_NC	285
+#define R_AARCH64_LDST64_ABS_LO12_NC	286
+#define R_AARCH64_LDST128_ABS_LO12_NC	299
+
+#define R_AARCH64_MOVW_PREL_G0		287
+#define R_AARCH64_MOVW_PREL_G0_NC	288
+#define R_AARCH64_MOVW_PREL_G1		289
+#define R_AARCH64_MOVW_PREL_G1_NC	290
+#define R_AARCH64_MOVW_PREL_G2		291
+#define R_AARCH64_MOVW_PREL_G2_NC	292
+#define R_AARCH64_MOVW_PREL_G3		293
+
+#define R_AARCH64_RELATIVE		1027
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS64
+#ifdef __AARCH64EB__
+#define ELF_DATA	ELFDATA2MSB
+#else
+#define ELF_DATA	ELFDATA2LSB
+#endif
+#define ELF_ARCH	EM_AARCH64
+
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
+#define ELF_PLATFORM_SIZE	16
+#ifdef __AARCH64EB__
+#define ELF_PLATFORM		("aarch64_be")
+#else
+#define ELF_PLATFORM		("aarch64")
+#endif
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x)		((x)->e_machine == EM_AARCH64)
+
+/*
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically.
+ *
+ * The decision process for determining the results are:
+ *
+ *                CPU*: | arm32      | arm64      |
+ * ELF:                 |            |            |
+ * ---------------------|------------|------------|
+ * missing PT_GNU_STACK | exec-all   | exec-none  |
+ * PT_GNU_STACK == RWX  | exec-stack | exec-stack |
+ * PT_GNU_STACK == RW   | exec-none  | exec-none  |
+ *
+ *  exec-all  : all PROT_READ user mappings are executable, except when
+ *              backed by files on a noexec-filesystem.
+ *  exec-none : only PROT_EXEC user mappings are executable.
+ *  exec-stack: only the stack and PROT_EXEC user mappings are executable.
+ *
+ *  *all arm64 CPUs support NX, so there is no "lacks NX" column.
+ *
+ */
+#define compat_elf_read_implies_exec(ex, stk)	(stk == EXSTACK_DEFAULT)
+
+#define CORE_DUMP_USE_REGSET
+#define ELF_EXEC_PAGESIZE	PAGE_SIZE
+
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#ifdef CONFIG_ARM64_FORCE_52BIT
+#define ELF_ET_DYN_BASE		(2 * TASK_SIZE_64 / 3)
+#else
+#define ELF_ET_DYN_BASE		(2 * DEFAULT_MAP_WINDOW_64 / 3)
+#endif /* CONFIG_ARM64_FORCE_52BIT */
+
+#ifndef __ASSEMBLY__
+
+#include <uapi/linux/elf.h>
+#include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <asm/processor.h> /* for signal_minsigstksz, used by ARCH_DLINFO */
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof(struct user_pt_regs) / sizeof(elf_greg_t))
+#define ELF_CORE_COPY_REGS(dest, regs)	\
+	*(struct user_pt_regs *)&(dest) = (regs)->user_regs;
+
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+typedef struct user_fpsimd_state elf_fpregset_t;
+
+/*
+ * When the program starts, a1 contains a pointer to a function to be
+ * registered with atexit, as per the SVR4 ABI.  A value of 0 means we have no
+ * such handler.
+ */
+#define ELF_PLAT_INIT(_r, load_addr)	(_r)->regs[0] = 0
+
+#define SET_PERSONALITY(ex)						\
+({									\
+	clear_thread_flag(TIF_32BIT);					\
+	current->personality &= ~READ_IMPLIES_EXEC;			\
+})
+
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
+#define ARCH_DLINFO							\
+do {									\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
+		    (elf_addr_t)current->mm->context.vdso);		\
+									\
+	/*								\
+	 * Should always be nonzero unless there's a kernel bug.	\
+	 * If we haven't determined a sensible value to give to		\
+	 * userspace, omit the entry:					\
+	 */								\
+	if (likely(signal_minsigstksz))					\
+		NEW_AUX_ENT(AT_MINSIGSTKSZ, signal_minsigstksz);	\
+	else								\
+		NEW_AUX_ENT(AT_IGNORE, 0);				\
+} while (0)
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp);
+
+/* 1GB of VA */
+#ifdef CONFIG_COMPAT
+#define STACK_RND_MASK			(test_thread_flag(TIF_32BIT) ? \
+						0x7ff >> (PAGE_SHIFT - 12) : \
+						0x3ffff >> (PAGE_SHIFT - 12))
+#else
+#define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
+#endif
+
+#ifdef __AARCH64EB__
+#define COMPAT_ELF_PLATFORM		("v8b")
+#else
+#define COMPAT_ELF_PLATFORM		("v8l")
+#endif
+
+#ifdef CONFIG_COMPAT
+
+/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */
+#define COMPAT_ELF_ET_DYN_BASE		0x000400000UL
+
+/* AArch32 registers. */
+#define COMPAT_ELF_NGREG		18
+typedef unsigned int			compat_elf_greg_t;
+typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
+
+/* AArch32 EABI. */
+#define EF_ARM_EABI_MASK		0xff000000
+int compat_elf_check_arch(const struct elf32_hdr *);
+#define compat_elf_check_arch		compat_elf_check_arch
+#define compat_start_thread		compat_start_thread
+/*
+ * Unlike the native SET_PERSONALITY macro, the compat version maintains
+ * READ_IMPLIES_EXEC across an execve() since this is the behaviour on
+ * arch/arm/.
+ */
+#define COMPAT_SET_PERSONALITY(ex)					\
+({									\
+	set_thread_flag(TIF_32BIT);					\
+ })
+#ifdef CONFIG_COMPAT_VDSO
+#define COMPAT_ARCH_DLINFO						\
+do {									\
+	/*								\
+	 * Note that we use Elf64_Off instead of elf_addr_t because	\
+	 * elf_addr_t in compat is defined as Elf32_Addr and casting	\
+	 * current->mm->context.vdso to it triggers a cast warning of	\
+	 * cast from pointer to integer of different size.		\
+	 */								\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
+			(Elf64_Off)current->mm->context.vdso);		\
+} while (0)
+#else
+#define COMPAT_ARCH_DLINFO
+#endif
+extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
+					  int uses_interp);
+#define compat_arch_setup_additional_pages \
+					aarch32_setup_additional_pages
+
+#endif /* CONFIG_COMPAT */
+
+struct arch_elf_state {
+	int flags;
+};
+
+#define ARM64_ELF_BTI		(1 << 0)
+
+#define INIT_ARCH_ELF_STATE {			\
+	.flags = 0,				\
+}
+
+static inline int arch_parse_elf_property(u32 type, const void *data,
+					  size_t datasz, bool compat,
+					  struct arch_elf_state *arch)
+{
+	/* No known properties for AArch32 yet */
+	if (IS_ENABLED(CONFIG_COMPAT) && compat)
+		return 0;
+
+	if (type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) {
+		const u32 *p = data;
+
+		if (datasz != sizeof(*p))
+			return -ENOEXEC;
+
+		if (system_supports_bti() &&
+		    (*p & GNU_PROPERTY_AARCH64_FEATURE_1_BTI))
+			arch->flags |= ARM64_ELF_BTI;
+	}
+
+	return 0;
+}
+
+static inline int arch_elf_pt_proc(void *ehdr, void *phdr,
+				   struct file *f, bool is_interp,
+				   struct arch_elf_state *state)
+{
+	return 0;
+}
+
+static inline int arch_check_elf(void *ehdr, bool has_interp,
+				 void *interp_ehdr,
+				 struct arch_elf_state *state)
+{
+	return 0;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
new file mode 100644
index 000000000..15b34fbfc
--- /dev/null
+++ b/arch/arm64/include/asm/esr.h
@@ -0,0 +1,358 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ASM_ESR_H
+#define __ASM_ESR_H
+
+#include <asm/memory.h>
+#include <asm/sysreg.h>
+
+#define ESR_ELx_EC_UNKNOWN	(0x00)
+#define ESR_ELx_EC_WFx		(0x01)
+/* Unallocated EC: 0x02 */
+#define ESR_ELx_EC_CP15_32	(0x03)
+#define ESR_ELx_EC_CP15_64	(0x04)
+#define ESR_ELx_EC_CP14_MR	(0x05)
+#define ESR_ELx_EC_CP14_LS	(0x06)
+#define ESR_ELx_EC_FP_ASIMD	(0x07)
+#define ESR_ELx_EC_CP10_ID	(0x08)	/* EL2 only */
+#define ESR_ELx_EC_PAC		(0x09)	/* EL2 and above */
+/* Unallocated EC: 0x0A - 0x0B */
+#define ESR_ELx_EC_CP14_64	(0x0C)
+#define ESR_ELx_EC_BTI		(0x0D)
+#define ESR_ELx_EC_ILL		(0x0E)
+/* Unallocated EC: 0x0F - 0x10 */
+#define ESR_ELx_EC_SVC32	(0x11)
+#define ESR_ELx_EC_HVC32	(0x12)	/* EL2 only */
+#define ESR_ELx_EC_SMC32	(0x13)	/* EL2 and above */
+/* Unallocated EC: 0x14 */
+#define ESR_ELx_EC_SVC64	(0x15)
+#define ESR_ELx_EC_HVC64	(0x16)	/* EL2 and above */
+#define ESR_ELx_EC_SMC64	(0x17)	/* EL2 and above */
+#define ESR_ELx_EC_SYS64	(0x18)
+#define ESR_ELx_EC_SVE		(0x19)
+#define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
+/* Unallocated EC: 0x1B */
+#define ESR_ELx_EC_FPAC		(0x1C)	/* EL1 and above */
+#define ESR_ELx_EC_SME		(0x1D)
+/* Unallocated EC: 0x1E */
+#define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
+#define ESR_ELx_EC_IABT_LOW	(0x20)
+#define ESR_ELx_EC_IABT_CUR	(0x21)
+#define ESR_ELx_EC_PC_ALIGN	(0x22)
+/* Unallocated EC: 0x23 */
+#define ESR_ELx_EC_DABT_LOW	(0x24)
+#define ESR_ELx_EC_DABT_CUR	(0x25)
+#define ESR_ELx_EC_SP_ALIGN	(0x26)
+/* Unallocated EC: 0x27 */
+#define ESR_ELx_EC_FP_EXC32	(0x28)
+/* Unallocated EC: 0x29 - 0x2B */
+#define ESR_ELx_EC_FP_EXC64	(0x2C)
+/* Unallocated EC: 0x2D - 0x2E */
+#define ESR_ELx_EC_SERROR	(0x2F)
+#define ESR_ELx_EC_BREAKPT_LOW	(0x30)
+#define ESR_ELx_EC_BREAKPT_CUR	(0x31)
+#define ESR_ELx_EC_SOFTSTP_LOW	(0x32)
+#define ESR_ELx_EC_SOFTSTP_CUR	(0x33)
+#define ESR_ELx_EC_WATCHPT_LOW	(0x34)
+#define ESR_ELx_EC_WATCHPT_CUR	(0x35)
+/* Unallocated EC: 0x36 - 0x37 */
+#define ESR_ELx_EC_BKPT32	(0x38)
+/* Unallocated EC: 0x39 */
+#define ESR_ELx_EC_VECTOR32	(0x3A)	/* EL2 only */
+/* Unallocated EC: 0x3B */
+#define ESR_ELx_EC_BRK64	(0x3C)
+/* Unallocated EC: 0x3D - 0x3F */
+#define ESR_ELx_EC_MAX		(0x3F)
+
+#define ESR_ELx_EC_SHIFT	(26)
+#define ESR_ELx_EC_WIDTH	(6)
+#define ESR_ELx_EC_MASK		(UL(0x3F) << ESR_ELx_EC_SHIFT)
+#define ESR_ELx_EC(esr)		(((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT)
+
+#define ESR_ELx_IL_SHIFT	(25)
+#define ESR_ELx_IL		(UL(1) << ESR_ELx_IL_SHIFT)
+#define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+#define ESR_ELx_ISS(esr)	((esr) & ESR_ELx_ISS_MASK)
+
+/* ISS field definitions shared by different classes */
+#define ESR_ELx_WNR_SHIFT	(6)
+#define ESR_ELx_WNR		(UL(1) << ESR_ELx_WNR_SHIFT)
+
+/* Asynchronous Error Type */
+#define ESR_ELx_IDS_SHIFT	(24)
+#define ESR_ELx_IDS		(UL(1) << ESR_ELx_IDS_SHIFT)
+#define ESR_ELx_AET_SHIFT	(10)
+#define ESR_ELx_AET		(UL(0x7) << ESR_ELx_AET_SHIFT)
+
+#define ESR_ELx_AET_UC		(UL(0) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UEU		(UL(1) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UEO		(UL(2) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_UER		(UL(3) << ESR_ELx_AET_SHIFT)
+#define ESR_ELx_AET_CE		(UL(6) << ESR_ELx_AET_SHIFT)
+
+/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_SET_SHIFT	(11)
+#define ESR_ELx_SET_MASK	(UL(3) << ESR_ELx_SET_SHIFT)
+#define ESR_ELx_FnV_SHIFT	(10)
+#define ESR_ELx_FnV		(UL(1) << ESR_ELx_FnV_SHIFT)
+#define ESR_ELx_EA_SHIFT	(9)
+#define ESR_ELx_EA		(UL(1) << ESR_ELx_EA_SHIFT)
+#define ESR_ELx_S1PTW_SHIFT	(7)
+#define ESR_ELx_S1PTW		(UL(1) << ESR_ELx_S1PTW_SHIFT)
+
+/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
+#define ESR_ELx_FSC		(0x3F)
+#define ESR_ELx_FSC_TYPE	(0x3C)
+#define ESR_ELx_FSC_LEVEL	(0x03)
+#define ESR_ELx_FSC_EXTABT	(0x10)
+#define ESR_ELx_FSC_MTE		(0x11)
+#define ESR_ELx_FSC_SERROR	(0x11)
+#define ESR_ELx_FSC_ACCESS	(0x08)
+#define ESR_ELx_FSC_FAULT	(0x04)
+#define ESR_ELx_FSC_PERM	(0x0C)
+
+/* ISS field definitions for Data Aborts */
+#define ESR_ELx_ISV_SHIFT	(24)
+#define ESR_ELx_ISV		(UL(1) << ESR_ELx_ISV_SHIFT)
+#define ESR_ELx_SAS_SHIFT	(22)
+#define ESR_ELx_SAS		(UL(3) << ESR_ELx_SAS_SHIFT)
+#define ESR_ELx_SSE_SHIFT	(21)
+#define ESR_ELx_SSE		(UL(1) << ESR_ELx_SSE_SHIFT)
+#define ESR_ELx_SRT_SHIFT	(16)
+#define ESR_ELx_SRT_MASK	(UL(0x1F) << ESR_ELx_SRT_SHIFT)
+#define ESR_ELx_SF_SHIFT	(15)
+#define ESR_ELx_SF 		(UL(1) << ESR_ELx_SF_SHIFT)
+#define ESR_ELx_AR_SHIFT	(14)
+#define ESR_ELx_AR 		(UL(1) << ESR_ELx_AR_SHIFT)
+#define ESR_ELx_CM_SHIFT	(8)
+#define ESR_ELx_CM 		(UL(1) << ESR_ELx_CM_SHIFT)
+
+/* ISS field definitions for exceptions taken in to Hyp */
+#define ESR_ELx_CV		(UL(1) << 24)
+#define ESR_ELx_COND_SHIFT	(20)
+#define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
+#define ESR_ELx_WFx_ISS_RN	(UL(0x1F) << 5)
+#define ESR_ELx_WFx_ISS_RV	(UL(1) << 2)
+#define ESR_ELx_WFx_ISS_TI	(UL(3) << 0)
+#define ESR_ELx_WFx_ISS_WFxT	(UL(2) << 0)
+#define ESR_ELx_WFx_ISS_WFI	(UL(0) << 0)
+#define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
+#define ESR_ELx_xVC_IMM_MASK	((UL(1) << 16) - 1)
+
+#define DISR_EL1_IDS		(UL(1) << 24)
+/*
+ * DISR_EL1 and ESR_ELx share the bottom 13 bits, but the RES0 bits may mean
+ * different things in the future...
+ */
+#define DISR_EL1_ESR_MASK	(ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC)
+
+/* ESR value templates for specific events */
+#define ESR_ELx_WFx_MASK	(ESR_ELx_EC_MASK |			\
+				 (ESR_ELx_WFx_ISS_TI & ~ESR_ELx_WFx_ISS_WFxT))
+#define ESR_ELx_WFx_WFI_VAL	((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) |	\
+				 ESR_ELx_WFx_ISS_WFI)
+
+/* BRK instruction trap from AArch64 state */
+#define ESR_ELx_BRK64_ISS_COMMENT_MASK	0xffff
+
+/* ISS field definitions for System instruction traps */
+#define ESR_ELx_SYS64_ISS_RES0_SHIFT	22
+#define ESR_ELx_SYS64_ISS_RES0_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT)
+#define ESR_ELx_SYS64_ISS_DIR_MASK	0x1
+#define ESR_ELx_SYS64_ISS_DIR_READ	0x1
+#define ESR_ELx_SYS64_ISS_DIR_WRITE	0x0
+
+#define ESR_ELx_SYS64_ISS_RT_SHIFT	5
+#define ESR_ELx_SYS64_ISS_RT_MASK	(UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRM_SHIFT	1
+#define ESR_ELx_SYS64_ISS_CRM_MASK	(UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRN_SHIFT	10
+#define ESR_ELx_SYS64_ISS_CRN_MASK	(UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP1_SHIFT	14
+#define ESR_ELx_SYS64_ISS_OP1_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP2_SHIFT	17
+#define ESR_ELx_SYS64_ISS_OP2_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP0_SHIFT	20
+#define ESR_ELx_SYS64_ISS_OP0_MASK	(UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT)
+#define ESR_ELx_SYS64_ISS_SYS_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+					 ESR_ELx_SYS64_ISS_OP1_MASK | \
+					 ESR_ELx_SYS64_ISS_OP2_MASK | \
+					 ESR_ELx_SYS64_ISS_CRN_MASK | \
+					 ESR_ELx_SYS64_ISS_CRM_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \
+					(((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \
+					 ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \
+					 ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \
+					 ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \
+					 ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_SYS64_ISS_SYS_OP_MASK	(ESR_ELx_SYS64_ISS_SYS_MASK | \
+					 ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_RT(esr) \
+	(((esr) & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT)
+/*
+ * User space cache operations have the following sysreg encoding
+ * in System instructions.
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 13, 14 }, WRITE (L=0)
+ */
+#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC	14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVADP	13
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAP	12
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU	11
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC	10
+#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU	5
+
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+						 ESR_ELx_SYS64_ISS_OP1_MASK | \
+						 ESR_ELx_SYS64_ISS_OP2_MASK | \
+						 ESR_ELx_SYS64_ISS_CRN_MASK | \
+						 ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
+				(ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
+				 ESR_ELx_SYS64_ISS_DIR_WRITE)
+/*
+ * User space MRS operations which are supported for emulation
+ * have the following sysreg encoding in System instructions.
+ * op0 = 3, op1= 0, crn = 0, {crm = 0, 4-7}, READ (L = 1)
+ */
+#define ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+						 ESR_ELx_SYS64_ISS_OP1_MASK | \
+						 ESR_ELx_SYS64_ISS_CRN_MASK | \
+						 ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL \
+				(ESR_ELx_SYS64_ISS_SYS_VAL(3, 0, 0, 0, 0) | \
+				 ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define ESR_ELx_SYS64_ISS_SYS_CTR	ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
+#define ESR_ELx_SYS64_ISS_SYS_CTR_READ	(ESR_ELx_SYS64_ISS_SYS_CTR | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define ESR_ELx_SYS64_ISS_SYS_CNTVCT	(ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 2, 14, 0) | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define ESR_ELx_SYS64_ISS_SYS_CNTVCTSS	(ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 6, 14, 0) | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define ESR_ELx_SYS64_ISS_SYS_CNTFRQ	(ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 0, 14, 0) | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define esr_sys64_to_sysreg(e)					\
+	sys_reg((((e) & ESR_ELx_SYS64_ISS_OP0_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_OP0_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_OP1_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_OP1_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_CRN_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_CRN_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_CRM_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_CRM_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_OP2_SHIFT))
+
+#define esr_cp15_to_sysreg(e)					\
+	sys_reg(3,						\
+		(((e) & ESR_ELx_SYS64_ISS_OP1_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_OP1_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_CRN_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_CRN_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_CRM_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_CRM_SHIFT),			\
+		(((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >>		\
+		 ESR_ELx_SYS64_ISS_OP2_SHIFT))
+
+/*
+ * ISS field definitions for floating-point exception traps
+ * (FP_EXC_32/FP_EXC_64).
+ *
+ * (The FPEXC_* constants are used instead for common bits.)
+ */
+
+#define ESR_ELx_FP_EXC_TFV	(UL(1) << 23)
+
+/*
+ * ISS field definitions for CP15 accesses
+ */
+#define ESR_ELx_CP15_32_ISS_DIR_MASK	0x1
+#define ESR_ELx_CP15_32_ISS_DIR_READ	0x1
+#define ESR_ELx_CP15_32_ISS_DIR_WRITE	0x0
+
+#define ESR_ELx_CP15_32_ISS_RT_SHIFT	5
+#define ESR_ELx_CP15_32_ISS_RT_MASK	(UL(0x1f) << ESR_ELx_CP15_32_ISS_RT_SHIFT)
+#define ESR_ELx_CP15_32_ISS_CRM_SHIFT	1
+#define ESR_ELx_CP15_32_ISS_CRM_MASK	(UL(0xf) << ESR_ELx_CP15_32_ISS_CRM_SHIFT)
+#define ESR_ELx_CP15_32_ISS_CRN_SHIFT	10
+#define ESR_ELx_CP15_32_ISS_CRN_MASK	(UL(0xf) << ESR_ELx_CP15_32_ISS_CRN_SHIFT)
+#define ESR_ELx_CP15_32_ISS_OP1_SHIFT	14
+#define ESR_ELx_CP15_32_ISS_OP1_MASK	(UL(0x7) << ESR_ELx_CP15_32_ISS_OP1_SHIFT)
+#define ESR_ELx_CP15_32_ISS_OP2_SHIFT	17
+#define ESR_ELx_CP15_32_ISS_OP2_MASK	(UL(0x7) << ESR_ELx_CP15_32_ISS_OP2_SHIFT)
+
+#define ESR_ELx_CP15_32_ISS_SYS_MASK	(ESR_ELx_CP15_32_ISS_OP1_MASK | \
+					 ESR_ELx_CP15_32_ISS_OP2_MASK | \
+					 ESR_ELx_CP15_32_ISS_CRN_MASK | \
+					 ESR_ELx_CP15_32_ISS_CRM_MASK | \
+					 ESR_ELx_CP15_32_ISS_DIR_MASK)
+#define ESR_ELx_CP15_32_ISS_SYS_VAL(op1, op2, crn, crm) \
+					(((op1) << ESR_ELx_CP15_32_ISS_OP1_SHIFT) | \
+					 ((op2) << ESR_ELx_CP15_32_ISS_OP2_SHIFT) | \
+					 ((crn) << ESR_ELx_CP15_32_ISS_CRN_SHIFT) | \
+					 ((crm) << ESR_ELx_CP15_32_ISS_CRM_SHIFT))
+
+#define ESR_ELx_CP15_64_ISS_DIR_MASK	0x1
+#define ESR_ELx_CP15_64_ISS_DIR_READ	0x1
+#define ESR_ELx_CP15_64_ISS_DIR_WRITE	0x0
+
+#define ESR_ELx_CP15_64_ISS_RT_SHIFT	5
+#define ESR_ELx_CP15_64_ISS_RT_MASK	(UL(0x1f) << ESR_ELx_CP15_64_ISS_RT_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_RT2_SHIFT	10
+#define ESR_ELx_CP15_64_ISS_RT2_MASK	(UL(0x1f) << ESR_ELx_CP15_64_ISS_RT2_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_OP1_SHIFT	16
+#define ESR_ELx_CP15_64_ISS_OP1_MASK	(UL(0xf) << ESR_ELx_CP15_64_ISS_OP1_SHIFT)
+#define ESR_ELx_CP15_64_ISS_CRM_SHIFT	1
+#define ESR_ELx_CP15_64_ISS_CRM_MASK	(UL(0xf) << ESR_ELx_CP15_64_ISS_CRM_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_SYS_VAL(op1, crm) \
+					(((op1) << ESR_ELx_CP15_64_ISS_OP1_SHIFT) | \
+					 ((crm) << ESR_ELx_CP15_64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_CP15_64_ISS_SYS_MASK	(ESR_ELx_CP15_64_ISS_OP1_MASK |	\
+					 ESR_ELx_CP15_64_ISS_CRM_MASK | \
+					 ESR_ELx_CP15_64_ISS_DIR_MASK)
+
+#define ESR_ELx_CP15_64_ISS_SYS_CNTVCT	(ESR_ELx_CP15_64_ISS_SYS_VAL(1, 14) | \
+					 ESR_ELx_CP15_64_ISS_DIR_READ)
+
+#define ESR_ELx_CP15_64_ISS_SYS_CNTVCTSS (ESR_ELx_CP15_64_ISS_SYS_VAL(9, 14) | \
+					 ESR_ELx_CP15_64_ISS_DIR_READ)
+
+#define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ	(ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
+					 ESR_ELx_CP15_32_ISS_DIR_READ)
+
+/*
+ * ISS values for SME traps
+ */
+
+#define ESR_ELx_SME_ISS_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_ILL		1
+#define ESR_ELx_SME_ISS_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_ZA_DISABLED	3
+
+#ifndef __ASSEMBLY__
+#include <asm/types.h>
+
+static inline bool esr_is_data_abort(unsigned long esr)
+{
+	const unsigned long ec = ESR_ELx_EC(esr);
+
+	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
+}
+
+const char *esr_get_class_string(unsigned long esr);
+#endif /* __ASSEMBLY */
+
+#endif /* __ASM_ESR_H */
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
new file mode 100644
index 000000000..19713d0f0
--- /dev/null
+++ b/arch/arm64/include/asm/exception.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/exception.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_EXCEPTION_H
+#define __ASM_EXCEPTION_H
+
+#include <asm/esr.h>
+#include <asm/kprobes.h>
+#include <asm/ptrace.h>
+
+#include <linux/interrupt.h>
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __exception_irq_entry	__irq_entry
+#else
+#define __exception_irq_entry	__kprobes
+#endif
+
+static inline unsigned long disr_to_esr(u64 disr)
+{
+	unsigned long esr = ESR_ELx_EC_SERROR << ESR_ELx_EC_SHIFT;
+
+	if ((disr & DISR_EL1_IDS) == 0)
+		esr |= (disr & DISR_EL1_ESR_MASK);
+	else
+		esr |= (disr & ESR_ELx_ISS_MASK);
+
+	return esr;
+}
+
+asmlinkage void handle_bad_stack(struct pt_regs *regs);
+
+asmlinkage void el1t_64_sync_handler(struct pt_regs *regs);
+asmlinkage void el1t_64_irq_handler(struct pt_regs *regs);
+asmlinkage void el1t_64_fiq_handler(struct pt_regs *regs);
+asmlinkage void el1t_64_error_handler(struct pt_regs *regs);
+
+asmlinkage void el1h_64_sync_handler(struct pt_regs *regs);
+asmlinkage void el1h_64_irq_handler(struct pt_regs *regs);
+asmlinkage void el1h_64_fiq_handler(struct pt_regs *regs);
+asmlinkage void el1h_64_error_handler(struct pt_regs *regs);
+
+asmlinkage void el0t_64_sync_handler(struct pt_regs *regs);
+asmlinkage void el0t_64_irq_handler(struct pt_regs *regs);
+asmlinkage void el0t_64_fiq_handler(struct pt_regs *regs);
+asmlinkage void el0t_64_error_handler(struct pt_regs *regs);
+
+asmlinkage void el0t_32_sync_handler(struct pt_regs *regs);
+asmlinkage void el0t_32_irq_handler(struct pt_regs *regs);
+asmlinkage void el0t_32_fiq_handler(struct pt_regs *regs);
+asmlinkage void el0t_32_error_handler(struct pt_regs *regs);
+
+asmlinkage void call_on_irq_stack(struct pt_regs *regs,
+				  void (*func)(struct pt_regs *));
+asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs);
+
+void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs);
+void do_undefinstr(struct pt_regs *regs, unsigned long esr);
+void do_el0_bti(struct pt_regs *regs);
+void do_el1_bti(struct pt_regs *regs, unsigned long esr);
+void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
+			struct pt_regs *regs);
+void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
+void do_sve_acc(unsigned long esr, struct pt_regs *regs);
+void do_sme_acc(unsigned long esr, struct pt_regs *regs);
+void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs);
+void do_sysinstr(unsigned long esr, struct pt_regs *regs);
+void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs);
+void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr);
+void do_cp15instr(unsigned long esr, struct pt_regs *regs);
+int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs);
+void do_el0_svc(struct pt_regs *regs);
+void do_el0_svc_compat(struct pt_regs *regs);
+void do_el0_fpac(struct pt_regs *regs, unsigned long esr);
+void do_el1_fpac(struct pt_regs *regs, unsigned long esr);
+void do_serror(struct pt_regs *regs, unsigned long esr);
+void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags);
+
+void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far);
+#endif	/* __ASM_EXCEPTION_H */
diff --git a/arch/arm64/include/asm/exec.h b/arch/arm64/include/asm/exec.h
new file mode 100644
index 000000000..9a1c22ce6
--- /dev/null
+++ b/arch/arm64/include/asm/exec.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/exec.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_EXEC_H
+#define __ASM_EXEC_H
+
+#include <linux/sched.h>
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif	/* __ASM_EXEC_H */
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
new file mode 100644
index 000000000..72b0e71cc
--- /dev/null
+++ b/arch/arm64/include/asm/extable.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative offsets: the first
+ * is the relative offset to an instruction that is allowed to fault,
+ * and the second is the relative offset at which the program should
+ * continue. No registers are modified, so it is entirely up to the
+ * continuation code to figure out what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+	int insn, fixup;
+	short type, data;
+};
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#define swap_ex_entry_fixup(a, b, tmp, delta)		\
+do {							\
+	(a)->fixup = (b)->fixup + (delta);		\
+	(b)->fixup = (tmp).fixup - (delta);		\
+	(a)->type = (b)->type;				\
+	(b)->type = (tmp).type;				\
+	(a)->data = (b)->data;				\
+	(b)->data = (tmp).data;				\
+} while (0)
+
+#ifdef CONFIG_BPF_JIT
+bool ex_handler_bpf(const struct exception_table_entry *ex,
+		    struct pt_regs *regs);
+#else /* !CONFIG_BPF_JIT */
+static inline
+bool ex_handler_bpf(const struct exception_table_entry *ex,
+		    struct pt_regs *regs)
+{
+	return false;
+}
+#endif /* !CONFIG_BPF_JIT */
+
+bool fixup_exception(struct pt_regs *regs);
+#endif
diff --git a/arch/arm64/include/asm/fb.h b/arch/arm64/include/asm/fb.h
new file mode 100644
index 000000000..bdc735ee1
--- /dev/null
+++ b/arch/arm64/include/asm/fb.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_FB_H_
+#define __ASM_FB_H_
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+}
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+	return 0;
+}
+
+#endif /* __ASM_FB_H_ */
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
new file mode 100644
index 000000000..71ed5fdf7
--- /dev/null
+++ b/arch/arm64/include/asm/fixmap.h
@@ -0,0 +1,115 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ * Copyright (C) 2013 Mark Salter <msalter@redhat.com>
+ *
+ * Adapted from arch/x86 version.
+ *
+ */
+
+#ifndef _ASM_ARM64_FIXMAP_H
+#define _ASM_ARM64_FIXMAP_H
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <asm/boot.h>
+#include <asm/page.h>
+#include <asm/pgtable-prot.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * Each enum increment in these 'compile-time allocated'
+ * memory buffers is page-sized. Use set_fixmap(idx,phys)
+ * to associate physical memory with a fixmap index.
+ */
+enum fixed_addresses {
+	FIX_HOLE,
+
+	/*
+	 * Reserve a virtual window for the FDT that is 2 MB larger than the
+	 * maximum supported size, and put it at the top of the fixmap region.
+	 * The additional space ensures that any FDT that does not exceed
+	 * MAX_FDT_SIZE can be mapped regardless of whether it crosses any
+	 * 2 MB alignment boundaries.
+	 *
+	 * Keep this at the top so it remains 2 MB aligned.
+	 */
+#define FIX_FDT_SIZE		(MAX_FDT_SIZE + SZ_2M)
+	FIX_FDT_END,
+	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+
+	FIX_EARLYCON_MEM_BASE,
+	FIX_TEXT_POKE0,
+
+#ifdef CONFIG_ACPI_APEI_GHES
+	/* Used for GHES mapping from assorted contexts */
+	FIX_APEI_GHES_IRQ,
+	FIX_APEI_GHES_SEA,
+#ifdef CONFIG_ARM_SDE_INTERFACE
+	FIX_APEI_GHES_SDEI_NORMAL,
+	FIX_APEI_GHES_SDEI_CRITICAL,
+#endif
+#endif /* CONFIG_ACPI_APEI_GHES */
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#ifdef CONFIG_RELOCATABLE
+	FIX_ENTRY_TRAMP_TEXT4,	/* one extra slot for the data page */
+#endif
+	FIX_ENTRY_TRAMP_TEXT3,
+	FIX_ENTRY_TRAMP_TEXT2,
+	FIX_ENTRY_TRAMP_TEXT1,
+#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1))
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+	__end_of_permanent_fixed_addresses,
+
+	/*
+	 * Temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 */
+#define NR_FIX_BTMAPS		(SZ_256K / PAGE_SIZE)
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+
+	/*
+	 * Used for kernel page table creation, so unmapped memory may be used
+	 * for tables.
+	 */
+	FIX_PTE,
+	FIX_PMD,
+	FIX_PUD,
+	FIX_PGD,
+
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+#define FIXMAP_PAGE_IO     __pgprot(PROT_DEVICE_nGnRE)
+
+void __init early_fixmap_init(void);
+
+#define __early_set_fixmap __set_fixmap
+
+#define __late_set_fixmap __set_fixmap
+#define __late_clear_fixmap(idx) __set_fixmap((idx), 0, FIXMAP_PAGE_CLEAR)
+
+extern void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
+
+#include <asm-generic/fixmap.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_ARM64_FIXMAP_H */
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
new file mode 100644
index 000000000..d720b6f7e
--- /dev/null
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -0,0 +1,389 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_FP_H
+#define __ASM_FP_H
+
+#include <asm/errno.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitmap.h>
+#include <linux/build_bug.h>
+#include <linux/bug.h>
+#include <linux/cache.h>
+#include <linux/init.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_COMPAT
+/* Masks for extracting the FPSR and FPCR from the FPSCR */
+#define VFP_FPSCR_STAT_MASK	0xf800009f
+#define VFP_FPSCR_CTRL_MASK	0x07f79f00
+/*
+ * The VFP state has 32x64-bit registers and a single 32-bit
+ * control/status register.
+ */
+#define VFP_STATE_SIZE		((32 * 8) + 4)
+#endif
+
+/*
+ * When we defined the maximum SVE vector length we defined the ABI so
+ * that the maximum vector length included all the reserved for future
+ * expansion bits in ZCR rather than those just currently defined by
+ * the architecture. While SME follows a similar pattern the fact that
+ * it includes a square matrix means that any allocations that attempt
+ * to cover the maximum potential vector length (such as happen with
+ * the regset used for ptrace) end up being extremely large. Define
+ * the much lower actual limit for use in such situations.
+ */
+#define SME_VQ_MAX	16
+
+struct task_struct;
+
+extern void fpsimd_save_state(struct user_fpsimd_state *state);
+extern void fpsimd_load_state(struct user_fpsimd_state *state);
+
+extern void fpsimd_thread_switch(struct task_struct *next);
+extern void fpsimd_flush_thread(void);
+
+extern void fpsimd_signal_preserve_current_state(void);
+extern void fpsimd_preserve_current_state(void);
+extern void fpsimd_restore_current_state(void);
+extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
+
+extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
+				     void *sve_state, unsigned int sve_vl,
+				     void *za_state, unsigned int sme_vl,
+				     u64 *svcr);
+
+extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void fpsimd_save_and_flush_cpu_state(void);
+
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SVCR_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
+}
+
+/* Maximum VL that SVE/SME VL-agnostic software can transparently support */
+#define VL_ARCH_MAX 0x100
+
+/* Offset of FFR in the SVE register dump */
+static inline size_t sve_ffr_offset(int vl)
+{
+	return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET;
+}
+
+static inline void *sve_pffr(struct thread_struct *thread)
+{
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
+}
+
+extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
+extern void sve_load_state(void const *state, u32 const *pfpsr,
+			   int restore_ffr);
+extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
+extern unsigned int sve_get_vl(void);
+extern void sve_set_vq(unsigned long vq_minus_1);
+extern void sme_set_vq(unsigned long vq_minus_1);
+extern void za_save_state(void *state);
+extern void za_load_state(void const *state);
+
+struct arm64_cpu_capabilities;
+extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+
+extern u64 read_zcr_features(void);
+extern u64 read_smcr_features(void);
+
+/*
+ * Helpers to translate bit indices in sve_vq_map to VQ values (and
+ * vice versa).  This allows find_next_bit() to be used to find the
+ * _maximum_ VQ not exceeding a certain value.
+ */
+static inline unsigned int __vq_to_bit(unsigned int vq)
+{
+	return SVE_VQ_MAX - vq;
+}
+
+static inline unsigned int __bit_to_vq(unsigned int bit)
+{
+	return SVE_VQ_MAX - bit;
+}
+
+
+struct vl_info {
+	enum vec_type type;
+	const char *name;		/* For display purposes */
+
+	/* Minimum supported vector length across all CPUs */
+	int min_vl;
+
+	/* Maximum supported vector length across all CPUs */
+	int max_vl;
+	int max_virtualisable_vl;
+
+	/*
+	 * Set of available vector lengths,
+	 * where length vq encoded as bit __vq_to_bit(vq):
+	 */
+	DECLARE_BITMAP(vq_map, SVE_VQ_MAX);
+
+	/* Set of vector lengths present on at least one cpu: */
+	DECLARE_BITMAP(vq_partial_map, SVE_VQ_MAX);
+};
+
+#ifdef CONFIG_ARM64_SVE
+
+extern void sve_alloc(struct task_struct *task, bool flush);
+extern void fpsimd_release_task(struct task_struct *task);
+extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void fpsimd_force_sync_to_sve(struct task_struct *task);
+extern void sve_sync_to_fpsimd(struct task_struct *task);
+extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
+
+extern int vec_set_vector_length(struct task_struct *task, enum vec_type type,
+				 unsigned long vl, unsigned long flags);
+
+extern int sve_set_current_vl(unsigned long arg);
+extern int sve_get_current_vl(void);
+
+static inline void sve_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0);
+}
+
+static inline void sve_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN);
+}
+
+#define sve_cond_update_zcr_vq(val, reg)		\
+	do {						\
+		u64 __zcr = read_sysreg_s((reg));	\
+		u64 __new = __zcr & ~ZCR_ELx_LEN_MASK;	\
+		__new |= (val) & ZCR_ELx_LEN_MASK;	\
+		if (__zcr != __new)			\
+			write_sysreg_s(__new, (reg));	\
+	} while (0)
+
+/*
+ * Probing and setup functions.
+ * Calls to these functions must be serialised with one another.
+ */
+enum vec_type;
+
+extern void __init vec_init_vq_map(enum vec_type type);
+extern void vec_update_vq_map(enum vec_type type);
+extern int vec_verify_vq_map(enum vec_type type);
+extern void __init sve_setup(void);
+
+extern __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX];
+
+static inline void write_vl(enum vec_type type, u64 val)
+{
+	u64 tmp;
+
+	switch (type) {
+#ifdef CONFIG_ARM64_SVE
+	case ARM64_VEC_SVE:
+		tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK;
+		write_sysreg_s(tmp | val, SYS_ZCR_EL1);
+		break;
+#endif
+#ifdef CONFIG_ARM64_SME
+	case ARM64_VEC_SME:
+		tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK;
+		write_sysreg_s(tmp | val, SYS_SMCR_EL1);
+		break;
+#endif
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
+static inline int vec_max_vl(enum vec_type type)
+{
+	return vl_info[type].max_vl;
+}
+
+static inline int vec_max_virtualisable_vl(enum vec_type type)
+{
+	return vl_info[type].max_virtualisable_vl;
+}
+
+static inline int sve_max_vl(void)
+{
+	return vec_max_vl(ARM64_VEC_SVE);
+}
+
+static inline int sve_max_virtualisable_vl(void)
+{
+	return vec_max_virtualisable_vl(ARM64_VEC_SVE);
+}
+
+/* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */
+static inline bool vq_available(enum vec_type type, unsigned int vq)
+{
+	return test_bit(__vq_to_bit(vq), vl_info[type].vq_map);
+}
+
+static inline bool sve_vq_available(unsigned int vq)
+{
+	return vq_available(ARM64_VEC_SVE, vq);
+}
+
+size_t sve_state_size(struct task_struct const *task);
+
+#else /* ! CONFIG_ARM64_SVE */
+
+static inline void sve_alloc(struct task_struct *task, bool flush) { }
+static inline void fpsimd_release_task(struct task_struct *task) { }
+static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
+static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
+
+static inline int sve_max_virtualisable_vl(void)
+{
+	return 0;
+}
+
+static inline int sve_set_current_vl(unsigned long arg)
+{
+	return -EINVAL;
+}
+
+static inline int sve_get_current_vl(void)
+{
+	return -EINVAL;
+}
+
+static inline int sve_max_vl(void)
+{
+	return -EINVAL;
+}
+
+static inline bool sve_vq_available(unsigned int vq) { return false; }
+
+static inline void sve_user_disable(void) { BUILD_BUG(); }
+static inline void sve_user_enable(void) { BUILD_BUG(); }
+
+#define sve_cond_update_zcr_vq(val, reg) do { } while (0)
+
+static inline void vec_init_vq_map(enum vec_type t) { }
+static inline void vec_update_vq_map(enum vec_type t) { }
+static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
+static inline void sve_setup(void) { }
+
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SVE */
+
+#ifdef CONFIG_ARM64_SME
+
+static inline void sme_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0);
+}
+
+static inline void sme_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN);
+}
+
+static inline void sme_smstart_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
+}
+
+extern void __init sme_setup(void);
+
+static inline int sme_max_vl(void)
+{
+	return vec_max_vl(ARM64_VEC_SME);
+}
+
+static inline int sme_max_virtualisable_vl(void)
+{
+	return vec_max_virtualisable_vl(ARM64_VEC_SME);
+}
+
+extern void sme_alloc(struct task_struct *task, bool flush);
+extern unsigned int sme_get_vl(void);
+extern int sme_set_current_vl(unsigned long arg);
+extern int sme_get_current_vl(void);
+
+/*
+ * Return how many bytes of memory are required to store the full SME
+ * specific state (currently just ZA) for task, given task's currently
+ * configured vector length.
+ */
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	unsigned int vl = task_get_sme_vl(task);
+
+	return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+#else
+
+static inline void sme_user_disable(void) { BUILD_BUG(); }
+static inline void sme_user_enable(void) { BUILD_BUG(); }
+
+static inline void sme_smstart_sm(void) { }
+static inline void sme_smstop_sm(void) { }
+static inline void sme_smstop(void) { }
+
+static inline void sme_alloc(struct task_struct *task, bool flush) { }
+static inline void sme_setup(void) { }
+static inline unsigned int sme_get_vl(void) { return 0; }
+static inline int sme_max_vl(void) { return 0; }
+static inline int sme_max_virtualisable_vl(void) { return 0; }
+static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
+static inline int sme_get_current_vl(void) { return -EINVAL; }
+
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
+#endif /* ! CONFIG_ARM64_SME */
+
+/* For use by EFI runtime services calls only */
+extern void __efi_fpsimd_begin(void);
+extern void __efi_fpsimd_end(void);
+
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
new file mode 100644
index 000000000..696d247cf
--- /dev/null
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -0,0 +1,343 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * FP/SIMD state saving and restoring macros
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ */
+
+#include <asm/assembler.h>
+
+.macro fpsimd_save state, tmpnr
+	stp	q0, q1, [\state, #16 * 0]
+	stp	q2, q3, [\state, #16 * 2]
+	stp	q4, q5, [\state, #16 * 4]
+	stp	q6, q7, [\state, #16 * 6]
+	stp	q8, q9, [\state, #16 * 8]
+	stp	q10, q11, [\state, #16 * 10]
+	stp	q12, q13, [\state, #16 * 12]
+	stp	q14, q15, [\state, #16 * 14]
+	stp	q16, q17, [\state, #16 * 16]
+	stp	q18, q19, [\state, #16 * 18]
+	stp	q20, q21, [\state, #16 * 20]
+	stp	q22, q23, [\state, #16 * 22]
+	stp	q24, q25, [\state, #16 * 24]
+	stp	q26, q27, [\state, #16 * 26]
+	stp	q28, q29, [\state, #16 * 28]
+	stp	q30, q31, [\state, #16 * 30]!
+	mrs	x\tmpnr, fpsr
+	str	w\tmpnr, [\state, #16 * 2]
+	mrs	x\tmpnr, fpcr
+	str	w\tmpnr, [\state, #16 * 2 + 4]
+.endm
+
+.macro fpsimd_restore_fpcr state, tmp
+	/*
+	 * Writes to fpcr may be self-synchronising, so avoid restoring
+	 * the register if it hasn't changed.
+	 */
+	mrs	\tmp, fpcr
+	cmp	\tmp, \state
+	b.eq	9999f
+	msr	fpcr, \state
+9999:
+.endm
+
+/* Clobbers \state */
+.macro fpsimd_restore state, tmpnr
+	ldp	q0, q1, [\state, #16 * 0]
+	ldp	q2, q3, [\state, #16 * 2]
+	ldp	q4, q5, [\state, #16 * 4]
+	ldp	q6, q7, [\state, #16 * 6]
+	ldp	q8, q9, [\state, #16 * 8]
+	ldp	q10, q11, [\state, #16 * 10]
+	ldp	q12, q13, [\state, #16 * 12]
+	ldp	q14, q15, [\state, #16 * 14]
+	ldp	q16, q17, [\state, #16 * 16]
+	ldp	q18, q19, [\state, #16 * 18]
+	ldp	q20, q21, [\state, #16 * 20]
+	ldp	q22, q23, [\state, #16 * 22]
+	ldp	q24, q25, [\state, #16 * 24]
+	ldp	q26, q27, [\state, #16 * 26]
+	ldp	q28, q29, [\state, #16 * 28]
+	ldp	q30, q31, [\state, #16 * 30]!
+	ldr	w\tmpnr, [\state, #16 * 2]
+	msr	fpsr, x\tmpnr
+	ldr	w\tmpnr, [\state, #16 * 2 + 4]
+	fpsimd_restore_fpcr x\tmpnr, \state
+.endm
+
+/* Sanity-check macros to help avoid encoding garbage instructions */
+
+.macro _check_general_reg nr
+	.if (\nr) < 0 || (\nr) > 30
+		.error "Bad register number \nr."
+	.endif
+.endm
+
+.macro _sve_check_zreg znr
+	.if (\znr) < 0 || (\znr) > 31
+		.error "Bad Scalable Vector Extension vector register number \znr."
+	.endif
+.endm
+
+.macro _sve_check_preg pnr
+	.if (\pnr) < 0 || (\pnr) > 15
+		.error "Bad Scalable Vector Extension predicate register number \pnr."
+	.endif
+.endm
+
+.macro _check_num n, min, max
+	.if (\n) < (\min) || (\n) > (\max)
+		.error "Number \n out of range [\min,\max]"
+	.endif
+.endm
+
+.macro _sme_check_wv v
+	.if (\v) < 12 || (\v) > 15
+		.error "Bad vector select register \v."
+	.endif
+.endm
+
+/* SVE instruction encodings for non-SVE-capable assemblers */
+/* (pre binutils 2.28, all kernel capable clang versions support SVE) */
+
+/* STR (vector): STR Z\nz, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_str_v nz, nxbase, offset=0
+	_sve_check_zreg \nz
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe5804000			\
+		| (\nz)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* LDR (vector): LDR Z\nz, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_ldr_v nz, nxbase, offset=0
+	_sve_check_zreg \nz
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0x85804000			\
+		| (\nz)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* STR (predicate): STR P\np, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_str_p np, nxbase, offset=0
+	_sve_check_preg \np
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe5800000			\
+		| (\np)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* LDR (predicate): LDR P\np, [X\nxbase, #\offset, MUL VL] */
+.macro _sve_ldr_p np, nxbase, offset=0
+	_sve_check_preg \np
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0x85800000			\
+		| (\np)				\
+		| ((\nxbase) << 5)		\
+		| (((\offset) & 7) << 10)	\
+		| (((\offset) & 0x1f8) << 13)
+.endm
+
+/* RDVL X\nx, #\imm */
+.macro _sve_rdvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5000			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/* RDFFR (unpredicated): RDFFR P\np.B */
+.macro _sve_rdffr np
+	_sve_check_preg \np
+	.inst	0x2519f000			\
+		| (\np)
+.endm
+
+/* WRFFR P\np.B */
+.macro _sve_wrffr np
+	_sve_check_preg \np
+	.inst	0x25289000			\
+		| ((\np) << 5)
+.endm
+
+/* PFALSE P\np.B */
+.macro _sve_pfalse np
+	_sve_check_preg \np
+	.inst	0x2518e400			\
+		| (\np)
+.endm
+
+/* SME instruction encodings for non-SME-capable assemblers */
+/* (pre binutils 2.38/LLVM 13) */
+
+/* RDSVL X\nx, #\imm */
+.macro _sme_rdsvl nx, imm
+	_check_general_reg \nx
+	_check_num (\imm), -0x20, 0x1f
+	.inst	0x04bf5800			\
+		| (\nx)				\
+		| (((\imm) & 0x3f) << 5)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ *	STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_str_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1200000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _sme_ldr_zav nw, nxbase, offset=0
+	_sme_check_wv \nw
+	_check_general_reg \nxbase
+	_check_num (\offset), -0x100, 0xff
+	.inst	0xe1000000			\
+		| (((\nw) & 3) << 13)		\
+		| ((\nxbase) << 5)		\
+		| ((\offset) & 7)
+.endm
+
+/*
+ * Zero the entire ZA array
+ *	ZERO ZA
+ */
+.macro zero_za
+	.inst 0xc00800ff
+.endm
+
+.macro __for from:req, to:req
+	.if (\from) == (\to)
+		_for__body %\from
+	.else
+		__for %\from, %((\from) + ((\to) - (\from)) / 2)
+		__for %((\from) + ((\to) - (\from)) / 2 + 1), %\to
+	.endif
+.endm
+
+.macro _for var:req, from:req, to:req, insn:vararg
+	.macro _for__body \var:req
+		.noaltmacro
+		\insn
+		.altmacro
+	.endm
+
+	.altmacro
+	__for \from, \to
+	.noaltmacro
+
+	.purgem _for__body
+.endm
+
+/* Update ZCR_EL1.LEN with the new VQ */
+.macro sve_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_ZCR_EL1
+		bic		\xtmp2, \xtmp, ZCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_ZCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
+/* Preserve the first 128-bits of Znz and zero the rest. */
+.macro _sve_flush_z nz
+	_sve_check_zreg \nz
+	mov	v\nz\().16b, v\nz\().16b
+.endm
+
+.macro sve_flush_z
+ _for n, 0, 31, _sve_flush_z	\n
+.endm
+.macro sve_flush_p
+ _for n, 0, 15, _sve_pfalse	\n
+.endm
+.macro sve_flush_ffr
+		_sve_wrffr	0
+.endm
+
+.macro sve_save nxbase, xpfpsr, save_ffr, nxtmp
+ _for n, 0, 31,	_sve_str_v	\n, \nxbase, \n - 34
+ _for n, 0, 15,	_sve_str_p	\n, \nxbase, \n - 16
+		cbz		\save_ffr, 921f
+		_sve_rdffr	0
+		b		922f
+921:
+		_sve_pfalse	0			// Zero out FFR
+922:
+		_sve_str_p	0, \nxbase
+		_sve_ldr_p	0, \nxbase, -16
+		mrs		x\nxtmp, fpsr
+		str		w\nxtmp, [\xpfpsr]
+		mrs		x\nxtmp, fpcr
+		str		w\nxtmp, [\xpfpsr, #4]
+.endm
+
+.macro sve_load nxbase, xpfpsr, restore_ffr, nxtmp
+ _for n, 0, 31,	_sve_ldr_v	\n, \nxbase, \n - 34
+		cbz		\restore_ffr, 921f
+		_sve_ldr_p	0, \nxbase
+		_sve_wrffr	0
+921:
+ _for n, 0, 15,	_sve_ldr_p	\n, \nxbase, \n - 16
+
+		ldr		w\nxtmp, [\xpfpsr]
+		msr		fpsr, x\nxtmp
+		ldr		w\nxtmp, [\xpfpsr, #4]
+		msr		fpcr, x\nxtmp
+.endm
+
+.macro sme_save_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_str_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
+
+.macro sme_load_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_ldr_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
new file mode 100644
index 000000000..329dbbd4d
--- /dev/null
+++ b/arch/arm64/include/asm/ftrace.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/ftrace.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ */
+#ifndef __ASM_FTRACE_H
+#define __ASM_FTRACE_H
+
+#include <asm/insn.h>
+
+#define HAVE_FUNCTION_GRAPH_FP_TEST
+
+/*
+ * HAVE_FUNCTION_GRAPH_RET_ADDR_PTR means that the architecture can provide a
+ * "return address pointer" which can be used to uniquely identify a return
+ * address which has been overwritten.
+ *
+ * On arm64 we use the address of the caller's frame record, which remains the
+ * same for the lifetime of the instrumented function, unlike the return
+ * address in the LR.
+ */
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#else
+#define MCOUNT_ADDR		((unsigned long)_mcount)
+#endif
+
+/* The BL at the callsite's adjusted rec->ip */
+#define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
+
+#define FTRACE_PLT_IDX		0
+#define FTRACE_REGS_PLT_IDX	1
+#define NR_FTRACE_PLTS		2
+
+/*
+ * Currently, gcc tends to save the link register after the local variables
+ * on the stack. This causes the max stack tracer to report the function
+ * frame sizes for the wrong functions. By defining
+ * ARCH_FTRACE_SHIFT_STACK_TRACER, it will tell the stack tracer to expect
+ * to find the return address on the stack after the local variables have
+ * been set up.
+ *
+ * Note, this may change in the future, and we will need to deal with that
+ * if it were to happen.
+ */
+#define ARCH_FTRACE_SHIFT_STACK_TRACER 1
+
+#ifndef __ASSEMBLY__
+#include <linux/compat.h>
+
+extern void _mcount(unsigned long);
+extern void *return_address(unsigned int);
+
+struct dyn_arch_ftrace {
+	/* No extra data needed for arm64 */
+};
+
+extern unsigned long ftrace_graph_call;
+
+extern void return_to_handler(void);
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/*
+	 * Adjust addr to point at the BL in the callsite.
+	 * See ftrace_init_nop() for the callsite sequence.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+		return addr + AARCH64_INSN_SIZE;
+	/*
+	 * addr is the address of the mcount call instruction.
+	 * recordmcount does the necessary offset calculation.
+	 */
+	return addr;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+struct dyn_ftrace;
+struct ftrace_ops;
+struct ftrace_regs;
+
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+#endif
+
+#define ftrace_return_address(n) return_address(n)
+
+/*
+ * Because AArch32 mode does not share the same syscall table with AArch64,
+ * tracing compat syscalls may result in reporting bogus syscalls or even
+ * hang-up, so just do not trace them.
+ * See kernel/trace/trace_syscalls.c
+ *
+ * x86 code says:
+ * If the user really wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+	return is_compat_task();
+}
+
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+
+static inline bool arch_syscall_match_sym_name(const char *sym,
+					       const char *name)
+{
+	/*
+	 * Since all syscall functions have __arm64_ prefix, we must skip it.
+	 * However, as we described above, we decided to ignore compat
+	 * syscalls, so we don't care about __arm64_compat_ prefix here.
+	 */
+	return !strcmp(sym + 8, name);
+}
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif /* __ASM_FTRACE_H */
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
new file mode 100644
index 000000000..bc06691d2
--- /dev/null
+++ b/arch/arm64/include/asm/futex.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_FUTEX_H
+#define __ASM_FUTEX_H
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+
+#include <asm/errno.h>
+
+#define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
+do {									\
+	unsigned int loops = FUTEX_MAX_LOOPS;				\
+									\
+	uaccess_enable_privileged();					\
+	asm volatile(							\
+"	prfm	pstl1strm, %2\n"					\
+"1:	ldxr	%w1, %2\n"						\
+	insn "\n"							\
+"2:	stlxr	%w0, %w3, %2\n"						\
+"	cbz	%w0, 3f\n"						\
+"	sub	%w4, %w4, %w0\n"					\
+"	cbnz	%w4, 1b\n"						\
+"	mov	%w0, %w6\n"						\
+"3:\n"									\
+"	dmb	ish\n"							\
+	_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %w0)				\
+	_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %w0)				\
+	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp),	\
+	  "+r" (loops)							\
+	: "r" (oparg), "Ir" (-EAGAIN)					\
+	: "memory");							\
+	uaccess_disable_privileged();					\
+} while (0)
+
+static inline int
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
+{
+	int oldval = 0, ret, tmp;
+	u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
+
+	if (!access_ok(_uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov	%w3, %w5",
+				  ret, oldval, uaddr, tmp, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("add	%w3, %w1, %w5",
+				  ret, oldval, uaddr, tmp, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("orr	%w3, %w1, %w5",
+				  ret, oldval, uaddr, tmp, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("and	%w3, %w1, %w5",
+				  ret, oldval, uaddr, tmp, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("eor	%w3, %w1, %w5",
+				  ret, oldval, uaddr, tmp, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	if (!ret)
+		*oval = oldval;
+
+	return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	unsigned int loops = FUTEX_MAX_LOOPS;
+	u32 val, tmp;
+	u32 __user *uaddr;
+
+	if (!access_ok(_uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	uaddr = __uaccess_mask_ptr(_uaddr);
+	uaccess_enable_privileged();
+	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
+"	prfm	pstl1strm, %2\n"
+"1:	ldxr	%w1, %2\n"
+"	sub	%w3, %w1, %w5\n"
+"	cbnz	%w3, 4f\n"
+"2:	stlxr	%w3, %w6, %2\n"
+"	cbz	%w3, 3f\n"
+"	sub	%w4, %w4, %w3\n"
+"	cbnz	%w4, 1b\n"
+"	mov	%w0, %w7\n"
+"3:\n"
+"	dmb	ish\n"
+"4:\n"
+	_ASM_EXTABLE_UACCESS_ERR(1b, 4b, %w0)
+	_ASM_EXTABLE_UACCESS_ERR(2b, 4b, %w0)
+	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+	: "r" (oldval), "r" (newval), "Ir" (-EAGAIN)
+	: "memory");
+	uaccess_disable_privileged();
+
+	if (!ret)
+		*uval = val;
+
+	return ret;
+}
+
+#endif /* __ASM_FUTEX_H */
diff --git a/arch/arm64/include/asm/gpr-num.h b/arch/arm64/include/asm/gpr-num.h
new file mode 100644
index 000000000..05da4a7c5
--- /dev/null
+++ b/arch/arm64/include/asm/gpr-num.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_GPR_NUM_H
+#define __ASM_GPR_NUM_H
+
+#ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+	.equ	.L__gpr_num_x\num, \num
+	.equ	.L__gpr_num_w\num, \num
+	.endr
+	.equ	.L__gpr_num_xzr, 31
+	.equ	.L__gpr_num_wzr, 31
+
+#else /* __ASSEMBLY__ */
+
+#define __DEFINE_ASM_GPR_NUMS					\
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+"	.equ	.L__gpr_num_x\\num, \\num\n"			\
+"	.equ	.L__gpr_num_w\\num, \\num\n"			\
+"	.endr\n"						\
+"	.equ	.L__gpr_num_xzr, 31\n"				\
+"	.equ	.L__gpr_num_wzr, 31\n"
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_GPR_NUM_H */
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
new file mode 100644
index 000000000..cbfa7b6f2
--- /dev/null
+++ b/arch/arm64/include/asm/hardirq.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_HARDIRQ_H
+#define __ASM_HARDIRQ_H
+
+#include <linux/cache.h>
+#include <linux/percpu.h>
+#include <linux/threads.h>
+#include <asm/barrier.h>
+#include <asm/irq.h>
+#include <asm/kvm_arm.h>
+#include <asm/sysreg.h>
+
+#define ack_bad_irq ack_bad_irq
+#include <asm-generic/hardirq.h>
+
+#define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
+
+struct nmi_ctx {
+	u64 hcr;
+	unsigned int cnt;
+};
+
+DECLARE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
+#define arch_nmi_enter()						\
+do {									\
+	struct nmi_ctx *___ctx;						\
+	u64 ___hcr;							\
+									\
+	if (!is_kernel_in_hyp_mode())					\
+		break;							\
+									\
+	___ctx = this_cpu_ptr(&nmi_contexts);				\
+	if (___ctx->cnt) {						\
+		___ctx->cnt++;						\
+		break;							\
+	}								\
+									\
+	___hcr = read_sysreg(hcr_el2);					\
+	if (!(___hcr & HCR_TGE)) {					\
+		write_sysreg(___hcr | HCR_TGE, hcr_el2);		\
+		isb();							\
+	}								\
+	/*								\
+	 * Make sure the sysreg write is performed before ___ctx->cnt	\
+	 * is set to 1. NMIs that see cnt == 1 will rely on us.		\
+	 */								\
+	barrier();							\
+	___ctx->cnt = 1;                                                \
+	/*								\
+	 * Make sure ___ctx->cnt is set before we save ___hcr. We	\
+	 * don't want ___ctx->hcr to be overwritten.			\
+	 */								\
+	barrier();							\
+	___ctx->hcr = ___hcr;						\
+} while (0)
+
+#define arch_nmi_exit()							\
+do {									\
+	struct nmi_ctx *___ctx;						\
+	u64 ___hcr;							\
+									\
+	if (!is_kernel_in_hyp_mode())					\
+		break;							\
+									\
+	___ctx = this_cpu_ptr(&nmi_contexts);				\
+	___hcr = ___ctx->hcr;						\
+	/*								\
+	 * Make sure we read ___ctx->hcr before we release		\
+	 * ___ctx->cnt as it makes ___ctx->hcr updatable again.		\
+	 */								\
+	barrier();							\
+	___ctx->cnt--;							\
+	/*								\
+	 * Make sure ___ctx->cnt release is visible before we		\
+	 * restore the sysreg. Otherwise a new NMI occurring		\
+	 * right after write_sysreg() can be fooled and think		\
+	 * we secured things for it.					\
+	 */								\
+	barrier();							\
+	if (!___ctx->cnt && !(___hcr & HCR_TGE))			\
+		write_sysreg(___hcr, hcr_el2);				\
+} while (0)
+
+static inline void ack_bad_irq(unsigned int irq)
+{
+	extern unsigned long irq_err_count;
+	irq_err_count++;
+}
+
+#endif /* __ASM_HARDIRQ_H */
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
new file mode 100644
index 000000000..d20f5da2d
--- /dev/null
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2013 Linaro Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ */
+
+#ifndef __ASM_HUGETLB_H
+#define __ASM_HUGETLB_H
+
+#include <asm/page.h>
+
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+extern bool arch_hugetlb_migration_supported(struct hstate *h);
+#endif
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_dcache_clean, &page->flags);
+}
+#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+
+pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
+#define arch_make_huge_pte arch_make_huge_pte
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, pte_t pte);
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+				      unsigned long addr, pte_t *ptep,
+				      pte_t pte, int dirty);
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+				    unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
+extern pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+				   unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
+extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+			   pte_t *ptep, unsigned long sz);
+#define __HAVE_ARCH_HUGE_PTEP_GET
+extern pte_t huge_ptep_get(pte_t *ptep);
+
+void __init arm64_hugetlb_cma_reserve(void);
+
+#include <asm-generic/hugetlb.h>
+
+#endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
new file mode 100644
index 000000000..fa4c6ff3a
--- /dev/null
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_HW_BREAKPOINT_H
+#define __ASM_HW_BREAKPOINT_H
+
+#include <asm/cputype.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+#include <asm/virt.h>
+
+struct arch_hw_breakpoint_ctrl {
+	u32 __reserved	: 19,
+	len		: 8,
+	type		: 2,
+	privilege	: 2,
+	enabled		: 1;
+};
+
+struct arch_hw_breakpoint {
+	u64 address;
+	u64 trigger;
+	struct arch_hw_breakpoint_ctrl ctrl;
+};
+
+/* Privilege Levels */
+#define AARCH64_BREAKPOINT_EL1	1
+#define AARCH64_BREAKPOINT_EL0	2
+
+#define DBG_HMC_HYP		(1 << 13)
+
+static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
+{
+	u32 val = (ctrl.len << 5) | (ctrl.type << 3) | (ctrl.privilege << 1) |
+		ctrl.enabled;
+
+	if (is_kernel_in_hyp_mode() && ctrl.privilege == AARCH64_BREAKPOINT_EL1)
+		val |= DBG_HMC_HYP;
+
+	return val;
+}
+
+static inline void decode_ctrl_reg(u32 reg,
+				   struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	ctrl->enabled	= reg & 0x1;
+	reg >>= 1;
+	ctrl->privilege	= reg & 0x3;
+	reg >>= 2;
+	ctrl->type	= reg & 0x3;
+	reg >>= 2;
+	ctrl->len	= reg & 0xff;
+}
+
+/* Breakpoint */
+#define ARM_BREAKPOINT_EXECUTE	0
+
+/* Watchpoints */
+#define ARM_BREAKPOINT_LOAD	1
+#define ARM_BREAKPOINT_STORE	2
+#define AARCH64_ESR_ACCESS_MASK	(1 << 6)
+
+/* Lengths */
+#define ARM_BREAKPOINT_LEN_1	0x1
+#define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_3	0x7
+#define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_5	0x1f
+#define ARM_BREAKPOINT_LEN_6	0x3f
+#define ARM_BREAKPOINT_LEN_7	0x7f
+#define ARM_BREAKPOINT_LEN_8	0xff
+
+/* Kernel stepping */
+#define ARM_KERNEL_STEP_NONE	0
+#define ARM_KERNEL_STEP_ACTIVE	1
+#define ARM_KERNEL_STEP_SUSPEND	2
+
+/*
+ * Limits.
+ * Changing these will require modifications to the register accessors.
+ */
+#define ARM_MAX_BRP		16
+#define ARM_MAX_WRP		16
+
+/* Virtual debug register bases. */
+#define AARCH64_DBG_REG_BVR	0
+#define AARCH64_DBG_REG_BCR	(AARCH64_DBG_REG_BVR + ARM_MAX_BRP)
+#define AARCH64_DBG_REG_WVR	(AARCH64_DBG_REG_BCR + ARM_MAX_BRP)
+#define AARCH64_DBG_REG_WCR	(AARCH64_DBG_REG_WVR + ARM_MAX_WRP)
+
+/* Debug register names. */
+#define AARCH64_DBG_REG_NAME_BVR	bvr
+#define AARCH64_DBG_REG_NAME_BCR	bcr
+#define AARCH64_DBG_REG_NAME_WVR	wvr
+#define AARCH64_DBG_REG_NAME_WCR	wcr
+
+/* Accessor macros for the debug registers. */
+#define AARCH64_DBG_READ(N, REG, VAL) do {\
+	VAL = read_sysreg(dbg##REG##N##_el1);\
+} while (0)
+
+#define AARCH64_DBG_WRITE(N, REG, VAL) do {\
+	write_sysreg(VAL, dbg##REG##N##_el1);\
+} while (0)
+
+struct task_struct;
+struct notifier_block;
+struct perf_event_attr;
+struct perf_event;
+struct pmu;
+
+extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
+				  int *gen_len, int *gen_type, int *offset);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+extern int arch_install_hw_breakpoint(struct perf_event *bp);
+extern void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+extern void hw_breakpoint_pmu_read(struct perf_event *bp);
+extern int hw_breakpoint_slots(int type);
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+extern void hw_breakpoint_thread_switch(struct task_struct *next);
+extern void ptrace_hw_copy_thread(struct task_struct *task);
+#else
+static inline void hw_breakpoint_thread_switch(struct task_struct *next)
+{
+}
+static inline void ptrace_hw_copy_thread(struct task_struct *task)
+{
+}
+#endif
+
+/* Determine number of BRP registers available. */
+static inline int get_num_brps(void)
+{
+	u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	return 1 +
+		cpuid_feature_extract_unsigned_field(dfr0,
+						ID_AA64DFR0_EL1_BRPs_SHIFT);
+}
+
+/* Determine number of WRP registers available. */
+static inline int get_num_wrps(void)
+{
+	u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	return 1 +
+		cpuid_feature_extract_unsigned_field(dfr0,
+						ID_AA64DFR0_EL1_WRPs_SHIFT);
+}
+
+#endif	/* __ASM_BREAKPOINT_H */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
new file mode 100644
index 000000000..298b386d3
--- /dev/null
+++ b/arch/arm64/include/asm/hwcap.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_HWCAP_H
+#define __ASM_HWCAP_H
+
+#include <uapi/asm/hwcap.h>
+#include <asm/cpufeature.h>
+
+#define COMPAT_HWCAP_SWP	(1 << 0)
+#define COMPAT_HWCAP_HALF	(1 << 1)
+#define COMPAT_HWCAP_THUMB	(1 << 2)
+#define COMPAT_HWCAP_26BIT	(1 << 3)
+#define COMPAT_HWCAP_FAST_MULT	(1 << 4)
+#define COMPAT_HWCAP_FPA	(1 << 5)
+#define COMPAT_HWCAP_VFP	(1 << 6)
+#define COMPAT_HWCAP_EDSP	(1 << 7)
+#define COMPAT_HWCAP_JAVA	(1 << 8)
+#define COMPAT_HWCAP_IWMMXT	(1 << 9)
+#define COMPAT_HWCAP_CRUNCH	(1 << 10) /* Obsolete */
+#define COMPAT_HWCAP_THUMBEE	(1 << 11)
+#define COMPAT_HWCAP_NEON	(1 << 12)
+#define COMPAT_HWCAP_VFPv3	(1 << 13)
+#define COMPAT_HWCAP_VFPV3D16	(1 << 14)
+#define COMPAT_HWCAP_TLS	(1 << 15)
+#define COMPAT_HWCAP_VFPv4	(1 << 16)
+#define COMPAT_HWCAP_IDIVA	(1 << 17)
+#define COMPAT_HWCAP_IDIVT	(1 << 18)
+#define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_VFPD32	(1 << 19)
+#define COMPAT_HWCAP_LPAE	(1 << 20)
+#define COMPAT_HWCAP_EVTSTRM	(1 << 21)
+
+#define COMPAT_HWCAP2_AES	(1 << 0)
+#define COMPAT_HWCAP2_PMULL	(1 << 1)
+#define COMPAT_HWCAP2_SHA1	(1 << 2)
+#define COMPAT_HWCAP2_SHA2	(1 << 3)
+#define COMPAT_HWCAP2_CRC32	(1 << 4)
+
+#ifndef __ASSEMBLY__
+#include <linux/log2.h>
+
+/*
+ * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
+ * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
+ * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here
+ * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart.
+ *
+ * Hwcaps should be set and tested within the kernel via the
+ * cpu_{set,have}_named_feature(feature) where feature is the unique suffix
+ * of KERNEL_HWCAP_{feature}.
+ */
+#define __khwcap_feature(x)		const_ilog2(HWCAP_ ## x)
+#define KERNEL_HWCAP_FP			__khwcap_feature(FP)
+#define KERNEL_HWCAP_ASIMD		__khwcap_feature(ASIMD)
+#define KERNEL_HWCAP_EVTSTRM		__khwcap_feature(EVTSTRM)
+#define KERNEL_HWCAP_AES		__khwcap_feature(AES)
+#define KERNEL_HWCAP_PMULL		__khwcap_feature(PMULL)
+#define KERNEL_HWCAP_SHA1		__khwcap_feature(SHA1)
+#define KERNEL_HWCAP_SHA2		__khwcap_feature(SHA2)
+#define KERNEL_HWCAP_CRC32		__khwcap_feature(CRC32)
+#define KERNEL_HWCAP_ATOMICS		__khwcap_feature(ATOMICS)
+#define KERNEL_HWCAP_FPHP		__khwcap_feature(FPHP)
+#define KERNEL_HWCAP_ASIMDHP		__khwcap_feature(ASIMDHP)
+#define KERNEL_HWCAP_CPUID		__khwcap_feature(CPUID)
+#define KERNEL_HWCAP_ASIMDRDM		__khwcap_feature(ASIMDRDM)
+#define KERNEL_HWCAP_JSCVT		__khwcap_feature(JSCVT)
+#define KERNEL_HWCAP_FCMA		__khwcap_feature(FCMA)
+#define KERNEL_HWCAP_LRCPC		__khwcap_feature(LRCPC)
+#define KERNEL_HWCAP_DCPOP		__khwcap_feature(DCPOP)
+#define KERNEL_HWCAP_SHA3		__khwcap_feature(SHA3)
+#define KERNEL_HWCAP_SM3		__khwcap_feature(SM3)
+#define KERNEL_HWCAP_SM4		__khwcap_feature(SM4)
+#define KERNEL_HWCAP_ASIMDDP		__khwcap_feature(ASIMDDP)
+#define KERNEL_HWCAP_SHA512		__khwcap_feature(SHA512)
+#define KERNEL_HWCAP_SVE		__khwcap_feature(SVE)
+#define KERNEL_HWCAP_ASIMDFHM		__khwcap_feature(ASIMDFHM)
+#define KERNEL_HWCAP_DIT		__khwcap_feature(DIT)
+#define KERNEL_HWCAP_USCAT		__khwcap_feature(USCAT)
+#define KERNEL_HWCAP_ILRCPC		__khwcap_feature(ILRCPC)
+#define KERNEL_HWCAP_FLAGM		__khwcap_feature(FLAGM)
+#define KERNEL_HWCAP_SSBS		__khwcap_feature(SSBS)
+#define KERNEL_HWCAP_SB			__khwcap_feature(SB)
+#define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
+#define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
+
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 64)
+#define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
+#define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
+#define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
+#define KERNEL_HWCAP_SVEPMULL		__khwcap2_feature(SVEPMULL)
+#define KERNEL_HWCAP_SVEBITPERM		__khwcap2_feature(SVEBITPERM)
+#define KERNEL_HWCAP_SVESHA3		__khwcap2_feature(SVESHA3)
+#define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
+#define KERNEL_HWCAP_FLAGM2		__khwcap2_feature(FLAGM2)
+#define KERNEL_HWCAP_FRINT		__khwcap2_feature(FRINT)
+#define KERNEL_HWCAP_SVEI8MM		__khwcap2_feature(SVEI8MM)
+#define KERNEL_HWCAP_SVEF32MM		__khwcap2_feature(SVEF32MM)
+#define KERNEL_HWCAP_SVEF64MM		__khwcap2_feature(SVEF64MM)
+#define KERNEL_HWCAP_SVEBF16		__khwcap2_feature(SVEBF16)
+#define KERNEL_HWCAP_I8MM		__khwcap2_feature(I8MM)
+#define KERNEL_HWCAP_BF16		__khwcap2_feature(BF16)
+#define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
+#define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
+#define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
+#define KERNEL_HWCAP_MTE		__khwcap2_feature(MTE)
+#define KERNEL_HWCAP_ECV		__khwcap2_feature(ECV)
+#define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
+#define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
+#define KERNEL_HWCAP_MTE3		__khwcap2_feature(MTE3)
+#define KERNEL_HWCAP_SME		__khwcap2_feature(SME)
+#define KERNEL_HWCAP_SME_I16I64		__khwcap2_feature(SME_I16I64)
+#define KERNEL_HWCAP_SME_F64F64		__khwcap2_feature(SME_F64F64)
+#define KERNEL_HWCAP_SME_I8I32		__khwcap2_feature(SME_I8I32)
+#define KERNEL_HWCAP_SME_F16F32		__khwcap2_feature(SME_F16F32)
+#define KERNEL_HWCAP_SME_B16F32		__khwcap2_feature(SME_B16F32)
+#define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
+#define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
+#define KERNEL_HWCAP_WFXT		__khwcap2_feature(WFXT)
+#define KERNEL_HWCAP_EBF16		__khwcap2_feature(EBF16)
+#define KERNEL_HWCAP_SVE_EBF16		__khwcap2_feature(SVE_EBF16)
+
+/*
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
+ */
+#define ELF_HWCAP		cpu_get_elf_hwcap()
+#define ELF_HWCAP2		cpu_get_elf_hwcap2()
+
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
+#define COMPAT_ELF_HWCAP2	(compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
+#endif
+
+enum {
+	CAP_HWCAP = 1,
+#ifdef CONFIG_COMPAT
+	CAP_COMPAT_HWCAP,
+	CAP_COMPAT_HWCAP2,
+#endif
+};
+
+#endif
+#endif
diff --git a/arch/arm64/include/asm/hyp_image.h b/arch/arm64/include/asm/hyp_image.h
new file mode 100644
index 000000000..b4b3076a7
--- /dev/null
+++ b/arch/arm64/include/asm/hyp_image.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Google LLC.
+ * Written by David Brazdil <dbrazdil@google.com>
+ */
+
+#ifndef __ARM64_HYP_IMAGE_H__
+#define __ARM64_HYP_IMAGE_H__
+
+#define __HYP_CONCAT(a, b)	a ## b
+#define HYP_CONCAT(a, b)	__HYP_CONCAT(a, b)
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+/*
+ * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_,
+ * to separate it from the kernel proper.
+ */
+#define kvm_nvhe_sym(sym)	__kvm_nvhe_##sym
+#else
+#define kvm_nvhe_sym(sym)	sym
+#endif
+
+#ifdef LINKER_SCRIPT
+
+/*
+ * KVM nVHE ELF section names are prefixed with .hyp, to separate them
+ * from the kernel proper.
+ */
+#define HYP_SECTION_NAME(NAME)	.hyp##NAME
+
+/* Symbol defined at the beginning of each hyp section. */
+#define HYP_SECTION_SYMBOL_NAME(NAME) \
+	HYP_CONCAT(__hyp_section_, HYP_SECTION_NAME(NAME))
+
+/*
+ * Helper to generate linker script statements starting a hyp section.
+ *
+ * A symbol with a well-known name is defined at the first byte. This
+ * is used as a base for hyp relocations (see gen-hyprel.c). It must
+ * be defined inside the section so the linker of `vmlinux` cannot
+ * separate it from the section data.
+ */
+#define BEGIN_HYP_SECTION(NAME)				\
+	HYP_SECTION_NAME(NAME) : {			\
+		HYP_SECTION_SYMBOL_NAME(NAME) = .;
+
+/* Helper to generate linker script statements ending a hyp section. */
+#define END_HYP_SECTION					\
+	}
+
+/* Defines an ELF hyp section from input section @NAME and its subsections. */
+#define HYP_SECTION(NAME)			\
+	BEGIN_HYP_SECTION(NAME)			\
+		*(NAME NAME##.*)		\
+	END_HYP_SECTION
+
+/*
+ * Defines a linker script alias of a kernel-proper symbol referenced by
+ * KVM nVHE hyp code.
+ */
+#define KVM_NVHE_ALIAS(sym)	kvm_nvhe_sym(sym) = sym;
+
+/* Defines a linker script alias for KVM nVHE hyp symbols */
+#define KVM_NVHE_ALIAS_HYP(first, sec)	kvm_nvhe_sym(first) = kvm_nvhe_sym(sec);
+
+#endif /* LINKER_SCRIPT */
+
+#endif /* __ARM64_HYP_IMAGE_H__ */
diff --git a/arch/arm64/include/asm/hyperv-tlfs.h b/arch/arm64/include/asm/hyperv-tlfs.h
new file mode 100644
index 000000000..bc6c7ac93
--- /dev/null
+++ b/arch/arm64/include/asm/hyperv-tlfs.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file contains definitions from the Hyper-V Hypervisor Top-Level
+ * Functional Specification (TLFS):
+ * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+ *
+ * Copyright (C) 2021, Microsoft, Inc.
+ *
+ * Author : Michael Kelley <mikelley@microsoft.com>
+ */
+
+#ifndef _ASM_HYPERV_TLFS_H
+#define _ASM_HYPERV_TLFS_H
+
+#include <linux/types.h>
+
+/*
+ * All data structures defined in the TLFS that are shared between Hyper-V
+ * and a guest VM use Little Endian byte ordering.  This matches the default
+ * byte ordering of Linux running on ARM64, so no special handling is required.
+ */
+
+/*
+ * These Hyper-V registers provide information equivalent to the CPUID
+ * instruction on x86/x64.
+ */
+#define HV_REGISTER_HYPERVISOR_VERSION		0x00000100 /*CPUID 0x40000002 */
+#define HV_REGISTER_FEATURES			0x00000200 /*CPUID 0x40000003 */
+#define HV_REGISTER_ENLIGHTENMENTS		0x00000201 /*CPUID 0x40000004 */
+
+/*
+ * Group C Features. See the asm-generic version of hyperv-tlfs.h
+ * for a description of Feature Groups.
+ */
+
+/* Crash MSRs available */
+#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE	BIT(8)
+
+/* STIMER direct mode is available */
+#define HV_STIMER_DIRECT_MODE_AVAILABLE		BIT(13)
+
+/*
+ * Synthetic register definitions equivalent to MSRs on x86/x64
+ */
+#define HV_REGISTER_CRASH_P0		0x00000210
+#define HV_REGISTER_CRASH_P1		0x00000211
+#define HV_REGISTER_CRASH_P2		0x00000212
+#define HV_REGISTER_CRASH_P3		0x00000213
+#define HV_REGISTER_CRASH_P4		0x00000214
+#define HV_REGISTER_CRASH_CTL		0x00000215
+
+#define HV_REGISTER_GUEST_OSID		0x00090002
+#define HV_REGISTER_VP_INDEX		0x00090003
+#define HV_REGISTER_TIME_REF_COUNT	0x00090004
+#define HV_REGISTER_REFERENCE_TSC	0x00090017
+
+#define HV_REGISTER_SINT0		0x000A0000
+#define HV_REGISTER_SCONTROL		0x000A0010
+#define HV_REGISTER_SIEFP		0x000A0012
+#define HV_REGISTER_SIMP		0x000A0013
+#define HV_REGISTER_EOM			0x000A0014
+
+#define HV_REGISTER_STIMER0_CONFIG	0x000B0000
+#define HV_REGISTER_STIMER0_COUNT	0x000B0001
+
+union hv_msi_entry {
+	u64 as_uint64[2];
+	struct {
+		u64 address;
+		u32 data;
+		u32 reserved;
+	} __packed;
+};
+
+#include <asm-generic/hyperv-tlfs.h>
+
+#endif
diff --git a/arch/arm64/include/asm/hypervisor.h b/arch/arm64/include/asm/hypervisor.h
new file mode 100644
index 000000000..0ae427f35
--- /dev/null
+++ b/arch/arm64/include/asm/hypervisor.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_HYPERVISOR_H
+#define _ASM_ARM64_HYPERVISOR_H
+
+#include <asm/xen/hypervisor.h>
+
+void kvm_init_hyp_services(void);
+bool kvm_arm_hyp_service_available(u32 func_id);
+
+#endif
diff --git a/arch/arm64/include/asm/image.h b/arch/arm64/include/asm/image.h
new file mode 100644
index 000000000..c2b13213c
--- /dev/null
+++ b/arch/arm64/include/asm/image.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_IMAGE_H
+#define __ASM_IMAGE_H
+
+#define ARM64_IMAGE_MAGIC	"ARM\x64"
+
+#define ARM64_IMAGE_FLAG_BE_SHIFT		0
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT	(ARM64_IMAGE_FLAG_BE_SHIFT + 1)
+#define ARM64_IMAGE_FLAG_PHYS_BASE_SHIFT \
+					(ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT + 2)
+#define ARM64_IMAGE_FLAG_BE_MASK		0x1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_MASK		0x3
+#define ARM64_IMAGE_FLAG_PHYS_BASE_MASK		0x1
+
+#define ARM64_IMAGE_FLAG_LE			0
+#define ARM64_IMAGE_FLAG_BE			1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_4K		1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_16K		2
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_64K		3
+#define ARM64_IMAGE_FLAG_PHYS_BASE		1
+
+#ifndef __ASSEMBLY__
+
+#define arm64_image_flag_field(flags, field) \
+				(((flags) >> field##_SHIFT) & field##_MASK)
+
+/*
+ * struct arm64_image_header - arm64 kernel image header
+ * See Documentation/arm64/booting.rst for details
+ *
+ * @code0:		Executable code, or
+ *   @mz_header		  alternatively used for part of MZ header
+ * @code1:		Executable code
+ * @text_offset:	Image load offset
+ * @image_size:		Effective Image size
+ * @flags:		kernel flags
+ * @reserved:		reserved
+ * @magic:		Magic number
+ * @reserved5:		reserved, or
+ *   @pe_header:	  alternatively used for PE COFF offset
+ */
+
+struct arm64_image_header {
+	__le32 code0;
+	__le32 code1;
+	__le64 text_offset;
+	__le64 image_size;
+	__le64 flags;
+	__le64 res2;
+	__le64 res3;
+	__le64 res4;
+	__le32 magic;
+	__le32 res5;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_IMAGE_H */
diff --git a/arch/arm64/include/asm/insn-def.h b/arch/arm64/include/asm/insn-def.h
new file mode 100644
index 000000000..1a7d0d483
--- /dev/null
+++ b/arch/arm64/include/asm/insn-def.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_INSN_DEF_H
+#define __ASM_INSN_DEF_H
+
+#include <asm/brk-imm.h>
+
+/* A64 instructions are always 32 bits. */
+#define	AARCH64_INSN_SIZE		4
+
+/*
+ * BRK instruction encoding
+ * The #imm16 value should be placed at bits[20:5] within BRK ins
+ */
+#define AARCH64_BREAK_MON	0xd4200000
+
+/*
+ * BRK instruction for provoking a fault on purpose
+ * Unlike kgdb, #imm16 value with unallocated handler is used for faulting.
+ */
+#define AARCH64_BREAK_FAULT	(AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5))
+
+#endif /* __ASM_INSN_DEF_H */
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
new file mode 100644
index 000000000..834bff720
--- /dev/null
+++ b/arch/arm64/include/asm/insn.h
@@ -0,0 +1,645 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com>
+ */
+#ifndef	__ASM_INSN_H
+#define	__ASM_INSN_H
+#include <linux/build_bug.h>
+#include <linux/types.h>
+
+#include <asm/insn-def.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
+ * Section C3.1 "A64 instruction index by encoding":
+ * AArch64 main encoding table
+ *  Bit position
+ *   28 27 26 25	Encoding Group
+ *   0  0  -  -		Unallocated
+ *   1  0  0  -		Data processing, immediate
+ *   1  0  1  -		Branch, exception generation and system instructions
+ *   -  1  -  0		Loads and stores
+ *   -  1  0  1		Data processing - register
+ *   0  1  1  1		Data processing - SIMD and floating point
+ *   1  1  1  1		Data processing - SIMD and floating point
+ * "-" means "don't care"
+ */
+enum aarch64_insn_encoding_class {
+	AARCH64_INSN_CLS_UNKNOWN,	/* UNALLOCATED */
+	AARCH64_INSN_CLS_SVE,		/* SVE instructions */
+	AARCH64_INSN_CLS_DP_IMM,	/* Data processing - immediate */
+	AARCH64_INSN_CLS_DP_REG,	/* Data processing - register */
+	AARCH64_INSN_CLS_DP_FPSIMD,	/* Data processing - SIMD and FP */
+	AARCH64_INSN_CLS_LDST,		/* Loads and stores */
+	AARCH64_INSN_CLS_BR_SYS,	/* Branch, exception generation and
+					 * system instructions */
+};
+
+enum aarch64_insn_hint_cr_op {
+	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
+	AARCH64_INSN_HINT_YIELD	= 0x1 << 5,
+	AARCH64_INSN_HINT_WFE	= 0x2 << 5,
+	AARCH64_INSN_HINT_WFI	= 0x3 << 5,
+	AARCH64_INSN_HINT_SEV	= 0x4 << 5,
+	AARCH64_INSN_HINT_SEVL	= 0x5 << 5,
+
+	AARCH64_INSN_HINT_XPACLRI    = 0x07 << 5,
+	AARCH64_INSN_HINT_PACIA_1716 = 0x08 << 5,
+	AARCH64_INSN_HINT_PACIB_1716 = 0x0A << 5,
+	AARCH64_INSN_HINT_AUTIA_1716 = 0x0C << 5,
+	AARCH64_INSN_HINT_AUTIB_1716 = 0x0E << 5,
+	AARCH64_INSN_HINT_PACIAZ     = 0x18 << 5,
+	AARCH64_INSN_HINT_PACIASP    = 0x19 << 5,
+	AARCH64_INSN_HINT_PACIBZ     = 0x1A << 5,
+	AARCH64_INSN_HINT_PACIBSP    = 0x1B << 5,
+	AARCH64_INSN_HINT_AUTIAZ     = 0x1C << 5,
+	AARCH64_INSN_HINT_AUTIASP    = 0x1D << 5,
+	AARCH64_INSN_HINT_AUTIBZ     = 0x1E << 5,
+	AARCH64_INSN_HINT_AUTIBSP    = 0x1F << 5,
+
+	AARCH64_INSN_HINT_ESB  = 0x10 << 5,
+	AARCH64_INSN_HINT_PSB  = 0x11 << 5,
+	AARCH64_INSN_HINT_TSB  = 0x12 << 5,
+	AARCH64_INSN_HINT_CSDB = 0x14 << 5,
+	AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5,
+
+	AARCH64_INSN_HINT_BTI   = 0x20 << 5,
+	AARCH64_INSN_HINT_BTIC  = 0x22 << 5,
+	AARCH64_INSN_HINT_BTIJ  = 0x24 << 5,
+	AARCH64_INSN_HINT_BTIJC = 0x26 << 5,
+};
+
+enum aarch64_insn_imm_type {
+	AARCH64_INSN_IMM_ADR,
+	AARCH64_INSN_IMM_26,
+	AARCH64_INSN_IMM_19,
+	AARCH64_INSN_IMM_16,
+	AARCH64_INSN_IMM_14,
+	AARCH64_INSN_IMM_12,
+	AARCH64_INSN_IMM_9,
+	AARCH64_INSN_IMM_7,
+	AARCH64_INSN_IMM_6,
+	AARCH64_INSN_IMM_S,
+	AARCH64_INSN_IMM_R,
+	AARCH64_INSN_IMM_N,
+	AARCH64_INSN_IMM_MAX
+};
+
+enum aarch64_insn_register_type {
+	AARCH64_INSN_REGTYPE_RT,
+	AARCH64_INSN_REGTYPE_RN,
+	AARCH64_INSN_REGTYPE_RT2,
+	AARCH64_INSN_REGTYPE_RM,
+	AARCH64_INSN_REGTYPE_RD,
+	AARCH64_INSN_REGTYPE_RA,
+	AARCH64_INSN_REGTYPE_RS,
+};
+
+enum aarch64_insn_register {
+	AARCH64_INSN_REG_0  = 0,
+	AARCH64_INSN_REG_1  = 1,
+	AARCH64_INSN_REG_2  = 2,
+	AARCH64_INSN_REG_3  = 3,
+	AARCH64_INSN_REG_4  = 4,
+	AARCH64_INSN_REG_5  = 5,
+	AARCH64_INSN_REG_6  = 6,
+	AARCH64_INSN_REG_7  = 7,
+	AARCH64_INSN_REG_8  = 8,
+	AARCH64_INSN_REG_9  = 9,
+	AARCH64_INSN_REG_10 = 10,
+	AARCH64_INSN_REG_11 = 11,
+	AARCH64_INSN_REG_12 = 12,
+	AARCH64_INSN_REG_13 = 13,
+	AARCH64_INSN_REG_14 = 14,
+	AARCH64_INSN_REG_15 = 15,
+	AARCH64_INSN_REG_16 = 16,
+	AARCH64_INSN_REG_17 = 17,
+	AARCH64_INSN_REG_18 = 18,
+	AARCH64_INSN_REG_19 = 19,
+	AARCH64_INSN_REG_20 = 20,
+	AARCH64_INSN_REG_21 = 21,
+	AARCH64_INSN_REG_22 = 22,
+	AARCH64_INSN_REG_23 = 23,
+	AARCH64_INSN_REG_24 = 24,
+	AARCH64_INSN_REG_25 = 25,
+	AARCH64_INSN_REG_26 = 26,
+	AARCH64_INSN_REG_27 = 27,
+	AARCH64_INSN_REG_28 = 28,
+	AARCH64_INSN_REG_29 = 29,
+	AARCH64_INSN_REG_FP = 29, /* Frame pointer */
+	AARCH64_INSN_REG_30 = 30,
+	AARCH64_INSN_REG_LR = 30, /* Link register */
+	AARCH64_INSN_REG_ZR = 31, /* Zero: as source register */
+	AARCH64_INSN_REG_SP = 31  /* Stack pointer: as load/store base reg */
+};
+
+enum aarch64_insn_special_register {
+	AARCH64_INSN_SPCLREG_SPSR_EL1	= 0xC200,
+	AARCH64_INSN_SPCLREG_ELR_EL1	= 0xC201,
+	AARCH64_INSN_SPCLREG_SP_EL0	= 0xC208,
+	AARCH64_INSN_SPCLREG_SPSEL	= 0xC210,
+	AARCH64_INSN_SPCLREG_CURRENTEL	= 0xC212,
+	AARCH64_INSN_SPCLREG_DAIF	= 0xDA11,
+	AARCH64_INSN_SPCLREG_NZCV	= 0xDA10,
+	AARCH64_INSN_SPCLREG_FPCR	= 0xDA20,
+	AARCH64_INSN_SPCLREG_DSPSR_EL0	= 0xDA28,
+	AARCH64_INSN_SPCLREG_DLR_EL0	= 0xDA29,
+	AARCH64_INSN_SPCLREG_SPSR_EL2	= 0xE200,
+	AARCH64_INSN_SPCLREG_ELR_EL2	= 0xE201,
+	AARCH64_INSN_SPCLREG_SP_EL1	= 0xE208,
+	AARCH64_INSN_SPCLREG_SPSR_INQ	= 0xE218,
+	AARCH64_INSN_SPCLREG_SPSR_ABT	= 0xE219,
+	AARCH64_INSN_SPCLREG_SPSR_UND	= 0xE21A,
+	AARCH64_INSN_SPCLREG_SPSR_FIQ	= 0xE21B,
+	AARCH64_INSN_SPCLREG_SPSR_EL3	= 0xF200,
+	AARCH64_INSN_SPCLREG_ELR_EL3	= 0xF201,
+	AARCH64_INSN_SPCLREG_SP_EL2	= 0xF210
+};
+
+enum aarch64_insn_variant {
+	AARCH64_INSN_VARIANT_32BIT,
+	AARCH64_INSN_VARIANT_64BIT
+};
+
+enum aarch64_insn_condition {
+	AARCH64_INSN_COND_EQ = 0x0, /* == */
+	AARCH64_INSN_COND_NE = 0x1, /* != */
+	AARCH64_INSN_COND_CS = 0x2, /* unsigned >= */
+	AARCH64_INSN_COND_CC = 0x3, /* unsigned < */
+	AARCH64_INSN_COND_MI = 0x4, /* < 0 */
+	AARCH64_INSN_COND_PL = 0x5, /* >= 0 */
+	AARCH64_INSN_COND_VS = 0x6, /* overflow */
+	AARCH64_INSN_COND_VC = 0x7, /* no overflow */
+	AARCH64_INSN_COND_HI = 0x8, /* unsigned > */
+	AARCH64_INSN_COND_LS = 0x9, /* unsigned <= */
+	AARCH64_INSN_COND_GE = 0xa, /* signed >= */
+	AARCH64_INSN_COND_LT = 0xb, /* signed < */
+	AARCH64_INSN_COND_GT = 0xc, /* signed > */
+	AARCH64_INSN_COND_LE = 0xd, /* signed <= */
+	AARCH64_INSN_COND_AL = 0xe, /* always */
+};
+
+enum aarch64_insn_branch_type {
+	AARCH64_INSN_BRANCH_NOLINK,
+	AARCH64_INSN_BRANCH_LINK,
+	AARCH64_INSN_BRANCH_RETURN,
+	AARCH64_INSN_BRANCH_COMP_ZERO,
+	AARCH64_INSN_BRANCH_COMP_NONZERO,
+};
+
+enum aarch64_insn_size_type {
+	AARCH64_INSN_SIZE_8,
+	AARCH64_INSN_SIZE_16,
+	AARCH64_INSN_SIZE_32,
+	AARCH64_INSN_SIZE_64,
+};
+
+enum aarch64_insn_ldst_type {
+	AARCH64_INSN_LDST_LOAD_REG_OFFSET,
+	AARCH64_INSN_LDST_STORE_REG_OFFSET,
+	AARCH64_INSN_LDST_LOAD_IMM_OFFSET,
+	AARCH64_INSN_LDST_STORE_IMM_OFFSET,
+	AARCH64_INSN_LDST_LOAD_PAIR_PRE_INDEX,
+	AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
+	AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+	AARCH64_INSN_LDST_LOAD_EX,
+	AARCH64_INSN_LDST_LOAD_ACQ_EX,
+	AARCH64_INSN_LDST_STORE_EX,
+	AARCH64_INSN_LDST_STORE_REL_EX,
+};
+
+enum aarch64_insn_adsb_type {
+	AARCH64_INSN_ADSB_ADD,
+	AARCH64_INSN_ADSB_SUB,
+	AARCH64_INSN_ADSB_ADD_SETFLAGS,
+	AARCH64_INSN_ADSB_SUB_SETFLAGS
+};
+
+enum aarch64_insn_movewide_type {
+	AARCH64_INSN_MOVEWIDE_ZERO,
+	AARCH64_INSN_MOVEWIDE_KEEP,
+	AARCH64_INSN_MOVEWIDE_INVERSE
+};
+
+enum aarch64_insn_bitfield_type {
+	AARCH64_INSN_BITFIELD_MOVE,
+	AARCH64_INSN_BITFIELD_MOVE_UNSIGNED,
+	AARCH64_INSN_BITFIELD_MOVE_SIGNED
+};
+
+enum aarch64_insn_data1_type {
+	AARCH64_INSN_DATA1_REVERSE_16,
+	AARCH64_INSN_DATA1_REVERSE_32,
+	AARCH64_INSN_DATA1_REVERSE_64,
+};
+
+enum aarch64_insn_data2_type {
+	AARCH64_INSN_DATA2_UDIV,
+	AARCH64_INSN_DATA2_SDIV,
+	AARCH64_INSN_DATA2_LSLV,
+	AARCH64_INSN_DATA2_LSRV,
+	AARCH64_INSN_DATA2_ASRV,
+	AARCH64_INSN_DATA2_RORV,
+};
+
+enum aarch64_insn_data3_type {
+	AARCH64_INSN_DATA3_MADD,
+	AARCH64_INSN_DATA3_MSUB,
+};
+
+enum aarch64_insn_logic_type {
+	AARCH64_INSN_LOGIC_AND,
+	AARCH64_INSN_LOGIC_BIC,
+	AARCH64_INSN_LOGIC_ORR,
+	AARCH64_INSN_LOGIC_ORN,
+	AARCH64_INSN_LOGIC_EOR,
+	AARCH64_INSN_LOGIC_EON,
+	AARCH64_INSN_LOGIC_AND_SETFLAGS,
+	AARCH64_INSN_LOGIC_BIC_SETFLAGS
+};
+
+enum aarch64_insn_prfm_type {
+	AARCH64_INSN_PRFM_TYPE_PLD,
+	AARCH64_INSN_PRFM_TYPE_PLI,
+	AARCH64_INSN_PRFM_TYPE_PST,
+};
+
+enum aarch64_insn_prfm_target {
+	AARCH64_INSN_PRFM_TARGET_L1,
+	AARCH64_INSN_PRFM_TARGET_L2,
+	AARCH64_INSN_PRFM_TARGET_L3,
+};
+
+enum aarch64_insn_prfm_policy {
+	AARCH64_INSN_PRFM_POLICY_KEEP,
+	AARCH64_INSN_PRFM_POLICY_STRM,
+};
+
+enum aarch64_insn_adr_type {
+	AARCH64_INSN_ADR_TYPE_ADRP,
+	AARCH64_INSN_ADR_TYPE_ADR,
+};
+
+enum aarch64_insn_mem_atomic_op {
+	AARCH64_INSN_MEM_ATOMIC_ADD,
+	AARCH64_INSN_MEM_ATOMIC_CLR,
+	AARCH64_INSN_MEM_ATOMIC_EOR,
+	AARCH64_INSN_MEM_ATOMIC_SET,
+	AARCH64_INSN_MEM_ATOMIC_SWP,
+};
+
+enum aarch64_insn_mem_order_type {
+	AARCH64_INSN_MEM_ORDER_NONE,
+	AARCH64_INSN_MEM_ORDER_ACQ,
+	AARCH64_INSN_MEM_ORDER_REL,
+	AARCH64_INSN_MEM_ORDER_ACQREL,
+};
+
+enum aarch64_insn_mb_type {
+	AARCH64_INSN_MB_SY,
+	AARCH64_INSN_MB_ST,
+	AARCH64_INSN_MB_LD,
+	AARCH64_INSN_MB_ISH,
+	AARCH64_INSN_MB_ISHST,
+	AARCH64_INSN_MB_ISHLD,
+	AARCH64_INSN_MB_NSH,
+	AARCH64_INSN_MB_NSHST,
+	AARCH64_INSN_MB_NSHLD,
+	AARCH64_INSN_MB_OSH,
+	AARCH64_INSN_MB_OSHST,
+	AARCH64_INSN_MB_OSHLD,
+};
+
+#define	__AARCH64_INSN_FUNCS(abbr, mask, val)				\
+static __always_inline bool aarch64_insn_is_##abbr(u32 code)		\
+{									\
+	BUILD_BUG_ON(~(mask) & (val));					\
+	return (code & (mask)) == (val);				\
+}									\
+static __always_inline u32 aarch64_insn_get_##abbr##_value(void)	\
+{									\
+	return (val);							\
+}
+
+__AARCH64_INSN_FUNCS(adr,	0x9F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
+__AARCH64_INSN_FUNCS(prfm,	0x3FC00000, 0x39800000)
+__AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
+__AARCH64_INSN_FUNCS(store_imm,	0x3FC00000, 0x39000000)
+__AARCH64_INSN_FUNCS(load_imm,	0x3FC00000, 0x39400000)
+__AARCH64_INSN_FUNCS(store_pre,	0x3FE00C00, 0x38000C00)
+__AARCH64_INSN_FUNCS(load_pre,	0x3FE00C00, 0x38400C00)
+__AARCH64_INSN_FUNCS(store_post,	0x3FE00C00, 0x38000400)
+__AARCH64_INSN_FUNCS(load_post,	0x3FE00C00, 0x38400400)
+__AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
+__AARCH64_INSN_FUNCS(str_imm,	0x3FC00000, 0x39000000)
+__AARCH64_INSN_FUNCS(ldadd,	0x3F20FC00, 0x38200000)
+__AARCH64_INSN_FUNCS(ldclr,	0x3F20FC00, 0x38201000)
+__AARCH64_INSN_FUNCS(ldeor,	0x3F20FC00, 0x38202000)
+__AARCH64_INSN_FUNCS(ldset,	0x3F20FC00, 0x38203000)
+__AARCH64_INSN_FUNCS(swp,	0x3F20FC00, 0x38208000)
+__AARCH64_INSN_FUNCS(cas,	0x3FA07C00, 0x08A07C00)
+__AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
+__AARCH64_INSN_FUNCS(ldr_imm,	0x3FC00000, 0x39400000)
+__AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
+__AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
+__AARCH64_INSN_FUNCS(exclusive,	0x3F800000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_ex,	0x3F400000, 0x08400000)
+__AARCH64_INSN_FUNCS(store_ex,	0x3F400000, 0x08000000)
+__AARCH64_INSN_FUNCS(stp,	0x7FC00000, 0x29000000)
+__AARCH64_INSN_FUNCS(ldp,	0x7FC00000, 0x29400000)
+__AARCH64_INSN_FUNCS(stp_post,	0x7FC00000, 0x28800000)
+__AARCH64_INSN_FUNCS(ldp_post,	0x7FC00000, 0x28C00000)
+__AARCH64_INSN_FUNCS(stp_pre,	0x7FC00000, 0x29800000)
+__AARCH64_INSN_FUNCS(ldp_pre,	0x7FC00000, 0x29C00000)
+__AARCH64_INSN_FUNCS(add_imm,	0x7F000000, 0x11000000)
+__AARCH64_INSN_FUNCS(adds_imm,	0x7F000000, 0x31000000)
+__AARCH64_INSN_FUNCS(sub_imm,	0x7F000000, 0x51000000)
+__AARCH64_INSN_FUNCS(subs_imm,	0x7F000000, 0x71000000)
+__AARCH64_INSN_FUNCS(movn,	0x7F800000, 0x12800000)
+__AARCH64_INSN_FUNCS(sbfm,	0x7F800000, 0x13000000)
+__AARCH64_INSN_FUNCS(bfm,	0x7F800000, 0x33000000)
+__AARCH64_INSN_FUNCS(movz,	0x7F800000, 0x52800000)
+__AARCH64_INSN_FUNCS(ubfm,	0x7F800000, 0x53000000)
+__AARCH64_INSN_FUNCS(movk,	0x7F800000, 0x72800000)
+__AARCH64_INSN_FUNCS(add,	0x7F200000, 0x0B000000)
+__AARCH64_INSN_FUNCS(adds,	0x7F200000, 0x2B000000)
+__AARCH64_INSN_FUNCS(sub,	0x7F200000, 0x4B000000)
+__AARCH64_INSN_FUNCS(subs,	0x7F200000, 0x6B000000)
+__AARCH64_INSN_FUNCS(madd,	0x7FE08000, 0x1B000000)
+__AARCH64_INSN_FUNCS(msub,	0x7FE08000, 0x1B008000)
+__AARCH64_INSN_FUNCS(udiv,	0x7FE0FC00, 0x1AC00800)
+__AARCH64_INSN_FUNCS(sdiv,	0x7FE0FC00, 0x1AC00C00)
+__AARCH64_INSN_FUNCS(lslv,	0x7FE0FC00, 0x1AC02000)
+__AARCH64_INSN_FUNCS(lsrv,	0x7FE0FC00, 0x1AC02400)
+__AARCH64_INSN_FUNCS(asrv,	0x7FE0FC00, 0x1AC02800)
+__AARCH64_INSN_FUNCS(rorv,	0x7FE0FC00, 0x1AC02C00)
+__AARCH64_INSN_FUNCS(rev16,	0x7FFFFC00, 0x5AC00400)
+__AARCH64_INSN_FUNCS(rev32,	0x7FFFFC00, 0x5AC00800)
+__AARCH64_INSN_FUNCS(rev64,	0x7FFFFC00, 0x5AC00C00)
+__AARCH64_INSN_FUNCS(and,	0x7F200000, 0x0A000000)
+__AARCH64_INSN_FUNCS(bic,	0x7F200000, 0x0A200000)
+__AARCH64_INSN_FUNCS(orr,	0x7F200000, 0x2A000000)
+__AARCH64_INSN_FUNCS(mov_reg,	0x7FE0FFE0, 0x2A0003E0)
+__AARCH64_INSN_FUNCS(orn,	0x7F200000, 0x2A200000)
+__AARCH64_INSN_FUNCS(eor,	0x7F200000, 0x4A000000)
+__AARCH64_INSN_FUNCS(eon,	0x7F200000, 0x4A200000)
+__AARCH64_INSN_FUNCS(ands,	0x7F200000, 0x6A000000)
+__AARCH64_INSN_FUNCS(bics,	0x7F200000, 0x6A200000)
+__AARCH64_INSN_FUNCS(and_imm,	0x7F800000, 0x12000000)
+__AARCH64_INSN_FUNCS(orr_imm,	0x7F800000, 0x32000000)
+__AARCH64_INSN_FUNCS(eor_imm,	0x7F800000, 0x52000000)
+__AARCH64_INSN_FUNCS(ands_imm,	0x7F800000, 0x72000000)
+__AARCH64_INSN_FUNCS(extr,	0x7FA00000, 0x13800000)
+__AARCH64_INSN_FUNCS(b,		0xFC000000, 0x14000000)
+__AARCH64_INSN_FUNCS(bl,	0xFC000000, 0x94000000)
+__AARCH64_INSN_FUNCS(cbz,	0x7F000000, 0x34000000)
+__AARCH64_INSN_FUNCS(cbnz,	0x7F000000, 0x35000000)
+__AARCH64_INSN_FUNCS(tbz,	0x7F000000, 0x36000000)
+__AARCH64_INSN_FUNCS(tbnz,	0x7F000000, 0x37000000)
+__AARCH64_INSN_FUNCS(bcond,	0xFF000010, 0x54000000)
+__AARCH64_INSN_FUNCS(svc,	0xFFE0001F, 0xD4000001)
+__AARCH64_INSN_FUNCS(hvc,	0xFFE0001F, 0xD4000002)
+__AARCH64_INSN_FUNCS(smc,	0xFFE0001F, 0xD4000003)
+__AARCH64_INSN_FUNCS(brk,	0xFFE0001F, 0xD4200000)
+__AARCH64_INSN_FUNCS(exception,	0xFF000000, 0xD4000000)
+__AARCH64_INSN_FUNCS(hint,	0xFFFFF01F, 0xD503201F)
+__AARCH64_INSN_FUNCS(br,	0xFFFFFC1F, 0xD61F0000)
+__AARCH64_INSN_FUNCS(br_auth,	0xFEFFF800, 0xD61F0800)
+__AARCH64_INSN_FUNCS(blr,	0xFFFFFC1F, 0xD63F0000)
+__AARCH64_INSN_FUNCS(blr_auth,	0xFEFFF800, 0xD63F0800)
+__AARCH64_INSN_FUNCS(ret,	0xFFFFFC1F, 0xD65F0000)
+__AARCH64_INSN_FUNCS(ret_auth,	0xFFFFFBFF, 0xD65F0BFF)
+__AARCH64_INSN_FUNCS(eret,	0xFFFFFFFF, 0xD69F03E0)
+__AARCH64_INSN_FUNCS(eret_auth,	0xFFFFFBFF, 0xD69F0BFF)
+__AARCH64_INSN_FUNCS(mrs,	0xFFF00000, 0xD5300000)
+__AARCH64_INSN_FUNCS(msr_imm,	0xFFF8F01F, 0xD500401F)
+__AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
+__AARCH64_INSN_FUNCS(dmb,	0xFFFFF0FF, 0xD50330BF)
+__AARCH64_INSN_FUNCS(dsb_base,	0xFFFFF0FF, 0xD503309F)
+__AARCH64_INSN_FUNCS(dsb_nxs,	0xFFFFF3FF, 0xD503323F)
+__AARCH64_INSN_FUNCS(isb,	0xFFFFF0FF, 0xD50330DF)
+__AARCH64_INSN_FUNCS(sb,	0xFFFFFFFF, 0xD50330FF)
+__AARCH64_INSN_FUNCS(clrex,	0xFFFFF0FF, 0xD503305F)
+__AARCH64_INSN_FUNCS(ssbb,	0xFFFFFFFF, 0xD503309F)
+__AARCH64_INSN_FUNCS(pssbb,	0xFFFFFFFF, 0xD503349F)
+
+#undef	__AARCH64_INSN_FUNCS
+
+bool aarch64_insn_is_steppable_hint(u32 insn);
+bool aarch64_insn_is_branch_imm(u32 insn);
+
+static inline bool aarch64_insn_is_adr_adrp(u32 insn)
+{
+	return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
+}
+
+static inline bool aarch64_insn_is_dsb(u32 insn)
+{
+	return aarch64_insn_is_dsb_base(insn) || aarch64_insn_is_dsb_nxs(insn);
+}
+
+static inline bool aarch64_insn_is_barrier(u32 insn)
+{
+	return aarch64_insn_is_dmb(insn) || aarch64_insn_is_dsb(insn) ||
+	       aarch64_insn_is_isb(insn) || aarch64_insn_is_sb(insn) ||
+	       aarch64_insn_is_clrex(insn) || aarch64_insn_is_ssbb(insn) ||
+	       aarch64_insn_is_pssbb(insn);
+}
+
+static inline bool aarch64_insn_is_store_single(u32 insn)
+{
+	return aarch64_insn_is_store_imm(insn) ||
+	       aarch64_insn_is_store_pre(insn) ||
+	       aarch64_insn_is_store_post(insn);
+}
+
+static inline bool aarch64_insn_is_store_pair(u32 insn)
+{
+	return aarch64_insn_is_stp(insn) ||
+	       aarch64_insn_is_stp_pre(insn) ||
+	       aarch64_insn_is_stp_post(insn);
+}
+
+static inline bool aarch64_insn_is_load_single(u32 insn)
+{
+	return aarch64_insn_is_load_imm(insn) ||
+	       aarch64_insn_is_load_pre(insn) ||
+	       aarch64_insn_is_load_post(insn);
+}
+
+static inline bool aarch64_insn_is_load_pair(u32 insn)
+{
+	return aarch64_insn_is_ldp(insn) ||
+	       aarch64_insn_is_ldp_pre(insn) ||
+	       aarch64_insn_is_ldp_post(insn);
+}
+
+enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
+bool aarch64_insn_uses_literal(u32 insn);
+bool aarch64_insn_is_branch(u32 insn);
+u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn);
+u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
+				  u32 insn, u64 imm);
+u32 aarch64_insn_decode_register(enum aarch64_insn_register_type type,
+					 u32 insn);
+u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+				enum aarch64_insn_branch_type type);
+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 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
+				     enum aarch64_insn_condition cond);
+u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op);
+u32 aarch64_insn_gen_nop(void);
+u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
+				enum aarch64_insn_branch_type type);
+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 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 aarch64_insn_gen_load_literal(unsigned long pc, unsigned long addr,
+				  enum aarch64_insn_register reg,
+				  bool is64bit);
+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 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 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 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr,
+			 enum aarch64_insn_register reg,
+			 enum aarch64_insn_adr_type type);
+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 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 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 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 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 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 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 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst,
+			      enum aarch64_insn_register src,
+			      enum aarch64_insn_variant variant);
+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 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 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
+			      enum aarch64_insn_prfm_type type,
+			      enum aarch64_insn_prfm_target target,
+			      enum aarch64_insn_prfm_policy policy);
+#ifdef CONFIG_ARM64_LSE_ATOMICS
+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 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);
+#else
+static inline
+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)
+{
+	return AARCH64_BREAK_FAULT;
+}
+
+static inline
+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)
+{
+	return AARCH64_BREAK_FAULT;
+}
+#endif
+u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type);
+
+s32 aarch64_get_branch_offset(u32 insn);
+u32 aarch64_set_branch_offset(u32 insn, s32 offset);
+
+s32 aarch64_insn_adrp_get_offset(u32 insn);
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset);
+
+bool aarch32_insn_is_wide(u32 insn);
+
+#define A32_RN_OFFSET	16
+#define A32_RT_OFFSET	12
+#define A32_RT2_OFFSET	 0
+
+u32 aarch64_insn_extract_system_reg(u32 insn);
+u32 aarch32_insn_extract_reg_num(u32 insn, int offset);
+u32 aarch32_insn_mcr_extract_opc2(u32 insn);
+u32 aarch32_insn_mcr_extract_crm(u32 insn);
+
+typedef bool (pstate_check_t)(unsigned long);
+extern pstate_check_t * const aarch32_opcode_cond_checks[16];
+
+#endif /* __ASSEMBLY__ */
+
+#endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
new file mode 100644
index 000000000..877495a0f
--- /dev/null
+++ b/arch/arm64/include/asm/io.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/io.h
+ *
+ * Copyright (C) 1996-2000 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_IO_H
+#define __ASM_IO_H
+
+#include <linux/types.h>
+#include <linux/pgtable.h>
+
+#include <asm/byteorder.h>
+#include <asm/barrier.h>
+#include <asm/memory.h>
+#include <asm/early_ioremap.h>
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Generic IO read/write.  These perform native-endian accesses.
+ */
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+{
+	asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+{
+	asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+#define __raw_writel __raw_writel
+static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr)
+{
+	asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
+{
+	asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+#define __raw_readb __raw_readb
+static inline u8 __raw_readb(const volatile void __iomem *addr)
+{
+	u8 val;
+	asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
+				 "ldarb %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
+	return val;
+}
+
+#define __raw_readw __raw_readw
+static inline u16 __raw_readw(const volatile void __iomem *addr)
+{
+	u16 val;
+
+	asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
+				 "ldarh %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
+	return val;
+}
+
+#define __raw_readl __raw_readl
+static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
+{
+	u32 val;
+	asm volatile(ALTERNATIVE("ldr %w0, [%1]",
+				 "ldar %w0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
+	return val;
+}
+
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
+{
+	u64 val;
+	asm volatile(ALTERNATIVE("ldr %0, [%1]",
+				 "ldar %0, [%1]",
+				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
+		     : "=r" (val) : "r" (addr));
+	return val;
+}
+
+/* IO barriers */
+#define __io_ar(v)							\
+({									\
+	unsigned long tmp;						\
+									\
+	dma_rmb();								\
+									\
+	/*								\
+	 * Create a dummy control dependency from the IO read to any	\
+	 * later instructions. This ensures that a subsequent call to	\
+	 * udelay() will be ordered due to the ISB in get_cycles().	\
+	 */								\
+	asm volatile("eor	%0, %1, %1\n"				\
+		     "cbnz	%0, ."					\
+		     : "=r" (tmp) : "r" ((unsigned long)(v))		\
+		     : "memory");					\
+})
+
+#define __io_bw()		dma_wmb()
+#define __io_br(v)
+#define __io_aw(v)
+
+/* arm64-specific, don't use in portable drivers */
+#define __iormb(v)		__io_ar(v)
+#define __iowmb()		__io_bw()
+#define __iomb()		dma_mb()
+
+/*
+ *  I/O port access primitives.
+ */
+#define arch_has_dev_port()	(1)
+#define IO_SPACE_LIMIT		(PCI_IO_SIZE - 1)
+#define PCI_IOBASE		((void __iomem *)PCI_IO_START)
+
+/*
+ * String version of I/O memory access operations.
+ */
+extern void __memcpy_fromio(void *, const volatile void __iomem *, size_t);
+extern void __memcpy_toio(volatile void __iomem *, const void *, size_t);
+extern void __memset_io(volatile void __iomem *, int, size_t);
+
+#define memset_io(c,v,l)	__memset_io((c),(v),(l))
+#define memcpy_fromio(a,c,l)	__memcpy_fromio((a),(c),(l))
+#define memcpy_toio(c,a,l)	__memcpy_toio((c),(a),(l))
+
+/*
+ * I/O memory mapping functions.
+ */
+
+bool ioremap_allowed(phys_addr_t phys_addr, size_t size, unsigned long prot);
+#define ioremap_allowed ioremap_allowed
+
+#define _PAGE_IOREMAP PROT_DEVICE_nGnRE
+
+#define ioremap_wc(addr, size)	\
+	ioremap_prot((addr), (size), PROT_NORMAL_NC)
+#define ioremap_np(addr, size)	\
+	ioremap_prot((addr), (size), PROT_DEVICE_nGnRnE)
+
+/*
+ * io{read,write}{16,32,64}be() macros
+ */
+#define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(__v); __v; })
+#define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(__v); __v; })
+#define ioread64be(p)		({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(__v); __v; })
+
+#define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
+#define iowrite64be(v,p)	({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
+
+#include <asm-generic/io.h>
+
+#define ioremap_cache ioremap_cache
+static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size)
+{
+	if (pfn_is_map_memory(__phys_to_pfn(addr)))
+		return (void __iomem *)__phys_to_virt(addr);
+
+	return ioremap_prot(addr, size, PROT_NORMAL);
+}
+
+/*
+ * More restrictive address range checking than the default implementation
+ * (PHYS_OFFSET and PHYS_MASK taken into account).
+ */
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
+extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
+					unsigned long flags);
+#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap
+
+#endif	/* __ASM_IO_H */
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
new file mode 100644
index 000000000..fac08e18b
--- /dev/null
+++ b/arch/arm64/include/asm/irq.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_IRQ_H
+#define __ASM_IRQ_H
+
+#ifndef __ASSEMBLER__
+
+#include <asm-generic/irq.h>
+
+struct pt_regs;
+
+int set_handle_irq(void (*handle_irq)(struct pt_regs *));
+#define set_handle_irq	set_handle_irq
+int set_handle_fiq(void (*handle_fiq)(struct pt_regs *));
+
+static inline int nr_legacy_irqs(void)
+{
+	return 0;
+}
+
+#endif /* !__ASSEMBLER__ */
+#endif
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
new file mode 100644
index 000000000..81bbfa3a0
--- /dev/null
+++ b/arch/arm64/include/asm/irq_work.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+extern void arch_irq_work_raise(void);
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return true;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
new file mode 100644
index 000000000..b57b9b1e4
--- /dev/null
+++ b/arch/arm64/include/asm/irqflags.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_IRQFLAGS_H
+#define __ASM_IRQFLAGS_H
+
+#include <asm/alternative.h>
+#include <asm/barrier.h>
+#include <asm/ptrace.h>
+#include <asm/sysreg.h>
+
+/*
+ * Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and
+ * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'daif'
+ * order:
+ * Masking debug exceptions causes all other exceptions to be masked too/
+ * Masking SError masks IRQ/FIQ, but not debug exceptions. IRQ and FIQ are
+ * always masked and unmasked together, and have no side effects for other
+ * flags. Keeping to this order makes it easier for entry.S to know which
+ * exceptions should be unmasked.
+ */
+
+/*
+ * CPU interrupt mask handling.
+ */
+static inline void arch_local_irq_enable(void)
+{
+	if (system_has_prio_mask_debugging()) {
+		u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
+
+		WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
+	}
+
+	asm volatile(ALTERNATIVE(
+		"msr	daifclr, #3		// arch_local_irq_enable",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		:
+		: "r" ((unsigned long) GIC_PRIO_IRQON)
+		: "memory");
+
+	pmr_sync();
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	if (system_has_prio_mask_debugging()) {
+		u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1);
+
+		WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF);
+	}
+
+	asm volatile(ALTERNATIVE(
+		"msr	daifset, #3		// arch_local_irq_disable",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		:
+		: "r" ((unsigned long) GIC_PRIO_IRQOFF)
+		: "memory");
+}
+
+/*
+ * Save the current interrupt enable state.
+ */
+static inline unsigned long arch_local_save_flags(void)
+{
+	unsigned long flags;
+
+	asm volatile(ALTERNATIVE(
+		"mrs	%0, daif",
+		__mrs_s("%0", SYS_ICC_PMR_EL1),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		: "=&r" (flags)
+		:
+		: "memory");
+
+	return flags;
+}
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	int res;
+
+	asm volatile(ALTERNATIVE(
+		"and	%w0, %w1, #" __stringify(PSR_I_BIT),
+		"eor	%w0, %w1, #" __stringify(GIC_PRIO_IRQON),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		: "=&r" (res)
+		: "r" ((int) flags)
+		: "memory");
+
+	return res;
+}
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+	unsigned long flags;
+
+	flags = arch_local_save_flags();
+
+	/*
+	 * There are too many states with IRQs disabled, just keep the current
+	 * state if interrupts are already disabled/masked.
+	 */
+	if (!arch_irqs_disabled_flags(flags))
+		arch_local_irq_disable();
+
+	return flags;
+}
+
+/*
+ * restore saved IRQ state
+ */
+static inline void arch_local_irq_restore(unsigned long flags)
+{
+	asm volatile(ALTERNATIVE(
+		"msr	daif, %0",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
+		ARM64_HAS_IRQ_PRIO_MASKING)
+		:
+		: "r" (flags)
+		: "memory");
+
+	pmr_sync();
+}
+
+#endif /* __ASM_IRQFLAGS_H */
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
new file mode 100644
index 000000000..cea441b6a
--- /dev/null
+++ b/arch/arm64/include/asm/jump_label.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Based on arch/arm/include/asm/jump_label.h
+ */
+#ifndef __ASM_JUMP_LABEL_H
+#define __ASM_JUMP_LABEL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/insn.h>
+
+#define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
+
+static __always_inline bool arch_static_branch(struct static_key *key,
+					       bool branch)
+{
+	asm_volatile_goto(
+		"1:	nop					\n\t"
+		 "	.pushsection	__jump_table, \"aw\"	\n\t"
+		 "	.align		3			\n\t"
+		 "	.long		1b - ., %l[l_yes] - .	\n\t"
+		 "	.quad		%c0 - .			\n\t"
+		 "	.popsection				\n\t"
+		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+						    bool branch)
+{
+	asm_volatile_goto(
+		"1:	b		%l[l_yes]		\n\t"
+		 "	.pushsection	__jump_table, \"aw\"	\n\t"
+		 "	.align		3			\n\t"
+		 "	.long		1b - ., %l[l_yes] - .	\n\t"
+		 "	.quad		%c0 - .			\n\t"
+		 "	.popsection				\n\t"
+		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+#endif  /* __ASSEMBLY__ */
+#endif	/* __ASM_JUMP_LABEL_H */
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
new file mode 100644
index 000000000..12d5f47f7
--- /dev/null
+++ b/arch/arm64/include/asm/kasan.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <asm/memory.h>
+#include <asm/mte-kasan.h>
+#include <asm/pgtable-types.h>
+
+#define arch_kasan_set_tag(addr, tag)	__tag_set(addr, tag)
+#define arch_kasan_reset_tag(addr)	__tag_reset(addr)
+#define arch_kasan_get_tag(addr)	__tag_get(addr)
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
+void kasan_init(void);
+
+/*
+ * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
+ * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses,
+ * where N = (1 << KASAN_SHADOW_SCALE_SHIFT).
+ *
+ * KASAN_SHADOW_OFFSET:
+ * This value is used to map an address to the corresponding shadow
+ * address by the following formula:
+ *     shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET
+ *
+ * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range
+ * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual
+ * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation:
+ *      KASAN_SHADOW_OFFSET = KASAN_SHADOW_END -
+ *				(1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT))
+ */
+#define _KASAN_SHADOW_START(va)	(KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_START      _KASAN_SHADOW_START(vabits_actual)
+
+void kasan_copy_shadow(pgd_t *pgdir);
+asmlinkage void kasan_early_init(void);
+
+#else
+static inline void kasan_init(void) { }
+static inline void kasan_copy_shadow(pgd_t *pgdir) { }
+#endif
+
+#endif
+#endif
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
new file mode 100644
index 000000000..32d14f481
--- /dev/null
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Kernel page table mapping
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ */
+
+#ifndef __ASM_KERNEL_PGTABLE_H
+#define __ASM_KERNEL_PGTABLE_H
+
+#include <asm/boot.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/sparsemem.h>
+
+/*
+ * The linear mapping and the start of memory are both 2M aligned (per
+ * the arm64 booting.txt requirements). Hence we can use section mapping
+ * with 4K (section size = 2M) but not with 16K (section size = 32M) or
+ * 64K (section size = 512M).
+ */
+#ifdef CONFIG_ARM64_4K_PAGES
+#define ARM64_KERNEL_USES_PMD_MAPS 1
+#else
+#define ARM64_KERNEL_USES_PMD_MAPS 0
+#endif
+
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. Both require pgd, pud (4 levels only) and pmd tables to (section)
+ * map the kernel. With the 64K page configuration, swapper and idmap need to
+ * map to pte level. The swapper also maps the FDT (see __create_page_tables
+ * for more information). Note that the number of ID map translation levels
+ * could be increased on the fly if system RAM is out of reach for the default
+ * VA range, so pages required to map highest possible PA are reserved in all
+ * cases.
+ */
+#if ARM64_KERNEL_USES_PMD_MAPS
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS - 1)
+#else
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS)
+#endif
+
+
+/*
+ * If KASLR is enabled, then an offset K is added to the kernel address
+ * space. The bottom 21 bits of this offset are zero to guarantee 2MB
+ * alignment for PA and VA.
+ *
+ * For each pagetable level of the swapper, we know that the shift will
+ * be larger than 21 (for the 4KB granule case we use section maps thus
+ * the smallest shift is actually 30) thus there is the possibility that
+ * KASLR can increase the number of pagetable entries by 1, so we make
+ * room for this extra entry.
+ *
+ * Note KASLR cannot increase the number of required entries for a level
+ * by more than one because it increments both the virtual start and end
+ * addresses equally (the extra entry comes from the case where the end
+ * address is just pushed over a boundary and the start address isn't).
+ */
+
+#ifdef CONFIG_RANDOMIZE_BASE
+#define EARLY_KASLR	(1)
+#else
+#define EARLY_KASLR	(0)
+#endif
+
+#define EARLY_ENTRIES(vstart, vend, shift, add) \
+	((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1 + add)
+
+#define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add))
+
+#if SWAPPER_PGTABLE_LEVELS > 3
+#define EARLY_PUDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT, add))
+#else
+#define EARLY_PUDS(vstart, vend, add) (0)
+#endif
+
+#if SWAPPER_PGTABLE_LEVELS > 2
+#define EARLY_PMDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT, add))
+#else
+#define EARLY_PMDS(vstart, vend, add) (0)
+#endif
+
+#define EARLY_PAGES(vstart, vend, add) ( 1 			/* PGDIR page */				\
+			+ EARLY_PGDS((vstart), (vend), add) 	/* each PGDIR needs a next level page table */	\
+			+ EARLY_PUDS((vstart), (vend), add)	/* each PUD needs a next level page table */	\
+			+ EARLY_PMDS((vstart), (vend), add))	/* each PMD needs a next level page table */
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EARLY_KASLR))
+
+/* the initial ID map may need two extra pages if it needs to be extended */
+#if VA_BITS < 48
+#define INIT_IDMAP_DIR_SIZE	((INIT_IDMAP_DIR_PAGES + 2) * PAGE_SIZE)
+#else
+#define INIT_IDMAP_DIR_SIZE	(INIT_IDMAP_DIR_PAGES * PAGE_SIZE)
+#endif
+#define INIT_IDMAP_DIR_PAGES	EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1)
+
+/* Initial memory map size */
+#if ARM64_KERNEL_USES_PMD_MAPS
+#define SWAPPER_BLOCK_SHIFT	PMD_SHIFT
+#define SWAPPER_BLOCK_SIZE	PMD_SIZE
+#define SWAPPER_TABLE_SHIFT	PUD_SHIFT
+#else
+#define SWAPPER_BLOCK_SHIFT	PAGE_SHIFT
+#define SWAPPER_BLOCK_SIZE	PAGE_SIZE
+#define SWAPPER_TABLE_SHIFT	PMD_SHIFT
+#endif
+
+/*
+ * Initial memory map attributes.
+ */
+#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#if ARM64_KERNEL_USES_PMD_MAPS
+#define SWAPPER_RW_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
+#define SWAPPER_RX_MMUFLAGS	(SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY)
+#else
+#define SWAPPER_RW_MMUFLAGS	(PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS)
+#define SWAPPER_RX_MMUFLAGS	(SWAPPER_RW_MMUFLAGS | PTE_RDONLY)
+#endif
+
+/*
+ * To make optimal use of block mappings when laying out the linear
+ * mapping, round down the base of physical memory to a size that can
+ * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE
+ * (64k granule), or a multiple that can be mapped using contiguous bits
+ * in the page tables: 32 * PMD_SIZE (16k granule)
+ */
+#if defined(CONFIG_ARM64_4K_PAGES)
+#define ARM64_MEMSTART_SHIFT		PUD_SHIFT
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define ARM64_MEMSTART_SHIFT		CONT_PMD_SHIFT
+#else
+#define ARM64_MEMSTART_SHIFT		PMD_SHIFT
+#endif
+
+/*
+ * sparsemem vmemmap imposes an additional requirement on the alignment of
+ * memstart_addr, due to the fact that the base of the vmemmap region
+ * has a direct correspondence, and needs to appear sufficiently aligned
+ * in the virtual address space.
+ */
+#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS
+#define ARM64_MEMSTART_ALIGN	(1UL << SECTION_SIZE_BITS)
+#else
+#define ARM64_MEMSTART_ALIGN	(1UL << ARM64_MEMSTART_SHIFT)
+#endif
+
+#endif	/* __ASM_KERNEL_PGTABLE_H */
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
new file mode 100644
index 000000000..559bfae26
--- /dev/null
+++ b/arch/arm64/include/asm/kexec.h
@@ -0,0 +1,141 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ */
+
+#ifndef _ARM64_KEXEC_H
+#define _ARM64_KEXEC_H
+
+/* Maximum physical address we can use pages from */
+
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can reach in physical address mode */
+
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can use for the control code buffer */
+
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE 4096
+
+#define KEXEC_ARCH KEXEC_ARCH_AARCH64
+
+#ifndef __ASSEMBLY__
+
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ *
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	} else {
+		u64 tmp1, tmp2;
+
+		__asm__ __volatile__ (
+			"stp	 x0,   x1, [%2, #16 *  0]\n"
+			"stp	 x2,   x3, [%2, #16 *  1]\n"
+			"stp	 x4,   x5, [%2, #16 *  2]\n"
+			"stp	 x6,   x7, [%2, #16 *  3]\n"
+			"stp	 x8,   x9, [%2, #16 *  4]\n"
+			"stp	x10,  x11, [%2, #16 *  5]\n"
+			"stp	x12,  x13, [%2, #16 *  6]\n"
+			"stp	x14,  x15, [%2, #16 *  7]\n"
+			"stp	x16,  x17, [%2, #16 *  8]\n"
+			"stp	x18,  x19, [%2, #16 *  9]\n"
+			"stp	x20,  x21, [%2, #16 * 10]\n"
+			"stp	x22,  x23, [%2, #16 * 11]\n"
+			"stp	x24,  x25, [%2, #16 * 12]\n"
+			"stp	x26,  x27, [%2, #16 * 13]\n"
+			"stp	x28,  x29, [%2, #16 * 14]\n"
+			"mov	 %0,  sp\n"
+			"stp	x30,  %0,  [%2, #16 * 15]\n"
+
+			"/* faked current PSTATE */\n"
+			"mrs	 %0, CurrentEL\n"
+			"mrs	 %1, SPSEL\n"
+			"orr	 %0, %0, %1\n"
+			"mrs	 %1, DAIF\n"
+			"orr	 %0, %0, %1\n"
+			"mrs	 %1, NZCV\n"
+			"orr	 %0, %0, %1\n"
+			/* pc */
+			"adr	 %1, 1f\n"
+		"1:\n"
+			"stp	 %1, %0,   [%2, #16 * 16]\n"
+			: "=&r" (tmp1), "=&r" (tmp2)
+			: "r" (newregs)
+			: "memory"
+		);
+	}
+}
+
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION)
+extern bool crash_is_nosave(unsigned long pfn);
+extern void crash_prepare_suspend(void);
+extern void crash_post_resume(void);
+
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
+#define crash_free_reserved_phys_range crash_free_reserved_phys_range
+#else
+static inline bool crash_is_nosave(unsigned long pfn) {return false; }
+static inline void crash_prepare_suspend(void) {}
+static inline void crash_post_resume(void) {}
+#endif
+
+struct kimage;
+
+#if defined(CONFIG_KEXEC_CORE)
+void cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
+		      unsigned long arg0, unsigned long arg1,
+		      unsigned long arg2);
+
+int machine_kexec_post_load(struct kimage *image);
+#define machine_kexec_post_load machine_kexec_post_load
+
+void arch_kexec_protect_crashkres(void);
+#define arch_kexec_protect_crashkres arch_kexec_protect_crashkres
+
+void arch_kexec_unprotect_crashkres(void);
+#define arch_kexec_unprotect_crashkres arch_kexec_unprotect_crashkres
+#endif
+
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	void *dtb;
+	phys_addr_t dtb_mem;
+	phys_addr_t kern_reloc;
+	phys_addr_t el2_vectors;
+	phys_addr_t ttbr0;
+	phys_addr_t ttbr1;
+	phys_addr_t zero_page;
+	unsigned long phys_offset;
+	unsigned long t0sz;
+};
+
+#ifdef CONFIG_KEXEC_FILE
+extern const struct kexec_file_ops kexec_image_ops;
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image);
+#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
+
+extern int load_other_segments(struct kimage *image,
+		unsigned long kernel_load_addr, unsigned long kernel_size,
+		char *initrd, unsigned long initrd_len,
+		char *cmdline);
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm64/include/asm/kfence.h b/arch/arm64/include/asm/kfence.h
new file mode 100644
index 000000000..a81937fae
--- /dev/null
+++ b/arch/arm64/include/asm/kfence.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arm64 KFENCE support.
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef __ASM_KFENCE_H
+#define __ASM_KFENCE_H
+
+#include <asm/set_memory.h>
+
+static inline bool arch_kfence_init_pool(void) { return true; }
+
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	set_memory_valid(addr, 1, !protect);
+
+	return true;
+}
+
+#ifdef CONFIG_KFENCE
+extern bool kfence_early_init;
+static inline bool arm64_kfence_can_set_direct_map(void)
+{
+	return !kfence_early_init;
+}
+#else /* CONFIG_KFENCE */
+static inline bool arm64_kfence_can_set_direct_map(void) { return false; }
+#endif /* CONFIG_KFENCE */
+
+#endif /* __ASM_KFENCE_H */
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
new file mode 100644
index 000000000..21fc85e9d
--- /dev/null
+++ b/arch/arm64/include/asm/kgdb.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/include/kgdb.h
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ */
+
+#ifndef __ARM_KGDB_H
+#define __ARM_KGDB_H
+
+#include <linux/ptrace.h>
+#include <asm/debug-monitors.h>
+
+#ifndef	__ASSEMBLY__
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm ("brk %0" : : "I" (KGDB_COMPILED_DBG_BRK_IMM));
+}
+
+extern void kgdb_handle_bus_error(void);
+extern int kgdb_fault_expected;
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
+ *
+ * General purpose regs:
+ *     r0-r30: 64 bit
+ *     sp,pc : 64 bit
+ *     pstate  : 32 bit
+ *     Total: 33 + 1
+ * FPU regs:
+ *     f0-f31: 128 bit
+ *     fpsr & fpcr: 32 bit
+ *     Total: 32 + 2
+ *
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
+ */
+
+#define _GP_REGS		33
+#define _FP_REGS		32
+#define _EXTRA_REGS		3
+/*
+ * general purpose registers size in bytes.
+ * pstate is only 4 bytes. subtract 4 bytes
+ */
+#define GP_REG_BYTES		(_GP_REGS * 8)
+#define DBG_MAX_REG_NUM		(_GP_REGS + _FP_REGS + _EXTRA_REGS)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+
+#define BUFMAX			2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * _GP_REGS: 8 bytes, _FP_REGS: 16 bytes and _EXTRA_REGS: 4 bytes each
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+
+#define NUMREGBYTES	((_GP_REGS * 8) + (_FP_REGS * 16) + \
+			(_EXTRA_REGS * 4))
+
+#endif /* __ASM_KGDB_H */
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
new file mode 100644
index 000000000..05cd82eec
--- /dev/null
+++ b/arch/arm64/include/asm/kprobes.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ */
+
+#ifndef _ARM_KPROBES_H
+#define _ARM_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#ifdef CONFIG_KPROBES
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			2
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	unsigned long saved_irqflag;
+	struct prev_kprobe prev_kprobe;
+};
+
+void arch_remove_kprobe(struct kprobe *);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+void __kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* CONFIG_KPROBES */
+#endif /* _ARM_KPROBES_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
new file mode 100644
index 000000000..8aa8492da
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -0,0 +1,364 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_ARM_H__
+#define __ARM64_KVM_ARM_H__
+
+#include <asm/esr.h>
+#include <asm/memory.h>
+#include <asm/types.h>
+
+/* Hyp Configuration Register (HCR) bits */
+
+#define HCR_TID5	(UL(1) << 58)
+#define HCR_DCT		(UL(1) << 57)
+#define HCR_ATA_SHIFT	56
+#define HCR_ATA		(UL(1) << HCR_ATA_SHIFT)
+#define HCR_AMVOFFEN	(UL(1) << 51)
+#define HCR_FIEN	(UL(1) << 47)
+#define HCR_FWB		(UL(1) << 46)
+#define HCR_API		(UL(1) << 41)
+#define HCR_APK		(UL(1) << 40)
+#define HCR_TEA		(UL(1) << 37)
+#define HCR_TERR	(UL(1) << 36)
+#define HCR_TLOR	(UL(1) << 35)
+#define HCR_E2H		(UL(1) << 34)
+#define HCR_ID		(UL(1) << 33)
+#define HCR_CD		(UL(1) << 32)
+#define HCR_RW_SHIFT	31
+#define HCR_RW		(UL(1) << HCR_RW_SHIFT)
+#define HCR_TRVM	(UL(1) << 30)
+#define HCR_HCD		(UL(1) << 29)
+#define HCR_TDZ		(UL(1) << 28)
+#define HCR_TGE		(UL(1) << 27)
+#define HCR_TVM		(UL(1) << 26)
+#define HCR_TTLB	(UL(1) << 25)
+#define HCR_TPU		(UL(1) << 24)
+#define HCR_TPC		(UL(1) << 23) /* HCR_TPCP if FEAT_DPB */
+#define HCR_TSW		(UL(1) << 22)
+#define HCR_TACR	(UL(1) << 21)
+#define HCR_TIDCP	(UL(1) << 20)
+#define HCR_TSC		(UL(1) << 19)
+#define HCR_TID3	(UL(1) << 18)
+#define HCR_TID2	(UL(1) << 17)
+#define HCR_TID1	(UL(1) << 16)
+#define HCR_TID0	(UL(1) << 15)
+#define HCR_TWE		(UL(1) << 14)
+#define HCR_TWI		(UL(1) << 13)
+#define HCR_DC		(UL(1) << 12)
+#define HCR_BSU		(3 << 10)
+#define HCR_BSU_IS	(UL(1) << 10)
+#define HCR_FB		(UL(1) << 9)
+#define HCR_VSE		(UL(1) << 8)
+#define HCR_VI		(UL(1) << 7)
+#define HCR_VF		(UL(1) << 6)
+#define HCR_AMO		(UL(1) << 5)
+#define HCR_IMO		(UL(1) << 4)
+#define HCR_FMO		(UL(1) << 3)
+#define HCR_PTW		(UL(1) << 2)
+#define HCR_SWIO	(UL(1) << 1)
+#define HCR_VM		(UL(1) << 0)
+#define HCR_RES0	((UL(1) << 48) | (UL(1) << 39))
+
+/*
+ * The bits we set in HCR:
+ * TLOR:	Trap LORegion register accesses
+ * RW:		64bit by default, can be overridden for 32bit VMs
+ * TACR:	Trap ACTLR
+ * TSC:		Trap SMC
+ * TSW:		Trap cache operations by set/way
+ * TWE:		Trap WFE
+ * TWI:		Trap WFI
+ * TIDCP:	Trap L2CTLR/L2ECTLR
+ * BSU_IS:	Upgrade barriers to the inner shareable domain
+ * FB:		Force broadcast of all maintenance operations
+ * AMO:		Override CPSR.A and enable signaling with VA
+ * IMO:		Override CPSR.I and enable signaling with VI
+ * FMO:		Override CPSR.F and enable signaling with VF
+ * SWIO:	Turn set/way invalidates into set/way clean+invalidate
+ * PTW:		Take a stage2 fault if a stage1 walk steps in device memory
+ * TID3:	Trap EL1 reads of group 3 ID registers
+ */
+#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
+			 HCR_BSU_IS | HCR_FB | HCR_TACR | \
+			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
+			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 )
+#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
+#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
+#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
+
+/* TCR_EL2 Registers bits */
+#define TCR_EL2_RES1		((1U << 31) | (1 << 23))
+#define TCR_EL2_TBI		(1 << 20)
+#define TCR_EL2_PS_SHIFT	16
+#define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
+#define TCR_EL2_PS_40B		(2 << TCR_EL2_PS_SHIFT)
+#define TCR_EL2_TG0_MASK	TCR_TG0_MASK
+#define TCR_EL2_SH0_MASK	TCR_SH0_MASK
+#define TCR_EL2_ORGN0_MASK	TCR_ORGN0_MASK
+#define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
+#define TCR_EL2_T0SZ_MASK	0x3f
+#define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
+
+/* VTCR_EL2 Registers bits */
+#define VTCR_EL2_RES1		(1U << 31)
+#define VTCR_EL2_HD		(1 << 22)
+#define VTCR_EL2_HA		(1 << 21)
+#define VTCR_EL2_PS_SHIFT	TCR_EL2_PS_SHIFT
+#define VTCR_EL2_PS_MASK	TCR_EL2_PS_MASK
+#define VTCR_EL2_TG0_MASK	TCR_TG0_MASK
+#define VTCR_EL2_TG0_4K		TCR_TG0_4K
+#define VTCR_EL2_TG0_16K	TCR_TG0_16K
+#define VTCR_EL2_TG0_64K	TCR_TG0_64K
+#define VTCR_EL2_SH0_MASK	TCR_SH0_MASK
+#define VTCR_EL2_SH0_INNER	TCR_SH0_INNER
+#define VTCR_EL2_ORGN0_MASK	TCR_ORGN0_MASK
+#define VTCR_EL2_ORGN0_WBWA	TCR_ORGN0_WBWA
+#define VTCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
+#define VTCR_EL2_IRGN0_WBWA	TCR_IRGN0_WBWA
+#define VTCR_EL2_SL0_SHIFT	6
+#define VTCR_EL2_SL0_MASK	(3 << VTCR_EL2_SL0_SHIFT)
+#define VTCR_EL2_T0SZ_MASK	0x3f
+#define VTCR_EL2_VS_SHIFT	19
+#define VTCR_EL2_VS_8BIT	(0 << VTCR_EL2_VS_SHIFT)
+#define VTCR_EL2_VS_16BIT	(1 << VTCR_EL2_VS_SHIFT)
+
+#define VTCR_EL2_T0SZ(x)	TCR_T0SZ(x)
+
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * The VTCR_EL2 is configured per VM and is initialised in kvm_arm_setup_stage2().
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together. With 16K pages, we concatenate 16 first level page tables.
+ *
+ */
+
+#define VTCR_EL2_COMMON_BITS	(VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
+				 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_RES1)
+
+/*
+ * VTCR_EL2:SL0 indicates the entry level for Stage2 translation.
+ * Interestingly, it depends on the page size.
+ * See D.10.2.121, VTCR_EL2, in ARM DDI 0487C.a
+ *
+ *	-----------------------------------------
+ *	| Entry level		|  4K  | 16K/64K |
+ *	------------------------------------------
+ *	| Level: 0		|  2   |   -     |
+ *	------------------------------------------
+ *	| Level: 1		|  1   |   2     |
+ *	------------------------------------------
+ *	| Level: 2		|  0   |   1     |
+ *	------------------------------------------
+ *	| Level: 3		|  -   |   0     |
+ *	------------------------------------------
+ *
+ * The table roughly translates to :
+ *
+ *	SL0(PAGE_SIZE, Entry_level) = TGRAN_SL0_BASE - Entry_Level
+ *
+ * Where TGRAN_SL0_BASE is a magic number depending on the page size:
+ * 	TGRAN_SL0_BASE(4K) = 2
+ *	TGRAN_SL0_BASE(16K) = 3
+ *	TGRAN_SL0_BASE(64K) = 3
+ * provided we take care of ruling out the unsupported cases and
+ * Entry_Level = 4 - Number_of_levels.
+ *
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+
+#define VTCR_EL2_TGRAN			VTCR_EL2_TG0_64K
+#define VTCR_EL2_TGRAN_SL0_BASE		3UL
+
+#elif defined(CONFIG_ARM64_16K_PAGES)
+
+#define VTCR_EL2_TGRAN			VTCR_EL2_TG0_16K
+#define VTCR_EL2_TGRAN_SL0_BASE		3UL
+
+#else	/* 4K */
+
+#define VTCR_EL2_TGRAN			VTCR_EL2_TG0_4K
+#define VTCR_EL2_TGRAN_SL0_BASE		2UL
+
+#endif
+
+#define VTCR_EL2_LVLS_TO_SL0(levels)	\
+	((VTCR_EL2_TGRAN_SL0_BASE - (4 - (levels))) << VTCR_EL2_SL0_SHIFT)
+#define VTCR_EL2_SL0_TO_LVLS(sl0)	\
+	((sl0) + 4 - VTCR_EL2_TGRAN_SL0_BASE)
+#define VTCR_EL2_LVLS(vtcr)		\
+	VTCR_EL2_SL0_TO_LVLS(((vtcr) & VTCR_EL2_SL0_MASK) >> VTCR_EL2_SL0_SHIFT)
+
+#define VTCR_EL2_FLAGS			(VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN)
+#define VTCR_EL2_IPA(vtcr)		(64 - ((vtcr) & VTCR_EL2_T0SZ_MASK))
+
+/*
+ * ARM VMSAv8-64 defines an algorithm for finding the translation table
+ * descriptors in section D4.2.8 in ARM DDI 0487C.a.
+ *
+ * The algorithm defines the expectations on the translation table
+ * addresses for each level, based on PAGE_SIZE, entry level
+ * and the translation table size (T0SZ). The variable "x" in the
+ * algorithm determines the alignment of a table base address at a given
+ * level and thus determines the alignment of VTTBR:BADDR for stage2
+ * page table entry level.
+ * Since the number of bits resolved at the entry level could vary
+ * depending on the T0SZ, the value of "x" is defined based on a
+ * Magic constant for a given PAGE_SIZE and Entry Level. The
+ * intermediate levels must be always aligned to the PAGE_SIZE (i.e,
+ * x = PAGE_SHIFT).
+ *
+ * The value of "x" for entry level is calculated as :
+ *    x = Magic_N - T0SZ
+ *
+ * where Magic_N is an integer depending on the page size and the entry
+ * level of the page table as below:
+ *
+ *	--------------------------------------------
+ *	| Entry level		|  4K    16K   64K |
+ *	--------------------------------------------
+ *	| Level: 0 (4 levels)	| 28   |  -  |  -  |
+ *	--------------------------------------------
+ *	| Level: 1 (3 levels)	| 37   | 31  | 25  |
+ *	--------------------------------------------
+ *	| Level: 2 (2 levels)	| 46   | 42  | 38  |
+ *	--------------------------------------------
+ *	| Level: 3 (1 level)	| -    | 53  | 51  |
+ *	--------------------------------------------
+ *
+ * We have a magic formula for the Magic_N below:
+ *
+ *  Magic_N(PAGE_SIZE, Level) = 64 - ((PAGE_SHIFT - 3) * Number_of_levels)
+ *
+ * where Number_of_levels = (4 - Level). We are only interested in the
+ * value for Entry_Level for the stage2 page table.
+ *
+ * So, given that T0SZ = (64 - IPA_SHIFT), we can compute 'x' as follows:
+ *
+ *	x = (64 - ((PAGE_SHIFT - 3) * Number_of_levels)) - (64 - IPA_SHIFT)
+ *	  = IPA_SHIFT - ((PAGE_SHIFT - 3) * Number of levels)
+ *
+ * Here is one way to explain the Magic Formula:
+ *
+ *  x = log2(Size_of_Entry_Level_Table)
+ *
+ * Since, we can resolve (PAGE_SHIFT - 3) bits at each level, and another
+ * PAGE_SHIFT bits in the PTE, we have :
+ *
+ *  Bits_Entry_level = IPA_SHIFT - ((PAGE_SHIFT - 3) * (n - 1) + PAGE_SHIFT)
+ *		     = IPA_SHIFT - (PAGE_SHIFT - 3) * n - 3
+ *  where n = number of levels, and since each pointer is 8bytes, we have:
+ *
+ *  x = Bits_Entry_Level + 3
+ *    = IPA_SHIFT - (PAGE_SHIFT - 3) * n
+ *
+ * The only constraint here is that, we have to find the number of page table
+ * levels for a given IPA size (which we do, see stage2_pt_levels())
+ */
+#define ARM64_VTTBR_X(ipa, levels)	((ipa) - ((levels) * (PAGE_SHIFT - 3)))
+
+#define VTTBR_CNP_BIT     (UL(1))
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
+
+/* Hyp System Trap Register */
+#define HSTR_EL2_T(x)	(1 << x)
+
+/* Hyp Coprocessor Trap Register Shifts */
+#define CPTR_EL2_TFP_SHIFT 10
+
+/* Hyp Coprocessor Trap Register */
+#define CPTR_EL2_TCPAC	(1U << 31)
+#define CPTR_EL2_TAM	(1 << 30)
+#define CPTR_EL2_TTA	(1 << 20)
+#define CPTR_EL2_TSM	(1 << 12)
+#define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
+#define CPTR_EL2_TZ	(1 << 8)
+#define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */
+#define CPTR_EL2_DEFAULT	CPTR_NVHE_EL2_RES1
+#define CPTR_NVHE_EL2_RES0	(GENMASK(63, 32) |	\
+				 GENMASK(29, 21) |	\
+				 GENMASK(19, 14) |	\
+				 BIT(11))
+
+/* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_E2TB_MASK	(UL(0x3))
+#define MDCR_EL2_E2TB_SHIFT	(UL(24))
+#define MDCR_EL2_HPMFZS		(UL(1) << 36)
+#define MDCR_EL2_HPMFZO		(UL(1) << 29)
+#define MDCR_EL2_MTPME		(UL(1) << 28)
+#define MDCR_EL2_TDCC		(UL(1) << 27)
+#define MDCR_EL2_HLP		(UL(1) << 26)
+#define MDCR_EL2_HCCD		(UL(1) << 23)
+#define MDCR_EL2_TTRF		(UL(1) << 19)
+#define MDCR_EL2_HPMD		(UL(1) << 17)
+#define MDCR_EL2_TPMS		(UL(1) << 14)
+#define MDCR_EL2_E2PB_MASK	(UL(0x3))
+#define MDCR_EL2_E2PB_SHIFT	(UL(12))
+#define MDCR_EL2_TDRA		(UL(1) << 11)
+#define MDCR_EL2_TDOSA		(UL(1) << 10)
+#define MDCR_EL2_TDA		(UL(1) << 9)
+#define MDCR_EL2_TDE		(UL(1) << 8)
+#define MDCR_EL2_HPME		(UL(1) << 7)
+#define MDCR_EL2_TPM		(UL(1) << 6)
+#define MDCR_EL2_TPMCR		(UL(1) << 5)
+#define MDCR_EL2_HPMN_MASK	(UL(0x1F))
+#define MDCR_EL2_RES0		(GENMASK(63, 37) |	\
+				 GENMASK(35, 30) |	\
+				 GENMASK(25, 24) |	\
+				 GENMASK(22, 20) |	\
+				 BIT(18) |		\
+				 GENMASK(16, 15))
+
+/* For compatibility with fault code shared with 32-bit */
+#define FSC_FAULT	ESR_ELx_FSC_FAULT
+#define FSC_ACCESS	ESR_ELx_FSC_ACCESS
+#define FSC_PERM	ESR_ELx_FSC_PERM
+#define FSC_SEA		ESR_ELx_FSC_EXTABT
+#define FSC_SEA_TTW0	(0x14)
+#define FSC_SEA_TTW1	(0x15)
+#define FSC_SEA_TTW2	(0x16)
+#define FSC_SEA_TTW3	(0x17)
+#define FSC_SECC	(0x18)
+#define FSC_SECC_TTW0	(0x1c)
+#define FSC_SECC_TTW1	(0x1d)
+#define FSC_SECC_TTW2	(0x1e)
+#define FSC_SECC_TTW3	(0x1f)
+
+/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
+#define HPFAR_MASK	(~UL(0xf))
+/*
+ * We have
+ *	PAR	[PA_Shift - 1	: 12] = PA	[PA_Shift - 1 : 12]
+ *	HPFAR	[PA_Shift - 9	: 4]  = FIPA	[PA_Shift - 1 : 12]
+ */
+#define PAR_TO_HPFAR(par)		\
+	(((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
+
+#define ECN(x) { ESR_ELx_EC_##x, #x }
+
+#define kvm_arm_exception_class \
+	ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \
+	ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \
+	ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \
+	ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \
+	ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \
+	ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
+	ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
+	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
+	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
+
+#define CPACR_EL1_TTA		(1 << 28)
+#define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\
+				 CPACR_EL1_ZEN_EL1EN)
+
+#endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
new file mode 100644
index 000000000..53035763e
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM_KVM_ASM_H__
+#define __ARM_KVM_ASM_H__
+
+#include <asm/hyp_image.h>
+#include <asm/insn.h>
+#include <asm/virt.h>
+
+#define ARM_EXIT_WITH_SERROR_BIT  31
+#define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
+#define ARM_EXCEPTION_IS_TRAP(x)  (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
+#define ARM_SERROR_PENDING(x)	  !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT))
+
+#define ARM_EXCEPTION_IRQ	  0
+#define ARM_EXCEPTION_EL1_SERROR  1
+#define ARM_EXCEPTION_TRAP	  2
+#define ARM_EXCEPTION_IL	  3
+/* The hyp-stub will return this for any kvm_call_hyp() call */
+#define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
+
+#define kvm_arm_exception_type					\
+	{ARM_EXCEPTION_IRQ,		"IRQ"		},	\
+	{ARM_EXCEPTION_EL1_SERROR, 	"SERROR"	},	\
+	{ARM_EXCEPTION_TRAP, 		"TRAP"		},	\
+	{ARM_EXCEPTION_HYP_GONE,	"HYP_GONE"	}
+
+/*
+ * Size of the HYP vectors preamble. kvm_patch_vector_branch() generates code
+ * that jumps over this.
+ */
+#define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
+
+#define KVM_HOST_SMCCC_ID(id)						\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   (id))
+
+#define KVM_HOST_SMCCC_FUNC(name) KVM_HOST_SMCCC_ID(__KVM_HOST_SMCCC_FUNC_##name)
+
+#define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init			0
+
+#ifndef __ASSEMBLY__
+
+#include <linux/mm.h>
+
+enum __kvm_host_smccc_func {
+	/* Hypercalls available only prior to pKVM finalisation */
+	/* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
+	__KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init,
+	__KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,
+	__KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector,
+	__KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config,
+	__KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize,
+
+	/* Hypercalls available after pKVM finalisation */
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
+	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
+	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
+	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
+	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs,
+	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps,
+};
+
+#define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
+#define DECLARE_KVM_NVHE_SYM(sym)	extern char kvm_nvhe_sym(sym)[]
+
+/*
+ * Define a pair of symbols sharing the same name but one defined in
+ * VHE and the other in nVHE hyp implementations.
+ */
+#define DECLARE_KVM_HYP_SYM(sym)		\
+	DECLARE_KVM_VHE_SYM(sym);		\
+	DECLARE_KVM_NVHE_SYM(sym)
+
+#define DECLARE_KVM_VHE_PER_CPU(type, sym)	\
+	DECLARE_PER_CPU(type, sym)
+#define DECLARE_KVM_NVHE_PER_CPU(type, sym)	\
+	DECLARE_PER_CPU(type, kvm_nvhe_sym(sym))
+
+#define DECLARE_KVM_HYP_PER_CPU(type, sym)	\
+	DECLARE_KVM_VHE_PER_CPU(type, sym);	\
+	DECLARE_KVM_NVHE_PER_CPU(type, sym)
+
+/*
+ * Compute pointer to a symbol defined in nVHE percpu region.
+ * Returns NULL if percpu memory has not been allocated yet.
+ */
+#define this_cpu_ptr_nvhe_sym(sym)	per_cpu_ptr_nvhe_sym(sym, smp_processor_id())
+#define per_cpu_ptr_nvhe_sym(sym, cpu)						\
+	({									\
+		unsigned long base, off;					\
+		base = kvm_arm_hyp_percpu_base[cpu];				\
+		off = (unsigned long)&CHOOSE_NVHE_SYM(sym) -			\
+		      (unsigned long)&CHOOSE_NVHE_SYM(__per_cpu_start);		\
+		base ? (typeof(CHOOSE_NVHE_SYM(sym))*)(base + off) : NULL;	\
+	})
+
+#if defined(__KVM_NVHE_HYPERVISOR__)
+
+#define CHOOSE_NVHE_SYM(sym)	sym
+#define CHOOSE_HYP_SYM(sym)	CHOOSE_NVHE_SYM(sym)
+
+/* The nVHE hypervisor shouldn't even try to access VHE symbols */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_VHE_SYM(sym)		__nvhe_undefined_symbol
+#define this_cpu_ptr_hyp_sym(sym)	(&__nvhe_undefined_symbol)
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(&__nvhe_undefined_symbol)
+
+#elif defined(__KVM_VHE_HYPERVISOR__)
+
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_HYP_SYM(sym)	CHOOSE_VHE_SYM(sym)
+
+/* The VHE hypervisor shouldn't even try to access nVHE symbols */
+extern void *__vhe_undefined_symbol;
+#define CHOOSE_NVHE_SYM(sym)		__vhe_undefined_symbol
+#define this_cpu_ptr_hyp_sym(sym)	(&__vhe_undefined_symbol)
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(&__vhe_undefined_symbol)
+
+#else
+
+/*
+ * BIG FAT WARNINGS:
+ *
+ * - Don't be tempted to change the following is_kernel_in_hyp_mode()
+ *   to has_vhe(). has_vhe() is implemented as a *final* capability,
+ *   while this is used early at boot time, when the capabilities are
+ *   not final yet....
+ *
+ * - Don't let the nVHE hypervisor have access to this, as it will
+ *   pick the *wrong* symbol (yes, it runs at EL2...).
+ */
+#define CHOOSE_HYP_SYM(sym)		(is_kernel_in_hyp_mode()	\
+					   ? CHOOSE_VHE_SYM(sym)	\
+					   : CHOOSE_NVHE_SYM(sym))
+
+#define this_cpu_ptr_hyp_sym(sym)	(is_kernel_in_hyp_mode()	\
+					   ? this_cpu_ptr(&sym)		\
+					   : this_cpu_ptr_nvhe_sym(sym))
+
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(is_kernel_in_hyp_mode()	\
+					   ? per_cpu_ptr(&sym, cpu)	\
+					   : per_cpu_ptr_nvhe_sym(sym, cpu))
+
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+
+#endif
+
+struct kvm_nvhe_init_params {
+	unsigned long mair_el2;
+	unsigned long tcr_el2;
+	unsigned long tpidr_el2;
+	unsigned long stack_hyp_va;
+	unsigned long stack_pa;
+	phys_addr_t pgd_pa;
+	unsigned long hcr_el2;
+	unsigned long vttbr;
+	unsigned long vtcr;
+};
+
+/*
+ * Used by the host in EL1 to dump the nVHE hypervisor backtrace on
+ * hyp_panic() in non-protected mode.
+ *
+ * @stack_base:                 hyp VA of the hyp_stack base.
+ * @overflow_stack_base:        hyp VA of the hyp_overflow_stack base.
+ * @fp:                         hyp FP where the backtrace begins.
+ * @pc:                         hyp PC where the backtrace begins.
+ */
+struct kvm_nvhe_stacktrace_info {
+	unsigned long stack_base;
+	unsigned long overflow_stack_base;
+	unsigned long fp;
+	unsigned long pc;
+};
+
+/* Translate a kernel address @ptr into its equivalent linear mapping */
+#define kvm_ksym_ref(ptr)						\
+	({								\
+		void *val = (ptr);					\
+		if (!is_kernel_in_hyp_mode())				\
+			val = lm_alias((ptr));				\
+		val;							\
+	 })
+#define kvm_ksym_ref_nvhe(sym)	kvm_ksym_ref(kvm_nvhe_sym(sym))
+
+struct kvm;
+struct kvm_vcpu;
+struct kvm_s2_mmu;
+
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
+DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
+#define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
+
+extern unsigned long kvm_arm_hyp_percpu_base[NR_CPUS];
+DECLARE_KVM_NVHE_SYM(__per_cpu_start);
+DECLARE_KVM_NVHE_SYM(__per_cpu_end);
+
+DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
+#define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
+
+extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
+				     int level);
+extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
+
+extern void __kvm_timer_set_cntvoff(u64 cntvoff);
+
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
+
+extern u64 __vgic_v3_get_gic_config(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
+extern void __vgic_v3_init_lrs(void);
+
+extern u64 __kvm_get_mdcr_el2(void);
+
+#define __KVM_EXTABLE(from, to)						\
+	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
+	"	.align		3\n"					\
+	"	.long		(" #from " - .), (" #to " - .)\n"	\
+	"	.popsection\n"
+
+
+#define __kvm_at(at_op, addr)						\
+( { 									\
+	int __kvm_at_err = 0;						\
+	u64 spsr, elr;							\
+	asm volatile(							\
+	"	mrs	%1, spsr_el2\n"					\
+	"	mrs	%2, elr_el2\n"					\
+	"1:	at	"at_op", %3\n"					\
+	"	isb\n"							\
+	"	b	9f\n"						\
+	"2:	msr	spsr_el2, %1\n"					\
+	"	msr	elr_el2, %2\n"					\
+	"	mov	%w0, %4\n"					\
+	"9:\n"								\
+	__KVM_EXTABLE(1b, 2b)						\
+	: "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr)		\
+	: "r" (addr), "i" (-EFAULT));					\
+	__kvm_at_err;							\
+} )
+
+
+#else /* __ASSEMBLY__ */
+
+.macro get_host_ctxt reg, tmp
+	adr_this_cpu \reg, kvm_host_data, \tmp
+	add	\reg, \reg, #HOST_DATA_CONTEXT
+.endm
+
+.macro get_vcpu_ptr vcpu, ctxt
+	get_host_ctxt \ctxt, \vcpu
+	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+.macro get_loaded_vcpu vcpu, ctxt
+	adr_this_cpu \ctxt, kvm_hyp_ctxt, \vcpu
+	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+.macro set_loaded_vcpu vcpu, ctxt, tmp
+	adr_this_cpu \ctxt, kvm_hyp_ctxt, \tmp
+	str	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+/*
+ * KVM extable for unexpected exceptions.
+ * Create a struct kvm_exception_table_entry output to a section that can be
+ * mapped by EL2. The table is not sorted.
+ *
+ * The caller must ensure:
+ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented
+ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup.
+ */
+.macro	_kvm_extable, from, to
+	.pushsection	__kvm_ex_table, "a"
+	.align		3
+	.long		(\from - .), (\to - .)
+	.popsection
+.endm
+
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
+#define CPU_LR_OFFSET		CPU_XREG_OFFSET(30)
+#define CPU_SP_EL0_OFFSET	(CPU_LR_OFFSET + 8)
+
+/*
+ * We treat x18 as callee-saved as the host may use it as a platform
+ * register (e.g. for shadow call stack).
+ */
+.macro save_callee_saved_regs ctxt
+	str	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
+	stp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	stp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	stp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	stp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	stp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	stp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro restore_callee_saved_regs ctxt
+	// We require \ctxt is not x18-x28
+	ldr	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
+	ldp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	ldp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	ldp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	ldp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	ldp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro save_sp_el0 ctxt, tmp
+	mrs	\tmp,	sp_el0
+	str	\tmp,	[\ctxt, #CPU_SP_EL0_OFFSET]
+.endm
+
+.macro restore_sp_el0 ctxt, tmp
+	ldr	\tmp,	  [\ctxt, #CPU_SP_EL0_OFFSET]
+	msr	sp_el0, \tmp
+.endm
+
+#endif
+
+#endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
new file mode 100644
index 000000000..0d40c48d8
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -0,0 +1,511 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/kvm_emulate.h
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ */
+
+#ifndef __ARM64_KVM_EMULATE_H__
+#define __ARM64_KVM_EMULATE_H__
+
+#include <linux/kvm_host.h>
+
+#include <asm/debug-monitors.h>
+#include <asm/esr.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/ptrace.h>
+#include <asm/cputype.h>
+#include <asm/virt.h>
+
+#define CURRENT_EL_SP_EL0_VECTOR	0x0
+#define CURRENT_EL_SP_ELx_VECTOR	0x200
+#define LOWER_EL_AArch64_VECTOR		0x400
+#define LOWER_EL_AArch32_VECTOR		0x600
+
+enum exception_type {
+	except_type_sync	= 0,
+	except_type_irq		= 0x80,
+	except_type_fiq		= 0x100,
+	except_type_serror	= 0x180,
+};
+
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
+void kvm_skip_instr32(struct kvm_vcpu *vcpu);
+
+void kvm_inject_undefined(struct kvm_vcpu *vcpu);
+void kvm_inject_vabt(struct kvm_vcpu *vcpu);
+void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_size_fault(struct kvm_vcpu *vcpu);
+
+void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
+
+#if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
+static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.hcr_el2 & HCR_RW);
+}
+#else
+static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED,
+			       &kvm->arch.flags));
+
+	return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
+}
+#endif
+
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (is_kernel_in_hyp_mode())
+		vcpu->arch.hcr_el2 |= HCR_E2H;
+	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) {
+		/* route synchronous external abort exceptions to EL2 */
+		vcpu->arch.hcr_el2 |= HCR_TEA;
+		/* trap error record accesses */
+		vcpu->arch.hcr_el2 |= HCR_TERR;
+	}
+
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
+		vcpu->arch.hcr_el2 |= HCR_FWB;
+	} else {
+		/*
+		 * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C
+		 * get set in SCTLR_EL1 such that we can detect when the guest
+		 * MMU gets turned on and do the necessary cache maintenance
+		 * then.
+		 */
+		vcpu->arch.hcr_el2 |= HCR_TVM;
+	}
+
+	if (vcpu_el1_is_32bit(vcpu))
+		vcpu->arch.hcr_el2 &= ~HCR_RW;
+
+	if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
+	    vcpu_el1_is_32bit(vcpu))
+		vcpu->arch.hcr_el2 |= HCR_TID2;
+
+	if (kvm_has_mte(vcpu->kvm))
+		vcpu->arch.hcr_el2 |= HCR_ATA;
+}
+
+static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
+{
+	return (unsigned long *)&vcpu->arch.hcr_el2;
+}
+
+static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 &= ~HCR_TWE;
+	if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) ||
+	    vcpu->kvm->arch.vgic.nassgireq)
+		vcpu->arch.hcr_el2 &= ~HCR_TWI;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TWI;
+}
+
+static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 |= HCR_TWE;
+	vcpu->arch.hcr_el2 |= HCR_TWI;
+}
+
+static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
+}
+
+static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
+}
+
+static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.vsesr_el2;
+}
+
+static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr)
+{
+	vcpu->arch.vsesr_el2 = vsesr;
+}
+
+static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
+{
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pc;
+}
+
+static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
+{
+	return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate;
+}
+
+static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
+{
+	return !!(*vcpu_cpsr(vcpu) & PSR_MODE32_BIT);
+}
+
+static __always_inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu))
+		return kvm_condition_valid32(vcpu);
+
+	return true;
+}
+
+static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
+{
+	*vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT;
+}
+
+/*
+ * vcpu_get_reg and vcpu_set_reg should always be passed a register number
+ * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on
+ * AArch32 with banked registers.
+ */
+static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
+					 u8 reg_num)
+{
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs[reg_num];
+}
+
+static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+				unsigned long val)
+{
+	if (reg_num != 31)
+		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
+}
+
+/*
+ * The layout of SPSR for an AArch32 state is different when observed from an
+ * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
+ * view given an AArch64 view.
+ *
+ * In ARM DDI 0487E.a see:
+ *
+ * - The AArch64 view (SPSR_EL2) in section C5.2.18, page C5-426
+ * - The AArch32 view (SPSR_abt) in section G8.2.126, page G8-6256
+ * - The AArch32 view (SPSR_und) in section G8.2.132, page G8-6280
+ *
+ * Which show the following differences:
+ *
+ * | Bit | AA64 | AA32 | Notes                       |
+ * +-----+------+------+-----------------------------|
+ * | 24  | DIT  | J    | J is RES0 in ARMv8          |
+ * | 21  | SS   | DIT  | SS doesn't exist in AArch32 |
+ *
+ * ... and all other bits are (currently) common.
+ */
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	const unsigned long overlap = BIT(24) | BIT(21);
+	unsigned long dit = !!(spsr & PSR_AA32_DIT_BIT);
+
+	spsr &= ~overlap;
+
+	spsr |= dit << 21;
+
+	return spsr;
+}
+
+static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
+{
+	u32 mode;
+
+	if (vcpu_mode_is_32bit(vcpu)) {
+		mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
+		return mode > PSR_AA32_MODE_USR;
+	}
+
+	mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
+
+	return mode != PSR_MODE_EL0t;
+}
+
+static __always_inline u64 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.esr_el2;
+}
+
+static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+
+	if (esr & ESR_ELx_CV)
+		return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
+
+	return -1;
+}
+
+static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.far_el2;
+}
+
+static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
+{
+	return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
+}
+
+static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.disr_el1;
+}
+
+static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_xVC_IMM_MASK;
+}
+
+static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_ISV);
+}
+
+static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC);
+}
+
+static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SSE);
+}
+
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SF);
+}
+
+static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
+{
+	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
+}
+
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
+}
+
+/* Always check for S1PTW *before* using this. */
+static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
+}
+
+static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_CM);
+}
+
+static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
+{
+	return 1 << ((kvm_vcpu_get_esr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
+}
+
+/* This one is not specific to Data Abort */
+static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_IL);
+}
+
+static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
+{
+	return ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
+}
+
+static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
+}
+
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
+static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
+}
+
+static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
+}
+
+static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+}
+
+static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
+{
+	switch (kvm_vcpu_trap_get_fault(vcpu)) {
+	case FSC_SEA:
+	case FSC_SEA_TTW0:
+	case FSC_SEA_TTW1:
+	case FSC_SEA_TTW2:
+	case FSC_SEA_TTW3:
+	case FSC_SECC:
+	case FSC_SECC_TTW0:
+	case FSC_SECC_TTW1:
+	case FSC_SECC_TTW2:
+	case FSC_SECC_TTW3:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	return ESR_ELx_SYS64_ISS_RT(esr);
+}
+
+static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_abt_iss1tw(vcpu)) {
+		/*
+		 * Only a permission fault on a S1PTW should be
+		 * considered as a write. Otherwise, page tables baked
+		 * in a read-only memslot will result in an exception
+		 * being delivered in the guest.
+		 *
+		 * The drawback is that we end-up faulting twice if the
+		 * guest is using any of HW AF/DB: a translation fault
+		 * to map the page containing the PT (read only at
+		 * first), then a permission fault to allow the flags
+		 * to be set.
+		 */
+		switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+		case ESR_ELx_FSC_PERM:
+			return true;
+		default:
+			return false;
+		}
+	}
+
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
+static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
+{
+	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
+}
+
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu)) {
+		*vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT;
+	} else {
+		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+		sctlr |= SCTLR_ELx_EE;
+		vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
+	}
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu))
+		return !!(*vcpu_cpsr(vcpu) & PSR_AA32_E_BIT);
+
+	if (vcpu_mode_priv(vcpu))
+		return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & SCTLR_ELx_EE);
+	else
+		return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & SCTLR_EL1_E0E);
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return be16_to_cpu(data & 0xffff);
+		case 4:
+			return be32_to_cpu(data & 0xffffffff);
+		default:
+			return be64_to_cpu(data);
+		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		case 4:
+			return le32_to_cpu(data & 0xffffffff);
+		default:
+			return le64_to_cpu(data);
+		}
+	}
+
+	return data;		/* Leave LE untouched */
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+						    unsigned long data,
+						    unsigned int len)
+{
+	if (kvm_vcpu_is_be(vcpu)) {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_be16(data & 0xffff);
+		case 4:
+			return cpu_to_be32(data & 0xffffffff);
+		default:
+			return cpu_to_be64(data);
+		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		case 4:
+			return cpu_to_le32(data & 0xffffffff);
+		default:
+			return cpu_to_le64(data);
+		}
+	}
+
+	return data;		/* Leave LE untouched */
+}
+
+static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(vcpu_get_flag(vcpu, PENDING_EXCEPTION));
+	vcpu_set_flag(vcpu, INCREMENT_PC);
+}
+
+#define kvm_pend_exception(v, e)					\
+	do {								\
+		WARN_ON(vcpu_get_flag((v), INCREMENT_PC));		\
+		vcpu_set_flag((v), PENDING_EXCEPTION);			\
+		vcpu_set_flag((v), e);					\
+	} while (0)
+
+
+static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature)
+{
+	return test_bit(feature, vcpu->arch.features);
+}
+
+#endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
new file mode 100644
index 000000000..577cf444c
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -0,0 +1,975 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/asm/kvm_host.h:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ */
+
+#ifndef __ARM64_KVM_HOST_H__
+#define __ARM64_KVM_HOST_H__
+
+#include <linux/arm-smccc.h>
+#include <linux/bitmap.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <linux/kvm_types.h>
+#include <linux/percpu.h>
+#include <linux/psci.h>
+#include <asm/arch_gicv3.h>
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/cputype.h>
+#include <asm/daifflags.h>
+#include <asm/fpsimd.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+
+#define __KVM_HAVE_ARCH_INTC_INITIALIZED
+
+#define KVM_HALT_POLL_NS_DEFAULT 500000
+
+#include <kvm/arm_vgic.h>
+#include <kvm/arm_arch_timer.h>
+#include <kvm/arm_pmu.h>
+
+#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
+
+#define KVM_VCPU_MAX_FEATURES 7
+
+#define KVM_REQ_SLEEP \
+	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
+#define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
+#define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
+#define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
+#define KVM_REQ_SUSPEND		KVM_ARCH_REQ(6)
+
+#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
+				     KVM_DIRTY_LOG_INITIALLY_SET)
+
+#define KVM_HAVE_MMU_RWLOCK
+
+/*
+ * Mode of operation configurable with kvm-arm.mode early param.
+ * See Documentation/admin-guide/kernel-parameters.txt for more information.
+ */
+enum kvm_mode {
+	KVM_MODE_DEFAULT,
+	KVM_MODE_PROTECTED,
+	KVM_MODE_NONE,
+};
+enum kvm_mode kvm_get_mode(void);
+
+DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
+extern unsigned int kvm_sve_max_vl;
+int kvm_arm_init_sve(void);
+
+u32 __attribute_const__ kvm_target_cpu(void);
+int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
+void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
+
+struct kvm_vmid {
+	atomic64_t id;
+};
+
+struct kvm_s2_mmu {
+	struct kvm_vmid vmid;
+
+	/*
+	 * stage2 entry level table
+	 *
+	 * Two kvm_s2_mmu structures in the same VM can point to the same
+	 * pgd here.  This happens when running a guest using a
+	 * translation regime that isn't affected by its own stage-2
+	 * translation, such as a non-VHE hypervisor running at vEL2, or
+	 * for vEL1/EL0 with vHCR_EL2.VM == 0.  In that case, we use the
+	 * canonical stage-2 page tables.
+	 */
+	phys_addr_t	pgd_phys;
+	struct kvm_pgtable *pgt;
+
+	/* The last vcpu id that ran on each physical CPU */
+	int __percpu *last_vcpu_ran;
+
+	struct kvm_arch *arch;
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/**
+ * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests
+ *
+ * @std_bmap: Bitmap of standard secure service calls
+ * @std_hyp_bmap: Bitmap of standard hypervisor service calls
+ * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls
+ */
+struct kvm_smccc_features {
+	unsigned long std_bmap;
+	unsigned long std_hyp_bmap;
+	unsigned long vendor_hyp_bmap;
+};
+
+struct kvm_arch {
+	struct kvm_s2_mmu mmu;
+
+	/* VTCR_EL2 value for this VM */
+	u64    vtcr;
+
+	/* Interrupt controller */
+	struct vgic_dist	vgic;
+
+	/* Mandated version of PSCI */
+	u32 psci_version;
+
+	/* Protects VM-scoped configuration data */
+	struct mutex config_lock;
+
+	/*
+	 * If we encounter a data abort without valid instruction syndrome
+	 * information, report this to user space.  User space can (and
+	 * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is
+	 * supported.
+	 */
+#define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER	0
+	/* Memory Tagging Extension enabled for the guest */
+#define KVM_ARCH_FLAG_MTE_ENABLED			1
+	/* At least one vCPU has ran in the VM */
+#define KVM_ARCH_FLAG_HAS_RAN_ONCE			2
+	/*
+	 * The following two bits are used to indicate the guest's EL1
+	 * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT
+	 * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set.
+	 * Otherwise, the guest's EL1 register width has not yet been
+	 * determined yet.
+	 */
+#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED		3
+#define KVM_ARCH_FLAG_EL1_32BIT				4
+	/* PSCI SYSTEM_SUSPEND enabled for the guest */
+#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED		5
+
+	unsigned long flags;
+
+	/*
+	 * VM-wide PMU filter, implemented as a bitmap and big enough for
+	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
+	 */
+	unsigned long *pmu_filter;
+	struct arm_pmu *arm_pmu;
+
+	cpumask_var_t supported_cpus;
+
+	u8 pfr0_csv2;
+	u8 pfr0_csv3;
+
+	/* Hypercall features firmware registers' descriptor */
+	struct kvm_smccc_features smccc_feat;
+};
+
+struct kvm_vcpu_fault_info {
+	u64 esr_el2;		/* Hyp Syndrom Register */
+	u64 far_el2;		/* Hyp Fault Address Register */
+	u64 hpfar_el2;		/* Hyp IPA Fault Address Register */
+	u64 disr_el1;		/* Deferred [SError] Status Register */
+};
+
+enum vcpu_sysreg {
+	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
+	MPIDR_EL1,	/* MultiProcessor Affinity Register */
+	CSSELR_EL1,	/* Cache Size Selection Register */
+	SCTLR_EL1,	/* System Control Register */
+	ACTLR_EL1,	/* Auxiliary Control Register */
+	CPACR_EL1,	/* Coprocessor Access Control */
+	ZCR_EL1,	/* SVE Control */
+	TTBR0_EL1,	/* Translation Table Base Register 0 */
+	TTBR1_EL1,	/* Translation Table Base Register 1 */
+	TCR_EL1,	/* Translation Control Register */
+	ESR_EL1,	/* Exception Syndrome Register */
+	AFSR0_EL1,	/* Auxiliary Fault Status Register 0 */
+	AFSR1_EL1,	/* Auxiliary Fault Status Register 1 */
+	FAR_EL1,	/* Fault Address Register */
+	MAIR_EL1,	/* Memory Attribute Indirection Register */
+	VBAR_EL1,	/* Vector Base Address Register */
+	CONTEXTIDR_EL1,	/* Context ID Register */
+	TPIDR_EL0,	/* Thread ID, User R/W */
+	TPIDRRO_EL0,	/* Thread ID, User R/O */
+	TPIDR_EL1,	/* Thread ID, Privileged */
+	AMAIR_EL1,	/* Aux Memory Attribute Indirection Register */
+	CNTKCTL_EL1,	/* Timer Control Register (EL1) */
+	PAR_EL1,	/* Physical Address Register */
+	MDSCR_EL1,	/* Monitor Debug System Control Register */
+	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+	OSLSR_EL1,	/* OS Lock Status Register */
+	DISR_EL1,	/* Deferred Interrupt Status Register */
+
+	/* Performance Monitors Registers */
+	PMCR_EL0,	/* Control Register */
+	PMSELR_EL0,	/* Event Counter Selection Register */
+	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
+	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
+	PMCCNTR_EL0,	/* Cycle Counter Register */
+	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
+	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
+	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
+	PMCNTENSET_EL0,	/* Count Enable Set Register */
+	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
+	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
+	PMUSERENR_EL0,	/* User Enable Register */
+
+	/* Pointer Authentication Registers in a strict increasing order. */
+	APIAKEYLO_EL1,
+	APIAKEYHI_EL1,
+	APIBKEYLO_EL1,
+	APIBKEYHI_EL1,
+	APDAKEYLO_EL1,
+	APDAKEYHI_EL1,
+	APDBKEYLO_EL1,
+	APDBKEYHI_EL1,
+	APGAKEYLO_EL1,
+	APGAKEYHI_EL1,
+
+	ELR_EL1,
+	SP_EL1,
+	SPSR_EL1,
+
+	CNTVOFF_EL2,
+	CNTV_CVAL_EL0,
+	CNTV_CTL_EL0,
+	CNTP_CVAL_EL0,
+	CNTP_CTL_EL0,
+
+	/* Memory Tagging Extension registers */
+	RGSR_EL1,	/* Random Allocation Tag Seed Register */
+	GCR_EL1,	/* Tag Control Register */
+	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
+	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
+
+	/* 32bit specific registers. Keep them at the end of the range */
+	DACR32_EL2,	/* Domain Access Control Register */
+	IFSR32_EL2,	/* Instruction Fault Status Register */
+	FPEXC32_EL2,	/* Floating-Point Exception Control Register */
+	DBGVCR32_EL2,	/* Debug Vector Catch Register */
+
+	NR_SYS_REGS	/* Nothing after this line! */
+};
+
+struct kvm_cpu_context {
+	struct user_pt_regs regs;	/* sp = sp_el0 */
+
+	u64	spsr_abt;
+	u64	spsr_und;
+	u64	spsr_irq;
+	u64	spsr_fiq;
+
+	struct user_fpsimd_state fp_regs;
+
+	u64 sys_regs[NR_SYS_REGS];
+
+	struct kvm_vcpu *__hyp_running_vcpu;
+};
+
+struct kvm_host_data {
+	struct kvm_cpu_context host_ctxt;
+};
+
+struct kvm_host_psci_config {
+	/* PSCI version used by host. */
+	u32 version;
+
+	/* Function IDs used by host if version is v0.1. */
+	struct psci_0_1_function_ids function_ids_0_1;
+
+	bool psci_0_1_cpu_suspend_implemented;
+	bool psci_0_1_cpu_on_implemented;
+	bool psci_0_1_cpu_off_implemented;
+	bool psci_0_1_migrate_implemented;
+};
+
+extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
+#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)
+
+extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
+#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)
+
+extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
+#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)
+
+struct vcpu_reset_state {
+	unsigned long	pc;
+	unsigned long	r0;
+	bool		be;
+	bool		reset;
+};
+
+struct kvm_vcpu_arch {
+	struct kvm_cpu_context ctxt;
+
+	/* Guest floating point state */
+	void *sve_state;
+	unsigned int sve_max_vl;
+	u64 svcr;
+
+	/* Stage 2 paging state used by the hardware on next switch */
+	struct kvm_s2_mmu *hw_mmu;
+
+	/* Values of trap registers for the guest. */
+	u64 hcr_el2;
+	u64 mdcr_el2;
+	u64 cptr_el2;
+
+	/* Values of trap registers for the host before guest entry. */
+	u64 mdcr_el2_host;
+
+	/* Exception Information */
+	struct kvm_vcpu_fault_info fault;
+
+	/* Ownership of the FP regs */
+	enum {
+		FP_STATE_FREE,
+		FP_STATE_HOST_OWNED,
+		FP_STATE_GUEST_OWNED,
+	} fp_state;
+
+	/* Configuration flags, set once and for all before the vcpu can run */
+	u8 cflags;
+
+	/* Input flags to the hypervisor code, potentially cleared after use */
+	u8 iflags;
+
+	/* State flags for kernel bookkeeping, unused by the hypervisor code */
+	u8 sflags;
+
+	/*
+	 * Don't run the guest (internal implementation need).
+	 *
+	 * Contrary to the flags above, this is set/cleared outside of
+	 * a vcpu context, and thus cannot be mixed with the flags
+	 * themselves (or the flag accesses need to be made atomic).
+	 */
+	bool pause;
+
+	/*
+	 * We maintain more than a single set of debug registers to support
+	 * debugging the guest from the host and to maintain separate host and
+	 * guest state during world switches. vcpu_debug_state are the debug
+	 * registers of the vcpu as the guest sees them.  host_debug_state are
+	 * the host registers which are saved and restored during
+	 * world switches. external_debug_state contains the debug
+	 * values we want to debug the guest. This is set via the
+	 * KVM_SET_GUEST_DEBUG ioctl.
+	 *
+	 * debug_ptr points to the set of debug registers that should be loaded
+	 * onto the hardware when running the guest.
+	 */
+	struct kvm_guest_debug_arch *debug_ptr;
+	struct kvm_guest_debug_arch vcpu_debug_state;
+	struct kvm_guest_debug_arch external_debug_state;
+
+	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
+	struct task_struct *parent_task;
+
+	struct {
+		/* {Break,watch}point registers */
+		struct kvm_guest_debug_arch regs;
+		/* Statistical profiling extension */
+		u64 pmscr_el1;
+		/* Self-hosted trace */
+		u64 trfcr_el1;
+	} host_debug_state;
+
+	/* VGIC state */
+	struct vgic_cpu vgic_cpu;
+	struct arch_timer_cpu timer_cpu;
+	struct kvm_pmu pmu;
+
+	/*
+	 * Guest registers we preserve during guest debugging.
+	 *
+	 * These shadow registers are updated by the kvm_handle_sys_reg
+	 * trap handler if the guest accesses or updates them while we
+	 * are using guest debug.
+	 */
+	struct {
+		u32	mdscr_el1;
+		bool	pstate_ss;
+	} guest_debug_preserved;
+
+	/* vcpu power state */
+	struct kvm_mp_state mp_state;
+	spinlock_t mp_state_lock;
+
+	/* Cache some mmu pages needed inside spinlock regions */
+	struct kvm_mmu_memory_cache mmu_page_cache;
+
+	/* Target CPU and feature flags */
+	int target;
+	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
+
+	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
+	u64 vsesr_el2;
+
+	/* Additional reset state */
+	struct vcpu_reset_state	reset_state;
+
+	/* Guest PV state */
+	struct {
+		u64 last_steal;
+		gpa_t base;
+	} steal;
+};
+
+/*
+ * Each 'flag' is composed of a comma-separated triplet:
+ *
+ * - the flag-set it belongs to in the vcpu->arch structure
+ * - the value for that flag
+ * - the mask for that flag
+ *
+ *  __vcpu_single_flag() builds such a triplet for a single-bit flag.
+ * unpack_vcpu_flag() extract the flag value from the triplet for
+ * direct use outside of the flag accessors.
+ */
+#define __vcpu_single_flag(_set, _f)	_set, (_f), (_f)
+
+#define __unpack_flag(_set, _f, _m)	_f
+#define unpack_vcpu_flag(...)		__unpack_flag(__VA_ARGS__)
+
+#define __build_check_flag(v, flagset, f, m)			\
+	do {							\
+		typeof(v->arch.flagset) *_fset;			\
+								\
+		/* Check that the flags fit in the mask */	\
+		BUILD_BUG_ON(HWEIGHT(m) != HWEIGHT((f) | (m)));	\
+		/* Check that the flags fit in the type */	\
+		BUILD_BUG_ON((sizeof(*_fset) * 8) <= __fls(m));	\
+	} while (0)
+
+#define __vcpu_get_flag(v, flagset, f, m)			\
+	({							\
+		__build_check_flag(v, flagset, f, m);		\
+								\
+		READ_ONCE(v->arch.flagset) & (m);		\
+	})
+
+/*
+ * Note that the set/clear accessors must be preempt-safe in order to
+ * avoid nesting them with load/put which also manipulate flags...
+ */
+#ifdef __KVM_NVHE_HYPERVISOR__
+/* the nVHE hypervisor is always non-preemptible */
+#define __vcpu_flags_preempt_disable()
+#define __vcpu_flags_preempt_enable()
+#else
+#define __vcpu_flags_preempt_disable()	preempt_disable()
+#define __vcpu_flags_preempt_enable()	preempt_enable()
+#endif
+
+#define __vcpu_set_flag(v, flagset, f, m)			\
+	do {							\
+		typeof(v->arch.flagset) *fset;			\
+								\
+		__build_check_flag(v, flagset, f, m);		\
+								\
+		fset = &v->arch.flagset;			\
+		__vcpu_flags_preempt_disable();			\
+		if (HWEIGHT(m) > 1)				\
+			*fset &= ~(m);				\
+		*fset |= (f);					\
+		__vcpu_flags_preempt_enable();			\
+	} while (0)
+
+#define __vcpu_clear_flag(v, flagset, f, m)			\
+	do {							\
+		typeof(v->arch.flagset) *fset;			\
+								\
+		__build_check_flag(v, flagset, f, m);		\
+								\
+		fset = &v->arch.flagset;			\
+		__vcpu_flags_preempt_disable();			\
+		*fset &= ~(m);					\
+		__vcpu_flags_preempt_enable();			\
+	} while (0)
+
+#define vcpu_get_flag(v, ...)	__vcpu_get_flag((v), __VA_ARGS__)
+#define vcpu_set_flag(v, ...)	__vcpu_set_flag((v), __VA_ARGS__)
+#define vcpu_clear_flag(v, ...)	__vcpu_clear_flag((v), __VA_ARGS__)
+
+/* SVE exposed to guest */
+#define GUEST_HAS_SVE		__vcpu_single_flag(cflags, BIT(0))
+/* SVE config completed */
+#define VCPU_SVE_FINALIZED	__vcpu_single_flag(cflags, BIT(1))
+/* PTRAUTH exposed to guest */
+#define GUEST_HAS_PTRAUTH	__vcpu_single_flag(cflags, BIT(2))
+
+/* Exception pending */
+#define PENDING_EXCEPTION	__vcpu_single_flag(iflags, BIT(0))
+/*
+ * PC increment. Overlaps with EXCEPT_MASK on purpose so that it can't
+ * be set together with an exception...
+ */
+#define INCREMENT_PC		__vcpu_single_flag(iflags, BIT(1))
+/* Target EL/MODE (not a single flag, but let's abuse the macro) */
+#define EXCEPT_MASK		__vcpu_single_flag(iflags, GENMASK(3, 1))
+
+/* Helpers to encode exceptions with minimum fuss */
+#define __EXCEPT_MASK_VAL	unpack_vcpu_flag(EXCEPT_MASK)
+#define __EXCEPT_SHIFT		__builtin_ctzl(__EXCEPT_MASK_VAL)
+#define __vcpu_except_flags(_f)	iflags, (_f << __EXCEPT_SHIFT), __EXCEPT_MASK_VAL
+
+/*
+ * When PENDING_EXCEPTION is set, EXCEPT_MASK can take the following
+ * values:
+ *
+ * For AArch32 EL1:
+ */
+#define EXCEPT_AA32_UND		__vcpu_except_flags(0)
+#define EXCEPT_AA32_IABT	__vcpu_except_flags(1)
+#define EXCEPT_AA32_DABT	__vcpu_except_flags(2)
+/* For AArch64: */
+#define EXCEPT_AA64_EL1_SYNC	__vcpu_except_flags(0)
+#define EXCEPT_AA64_EL1_IRQ	__vcpu_except_flags(1)
+#define EXCEPT_AA64_EL1_FIQ	__vcpu_except_flags(2)
+#define EXCEPT_AA64_EL1_SERR	__vcpu_except_flags(3)
+/* For AArch64 with NV (one day): */
+#define EXCEPT_AA64_EL2_SYNC	__vcpu_except_flags(4)
+#define EXCEPT_AA64_EL2_IRQ	__vcpu_except_flags(5)
+#define EXCEPT_AA64_EL2_FIQ	__vcpu_except_flags(6)
+#define EXCEPT_AA64_EL2_SERR	__vcpu_except_flags(7)
+/* Guest debug is live */
+#define DEBUG_DIRTY		__vcpu_single_flag(iflags, BIT(4))
+/* Save SPE context if active  */
+#define DEBUG_STATE_SAVE_SPE	__vcpu_single_flag(iflags, BIT(5))
+/* Save TRBE context if active  */
+#define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))
+
+/* SVE enabled for host EL0 */
+#define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))
+/* SME enabled for EL0 */
+#define HOST_SME_ENABLED	__vcpu_single_flag(sflags, BIT(1))
+/* Physical CPU not in supported_cpus */
+#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(2))
+/* WFIT instruction trapped */
+#define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))
+/* vcpu system registers loaded on physical CPU */
+#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
+/* Software step state is Active-pending */
+#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
+/* WFI instruction trapped */
+#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))
+
+
+/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
+#define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) +	\
+			     sve_ffr_offset((vcpu)->arch.sve_max_vl))
+
+#define vcpu_sve_max_vq(vcpu)	sve_vq_from_vl((vcpu)->arch.sve_max_vl)
+
+#define vcpu_sve_state_size(vcpu) ({					\
+	size_t __size_ret;						\
+	unsigned int __vcpu_vq;						\
+									\
+	if (WARN_ON(!sve_vl_valid((vcpu)->arch.sve_max_vl))) {		\
+		__size_ret = 0;						\
+	} else {							\
+		__vcpu_vq = vcpu_sve_max_vq(vcpu);			\
+		__size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq);		\
+	}								\
+									\
+	__size_ret;							\
+})
+
+#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
+				 KVM_GUESTDBG_USE_SW_BP | \
+				 KVM_GUESTDBG_USE_HW | \
+				 KVM_GUESTDBG_SINGLESTEP)
+
+#define vcpu_has_sve(vcpu) (system_supports_sve() &&			\
+			    vcpu_get_flag(vcpu, GUEST_HAS_SVE))
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+#define vcpu_has_ptrauth(vcpu)						\
+	((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) ||		\
+	  cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) &&		\
+	  vcpu_get_flag(vcpu, GUEST_HAS_PTRAUTH))
+#else
+#define vcpu_has_ptrauth(vcpu)		false
+#endif
+
+#define vcpu_on_unsupported_cpu(vcpu)					\
+	vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU)
+
+#define vcpu_set_on_unsupported_cpu(vcpu)				\
+	vcpu_set_flag(vcpu, ON_UNSUPPORTED_CPU)
+
+#define vcpu_clear_on_unsupported_cpu(vcpu)				\
+	vcpu_clear_flag(vcpu, ON_UNSUPPORTED_CPU)
+
+#define vcpu_gp_regs(v)		(&(v)->arch.ctxt.regs)
+
+/*
+ * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the
+ * memory backed version of a register, and not the one most recently
+ * accessed by a running VCPU.  For example, for userspace access or
+ * for system registers that are never context switched, but only
+ * emulated.
+ */
+#define __ctxt_sys_reg(c,r)	(&(c)->sys_regs[(r)])
+
+#define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
+
+#define __vcpu_sys_reg(v,r)	(ctxt_sys_reg(&(v)->arch.ctxt, (r)))
+
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
+
+static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
+{
+	/*
+	 * *** VHE ONLY ***
+	 *
+	 * System registers listed in the switch are not saved on every
+	 * exit from the guest but are only saved on vcpu_put.
+	 *
+	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
+	 * should never be listed below, because the guest cannot modify its
+	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
+	 * thread when emulating cross-VCPU communication.
+	 */
+	if (!has_vhe())
+		return false;
+
+	switch (reg) {
+	case CSSELR_EL1:	*val = read_sysreg_s(SYS_CSSELR_EL1);	break;
+	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
+	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
+	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
+	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
+	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
+	case PAR_EL1:		*val = read_sysreg_par();		break;
+	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
+	default:		return false;
+	}
+
+	return true;
+}
+
+static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
+{
+	/*
+	 * *** VHE ONLY ***
+	 *
+	 * System registers listed in the switch are not restored on every
+	 * entry to the guest but are only restored on vcpu_load.
+	 *
+	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
+	 * should never be listed below, because the MPIDR should only be set
+	 * once, before running the VCPU, and never changed later.
+	 */
+	if (!has_vhe())
+		return false;
+
+	switch (reg) {
+	case CSSELR_EL1:	write_sysreg_s(val, SYS_CSSELR_EL1);	break;
+	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
+	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
+	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
+	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
+	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
+	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
+	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
+	default:		return false;
+	}
+
+	return true;
+}
+
+struct kvm_vm_stat {
+	struct kvm_vm_stat_generic generic;
+};
+
+struct kvm_vcpu_stat {
+	struct kvm_vcpu_stat_generic generic;
+	u64 hvc_exit_stat;
+	u64 wfe_exit_stat;
+	u64 wfi_exit_stat;
+	u64 mmio_exit_user;
+	u64 mmio_exit_kernel;
+	u64 signal_exits;
+	u64 exits;
+};
+
+void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
+unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
+int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
+unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+
+int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
+			      struct kvm_vcpu_events *events);
+
+int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
+			      struct kvm_vcpu_events *events);
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+
+void kvm_arm_halt_guest(struct kvm *kvm);
+void kvm_arm_resume_guest(struct kvm *kvm);
+
+#define vcpu_has_run_once(vcpu)	!!rcu_access_pointer((vcpu)->pid)
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+#define kvm_call_hyp_nvhe(f, ...)						\
+	({								\
+		struct arm_smccc_res res;				\
+									\
+		arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(f),		\
+				  ##__VA_ARGS__, &res);			\
+		WARN_ON(res.a0 != SMCCC_RET_SUCCESS);			\
+									\
+		res.a1;							\
+	})
+
+/*
+ * The couple of isb() below are there to guarantee the same behaviour
+ * on VHE as on !VHE, where the eret to EL1 acts as a context
+ * synchronization event.
+ */
+#define kvm_call_hyp(f, ...)						\
+	do {								\
+		if (has_vhe()) {					\
+			f(__VA_ARGS__);					\
+			isb();						\
+		} else {						\
+			kvm_call_hyp_nvhe(f, ##__VA_ARGS__);		\
+		}							\
+	} while(0)
+
+#define kvm_call_hyp_ret(f, ...)					\
+	({								\
+		typeof(f(__VA_ARGS__)) ret;				\
+									\
+		if (has_vhe()) {					\
+			ret = f(__VA_ARGS__);				\
+			isb();						\
+		} else {						\
+			ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__);	\
+		}							\
+									\
+		ret;							\
+	})
+#else /* __KVM_NVHE_HYPERVISOR__ */
+#define kvm_call_hyp(f, ...) f(__VA_ARGS__)
+#define kvm_call_hyp_ret(f, ...) f(__VA_ARGS__)
+#define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__)
+#endif /* __KVM_NVHE_HYPERVISOR__ */
+
+void force_vm_exit(const cpumask_t *mask);
+
+int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
+void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);
+
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu);
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
+int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
+int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
+
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
+
+int kvm_sys_reg_table_init(void);
+
+/* MMIO helpers */
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu);
+int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa);
+
+/*
+ * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
+ * arrived in guest context.  For arm64, any event that arrives while a vCPU is
+ * loaded is considered to be "in guest".
+ */
+static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
+}
+
+long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
+
+bool kvm_arm_pvtime_supported(void);
+int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+
+extern unsigned int kvm_arm_vmid_bits;
+int kvm_arm_vmid_alloc_init(void);
+void kvm_arm_vmid_alloc_free(void);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_clear_active(void);
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+	vcpu_arch->steal.base = GPA_INVALID;
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return (vcpu_arch->steal.base != GPA_INVALID);
+}
+
+void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
+
+struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
+
+DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);
+
+static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
+{
+	/* The host's MPIDR is immutable, so let's set it up at boot time */
+	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
+}
+
+static inline bool kvm_system_needs_idmapped_vectors(void)
+{
+	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
+}
+
+void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
+
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+
+void kvm_arm_init_debug(void);
+void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
+void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
+void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
+void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+
+#define kvm_vcpu_os_lock_enabled(vcpu)		\
+	(!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & SYS_OSLSR_OSLK))
+
+int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+
+long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
+				struct kvm_arm_copy_mte_tags *copy_tags);
+
+/* Guest/host FPSIMD coordination helpers */
+int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu);
+void kvm_vcpu_unshare_task_fp(struct kvm_vcpu *vcpu);
+
+static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
+{
+	return (!has_vhe() && attr->exclude_host);
+}
+
+/* Flags for host debug state */
+void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_KVM
+void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
+void kvm_clr_pmu_events(u32 clr);
+#else
+static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
+static inline void kvm_clr_pmu_events(u32 clr) {}
+#endif
+
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
+
+int kvm_set_ipa_limit(void);
+
+#define __KVM_HAVE_ARCH_VM_ALLOC
+struct kvm *kvm_arch_alloc_vm(void);
+
+int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
+
+static inline bool kvm_vm_is_protected(struct kvm *kvm)
+{
+	return false;
+}
+
+void kvm_init_protected_traps(struct kvm_vcpu *vcpu);
+
+int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
+bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
+
+#define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED)
+
+#define kvm_has_mte(kvm)					\
+	(system_supports_mte() &&				\
+	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))
+
+#define kvm_supports_32bit_el0()				\
+	(system_supports_32bit_el0() &&				\
+	 !static_branch_unlikely(&arm64_mismatched_32bit_el0))
+
+int kvm_trng_call(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_KVM
+extern phys_addr_t hyp_mem_base;
+extern phys_addr_t hyp_mem_size;
+void __init kvm_hyp_reserve(void);
+#else
+static inline void kvm_hyp_reserve(void) { }
+#endif
+
+void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
+bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
+
+#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
new file mode 100644
index 000000000..aa7fa2a08
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_H__
+#define __ARM64_KVM_HYP_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/alternative.h>
+#include <asm/sysreg.h>
+
+DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
+DECLARE_PER_CPU(unsigned long, kvm_hyp_vector);
+DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
+
+#define read_sysreg_elx(r,nvh,vh)					\
+	({								\
+		u64 reg;						\
+		asm volatile(ALTERNATIVE(__mrs_s("%0", r##nvh),	\
+					 __mrs_s("%0", r##vh),		\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+			     : "=r" (reg));				\
+		reg;							\
+	})
+
+#define write_sysreg_elx(v,r,nvh,vh)					\
+	do {								\
+		u64 __val = (u64)(v);					\
+		asm volatile(ALTERNATIVE(__msr_s(r##nvh, "%x0"),	\
+					 __msr_s(r##vh, "%x0"),		\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 : : "rZ" (__val));		\
+	} while (0)
+
+/*
+ * Unified accessors for registers that have a different encoding
+ * between VHE and non-VHE. They must be specified without their "ELx"
+ * encoding, but with the SYS_ prefix, as defined in asm/sysreg.h.
+ */
+
+#define read_sysreg_el0(r)	read_sysreg_elx(r, _EL0, _EL02)
+#define write_sysreg_el0(v,r)	write_sysreg_elx(v, r, _EL0, _EL02)
+#define read_sysreg_el1(r)	read_sysreg_elx(r, _EL1, _EL12)
+#define write_sysreg_el1(v,r)	write_sysreg_elx(v, r, _EL1, _EL12)
+#define read_sysreg_el2(r)	read_sysreg_elx(r, _EL2, _EL1)
+#define write_sysreg_el2(v,r)	write_sysreg_elx(v, r, _EL2, _EL1)
+
+/*
+ * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the
+ * static inline can allow the compiler to out-of-line this. KVM always wants
+ * the macro version as its always inlined.
+ */
+#define __kvm_swab32(x)	___constant_swab32(x)
+
+int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
+
+void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
+void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
+int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __timer_enable_traps(struct kvm_vcpu *vcpu);
+void __timer_disable_traps(struct kvm_vcpu *vcpu);
+#endif
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
+#else
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
+#endif
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
+void __debug_switch_to_host(struct kvm_vcpu *vcpu);
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+#endif
+
+void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
+void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
+void __sve_restore_state(void *sve_pffr, u32 *fpsr);
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
+void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu);
+#endif
+
+u64 __guest_enter(struct kvm_vcpu *vcpu);
+
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+			       u64 elr, u64 par);
+#endif
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __pkvm_init_switch_pgd(phys_addr_t phys, unsigned long size,
+			    phys_addr_t pgd, void *sp, void *cont_fn);
+int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
+		unsigned long *per_cpu_base, u32 hyp_va_bits);
+void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
+#endif
+
+extern u64 kvm_nvhe_sym(id_aa64pfr0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64pfr1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar2_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val);
+
+#endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
new file mode 100644
index 000000000..778408108
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -0,0 +1,302 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_MMU_H__
+#define __ARM64_KVM_MMU_H__
+
+#include <asm/page.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
+#include <asm/cpufeature.h>
+
+/*
+ * As ARMv8.0 only has the TTBR0_EL2 register, we cannot express
+ * "negative" addresses. This makes it impossible to directly share
+ * mappings with the kernel.
+ *
+ * Instead, give the HYP mode its own VA region at a fixed offset from
+ * the kernel by just masking the top bits (which are all ones for a
+ * kernel address). We need to find out how many bits to mask.
+ *
+ * We want to build a set of page tables that cover both parts of the
+ * idmap (the trampoline page used to initialize EL2), and our normal
+ * runtime VA space, at the same time.
+ *
+ * Given that the kernel uses VA_BITS for its entire address space,
+ * and that half of that space (VA_BITS - 1) is used for the linear
+ * mapping, we can also limit the EL2 space to (VA_BITS - 1).
+ *
+ * The main question is "Within the VA_BITS space, does EL2 use the
+ * top or the bottom half of that space to shadow the kernel's linear
+ * mapping?". As we need to idmap the trampoline page, this is
+ * determined by the range in which this page lives.
+ *
+ * If the page is in the bottom half, we have to use the top half. If
+ * the page is in the top half, we have to use the bottom half:
+ *
+ * T = __pa_symbol(__hyp_idmap_text_start)
+ * if (T & BIT(VA_BITS - 1))
+ *	HYP_VA_MIN = 0  //idmap in upper half
+ * else
+ *	HYP_VA_MIN = 1 << (VA_BITS - 1)
+ * HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1
+ *
+ * When using VHE, there are no separate hyp mappings and all KVM
+ * functionality is already mapped as part of the main kernel
+ * mappings, and none of this applies in that case.
+ */
+
+#ifdef __ASSEMBLY__
+
+#include <asm/alternative.h>
+
+/*
+ * Convert a kernel VA into a HYP VA.
+ * reg: VA to be converted.
+ *
+ * The actual code generation takes place in kvm_update_va_mask, and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_update_va_mask uses the
+ * specific registers encoded in the instructions).
+ */
+.macro kern_hyp_va	reg
+alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask
+	and     \reg, \reg, #1		/* mask with va_mask */
+	ror	\reg, \reg, #1		/* rotate to the first tag bit */
+	add	\reg, \reg, #0		/* insert the low 12 bits of the tag */
+	add	\reg, \reg, #0, lsl 12	/* insert the top 12 bits of the tag */
+	ror	\reg, \reg, #63		/* rotate back */
+alternative_cb_end
+.endm
+
+/*
+ * Convert a hypervisor VA to a PA
+ * reg: hypervisor address to be converted in place
+ * tmp: temporary register
+ */
+.macro hyp_pa reg, tmp
+	ldr_l	\tmp, hyp_physvirt_offset
+	add	\reg, \reg, \tmp
+.endm
+
+/*
+ * Convert a hypervisor VA to a kernel image address
+ * reg: hypervisor address to be converted in place
+ * tmp: temporary register
+ *
+ * The actual code generation takes place in kvm_get_kimage_voffset, and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_get_kimage_voffset uses the
+ * specific registers encoded in the instructions).
+ */
+.macro hyp_kimg_va reg, tmp
+	/* Convert hyp VA -> PA. */
+	hyp_pa	\reg, \tmp
+
+	/* Load kimage_voffset. */
+alternative_cb ARM64_ALWAYS_SYSTEM, kvm_get_kimage_voffset
+	movz	\tmp, #0
+	movk	\tmp, #0, lsl #16
+	movk	\tmp, #0, lsl #32
+	movk	\tmp, #0, lsl #48
+alternative_cb_end
+
+	/* Convert PA -> kimg VA. */
+	add	\reg, \reg, \tmp
+.endm
+
+#else
+
+#include <linux/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/cache.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+#include <asm/kvm_host.h>
+
+void kvm_update_va_mask(struct alt_instr *alt,
+			__le32 *origptr, __le32 *updptr, int nr_inst);
+void kvm_compute_layout(void);
+void kvm_apply_hyp_relocations(void);
+
+#define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
+
+static __always_inline unsigned long __kern_hyp_va(unsigned long v)
+{
+	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
+				    "ror %0, %0, #1\n"
+				    "add %0, %0, #0\n"
+				    "add %0, %0, #0, lsl 12\n"
+				    "ror %0, %0, #63\n",
+				    ARM64_ALWAYS_SYSTEM,
+				    kvm_update_va_mask)
+		     : "+r" (v));
+	return v;
+}
+
+#define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
+
+/*
+ * We currently support using a VM-specified IPA size. For backward
+ * compatibility, the default IPA size is fixed to 40bits.
+ */
+#define KVM_PHYS_SHIFT	(40)
+
+#define kvm_phys_shift(kvm)		VTCR_EL2_IPA(kvm->arch.vtcr)
+#define kvm_phys_size(kvm)		(_AC(1, ULL) << kvm_phys_shift(kvm))
+#define kvm_phys_mask(kvm)		(kvm_phys_size(kvm) - _AC(1, ULL))
+
+#include <asm/kvm_pgtable.h>
+#include <asm/stage2_pgtable.h>
+
+int kvm_share_hyp(void *from, void *to);
+void kvm_unshare_hyp(void *from, void *to);
+int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
+int __create_hyp_mappings(unsigned long start, unsigned long size,
+			  unsigned long phys, enum kvm_pgtable_prot prot);
+int hyp_alloc_private_va_range(size_t size, unsigned long *haddr);
+int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
+			   void __iomem **kaddr,
+			   void __iomem **haddr);
+int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
+			     void **haddr);
+void free_hyp_pgds(void);
+
+void stage2_unmap_vm(struct kvm *kvm);
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu);
+void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
+int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
+			  phys_addr_t pa, unsigned long size, bool writable);
+
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
+
+phys_addr_t kvm_mmu_get_httbr(void);
+phys_addr_t kvm_get_idmap_vector(void);
+int kvm_mmu_init(u32 *hyp_va_bits);
+
+static inline void *__kvm_vector_slot2addr(void *base,
+					   enum arm64_hyp_spectre_vector slot)
+{
+	int idx = slot - (slot != HYP_VECTOR_DIRECT);
+
+	return base + (idx * SZ_2K);
+}
+
+struct kvm;
+
+#define kvm_flush_dcache_to_poc(a,l)	\
+	dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
+{
+	return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+}
+
+static inline void __clean_dcache_guest_page(void *va, size_t size)
+{
+	/*
+	 * With FWB, we ensure that the guest always accesses memory using
+	 * cacheable attributes, and we don't have to clean to PoC when
+	 * faulting in pages. Furthermore, FWB implies IDC, so cleaning to
+	 * PoU is not required either in this case.
+	 */
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+		return;
+
+	kvm_flush_dcache_to_poc(va, size);
+}
+
+static inline void __invalidate_icache_guest_page(void *va, size_t size)
+{
+	if (icache_is_aliasing()) {
+		/* any kind of VIPT cache */
+		icache_inval_all_pou();
+	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
+		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
+		icache_inval_pou((unsigned long)va, (unsigned long)va + size);
+	}
+}
+
+void kvm_set_way_flush(struct kvm_vcpu *vcpu);
+void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
+
+static inline unsigned int kvm_get_vmid_bits(void)
+{
+	int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+
+	return get_vmid_bits(reg);
+}
+
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+				      gpa_t gpa, void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_read_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
+static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+				       const void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_write_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
+#define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
+
+/*
+ * When this is (directly or indirectly) used on the TLB invalidation
+ * path, we rely on a previously issued DSB so that page table updates
+ * and VMID reads are correctly ordered.
+ */
+static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
+{
+	struct kvm_vmid *vmid = &mmu->vmid;
+	u64 vmid_field, baddr;
+	u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
+
+	baddr = mmu->pgd_phys;
+	vmid_field = atomic64_read(&vmid->id) << VTTBR_VMID_SHIFT;
+	vmid_field &= VTTBR_VMID_MASK(kvm_arm_vmid_bits);
+	return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
+}
+
+/*
+ * Must be called from hyp code running at EL2 with an updated VTTBR
+ * and interrupts disabled.
+ */
+static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu,
+					  struct kvm_arch *arch)
+{
+	write_sysreg(arch->vtcr, vtcr_el2);
+	write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
+
+	/*
+	 * ARM errata 1165522 and 1530923 require the actual execution of the
+	 * above before we can switch to the EL1/EL0 translation regime used by
+	 * the guest.
+	 */
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+}
+
+static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
+{
+	return container_of(mmu->arch, struct kvm, arch);
+}
+#endif /* __ASSEMBLY__ */
+#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_mte.h b/arch/arm64/include/asm/kvm_mte.h
new file mode 100644
index 000000000..de002636e
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_mte.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2021 ARM Ltd.
+ */
+#ifndef __ASM_KVM_MTE_H
+#define __ASM_KVM_MTE_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/sysreg.h>
+
+#ifdef CONFIG_ARM64_MTE
+
+.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
+alternative_if_not ARM64_MTE
+	b	.L__skip_switch\@
+alternative_else_nop_endif
+	mrs	\reg1, hcr_el2
+	tbz	\reg1, #(HCR_ATA_SHIFT), .L__skip_switch\@
+
+	mrs_s	\reg1, SYS_RGSR_EL1
+	str	\reg1, [\h_ctxt, #CPU_RGSR_EL1]
+	mrs_s	\reg1, SYS_GCR_EL1
+	str	\reg1, [\h_ctxt, #CPU_GCR_EL1]
+
+	ldr	\reg1, [\g_ctxt, #CPU_RGSR_EL1]
+	msr_s	SYS_RGSR_EL1, \reg1
+	ldr	\reg1, [\g_ctxt, #CPU_GCR_EL1]
+	msr_s	SYS_GCR_EL1, \reg1
+
+.L__skip_switch\@:
+.endm
+
+.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
+alternative_if_not ARM64_MTE
+	b	.L__skip_switch\@
+alternative_else_nop_endif
+	mrs	\reg1, hcr_el2
+	tbz	\reg1, #(HCR_ATA_SHIFT), .L__skip_switch\@
+
+	mrs_s	\reg1, SYS_RGSR_EL1
+	str	\reg1, [\g_ctxt, #CPU_RGSR_EL1]
+	mrs_s	\reg1, SYS_GCR_EL1
+	str	\reg1, [\g_ctxt, #CPU_GCR_EL1]
+
+	ldr	\reg1, [\h_ctxt, #CPU_RGSR_EL1]
+	msr_s	SYS_RGSR_EL1, \reg1
+	ldr	\reg1, [\h_ctxt, #CPU_GCR_EL1]
+	msr_s	SYS_GCR_EL1, \reg1
+
+	isb
+
+.L__skip_switch\@:
+.endm
+
+#else /* !CONFIG_ARM64_MTE */
+
+.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
+.endm
+
+.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
+.endm
+
+#endif /* CONFIG_ARM64_MTE */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_KVM_MTE_H */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
new file mode 100644
index 000000000..3252eb50e
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -0,0 +1,558 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Google LLC
+ * Author: Will Deacon <will@kernel.org>
+ */
+
+#ifndef __ARM64_KVM_PGTABLE_H__
+#define __ARM64_KVM_PGTABLE_H__
+
+#include <linux/bits.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+
+#define KVM_PGTABLE_MAX_LEVELS		4U
+
+/*
+ * The largest supported block sizes for KVM (no 52-bit PA support):
+ *  - 4K (level 1):	1GB
+ *  - 16K (level 2):	32MB
+ *  - 64K (level 2):	512MB
+ */
+#ifdef CONFIG_ARM64_4K_PAGES
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1U
+#else
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
+#endif
+
+static inline u64 kvm_get_parange(u64 mmfr0)
+{
+	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
+				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
+	if (parange > ID_AA64MMFR0_EL1_PARANGE_MAX)
+		parange = ID_AA64MMFR0_EL1_PARANGE_MAX;
+
+	return parange;
+}
+
+typedef u64 kvm_pte_t;
+
+#define KVM_PTE_VALID			BIT(0)
+
+#define KVM_PTE_ADDR_MASK		GENMASK(47, PAGE_SHIFT)
+#define KVM_PTE_ADDR_51_48		GENMASK(15, 12)
+
+static inline bool kvm_pte_valid(kvm_pte_t pte)
+{
+	return pte & KVM_PTE_VALID;
+}
+
+static inline u64 kvm_pte_to_phys(kvm_pte_t pte)
+{
+	u64 pa = pte & KVM_PTE_ADDR_MASK;
+
+	if (PAGE_SHIFT == 16)
+		pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+
+	return pa;
+}
+
+static inline u64 kvm_granule_shift(u32 level)
+{
+	/* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
+	return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
+}
+
+static inline u64 kvm_granule_size(u32 level)
+{
+	return BIT(kvm_granule_shift(level));
+}
+
+static inline bool kvm_level_supports_block_mapping(u32 level)
+{
+	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
+}
+
+/**
+ * struct kvm_pgtable_mm_ops - Memory management callbacks.
+ * @zalloc_page:		Allocate a single zeroed memory page.
+ *				The @arg parameter can be used by the walker
+ *				to pass a memcache. The initial refcount of
+ *				the page is 1.
+ * @zalloc_pages_exact:		Allocate an exact number of zeroed memory pages.
+ *				The @size parameter is in bytes, and is rounded
+ *				up to the next page boundary. The resulting
+ *				allocation is physically contiguous.
+ * @free_pages_exact:		Free an exact number of memory pages previously
+ *				allocated by zalloc_pages_exact.
+ * @get_page:			Increment the refcount on a page.
+ * @put_page:			Decrement the refcount on a page. When the
+ *				refcount reaches 0 the page is automatically
+ *				freed.
+ * @page_count:			Return the refcount of a page.
+ * @phys_to_virt:		Convert a physical address into a virtual
+ *				address	mapped in the current context.
+ * @virt_to_phys:		Convert a virtual address mapped in the current
+ *				context into a physical address.
+ * @dcache_clean_inval_poc:	Clean and invalidate the data cache to the PoC
+ *				for the	specified memory address range.
+ * @icache_inval_pou:		Invalidate the instruction cache to the PoU
+ *				for the specified memory address range.
+ */
+struct kvm_pgtable_mm_ops {
+	void*		(*zalloc_page)(void *arg);
+	void*		(*zalloc_pages_exact)(size_t size);
+	void		(*free_pages_exact)(void *addr, size_t size);
+	void		(*get_page)(void *addr);
+	void		(*put_page)(void *addr);
+	int		(*page_count)(void *addr);
+	void*		(*phys_to_virt)(phys_addr_t phys);
+	phys_addr_t	(*virt_to_phys)(void *addr);
+	void		(*dcache_clean_inval_poc)(void *addr, size_t size);
+	void		(*icache_inval_pou)(void *addr, size_t size);
+};
+
+/**
+ * enum kvm_pgtable_stage2_flags - Stage-2 page-table flags.
+ * @KVM_PGTABLE_S2_NOFWB:	Don't enforce Normal-WB even if the CPUs have
+ *				ARM64_HAS_STAGE2_FWB.
+ * @KVM_PGTABLE_S2_IDMAP:	Only use identity mappings.
+ */
+enum kvm_pgtable_stage2_flags {
+	KVM_PGTABLE_S2_NOFWB			= BIT(0),
+	KVM_PGTABLE_S2_IDMAP			= BIT(1),
+};
+
+/**
+ * enum kvm_pgtable_prot - Page-table permissions and attributes.
+ * @KVM_PGTABLE_PROT_X:		Execute permission.
+ * @KVM_PGTABLE_PROT_W:		Write permission.
+ * @KVM_PGTABLE_PROT_R:		Read permission.
+ * @KVM_PGTABLE_PROT_DEVICE:	Device attributes.
+ * @KVM_PGTABLE_PROT_SW0:	Software bit 0.
+ * @KVM_PGTABLE_PROT_SW1:	Software bit 1.
+ * @KVM_PGTABLE_PROT_SW2:	Software bit 2.
+ * @KVM_PGTABLE_PROT_SW3:	Software bit 3.
+ */
+enum kvm_pgtable_prot {
+	KVM_PGTABLE_PROT_X			= BIT(0),
+	KVM_PGTABLE_PROT_W			= BIT(1),
+	KVM_PGTABLE_PROT_R			= BIT(2),
+
+	KVM_PGTABLE_PROT_DEVICE			= BIT(3),
+
+	KVM_PGTABLE_PROT_SW0			= BIT(55),
+	KVM_PGTABLE_PROT_SW1			= BIT(56),
+	KVM_PGTABLE_PROT_SW2			= BIT(57),
+	KVM_PGTABLE_PROT_SW3			= BIT(58),
+};
+
+#define KVM_PGTABLE_PROT_RW	(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
+#define KVM_PGTABLE_PROT_RWX	(KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X)
+
+#define PKVM_HOST_MEM_PROT	KVM_PGTABLE_PROT_RWX
+#define PKVM_HOST_MMIO_PROT	KVM_PGTABLE_PROT_RW
+
+#define PAGE_HYP		KVM_PGTABLE_PROT_RW
+#define PAGE_HYP_EXEC		(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X)
+#define PAGE_HYP_RO		(KVM_PGTABLE_PROT_R)
+#define PAGE_HYP_DEVICE		(PAGE_HYP | KVM_PGTABLE_PROT_DEVICE)
+
+typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
+					   enum kvm_pgtable_prot prot);
+
+/**
+ * struct kvm_pgtable - KVM page-table.
+ * @ia_bits:		Maximum input address size, in bits.
+ * @start_level:	Level at which the page-table walk starts.
+ * @pgd:		Pointer to the first top-level entry of the page-table.
+ * @mm_ops:		Memory management callbacks.
+ * @mmu:		Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
+ * @flags:		Stage-2 page-table flags.
+ * @force_pte_cb:	Function that returns true if page level mappings must
+ *			be used instead of block mappings.
+ */
+struct kvm_pgtable {
+	u32					ia_bits;
+	u32					start_level;
+	kvm_pte_t				*pgd;
+	struct kvm_pgtable_mm_ops		*mm_ops;
+
+	/* Stage-2 only */
+	struct kvm_s2_mmu			*mmu;
+	enum kvm_pgtable_stage2_flags		flags;
+	kvm_pgtable_force_pte_cb_t		force_pte_cb;
+};
+
+/**
+ * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
+ * @KVM_PGTABLE_WALK_LEAF:		Visit leaf entries, including invalid
+ *					entries.
+ * @KVM_PGTABLE_WALK_TABLE_PRE:		Visit table entries before their
+ *					children.
+ * @KVM_PGTABLE_WALK_TABLE_POST:	Visit table entries after their
+ *					children.
+ */
+enum kvm_pgtable_walk_flags {
+	KVM_PGTABLE_WALK_LEAF			= BIT(0),
+	KVM_PGTABLE_WALK_TABLE_PRE		= BIT(1),
+	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
+};
+
+typedef int (*kvm_pgtable_visitor_fn_t)(u64 addr, u64 end, u32 level,
+					kvm_pte_t *ptep,
+					enum kvm_pgtable_walk_flags flag,
+					void * const arg);
+
+/**
+ * struct kvm_pgtable_walker - Hook into a page-table walk.
+ * @cb:		Callback function to invoke during the walk.
+ * @arg:	Argument passed to the callback function.
+ * @flags:	Bitwise-OR of flags to identify the entry types on which to
+ *		invoke the callback function.
+ */
+struct kvm_pgtable_walker {
+	const kvm_pgtable_visitor_fn_t		cb;
+	void * const				arg;
+	const enum kvm_pgtable_walk_flags	flags;
+};
+
+/**
+ * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table.
+ * @pgt:	Uninitialised page-table structure to initialise.
+ * @va_bits:	Maximum virtual address bits.
+ * @mm_ops:	Memory management callbacks.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
+			 struct kvm_pgtable_mm_ops *mm_ops);
+
+/**
+ * kvm_pgtable_hyp_destroy() - Destroy an unused hypervisor stage-1 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_hyp_init().
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt);
+
+/**
+ * kvm_pgtable_hyp_map() - Install a mapping in a hypervisor stage-1 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_hyp_init().
+ * @addr:	Virtual address at which to place the mapping.
+ * @size:	Size of the mapping.
+ * @phys:	Physical address of the memory to map.
+ * @prot:	Permissions and attributes for the mapping.
+ *
+ * The offset of @addr within a page is ignored, @size is rounded-up to
+ * the next page boundary and @phys is rounded-down to the previous page
+ * boundary.
+ *
+ * If device attributes are not explicitly requested in @prot, then the
+ * mapping will be normal, cacheable. Attempts to install a new mapping
+ * for a virtual address that is already mapped will be rejected with an
+ * error and a WARN().
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
+			enum kvm_pgtable_prot prot);
+
+/**
+ * kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_hyp_init().
+ * @addr:	Virtual address from which to remove the mapping.
+ * @size:	Size of the mapping.
+ *
+ * The offset of @addr within a page is ignored, @size is rounded-up to
+ * the next page boundary and @phys is rounded-down to the previous page
+ * boundary.
+ *
+ * TLB invalidation is performed for each page-table entry cleared during the
+ * unmapping operation and the reference count for the page-table page
+ * containing the cleared entry is decremented, with unreferenced pages being
+ * freed. The unmapping operation will stop early if it encounters either an
+ * invalid page-table entry or a valid block mapping which maps beyond the range
+ * being unmapped.
+ *
+ * Return: Number of bytes unmapped, which may be 0.
+ */
+u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
+/**
+ * kvm_get_vtcr() - Helper to construct VTCR_EL2
+ * @mmfr0:	Sanitized value of SYS_ID_AA64MMFR0_EL1 register.
+ * @mmfr1:	Sanitized value of SYS_ID_AA64MMFR1_EL1 register.
+ * @phys_shfit:	Value to set in VTCR_EL2.T0SZ.
+ *
+ * The VTCR value is common across all the physical CPUs on the system.
+ * We use system wide sanitised values to fill in different fields,
+ * except for Hardware Management of Access Flags. HA Flag is set
+ * unconditionally on all CPUs, as it is safe to run with or without
+ * the feature and the bit is RES0 on CPUs that don't support it.
+ *
+ * Return: VTCR_EL2 value
+ */
+u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift);
+
+/**
+ * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table.
+ * @pgt:	Uninitialised page-table structure to initialise.
+ * @mmu:	S2 MMU context for this S2 translation
+ * @mm_ops:	Memory management callbacks.
+ * @flags:	Stage-2 configuration flags.
+ * @force_pte_cb: Function that returns true if page level mappings must
+ *		be used instead of block mappings.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
+			      struct kvm_pgtable_mm_ops *mm_ops,
+			      enum kvm_pgtable_stage2_flags flags,
+			      kvm_pgtable_force_pte_cb_t force_pte_cb);
+
+#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \
+	__kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL)
+
+/**
+ * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+
+/**
+ * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address at which to place the mapping.
+ * @size:	Size of the mapping.
+ * @phys:	Physical address of the memory to map.
+ * @prot:	Permissions and attributes for the mapping.
+ * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
+ *		page-table pages.
+ *
+ * The offset of @addr within a page is ignored, @size is rounded-up to
+ * the next page boundary and @phys is rounded-down to the previous page
+ * boundary.
+ *
+ * If device attributes are not explicitly requested in @prot, then the
+ * mapping will be normal, cacheable.
+ *
+ * Note that the update of a valid leaf PTE in this function will be aborted,
+ * if it's trying to recreate the exact same mapping or only change the access
+ * permissions. Instead, the vCPU will exit one more time from guest if still
+ * needed and then go through the path of relaxing permissions.
+ *
+ * Note that this function will both coalesce existing table entries and split
+ * existing block mappings, relying on page-faults to fault back areas outside
+ * of the new mapping lazily.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			   u64 phys, enum kvm_pgtable_prot prot,
+			   void *mc);
+
+/**
+ * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to
+ *				    track ownership.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Base intermediate physical address to annotate.
+ * @size:	Size of the annotated range.
+ * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
+ *		page-table pages.
+ * @owner_id:	Unique identifier for the owner of the page.
+ *
+ * By default, all page-tables are owned by identifier 0. This function can be
+ * used to mark portions of the IPA space as owned by other entities. When a
+ * stage 2 is used with identity-mappings, these annotations allow to use the
+ * page-table data structure as a simple rmap.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
+				 void *mc, u8 owner_id);
+
+/**
+ * kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address from which to remove the mapping.
+ * @size:	Size of the mapping.
+ *
+ * The offset of @addr within a page is ignored and @size is rounded-up to
+ * the next page boundary.
+ *
+ * TLB invalidation is performed for each page-table entry cleared during the
+ * unmapping operation and the reference count for the page-table page
+ * containing the cleared entry is decremented, with unreferenced pages being
+ * freed. Unmapping a cacheable page will ensure that it is clean to the PoC if
+ * FWB is not supported by the CPU.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
+/**
+ * kvm_pgtable_stage2_wrprotect() - Write-protect guest stage-2 address range
+ *                                  without TLB invalidation.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address from which to write-protect,
+ * @size:	Size of the range.
+ *
+ * The offset of @addr within a page is ignored and @size is rounded-up to
+ * the next page boundary.
+ *
+ * Note that it is the caller's responsibility to invalidate the TLB after
+ * calling this function to ensure that the updated permissions are visible
+ * to the CPUs.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
+/**
+ * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * The offset of @addr within a page is ignored.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * set the access flag in that entry.
+ *
+ * Return: The old page-table entry prior to setting the flag, 0 on failure.
+ */
+kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
+
+/**
+ * kvm_pgtable_stage2_mkold() - Clear the access flag in a page-table entry.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * The offset of @addr within a page is ignored.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * clear the access flag in that entry.
+ *
+ * Note that it is the caller's responsibility to invalidate the TLB after
+ * calling this function to ensure that the updated permissions are visible
+ * to the CPUs.
+ *
+ * Return: The old page-table entry prior to clearing the flag, 0 on failure.
+ */
+kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
+
+/**
+ * kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a
+ *				      page-table entry.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ * @prot:	Additional permissions to grant for the mapping.
+ *
+ * The offset of @addr within a page is ignored.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * relax the permissions in that entry according to the read, write and
+ * execute permissions specified by @prot. No permissions are removed, and
+ * TLB invalidation is performed after updating the entry. Software bits cannot
+ * be set or cleared using kvm_pgtable_stage2_relax_perms().
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
+				   enum kvm_pgtable_prot prot);
+
+/**
+ * kvm_pgtable_stage2_is_young() - Test whether a page-table entry has the
+ *				   access flag set.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * The offset of @addr within a page is ignored.
+ *
+ * Return: True if the page-table entry has the access flag set, false otherwise.
+ */
+bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
+
+/**
+ * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
+ * 				      of Coherency for guest stage-2 address
+ *				      range.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address from which to flush.
+ * @size:	Size of the range.
+ *
+ * The offset of @addr within a page is ignored and @size is rounded-up to
+ * the next page boundary.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
+/**
+ * kvm_pgtable_walk() - Walk a page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().
+ * @addr:	Input address for the start of the walk.
+ * @size:	Size of the range to walk.
+ * @walker:	Walker callback description.
+ *
+ * The offset of @addr within a page is ignored and @size is rounded-up to
+ * the next page boundary.
+ *
+ * The walker will walk the page-table entries corresponding to the input
+ * address range specified, visiting entries according to the walker flags.
+ * Invalid entries are treated as leaf entries. Leaf entries are reloaded
+ * after invoking the walker callback, allowing the walker to descend into
+ * a newly installed table.
+ *
+ * Returning a negative error code from the walker callback function will
+ * terminate the walk immediately with the same error code.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
+		     struct kvm_pgtable_walker *walker);
+
+/**
+ * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry
+ *			    with its level.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_*_init()
+ *		or a similar initialiser.
+ * @addr:	Input address for the start of the walk.
+ * @ptep:	Pointer to storage for the retrieved PTE.
+ * @level:	Pointer to storage for the level of the retrieved PTE.
+ *
+ * The offset of @addr within a page is ignored.
+ *
+ * The walker will walk the page-table entries corresponding to the input
+ * address specified, retrieving the leaf corresponding to this address.
+ * Invalid entries are treated as leaf entries.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
+			 kvm_pte_t *ptep, u32 *level);
+
+/**
+ * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
+ *				   stage-2 Page-Table Entry.
+ * @pte:	Page-table entry
+ *
+ * Return: protection attributes of the page-table entry in the enum
+ *	   kvm_pgtable_prot format.
+ */
+enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte);
+
+/**
+ * kvm_pgtable_hyp_pte_prot() - Retrieve the protection attributes of a stage-1
+ *				Page-Table Entry.
+ * @pte:	Page-table entry
+ *
+ * Return: protection attributes of the page-table entry in the enum
+ *	   kvm_pgtable_prot format.
+ */
+enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte);
+#endif	/* __ARM64_KVM_PGTABLE_H__ */
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
new file mode 100644
index 000000000..9f4ad2a8d
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 - Google LLC
+ * Author: Quentin Perret <qperret@google.com>
+ */
+#ifndef __ARM64_KVM_PKVM_H__
+#define __ARM64_KVM_PKVM_H__
+
+#include <linux/memblock.h>
+#include <asm/kvm_pgtable.h>
+
+#define HYP_MEMBLOCK_REGIONS 128
+
+extern struct memblock_region kvm_nvhe_sym(hyp_memory)[];
+extern unsigned int kvm_nvhe_sym(hyp_memblock_nr);
+
+static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
+{
+	unsigned long total = 0, i;
+
+	/* Provision the worst case scenario */
+	for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+		nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE);
+		total += nr_pages;
+	}
+
+	return total;
+}
+
+static inline unsigned long __hyp_pgtable_total_pages(void)
+{
+	unsigned long res = 0, i;
+
+	/* Cover all of memory with page-granularity */
+	for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) {
+		struct memblock_region *reg = &kvm_nvhe_sym(hyp_memory)[i];
+		res += __hyp_pgtable_max_pages(reg->size >> PAGE_SHIFT);
+	}
+
+	return res;
+}
+
+static inline unsigned long hyp_s1_pgtable_pages(void)
+{
+	unsigned long res;
+
+	res = __hyp_pgtable_total_pages();
+
+	/* Allow 1 GiB for private mappings */
+	res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
+
+	return res;
+}
+
+static inline unsigned long host_s2_pgtable_pages(void)
+{
+	unsigned long res;
+
+	/*
+	 * Include an extra 16 pages to safely upper-bound the worst case of
+	 * concatenated pgds.
+	 */
+	res = __hyp_pgtable_total_pages() + 16;
+
+	/* Allow 1 GiB for MMIO mappings */
+	res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
+
+	return res;
+}
+
+#endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h
new file mode 100644
index 000000000..0cd096525
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_ptrauth.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* arch/arm64/include/asm/kvm_ptrauth.h: Guest/host ptrauth save/restore
+ * Copyright 2019 Arm Limited
+ * Authors: Mark Rutland <mark.rutland@arm.com>
+ *         Amit Daniel Kachhap <amit.kachhap@arm.com>
+ */
+
+#ifndef __ASM_KVM_PTRAUTH_H
+#define __ASM_KVM_PTRAUTH_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/sysreg.h>
+
+#ifdef	CONFIG_ARM64_PTR_AUTH
+
+#define PTRAUTH_REG_OFFSET(x)	(x - CPU_APIAKEYLO_EL1)
+
+/*
+ * CPU_AP*_EL1 values exceed immediate offset range (512) for stp
+ * instruction so below macros takes CPU_APIAKEYLO_EL1 as base and
+ * calculates the offset of the keys from this base to avoid an extra add
+ * instruction. These macros assumes the keys offsets follow the order of
+ * the sysreg enum in kvm_host.h.
+ */
+.macro	ptrauth_save_state base, reg1, reg2
+	mrs_s	\reg1, SYS_APIAKEYLO_EL1
+	mrs_s	\reg2, SYS_APIAKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIAKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APIBKEYLO_EL1
+	mrs_s	\reg2, SYS_APIBKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIBKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APDAKEYLO_EL1
+	mrs_s	\reg2, SYS_APDAKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDAKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APDBKEYLO_EL1
+	mrs_s	\reg2, SYS_APDBKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDBKEYLO_EL1)]
+	mrs_s	\reg1, SYS_APGAKEYLO_EL1
+	mrs_s	\reg2, SYS_APGAKEYHI_EL1
+	stp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APGAKEYLO_EL1)]
+.endm
+
+.macro	ptrauth_restore_state base, reg1, reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIAKEYLO_EL1)]
+	msr_s	SYS_APIAKEYLO_EL1, \reg1
+	msr_s	SYS_APIAKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APIBKEYLO_EL1)]
+	msr_s	SYS_APIBKEYLO_EL1, \reg1
+	msr_s	SYS_APIBKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDAKEYLO_EL1)]
+	msr_s	SYS_APDAKEYLO_EL1, \reg1
+	msr_s	SYS_APDAKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APDBKEYLO_EL1)]
+	msr_s	SYS_APDBKEYLO_EL1, \reg1
+	msr_s	SYS_APDBKEYHI_EL1, \reg2
+	ldp	\reg1, \reg2, [\base, #PTRAUTH_REG_OFFSET(CPU_APGAKEYLO_EL1)]
+	msr_s	SYS_APGAKEYLO_EL1, \reg1
+	msr_s	SYS_APGAKEYHI_EL1, \reg2
+.endm
+
+/*
+ * Both ptrauth_switch_to_guest and ptrauth_switch_to_hyp macros will
+ * check for the presence ARM64_HAS_ADDRESS_AUTH, which is defined as
+ * (ARM64_HAS_ADDRESS_AUTH_ARCH || ARM64_HAS_ADDRESS_AUTH_IMP_DEF) and
+ * then proceed ahead with the save/restore of Pointer Authentication
+ * key registers if enabled for the guest.
+ */
+.macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
+alternative_else_nop_endif
+	mrs	\reg1, hcr_el2
+	and	\reg1, \reg1, #(HCR_API | HCR_APK)
+	cbz	\reg1, .L__skip_switch\@
+	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
+	ptrauth_restore_state	\reg1, \reg2, \reg3
+.L__skip_switch\@:
+.endm
+
+.macro ptrauth_switch_to_hyp g_ctxt, h_ctxt, reg1, reg2, reg3
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.L__skip_switch\@
+alternative_else_nop_endif
+	mrs	\reg1, hcr_el2
+	and	\reg1, \reg1, #(HCR_API | HCR_APK)
+	cbz	\reg1, .L__skip_switch\@
+	add	\reg1, \g_ctxt, #CPU_APIAKEYLO_EL1
+	ptrauth_save_state	\reg1, \reg2, \reg3
+	add	\reg1, \h_ctxt, #CPU_APIAKEYLO_EL1
+	ptrauth_restore_state	\reg1, \reg2, \reg3
+	isb
+.L__skip_switch\@:
+.endm
+
+#else /* !CONFIG_ARM64_PTR_AUTH */
+.macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3
+.endm
+.macro ptrauth_switch_to_hyp g_ctxt, h_ctxt, reg1, reg2, reg3
+.endm
+#endif /* CONFIG_ARM64_PTR_AUTH */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_KVM_PTRAUTH_H */
diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h
new file mode 100644
index 000000000..87e10d9a6
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_ras.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018 - Arm Ltd */
+
+#ifndef __ARM64_KVM_RAS_H__
+#define __ARM64_KVM_RAS_H__
+
+#include <linux/acpi.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+#include <asm/acpi.h>
+
+/*
+ * Was this synchronous external abort a RAS notification?
+ * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
+ */
+static inline int kvm_handle_guest_sea(phys_addr_t addr, u64 esr)
+{
+	/* apei_claim_sea(NULL) expects to mask interrupts itself */
+	lockdep_assert_irqs_enabled();
+
+	return apei_claim_sea(NULL);
+}
+
+#endif /* __ARM64_KVM_RAS_H__ */
diff --git a/arch/arm64/include/asm/kvm_types.h b/arch/arm64/include/asm/kvm_types.h
new file mode 100644
index 000000000..9a126b9e2
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_types.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_KVM_TYPES_H
+#define _ASM_ARM64_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40
+
+#endif /* _ASM_ARM64_KVM_TYPES_H */
+
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
new file mode 100644
index 000000000..1436fa1cd
--- /dev/null
+++ b/arch/arm64/include/asm/linkage.h
@@ -0,0 +1,46 @@
+#ifndef __ASM_LINKAGE_H
+#define __ASM_LINKAGE_H
+
+#ifdef __ASSEMBLY__
+#include <asm/assembler.h>
+#endif
+
+#define __ALIGN		.align 2
+#define __ALIGN_STR	".align 2"
+
+/*
+ * When using in-kernel BTI we need to ensure that PCS-conformant
+ * assembly functions have suitable annotations.  Override
+ * SYM_FUNC_START to insert a BTI landing pad at the start of
+ * everything, the override is done unconditionally so we're more
+ * likely to notice any drift from the overridden definitions.
+ */
+#define SYM_FUNC_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	bti c ;
+
+#define SYM_FUNC_START_NOALIGN(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
+	bti c ;
+
+#define SYM_FUNC_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)	\
+	bti c ;
+
+#define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
+	bti c ;
+
+#define SYM_FUNC_START_WEAK(name)			\
+	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)	\
+	bti c ;
+
+#define SYM_FUNC_START_WEAK_NOALIGN(name)		\
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
+	bti c ;
+
+#define SYM_TYPED_FUNC_START(name)				\
+	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)	\
+	bti c ;
+
+#endif
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
new file mode 100644
index 000000000..c503db8e7
--- /dev/null
+++ b/arch/arm64/include/asm/lse.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_LSE_H
+#define __ASM_LSE_H
+
+#include <asm/atomic_ll_sc.h>
+
+#ifdef CONFIG_ARM64_LSE_ATOMICS
+
+#define __LSE_PREAMBLE	".arch_extension lse\n"
+
+#include <linux/compiler_types.h>
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/stringify.h>
+#include <asm/alternative.h>
+#include <asm/alternative-macros.h>
+#include <asm/atomic_lse.h>
+#include <asm/cpucaps.h>
+
+static __always_inline bool system_uses_lse_atomics(void)
+{
+	return alternative_has_feature_likely(ARM64_HAS_LSE_ATOMICS);
+}
+
+#define __lse_ll_sc_body(op, ...)					\
+({									\
+	system_uses_lse_atomics() ?					\
+		__lse_##op(__VA_ARGS__) :				\
+		__ll_sc_##op(__VA_ARGS__);				\
+})
+
+/* In-line patching at runtime */
+#define ARM64_LSE_ATOMIC_INSN(llsc, lse)				\
+	ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS)
+
+#else	/* CONFIG_ARM64_LSE_ATOMICS */
+
+static inline bool system_uses_lse_atomics(void) { return false; }
+
+#define __lse_ll_sc_body(op, ...)		__ll_sc_##op(__VA_ARGS__)
+
+#define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc
+
+#endif	/* CONFIG_ARM64_LSE_ATOMICS */
+#endif	/* __ASM_LSE_H */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
new file mode 100644
index 000000000..9dd08cd33
--- /dev/null
+++ b/arch/arm64/include/asm/memory.h
@@ -0,0 +1,395 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/memory.h
+ *
+ * Copyright (C) 2000-2002 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Note: this file should not be included by non-asm/.h files
+ */
+#ifndef __ASM_MEMORY_H
+#define __ASM_MEMORY_H
+
+#include <linux/const.h>
+#include <linux/sizes.h>
+#include <asm/page-def.h>
+
+/*
+ * Size of the PCI I/O space. This must remain a power of two so that
+ * IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses.
+ */
+#define PCI_IO_SIZE		SZ_16M
+
+/*
+ * VMEMMAP_SIZE - allows the whole linear region to be covered by
+ *                a struct page array
+ *
+ * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE
+ * needs to cover the memory region from the beginning of the 52-bit
+ * PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to
+ * keep a constant PAGE_OFFSET and "fallback" to using the higher end
+ * of the VMEMMAP where 52-bit support is not available in hardware.
+ */
+#define VMEMMAP_SHIFT	(PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT)
+#define VMEMMAP_SIZE	((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) >> VMEMMAP_SHIFT)
+
+/*
+ * PAGE_OFFSET - the virtual address of the start of the linear map, at the
+ *               start of the TTBR1 address space.
+ * PAGE_END - the end of the linear map, where all other kernel mappings begin.
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image.
+ * VA_BITS - the maximum number of bits for virtual addresses.
+ */
+#define VA_BITS			(CONFIG_ARM64_VA_BITS)
+#define _PAGE_OFFSET(va)	(-(UL(1) << (va)))
+#define PAGE_OFFSET		(_PAGE_OFFSET(VA_BITS))
+#define KIMAGE_VADDR		(MODULES_END)
+#define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
+#define MODULES_VADDR		(_PAGE_END(VA_BITS_MIN))
+#define MODULES_VSIZE		(SZ_128M)
+#define VMEMMAP_START		(-(UL(1) << (VA_BITS - VMEMMAP_SHIFT)))
+#define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
+#define PCI_IO_END		(VMEMMAP_START - SZ_8M)
+#define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
+#define FIXADDR_TOP		(VMEMMAP_START - SZ_32M)
+
+#if VA_BITS > 48
+#define VA_BITS_MIN		(48)
+#else
+#define VA_BITS_MIN		(VA_BITS)
+#endif
+
+#define _PAGE_END(va)		(-(UL(1) << ((va) - 1)))
+
+#define KERNEL_START		_text
+#define KERNEL_END		_end
+
+/*
+ * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual
+ * address space for the shadow region respectively. They can bloat the stack
+ * significantly, so double the (minimum) stack size when they are in use.
+ */
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+#define KASAN_SHADOW_END	((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \
+					+ KASAN_SHADOW_OFFSET)
+#define PAGE_END		(KASAN_SHADOW_END - (1UL << (vabits_actual - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_THREAD_SHIFT	1
+#else
+#define KASAN_THREAD_SHIFT	0
+#define PAGE_END		(_PAGE_END(VA_BITS_MIN))
+#endif /* CONFIG_KASAN */
+
+#define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
+
+/*
+ * VMAP'd stacks are allocated at page granularity, so we must ensure that such
+ * stacks are a multiple of page size.
+ */
+#if defined(CONFIG_VMAP_STACK) && (MIN_THREAD_SHIFT < PAGE_SHIFT)
+#define THREAD_SHIFT		PAGE_SHIFT
+#else
+#define THREAD_SHIFT		MIN_THREAD_SHIFT
+#endif
+
+#if THREAD_SHIFT >= PAGE_SHIFT
+#define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
+#endif
+
+#define THREAD_SIZE		(UL(1) << THREAD_SHIFT)
+
+/*
+ * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by
+ * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry
+ * assembly.
+ */
+#ifdef CONFIG_VMAP_STACK
+#define THREAD_ALIGN		(2 * THREAD_SIZE)
+#else
+#define THREAD_ALIGN		THREAD_SIZE
+#endif
+
+#define IRQ_STACK_SIZE		THREAD_SIZE
+
+#define OVERFLOW_STACK_SIZE	SZ_4K
+
+/*
+ * With the minimum frame size of [x29, x30], exactly half the combined
+ * sizes of the hyp and overflow stacks is the maximum size needed to
+ * save the unwinded stacktrace; plus an additional entry to delimit the
+ * end.
+ */
+#define NVHE_STACKTRACE_SIZE	((OVERFLOW_STACK_SIZE + PAGE_SIZE) / 2 + sizeof(long))
+
+/*
+ * Alignment of kernel segments (e.g. .text, .data).
+ *
+ *  4 KB granule:  16 level 3 entries, with contiguous bit
+ * 16 KB granule:   4 level 3 entries, without contiguous bit
+ * 64 KB granule:   1 level 3 entry
+ */
+#define SEGMENT_ALIGN		SZ_64K
+
+/*
+ * Memory types available.
+ *
+ * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in
+ *	      the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note
+ *	      that protection_map[] only contains MT_NORMAL attributes.
+ */
+#define MT_NORMAL		0
+#define MT_NORMAL_TAGGED	1
+#define MT_NORMAL_NC		2
+#define MT_DEVICE_nGnRnE	3
+#define MT_DEVICE_nGnRE		4
+
+/*
+ * Memory types for Stage-2 translation
+ */
+#define MT_S2_NORMAL		0xf
+#define MT_S2_DEVICE_nGnRE	0x1
+
+/*
+ * Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001
+ * Stage-2 enforces Normal-WB and Device-nGnRE
+ */
+#define MT_S2_FWB_NORMAL	6
+#define MT_S2_FWB_DEVICE_nGnRE	1
+
+#ifdef CONFIG_ARM64_4K_PAGES
+#define IOREMAP_MAX_ORDER	(PUD_SHIFT)
+#else
+#define IOREMAP_MAX_ORDER	(PMD_SHIFT)
+#endif
+
+/*
+ *  Open-coded (swapper_pg_dir - reserved_pg_dir) as this cannot be calculated
+ *  until link time.
+ */
+#define RESERVED_SWAPPER_OFFSET	(PAGE_SIZE)
+
+/*
+ *  Open-coded (swapper_pg_dir - tramp_pg_dir) as this cannot be calculated
+ *  until link time.
+ */
+#define TRAMP_SWAPPER_OFFSET	(2 * PAGE_SIZE)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/mmdebug.h>
+#include <linux/types.h>
+#include <asm/bug.h>
+
+#if VA_BITS > 48
+extern u64			vabits_actual;
+#else
+#define vabits_actual		((u64)VA_BITS)
+#endif
+
+extern s64			memstart_addr;
+/* PHYS_OFFSET - the physical address of the start of memory. */
+#define PHYS_OFFSET		({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
+
+/* the virtual base of the kernel image */
+extern u64			kimage_vaddr;
+
+/* the offset between the kernel virtual and physical mappings */
+extern u64			kimage_voffset;
+
+static inline unsigned long kaslr_offset(void)
+{
+	return kimage_vaddr - KIMAGE_VADDR;
+}
+
+/*
+ * Allow all memory at the discovery stage. We will clip it later.
+ */
+#define MIN_MEMBLOCK_ADDR	0
+#define MAX_MEMBLOCK_ADDR	U64_MAX
+
+/*
+ * PFNs are used to describe any physical page; this means
+ * PFN 0 == physical address 0.
+ *
+ * This is the PFN of the first RAM page in the kernel
+ * direct-mapped view.  We assume this is the first page
+ * of RAM in the mem_map as well.
+ */
+#define PHYS_PFN_OFFSET	(PHYS_OFFSET >> PAGE_SHIFT)
+
+/*
+ * When dealing with data aborts, watchpoints, or instruction traps we may end
+ * up with a tagged userland pointer. Clear the tag to get a sane pointer to
+ * pass on to access_ok(), for instance.
+ */
+#define __untagged_addr(addr)	\
+	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
+
+#define untagged_addr(addr)	({					\
+	u64 __addr = (__force u64)(addr);					\
+	__addr &= __untagged_addr(__addr);				\
+	(__force __typeof__(addr))__addr;				\
+})
+
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
+#define __tag_shifted(tag)	((u64)(tag) << 56)
+#define __tag_reset(addr)	__untagged_addr(addr)
+#define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
+#else
+#define __tag_shifted(tag)	0UL
+#define __tag_reset(addr)	(addr)
+#define __tag_get(addr)		0
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
+
+static inline const void *__tag_set(const void *addr, u8 tag)
+{
+	u64 __addr = (u64)addr & ~__tag_shifted(0xff);
+	return (const void *)(__addr | __tag_shifted(tag));
+}
+
+#ifdef CONFIG_KASAN_HW_TAGS
+#define arch_enable_tagging_sync()		mte_enable_kernel_sync()
+#define arch_enable_tagging_async()		mte_enable_kernel_async()
+#define arch_enable_tagging_asymm()		mte_enable_kernel_asymm()
+#define arch_force_async_tag_fault()		mte_check_tfsr_exit()
+#define arch_get_random_tag()			mte_get_random_tag()
+#define arch_get_mem_tag(addr)			mte_get_mem_tag(addr)
+#define arch_set_mem_tag_range(addr, size, tag, init)	\
+			mte_set_mem_tag_range((addr), (size), (tag), (init))
+#endif /* CONFIG_KASAN_HW_TAGS */
+
+/*
+ * Physical vs virtual RAM address space conversion.  These are
+ * private definitions which should NOT be used outside memory.h
+ * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
+ */
+
+
+/*
+ * Check whether an arbitrary address is within the linear map, which
+ * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the
+ * kernel's TTBR1 address range.
+ */
+#define __is_lm_address(addr)	(((u64)(addr) - PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
+
+#define __lm_to_phys(addr)	(((addr) - PAGE_OFFSET) + PHYS_OFFSET)
+#define __kimg_to_phys(addr)	((addr) - kimage_voffset)
+
+#define __virt_to_phys_nodebug(x) ({					\
+	phys_addr_t __x = (phys_addr_t)(__tag_reset(x));		\
+	__is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x);	\
+})
+
+#define __pa_symbol_nodebug(x)	__kimg_to_phys((phys_addr_t)(x))
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern phys_addr_t __virt_to_phys(unsigned long x);
+extern phys_addr_t __phys_addr_symbol(unsigned long x);
+#else
+#define __virt_to_phys(x)	__virt_to_phys_nodebug(x)
+#define __phys_addr_symbol(x)	__pa_symbol_nodebug(x)
+#endif /* CONFIG_DEBUG_VIRTUAL */
+
+#define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
+#define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
+
+/*
+ * Convert a page to/from a physical address
+ */
+#define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
+#define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
+
+/*
+ * Note: Drivers should NOT use these.  They are the wrong
+ * translation for translating DMA addresses.  Use the driver
+ * DMA support - see dma-mapping.h.
+ */
+#define virt_to_phys virt_to_phys
+static inline phys_addr_t virt_to_phys(const volatile void *x)
+{
+	return __virt_to_phys((unsigned long)(x));
+}
+
+#define phys_to_virt phys_to_virt
+static inline void *phys_to_virt(phys_addr_t x)
+{
+	return (void *)(__phys_to_virt(x));
+}
+
+/*
+ * Drivers should NOT use these either.
+ */
+#define __pa(x)			__virt_to_phys((unsigned long)(x))
+#define __pa_symbol(x)		__phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0))
+#define __pa_nodebug(x)		__virt_to_phys_nodebug((unsigned long)(x))
+#define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
+#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define virt_to_pfn(x)		__phys_to_pfn(__virt_to_phys((unsigned long)(x)))
+#define sym_to_pfn(x)		__phys_to_pfn(__pa_symbol(x))
+
+/*
+ *  virt_to_page(x)	convert a _valid_ virtual address to struct page *
+ *  virt_addr_valid(x)	indicates whether a virtual address is valid
+ */
+#define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
+
+#if defined(CONFIG_DEBUG_VIRTUAL)
+#define page_to_virt(x)	({						\
+	__typeof__(x) __page = x;					\
+	void *__addr = __va(page_to_phys(__page));			\
+	(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
+#define virt_to_page(x)		pfn_to_page(virt_to_pfn(x))
+#else
+#define page_to_virt(x)	({						\
+	__typeof__(x) __page = x;					\
+	u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\
+	u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE);			\
+	(void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
+
+#define virt_to_page(x)	({						\
+	u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE;	\
+	u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page));	\
+	(struct page *)__addr;						\
+})
+#endif /* CONFIG_DEBUG_VIRTUAL */
+
+#define virt_addr_valid(addr)	({					\
+	__typeof__(addr) __addr = __tag_reset(addr);			\
+	__is_lm_address(__addr) && pfn_is_map_memory(virt_to_pfn(__addr));	\
+})
+
+void dump_mem_limit(void);
+
+static inline bool defer_reserve_crashkernel(void)
+{
+	return IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32);
+}
+#endif /* !ASSEMBLY */
+
+/*
+ * Given that the GIC architecture permits ITS implementations that can only be
+ * configured with a LPI table address once, GICv3 systems with many CPUs may
+ * end up reserving a lot of different regions after a kexec for their LPI
+ * tables (one per CPU), as we are forced to reuse the same memory after kexec
+ * (and thus reserve it persistently with EFI beforehand)
+ */
+#if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS)
+# define INIT_MEMBLOCK_RESERVED_REGIONS	(INIT_MEMBLOCK_REGIONS + NR_CPUS + 1)
+#endif
+
+/*
+ * memory regions which marked with flag MEMBLOCK_NOMAP(for example, the memory
+ * of the EFI_UNUSABLE_MEMORY type) may divide a continuous memory block into
+ * multiple parts. As a result, the number of memory regions is large.
+ */
+#ifdef CONFIG_EFI
+#define INIT_MEMBLOCK_MEMORY_REGIONS	(INIT_MEMBLOCK_REGIONS * 8)
+#endif
+
+#include <asm-generic/memory_model.h>
+
+#endif /* __ASM_MEMORY_H */
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
new file mode 100644
index 000000000..5966ee4a6
--- /dev/null
+++ b/arch/arm64/include/asm/mman.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <uapi/asm/mman.h>
+
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+	unsigned long pkey __always_unused)
+{
+	unsigned long ret = 0;
+
+	if (system_supports_bti() && (prot & PROT_BTI))
+		ret |= VM_ARM64_BTI;
+
+	if (system_supports_mte() && (prot & PROT_MTE))
+		ret |= VM_MTE;
+
+	return ret;
+}
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+{
+	/*
+	 * Only allow MTE on anonymous mappings as these are guaranteed to be
+	 * backed by tags-capable memory. The vm_flags may be overridden by a
+	 * filesystem supporting MTE (RAM-based).
+	 */
+	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+		return VM_MTE_ALLOWED;
+
+	return 0;
+}
+#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+
+static inline bool arch_validate_prot(unsigned long prot,
+	unsigned long addr __always_unused)
+{
+	unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
+
+	if (system_supports_bti())
+		supported |= PROT_BTI;
+
+	if (system_supports_mte())
+		supported |= PROT_MTE;
+
+	return (prot & ~supported) == 0;
+}
+#define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
+
+static inline bool arch_validate_flags(unsigned long vm_flags)
+{
+	if (!system_supports_mte())
+		return true;
+
+	/* only allow VM_MTE if VM_MTE_ALLOWED has been set previously */
+	return !(vm_flags & VM_MTE) || (vm_flags & VM_MTE_ALLOWED);
+}
+#define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags)
+
+#endif /* ! __ASM_MMAN_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
new file mode 100644
index 000000000..48f8466a4
--- /dev/null
+++ b/arch/arm64/include/asm/mmu.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_MMU_H
+#define __ASM_MMU_H
+
+#include <asm/cputype.h>
+
+#define MMCF_AARCH32	0x1	/* mm context flag for AArch32 executables */
+#define USER_ASID_BIT	48
+#define USER_ASID_FLAG	(UL(1) << USER_ASID_BIT)
+#define TTBR_ASID_MASK	(UL(0xffff) << 48)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/refcount.h>
+#include <asm/cpufeature.h>
+
+typedef struct {
+	atomic64_t	id;
+#ifdef CONFIG_COMPAT
+	void		*sigpage;
+#endif
+	refcount_t	pinned;
+	void		*vdso;
+	unsigned long	flags;
+} mm_context_t;
+
+/*
+ * We use atomic64_read() here because the ASID for an 'mm_struct' can
+ * be reallocated when scheduling one of its threads following a
+ * rollover event (see new_context() and flush_context()). In this case,
+ * a concurrent TLBI (e.g. via try_to_unmap_one() and ptep_clear_flush())
+ * may use a stale ASID. This is fine in principle as the new ASID is
+ * guaranteed to be clean in the TLB, but the TLBI routines have to take
+ * care to handle the following race:
+ *
+ *    CPU 0                    CPU 1                          CPU 2
+ *
+ *    // ptep_clear_flush(mm)
+ *    xchg_relaxed(pte, 0)
+ *    DSB ISHST
+ *    old = ASID(mm)
+ *         |                                                  <rollover>
+ *         |                   new = new_context(mm)
+ *         \-----------------> atomic_set(mm->context.id, new)
+ *                             cpu_switch_mm(mm)
+ *                             // Hardware walk of pte using new ASID
+ *    TLBI(old)
+ *
+ * In this scenario, the barrier on CPU 0 and the dependency on CPU 1
+ * ensure that the page-table walker on CPU 1 *must* see the invalid PTE
+ * written by CPU 0.
+ */
+#define ASID(mm)	(atomic64_read(&(mm)->context.id) & 0xffff)
+
+static inline bool arm64_kernel_unmapped_at_el0(void)
+{
+	return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+}
+
+extern void arm64_memblock_init(void);
+extern void paging_init(void);
+extern void bootmem_init(void);
+extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
+extern void init_mem_pgprot(void);
+extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
+			       unsigned long virt, phys_addr_t size,
+			       pgprot_t prot, bool page_mappings_only);
+extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot);
+extern void mark_linear_text_alias_ro(void);
+extern bool kaslr_requires_kpti(void);
+
+#define INIT_MM_CONTEXT(name)	\
+	.pgd = init_pg_dir,
+
+#endif	/* !__ASSEMBLY__ */
+#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
new file mode 100644
index 000000000..d3f8b5df0
--- /dev/null
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/mmu_context.h
+ *
+ * Copyright (C) 1996 Russell King.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_MMU_CONTEXT_H
+#define __ASM_MMU_CONTEXT_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/sched/hotplug.h>
+#include <linux/mm_types.h>
+#include <linux/pgtable.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/proc-fns.h>
+#include <asm-generic/mm_hooks.h>
+#include <asm/cputype.h>
+#include <asm/sysreg.h>
+#include <asm/tlbflush.h>
+
+extern bool rodata_full;
+
+static inline void contextidr_thread_switch(struct task_struct *next)
+{
+	if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))
+		return;
+
+	write_sysreg(task_pid_nr(next), contextidr_el1);
+	isb();
+}
+
+/*
+ * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0.
+ */
+static inline void cpu_set_reserved_ttbr0(void)
+{
+	unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
+
+	write_sysreg(ttbr, ttbr0_el1);
+	isb();
+}
+
+void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+
+static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+	BUG_ON(pgd == swapper_pg_dir);
+	cpu_set_reserved_ttbr0();
+	cpu_do_switch_mm(virt_to_phys(pgd),mm);
+}
+
+/*
+ * TCR.T0SZ value to use when the ID map is active. Usually equals
+ * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
+ * physical memory, in which case it will be smaller.
+ */
+extern int idmap_t0sz;
+
+/*
+ * Ensure TCR.T0SZ is set to the provided value.
+ */
+static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
+{
+	unsigned long tcr = read_sysreg(tcr_el1);
+
+	if ((tcr & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET == t0sz)
+		return;
+
+	tcr &= ~TCR_T0SZ_MASK;
+	tcr |= t0sz << TCR_T0SZ_OFFSET;
+	write_sysreg(tcr, tcr_el1);
+	isb();
+}
+
+#define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual))
+#define cpu_set_idmap_tcr_t0sz()	__cpu_set_tcr_t0sz(idmap_t0sz)
+
+/*
+ * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm.
+ *
+ * The idmap lives in the same VA range as userspace, but uses global entries
+ * and may use a different TCR_EL1.T0SZ. To avoid issues resulting from
+ * speculative TLB fetches, we must temporarily install the reserved page
+ * tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ.
+ *
+ * If current is a not a user task, the mm covers the TTBR1_EL1 page tables,
+ * which should not be installed in TTBR0_EL1. In this case we can leave the
+ * reserved page tables in place.
+ */
+static inline void cpu_uninstall_idmap(void)
+{
+	struct mm_struct *mm = current->active_mm;
+
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	cpu_set_default_tcr_t0sz();
+
+	if (mm != &init_mm && !system_uses_ttbr0_pan())
+		cpu_switch_mm(mm->pgd, mm);
+}
+
+static inline void __cpu_install_idmap(pgd_t *idmap)
+{
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	cpu_set_idmap_tcr_t0sz();
+
+	cpu_switch_mm(lm_alias(idmap), &init_mm);
+}
+
+static inline void cpu_install_idmap(void)
+{
+	__cpu_install_idmap(idmap_pg_dir);
+}
+
+/*
+ * Load our new page tables. A strict BBM approach requires that we ensure that
+ * TLBs are free of any entries that may overlap with the global mappings we are
+ * about to install.
+ *
+ * For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero
+ * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime
+ * services), while for a userspace-driven test_resume cycle it points to
+ * userspace page tables (and we must point it at a zero page ourselves).
+ *
+ * We change T0SZ as part of installing the idmap. This is undone by
+ * cpu_uninstall_idmap() in __cpu_suspend_exit().
+ */
+static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
+{
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	__cpu_set_tcr_t0sz(t0sz);
+
+	/* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */
+	write_sysreg(ttbr0, ttbr0_el1);
+	isb();
+}
+
+/*
+ * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
+ * avoiding the possibility of conflicting TLB entries being allocated.
+ */
+static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+{
+	typedef void (ttbr_replace_func)(phys_addr_t);
+	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
+	ttbr_replace_func *replace_phys;
+
+	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
+	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
+
+	if (system_supports_cnp() && !WARN_ON(pgdp != lm_alias(swapper_pg_dir))) {
+		/*
+		 * cpu_replace_ttbr1() is used when there's a boot CPU
+		 * up (i.e. cpufeature framework is not up yet) and
+		 * latter only when we enable CNP via cpufeature's
+		 * enable() callback.
+		 * Also we rely on the cpu_hwcap bit being set before
+		 * calling the enable() function.
+		 */
+		ttbr1 |= TTBR_CNP_BIT;
+	}
+
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
+
+	__cpu_install_idmap(idmap);
+	replace_phys(ttbr1);
+	cpu_uninstall_idmap();
+}
+
+/*
+ * It would be nice to return ASIDs back to the allocator, but unfortunately
+ * that introduces a race with a generation rollover where we could erroneously
+ * free an ASID allocated in a future generation. We could workaround this by
+ * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap),
+ * but we'd then need to make sure that we didn't dirty any TLBs afterwards.
+ * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you
+ * take CPU migration into account.
+ */
+void check_and_switch_context(struct mm_struct *mm);
+
+#define init_new_context(tsk, mm) init_new_context(tsk, mm)
+static inline int
+init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	atomic64_set(&mm->context.id, 0);
+	refcount_set(&mm->context.pinned, 0);
+	return 0;
+}
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+				      struct mm_struct *mm)
+{
+	u64 ttbr;
+
+	if (!system_uses_ttbr0_pan())
+		return;
+
+	if (mm == &init_mm)
+		ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir));
+	else
+		ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48;
+
+	WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr);
+}
+#else
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+				      struct mm_struct *mm)
+{
+}
+#endif
+
+#define enter_lazy_tlb enter_lazy_tlb
+static inline void
+enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	/*
+	 * We don't actually care about the ttbr0 mapping, so point it at the
+	 * zero page.
+	 */
+	update_saved_ttbr0(tsk, &init_mm);
+}
+
+static inline void __switch_mm(struct mm_struct *next)
+{
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
+	check_and_switch_context(next);
+}
+
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
+{
+	if (prev != next)
+		__switch_mm(next);
+
+	/*
+	 * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
+	 * value may have not been initialised yet (activate_mm caller) or the
+	 * ASID has changed since the last run (following the context switch
+	 * of another thread of the same process).
+	 */
+	update_saved_ttbr0(tsk, next);
+}
+
+static inline const struct cpumask *
+task_cpu_possible_mask(struct task_struct *p)
+{
+	if (!static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		return cpu_possible_mask;
+
+	if (!is_compat_thread(task_thread_info(p)))
+		return cpu_possible_mask;
+
+	return system_32bit_el0_cpumask();
+}
+#define task_cpu_possible_mask	task_cpu_possible_mask
+
+void verify_cpu_asid_bits(void);
+void post_ttbr_update_workaround(void);
+
+unsigned long arm64_mm_context_get(struct mm_struct *mm);
+void arm64_mm_context_put(struct mm_struct *mm);
+
+#include <asm-generic/mmu_context.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* !__ASM_MMU_CONTEXT_H */
diff --git a/arch/arm64/include/asm/mmzone.h b/arch/arm64/include/asm/mmzone.h
new file mode 100644
index 000000000..fa17e01d9
--- /dev/null
+++ b/arch/arm64/include/asm/mmzone.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+#endif /* __ASM_MMZONE_H */
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
new file mode 100644
index 000000000..18734fed3
--- /dev/null
+++ b/arch/arm64/include/asm/module.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_MODULE_H
+#define __ASM_MODULE_H
+
+#include <asm-generic/module.h>
+
+#ifdef CONFIG_ARM64_MODULE_PLTS
+struct mod_plt_sec {
+	int			plt_shndx;
+	int			plt_num_entries;
+	int			plt_max_entries;
+};
+
+struct mod_arch_specific {
+	struct mod_plt_sec	core;
+	struct mod_plt_sec	init;
+
+	/* for CONFIG_DYNAMIC_FTRACE */
+	struct plt_entry	*ftrace_trampolines;
+};
+#endif
+
+u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
+			  void *loc, const Elf64_Rela *rela,
+			  Elf64_Sym *sym);
+
+u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs,
+				void *loc, u64 val);
+
+#ifdef CONFIG_RANDOMIZE_BASE
+extern u64 module_alloc_base;
+#else
+#define module_alloc_base	((u64)_etext - MODULES_VSIZE)
+#endif
+
+struct plt_entry {
+	/*
+	 * A program that conforms to the AArch64 Procedure Call Standard
+	 * (AAPCS64) must assume that a veneer that alters IP0 (x16) and/or
+	 * IP1 (x17) may be inserted at any branch instruction that is
+	 * exposed to a relocation that supports long branches. Since that
+	 * is exactly what we are dealing with here, we are free to use x16
+	 * as a scratch register in the PLT veneers.
+	 */
+	__le32	adrp;	/* adrp	x16, ....			*/
+	__le32	add;	/* add	x16, x16, #0x....		*/
+	__le32	br;	/* br	x16				*/
+};
+
+static inline bool is_forbidden_offset_for_adrp(void *place)
+{
+	return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
+	       cpus_have_const_cap(ARM64_WORKAROUND_843419) &&
+	       ((u64)place & 0xfff) >= 0xff8;
+}
+
+struct plt_entry get_plt_entry(u64 dst, void *pc);
+
+static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+				    const Elf_Shdr *sechdrs,
+				    const char *name)
+{
+	const Elf_Shdr *s, *se;
+	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
+	}
+
+	return NULL;
+}
+
+#endif /* __ASM_MODULE_H */
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
new file mode 100644
index 000000000..094701ec5
--- /dev/null
+++ b/arch/arm64/include/asm/module.lds.h
@@ -0,0 +1,20 @@
+SECTIONS {
+#ifdef CONFIG_ARM64_MODULE_PLTS
+	.plt 0 : { BYTE(0) }
+	.init.plt 0 : { BYTE(0) }
+	.text.ftrace_trampoline 0 : { BYTE(0) }
+#endif
+
+#ifdef CONFIG_KASAN_SW_TAGS
+	/*
+	 * Outlined checks go into comdat-deduplicated sections named .text.hot.
+	 * Because they are in comdats they are not combined by the linker and
+	 * we otherwise end up with multiple sections with the same .text.hot
+	 * name in the .ko file. The kernel module loader warns if it sees
+	 * multiple sections with the same name so we use this sections
+	 * directive to force them into a single section and silence the
+	 * warning.
+	 */
+	.text.hot : { *(.text.hot) }
+#endif
+}
diff --git a/arch/arm64/include/asm/mshyperv.h b/arch/arm64/include/asm/mshyperv.h
new file mode 100644
index 000000000..20070a847
--- /dev/null
+++ b/arch/arm64/include/asm/mshyperv.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Linux-specific definitions for managing interactions with Microsoft's
+ * Hyper-V hypervisor. The definitions in this file are specific to
+ * the ARM64 architecture.  See include/asm-generic/mshyperv.h for
+ * definitions are that architecture independent.
+ *
+ * Definitions that are specified in the Hyper-V Top Level Functional
+ * Spec (TLFS) should not go in this file, but should instead go in
+ * hyperv-tlfs.h.
+ *
+ * Copyright (C) 2021, Microsoft, Inc.
+ *
+ * Author : Michael Kelley <mikelley@microsoft.com>
+ */
+
+#ifndef _ASM_MSHYPERV_H
+#define _ASM_MSHYPERV_H
+
+#include <linux/types.h>
+#include <linux/arm-smccc.h>
+#include <asm/hyperv-tlfs.h>
+
+/*
+ * Declare calls to get and set Hyper-V VP register values on ARM64, which
+ * requires a hypercall.
+ */
+
+void hv_set_vpreg(u32 reg, u64 value);
+u64 hv_get_vpreg(u32 reg);
+void hv_get_vpreg_128(u32 reg, struct hv_get_vp_registers_output *result);
+
+static inline void hv_set_register(unsigned int reg, u64 value)
+{
+	hv_set_vpreg(reg, value);
+}
+
+static inline u64 hv_get_register(unsigned int reg)
+{
+	return hv_get_vpreg(reg);
+}
+
+/* SMCCC hypercall parameters */
+#define HV_SMCCC_FUNC_NUMBER	1
+#define HV_FUNC_ID	ARM_SMCCC_CALL_VAL(			\
+				ARM_SMCCC_STD_CALL,		\
+				ARM_SMCCC_SMC_64,		\
+				ARM_SMCCC_OWNER_VENDOR_HYP,	\
+				HV_SMCCC_FUNC_NUMBER)
+
+#include <asm-generic/mshyperv.h>
+
+#endif
diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h
new file mode 100644
index 000000000..14ee86b01
--- /dev/null
+++ b/arch/arm64/include/asm/mte-def.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_DEF_H
+#define __ASM_MTE_DEF_H
+
+#define MTE_GRANULE_SIZE	UL(16)
+#define MTE_GRANULE_MASK	(~(MTE_GRANULE_SIZE - 1))
+#define MTE_GRANULES_PER_PAGE	(PAGE_SIZE / MTE_GRANULE_SIZE)
+#define MTE_TAG_SHIFT		56
+#define MTE_TAG_SIZE		4
+#define MTE_TAG_MASK		GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT)
+#define MTE_PAGE_TAG_STORAGE	(MTE_GRANULES_PER_PAGE * MTE_TAG_SIZE / 8)
+
+#define __MTE_PREAMBLE		ARM64_ASM_PREAMBLE ".arch_extension memtag\n"
+
+#endif /* __ASM_MTE_DEF_H  */
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
new file mode 100644
index 000000000..9f79425fc
--- /dev/null
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_KASAN_H
+#define __ASM_MTE_KASAN_H
+
+#include <asm/compiler.h>
+#include <asm/cputype.h>
+#include <asm/mte-def.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+#ifdef CONFIG_ARM64_MTE
+
+/*
+ * These functions are meant to be only used from KASAN runtime through
+ * the arch_*() interface defined in asm/memory.h.
+ * These functions don't include system_supports_mte() checks,
+ * as KASAN only calls them when MTE is supported and enabled.
+ */
+
+static inline u8 mte_get_ptr_tag(void *ptr)
+{
+	/* Note: The format of KASAN tags is 0xF<x> */
+	u8 tag = 0xF0 | (u8)(((u64)(ptr)) >> MTE_TAG_SHIFT);
+
+	return tag;
+}
+
+/* Get allocation tag for the address. */
+static inline u8 mte_get_mem_tag(void *addr)
+{
+	asm(__MTE_PREAMBLE "ldg %0, [%0]"
+		: "+r" (addr));
+
+	return mte_get_ptr_tag(addr);
+}
+
+/* Generate a random tag. */
+static inline u8 mte_get_random_tag(void)
+{
+	void *addr;
+
+	asm(__MTE_PREAMBLE "irg %0, %0"
+		: "=r" (addr));
+
+	return mte_get_ptr_tag(addr);
+}
+
+static inline u64 __stg_post(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "stg %0, [%0], #16"
+		     : "+r"(p)
+		     :
+		     : "memory");
+	return p;
+}
+
+static inline u64 __stzg_post(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "stzg %0, [%0], #16"
+		     : "+r"(p)
+		     :
+		     : "memory");
+	return p;
+}
+
+static inline void __dc_gva(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "dc gva, %0" : : "r"(p) : "memory");
+}
+
+static inline void __dc_gzva(u64 p)
+{
+	asm volatile(__MTE_PREAMBLE "dc gzva, %0" : : "r"(p) : "memory");
+}
+
+/*
+ * Assign allocation tags for a region of memory based on the pointer tag.
+ * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and
+ * size must be MTE_GRANULE_SIZE aligned.
+ */
+static inline void mte_set_mem_tag_range(void *addr, size_t size, u8 tag,
+					 bool init)
+{
+	u64 curr, mask, dczid, dczid_bs, dczid_dzp, end1, end2, end3;
+
+	/* Read DC G(Z)VA block size from the system register. */
+	dczid = read_cpuid(DCZID_EL0);
+	dczid_bs = 4ul << (dczid & 0xf);
+	dczid_dzp = (dczid >> 4) & 1;
+
+	curr = (u64)__tag_set(addr, tag);
+	mask = dczid_bs - 1;
+	/* STG/STZG up to the end of the first block. */
+	end1 = curr | mask;
+	end3 = curr + size;
+	/* DC GVA / GZVA in [end1, end2) */
+	end2 = end3 & ~mask;
+
+	/*
+	 * The following code uses STG on the first DC GVA block even if the
+	 * start address is aligned - it appears to be faster than an alignment
+	 * check + conditional branch. Also, if the range size is at least 2 DC
+	 * GVA blocks, the first two loops can use post-condition to save one
+	 * branch each.
+	 */
+#define SET_MEMTAG_RANGE(stg_post, dc_gva)		\
+	do {						\
+		if (!dczid_dzp && size >= 2 * dczid_bs) {\
+			do {				\
+				curr = stg_post(curr);	\
+			} while (curr < end1);		\
+							\
+			do {				\
+				dc_gva(curr);		\
+				curr += dczid_bs;	\
+			} while (curr < end2);		\
+		}					\
+							\
+		while (curr < end3)			\
+			curr = stg_post(curr);		\
+	} while (0)
+
+	if (init)
+		SET_MEMTAG_RANGE(__stzg_post, __dc_gzva);
+	else
+		SET_MEMTAG_RANGE(__stg_post, __dc_gva);
+#undef SET_MEMTAG_RANGE
+}
+
+void mte_enable_kernel_sync(void);
+void mte_enable_kernel_async(void);
+void mte_enable_kernel_asymm(void);
+
+#else /* CONFIG_ARM64_MTE */
+
+static inline u8 mte_get_ptr_tag(void *ptr)
+{
+	return 0xFF;
+}
+
+static inline u8 mte_get_mem_tag(void *addr)
+{
+	return 0xFF;
+}
+
+static inline u8 mte_get_random_tag(void)
+{
+	return 0xFF;
+}
+
+static inline void mte_set_mem_tag_range(void *addr, size_t size,
+						u8 tag, bool init)
+{
+}
+
+static inline void mte_enable_kernel_sync(void)
+{
+}
+
+static inline void mte_enable_kernel_async(void)
+{
+}
+
+static inline void mte_enable_kernel_asymm(void)
+{
+}
+
+#endif /* CONFIG_ARM64_MTE */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_MTE_KASAN_H  */
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
new file mode 100644
index 000000000..3f8199ba2
--- /dev/null
+++ b/arch/arm64/include/asm/mte.h
@@ -0,0 +1,198 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_H
+#define __ASM_MTE_H
+
+#include <asm/compiler.h>
+#include <asm/mte-def.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitfield.h>
+#include <linux/kasan-enabled.h>
+#include <linux/page-flags.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+
+#include <asm/pgtable-types.h>
+
+void mte_clear_page_tags(void *addr);
+unsigned long mte_copy_tags_from_user(void *to, const void __user *from,
+				      unsigned long n);
+unsigned long mte_copy_tags_to_user(void __user *to, void *from,
+				    unsigned long n);
+int mte_save_tags(struct page *page);
+void mte_save_page_tags(const void *page_addr, void *tag_storage);
+bool mte_restore_tags(swp_entry_t entry, struct page *page);
+void mte_restore_page_tags(void *page_addr, const void *tag_storage);
+void mte_invalidate_tags(int type, pgoff_t offset);
+void mte_invalidate_tags_area(int type);
+void *mte_allocate_tag_storage(void);
+void mte_free_tag_storage(char *storage);
+
+#ifdef CONFIG_ARM64_MTE
+
+/* track which pages have valid allocation tags */
+#define PG_mte_tagged	PG_arch_2
+
+static inline void set_page_mte_tagged(struct page *page)
+{
+	/*
+	 * Ensure that the tags written prior to this function are visible
+	 * before the page flags update.
+	 */
+	smp_wmb();
+	set_bit(PG_mte_tagged, &page->flags);
+}
+
+static inline bool page_mte_tagged(struct page *page)
+{
+	bool ret = test_bit(PG_mte_tagged, &page->flags);
+
+	/*
+	 * If the page is tagged, ensure ordering with a likely subsequent
+	 * read of the tags.
+	 */
+	if (ret)
+		smp_rmb();
+	return ret;
+}
+
+void mte_zero_clear_page_tags(void *addr);
+void mte_sync_tags(pte_t old_pte, pte_t pte);
+void mte_copy_page_tags(void *kto, const void *kfrom);
+void mte_thread_init_user(void);
+void mte_thread_switch(struct task_struct *next);
+void mte_cpu_setup(void);
+void mte_suspend_enter(void);
+void mte_suspend_exit(void);
+long set_mte_ctrl(struct task_struct *task, unsigned long arg);
+long get_mte_ctrl(struct task_struct *task);
+int mte_ptrace_copy_tags(struct task_struct *child, long request,
+			 unsigned long addr, unsigned long data);
+size_t mte_probe_user_range(const char __user *uaddr, size_t size);
+
+#else /* CONFIG_ARM64_MTE */
+
+/* unused if !CONFIG_ARM64_MTE, silence the compiler */
+#define PG_mte_tagged	0
+
+static inline void set_page_mte_tagged(struct page *page)
+{
+}
+static inline bool page_mte_tagged(struct page *page)
+{
+	return false;
+}
+static inline void mte_zero_clear_page_tags(void *addr)
+{
+}
+static inline void mte_sync_tags(pte_t old_pte, pte_t pte)
+{
+}
+static inline void mte_copy_page_tags(void *kto, const void *kfrom)
+{
+}
+static inline void mte_thread_init_user(void)
+{
+}
+static inline void mte_thread_switch(struct task_struct *next)
+{
+}
+static inline void mte_suspend_enter(void)
+{
+}
+static inline void mte_suspend_exit(void)
+{
+}
+static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg)
+{
+	return 0;
+}
+static inline long get_mte_ctrl(struct task_struct *task)
+{
+	return 0;
+}
+static inline int mte_ptrace_copy_tags(struct task_struct *child,
+				       long request, unsigned long addr,
+				       unsigned long data)
+{
+	return -EIO;
+}
+
+#endif /* CONFIG_ARM64_MTE */
+
+static inline void mte_disable_tco_entry(struct task_struct *task)
+{
+	if (!system_supports_mte())
+		return;
+
+	/*
+	 * Re-enable tag checking (TCO set on exception entry). This is only
+	 * necessary if MTE is enabled in either the kernel or the userspace
+	 * task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set
+	 * for both). With MTE disabled in the kernel and disabled or
+	 * asynchronous in userspace, tag check faults (including in uaccesses)
+	 * are not reported, therefore there is no need to re-enable checking.
+	 * This is beneficial on microarchitectures where re-enabling TCO is
+	 * expensive.
+	 */
+	if (kasan_hw_tags_enabled() ||
+	    (task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT)))
+		asm volatile(SET_PSTATE_TCO(0));
+}
+
+#ifdef CONFIG_KASAN_HW_TAGS
+/* Whether the MTE asynchronous mode is enabled. */
+DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode);
+
+static inline bool system_uses_mte_async_or_asymm_mode(void)
+{
+	return static_branch_unlikely(&mte_async_or_asymm_mode);
+}
+
+void mte_check_tfsr_el1(void);
+
+static inline void mte_check_tfsr_entry(void)
+{
+	if (!system_supports_mte())
+		return;
+
+	mte_check_tfsr_el1();
+}
+
+static inline void mte_check_tfsr_exit(void)
+{
+	if (!system_supports_mte())
+		return;
+
+	/*
+	 * The asynchronous faults are sync'ed automatically with
+	 * TFSR_EL1 on kernel entry but for exit an explicit dsb()
+	 * is required.
+	 */
+	dsb(nsh);
+	isb();
+
+	mte_check_tfsr_el1();
+}
+#else
+static inline bool system_uses_mte_async_or_asymm_mode(void)
+{
+	return false;
+}
+static inline void mte_check_tfsr_el1(void)
+{
+}
+static inline void mte_check_tfsr_entry(void)
+{
+}
+static inline void mte_check_tfsr_exit(void)
+{
+}
+#endif /* CONFIG_KASAN_HW_TAGS */
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_MTE_H  */
diff --git a/arch/arm64/include/asm/neon-intrinsics.h b/arch/arm64/include/asm/neon-intrinsics.h
new file mode 100644
index 000000000..5f13505d3
--- /dev/null
+++ b/arch/arm64/include/asm/neon-intrinsics.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2018 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#ifndef __ASM_NEON_INTRINSICS_H
+#define __ASM_NEON_INTRINSICS_H
+
+#include <asm-generic/int-ll64.h>
+
+/*
+ * In the kernel, u64/s64 are [un]signed long long, not [un]signed long.
+ * So by redefining these macros to the former, we can force gcc-stdint.h
+ * to define uint64_t / in64_t in a compatible manner.
+ */
+
+#ifdef __INT64_TYPE__
+#undef __INT64_TYPE__
+#define __INT64_TYPE__		long long
+#endif
+
+#ifdef __UINT64_TYPE__
+#undef __UINT64_TYPE__
+#define __UINT64_TYPE__		unsigned long long
+#endif
+
+/*
+ * genksyms chokes on the ARM NEON instrinsics system header, but we
+ * don't export anything it defines anyway, so just disregard when
+ * genksyms execute.
+ */
+#ifndef __GENKSYMS__
+#include <arm_neon.h>
+#endif
+
+#ifdef CONFIG_CC_IS_CLANG
+#pragma clang diagnostic ignored "-Wincompatible-pointer-types"
+#endif
+
+#endif /* __ASM_NEON_INTRINSICS_H */
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
new file mode 100644
index 000000000..d4b1d172a
--- /dev/null
+++ b/arch/arm64/include/asm/neon.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/arch/arm64/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#ifndef __ASM_NEON_H
+#define __ASM_NEON_H
+
+#include <linux/types.h>
+#include <asm/fpsimd.h>
+
+#define cpu_has_neon()		system_supports_fpsimd()
+
+void kernel_neon_begin(void);
+void kernel_neon_end(void);
+
+#endif /* ! __ASM_NEON_H */
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
new file mode 100644
index 000000000..8c8cf4297
--- /dev/null
+++ b/arch/arm64/include/asm/numa.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <asm/topology.h>
+#include <asm-generic/numa.h>
+
+#endif	/* __ASM_NUMA_H */
diff --git a/arch/arm64/include/asm/page-def.h b/arch/arm64/include/asm/page-def.h
new file mode 100644
index 000000000..2403f7b4c
--- /dev/null
+++ b/arch/arm64/include/asm/page-def.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/page.h
+ *
+ * Copyright (C) 1995-2003 Russell King
+ * Copyright (C) 2017 ARM Ltd.
+ */
+#ifndef __ASM_PAGE_DEF_H
+#define __ASM_PAGE_DEF_H
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
+#define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE-1))
+
+#endif /* __ASM_PAGE_DEF_H */
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
new file mode 100644
index 000000000..993a27ea6
--- /dev/null
+++ b/arch/arm64/include/asm/page.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/page.h
+ *
+ * Copyright (C) 1995-2003 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PAGE_H
+#define __ASM_PAGE_H
+
+#include <asm/page-def.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/personality.h> /* for READ_IMPLIES_EXEC */
+#include <linux/types.h> /* for gfp_t */
+#include <asm/pgtable-types.h>
+
+struct page;
+struct vm_area_struct;
+
+extern void copy_page(void *to, const void *from);
+extern void clear_page(void *to);
+
+void copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr, struct vm_area_struct *vma);
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+
+void copy_highpage(struct page *to, struct page *from);
+#define __HAVE_ARCH_COPY_HIGHPAGE
+
+struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
+						unsigned long vaddr);
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE
+
+void tag_clear_highpage(struct page *to);
+#define __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
+
+#define clear_user_page(page, vaddr, pg)	clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
+
+typedef struct page *pgtable_t;
+
+int pfn_is_map_memory(unsigned long pfn);
+
+#include <asm/memory.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
+
+#include <asm-generic/getorder.h>
+
+#endif
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
new file mode 100644
index 000000000..9aa193e0e
--- /dev/null
+++ b/arch/arm64/include/asm/paravirt.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_PARAVIRT_H
+#define _ASM_ARM64_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 dummy_steal_clock(int cpu);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return static_call(pv_steal_clock)(cpu);
+}
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif // CONFIG_PARAVIRT
+
+#endif
diff --git a/arch/arm64/include/asm/paravirt_api_clock.h b/arch/arm64/include/asm/paravirt_api_clock.h
new file mode 100644
index 000000000..65ac7cee0
--- /dev/null
+++ b/arch/arm64/include/asm/paravirt_api_clock.h
@@ -0,0 +1 @@
+#include <asm/paravirt.h>
diff --git a/arch/arm64/include/asm/patching.h b/arch/arm64/include/asm/patching.h
new file mode 100644
index 000000000..6bf5adc56
--- /dev/null
+++ b/arch/arm64/include/asm/patching.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef	__ASM_PATCHING_H
+#define	__ASM_PATCHING_H
+
+#include <linux/types.h>
+
+int aarch64_insn_read(void *addr, u32 *insnp);
+int aarch64_insn_write(void *addr, u32 insn);
+
+int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
+int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+
+#endif	/* __ASM_PATCHING_H */
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
new file mode 100644
index 000000000..016eb6b46
--- /dev/null
+++ b/arch/arm64/include/asm/pci.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_PCI_H
+#define __ASM_PCI_H
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO		0x1000
+
+/*
+ * Set to 1 if the kernel should re-assign all PCI bus numbers
+ */
+#define pcibios_assign_all_busses() \
+	(pci_has_flag(PCI_REASSIGN_ALL_BUS))
+
+#define arch_can_pci_mmap_wc() 1
+
+/* Generic PCI */
+#include <asm-generic/pci.h>
+
+#endif  /* __ASM_PCI_H */
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
new file mode 100644
index 000000000..b9ba19dbd
--- /dev/null
+++ b/arch/arm64/include/asm/percpu.h
@@ -0,0 +1,261 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ */
+#ifndef __ASM_PERCPU_H
+#define __ASM_PERCPU_H
+
+#include <linux/preempt.h>
+
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+#include <asm/stack_pointer.h>
+#include <asm/sysreg.h>
+
+static inline void set_my_cpu_offset(unsigned long off)
+{
+	asm volatile(ALTERNATIVE("msr tpidr_el1, %0",
+				 "msr tpidr_el2, %0",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+			:: "r" (off) : "memory");
+}
+
+static inline unsigned long __hyp_my_cpu_offset(void)
+{
+	/*
+	 * Non-VHE hyp code runs with preemption disabled. No need to hazard
+	 * the register access against barrier() as in __kern_my_cpu_offset.
+	 */
+	return read_sysreg(tpidr_el2);
+}
+
+static inline unsigned long __kern_my_cpu_offset(void)
+{
+	unsigned long off;
+
+	/*
+	 * We want to allow caching the value, so avoid using volatile and
+	 * instead use a fake stack read to hazard against barrier().
+	 */
+	asm(ALTERNATIVE("mrs %0, tpidr_el1",
+			"mrs %0, tpidr_el2",
+			ARM64_HAS_VIRT_HOST_EXTN)
+		: "=r" (off) :
+		"Q" (*(const unsigned long *)current_stack_pointer));
+
+	return off;
+}
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+#define __my_cpu_offset __hyp_my_cpu_offset()
+#else
+#define __my_cpu_offset __kern_my_cpu_offset()
+#endif
+
+#define PERCPU_RW_OPS(sz)						\
+static inline unsigned long __percpu_read_##sz(void *ptr)		\
+{									\
+	return READ_ONCE(*(u##sz *)ptr);				\
+}									\
+									\
+static inline void __percpu_write_##sz(void *ptr, unsigned long val)	\
+{									\
+	WRITE_ONCE(*(u##sz *)ptr, (u##sz)val);				\
+}
+
+#define __PERCPU_OP_CASE(w, sfx, name, sz, op_llsc, op_lse)		\
+static inline void							\
+__percpu_##name##_case_##sz(void *ptr, unsigned long val)		\
+{									\
+	unsigned int loop;						\
+	u##sz tmp;							\
+									\
+	asm volatile (ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"1:	ldxr" #sfx "\t%" #w "[tmp], %[ptr]\n"			\
+		#op_llsc "\t%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
+	"	stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n"		\
+	"	cbnz	%w[loop], 1b",					\
+	/* LSE atomics */						\
+		#op_lse "\t%" #w "[val], %[ptr]\n"			\
+		__nops(3))						\
+	: [loop] "=&r" (loop), [tmp] "=&r" (tmp),			\
+	  [ptr] "+Q"(*(u##sz *)ptr)					\
+	: [val] "r" ((u##sz)(val)));					\
+}
+
+#define __PERCPU_RET_OP_CASE(w, sfx, name, sz, op_llsc, op_lse)		\
+static inline u##sz							\
+__percpu_##name##_return_case_##sz(void *ptr, unsigned long val)	\
+{									\
+	unsigned int loop;						\
+	u##sz ret;							\
+									\
+	asm volatile (ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"1:	ldxr" #sfx "\t%" #w "[ret], %[ptr]\n"			\
+		#op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n"	\
+	"	stxr" #sfx "\t%w[loop], %" #w "[ret], %[ptr]\n"		\
+	"	cbnz	%w[loop], 1b",					\
+	/* LSE atomics */						\
+		#op_lse "\t%" #w "[val], %" #w "[ret], %[ptr]\n"	\
+		#op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n"	\
+		__nops(2))						\
+	: [loop] "=&r" (loop), [ret] "=&r" (ret),			\
+	  [ptr] "+Q"(*(u##sz *)ptr)					\
+	: [val] "r" ((u##sz)(val)));					\
+									\
+	return ret;							\
+}
+
+#define PERCPU_OP(name, op_llsc, op_lse)				\
+	__PERCPU_OP_CASE(w, b, name,  8, op_llsc, op_lse)		\
+	__PERCPU_OP_CASE(w, h, name, 16, op_llsc, op_lse)		\
+	__PERCPU_OP_CASE(w,  , name, 32, op_llsc, op_lse)		\
+	__PERCPU_OP_CASE( ,  , name, 64, op_llsc, op_lse)
+
+#define PERCPU_RET_OP(name, op_llsc, op_lse)				\
+	__PERCPU_RET_OP_CASE(w, b, name,  8, op_llsc, op_lse)		\
+	__PERCPU_RET_OP_CASE(w, h, name, 16, op_llsc, op_lse)		\
+	__PERCPU_RET_OP_CASE(w,  , name, 32, op_llsc, op_lse)		\
+	__PERCPU_RET_OP_CASE( ,  , name, 64, op_llsc, op_lse)
+
+PERCPU_RW_OPS(8)
+PERCPU_RW_OPS(16)
+PERCPU_RW_OPS(32)
+PERCPU_RW_OPS(64)
+PERCPU_OP(add, add, stadd)
+PERCPU_OP(andnot, bic, stclr)
+PERCPU_OP(or, orr, stset)
+PERCPU_RET_OP(add, add, ldadd)
+
+#undef PERCPU_RW_OPS
+#undef __PERCPU_OP_CASE
+#undef __PERCPU_RET_OP_CASE
+#undef PERCPU_OP
+#undef PERCPU_RET_OP
+
+/*
+ * It would be nice to avoid the conditional call into the scheduler when
+ * re-enabling preemption for preemptible kernels, but doing that in a way
+ * which builds inside a module would mean messing directly with the preempt
+ * count. If you do this, peterz and tglx will hunt you down.
+ */
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
+({									\
+	int __ret;							\
+	preempt_disable_notrace();					\
+	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
+					raw_cpu_ptr(&(ptr2)),		\
+					o1, o2, n1, n2);		\
+	preempt_enable_notrace();					\
+	__ret;								\
+})
+
+#define _pcp_protect(op, pcp, ...)					\
+({									\
+	preempt_disable_notrace();					\
+	op(raw_cpu_ptr(&(pcp)), __VA_ARGS__);				\
+	preempt_enable_notrace();					\
+})
+
+#define _pcp_protect_return(op, pcp, args...)				\
+({									\
+	typeof(pcp) __retval;						\
+	preempt_disable_notrace();					\
+	__retval = (typeof(pcp))op(raw_cpu_ptr(&(pcp)), ##args);	\
+	preempt_enable_notrace();					\
+	__retval;							\
+})
+
+#define this_cpu_read_1(pcp)		\
+	_pcp_protect_return(__percpu_read_8, pcp)
+#define this_cpu_read_2(pcp)		\
+	_pcp_protect_return(__percpu_read_16, pcp)
+#define this_cpu_read_4(pcp)		\
+	_pcp_protect_return(__percpu_read_32, pcp)
+#define this_cpu_read_8(pcp)		\
+	_pcp_protect_return(__percpu_read_64, pcp)
+
+#define this_cpu_write_1(pcp, val)	\
+	_pcp_protect(__percpu_write_8, pcp, (unsigned long)val)
+#define this_cpu_write_2(pcp, val)	\
+	_pcp_protect(__percpu_write_16, pcp, (unsigned long)val)
+#define this_cpu_write_4(pcp, val)	\
+	_pcp_protect(__percpu_write_32, pcp, (unsigned long)val)
+#define this_cpu_write_8(pcp, val)	\
+	_pcp_protect(__percpu_write_64, pcp, (unsigned long)val)
+
+#define this_cpu_add_1(pcp, val)	\
+	_pcp_protect(__percpu_add_case_8, pcp, val)
+#define this_cpu_add_2(pcp, val)	\
+	_pcp_protect(__percpu_add_case_16, pcp, val)
+#define this_cpu_add_4(pcp, val)	\
+	_pcp_protect(__percpu_add_case_32, pcp, val)
+#define this_cpu_add_8(pcp, val)	\
+	_pcp_protect(__percpu_add_case_64, pcp, val)
+
+#define this_cpu_add_return_1(pcp, val)	\
+	_pcp_protect_return(__percpu_add_return_case_8, pcp, val)
+#define this_cpu_add_return_2(pcp, val)	\
+	_pcp_protect_return(__percpu_add_return_case_16, pcp, val)
+#define this_cpu_add_return_4(pcp, val)	\
+	_pcp_protect_return(__percpu_add_return_case_32, pcp, val)
+#define this_cpu_add_return_8(pcp, val)	\
+	_pcp_protect_return(__percpu_add_return_case_64, pcp, val)
+
+#define this_cpu_and_1(pcp, val)	\
+	_pcp_protect(__percpu_andnot_case_8, pcp, ~val)
+#define this_cpu_and_2(pcp, val)	\
+	_pcp_protect(__percpu_andnot_case_16, pcp, ~val)
+#define this_cpu_and_4(pcp, val)	\
+	_pcp_protect(__percpu_andnot_case_32, pcp, ~val)
+#define this_cpu_and_8(pcp, val)	\
+	_pcp_protect(__percpu_andnot_case_64, pcp, ~val)
+
+#define this_cpu_or_1(pcp, val)		\
+	_pcp_protect(__percpu_or_case_8, pcp, val)
+#define this_cpu_or_2(pcp, val)		\
+	_pcp_protect(__percpu_or_case_16, pcp, val)
+#define this_cpu_or_4(pcp, val)		\
+	_pcp_protect(__percpu_or_case_32, pcp, val)
+#define this_cpu_or_8(pcp, val)		\
+	_pcp_protect(__percpu_or_case_64, pcp, val)
+
+#define this_cpu_xchg_1(pcp, val)	\
+	_pcp_protect_return(xchg_relaxed, pcp, val)
+#define this_cpu_xchg_2(pcp, val)	\
+	_pcp_protect_return(xchg_relaxed, pcp, val)
+#define this_cpu_xchg_4(pcp, val)	\
+	_pcp_protect_return(xchg_relaxed, pcp, val)
+#define this_cpu_xchg_8(pcp, val)	\
+	_pcp_protect_return(xchg_relaxed, pcp, val)
+
+#define this_cpu_cmpxchg_1(pcp, o, n)	\
+	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
+#define this_cpu_cmpxchg_2(pcp, o, n)	\
+	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
+#define this_cpu_cmpxchg_4(pcp, o, n)	\
+	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
+#define this_cpu_cmpxchg_8(pcp, o, n)	\
+	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+extern unsigned long __hyp_per_cpu_offset(unsigned int cpu);
+#define __per_cpu_offset
+#define per_cpu_offset(cpu)	__hyp_per_cpu_offset((cpu))
+#endif
+
+#include <asm-generic/percpu.h>
+
+/* Redefine macros for nVHE hyp under DEBUG_PREEMPT to avoid its dependencies. */
+#if defined(__KVM_NVHE_HYPERVISOR__) && defined(CONFIG_DEBUG_PREEMPT)
+#undef	this_cpu_ptr
+#define	this_cpu_ptr		raw_cpu_ptr
+#undef	__this_cpu_read
+#define	__this_cpu_read		raw_cpu_read
+#undef	__this_cpu_write
+#define	__this_cpu_write	raw_cpu_write
+#endif
+
+#endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
new file mode 100644
index 000000000..3eaf462f5
--- /dev/null
+++ b/arch/arm64/include/asm/perf_event.h
@@ -0,0 +1,276 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __ASM_PERF_EVENT_H
+#define __ASM_PERF_EVENT_H
+
+#include <asm/stack_pointer.h>
+#include <asm/ptrace.h>
+
+#define	ARMV8_PMU_MAX_COUNTERS	32
+#define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
+
+/*
+ * Common architectural and microarchitectural event numbers.
+ */
+#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x0000
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL			0x0001
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL			0x0002
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x0003
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x0004
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL			0x0005
+#define ARMV8_PMUV3_PERFCTR_LD_RETIRED				0x0006
+#define ARMV8_PMUV3_PERFCTR_ST_RETIRED				0x0007
+#define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x0008
+#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x0009
+#define ARMV8_PMUV3_PERFCTR_EXC_RETURN				0x000A
+#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED			0x000B
+#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED			0x000C
+#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED			0x000D
+#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED			0x000E
+#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED		0x000F
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x0010
+#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x0011
+#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x0012
+#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x0013
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE				0x0014
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB			0x0015
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE				0x0016
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL			0x0017
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB			0x0018
+#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x0019
+#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR			0x001A
+#define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x001B
+#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED			0x001C
+#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x001D
+#define ARMV8_PMUV3_PERFCTR_CHAIN				0x001E
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x001F
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x0020
+#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x0021
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x0022
+#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x0023
+#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x0024
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x0025
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x0026
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x0027
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x0028
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x0029
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x002A
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x002B
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x002C
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x002D
+#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL			0x002E
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x002F
+#define ARMV8_PMUV3_PERFCTR_L2I_TLB				0x0030
+#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS			0x0031
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE				0x0032
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS			0x0033
+#define ARMV8_PMUV3_PERFCTR_DTLB_WALK				0x0034
+#define ARMV8_PMUV3_PERFCTR_ITLB_WALK				0x0035
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x0036
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x0037
+#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x0038
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD			0x0039
+#define ARMV8_PMUV3_PERFCTR_OP_RETIRED				0x003A
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x003B
+#define ARMV8_PMUV3_PERFCTR_STALL				0x003C
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND			0x003D
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND			0x003E
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT				0x003F
+
+/* Statistical profiling extension microarchitectural events */
+#define	ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
+#define	ARMV8_SPE_PERFCTR_SAMPLE_FEED				0x4001
+#define	ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4002
+#define	ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4003
+
+/* AMUv1 architecture events */
+#define	ARMV8_AMU_PERFCTR_CNT_CYCLES				0x4004
+#define	ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM			0x4005
+
+/* long-latency read miss events */
+#define	ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS			0x4006
+#define	ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD			0x4009
+#define	ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS			0x400A
+#define	ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD			0x400B
+
+/* Trace buffer events */
+#define ARMV8_PMUV3_PERFCTR_TRB_WRAP				0x400C
+#define ARMV8_PMUV3_PERFCTR_TRB_TRIG				0x400E
+
+/* Trace unit events */
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT0				0x4010
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT1				0x4011
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT2				0x4012
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT3				0x4013
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4			0x4018
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5			0x4019
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6			0x401A
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7			0x401B
+
+/* additional latency from alignment events */
+#define	ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT			0x4020
+#define	ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT			0x4021
+#define	ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT			0x4022
+
+/* Armv8.5 Memory Tagging Extension events */
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED			0x4024
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD			0x4025
+#define	ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR			0x4026
+
+/* ARMv8 recommended implementation defined event types */
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x0040
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x0041
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD		0x0042
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR		0x0043
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER		0x0044
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER		0x0045
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM		0x0046
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN			0x0047
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL			0x0048
+
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD			0x004C
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR			0x004D
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD				0x004E
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR				0x004F
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD			0x0050
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR			0x0051
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD		0x0052
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR		0x0053
+
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM		0x0056
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN			0x0057
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL			0x0058
+
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD			0x005C
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR			0x005D
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD				0x005E
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR				0x005F
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD			0x0060
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR			0x0061
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED			0x0062
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED		0x0063
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL			0x0064
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH			0x0065
+#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD			0x0066
+#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR			0x0067
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC			0x0068
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC			0x0069
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC		0x006A
+
+#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC				0x006C
+#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC			0x006D
+#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC			0x006E
+#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC				0x006F
+#define ARMV8_IMPDEF_PERFCTR_LD_SPEC				0x0070
+#define ARMV8_IMPDEF_PERFCTR_ST_SPEC				0x0071
+#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC				0x0072
+#define ARMV8_IMPDEF_PERFCTR_DP_SPEC				0x0073
+#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC				0x0074
+#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC				0x0075
+#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC			0x0076
+#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC			0x0077
+#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC			0x0078
+#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC			0x0079
+#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC			0x007A
+
+#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC				0x007C
+#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC				0x007D
+#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC				0x007E
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF				0x0081
+#define ARMV8_IMPDEF_PERFCTR_EXC_SVC				0x0082
+#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT				0x0083
+#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT				0x0084
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ				0x0086
+#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ				0x0087
+#define ARMV8_IMPDEF_PERFCTR_EXC_SMC				0x0088
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_HVC				0x008A
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT			0x008B
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT			0x008C
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER			0x008D
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ			0x008E
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ			0x008F
+#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC				0x0090
+#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC				0x0091
+
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD			0x00A0
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR			0x00A1
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD		0x00A2
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR		0x00A3
+
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM		0x00A6
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN			0x00A7
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL			0x00A8
+
+/*
+ * Per-CPU PMCR: config reg
+ */
+#define ARMV8_PMU_PMCR_E	(1 << 0) /* Enable all counters */
+#define ARMV8_PMU_PMCR_P	(1 << 1) /* Reset all counters */
+#define ARMV8_PMU_PMCR_C	(1 << 2) /* Cycle counter reset */
+#define ARMV8_PMU_PMCR_D	(1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV8_PMU_PMCR_X	(1 << 4) /* Export to ETM */
+#define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
+#define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
+#define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
+#define	ARMV8_PMU_PMCR_N_SHIFT	11	 /* Number of counters supported */
+#define	ARMV8_PMU_PMCR_N_MASK	0x1f
+#define	ARMV8_PMU_PMCR_MASK	0xff	 /* Mask for writable bits */
+
+/*
+ * PMOVSR: counters overflow flag status reg
+ */
+#define	ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
+#define	ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+
+/*
+ * PMXEVTYPER: Event selection reg
+ */
+#define	ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
+#define	ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+
+/*
+ * Event filters for PMUv3
+ */
+#define	ARMV8_PMU_EXCLUDE_EL1	(1U << 31)
+#define	ARMV8_PMU_EXCLUDE_EL0	(1U << 30)
+#define	ARMV8_PMU_INCLUDE_EL2	(1U << 27)
+
+/*
+ * PMUSERENR: user enable reg
+ */
+#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
+#define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
+#define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
+#define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+
+/* PMMIR_EL1.SLOTS mask */
+#define ARMV8_PMU_SLOTS_MASK	0xff
+
+#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
+#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
+#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
+#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+
+#ifdef CONFIG_PERF_EVENTS
+struct pt_regs;
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
+#endif
+
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->pc = (__ip);    \
+	(regs)->regs[29] = (unsigned long) __builtin_frame_address(0); \
+	(regs)->sp = current_stack_pointer; \
+	(regs)->pstate = PSR_MODE_EL1h;	\
+}
+
+#endif
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
new file mode 100644
index 000000000..237224484
--- /dev/null
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/pgalloc.h
+ *
+ * Copyright (C) 2000-2001 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PGALLOC_H
+#define __ASM_PGALLOC_H
+
+#include <asm/pgtable-hwdef.h>
+#include <asm/processor.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#define __HAVE_ARCH_PGD_FREE
+#include <asm-generic/pgalloc.h>
+
+#define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
+{
+	set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot));
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
+{
+	pudval_t pudval = PUD_TYPE_TABLE;
+
+	pudval |= (mm == &init_mm) ? PUD_TABLE_UXN : PUD_TABLE_PXN;
+	__pud_populate(pudp, __pa(pmdp), pudval);
+}
+#else
+static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
+{
+	BUILD_BUG();
+}
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
+{
+	set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot));
+}
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
+{
+	p4dval_t p4dval = P4D_TYPE_TABLE;
+
+	p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN;
+	__p4d_populate(p4dp, __pa(pudp), p4dval);
+}
+#else
+static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
+{
+	BUILD_BUG();
+}
+#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
+
+extern pgd_t *pgd_alloc(struct mm_struct *mm);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp);
+
+static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep,
+				  pmdval_t prot)
+{
+	set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot));
+}
+
+/*
+ * Populate the pmdp entry with a pointer to the pte.  This pmd is part
+ * of the mm address space.
+ */
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
+{
+	VM_BUG_ON(mm && mm != &init_mm);
+	__pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
+}
+
+static inline void
+pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
+{
+	VM_BUG_ON(mm == &init_mm);
+	__pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_PXN);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
new file mode 100644
index 000000000..5ab8d1631
--- /dev/null
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -0,0 +1,295 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PGTABLE_HWDEF_H
+#define __ASM_PGTABLE_HWDEF_H
+
+#include <asm/memory.h>
+
+/*
+ * Number of page-table levels required to address 'va_bits' wide
+ * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
+ * bits with (PAGE_SHIFT - 3) bits at each page table level. Hence:
+ *
+ *  levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3))
+ *
+ * where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d))
+ *
+ * We cannot include linux/kernel.h which defines DIV_ROUND_UP here
+ * due to build issues. So we open code DIV_ROUND_UP here:
+ *
+ *	((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3))
+ *
+ * which gets simplified as :
+ */
+#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
+
+/*
+ * Size mapped by an entry at level n ( 0 <= n <= 3)
+ * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
+ * in the final page. The maximum number of translation levels supported by
+ * the architecture is 4. Hence, starting at level n, we have further
+ * ((4 - n) - 1) levels of translation excluding the offset within the page.
+ * So, the total number of bits mapped by an entry at level n is :
+ *
+ *  ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT
+ *
+ * Rearranging it a bit we get :
+ *   (4 - n) * (PAGE_SHIFT - 3) + 3
+ */
+#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n)	((PAGE_SHIFT - 3) * (4 - (n)) + 3)
+
+#define PTRS_PER_PTE		(1 << (PAGE_SHIFT - 3))
+
+/*
+ * PMD_SHIFT determines the size a level 2 page table entry can map.
+ */
+#if CONFIG_PGTABLE_LEVELS > 2
+#define PMD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
+#define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PTRS_PER_PMD		(1 << (PAGE_SHIFT - 3))
+#endif
+
+/*
+ * PUD_SHIFT determines the size a level 1 page table entry can map.
+ */
+#if CONFIG_PGTABLE_LEVELS > 3
+#define PUD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
+#define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK		(~(PUD_SIZE-1))
+#define PTRS_PER_PUD		(1 << (PAGE_SHIFT - 3))
+#endif
+
+/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map
+ * (depending on the configuration, this level can be 0, 1 or 2).
+ */
+#define PGDIR_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
+#define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+#define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))
+
+/*
+ * Contiguous page definitions.
+ */
+#define CONT_PTE_SHIFT		(CONFIG_ARM64_CONT_PTE_SHIFT + PAGE_SHIFT)
+#define CONT_PTES		(1 << (CONT_PTE_SHIFT - PAGE_SHIFT))
+#define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
+#define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
+
+#define CONT_PMD_SHIFT		(CONFIG_ARM64_CONT_PMD_SHIFT + PMD_SHIFT)
+#define CONT_PMDS		(1 << (CONT_PMD_SHIFT - PMD_SHIFT))
+#define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
+#define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
+
+/*
+ * Hardware page table definitions.
+ *
+ * Level 0 descriptor (P4D).
+ */
+#define P4D_TYPE_TABLE		(_AT(p4dval_t, 3) << 0)
+#define P4D_TABLE_BIT		(_AT(p4dval_t, 1) << 1)
+#define P4D_TYPE_MASK		(_AT(p4dval_t, 3) << 0)
+#define P4D_TYPE_SECT		(_AT(p4dval_t, 1) << 0)
+#define P4D_SECT_RDONLY		(_AT(p4dval_t, 1) << 7)		/* AP[2] */
+#define P4D_TABLE_PXN		(_AT(p4dval_t, 1) << 59)
+#define P4D_TABLE_UXN		(_AT(p4dval_t, 1) << 60)
+
+/*
+ * Level 1 descriptor (PUD).
+ */
+#define PUD_TYPE_TABLE		(_AT(pudval_t, 3) << 0)
+#define PUD_TABLE_BIT		(_AT(pudval_t, 1) << 1)
+#define PUD_TYPE_MASK		(_AT(pudval_t, 3) << 0)
+#define PUD_TYPE_SECT		(_AT(pudval_t, 1) << 0)
+#define PUD_SECT_RDONLY		(_AT(pudval_t, 1) << 7)		/* AP[2] */
+#define PUD_TABLE_PXN		(_AT(pudval_t, 1) << 59)
+#define PUD_TABLE_UXN		(_AT(pudval_t, 1) << 60)
+
+/*
+ * Level 2 descriptor (PMD).
+ */
+#define PMD_TYPE_MASK		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_TABLE		(_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_SECT		(_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT		(_AT(pmdval_t, 1) << 1)
+
+/*
+ * Section
+ */
+#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
+#define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
+#define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_NG		(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_CONT		(_AT(pmdval_t, 1) << 52)
+#define PMD_SECT_PXN		(_AT(pmdval_t, 1) << 53)
+#define PMD_SECT_UXN		(_AT(pmdval_t, 1) << 54)
+#define PMD_TABLE_PXN		(_AT(pmdval_t, 1) << 59)
+#define PMD_TABLE_UXN		(_AT(pmdval_t, 1) << 60)
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PMD_ATTRINDX(t)		(_AT(pmdval_t, (t)) << 2)
+#define PMD_ATTRINDX_MASK	(_AT(pmdval_t, 7) << 2)
+
+/*
+ * Level 3 descriptor (PTE).
+ */
+#define PTE_VALID		(_AT(pteval_t, 1) << 0)
+#define PTE_TYPE_MASK		(_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_PAGE		(_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
+#define PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
+#define PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
+#define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
+#define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
+#define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_GP			(_AT(pteval_t, 1) << 50)	/* BTI guarded */
+#define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
+#define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
+#define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
+#define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
+
+#define PTE_ADDR_LOW		(((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define PTE_ADDR_HIGH		(_AT(pteval_t, 0xf) << 12)
+#define PTE_ADDR_MASK		(PTE_ADDR_LOW | PTE_ADDR_HIGH)
+#else
+#define PTE_ADDR_MASK		PTE_ADDR_LOW
+#endif
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PTE_ATTRINDX(t)		(_AT(pteval_t, (t)) << 2)
+#define PTE_ATTRINDX_MASK	(_AT(pteval_t, 7) << 2)
+
+/*
+ * Memory Attribute override for Stage-2 (MemAttr[3:0])
+ */
+#define PTE_S2_MEMATTR(t)	(_AT(pteval_t, (t)) << 2)
+
+/*
+ * Highest possible physical address supported.
+ */
+#define PHYS_MASK_SHIFT		(CONFIG_ARM64_PA_BITS)
+#define PHYS_MASK		((UL(1) << PHYS_MASK_SHIFT) - 1)
+
+#define TTBR_CNP_BIT		(UL(1) << 0)
+
+/*
+ * TCR flags.
+ */
+#define TCR_T0SZ_OFFSET		0
+#define TCR_T1SZ_OFFSET		16
+#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_T0SZ_OFFSET)
+#define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_T1SZ_OFFSET)
+#define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
+#define TCR_TxSZ_WIDTH		6
+#define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
+#define TCR_T1SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET)
+
+#define TCR_EPD0_SHIFT		7
+#define TCR_EPD0_MASK		(UL(1) << TCR_EPD0_SHIFT)
+#define TCR_IRGN0_SHIFT		8
+#define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NC		(UL(0) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBWA		(UL(1) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WT		(UL(2) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBnWA		(UL(3) << TCR_IRGN0_SHIFT)
+
+#define TCR_EPD1_SHIFT		23
+#define TCR_EPD1_MASK		(UL(1) << TCR_EPD1_SHIFT)
+#define TCR_IRGN1_SHIFT		24
+#define TCR_IRGN1_MASK		(UL(3) << TCR_IRGN1_SHIFT)
+#define TCR_IRGN1_NC		(UL(0) << TCR_IRGN1_SHIFT)
+#define TCR_IRGN1_WBWA		(UL(1) << TCR_IRGN1_SHIFT)
+#define TCR_IRGN1_WT		(UL(2) << TCR_IRGN1_SHIFT)
+#define TCR_IRGN1_WBnWA		(UL(3) << TCR_IRGN1_SHIFT)
+
+#define TCR_IRGN_NC		(TCR_IRGN0_NC | TCR_IRGN1_NC)
+#define TCR_IRGN_WBWA		(TCR_IRGN0_WBWA | TCR_IRGN1_WBWA)
+#define TCR_IRGN_WT		(TCR_IRGN0_WT | TCR_IRGN1_WT)
+#define TCR_IRGN_WBnWA		(TCR_IRGN0_WBnWA | TCR_IRGN1_WBnWA)
+#define TCR_IRGN_MASK		(TCR_IRGN0_MASK | TCR_IRGN1_MASK)
+
+
+#define TCR_ORGN0_SHIFT		10
+#define TCR_ORGN0_MASK		(UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NC		(UL(0) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBWA		(UL(1) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WT		(UL(2) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBnWA		(UL(3) << TCR_ORGN0_SHIFT)
+
+#define TCR_ORGN1_SHIFT		26
+#define TCR_ORGN1_MASK		(UL(3) << TCR_ORGN1_SHIFT)
+#define TCR_ORGN1_NC		(UL(0) << TCR_ORGN1_SHIFT)
+#define TCR_ORGN1_WBWA		(UL(1) << TCR_ORGN1_SHIFT)
+#define TCR_ORGN1_WT		(UL(2) << TCR_ORGN1_SHIFT)
+#define TCR_ORGN1_WBnWA		(UL(3) << TCR_ORGN1_SHIFT)
+
+#define TCR_ORGN_NC		(TCR_ORGN0_NC | TCR_ORGN1_NC)
+#define TCR_ORGN_WBWA		(TCR_ORGN0_WBWA | TCR_ORGN1_WBWA)
+#define TCR_ORGN_WT		(TCR_ORGN0_WT | TCR_ORGN1_WT)
+#define TCR_ORGN_WBnWA		(TCR_ORGN0_WBnWA | TCR_ORGN1_WBnWA)
+#define TCR_ORGN_MASK		(TCR_ORGN0_MASK | TCR_ORGN1_MASK)
+
+#define TCR_SH0_SHIFT		12
+#define TCR_SH0_MASK		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_SH0_INNER		(UL(3) << TCR_SH0_SHIFT)
+
+#define TCR_SH1_SHIFT		28
+#define TCR_SH1_MASK		(UL(3) << TCR_SH1_SHIFT)
+#define TCR_SH1_INNER		(UL(3) << TCR_SH1_SHIFT)
+#define TCR_SHARED		(TCR_SH0_INNER | TCR_SH1_INNER)
+
+#define TCR_TG0_SHIFT		14
+#define TCR_TG0_MASK		(UL(3) << TCR_TG0_SHIFT)
+#define TCR_TG0_4K		(UL(0) << TCR_TG0_SHIFT)
+#define TCR_TG0_64K		(UL(1) << TCR_TG0_SHIFT)
+#define TCR_TG0_16K		(UL(2) << TCR_TG0_SHIFT)
+
+#define TCR_TG1_SHIFT		30
+#define TCR_TG1_MASK		(UL(3) << TCR_TG1_SHIFT)
+#define TCR_TG1_16K		(UL(1) << TCR_TG1_SHIFT)
+#define TCR_TG1_4K		(UL(2) << TCR_TG1_SHIFT)
+#define TCR_TG1_64K		(UL(3) << TCR_TG1_SHIFT)
+
+#define TCR_IPS_SHIFT		32
+#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
+#define TCR_A1			(UL(1) << 22)
+#define TCR_ASID16		(UL(1) << 36)
+#define TCR_TBI0		(UL(1) << 37)
+#define TCR_TBI1		(UL(1) << 38)
+#define TCR_HA			(UL(1) << 39)
+#define TCR_HD			(UL(1) << 40)
+#define TCR_TBID1		(UL(1) << 52)
+#define TCR_NFD0		(UL(1) << 53)
+#define TCR_NFD1		(UL(1) << 54)
+#define TCR_E0PD0		(UL(1) << 55)
+#define TCR_E0PD1		(UL(1) << 56)
+#define TCR_TCMA0		(UL(1) << 57)
+#define TCR_TCMA1		(UL(1) << 58)
+
+/*
+ * TTBR.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+/*
+ * TTBR_ELx[1] is RES0 in this configuration.
+ */
+#define TTBR_BADDR_MASK_52	GENMASK_ULL(47, 2)
+#endif
+
+#ifdef CONFIG_ARM64_VA_BITS_52
+/* Must be at least 64-byte aligned to prevent corruption of the TTBR */
+#define TTBR1_BADDR_4852_OFFSET	(((UL(1) << (52 - PGDIR_SHIFT)) - \
+				 (UL(1) << (48 - PGDIR_SHIFT))) * 8)
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
new file mode 100644
index 000000000..9b165117a
--- /dev/null
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 ARM Ltd.
+ */
+#ifndef __ASM_PGTABLE_PROT_H
+#define __ASM_PGTABLE_PROT_H
+
+#include <asm/memory.h>
+#include <asm/pgtable-hwdef.h>
+
+#include <linux/const.h>
+
+/*
+ * Software defined PTE bits definition.
+ */
+#define PTE_WRITE		(PTE_DBM)		 /* same as DBM (51) */
+#define PTE_SWP_EXCLUSIVE	(_AT(pteval_t, 1) << 2)	 /* only for swp ptes */
+#define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
+#define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
+#define PTE_DEVMAP		(_AT(pteval_t, 1) << 57)
+#define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
+
+/*
+ * This bit indicates that the entry is present i.e. pmd_page()
+ * still points to a valid huge page in memory even if the pmd
+ * has been invalidated.
+ */
+#define PMD_PRESENT_INVALID	(_AT(pteval_t, 1) << 59) /* only when !PMD_SECT_VALID */
+
+#ifndef __ASSEMBLY__
+
+#include <asm/cpufeature.h>
+#include <asm/pgtable-types.h>
+
+extern bool arm64_use_ng_mappings;
+
+#define _PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define _PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#define PTE_MAYBE_NG		(arm64_use_ng_mappings ? PTE_NG : 0)
+#define PMD_MAYBE_NG		(arm64_use_ng_mappings ? PMD_SECT_NG : 0)
+
+/*
+ * If we have userspace only BTI we don't want to mark kernel pages
+ * guarded even if the system does support BTI.
+ */
+#ifdef CONFIG_ARM64_BTI_KERNEL
+#define PTE_MAYBE_GP		(system_supports_bti() ? PTE_GP : 0)
+#else
+#define PTE_MAYBE_GP		0
+#endif
+
+#define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
+#define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
+
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_NORMAL_TAGGED	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_TAGGED))
+
+#define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
+#define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
+
+#define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+
+#define PAGE_KERNEL		__pgprot(PROT_NORMAL)
+#define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
+#define PAGE_KERNEL_ROX		__pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
+#define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)
+#define PAGE_KERNEL_EXEC_CONT	__pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
+
+#define PAGE_S2_MEMATTR(attr, has_fwb)					\
+	({								\
+		u64 __val;						\
+		if (has_fwb)						\
+			__val = PTE_S2_MEMATTR(MT_S2_FWB_ ## attr);	\
+		else							\
+			__val = PTE_S2_MEMATTR(MT_S2_ ## attr);		\
+		__val;							\
+	 })
+
+#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
+/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */
+#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
+#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
+#define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_PGTABLE_PROT_H */
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
new file mode 100644
index 000000000..b8f158ae2
--- /dev/null
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Page table types definitions.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ */
+
+#ifndef __ASM_PGTABLE_TYPES_H
+#define __ASM_PGTABLE_TYPES_H
+
+#include <asm/types.h>
+
+typedef u64 pteval_t;
+typedef u64 pmdval_t;
+typedef u64 pudval_t;
+typedef u64 p4dval_t;
+typedef u64 pgdval_t;
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+#define pte_val(x)	((x).pte)
+#define __pte(x)	((pte_t) { (x) } )
+
+#if CONFIG_PGTABLE_LEVELS > 2
+typedef struct { pmdval_t pmd; } pmd_t;
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x)	((pmd_t) { (x) } )
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 3
+typedef struct { pudval_t pud; } pud_t;
+#define pud_val(x)	((x).pud)
+#define __pud(x)	((pud_t) { (x) } )
+#endif
+
+typedef struct { pgdval_t pgd; } pgd_t;
+#define pgd_val(x)	((x).pgd)
+#define __pgd(x)	((pgd_t) { (x) } )
+
+typedef struct { pteval_t pgprot; } pgprot_t;
+#define pgprot_val(x)	((x).pgprot)
+#define __pgprot(x)	((pgprot_t) { (x) } )
+
+#if CONFIG_PGTABLE_LEVELS == 2
+#include <asm-generic/pgtable-nopmd.h>
+#elif CONFIG_PGTABLE_LEVELS == 3
+#include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 4
+#include <asm-generic/pgtable-nop4d.h>
+#endif
+
+#endif	/* __ASM_PGTABLE_TYPES_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
new file mode 100644
index 000000000..56c7df4c6
--- /dev/null
+++ b/arch/arm64/include/asm/pgtable.h
@@ -0,0 +1,1107 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PGTABLE_H
+#define __ASM_PGTABLE_H
+
+#include <asm/bug.h>
+#include <asm/proc-fns.h>
+
+#include <asm/memory.h>
+#include <asm/mte.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/pgtable-prot.h>
+#include <asm/tlbflush.h>
+
+/*
+ * VMALLOC range.
+ *
+ * VMALLOC_START: beginning of the kernel vmalloc space
+ * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space
+ *	and fixed mappings
+ */
+#define VMALLOC_START		(MODULES_END)
+#define VMALLOC_END		(VMEMMAP_START - SZ_256M)
+
+#define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
+
+#ifndef __ASSEMBLY__
+
+#include <asm/cmpxchg.h>
+#include <asm/fixmap.h>
+#include <linux/mmdebug.h>
+#include <linux/mm_types.h>
+#include <linux/sched.h>
+#include <linux/page_table_check.h>
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+
+/* Set stride and tlb_level in flush_*_tlb_range */
+#define flush_pmd_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2)
+#define flush_pud_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline bool arch_thp_swp_supported(void)
+{
+	return !system_supports_mte();
+}
+#define arch_thp_swp_supported arch_thp_swp_supported
+
+/*
+ * Outside of a few very special situations (e.g. hibernation), we always
+ * use broadcast TLB invalidation instructions, therefore a spurious page
+ * fault on one CPU which has been handled concurrently by another CPU
+ * does not need to perform additional invalidation.
+ */
+#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr)	phys_to_page(__pa_symbol(empty_zero_page))
+
+#define pte_ERROR(e)	\
+	pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e))
+
+/*
+ * Macros to convert between a physical address and its placement in a
+ * page table entry, taking care of 52-bit addresses.
+ */
+#ifdef CONFIG_ARM64_PA_BITS_52
+static inline phys_addr_t __pte_to_phys(pte_t pte)
+{
+	return (pte_val(pte) & PTE_ADDR_LOW) |
+		((pte_val(pte) & PTE_ADDR_HIGH) << 36);
+}
+static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
+{
+	return (phys | (phys >> 36)) & PTE_ADDR_MASK;
+}
+#else
+#define __pte_to_phys(pte)	(pte_val(pte) & PTE_ADDR_MASK)
+#define __phys_to_pte_val(phys)	(phys)
+#endif
+
+#define pte_pfn(pte)		(__pte_to_phys(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn,prot)	\
+	__pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+#define pte_none(pte)		(!pte_val(pte))
+#define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
+#define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
+
+/*
+ * The following only work if pte_present(). Undefined behaviour otherwise.
+ */
+#define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
+#define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
+#define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
+#define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
+#define pte_tagged(pte)		((pte_val(pte) & PTE_ATTRINDX_MASK) == \
+				 PTE_ATTRINDX(MT_NORMAL_TAGGED))
+
+#define pte_cont_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK;	\
+	(__boundary - 1 < (end) - 1) ? __boundary : (end);			\
+})
+
+#define pmd_cont_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK;	\
+	(__boundary - 1 < (end) - 1) ? __boundary : (end);			\
+})
+
+#define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
+#define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
+#define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
+
+#define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
+/*
+ * Execute-only user mappings do not have the PTE_USER bit set. All valid
+ * kernel mappings have the PTE_UXN bit set.
+ */
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
+/*
+ * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
+ * so that we don't erroneously return false for pages that have been
+ * remapped as PROT_NONE but are yet to be flushed from the TLB.
+ * Note that we can't make any assumptions based on the state of the access
+ * flag, since ptep_clear_flush_young() elides a DSB when invalidating the
+ * TLB.
+ */
+#define pte_accessible(mm, pte)	\
+	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
+
+/*
+ * p??_access_permitted() is true for valid user mappings (PTE_USER
+ * bit set, subject to the write permission check). For execute-only
+ * mappings, like PROT_EXEC with EPAN (both PTE_USER and PTE_UXN bits
+ * not set) must return false. PROT_NONE mappings do not have the
+ * PTE_VALID bit set.
+ */
+#define pte_access_permitted(pte, write) \
+	(((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte)))
+#define pmd_access_permitted(pmd, write) \
+	(pte_access_permitted(pmd_pte(pmd), (write)))
+#define pud_access_permitted(pud, write) \
+	(pte_access_permitted(pud_pte(pud), (write)))
+
+static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
+{
+	pte_val(pte) &= ~pgprot_val(prot);
+	return pte;
+}
+
+static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
+{
+	pte_val(pte) |= pgprot_val(prot);
+	return pte;
+}
+
+static inline pmd_t clear_pmd_bit(pmd_t pmd, pgprot_t prot)
+{
+	pmd_val(pmd) &= ~pgprot_val(prot);
+	return pmd;
+}
+
+static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot)
+{
+	pmd_val(pmd) |= pgprot_val(prot);
+	return pmd;
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+	return pte;
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+	return pte;
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
+
+	if (pte_write(pte))
+		pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+
+	return pte;
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	/*
+	 * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+	 * clear), set the PTE_DIRTY bit.
+	 */
+	if (pte_hw_dirty(pte))
+		pte = pte_mkdirty(pte);
+
+	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
+	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+	return pte;
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_AF));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_AF));
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
+}
+
+static inline pte_t pte_mkcont(pte_t pte)
+{
+	pte = set_pte_bit(pte, __pgprot(PTE_CONT));
+	return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
+}
+
+static inline pte_t pte_mknoncont(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_CONT));
+}
+
+static inline pte_t pte_mkpresent(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_VALID));
+}
+
+static inline pmd_t pmd_mkcont(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
+}
+
+static inline pte_t pte_mkdevmap(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
+}
+
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+	WRITE_ONCE(*ptep, pte);
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
+}
+
+extern void __sync_icache_dcache(pte_t pteval);
+
+/*
+ * PTE bits configuration in the presence of hardware Dirty Bit Management
+ * (PTE_WRITE == PTE_DBM):
+ *
+ * Dirty  Writable | PTE_RDONLY  PTE_WRITE  PTE_DIRTY (sw)
+ *   0      0      |   1           0          0
+ *   0      1      |   1           1          0
+ *   1      0      |   1           0          1
+ *   1      1      |   0           1          x
+ *
+ * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
+ * the page fault mechanism. Checking the dirty status of a pte becomes:
+ *
+ *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
+ */
+
+static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
+					   pte_t pte)
+{
+	pte_t old_pte;
+
+	if (!IS_ENABLED(CONFIG_DEBUG_VM))
+		return;
+
+	old_pte = READ_ONCE(*ptep);
+
+	if (!pte_valid(old_pte) || !pte_valid(pte))
+		return;
+	if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1)
+		return;
+
+	/*
+	 * Check for potential race with hardware updates of the pte
+	 * (ptep_set_access_flags safely changes valid ptes without going
+	 * through an invalid entry).
+	 */
+	VM_WARN_ONCE(!pte_young(pte),
+		     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+		     __func__, pte_val(old_pte), pte_val(pte));
+	VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
+		     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+		     __func__, pte_val(old_pte), pte_val(pte));
+}
+
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte)
+{
+	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
+		__sync_icache_dcache(pte);
+
+	/*
+	 * If the PTE would provide user space access to the tags associated
+	 * with it then ensure that the MTE tags are synchronised.  Although
+	 * pte_access_permitted() returns false for exec only mappings, they
+	 * don't expose tags (instruction fetches don't check tags).
+	 */
+	if (system_supports_mte() && pte_access_permitted(pte, false) &&
+	    !pte_special(pte)) {
+		pte_t old_pte = READ_ONCE(*ptep);
+		/*
+		 * We only need to synchronise if the new PTE has tags enabled
+		 * or if swapping in (in which case another mapping may have
+		 * set tags in the past even if this PTE isn't tagged).
+		 * (!pte_none() && !pte_present()) is an open coded version of
+		 * is_swap_pte()
+		 */
+		if (pte_tagged(pte) || (!pte_none(old_pte) && !pte_present(old_pte)))
+			mte_sync_tags(old_pte, pte);
+	}
+
+	__check_racy_pte_update(mm, ptep, pte);
+
+	set_pte(ptep, pte);
+}
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+	page_table_check_pte_set(mm, addr, ptep, pte);
+	return __set_pte_at(mm, addr, ptep, pte);
+}
+
+/*
+ * Huge pte definitions.
+ */
+#define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+/*
+ * Hugetlb definitions.
+ */
+#define HUGE_MAX_HSTATE		4
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+static inline pte_t pgd_pte(pgd_t pgd)
+{
+	return __pte(pgd_val(pgd));
+}
+
+static inline pte_t p4d_pte(p4d_t p4d)
+{
+	return __pte(p4d_val(p4d));
+}
+
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+static inline pud_t pte_pud(pte_t pte)
+{
+	return __pud(pte_val(pte));
+}
+
+static inline pmd_t pud_pmd(pud_t pud)
+{
+	return __pmd(pud_val(pud));
+}
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
+
+static inline pgprot_t mk_pud_sect_prot(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT);
+}
+
+static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
+}
+
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & PTE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
+}
+
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
+
+	return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * See the comment in include/linux/pgtable.h
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif
+
+#define pmd_present_invalid(pmd)     (!!(pmd_val(pmd) & PMD_PRESENT_INVALID))
+
+static inline int pmd_present(pmd_t pmd)
+{
+	return pte_present(pmd_pte(pmd)) || pmd_present_invalid(pmd);
+}
+
+/*
+ * THP definitions.
+ */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
+#define pmd_user(pmd)		pte_user(pmd_pte(pmd))
+#define pmd_user_exec(pmd)	pte_user_exec(pmd_pte(pmd))
+#define pmd_cont(pmd)		pte_cont(pmd_pte(pmd))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+
+static inline pmd_t pmd_mkinvalid(pmd_t pmd)
+{
+	pmd = set_pmd_bit(pmd, __pgprot(PMD_PRESENT_INVALID));
+	pmd = clear_pmd_bit(pmd, __pgprot(PMD_SECT_VALID));
+
+	return pmd;
+}
+
+#define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
+
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+
+#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_devmap(pmd)		pte_devmap(pmd_pte(pmd))
+#endif
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+	return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP)));
+}
+
+#define __pmd_to_phys(pmd)	__pte_to_phys(pmd_pte(pmd))
+#define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
+#define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	__pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+#define pud_young(pud)		pte_young(pud_pte(pud))
+#define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
+#define pud_write(pud)		pte_write(pud_pte(pud))
+
+#define pud_mkhuge(pud)		(__pud(pud_val(pud) & ~PUD_TABLE_BIT))
+
+#define __pud_to_phys(pud)	__pte_to_phys(pud_pte(pud))
+#define __phys_to_pud_val(phys)	__phys_to_pte_val(phys)
+#define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
+#define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	page_table_check_pmd_set(mm, addr, pmdp, pmd);
+	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+}
+
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+			      pud_t *pudp, pud_t pud)
+{
+	page_table_check_pud_set(mm, addr, pudp, pud);
+	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+}
+
+#define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
+#define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)
+
+#define __pgd_to_phys(pgd)	__pte_to_phys(pgd_pte(pgd))
+#define __phys_to_pgd_val(phys)	__phys_to_pte_val(phys)
+
+#define __pgprot_modify(prot,mask,bits) \
+	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
+#define pgprot_nx(prot) \
+	__pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN)
+
+/*
+ * Mark the prot value as uncacheable and unbufferable.
+ */
+#define pgprot_noncached(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
+#define pgprot_writecombine(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
+#define pgprot_device(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
+#define pgprot_tagged(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED))
+#define pgprot_mhp	pgprot_tagged
+/*
+ * DMA allocations for non-coherent devices use what the Arm architecture calls
+ * "Normal non-cacheable" memory, which permits speculation, unaligned accesses
+ * and merging of writes.  This is different from "Device-nGnR[nE]" memory which
+ * is intended for MMIO and thus forbids speculation, preserves access size,
+ * requires strict alignment and can also force write responses to come from the
+ * endpoint.
+ */
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, \
+			PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
+
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+
+#define pmd_table(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
+				 PMD_TYPE_TABLE)
+#define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
+				 PMD_TYPE_SECT)
+#define pmd_leaf(pmd)		(pmd_present(pmd) && !pmd_table(pmd))
+#define pmd_bad(pmd)		(!pmd_table(pmd))
+
+#define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
+#define pte_leaf_size(pte)	(pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE)
+
+#if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
+static inline bool pud_sect(pud_t pud) { return false; }
+static inline bool pud_table(pud_t pud) { return true; }
+#else
+#define pud_sect(pud)		((pud_val(pud) & PUD_TYPE_MASK) == \
+				 PUD_TYPE_SECT)
+#define pud_table(pud)		((pud_val(pud) & PUD_TYPE_MASK) == \
+				 PUD_TYPE_TABLE)
+#endif
+
+extern pgd_t init_pg_dir[PTRS_PER_PGD];
+extern pgd_t init_pg_end[];
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_end[];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
+extern pgd_t reserved_pg_dir[PTRS_PER_PGD];
+
+extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline bool in_swapper_pgdir(void *addr)
+{
+	return ((unsigned long)addr & PAGE_MASK) ==
+	        ((unsigned long)swapper_pg_dir & PAGE_MASK);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+#ifdef __PAGETABLE_PMD_FOLDED
+	if (in_swapper_pgdir(pmdp)) {
+		set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd)));
+		return;
+	}
+#endif /* __PAGETABLE_PMD_FOLDED */
+
+	WRITE_ONCE(*pmdp, pmd);
+
+	if (pmd_valid(pmd)) {
+		dsb(ishst);
+		isb();
+	}
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	set_pmd(pmdp, __pmd(0));
+}
+
+static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
+{
+	return __pmd_to_phys(pmd);
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+	return (unsigned long)__va(pmd_page_paddr(pmd));
+}
+
+/* Find an entry in the third-level page table. */
+#define pte_offset_phys(dir,addr)	(pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t))
+
+#define pte_set_fixmap(addr)		((pte_t *)set_fixmap_offset(FIX_PTE, addr))
+#define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
+#define pte_clear_fixmap()		clear_fixmap(FIX_PTE)
+
+#define pmd_page(pmd)			phys_to_page(__pmd_to_phys(pmd))
+
+/* use ONLY for statically allocated translation tables */
+#define pte_offset_kimg(dir,addr)	((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr))))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+#define pmd_ERROR(e)	\
+	pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
+
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_bad(pud)		(!pud_table(pud))
+#define pud_present(pud)	pte_present(pud_pte(pud))
+#define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
+#define pud_valid(pud)		pte_valid(pud_pte(pud))
+#define pud_user(pud)		pte_user(pud_pte(pud))
+#define pud_user_exec(pud)	pte_user_exec(pud_pte(pud))
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+#ifdef __PAGETABLE_PUD_FOLDED
+	if (in_swapper_pgdir(pudp)) {
+		set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud)));
+		return;
+	}
+#endif /* __PAGETABLE_PUD_FOLDED */
+
+	WRITE_ONCE(*pudp, pud);
+
+	if (pud_valid(pud)) {
+		dsb(ishst);
+		isb();
+	}
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	set_pud(pudp, __pud(0));
+}
+
+static inline phys_addr_t pud_page_paddr(pud_t pud)
+{
+	return __pud_to_phys(pud);
+}
+
+static inline pmd_t *pud_pgtable(pud_t pud)
+{
+	return (pmd_t *)__va(pud_page_paddr(pud));
+}
+
+/* Find an entry in the second-level page table. */
+#define pmd_offset_phys(dir, addr)	(pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t))
+
+#define pmd_set_fixmap(addr)		((pmd_t *)set_fixmap_offset(FIX_PMD, addr))
+#define pmd_set_fixmap_offset(pud, addr)	pmd_set_fixmap(pmd_offset_phys(pud, addr))
+#define pmd_clear_fixmap()		clear_fixmap(FIX_PMD)
+
+#define pud_page(pud)			phys_to_page(__pud_to_phys(pud))
+
+/* use ONLY for statically allocated translation tables */
+#define pmd_offset_kimg(dir,addr)	((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr))))
+
+#else
+
+#define pud_page_paddr(pud)	({ BUILD_BUG(); 0; })
+
+/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
+#define pmd_set_fixmap(addr)		NULL
+#define pmd_set_fixmap_offset(pudp, addr)	((pmd_t *)pudp)
+#define pmd_clear_fixmap()
+
+#define pmd_offset_kimg(dir,addr)	((pmd_t *)dir)
+
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+#define pud_ERROR(e)	\
+	pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e))
+
+#define p4d_none(p4d)		(!p4d_val(p4d))
+#define p4d_bad(p4d)		(!(p4d_val(p4d) & 2))
+#define p4d_present(p4d)	(p4d_val(p4d))
+
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	if (in_swapper_pgdir(p4dp)) {
+		set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d)));
+		return;
+	}
+
+	WRITE_ONCE(*p4dp, p4d);
+	dsb(ishst);
+	isb();
+}
+
+static inline void p4d_clear(p4d_t *p4dp)
+{
+	set_p4d(p4dp, __p4d(0));
+}
+
+static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
+{
+	return __p4d_to_phys(p4d);
+}
+
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+	return (pud_t *)__va(p4d_page_paddr(p4d));
+}
+
+/* Find an entry in the first-level page table. */
+#define pud_offset_phys(dir, addr)	(p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
+
+#define pud_set_fixmap(addr)		((pud_t *)set_fixmap_offset(FIX_PUD, addr))
+#define pud_set_fixmap_offset(p4d, addr)	pud_set_fixmap(pud_offset_phys(p4d, addr))
+#define pud_clear_fixmap()		clear_fixmap(FIX_PUD)
+
+#define p4d_page(p4d)		pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d)))
+
+/* use ONLY for statically allocated translation tables */
+#define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
+
+#else
+
+#define p4d_page_paddr(p4d)	({ BUILD_BUG(); 0;})
+#define pgd_page_paddr(pgd)	({ BUILD_BUG(); 0;})
+
+/* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */
+#define pud_set_fixmap(addr)		NULL
+#define pud_set_fixmap_offset(pgdp, addr)	((pud_t *)pgdp)
+#define pud_clear_fixmap()
+
+#define pud_offset_kimg(dir,addr)	((pud_t *)dir)
+
+#endif  /* CONFIG_PGTABLE_LEVELS > 3 */
+
+#define pgd_ERROR(e)	\
+	pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e))
+
+#define pgd_set_fixmap(addr)	((pgd_t *)set_fixmap_offset(FIX_PGD, addr))
+#define pgd_clear_fixmap()	clear_fixmap(FIX_PGD)
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	/*
+	 * Normal and Normal-Tagged are two different memory types and indices
+	 * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK.
+	 */
+	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP |
+			      PTE_ATTRINDX_MASK;
+	/* preserve the hardware dirty information */
+	if (pte_hw_dirty(pte))
+		pte = pte_mkdirty(pte);
+	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+	/*
+	 * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware
+	 * dirtiness again.
+	 */
+	if (pte_sw_dirty(pte))
+		pte = pte_mkdirty(pte);
+	return pte;
+}
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PAGE_TABLE_CHECK
+static inline bool pte_user_accessible_page(pte_t pte)
+{
+	return pte_present(pte) && (pte_user(pte) || pte_user_exec(pte));
+}
+
+static inline bool pmd_user_accessible_page(pmd_t pmd)
+{
+	return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+}
+
+static inline bool pud_user_accessible_page(pud_t pud)
+{
+	return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
+}
+#endif
+
+/*
+ * Atomic pte/pmd modifications.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline int __ptep_test_and_clear_young(pte_t *ptep)
+{
+	pte_t old_pte, pte;
+
+	pte = READ_ONCE(*ptep);
+	do {
+		old_pte = pte;
+		pte = pte_mkold(pte);
+		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+					       pte_val(old_pte), pte_val(pte));
+	} while (pte_val(pte) != pte_val(old_pte));
+
+	return pte_young(pte);
+}
+
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pte_t *ptep)
+{
+	return __ptep_test_and_clear_young(ptep);
+}
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
+					 unsigned long address, pte_t *ptep)
+{
+	int young = ptep_test_and_clear_young(vma, address, ptep);
+
+	if (young) {
+		/*
+		 * We can elide the trailing DSB here since the worst that can
+		 * happen is that a CPU continues to use the young entry in its
+		 * TLB and we mistakenly reclaim the associated page. The
+		 * window for such an event is bounded by the next
+		 * context-switch, which provides a DSB to complete the TLB
+		 * invalidation.
+		 */
+		flush_tlb_page_nosync(vma, address);
+	}
+
+	return young;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long address,
+					    pmd_t *pmdp)
+{
+	return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
+
+	page_table_check_pte_clear(mm, address, pte);
+
+	return pte;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
+{
+	pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0));
+
+	page_table_check_pmd_clear(mm, address, pmd);
+
+	return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * ptep_set_wrprotect - mark read-only while trasferring potential hardware
+ * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
+ */
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
+{
+	pte_t old_pte, pte;
+
+	pte = READ_ONCE(*ptep);
+	do {
+		old_pte = pte;
+		pte = pte_wrprotect(pte);
+		pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+					       pte_val(old_pte), pte_val(pte));
+	} while (pte_val(pte) != pte_val(old_pte));
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pmd_t *pmdp)
+{
+	ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
+}
+
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
+	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
+}
+#endif
+
+/*
+ * Encode and decode a swap entry:
+ *	bits 0-1:	present (must be zero)
+ *	bits 2:		remember PG_anon_exclusive
+ *	bits 3-7:	swap type
+ *	bits 8-57:	swap offset
+ *	bit  58:	PTE_PROT_NONE (must be zero)
+ */
+#define __SWP_TYPE_SHIFT	3
+#define __SWP_TYPE_BITS		5
+#define __SWP_OFFSET_BITS	50
+#define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+#define __SWP_OFFSET_MASK	((1UL << __SWP_OFFSET_BITS) - 1)
+
+#define __swp_type(x)		(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
+#define __swp_offset(x)		(((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK)
+#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+#define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val(pmd) })
+#define __swp_entry_to_pmd(swp)		__pmd((swp).val)
+#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+
+/*
+ * Ensure that there are not more swap files than can be encoded in the kernel
+ * PTEs.
+ */
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+extern int kern_addr_valid(unsigned long addr);
+
+#ifdef CONFIG_ARM64_MTE
+
+#define __HAVE_ARCH_PREPARE_TO_SWAP
+static inline int arch_prepare_to_swap(struct page *page)
+{
+	if (system_supports_mte())
+		return mte_save_tags(page);
+	return 0;
+}
+
+#define __HAVE_ARCH_SWAP_INVALIDATE
+static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
+{
+	if (system_supports_mte())
+		mte_invalidate_tags(type, offset);
+}
+
+static inline void arch_swap_invalidate_area(int type)
+{
+	if (system_supports_mte())
+		mte_invalidate_tags_area(type);
+}
+
+#define __HAVE_ARCH_SWAP_RESTORE
+static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
+{
+	if (system_supports_mte() && mte_restore_tags(entry, &folio->page))
+		set_page_mte_tagged(&folio->page);
+}
+
+#endif /* CONFIG_ARM64_MTE */
+
+/*
+ * On AArch64, the cache coherency is handled via the set_pte_at() function.
+ */
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+	/*
+	 * We don't do anything here, so there's a very small chance of
+	 * us retaking a user fault which we just fixed up. The alternative
+	 * is doing a dsb(ishst), but that penalises the fastpath.
+	 */
+}
+
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
+#else
+#define phys_to_ttbr(addr)	(addr)
+#endif
+
+/*
+ * On arm64 without hardware Access Flag, copying from user will fail because
+ * the pte is old and cannot be marked young. So we always end up with zeroed
+ * page after fork() + CoW for pfn mappings. We don't always have a
+ * hardware-managed access flag on arm64.
+ */
+#define arch_has_hw_pte_young		cpu_has_hw_af
+
+/*
+ * Experimentally, it's cheap to set the access flag in hardware and we
+ * benefit from prefaulting mappings as 'old' to start with.
+ */
+#define arch_wants_old_prefaulted_pte	cpu_has_hw_af
+
+static inline bool pud_sect_supported(void)
+{
+	return PAGE_SIZE == SZ_4K;
+}
+
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
new file mode 100644
index 000000000..efb098de3
--- /dev/null
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_POINTER_AUTH_H
+#define __ASM_POINTER_AUTH_H
+
+#include <linux/bitops.h>
+#include <linux/prctl.h>
+#include <linux/random.h>
+
+#include <asm/cpufeature.h>
+#include <asm/memory.h>
+#include <asm/sysreg.h>
+
+#define PR_PAC_ENABLED_KEYS_MASK                                               \
+	(PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY)
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+/*
+ * Each key is a 128-bit quantity which is split across a pair of 64-bit
+ * registers (Lo and Hi).
+ */
+struct ptrauth_key {
+	unsigned long lo, hi;
+};
+
+/*
+ * We give each process its own keys, which are shared by all threads. The keys
+ * are inherited upon fork(), and reinitialised upon exec*().
+ */
+struct ptrauth_keys_user {
+	struct ptrauth_key apia;
+	struct ptrauth_key apib;
+	struct ptrauth_key apda;
+	struct ptrauth_key apdb;
+	struct ptrauth_key apga;
+};
+
+#define __ptrauth_key_install_nosync(k, v)			\
+do {								\
+	struct ptrauth_key __pki_v = (v);			\
+	write_sysreg_s(__pki_v.lo, SYS_ ## k ## KEYLO_EL1);	\
+	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
+} while (0)
+
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+
+struct ptrauth_keys_kernel {
+	struct ptrauth_key apia;
+};
+
+static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (system_supports_address_auth())
+		get_random_bytes(&keys->apia, sizeof(keys->apia));
+}
+
+static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (!system_supports_address_auth())
+		return;
+
+	__ptrauth_key_install_nosync(APIA, keys->apia);
+	isb();
+}
+
+#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
+static inline void ptrauth_keys_install_user(struct ptrauth_keys_user *keys)
+{
+	if (system_supports_address_auth()) {
+		__ptrauth_key_install_nosync(APIB, keys->apib);
+		__ptrauth_key_install_nosync(APDA, keys->apda);
+		__ptrauth_key_install_nosync(APDB, keys->apdb);
+	}
+
+	if (system_supports_generic_auth())
+		__ptrauth_key_install_nosync(APGA, keys->apga);
+}
+
+static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys)
+{
+	if (system_supports_address_auth()) {
+		get_random_bytes(&keys->apia, sizeof(keys->apia));
+		get_random_bytes(&keys->apib, sizeof(keys->apib));
+		get_random_bytes(&keys->apda, sizeof(keys->apda));
+		get_random_bytes(&keys->apdb, sizeof(keys->apdb));
+	}
+
+	if (system_supports_generic_auth())
+		get_random_bytes(&keys->apga, sizeof(keys->apga));
+
+	ptrauth_keys_install_user(keys);
+}
+
+extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
+
+extern int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys,
+				    unsigned long enabled);
+extern int ptrauth_get_enabled_keys(struct task_struct *tsk);
+
+static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
+{
+	return ptrauth_clear_pac(ptr);
+}
+
+static __always_inline void ptrauth_enable(void)
+{
+	if (!system_supports_address_auth())
+		return;
+	sysreg_clear_set(sctlr_el1, 0, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB |
+					SCTLR_ELx_ENDA | SCTLR_ELx_ENDB));
+	isb();
+}
+
+#define ptrauth_suspend_exit()                                                 \
+	ptrauth_keys_install_user(&current->thread.keys_user)
+
+#define ptrauth_thread_init_user()                                             \
+	do {                                                                   \
+		ptrauth_keys_init_user(&current->thread.keys_user);            \
+									       \
+		/* enable all keys */                                          \
+		if (system_supports_address_auth())                            \
+			ptrauth_set_enabled_keys(current,                      \
+						 PR_PAC_ENABLED_KEYS_MASK,     \
+						 PR_PAC_ENABLED_KEYS_MASK);    \
+	} while (0)
+
+#define ptrauth_thread_switch_user(tsk)                                        \
+	ptrauth_keys_install_user(&(tsk)->thread.keys_user)
+
+#else /* CONFIG_ARM64_PTR_AUTH */
+#define ptrauth_enable()
+#define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
+#define ptrauth_set_enabled_keys(tsk, keys, enabled)	(-EINVAL)
+#define ptrauth_get_enabled_keys(tsk)	(-EINVAL)
+#define ptrauth_strip_insn_pac(lr)	(lr)
+#define ptrauth_suspend_exit()
+#define ptrauth_thread_init_user()
+#define ptrauth_thread_switch_user(tsk)
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+#define ptrauth_thread_init_kernel(tsk)					\
+	ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
+#define ptrauth_thread_switch_kernel(tsk)				\
+	ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel)
+#else
+#define ptrauth_thread_init_kernel(tsk)
+#define ptrauth_thread_switch_kernel(tsk)
+#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */
+
+#endif /* __ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
new file mode 100644
index 000000000..0159b625c
--- /dev/null
+++ b/arch/arm64/include/asm/preempt.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <linux/jump_label.h>
+#include <linux/thread_info.h>
+
+#define PREEMPT_NEED_RESCHED	BIT(32)
+#define PREEMPT_ENABLED	(PREEMPT_NEED_RESCHED)
+
+static inline int preempt_count(void)
+{
+	return READ_ONCE(current_thread_info()->preempt.count);
+}
+
+static inline void preempt_count_set(u64 pc)
+{
+	/* Preserve existing value of PREEMPT_NEED_RESCHED */
+	WRITE_ONCE(current_thread_info()->preempt.count, pc);
+}
+
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+static inline void set_preempt_need_resched(void)
+{
+	current_thread_info()->preempt.need_resched = 0;
+}
+
+static inline void clear_preempt_need_resched(void)
+{
+	current_thread_info()->preempt.need_resched = 1;
+}
+
+static inline bool test_preempt_need_resched(void)
+{
+	return !current_thread_info()->preempt.need_resched;
+}
+
+static inline void __preempt_count_add(int val)
+{
+	u32 pc = READ_ONCE(current_thread_info()->preempt.count);
+	pc += val;
+	WRITE_ONCE(current_thread_info()->preempt.count, pc);
+}
+
+static inline void __preempt_count_sub(int val)
+{
+	u32 pc = READ_ONCE(current_thread_info()->preempt.count);
+	pc -= val;
+	WRITE_ONCE(current_thread_info()->preempt.count, pc);
+}
+
+static inline bool __preempt_count_dec_and_test(void)
+{
+	struct thread_info *ti = current_thread_info();
+	u64 pc = READ_ONCE(ti->preempt_count);
+
+	/* Update only the count field, leaving need_resched unchanged */
+	WRITE_ONCE(ti->preempt.count, --pc);
+
+	/*
+	 * If we wrote back all zeroes, then we're preemptible and in
+	 * need of a reschedule. Otherwise, we need to reload the
+	 * preempt_count in case the need_resched flag was cleared by an
+	 * interrupt occurring between the non-atomic READ_ONCE/WRITE_ONCE
+	 * pair.
+	 */
+	return !pc || !READ_ONCE(ti->preempt_count);
+}
+
+static inline bool should_resched(int preempt_offset)
+{
+	u64 pc = READ_ONCE(current_thread_info()->preempt_count);
+	return pc == preempt_offset;
+}
+
+#ifdef CONFIG_PREEMPTION
+
+void preempt_schedule(void);
+void preempt_schedule_notrace(void);
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_preempt_schedule(void);
+#define __preempt_schedule()		dynamic_preempt_schedule()
+void dynamic_preempt_schedule_notrace(void);
+#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
+
+#else /* CONFIG_PREEMPT_DYNAMIC */
+
+#define __preempt_schedule()		preempt_schedule()
+#define __preempt_schedule_notrace()	preempt_schedule_notrace()
+
+#endif /* CONFIG_PREEMPT_DYNAMIC */
+#endif /* CONFIG_PREEMPTION */
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h
new file mode 100644
index 000000000..006946745
--- /dev/null
+++ b/arch/arm64/include/asm/probes.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/probes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ */
+#ifndef _ARM_PROBES_H
+#define _ARM_PROBES_H
+
+#include <asm/insn.h>
+
+typedef u32 probe_opcode_t;
+typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_probe_insn {
+	probe_opcode_t *insn;
+	pstate_check_t *pstate_cc;
+	probes_handler_t *handler;
+	/* restore address after step xol */
+	unsigned long restore;
+};
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
new file mode 100644
index 000000000..0d5d1f052
--- /dev/null
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/proc-fns.h
+ *
+ * Copyright (C) 1997-1999 Russell King
+ * Copyright (C) 2000 Deep Blue Solutions Ltd
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PROCFNS_H
+#define __ASM_PROCFNS_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/page.h>
+
+struct cpu_suspend_ctx;
+
+extern void cpu_do_idle(void);
+extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
+extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
+
+#include <asm/memory.h>
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_PROCFNS_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
new file mode 100644
index 000000000..400f89563
--- /dev/null
+++ b/arch/arm64/include/asm/processor.h
@@ -0,0 +1,413 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/processor.h
+ *
+ * Copyright (C) 1995-1999 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PROCESSOR_H
+#define __ASM_PROCESSOR_H
+
+/*
+ * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is
+ * no point in shifting all network buffers by 2 bytes just to make some IP
+ * header fields appear aligned in memory, potentially sacrificing some DMA
+ * performance on some platforms.
+ */
+#define NET_IP_ALIGN	0
+
+#define MTE_CTRL_GCR_USER_EXCL_SHIFT	0
+#define MTE_CTRL_GCR_USER_EXCL_MASK	0xffff
+
+#define MTE_CTRL_TCF_SYNC		(1UL << 16)
+#define MTE_CTRL_TCF_ASYNC		(1UL << 17)
+#define MTE_CTRL_TCF_ASYMM		(1UL << 18)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/build_bug.h>
+#include <linux/cache.h>
+#include <linux/init.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/thread_info.h>
+
+#include <vdso/processor.h>
+
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+#include <asm/hw_breakpoint.h>
+#include <asm/kasan.h>
+#include <asm/lse.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/pointer_auth.h>
+#include <asm/ptrace.h>
+#include <asm/spectre.h>
+#include <asm/types.h>
+
+/*
+ * TASK_SIZE - the maximum size of a user space task.
+ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
+ */
+
+#define DEFAULT_MAP_WINDOW_64	(UL(1) << VA_BITS_MIN)
+#define TASK_SIZE_64		(UL(1) << vabits_actual)
+#define TASK_SIZE_MAX		(UL(1) << VA_BITS)
+
+#ifdef CONFIG_COMPAT
+#if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
+#define TASK_SIZE_32		UL(0x100000000)
+#else
+#define TASK_SIZE_32		(UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
+#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
+#define DEFAULT_MAP_WINDOW	(test_thread_flag(TIF_32BIT) ? \
+				TASK_SIZE_32 : DEFAULT_MAP_WINDOW_64)
+#else
+#define TASK_SIZE		TASK_SIZE_64
+#define DEFAULT_MAP_WINDOW	DEFAULT_MAP_WINDOW_64
+#endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_ARM64_FORCE_52BIT
+#define STACK_TOP_MAX		TASK_SIZE_64
+#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
+#else
+#define STACK_TOP_MAX		DEFAULT_MAP_WINDOW_64
+#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(DEFAULT_MAP_WINDOW / 4))
+#endif /* CONFIG_ARM64_FORCE_52BIT */
+
+#ifdef CONFIG_COMPAT
+#define AARCH32_VECTORS_BASE	0xffff0000
+#define STACK_TOP		(test_thread_flag(TIF_32BIT) ? \
+				AARCH32_VECTORS_BASE : STACK_TOP_MAX)
+#else
+#define STACK_TOP		STACK_TOP_MAX
+#endif /* CONFIG_COMPAT */
+
+#ifndef CONFIG_ARM64_FORCE_52BIT
+#define arch_get_mmap_end(addr, len, flags) \
+		(((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW)
+
+#define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \
+					base + TASK_SIZE - DEFAULT_MAP_WINDOW :\
+					base)
+#endif /* CONFIG_ARM64_FORCE_52BIT */
+
+extern phys_addr_t arm64_dma_phys_limit;
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
+
+struct debug_info {
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	/* Have we suspended stepping by a debugger? */
+	int			suspended_step;
+	/* Allow breakpoints and watchpoints to be disabled for this thread. */
+	int			bps_disabled;
+	int			wps_disabled;
+	/* Hardware breakpoints pinned to this task. */
+	struct perf_event	*hbp_break[ARM_MAX_BRP];
+	struct perf_event	*hbp_watch[ARM_MAX_WRP];
+#endif
+};
+
+enum vec_type {
+	ARM64_VEC_SVE = 0,
+	ARM64_VEC_SME,
+	ARM64_VEC_MAX,
+};
+
+struct cpu_context {
+	unsigned long x19;
+	unsigned long x20;
+	unsigned long x21;
+	unsigned long x22;
+	unsigned long x23;
+	unsigned long x24;
+	unsigned long x25;
+	unsigned long x26;
+	unsigned long x27;
+	unsigned long x28;
+	unsigned long fp;
+	unsigned long sp;
+	unsigned long pc;
+};
+
+struct thread_struct {
+	struct cpu_context	cpu_context;	/* cpu context */
+
+	/*
+	 * Whitelisted fields for hardened usercopy:
+	 * Maintainers must ensure manually that this contains no
+	 * implicit padding.
+	 */
+	struct {
+		unsigned long	tp_value;	/* TLS register */
+		unsigned long	tp2_value;
+		struct user_fpsimd_state fpsimd_state;
+	} uw;
+
+	unsigned int		fpsimd_cpu;
+	void			*sve_state;	/* SVE registers, if any */
+	void			*za_state;	/* ZA register, if any */
+	unsigned int		vl[ARM64_VEC_MAX];	/* vector length */
+	unsigned int		vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
+	unsigned long		fault_address;	/* fault info */
+	unsigned long		fault_code;	/* ESR_EL1 value */
+	struct debug_info	debug;		/* debugging */
+#ifdef CONFIG_ARM64_PTR_AUTH
+	struct ptrauth_keys_user	keys_user;
+#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL
+	struct ptrauth_keys_kernel	keys_kernel;
+#endif
+#endif
+#ifdef CONFIG_ARM64_MTE
+	u64			mte_ctrl;
+#endif
+	u64			sctlr_user;
+	u64			svcr;
+	u64			tpidr2_el0;
+};
+
+static inline unsigned int thread_get_vl(struct thread_struct *thread,
+					 enum vec_type type)
+{
+	return thread->vl[type];
+}
+
+static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SVE);
+}
+
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
+static inline unsigned int thread_get_cur_vl(struct thread_struct *thread)
+{
+	if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK))
+		return thread_get_sme_vl(thread);
+	else
+		return thread_get_sve_vl(thread);
+}
+
+unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
+void task_set_vl(struct task_struct *task, enum vec_type type,
+		 unsigned long vl);
+void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
+			unsigned long vl);
+unsigned int task_get_vl_onexec(const struct task_struct *task,
+				enum vec_type type);
+
+static inline unsigned int task_get_sve_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SVE);
+}
+
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
+static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
+{
+	task_set_vl(task, ARM64_VEC_SVE, vl);
+}
+
+static inline unsigned int task_get_sve_vl_onexec(const struct task_struct *task)
+{
+	return task_get_vl_onexec(task, ARM64_VEC_SVE);
+}
+
+static inline void task_set_sve_vl_onexec(struct task_struct *task,
+					  unsigned long vl)
+{
+	task_set_vl_onexec(task, ARM64_VEC_SVE, vl);
+}
+
+#define SCTLR_USER_MASK                                                        \
+	(SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | SCTLR_ELx_ENDA | SCTLR_ELx_ENDB |   \
+	 SCTLR_EL1_TCF0_MASK)
+
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+						unsigned long *size)
+{
+	/* Verify that there is no padding among the whitelisted fields: */
+	BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) !=
+		     sizeof_field(struct thread_struct, uw.tp_value) +
+		     sizeof_field(struct thread_struct, uw.tp2_value) +
+		     sizeof_field(struct thread_struct, uw.fpsimd_state));
+
+	*offset = offsetof(struct thread_struct, uw);
+	*size = sizeof_field(struct thread_struct, uw);
+}
+
+#ifdef CONFIG_COMPAT
+#define task_user_tls(t)						\
+({									\
+	unsigned long *__tls;						\
+	if (is_compat_thread(task_thread_info(t)))			\
+		__tls = &(t)->thread.uw.tp2_value;			\
+	else								\
+		__tls = &(t)->thread.uw.tp_value;			\
+	__tls;								\
+ })
+#else
+#define task_user_tls(t)	(&(t)->thread.uw.tp_value)
+#endif
+
+/* Sync TPIDR_EL0 back to thread_struct for current */
+void tls_preserve_current_state(void);
+
+#define INIT_THREAD {				\
+	.fpsimd_cpu = NR_CPUS,			\
+}
+
+static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
+{
+	s32 previous_syscall = regs->syscallno;
+	memset(regs, 0, sizeof(*regs));
+	regs->syscallno = previous_syscall;
+	regs->pc = pc;
+
+	if (system_uses_irq_prio_masking())
+		regs->pmr_save = GIC_PRIO_IRQON;
+}
+
+static inline void start_thread(struct pt_regs *regs, unsigned long pc,
+				unsigned long sp)
+{
+	start_thread_common(regs, pc);
+	regs->pstate = PSR_MODE_EL0t;
+	spectre_v4_enable_task_mitigation(current);
+	regs->sp = sp;
+}
+
+#ifdef CONFIG_COMPAT
+static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
+				       unsigned long sp)
+{
+	start_thread_common(regs, pc);
+	regs->pstate = PSR_AA32_MODE_USR;
+	if (pc & 1)
+		regs->pstate |= PSR_AA32_T_BIT;
+
+#ifdef __AARCH64EB__
+	regs->pstate |= PSR_AA32_E_BIT;
+#endif
+
+	spectre_v4_enable_task_mitigation(current);
+	regs->compat_sp = sp;
+}
+#endif
+
+static __always_inline bool is_ttbr0_addr(unsigned long addr)
+{
+	/* entry assembly clears tags for TTBR0 addrs */
+	return addr < TASK_SIZE;
+}
+
+static __always_inline bool is_ttbr1_addr(unsigned long addr)
+{
+	/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
+	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
+}
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+unsigned long __get_wchan(struct task_struct *p);
+
+void update_sctlr_el1(u64 sctlr);
+
+/* Thread switching */
+extern struct task_struct *cpu_switch_to(struct task_struct *prev,
+					 struct task_struct *next);
+
+#define task_pt_regs(p) \
+	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
+
+#define KSTK_EIP(tsk)	((unsigned long)task_pt_regs(tsk)->pc)
+#define KSTK_ESP(tsk)	user_stack_pointer(task_pt_regs(tsk))
+
+/*
+ * Prefetching support
+ */
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(const void *ptr)
+{
+	asm volatile("prfm pldl1keep, %a0\n" : : "p" (ptr));
+}
+
+#define ARCH_HAS_PREFETCHW
+static inline void prefetchw(const void *ptr)
+{
+	asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr));
+}
+
+#define ARCH_HAS_SPINLOCK_PREFETCH
+static inline void spin_lock_prefetch(const void *ptr)
+{
+	asm volatile(ARM64_LSE_ATOMIC_INSN(
+		     "prfm pstl1strm, %a0",
+		     "nop") : : "p" (ptr));
+}
+
+extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
+extern void __init minsigstksz_setup(void);
+
+/*
+ * Not at the top of the file due to a direct #include cycle between
+ * <asm/fpsimd.h> and <asm/processor.h>.  Deferring this #include
+ * ensures that contents of processor.h are visible to fpsimd.h even if
+ * processor.h is included first.
+ *
+ * These prctl helpers are the only things in this file that require
+ * fpsimd.h.  The core code expects them to be in this header.
+ */
+#include <asm/fpsimd.h>
+
+/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */
+#define SVE_SET_VL(arg)	sve_set_current_vl(arg)
+#define SVE_GET_VL()	sve_get_current_vl()
+#define SME_SET_VL(arg)	sme_set_current_vl(arg)
+#define SME_GET_VL()	sme_get_current_vl()
+
+/* PR_PAC_RESET_KEYS prctl */
+#define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
+
+/* PR_PAC_{SET,GET}_ENABLED_KEYS prctl */
+#define PAC_SET_ENABLED_KEYS(tsk, keys, enabled)				\
+	ptrauth_set_enabled_keys(tsk, keys, enabled)
+#define PAC_GET_ENABLED_KEYS(tsk) ptrauth_get_enabled_keys(tsk)
+
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
+long get_tagged_addr_ctrl(struct task_struct *task);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(current, arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl(current)
+#endif
+
+/*
+ * For CONFIG_GCC_PLUGIN_STACKLEAK
+ *
+ * These need to be macros because otherwise we get stuck in a nightmare
+ * of header definitions for the use of task_stack_page.
+ */
+
+/*
+ * The top of the current task's task stack
+ */
+#define current_top_of_stack()	((unsigned long)current->stack + THREAD_SIZE)
+#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, 1))
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
new file mode 100644
index 000000000..b1dd7ecff
--- /dev/null
+++ b/arch/arm64/include/asm/ptdump.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 ARM Ltd.
+ */
+#ifndef __ASM_PTDUMP_H
+#define __ASM_PTDUMP_H
+
+#ifdef CONFIG_PTDUMP_CORE
+
+#include <linux/mm_types.h>
+#include <linux/seq_file.h>
+
+struct addr_marker {
+	unsigned long start_address;
+	char *name;
+};
+
+struct ptdump_info {
+	struct mm_struct		*mm;
+	const struct addr_marker	*markers;
+	unsigned long			base_addr;
+};
+
+void ptdump_walk(struct seq_file *s, struct ptdump_info *info);
+#ifdef CONFIG_PTDUMP_DEBUGFS
+void __init ptdump_debugfs_register(struct ptdump_info *info, const char *name);
+#else
+static inline void ptdump_debugfs_register(struct ptdump_info *info,
+					   const char *name) { }
+#endif
+void ptdump_check_wx(void);
+#endif /* CONFIG_PTDUMP_CORE */
+
+#ifdef CONFIG_DEBUG_WX
+#define debug_checkwx()	ptdump_check_wx()
+#else
+#define debug_checkwx()	do { } while (0)
+#endif
+
+#endif /* __ASM_PTDUMP_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
new file mode 100644
index 000000000..41b332c05
--- /dev/null
+++ b/arch/arm64/include/asm/ptrace.h
@@ -0,0 +1,393 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/ptrace.h
+ *
+ * Copyright (C) 1996-2003 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_PTRACE_H
+#define __ASM_PTRACE_H
+
+#include <asm/cpufeature.h>
+
+#include <uapi/asm/ptrace.h>
+
+/* Current Exception Level values, as contained in CurrentEL */
+#define CurrentEL_EL1		(1 << 2)
+#define CurrentEL_EL2		(2 << 2)
+
+#define INIT_PSTATE_EL1 \
+	(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL1h)
+#define INIT_PSTATE_EL2 \
+	(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL2h)
+
+/*
+ * PMR values used to mask/unmask interrupts.
+ *
+ * GIC priority masking works as follows: if an IRQ's priority is a higher value
+ * than the value held in PMR, that IRQ is masked. Lowering the value of PMR
+ * means masking more IRQs (or at least that the same IRQs remain masked).
+ *
+ * To mask interrupts, we clear the most significant bit of PMR.
+ *
+ * Some code sections either automatically switch back to PSR.I or explicitly
+ * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included
+ * in the priority mask, it indicates that PSR.I should be set and
+ * interrupt disabling temporarily does not rely on IRQ priorities.
+ */
+#define GIC_PRIO_IRQON			0xe0
+#define __GIC_PRIO_IRQOFF		(GIC_PRIO_IRQON & ~0x80)
+#define __GIC_PRIO_IRQOFF_NS		0xa0
+#define GIC_PRIO_PSR_I_SET		(1 << 4)
+
+#define GIC_PRIO_IRQOFF							\
+	({								\
+		extern struct static_key_false gic_nonsecure_priorities;\
+		u8 __prio = __GIC_PRIO_IRQOFF;				\
+									\
+		if (static_branch_unlikely(&gic_nonsecure_priorities))	\
+			__prio = __GIC_PRIO_IRQOFF_NS;			\
+									\
+		__prio;							\
+	})
+
+/* Additional SPSR bits not exposed in the UABI */
+#define PSR_MODE_THREAD_BIT	(1 << 0)
+#define PSR_IL_BIT		(1 << 20)
+
+/* AArch32-specific ptrace requests */
+#define COMPAT_PTRACE_GETREGS		12
+#define COMPAT_PTRACE_SETREGS		13
+#define COMPAT_PTRACE_GET_THREAD_AREA	22
+#define COMPAT_PTRACE_SET_SYSCALL	23
+#define COMPAT_PTRACE_GETVFPREGS	27
+#define COMPAT_PTRACE_SETVFPREGS	28
+#define COMPAT_PTRACE_GETHBPREGS	29
+#define COMPAT_PTRACE_SETHBPREGS	30
+
+/* SPSR_ELx bits for exceptions taken from AArch32 */
+#define PSR_AA32_MODE_MASK	0x0000001f
+#define PSR_AA32_MODE_USR	0x00000010
+#define PSR_AA32_MODE_FIQ	0x00000011
+#define PSR_AA32_MODE_IRQ	0x00000012
+#define PSR_AA32_MODE_SVC	0x00000013
+#define PSR_AA32_MODE_ABT	0x00000017
+#define PSR_AA32_MODE_HYP	0x0000001a
+#define PSR_AA32_MODE_UND	0x0000001b
+#define PSR_AA32_MODE_SYS	0x0000001f
+#define PSR_AA32_T_BIT		0x00000020
+#define PSR_AA32_F_BIT		0x00000040
+#define PSR_AA32_I_BIT		0x00000080
+#define PSR_AA32_A_BIT		0x00000100
+#define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_PAN_BIT	0x00400000
+#define PSR_AA32_SSBS_BIT	0x00800000
+#define PSR_AA32_DIT_BIT	0x01000000
+#define PSR_AA32_Q_BIT		0x08000000
+#define PSR_AA32_V_BIT		0x10000000
+#define PSR_AA32_C_BIT		0x20000000
+#define PSR_AA32_Z_BIT		0x40000000
+#define PSR_AA32_N_BIT		0x80000000
+#define PSR_AA32_IT_MASK	0x0600fc00	/* If-Then execution state mask */
+#define PSR_AA32_GE_MASK	0x000f0000
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define PSR_AA32_ENDSTATE	PSR_AA32_E_BIT
+#else
+#define PSR_AA32_ENDSTATE	0
+#endif
+
+/* AArch32 CPSR bits, as seen in AArch32 */
+#define COMPAT_PSR_DIT_BIT	0x00200000
+
+/*
+ * These are 'magic' values for PTRACE_PEEKUSR that return info about where a
+ * process is located in memory.
+ */
+#define COMPAT_PT_TEXT_ADDR		0x10000
+#define COMPAT_PT_DATA_ADDR		0x10004
+#define COMPAT_PT_TEXT_END_ADDR		0x10008
+
+/*
+ * If pt_regs.syscallno == NO_SYSCALL, then the thread is not executing
+ * a syscall -- i.e., its most recent entry into the kernel from
+ * userspace was not via SVC, or otherwise a tracer cancelled the syscall.
+ *
+ * This must have the value -1, for ABI compatibility with ptrace etc.
+ */
+#define NO_SYSCALL (-1)
+
+#ifndef __ASSEMBLY__
+#include <linux/bug.h>
+#include <linux/types.h>
+
+/* sizeof(struct user) for AArch32 */
+#define COMPAT_USER_SZ	296
+
+/* Architecturally defined mapping between AArch32 and AArch64 registers */
+#define compat_usr(x)	regs[(x)]
+#define compat_fp	regs[11]
+#define compat_sp	regs[13]
+#define compat_lr	regs[14]
+#define compat_sp_hyp	regs[15]
+#define compat_lr_irq	regs[16]
+#define compat_sp_irq	regs[17]
+#define compat_lr_svc	regs[18]
+#define compat_sp_svc	regs[19]
+#define compat_lr_abt	regs[20]
+#define compat_sp_abt	regs[21]
+#define compat_lr_und	regs[22]
+#define compat_sp_und	regs[23]
+#define compat_r8_fiq	regs[24]
+#define compat_r9_fiq	regs[25]
+#define compat_r10_fiq	regs[26]
+#define compat_r11_fiq	regs[27]
+#define compat_r12_fiq	regs[28]
+#define compat_sp_fiq	regs[29]
+#define compat_lr_fiq	regs[30]
+
+static inline unsigned long compat_psr_to_pstate(const unsigned long psr)
+{
+	unsigned long pstate;
+
+	pstate = psr & ~COMPAT_PSR_DIT_BIT;
+
+	if (psr & COMPAT_PSR_DIT_BIT)
+		pstate |= PSR_AA32_DIT_BIT;
+
+	return pstate;
+}
+
+static inline unsigned long pstate_to_compat_psr(const unsigned long pstate)
+{
+	unsigned long psr;
+
+	psr = pstate & ~PSR_AA32_DIT_BIT;
+
+	if (pstate & PSR_AA32_DIT_BIT)
+		psr |= COMPAT_PSR_DIT_BIT;
+
+	return psr;
+}
+
+/*
+ * This struct defines the way the registers are stored on the stack during an
+ * exception. Note that sizeof(struct pt_regs) has to be a multiple of 16 (for
+ * stack alignment). struct user_pt_regs must form a prefix of struct pt_regs.
+ */
+struct pt_regs {
+	union {
+		struct user_pt_regs user_regs;
+		struct {
+			u64 regs[31];
+			u64 sp;
+			u64 pc;
+			u64 pstate;
+		};
+	};
+	u64 orig_x0;
+#ifdef __AARCH64EB__
+	u32 unused2;
+	s32 syscallno;
+#else
+	s32 syscallno;
+	u32 unused2;
+#endif
+	u64 sdei_ttbr1;
+	/* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */
+	u64 pmr_save;
+	u64 stackframe[2];
+
+	/* Only valid for some EL1 exceptions. */
+	u64 lockdep_hardirqs;
+	u64 exit_rcu;
+};
+
+static inline bool in_syscall(struct pt_regs const *regs)
+{
+	return regs->syscallno != NO_SYSCALL;
+}
+
+static inline void forget_syscall(struct pt_regs *regs)
+{
+	regs->syscallno = NO_SYSCALL;
+}
+
+#define MAX_REG_OFFSET offsetof(struct pt_regs, pstate)
+
+#define arch_has_single_step()	(1)
+
+#ifdef CONFIG_COMPAT
+#define compat_thumb_mode(regs) \
+	(((regs)->pstate & PSR_AA32_T_BIT))
+#else
+#define compat_thumb_mode(regs) (0)
+#endif
+
+#define user_mode(regs)	\
+	(((regs)->pstate & PSR_MODE_MASK) == PSR_MODE_EL0t)
+
+#define compat_user_mode(regs)	\
+	(((regs)->pstate & (PSR_MODE32_BIT | PSR_MODE_MASK)) == \
+	 (PSR_MODE32_BIT | PSR_MODE_EL0t))
+
+#define processor_mode(regs) \
+	((regs)->pstate & PSR_MODE_MASK)
+
+#define irqs_priority_unmasked(regs)					\
+	(system_uses_irq_prio_masking() ?				\
+		(regs)->pmr_save == GIC_PRIO_IRQON :			\
+		true)
+
+#define interrupts_enabled(regs)			\
+	(!((regs)->pstate & PSR_I_BIT) && irqs_priority_unmasked(regs))
+
+#define fast_interrupts_enabled(regs) \
+	(!((regs)->pstate & PSR_F_BIT))
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	if (compat_user_mode(regs))
+		return regs->compat_sp;
+	return regs->sp;
+}
+
+extern int regs_query_register_offset(const char *name);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+					       unsigned int n);
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	pt_regs from which register value is gotten
+ * @offset:	offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+	u64 val = 0;
+
+	WARN_ON(offset & 7);
+
+	offset >>= 3;
+	switch (offset) {
+	case 0 ... 30:
+		val = regs->regs[offset];
+		break;
+	case offsetof(struct pt_regs, sp) >> 3:
+		val = regs->sp;
+		break;
+	case offsetof(struct pt_regs, pc) >> 3:
+		val = regs->pc;
+		break;
+	case offsetof(struct pt_regs, pstate) >> 3:
+		val = regs->pstate;
+		break;
+	default:
+		val = 0;
+	}
+
+	return val;
+}
+
+/*
+ * Read a register given an architectural register index r.
+ * This handles the common case where 31 means XZR, not SP.
+ */
+static inline unsigned long pt_regs_read_reg(const struct pt_regs *regs, int r)
+{
+	return (r == 31) ? 0 : regs->regs[r];
+}
+
+/*
+ * Write a register given an architectural register index r.
+ * This handles the common case where 31 means XZR, not SP.
+ */
+static inline void pt_regs_write_reg(struct pt_regs *regs, int r,
+				     unsigned long val)
+{
+	if (r != 31)
+		regs->regs[r] = val;
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	unsigned long val = regs->regs[0];
+
+	/*
+	 * Audit currently uses regs_return_value() instead of
+	 * syscall_get_return_value(). Apply the same sign-extension here until
+	 * audit is updated to use syscall_get_return_value().
+	 */
+	if (compat_user_mode(regs))
+		val = sign_extend64(val, 31);
+
+	return val;
+}
+
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->regs[0] = rc;
+}
+
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:	pt_regs of that context
+ * @n:		function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note that this chooses the most likely register mapping. In very rare
+ * cases this may not return correct data, for example, if one of the
+ * function parameters is 16 bytes or bigger. In such cases, we cannot
+ * get access the parameter correctly and the register assignment of
+ * subsequent parameters will be shifted.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						     unsigned int n)
+{
+#define NR_REG_ARGUMENTS 8
+	if (n < NR_REG_ARGUMENTS)
+		return pt_regs_read_reg(regs, n);
+	return 0;
+}
+
+/* We must avoid circular header include via sched.h */
+struct task_struct;
+int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
+
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+	return regs->pc;
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+		unsigned long val)
+{
+	regs->pc = val;
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return regs->regs[29];
+}
+
+#define procedure_link_pointer(regs)	((regs)->regs[30])
+
+static inline void procedure_link_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	procedure_link_pointer(regs) = val;
+}
+
+extern unsigned long profile_pc(struct pt_regs *regs);
+
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/arm64/include/asm/pvclock-abi.h b/arch/arm64/include/asm/pvclock-abi.h
new file mode 100644
index 000000000..c4f1c0a07
--- /dev/null
+++ b/arch/arm64/include/asm/pvclock-abi.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Arm Ltd. */
+
+#ifndef __ASM_PVCLOCK_ABI_H
+#define __ASM_PVCLOCK_ABI_H
+
+/* The below structure is defined in ARM DEN0057A */
+
+struct pvclock_vcpu_stolen_time {
+	__le32 revision;
+	__le32 attributes;
+	__le64 stolen_time;
+	/* Structure must be 64 byte aligned, pad to that size */
+	u8 padding[48];
+} __packed;
+
+#endif
diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonce.h
new file mode 100644
index 000000000..56f7b1d4d
--- /dev/null
+++ b/arch/arm64/include/asm/rwonce.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__)
+
+#include <linux/compiler_types.h>
+#include <asm/alternative-macros.h>
+
+#ifndef BUILD_VDSO
+
+#ifdef CONFIG_AS_HAS_LDAPR
+#define __LOAD_RCPC(sfx, regs...)					\
+	ALTERNATIVE(							\
+		"ldar"	#sfx "\t" #regs,				\
+		".arch_extension rcpc\n"				\
+		"ldapr"	#sfx "\t" #regs,				\
+	ARM64_HAS_LDAPR)
+#else
+#define __LOAD_RCPC(sfx, regs...)	"ldar" #sfx "\t" #regs
+#endif /* CONFIG_AS_HAS_LDAPR */
+
+/*
+ * When building with LTO, there is an increased risk of the compiler
+ * converting an address dependency headed by a READ_ONCE() invocation
+ * into a control dependency and consequently allowing for harmful
+ * reordering by the CPU.
+ *
+ * Ensure that such transformations are harmless by overriding the generic
+ * READ_ONCE() definition with one that provides RCpc acquire semantics
+ * when building with LTO.
+ */
+#define __READ_ONCE(x)							\
+({									\
+	typeof(&(x)) __x = &(x);					\
+	int atomic = 1;							\
+	union { __unqual_scalar_typeof(*__x) __val; char __c[1]; } __u;	\
+	switch (sizeof(x)) {						\
+	case 1:								\
+		asm volatile(__LOAD_RCPC(b, %w0, %1)			\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*__x) : "memory");			\
+		break;							\
+	case 2:								\
+		asm volatile(__LOAD_RCPC(h, %w0, %1)			\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*__x) : "memory");			\
+		break;							\
+	case 4:								\
+		asm volatile(__LOAD_RCPC(, %w0, %1)			\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*__x) : "memory");			\
+		break;							\
+	case 8:								\
+		asm volatile(__LOAD_RCPC(, %0, %1)			\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*__x) : "memory");			\
+		break;							\
+	default:							\
+		atomic = 0;						\
+	}								\
+	atomic ? (typeof(*__x))__u.__val : (*(volatile typeof(__x))__x);\
+})
+
+#endif	/* !BUILD_VDSO */
+#endif	/* CONFIG_LTO && !__ASSEMBLY__ */
+
+#include <asm-generic/rwonce.h>
+
+#endif	/* __ASM_RWONCE_H */
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
new file mode 100644
index 000000000..5cd4d09bc
--- /dev/null
+++ b/arch/arm64/include/asm/scs.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+	scs_sp	.req	x18
+
+	.macro scs_load_current
+	get_current_task scs_sp
+	ldr	scs_sp, [scs_sp, #TSK_TI_SCS_SP]
+	.endm
+
+	.macro scs_save tsk
+	str	scs_sp, [\tsk, #TSK_TI_SCS_SP]
+	.endm
+#else
+	.macro scs_load_current
+	.endm
+
+	.macro scs_save tsk
+	.endm
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#endif /* __ASSEMBLY __ */
+
+#endif /* _ASM_SCS_H */
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
new file mode 100644
index 000000000..484cb6972
--- /dev/null
+++ b/arch/arm64/include/asm/sdei.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2017 Arm Ltd.
+#ifndef __ASM_SDEI_H
+#define __ASM_SDEI_H
+
+/* Values for sdei_exit_mode */
+#define SDEI_EXIT_HVC  0
+#define SDEI_EXIT_SMC  1
+
+#define SDEI_STACK_SIZE		IRQ_STACK_SIZE
+
+#ifndef __ASSEMBLY__
+
+#include <linux/linkage.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/virt.h>
+
+DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event);
+DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event);
+
+extern unsigned long sdei_exit_mode;
+
+/* Software Delegated Exception entry point from firmware*/
+asmlinkage void __sdei_asm_handler(unsigned long event_num, unsigned long arg,
+				   unsigned long pc, unsigned long pstate);
+
+/* and its CONFIG_UNMAP_KERNEL_AT_EL0 trampoline */
+asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num,
+						   unsigned long arg,
+						   unsigned long pc,
+						   unsigned long pstate);
+
+/* Abort a running handler. Context is discarded. */
+void __sdei_handler_abort(void);
+
+/*
+ * The above entry point does the minimum to call C code. This function does
+ * anything else, before calling the driver.
+ */
+struct sdei_registered_event;
+asmlinkage unsigned long __sdei_handler(struct pt_regs *regs,
+					struct sdei_registered_event *arg);
+
+unsigned long do_sdei_event(struct pt_regs *regs,
+			    struct sdei_registered_event *arg);
+
+unsigned long sdei_arch_get_entry_point(int conduit);
+#define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_SDEI_H */
diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h
new file mode 100644
index 000000000..302562337
--- /dev/null
+++ b/arch/arm64/include/asm/seccomp.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/seccomp.h
+ *
+ * Copyright (C) 2014 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ */
+#ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
+
+#include <asm/unistd.h>
+
+#ifdef CONFIG_COMPAT
+#define __NR_seccomp_read_32		__NR_compat_read
+#define __NR_seccomp_write_32		__NR_compat_write
+#define __NR_seccomp_exit_32		__NR_compat_exit
+#define __NR_seccomp_sigreturn_32	__NR_compat_rt_sigreturn
+#endif /* CONFIG_COMPAT */
+
+#include <asm-generic/seccomp.h>
+
+#define SECCOMP_ARCH_NATIVE		AUDIT_ARCH_AARCH64
+#define SECCOMP_ARCH_NATIVE_NR		NR_syscalls
+#define SECCOMP_ARCH_NATIVE_NAME	"aarch64"
+#ifdef CONFIG_COMPAT
+# define SECCOMP_ARCH_COMPAT		AUDIT_ARCH_ARM
+# define SECCOMP_ARCH_COMPAT_NR	__NR_compat_syscalls
+# define SECCOMP_ARCH_COMPAT_NAME	"arm"
+#endif
+
+#endif /* _ASM_SECCOMP_H */
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
new file mode 100644
index 000000000..40971ac13
--- /dev/null
+++ b/arch/arm64/include/asm/sections.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 ARM Limited
+ */
+#ifndef __ASM_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char __alt_instructions[], __alt_instructions_end[];
+extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
+extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+extern char __hyp_text_start[], __hyp_text_end[];
+extern char __hyp_rodata_start[], __hyp_rodata_end[];
+extern char __hyp_reloc_begin[], __hyp_reloc_end[];
+extern char __hyp_bss_start[], __hyp_bss_end[];
+extern char __idmap_text_start[], __idmap_text_end[];
+extern char __initdata_begin[], __initdata_end[];
+extern char __inittext_begin[], __inittext_end[];
+extern char __exittext_begin[], __exittext_end[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __mmuoff_data_start[], __mmuoff_data_end[];
+extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
+extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[];
+
+static inline size_t entry_tramp_text_size(void)
+{
+	return __entry_tramp_text_end - __entry_tramp_text_start;
+}
+
+#endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/set_memory.h b/arch/arm64/include/asm/set_memory.h
new file mode 100644
index 000000000..0f740b781
--- /dev/null
+++ b/arch/arm64/include/asm/set_memory.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_ARM64_SET_MEMORY_H
+#define _ASM_ARM64_SET_MEMORY_H
+
+#include <asm-generic/set_memory.h>
+
+bool can_set_direct_map(void);
+#define can_set_direct_map can_set_direct_map
+
+int set_memory_valid(unsigned long addr, int numpages, int enable);
+
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+bool kernel_page_present(struct page *page);
+
+#endif /* _ASM_ARM64_SET_MEMORY_H */
diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h
new file mode 100644
index 000000000..2e4d7da74
--- /dev/null
+++ b/arch/arm64/include/asm/setup.h
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __ARM64_ASM_SETUP_H
+#define __ARM64_ASM_SETUP_H
+
+#include <linux/string.h>
+
+#include <uapi/asm/setup.h>
+
+void *get_early_fdt_ptr(void);
+void early_fdt_map(u64 dt_phys);
+
+/*
+ * These two variables are used in the head.S file.
+ */
+extern phys_addr_t __fdt_pointer __initdata;
+extern u64 __cacheline_aligned boot_args[4];
+
+static inline bool arch_parse_debug_rodata(char *arg)
+{
+	extern bool rodata_enabled;
+	extern bool rodata_full;
+
+	if (!arg)
+		return false;
+
+	if (!strcmp(arg, "full")) {
+		rodata_enabled = rodata_full = true;
+		return true;
+	}
+
+	if (!strcmp(arg, "off")) {
+		rodata_enabled = rodata_full = false;
+		return true;
+	}
+
+	if (!strcmp(arg, "on")) {
+		rodata_enabled = true;
+		rodata_full = false;
+		return true;
+	}
+
+	return false;
+}
+#define arch_parse_debug_rodata arch_parse_debug_rodata
+
+#endif
diff --git a/arch/arm64/include/asm/shmparam.h b/arch/arm64/include/asm/shmparam.h
new file mode 100644
index 000000000..f920e22ec
--- /dev/null
+++ b/arch/arm64/include/asm/shmparam.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SHMPARAM_H
+#define __ASM_SHMPARAM_H
+
+/*
+ * For IPC syscalls from compat tasks, we need to use the legacy 16k
+ * alignment value. Since we don't have aliasing D-caches, the rest of
+ * the time we can safely use PAGE_SIZE.
+ */
+#define COMPAT_SHMLBA	(4 * PAGE_SIZE)
+
+#include <asm-generic/shmparam.h>
+
+#endif /* __ASM_SHMPARAM_H */
diff --git a/arch/arm64/include/asm/signal.h b/arch/arm64/include/asm/signal.h
new file mode 100644
index 000000000..ef449f5f4
--- /dev/null
+++ b/arch/arm64/include/asm/signal.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARM64_ASM_SIGNAL_H
+#define __ARM64_ASM_SIGNAL_H
+
+#include <asm/memory.h>
+#include <uapi/asm/signal.h>
+#include <uapi/asm/siginfo.h>
+
+static inline void __user *arch_untagged_si_addr(void __user *addr,
+						 unsigned long sig,
+						 unsigned long si_code)
+{
+	/*
+	 * For historical reasons, all bits of the fault address are exposed as
+	 * address bits for watchpoint exceptions. New architectures should
+	 * handle the tag bits consistently.
+	 */
+	if (sig == SIGTRAP && si_code == TRAP_BRKPT)
+		return addr;
+
+	return untagged_addr(addr);
+}
+#define arch_untagged_si_addr arch_untagged_si_addr
+
+#endif
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
new file mode 100644
index 000000000..7e9f163d0
--- /dev/null
+++ b/arch/arm64/include/asm/signal32.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SIGNAL32_H
+#define __ASM_SIGNAL32_H
+
+#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
+
+struct compat_sigcontext {
+	/* We always set these two fields to 0 */
+	compat_ulong_t			trap_no;
+	compat_ulong_t			error_code;
+
+	compat_ulong_t			oldmask;
+	compat_ulong_t			arm_r0;
+	compat_ulong_t			arm_r1;
+	compat_ulong_t			arm_r2;
+	compat_ulong_t			arm_r3;
+	compat_ulong_t			arm_r4;
+	compat_ulong_t			arm_r5;
+	compat_ulong_t			arm_r6;
+	compat_ulong_t			arm_r7;
+	compat_ulong_t			arm_r8;
+	compat_ulong_t			arm_r9;
+	compat_ulong_t			arm_r10;
+	compat_ulong_t			arm_fp;
+	compat_ulong_t			arm_ip;
+	compat_ulong_t			arm_sp;
+	compat_ulong_t			arm_lr;
+	compat_ulong_t			arm_pc;
+	compat_ulong_t			arm_cpsr;
+	compat_ulong_t			fault_address;
+};
+
+struct compat_ucontext {
+	compat_ulong_t			uc_flags;
+	compat_uptr_t			uc_link;
+	compat_stack_t			uc_stack;
+	struct compat_sigcontext	uc_mcontext;
+	compat_sigset_t			uc_sigmask;
+	int 				__unused[32 - (sizeof(compat_sigset_t) / sizeof(int))];
+	compat_ulong_t			uc_regspace[128] __attribute__((__aligned__(8)));
+};
+
+struct compat_sigframe {
+	struct compat_ucontext	uc;
+	compat_ulong_t		retcode[2];
+};
+
+struct compat_rt_sigframe {
+	struct compat_siginfo info;
+	struct compat_sigframe sig;
+};
+
+int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
+		       struct pt_regs *regs);
+int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
+			  struct pt_regs *regs);
+
+void compat_setup_restart_syscall(struct pt_regs *regs);
+#else
+
+static inline int compat_setup_frame(int usid, struct ksignal *ksig,
+				     sigset_t *set, struct pt_regs *regs)
+{
+	return -ENOSYS;
+}
+
+static inline int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
+					struct pt_regs *regs)
+{
+	return -ENOSYS;
+}
+
+static inline void compat_setup_restart_syscall(struct pt_regs *regs)
+{
+}
+#endif /* CONFIG_COMPAT */
+#endif /* __ASM_SIGNAL32_H */
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
new file mode 100644
index 000000000..6a75d7ecd
--- /dev/null
+++ b/arch/arm64/include/asm/simd.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+DECLARE_PER_CPU(bool, fpsimd_context_busy);
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ *                instructions or access the SIMD register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+	/*
+	 * We must make sure that the SVE has been initialized properly
+	 * before using the SIMD in kernel.
+	 * fpsimd_context_busy is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled. Since
+	 * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy
+	 * cannot change under our feet -- if it's set we cannot be
+	 * migrated, and if it's clear we cannot be migrated to a CPU
+	 * where it is set.
+	 */
+	return !WARN_ON(!system_capabilities_finalized()) &&
+	       system_supports_fpsimd() &&
+	       !in_hardirq() && !irqs_disabled() && !in_nmi() &&
+	       !this_cpu_read(fpsimd_context_busy);
+}
+
+#else /* ! CONFIG_KERNEL_MODE_NEON */
+
+static __must_check inline bool may_use_simd(void) {
+	return false;
+}
+
+#endif /* ! CONFIG_KERNEL_MODE_NEON */
+
+#endif
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
new file mode 100644
index 000000000..fc55f5a57
--- /dev/null
+++ b/arch/arm64/include/asm/smp.h
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+#include <linux/const.h>
+
+/* Values for secondary_data.status */
+#define CPU_STUCK_REASON_SHIFT		(8)
+#define CPU_BOOT_STATUS_MASK		((UL(1) << CPU_STUCK_REASON_SHIFT) - 1)
+
+#define CPU_MMU_OFF			(-1)
+#define CPU_BOOT_SUCCESS		(0)
+/* The cpu invoked ops->cpu_die, synchronise it with cpu_kill */
+#define CPU_KILL_ME			(1)
+/* The cpu couldn't die gracefully and is looping in the kernel */
+#define CPU_STUCK_IN_KERNEL		(2)
+/* Fatal system error detected by secondary CPU, crash the system */
+#define CPU_PANIC_KERNEL		(3)
+
+#define CPU_STUCK_REASON_52_BIT_VA	(UL(1) << CPU_STUCK_REASON_SHIFT)
+#define CPU_STUCK_REASON_NO_GRAN	(UL(2) << CPU_STUCK_REASON_SHIFT)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/percpu.h>
+
+#include <linux/threads.h>
+#include <linux/cpumask.h>
+#include <linux/thread_info.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
+
+/*
+ * We don't use this_cpu_read(cpu_number) as that has implicit writes to
+ * preempt_count, and associated (compiler) barriers, that we'd like to avoid
+ * the expense of. If we're preemptible, the value can be stale at use anyway.
+ * And we can't use this_cpu_ptr() either, as that winds up recursing back
+ * here under CONFIG_DEBUG_PREEMPT=y.
+ */
+#define raw_smp_processor_id() (*raw_cpu_ptr(&cpu_number))
+
+/*
+ * Logical CPU mapping.
+ */
+extern u64 __cpu_logical_map[NR_CPUS];
+extern u64 cpu_logical_map(unsigned int cpu);
+
+static inline void set_cpu_logical_map(unsigned int cpu, u64 hwid)
+{
+	__cpu_logical_map[cpu] = hwid;
+}
+
+struct seq_file;
+
+/*
+ * Discover the set of possible CPUs and determine their
+ * SMP operations.
+ */
+extern void smp_init_cpus(void);
+
+/*
+ * Register IPI interrupts with the arch SMP code
+ */
+extern void set_smp_ipi_range(int ipi_base, int nr_ipi);
+
+/*
+ * Called from the secondary holding pen, this is the secondary CPU entry point.
+ */
+asmlinkage void secondary_start_kernel(void);
+
+/*
+ * Initial data for bringing up a secondary CPU.
+ * @status - Result passed back from the secondary CPU to
+ *           indicate failure.
+ */
+struct secondary_data {
+	struct task_struct *task;
+	long status;
+};
+
+extern struct secondary_data secondary_data;
+extern long __early_cpu_boot_status;
+extern void secondary_entry(void);
+
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
+extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+#else
+static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
+{
+	BUILD_BUG();
+}
+#endif
+
+extern int __cpu_disable(void);
+
+extern void __cpu_die(unsigned int cpu);
+extern void cpu_die(void);
+extern void cpu_die_early(void);
+
+static inline void cpu_park_loop(void)
+{
+	for (;;) {
+		wfe();
+		wfi();
+	}
+}
+
+static inline void update_cpu_boot_status(int val)
+{
+	WRITE_ONCE(secondary_data.status, val);
+	/* Ensure the visibility of the status update */
+	dsb(ishst);
+}
+
+/*
+ * The calling secondary CPU has detected serious configuration mismatch,
+ * which calls for a kernel panic. Update the boot status and park the calling
+ * CPU.
+ */
+static inline void cpu_panic_kernel(void)
+{
+	update_cpu_boot_status(CPU_PANIC_KERNEL);
+	cpu_park_loop();
+}
+
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
+extern void crash_smp_send_stop(void);
+extern bool smp_crash_stop_failed(void);
+extern void panic_smp_self_stop(void);
+
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
new file mode 100644
index 000000000..97ddc6c20
--- /dev/null
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Definitions specific to SMP platforms.
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ */
+
+#ifndef __ASM_SMP_PLAT_H
+#define __ASM_SMP_PLAT_H
+
+#include <linux/cpumask.h>
+
+#include <asm/smp.h>
+#include <asm/types.h>
+
+struct mpidr_hash {
+	u64	mask;
+	u32	shift_aff[4];
+	u32	bits;
+};
+
+extern struct mpidr_hash mpidr_hash;
+
+static inline u32 mpidr_hash_size(void)
+{
+	return 1 << mpidr_hash.bits;
+}
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR.Aff*
+ *  - mpidr: MPIDR.Aff* bits to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u64 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+#endif /* __ASM_SMP_PLAT_H */
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
new file mode 100644
index 000000000..4b7346342
--- /dev/null
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SPARSEMEM_H
+#define __ASM_SPARSEMEM_H
+
+#define MAX_PHYSMEM_BITS	CONFIG_ARM64_PA_BITS
+
+/*
+ * Section size must be at least 512MB for 64K base
+ * page size config. Otherwise it will be less than
+ * (MAX_ORDER - 1) and the build process will fail.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define SECTION_SIZE_BITS 29
+
+#else
+
+/*
+ * Section size must be at least 128MB for 4K base
+ * page size config. Otherwise PMD based huge page
+ * entries could not be created for vmemmap mappings.
+ * 16K follows 4K for simplicity.
+ */
+#define SECTION_SIZE_BITS 27
+#endif /* CONFIG_ARM64_64K_PAGES */
+
+#endif
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
new file mode 100644
index 000000000..aa3d3607d
--- /dev/null
+++ b/arch/arm64/include/asm/spectre.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Interface for managing mitigations for Spectre vulnerabilities.
+ *
+ * Copyright (C) 2020 Google LLC
+ * Author: Will Deacon <will@kernel.org>
+ */
+
+#ifndef __ASM_SPECTRE_H
+#define __ASM_SPECTRE_H
+
+#define BP_HARDEN_EL2_SLOTS 4
+#define __BP_HARDEN_HYP_VECS_SZ	((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+
+#include <asm/cpufeature.h>
+#include <asm/virt.h>
+
+/* Watch out, ordering is important here. */
+enum mitigation_state {
+	SPECTRE_UNAFFECTED,
+	SPECTRE_MITIGATED,
+	SPECTRE_VULNERABLE,
+};
+
+struct task_struct;
+
+/*
+ * Note: the order of this enum corresponds to __bp_harden_hyp_vecs and
+ * we rely on having the direct vectors first.
+ */
+enum arm64_hyp_spectre_vector {
+	/*
+	 * Take exceptions directly to __kvm_hyp_vector. This must be
+	 * 0 so that it used by default when mitigations are not needed.
+	 */
+	HYP_VECTOR_DIRECT,
+
+	/*
+	 * Bounce via a slot in the hypervisor text mapping of
+	 * __bp_harden_hyp_vecs, which contains an SMC call.
+	 */
+	HYP_VECTOR_SPECTRE_DIRECT,
+
+	/*
+	 * Bounce via a slot in a special mapping of __bp_harden_hyp_vecs
+	 * next to the idmap page.
+	 */
+	HYP_VECTOR_INDIRECT,
+
+	/*
+	 * Bounce via a slot in a special mapping of __bp_harden_hyp_vecs
+	 * next to the idmap page, which contains an SMC call.
+	 */
+	HYP_VECTOR_SPECTRE_INDIRECT,
+};
+
+typedef void (*bp_hardening_cb_t)(void);
+
+struct bp_hardening_data {
+	enum arm64_hyp_spectre_vector	slot;
+	bp_hardening_cb_t		fn;
+};
+
+DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+/* Called during entry so must be __always_inline */
+static __always_inline void arm64_apply_bp_hardening(void)
+{
+	struct bp_hardening_data *d;
+
+	if (!cpus_have_const_cap(ARM64_SPECTRE_V2))
+		return;
+
+	d = this_cpu_ptr(&bp_hardening_data);
+	if (d->fn)
+		d->fn();
+}
+
+enum mitigation_state arm64_get_spectre_v2_state(void);
+bool has_spectre_v2(const struct arm64_cpu_capabilities *cap, int scope);
+void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+
+bool has_spectre_v3a(const struct arm64_cpu_capabilities *cap, int scope);
+void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+
+enum mitigation_state arm64_get_spectre_v4_state(void);
+bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope);
+void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+void spectre_v4_enable_task_mitigation(struct task_struct *tsk);
+
+enum mitigation_state arm64_get_meltdown_state(void);
+
+enum mitigation_state arm64_get_spectre_bhb_state(void);
+bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
+u8 spectre_bhb_loop_affected(int scope);
+void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+#endif	/* __ASSEMBLY__ */
+#endif	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
new file mode 100644
index 000000000..0525c0b08
--- /dev/null
+++ b/arch/arm64/include/asm/spinlock.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
+
+/* See include/linux/spinlock.h */
+#define smp_mb__after_spinlock()	smp_mb()
+
+/*
+ * Changing this will break osq_lock() thanks to the call inside
+ * smp_cond_load_relaxed().
+ *
+ * See:
+ * https://lore.kernel.org/lkml/20200110100612.GC2827@hirez.programming.kicks-ass.net
+ */
+#define vcpu_is_preempted vcpu_is_preempted
+static inline bool vcpu_is_preempted(int cpu)
+{
+	return false;
+}
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
new file mode 100644
index 000000000..11ab1c077
--- /dev/null
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+#if !defined(__LINUX_SPINLOCK_TYPES_RAW_H) && !defined(__ASM_SPINLOCK_H)
+# error "please don't include this file directly"
+#endif
+
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
+
+#endif
diff --git a/arch/arm64/include/asm/stack_pointer.h b/arch/arm64/include/asm/stack_pointer.h
new file mode 100644
index 000000000..8e57c96ad
--- /dev/null
+++ b/arch/arm64/include/asm/stack_pointer.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_STACK_POINTER_H
+#define __ASM_STACK_POINTER_H
+
+/*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+#endif /* __ASM_STACK_POINTER_H */
diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h
new file mode 100644
index 000000000..33f1bb453
--- /dev/null
+++ b/arch/arm64/include/asm/stackprotector.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on ARM.  This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef __ASM_STACKPROTECTOR_H
+#define __ASM_STACKPROTECTOR_H
+
+#include <linux/random.h>
+#include <linux/version.h>
+#include <asm/pointer_auth.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+#if defined(CONFIG_STACKPROTECTOR)
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+	canary &= CANARY_MASK;
+
+	current->stack_canary = canary;
+	if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK))
+		__stack_chk_guard = current->stack_canary;
+#endif
+	ptrauth_thread_init_kernel(current);
+	ptrauth_thread_switch_kernel(current);
+	ptrauth_enable();
+}
+
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
new file mode 100644
index 000000000..327cdcfcb
--- /dev/null
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_STACKTRACE_H
+#define __ASM_STACKTRACE_H
+
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/llist.h>
+
+#include <asm/memory.h>
+#include <asm/pointer_auth.h>
+#include <asm/ptrace.h>
+#include <asm/sdei.h>
+
+#include <asm/stacktrace/common.h>
+
+extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+			   const char *loglvl);
+
+DECLARE_PER_CPU(unsigned long *, irq_stack_ptr);
+
+static inline struct stack_info stackinfo_get_irq(void)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
+	unsigned long high = low + IRQ_STACK_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+
+static inline bool on_irq_stack(unsigned long sp, unsigned long size)
+{
+	struct stack_info info = stackinfo_get_irq();
+	return stackinfo_on_stack(&info, sp, size);
+}
+
+static inline struct stack_info stackinfo_get_task(const struct task_struct *tsk)
+{
+	unsigned long low = (unsigned long)task_stack_page(tsk);
+	unsigned long high = low + THREAD_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+
+static inline bool on_task_stack(const struct task_struct *tsk,
+				 unsigned long sp, unsigned long size)
+{
+	struct stack_info info = stackinfo_get_task(tsk);
+	return stackinfo_on_stack(&info, sp, size);
+}
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+
+static inline struct stack_info stackinfo_get_overflow(void)
+{
+	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
+	unsigned long high = low + OVERFLOW_STACK_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+#else
+#define stackinfo_get_overflow()	stackinfo_get_unknown()
+#endif
+
+#if defined(CONFIG_ARM_SDE_INTERFACE) && defined(CONFIG_VMAP_STACK)
+DECLARE_PER_CPU(unsigned long *, sdei_stack_normal_ptr);
+DECLARE_PER_CPU(unsigned long *, sdei_stack_critical_ptr);
+
+static inline struct stack_info stackinfo_get_sdei_normal(void)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
+	unsigned long high = low + SDEI_STACK_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+
+static inline struct stack_info stackinfo_get_sdei_critical(void)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
+	unsigned long high = low + SDEI_STACK_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+#else
+#define stackinfo_get_sdei_normal()	stackinfo_get_unknown()
+#define stackinfo_get_sdei_critical()	stackinfo_get_unknown()
+#endif
+
+#ifdef CONFIG_EFI
+extern u64 *efi_rt_stack_top;
+
+static inline struct stack_info stackinfo_get_efi(void)
+{
+	unsigned long high = (u64)efi_rt_stack_top;
+	unsigned long low = high - THREAD_SIZE;
+
+	return (struct stack_info) {
+		.low = low,
+		.high = high,
+	};
+}
+#endif
+
+#endif	/* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h
new file mode 100644
index 000000000..508f734de
--- /dev/null
+++ b/arch/arm64/include/asm/stacktrace/common.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common arm64 stack unwinder code.
+ *
+ * See: arch/arm64/kernel/stacktrace.c for the reference implementation.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_STACKTRACE_COMMON_H
+#define __ASM_STACKTRACE_COMMON_H
+
+#include <linux/kprobes.h>
+#include <linux/types.h>
+
+struct stack_info {
+	unsigned long low;
+	unsigned long high;
+};
+
+/**
+ * struct unwind_state - state used for robust unwinding.
+ *
+ * @fp:          The fp value in the frame record (or the real fp)
+ * @pc:          The lr value in the frame record (or the real lr)
+ *
+ * @kr_cur:      When KRETPROBES is selected, holds the kretprobe instance
+ *               associated with the most recently encountered replacement lr
+ *               value.
+ *
+ * @task:        The task being unwound.
+ *
+ * @stack:       The stack currently being unwound.
+ * @stacks:      An array of stacks which can be unwound.
+ * @nr_stacks:   The number of stacks in @stacks.
+ */
+struct unwind_state {
+	unsigned long fp;
+	unsigned long pc;
+#ifdef CONFIG_KRETPROBES
+	struct llist_node *kr_cur;
+#endif
+	struct task_struct *task;
+
+	struct stack_info stack;
+	struct stack_info *stacks;
+	int nr_stacks;
+};
+
+static inline struct stack_info stackinfo_get_unknown(void)
+{
+	return (struct stack_info) {
+		.low = 0,
+		.high = 0,
+	};
+}
+
+static inline bool stackinfo_on_stack(const struct stack_info *info,
+				      unsigned long sp, unsigned long size)
+{
+	if (!info->low)
+		return false;
+
+	if (sp < info->low || sp + size < sp || sp + size > info->high)
+		return false;
+
+	return true;
+}
+
+static inline void unwind_init_common(struct unwind_state *state,
+				      struct task_struct *task)
+{
+	state->task = task;
+#ifdef CONFIG_KRETPROBES
+	state->kr_cur = NULL;
+#endif
+
+	state->stack = stackinfo_get_unknown();
+}
+
+static struct stack_info *unwind_find_next_stack(const struct unwind_state *state,
+						 unsigned long sp,
+						 unsigned long size)
+{
+	for (int i = 0; i < state->nr_stacks; i++) {
+		struct stack_info *info = &state->stacks[i];
+
+		if (stackinfo_on_stack(info, sp, size))
+			return info;
+	}
+
+	return NULL;
+}
+
+/**
+ * unwind_consume_stack() - Check if an object is on an accessible stack,
+ * updating stack boundaries so that future unwind steps cannot consume this
+ * object again.
+ *
+ * @state: the current unwind state.
+ * @sp:    the base address of the object.
+ * @size:  the size of the object.
+ *
+ * Return: 0 upon success, an error code otherwise.
+ */
+static inline int unwind_consume_stack(struct unwind_state *state,
+				       unsigned long sp,
+				       unsigned long size)
+{
+	struct stack_info *next;
+
+	if (stackinfo_on_stack(&state->stack, sp, size))
+		goto found;
+
+	next = unwind_find_next_stack(state, sp, size);
+	if (!next)
+		return -EINVAL;
+
+	/*
+	 * Stack transitions are strictly one-way, and once we've
+	 * transitioned from one stack to another, it's never valid to
+	 * unwind back to the old stack.
+	 *
+	 * Remove the current stack from the list of stacks so that it cannot
+	 * be found on a subsequent transition.
+	 *
+	 * Note that stacks can nest in several valid orders, e.g.
+	 *
+	 *   TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
+	 *   TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
+	 *   HYP -> OVERFLOW
+	 *
+	 * ... so we do not check the specific order of stack
+	 * transitions.
+	 */
+	state->stack = *next;
+	*next = stackinfo_get_unknown();
+
+found:
+	/*
+	 * Future unwind steps can only consume stack above this frame record.
+	 * Update the current stack to start immediately above it.
+	 */
+	state->stack.low = sp + size;
+	return 0;
+}
+
+/**
+ * unwind_next_frame_record() - Unwind to the next frame record.
+ *
+ * @state:        the current unwind state.
+ *
+ * Return: 0 upon success, an error code otherwise.
+ */
+static inline int
+unwind_next_frame_record(struct unwind_state *state)
+{
+	unsigned long fp = state->fp;
+	int err;
+
+	if (fp & 0x7)
+		return -EINVAL;
+
+	err = unwind_consume_stack(state, fp, 16);
+	if (err)
+		return err;
+
+	/*
+	 * Record this frame record's values.
+	 */
+	state->fp = READ_ONCE(*(unsigned long *)(fp));
+	state->pc = READ_ONCE(*(unsigned long *)(fp + 8));
+
+	return 0;
+}
+
+#endif	/* __ASM_STACKTRACE_COMMON_H */
diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h
new file mode 100644
index 000000000..25ab83a31
--- /dev/null
+++ b/arch/arm64/include/asm/stacktrace/nvhe.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * KVM nVHE hypervisor stack tracing support.
+ *
+ * The unwinder implementation depends on the nVHE mode:
+ *
+ *   1) Non-protected nVHE mode - the host can directly access the
+ *      HYP stack pages and unwind the HYP stack in EL1. This saves having
+ *      to allocate shared buffers for the host to read the unwinded
+ *      stacktrace.
+ *
+ *   2) pKVM (protected nVHE) mode - the host cannot directly access
+ *      the HYP memory. The stack is unwinded in EL2 and dumped to a shared
+ *      buffer where the host can read and print the stacktrace.
+ *
+ * Copyright (C) 2022 Google LLC
+ */
+#ifndef __ASM_STACKTRACE_NVHE_H
+#define __ASM_STACKTRACE_NVHE_H
+
+#include <asm/stacktrace/common.h>
+
+/**
+ * kvm_nvhe_unwind_init() - Start an unwind from the given nVHE HYP fp and pc
+ *
+ * @state : unwind_state to initialize
+ * @fp    : frame pointer at which to start the unwinding.
+ * @pc    : program counter at which to start the unwinding.
+ */
+static inline void kvm_nvhe_unwind_init(struct unwind_state *state,
+					unsigned long fp,
+					unsigned long pc)
+{
+	unwind_init_common(state, NULL);
+
+	state->fp = fp;
+	state->pc = pc;
+}
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+/*
+ * Conventional (non-protected) nVHE HYP stack unwinder
+ *
+ * In non-protected mode, the unwinding is done from kernel proper context
+ * (by the host in EL1).
+ */
+
+DECLARE_KVM_NVHE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_stacktrace_info, kvm_stacktrace_info);
+DECLARE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
+
+void kvm_nvhe_dump_backtrace(unsigned long hyp_offset);
+
+#endif	/* __KVM_NVHE_HYPERVISOR__ */
+#endif	/* __ASM_STACKTRACE_NVHE_H */
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
new file mode 100644
index 000000000..c8dca8ae3
--- /dev/null
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ *
+ * stage2 page table helpers
+ */
+
+#ifndef __ARM64_S2_PGTABLE_H_
+#define __ARM64_S2_PGTABLE_H_
+
+#include <linux/pgtable.h>
+
+/*
+ * The hardware supports concatenation of up to 16 tables at stage2 entry
+ * level and we use the feature whenever possible, which means we resolve 4
+ * additional bits of address at the entry level.
+ *
+ * This implies, the total number of page table levels required for
+ * IPA_SHIFT at stage2 expected by the hardware can be calculated using
+ * the same logic used for the (non-collapsable) stage1 page tables but for
+ * (IPA_SHIFT - 4).
+ */
+#define stage2_pgtable_levels(ipa)	ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
+#define kvm_stage2_levels(kvm)		VTCR_EL2_LVLS(kvm->arch.vtcr)
+
+/*
+ * kvm_mmmu_cache_min_pages() is the number of pages required to install
+ * a stage-2 translation. We pre-allocate the entry level page table at
+ * the VM creation.
+ */
+#define kvm_mmu_cache_min_pages(kvm)	(kvm_stage2_levels(kvm) - 1)
+
+#endif	/* __ARM64_S2_PGTABLE_H_ */
diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h
new file mode 100644
index 000000000..3b4a62f5a
--- /dev/null
+++ b/arch/arm64/include/asm/stat.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_STAT_H
+#define __ASM_STAT_H
+
+#include <uapi/asm/stat.h>
+
+#ifdef CONFIG_COMPAT
+
+#include <linux/time.h>
+#include <asm/compat.h>
+
+/*
+ * struct stat64 is needed for compat tasks only. Its definition is different
+ * from the generic struct stat64.
+ */
+struct stat64 {
+	compat_u64	st_dev;
+	unsigned char   __pad0[4];
+
+#define STAT64_HAS_BROKEN_ST_INO	1
+	compat_ulong_t	__st_ino;
+	compat_uint_t	st_mode;
+	compat_uint_t	st_nlink;
+
+	compat_ulong_t	st_uid;
+	compat_ulong_t	st_gid;
+
+	compat_u64	st_rdev;
+	unsigned char   __pad3[4];
+
+	compat_s64	st_size;
+	compat_ulong_t	st_blksize;
+	compat_u64	st_blocks;	/* Number of 512-byte blocks allocated. */
+
+	compat_ulong_t	st_atime;
+	compat_ulong_t	st_atime_nsec;
+
+	compat_ulong_t	st_mtime;
+	compat_ulong_t	st_mtime_nsec;
+
+	compat_ulong_t	st_ctime;
+	compat_ulong_t	st_ctime_nsec;
+
+	compat_u64	st_ino;
+};
+
+#endif
+#endif
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
new file mode 100644
index 000000000..3a3264ff4
--- /dev/null
+++ b/arch/arm64/include/asm/string.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ */
+#ifndef __ASM_STRING_H
+#define __ASM_STRING_H
+
+#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
+#define __HAVE_ARCH_STRRCHR
+extern char *strrchr(const char *, int c);
+
+#define __HAVE_ARCH_STRCHR
+extern char *strchr(const char *, int c);
+
+#define __HAVE_ARCH_STRCMP
+extern int strcmp(const char *, const char *);
+
+#define __HAVE_ARCH_STRNCMP
+extern int strncmp(const char *, const char *, __kernel_size_t);
+
+#define __HAVE_ARCH_STRLEN
+extern __kernel_size_t strlen(const char *);
+
+#define __HAVE_ARCH_STRNLEN
+extern __kernel_size_t strnlen(const char *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMCMP
+extern int memcmp(const void *, const void *, size_t);
+
+#define __HAVE_ARCH_MEMCHR
+extern void *memchr(const void *, int, __kernel_size_t);
+#endif
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *, const void *, __kernel_size_t);
+extern void *__memcpy(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *, int, __kernel_size_t);
+extern void *__memset(void *, int, __kernel_size_t);
+
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+#define __HAVE_ARCH_MEMCPY_FLUSHCACHE
+void memcpy_flushcache(void *dst, const void *src, size_t cnt);
+#endif
+
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+	!defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
new file mode 100644
index 000000000..0cde2f473
--- /dev/null
+++ b/arch/arm64/include/asm/suspend.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_SUSPEND_H
+#define __ASM_SUSPEND_H
+
+#define NR_CTX_REGS 13
+#define NR_CALLEE_SAVED_REGS 12
+
+/*
+ * struct cpu_suspend_ctx must be 16-byte aligned since it is allocated on
+ * the stack, which must be 16-byte aligned on v8
+ */
+struct cpu_suspend_ctx {
+	/*
+	 * This struct must be kept in sync with
+	 * cpu_do_{suspend/resume} in mm/proc.S
+	 */
+	u64 ctx_regs[NR_CTX_REGS];
+	u64 sp;
+} __aligned(16);
+
+/*
+ * Memory to save the cpu state is allocated on the stack by
+ * __cpu_suspend_enter()'s caller, and populated by __cpu_suspend_enter().
+ * This data must survive until cpu_resume() is called.
+ *
+ * This struct desribes the size and the layout of the saved cpu state.
+ * The layout of the callee_saved_regs is defined by the implementation
+ * of __cpu_suspend_enter(), and cpu_resume(). This struct must be passed
+ * in by the caller as __cpu_suspend_enter()'s stack-frame is gone once it
+ * returns, and the data would be subsequently corrupted by the call to the
+ * finisher.
+ */
+struct sleep_stack_data {
+	struct cpu_suspend_ctx	system_regs;
+	unsigned long		callee_saved_regs[NR_CALLEE_SAVED_REGS];
+};
+
+extern unsigned long *sleep_save_stash;
+
+extern int cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
+extern void cpu_resume(void);
+int __cpu_suspend_enter(struct sleep_stack_data *state);
+void __cpu_suspend_exit(void);
+void _cpu_resume(void);
+
+int swsusp_arch_suspend(void);
+int swsusp_arch_resume(void);
+int arch_hibernation_header_save(void *addr, unsigned int max_size);
+int arch_hibernation_header_restore(void *addr);
+
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
+#endif
diff --git a/arch/arm64/include/asm/sync_bitops.h b/arch/arm64/include/asm/sync_bitops.h
new file mode 100644
index 000000000..e9c1a02c2
--- /dev/null
+++ b/arch/arm64/include/asm/sync_bitops.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_SYNC_BITOPS_H__
+#define __ASM_SYNC_BITOPS_H__
+
+#include <asm/bitops.h>
+#include <asm/cmpxchg.h>
+
+/* sync_bitops functions are equivalent to the SMP implementation of the
+ * original functions, independently from CONFIG_SMP being defined.
+ *
+ * We need them because _set_bit etc are not SMP safe if !CONFIG_SMP. But
+ * under Xen you might be communicating with a completely external entity
+ * who might be on another CPU (e.g. two uniprocessor guests communicating
+ * via event channels and grant tables). So we need a variant of the bit
+ * ops which are SMP safe even on a UP kernel.
+ */
+
+#define sync_set_bit(nr, p)			set_bit(nr, p)
+#define sync_clear_bit(nr, p)			clear_bit(nr, p)
+#define sync_change_bit(nr, p)			change_bit(nr, p)
+#define sync_test_and_set_bit(nr, p)		test_and_set_bit(nr, p)
+#define sync_test_and_clear_bit(nr, p)		test_and_clear_bit(nr, p)
+#define sync_test_and_change_bit(nr, p)		test_and_change_bit(nr, p)
+#define sync_test_bit(nr, addr)			test_bit(nr, addr)
+#define arch_sync_cmpxchg			arch_cmpxchg
+
+#endif
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
new file mode 100644
index 000000000..4cfe9b497
--- /dev/null
+++ b/arch/arm64/include/asm/syscall.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SYSCALL_H
+#define __ASM_SYSCALL_H
+
+#include <uapi/linux/audit.h>
+#include <linux/compat.h>
+#include <linux/err.h>
+
+typedef long (*syscall_fn_t)(const struct pt_regs *regs);
+
+extern const syscall_fn_t sys_call_table[];
+
+#ifdef CONFIG_COMPAT
+extern const syscall_fn_t compat_sys_call_table[];
+#endif
+
+static inline int syscall_get_nr(struct task_struct *task,
+				 struct pt_regs *regs)
+{
+	return regs->syscallno;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->regs[0] = regs->orig_x0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	unsigned long val = regs->regs[0];
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = sign_extend64(val, 31);
+
+	return val;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = syscall_get_return_value(task, regs);
+
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	if (error)
+		val = error;
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = lower_32_bits(val);
+
+	regs->regs[0] = val;
+}
+
+#define SYSCALL_MAX_ARGS 6
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned long *args)
+{
+	args[0] = regs->orig_x0;
+	args++;
+
+	memcpy(args, &regs->regs[1], 5 * sizeof(args[0]));
+}
+
+/*
+ * We don't care about endianness (__AUDIT_ARCH_LE bit) here because
+ * AArch64 has the same system calls both on little- and big- endian.
+ */
+static inline int syscall_get_arch(struct task_struct *task)
+{
+	if (is_compat_thread(task_thread_info(task)))
+		return AUDIT_ARCH_ARM;
+
+	return AUDIT_ARCH_AARCH64;
+}
+
+#endif	/* __ASM_SYSCALL_H */
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
new file mode 100644
index 000000000..d30217c21
--- /dev/null
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - arm64 specific wrappers to syscall definitions
+ *
+ * Based on arch/x86/include/asm_syscall_wrapper.h
+ */
+
+#ifndef __ASM_SYSCALL_WRAPPER_H
+#define __ASM_SYSCALL_WRAPPER_H
+
+#include <asm/ptrace.h>
+
+#define SC_ARM64_REGS_TO_ARGS(x, ...)				\
+	__MAP(x,__SC_ARGS					\
+	      ,,regs->regs[0],,regs->regs[1],,regs->regs[2]	\
+	      ,,regs->regs[3],,regs->regs[4],,regs->regs[5])
+
+#ifdef CONFIG_COMPAT
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__arm64_compat_sys##name, ERRNO);				\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs)		\
+	{										\
+		return __se_compat_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}										\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{										\
+		return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));	\
+	}										\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define COMPAT_SYSCALL_DEFINE0(sname)							\
+	asmlinkage long __arm64_compat_sys_##sname(const struct pt_regs *__unused);	\
+	ALLOW_ERROR_INJECTION(__arm64_compat_sys_##sname, ERRNO);			\
+	asmlinkage long __arm64_compat_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL_COMPAT(name) 							\
+	asmlinkage long __weak __arm64_compat_sys_##name(const struct pt_regs *regs)	\
+	{										\
+		return sys_ni_syscall();						\
+	}
+
+#define COMPAT_SYS_NI(name) \
+	SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers);
+
+#endif /* CONFIG_COMPAT */
+
+#define __SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __arm64_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__arm64_sys##name, ERRNO);			\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __arm64_sys##name(const struct pt_regs *regs)		\
+	{									\
+		return __se_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}									\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{									\
+		long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		__MAP(x,__SC_TEST,__VA_ARGS__);					\
+		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));		\
+		return ret;							\
+	}									\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define SYSCALL_DEFINE0(sname)							\
+	SYSCALL_METADATA(_##sname, 0);						\
+	asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused);	\
+	ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO);			\
+	asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL(name)							\
+	asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs)	\
+	{									\
+		return sys_ni_syscall();					\
+	}
+
+#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
+
+#endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 000000000..3a448ab09
--- /dev/null
+++ b/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,1072 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#include <linux/bits.h>
+#include <linux/stringify.h>
+#include <linux/kasan-tags.h>
+
+#include <asm/gpr-num.h>
+
+/*
+ * ARMv8 ARM reserves the following encoding for system registers:
+ * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
+ *  C5.2, version:ARM DDI 0487A.f)
+ *	[20-19] : Op0
+ *	[18-16] : Op1
+ *	[15-12] : CRn
+ *	[11-8]  : CRm
+ *	[7-5]   : Op2
+ */
+#define Op0_shift	19
+#define Op0_mask	0x3
+#define Op1_shift	16
+#define Op1_mask	0x7
+#define CRn_shift	12
+#define CRn_mask	0xf
+#define CRm_shift	8
+#define CRm_mask	0xf
+#define Op2_shift	5
+#define Op2_mask	0x7
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+	(((op0) << Op0_shift) | ((op1) << Op1_shift) | \
+	 ((crn) << CRn_shift) | ((crm) << CRm_shift) | \
+	 ((op2) << Op2_shift))
+
+#define sys_insn	sys_reg
+
+#define sys_reg_Op0(id)	(((id) >> Op0_shift) & Op0_mask)
+#define sys_reg_Op1(id)	(((id) >> Op1_shift) & Op1_mask)
+#define sys_reg_CRn(id)	(((id) >> CRn_shift) & CRn_mask)
+#define sys_reg_CRm(id)	(((id) >> CRm_shift) & CRm_mask)
+#define sys_reg_Op2(id)	(((id) >> Op2_shift) & Op2_mask)
+
+#ifndef CONFIG_BROKEN_GAS_INST
+
+#ifdef __ASSEMBLY__
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x)			.inst(x)
+#else
+#define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
+#endif
+
+#else  /* CONFIG_BROKEN_GAS_INST */
+
+#ifndef CONFIG_CPU_BIG_ENDIAN
+#define __INSTR_BSWAP(x)		(x)
+#else  /* CONFIG_CPU_BIG_ENDIAN */
+#define __INSTR_BSWAP(x)		((((x) << 24) & 0xff000000)	| \
+					 (((x) <<  8) & 0x00ff0000)	| \
+					 (((x) >>  8) & 0x0000ff00)	| \
+					 (((x) >> 24) & 0x000000ff))
+#endif	/* CONFIG_CPU_BIG_ENDIAN */
+
+#ifdef __ASSEMBLY__
+#define __emit_inst(x)			.long __INSTR_BSWAP(x)
+#else  /* __ASSEMBLY__ */
+#define __emit_inst(x)			".long " __stringify(__INSTR_BSWAP(x)) "\n\t"
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* CONFIG_BROKEN_GAS_INST */
+
+/*
+ * Instructions for modifying PSTATE fields.
+ * As per Arm ARM for v8-A, Section "C.5.1.3 op0 == 0b00, architectural hints,
+ * barriers and CLREX, and PSTATE access", ARM DDI 0487 C.a, system instructions
+ * for accessing PSTATE fields have the following encoding:
+ *	Op0 = 0, CRn = 4
+ *	Op1, Op2 encodes the PSTATE field modified and defines the constraints.
+ *	CRm = Imm4 for the instruction.
+ *	Rt = 0x1f
+ */
+#define pstate_field(op1, op2)		((op1) << Op1_shift | (op2) << Op2_shift)
+#define PSTATE_Imm_shift		CRm_shift
+
+#define PSTATE_PAN			pstate_field(0, 4)
+#define PSTATE_UAO			pstate_field(0, 3)
+#define PSTATE_SSBS			pstate_field(3, 1)
+#define PSTATE_TCO			pstate_field(3, 4)
+
+#define SET_PSTATE_PAN(x)		__emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_UAO(x)		__emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_SSBS(x)		__emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_TCO(x)		__emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
+
+#define set_pstate_pan(x)		asm volatile(SET_PSTATE_PAN(x))
+#define set_pstate_uao(x)		asm volatile(SET_PSTATE_UAO(x))
+#define set_pstate_ssbs(x)		asm volatile(SET_PSTATE_SSBS(x))
+
+#define __SYS_BARRIER_INSN(CRm, op2, Rt) \
+	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
+
+#define SB_BARRIER_INSN			__SYS_BARRIER_INSN(0, 7, 31)
+
+#define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
+#define SYS_DC_IGSW			sys_insn(1, 0, 7, 6, 4)
+#define SYS_DC_IGDSW			sys_insn(1, 0, 7, 6, 6)
+#define SYS_DC_CSW			sys_insn(1, 0, 7, 10, 2)
+#define SYS_DC_CGSW			sys_insn(1, 0, 7, 10, 4)
+#define SYS_DC_CGDSW			sys_insn(1, 0, 7, 10, 6)
+#define SYS_DC_CISW			sys_insn(1, 0, 7, 14, 2)
+#define SYS_DC_CIGSW			sys_insn(1, 0, 7, 14, 4)
+#define SYS_DC_CIGDSW			sys_insn(1, 0, 7, 14, 6)
+
+/*
+ * Automatically generated definitions for system registers, the
+ * manual encodings below are in the process of being converted to
+ * come from here. The header relies on the definition of sys_reg()
+ * earlier in this file.
+ */
+#include "asm/sysreg-defs.h"
+
+/*
+ * System registers, organised loosely by encoding but grouped together
+ * where the architected name contains an index. e.g. ID_MMFR<n>_EL1.
+ */
+#define SYS_SVCR_SMSTOP_SM_EL0		sys_reg(0, 3, 4, 2, 3)
+#define SYS_SVCR_SMSTART_SM_EL0		sys_reg(0, 3, 4, 3, 3)
+#define SYS_SVCR_SMSTOP_SMZA_EL0	sys_reg(0, 3, 4, 6, 3)
+
+#define SYS_OSDTRRX_EL1			sys_reg(2, 0, 0, 0, 2)
+#define SYS_MDCCINT_EL1			sys_reg(2, 0, 0, 2, 0)
+#define SYS_MDSCR_EL1			sys_reg(2, 0, 0, 2, 2)
+#define SYS_OSDTRTX_EL1			sys_reg(2, 0, 0, 3, 2)
+#define SYS_OSECCR_EL1			sys_reg(2, 0, 0, 6, 2)
+#define SYS_DBGBVRn_EL1(n)		sys_reg(2, 0, 0, n, 4)
+#define SYS_DBGBCRn_EL1(n)		sys_reg(2, 0, 0, n, 5)
+#define SYS_DBGWVRn_EL1(n)		sys_reg(2, 0, 0, n, 6)
+#define SYS_DBGWCRn_EL1(n)		sys_reg(2, 0, 0, n, 7)
+#define SYS_MDRAR_EL1			sys_reg(2, 0, 1, 0, 0)
+
+#define SYS_OSLAR_EL1			sys_reg(2, 0, 1, 0, 4)
+#define SYS_OSLAR_OSLK			BIT(0)
+
+#define SYS_OSLSR_EL1			sys_reg(2, 0, 1, 1, 4)
+#define SYS_OSLSR_OSLM_MASK		(BIT(3) | BIT(0))
+#define SYS_OSLSR_OSLM_NI		0
+#define SYS_OSLSR_OSLM_IMPLEMENTED	BIT(3)
+#define SYS_OSLSR_OSLK			BIT(1)
+
+#define SYS_OSDLR_EL1			sys_reg(2, 0, 1, 3, 4)
+#define SYS_DBGPRCR_EL1			sys_reg(2, 0, 1, 4, 4)
+#define SYS_DBGCLAIMSET_EL1		sys_reg(2, 0, 7, 8, 6)
+#define SYS_DBGCLAIMCLR_EL1		sys_reg(2, 0, 7, 9, 6)
+#define SYS_DBGAUTHSTATUS_EL1		sys_reg(2, 0, 7, 14, 6)
+#define SYS_MDCCSR_EL0			sys_reg(2, 3, 0, 1, 0)
+#define SYS_DBGDTR_EL0			sys_reg(2, 3, 0, 4, 0)
+#define SYS_DBGDTRRX_EL0		sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGDTRTX_EL0		sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGVCR32_EL2		sys_reg(2, 4, 0, 7, 0)
+
+#define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
+#define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
+#define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
+
+#define SYS_ID_PFR0_EL1			sys_reg(3, 0, 0, 1, 0)
+#define SYS_ID_PFR1_EL1			sys_reg(3, 0, 0, 1, 1)
+#define SYS_ID_PFR2_EL1			sys_reg(3, 0, 0, 3, 4)
+#define SYS_ID_DFR0_EL1			sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_DFR1_EL1			sys_reg(3, 0, 0, 3, 5)
+#define SYS_ID_AFR0_EL1			sys_reg(3, 0, 0, 1, 3)
+#define SYS_ID_MMFR0_EL1		sys_reg(3, 0, 0, 1, 4)
+#define SYS_ID_MMFR1_EL1		sys_reg(3, 0, 0, 1, 5)
+#define SYS_ID_MMFR2_EL1		sys_reg(3, 0, 0, 1, 6)
+#define SYS_ID_MMFR3_EL1		sys_reg(3, 0, 0, 1, 7)
+#define SYS_ID_MMFR4_EL1		sys_reg(3, 0, 0, 2, 6)
+#define SYS_ID_MMFR5_EL1		sys_reg(3, 0, 0, 3, 6)
+
+#define SYS_ID_ISAR0_EL1		sys_reg(3, 0, 0, 2, 0)
+#define SYS_ID_ISAR1_EL1		sys_reg(3, 0, 0, 2, 1)
+#define SYS_ID_ISAR2_EL1		sys_reg(3, 0, 0, 2, 2)
+#define SYS_ID_ISAR3_EL1		sys_reg(3, 0, 0, 2, 3)
+#define SYS_ID_ISAR4_EL1		sys_reg(3, 0, 0, 2, 4)
+#define SYS_ID_ISAR5_EL1		sys_reg(3, 0, 0, 2, 5)
+#define SYS_ID_ISAR6_EL1		sys_reg(3, 0, 0, 2, 7)
+
+#define SYS_MVFR0_EL1			sys_reg(3, 0, 0, 3, 0)
+#define SYS_MVFR1_EL1			sys_reg(3, 0, 0, 3, 1)
+#define SYS_MVFR2_EL1			sys_reg(3, 0, 0, 3, 2)
+
+#define SYS_ACTLR_EL1			sys_reg(3, 0, 1, 0, 1)
+#define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
+#define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
+
+#define SYS_TRFCR_EL1			sys_reg(3, 0, 1, 2, 1)
+
+#define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
+
+#define SYS_APIAKEYLO_EL1		sys_reg(3, 0, 2, 1, 0)
+#define SYS_APIAKEYHI_EL1		sys_reg(3, 0, 2, 1, 1)
+#define SYS_APIBKEYLO_EL1		sys_reg(3, 0, 2, 1, 2)
+#define SYS_APIBKEYHI_EL1		sys_reg(3, 0, 2, 1, 3)
+
+#define SYS_APDAKEYLO_EL1		sys_reg(3, 0, 2, 2, 0)
+#define SYS_APDAKEYHI_EL1		sys_reg(3, 0, 2, 2, 1)
+#define SYS_APDBKEYLO_EL1		sys_reg(3, 0, 2, 2, 2)
+#define SYS_APDBKEYHI_EL1		sys_reg(3, 0, 2, 2, 3)
+
+#define SYS_APGAKEYLO_EL1		sys_reg(3, 0, 2, 3, 0)
+#define SYS_APGAKEYHI_EL1		sys_reg(3, 0, 2, 3, 1)
+
+#define SYS_SPSR_EL1			sys_reg(3, 0, 4, 0, 0)
+#define SYS_ELR_EL1			sys_reg(3, 0, 4, 0, 1)
+
+#define SYS_ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+
+#define SYS_AFSR0_EL1			sys_reg(3, 0, 5, 1, 0)
+#define SYS_AFSR1_EL1			sys_reg(3, 0, 5, 1, 1)
+#define SYS_ESR_EL1			sys_reg(3, 0, 5, 2, 0)
+
+#define SYS_ERRIDR_EL1			sys_reg(3, 0, 5, 3, 0)
+#define SYS_ERRSELR_EL1			sys_reg(3, 0, 5, 3, 1)
+#define SYS_ERXFR_EL1			sys_reg(3, 0, 5, 4, 0)
+#define SYS_ERXCTLR_EL1			sys_reg(3, 0, 5, 4, 1)
+#define SYS_ERXSTATUS_EL1		sys_reg(3, 0, 5, 4, 2)
+#define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
+#define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+#define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
+#define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
+
+#define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
+
+#define SYS_PAR_EL1_F			BIT(0)
+#define SYS_PAR_EL1_FST			GENMASK(6, 1)
+
+/*** Statistical Profiling Extension ***/
+/* ID registers */
+#define SYS_PMSIDR_EL1			sys_reg(3, 0, 9, 9, 7)
+#define SYS_PMSIDR_EL1_FE_SHIFT		0
+#define SYS_PMSIDR_EL1_FT_SHIFT		1
+#define SYS_PMSIDR_EL1_FL_SHIFT		2
+#define SYS_PMSIDR_EL1_ARCHINST_SHIFT	3
+#define SYS_PMSIDR_EL1_LDS_SHIFT	4
+#define SYS_PMSIDR_EL1_ERND_SHIFT	5
+#define SYS_PMSIDR_EL1_INTERVAL_SHIFT	8
+#define SYS_PMSIDR_EL1_INTERVAL_MASK	0xfUL
+#define SYS_PMSIDR_EL1_MAXSIZE_SHIFT	12
+#define SYS_PMSIDR_EL1_MAXSIZE_MASK	0xfUL
+#define SYS_PMSIDR_EL1_COUNTSIZE_SHIFT	16
+#define SYS_PMSIDR_EL1_COUNTSIZE_MASK	0xfUL
+
+#define SYS_PMBIDR_EL1			sys_reg(3, 0, 9, 10, 7)
+#define SYS_PMBIDR_EL1_ALIGN_SHIFT	0
+#define SYS_PMBIDR_EL1_ALIGN_MASK	0xfU
+#define SYS_PMBIDR_EL1_P_SHIFT		4
+#define SYS_PMBIDR_EL1_F_SHIFT		5
+
+/* Sampling controls */
+#define SYS_PMSCR_EL1			sys_reg(3, 0, 9, 9, 0)
+#define SYS_PMSCR_EL1_E0SPE_SHIFT	0
+#define SYS_PMSCR_EL1_E1SPE_SHIFT	1
+#define SYS_PMSCR_EL1_CX_SHIFT		3
+#define SYS_PMSCR_EL1_PA_SHIFT		4
+#define SYS_PMSCR_EL1_TS_SHIFT		5
+#define SYS_PMSCR_EL1_PCT_SHIFT		6
+
+#define SYS_PMSCR_EL2			sys_reg(3, 4, 9, 9, 0)
+#define SYS_PMSCR_EL2_E0HSPE_SHIFT	0
+#define SYS_PMSCR_EL2_E2SPE_SHIFT	1
+#define SYS_PMSCR_EL2_CX_SHIFT		3
+#define SYS_PMSCR_EL2_PA_SHIFT		4
+#define SYS_PMSCR_EL2_TS_SHIFT		5
+#define SYS_PMSCR_EL2_PCT_SHIFT		6
+
+#define SYS_PMSICR_EL1			sys_reg(3, 0, 9, 9, 2)
+
+#define SYS_PMSIRR_EL1			sys_reg(3, 0, 9, 9, 3)
+#define SYS_PMSIRR_EL1_RND_SHIFT	0
+#define SYS_PMSIRR_EL1_INTERVAL_SHIFT	8
+#define SYS_PMSIRR_EL1_INTERVAL_MASK	0xffffffUL
+
+/* Filtering controls */
+#define SYS_PMSNEVFR_EL1		sys_reg(3, 0, 9, 9, 1)
+
+#define SYS_PMSFCR_EL1			sys_reg(3, 0, 9, 9, 4)
+#define SYS_PMSFCR_EL1_FE_SHIFT		0
+#define SYS_PMSFCR_EL1_FT_SHIFT		1
+#define SYS_PMSFCR_EL1_FL_SHIFT		2
+#define SYS_PMSFCR_EL1_B_SHIFT		16
+#define SYS_PMSFCR_EL1_LD_SHIFT		17
+#define SYS_PMSFCR_EL1_ST_SHIFT		18
+
+#define SYS_PMSEVFR_EL1			sys_reg(3, 0, 9, 9, 5)
+#define SYS_PMSEVFR_EL1_RES0_8_2	\
+	(GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\
+	 BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0))
+#define SYS_PMSEVFR_EL1_RES0_8_3	\
+	(SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11)))
+
+#define SYS_PMSLATFR_EL1		sys_reg(3, 0, 9, 9, 6)
+#define SYS_PMSLATFR_EL1_MINLAT_SHIFT	0
+
+/* Buffer controls */
+#define SYS_PMBLIMITR_EL1		sys_reg(3, 0, 9, 10, 0)
+#define SYS_PMBLIMITR_EL1_E_SHIFT	0
+#define SYS_PMBLIMITR_EL1_FM_SHIFT	1
+#define SYS_PMBLIMITR_EL1_FM_MASK	0x3UL
+#define SYS_PMBLIMITR_EL1_FM_STOP_IRQ	(0 << SYS_PMBLIMITR_EL1_FM_SHIFT)
+
+#define SYS_PMBPTR_EL1			sys_reg(3, 0, 9, 10, 1)
+
+/* Buffer error reporting */
+#define SYS_PMBSR_EL1			sys_reg(3, 0, 9, 10, 3)
+#define SYS_PMBSR_EL1_COLL_SHIFT	16
+#define SYS_PMBSR_EL1_S_SHIFT		17
+#define SYS_PMBSR_EL1_EA_SHIFT		18
+#define SYS_PMBSR_EL1_DL_SHIFT		19
+#define SYS_PMBSR_EL1_EC_SHIFT		26
+#define SYS_PMBSR_EL1_EC_MASK		0x3fUL
+
+#define SYS_PMBSR_EL1_EC_BUF		(0x0UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S1	(0x24UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S2	(0x25UL << SYS_PMBSR_EL1_EC_SHIFT)
+
+#define SYS_PMBSR_EL1_FAULT_FSC_SHIFT	0
+#define SYS_PMBSR_EL1_FAULT_FSC_MASK	0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_SHIFT	0
+#define SYS_PMBSR_EL1_BUF_BSC_MASK	0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_FULL	(0x1UL << SYS_PMBSR_EL1_BUF_BSC_SHIFT)
+
+/*** End of Statistical Profiling Extension ***/
+
+/*
+ * TRBE Registers
+ */
+#define SYS_TRBLIMITR_EL1		sys_reg(3, 0, 9, 11, 0)
+#define SYS_TRBPTR_EL1			sys_reg(3, 0, 9, 11, 1)
+#define SYS_TRBBASER_EL1		sys_reg(3, 0, 9, 11, 2)
+#define SYS_TRBSR_EL1			sys_reg(3, 0, 9, 11, 3)
+#define SYS_TRBMAR_EL1			sys_reg(3, 0, 9, 11, 4)
+#define SYS_TRBTRG_EL1			sys_reg(3, 0, 9, 11, 6)
+#define SYS_TRBIDR_EL1			sys_reg(3, 0, 9, 11, 7)
+
+#define TRBLIMITR_LIMIT_MASK		GENMASK_ULL(51, 0)
+#define TRBLIMITR_LIMIT_SHIFT		12
+#define TRBLIMITR_NVM			BIT(5)
+#define TRBLIMITR_TRIG_MODE_MASK	GENMASK(1, 0)
+#define TRBLIMITR_TRIG_MODE_SHIFT	3
+#define TRBLIMITR_FILL_MODE_MASK	GENMASK(1, 0)
+#define TRBLIMITR_FILL_MODE_SHIFT	1
+#define TRBLIMITR_ENABLE		BIT(0)
+#define TRBPTR_PTR_MASK			GENMASK_ULL(63, 0)
+#define TRBPTR_PTR_SHIFT		0
+#define TRBBASER_BASE_MASK		GENMASK_ULL(51, 0)
+#define TRBBASER_BASE_SHIFT		12
+#define TRBSR_EC_MASK			GENMASK(5, 0)
+#define TRBSR_EC_SHIFT			26
+#define TRBSR_IRQ			BIT(22)
+#define TRBSR_TRG			BIT(21)
+#define TRBSR_WRAP			BIT(20)
+#define TRBSR_ABORT			BIT(18)
+#define TRBSR_STOP			BIT(17)
+#define TRBSR_MSS_MASK			GENMASK(15, 0)
+#define TRBSR_MSS_SHIFT			0
+#define TRBSR_BSC_MASK			GENMASK(5, 0)
+#define TRBSR_BSC_SHIFT			0
+#define TRBSR_FSC_MASK			GENMASK(5, 0)
+#define TRBSR_FSC_SHIFT			0
+#define TRBMAR_SHARE_MASK		GENMASK(1, 0)
+#define TRBMAR_SHARE_SHIFT		8
+#define TRBMAR_OUTER_MASK		GENMASK(3, 0)
+#define TRBMAR_OUTER_SHIFT		4
+#define TRBMAR_INNER_MASK		GENMASK(3, 0)
+#define TRBMAR_INNER_SHIFT		0
+#define TRBTRG_TRG_MASK			GENMASK(31, 0)
+#define TRBTRG_TRG_SHIFT		0
+#define TRBIDR_FLAG			BIT(5)
+#define TRBIDR_PROG			BIT(4)
+#define TRBIDR_ALIGN_MASK		GENMASK(3, 0)
+#define TRBIDR_ALIGN_SHIFT		0
+
+#define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
+#define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
+
+#define SYS_PMMIR_EL1			sys_reg(3, 0, 9, 14, 6)
+
+#define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
+#define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
+
+#define SYS_VBAR_EL1			sys_reg(3, 0, 12, 0, 0)
+#define SYS_DISR_EL1			sys_reg(3, 0, 12, 1, 1)
+
+#define SYS_ICC_IAR0_EL1		sys_reg(3, 0, 12, 8, 0)
+#define SYS_ICC_EOIR0_EL1		sys_reg(3, 0, 12, 8, 1)
+#define SYS_ICC_HPPIR0_EL1		sys_reg(3, 0, 12, 8, 2)
+#define SYS_ICC_BPR0_EL1		sys_reg(3, 0, 12, 8, 3)
+#define SYS_ICC_AP0Rn_EL1(n)		sys_reg(3, 0, 12, 8, 4 | n)
+#define SYS_ICC_AP0R0_EL1		SYS_ICC_AP0Rn_EL1(0)
+#define SYS_ICC_AP0R1_EL1		SYS_ICC_AP0Rn_EL1(1)
+#define SYS_ICC_AP0R2_EL1		SYS_ICC_AP0Rn_EL1(2)
+#define SYS_ICC_AP0R3_EL1		SYS_ICC_AP0Rn_EL1(3)
+#define SYS_ICC_AP1Rn_EL1(n)		sys_reg(3, 0, 12, 9, n)
+#define SYS_ICC_AP1R0_EL1		SYS_ICC_AP1Rn_EL1(0)
+#define SYS_ICC_AP1R1_EL1		SYS_ICC_AP1Rn_EL1(1)
+#define SYS_ICC_AP1R2_EL1		SYS_ICC_AP1Rn_EL1(2)
+#define SYS_ICC_AP1R3_EL1		SYS_ICC_AP1Rn_EL1(3)
+#define SYS_ICC_DIR_EL1			sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_RPR_EL1			sys_reg(3, 0, 12, 11, 3)
+#define SYS_ICC_SGI1R_EL1		sys_reg(3, 0, 12, 11, 5)
+#define SYS_ICC_ASGI1R_EL1		sys_reg(3, 0, 12, 11, 6)
+#define SYS_ICC_SGI0R_EL1		sys_reg(3, 0, 12, 11, 7)
+#define SYS_ICC_IAR1_EL1		sys_reg(3, 0, 12, 12, 0)
+#define SYS_ICC_EOIR1_EL1		sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_HPPIR1_EL1		sys_reg(3, 0, 12, 12, 2)
+#define SYS_ICC_BPR1_EL1		sys_reg(3, 0, 12, 12, 3)
+#define SYS_ICC_CTLR_EL1		sys_reg(3, 0, 12, 12, 4)
+#define SYS_ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define SYS_ICC_IGRPEN0_EL1		sys_reg(3, 0, 12, 12, 6)
+#define SYS_ICC_IGRPEN1_EL1		sys_reg(3, 0, 12, 12, 7)
+
+#define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
+
+#define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
+#define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
+
+#define SYS_RNDR_EL0			sys_reg(3, 3, 2, 4, 0)
+#define SYS_RNDRRS_EL0			sys_reg(3, 3, 2, 4, 1)
+
+#define SYS_PMCR_EL0			sys_reg(3, 3, 9, 12, 0)
+#define SYS_PMCNTENSET_EL0		sys_reg(3, 3, 9, 12, 1)
+#define SYS_PMCNTENCLR_EL0		sys_reg(3, 3, 9, 12, 2)
+#define SYS_PMOVSCLR_EL0		sys_reg(3, 3, 9, 12, 3)
+#define SYS_PMSWINC_EL0			sys_reg(3, 3, 9, 12, 4)
+#define SYS_PMSELR_EL0			sys_reg(3, 3, 9, 12, 5)
+#define SYS_PMCEID0_EL0			sys_reg(3, 3, 9, 12, 6)
+#define SYS_PMCEID1_EL0			sys_reg(3, 3, 9, 12, 7)
+#define SYS_PMCCNTR_EL0			sys_reg(3, 3, 9, 13, 0)
+#define SYS_PMXEVTYPER_EL0		sys_reg(3, 3, 9, 13, 1)
+#define SYS_PMXEVCNTR_EL0		sys_reg(3, 3, 9, 13, 2)
+#define SYS_PMUSERENR_EL0		sys_reg(3, 3, 9, 14, 0)
+#define SYS_PMOVSSET_EL0		sys_reg(3, 3, 9, 14, 3)
+
+#define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
+#define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
+#define SYS_TPIDR2_EL0			sys_reg(3, 3, 13, 0, 5)
+
+#define SYS_SCXTNUM_EL0			sys_reg(3, 3, 13, 0, 7)
+
+/* Definitions for system register interface to AMU for ARMv8.4 onwards */
+#define SYS_AM_EL0(crm, op2)		sys_reg(3, 3, 13, (crm), (op2))
+#define SYS_AMCR_EL0			SYS_AM_EL0(2, 0)
+#define SYS_AMCFGR_EL0			SYS_AM_EL0(2, 1)
+#define SYS_AMCGCR_EL0			SYS_AM_EL0(2, 2)
+#define SYS_AMUSERENR_EL0		SYS_AM_EL0(2, 3)
+#define SYS_AMCNTENCLR0_EL0		SYS_AM_EL0(2, 4)
+#define SYS_AMCNTENSET0_EL0		SYS_AM_EL0(2, 5)
+#define SYS_AMCNTENCLR1_EL0		SYS_AM_EL0(3, 0)
+#define SYS_AMCNTENSET1_EL0		SYS_AM_EL0(3, 1)
+
+/*
+ * Group 0 of activity monitors (architected):
+ *                op0  op1  CRn   CRm       op2
+ * Counter:       11   011  1101  010:n<3>  n<2:0>
+ * Type:          11   011  1101  011:n<3>  n<2:0>
+ * n: 0-15
+ *
+ * Group 1 of activity monitors (auxiliary):
+ *                op0  op1  CRn   CRm       op2
+ * Counter:       11   011  1101  110:n<3>  n<2:0>
+ * Type:          11   011  1101  111:n<3>  n<2:0>
+ * n: 0-15
+ */
+
+#define SYS_AMEVCNTR0_EL0(n)		SYS_AM_EL0(4 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER0_EL0(n)		SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVCNTR1_EL0(n)		SYS_AM_EL0(12 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER1_EL0(n)		SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
+
+/* AMU v1: Fixed (architecturally defined) activity monitors */
+#define SYS_AMEVCNTR0_CORE_EL0		SYS_AMEVCNTR0_EL0(0)
+#define SYS_AMEVCNTR0_CONST_EL0		SYS_AMEVCNTR0_EL0(1)
+#define SYS_AMEVCNTR0_INST_RET_EL0	SYS_AMEVCNTR0_EL0(2)
+#define SYS_AMEVCNTR0_MEM_STALL		SYS_AMEVCNTR0_EL0(3)
+
+#define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
+
+#define SYS_CNTPCTSS_EL0		sys_reg(3, 3, 14, 0, 5)
+#define SYS_CNTVCTSS_EL0		sys_reg(3, 3, 14, 0, 6)
+
+#define SYS_CNTP_TVAL_EL0		sys_reg(3, 3, 14, 2, 0)
+#define SYS_CNTP_CTL_EL0		sys_reg(3, 3, 14, 2, 1)
+#define SYS_CNTP_CVAL_EL0		sys_reg(3, 3, 14, 2, 2)
+
+#define SYS_CNTV_CTL_EL0		sys_reg(3, 3, 14, 3, 1)
+#define SYS_CNTV_CVAL_EL0		sys_reg(3, 3, 14, 3, 2)
+
+#define SYS_AARCH32_CNTP_TVAL		sys_reg(0, 0, 14, 2, 0)
+#define SYS_AARCH32_CNTP_CTL		sys_reg(0, 0, 14, 2, 1)
+#define SYS_AARCH32_CNTP_CVAL		sys_reg(0, 2, 0, 14, 0)
+
+#define __PMEV_op2(n)			((n) & 0x7)
+#define __CNTR_CRm(n)			(0x8 | (((n) >> 3) & 0x3))
+#define SYS_PMEVCNTRn_EL0(n)		sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
+#define __TYPER_CRm(n)			(0xc | (((n) >> 3) & 0x3))
+#define SYS_PMEVTYPERn_EL0(n)		sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
+
+#define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
+
+#define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
+#define SYS_HFGRTR_EL2			sys_reg(3, 4, 1, 1, 4)
+#define SYS_HFGWTR_EL2			sys_reg(3, 4, 1, 1, 5)
+#define SYS_HFGITR_EL2			sys_reg(3, 4, 1, 1, 6)
+#define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
+#define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
+#define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
+#define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
+#define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
+#define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
+#define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
+#define SYS_ESR_EL2			sys_reg(3, 4, 5, 2, 0)
+#define SYS_VSESR_EL2			sys_reg(3, 4, 5, 2, 3)
+#define SYS_FPEXC32_EL2			sys_reg(3, 4, 5, 3, 0)
+#define SYS_TFSR_EL2			sys_reg(3, 4, 5, 6, 0)
+
+#define SYS_VDISR_EL2			sys_reg(3, 4, 12, 1,  1)
+#define __SYS__AP0Rx_EL2(x)		sys_reg(3, 4, 12, 8, x)
+#define SYS_ICH_AP0R0_EL2		__SYS__AP0Rx_EL2(0)
+#define SYS_ICH_AP0R1_EL2		__SYS__AP0Rx_EL2(1)
+#define SYS_ICH_AP0R2_EL2		__SYS__AP0Rx_EL2(2)
+#define SYS_ICH_AP0R3_EL2		__SYS__AP0Rx_EL2(3)
+
+#define __SYS__AP1Rx_EL2(x)		sys_reg(3, 4, 12, 9, x)
+#define SYS_ICH_AP1R0_EL2		__SYS__AP1Rx_EL2(0)
+#define SYS_ICH_AP1R1_EL2		__SYS__AP1Rx_EL2(1)
+#define SYS_ICH_AP1R2_EL2		__SYS__AP1Rx_EL2(2)
+#define SYS_ICH_AP1R3_EL2		__SYS__AP1Rx_EL2(3)
+
+#define SYS_ICH_VSEIR_EL2		sys_reg(3, 4, 12, 9, 4)
+#define SYS_ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+#define SYS_ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#define SYS_ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
+#define SYS_ICH_MISR_EL2		sys_reg(3, 4, 12, 11, 2)
+#define SYS_ICH_EISR_EL2		sys_reg(3, 4, 12, 11, 3)
+#define SYS_ICH_ELRSR_EL2		sys_reg(3, 4, 12, 11, 5)
+#define SYS_ICH_VMCR_EL2		sys_reg(3, 4, 12, 11, 7)
+
+#define __SYS__LR0_EL2(x)		sys_reg(3, 4, 12, 12, x)
+#define SYS_ICH_LR0_EL2			__SYS__LR0_EL2(0)
+#define SYS_ICH_LR1_EL2			__SYS__LR0_EL2(1)
+#define SYS_ICH_LR2_EL2			__SYS__LR0_EL2(2)
+#define SYS_ICH_LR3_EL2			__SYS__LR0_EL2(3)
+#define SYS_ICH_LR4_EL2			__SYS__LR0_EL2(4)
+#define SYS_ICH_LR5_EL2			__SYS__LR0_EL2(5)
+#define SYS_ICH_LR6_EL2			__SYS__LR0_EL2(6)
+#define SYS_ICH_LR7_EL2			__SYS__LR0_EL2(7)
+
+#define __SYS__LR8_EL2(x)		sys_reg(3, 4, 12, 13, x)
+#define SYS_ICH_LR8_EL2			__SYS__LR8_EL2(0)
+#define SYS_ICH_LR9_EL2			__SYS__LR8_EL2(1)
+#define SYS_ICH_LR10_EL2		__SYS__LR8_EL2(2)
+#define SYS_ICH_LR11_EL2		__SYS__LR8_EL2(3)
+#define SYS_ICH_LR12_EL2		__SYS__LR8_EL2(4)
+#define SYS_ICH_LR13_EL2		__SYS__LR8_EL2(5)
+#define SYS_ICH_LR14_EL2		__SYS__LR8_EL2(6)
+#define SYS_ICH_LR15_EL2		__SYS__LR8_EL2(7)
+
+/* VHE encodings for architectural EL0/1 system registers */
+#define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
+#define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
+#define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
+#define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
+#define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
+#define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
+#define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
+#define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
+#define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
+#define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
+#define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
+#define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
+#define SYS_VBAR_EL12			sys_reg(3, 5, 12, 0, 0)
+#define SYS_CNTKCTL_EL12		sys_reg(3, 5, 14, 1, 0)
+#define SYS_CNTP_TVAL_EL02		sys_reg(3, 5, 14, 2, 0)
+#define SYS_CNTP_CTL_EL02		sys_reg(3, 5, 14, 2, 1)
+#define SYS_CNTP_CVAL_EL02		sys_reg(3, 5, 14, 2, 2)
+#define SYS_CNTV_TVAL_EL02		sys_reg(3, 5, 14, 3, 0)
+#define SYS_CNTV_CTL_EL02		sys_reg(3, 5, 14, 3, 1)
+#define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
+
+/* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_ENTP2	(BIT(60))
+#define SCTLR_ELx_DSSBS	(BIT(44))
+#define SCTLR_ELx_ATA	(BIT(43))
+
+#define SCTLR_ELx_ENIA_SHIFT	31
+
+#define SCTLR_ELx_ITFSB	 (BIT(37))
+#define SCTLR_ELx_ENIA	 (BIT(SCTLR_ELx_ENIA_SHIFT))
+#define SCTLR_ELx_ENIB	 (BIT(30))
+#define SCTLR_ELx_LSMAOE (BIT(29))
+#define SCTLR_ELx_nTLSMD (BIT(28))
+#define SCTLR_ELx_ENDA	 (BIT(27))
+#define SCTLR_ELx_EE     (BIT(25))
+#define SCTLR_ELx_EIS	 (BIT(22))
+#define SCTLR_ELx_IESB	 (BIT(21))
+#define SCTLR_ELx_TSCXT	 (BIT(20))
+#define SCTLR_ELx_WXN	 (BIT(19))
+#define SCTLR_ELx_ENDB	 (BIT(13))
+#define SCTLR_ELx_I	 (BIT(12))
+#define SCTLR_ELx_EOS	 (BIT(11))
+#define SCTLR_ELx_SA	 (BIT(3))
+#define SCTLR_ELx_C	 (BIT(2))
+#define SCTLR_ELx_A	 (BIT(1))
+#define SCTLR_ELx_M	 (BIT(0))
+
+/* SCTLR_EL2 specific flags. */
+#define SCTLR_EL2_RES1	((BIT(4))  | (BIT(5))  | (BIT(11)) | (BIT(16)) | \
+			 (BIT(18)) | (BIT(22)) | (BIT(23)) | (BIT(28)) | \
+			 (BIT(29)))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL2		SCTLR_ELx_EE
+#else
+#define ENDIAN_SET_EL2		0
+#endif
+
+#define INIT_SCTLR_EL2_MMU_ON						\
+	(SCTLR_ELx_M  | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I |	\
+	 SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 |		\
+	 SCTLR_ELx_ITFSB | SCTLR_EL2_RES1)
+
+#define INIT_SCTLR_EL2_MMU_OFF \
+	(SCTLR_EL2_RES1 | ENDIAN_SET_EL2)
+
+/* SCTLR_EL1 specific flags. */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL1		(SCTLR_EL1_E0E | SCTLR_ELx_EE)
+#else
+#define ENDIAN_SET_EL1		0
+#endif
+
+#define INIT_SCTLR_EL1_MMU_OFF \
+	(ENDIAN_SET_EL1 | SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | \
+	 SCTLR_EL1_EIS  | SCTLR_EL1_TSCXT  | SCTLR_EL1_EOS)
+
+#define INIT_SCTLR_EL1_MMU_ON \
+	(SCTLR_ELx_M      | SCTLR_ELx_C      | SCTLR_ELx_SA    | \
+	 SCTLR_EL1_SA0    | SCTLR_EL1_SED    | SCTLR_ELx_I     | \
+	 SCTLR_EL1_DZE    | SCTLR_EL1_UCT    | SCTLR_EL1_nTWE  | \
+	 SCTLR_ELx_IESB   | SCTLR_EL1_SPAN   | SCTLR_ELx_ITFSB | \
+	 ENDIAN_SET_EL1   | SCTLR_EL1_UCI    | SCTLR_EL1_EPAN  | \
+	 SCTLR_EL1_LSMAOE | SCTLR_EL1_nTLSMD | SCTLR_EL1_EIS   | \
+	 SCTLR_EL1_TSCXT  | SCTLR_EL1_EOS)
+
+/* MAIR_ELx memory attributes (used by Linux) */
+#define MAIR_ATTR_DEVICE_nGnRnE		UL(0x00)
+#define MAIR_ATTR_DEVICE_nGnRE		UL(0x04)
+#define MAIR_ATTR_NORMAL_NC		UL(0x44)
+#define MAIR_ATTR_NORMAL_TAGGED		UL(0xf0)
+#define MAIR_ATTR_NORMAL		UL(0xff)
+#define MAIR_ATTR_MASK			UL(0xff)
+
+/* Position the attr at the correct index */
+#define MAIR_ATTRIDX(attr, idx)		((attr) << ((idx) * 8))
+
+/* id_aa64pfr0 */
+#define ID_AA64PFR0_EL1_ELx_64BIT_ONLY		0x1
+#define ID_AA64PFR0_EL1_ELx_32BIT_64BIT		0x2
+
+/* id_aa64mmfr0 */
+#define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN	0x0
+#define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX	0x7
+#define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN	0x0
+#define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX	0x7
+#define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN	0x1
+#define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX	0xf
+
+#define ARM64_MIN_PARANGE_BITS		32
+
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT	0x0
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE		0x1
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN		0x2
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX		0x7
+
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define ID_AA64MMFR0_EL1_PARANGE_MAX	ID_AA64MMFR0_EL1_PARANGE_52
+#else
+#define ID_AA64MMFR0_EL1_PARANGE_MAX	ID_AA64MMFR0_EL1_PARANGE_48
+#endif
+
+#define ID_DFR0_PERFMON_SHIFT		24
+
+#define ID_DFR0_PERFMON_8_0		0x3
+#define ID_DFR0_PERFMON_8_1		0x4
+#define ID_DFR0_PERFMON_8_4		0x5
+#define ID_DFR0_PERFMON_8_5		0x6
+
+#define ID_ISAR4_SWP_FRAC_SHIFT		28
+#define ID_ISAR4_PSR_M_SHIFT		24
+#define ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT	20
+#define ID_ISAR4_BARRIER_SHIFT		16
+#define ID_ISAR4_SMC_SHIFT		12
+#define ID_ISAR4_WRITEBACK_SHIFT	8
+#define ID_ISAR4_WITHSHIFTS_SHIFT	4
+#define ID_ISAR4_UNPRIV_SHIFT		0
+
+#define ID_DFR1_MTPMU_SHIFT		0
+
+#define ID_ISAR0_DIVIDE_SHIFT		24
+#define ID_ISAR0_DEBUG_SHIFT		20
+#define ID_ISAR0_COPROC_SHIFT		16
+#define ID_ISAR0_CMPBRANCH_SHIFT	12
+#define ID_ISAR0_BITFIELD_SHIFT		8
+#define ID_ISAR0_BITCOUNT_SHIFT		4
+#define ID_ISAR0_SWAP_SHIFT		0
+
+#define ID_ISAR5_RDM_SHIFT		24
+#define ID_ISAR5_CRC32_SHIFT		16
+#define ID_ISAR5_SHA2_SHIFT		12
+#define ID_ISAR5_SHA1_SHIFT		8
+#define ID_ISAR5_AES_SHIFT		4
+#define ID_ISAR5_SEVL_SHIFT		0
+
+#define ID_ISAR6_I8MM_SHIFT		24
+#define ID_ISAR6_BF16_SHIFT		20
+#define ID_ISAR6_SPECRES_SHIFT		16
+#define ID_ISAR6_SB_SHIFT		12
+#define ID_ISAR6_FHM_SHIFT		8
+#define ID_ISAR6_DP_SHIFT		4
+#define ID_ISAR6_JSCVT_SHIFT		0
+
+#define ID_MMFR0_INNERSHR_SHIFT		28
+#define ID_MMFR0_FCSE_SHIFT		24
+#define ID_MMFR0_AUXREG_SHIFT		20
+#define ID_MMFR0_TCM_SHIFT		16
+#define ID_MMFR0_SHARELVL_SHIFT		12
+#define ID_MMFR0_OUTERSHR_SHIFT		8
+#define ID_MMFR0_PMSA_SHIFT		4
+#define ID_MMFR0_VMSA_SHIFT		0
+
+#define ID_MMFR4_EVT_SHIFT		28
+#define ID_MMFR4_CCIDX_SHIFT		24
+#define ID_MMFR4_LSM_SHIFT		20
+#define ID_MMFR4_HPDS_SHIFT		16
+#define ID_MMFR4_CNP_SHIFT		12
+#define ID_MMFR4_XNX_SHIFT		8
+#define ID_MMFR4_AC2_SHIFT		4
+#define ID_MMFR4_SPECSEI_SHIFT		0
+
+#define ID_MMFR5_ETS_SHIFT		0
+
+#define ID_PFR0_DIT_SHIFT		24
+#define ID_PFR0_CSV2_SHIFT		16
+#define ID_PFR0_STATE3_SHIFT		12
+#define ID_PFR0_STATE2_SHIFT		8
+#define ID_PFR0_STATE1_SHIFT		4
+#define ID_PFR0_STATE0_SHIFT		0
+
+#define ID_DFR0_PERFMON_SHIFT		24
+#define ID_DFR0_MPROFDBG_SHIFT		20
+#define ID_DFR0_MMAPTRC_SHIFT		16
+#define ID_DFR0_COPTRC_SHIFT		12
+#define ID_DFR0_MMAPDBG_SHIFT		8
+#define ID_DFR0_COPSDBG_SHIFT		4
+#define ID_DFR0_COPDBG_SHIFT		0
+
+#define ID_PFR2_SSBS_SHIFT		4
+#define ID_PFR2_CSV3_SHIFT		0
+
+#define MVFR0_FPROUND_SHIFT		28
+#define MVFR0_FPSHVEC_SHIFT		24
+#define MVFR0_FPSQRT_SHIFT		20
+#define MVFR0_FPDIVIDE_SHIFT		16
+#define MVFR0_FPTRAP_SHIFT		12
+#define MVFR0_FPDP_SHIFT		8
+#define MVFR0_FPSP_SHIFT		4
+#define MVFR0_SIMD_SHIFT		0
+
+#define MVFR1_SIMDFMAC_SHIFT		28
+#define MVFR1_FPHP_SHIFT		24
+#define MVFR1_SIMDHP_SHIFT		20
+#define MVFR1_SIMDSP_SHIFT		16
+#define MVFR1_SIMDINT_SHIFT		12
+#define MVFR1_SIMDLS_SHIFT		8
+#define MVFR1_FPDNAN_SHIFT		4
+#define MVFR1_FPFTZ_SHIFT		0
+
+#define ID_PFR1_GIC_SHIFT		28
+#define ID_PFR1_VIRT_FRAC_SHIFT		24
+#define ID_PFR1_SEC_FRAC_SHIFT		20
+#define ID_PFR1_GENTIMER_SHIFT		16
+#define ID_PFR1_VIRTUALIZATION_SHIFT	12
+#define ID_PFR1_MPROGMOD_SHIFT		8
+#define ID_PFR1_SECURITY_SHIFT		4
+#define ID_PFR1_PROGMOD_SHIFT		0
+
+#if defined(CONFIG_ARM64_4K_PAGES)
+#define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN
+#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX
+#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN16_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN
+#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX
+#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT
+#elif defined(CONFIG_ARM64_64K_PAGES)
+#define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN64_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN
+#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX
+#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT
+#endif
+
+#define MVFR2_FPMISC_SHIFT		4
+#define MVFR2_SIMDMISC_SHIFT		0
+
+#define CPACR_EL1_FPEN_EL1EN	(BIT(20)) /* enable EL1 access */
+#define CPACR_EL1_FPEN_EL0EN	(BIT(21)) /* enable EL0 access, if EL1EN set */
+
+#define CPACR_EL1_SMEN_EL1EN	(BIT(24)) /* enable EL1 access */
+#define CPACR_EL1_SMEN_EL0EN	(BIT(25)) /* enable EL0 access, if EL1EN set */
+
+#define CPACR_EL1_ZEN_EL1EN	(BIT(16)) /* enable EL1 access */
+#define CPACR_EL1_ZEN_EL0EN	(BIT(17)) /* enable EL0 access, if EL1EN set */
+
+/* GCR_EL1 Definitions */
+#define SYS_GCR_EL1_RRND	(BIT(16))
+#define SYS_GCR_EL1_EXCL_MASK	0xffffUL
+
+#ifdef CONFIG_KASAN_HW_TAGS
+/*
+ * KASAN always uses a whole byte for its tags. With CONFIG_KASAN_HW_TAGS it
+ * only uses tags in the range 0xF0-0xFF, which we map to MTE tags 0x0-0xF.
+ */
+#define __MTE_TAG_MIN		(KASAN_TAG_MIN & 0xf)
+#define __MTE_TAG_MAX		(KASAN_TAG_MAX & 0xf)
+#define __MTE_TAG_INCL		GENMASK(__MTE_TAG_MAX, __MTE_TAG_MIN)
+#define KERNEL_GCR_EL1_EXCL	(SYS_GCR_EL1_EXCL_MASK & ~__MTE_TAG_INCL)
+#else
+#define KERNEL_GCR_EL1_EXCL	SYS_GCR_EL1_EXCL_MASK
+#endif
+
+#define KERNEL_GCR_EL1		(SYS_GCR_EL1_RRND | KERNEL_GCR_EL1_EXCL)
+
+/* RGSR_EL1 Definitions */
+#define SYS_RGSR_EL1_TAG_MASK	0xfUL
+#define SYS_RGSR_EL1_SEED_SHIFT	8
+#define SYS_RGSR_EL1_SEED_MASK	0xffffUL
+
+/* GMID_EL1 field definitions */
+#define GMID_EL1_BS_SHIFT	0
+#define GMID_EL1_BS_SIZE	4
+
+/* TFSR{,E0}_EL1 bit definitions */
+#define SYS_TFSR_EL1_TF0_SHIFT	0
+#define SYS_TFSR_EL1_TF1_SHIFT	1
+#define SYS_TFSR_EL1_TF0	(UL(1) << SYS_TFSR_EL1_TF0_SHIFT)
+#define SYS_TFSR_EL1_TF1	(UL(1) << SYS_TFSR_EL1_TF1_SHIFT)
+
+/* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
+#define SYS_MPIDR_SAFE_VAL	(BIT(31))
+
+#define TRFCR_ELx_TS_SHIFT		5
+#define TRFCR_ELx_TS_MASK		((0x3UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_ELx_TS_VIRTUAL		((0x1UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_ELx_TS_GUEST_PHYSICAL	((0x2UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_ELx_TS_PHYSICAL		((0x3UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_EL2_CX			BIT(3)
+#define TRFCR_ELx_ExTRE			BIT(1)
+#define TRFCR_ELx_E0TRE			BIT(0)
+
+/* GIC Hypervisor interface registers */
+/* ICH_MISR_EL2 bit definitions */
+#define ICH_MISR_EOI		(1 << 0)
+#define ICH_MISR_U		(1 << 1)
+
+/* ICH_LR*_EL2 bit definitions */
+#define ICH_LR_VIRTUAL_ID_MASK	((1ULL << 32) - 1)
+
+#define ICH_LR_EOI		(1ULL << 41)
+#define ICH_LR_GROUP		(1ULL << 60)
+#define ICH_LR_HW		(1ULL << 61)
+#define ICH_LR_STATE		(3ULL << 62)
+#define ICH_LR_PENDING_BIT	(1ULL << 62)
+#define ICH_LR_ACTIVE_BIT	(1ULL << 63)
+#define ICH_LR_PHYS_ID_SHIFT	32
+#define ICH_LR_PHYS_ID_MASK	(0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PRIORITY_SHIFT	48
+#define ICH_LR_PRIORITY_MASK	(0xffULL << ICH_LR_PRIORITY_SHIFT)
+
+/* ICH_HCR_EL2 bit definitions */
+#define ICH_HCR_EN		(1 << 0)
+#define ICH_HCR_UIE		(1 << 1)
+#define ICH_HCR_NPIE		(1 << 3)
+#define ICH_HCR_TC		(1 << 10)
+#define ICH_HCR_TALL0		(1 << 11)
+#define ICH_HCR_TALL1		(1 << 12)
+#define ICH_HCR_TDIR		(1 << 14)
+#define ICH_HCR_EOIcount_SHIFT	27
+#define ICH_HCR_EOIcount_MASK	(0x1f << ICH_HCR_EOIcount_SHIFT)
+
+/* ICH_VMCR_EL2 bit definitions */
+#define ICH_VMCR_ACK_CTL_SHIFT	2
+#define ICH_VMCR_ACK_CTL_MASK	(1 << ICH_VMCR_ACK_CTL_SHIFT)
+#define ICH_VMCR_FIQ_EN_SHIFT	3
+#define ICH_VMCR_FIQ_EN_MASK	(1 << ICH_VMCR_FIQ_EN_SHIFT)
+#define ICH_VMCR_CBPR_SHIFT	4
+#define ICH_VMCR_CBPR_MASK	(1 << ICH_VMCR_CBPR_SHIFT)
+#define ICH_VMCR_EOIM_SHIFT	9
+#define ICH_VMCR_EOIM_MASK	(1 << ICH_VMCR_EOIM_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT	18
+#define ICH_VMCR_BPR1_MASK	(7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT	21
+#define ICH_VMCR_BPR0_MASK	(7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT	24
+#define ICH_VMCR_PMR_MASK	(0xffUL << ICH_VMCR_PMR_SHIFT)
+#define ICH_VMCR_ENG0_SHIFT	0
+#define ICH_VMCR_ENG0_MASK	(1 << ICH_VMCR_ENG0_SHIFT)
+#define ICH_VMCR_ENG1_SHIFT	1
+#define ICH_VMCR_ENG1_MASK	(1 << ICH_VMCR_ENG1_SHIFT)
+
+/* ICH_VTR_EL2 bit definitions */
+#define ICH_VTR_PRI_BITS_SHIFT	29
+#define ICH_VTR_PRI_BITS_MASK	(7 << ICH_VTR_PRI_BITS_SHIFT)
+#define ICH_VTR_ID_BITS_SHIFT	23
+#define ICH_VTR_ID_BITS_MASK	(7 << ICH_VTR_ID_BITS_SHIFT)
+#define ICH_VTR_SEIS_SHIFT	22
+#define ICH_VTR_SEIS_MASK	(1 << ICH_VTR_SEIS_SHIFT)
+#define ICH_VTR_A3V_SHIFT	21
+#define ICH_VTR_A3V_MASK	(1 << ICH_VTR_A3V_SHIFT)
+#define ICH_VTR_TDS_SHIFT	19
+#define ICH_VTR_TDS_MASK	(1 << ICH_VTR_TDS_SHIFT)
+
+/* HFG[WR]TR_EL2 bit definitions */
+#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT	55
+#define HFGxTR_EL2_nTPIDR2_EL0_MASK	BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT)
+#define HFGxTR_EL2_nSMPRI_EL1_SHIFT	54
+#define HFGxTR_EL2_nSMPRI_EL1_MASK	BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT)
+
+#define ARM64_FEATURE_FIELD_BITS	4
+
+/* Create a mask for the feature bits of the specified feature. */
+#define ARM64_FEATURE_MASK(x)	(GENMASK_ULL(x##_SHIFT + ARM64_FEATURE_FIELD_BITS - 1, x##_SHIFT))
+
+#ifdef __ASSEMBLY__
+
+	.macro	mrs_s, rt, sreg
+	 __emit_inst(0xd5200000|(\sreg)|(.L__gpr_num_\rt))
+	.endm
+
+	.macro	msr_s, sreg, rt
+	__emit_inst(0xd5000000|(\sreg)|(.L__gpr_num_\rt))
+	.endm
+
+#else
+
+#include <linux/bitfield.h>
+#include <linux/build_bug.h>
+#include <linux/types.h>
+#include <asm/alternative.h>
+
+#define DEFINE_MRS_S						\
+	__DEFINE_ASM_GPR_NUMS					\
+"	.macro	mrs_s, rt, sreg\n"				\
+	__emit_inst(0xd5200000|(\\sreg)|(.L__gpr_num_\\rt))	\
+"	.endm\n"
+
+#define DEFINE_MSR_S						\
+	__DEFINE_ASM_GPR_NUMS					\
+"	.macro	msr_s, sreg, rt\n"				\
+	__emit_inst(0xd5000000|(\\sreg)|(.L__gpr_num_\\rt))	\
+"	.endm\n"
+
+#define UNDEFINE_MRS_S						\
+"	.purgem	mrs_s\n"
+
+#define UNDEFINE_MSR_S						\
+"	.purgem	msr_s\n"
+
+#define __mrs_s(v, r)						\
+	DEFINE_MRS_S						\
+"	mrs_s " v ", " __stringify(r) "\n"			\
+	UNDEFINE_MRS_S
+
+#define __msr_s(r, v)						\
+	DEFINE_MSR_S						\
+"	msr_s " __stringify(r) ", " v "\n"			\
+	UNDEFINE_MSR_S
+
+/*
+ * Unlike read_cpuid, calls to read_sysreg are never expected to be
+ * optimized away or replaced with synthetic values.
+ */
+#define read_sysreg(r) ({					\
+	u64 __val;						\
+	asm volatile("mrs %0, " __stringify(r) : "=r" (__val));	\
+	__val;							\
+})
+
+/*
+ * The "Z" constraint normally means a zero immediate, but when combined with
+ * the "%x0" template means XZR.
+ */
+#define write_sysreg(v, r) do {					\
+	u64 __val = (u64)(v);					\
+	asm volatile("msr " __stringify(r) ", %x0"		\
+		     : : "rZ" (__val));				\
+} while (0)
+
+/*
+ * For registers without architectural names, or simply unsupported by
+ * GAS.
+ */
+#define read_sysreg_s(r) ({						\
+	u64 __val;							\
+	asm volatile(__mrs_s("%0", r) : "=r" (__val));			\
+	__val;								\
+})
+
+#define write_sysreg_s(v, r) do {					\
+	u64 __val = (u64)(v);						\
+	asm volatile(__msr_s(r, "%x0") : : "rZ" (__val));		\
+} while (0)
+
+/*
+ * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the
+ * set mask are set. Other bits are left as-is.
+ */
+#define sysreg_clear_set(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg(__scs_new, sysreg);			\
+} while (0)
+
+#define sysreg_clear_set_s(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg_s(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg_s(__scs_new, sysreg);			\
+} while (0)
+
+#define read_sysreg_par() ({						\
+	u64 par;							\
+	asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412));	\
+	par = read_sysreg(par_el1);					\
+	asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412));	\
+	par;								\
+})
+
+#define SYS_FIELD_GET(reg, field, val)		\
+		 FIELD_GET(reg##_##field##_MASK, val)
+
+#define SYS_FIELD_PREP(reg, field, val)		\
+		 FIELD_PREP(reg##_##field##_MASK, val)
+
+#define SYS_FIELD_PREP_ENUM(reg, field, val)		\
+		 FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val)
+
+#endif
+
+#endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
new file mode 100644
index 000000000..c34344256
--- /dev/null
+++ b/arch/arm64/include/asm/system_misc.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/system_misc.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_SYSTEM_MISC_H
+#define __ASM_SYSTEM_MISC_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/irqflags.h>
+#include <linux/signal.h>
+#include <linux/ratelimit.h>
+#include <linux/reboot.h>
+
+struct pt_regs;
+
+void die(const char *msg, struct pt_regs *regs, long err);
+
+struct siginfo;
+void arm64_notify_die(const char *str, struct pt_regs *regs,
+		      int signo, int sicode, unsigned long far,
+		      unsigned long err);
+
+void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long,
+					     struct pt_regs *),
+			   int sig, int code, const char *name);
+
+struct mm_struct;
+extern void __show_regs(struct pt_regs *);
+
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
new file mode 100644
index 000000000..848739c15
--- /dev/null
+++ b/arch/arm64/include/asm/thread_info.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/thread_info.h
+ *
+ * Copyright (C) 2002 Russell King.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_THREAD_INFO_H
+#define __ASM_THREAD_INFO_H
+
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+#include <asm/memory.h>
+#include <asm/stack_pointer.h>
+#include <asm/types.h>
+
+/*
+ * low level task data that entry.S needs immediate access to.
+ */
+struct thread_info {
+	unsigned long		flags;		/* low level flags */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	u64			ttbr0;		/* saved TTBR0_EL1 */
+#endif
+	union {
+		u64		preempt_count;	/* 0 => preemptible, <0 => bug */
+		struct {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+			u32	need_resched;
+			u32	count;
+#else
+			u32	count;
+			u32	need_resched;
+#endif
+		} preempt;
+	};
+#ifdef CONFIG_SHADOW_CALL_STACK
+	void			*scs_base;
+	void			*scs_sp;
+#endif
+	u32			cpu;
+};
+
+#define thread_saved_pc(tsk)	\
+	((unsigned long)(tsk->thread.cpu_context.pc))
+#define thread_saved_sp(tsk)	\
+	((unsigned long)(tsk->thread.cpu_context.sp))
+#define thread_saved_fp(tsk)	\
+	((unsigned long)(tsk->thread.cpu_context.fp))
+
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec     arch_setup_new_exec
+
+void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst,
+				struct task_struct *src);
+
+#endif
+
+#define TIF_SIGPENDING		0	/* signal pending */
+#define TIF_NEED_RESCHED	1	/* rescheduling necessary */
+#define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
+#define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
+#define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
+#define TIF_MTE_ASYNC_FAULT	5	/* MTE Asynchronous Tag Check Fault */
+#define TIF_NOTIFY_SIGNAL	6	/* signal notifications exist */
+#define TIF_SYSCALL_TRACE	8	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
+#define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
+#define TIF_SECCOMP		11	/* syscall secure computing */
+#define TIF_SYSCALL_EMU		12	/* syscall emulation active */
+#define TIF_MEMDIE		18	/* is terminating due to OOM killer */
+#define TIF_FREEZE		19
+#define TIF_RESTORE_SIGMASK	20
+#define TIF_SINGLESTEP		21
+#define TIF_32BIT		22	/* 32bit process */
+#define TIF_SVE			23	/* Scalable Vector Extension in use */
+#define TIF_SVE_VL_INHERIT	24	/* Inherit SVE vl_onexec across exec */
+#define TIF_SSBD		25	/* Wants SSB mitigation */
+#define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
+#define TIF_SME			27	/* SME in use */
+#define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
+
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_32BIT		(1 << TIF_32BIT)
+#define _TIF_SVE		(1 << TIF_SVE)
+#define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
+#define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
+
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
+				 _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \
+				 _TIF_NOTIFY_SIGNAL)
+
+#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
+				 _TIF_SYSCALL_EMU)
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+#define INIT_SCS							\
+	.scs_base	= init_shadow_call_stack,			\
+	.scs_sp		= init_shadow_call_stack,
+#else
+#define INIT_SCS
+#endif
+
+#define INIT_THREAD_INFO(tsk)						\
+{									\
+	.flags		= _TIF_FOREIGN_FPSTATE,				\
+	.preempt_count	= INIT_PREEMPT_COUNT,				\
+	INIT_SCS							\
+}
+
+#endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/timex.h b/arch/arm64/include/asm/timex.h
new file mode 100644
index 000000000..cf59ce91b
--- /dev/null
+++ b/arch/arm64/include/asm/timex.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_TIMEX_H
+#define __ASM_TIMEX_H
+
+#include <asm/arch_timer.h>
+
+/*
+ * Use the current timer as a cycle counter since this is what we use for
+ * the delay loop.
+ */
+#define get_cycles()	arch_timer_read_counter()
+
+#include <asm-generic/timex.h>
+
+#endif
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
new file mode 100644
index 000000000..c995d1f45
--- /dev/null
+++ b/arch/arm64/include/asm/tlb.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/tlb.h
+ *
+ * Copyright (C) 2002 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_TLB_H
+#define __ASM_TLB_H
+
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+static inline void __tlb_remove_table(void *_table)
+{
+	free_page_and_swap_cache((struct page *)_table);
+}
+
+#define tlb_flush tlb_flush
+static void tlb_flush(struct mmu_gather *tlb);
+
+#include <asm-generic/tlb.h>
+
+/*
+ * get the tlbi levels in arm64.  Default value is 0 if more than one
+ * of cleared_* is set or neither is set.
+ * Arm64 doesn't support p4ds now.
+ */
+static inline int tlb_get_level(struct mmu_gather *tlb)
+{
+	/* The TTL field is only valid for the leaf entry. */
+	if (tlb->freed_tables)
+		return 0;
+
+	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 3;
+
+	if (tlb->cleared_pmds && !(tlb->cleared_ptes ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 2;
+
+	if (tlb->cleared_puds && !(tlb->cleared_ptes ||
+				   tlb->cleared_pmds ||
+				   tlb->cleared_p4ds))
+		return 1;
+
+	return 0;
+}
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
+	bool last_level = !tlb->freed_tables;
+	unsigned long stride = tlb_get_unmap_size(tlb);
+	int tlb_level = tlb_get_level(tlb);
+
+	/*
+	 * If we're tearing down the address space then we only care about
+	 * invalidating the walk-cache, since the ASID allocator won't
+	 * reallocate our ASID without invalidating the entire TLB.
+	 */
+	if (tlb->fullmm) {
+		if (!last_level)
+			flush_tlb_mm(tlb->mm);
+		return;
+	}
+
+	__flush_tlb_range(&vma, tlb->start, tlb->end, stride,
+			  last_level, tlb_level);
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+				  unsigned long addr)
+{
+	pgtable_pte_page_dtor(pte);
+	tlb_remove_table(tlb, pte);
+}
+
+#if CONFIG_PGTABLE_LEVELS > 2
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr)
+{
+	struct page *page = virt_to_page(pmdp);
+
+	pgtable_pmd_page_dtor(page);
+	tlb_remove_table(tlb, page);
+}
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 3
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
+				  unsigned long addr)
+{
+	tlb_remove_table(tlb, virt_to_page(pudp));
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
new file mode 100644
index 000000000..412a3b9a3
--- /dev/null
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -0,0 +1,408 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/tlbflush.h
+ *
+ * Copyright (C) 1999-2003 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_TLBFLUSH_H
+#define __ASM_TLBFLUSH_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/bitfield.h>
+#include <linux/mm_types.h>
+#include <linux/sched.h>
+#include <asm/cputype.h>
+#include <asm/mmu.h>
+
+/*
+ * Raw TLBI operations.
+ *
+ * Where necessary, use the __tlbi() macro to avoid asm()
+ * boilerplate. Drivers and most kernel code should use the TLB
+ * management routines in preference to the macro below.
+ *
+ * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
+ * on whether a particular TLBI operation takes an argument or
+ * not. The macros handles invoking the asm with or without the
+ * register argument as appropriate.
+ */
+#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op "\n"				       \
+		   ALTERNATIVE("nop\n			nop",		       \
+			       "dsb ish\n		tlbi " #op,	       \
+			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
+			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
+			    : : )
+
+#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
+			       "tlbi " #op ", %0\n"			       \
+		   ALTERNATIVE("nop\n			nop",		       \
+			       "dsb ish\n		tlbi " #op ", %0",     \
+			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
+			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
+			    : : "r" (arg))
+
+#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
+
+#define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)
+
+#define __tlbi_user(op, arg) do {						\
+	if (arm64_kernel_unmapped_at_el0())					\
+		__tlbi(op, (arg) | USER_ASID_FLAG);				\
+} while (0)
+
+/* This macro creates a properly formatted VA operand for the TLBI */
+#define __TLBI_VADDR(addr, asid)				\
+	({							\
+		unsigned long __ta = (addr) >> 12;		\
+		__ta &= GENMASK_ULL(43, 0);			\
+		__ta |= (unsigned long)(asid) << 48;		\
+		__ta;						\
+	})
+
+/*
+ * Get translation granule of the system, which is decided by
+ * PAGE_SIZE.  Used by TTL.
+ *  - 4KB	: 1
+ *  - 16KB	: 2
+ *  - 64KB	: 3
+ */
+#define TLBI_TTL_TG_4K		1
+#define TLBI_TTL_TG_16K		2
+#define TLBI_TTL_TG_64K		3
+
+static inline unsigned long get_trans_granule(void)
+{
+	switch (PAGE_SIZE) {
+	case SZ_4K:
+		return TLBI_TTL_TG_4K;
+	case SZ_16K:
+		return TLBI_TTL_TG_16K;
+	case SZ_64K:
+		return TLBI_TTL_TG_64K;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * Level-based TLBI operations.
+ *
+ * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
+ * the level at which the invalidation must take place. If the level is
+ * wrong, no invalidation may take place. In the case where the level
+ * cannot be easily determined, a 0 value for the level parameter will
+ * perform a non-hinted invalidation.
+ *
+ * For Stage-2 invalidation, use the level values provided to that effect
+ * in asm/stage2_pgtable.h.
+ */
+#define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
+
+#define __tlbi_level(op, addr, level) do {				\
+	u64 arg = addr;							\
+									\
+	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
+	    level) {							\
+		u64 ttl = level & 3;					\
+		ttl |= get_trans_granule() << 2;			\
+		arg &= ~TLBI_TTL_MASK;					\
+		arg |= FIELD_PREP(TLBI_TTL_MASK, ttl);			\
+	}								\
+									\
+	__tlbi(op, arg);						\
+} while(0)
+
+#define __tlbi_user_level(op, arg, level) do {				\
+	if (arm64_kernel_unmapped_at_el0())				\
+		__tlbi_level(op, (arg | USER_ASID_FLAG), level);	\
+} while (0)
+
+/*
+ * This macro creates a properly formatted VA operand for the TLB RANGE.
+ * The value bit assignments are:
+ *
+ * +----------+------+-------+-------+-------+----------------------+
+ * |   ASID   |  TG  | SCALE |  NUM  |  TTL  |        BADDR         |
+ * +-----------------+-------+-------+-------+----------------------+
+ * |63      48|47  46|45   44|43   39|38   37|36                   0|
+ *
+ * The address range is determined by below formula:
+ * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
+ *
+ */
+#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)		\
+	({							\
+		unsigned long __ta = (addr) >> PAGE_SHIFT;	\
+		__ta &= GENMASK_ULL(36, 0);			\
+		__ta |= (unsigned long)(ttl) << 37;		\
+		__ta |= (unsigned long)(num) << 39;		\
+		__ta |= (unsigned long)(scale) << 44;		\
+		__ta |= get_trans_granule() << 46;		\
+		__ta |= (unsigned long)(asid) << 48;		\
+		__ta;						\
+	})
+
+/* These macros are used by the TLBI RANGE feature. */
+#define __TLBI_RANGE_PAGES(num, scale)	\
+	((unsigned long)((num) + 1) << (5 * (scale) + 1))
+#define MAX_TLBI_RANGE_PAGES		__TLBI_RANGE_PAGES(31, 3)
+
+/*
+ * Generate 'num' values from -1 to 30 with -1 rejected by the
+ * __flush_tlb_range() loop below.
+ */
+#define TLBI_RANGE_MASK			GENMASK_ULL(4, 0)
+#define __TLBI_RANGE_NUM(pages, scale)	\
+	((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1)
+
+/*
+ *	TLB Invalidation
+ *	================
+ *
+ * 	This header file implements the low-level TLB invalidation routines
+ *	(sometimes referred to as "flushing" in the kernel) for arm64.
+ *
+ *	Every invalidation operation uses the following template:
+ *
+ *	DSB ISHST	// Ensure prior page-table updates have completed
+ *	TLBI ...	// Invalidate the TLB
+ *	DSB ISH		// Ensure the TLB invalidation has completed
+ *      if (invalidated kernel mappings)
+ *		ISB	// Discard any instructions fetched from the old mapping
+ *
+ *
+ *	The following functions form part of the "core" TLB invalidation API,
+ *	as documented in Documentation/core-api/cachetlb.rst:
+ *
+ *	flush_tlb_all()
+ *		Invalidate the entire TLB (kernel + user) on all CPUs
+ *
+ *	flush_tlb_mm(mm)
+ *		Invalidate an entire user address space on all CPUs.
+ *		The 'mm' argument identifies the ASID to invalidate.
+ *
+ *	flush_tlb_range(vma, start, end)
+ *		Invalidate the virtual-address range '[start, end)' on all
+ *		CPUs for the user address space corresponding to 'vma->mm'.
+ *		Note that this operation also invalidates any walk-cache
+ *		entries associated with translations for the specified address
+ *		range.
+ *
+ *	flush_tlb_kernel_range(start, end)
+ *		Same as flush_tlb_range(..., start, end), but applies to
+ * 		kernel mappings rather than a particular user address space.
+ *		Whilst not explicitly documented, this function is used when
+ *		unmapping pages from vmalloc/io space.
+ *
+ *	flush_tlb_page(vma, addr)
+ *		Invalidate a single user mapping for address 'addr' in the
+ *		address space corresponding to 'vma->mm'.  Note that this
+ *		operation only invalidates a single, last-level page-table
+ *		entry and therefore does not affect any walk-caches.
+ *
+ *
+ *	Next, we have some undocumented invalidation routines that you probably
+ *	don't want to call unless you know what you're doing:
+ *
+ *	local_flush_tlb_all()
+ *		Same as flush_tlb_all(), but only applies to the calling CPU.
+ *
+ *	__flush_tlb_kernel_pgtable(addr)
+ *		Invalidate a single kernel mapping for address 'addr' on all
+ *		CPUs, ensuring that any walk-cache entries associated with the
+ *		translation are also invalidated.
+ *
+ *	__flush_tlb_range(vma, start, end, stride, last_level)
+ *		Invalidate the virtual-address range '[start, end)' on all
+ *		CPUs for the user address space corresponding to 'vma->mm'.
+ *		The invalidation operations are issued at a granularity
+ *		determined by 'stride' and only affect any walk-cache entries
+ *		if 'last_level' is equal to false.
+ *
+ *
+ *	Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
+ *	on top of these routines, since that is our interface to the mmu_gather
+ *	API as used by munmap() and friends.
+ */
+static inline void local_flush_tlb_all(void)
+{
+	dsb(nshst);
+	__tlbi(vmalle1);
+	dsb(nsh);
+	isb();
+}
+
+static inline void flush_tlb_all(void)
+{
+	dsb(ishst);
+	__tlbi(vmalle1is);
+	dsb(ish);
+	isb();
+}
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	unsigned long asid;
+
+	dsb(ishst);
+	asid = __TLBI_VADDR(0, ASID(mm));
+	__tlbi(aside1is, asid);
+	__tlbi_user(aside1is, asid);
+	dsb(ish);
+}
+
+static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
+					 unsigned long uaddr)
+{
+	unsigned long addr;
+
+	dsb(ishst);
+	addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm));
+	__tlbi(vale1is, addr);
+	__tlbi_user(vale1is, addr);
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long uaddr)
+{
+	flush_tlb_page_nosync(vma, uaddr);
+	dsb(ish);
+}
+
+/*
+ * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
+ * necessarily a performance improvement.
+ */
+#define MAX_TLBI_OPS	PTRS_PER_PTE
+
+static inline void __flush_tlb_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end,
+				     unsigned long stride, bool last_level,
+				     int tlb_level)
+{
+	int num = 0;
+	int scale = 0;
+	unsigned long asid, addr, pages;
+
+	start = round_down(start, stride);
+	end = round_up(end, stride);
+	pages = (end - start) >> PAGE_SHIFT;
+
+	/*
+	 * When not uses TLB range ops, we can handle up to
+	 * (MAX_TLBI_OPS - 1) pages;
+	 * When uses TLB range ops, we can handle up to
+	 * (MAX_TLBI_RANGE_PAGES - 1) pages.
+	 */
+	if ((!system_supports_tlb_range() &&
+	     (end - start) >= (MAX_TLBI_OPS * stride)) ||
+	    pages >= MAX_TLBI_RANGE_PAGES) {
+		flush_tlb_mm(vma->vm_mm);
+		return;
+	}
+
+	dsb(ishst);
+	asid = ASID(vma->vm_mm);
+
+	/*
+	 * When the CPU does not support TLB range operations, flush the TLB
+	 * entries one by one at the granularity of 'stride'. If the TLB
+	 * range ops are supported, then:
+	 *
+	 * 1. If 'pages' is odd, flush the first page through non-range
+	 *    operations;
+	 *
+	 * 2. For remaining pages: the minimum range granularity is decided
+	 *    by 'scale', so multiple range TLBI operations may be required.
+	 *    Start from scale = 0, flush the corresponding number of pages
+	 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
+	 *    until no pages left.
+	 *
+	 * Note that certain ranges can be represented by either num = 31 and
+	 * scale or num = 0 and scale + 1. The loop below favours the latter
+	 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+	 */
+	while (pages > 0) {
+		if (!system_supports_tlb_range() ||
+		    pages % 2 == 1) {
+			addr = __TLBI_VADDR(start, asid);
+			if (last_level) {
+				__tlbi_level(vale1is, addr, tlb_level);
+				__tlbi_user_level(vale1is, addr, tlb_level);
+			} else {
+				__tlbi_level(vae1is, addr, tlb_level);
+				__tlbi_user_level(vae1is, addr, tlb_level);
+			}
+			start += stride;
+			pages -= stride >> PAGE_SHIFT;
+			continue;
+		}
+
+		num = __TLBI_RANGE_NUM(pages, scale);
+		if (num >= 0) {
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,
+						  num, tlb_level);
+			if (last_level) {
+				__tlbi(rvale1is, addr);
+				__tlbi_user(rvale1is, addr);
+			} else {
+				__tlbi(rvae1is, addr);
+				__tlbi_user(rvae1is, addr);
+			}
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
+			pages -= __TLBI_RANGE_PAGES(num, scale);
+		}
+		scale++;
+	}
+	dsb(ish);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	/*
+	 * We cannot use leaf-only invalidation here, since we may be invalidating
+	 * table entries as part of collapsing hugepages or moving page tables.
+	 * Set the tlb_level to 0 because we can not get enough information here.
+	 */
+	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	if ((end - start) > (MAX_TLBI_OPS * PAGE_SIZE)) {
+		flush_tlb_all();
+		return;
+	}
+
+	start = __TLBI_VADDR(start, 0);
+	end = __TLBI_VADDR(end, 0);
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+		__tlbi(vaale1is, addr);
+	dsb(ish);
+	isb();
+}
+
+/*
+ * Used to invalidate the TLB (walk caches) corresponding to intermediate page
+ * table levels (pgd/pud/pmd).
+ */
+static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
+{
+	unsigned long addr = __TLBI_VADDR(kaddr, 0);
+
+	dsb(ishst);
+	__tlbi(vaae1is, addr);
+	dsb(ish);
+	isb();
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 000000000..9fab663dd
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_NUMA
+
+struct pci_bus;
+int pcibus_to_node(struct pci_bus *bus);
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+
+#endif /* CONFIG_NUMA */
+
+#include <linux/arch_topology.h>
+
+void update_freq_counters_refs(void);
+
+/* Replace task scheduler's default frequency-invariant accounting */
+#define arch_scale_freq_tick topology_scale_freq_tick
+#define arch_set_freq_scale topology_set_freq_scale
+#define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
+
+#ifdef CONFIG_ACPI_CPPC_LIB
+#define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
+#endif
+
+/* Replace task scheduler's default cpu-invariant accounting */
+#define arch_scale_cpu_capacity topology_get_cpu_scale
+
+/* Enable topology flag updates */
+#define arch_update_cpu_topology topology_update_cpu_topology
+
+/* Replace task scheduler's default thermal pressure API */
+#define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_update_thermal_pressure	topology_update_thermal_pressure
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/trans_pgd.h b/arch/arm64/include/asm/trans_pgd.h
new file mode 100644
index 000000000..033d400a4
--- /dev/null
+++ b/arch/arm64/include/asm/trans_pgd.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+#ifndef _ASM_TRANS_TABLE_H
+#define _ASM_TRANS_TABLE_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+#include <asm/pgtable-types.h>
+
+/*
+ * trans_alloc_page
+ *	- Allocator that should return exactly one zeroed page, if this
+ *	  allocator fails, trans_pgd_create_copy() and trans_pgd_idmap_page()
+ *	  return -ENOMEM error.
+ *
+ * trans_alloc_arg
+ *	- Passed to trans_alloc_page as an argument
+ */
+
+struct trans_pgd_info {
+	void * (*trans_alloc_page)(void *arg);
+	void *trans_alloc_arg;
+};
+
+int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **trans_pgd,
+			  unsigned long start, unsigned long end);
+
+int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0,
+			 unsigned long *t0sz, void *page);
+
+int trans_pgd_copy_el2_vectors(struct trans_pgd_info *info,
+			       phys_addr_t *el2_vectors);
+
+extern char trans_pgd_stub_vectors[];
+
+#endif /* _ASM_TRANS_TABLE_H */
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
new file mode 100644
index 000000000..6e5826470
--- /dev/null
+++ b/arch/arm64/include/asm/traps.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/traps.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_TRAP_H
+#define __ASM_TRAP_H
+
+#include <linux/list.h>
+#include <asm/esr.h>
+#include <asm/sections.h>
+
+struct pt_regs;
+
+struct undef_hook {
+	struct list_head node;
+	u32 instr_mask;
+	u32 instr_val;
+	u64 pstate_mask;
+	u64 pstate_val;
+	int (*fn)(struct pt_regs *regs, u32 instr);
+};
+
+void register_undef_hook(struct undef_hook *hook);
+void unregister_undef_hook(struct undef_hook *hook);
+void force_signal_inject(int signal, int code, unsigned long address, unsigned long err);
+void arm64_notify_segfault(unsigned long addr);
+void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str);
+void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str);
+void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str);
+
+/*
+ * Move regs->pc to next instruction and do necessary setup before it
+ * is executed.
+ */
+void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size);
+
+static inline int __in_irqentry_text(unsigned long ptr)
+{
+	return ptr >= (unsigned long)&__irqentry_text_start &&
+	       ptr < (unsigned long)&__irqentry_text_end;
+}
+
+static inline int in_entry_text(unsigned long ptr)
+{
+	return ptr >= (unsigned long)&__entry_text_start &&
+	       ptr < (unsigned long)&__entry_text_end;
+}
+
+/*
+ * CPUs with the RAS extensions have an Implementation-Defined-Syndrome bit
+ * to indicate whether this ESR has a RAS encoding. CPUs without this feature
+ * have a ISS-Valid bit in the same position.
+ * If this bit is set, we know its not a RAS SError.
+ * If its clear, we need to know if the CPU supports RAS. Uncategorized RAS
+ * errors share the same encoding as an all-zeros encoding from a CPU that
+ * doesn't support RAS.
+ */
+static inline bool arm64_is_ras_serror(unsigned long esr)
+{
+	WARN_ON(preemptible());
+
+	if (esr & ESR_ELx_IDS)
+		return false;
+
+	if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN))
+		return true;
+	else
+		return false;
+}
+
+/*
+ * Return the AET bits from a RAS SError's ESR.
+ *
+ * It is implementation defined whether Uncategorized errors are containable.
+ * We treat them as Uncontainable.
+ * Non-RAS SError's are reported as Uncontained/Uncategorized.
+ */
+static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr)
+{
+	unsigned long aet = esr & ESR_ELx_AET;
+
+	if (!arm64_is_ras_serror(esr)) {
+		/* Not a RAS error, we can't interpret the ESR. */
+		return ESR_ELx_AET_UC;
+	}
+
+	/*
+	 * AET is RES0 if 'the value returned in the DFSC field is not
+	 * [ESR_ELx_FSC_SERROR]'
+	 */
+	if ((esr & ESR_ELx_FSC) != ESR_ELx_FSC_SERROR) {
+		/* No severity information : Uncategorized */
+		return ESR_ELx_AET_UC;
+	}
+
+	return aet;
+}
+
+bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr);
+void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr);
+#endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
new file mode 100644
index 000000000..5c7b2f9d5
--- /dev/null
+++ b/arch/arm64/include/asm/uaccess.h
@@ -0,0 +1,478 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Based on arch/arm/include/asm/uaccess.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef __ASM_UACCESS_H
+#define __ASM_UACCESS_H
+
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+
+/*
+ * User space memory access functions
+ */
+#include <linux/bitops.h>
+#include <linux/kasan-checks.h>
+#include <linux/string.h>
+
+#include <asm/asm-extable.h>
+#include <asm/cpufeature.h>
+#include <asm/mmu.h>
+#include <asm/mte.h>
+#include <asm/ptrace.h>
+#include <asm/memory.h>
+#include <asm/extable.h>
+
+static inline int __access_ok(const void __user *ptr, unsigned long size);
+
+/*
+ * Test whether a block of memory is a valid user space address.
+ * Returns 1 if the range is valid, 0 otherwise.
+ *
+ * This is equivalent to the following test:
+ * (u65)addr + (u65)size <= (u65)TASK_SIZE_MAX
+ */
+static inline int access_ok(const void __user *addr, unsigned long size)
+{
+	/*
+	 * Asynchronous I/O running in a kernel thread does not have the
+	 * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag
+	 * the user address before checking.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) &&
+	    (current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR)))
+		addr = untagged_addr(addr);
+
+	return likely(__access_ok(addr, size));
+}
+#define access_ok access_ok
+
+#include <asm-generic/access_ok.h>
+
+/*
+ * User access enabling/disabling.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void __uaccess_ttbr0_disable(void)
+{
+	unsigned long flags, ttbr;
+
+	local_irq_save(flags);
+	ttbr = read_sysreg(ttbr1_el1);
+	ttbr &= ~TTBR_ASID_MASK;
+	/* reserved_pg_dir placed before swapper_pg_dir */
+	write_sysreg(ttbr - RESERVED_SWAPPER_OFFSET, ttbr0_el1);
+	isb();
+	/* Set reserved ASID */
+	write_sysreg(ttbr, ttbr1_el1);
+	isb();
+	local_irq_restore(flags);
+}
+
+static inline void __uaccess_ttbr0_enable(void)
+{
+	unsigned long flags, ttbr0, ttbr1;
+
+	/*
+	 * Disable interrupts to avoid preemption between reading the 'ttbr0'
+	 * variable and the MSR. A context switch could trigger an ASID
+	 * roll-over and an update of 'ttbr0'.
+	 */
+	local_irq_save(flags);
+	ttbr0 = READ_ONCE(current_thread_info()->ttbr0);
+
+	/* Restore active ASID */
+	ttbr1 = read_sysreg(ttbr1_el1);
+	ttbr1 &= ~TTBR_ASID_MASK;		/* safety measure */
+	ttbr1 |= ttbr0 & TTBR_ASID_MASK;
+	write_sysreg(ttbr1, ttbr1_el1);
+	isb();
+
+	/* Restore user page table */
+	write_sysreg(ttbr0, ttbr0_el1);
+	isb();
+	local_irq_restore(flags);
+}
+
+static inline bool uaccess_ttbr0_disable(void)
+{
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_disable();
+	return true;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_enable();
+	return true;
+}
+#else
+static inline bool uaccess_ttbr0_disable(void)
+{
+	return false;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	return false;
+}
+#endif
+
+static inline void __uaccess_disable_hw_pan(void)
+{
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+}
+
+static inline void __uaccess_enable_hw_pan(void)
+{
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+			CONFIG_ARM64_PAN));
+}
+
+/*
+ * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0
+ * affects EL0 and TCF affects EL1 irrespective of which TTBR is
+ * used.
+ * The kernel accesses TTBR0 usually with LDTR/STTR instructions
+ * when UAO is available, so these would act as EL0 accesses using
+ * TCF0.
+ * However futex.h code uses exclusives which would be executed as
+ * EL1, this can potentially cause a tag check fault even if the
+ * user disables TCF0.
+ *
+ * To address the problem we set the PSTATE.TCO bit in uaccess_enable()
+ * and reset it in uaccess_disable().
+ *
+ * The Tag check override (TCO) bit disables temporarily the tag checking
+ * preventing the issue.
+ */
+static inline void __uaccess_disable_tco(void)
+{
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+static inline void __uaccess_enable_tco(void)
+{
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+/*
+ * These functions disable tag checking only if in MTE async mode
+ * since the sync mode generates exceptions synchronously and the
+ * nofault or load_unaligned_zeropad can handle them.
+ */
+static inline void __uaccess_disable_tco_async(void)
+{
+	if (system_uses_mte_async_or_asymm_mode())
+		 __uaccess_disable_tco();
+}
+
+static inline void __uaccess_enable_tco_async(void)
+{
+	if (system_uses_mte_async_or_asymm_mode())
+		__uaccess_enable_tco();
+}
+
+static inline void uaccess_disable_privileged(void)
+{
+	__uaccess_disable_tco();
+
+	if (uaccess_ttbr0_disable())
+		return;
+
+	__uaccess_enable_hw_pan();
+}
+
+static inline void uaccess_enable_privileged(void)
+{
+	__uaccess_enable_tco();
+
+	if (uaccess_ttbr0_enable())
+		return;
+
+	__uaccess_disable_hw_pan();
+}
+
+/*
+ * Sanitize a uaccess pointer such that it cannot reach any kernel address.
+ *
+ * Clearing bit 55 ensures the pointer cannot address any portion of the TTBR1
+ * address range (i.e. any kernel address), and either the pointer falls within
+ * the TTBR0 address range or must cause a fault.
+ */
+#define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
+static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
+{
+	void __user *safe_ptr;
+
+	asm volatile(
+	"	bic	%0, %1, %2\n"
+	: "=r" (safe_ptr)
+	: "r" (ptr),
+	  "i" (BIT(55))
+	);
+
+	return safe_ptr;
+}
+
+/*
+ * The "__xxx" versions of the user access functions do not verify the address
+ * space - it must have been done previously with a separate "access_ok()"
+ * call.
+ *
+ * The "__xxx_error" versions set the third argument to -EFAULT if an error
+ * occurs, and leave it unchanged on success.
+ */
+#define __get_mem_asm(load, reg, x, addr, err, type)			\
+	asm volatile(							\
+	"1:	" load "	" reg "1, [%2]\n"			\
+	"2:\n"								\
+	_ASM_EXTABLE_##type##ACCESS_ERR_ZERO(1b, 2b, %w0, %w1)		\
+	: "+r" (err), "=&r" (x)						\
+	: "r" (addr))
+
+#define __raw_get_mem(ldr, x, ptr, err, type)					\
+do {										\
+	unsigned long __gu_val;							\
+	switch (sizeof(*(ptr))) {						\
+	case 1:									\
+		__get_mem_asm(ldr "b", "%w", __gu_val, (ptr), (err), type);	\
+		break;								\
+	case 2:									\
+		__get_mem_asm(ldr "h", "%w", __gu_val, (ptr), (err), type);	\
+		break;								\
+	case 4:									\
+		__get_mem_asm(ldr, "%w", __gu_val, (ptr), (err), type);		\
+		break;								\
+	case 8:									\
+		__get_mem_asm(ldr, "%x",  __gu_val, (ptr), (err), type);	\
+		break;								\
+	default:								\
+		BUILD_BUG();							\
+	}									\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
+} while (0)
+
+/*
+ * We must not call into the scheduler between uaccess_ttbr0_enable() and
+ * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions,
+ * we must evaluate these outside of the critical section.
+ */
+#define __raw_get_user(x, ptr, err)					\
+do {									\
+	__typeof__(*(ptr)) __user *__rgu_ptr = (ptr);			\
+	__typeof__(x) __rgu_val;					\
+	__chk_user_ptr(ptr);						\
+									\
+	uaccess_ttbr0_enable();						\
+	__raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err, U);		\
+	uaccess_ttbr0_disable();					\
+									\
+	(x) = __rgu_val;						\
+} while (0)
+
+#define __get_user_error(x, ptr, err)					\
+do {									\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(__p, sizeof(*__p))) {				\
+		__p = uaccess_mask_ptr(__p);				\
+		__raw_get_user((x), __p, (err));			\
+	} else {							\
+		(x) = (__force __typeof__(x))0; (err) = -EFAULT;	\
+	}								\
+} while (0)
+
+#define __get_user(x, ptr)						\
+({									\
+	int __gu_err = 0;						\
+	__get_user_error((x), (ptr), __gu_err);				\
+	__gu_err;							\
+})
+
+#define get_user	__get_user
+
+/*
+ * We must not call into the scheduler between __uaccess_enable_tco_async() and
+ * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	__typeof__(dst) __gkn_dst = (dst);				\
+	__typeof__(src) __gkn_src = (src);				\
+	int __gkn_err = 0;						\
+									\
+	__uaccess_enable_tco_async();					\
+	__raw_get_mem("ldr", *((type *)(__gkn_dst)),			\
+		      (__force type *)(__gkn_src), __gkn_err, K);	\
+	__uaccess_disable_tco_async();					\
+									\
+	if (unlikely(__gkn_err))					\
+		goto err_label;						\
+} while (0)
+
+#define __put_mem_asm(store, reg, x, addr, err, type)			\
+	asm volatile(							\
+	"1:	" store "	" reg "1, [%2]\n"			\
+	"2:\n"								\
+	_ASM_EXTABLE_##type##ACCESS_ERR(1b, 2b, %w0)			\
+	: "+r" (err)							\
+	: "r" (x), "r" (addr))
+
+#define __raw_put_mem(str, x, ptr, err, type)					\
+do {										\
+	__typeof__(*(ptr)) __pu_val = (x);					\
+	switch (sizeof(*(ptr))) {						\
+	case 1:									\
+		__put_mem_asm(str "b", "%w", __pu_val, (ptr), (err), type);	\
+		break;								\
+	case 2:									\
+		__put_mem_asm(str "h", "%w", __pu_val, (ptr), (err), type);	\
+		break;								\
+	case 4:									\
+		__put_mem_asm(str, "%w", __pu_val, (ptr), (err), type);		\
+		break;								\
+	case 8:									\
+		__put_mem_asm(str, "%x", __pu_val, (ptr), (err), type);		\
+		break;								\
+	default:								\
+		BUILD_BUG();							\
+	}									\
+} while (0)
+
+/*
+ * We must not call into the scheduler between uaccess_ttbr0_enable() and
+ * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions,
+ * we must evaluate these outside of the critical section.
+ */
+#define __raw_put_user(x, ptr, err)					\
+do {									\
+	__typeof__(*(ptr)) __user *__rpu_ptr = (ptr);			\
+	__typeof__(*(ptr)) __rpu_val = (x);				\
+	__chk_user_ptr(__rpu_ptr);					\
+									\
+	uaccess_ttbr0_enable();						\
+	__raw_put_mem("sttr", __rpu_val, __rpu_ptr, err, U);		\
+	uaccess_ttbr0_disable();					\
+} while (0)
+
+#define __put_user_error(x, ptr, err)					\
+do {									\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(__p, sizeof(*__p))) {				\
+		__p = uaccess_mask_ptr(__p);				\
+		__raw_put_user((x), __p, (err));			\
+	} else	{							\
+		(err) = -EFAULT;					\
+	}								\
+} while (0)
+
+#define __put_user(x, ptr)						\
+({									\
+	int __pu_err = 0;						\
+	__put_user_error((x), (ptr), __pu_err);				\
+	__pu_err;							\
+})
+
+#define put_user	__put_user
+
+/*
+ * We must not call into the scheduler between __uaccess_enable_tco_async() and
+ * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	__typeof__(dst) __pkn_dst = (dst);				\
+	__typeof__(src) __pkn_src = (src);				\
+	int __pkn_err = 0;						\
+									\
+	__uaccess_enable_tco_async();					\
+	__raw_put_mem("str", *((type *)(__pkn_src)),			\
+		      (__force type *)(__pkn_dst), __pkn_err, K);	\
+	__uaccess_disable_tco_async();					\
+									\
+	if (unlikely(__pkn_err))					\
+		goto err_label;						\
+} while(0)
+
+extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
+#define raw_copy_from_user(to, from, n)					\
+({									\
+	unsigned long __acfu_ret;					\
+	uaccess_ttbr0_enable();						\
+	__acfu_ret = __arch_copy_from_user((to),			\
+				      __uaccess_mask_ptr(from), (n));	\
+	uaccess_ttbr0_disable();					\
+	__acfu_ret;							\
+})
+
+extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
+#define raw_copy_to_user(to, from, n)					\
+({									\
+	unsigned long __actu_ret;					\
+	uaccess_ttbr0_enable();						\
+	__actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to),	\
+				    (from), (n));			\
+	uaccess_ttbr0_disable();					\
+	__actu_ret;							\
+})
+
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
+
+extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n);
+static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n)
+{
+	if (access_ok(to, n)) {
+		uaccess_ttbr0_enable();
+		n = __arch_clear_user(__uaccess_mask_ptr(to), n);
+		uaccess_ttbr0_disable();
+	}
+	return n;
+}
+#define clear_user	__clear_user
+
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern __must_check long strnlen_user(const char __user *str, long n);
+
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+struct page;
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len);
+extern unsigned long __must_check __copy_user_flushcache(void *to, const void __user *from, unsigned long n);
+
+static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
+{
+	kasan_check_write(dst, size);
+	return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size);
+}
+#endif
+
+#ifdef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
+
+/*
+ * Return 0 on success, the number of bytes not probed otherwise.
+ */
+static inline size_t probe_subpage_writeable(const char __user *uaddr,
+					     size_t size)
+{
+	if (!system_supports_mte())
+		return 0;
+	return mte_probe_user_range(uaddr, size);
+}
+
+#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
+
+#endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
new file mode 100644
index 000000000..037feba03
--- /dev/null
+++ b/arch/arm64/include/asm/unistd.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifdef CONFIG_COMPAT
+#define __ARCH_WANT_COMPAT_STAT
+#define __ARCH_WANT_COMPAT_STAT64
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_COMPAT_SYS_SENDFILE
+#define __ARCH_WANT_SYS_UTIME32
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_SYS_VFORK
+
+/*
+ * Compat syscall numbers used by the AArch64 kernel.
+ */
+#define __NR_compat_restart_syscall	0
+#define __NR_compat_exit		1
+#define __NR_compat_read		3
+#define __NR_compat_write		4
+#define __NR_compat_gettimeofday	78
+#define __NR_compat_sigreturn		119
+#define __NR_compat_rt_sigreturn	173
+#define __NR_compat_clock_gettime	263
+#define __NR_compat_clock_getres	264
+#define __NR_compat_clock_gettime64	403
+#define __NR_compat_clock_getres_time64	406
+
+/*
+ * The following SVCs are ARM private.
+ */
+#define __ARM_NR_COMPAT_BASE		0x0f0000
+#define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE + 2)
+#define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
+#define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
+
+#define __NR_compat_syscalls		451
+#endif
+
+#define __ARCH_WANT_SYS_CLONE
+
+#ifndef __COMPAT_SYSCALL_NR
+#include <uapi/asm/unistd.h>
+#endif
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
new file mode 100644
index 000000000..604a2053d
--- /dev/null
+++ b/arch/arm64/include/asm/unistd32.h
@@ -0,0 +1,914 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AArch32 (compat) system call definitions.
+ *
+ * Copyright (C) 2001-2005 Russell King
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#define __NR_restart_syscall 0
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_exit 1
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_fork 2
+__SYSCALL(__NR_fork, sys_fork)
+#define __NR_read 3
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 4
+__SYSCALL(__NR_write, sys_write)
+#define __NR_open 5
+__SYSCALL(__NR_open, compat_sys_open)
+#define __NR_close 6
+__SYSCALL(__NR_close, sys_close)
+			/* 7 was sys_waitpid */
+__SYSCALL(7, sys_ni_syscall)
+#define __NR_creat 8
+__SYSCALL(__NR_creat, sys_creat)
+#define __NR_link 9
+__SYSCALL(__NR_link, sys_link)
+#define __NR_unlink 10
+__SYSCALL(__NR_unlink, sys_unlink)
+#define __NR_execve 11
+__SYSCALL(__NR_execve, compat_sys_execve)
+#define __NR_chdir 12
+__SYSCALL(__NR_chdir, sys_chdir)
+			/* 13 was sys_time */
+__SYSCALL(13, sys_ni_syscall)
+#define __NR_mknod 14
+__SYSCALL(__NR_mknod, sys_mknod)
+#define __NR_chmod 15
+__SYSCALL(__NR_chmod, sys_chmod)
+#define __NR_lchown 16
+__SYSCALL(__NR_lchown, sys_lchown16)
+			/* 17 was sys_break */
+__SYSCALL(17, sys_ni_syscall)
+			/* 18 was sys_stat */
+__SYSCALL(18, sys_ni_syscall)
+#define __NR_lseek 19
+__SYSCALL(__NR_lseek, compat_sys_lseek)
+#define __NR_getpid 20
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_mount 21
+__SYSCALL(__NR_mount, sys_mount)
+			/* 22 was sys_umount */
+__SYSCALL(22, sys_ni_syscall)
+#define __NR_setuid 23
+__SYSCALL(__NR_setuid, sys_setuid16)
+#define __NR_getuid 24
+__SYSCALL(__NR_getuid, sys_getuid16)
+			/* 25 was sys_stime */
+__SYSCALL(25, sys_ni_syscall)
+#define __NR_ptrace 26
+__SYSCALL(__NR_ptrace, compat_sys_ptrace)
+			/* 27 was sys_alarm */
+__SYSCALL(27, sys_ni_syscall)
+			/* 28 was sys_fstat */
+__SYSCALL(28, sys_ni_syscall)
+#define __NR_pause 29
+__SYSCALL(__NR_pause, sys_pause)
+			/* 30 was sys_utime */
+__SYSCALL(30, sys_ni_syscall)
+			/* 31 was sys_stty */
+__SYSCALL(31, sys_ni_syscall)
+			/* 32 was sys_gtty */
+__SYSCALL(32, sys_ni_syscall)
+#define __NR_access 33
+__SYSCALL(__NR_access, sys_access)
+#define __NR_nice 34
+__SYSCALL(__NR_nice, sys_nice)
+			/* 35 was sys_ftime */
+__SYSCALL(35, sys_ni_syscall)
+#define __NR_sync 36
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_kill 37
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_rename 38
+__SYSCALL(__NR_rename, sys_rename)
+#define __NR_mkdir 39
+__SYSCALL(__NR_mkdir, sys_mkdir)
+#define __NR_rmdir 40
+__SYSCALL(__NR_rmdir, sys_rmdir)
+#define __NR_dup 41
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_pipe 42
+__SYSCALL(__NR_pipe, sys_pipe)
+#define __NR_times 43
+__SYSCALL(__NR_times, compat_sys_times)
+			/* 44 was sys_prof */
+__SYSCALL(44, sys_ni_syscall)
+#define __NR_brk 45
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_setgid 46
+__SYSCALL(__NR_setgid, sys_setgid16)
+#define __NR_getgid 47
+__SYSCALL(__NR_getgid, sys_getgid16)
+			/* 48 was sys_signal */
+__SYSCALL(48, sys_ni_syscall)
+#define __NR_geteuid 49
+__SYSCALL(__NR_geteuid, sys_geteuid16)
+#define __NR_getegid 50
+__SYSCALL(__NR_getegid, sys_getegid16)
+#define __NR_acct 51
+__SYSCALL(__NR_acct, sys_acct)
+#define __NR_umount2 52
+__SYSCALL(__NR_umount2, sys_umount)
+			/* 53 was sys_lock */
+__SYSCALL(53, sys_ni_syscall)
+#define __NR_ioctl 54
+__SYSCALL(__NR_ioctl, compat_sys_ioctl)
+#define __NR_fcntl 55
+__SYSCALL(__NR_fcntl, compat_sys_fcntl)
+			/* 56 was sys_mpx */
+__SYSCALL(56, sys_ni_syscall)
+#define __NR_setpgid 57
+__SYSCALL(__NR_setpgid, sys_setpgid)
+			/* 58 was sys_ulimit */
+__SYSCALL(58, sys_ni_syscall)
+			/* 59 was sys_olduname */
+__SYSCALL(59, sys_ni_syscall)
+#define __NR_umask 60
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_chroot 61
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_ustat 62
+__SYSCALL(__NR_ustat, compat_sys_ustat)
+#define __NR_dup2 63
+__SYSCALL(__NR_dup2, sys_dup2)
+#define __NR_getppid 64
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getpgrp 65
+__SYSCALL(__NR_getpgrp, sys_getpgrp)
+#define __NR_setsid 66
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_sigaction 67
+__SYSCALL(__NR_sigaction, compat_sys_sigaction)
+			/* 68 was sys_sgetmask */
+__SYSCALL(68, sys_ni_syscall)
+			/* 69 was sys_ssetmask */
+__SYSCALL(69, sys_ni_syscall)
+#define __NR_setreuid 70
+__SYSCALL(__NR_setreuid, sys_setreuid16)
+#define __NR_setregid 71
+__SYSCALL(__NR_setregid, sys_setregid16)
+#define __NR_sigsuspend 72
+__SYSCALL(__NR_sigsuspend, sys_sigsuspend)
+#define __NR_sigpending 73
+__SYSCALL(__NR_sigpending, compat_sys_sigpending)
+#define __NR_sethostname 74
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setrlimit 75
+__SYSCALL(__NR_setrlimit, compat_sys_setrlimit)
+			/* 76 was compat_sys_getrlimit */
+__SYSCALL(76, sys_ni_syscall)
+#define __NR_getrusage 77
+__SYSCALL(__NR_getrusage, compat_sys_getrusage)
+#define __NR_gettimeofday 78
+__SYSCALL(__NR_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 79
+__SYSCALL(__NR_settimeofday, compat_sys_settimeofday)
+#define __NR_getgroups 80
+__SYSCALL(__NR_getgroups, sys_getgroups16)
+#define __NR_setgroups 81
+__SYSCALL(__NR_setgroups, sys_setgroups16)
+			/* 82 was compat_sys_select */
+__SYSCALL(82, sys_ni_syscall)
+#define __NR_symlink 83
+__SYSCALL(__NR_symlink, sys_symlink)
+			/* 84 was sys_lstat */
+__SYSCALL(84, sys_ni_syscall)
+#define __NR_readlink 85
+__SYSCALL(__NR_readlink, sys_readlink)
+#define __NR_uselib 86
+__SYSCALL(__NR_uselib, sys_uselib)
+#define __NR_swapon 87
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_reboot 88
+__SYSCALL(__NR_reboot, sys_reboot)
+			/* 89 was sys_readdir */
+__SYSCALL(89, sys_ni_syscall)
+			/* 90 was sys_mmap */
+__SYSCALL(90, sys_ni_syscall)
+#define __NR_munmap 91
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_truncate 92
+__SYSCALL(__NR_truncate, compat_sys_truncate)
+#define __NR_ftruncate 93
+__SYSCALL(__NR_ftruncate, compat_sys_ftruncate)
+#define __NR_fchmod 94
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchown 95
+__SYSCALL(__NR_fchown, sys_fchown16)
+#define __NR_getpriority 96
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_setpriority 97
+__SYSCALL(__NR_setpriority, sys_setpriority)
+			/* 98 was sys_profil */
+__SYSCALL(98, sys_ni_syscall)
+#define __NR_statfs 99
+__SYSCALL(__NR_statfs, compat_sys_statfs)
+#define __NR_fstatfs 100
+__SYSCALL(__NR_fstatfs, compat_sys_fstatfs)
+			/* 101 was sys_ioperm */
+__SYSCALL(101, sys_ni_syscall)
+			/* 102 was sys_socketcall */
+__SYSCALL(102, sys_ni_syscall)
+#define __NR_syslog 103
+__SYSCALL(__NR_syslog, sys_syslog)
+#define __NR_setitimer 104
+__SYSCALL(__NR_setitimer, compat_sys_setitimer)
+#define __NR_getitimer 105
+__SYSCALL(__NR_getitimer, compat_sys_getitimer)
+#define __NR_stat 106
+__SYSCALL(__NR_stat, compat_sys_newstat)
+#define __NR_lstat 107
+__SYSCALL(__NR_lstat, compat_sys_newlstat)
+#define __NR_fstat 108
+__SYSCALL(__NR_fstat, compat_sys_newfstat)
+			/* 109 was sys_uname */
+__SYSCALL(109, sys_ni_syscall)
+			/* 110 was sys_iopl */
+__SYSCALL(110, sys_ni_syscall)
+#define __NR_vhangup 111
+__SYSCALL(__NR_vhangup, sys_vhangup)
+			/* 112 was sys_idle */
+__SYSCALL(112, sys_ni_syscall)
+			/* 113 was sys_syscall */
+__SYSCALL(113, sys_ni_syscall)
+#define __NR_wait4 114
+__SYSCALL(__NR_wait4, compat_sys_wait4)
+#define __NR_swapoff 115
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_sysinfo 116
+__SYSCALL(__NR_sysinfo, compat_sys_sysinfo)
+			/* 117 was sys_ipc */
+__SYSCALL(117, sys_ni_syscall)
+#define __NR_fsync 118
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_sigreturn 119
+__SYSCALL(__NR_sigreturn, compat_sys_sigreturn)
+#define __NR_clone 120
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_setdomainname 121
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_uname 122
+__SYSCALL(__NR_uname, sys_newuname)
+			/* 123 was sys_modify_ldt */
+__SYSCALL(123, sys_ni_syscall)
+#define __NR_adjtimex 124
+__SYSCALL(__NR_adjtimex, sys_adjtimex_time32)
+#define __NR_mprotect 125
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_sigprocmask 126
+__SYSCALL(__NR_sigprocmask, compat_sys_sigprocmask)
+			/* 127 was sys_create_module */
+__SYSCALL(127, sys_ni_syscall)
+#define __NR_init_module 128
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 129
+__SYSCALL(__NR_delete_module, sys_delete_module)
+			/* 130 was sys_get_kernel_syms */
+__SYSCALL(130, sys_ni_syscall)
+#define __NR_quotactl 131
+__SYSCALL(__NR_quotactl, sys_quotactl)
+#define __NR_getpgid 132
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_fchdir 133
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_bdflush 134
+__SYSCALL(__NR_bdflush, sys_ni_syscall)
+#define __NR_sysfs 135
+__SYSCALL(__NR_sysfs, sys_sysfs)
+#define __NR_personality 136
+__SYSCALL(__NR_personality, sys_personality)
+			/* 137 was sys_afs_syscall */
+__SYSCALL(137, sys_ni_syscall)
+#define __NR_setfsuid 138
+__SYSCALL(__NR_setfsuid, sys_setfsuid16)
+#define __NR_setfsgid 139
+__SYSCALL(__NR_setfsgid, sys_setfsgid16)
+#define __NR__llseek 140
+__SYSCALL(__NR__llseek, sys_llseek)
+#define __NR_getdents 141
+__SYSCALL(__NR_getdents, compat_sys_getdents)
+#define __NR__newselect 142
+__SYSCALL(__NR__newselect, compat_sys_select)
+#define __NR_flock 143
+__SYSCALL(__NR_flock, sys_flock)
+#define __NR_msync 144
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_readv 145
+__SYSCALL(__NR_readv, sys_readv)
+#define __NR_writev 146
+__SYSCALL(__NR_writev, sys_writev)
+#define __NR_getsid 147
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_fdatasync 148
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+			/* 149 was sys_sysctl */
+__SYSCALL(149, sys_ni_syscall)
+#define __NR_mlock 150
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 151
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 152
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 153
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_sched_setparam 154
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_getparam 155
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setscheduler 156
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 157
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_yield 158
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 159
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 160
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 161
+__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32)
+#define __NR_nanosleep 162
+__SYSCALL(__NR_nanosleep, sys_nanosleep_time32)
+#define __NR_mremap 163
+__SYSCALL(__NR_mremap, sys_mremap)
+#define __NR_setresuid 164
+__SYSCALL(__NR_setresuid, sys_setresuid16)
+#define __NR_getresuid 165
+__SYSCALL(__NR_getresuid, sys_getresuid16)
+			/* 166 was sys_vm86 */
+__SYSCALL(166, sys_ni_syscall)
+			/* 167 was sys_query_module */
+__SYSCALL(167, sys_ni_syscall)
+#define __NR_poll 168
+__SYSCALL(__NR_poll, sys_poll)
+#define __NR_nfsservctl 169
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+#define __NR_setresgid 170
+__SYSCALL(__NR_setresgid, sys_setresgid16)
+#define __NR_getresgid 171
+__SYSCALL(__NR_getresgid, sys_getresgid16)
+#define __NR_prctl 172
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_rt_sigreturn 173
+__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn)
+#define __NR_rt_sigaction 174
+__SYSCALL(__NR_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 175
+__SYSCALL(__NR_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 176
+__SYSCALL(__NR_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 177
+__SYSCALL(__NR_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32)
+#define __NR_rt_sigqueueinfo 178
+__SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigsuspend 179
+__SYSCALL(__NR_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_pread64 180
+__SYSCALL(__NR_pread64, compat_sys_aarch32_pread64)
+#define __NR_pwrite64 181
+__SYSCALL(__NR_pwrite64, compat_sys_aarch32_pwrite64)
+#define __NR_chown 182
+__SYSCALL(__NR_chown, sys_chown16)
+#define __NR_getcwd 183
+__SYSCALL(__NR_getcwd, sys_getcwd)
+#define __NR_capget 184
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 185
+__SYSCALL(__NR_capset, sys_capset)
+#define __NR_sigaltstack 186
+__SYSCALL(__NR_sigaltstack, compat_sys_sigaltstack)
+#define __NR_sendfile 187
+__SYSCALL(__NR_sendfile, compat_sys_sendfile)
+			/* 188 reserved */
+__SYSCALL(188, sys_ni_syscall)
+			/* 189 reserved */
+__SYSCALL(189, sys_ni_syscall)
+#define __NR_vfork 190
+__SYSCALL(__NR_vfork, sys_vfork)
+#define __NR_ugetrlimit 191	/* SuS compliant getrlimit */
+__SYSCALL(__NR_ugetrlimit, compat_sys_getrlimit)		/* SuS compliant getrlimit */
+#define __NR_mmap2 192
+__SYSCALL(__NR_mmap2, compat_sys_aarch32_mmap2)
+#define __NR_truncate64 193
+__SYSCALL(__NR_truncate64, compat_sys_aarch32_truncate64)
+#define __NR_ftruncate64 194
+__SYSCALL(__NR_ftruncate64, compat_sys_aarch32_ftruncate64)
+#define __NR_stat64 195
+__SYSCALL(__NR_stat64, sys_stat64)
+#define __NR_lstat64 196
+__SYSCALL(__NR_lstat64, sys_lstat64)
+#define __NR_fstat64 197
+__SYSCALL(__NR_fstat64, sys_fstat64)
+#define __NR_lchown32 198
+__SYSCALL(__NR_lchown32, sys_lchown)
+#define __NR_getuid32 199
+__SYSCALL(__NR_getuid32, sys_getuid)
+#define __NR_getgid32 200
+__SYSCALL(__NR_getgid32, sys_getgid)
+#define __NR_geteuid32 201
+__SYSCALL(__NR_geteuid32, sys_geteuid)
+#define __NR_getegid32 202
+__SYSCALL(__NR_getegid32, sys_getegid)
+#define __NR_setreuid32 203
+__SYSCALL(__NR_setreuid32, sys_setreuid)
+#define __NR_setregid32 204
+__SYSCALL(__NR_setregid32, sys_setregid)
+#define __NR_getgroups32 205
+__SYSCALL(__NR_getgroups32, sys_getgroups)
+#define __NR_setgroups32 206
+__SYSCALL(__NR_setgroups32, sys_setgroups)
+#define __NR_fchown32 207
+__SYSCALL(__NR_fchown32, sys_fchown)
+#define __NR_setresuid32 208
+__SYSCALL(__NR_setresuid32, sys_setresuid)
+#define __NR_getresuid32 209
+__SYSCALL(__NR_getresuid32, sys_getresuid)
+#define __NR_setresgid32 210
+__SYSCALL(__NR_setresgid32, sys_setresgid)
+#define __NR_getresgid32 211
+__SYSCALL(__NR_getresgid32, sys_getresgid)
+#define __NR_chown32 212
+__SYSCALL(__NR_chown32, sys_chown)
+#define __NR_setuid32 213
+__SYSCALL(__NR_setuid32, sys_setuid)
+#define __NR_setgid32 214
+__SYSCALL(__NR_setgid32, sys_setgid)
+#define __NR_setfsuid32 215
+__SYSCALL(__NR_setfsuid32, sys_setfsuid)
+#define __NR_setfsgid32 216
+__SYSCALL(__NR_setfsgid32, sys_setfsgid)
+#define __NR_getdents64 217
+__SYSCALL(__NR_getdents64, sys_getdents64)
+#define __NR_pivot_root 218
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+#define __NR_mincore 219
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 220
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_fcntl64 221
+__SYSCALL(__NR_fcntl64, compat_sys_fcntl64)
+			/* 222 for tux */
+__SYSCALL(222, sys_ni_syscall)
+			/* 223 is unused */
+__SYSCALL(223, sys_ni_syscall)
+#define __NR_gettid 224
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_readahead 225
+__SYSCALL(__NR_readahead, compat_sys_aarch32_readahead)
+#define __NR_setxattr 226
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 227
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 228
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 229
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 230
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 231
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 232
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 233
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 234
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 235
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 236
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 237
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+#define __NR_tkill 238
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_sendfile64 239
+__SYSCALL(__NR_sendfile64, sys_sendfile64)
+#define __NR_futex 240
+__SYSCALL(__NR_futex, sys_futex_time32)
+#define __NR_sched_setaffinity 241
+__SYSCALL(__NR_sched_setaffinity, compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 242
+__SYSCALL(__NR_sched_getaffinity, compat_sys_sched_getaffinity)
+#define __NR_io_setup 243
+__SYSCALL(__NR_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 244
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_getevents 245
+__SYSCALL(__NR_io_getevents, sys_io_getevents_time32)
+#define __NR_io_submit 246
+__SYSCALL(__NR_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 247
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_exit_group 248
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_lookup_dcookie 249
+__SYSCALL(__NR_lookup_dcookie, compat_sys_lookup_dcookie)
+#define __NR_epoll_create 250
+__SYSCALL(__NR_epoll_create, sys_epoll_create)
+#define __NR_epoll_ctl 251
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_wait 252
+__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
+#define __NR_remap_file_pages 253
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+			/* 254 for set_thread_area */
+__SYSCALL(254, sys_ni_syscall)
+			/* 255 for get_thread_area */
+__SYSCALL(255, sys_ni_syscall)
+#define __NR_set_tid_address 256
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_timer_create 257
+__SYSCALL(__NR_timer_create, compat_sys_timer_create)
+#define __NR_timer_settime 258
+__SYSCALL(__NR_timer_settime, sys_timer_settime32)
+#define __NR_timer_gettime 259
+__SYSCALL(__NR_timer_gettime, sys_timer_gettime32)
+#define __NR_timer_getoverrun 260
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_delete 261
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 262
+__SYSCALL(__NR_clock_settime, sys_clock_settime32)
+#define __NR_clock_gettime 263
+__SYSCALL(__NR_clock_gettime, sys_clock_gettime32)
+#define __NR_clock_getres 264
+__SYSCALL(__NR_clock_getres, sys_clock_getres_time32)
+#define __NR_clock_nanosleep 265
+__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep_time32)
+#define __NR_statfs64 266
+__SYSCALL(__NR_statfs64, compat_sys_aarch32_statfs64)
+#define __NR_fstatfs64 267
+__SYSCALL(__NR_fstatfs64, compat_sys_aarch32_fstatfs64)
+#define __NR_tgkill 268
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_utimes 269
+__SYSCALL(__NR_utimes, sys_utimes_time32)
+#define __NR_arm_fadvise64_64 270
+__SYSCALL(__NR_arm_fadvise64_64, compat_sys_aarch32_fadvise64_64)
+#define __NR_pciconfig_iobase 271
+__SYSCALL(__NR_pciconfig_iobase, sys_pciconfig_iobase)
+#define __NR_pciconfig_read 272
+__SYSCALL(__NR_pciconfig_read, sys_pciconfig_read)
+#define __NR_pciconfig_write 273
+__SYSCALL(__NR_pciconfig_write, sys_pciconfig_write)
+#define __NR_mq_open 274
+__SYSCALL(__NR_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 275
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 276
+__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend_time32)
+#define __NR_mq_timedreceive 277
+__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive_time32)
+#define __NR_mq_notify 278
+__SYSCALL(__NR_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 279
+__SYSCALL(__NR_mq_getsetattr, compat_sys_mq_getsetattr)
+#define __NR_waitid 280
+__SYSCALL(__NR_waitid, compat_sys_waitid)
+#define __NR_socket 281
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_bind 282
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_connect 283
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_listen 284
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 285
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_getsockname 286
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 287
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_socketpair 288
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_send 289
+__SYSCALL(__NR_send, sys_send)
+#define __NR_sendto 290
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recv 291
+__SYSCALL(__NR_recv, compat_sys_recv)
+#define __NR_recvfrom 292
+__SYSCALL(__NR_recvfrom, compat_sys_recvfrom)
+#define __NR_shutdown 293
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_setsockopt 294
+__SYSCALL(__NR_setsockopt, sys_setsockopt)
+#define __NR_getsockopt 295
+__SYSCALL(__NR_getsockopt, sys_getsockopt)
+#define __NR_sendmsg 296
+__SYSCALL(__NR_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 297
+__SYSCALL(__NR_recvmsg, compat_sys_recvmsg)
+#define __NR_semop 298
+__SYSCALL(__NR_semop, sys_semop)
+#define __NR_semget 299
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 300
+__SYSCALL(__NR_semctl, compat_sys_old_semctl)
+#define __NR_msgsnd 301
+__SYSCALL(__NR_msgsnd, compat_sys_msgsnd)
+#define __NR_msgrcv 302
+__SYSCALL(__NR_msgrcv, compat_sys_msgrcv)
+#define __NR_msgget 303
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 304
+__SYSCALL(__NR_msgctl, compat_sys_old_msgctl)
+#define __NR_shmat 305
+__SYSCALL(__NR_shmat, compat_sys_shmat)
+#define __NR_shmdt 306
+__SYSCALL(__NR_shmdt, sys_shmdt)
+#define __NR_shmget 307
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 308
+__SYSCALL(__NR_shmctl, compat_sys_old_shmctl)
+#define __NR_add_key 309
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 310
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 311
+__SYSCALL(__NR_keyctl, compat_sys_keyctl)
+#define __NR_semtimedop 312
+__SYSCALL(__NR_semtimedop, sys_semtimedop_time32)
+#define __NR_vserver 313
+__SYSCALL(__NR_vserver, sys_ni_syscall)
+#define __NR_ioprio_set 314
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 315
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+#define __NR_inotify_init 316
+__SYSCALL(__NR_inotify_init, sys_inotify_init)
+#define __NR_inotify_add_watch 317
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 318
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_mbind 319
+__SYSCALL(__NR_mbind, sys_mbind)
+#define __NR_get_mempolicy 320
+__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
+#define __NR_set_mempolicy 321
+__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
+#define __NR_openat 322
+__SYSCALL(__NR_openat, compat_sys_openat)
+#define __NR_mkdirat 323
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_mknodat 324
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_fchownat 325
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_futimesat 326
+__SYSCALL(__NR_futimesat, sys_futimesat_time32)
+#define __NR_fstatat64 327
+__SYSCALL(__NR_fstatat64, sys_fstatat64)
+#define __NR_unlinkat 328
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_renameat 329
+__SYSCALL(__NR_renameat, sys_renameat)
+#define __NR_linkat 330
+__SYSCALL(__NR_linkat, sys_linkat)
+#define __NR_symlinkat 331
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_readlinkat 332
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR_fchmodat 333
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_faccessat 334
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_pselect6 335
+__SYSCALL(__NR_pselect6, compat_sys_pselect6_time32)
+#define __NR_ppoll 336
+__SYSCALL(__NR_ppoll, compat_sys_ppoll_time32)
+#define __NR_unshare 337
+__SYSCALL(__NR_unshare, sys_unshare)
+#define __NR_set_robust_list 338
+__SYSCALL(__NR_set_robust_list, compat_sys_set_robust_list)
+#define __NR_get_robust_list 339
+__SYSCALL(__NR_get_robust_list, compat_sys_get_robust_list)
+#define __NR_splice 340
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_sync_file_range2 341
+__SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2)
+#define __NR_tee 342
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_vmsplice 343
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
+#define __NR_move_pages 344
+__SYSCALL(__NR_move_pages, sys_move_pages)
+#define __NR_getcpu 345
+__SYSCALL(__NR_getcpu, sys_getcpu)
+#define __NR_epoll_pwait 346
+__SYSCALL(__NR_epoll_pwait, compat_sys_epoll_pwait)
+#define __NR_kexec_load 347
+__SYSCALL(__NR_kexec_load, compat_sys_kexec_load)
+#define __NR_utimensat 348
+__SYSCALL(__NR_utimensat, sys_utimensat_time32)
+#define __NR_signalfd 349
+__SYSCALL(__NR_signalfd, compat_sys_signalfd)
+#define __NR_timerfd_create 350
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_eventfd 351
+__SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate 352
+__SYSCALL(__NR_fallocate, compat_sys_aarch32_fallocate)
+#define __NR_timerfd_settime 353
+__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime32)
+#define __NR_timerfd_gettime 354
+__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime32)
+#define __NR_signalfd4 355
+__SYSCALL(__NR_signalfd4, compat_sys_signalfd4)
+#define __NR_eventfd2 356
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+#define __NR_epoll_create1 357
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_dup3 358
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR_pipe2 359
+__SYSCALL(__NR_pipe2, sys_pipe2)
+#define __NR_inotify_init1 360
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_preadv 361
+__SYSCALL(__NR_preadv, compat_sys_preadv)
+#define __NR_pwritev 362
+__SYSCALL(__NR_pwritev, compat_sys_pwritev)
+#define __NR_rt_tgsigqueueinfo 363
+__SYSCALL(__NR_rt_tgsigqueueinfo, compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 364
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_recvmmsg 365
+__SYSCALL(__NR_recvmmsg, compat_sys_recvmmsg_time32)
+#define __NR_accept4 366
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_fanotify_init 367
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 368
+__SYSCALL(__NR_fanotify_mark, compat_sys_fanotify_mark)
+#define __NR_prlimit64 369
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_name_to_handle_at 370
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 371
+__SYSCALL(__NR_open_by_handle_at, compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 372
+__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime32)
+#define __NR_syncfs 373
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_sendmmsg 374
+__SYSCALL(__NR_sendmmsg, compat_sys_sendmmsg)
+#define __NR_setns 375
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_process_vm_readv 376
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
+#define __NR_process_vm_writev 377
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
+#define __NR_kcmp 378
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 379
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 380
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 381
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 382
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 383
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 384
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 385
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 386
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 387
+__SYSCALL(__NR_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 388
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 389
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 390
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 391
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 392
+__SYSCALL(__NR_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 393
+__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 394
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 395
+__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
+#define __NR_pkey_free 396
+__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 397
+__SYSCALL(__NR_statx, sys_statx)
+#define __NR_rseq 398
+__SYSCALL(__NR_rseq, sys_rseq)
+#define __NR_io_pgetevents 399
+__SYSCALL(__NR_io_pgetevents, compat_sys_io_pgetevents)
+#define __NR_migrate_pages 400
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
+#define __NR_kexec_file_load 401
+__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
+/* 402 is unused */
+#define __NR_clock_gettime64 403
+__SYSCALL(__NR_clock_gettime64, sys_clock_gettime)
+#define __NR_clock_settime64 404
+__SYSCALL(__NR_clock_settime64, sys_clock_settime)
+#define __NR_clock_adjtime64 405
+__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime)
+#define __NR_clock_getres_time64 406
+__SYSCALL(__NR_clock_getres_time64, sys_clock_getres)
+#define __NR_clock_nanosleep_time64 407
+__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep)
+#define __NR_timer_gettime64 408
+__SYSCALL(__NR_timer_gettime64, sys_timer_gettime)
+#define __NR_timer_settime64 409
+__SYSCALL(__NR_timer_settime64, sys_timer_settime)
+#define __NR_timerfd_gettime64 410
+__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime)
+#define __NR_timerfd_settime64 411
+__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime)
+#define __NR_utimensat_time64 412
+__SYSCALL(__NR_utimensat_time64, sys_utimensat)
+#define __NR_pselect6_time64 413
+__SYSCALL(__NR_pselect6_time64, compat_sys_pselect6_time64)
+#define __NR_ppoll_time64 414
+__SYSCALL(__NR_ppoll_time64, compat_sys_ppoll_time64)
+#define __NR_io_pgetevents_time64 416
+__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+#define __NR_recvmmsg_time64 417
+__SYSCALL(__NR_recvmmsg_time64, compat_sys_recvmmsg_time64)
+#define __NR_mq_timedsend_time64 418
+__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend)
+#define __NR_mq_timedreceive_time64 419
+__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive)
+#define __NR_semtimedop_time64 420
+__SYSCALL(__NR_semtimedop_time64, sys_semtimedop)
+#define __NR_rt_sigtimedwait_time64 421
+__SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64)
+#define __NR_futex_time64 422
+__SYSCALL(__NR_futex_time64, sys_futex)
+#define __NR_sched_rr_get_interval_time64 423
+__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+#define __NR_open_tree 428
+__SYSCALL(__NR_open_tree, sys_open_tree)
+#define __NR_move_mount 429
+__SYSCALL(__NR_move_mount, sys_move_mount)
+#define __NR_fsopen 430
+__SYSCALL(__NR_fsopen, sys_fsopen)
+#define __NR_fsconfig 431
+__SYSCALL(__NR_fsconfig, sys_fsconfig)
+#define __NR_fsmount 432
+__SYSCALL(__NR_fsmount, sys_fsmount)
+#define __NR_fspick 433
+__SYSCALL(__NR_fspick, sys_fspick)
+#define __NR_pidfd_open 434
+__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+#define __NR_clone3 435
+__SYSCALL(__NR_clone3, sys_clone3)
+#define __NR_close_range 436
+__SYSCALL(__NR_close_range, sys_close_range)
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2)
+#define __NR_mount_setattr 442
+__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
+#define __NR_quotactl_fd 443
+__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd)
+#define __NR_landlock_create_ruleset 444
+__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
+#define __NR_landlock_add_rule 445
+__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
+#define __NR_landlock_restrict_self 446
+__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+#define __NR_process_mrelease 448
+__SYSCALL(__NR_process_mrelease, sys_process_mrelease)
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+
+/*
+ * Please add new compat syscalls above this comment and update
+ * __NR_compat_syscalls in asm/unistd.h.
+ */
diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
new file mode 100644
index 000000000..315eef654
--- /dev/null
+++ b/arch/arm64/include/asm/uprobes.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
+ */
+
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
+#include <asm/probes.h>
+
+#define MAX_UINSN_BYTES		AARCH64_INSN_SIZE
+
+#define UPROBE_SWBP_INSN	BRK64_OPCODE_UPROBES
+#define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
+#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+
+typedef u32 uprobe_opcode_t;
+
+struct arch_uprobe_task {
+};
+
+struct arch_uprobe {
+	union {
+		u8 insn[MAX_UINSN_BYTES];
+		u8 ixol[MAX_UINSN_BYTES];
+	};
+	struct arch_probe_insn api;
+	bool simulate;
+};
+
+#endif
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
new file mode 100644
index 000000000..b4ae32109
--- /dev/null
+++ b/arch/arm64/include/asm/vdso.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Limited
+ */
+#ifndef __ASM_VDSO_H
+#define __ASM_VDSO_H
+
+/*
+ * Default link address for the vDSO.
+ * Since we randomise the VDSO mapping, there's little point in trying
+ * to prelink this.
+ */
+#define VDSO_LBASE	0x0
+
+#define __VVAR_PAGES    2
+
+#ifndef __ASSEMBLY__
+
+#include <generated/vdso-offsets.h>
+#ifdef CONFIG_COMPAT_VDSO
+#include <generated/vdso32-offsets.h>
+#endif
+
+#define VDSO_SYMBOL(base, name)						   \
+({									   \
+	(void *)(vdso_offset_##name - VDSO_LBASE + (unsigned long)(base)); \
+})
+
+extern char vdso_start[], vdso_end[];
+extern char vdso32_start[], vdso32_end[];
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_H */
diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h
new file mode 100644
index 000000000..b054d9feb
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/clocksource.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+#define VDSO_ARCH_CLOCKMODES					\
+	/* vdso clocksource for both 32 and 64bit tasks */	\
+	VDSO_CLOCKMODE_ARCHTIMER,				\
+	/* vdso clocksource for 64bit tasks only */		\
+	VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT
+
+#endif
diff --git a/arch/arm64/include/asm/vdso/compat_barrier.h b/arch/arm64/include/asm/vdso/compat_barrier.h
new file mode 100644
index 000000000..3ac35f4a6
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/compat_barrier.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __COMPAT_BARRIER_H
+#define __COMPAT_BARRIER_H
+
+#ifndef __ASSEMBLY__
+/*
+ * Warning: This code is meant to be used with
+ * ENABLE_COMPAT_VDSO only.
+ */
+#ifndef ENABLE_COMPAT_VDSO
+#error This header is meant to be used with ENABLE_COMPAT_VDSO only
+#endif
+
+#ifdef dmb
+#undef dmb
+#endif
+
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+
+#define aarch32_smp_mb()	dmb(ish)
+#define aarch32_smp_rmb()	dmb(ishld)
+#define aarch32_smp_wmb()	dmb(ishst)
+
+#undef smp_mb
+#undef smp_rmb
+#undef smp_wmb
+
+#define smp_mb()	aarch32_smp_mb()
+#define smp_rmb()	aarch32_smp_rmb()
+#define smp_wmb()	aarch32_smp_wmb()
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __COMPAT_BARRIER_H */
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
new file mode 100644
index 000000000..ecb6fd4c3
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/barrier.h>
+#include <asm/unistd.h>
+#include <asm/errno.h>
+
+#include <asm/vdso/compat_barrier.h>
+
+#define VDSO_HAS_CLOCK_GETRES		1
+
+#define BUILD_VDSO32			1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			  struct timezone *_tz)
+{
+	register struct timezone *tz asm("r1") = _tz;
+	register struct __kernel_old_timeval *tv asm("r0") = _tv;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_gettimeofday;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (tv), "r" (tz), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_clock_gettime64;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+	register struct old_timespec32 *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_clock_gettime;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_clock_getres_time64;
+
+	asm volatile(
+	"       swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+	register struct old_timespec32 *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_clock_getres;
+
+	asm volatile(
+	"       swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
+{
+	u64 res;
+
+	/*
+	 * Core checks for mode already, so this raced against a concurrent
+	 * update. Return something. Core will do another round and then
+	 * see the mode change and fallback to the syscall.
+	 */
+	if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
+		return 0;
+
+	/*
+	 * This isb() is required to prevent that the counter value
+	 * is speculated.
+	 */
+	isb();
+	asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (res));
+	/*
+	 * This isb() is required to prevent that the seq lock is
+	 * speculated.
+	 */
+	isb();
+
+	return res;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	const struct vdso_data *ret;
+
+	/*
+	 * This simply puts &_vdso_data into ret. The reason why we don't use
+	 * `ret = _vdso_data` is that the compiler tends to optimise this in a
+	 * very suboptimal way: instead of keeping &_vdso_data in a register,
+	 * it goes through a relocation almost every time _vdso_data must be
+	 * accessed (even in subfunctions). This is both time and space
+	 * consuming: each relocation uses a word in the code section, and it
+	 * has to be loaded at runtime.
+	 *
+	 * This trick hides the assignment from the compiler. Since it cannot
+	 * track where the pointer comes from, it will only use one relocation
+	 * where __arch_get_vdso_data() is called, and then keep the result in
+	 * a register.
+	 */
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data));
+
+	return ret;
+}
+
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
+{
+	const struct vdso_data *ret;
+
+	/* See __arch_get_vdso_data(). */
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data));
+
+	return ret;
+}
+#endif
+
+static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+{
+	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
+}
+#define vdso_clocksource_ok	vdso_clocksource_ok
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000..764d13e29
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/alternative.h>
+#include <asm/barrier.h>
+#include <asm/unistd.h>
+#include <asm/sysreg.h>
+
+#define VDSO_HAS_CLOCK_GETRES		1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			  struct timezone *_tz)
+{
+	register struct timezone *tz asm("x1") = _tz;
+	register struct __kernel_old_timeval *tv asm("x0") = _tv;
+	register long ret asm ("x0");
+	register long nr asm("x8") = __NR_gettimeofday;
+
+	asm volatile(
+	"       svc #0\n"
+	: "=r" (ret)
+	: "r" (tv), "r" (tz), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("x1") = _ts;
+	register clockid_t clkid asm("x0") = _clkid;
+	register long ret asm ("x0");
+	register long nr asm("x8") = __NR_clock_gettime;
+
+	asm volatile(
+	"       svc #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("x1") = _ts;
+	register clockid_t clkid asm("x0") = _clkid;
+	register long ret asm ("x0");
+	register long nr asm("x8") = __NR_clock_getres;
+
+	asm volatile(
+	"       svc #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
+						 const struct vdso_data *vd)
+{
+	u64 res;
+
+	/*
+	 * Core checks for mode already, so this raced against a concurrent
+	 * update. Return something. Core will do another round and then
+	 * see the mode change and fallback to the syscall.
+	 */
+	if (clock_mode == VDSO_CLOCKMODE_NONE)
+		return 0;
+
+	/*
+	 * If FEAT_ECV is available, use the self-synchronizing counter.
+	 * Otherwise the isb is required to prevent that the counter value
+	 * is speculated.
+	*/
+	asm volatile(
+	ALTERNATIVE("isb\n"
+		    "mrs %0, cntvct_el0",
+		    "nop\n"
+		    __mrs_s("%0", SYS_CNTVCTSS_EL0),
+		    ARM64_HAS_ECV)
+	: "=r" (res)
+	:
+	: "memory");
+
+	arch_counter_enforce_ordering(res);
+
+	return res;
+}
+
+static __always_inline
+const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return _vdso_data;
+}
+
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
+{
+	return _timens_data;
+}
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/asm/vdso/processor.h b/arch/arm64/include/asm/vdso/processor.h
new file mode 100644
index 000000000..ff830b766
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/processor.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+static inline void cpu_relax(void)
+{
+	asm volatile("yield" ::: "memory");
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000..f94b1457c
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+
+#define VDSO_PRECISION_MASK	~(0xFF00ULL<<48)
+
+extern struct vdso_data *vdso_data;
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__arm64_get_k_vdso_data(void)
+{
+	return vdso_data;
+}
+#define __arch_get_k_vdso_data __arm64_get_k_vdso_data
+
+static __always_inline
+void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
+{
+	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
+	vdata[CS_RAW].mask		= VDSO_PRECISION_MASK;
+}
+#define __arch_update_vsyscall __arm64_update_vsyscall
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
new file mode 100644
index 000000000..bc9a2145f
--- /dev/null
+++ b/arch/arm64/include/asm/vectors.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 ARM Ltd.
+ */
+#ifndef __ASM_VECTORS_H
+#define __ASM_VECTORS_H
+
+#include <linux/bug.h>
+#include <linux/percpu.h>
+
+#include <asm/fixmap.h>
+
+extern char vectors[];
+extern char tramp_vectors[];
+extern char __bp_harden_el1_vectors[];
+
+/*
+ * Note: the order of this enum corresponds to two arrays in entry.S:
+ * tramp_vecs and __bp_harden_el1_vectors. By default the canonical
+ * 'full fat' vectors are used directly.
+ */
+enum arm64_bp_harden_el1_vectors {
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	/*
+	 * Perform the BHB loop mitigation, before branching to the canonical
+	 * vectors.
+	 */
+	EL1_VECTOR_BHB_LOOP,
+
+	/*
+	 * Make the SMC call for firmware mitigation, before branching to the
+	 * canonical vectors.
+	 */
+	EL1_VECTOR_BHB_FW,
+
+	/*
+	 * Use the ClearBHB instruction, before branching to the canonical
+	 * vectors.
+	 */
+	EL1_VECTOR_BHB_CLEAR_INSN,
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+	/*
+	 * Remap the kernel before branching to the canonical vectors.
+	 */
+	EL1_VECTOR_KPTI,
+};
+
+#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+#define EL1_VECTOR_BHB_LOOP		-1
+#define EL1_VECTOR_BHB_FW		-1
+#define EL1_VECTOR_BHB_CLEAR_INSN	-1
+#endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+/* The vectors to use on return from EL0. e.g. to remap the kernel */
+DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
+
+#ifndef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_VALIAS	0ul
+#endif
+
+static inline const char *
+arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
+{
+	if (arm64_kernel_unmapped_at_el0())
+		return (char *)(TRAMP_VALIAS + SZ_2K * slot);
+
+	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);
+
+	return __bp_harden_el1_vectors + SZ_2K * slot;
+}
+
+#endif /* __ASM_VECTORS_H */
diff --git a/arch/arm64/include/asm/vermagic.h b/arch/arm64/include/asm/vermagic.h
new file mode 100644
index 000000000..a1eec6a00
--- /dev/null
+++ b/arch/arm64/include/asm/vermagic.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#ifndef _ASM_VERMAGIC_H
+#define _ASM_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC	"aarch64"
+
+#endif /* _ASM_VERMAGIC_H */
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
new file mode 100644
index 000000000..4eb601e7d
--- /dev/null
+++ b/arch/arm64/include/asm/virt.h
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ASM__VIRT_H
+#define __ASM__VIRT_H
+
+/*
+ * The arm64 hcall implementation uses x0 to specify the hcall
+ * number. A value less than HVC_STUB_HCALL_NR indicates a special
+ * hcall, such as set vector. Any other value is handled in a
+ * hypervisor specific way.
+ *
+ * The hypercall is allowed to clobber any of the caller-saved
+ * registers (x0-x18), so it is advisable to use it through the
+ * indirection of a function call (as implemented in hyp-stub.S).
+ */
+
+/*
+ * HVC_SET_VECTORS - Set the value of the vbar_el2 register.
+ *
+ * @x1: Physical address of the new vector table.
+ */
+#define HVC_SET_VECTORS 0
+
+/*
+ * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
+ */
+#define HVC_SOFT_RESTART 1
+
+/*
+ * HVC_RESET_VECTORS - Restore the vectors to the original HYP stubs
+ */
+#define HVC_RESET_VECTORS 2
+
+/*
+ * HVC_FINALISE_EL2 - Upgrade the CPU from EL1 to EL2, if possible
+ */
+#define HVC_FINALISE_EL2	3
+
+/* Max number of HYP stub hypercalls */
+#define HVC_STUB_HCALL_NR 4
+
+/* Error returned when an invalid stub number is passed into x0 */
+#define HVC_STUB_ERR	0xbadca11
+
+#define BOOT_CPU_MODE_EL1	(0xe11)
+#define BOOT_CPU_MODE_EL2	(0xe12)
+
+/*
+ * Flags returned together with the boot mode, but not preserved in
+ * __boot_cpu_mode. Used by the idreg override code to work out the
+ * boot state.
+ */
+#define BOOT_CPU_FLAG_E2H	BIT_ULL(32)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
+#include <asm/cpufeature.h>
+
+/*
+ * __boot_cpu_mode records what mode CPUs were booted in.
+ * A correctly-implemented bootloader must start all CPUs in the same mode:
+ * In this case, both 32bit halves of __boot_cpu_mode will contain the
+ * same value (either 0 if booted in EL1, BOOT_CPU_MODE_EL2 if booted in EL2).
+ *
+ * Should the bootloader fail to do this, the two values will be different.
+ * This allows the kernel to flag an error when the secondaries have come up.
+ */
+extern u32 __boot_cpu_mode[2];
+
+#define ARM64_VECTOR_TABLE_LEN	SZ_2K
+
+void __hyp_set_vectors(phys_addr_t phys_vector_base);
+void __hyp_reset_vectors(void);
+
+DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
+
+/* Reports the availability of HYP mode */
+static inline bool is_hyp_mode_available(void)
+{
+	/*
+	 * If KVM protected mode is initialized, all CPUs must have been booted
+	 * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1.
+	 */
+	if (IS_ENABLED(CONFIG_KVM) &&
+	    static_branch_likely(&kvm_protected_mode_initialized))
+		return true;
+
+	return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 &&
+		__boot_cpu_mode[1] == BOOT_CPU_MODE_EL2);
+}
+
+/* Check if the bootloader has booted CPUs in different modes */
+static inline bool is_hyp_mode_mismatched(void)
+{
+	/*
+	 * If KVM protected mode is initialized, all CPUs must have been booted
+	 * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1.
+	 */
+	if (IS_ENABLED(CONFIG_KVM) &&
+	    static_branch_likely(&kvm_protected_mode_initialized))
+		return false;
+
+	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
+}
+
+static inline bool is_kernel_in_hyp_mode(void)
+{
+	return read_sysreg(CurrentEL) == CurrentEL_EL2;
+}
+
+static __always_inline bool has_vhe(void)
+{
+	/*
+	 * Code only run in VHE/NVHE hyp context can assume VHE is present or
+	 * absent. Otherwise fall back to caps.
+	 * This allows the compiler to discard VHE-specific code from the
+	 * nVHE object, reducing the number of external symbol references
+	 * needed to link.
+	 */
+	if (is_vhe_hyp_code())
+		return true;
+	else if (is_nvhe_hyp_code())
+		return false;
+	else
+		return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
+}
+
+static __always_inline bool is_protected_kvm_enabled(void)
+{
+	if (is_vhe_hyp_code())
+		return false;
+	else
+		return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE);
+}
+
+static inline bool is_hyp_nvhe(void)
+{
+	return is_hyp_mode_available() && !is_kernel_in_hyp_mode();
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
new file mode 100644
index 000000000..38fafffe6
--- /dev/null
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_ARM64_VMALLOC_H
+#define _ASM_ARM64_VMALLOC_H
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+
+#define arch_vmap_pud_supported arch_vmap_pud_supported
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+	/*
+	 * SW table walks can't handle removal of intermediate entries.
+	 */
+	return pud_sect_supported() &&
+	       !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+}
+
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+	/* See arch_vmap_pud_supported() */
+	return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+}
+
+#endif
+
+#define arch_vmap_pgprot_tagged arch_vmap_pgprot_tagged
+static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot)
+{
+	return pgprot_tagged(prot);
+}
+
+#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
new file mode 100644
index 000000000..20873099c
--- /dev/null
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2017 Arm Ltd.
+#ifndef __ASM_VMAP_STACK_H
+#define __ASM_VMAP_STACK_H
+
+#include <linux/bug.h>
+#include <linux/gfp.h>
+#include <linux/kconfig.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <asm/memory.h>
+#include <asm/thread_info.h>
+
+/*
+ * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
+ * stacks need to have the same alignment.
+ */
+static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
+{
+	void *p;
+
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
+
+	p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
+			__builtin_return_address(0));
+	return kasan_reset_tag(p);
+}
+
+#endif /* __ASM_VMAP_STACK_H */
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
new file mode 100644
index 000000000..1c8e4f249
--- /dev/null
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ */
+#ifndef __ASM_WORD_AT_A_TIME_H
+#define __ASM_WORD_AT_A_TIME_H
+
+#include <linux/uaccess.h>
+
+#ifndef __AARCH64EB__
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits,
+				     const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+#define prep_zero_mask(a, bits, c) (bits)
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return fls64(mask) >> 3;
+}
+
+#define zero_bytemask(mask) (mask)
+
+#else	/* __AARCH64EB__ */
+#include <asm-generic/word-at-a-time.h>
+#endif
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret;
+
+	__uaccess_enable_tco_async();
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	ldr	%0, %2\n"
+	"2:\n"
+	_ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
+	: "=&r" (ret)
+	: "r" (addr), "Q" (*(unsigned long *)addr));
+
+	__uaccess_disable_tco_async();
+
+	return ret;
+}
+
+#endif /* __ASM_WORD_AT_A_TIME_H */
diff --git a/arch/arm64/include/asm/xen/events.h b/arch/arm64/include/asm/xen/events.h
new file mode 100644
index 000000000..2788e95d0
--- /dev/null
+++ b/arch/arm64/include/asm/xen/events.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_XEN_EVENTS_H
+#define _ASM_ARM64_XEN_EVENTS_H
+
+#include <asm/ptrace.h>
+#include <asm/atomic.h>
+
+enum ipi_vector {
+	XEN_PLACEHOLDER_VECTOR,
+
+	/* Xen IPIs go here */
+	XEN_NR_IPIS,
+};
+
+static inline int xen_irqs_disabled(struct pt_regs *regs)
+{
+	return !interrupts_enabled(regs);
+}
+
+#define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
+
+/* Rebind event channel is supported by default */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return true;
+}
+
+#endif /* _ASM_ARM64_XEN_EVENTS_H */
diff --git a/arch/arm64/include/asm/xen/hypercall.h b/arch/arm64/include/asm/xen/hypercall.h
new file mode 100644
index 000000000..3522cbaed
--- /dev/null
+++ b/arch/arm64/include/asm/xen/hypercall.h
@@ -0,0 +1 @@
+#include <xen/arm/hypercall.h>
diff --git a/arch/arm64/include/asm/xen/hypervisor.h b/arch/arm64/include/asm/xen/hypervisor.h
new file mode 100644
index 000000000..d6e7709d0
--- /dev/null
+++ b/arch/arm64/include/asm/xen/hypervisor.h
@@ -0,0 +1 @@
+#include <xen/arm/hypervisor.h>
diff --git a/arch/arm64/include/asm/xen/interface.h b/arch/arm64/include/asm/xen/interface.h
new file mode 100644
index 000000000..88c0d75da
--- /dev/null
+++ b/arch/arm64/include/asm/xen/interface.h
@@ -0,0 +1 @@
+#include <xen/arm/interface.h>
diff --git a/arch/arm64/include/asm/xen/page.h b/arch/arm64/include/asm/xen/page.h
new file mode 100644
index 000000000..dffdc7732
--- /dev/null
+++ b/arch/arm64/include/asm/xen/page.h
@@ -0,0 +1,7 @@
+#include <xen/arm/page.h>
+#include <asm/mmu.h>
+
+static inline bool xen_kernel_unmapped_at_usr(void)
+{
+	return arm64_kernel_unmapped_at_el0();
+}
diff --git a/arch/arm64/include/asm/xen/swiotlb-xen.h b/arch/arm64/include/asm/xen/swiotlb-xen.h
new file mode 100644
index 000000000..455ade5d5
--- /dev/null
+++ b/arch/arm64/include/asm/xen/swiotlb-xen.h
@@ -0,0 +1 @@
+#include <xen/arm/swiotlb-xen.h>
diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h
new file mode 100644
index 000000000..7ebb7eb0b
--- /dev/null
+++ b/arch/arm64/include/asm/xen/xen-ops.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <xen/arm/xen-ops.h>
diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h
new file mode 100644
index 000000000..befcd8a7a
--- /dev/null
+++ b/arch/arm64/include/asm/xor.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * arch/arm64/include/asm/xor.h
+ *
+ * Authors: Jackie Liu <liuyun01@kylinos.cn>
+ * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+extern struct xor_block_template const xor_block_inner_neon;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+	   const unsigned long * __restrict p2)
+{
+	kernel_neon_begin();
+	xor_block_inner_neon.do_2(bytes, p1, p2);
+	kernel_neon_end();
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+	   const unsigned long * __restrict p2,
+	   const unsigned long * __restrict p3)
+{
+	kernel_neon_begin();
+	xor_block_inner_neon.do_3(bytes, p1, p2, p3);
+	kernel_neon_end();
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
+	   const unsigned long * __restrict p2,
+	   const unsigned long * __restrict p3,
+	   const unsigned long * __restrict p4)
+{
+	kernel_neon_begin();
+	xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4);
+	kernel_neon_end();
+}
+
+static void
+xor_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)
+{
+	kernel_neon_begin();
+	xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5);
+	kernel_neon_end();
+}
+
+static struct xor_block_template xor_block_arm64 = {
+	.name   = "arm64_neon",
+	.do_2   = xor_neon_2,
+	.do_3   = xor_neon_3,
+	.do_4   = xor_neon_4,
+	.do_5	= xor_neon_5
+};
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES           \
+	do {        \
+		xor_speed(&xor_block_8regs);    \
+		xor_speed(&xor_block_32regs);    \
+		if (cpu_has_neon()) { \
+			xor_speed(&xor_block_arm64);\
+		} \
+	} while (0)
+
+#endif /* ! CONFIG_KERNEL_MODE_NEON */