Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "The bulk is in-kernel pointer authentication, activity monitors and
  lots of asm symbol annotations. I also queued the sys_mremap() patch
  commenting the asymmetry in the address untagging.

  Summary:

   - In-kernel Pointer Authentication support (previously only offered
     to user space).

   - ARM Activity Monitors (AMU) extension support allowing better CPU
     utilisation numbers for the scheduler (frequency invariance).

   - Memory hot-remove support for arm64.

   - Lots of asm annotations (SYM_*) in preparation for the in-kernel
     Branch Target Identification (BTI) support.

   - arm64 perf updates: ARMv8.5-PMU 64-bit counters, refactoring the
     PMU init callbacks, support for new DT compatibles.

   - IPv6 header checksum optimisation.

   - Fixes: SDEI (software delegated exception interface) double-lock on
     hibernate with shared events.

   - Minor clean-ups and refactoring: cpu_ops accessor,
     cpu_do_switch_mm() converted to C, cpufeature finalisation helper.

   - sys_mremap() comment explaining the asymmetric address untagging
     behaviour"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (81 commits)
  mm/mremap: Add comment explaining the untagging behaviour of mremap()
  arm64: head: Convert install_el2_stub to SYM_INNER_LABEL
  arm64: Introduce get_cpu_ops() helper function
  arm64: Rename cpu_read_ops() to init_cpu_ops()
  arm64: Declare ACPI parking protocol CPU operation if needed
  arm64: move kimage_vaddr to .rodata
  arm64: use mov_q instead of literal ldr
  arm64: Kconfig: verify binutils support for ARM64_PTR_AUTH
  lkdtm: arm64: test kernel pointer authentication
  arm64: compile the kernel with ptrauth return address signing
  kconfig: Add support for 'as-option'
  arm64: suspend: restore the kernel ptrauth keys
  arm64: __show_regs: strip PAC from lr in printk
  arm64: unwind: strip PAC from kernel addresses
  arm64: mask PAC bits of __builtin_return_address
  arm64: initialize ptrauth keys for kernel booting task
  arm64: initialize and switch ptrauth kernel keys
  arm64: enable ptrauth earlier
  arm64: cpufeature: handle conflicts based on capability
  arm64: cpufeature: Move cpu capability helpers inside C file
  ...

23 files changed, 332 insertions, 83 deletions

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 000000000000..ce2a8486992b
--- /dev/null
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -0,0 +1,65 @@
+/* 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
+/*
+ * 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
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+	b	.Laddr_auth_skip_\@
+alternative_else_nop_endif
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
+	msr_s	SYS_APIAKEYLO_EL1, \tmp2
+	msr_s	SYS_APIAKEYHI_EL1, \tmp3
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIB]
+	msr_s	SYS_APIBKEYLO_EL1, \tmp2
+	msr_s	SYS_APIBKEYHI_EL1, \tmp3
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDA]
+	msr_s	SYS_APDAKEYLO_EL1, \tmp2
+	msr_s	SYS_APDAKEYHI_EL1, \tmp3
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDB]
+	msr_s	SYS_APDBKEYLO_EL1, \tmp2
+	msr_s	SYS_APDBKEYHI_EL1, \tmp3
+.Laddr_auth_skip_\@:
+alternative_if ARM64_HAS_GENERIC_AUTH
+	ldp	\tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APGA]
+	msr_s	SYS_APGAKEYLO_EL1, \tmp2
+	msr_s	SYS_APGAKEYHI_EL1, \tmp3
+alternative_else_nop_endif
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+	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
+	.if     \sync == 1
+	isb
+	.endif
+alternative_else_nop_endif
+	.endm
+
+#else /* CONFIG_ARM64_PTR_AUTH */
+
+	.macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+	.endm
+
+	.macro ptrauth_keys_install_kernel tsk, sync, 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
index aca337d79d12..0bff325117b4 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -257,12 +257,6 @@ alternative_endif
 	.endm
 
 /*
- * mmid - get context id from mm pointer (mm->context.id)
- */
-	.macro	mmid, rd, rn
-	ldr	\rd, [\rn, #MM_CONTEXT_ID]
-	.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
  */
@@ -431,6 +425,16 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	.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_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
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 8d2a7de39744..b6f7bc6da5fb 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -5,7 +5,12 @@
 #ifndef __ASM_CHECKSUM_H
 #define __ASM_CHECKSUM_H
 
-#include <linux/types.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)
 {
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
new file mode 100644
index 000000000000..eece20d2c55f
--- /dev/null
+++ b/arch/arm64/include/asm/compiler.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_COMPILER_H
+#define __ASM_COMPILER_H
+
+#if defined(CONFIG_ARM64_PTR_AUTH)
+
+/*
+ * 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 /* CONFIG_ARM64_PTR_AUTH */
+
+#endif /* __ASM_COMPILER_H */
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 86aabf1e0199..d28e8f37d3b4 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -55,12 +55,12 @@ struct cpu_operations {
 #endif
 };
 
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
-int __init cpu_read_ops(int cpu);
+int __init init_cpu_ops(int cpu);
+extern const struct cpu_operations *get_cpu_ops(int cpu);
 
-static inline void __init cpu_read_bootcpu_ops(void)
+static inline void __init init_bootcpu_ops(void)
 {
-	cpu_read_ops(0);
+	init_cpu_ops(0);
 }
 
 #endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 865e0253fc1e..8eb5a088ae65 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -58,7 +58,10 @@
 #define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE	48
 #define ARM64_HAS_E0PD				49
 #define ARM64_HAS_RNG				50
+#define ARM64_HAS_AMU_EXTN			51
+#define ARM64_HAS_ADDRESS_AUTH			52
+#define ARM64_HAS_GENERIC_AUTH			53
 
-#define ARM64_NCAPS				51
+#define ARM64_NCAPS				54
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 2a746b99e937..afe08251ff95 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -208,6 +208,10 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
  *     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.
  */
 
 
@@ -240,6 +244,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 #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
@@ -279,9 +285,20 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 
 /*
  * 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.
+ * 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_STRICT_BOOT_CPU_FEATURE ARM64_CPUCAP_SCOPE_BOOT_CPU
+#define ARM64_CPUCAP_BOOT_CPU_FEATURE                  \
+	(ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
 
 struct arm64_cpu_capabilities {
 	const char *desc;
@@ -340,18 +357,6 @@ static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
 	return cap->type & ARM64_CPUCAP_SCOPE_MASK;
 }
 
-static inline bool
-cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
-{
-	return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU);
-}
-
-static inline bool
-cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
-{
-	return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
-}
-
 /*
  * Generic helper for handling capabilties with multiple (match,enable) pairs
  * of call backs, sharing the same capability bit.
@@ -390,14 +395,16 @@ 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))
 
-/* System capability check for constant caps */
-static __always_inline bool __cpus_have_const_cap(int num)
+static __always_inline bool system_capabilities_finalized(void)
 {
-	if (num >= ARM64_NCAPS)
-		return false;
-	return static_branch_unlikely(&cpu_hwcap_keys[num]);
+	return static_branch_likely(&arm64_const_caps_ready);
 }
 
+/*
+ * Test for a capability with a runtime check.
+ *
+ * Before the capability is detected, this returns false.
+ */
 static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
@@ -405,14 +412,53 @@ static inline bool cpus_have_cap(unsigned int num)
 	return 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 static_branch_unlikely(&cpu_hwcap_keys[num]);
+}
+
+/*
+ * Test for a capability, possibly with a runtime check.
+ *
+ * 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 (static_branch_likely(&arm64_const_caps_ready))
+	if (system_capabilities_finalized())
 		return __cpus_have_const_cap(num);
 	else
 		return cpus_have_cap(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();
+}
+
 static inline void cpus_set_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS) {
@@ -447,6 +493,29 @@ 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 == 0xf)
+		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);
@@ -590,15 +659,13 @@ static __always_inline bool system_supports_cnp(void)
 static inline bool system_supports_address_auth(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		(cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) ||
-		 cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF));
+		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_ARCH) ||
-		 cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
+		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
 static inline bool system_uses_irq_prio_masking(void)
@@ -613,11 +680,6 @@ static inline bool system_has_prio_mask_debugging(void)
 	       system_uses_irq_prio_masking();
 }
 
-static inline bool system_capabilities_finalized(void)
-{
-	return static_branch_likely(&arm64_const_caps_ready);
-}
-
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1
@@ -678,6 +740,11 @@ static inline bool cpu_has_hw_af(void)
 						ID_AA64MMFR1_HADBS_SHIFT);
 }
 
+#ifdef CONFIG_ARM64_AMU_EXTN
+/* Check whether the cpu supports the Activity Monitors Unit (AMU) */
+extern bool cpu_has_amu_feat(int cpu);
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index cb29253ae86b..6a395a7e6707 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -60,7 +60,7 @@
 #define ESR_ELx_EC_BKPT32	(0x38)
 /* Unallocated EC: 0x39 */
 #define ESR_ELx_EC_VECTOR32	(0x3A)	/* EL2 only */
-/* Unallocted EC: 0x3B */
+/* Unallocated EC: 0x3B */
 #define ESR_ELx_EC_BRK64	(0x3C)
 /* Unallocated EC: 0x3D - 0x3F */
 #define ESR_ELx_EC_MAX		(0x3F)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6e5d839f42b5..51c1d9918999 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -267,6 +267,7 @@
 
 /* Hyp Coprocessor Trap Register */
 #define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 44a243754c1b..7c7eeeaab9fa 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -36,6 +36,8 @@
  */
 #define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
 
+#define __SMCCC_WORKAROUND_1_SMC_SZ 36
+
 #ifndef __ASSEMBLY__
 
 #include <linux/mm.h>
@@ -75,6 +77,8 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
+extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
+
 /* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
 #define __hyp_this_cpu_ptr(sym)						\
 	({								\
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 785762860c63..30b0e8d6b895 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -481,7 +481,7 @@ static inline void *kvm_get_hyp_vector(void)
 	int slot = -1;
 
 	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
-		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
+		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
 		slot = data->hyp_vectors_slot;
 	}
 
@@ -510,14 +510,13 @@ static inline int kvm_map_vectors(void)
 	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
 	 */
 	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
-		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
+		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
 		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
 	}
 
 	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
-		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start);
-		unsigned long size = (__bp_harden_hyp_vecs_end -
-				      __bp_harden_hyp_vecs_start);
+		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
+		unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
 
 		/*
 		 * Always allocate a spare vector slot, as we don't
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 4d94676e5a8b..2be67b232499 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -54,6 +54,7 @@
 #define MODULES_VADDR		(BPF_JIT_REGION_END)
 #define MODULES_VSIZE		(SZ_128M)
 #define VMEMMAP_START		(-VMEMMAP_SIZE - SZ_2M)
+#define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index d79ce6df9e12..68140fdd89d6 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -13,6 +13,7 @@
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
 #define BP_HARDEN_EL2_SLOTS 4
+#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K)
 
 #ifndef __ASSEMBLY__
 
@@ -23,9 +24,9 @@ typedef struct {
 } mm_context_t;
 
 /*
- * This macro is only used by the TLBI code, which cannot race with an
- * ASID change and therefore doesn't need to reload the counter using
- * atomic64_read.
+ * This macro is only used by the TLBI and low-level switch_mm() code,
+ * neither of which can race with an ASID change. We therefore don't
+ * need to reload the counter using atomic64_read().
  */
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
@@ -43,7 +44,8 @@ struct bp_hardening_data {
 
 #if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) ||	\
      defined(CONFIG_HARDEN_EL2_VECTORS))
-extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+extern char __bp_harden_hyp_vecs[];
 extern atomic_t arm64_el2_vector_last_slot;
 #endif  /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
 
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3827ff4040a3..ab46187c6300 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -46,6 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void)
 	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);
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index d39ddb258a04..75d6cd23a679 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from,
 extern void copy_page(void *to, const void *from);
 extern void clear_page(void *to);
 
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
 #define clear_user_page(addr,vaddr,pg)  __cpu_clear_user_page(addr, vaddr)
 #define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
 
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2bdbc79bbd01..e7765b62c712 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -176,9 +176,10 @@
 #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	0x7f	 /* Mask for writable bits */
+#define	ARMV8_PMU_PMCR_MASK	0xff	 /* Mask for writable bits */
 
 /*
  * PMOVSR: counters overflow flag status reg
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 7a24bad1a58b..70c47156e54b 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -22,7 +22,7 @@ struct ptrauth_key {
  * 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 {
+struct ptrauth_keys_user {
 	struct ptrauth_key apia;
 	struct ptrauth_key apib;
 	struct ptrauth_key apda;
@@ -30,7 +30,11 @@ struct ptrauth_keys {
 	struct ptrauth_key apga;
 };
 
-static inline void ptrauth_keys_init(struct ptrauth_keys *keys)
+struct ptrauth_keys_kernel {
+	struct ptrauth_key apia;
+};
+
+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));
@@ -50,48 +54,38 @@ do {								\
 	write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1);	\
 } while (0)
 
-static inline void ptrauth_keys_switch(struct ptrauth_keys *keys)
+static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
 {
-	if (system_supports_address_auth()) {
-		__ptrauth_key_install(APIA, keys->apia);
-		__ptrauth_key_install(APIB, keys->apib);
-		__ptrauth_key_install(APDA, keys->apda);
-		__ptrauth_key_install(APDB, keys->apdb);
-	}
+	if (system_supports_address_auth())
+		get_random_bytes(&keys->apia, sizeof(keys->apia));
+}
 
-	if (system_supports_generic_auth())
-		__ptrauth_key_install(APGA, keys->apga);
+static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
+{
+	if (system_supports_address_auth())
+		__ptrauth_key_install(APIA, keys->apia);
 }
 
 extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
 
-/*
- * The EL0 pointer bits used by a pointer authentication code.
- * This is dependent on TBI0 being enabled, or bits 63:56 would also apply.
- */
-#define ptrauth_user_pac_mask()	GENMASK(54, vabits_actual)
-
-/* Only valid for EL0 TTBR0 instruction pointers */
 static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
 {
-	return ptr & ~ptrauth_user_pac_mask();
+	return ptrauth_clear_pac(ptr);
 }
 
 #define ptrauth_thread_init_user(tsk)					\
-do {									\
-	struct task_struct *__ptiu_tsk = (tsk);				\
-	ptrauth_keys_init(&__ptiu_tsk->thread.keys_user);		\
-	ptrauth_keys_switch(&__ptiu_tsk->thread.keys_user);		\
-} while (0)
-
-#define ptrauth_thread_switch(tsk)	\
-	ptrauth_keys_switch(&(tsk)->thread.keys_user)
+	ptrauth_keys_init_user(&(tsk)->thread.keys_user)
+#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 /* CONFIG_ARM64_PTR_AUTH */
 #define ptrauth_prctl_reset_keys(tsk, arg)	(-EINVAL)
 #define ptrauth_strip_insn_pac(lr)	(lr)
 #define ptrauth_thread_init_user(tsk)
-#define ptrauth_thread_switch(tsk)
+#define ptrauth_thread_init_kernel(tsk)
+#define ptrauth_thread_switch_kernel(tsk)
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
 #endif /* __ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index a2ce65a0c1fa..0d5d1f0525eb 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -13,11 +13,9 @@
 
 #include <asm/page.h>
 
-struct mm_struct;
 struct cpu_suspend_ctx;
 
 extern void cpu_do_idle(void);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e51ef2dc5749..240fe5e5b720 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -148,7 +148,8 @@ struct thread_struct {
 	unsigned long		fault_code;	/* ESR_EL1 value */
 	struct debug_info	debug;		/* debugging */
 #ifdef CONFIG_ARM64_PTR_AUTH
-	struct ptrauth_keys	keys_user;
+	struct ptrauth_keys_user	keys_user;
+	struct ptrauth_keys_kernel	keys_kernel;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a0c8a0b65259..40d5ba029615 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -23,6 +23,14 @@
 #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)
 
+/* Possible options for __cpu_setup */
+/* Option to setup primary cpu */
+#define ARM64_CPU_BOOT_PRIMARY		(1)
+/* Option to setup secondary cpus */
+#define ARM64_CPU_BOOT_SECONDARY	(2)
+/* Option to setup cpus for different cpu run time services */
+#define ARM64_CPU_RUNTIME		(3)
+
 #ifndef __ASSEMBLY__
 
 #include <asm/percpu.h>
@@ -30,6 +38,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
+#include <asm/pointer_auth.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
@@ -87,6 +96,9 @@ asmlinkage void secondary_start_kernel(void);
 struct secondary_data {
 	void *stack;
 	struct task_struct *task;
+#ifdef CONFIG_ARM64_PTR_AUTH
+	struct ptrauth_keys_kernel ptrauth_key;
+#endif
 	long status;
 };
 
diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h
index 5884a2b02827..7263e0bac680 100644
--- a/arch/arm64/include/asm/stackprotector.h
+++ b/arch/arm64/include/asm/stackprotector.h
@@ -15,6 +15,7 @@
 
 #include <linux/random.h>
 #include <linux/version.h>
+#include <asm/pointer_auth.h>
 
 extern unsigned long __stack_chk_guard;
 
@@ -26,6 +27,7 @@ extern unsigned long __stack_chk_guard;
  */
 static __always_inline void boot_init_stack_canary(void)
 {
+#if defined(CONFIG_STACKPROTECTOR)
 	unsigned long canary;
 
 	/* Try to get a semi random initial value. */
@@ -36,6 +38,9 @@ static __always_inline void boot_init_stack_canary(void)
 	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);
 }
 
 #endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b91570ff9db1..ebc622432831 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -386,6 +386,42 @@
 #define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
 #define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
 
+/* 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_AMEVTYPE0_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_AMEVTYPE1_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_CNTP_TVAL_EL0		sys_reg(3, 3, 14, 2, 0)
@@ -598,6 +634,7 @@
 #define ID_AA64PFR0_CSV3_SHIFT		60
 #define ID_AA64PFR0_CSV2_SHIFT		56
 #define ID_AA64PFR0_DIT_SHIFT		48
+#define ID_AA64PFR0_AMU_SHIFT		44
 #define ID_AA64PFR0_SVE_SHIFT		32
 #define ID_AA64PFR0_RAS_SHIFT		28
 #define ID_AA64PFR0_GIC_SHIFT		24
@@ -608,6 +645,7 @@
 #define ID_AA64PFR0_EL1_SHIFT		4
 #define ID_AA64PFR0_EL0_SHIFT		0
 
+#define ID_AA64PFR0_AMU			0x1
 #define ID_AA64PFR0_SVE			0x1
 #define ID_AA64PFR0_RAS_V1		0x1
 #define ID_AA64PFR0_FP_NI		0xf
@@ -702,6 +740,16 @@
 #define ID_AA64DFR0_TRACEVER_SHIFT	4
 #define ID_AA64DFR0_DEBUGVER_SHIFT	0
 
+#define ID_AA64DFR0_PMUVER_8_0		0x1
+#define ID_AA64DFR0_PMUVER_8_1		0x4
+#define ID_AA64DFR0_PMUVER_8_4		0x5
+#define ID_AA64DFR0_PMUVER_8_5		0x6
+#define ID_AA64DFR0_PMUVER_IMP_DEF	0xf
+
+#define ID_DFR0_PERFMON_SHIFT		24
+
+#define ID_DFR0_PERFMON_8_1		0x4
+
 #define ID_ISAR5_RDM_SHIFT		24
 #define ID_ISAR5_CRC32_SHIFT		16
 #define ID_ISAR5_SHA2_SHIFT		12
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index cbd70d78ef15..0cc835ddfcd1 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -16,6 +16,15 @@ int pcibus_to_node(struct pci_bus *bus);
 
 #include <linux/arch_topology.h>
 
+#ifdef CONFIG_ARM64_AMU_EXTN
+/*
+ * Replace task scheduler's default counter-based
+ * frequency-invariance scale factor setting.
+ */
+void topology_scale_freq_tick(void);
+#define arch_scale_freq_tick topology_scale_freq_tick
+#endif /* CONFIG_ARM64_AMU_EXTN */
+
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale