Merge tag 'kvmarm-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 changes for 6.11

 - Initial infrastructure for shadow stage-2 MMUs, as part of nested
   virtualization enablement

 - Support for userspace changes to the guest CTR_EL0 value, enabling
   (in part) migration of VMs between heterogenous hardware

 - Fixes + improvements to pKVM's FF-A proxy, adding support for v1.1 of
   the protocol

 - FPSIMD/SVE support for nested, including merged trap configuration
   and exception routing

 - New command-line parameter to control the WFx trap behavior under KVM

 - Introduce kCFI hardening in the EL2 hypervisor

 - Fixes + cleanups for handling presence/absence of FEAT_TCRX

 - Miscellaneous fixes + documentation updates

33 files changed, 2718 insertions, 374 deletions

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 7abf09df7033..8eccf497894e 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -152,6 +152,7 @@
 #define ESR_ELx_Xs_MASK		(GENMASK_ULL(4, 0))
 
 /* ISS field definitions for exceptions taken in to Hyp */
+#define ESR_ELx_FSC_ADDRSZ	(0x00)
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -379,6 +380,11 @@
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
+static inline unsigned long esr_brk_comment(unsigned long esr)
+{
+	return esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+}
+
 static inline bool esr_is_data_abort(unsigned long esr)
 {
 	const unsigned long ec = ESR_ELx_EC(esr);
@@ -386,6 +392,12 @@ static inline bool esr_is_data_abort(unsigned long esr)
 	return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
 }
 
+static inline bool esr_is_cfi_brk(unsigned long esr)
+{
+	return ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
+	       (esr_brk_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE;
+}
+
 static inline bool esr_fsc_is_translation_fault(unsigned long esr)
 {
 	/* Translation fault, level -1 */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index b2adc2c6c82a..d81cc746e0eb 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -102,7 +102,6 @@
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
-#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En)
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index a6330460d9e5..2181a11b9d92 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -232,6 +232,8 @@ extern void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 					phys_addr_t start, unsigned long pages);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 
+extern int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding);
+
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 21650e7924d4..a601a9305b10 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -11,6 +11,7 @@
 #ifndef __ARM64_KVM_EMULATE_H__
 #define __ARM64_KVM_EMULATE_H__
 
+#include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 
 #include <asm/debug-monitors.h>
@@ -55,6 +56,14 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
 int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
 int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
 
+static inline void kvm_inject_nested_sve_trap(struct kvm_vcpu *vcpu)
+{
+	u64 esr = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SVE) |
+		  ESR_ELx_IL;
+
+	kvm_inject_nested_sync(vcpu, esr);
+}
+
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -69,39 +78,17 @@ static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
-	if (has_vhe() || has_hvhe())
-		vcpu->arch.hcr_el2 |= HCR_E2H;
-	if (cpus_have_final_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 (!vcpu_has_run_once(vcpu))
+		vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 
-	if (cpus_have_final_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.
-		 */
+	/*
+	 * 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.
+	 */
+	if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 		vcpu->arch.hcr_el2 |= HCR_TVM;
-	}
-
-	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
-	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
-		vcpu->arch.hcr_el2 |= HCR_TID4;
-	else
-		vcpu->arch.hcr_el2 |= HCR_TID2;
-
-	if (vcpu_el1_is_32bit(vcpu))
-		vcpu->arch.hcr_el2 &= ~HCR_RW;
-
-	if (kvm_has_mte(vcpu->kvm))
-		vcpu->arch.hcr_el2 |= HCR_ATA;
 }
 
 static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
@@ -660,4 +647,50 @@ static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu)
 
 	kvm_write_cptr_el2(val);
 }
+
+/*
+ * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
+ * format if E2H isn't set.
+ */
+static inline u64 vcpu_sanitised_cptr_el2(const struct kvm_vcpu *vcpu)
+{
+	u64 cptr = __vcpu_sys_reg(vcpu, CPTR_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		cptr = translate_cptr_el2_to_cpacr_el1(cptr);
+
+	return cptr;
+}
+
+static inline bool ____cptr_xen_trap_enabled(const struct kvm_vcpu *vcpu,
+					     unsigned int xen)
+{
+	switch (xen) {
+	case 0b00:
+	case 0b10:
+		return true;
+	case 0b01:
+		return vcpu_el2_tge_is_set(vcpu) && !vcpu_is_el2(vcpu);
+	case 0b11:
+	default:
+		return false;
+	}
+}
+
+#define __guest_hyp_cptr_xen_trap_enabled(vcpu, xen)				\
+	(!vcpu_has_nv(vcpu) ? false :						\
+	 ____cptr_xen_trap_enabled(vcpu,					\
+				   SYS_FIELD_GET(CPACR_ELx, xen,		\
+						 vcpu_sanitised_cptr_el2(vcpu))))
+
+static inline bool guest_hyp_fpsimd_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	return __guest_hyp_cptr_xen_trap_enabled(vcpu, FPEN);
+}
+
+static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu)
+{
+	return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN);
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 36b8e97bf49e..25a3b72fbacf 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -189,6 +189,33 @@ struct kvm_s2_mmu {
 	uint64_t split_page_chunk_size;
 
 	struct kvm_arch *arch;
+
+	/*
+	 * For a shadow stage-2 MMU, the virtual vttbr used by the
+	 * host to parse the guest S2.
+	 * This either contains:
+	 * - the virtual VTTBR programmed by the guest hypervisor with
+         *   CnP cleared
+	 * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid
+	 *
+	 * We also cache the full VTCR which gets used for TLB invalidation,
+	 * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted
+	 * to be cached in a TLB" to the letter.
+	 */
+	u64	tlb_vttbr;
+	u64	tlb_vtcr;
+
+	/*
+	 * true when this represents a nested context where virtual
+	 * HCR_EL2.VM == 1
+	 */
+	bool	nested_stage2_enabled;
+
+	/*
+	 *  0: Nobody is currently using this, check vttbr for validity
+	 * >0: Somebody is actively using this.
+	 */
+	atomic_t refcnt;
 };
 
 struct kvm_arch_memory_slot {
@@ -256,6 +283,14 @@ struct kvm_arch {
 	 */
 	u64 fgu[__NR_FGT_GROUP_IDS__];
 
+	/*
+	 * Stage 2 paging state for VMs with nested S2 using a virtual
+	 * VMID.
+	 */
+	struct kvm_s2_mmu *nested_mmus;
+	size_t nested_mmus_size;
+	int nested_mmus_next;
+
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
@@ -327,11 +362,11 @@ struct kvm_arch {
 	 * Atomic access to multiple idregs are guarded by kvm_arch.config_lock.
 	 */
 #define IDREG_IDX(id)		(((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id))
-#define IDX_IDREG(idx)		sys_reg(3, 0, 0, ((idx) >> 3) + 1, (idx) & Op2_mask)
-#define IDREG(kvm, id)		((kvm)->arch.id_regs[IDREG_IDX(id)])
 #define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
 	u64 id_regs[KVM_ARM_ID_REG_NUM];
 
+	u64 ctr_el0;
+
 	/* Masks for VNCR-baked sysregs */
 	struct kvm_sysreg_masks	*sysreg_masks;
 
@@ -423,6 +458,7 @@ enum vcpu_sysreg {
 	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
+	ZCR_EL2,	/* SVE Control Register (EL2) */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
@@ -867,6 +903,9 @@ struct kvm_vcpu_arch {
 
 #define vcpu_sve_max_vq(vcpu)	sve_vq_from_vl((vcpu)->arch.sve_max_vl)
 
+#define vcpu_sve_zcr_elx(vcpu)						\
+	(unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1)
+
 #define vcpu_sve_state_size(vcpu) ({					\
 	size_t __size_ret;						\
 	unsigned int __vcpu_vq;						\
@@ -991,6 +1030,7 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	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;
+	case ZCR_EL1:		*val = read_sysreg_s(SYS_ZCR_EL12);	break;
 	default:		return false;
 	}
 
@@ -1036,6 +1076,7 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	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;
+	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
 	default:		return false;
 	}
 
@@ -1145,7 +1186,7 @@ int __init populate_nv_trap_config(void);
 bool lock_all_vcpus(struct kvm *kvm);
 void unlock_all_vcpus(struct kvm *kvm);
 
-void kvm_init_sysreg(struct kvm_vcpu *);
+void kvm_calculate_traps(struct kvm_vcpu *vcpu);
 
 /* MMIO helpers */
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
@@ -1306,6 +1347,7 @@ void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu);
 
 int __init kvm_set_ipa_limit(void);
+u32 kvm_get_pa_bits(struct kvm *kvm);
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
 struct kvm *kvm_arch_alloc_vm(void);
@@ -1355,6 +1397,24 @@ static inline void kvm_hyp_reserve(void) { }
 void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
 bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
 
+static inline u64 *__vm_id_reg(struct kvm_arch *ka, u32 reg)
+{
+	switch (reg) {
+	case sys_reg(3, 0, 0, 1, 0) ... sys_reg(3, 0, 0, 7, 7):
+		return &ka->id_regs[IDREG_IDX(reg)];
+	case SYS_CTR_EL0:
+		return &ka->ctr_el0;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+}
+
+#define kvm_read_vm_id_reg(kvm, reg)					\
+	({ u64 __val = *__vm_id_reg(&(kvm)->arch, reg); __val; })
+
+void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
+
 #define __expand_field_sign_unsigned(id, fld, val)			\
 	((u64)SYS_FIELD_VALUE(id, fld, val))
 
@@ -1371,7 +1431,7 @@ bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
 
 #define get_idreg_field_unsigned(kvm, id, fld)				\
 	({								\
-		u64 __val = IDREG((kvm), SYS_##id);			\
+		u64 __val = kvm_read_vm_id_reg((kvm), SYS_##id);	\
 		FIELD_GET(id##_##fld##_MASK, __val);			\
 	})
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index b05bceca3385..c838309e4ec4 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -124,8 +124,8 @@ void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
 #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);
+void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
+		void (*fn)(void));
 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);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index d5e48d870461..216ca424bb16 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -98,6 +98,7 @@ alternative_cb_end
 #include <asm/mmu_context.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
+#include <asm/kvm_nested.h>
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
@@ -165,6 +166,10 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
 int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
 void __init free_hyp_pgds(void);
 
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
+
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
 void kvm_uninit_stage2_mmu(struct kvm *kvm);
@@ -326,5 +331,26 @@ static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
 {
 	return container_of(mmu->arch, struct kvm, arch);
 }
+
+static inline u64 get_vmid(u64 vttbr)
+{
+	return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >>
+		VTTBR_VMID_SHIFT;
+}
+
+static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu)
+{
+	return !(mmu->tlb_vttbr & VTTBR_CNP_BIT);
+}
+
+static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
+{
+	/*
+	 * Be careful, mmu may not be fully initialised so do look at
+	 * *any* of its fields.
+	 */
+	return &kvm->arch.mmu != mmu;
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 5e0ab0596246..5b06c31035a2 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -5,6 +5,7 @@
 #include <linux/bitfield.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_pgtable.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
@@ -32,7 +33,7 @@ static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
 
 static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
 {
-	u64 cpacr_el1 = 0;
+	u64 cpacr_el1 = CPACR_ELx_RES1;
 
 	if (cptr_el2 & CPTR_EL2_TTA)
 		cpacr_el1 |= CPACR_ELx_TTA;
@@ -41,6 +42,8 @@ static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
 	if (!(cptr_el2 & CPTR_EL2_TZ))
 		cpacr_el1 |= CPACR_ELx_ZEN;
 
+	cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM);
+
 	return cpacr_el1;
 }
 
@@ -61,6 +64,125 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
 }
 
 extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
+extern void kvm_init_nested(struct kvm *kvm);
+extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
+extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
+extern struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu);
+
+union tlbi_info;
+
+extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
+				       const union tlbi_info *info,
+				       void (*)(struct kvm_s2_mmu *,
+						const union tlbi_info *));
+extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
+extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+
+struct kvm_s2_trans {
+	phys_addr_t output;
+	unsigned long block_size;
+	bool writable;
+	bool readable;
+	int level;
+	u32 esr;
+	u64 upper_attr;
+};
+
+static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans)
+{
+	return trans->output;
+}
+
+static inline unsigned long kvm_s2_trans_size(struct kvm_s2_trans *trans)
+{
+	return trans->block_size;
+}
+
+static inline u32 kvm_s2_trans_esr(struct kvm_s2_trans *trans)
+{
+	return trans->esr;
+}
+
+static inline bool kvm_s2_trans_readable(struct kvm_s2_trans *trans)
+{
+	return trans->readable;
+}
+
+static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans)
+{
+	return trans->writable;
+}
+
+static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans)
+{
+	return !(trans->upper_attr & BIT(54));
+}
+
+extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
+			      struct kvm_s2_trans *result);
+extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
+				    struct kvm_s2_trans *trans);
+extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
+extern void kvm_nested_s2_wp(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_flush(struct kvm *kvm);
+
+unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
+
+static inline bool kvm_supported_tlbi_s1e1_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+
+	if (!(sys_reg_Op0(instr) == TLBI_Op0 &&
+	      sys_reg_Op1(instr) == TLBI_Op1_EL1))
+		return false;
+
+	if (!(sys_reg_CRn(instr) == TLBI_CRn_XS ||
+	      (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	       kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))))
+		return false;
+
+	if (CRm == TLBI_CRm_nROS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS ||
+	     CRm == TLBI_CRm_RNS) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	return true;
+}
+
+static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+
+	if (!(sys_reg_Op0(instr) == TLBI_Op0 &&
+	      sys_reg_Op1(instr) == TLBI_Op1_EL2))
+		return false;
+
+	if (!(sys_reg_CRn(instr) == TLBI_CRn_XS ||
+	      (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	       kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAIS || CRm == TLBI_CRm_IPAONS)
+		return false;
+
+	if (CRm == TLBI_CRm_nROS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	if ((CRm == TLBI_CRm_RIS || CRm == TLBI_CRm_ROS ||
+	     CRm == TLBI_CRm_RNS) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	return true;
+}
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
 
@@ -76,4 +198,11 @@ static inline bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr)
 }
 #endif
 
+#define KVM_NV_GUEST_MAP_SZ	(KVM_PGTABLE_PROT_SW1 | KVM_PGTABLE_PROT_SW0)
+
+static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans)
+{
+	return FIELD_PREP(KVM_NV_GUEST_MAP_SZ, trans->level);
+}
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index af3b206fa423..be4152819456 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -654,6 +654,23 @@
 #define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
 
 /* TLBI instructions */
+#define TLBI_Op0	1
+
+#define TLBI_Op1_EL1	0	/* Accessible from EL1 or higher */
+#define TLBI_Op1_EL2	4	/* Accessible from EL2 or higher */
+
+#define TLBI_CRn_XS	8	/* Extra Slow (the common one) */
+#define TLBI_CRn_nXS	9	/* not Extra Slow (which nobody uses)*/
+
+#define TLBI_CRm_IPAIS	0	/* S2 Inner-Shareable */
+#define TLBI_CRm_nROS	1	/* non-Range, Outer-Sharable */
+#define TLBI_CRm_RIS	2	/* Range, Inner-Sharable */
+#define TLBI_CRm_nRIS	3	/* non-Range, Inner-Sharable */
+#define TLBI_CRm_IPAONS	4	/* S2 Outer and Non-Shareable */
+#define TLBI_CRm_ROS	5	/* Range, Outer-Sharable */
+#define TLBI_CRm_RNS	6	/* Range, Non-Sharable */
+#define TLBI_CRm_nRNS	7	/* non-Range, Non-Sharable */
+
 #define OP_TLBI_VMALLE1OS		sys_insn(1, 0, 8, 1, 0)
 #define OP_TLBI_VAE1OS			sys_insn(1, 0, 8, 1, 1)
 #define OP_TLBI_ASIDE1OS		sys_insn(1, 0, 8, 1, 2)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 81496083c041..27de1dddb0ab 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -128,6 +128,7 @@ int main(void)
   DEFINE(VCPU_FAULT_DISR,	offsetof(struct kvm_vcpu, arch.fault.disr_el1));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_cpu_context, regs));
+  DEFINE(CPU_ELR_EL2,		offsetof(struct kvm_cpu_context, sys_regs[ELR_EL2]));
   DEFINE(CPU_RGSR_EL1,		offsetof(struct kvm_cpu_context, sys_regs[RGSR_EL1]));
   DEFINE(CPU_GCR_EL1,		offsetof(struct kvm_cpu_context, sys_regs[GCR_EL1]));
   DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 64f2ecbdfe5c..024a7b245056 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -312,9 +312,7 @@ static int call_break_hook(struct pt_regs *regs, unsigned long esr)
 	 * entirely not preemptible, and we can use rcu list safely here.
 	 */
 	list_for_each_entry_rcu(hook, list, node) {
-		unsigned long comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
-
-		if ((comment & ~hook->mask) == hook->imm)
+		if ((esr_brk_comment(esr) & ~hook->mask) == hook->imm)
 			fn = hook->fn;
 	}
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 215e6d7f2df8..9e22683aa921 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -1105,8 +1105,6 @@ static struct break_hook ubsan_break_hook = {
 };
 #endif
 
-#define esr_comment(esr) ((esr) & ESR_ELx_BRK64_ISS_COMMENT_MASK)
-
 /*
  * Initial handler for AArch64 BRK exceptions
  * This handler only used until debug_traps_init().
@@ -1115,15 +1113,15 @@ int __init early_brk64(unsigned long addr, unsigned long esr,
 		struct pt_regs *regs)
 {
 #ifdef CONFIG_CFI_CLANG
-	if ((esr_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE)
+	if (esr_is_cfi_brk(esr))
 		return cfi_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 #ifdef CONFIG_KASAN_SW_TAGS
-	if ((esr_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
+	if ((esr_brk_comment(esr) & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 #ifdef CONFIG_UBSAN_TRAP
-	if ((esr_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM)
+	if ((esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM)
 		return ubsan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 59716789fe0f..c818818398a5 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -48,6 +48,15 @@
 
 static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;
 
+enum kvm_wfx_trap_policy {
+	KVM_WFX_NOTRAP_SINGLE_TASK, /* Default option */
+	KVM_WFX_NOTRAP,
+	KVM_WFX_TRAP,
+};
+
+static enum kvm_wfx_trap_policy kvm_wfi_trap_policy __read_mostly = KVM_WFX_NOTRAP_SINGLE_TASK;
+static enum kvm_wfx_trap_policy kvm_wfe_trap_policy __read_mostly = KVM_WFX_NOTRAP_SINGLE_TASK;
+
 DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector);
 
 DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
@@ -170,6 +179,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_unlock(&kvm->lock);
 #endif
 
+	kvm_init_nested(kvm);
+
 	ret = kvm_share_hyp(kvm, kvm + 1);
 	if (ret)
 		return ret;
@@ -546,11 +557,32 @@ static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool kvm_vcpu_should_clear_twi(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(kvm_wfi_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK))
+		return kvm_wfi_trap_policy == KVM_WFX_NOTRAP;
+
+	return single_task_running() &&
+	       (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) ||
+		vcpu->kvm->arch.vgic.nassgireq);
+}
+
+static bool kvm_vcpu_should_clear_twe(struct kvm_vcpu *vcpu)
+{
+	if (unlikely(kvm_wfe_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK))
+		return kvm_wfe_trap_policy == KVM_WFX_NOTRAP;
+
+	return single_task_running();
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
+	if (vcpu_has_nv(vcpu))
+		kvm_vcpu_load_hw_mmu(vcpu);
+
 	mmu = vcpu->arch.hw_mmu;
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
@@ -579,10 +611,15 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
 		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
 
-	if (single_task_running())
-		vcpu_clear_wfx_traps(vcpu);
+	if (kvm_vcpu_should_clear_twe(vcpu))
+		vcpu->arch.hcr_el2 &= ~HCR_TWE;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TWE;
+
+	if (kvm_vcpu_should_clear_twi(vcpu))
+		vcpu->arch.hcr_el2 &= ~HCR_TWI;
 	else
-		vcpu_set_wfx_traps(vcpu);
+		vcpu->arch.hcr_el2 |= HCR_TWI;
 
 	vcpu_set_pauth_traps(vcpu);
 
@@ -601,6 +638,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_timer_vcpu_put(vcpu);
 	kvm_vgic_put(vcpu);
 	kvm_vcpu_pmu_restore_host(vcpu);
+	if (vcpu_has_nv(vcpu))
+		kvm_vcpu_put_hw_mmu(vcpu);
 	kvm_arm_vmid_clear_active();
 
 	vcpu_clear_on_unsupported_cpu(vcpu);
@@ -797,7 +836,7 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	 * This needs to happen after NV has imposed its own restrictions on
 	 * the feature set
 	 */
-	kvm_init_sysreg(vcpu);
+	kvm_calculate_traps(vcpu);
 
 	ret = kvm_timer_enable(vcpu);
 	if (ret)
@@ -1419,11 +1458,6 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu,
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features))
 		return -EINVAL;
 
-	/* Disallow NV+SVE for the time being */
-	if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features) &&
-	    test_bit(KVM_ARM_VCPU_SVE, &features))
-		return -EINVAL;
-
 	if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features))
 		return 0;
 
@@ -1459,6 +1493,10 @@ static int kvm_setup_vcpu(struct kvm_vcpu *vcpu)
 	if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu)
 		ret = kvm_arm_set_default_pmu(kvm);
 
+	/* Prepare for nested if required */
+	if (!ret && vcpu_has_nv(vcpu))
+		ret = kvm_vcpu_init_nested(vcpu);
+
 	return ret;
 }
 
@@ -2858,6 +2896,36 @@ static int __init early_kvm_mode_cfg(char *arg)
 }
 early_param("kvm-arm.mode", early_kvm_mode_cfg);
 
+static int __init early_kvm_wfx_trap_policy_cfg(char *arg, enum kvm_wfx_trap_policy *p)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (strcmp(arg, "trap") == 0) {
+		*p = KVM_WFX_TRAP;
+		return 0;
+	}
+
+	if (strcmp(arg, "notrap") == 0) {
+		*p = KVM_WFX_NOTRAP;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int __init early_kvm_wfi_trap_policy_cfg(char *arg)
+{
+	return early_kvm_wfx_trap_policy_cfg(arg, &kvm_wfi_trap_policy);
+}
+early_param("kvm-arm.wfi_trap_policy", early_kvm_wfi_trap_policy_cfg);
+
+static int __init early_kvm_wfe_trap_policy_cfg(char *arg)
+{
+	return early_kvm_wfx_trap_policy_cfg(arg, &kvm_wfe_trap_policy);
+}
+early_param("kvm-arm.wfe_trap_policy", early_kvm_wfe_trap_policy_cfg);
+
 enum kvm_mode kvm_get_mode(void)
 {
 	return kvm_mode;
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 54090967a335..05166eccea0a 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -79,6 +79,12 @@ enum cgt_group_id {
 	CGT_MDCR_E2TB,
 	CGT_MDCR_TDCC,
 
+	CGT_CPACR_E0POE,
+	CGT_CPTR_TAM,
+	CGT_CPTR_TCPAC,
+
+	CGT_HCRX_TCR2En,
+
 	/*
 	 * Anything after this point is a combination of coarse trap
 	 * controls, which must all be evaluated to decide what to do.
@@ -89,6 +95,7 @@ enum cgt_group_id {
 	CGT_HCR_TTLB_TTLBIS,
 	CGT_HCR_TTLB_TTLBOS,
 	CGT_HCR_TVM_TRVM,
+	CGT_HCR_TVM_TRVM_HCRX_TCR2En,
 	CGT_HCR_TPU_TICAB,
 	CGT_HCR_TPU_TOCU,
 	CGT_HCR_NV1_nNV2_ENSCXT,
@@ -106,6 +113,8 @@ enum cgt_group_id {
 	CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__,
 	CGT_CNTHCTL_EL1PTEN,
 
+	CGT_CPTR_TTA,
+
 	/* Must be last */
 	__NR_CGT_GROUP_IDS__
 };
@@ -345,6 +354,30 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= MDCR_EL2_TDCC,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
+	[CGT_CPACR_E0POE] = {
+		.index		= CPTR_EL2,
+		.value		= CPACR_ELx_E0POE,
+		.mask		= CPACR_ELx_E0POE,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_CPTR_TAM] = {
+		.index		= CPTR_EL2,
+		.value		= CPTR_EL2_TAM,
+		.mask		= CPTR_EL2_TAM,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_CPTR_TCPAC] = {
+		.index		= CPTR_EL2,
+		.value		= CPTR_EL2_TCPAC,
+		.mask		= CPTR_EL2_TCPAC,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_HCRX_TCR2En] = {
+		.index		= HCRX_EL2,
+		.value 		= 0,
+		.mask		= HCRX_EL2_TCR2En,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 };
 
 #define MCB(id, ...)						\
@@ -359,6 +392,8 @@ static const enum cgt_group_id *coarse_control_combo[] = {
 	MCB(CGT_HCR_TTLB_TTLBIS,	CGT_HCR_TTLB, CGT_HCR_TTLBIS),
 	MCB(CGT_HCR_TTLB_TTLBOS,	CGT_HCR_TTLB, CGT_HCR_TTLBOS),
 	MCB(CGT_HCR_TVM_TRVM,		CGT_HCR_TVM, CGT_HCR_TRVM),
+	MCB(CGT_HCR_TVM_TRVM_HCRX_TCR2En,
+					CGT_HCR_TVM, CGT_HCR_TRVM, CGT_HCRX_TCR2En),
 	MCB(CGT_HCR_TPU_TICAB,		CGT_HCR_TPU, CGT_HCR_TICAB),
 	MCB(CGT_HCR_TPU_TOCU,		CGT_HCR_TPU, CGT_HCR_TOCU),
 	MCB(CGT_HCR_NV1_nNV2_ENSCXT,	CGT_HCR_NV1_nNV2, CGT_HCR_ENSCXT),
@@ -410,12 +445,26 @@ static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu)
 	return BEHAVE_FORWARD_ANY;
 }
 
+static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu)
+{
+	u64 val = __vcpu_sys_reg(vcpu, CPTR_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		val = translate_cptr_el2_to_cpacr_el1(val);
+
+	if (val & CPACR_ELx_TTA)
+		return BEHAVE_FORWARD_ANY;
+
+	return BEHAVE_HANDLE_LOCALLY;
+}
+
 #define CCC(id, fn)				\
 	[id - __COMPLEX_CONDITIONS__] = fn
 
 static const complex_condition_check ccc[] = {
 	CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten),
 	CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten),
+	CCC(CGT_CPTR_TTA, check_cptr_tta),
 };
 
 /*
@@ -622,6 +671,7 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_MAIR_EL1,		CGT_HCR_TVM_TRVM),
 	SR_TRAP(SYS_AMAIR_EL1,		CGT_HCR_TVM_TRVM),
 	SR_TRAP(SYS_CONTEXTIDR_EL1,	CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_TCR2_EL1,		CGT_HCR_TVM_TRVM_HCRX_TCR2En),
 	SR_TRAP(SYS_DC_ZVA,		CGT_HCR_TDZ),
 	SR_TRAP(SYS_DC_GVA,		CGT_HCR_TDZ),
 	SR_TRAP(SYS_DC_GZVA,		CGT_HCR_TDZ),
@@ -1000,6 +1050,59 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_TRBPTR_EL1, 	CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBSR_EL1, 		CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBTRG_EL1,		CGT_MDCR_E2TB),
+	SR_TRAP(SYS_CPACR_EL1,		CGT_CPTR_TCPAC),
+	SR_TRAP(SYS_AMUSERENR_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCFGR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCGCR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENCLR0_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENCLR1_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENSET0_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENSET1_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(4),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(5),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(6),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(7),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(8),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(9),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(10),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(11),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(12),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(13),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(14),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(15),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(4),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(5),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(6),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(7),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(8),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(9),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(10),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(11),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(12),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(13),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(14),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(15),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_POR_EL0,		CGT_CPACR_E0POE),
+	/* op0=2, op1=1, and CRn<0b1000 */
+	SR_RANGE_TRAP(sys_reg(2, 1, 0, 0, 0),
+		      sys_reg(2, 1, 7, 15, 7), CGT_CPTR_TTA),
 	SR_TRAP(SYS_CNTP_TVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTP_CVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTP_CTL_EL0,	CGT_CNTHCTL_EL1PTEN),
@@ -1071,6 +1174,7 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_TPIDRRO_EL0,		HFGxTR, TPIDRRO_EL0, 1),
 	SR_FGT(SYS_TPIDR_EL1,		HFGxTR, TPIDR_EL1, 1),
 	SR_FGT(SYS_TCR_EL1,		HFGxTR, TCR_EL1, 1),
+	SR_FGT(SYS_TCR2_EL1,		HFGxTR, TCR_EL1, 1),
 	SR_FGT(SYS_SCXTNUM_EL0,		HFGxTR, SCXTNUM_EL0, 1),
 	SR_FGT(SYS_SCXTNUM_EL1, 	HFGxTR, SCXTNUM_EL1, 1),
 	SR_FGT(SYS_SCTLR_EL1, 		HFGxTR, SCTLR_EL1, 1),
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 521b32868d0d..c53e5b14038d 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -178,7 +178,13 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	if (guest_owns_fp_regs()) {
 		if (vcpu_has_sve(vcpu)) {
-			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+			u64 zcr = read_sysreg_el1(SYS_ZCR);
+
+			/*
+			 * If the vCPU is in the hyp context then ZCR_EL1 is
+			 * loaded with its vEL2 counterpart.
+			 */
+			__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr;
 
 			/*
 			 * Restore the VL that was saved when bound to the CPU,
@@ -189,11 +195,14 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 			 * Note that this means that at guest exit ZCR_EL1 is
 			 * not necessarily the same as on guest entry.
 			 *
-			 * Restoring the VL isn't needed in VHE mode since
-			 * ZCR_EL2 (accessed via ZCR_EL1) would fulfill the same
-			 * role when doing the save from EL2.
+			 * ZCR_EL2 holds the guest hypervisor's VL when running
+			 * a nested guest, which could be smaller than the
+			 * max for the vCPU. Similar to above, we first need to
+			 * switch to a VL consistent with the layout of the
+			 * vCPU's SVE state. KVM support for NV implies VHE, so
+			 * using the ZCR_EL1 alias is safe.
 			 */
-			if (!has_vhe())
+			if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)))
 				sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
 						       SYS_ZCR_EL1);
 		}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index b037f0a0e27e..d7c2990e7c9e 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -94,11 +94,19 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Guest access to FP/ASIMD registers are routed to this handler only
- * when the system doesn't support FP/ASIMD.
+ * This handles the cases where the system does not support FP/ASIMD or when
+ * we are running nested virtualization and the guest hypervisor is trapping
+ * FP/ASIMD accesses by its guest guest.
+ *
+ * All other handling of guest vs. host FP/ASIMD register state is handled in
+ * fixup_guest_exit().
  */
-static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
+static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu)
 {
+	if (guest_hyp_fpsimd_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	/* This is the case when the system doesn't support FP/ASIMD. */
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
@@ -209,6 +217,9 @@ static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
  */
 static int handle_sve(struct kvm_vcpu *vcpu)
 {
+	if (guest_hyp_sve_traps_enabled(vcpu))
+		return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
@@ -304,7 +315,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BKPT32]	= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
-	[ESR_ELx_EC_FP_ASIMD]	= handle_no_fpsimd,
+	[ESR_ELx_EC_FP_ASIMD]	= kvm_handle_fpasimd,
 	[ESR_ELx_EC_PAC]	= kvm_handle_ptrauth,
 };
 
@@ -411,6 +422,20 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
 }
 
+static void print_nvhe_hyp_panic(const char *name, u64 panic_addr)
+{
+	kvm_err("nVHE hyp %s at: [<%016llx>] %pB!\n", name, panic_addr,
+		(void *)(panic_addr + kaslr_offset()));
+}
+
+static void kvm_nvhe_report_cfi_failure(u64 panic_addr)
+{
+	print_nvhe_hyp_panic("CFI failure", panic_addr);
+
+	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE))
+		kvm_err(" (CONFIG_CFI_PERMISSIVE ignored for hyp failures)\n");
+}
+
 void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 					      u64 elr_virt, u64 elr_phys,
 					      u64 par, uintptr_t vcpu,
@@ -423,7 +448,7 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 	if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) {
 		kvm_err("Invalid host exception to nVHE hyp!\n");
 	} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
-		   (esr & ESR_ELx_BRK64_ISS_COMMENT_MASK) == BUG_BRK_IMM) {
+		   esr_brk_comment(esr) == BUG_BRK_IMM) {
 		const char *file = NULL;
 		unsigned int line = 0;
 
@@ -439,11 +464,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
 		if (file)
 			kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
 		else
-			kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr,
-					(void *)(panic_addr + kaslr_offset()));
+			print_nvhe_hyp_panic("BUG", panic_addr);
+	} else if (IS_ENABLED(CONFIG_CFI_CLANG) && esr_is_cfi_brk(esr)) {
+		kvm_nvhe_report_cfi_failure(panic_addr);
 	} else {
-		kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr,
-				(void *)(panic_addr + kaslr_offset()));
+		print_nvhe_hyp_panic("panic", panic_addr);
 	}
 
 	/* Dump the nVHE hypervisor backtrace */
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index f3aa7738b477..4433a234aa9b 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -83,6 +83,14 @@ alternative_else_nop_endif
 	eret
 	sb
 
+SYM_INNER_LABEL(__guest_exit_restore_elr_and_panic, SYM_L_GLOBAL)
+	// x2-x29,lr: vcpu regs
+	// vcpu x0-x1 on the stack
+
+	adr_this_cpu x0, kvm_hyp_ctxt, x1
+	ldr	x0, [x0, #CPU_ELR_EL2]
+	msr	elr_el2, x0
+
 SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 	// x2-x29,lr: vcpu regs
 	// vcpu x0-x1 on the stack
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 0c4de44534b7..f59ccfe11ab9 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -314,11 +314,24 @@ static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The vCPU's saved SVE state layout always matches the max VL of the
+	 * vCPU. Start off with the max VL so we can load the SVE state.
+	 */
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
 	__sve_restore_state(vcpu_sve_pffr(vcpu),
 			    &vcpu->arch.ctxt.fp_regs.fpsr,
 			    true);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
+
+	/*
+	 * The effective VL for a VM could differ from the max VL when running a
+	 * nested guest, as the guest hypervisor could select a smaller VL. Slap
+	 * that into hardware before wrapping up.
+	 */
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+		sve_cond_update_zcr_vq(__vcpu_sys_reg(vcpu, ZCR_EL2), SYS_ZCR_EL2);
+
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR);
 }
 
 static inline void __hyp_sve_save_host(void)
@@ -354,10 +367,19 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Only handle traps the vCPU can support here: */
 	switch (esr_ec) {
 	case ESR_ELx_EC_FP_ASIMD:
+		/* Forward traps to the guest hypervisor as required */
+		if (guest_hyp_fpsimd_traps_enabled(vcpu))
+			return false;
 		break;
+	case ESR_ELx_EC_SYS64:
+		if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu)))
+			return false;
+		fallthrough;
 	case ESR_ELx_EC_SVE:
 		if (!sve_guest)
 			return false;
+		if (guest_hyp_sve_traps_enabled(vcpu))
+			return false;
 		break;
 	default:
 		return false;
@@ -693,7 +715,7 @@ guest:
 
 static inline void __kvm_unexpected_el2_exception(void)
 {
-	extern char __guest_exit_panic[];
+	extern char __guest_exit_restore_elr_and_panic[];
 	unsigned long addr, fixup;
 	struct kvm_exception_table_entry *entry, *end;
 	unsigned long elr_el2 = read_sysreg(elr_el2);
@@ -715,7 +737,8 @@ static inline void __kvm_unexpected_el2_exception(void)
 	}
 
 	/* Trigger a panic after restoring the hyp context. */
-	write_sysreg(__guest_exit_panic, elr_el2);
+	this_cpu_ptr(&kvm_hyp_ctxt)->sys_regs[ELR_EL2] = elr_el2;
+	write_sysreg(__guest_exit_restore_elr_and_panic, elr_el2);
 }
 
 #endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 4be6a7fa0070..4c0fdabaf8ae 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -55,6 +55,17 @@ static inline bool ctxt_has_s1pie(struct kvm_cpu_context *ctxt)
 	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, S1PIE, IMP);
 }
 
+static inline bool ctxt_has_tcrx(struct kvm_cpu_context *ctxt)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!cpus_have_final_cap(ARM64_HAS_TCR2))
+		return false;
+
+	vcpu = ctxt_to_vcpu(ctxt);
+	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, TCRX, IMP);
+}
+
 static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt_sys_reg(ctxt, SCTLR_EL1)	= read_sysreg_el1(SYS_SCTLR);
@@ -62,8 +73,14 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, TTBR0_EL1)	= read_sysreg_el1(SYS_TTBR0);
 	ctxt_sys_reg(ctxt, TTBR1_EL1)	= read_sysreg_el1(SYS_TTBR1);
 	ctxt_sys_reg(ctxt, TCR_EL1)	= read_sysreg_el1(SYS_TCR);
-	if (cpus_have_final_cap(ARM64_HAS_TCR2))
+	if (ctxt_has_tcrx(ctxt)) {
 		ctxt_sys_reg(ctxt, TCR2_EL1)	= read_sysreg_el1(SYS_TCR2);
+
+		if (ctxt_has_s1pie(ctxt)) {
+			ctxt_sys_reg(ctxt, PIR_EL1)	= read_sysreg_el1(SYS_PIR);
+			ctxt_sys_reg(ctxt, PIRE0_EL1)	= read_sysreg_el1(SYS_PIRE0);
+		}
+	}
 	ctxt_sys_reg(ctxt, ESR_EL1)	= read_sysreg_el1(SYS_ESR);
 	ctxt_sys_reg(ctxt, AFSR0_EL1)	= read_sysreg_el1(SYS_AFSR0);
 	ctxt_sys_reg(ctxt, AFSR1_EL1)	= read_sysreg_el1(SYS_AFSR1);
@@ -73,10 +90,6 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
 	ctxt_sys_reg(ctxt, AMAIR_EL1)	= read_sysreg_el1(SYS_AMAIR);
 	ctxt_sys_reg(ctxt, CNTKCTL_EL1)	= read_sysreg_el1(SYS_CNTKCTL);
-	if (ctxt_has_s1pie(ctxt)) {
-		ctxt_sys_reg(ctxt, PIR_EL1)	= read_sysreg_el1(SYS_PIR);
-		ctxt_sys_reg(ctxt, PIRE0_EL1)	= read_sysreg_el1(SYS_PIRE0);
-	}
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg_par();
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
@@ -138,8 +151,14 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1),	SYS_CPACR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1),	SYS_TTBR0);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1),	SYS_TTBR1);
-	if (cpus_have_final_cap(ARM64_HAS_TCR2))
+	if (ctxt_has_tcrx(ctxt)) {
 		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR2_EL1),	SYS_TCR2);
+
+		if (ctxt_has_s1pie(ctxt)) {
+			write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1),	SYS_PIR);
+			write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1),	SYS_PIRE0);
+		}
+	}
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1),	SYS_ESR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1),	SYS_AFSR0);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1),	SYS_AFSR1);
@@ -149,10 +168,6 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1),	SYS_AMAIR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL);
-	if (ctxt_has_s1pie(ctxt)) {
-		write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1),	SYS_PIR);
-		write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1),	SYS_PIRE0);
-	}
 	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
 	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
index d9fd5e6c7d3c..146e0aebfa1c 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
@@ -9,7 +9,7 @@
 #include <asm/kvm_host.h>
 
 #define FFA_MIN_FUNC_NUM 0x60
-#define FFA_MAX_FUNC_NUM 0x7F
+#define FFA_MAX_FUNC_NUM 0xFF
 
 int hyp_ffa_init(void *pages);
 bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 50fa0ffb6b7e..782b34b004be 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -89,9 +89,9 @@ quiet_cmd_hyprel = HYPREL  $@
 quiet_cmd_hypcopy = HYPCOPY $@
       cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
 
-# Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
-# This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
-KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
 # Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile'
 # when profile optimization is applied. gen-hyprel does not support SHT_REL and
 # causes a build failure. Remove profile optimization flags.
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index efb053af331c..e715c157c2c4 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -67,6 +67,9 @@ struct kvm_ffa_buffers {
  */
 static struct kvm_ffa_buffers hyp_buffers;
 static struct kvm_ffa_buffers host_buffers;
+static u32 hyp_ffa_version;
+static bool has_version_negotiated;
+static hyp_spinlock_t version_lock;
 
 static void ffa_to_smccc_error(struct arm_smccc_res *res, u64 ffa_errno)
 {
@@ -462,7 +465,7 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id,
 	memcpy(buf, host_buffers.tx, fraglen);
 
 	ep_mem_access = (void *)buf +
-			ffa_mem_desc_offset(buf, 0, FFA_VERSION_1_0);
+			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
 	offset = ep_mem_access->composite_off;
 	if (!offset || buf->ep_count != 1 || buf->sender_id != HOST_FFA_ID) {
 		ret = FFA_RET_INVALID_PARAMETERS;
@@ -541,7 +544,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
 	fraglen = res->a2;
 
 	ep_mem_access = (void *)buf +
-			ffa_mem_desc_offset(buf, 0, FFA_VERSION_1_0);
+			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
 	offset = ep_mem_access->composite_off;
 	/*
 	 * We can trust the SPMD to get this right, but let's at least
@@ -651,6 +654,132 @@ out_handled:
 	return true;
 }
 
+static int hyp_ffa_post_init(void)
+{
+	size_t min_rxtx_sz;
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res);
+	if (res.a0 != FFA_SUCCESS)
+		return -EOPNOTSUPP;
+
+	if (res.a2 != HOST_FFA_ID)
+		return -EINVAL;
+
+	arm_smccc_1_1_smc(FFA_FEATURES, FFA_FN64_RXTX_MAP,
+			  0, 0, 0, 0, 0, 0, &res);
+	if (res.a0 != FFA_SUCCESS)
+		return -EOPNOTSUPP;
+
+	switch (res.a2) {
+	case FFA_FEAT_RXTX_MIN_SZ_4K:
+		min_rxtx_sz = SZ_4K;
+		break;
+	case FFA_FEAT_RXTX_MIN_SZ_16K:
+		min_rxtx_sz = SZ_16K;
+		break;
+	case FFA_FEAT_RXTX_MIN_SZ_64K:
+		min_rxtx_sz = SZ_64K;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (min_rxtx_sz > PAGE_SIZE)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static void do_ffa_version(struct arm_smccc_res *res,
+			   struct kvm_cpu_context *ctxt)
+{
+	DECLARE_REG(u32, ffa_req_version, ctxt, 1);
+
+	if (FFA_MAJOR_VERSION(ffa_req_version) != 1) {
+		res->a0 = FFA_RET_NOT_SUPPORTED;
+		return;
+	}
+
+	hyp_spin_lock(&version_lock);
+	if (has_version_negotiated) {
+		res->a0 = hyp_ffa_version;
+		goto unlock;
+	}
+
+	/*
+	 * If the client driver tries to downgrade the version, we need to ask
+	 * first if TEE supports it.
+	 */
+	if (FFA_MINOR_VERSION(ffa_req_version) < FFA_MINOR_VERSION(hyp_ffa_version)) {
+		arm_smccc_1_1_smc(FFA_VERSION, ffa_req_version, 0,
+				  0, 0, 0, 0, 0,
+				  res);
+		if (res->a0 == FFA_RET_NOT_SUPPORTED)
+			goto unlock;
+
+		hyp_ffa_version = ffa_req_version;
+	}
+
+	if (hyp_ffa_post_init())
+		res->a0 = FFA_RET_NOT_SUPPORTED;
+	else {
+		has_version_negotiated = true;
+		res->a0 = hyp_ffa_version;
+	}
+unlock:
+	hyp_spin_unlock(&version_lock);
+}
+
+static void do_ffa_part_get(struct arm_smccc_res *res,
+			    struct kvm_cpu_context *ctxt)
+{
+	DECLARE_REG(u32, uuid0, ctxt, 1);
+	DECLARE_REG(u32, uuid1, ctxt, 2);
+	DECLARE_REG(u32, uuid2, ctxt, 3);
+	DECLARE_REG(u32, uuid3, ctxt, 4);
+	DECLARE_REG(u32, flags, ctxt, 5);
+	u32 count, partition_sz, copy_sz;
+
+	hyp_spin_lock(&host_buffers.lock);
+	if (!host_buffers.rx) {
+		ffa_to_smccc_res(res, FFA_RET_BUSY);
+		goto out_unlock;
+	}
+
+	arm_smccc_1_1_smc(FFA_PARTITION_INFO_GET, uuid0, uuid1,
+			  uuid2, uuid3, flags, 0, 0,
+			  res);
+
+	if (res->a0 != FFA_SUCCESS)
+		goto out_unlock;
+
+	count = res->a2;
+	if (!count)
+		goto out_unlock;
+
+	if (hyp_ffa_version > FFA_VERSION_1_0) {
+		/* Get the number of partitions deployed in the system */
+		if (flags & 0x1)
+			goto out_unlock;
+
+		partition_sz  = res->a3;
+	} else {
+		/* FFA_VERSION_1_0 lacks the size in the response */
+		partition_sz = FFA_1_0_PARTITON_INFO_SZ;
+	}
+
+	copy_sz = partition_sz * count;
+	if (copy_sz > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
+		ffa_to_smccc_res(res, FFA_RET_ABORTED);
+		goto out_unlock;
+	}
+
+	memcpy(host_buffers.rx, hyp_buffers.rx, copy_sz);
+out_unlock:
+	hyp_spin_unlock(&host_buffers.lock);
+}
+
 bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 {
 	struct arm_smccc_res res;
@@ -671,6 +800,11 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 	if (!is_ffa_call(func_id))
 		return false;
 
+	if (!has_version_negotiated && func_id != FFA_VERSION) {
+		ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS);
+		goto out_handled;
+	}
+
 	switch (func_id) {
 	case FFA_FEATURES:
 		if (!do_ffa_features(&res, host_ctxt))
@@ -697,6 +831,12 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 	case FFA_MEM_FRAG_TX:
 		do_ffa_mem_frag_tx(&res, host_ctxt);
 		goto out_handled;
+	case FFA_VERSION:
+		do_ffa_version(&res, host_ctxt);
+		goto out_handled;
+	case FFA_PARTITION_INFO_GET:
+		do_ffa_part_get(&res, host_ctxt);
+		goto out_handled;
 	}
 
 	if (ffa_call_supported(func_id))
@@ -711,13 +851,12 @@ out_handled:
 int hyp_ffa_init(void *pages)
 {
 	struct arm_smccc_res res;
-	size_t min_rxtx_sz;
 	void *tx, *rx;
 
 	if (kvm_host_psci_config.smccc_version < ARM_SMCCC_VERSION_1_2)
 		return 0;
 
-	arm_smccc_1_1_smc(FFA_VERSION, FFA_VERSION_1_0, 0, 0, 0, 0, 0, 0, &res);
+	arm_smccc_1_1_smc(FFA_VERSION, FFA_VERSION_1_1, 0, 0, 0, 0, 0, 0, &res);
 	if (res.a0 == FFA_RET_NOT_SUPPORTED)
 		return 0;
 
@@ -737,34 +876,10 @@ int hyp_ffa_init(void *pages)
 	if (FFA_MAJOR_VERSION(res.a0) != 1)
 		return -EOPNOTSUPP;
 
-	arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res);
-	if (res.a0 != FFA_SUCCESS)
-		return -EOPNOTSUPP;
-
-	if (res.a2 != HOST_FFA_ID)
-		return -EINVAL;
-
-	arm_smccc_1_1_smc(FFA_FEATURES, FFA_FN64_RXTX_MAP,
-			  0, 0, 0, 0, 0, 0, &res);
-	if (res.a0 != FFA_SUCCESS)
-		return -EOPNOTSUPP;
-
-	switch (res.a2) {
-	case FFA_FEAT_RXTX_MIN_SZ_4K:
-		min_rxtx_sz = SZ_4K;
-		break;
-	case FFA_FEAT_RXTX_MIN_SZ_16K:
-		min_rxtx_sz = SZ_16K;
-		break;
-	case FFA_FEAT_RXTX_MIN_SZ_64K:
-		min_rxtx_sz = SZ_64K;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (min_rxtx_sz > PAGE_SIZE)
-		return -EOPNOTSUPP;
+	if (FFA_MINOR_VERSION(res.a0) < FFA_MINOR_VERSION(FFA_VERSION_1_1))
+		hyp_ffa_version = res.a0;
+	else
+		hyp_ffa_version = FFA_VERSION_1_1;
 
 	tx = pages;
 	pages += KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE;
@@ -787,5 +902,6 @@ int hyp_ffa_init(void *pages)
 		.lock	= __HYP_SPIN_LOCK_UNLOCKED,
 	};
 
+	version_lock = __HYP_SPIN_LOCK_UNLOCKED;
 	return 0;
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
index 6bc88a756cb7..b63f4e1c1033 100644
--- a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
+++ b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
@@ -50,6 +50,9 @@
 #ifndef R_AARCH64_ABS64
 #define R_AARCH64_ABS64			257
 #endif
+#ifndef R_AARCH64_ABS32
+#define R_AARCH64_ABS32			258
+#endif
 #ifndef R_AARCH64_PREL64
 #define R_AARCH64_PREL64		260
 #endif
@@ -383,6 +386,9 @@ static void emit_rela_section(Elf64_Shdr *sh_rela)
 		case R_AARCH64_ABS64:
 			emit_rela_abs64(rela, sh_orig_name);
 			break;
+		/* Allow 32-bit absolute relocation, for kCFI type hashes. */
+		case R_AARCH64_ABS32:
+			break;
 		/* Allow position-relative data relocations. */
 		case R_AARCH64_PREL64:
 		case R_AARCH64_PREL32:
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 135cfb294ee5..3d610fc51f4d 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -197,12 +197,6 @@ SYM_FUNC_END(__host_hvc)
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
 
-	/* If a guest is loaded, panic out of it. */
-	stp	x0, x1, [sp, #-16]!
-	get_loaded_vcpu x0, x1
-	cbnz	x0, __guest_exit_panic
-	add	sp, sp, #16
-
 	/*
 	 * The panic may not be clean if the exception is taken before the host
 	 * context has been saved by __host_exit or after the hyp context has
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 2994878d68ea..07120b37da35 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -5,6 +5,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/cfi_types.h>
 #include <linux/linkage.h>
 
 #include <asm/alternative.h>
@@ -265,33 +266,38 @@ alternative_else_nop_endif
 
 SYM_CODE_END(__kvm_handle_stub_hvc)
 
-SYM_FUNC_START(__pkvm_init_switch_pgd)
+/*
+ * void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
+ *                             void (*fn)(void));
+ *
+ * SYM_TYPED_FUNC_START() allows C to call this ID-mapped function indirectly
+ * using a physical pointer without triggering a kCFI failure.
+ */
+SYM_TYPED_FUNC_START(__pkvm_init_switch_pgd)
 	/* Turn the MMU off */
 	pre_disable_mmu_workaround
-	mrs	x2, sctlr_el2
-	bic	x3, x2, #SCTLR_ELx_M
-	msr	sctlr_el2, x3
+	mrs	x3, sctlr_el2
+	bic	x4, x3, #SCTLR_ELx_M
+	msr	sctlr_el2, x4
 	isb
 
 	tlbi	alle2
 
 	/* Install the new pgtables */
-	ldr	x3, [x0, #NVHE_INIT_PGD_PA]
-	phys_to_ttbr x4, x3
+	phys_to_ttbr x5, x0
 alternative_if ARM64_HAS_CNP
-	orr	x4, x4, #TTBR_CNP_BIT
+	orr	x5, x5, #TTBR_CNP_BIT
 alternative_else_nop_endif
-	msr	ttbr0_el2, x4
+	msr	ttbr0_el2, x5
 
 	/* Set the new stack pointer */
-	ldr	x0, [x0, #NVHE_INIT_STACK_HYP_VA]
-	mov	sp, x0
+	mov	sp, x1
 
 	/* And turn the MMU back on! */
 	dsb	nsh
 	isb
-	set_sctlr_el2	x2
-	ret	x1
+	set_sctlr_el2	x3
+	ret	x2
 SYM_FUNC_END(__pkvm_init_switch_pgd)
 
 	.popsection
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index f4350ba07b0b..174007f3fadd 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -339,7 +339,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 {
 	struct kvm_nvhe_init_params *params;
 	void *virt = hyp_phys_to_virt(phys);
-	void (*fn)(phys_addr_t params_pa, void *finalize_fn_va);
+	typeof(__pkvm_init_switch_pgd) *fn;
 	int ret;
 
 	BUG_ON(kvm_check_pvm_sysreg_table());
@@ -363,7 +363,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 	/* Jump in the idmap page to switch to the new page-tables */
 	params = this_cpu_ptr(&kvm_init_params);
 	fn = (typeof(fn))__hyp_pa(__pkvm_init_switch_pgd);
-	fn(__hyp_pa(params), __pkvm_init_finalise);
+	fn(params->pgd_pa, params->stack_hyp_va, __pkvm_init_finalise);
 
 	unreachable();
 }
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 8fbb6a2e0559..77010b76c150 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -65,6 +65,77 @@ static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 	return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE);
 }
 
+static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	u64 cptr;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+	u64 val = CPACR_ELx_TTA | CPTR_EL2_TAM;
+
+	if (guest_owns_fp_regs()) {
+		val |= CPACR_ELx_FPEN;
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_ELx_ZEN;
+	} else {
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	if (!vcpu_has_nv(vcpu))
+		goto write;
+
+	/*
+	 * The architecture is a bit crap (what a surprise): an EL2 guest
+	 * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
+	 * as they are RES0 in the guest's view. To work around it, trap the
+	 * sucker using the very same bit it can't set...
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
+		val |= CPTR_EL2_TCPAC;
+
+	/*
+	 * Layer the guest hypervisor's trap configuration on top of our own if
+	 * we're in a nested context.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		goto write;
+
+	cptr = vcpu_sanitised_cptr_el2(vcpu);
+
+	/*
+	 * Pay attention, there's some interesting detail here.
+	 *
+	 * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
+	 * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
+	 *
+	 *  - CPTR_EL2.xEN = x0, traps are enabled
+	 *  - CPTR_EL2.xEN = x1, traps are disabled
+	 *
+	 * In other words, bit[0] determines if guest accesses trap or not. In
+	 * the interest of simplicity, clear the entire field if the guest
+	 * hypervisor has traps enabled to dispel any illusion of something more
+	 * complicated taking place.
+	 */
+	if (!(SYS_FIELD_GET(CPACR_ELx, FPEN, cptr) & BIT(0)))
+		val &= ~CPACR_ELx_FPEN;
+	if (!(SYS_FIELD_GET(CPACR_ELx, ZEN, cptr) & BIT(0)))
+		val &= ~CPACR_ELx_ZEN;
+
+	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+		val |= cptr & CPACR_ELx_E0POE;
+
+	val |= cptr & CPTR_EL2_TCPAC;
+
+write:
+	write_sysreg(val, cpacr_el1);
+}
+
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
@@ -91,30 +162,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	val = read_sysreg(cpacr_el1);
-	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);
-
-	/*
-	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
-	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
-	 * except for some missing controls, such as TAM.
-	 * In this case, CPTR_EL2.TAM has the same position with or without
-	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
-	 * shift value for trapping the AMU accesses.
-	 */
-
-	val |= CPTR_EL2_TAM;
-
-	if (guest_owns_fp_regs()) {
-		if (vcpu_has_sve(vcpu))
-			val |= CPACR_ELx_ZEN;
-	} else {
-		val &= ~CPACR_ELx_FPEN;
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	write_sysreg(val, cpacr_el1);
+	__activate_cptr_traps(vcpu);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
 }
@@ -266,10 +314,111 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
 }
 
+static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	int ret = -EINVAL;
+	u32 instr;
+	u64 val;
+
+	/*
+	 * Ideally, we would never trap on EL2 S1 TLB invalidations using
+	 * the EL1 instructions when the guest's HCR_EL2.{E2H,TGE}=={1,1}.
+	 * But "thanks" to FEAT_NV2, we don't trap writes to HCR_EL2,
+	 * meaning that we can't track changes to the virtual TGE bit. So we
+	 * have to leave HCR_EL2.TTLB set on the host. Oopsie...
+	 *
+	 * Try and handle these invalidation as quickly as possible, without
+	 * fully exiting. Note that we don't need to consider any forwarding
+	 * here, as having E2H+TGE set is the very definition of being
+	 * InHost.
+	 *
+	 * For the lesser hypervisors out there that have failed to get on
+	 * with the VHE program, we can also handle the nVHE style of EL2
+	 * invalidation.
+	 */
+	if (!(is_hyp_ctxt(vcpu)))
+		return false;
+
+	instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+	val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+
+	if ((kvm_supported_tlbi_s1e1_op(vcpu, instr) &&
+	     vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) ||
+	    kvm_supported_tlbi_s1e2_op (vcpu, instr))
+		ret = __kvm_tlbi_s1e2(NULL, val, instr);
+
+	if (ret)
+		return false;
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	int rt;
+
+	if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1)
+		return false;
+
+	rt = kvm_vcpu_sys_get_rt(vcpu);
+
+	if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) {
+		vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2));
+	} else {
+		vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2);
+		__activate_cptr_traps(vcpu);
+	}
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_zcr_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+
+	if (!vcpu_has_nv(vcpu))
+		return false;
+
+	if (sysreg != SYS_ZCR_EL2)
+		return false;
+
+	if (guest_owns_fp_regs())
+		return false;
+
+	/*
+	 * ZCR_EL2 traps are handled in the slow path, with the expectation
+	 * that the guest's FP context has already been loaded onto the CPU.
+	 *
+	 * Load the guest's FP context and unconditionally forward to the
+	 * slow path for handling (i.e. return false).
+	 */
+	kvm_hyp_handle_fpsimd(vcpu, exit_code);
+	return false;
+}
+
+static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_zcr_el2(vcpu, exit_code))
+		return true;
+
+	return kvm_hyp_handle_sysreg(vcpu, exit_code);
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
-	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg_vhe,
 	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
@@ -388,7 +537,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static void __hyp_call_panic(u64 spsr, u64 elr, u64 par)
+static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
@@ -413,7 +562,6 @@ void __noreturn hyp_panic(void)
 	u64 par = read_sysreg_par();
 
 	__hyp_call_panic(spsr, elr, par);
-	unreachable();
 }
 
 asmlinkage void kvm_unexpected_el2_exception(void)
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 5fa0359f3a87..3d50a1bd2bdb 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -219,3 +219,150 @@ void __kvm_flush_vm_context(void)
 	__tlbi(alle1is);
 	dsb(ish);
 }
+
+/*
+ * TLB invalidation emulation for NV. For any given instruction, we
+ * perform the following transformtions:
+ *
+ * - a TLBI targeting EL2 S1 is remapped to EL1 S1
+ * - a non-shareable TLBI is upgraded to being inner-shareable
+ * - an outer-shareable TLBI is also mapped to inner-shareable
+ * - an nXS TLBI is upgraded to XS
+ */
+int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
+{
+	struct tlb_inv_context cxt;
+	int ret = 0;
+
+	/*
+	 * The guest will have provided its own DSB ISHST before trapping.
+	 * If it hasn't, that's its own problem, and we won't paper over it
+	 * (plus, there is plenty of extra synchronisation before we even
+	 * get here...).
+	 */
+
+	if (mmu)
+		enter_vmid_context(mmu, &cxt);
+
+	switch (sys_encoding) {
+	case OP_TLBI_ALLE2:
+	case OP_TLBI_ALLE2IS:
+	case OP_TLBI_ALLE2OS:
+	case OP_TLBI_VMALLE1:
+	case OP_TLBI_VMALLE1IS:
+	case OP_TLBI_VMALLE1OS:
+	case OP_TLBI_ALLE2NXS:
+	case OP_TLBI_ALLE2ISNXS:
+	case OP_TLBI_ALLE2OSNXS:
+	case OP_TLBI_VMALLE1NXS:
+	case OP_TLBI_VMALLE1ISNXS:
+	case OP_TLBI_VMALLE1OSNXS:
+		__tlbi(vmalle1is);
+		break;
+	case OP_TLBI_VAE2:
+	case OP_TLBI_VAE2IS:
+	case OP_TLBI_VAE2OS:
+	case OP_TLBI_VAE1:
+	case OP_TLBI_VAE1IS:
+	case OP_TLBI_VAE1OS:
+	case OP_TLBI_VAE2NXS:
+	case OP_TLBI_VAE2ISNXS:
+	case OP_TLBI_VAE2OSNXS:
+	case OP_TLBI_VAE1NXS:
+	case OP_TLBI_VAE1ISNXS:
+	case OP_TLBI_VAE1OSNXS:
+		__tlbi(vae1is, va);
+		break;
+	case OP_TLBI_VALE2:
+	case OP_TLBI_VALE2IS:
+	case OP_TLBI_VALE2OS:
+	case OP_TLBI_VALE1:
+	case OP_TLBI_VALE1IS:
+	case OP_TLBI_VALE1OS:
+	case OP_TLBI_VALE2NXS:
+	case OP_TLBI_VALE2ISNXS:
+	case OP_TLBI_VALE2OSNXS:
+	case OP_TLBI_VALE1NXS:
+	case OP_TLBI_VALE1ISNXS:
+	case OP_TLBI_VALE1OSNXS:
+		__tlbi(vale1is, va);
+		break;
+	case OP_TLBI_ASIDE1:
+	case OP_TLBI_ASIDE1IS:
+	case OP_TLBI_ASIDE1OS:
+	case OP_TLBI_ASIDE1NXS:
+	case OP_TLBI_ASIDE1ISNXS:
+	case OP_TLBI_ASIDE1OSNXS:
+		__tlbi(aside1is, va);
+		break;
+	case OP_TLBI_VAAE1:
+	case OP_TLBI_VAAE1IS:
+	case OP_TLBI_VAAE1OS:
+	case OP_TLBI_VAAE1NXS:
+	case OP_TLBI_VAAE1ISNXS:
+	case OP_TLBI_VAAE1OSNXS:
+		__tlbi(vaae1is, va);
+		break;
+	case OP_TLBI_VAALE1:
+	case OP_TLBI_VAALE1IS:
+	case OP_TLBI_VAALE1OS:
+	case OP_TLBI_VAALE1NXS:
+	case OP_TLBI_VAALE1ISNXS:
+	case OP_TLBI_VAALE1OSNXS:
+		__tlbi(vaale1is, va);
+		break;
+	case OP_TLBI_RVAE2:
+	case OP_TLBI_RVAE2IS:
+	case OP_TLBI_RVAE2OS:
+	case OP_TLBI_RVAE1:
+	case OP_TLBI_RVAE1IS:
+	case OP_TLBI_RVAE1OS:
+	case OP_TLBI_RVAE2NXS:
+	case OP_TLBI_RVAE2ISNXS:
+	case OP_TLBI_RVAE2OSNXS:
+	case OP_TLBI_RVAE1NXS:
+	case OP_TLBI_RVAE1ISNXS:
+	case OP_TLBI_RVAE1OSNXS:
+		__tlbi(rvae1is, va);
+		break;
+	case OP_TLBI_RVALE2:
+	case OP_TLBI_RVALE2IS:
+	case OP_TLBI_RVALE2OS:
+	case OP_TLBI_RVALE1:
+	case OP_TLBI_RVALE1IS:
+	case OP_TLBI_RVALE1OS:
+	case OP_TLBI_RVALE2NXS:
+	case OP_TLBI_RVALE2ISNXS:
+	case OP_TLBI_RVALE2OSNXS:
+	case OP_TLBI_RVALE1NXS:
+	case OP_TLBI_RVALE1ISNXS:
+	case OP_TLBI_RVALE1OSNXS:
+		__tlbi(rvale1is, va);
+		break;
+	case OP_TLBI_RVAAE1:
+	case OP_TLBI_RVAAE1IS:
+	case OP_TLBI_RVAAE1OS:
+	case OP_TLBI_RVAAE1NXS:
+	case OP_TLBI_RVAAE1ISNXS:
+	case OP_TLBI_RVAAE1OSNXS:
+		__tlbi(rvaae1is, va);
+		break;
+	case OP_TLBI_RVAALE1:
+	case OP_TLBI_RVAALE1IS:
+	case OP_TLBI_RVAALE1OS:
+	case OP_TLBI_RVAALE1NXS:
+	case OP_TLBI_RVAALE1ISNXS:
+	case OP_TLBI_RVAALE1OSNXS:
+		__tlbi(rvaale1is, va);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	dsb(ish);
+	isb();
+
+	if (mmu)
+		exit_vmid_context(&cxt);
+
+	return ret;
+}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8bcab0cc3fe9..6981b1bc0946 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -328,18 +328,23 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 				   may_block));
 }
 
-static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
 {
 	__unmap_stage2_range(mmu, start, size, true);
 }
 
+void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
+{
+	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
+}
+
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
 
-	stage2_apply_range_resched(&kvm->arch.mmu, addr, end, kvm_pgtable_stage2_flush);
+	kvm_stage2_flush_range(&kvm->arch.mmu, addr, end);
 }
 
 /**
@@ -362,6 +367,8 @@ static void stage2_flush_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_flush_memslot(kvm, memslot);
 
+	kvm_nested_s2_flush(kvm);
+
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
@@ -855,21 +862,9 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 	.icache_inval_pou	= invalidate_icache_guest_page,
 };
 
-/**
- * kvm_init_stage2_mmu - Initialise a S2 MMU structure
- * @kvm:	The pointer to the KVM structure
- * @mmu:	The pointer to the s2 MMU structure
- * @type:	The machine type of the virtual machine
- *
- * Allocates only the stage-2 HW PGD level table(s).
- * Note we don't need locking here as this is only called when the VM is
- * created, which can only be done once.
- */
-int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
+static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 {
 	u32 kvm_ipa_limit = get_kvm_ipa_limit();
-	int cpu, err;
-	struct kvm_pgtable *pgt;
 	u64 mmfr0, mmfr1;
 	u32 phys_shift;
 
@@ -896,11 +891,51 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
 	mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
 
+	return 0;
+}
+
+/**
+ * kvm_init_stage2_mmu - Initialise a S2 MMU structure
+ * @kvm:	The pointer to the KVM structure
+ * @mmu:	The pointer to the s2 MMU structure
+ * @type:	The machine type of the virtual machine
+ *
+ * Allocates only the stage-2 HW PGD level table(s).
+ * Note we don't need locking here as this is only called in two cases:
+ *
+ * - when the VM is created, which can't race against anything
+ *
+ * - when secondary kvm_s2_mmu structures are initialised for NV
+ *   guests, and the caller must hold kvm->lock as this is called on a
+ *   per-vcpu basis.
+ */
+int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
+{
+	int cpu, err;
+	struct kvm_pgtable *pgt;
+
+	/*
+	 * If we already have our page tables in place, and that the
+	 * MMU context is the canonical one, we have a bug somewhere,
+	 * as this is only supposed to ever happen once per VM.
+	 *
+	 * Otherwise, we're building nested page tables, and that's
+	 * probably because userspace called KVM_ARM_VCPU_INIT more
+	 * than once on the same vcpu. Since that's actually legal,
+	 * don't kick a fuss and leave gracefully.
+	 */
 	if (mmu->pgt != NULL) {
+		if (kvm_is_nested_s2_mmu(kvm, mmu))
+			return 0;
+
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
 
+	err = kvm_init_ipa_range(mmu, type);
+	if (err)
+		return err;
+
 	pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT);
 	if (!pgt)
 		return -ENOMEM;
@@ -925,6 +960,10 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
+
+	if (kvm_is_nested_s2_mmu(kvm, mmu))
+		kvm_init_nested_s2_mmu(mmu);
+
 	return 0;
 
 out_destroy_pgtable:
@@ -976,7 +1015,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
 
 		if (!(vma->vm_flags & VM_PFNMAP)) {
 			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
-			unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
 		}
 		hva = vm_end;
 	} while (hva < reg_end);
@@ -1003,6 +1042,8 @@ void stage2_unmap_vm(struct kvm *kvm)
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
+	kvm_nested_s2_unmap(kvm);
+
 	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -1102,12 +1143,12 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 }
 
 /**
- * stage2_wp_range() - write protect stage2 memory region range
+ * kvm_stage2_wp_range() - write protect stage2 memory region range
  * @mmu:        The KVM stage-2 MMU pointer
  * @addr:	Start address of range
  * @end:	End address of range
  */
-static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
+void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
 	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
 }
@@ -1138,7 +1179,8 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
 	write_lock(&kvm->mmu_lock);
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_nested_s2_wp(kvm);
 	write_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs_memslot(kvm, memslot);
 }
@@ -1192,7 +1234,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
-	stage2_wp_range(&kvm->arch.mmu, start, end);
+	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
 
 	/*
 	 * Eager-splitting is done when manual-protect is set.  We
@@ -1204,6 +1246,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	 */
 	if (kvm_dirty_log_manual_protect_and_init_set(kvm))
 		kvm_mmu_split_huge_pages(kvm, start, end);
+
+	kvm_nested_s2_wp(kvm);
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
@@ -1375,6 +1419,7 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 }
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
+			  struct kvm_s2_trans *nested,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  bool fault_is_perm)
 {
@@ -1383,6 +1428,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	bool exec_fault, mte_allowed;
 	bool device = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
+	phys_addr_t ipa = fault_ipa;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
@@ -1466,10 +1512,38 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	vma_pagesize = 1UL << vma_shift;
+
+	if (nested) {
+		unsigned long max_map_size;
+
+		max_map_size = force_pte ? PAGE_SIZE : PUD_SIZE;
+
+		ipa = kvm_s2_trans_output(nested);
+
+		/*
+		 * If we're about to create a shadow stage 2 entry, then we
+		 * can only create a block mapping if the guest stage 2 page
+		 * table uses at least as big a mapping.
+		 */
+		max_map_size = min(kvm_s2_trans_size(nested), max_map_size);
+
+		/*
+		 * Be careful that if the mapping size falls between
+		 * two host sizes, take the smallest of the two.
+		 */
+		if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE)
+			max_map_size = PMD_SIZE;
+		else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE)
+			max_map_size = PAGE_SIZE;
+
+		force_pte = (max_map_size == PAGE_SIZE);
+		vma_pagesize = min(vma_pagesize, (long)max_map_size);
+	}
+
 	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
 		fault_ipa &= ~(vma_pagesize - 1);
 
-	gfn = fault_ipa >> PAGE_SHIFT;
+	gfn = ipa >> PAGE_SHIFT;
 	mte_allowed = kvm_vma_mte_allowed(vma);
 
 	vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
@@ -1520,6 +1594,25 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
+	/*
+	 * Potentially reduce shadow S2 permissions to match the guest's own
+	 * S2. For exec faults, we'd only reach this point if the guest
+	 * actually allowed it (see kvm_s2_handle_perm_fault).
+	 *
+	 * Also encode the level of the original translation in the SW bits
+	 * of the leaf entry as a proxy for the span of that translation.
+	 * This will be retrieved on TLB invalidation from the guest and
+	 * used to limit the invalidation scope if a TTL hint or a range
+	 * isn't provided.
+	 */
+	if (nested) {
+		writable &= kvm_s2_trans_writable(nested);
+		if (!kvm_s2_trans_readable(nested))
+			prot &= ~KVM_PGTABLE_PROT_R;
+
+		prot |= kvm_encode_nested_level(nested);
+	}
+
 	read_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_invalidate_retry(kvm, mmu_seq)) {
@@ -1566,7 +1659,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			prot |= KVM_PGTABLE_PROT_NORMAL_NC;
 		else
 			prot |= KVM_PGTABLE_PROT_DEVICE;
-	} else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC)) {
+	} else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC) &&
+		   (!nested || kvm_s2_trans_executable(nested))) {
 		prot |= KVM_PGTABLE_PROT_X;
 	}
 
@@ -1575,14 +1669,21 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_is_perm && vma_pagesize == fault_granule)
+	if (fault_is_perm && vma_pagesize == fault_granule) {
+		/*
+		 * Drop the SW bits in favour of those stored in the
+		 * PTE, which will be preserved.
+		 */
+		prot &= ~KVM_NV_GUEST_MAP_SZ;
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
-	else
+	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
 					     memcache,
 					     KVM_PGTABLE_WALK_HANDLE_FAULT |
 					     KVM_PGTABLE_WALK_SHARED);
+	}
+
 out_unlock:
 	read_unlock(&kvm->mmu_lock);
 
@@ -1626,8 +1727,10 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
  */
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
+	struct kvm_s2_trans nested_trans, *nested = NULL;
 	unsigned long esr;
-	phys_addr_t fault_ipa;
+	phys_addr_t fault_ipa; /* The address we faulted on */
+	phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
 	struct kvm_memory_slot *memslot;
 	unsigned long hva;
 	bool is_iabt, write_fault, writable;
@@ -1636,7 +1739,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 
 	esr = kvm_vcpu_get_esr(vcpu);
 
-	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
 	if (esr_fsc_is_translation_fault(esr)) {
@@ -1686,7 +1789,42 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
-	gfn = fault_ipa >> PAGE_SHIFT;
+	/*
+	 * We may have faulted on a shadow stage 2 page table if we are
+	 * running a nested guest.  In this case, we have to resolve the L2
+	 * IPA to the L1 IPA first, before knowing what kind of memory should
+	 * back the L1 IPA.
+	 *
+	 * If the shadow stage 2 page table walk faults, then we simply inject
+	 * this to the guest and carry on.
+	 *
+	 * If there are no shadow S2 PTs because S2 is disabled, there is
+	 * nothing to walk and we treat it as a 1:1 before going through the
+	 * canonical translation.
+	 */
+	if (kvm_is_nested_s2_mmu(vcpu->kvm,vcpu->arch.hw_mmu) &&
+	    vcpu->arch.hw_mmu->nested_stage2_enabled) {
+		u32 esr;
+
+		ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
+		if (ret) {
+			esr = kvm_s2_trans_esr(&nested_trans);
+			kvm_inject_s2_fault(vcpu, esr);
+			goto out_unlock;
+		}
+
+		ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans);
+		if (ret) {
+			esr = kvm_s2_trans_esr(&nested_trans);
+			kvm_inject_s2_fault(vcpu, esr);
+			goto out_unlock;
+		}
+
+		ipa = kvm_s2_trans_output(&nested_trans);
+		nested = &nested_trans;
+	}
+
+	gfn = ipa >> PAGE_SHIFT;
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
 	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
 	write_fault = kvm_is_write_fault(vcpu);
@@ -1730,13 +1868,13 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		 * faulting VA. This is always 12 bits, irrespective
 		 * of the page size.
 		 */
-		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
-		ret = io_mem_abort(vcpu, fault_ipa);
+		ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
+		ret = io_mem_abort(vcpu, ipa);
 		goto out_unlock;
 	}
 
 	/* Userspace should not be able to register out-of-bounds IPAs */
-	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
+	VM_BUG_ON(ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
 
 	if (esr_fsc_is_access_flag_fault(esr)) {
 		handle_access_fault(vcpu, fault_ipa);
@@ -1744,7 +1882,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
+	ret = user_mem_abort(vcpu, fault_ipa, nested, memslot, hva,
 			     esr_fsc_is_permission_fault(esr));
 	if (ret == 0)
 		ret = 1;
@@ -1767,6 +1905,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 			     (range->end - range->start) << PAGE_SHIFT,
 			     range->may_block);
 
+	kvm_nested_s2_unmap(kvm);
 	return false;
 }
 
@@ -1780,6 +1919,10 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, true);
+	/*
+	 * TODO: Handle nested_mmu structures here using the reverse mapping in
+	 * a later version of patch series.
+	 */
 }
 
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -2022,11 +2165,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-	kvm_uninit_stage2_mmu(kvm);
-}
-
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
@@ -2034,7 +2172,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
 	write_lock(&kvm->mmu_lock);
-	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
+	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
+	kvm_nested_s2_unmap(kvm);
 	write_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index bae8536cbf00..de789e0f1ae9 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -4,10 +4,13 @@
  * Author: Jintack Lim <jintack.lim@linaro.org>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_arm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
 #include <asm/kvm_nested.h>
 #include <asm/sysreg.h>
 
@@ -17,149 +20,910 @@
 #define NV_FTR(r, f)		ID_AA64##r##_EL1_##f
 
 /*
- * Our emulated CPU doesn't support all the possible features. For the
- * sake of simplicity (and probably mental sanity), wipe out a number
- * of feature bits we don't intend to support for the time being.
- * This list should get updated as new features get added to the NV
- * support, and new extension to the architecture.
+ * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between
+ * memory usage and potential number of different sets of S2 PTs in
+ * the guests. Running out of S2 MMUs only affects performance (we
+ * will invalidate them more often).
  */
-static u64 limit_nv_id_reg(u32 id, u64 val)
+#define S2_MMU_PER_VCPU		2
+
+void kvm_init_nested(struct kvm *kvm)
 {
-	u64 tmp;
+	kvm->arch.nested_mmus = NULL;
+	kvm->arch.nested_mmus_size = 0;
+}
 
-	switch (id) {
-	case SYS_ID_AA64ISAR0_EL1:
-		/* Support everything but TME, O.S. and Range TLBIs */
-		val &= ~(NV_FTR(ISAR0, TLB)		|
-			 NV_FTR(ISAR0, TME));
-		break;
+static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
+{
+	/*
+	 * We only initialise the IPA range on the canonical MMU, which
+	 * defines the contract between KVM and userspace on where the
+	 * "hardware" is in the IPA space. This affects the validity of MMIO
+	 * exits forwarded to userspace, for example.
+	 *
+	 * For nested S2s, we use the PARange as exposed to the guest, as it
+	 * is allowed to use it at will to expose whatever memory map it
+	 * wants to its own guests as it would be on real HW.
+	 */
+	return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm));
+}
 
-	case SYS_ID_AA64ISAR1_EL1:
-		/* Support everything but Spec Invalidation */
-		val &= ~(GENMASK_ULL(63, 56)	|
-			 NV_FTR(ISAR1, SPECRES));
-		break;
+int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_s2_mmu *tmp;
+	int num_mmus, ret = 0;
+
+	/*
+	 * Let's treat memory allocation failures as benign: If we fail to
+	 * allocate anything, return an error and keep the allocated array
+	 * alive. Userspace may try to recover by intializing the vcpu
+	 * again, and there is no reason to affect the whole VM for this.
+	 */
+	num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU;
+	tmp = kvrealloc(kvm->arch.nested_mmus,
+			size_mul(sizeof(*kvm->arch.nested_mmus), kvm->arch.nested_mmus_size),
+			size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus),
+			GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!tmp)
+		return -ENOMEM;
+
+	/*
+	 * If we went through a realocation, adjust the MMU back-pointers in
+	 * the previously initialised kvm_pgtable structures.
+	 */
+	if (kvm->arch.nested_mmus != tmp)
+		for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
+			tmp[i].pgt->mmu = &tmp[i];
+
+	for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
+		ret = init_nested_s2_mmu(kvm, &tmp[i]);
+
+	if (ret) {
+		for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
+			kvm_free_stage2_pgd(&tmp[i]);
+
+		return ret;
+	}
 
-	case SYS_ID_AA64PFR0_EL1:
-		/* No AMU, MPAM, S-EL2, RAS or SVE */
-		val &= ~(GENMASK_ULL(55, 52)	|
-			 NV_FTR(PFR0, AMU)	|
-			 NV_FTR(PFR0, MPAM)	|
-			 NV_FTR(PFR0, SEL2)	|
-			 NV_FTR(PFR0, RAS)	|
-			 NV_FTR(PFR0, SVE)	|
-			 NV_FTR(PFR0, EL3)	|
-			 NV_FTR(PFR0, EL2)	|
-			 NV_FTR(PFR0, EL1));
-		/* 64bit EL1/EL2/EL3 only */
-		val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001);
-		val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001);
-		val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001);
+	kvm->arch.nested_mmus_size = num_mmus;
+	kvm->arch.nested_mmus = tmp;
+
+	return 0;
+}
+
+struct s2_walk_info {
+	int	     (*read_desc)(phys_addr_t pa, u64 *desc, void *data);
+	void	     *data;
+	u64	     baddr;
+	unsigned int max_oa_bits;
+	unsigned int pgshift;
+	unsigned int sl;
+	unsigned int t0sz;
+	bool	     be;
+};
+
+static unsigned int ps_to_output_size(unsigned int ps)
+{
+	switch (ps) {
+	case 0: return 32;
+	case 1: return 36;
+	case 2: return 40;
+	case 3: return 42;
+	case 4: return 44;
+	case 5:
+	default:
+		return 48;
+	}
+}
+
+static u32 compute_fsc(int level, u32 fsc)
+{
+	return fsc | (level & 0x3);
+}
+
+static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc)
+{
+	u32 esr;
+
+	esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC;
+	esr |= compute_fsc(level, fsc);
+	return esr;
+}
+
+static int get_ia_size(struct s2_walk_info *wi)
+{
+	return 64 - wi->t0sz;
+}
+
+static int check_base_s2_limits(struct s2_walk_info *wi,
+				int level, int input_size, int stride)
+{
+	int start_size, ia_size;
+
+	ia_size = get_ia_size(wi);
+
+	/* Check translation limits */
+	switch (BIT(wi->pgshift)) {
+	case SZ_64K:
+		if (level == 0 || (level == 1 && ia_size <= 42))
+			return -EFAULT;
 		break;
+	case SZ_16K:
+		if (level == 0 || (level == 1 && ia_size <= 40))
+			return -EFAULT;
+		break;
+	case SZ_4K:
+		if (level < 0 || (level == 0 && ia_size <= 42))
+			return -EFAULT;
+		break;
+	}
+
+	/* Check input size limits */
+	if (input_size > ia_size)
+		return -EFAULT;
+
+	/* Check number of entries in starting level table */
+	start_size = input_size - ((3 - level) * stride + wi->pgshift);
+	if (start_size < 1 || start_size > stride + 4)
+		return -EFAULT;
+
+	return 0;
+}
+
+/* Check if output is within boundaries */
+static int check_output_size(struct s2_walk_info *wi, phys_addr_t output)
+{
+	unsigned int output_size = wi->max_oa_bits;
+
+	if (output_size != 48 && (output & GENMASK_ULL(47, output_size)))
+		return -1;
+
+	return 0;
+}
 
-	case SYS_ID_AA64PFR1_EL1:
-		/* Only support BTI, SSBS, CSV2_frac */
-		val &= (NV_FTR(PFR1, BT)	|
-			NV_FTR(PFR1, SSBS)	|
-			NV_FTR(PFR1, CSV2_frac));
+/*
+ * This is essentially a C-version of the pseudo code from the ARM ARM
+ * AArch64.TranslationTableWalk  function.  I strongly recommend looking at
+ * that pseudocode in trying to understand this.
+ *
+ * Must be called with the kvm->srcu read lock held
+ */
+static int walk_nested_s2_pgd(phys_addr_t ipa,
+			      struct s2_walk_info *wi, struct kvm_s2_trans *out)
+{
+	int first_block_level, level, stride, input_size, base_lower_bound;
+	phys_addr_t base_addr;
+	unsigned int addr_top, addr_bottom;
+	u64 desc;  /* page table entry */
+	int ret;
+	phys_addr_t paddr;
+
+	switch (BIT(wi->pgshift)) {
+	default:
+	case SZ_64K:
+	case SZ_16K:
+		level = 3 - wi->sl;
+		first_block_level = 2;
 		break;
+	case SZ_4K:
+		level = 2 - wi->sl;
+		first_block_level = 1;
+		break;
+	}
+
+	stride = wi->pgshift - 3;
+	input_size = get_ia_size(wi);
+	if (input_size > 48 || input_size < 25)
+		return -EFAULT;
+
+	ret = check_base_s2_limits(wi, level, input_size, stride);
+	if (WARN_ON(ret))
+		return ret;
+
+	base_lower_bound = 3 + input_size - ((3 - level) * stride +
+			   wi->pgshift);
+	base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound);
+
+	if (check_output_size(wi, base_addr)) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		return 1;
+	}
+
+	addr_top = input_size - 1;
+
+	while (1) {
+		phys_addr_t index;
+
+		addr_bottom = (3 - level) * stride + wi->pgshift;
+		index = (ipa & GENMASK_ULL(addr_top, addr_bottom))
+			>> (addr_bottom - 3);
+
+		paddr = base_addr | index;
+		ret = wi->read_desc(paddr, &desc, wi->data);
+		if (ret < 0)
+			return ret;
 
-	case SYS_ID_AA64MMFR0_EL1:
-		/* Hide ECV, ExS, Secure Memory */
-		val &= ~(NV_FTR(MMFR0, ECV)		|
-			 NV_FTR(MMFR0, EXS)		|
-			 NV_FTR(MMFR0, TGRAN4_2)	|
-			 NV_FTR(MMFR0, TGRAN16_2)	|
-			 NV_FTR(MMFR0, TGRAN64_2)	|
-			 NV_FTR(MMFR0, SNSMEM));
-
-		/* Disallow unsupported S2 page sizes */
-		switch (PAGE_SIZE) {
-		case SZ_64K:
-			val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001);
-			fallthrough;
-		case SZ_16K:
-			val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001);
-			fallthrough;
-		case SZ_4K:
-			/* Support everything */
-			break;
-		}
 		/*
-		 * Since we can't support a guest S2 page size smaller than
-		 * the host's own page size (due to KVM only populating its
-		 * own S2 using the kernel's page size), advertise the
-		 * limitation using FEAT_GTG.
+		 * Handle reversedescriptors if endianness differs between the
+		 * host and the guest hypervisor.
 		 */
-		switch (PAGE_SIZE) {
-		case SZ_4K:
-			val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010);
-			fallthrough;
-		case SZ_16K:
-			val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010);
-			fallthrough;
-		case SZ_64K:
-			val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010);
+		if (wi->be)
+			desc = be64_to_cpu((__force __be64)desc);
+		else
+			desc = le64_to_cpu((__force __le64)desc);
+
+		/* Check for valid descriptor at this point */
+		if (!(desc & 1) || ((desc & 3) == 1 && level == 3)) {
+			out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+			out->upper_attr = desc;
+			return 1;
+		}
+
+		/* We're at the final level or block translation level */
+		if ((desc & 3) == 1 || level == 3)
+			break;
+
+		if (check_output_size(wi, desc)) {
+			out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+			out->upper_attr = desc;
+			return 1;
+		}
+
+		base_addr = desc & GENMASK_ULL(47, wi->pgshift);
+
+		level += 1;
+		addr_top = addr_bottom - 1;
+	}
+
+	if (level < first_block_level) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	/*
+	 * We don't use the contiguous bit in the stage-2 ptes, so skip check
+	 * for misprogramming of the contiguous bit.
+	 */
+
+	if (check_output_size(wi, desc)) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	if (!(desc & BIT(10))) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	/* Calculate and return the result */
+	paddr = (desc & GENMASK_ULL(47, addr_bottom)) |
+		(ipa & GENMASK_ULL(addr_bottom - 1, 0));
+	out->output = paddr;
+	out->block_size = 1UL << ((3 - level) * stride + wi->pgshift);
+	out->readable = desc & (0b01 << 6);
+	out->writable = desc & (0b10 << 6);
+	out->level = level;
+	out->upper_attr = desc & GENMASK_ULL(63, 52);
+	return 0;
+}
+
+static int read_guest_s2_desc(phys_addr_t pa, u64 *desc, void *data)
+{
+	struct kvm_vcpu *vcpu = data;
+
+	return kvm_read_guest(vcpu->kvm, pa, desc, sizeof(*desc));
+}
+
+static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi)
+{
+	wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK;
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		wi->pgshift = 12;	 break;
+	case VTCR_EL2_TG0_16K:
+		wi->pgshift = 14;	 break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		wi->pgshift = 16;	 break;
+	}
+
+	wi->sl = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
+	/* Global limit for now, should eventually be per-VM */
+	wi->max_oa_bits = min(get_kvm_ipa_limit(),
+			      ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr)));
+}
+
+int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
+		       struct kvm_s2_trans *result)
+{
+	u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	struct s2_walk_info wi;
+	int ret;
+
+	result->esr = 0;
+
+	if (!vcpu_has_nv(vcpu))
+		return 0;
+
+	wi.read_desc = read_guest_s2_desc;
+	wi.data = vcpu;
+	wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+
+	vtcr_to_walk_info(vtcr, &wi);
+
+	wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE;
+
+	ret = walk_nested_s2_pgd(gipa, &wi, result);
+	if (ret)
+		result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC);
+
+	return ret;
+}
+
+static unsigned int ttl_to_size(u8 ttl)
+{
+	int level = ttl & 3;
+	int gran = (ttl >> 2) & 3;
+	unsigned int max_size = 0;
+
+	switch (gran) {
+	case TLBI_TTL_TG_4K:
+		switch (level) {
+		case 0:
+			break;
+		case 1:
+			max_size = SZ_1G;
+			break;
+		case 2:
+			max_size = SZ_2M;
+			break;
+		case 3:
+			max_size = SZ_4K;
 			break;
 		}
-		/* Cap PARange to 48bits */
-		tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val);
-		if (tmp > 0b0101) {
-			val &= ~NV_FTR(MMFR0, PARANGE);
-			val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101);
+		break;
+	case TLBI_TTL_TG_16K:
+		switch (level) {
+		case 0:
+		case 1:
+			break;
+		case 2:
+			max_size = SZ_32M;
+			break;
+		case 3:
+			max_size = SZ_16K;
+			break;
 		}
 		break;
-
-	case SYS_ID_AA64MMFR1_EL1:
-		val &= (NV_FTR(MMFR1, HCX)	|
-			NV_FTR(MMFR1, PAN)	|
-			NV_FTR(MMFR1, LO)	|
-			NV_FTR(MMFR1, HPDS)	|
-			NV_FTR(MMFR1, VH)	|
-			NV_FTR(MMFR1, VMIDBits));
+	case TLBI_TTL_TG_64K:
+		switch (level) {
+		case 0:
+		case 1:
+			/* No 52bit IPA support */
+			break;
+		case 2:
+			max_size = SZ_512M;
+			break;
+		case 3:
+			max_size = SZ_64K;
+			break;
+		}
+		break;
+	default:			/* No size information */
 		break;
+	}
 
-	case SYS_ID_AA64MMFR2_EL1:
-		val &= ~(NV_FTR(MMFR2, BBM)	|
-			 NV_FTR(MMFR2, TTL)	|
-			 GENMASK_ULL(47, 44)	|
-			 NV_FTR(MMFR2, ST)	|
-			 NV_FTR(MMFR2, CCIDX)	|
-			 NV_FTR(MMFR2, VARange));
+	return max_size;
+}
 
-		/* Force TTL support */
-		val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001);
+/*
+ * Compute the equivalent of the TTL field by parsing the shadow PT.  The
+ * granule size is extracted from the cached VTCR_EL2.TG0 while the level is
+ * retrieved from first entry carrying the level as a tag.
+ */
+static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr)
+{
+	u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr;
+	kvm_pte_t pte;
+	u8 ttl, level;
+
+	lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(mmu)->mmu_lock);
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		ttl = (TLBI_TTL_TG_4K << 2);
+		break;
+	case VTCR_EL2_TG0_16K:
+		ttl = (TLBI_TTL_TG_16K << 2);
 		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		ttl = (TLBI_TTL_TG_64K << 2);
+		break;
+	}
 
-	case SYS_ID_AA64MMFR4_EL1:
-		val = 0;
-		if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
-			val |= FIELD_PREP(NV_FTR(MMFR4, E2H0),
-					  ID_AA64MMFR4_EL1_E2H0_NI_NV1);
+	tmp = addr;
+
+again:
+	/* Iteratively compute the block sizes for a particular granule size */
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		if	(sz < SZ_4K)	sz = SZ_4K;
+		else if (sz < SZ_2M)	sz = SZ_2M;
+		else if (sz < SZ_1G)	sz = SZ_1G;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_16K:
+		if	(sz < SZ_16K)	sz = SZ_16K;
+		else if (sz < SZ_32M)	sz = SZ_32M;
+		else			sz = 0;
 		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		if	(sz < SZ_64K)	sz = SZ_64K;
+		else if (sz < SZ_512M)	sz = SZ_512M;
+		else			sz = 0;
+		break;
+	}
+
+	if (sz == 0)
+		return 0;
+
+	tmp &= ~(sz - 1);
+	if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL))
+		goto again;
+	if (!(pte & PTE_VALID))
+		goto again;
+	level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte);
+	if (!level)
+		goto again;
+
+	ttl |= level;
 
-	case SYS_ID_AA64DFR0_EL1:
-		/* Only limited support for PMU, Debug, BPs and WPs */
-		val &= (NV_FTR(DFR0, PMUVer)	|
-			NV_FTR(DFR0, WRPs)	|
-			NV_FTR(DFR0, BRPs)	|
-			NV_FTR(DFR0, DebugVer));
-
-		/* Cap Debug to ARMv8.1 */
-		tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val);
-		if (tmp > 0b0111) {
-			val &= ~NV_FTR(DFR0, DebugVer);
-			val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111);
+	/*
+	 * We now have found some level information in the shadow S2. Check
+	 * that the resulting range is actually including the original IPA.
+	 */
+	sz = ttl_to_size(ttl);
+	if (addr < (tmp + sz))
+		return ttl;
+
+	return 0;
+}
+
+unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
+	unsigned long max_size;
+	u8 ttl;
+
+	ttl = FIELD_GET(TLBI_TTL_MASK, val);
+
+	if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) {
+		/* No TTL, check the shadow S2 for a hint */
+		u64 addr = (val & GENMASK_ULL(35, 0)) << 12;
+		ttl = get_guest_mapping_ttl(mmu, addr);
+	}
+
+	max_size = ttl_to_size(ttl);
+
+	if (!max_size) {
+		/* Compute the maximum extent of the invalidation */
+		switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
+		case VTCR_EL2_TG0_4K:
+			max_size = SZ_1G;
+			break;
+		case VTCR_EL2_TG0_16K:
+			max_size = SZ_32M;
+			break;
+		case VTCR_EL2_TG0_64K:
+		default:    /* IMPDEF: treat any other value as 64k */
+			/*
+			 * No, we do not support 52bit IPA in nested yet. Once
+			 * we do, this should be 4TB.
+			 */
+			max_size = SZ_512M;
+			break;
 		}
-		break;
+	}
 
-	default:
-		/* Unknown register, just wipe it clean */
-		val = 0;
+	WARN_ON(!max_size);
+	return max_size;
+}
+
+/*
+ * We can have multiple *different* MMU contexts with the same VMID:
+ *
+ * - S2 being enabled or not, hence differing by the HCR_EL2.VM bit
+ *
+ * - Multiple vcpus using private S2s (huh huh...), hence differing by the
+ *   VBBTR_EL2.BADDR address
+ *
+ * - A combination of the above...
+ *
+ * We can always identify which MMU context to pick at run-time.  However,
+ * TLB invalidation involving a VMID must take action on all the TLBs using
+ * this particular VMID. This translates into applying the same invalidation
+ * operation to all the contexts that are using this VMID. Moar phun!
+ */
+void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
+				const union tlbi_info *info,
+				void (*tlbi_callback)(struct kvm_s2_mmu *,
+						      const union tlbi_info *))
+{
+	write_lock(&kvm->mmu_lock);
+
+	for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!kvm_s2_mmu_valid(mmu))
+			continue;
+
+		if (vmid == get_vmid(mmu->tlb_vttbr))
+			tlbi_callback(mmu, info);
+	}
+
+	write_unlock(&kvm->mmu_lock);
+}
+
+struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool nested_stage2_enabled;
+	u64 vttbr, vtcr, hcr;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	hcr = vcpu_read_sys_reg(vcpu, HCR_EL2);
+
+	nested_stage2_enabled = hcr & HCR_VM;
+
+	/* Don't consider the CnP bit for the vttbr match */
+	vttbr &= ~VTTBR_CNP_BIT;
+
+	/*
+	 * Two possibilities when looking up a S2 MMU context:
+	 *
+	 * - either S2 is enabled in the guest, and we need a context that is
+	 *   S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR,
+	 *   which makes it safe from a TLB conflict perspective (a broken
+	 *   guest won't be able to generate them),
+	 *
+	 * - or S2 is disabled, and we need a context that is S2-disabled
+	 *   and matches the VMID only, as all TLBs are tagged by VMID even
+	 *   if S2 translation is disabled.
+	 */
+	for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!kvm_s2_mmu_valid(mmu))
+			continue;
+
+		if (nested_stage2_enabled &&
+		    mmu->nested_stage2_enabled &&
+		    vttbr == mmu->tlb_vttbr &&
+		    vtcr == mmu->tlb_vtcr)
+			return mmu;
+
+		if (!nested_stage2_enabled &&
+		    !mmu->nested_stage2_enabled &&
+		    get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr))
+			return mmu;
+	}
+	return NULL;
+}
+
+static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_s2_mmu *s2_mmu;
+	int i;
+
+	lockdep_assert_held_write(&vcpu->kvm->mmu_lock);
+
+	s2_mmu = lookup_s2_mmu(vcpu);
+	if (s2_mmu)
+		goto out;
+
+	/*
+	 * Make sure we don't always search from the same point, or we
+	 * will always reuse a potentially active context, leaving
+	 * free contexts unused.
+	 */
+	for (i = kvm->arch.nested_mmus_next;
+	     i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
+	     i++) {
+		s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
+
+		if (atomic_read(&s2_mmu->refcnt) == 0)
+			break;
+	}
+	BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
+
+	/* Set the scene for the next search */
+	kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
+
+	/* Clear the old state */
+	if (kvm_s2_mmu_valid(s2_mmu))
+		kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+
+	/*
+	 * The virtual VMID (modulo CnP) will be used as a key when matching
+	 * an existing kvm_s2_mmu.
+	 *
+	 * We cache VTCR at allocation time, once and for all. It'd be great
+	 * if the guest didn't screw that one up, as this is not very
+	 * forgiving...
+	 */
+	s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT;
+	s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM;
+
+out:
+	atomic_inc(&s2_mmu->refcnt);
+	return s2_mmu;
+}
+
+void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
+{
+	/* CnP being set denotes an invalid entry */
+	mmu->tlb_vttbr = VTTBR_CNP_BIT;
+	mmu->nested_stage2_enabled = false;
+	atomic_set(&mmu->refcnt, 0);
+}
+
+void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
+{
+	if (is_hyp_ctxt(vcpu)) {
+		vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+	} else {
+		write_lock(&vcpu->kvm->mmu_lock);
+		vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
+		write_unlock(&vcpu->kvm->mmu_lock);
+	}
+}
+
+void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
+{
+	if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
+		atomic_dec(&vcpu->arch.hw_mmu->refcnt);
+		vcpu->arch.hw_mmu = NULL;
+	}
+}
+
+/*
+ * Returns non-zero if permission fault is handled by injecting it to the next
+ * level hypervisor.
+ */
+int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
+{
+	bool forward_fault = false;
+
+	trans->esr = 0;
+
+	if (!kvm_vcpu_trap_is_permission_fault(vcpu))
+		return 0;
+
+	if (kvm_vcpu_trap_is_iabt(vcpu)) {
+		forward_fault = !kvm_s2_trans_executable(trans);
+	} else {
+		bool write_fault = kvm_is_write_fault(vcpu);
+
+		forward_fault = ((write_fault && !trans->writable) ||
+				 (!write_fault && !trans->readable));
+	}
+
+	if (forward_fault)
+		trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM);
+
+	return forward_fault;
+}
+
+int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
+{
+	vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2);
+	vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2);
+
+	return kvm_inject_nested_sync(vcpu, esr_el2);
+}
+
+void kvm_nested_s2_wp(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu));
+	}
+}
+
+void kvm_nested_s2_unmap(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
+	}
+}
+
+void kvm_nested_s2_flush(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu));
+	}
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!WARN_ON(atomic_read(&mmu->refcnt)))
+			kvm_free_stage2_pgd(mmu);
+	}
+	kfree(kvm->arch.nested_mmus);
+	kvm->arch.nested_mmus = NULL;
+	kvm->arch.nested_mmus_size = 0;
+	kvm_uninit_stage2_mmu(kvm);
+}
+
+/*
+ * Our emulated CPU doesn't support all the possible features. For the
+ * sake of simplicity (and probably mental sanity), wipe out a number
+ * of feature bits we don't intend to support for the time being.
+ * This list should get updated as new features get added to the NV
+ * support, and new extension to the architecture.
+ */
+static void limit_nv_id_regs(struct kvm *kvm)
+{
+	u64 val, tmp;
+
+	/* Support everything but TME */
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1);
+	val &= ~NV_FTR(ISAR0, TME);
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1, val);
+
+	/* Support everything but Spec Invalidation and LS64 */
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1);
+	val &= ~(NV_FTR(ISAR1, LS64)	|
+		 NV_FTR(ISAR1, SPECRES));
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1, val);
+
+	/* No AMU, MPAM, S-EL2, or RAS */
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1);
+	val &= ~(GENMASK_ULL(55, 52)	|
+		 NV_FTR(PFR0, AMU)	|
+		 NV_FTR(PFR0, MPAM)	|
+		 NV_FTR(PFR0, SEL2)	|
+		 NV_FTR(PFR0, RAS)	|
+		 NV_FTR(PFR0, EL3)	|
+		 NV_FTR(PFR0, EL2)	|
+		 NV_FTR(PFR0, EL1));
+	/* 64bit EL1/EL2/EL3 only */
+	val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001);
+	val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001);
+	val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001);
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val);
+
+	/* Only support BTI, SSBS, CSV2_frac */
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1);
+	val &= (NV_FTR(PFR1, BT)	|
+		NV_FTR(PFR1, SSBS)	|
+		NV_FTR(PFR1, CSV2_frac));
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1, val);
+
+	/* Hide ECV, ExS, Secure Memory */
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1);
+	val &= ~(NV_FTR(MMFR0, ECV)		|
+		 NV_FTR(MMFR0, EXS)		|
+		 NV_FTR(MMFR0, TGRAN4_2)	|
+		 NV_FTR(MMFR0, TGRAN16_2)	|
+		 NV_FTR(MMFR0, TGRAN64_2)	|
+		 NV_FTR(MMFR0, SNSMEM));
+
+	/* Disallow unsupported S2 page sizes */
+	switch (PAGE_SIZE) {
+	case SZ_64K:
+		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001);
+		fallthrough;
+	case SZ_16K:
+		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001);
+		fallthrough;
+	case SZ_4K:
+		/* Support everything */
 		break;
 	}
+	/*
+	 * Since we can't support a guest S2 page size smaller than
+	 * the host's own page size (due to KVM only populating its
+	 * own S2 using the kernel's page size), advertise the
+	 * limitation using FEAT_GTG.
+	 */
+	switch (PAGE_SIZE) {
+	case SZ_4K:
+		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010);
+		fallthrough;
+	case SZ_16K:
+		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010);
+		fallthrough;
+	case SZ_64K:
+		val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010);
+		break;
+	}
+	/* Cap PARange to 48bits */
+	tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val);
+	if (tmp > 0b0101) {
+		val &= ~NV_FTR(MMFR0, PARANGE);
+		val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101);
+	}
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1, val);
+
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1);
+	val &= (NV_FTR(MMFR1, HCX)	|
+		NV_FTR(MMFR1, PAN)	|
+		NV_FTR(MMFR1, LO)	|
+		NV_FTR(MMFR1, HPDS)	|
+		NV_FTR(MMFR1, VH)	|
+		NV_FTR(MMFR1, VMIDBits));
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1, val);
+
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1);
+	val &= ~(NV_FTR(MMFR2, BBM)	|
+		 NV_FTR(MMFR2, TTL)	|
+		 GENMASK_ULL(47, 44)	|
+		 NV_FTR(MMFR2, ST)	|
+		 NV_FTR(MMFR2, CCIDX)	|
+		 NV_FTR(MMFR2, VARange));
 
-	return val;
+	/* Force TTL support */
+	val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001);
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1, val);
+
+	val = 0;
+	if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
+		val |= FIELD_PREP(NV_FTR(MMFR4, E2H0),
+				  ID_AA64MMFR4_EL1_E2H0_NI_NV1);
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR4_EL1, val);
+
+	/* Only limited support for PMU, Debug, BPs and WPs */
+	val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1);
+	val &= (NV_FTR(DFR0, PMUVer)	|
+		NV_FTR(DFR0, WRPs)	|
+		NV_FTR(DFR0, BRPs)	|
+		NV_FTR(DFR0, DebugVer));
+
+	/* Cap Debug to ARMv8.1 */
+	tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val);
+	if (tmp > 0b0111) {
+		val &= ~NV_FTR(DFR0, DebugVer);
+		val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111);
+	}
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1, val);
 }
 
 u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr)
@@ -198,15 +962,13 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		goto out;
 
 	kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)),
-					 GFP_KERNEL);
+					 GFP_KERNEL_ACCOUNT);
 	if (!kvm->arch.sysreg_masks) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	for (int i = 0; i < KVM_ARM_ID_REG_NUM; i++)
-		kvm->arch.id_regs[i] = limit_nv_id_reg(IDX_IDREG(i),
-						       kvm->arch.id_regs[i]);
+	limit_nv_id_regs(kvm);
 
 	/* VTTBR_EL2 */
 	res0 = res1 = 0;
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index a35ce10e0a9f..7848daeafd03 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -54,7 +54,7 @@ static u32 __kvm_pmu_event_mask(unsigned int pmuver)
 
 static u32 kvm_pmu_event_mask(struct kvm *kvm)
 {
-	u64 dfr0 = IDREG(kvm, SYS_ID_AA64DFR0_EL1);
+	u64 dfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1);
 	u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0);
 
 	return __kvm_pmu_event_mask(pmuver);
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 3fc8ca164dbe..0b0ae5ae7bc2 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -268,6 +268,12 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
+u32 kvm_get_pa_bits(struct kvm *kvm)
+{
+	/* Fixed limit until we can configure ID_AA64MMFR0.PARange */
+	return kvm_ipa_limit;
+}
+
 u32 get_kvm_ipa_limit(void)
 {
 	return kvm_ipa_limit;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 22b45a15d068..c90324060436 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -121,6 +121,7 @@ static bool get_el2_to_el1_mapping(unsigned int reg,
 		MAPPED_EL2_SYSREG(AMAIR_EL2,   AMAIR_EL1,   NULL	     );
 		MAPPED_EL2_SYSREG(ELR_EL2,     ELR_EL1,	    NULL	     );
 		MAPPED_EL2_SYSREG(SPSR_EL2,    SPSR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(ZCR_EL2,     ZCR_EL1,     NULL	     );
 	default:
 		return false;
 	}
@@ -383,6 +384,12 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 	u64 val, mask, shift;
 
+	if (reg_to_encoding(r) == SYS_TCR2_EL1 &&
+	    !kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, TCRX, IMP)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
 	BUG_ON(!p->is_write);
 
 	get_access_mask(r, &mask, &shift);
@@ -1565,7 +1572,7 @@ static u64 kvm_read_sanitised_id_reg(struct kvm_vcpu *vcpu,
 
 static u64 read_id_reg(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	return IDREG(vcpu->kvm, reg_to_encoding(r));
+	return kvm_read_vm_id_reg(vcpu->kvm, reg_to_encoding(r));
 }
 
 static bool is_feature_id_reg(u32 encoding)
@@ -1583,6 +1590,9 @@ static bool is_feature_id_reg(u32 encoding)
  */
 static inline bool is_vm_ftr_id_reg(u32 id)
 {
+	if (id == SYS_CTR_EL0)
+		return true;
+
 	return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 &&
 		sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 &&
 		sys_reg_CRm(id) < 8);
@@ -1851,7 +1861,7 @@ static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 
 	ret = arm64_check_features(vcpu, rd, val);
 	if (!ret)
-		IDREG(vcpu->kvm, id) = val;
+		kvm_set_vm_id_reg(vcpu->kvm, id, val);
 
 	mutex_unlock(&vcpu->kvm->arch.config_lock);
 
@@ -1867,6 +1877,18 @@ static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	return ret;
 }
 
+void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val)
+{
+	u64 *p = __vm_id_reg(&kvm->arch, reg);
+
+	lockdep_assert_held(&kvm->arch.config_lock);
+
+	if (KVM_BUG_ON(kvm_vm_has_ran_once(kvm) || !p, kvm))
+		return;
+
+	*p = val;
+}
+
 static int get_raz_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		       u64 *val)
 {
@@ -1886,7 +1908,7 @@ static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write)
 		return write_to_read_only(vcpu, p, r);
 
-	p->regval = read_sanitised_ftr_reg(SYS_CTR_EL0);
+	p->regval = kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0);
 	return true;
 }
 
@@ -2199,6 +2221,40 @@ static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	return __vcpu_sys_reg(vcpu, r->reg) = val;
 }
 
+static unsigned int sve_el2_visibility(const struct kvm_vcpu *vcpu,
+				       const struct sys_reg_desc *rd)
+{
+	unsigned int r;
+
+	r = el2_visibility(vcpu, rd);
+	if (r)
+		return r;
+
+	return sve_visibility(vcpu, rd);
+}
+
+static bool access_zcr_el2(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	unsigned int vq;
+
+	if (guest_hyp_sve_traps_enabled(vcpu)) {
+		kvm_inject_nested_sve_trap(vcpu);
+		return true;
+	}
+
+	if (!p->is_write) {
+		p->regval = vcpu_read_sys_reg(vcpu, ZCR_EL2);
+		return true;
+	}
+
+	vq = SYS_FIELD_GET(ZCR_ELx, LEN, p->regval) + 1;
+	vq = min(vq, vcpu_sve_max_vq(vcpu));
+	vcpu_write_sys_reg(vcpu, vq - 1, ZCR_EL2);
+	return true;
+}
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -2471,11 +2527,14 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
 	{ SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1,
-	  .set_user = set_clidr },
+	  .set_user = set_clidr, .val = ~CLIDR_EL1_RES0 },
 	{ SYS_DESC(SYS_CCSIDR2_EL1), undef_access },
 	{ SYS_DESC(SYS_SMIDR_EL1), undef_access },
 	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
-	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
+	ID_WRITABLE(CTR_EL0, CTR_EL0_DIC_MASK |
+			     CTR_EL0_IDC_MASK |
+			     CTR_EL0_DminLine_MASK |
+			     CTR_EL0_IminLine_MASK),
 	{ SYS_DESC(SYS_SVCR), undef_access },
 
 	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr,
@@ -2688,6 +2747,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG_VNCR(HFGITR_EL2, reset_val, 0),
 	EL2_REG_VNCR(HACR_EL2, reset_val, 0),
 
+	{ SYS_DESC(SYS_ZCR_EL2), .access = access_zcr_el2, .reset = reset_val,
+	  .visibility = sve_el2_visibility, .reg = ZCR_EL2 },
+
 	EL2_REG_VNCR(HCRX_EL2, reset_val, 0),
 
 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
@@ -2741,6 +2803,264 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
 };
 
+static bool kvm_supported_tlbi_s12_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+
+	if (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
+		return false;
+
+	if (CRm == TLBI_CRm_nROS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	return true;
+}
+
+static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+	if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	write_lock(&vcpu->kvm->mmu_lock);
+
+	/*
+	 * Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
+	 * corresponding VMIDs.
+	 */
+	kvm_nested_s2_unmap(vcpu->kvm);
+
+	write_unlock(&vcpu->kvm->mmu_lock);
+
+	return true;
+}
+
+static bool kvm_supported_tlbi_ipas2_op(struct kvm_vcpu *vpcu, u32 instr)
+{
+	struct kvm *kvm = vpcu->kvm;
+	u8 CRm = sys_reg_CRm(instr);
+	u8 Op2 = sys_reg_Op2(instr);
+
+	if (sys_reg_CRn(instr) == TLBI_CRn_nXS &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAIS && (Op2 == 2 || Op2 == 6) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAONS && (Op2 == 0 || Op2 == 4) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
+		return false;
+
+	if (CRm == TLBI_CRm_IPAONS && (Op2 == 3 || Op2 == 7) &&
+	    !kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
+		return false;
+
+	return true;
+}
+
+/* Only defined here as this is an internal "abstraction" */
+union tlbi_info {
+	struct {
+		u64	start;
+		u64	size;
+	} range;
+
+	struct {
+		u64	addr;
+	} ipa;
+
+	struct {
+		u64	addr;
+		u32	encoding;
+	} va;
+};
+
+static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
+			       const union tlbi_info *info)
+{
+	kvm_stage2_unmap_range(mmu, info->range.start, info->range.size);
+}
+
+static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+				const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 limit, vttbr;
+
+	if (!kvm_supported_tlbi_s12_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	limit = BIT_ULL(kvm_get_pa_bits(vcpu->kvm));
+
+	kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+				   &(union tlbi_info) {
+					   .range = {
+						   .start = 0,
+						   .size = limit,
+					   },
+				   },
+				   s2_mmu_unmap_range);
+
+	return true;
+}
+
+static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	u64 base, range, tg, num, scale;
+	int shift;
+
+	if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	/*
+	 * Because the shadow S2 structure doesn't necessarily reflect that
+	 * of the guest's S2 (different base granule size, for example), we
+	 * decide to ignore TTL and only use the described range.
+	 */
+	tg	= FIELD_GET(GENMASK(47, 46), p->regval);
+	scale	= FIELD_GET(GENMASK(45, 44), p->regval);
+	num	= FIELD_GET(GENMASK(43, 39), p->regval);
+	base	= p->regval & GENMASK(36, 0);
+
+	switch(tg) {
+	case 1:
+		shift = 12;
+		break;
+	case 2:
+		shift = 14;
+		break;
+	case 3:
+	default:		/* IMPDEF: handle tg==0 as 64k */
+		shift = 16;
+		break;
+	}
+
+	base <<= shift;
+	range = __TLBI_RANGE_PAGES(num, scale) << shift;
+
+	kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+				   &(union tlbi_info) {
+					   .range = {
+						   .start = base,
+						   .size = range,
+					   },
+				   },
+				   s2_mmu_unmap_range);
+
+	return true;
+}
+
+static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
+			     const union tlbi_info *info)
+{
+	unsigned long max_size;
+	u64 base_addr;
+
+	/*
+	 * We drop a number of things from the supplied value:
+	 *
+	 * - NS bit: we're non-secure only.
+	 *
+	 * - IPA[51:48]: We don't support 52bit IPA just yet...
+	 *
+	 * And of course, adjust the IPA to be on an actual address.
+	 */
+	base_addr = (info->ipa.addr & GENMASK_ULL(35, 0)) << 12;
+	max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
+	base_addr &= ~(max_size - 1);
+
+	kvm_stage2_unmap_range(mmu, base_addr, max_size);
+}
+
+static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+
+	if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+				   &(union tlbi_info) {
+					   .ipa = {
+						   .addr = p->regval,
+					   },
+				   },
+				   s2_mmu_unmap_ipa);
+
+	return true;
+}
+
+static void s2_mmu_tlbi_s1e1(struct kvm_s2_mmu *mmu,
+			     const union tlbi_info *info)
+{
+	WARN_ON(__kvm_tlbi_s1e2(mmu, info->va.addr, info->va.encoding));
+}
+
+static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+
+	/*
+	 * If we're here, this is because we've trapped on a EL1 TLBI
+	 * instruction that affects the EL1 translation regime while
+	 * we're running in a context that doesn't allow us to let the
+	 * HW do its thing (aka vEL2):
+	 *
+	 * - HCR_EL2.E2H == 0 : a non-VHE guest
+	 * - HCR_EL2.{E2H,TGE} == { 1, 0 } : a VHE guest in guest mode
+	 *
+	 * We don't expect these helpers to ever be called when running
+	 * in a vEL1 context.
+	 */
+
+	WARN_ON(!vcpu_is_el2(vcpu));
+
+	if (!kvm_supported_tlbi_s1e1_op(vcpu, sys_encoding)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
+	kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+				   &(union tlbi_info) {
+					   .va = {
+						   .addr = p->regval,
+						   .encoding = sys_encoding,
+					   },
+				   },
+				   s2_mmu_tlbi_s1e1);
+
+	return true;
+}
+
+#define SYS_INSN(insn, access_fn)					\
+	{								\
+		SYS_DESC(OP_##insn),					\
+		.access = (access_fn),					\
+	}
+
 static struct sys_reg_desc sys_insn_descs[] = {
 	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
 	{ SYS_DESC(SYS_DC_IGSW), access_dcgsw },
@@ -2751,9 +3071,147 @@ static struct sys_reg_desc sys_insn_descs[] = {
 	{ SYS_DESC(SYS_DC_CISW), access_dcsw },
 	{ SYS_DESC(SYS_DC_CIGSW), access_dcgsw },
 	{ SYS_DESC(SYS_DC_CIGDSW), access_dcgsw },
-};
 
-static const struct sys_reg_desc *first_idreg;
+	SYS_INSN(TLBI_VMALLE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1OS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_RVAE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAAE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVALE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAALE1IS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_VMALLE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1IS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1IS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_RVAE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAAE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVALE1OS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAALE1OS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_RVAE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAAE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVALE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAALE1, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_VMALLE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_VMALLE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1OSNXS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_RVAE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAAE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVALE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAALE1ISNXS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_VMALLE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1ISNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1ISNXS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_RVAE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAAE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVALE1OSNXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAALE1OSNXS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_RVAE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAAE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVALE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_RVAALE1NXS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_VMALLE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_ASIDE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAAE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VALE1NXS, handle_tlbi_el1),
+	SYS_INSN(TLBI_VAALE1NXS, handle_tlbi_el1),
+
+	SYS_INSN(TLBI_IPAS2E1IS, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2E1IS, handle_ripas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1IS, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2LE1IS, handle_ripas2e1is),
+
+	SYS_INSN(TLBI_ALLE2OS, trap_undef),
+	SYS_INSN(TLBI_VAE2OS, trap_undef),
+	SYS_INSN(TLBI_ALLE1OS, handle_alle1is),
+	SYS_INSN(TLBI_VALE2OS, trap_undef),
+	SYS_INSN(TLBI_VMALLS12E1OS, handle_vmalls12e1is),
+
+	SYS_INSN(TLBI_RVAE2IS, trap_undef),
+	SYS_INSN(TLBI_RVALE2IS, trap_undef),
+
+	SYS_INSN(TLBI_ALLE1IS, handle_alle1is),
+	SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is),
+	SYS_INSN(TLBI_IPAS2E1OS, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2E1, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2E1, handle_ripas2e1is),
+	SYS_INSN(TLBI_RIPAS2E1OS, handle_ripas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1OS, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2LE1, handle_ripas2e1is),
+	SYS_INSN(TLBI_RIPAS2LE1OS, handle_ripas2e1is),
+	SYS_INSN(TLBI_RVAE2OS, trap_undef),
+	SYS_INSN(TLBI_RVALE2OS, trap_undef),
+	SYS_INSN(TLBI_RVAE2, trap_undef),
+	SYS_INSN(TLBI_RVALE2, trap_undef),
+	SYS_INSN(TLBI_ALLE1, handle_alle1is),
+	SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is),
+
+	SYS_INSN(TLBI_IPAS2E1ISNXS, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2E1ISNXS, handle_ripas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1ISNXS, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2LE1ISNXS, handle_ripas2e1is),
+
+	SYS_INSN(TLBI_ALLE2OSNXS, trap_undef),
+	SYS_INSN(TLBI_VAE2OSNXS, trap_undef),
+	SYS_INSN(TLBI_ALLE1OSNXS, handle_alle1is),
+	SYS_INSN(TLBI_VALE2OSNXS, trap_undef),
+	SYS_INSN(TLBI_VMALLS12E1OSNXS, handle_vmalls12e1is),
+
+	SYS_INSN(TLBI_RVAE2ISNXS, trap_undef),
+	SYS_INSN(TLBI_RVALE2ISNXS, trap_undef),
+	SYS_INSN(TLBI_ALLE2ISNXS, trap_undef),
+	SYS_INSN(TLBI_VAE2ISNXS, trap_undef),
+
+	SYS_INSN(TLBI_ALLE1ISNXS, handle_alle1is),
+	SYS_INSN(TLBI_VALE2ISNXS, trap_undef),
+	SYS_INSN(TLBI_VMALLS12E1ISNXS, handle_vmalls12e1is),
+	SYS_INSN(TLBI_IPAS2E1OSNXS, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2E1NXS, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2E1NXS, handle_ripas2e1is),
+	SYS_INSN(TLBI_RIPAS2E1OSNXS, handle_ripas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1OSNXS, handle_ipas2e1is),
+	SYS_INSN(TLBI_IPAS2LE1NXS, handle_ipas2e1is),
+	SYS_INSN(TLBI_RIPAS2LE1NXS, handle_ripas2e1is),
+	SYS_INSN(TLBI_RIPAS2LE1OSNXS, handle_ripas2e1is),
+	SYS_INSN(TLBI_RVAE2OSNXS, trap_undef),
+	SYS_INSN(TLBI_RVALE2OSNXS, trap_undef),
+	SYS_INSN(TLBI_RVAE2NXS, trap_undef),
+	SYS_INSN(TLBI_RVALE2NXS, trap_undef),
+	SYS_INSN(TLBI_ALLE2NXS, trap_undef),
+	SYS_INSN(TLBI_VAE2NXS, trap_undef),
+	SYS_INSN(TLBI_ALLE1NXS, handle_alle1is),
+	SYS_INSN(TLBI_VALE2NXS, trap_undef),
+	SYS_INSN(TLBI_VMALLS12E1NXS, handle_vmalls12e1is),
+};
 
 static bool trap_dbgdidr(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
@@ -2762,7 +3220,7 @@ static bool trap_dbgdidr(struct kvm_vcpu *vcpu,
 	if (p->is_write) {
 		return ignore_write(vcpu, p);
 	} else {
-		u64 dfr = IDREG(vcpu->kvm, SYS_ID_AA64DFR0_EL1);
+		u64 dfr = kvm_read_vm_id_reg(vcpu->kvm, SYS_ID_AA64DFR0_EL1);
 		u32 el3 = kvm_has_feat(vcpu->kvm, ID_AA64PFR0_EL1, EL3, IMP);
 
 		p->regval = ((SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr) << 28) |
@@ -3440,6 +3898,25 @@ static bool emulate_sys_reg(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+static const struct sys_reg_desc *idregs_debug_find(struct kvm *kvm, u8 pos)
+{
+	unsigned long i, idreg_idx = 0;
+
+	for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) {
+		const struct sys_reg_desc *r = &sys_reg_descs[i];
+
+		if (!is_vm_ftr_id_reg(reg_to_encoding(r)))
+			continue;
+
+		if (idreg_idx == pos)
+			return r;
+
+		idreg_idx++;
+	}
+
+	return NULL;
+}
+
 static void *idregs_debug_start(struct seq_file *s, loff_t *pos)
 {
 	struct kvm *kvm = s->private;
@@ -3451,7 +3928,7 @@ static void *idregs_debug_start(struct seq_file *s, loff_t *pos)
 	if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags) &&
 	    *iter == (u8)~0) {
 		*iter = *pos;
-		if (*iter >= KVM_ARM_ID_REG_NUM)
+		if (!idregs_debug_find(kvm, *iter))
 			iter = NULL;
 	} else {
 		iter = ERR_PTR(-EBUSY);
@@ -3468,7 +3945,7 @@ static void *idregs_debug_next(struct seq_file *s, void *v, loff_t *pos)
 
 	(*pos)++;
 
-	if ((kvm->arch.idreg_debugfs_iter + 1) < KVM_ARM_ID_REG_NUM) {
+	if (idregs_debug_find(kvm, kvm->arch.idreg_debugfs_iter + 1)) {
 		kvm->arch.idreg_debugfs_iter++;
 
 		return &kvm->arch.idreg_debugfs_iter;
@@ -3493,16 +3970,16 @@ static void idregs_debug_stop(struct seq_file *s, void *v)
 
 static int idregs_debug_show(struct seq_file *s, void *v)
 {
-	struct kvm *kvm = s->private;
 	const struct sys_reg_desc *desc;
+	struct kvm *kvm = s->private;
 
-	desc = first_idreg + kvm->arch.idreg_debugfs_iter;
+	desc = idregs_debug_find(kvm, kvm->arch.idreg_debugfs_iter);
 
 	if (!desc->name)
 		return 0;
 
 	seq_printf(s, "%20s:\t%016llx\n",
-		   desc->name, IDREG(kvm, IDX_IDREG(kvm->arch.idreg_debugfs_iter)));
+		   desc->name, kvm_read_vm_id_reg(kvm, reg_to_encoding(desc)));
 
 	return 0;
 }
@@ -3532,8 +4009,7 @@ static void reset_vm_ftr_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc
 	if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))
 		return;
 
-	lockdep_assert_held(&kvm->arch.config_lock);
-	IDREG(kvm, id) = reg->reset(vcpu, reg);
+	kvm_set_vm_id_reg(kvm, id, reg->reset(vcpu, reg));
 }
 
 static void reset_vcpu_ftr_id_reg(struct kvm_vcpu *vcpu,
@@ -3686,8 +4162,8 @@ id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id,
  */
 
 #define FUNCTION_INVARIANT(reg)						\
-	static u64 get_##reg(struct kvm_vcpu *v,			\
-			      const struct sys_reg_desc *r)		\
+	static u64 reset_##reg(struct kvm_vcpu *v,			\
+			       const struct sys_reg_desc *r)		\
 	{								\
 		((struct sys_reg_desc *)r)->val = read_sysreg(reg);	\
 		return ((struct sys_reg_desc *)r)->val;			\
@@ -3697,18 +4173,11 @@ FUNCTION_INVARIANT(midr_el1)
 FUNCTION_INVARIANT(revidr_el1)
 FUNCTION_INVARIANT(aidr_el1)
 
-static u64 get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r)
-{
-	((struct sys_reg_desc *)r)->val = read_sanitised_ftr_reg(SYS_CTR_EL0);
-	return ((struct sys_reg_desc *)r)->val;
-}
-
 /* ->val is filled in by kvm_sys_reg_table_init() */
 static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = {
-	{ SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },
-	{ SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 },
-	{ SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 },
-	{ SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 },
+	{ SYS_DESC(SYS_MIDR_EL1), NULL, reset_midr_el1 },
+	{ SYS_DESC(SYS_REVIDR_EL1), NULL, reset_revidr_el1 },
+	{ SYS_DESC(SYS_AIDR_EL1), NULL, reset_aidr_el1 },
 };
 
 static int get_invariant_sys_reg(u64 id, u64 __user *uaddr)
@@ -4019,20 +4488,11 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *
 		if (!is_feature_id_reg(encoding) || !reg->set_user)
 			continue;
 
-		/*
-		 * For ID registers, we return the writable mask. Other feature
-		 * registers return a full 64bit mask. That's not necessary
-		 * compliant with a given revision of the architecture, but the
-		 * RES0/RES1 definitions allow us to do that.
-		 */
-		if (is_vm_ftr_id_reg(encoding)) {
-			if (!reg->val ||
-			    (is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0()))
-				continue;
-			val = reg->val;
-		} else {
-			val = ~0UL;
+		if (!reg->val ||
+		    (is_aa32_id_reg(encoding) && !kvm_supports_32bit_el0())) {
+			continue;
 		}
+		val = reg->val;
 
 		if (put_user(val, (masks + KVM_ARM_FEATURE_ID_RANGE_INDEX(encoding))))
 			return -EFAULT;
@@ -4041,11 +4501,34 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *
 	return 0;
 }
 
-void kvm_init_sysreg(struct kvm_vcpu *vcpu)
+static void vcpu_set_hcr(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
 
-	mutex_lock(&kvm->arch.config_lock);
+	if (has_vhe() || has_hvhe())
+		vcpu->arch.hcr_el2 |= HCR_E2H;
+	if (cpus_have_final_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_final_cap(ARM64_HAS_STAGE2_FWB))
+		vcpu->arch.hcr_el2 |= HCR_FWB;
+
+	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
+	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE) &&
+	    kvm_read_vm_id_reg(kvm, SYS_CTR_EL0) == read_sanitised_ftr_reg(SYS_CTR_EL0))
+		vcpu->arch.hcr_el2 |= HCR_TID4;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TID2;
+
+	if (vcpu_el1_is_32bit(vcpu))
+		vcpu->arch.hcr_el2 &= ~HCR_RW;
+
+	if (kvm_has_mte(vcpu->kvm))
+		vcpu->arch.hcr_el2 |= HCR_ATA;
 
 	/*
 	 * In the absence of FGT, we cannot independently trap TLBI
@@ -4054,12 +4537,29 @@ void kvm_init_sysreg(struct kvm_vcpu *vcpu)
 	 */
 	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
 		vcpu->arch.hcr_el2 |= HCR_TTLBOS;
+}
+
+void kvm_calculate_traps(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&kvm->arch.config_lock);
+	vcpu_set_hcr(vcpu);
 
 	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
-		vcpu->arch.hcrx_el2 = HCRX_GUEST_FLAGS;
+		/*
+		 * In general, all HCRX_EL2 bits are gated by a feature.
+		 * The only reason we can set SMPME without checking any
+		 * feature is that its effects are not directly observable
+		 * from the guest.
+		 */
+		vcpu->arch.hcrx_el2 = HCRX_EL2_SMPME;
 
 		if (kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
 			vcpu->arch.hcrx_el2 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
+
+		if (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
+			vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En;
 	}
 
 	if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))
@@ -4115,7 +4615,6 @@ out:
 
 int __init kvm_sys_reg_table_init(void)
 {
-	struct sys_reg_params params;
 	bool valid = true;
 	unsigned int i;
 	int ret = 0;
@@ -4136,12 +4635,6 @@ int __init kvm_sys_reg_table_init(void)
 	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
 		invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]);
 
-	/* Find the first idreg (SYS_ID_PFR0_EL1) in sys_reg_descs. */
-	params = encoding_to_params(SYS_ID_PFR0_EL1);
-	first_idreg = find_reg(&params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
-	if (!first_idreg)
-		return -EINVAL;
-
 	ret = populate_nv_trap_config();
 
 	for (i = 0; !ret && i < ARRAY_SIZE(sys_reg_descs); i++)