Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Correctly handle 'invariant' system registers for protected VMs

   - Improved handling of VNCR data aborts, including external aborts

   - Fixes for handling of FEAT_RAS for NV guests, providing a sane
     fault context during SEA injection and preventing the use of
     RASv1p1 fault injection hardware

   - Ensure that page table destruction when a VM is destroyed gives an
     opportunity to reschedule

   - Large fix to KVM's infrastructure for managing guest context loaded
     on the CPU, addressing issues where the output of AT emulation
     doesn't get reflected to the guest

   - Fix AT S12 emulation to actually perform stage-2 translation when
     necessary

   - Avoid attempting vLPI irqbypass when GICv4 has been explicitly
     disabled for a VM

   - Minor KVM + selftest fixes

  RISC-V:

   - Fix pte settings within kvm_riscv_gstage_ioremap()

   - Fix comments in kvm_riscv_check_vcpu_requests()

   - Fix stack overrun when setting vlenb via ONE_REG

  x86:

   - Use array_index_nospec() to sanitize the target vCPU ID when
     handling PV IPIs and yields as the ID is guest-controlled.

   - Drop a superfluous cpumask_empty() check when reclaiming SEV
     memory, as the common case, by far, is that at least one CPU will
     have entered the VM, and wbnoinvd_on_cpus_mask() will naturally
     handle the rare case where the set of have_run_cpus is empty.

  Selftests (not KVM):

   - Rename the is_signed_type() macro in kselftest_harness.h to
     is_signed_var() to fix a collision with linux/overflow.h. The
     collision generates compiler warnings due to the two macros having
     different meaning"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (29 commits)
  KVM: arm64: nv: Fix ATS12 handling of single-stage translation
  KVM: arm64: Remove __vcpu_{read,write}_sys_reg_{from,to}_cpu()
  KVM: arm64: Fix vcpu_{read,write}_sys_reg() accessors
  KVM: arm64: Simplify sysreg access on exception delivery
  KVM: arm64: Check for SYSREGS_ON_CPU before accessing the 32bit state
  RISC-V: KVM: fix stack overrun when loading vlenb
  RISC-V: KVM: Correct kvm_riscv_check_vcpu_requests() comment
  RISC-V: KVM: Fix pte settings within kvm_riscv_gstage_ioremap()
  KVM: arm64: selftests: Sync ID_AA64MMFR3_EL1 in set_id_regs
  KVM: arm64: Get rid of ARM64_FEATURE_MASK()
  KVM: arm64: Make ID_AA64PFR1_EL1.RAS_frac writable
  KVM: arm64: Make ID_AA64PFR0_EL1.RAS writable
  KVM: arm64: Ignore HCR_EL2.FIEN set by L1 guest's EL2
  KVM: arm64: Handle RASv1p1 registers
  arm64: Add capability denoting FEAT_RASv1p1
  KVM: arm64: Reschedule as needed when destroying the stage-2 page-tables
  KVM: arm64: Split kvm_pgtable_stage2_destroy()
  selftests: harness: Rename is_signed_type() to avoid collision with overflow.h
  KVM: SEV: don't check have_run_cpus in sev_writeback_caches()
  KVM: arm64: Correctly populate FAR_EL2 on nested SEA injection
  ...

arch/arm64/include/asm/kvm_host.h

@@ -1160,115 +1160,8 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 		__v;							\
 	})
 
-u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
-void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
-
-static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
-{
-	/*
-	 * *** VHE ONLY ***
-	 *
-	 * System registers listed in the switch are not saved on every
-	 * exit from the guest but are only saved on vcpu_put.
-	 *
-	 * SYSREGS_ON_CPU *MUST* be checked before using this helper.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the guest cannot modify its
-	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
-	 * thread when emulating cross-VCPU communication.
-	 */
-	if (!has_vhe())
-		return false;
-
-	switch (reg) {
-	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
-	case TCR2_EL1:		*val = read_sysreg_s(SYS_TCR2_EL12);	break;
-	case PIR_EL1:		*val = read_sysreg_s(SYS_PIR_EL12);	break;
-	case PIRE0_EL1:		*val = read_sysreg_s(SYS_PIRE0_EL12);	break;
-	case POR_EL1:		*val = read_sysreg_s(SYS_POR_EL12);	break;
-	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
-	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
-	case SPSR_EL1:		*val = read_sysreg_s(SYS_SPSR_EL12);	break;
-	case PAR_EL1:		*val = read_sysreg_par();		break;
-	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
-	case ZCR_EL1:		*val = read_sysreg_s(SYS_ZCR_EL12);	break;
-	case SCTLR2_EL1:	*val = read_sysreg_s(SYS_SCTLR2_EL12);	break;
-	default:		return false;
-	}
-
-	return true;
-}
-
-static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
-{
-	/*
-	 * *** VHE ONLY ***
-	 *
-	 * System registers listed in the switch are not restored on every
-	 * entry to the guest but are only restored on vcpu_load.
-	 *
-	 * SYSREGS_ON_CPU *MUST* be checked before using this helper.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the MPIDR should only be set
-	 * once, before running the VCPU, and never changed later.
-	 */
-	if (!has_vhe())
-		return false;
-
-	switch (reg) {
-	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
-	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
-	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
-	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
-	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
-	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
-	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
-	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
-	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
-	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
-	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
-	case SCTLR2_EL1:	write_sysreg_s(val, SYS_SCTLR2_EL12);	break;
-	default:		return false;
-	}
-
-	return true;
-}
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+void vcpu_write_sys_reg(struct kvm_vcpu *, u64, enum vcpu_sysreg);
 
 struct kvm_vm_stat {
 	struct kvm_vm_stat_generic generic;

arch/arm64/include/asm/kvm_mmu.h

@@ -180,6 +180,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
+int kvm_handle_guest_sea(struct kvm_vcpu *vcpu);
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);

arch/arm64/include/asm/kvm_pgtable.h

@@ -355,6 +355,11 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke
 	return pteref;
 }
 
+static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref)
+{
+	return pteref;
+}
+
 static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
 {
 	/*
@@ -384,6 +389,11 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke
 	return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED));
 }
 
+static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref)
+{
+	return rcu_dereference_raw(pteref);
+}
+
 static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
 {
 	if (walker->flags & KVM_PGTABLE_WALK_SHARED)
@@ -551,6 +561,26 @@ static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2
  */
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
+/**
+ * kvm_pgtable_stage2_destroy_range() - Destroy the unlinked range of addresses.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:      Intermediate physical address at which to place the mapping.
+ * @size:      Size of the mapping.
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+
+/**
+ * kvm_pgtable_stage2_destroy_pgd() - Destroy the PGD of guest stage-2 page-table.
+ * @pgt:       Page-table structure initialised by kvm_pgtable_stage2_init*().
+ *
+ * It is assumed that the rest of the page-table is freed before this operation.
+ */
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
+
 /**
  * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure.
  * @mm_ops:	Memory management callbacks.

arch/arm64/include/asm/kvm_pkvm.h

@@ -179,7 +179,9 @@ struct pkvm_mapping {
 
 int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			     struct kvm_pgtable_mm_ops *mm_ops);
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 			    enum kvm_pgtable_prot prot, void *mc,
 			    enum kvm_pgtable_walk_flags flags);

arch/arm64/include/asm/kvm_ras.h

@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2018 - Arm Ltd */
-
-#ifndef __ARM64_KVM_RAS_H__
-#define __ARM64_KVM_RAS_H__
-
-#include <linux/acpi.h>
-#include <linux/errno.h>
-#include <linux/types.h>
-
-#include <asm/acpi.h>
-
-/*
- * Was this synchronous external abort a RAS notification?
- * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
- */
-static inline int kvm_handle_guest_sea(void)
-{
-	/* apei_claim_sea(NULL) expects to mask interrupts itself */
-	lockdep_assert_irqs_enabled();
-
-	return apei_claim_sea(NULL);
-}
-
-#endif /* __ARM64_KVM_RAS_H__ */

arch/arm64/include/asm/sysreg.h

@@ -1142,9 +1142,6 @@
 
 #define ARM64_FEATURE_FIELD_BITS	4
 
-/* Defined for compatibility only, do not add new users. */
-#define ARM64_FEATURE_MASK(x)	(x##_MASK)
-
 #ifdef __ASSEMBLY__
 
 	.macro	mrs_s, rt, sreg

arch/arm64/kernel/cpufeature.c

@@ -2269,6 +2269,24 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
 	/* Firmware may have left a deferred SError in this register. */
 	write_sysreg_s(0, SYS_DISR_EL1);
 }
+static bool has_rasv1p1(const struct arm64_cpu_capabilities *__unused, int scope)
+{
+	const struct arm64_cpu_capabilities rasv1p1_caps[] = {
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, V1P1)
+		},
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP)
+		},
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, RAS_frac, RASv1p1)
+		},
+	};
+
+	return (has_cpuid_feature(&rasv1p1_caps[0], scope) ||
+		(has_cpuid_feature(&rasv1p1_caps[1], scope) &&
+		 has_cpuid_feature(&rasv1p1_caps[2], scope)));
+}
 #endif /* CONFIG_ARM64_RAS_EXTN */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -2687,6 +2705,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_clear_disr,
 		ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP)
 	},
+	{
+		.desc = "RASv1p1 Extension Support",
+		.capability = ARM64_HAS_RASV1P1_EXTN,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_rasv1p1,
+	},
 #endif /* CONFIG_ARM64_RAS_EXTN */
 #ifdef CONFIG_ARM64_AMU_EXTN
 	{

arch/arm64/kvm/arm.c

@@ -2408,12 +2408,12 @@ static u64 get_hyp_id_aa64pfr0_el1(void)
 	 */
 	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
-	val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) |
-		 ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3));
+	val &= ~(ID_AA64PFR0_EL1_CSV2 |
+		 ID_AA64PFR0_EL1_CSV3);
 
-	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2),
+	val |= FIELD_PREP(ID_AA64PFR0_EL1_CSV2,
 			  arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED);
-	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3),
+	val |= FIELD_PREP(ID_AA64PFR0_EL1_CSV3,
 			  arm64_get_meltdown_state() == SPECTRE_UNAFFECTED);
 
 	return val;

arch/arm64/kvm/at.c

@@ -1420,10 +1420,10 @@ void __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 		return;
 
 	/*
-	 * If we only have a single stage of translation (E2H=0 or
-	 * TGE=1), exit early. Same thing if {VM,DC}=={0,0}.
+	 * If we only have a single stage of translation (EL2&0), exit
+	 * early. Same thing if {VM,DC}=={0,0}.
 	 */
-	if (!vcpu_el2_e2h_is_set(vcpu) || vcpu_el2_tge_is_set(vcpu) ||
+	if (compute_translation_regime(vcpu, op) == TR_EL20 ||
 	    !(vcpu_read_sys_reg(vcpu, HCR_EL2) & (HCR_VM | HCR_DC)))
 		return;
 

arch/arm64/kvm/emulate-nested.c

@@ -2833,7 +2833,7 @@ int kvm_inject_nested_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr)
 			     iabt ? ESR_ELx_EC_IABT_LOW : ESR_ELx_EC_DABT_LOW);
 	esr |= ESR_ELx_FSC_EXTABT | ESR_ELx_IL;
 
-	vcpu_write_sys_reg(vcpu, FAR_EL2, addr);
+	vcpu_write_sys_reg(vcpu, addr, FAR_EL2);
 
 	if (__vcpu_sys_reg(vcpu, SCTLR2_EL2) & SCTLR2_EL1_EASE)
 		return kvm_inject_nested(vcpu, esr, except_type_serror);

arch/arm64/kvm/hyp/exception.c

@@ -22,36 +22,28 @@
 
 static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
-	u64 val;
-
-	if (unlikely(vcpu_has_nv(vcpu)))
+	if (has_vhe())
 		return vcpu_read_sys_reg(vcpu, reg);
-	else if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-		 __vcpu_read_sys_reg_from_cpu(reg, &val))
-		return val;
 
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (unlikely(vcpu_has_nv(vcpu)))
+	if (has_vhe())
 		vcpu_write_sys_reg(vcpu, val, reg);
-	else if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU) ||
-		 !__vcpu_write_sys_reg_to_cpu(val, reg))
+	else
 		__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 			      u64 val)
 {
-	if (unlikely(vcpu_has_nv(vcpu))) {
+	if (has_vhe()) {
 		if (target_mode == PSR_MODE_EL1h)
 			vcpu_write_sys_reg(vcpu, val, SPSR_EL1);
 		else
 			vcpu_write_sys_reg(vcpu, val, SPSR_EL2);
-	} else if (has_vhe()) {
-		write_sysreg_el1(val, SYS_SPSR);
 	} else {
 		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, val);
 	}
@@ -59,7 +51,7 @@ static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 
 static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (has_vhe())
+	if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
 		write_sysreg(val, spsr_abt);
 	else
 		vcpu->arch.ctxt.spsr_abt = val;
@@ -67,7 +59,7 @@ static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
 
 static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (has_vhe())
+	if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
 		write_sysreg(val, spsr_und);
 	else
 		vcpu->arch.ctxt.spsr_und = val;

arch/arm64/kvm/hyp/nvhe/list_debug.c

@@ -17,7 +17,7 @@ static inline __must_check bool nvhe_check_data_corruption(bool v)
 		bool corruption = unlikely(condition);			 \
 		if (corruption) {					 \
 			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
-				BUG_ON(1);				 \
+				BUG();				 	 \
 			} else						 \
 				WARN_ON(1);				 \
 		}							 \

arch/arm64/kvm/hyp/nvhe/sys_regs.c

@@ -253,6 +253,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+	__vcpu_assign_sys_reg(vcpu, read_sysreg_el1(SYS_VBAR), VBAR_EL1);
 
 	kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
 
@@ -372,6 +373,9 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 
 	/* Debug and Trace Registers are restricted. */
 
+	/* Group 1 ID registers */
+	HOST_HANDLED(SYS_REVIDR_EL1),
+
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
 	AARCH32(SYS_ID_PFR0_EL1),
@@ -460,6 +464,7 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 
 	HOST_HANDLED(SYS_CCSIDR_EL1),
 	HOST_HANDLED(SYS_CLIDR_EL1),
+	HOST_HANDLED(SYS_AIDR_EL1),
 	HOST_HANDLED(SYS_CSSELR_EL1),
 	HOST_HANDLED(SYS_CTR_EL0),
 

arch/arm64/kvm/hyp/pgtable.c

@@ -1551,21 +1551,38 @@ static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	return 0;
 }
 
-void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+				       u64 addr, u64 size)
 {
-	size_t pgd_sz;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_free_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF |
 			  KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+}
+
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	size_t pgd_sz;
+
 	pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE;
-	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz);
+
+	/*
+	 * Since the pgtable is unlinked at this point, and not shared with
+	 * other walkers, safely deference pgd with kvm_dereference_pteref_raw()
+	 */
+	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref_raw(pgt->pgd), pgd_sz);
 	pgt->pgd = NULL;
 }
 
+void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits));
+	kvm_pgtable_stage2_destroy_pgd(pgt);
+}
+
 void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;

arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c

@@ -20,7 +20,7 @@ static bool __is_be(struct kvm_vcpu *vcpu)
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
 
-	return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+	return !!(read_sysreg_el1(SYS_SCTLR) & SCTLR_ELx_EE);
 }
 
 /*

arch/arm64/kvm/hyp/vhe/switch.c

@@ -43,8 +43,11 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
  *
  * - API/APK: they are already accounted for by vcpu_load(), and can
  *   only take effect across a load/put cycle (such as ERET)
+ *
+ * - FIEN: no way we let a guest have access to the RAS "Common Fault
+ *   Injection" thing, whatever that does
  */
-#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK)
+#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK | HCR_FIEN)
 
 static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/mmu.c

@@ -4,19 +4,20 @@
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/acpi.h>
 #include <linux/mman.h>
 #include <linux/kvm_host.h>
 #include <linux/io.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/signal.h>
 #include <trace/events/kvm.h>
+#include <asm/acpi.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
 #include <asm/kvm_pkvm.h>
-#include <asm/kvm_ras.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/virt.h>
@@ -903,6 +904,38 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 	return 0;
 }
 
+/*
+ * Assume that @pgt is valid and unlinked from the KVM MMU to free the
+ * page-table without taking the kvm_mmu_lock and without performing any
+ * TLB invalidations.
+ *
+ * Also, the range of addresses can be large enough to cause need_resched
+ * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke
+ * cond_resched() periodically to prevent hogging the CPU for a long time
+ * and schedule something else, if required.
+ */
+static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr,
+				   phys_addr_t end)
+{
+	u64 next;
+
+	do {
+		next = stage2_range_addr_end(addr, end);
+		KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr,
+								next - addr);
+		if (next != end)
+			cond_resched();
+	} while (addr = next, addr != end);
+}
+
+static void kvm_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr);
+
+	stage2_destroy_range(pgt, 0, BIT(ia_bits));
+	KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt);
+}
+
 /**
  * kvm_init_stage2_mmu - Initialise a S2 MMU structure
  * @kvm:	The pointer to the KVM structure
@@ -979,7 +1012,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return 0;
 
 out_destroy_pgtable:
-	KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
+	kvm_stage2_destroy(pgt);
 out_free_pgtable:
 	kfree(pgt);
 	return err;
@@ -1076,7 +1109,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
-		KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
+		kvm_stage2_destroy(pgt);
 		kfree(pgt);
 	}
 }
@@ -1811,6 +1844,19 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
+int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Give APEI the opportunity to claim the abort before handling it
+	 * within KVM. apei_claim_sea() expects to be called with IRQs enabled.
+	 */
+	lockdep_assert_irqs_enabled();
+	if (apei_claim_sea(NULL) == 0)
+		return 1;
+
+	return kvm_inject_serror(vcpu);
+}
+
 /**
  * kvm_handle_guest_abort - handles all 2nd stage aborts
  * @vcpu:	the VCPU pointer
@@ -1834,17 +1880,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	/* Synchronous External Abort? */
-	if (kvm_vcpu_abt_issea(vcpu)) {
-		/*
-		 * For RAS the host kernel may handle this abort.
-		 * There is no need to pass the error into the guest.
-		 */
-		if (kvm_handle_guest_sea())
-			return kvm_inject_serror(vcpu);
-
-		return 1;
-	}
+	if (kvm_vcpu_abt_issea(vcpu))
+		return kvm_handle_guest_sea(vcpu);
 
 	esr = kvm_vcpu_get_esr(vcpu);
 

arch/arm64/kvm/nested.c

@@ -1287,7 +1287,10 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 	struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
 	u64 esr = kvm_vcpu_get_esr(vcpu);
 
-	BUG_ON(!(esr & ESR_ELx_VNCR_SHIFT));
+	WARN_ON_ONCE(!(esr & ESR_ELx_VNCR));
+
+	if (kvm_vcpu_abt_issea(vcpu))
+		return kvm_handle_guest_sea(vcpu);
 
 	if (esr_fsc_is_permission_fault(esr)) {
 		inject_vncr_perm(vcpu);

arch/arm64/kvm/pkvm.c

@@ -316,9 +316,16 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e
 	return 0;
 }
 
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size)
 {
-	__pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL));
+	__pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+}
+
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	/* Expected to be called after all pKVM mappings have been released. */
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&pgt->pkvm_mappings.rb_root));
 }
 
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,