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

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Take care of faults occuring between the PARange and IPA range by
     injecting an exception

   - Fix S2 faults taken from a host EL0 in protected mode

   - Work around Oops caused by a PMU access from a 32bit guest when PMU
     has been created. This is a temporary bodge until we fix it for
     good.

  x86:

   - Fix potential races when walking host page table

   - Fix shadow page table leak when KVM runs nested

   - Work around bug in userspace when KVM synthesizes leaf 0x80000021
     on older (pre-EPYC) or Intel processors

  Generic (but affects only RISC-V):

   - Fix bad user ABI for KVM_EXIT_SYSTEM_EVENT"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: work around QEMU issue with synthetic CPUID leaves
  Revert "x86/mm: Introduce lookup_address_in_mm()"
  KVM: x86/mmu: fix potential races when walking host page table
  KVM: fix bad user ABI for KVM_EXIT_SYSTEM_EVENT
  KVM: x86/mmu: Do not create SPTEs for GFNs that exceed host.MAXPHYADDR
  KVM: arm64: Inject exception on out-of-IPA-range translation fault
  KVM/arm64: Don't emulate a PMU for 32-bit guests if feature not set
  KVM: arm64: Handle host stage-2 faults from 32-bit EL0

6 files changed, 81 insertions, 11 deletions

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 7496deab025a..f71358271b71 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -40,6 +40,7 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_size_fault(struct kvm_vcpu *vcpu);
 
 void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 3d613e721a75..727c979b2b69 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -198,15 +198,15 @@ SYM_CODE_START(__kvm_hyp_host_vector)
 	invalid_host_el2_vect			// FIQ EL2h
 	invalid_host_el2_vect			// Error EL2h
 
-	host_el1_sync_vect			// Synchronous 64-bit EL1
-	invalid_host_el1_vect			// IRQ 64-bit EL1
-	invalid_host_el1_vect			// FIQ 64-bit EL1
-	invalid_host_el1_vect			// Error 64-bit EL1
-
-	invalid_host_el1_vect			// Synchronous 32-bit EL1
-	invalid_host_el1_vect			// IRQ 32-bit EL1
-	invalid_host_el1_vect			// FIQ 32-bit EL1
-	invalid_host_el1_vect			// Error 32-bit EL1
+	host_el1_sync_vect			// Synchronous 64-bit EL1/EL0
+	invalid_host_el1_vect			// IRQ 64-bit EL1/EL0
+	invalid_host_el1_vect			// FIQ 64-bit EL1/EL0
+	invalid_host_el1_vect			// Error 64-bit EL1/EL0
+
+	host_el1_sync_vect			// Synchronous 32-bit EL1/EL0
+	invalid_host_el1_vect			// IRQ 32-bit EL1/EL0
+	invalid_host_el1_vect			// FIQ 32-bit EL1/EL0
+	invalid_host_el1_vect			// Error 32-bit EL1/EL0
 SYM_CODE_END(__kvm_hyp_host_vector)
 
 /*
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index b47df73e98d7..ba20405d2dc2 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -145,6 +145,34 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 		inject_abt64(vcpu, true, addr);
 }
 
+void kvm_inject_size_fault(struct kvm_vcpu *vcpu)
+{
+	unsigned long addr, esr;
+
+	addr  = kvm_vcpu_get_fault_ipa(vcpu);
+	addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
+
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		kvm_inject_pabt(vcpu, addr);
+	else
+		kvm_inject_dabt(vcpu, addr);
+
+	/*
+	 * If AArch64 or LPAE, set FSC to 0 to indicate an Address
+	 * Size Fault at level 0, as if exceeding PARange.
+	 *
+	 * Non-LPAE guests will only get the external abort, as there
+	 * is no way to to describe the ASF.
+	 */
+	if (vcpu_el1_is_32bit(vcpu) &&
+	    !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE))
+		return;
+
+	esr = vcpu_read_sys_reg(vcpu, ESR_EL1);
+	esr &= ~GENMASK_ULL(5, 0);
+	vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
+}
+
 /**
  * kvm_inject_undefined - inject an undefined instruction into the guest
  * @vcpu: The vCPU in which to inject the exception
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 53ae2c0640bc..5400fc020164 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1337,6 +1337,25 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
+	if (fault_status == FSC_FAULT) {
+		/* Beyond sanitised PARange (which is the IPA limit) */
+		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
+			kvm_inject_size_fault(vcpu);
+			return 1;
+		}
+
+		/* Falls between the IPA range and the PARange? */
+		if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) {
+			fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
+
+			if (is_iabt)
+				kvm_inject_pabt(vcpu, fault_ipa);
+			else
+				kvm_inject_dabt(vcpu, fault_ipa);
+			return 1;
+		}
+	}
+
 	/* Synchronous External Abort? */
 	if (kvm_vcpu_abt_issea(vcpu)) {
 		/*
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 78fdc443adc7..3dc990ac4f44 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -177,6 +177,9 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return 0;
+
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
 	if (kvm_pmu_pmc_is_chained(pmc) &&
@@ -198,6 +201,9 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 {
 	u64 reg;
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return;
+
 	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
 	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
 	__vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
@@ -322,6 +328,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	struct kvm_pmc *pmc;
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return;
+
 	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val)
 		return;
 
@@ -357,7 +366,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	struct kvm_pmc *pmc;
 
-	if (!val)
+	if (!kvm_vcpu_has_pmu(vcpu) || !val)
 		return;
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
@@ -527,6 +536,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	int i;
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return;
+
 	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
 		return;
 
@@ -576,6 +588,9 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return;
+
 	if (val & ARMV8_PMU_PMCR_E) {
 		kvm_pmu_enable_counter_mask(vcpu,
 		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0));
@@ -739,6 +754,9 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 {
 	u64 reg, mask;
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return;
+
 	mask  =  ARMV8_PMU_EVTYPE_MASK;
 	mask &= ~ARMV8_PMU_EVTYPE_EVENT;
 	mask |= kvm_pmu_event_mask(vcpu->kvm);
@@ -827,6 +845,9 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	u64 val, mask = 0;
 	int base, i, nr_events;
 
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return 0;
+
 	if (!pmceid1) {
 		val = read_sysreg(pmceid0_el0);
 		base = 0;
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index baac2b405f23..708d80e8e60d 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -181,7 +181,8 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
 
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
 	vcpu->run->system_event.type = type;
-	vcpu->run->system_event.flags = flags;
+	vcpu->run->system_event.ndata = 1;
+	vcpu->run->system_event.data[0] = flags;
 	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 }