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

Pull kvm fixes from Paolo Bonzini:
 "A bit on the bigger side, mostly due to me being on vacation, then
  busy, then on parental leave, but there's nothing worrisome.

  ARM:
   - Multiple stolen time fixes, with a new capability to match x86
   - Fix for hugetlbfs mappings when PUD and PMD are the same level
   - Fix for hugetlbfs mappings when PTE mappings are enforced (dirty
     logging, for example)
   - Fix tracing output of 64bit values

  x86:
   - nSVM state restore fixes
   - Async page fault fixes
   - Lots of small fixes everywhere"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (25 commits)
  KVM: emulator: more strict rsm checks.
  KVM: nSVM: more strict SMM checks when returning to nested guest
  SVM: nSVM: setup nested msr permission bitmap on nested state load
  SVM: nSVM: correctly restore GIF on vmexit from nesting after migration
  x86/kvm: don't forget to ACK async PF IRQ
  x86/kvm: properly use DEFINE_IDTENTRY_SYSVEC() macro
  KVM: VMX: Don't freeze guest when event delivery causes an APIC-access exit
  KVM: SVM: avoid emulation with stale next_rip
  KVM: x86: always allow writing '0' to MSR_KVM_ASYNC_PF_EN
  KVM: SVM: Periodically schedule when unregistering regions on destroy
  KVM: MIPS: Change the definition of kvm type
  kvm x86/mmu: use KVM_REQ_MMU_SYNC to sync when needed
  KVM: nVMX: Fix the update value of nested load IA32_PERF_GLOBAL_CTRL control
  KVM: fix memory leak in kvm_io_bus_unregister_dev()
  KVM: Check the allocation of pv cpu mask
  KVM: nVMX: Update VMCS02 when L2 PAE PDPTE updates detected
  KVM: arm64: Update page shift if stage 2 block mapping not supported
  KVM: arm64: Fix address truncation in traces
  KVM: arm64: Do not try to map PUDs when they are folded into PMD
  arm64/x86: KVM: Introduce steal-time cap
  ...

21 files changed, 180 insertions, 81 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index eb3a1316f03ec9..d2b733dc7892cb 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6130,7 +6130,7 @@ HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
 -----------------------------------
 
-:Architecture: x86
+:Architectures: x86
 
 This capability indicates that KVM running on top of Hyper-V hypervisor
 enables Direct TLB flush for its guests meaning that TLB flush
@@ -6143,19 +6143,33 @@ in CPUID and only exposes Hyper-V identification. In this case, guest
 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
 
 8.22 KVM_CAP_S390_VCPU_RESETS
+-----------------------------
 
-Architectures: s390
+:Architectures: s390
 
 This capability indicates that the KVM_S390_NORMAL_RESET and
 KVM_S390_CLEAR_RESET ioctls are available.
 
 8.23 KVM_CAP_S390_PROTECTED
+---------------------------
 
-Architecture: s390
-
+:Architectures: s390
 
 This capability indicates that the Ultravisor has been initialized and
 KVM can therefore start protected VMs.
 This capability governs the KVM_S390_PV_COMMAND ioctl and the
 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
 guests when the state change is invalid.
+
+8.24 KVM_CAP_STEAL_TIME
+-----------------------
+
+:Architectures: arm64, x86
+
+This capability indicates that KVM supports steal time accounting.
+When steal time accounting is supported it may be enabled with
+architecture-specific interfaces.  This capability and the architecture-
+specific interfaces must be consistent, i.e. if one says the feature
+is supported, than the other should as well and vice versa.  For arm64
+see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
+For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e52c927aade538..905c2b87e05acc 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -368,7 +368,6 @@ struct kvm_vcpu_arch {
 
 	/* Guest PV state */
 	struct {
-		u64 steal;
 		u64 last_steal;
 		gpa_t base;
 	} steal;
@@ -544,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
 
+bool kvm_arm_pvtime_supported(void);
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 46dc3d75cf1359..b588c3b5c2f07b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ba00bcc0c88463..9a636b8064f1fe 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1877,6 +1877,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
 		force_pte = true;
 		vma_pagesize = PAGE_SIZE;
+		vma_shift = PAGE_SHIFT;
 	}
 
 	/*
@@ -1970,7 +1971,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		(fault_status == FSC_PERM &&
 		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
 
-	if (vma_pagesize == PUD_SIZE) {
+	/*
+	 * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+	 * all we have is a 2-level page table. Trying to map a PUD in
+	 * this case would be fatally wrong.
+	 */
+	if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
 		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
 
 		new_pud = kvm_pud_mkhuge(new_pud);
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index f7b52ce1557ec3..920ac43077ad3b 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -13,25 +13,22 @@
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	u64 steal;
-	__le64 steal_le;
-	u64 offset;
-	int idx;
 	u64 base = vcpu->arch.steal.base;
+	u64 last_steal = vcpu->arch.steal.last_steal;
+	u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	u64 steal = 0;
+	int idx;
 
 	if (base == GPA_INVALID)
 		return;
 
-	/* Let's do the local bookkeeping */
-	steal = vcpu->arch.steal.steal;
-	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
-	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-	vcpu->arch.steal.steal = steal;
-
-	steal_le = cpu_to_le64(steal);
 	idx = srcu_read_lock(&kvm->srcu);
-	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
-	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	if (!kvm_get_guest(kvm, base + offset, steal)) {
+		steal = le64_to_cpu(steal);
+		vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay);
+		steal += vcpu->arch.steal.last_steal - last_steal;
+		kvm_put_guest(kvm, base + offset, cpu_to_le64(steal));
+	}
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -43,7 +40,8 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 	case ARM_SMCCC_HV_PV_TIME_ST:
-		val = SMCCC_RET_SUCCESS;
+		if (vcpu->arch.steal.base != GPA_INVALID)
+			val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
@@ -64,7 +62,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	 * Start counting stolen time from the time the guest requests
 	 * the feature enabled.
 	 */
-	vcpu->arch.steal.steal = 0;
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
 
 	idx = srcu_read_lock(&kvm->srcu);
@@ -74,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index 4691053c5ee426..ff0444352bba3e 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -23,7 +23,7 @@ TRACE_EVENT(kvm_entry,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+	TP_printk("PC: 0x%016lx", __entry->vcpu_pc)
 );
 
 TRACE_EVENT(kvm_exit,
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_exit,
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx",
 		  __print_symbolic(__entry->ret, kvm_arm_exception_type),
 		  __entry->esr_ec,
 		  __print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
@@ -69,7 +69,7 @@ TRACE_EVENT(kvm_guest_fault,
 		__entry->ipa			= ipa;
 	),
 
-	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
 		  __entry->ipa, __entry->hsr,
 		  __entry->hxfar, __entry->vcpu_pc)
 );
@@ -131,7 +131,7 @@ TRACE_EVENT(kvm_mmio_emulate,
 		__entry->cpsr			= cpsr;
 	),
 
-	TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+	TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)",
 		  __entry->vcpu_pc, __entry->instr, __entry->cpsr)
 );
 
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_unmap_hva_range,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+	TP_printk("mmu notifier unmap range: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -165,7 +165,7 @@ TRACE_EVENT(kvm_set_spte_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier set pte hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_age_hva,
@@ -182,7 +182,7 @@ TRACE_EVENT(kvm_age_hva,
 		__entry->end		= end;
 	),
 
-	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+	TP_printk("mmu notifier age hva: %#016lx -- %#016lx",
 		  __entry->start, __entry->end)
 );
 
@@ -198,7 +198,7 @@ TRACE_EVENT(kvm_test_age_hva,
 		__entry->hva		= hva;
 	),
 
-	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+	TP_printk("mmu notifier test age hva: %#016lx", __entry->hva)
 );
 
 TRACE_EVENT(kvm_set_way_flush,
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 2c56d1e0f5bd54..8d78acc4fba7ef 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -22,7 +22,7 @@ TRACE_EVENT(kvm_wfx_arm64,
 		__entry->is_wfe  = is_wfe;
 	),
 
-	TP_printk("guest executed wf%c at: 0x%08lx",
+	TP_printk("guest executed wf%c at: 0x%016lx",
 		  __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
 );
 
@@ -42,7 +42,7 @@ TRACE_EVENT(kvm_hvc_arm64,
 		__entry->imm = imm;
 	),
 
-	TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)",
+	TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)",
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
@@ -135,7 +135,7 @@ TRACE_EVENT(trap_reg,
 		__entry->write_value = write_value;
 	),
 
-	TP_printk("%s %s reg %d (0x%08llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
+	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
 );
 
 TRACE_EVENT(kvm_handle_sys_reg,
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7de85d2253ff5c..0c50ac4442221f 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -137,6 +137,8 @@ extern void kvm_init_loongson_ipi(struct kvm *kvm);
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	switch (type) {
+	case KVM_VM_MIPS_AUTO:
+		break;
 #ifdef CONFIG_KVM_MIPS_VZ
 	case KVM_VM_MIPS_VZ:
 #else
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 08320b0b2b276f..1b51b727b14057 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -270,9 +270,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	u32 token;
-	irqentry_state_t state;
 
-	state = irqentry_enter(regs);
+	ack_APIC_irq();
 
 	inc_irq_stat(irq_hv_callback_count);
 
@@ -283,7 +282,6 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 		wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
 	}
 
-	irqentry_exit(regs, state);
 	set_irq_regs(old_regs);
 }
 
@@ -654,7 +652,6 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (pv_tlb_flush_supported()) {
-		pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
@@ -767,6 +764,14 @@ static __init int activate_jump_labels(void)
 }
 arch_initcall(activate_jump_labels);
 
+static void kvm_free_pv_cpu_mask(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		free_cpumask_var(per_cpu(__pv_cpu_mask, cpu));
+}
+
 static __init int kvm_alloc_cpumask(void)
 {
 	int cpu;
@@ -785,11 +790,20 @@ static __init int kvm_alloc_cpumask(void)
 
 	if (alloc)
 		for_each_possible_cpu(cpu) {
-			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
-				GFP_KERNEL, cpu_to_node(cpu));
+			if (!zalloc_cpumask_var_node(
+				per_cpu_ptr(&__pv_cpu_mask, cpu),
+				GFP_KERNEL, cpu_to_node(cpu))) {
+				goto zalloc_cpumask_fail;
+			}
 		}
 
+	apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
+	pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 	return 0;
+
+zalloc_cpumask_fail:
+	kvm_free_pv_cpu_mask();
+	return -ENOMEM;
 }
 arch_initcall(kvm_alloc_cpumask);
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5299ef5ff18d0b..2f6510de6b0c03 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2505,9 +2505,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
 	val = GET_SMSTATE(u32, smstate, 0x7fcc);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7fc8);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
 	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
@@ -2560,16 +2565,23 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
 	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
 	val = GET_SMSTATE(u32, smstate, 0x7f68);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7f60);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
 	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
 	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
-	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
 	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 43fdb0c12a5dd5..71aa3da2a0b7b0 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2469,7 +2469,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		}
 
 		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
 
 		__clear_sp_write_flooding_count(sp);
 
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index fb68467e60496a..e90bc436f5849b 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -586,7 +586,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	/* Give the current vmcb to the guest */
-	svm_set_gif(svm, false);
 
 	nested_vmcb->save.es     = vmcb->save.es;
 	nested_vmcb->save.cs     = vmcb->save.cs;
@@ -632,6 +631,9 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(&vmcb->control, &hsave->control);
 
+	/* On vmexit the  GIF is set to false */
+	svm_set_gif(svm, false);
+
 	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
 		svm->vcpu.arch.l1_tsc_offset;
 
@@ -1132,6 +1134,9 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	load_nested_vmcb_control(svm, &ctl);
 	nested_prepare_vmcb_control(svm);
 
+	if (!nested_svm_vmrun_msrpm(svm))
+		return -EINVAL;
+
 out_set_gif:
 	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
 	return 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 402dc4234e3978..7bf7bf73497948 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1106,6 +1106,7 @@ void sev_vm_destroy(struct kvm *kvm)
 		list_for_each_safe(pos, q, head) {
 			__unregister_enc_region_locked(kvm,
 				list_entry(pos, struct enc_region, list));
+			cond_resched();
 		}
 	}
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0194336b64a4c0..c44f3e9140d5fe 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2938,8 +2938,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	if (npt_enabled)
 		vcpu->arch.cr3 = svm->vmcb->save.cr3;
 
-	svm_complete_interrupts(svm);
-
 	if (is_guest_mode(vcpu)) {
 		int vmexit;
 
@@ -3504,7 +3502,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	stgi();
 
 	/* Any pending NMI will happen here */
-	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_after_interrupt(&svm->vcpu);
@@ -3518,6 +3515,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
+	vmcb_mark_all_clean(svm->vmcb);
 
 	/* if exit due to PF check for async PF */
 	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
@@ -3537,7 +3535,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 		     SVM_EXIT_EXCP_BASE + MC_VECTOR))
 		svm_handle_mce(svm);
 
-	vmcb_mark_all_clean(svm->vmcb);
+	svm_complete_interrupts(svm);
+	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 	return exit_fastpath;
 }
 
@@ -3900,21 +3899,28 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *nested_vmcb;
 	struct kvm_host_map map;
-	u64 guest;
-	u64 vmcb;
 	int ret = 0;
 
-	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
+	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+		u64 vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
 
-	if (guest) {
-		if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL)
-			return 1;
-		nested_vmcb = map.hva;
-		ret = enter_svm_guest_mode(svm, vmcb, nested_vmcb);
-		kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		if (guest) {
+			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+				return 1;
+
+			if (!(saved_efer & EFER_SVME))
+				return 1;
+
+			if (kvm_vcpu_map(&svm->vcpu,
+					 gpa_to_gfn(vmcb), &map) == -EINVAL)
+				return 1;
+
+			ret = enter_svm_guest_mode(svm, vmcb, map.hva);
+			kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		}
 	}
 
 	return ret;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 23b58c28a1c926..1bb6b31eb64666 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4404,6 +4404,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 		kvm_vcpu_flush_tlb_current(vcpu);
 
+	/*
+	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
+	 * now and the new vmentry.  Ensure that the VMCS02 PDPTR fields are
+	 * up-to-date before switching to L1.
+	 */
+	if (enable_ept && is_pae_paging(vcpu))
+		vmx_ept_load_pdptrs(vcpu);
+
 	leave_guest_mode(vcpu);
 
 	if (nested_cpu_has_preemption_timer(vmcs12))
@@ -4668,7 +4676,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 		vmx->nested.msrs.entry_ctls_high &=
 				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 		vmx->nested.msrs.exit_ctls_high &=
-				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+				~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 	}
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 819c185adf09b3..8646a797b7a838 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2971,7 +2971,7 @@ static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	vpid_sync_context(to_vmx(vcpu)->vpid);
 }
 
-static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
@@ -3114,7 +3114,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd,
 			guest_cr3 = vcpu->arch.cr3;
 		else /* vmcs01.GUEST_CR3 is already up-to-date. */
 			update_guest_cr3 = false;
-		ept_load_pdptrs(vcpu);
+		vmx_ept_load_pdptrs(vcpu);
 	} else {
 		guest_cr3 = pgd;
 	}
@@ -6054,6 +6054,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 26175a4759fa5f..a2f82127c1707a 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -356,6 +356,7 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
 int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
 int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 			      struct x86_exception *e);
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d39d6cf1d4737b..1994602a0851f2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2731,7 +2731,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 1;
 
 	if (!lapic_in_kernel(vcpu))
-		return 1;
+		return data ? 1 : 0;
 
 	vcpu->arch.apf.msr_en_val = data;
 
@@ -3578,6 +3578,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = sched_info_on();
+		break;
 	default:
 		break;
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a23076765b4cc2..05e3c2fb3ef782 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -749,25 +749,46 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
 
-#define __kvm_put_guest(kvm, gfn, offset, value, type)			\
+#define __kvm_get_guest(kvm, gfn, offset, v)				\
 ({									\
 	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
-	type __user *__uaddr = (type __user *)(__addr + offset);	\
+	typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset);	\
 	int __ret = -EFAULT;						\
 									\
 	if (!kvm_is_error_hva(__addr))					\
-		__ret = put_user(value, __uaddr);			\
+		__ret = get_user(v, __uaddr);				\
+	__ret;								\
+})
+
+#define kvm_get_guest(kvm, gpa, v)					\
+({									\
+	gpa_t __gpa = gpa;						\
+	struct kvm *__kvm = kvm;					\
+									\
+	__kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT,			\
+			offset_in_page(__gpa), v);			\
+})
+
+#define __kvm_put_guest(kvm, gfn, offset, v)				\
+({									\
+	unsigned long __addr = gfn_to_hva(kvm, gfn);			\
+	typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset);	\
+	int __ret = -EFAULT;						\
+									\
+	if (!kvm_is_error_hva(__addr))					\
+		__ret = put_user(v, __uaddr);				\
 	if (!__ret)							\
 		mark_page_dirty(kvm, gfn);				\
 	__ret;								\
 })
 
-#define kvm_put_guest(kvm, gpa, value, type)				\
+#define kvm_put_guest(kvm, gpa, v)					\
 ({									\
 	gpa_t __gpa = gpa;						\
 	struct kvm *__kvm = kvm;					\
+									\
 	__kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT,			\
-			offset_in_page(__gpa), (value), type);		\
+			offset_in_page(__gpa), v);			\
 })
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6d86033c4fa3d..7d8eced6f459b0 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -1035,6 +1036,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 67cd0b88a6b6ff..cf88233b819a08 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4332,7 +4332,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			       struct kvm_io_device *dev)
 {
-	int i;
+	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm_get_bus(kvm, bus_idx);
@@ -4349,17 +4349,20 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
 			  GFP_KERNEL_ACCOUNT);
-	if (!new_bus)  {
+	if (new_bus) {
+		memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+		new_bus->dev_count--;
+		memcpy(new_bus->range + i, bus->range + i + 1,
+		       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
+	} else {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		goto broken;
+		for (j = 0; j < bus->dev_count; j++) {
+			if (j == i)
+				continue;
+			kvm_iodevice_destructor(bus->range[j].dev);
+		}
 	}
 
-	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
-	new_bus->dev_count--;
-	memcpy(new_bus->range + i, bus->range + i + 1,
-	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
-
-broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);