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

Pull KVM fixes from Paolo Bonzini:
 "More fixes for ARM and x86"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: LAPIC: Advancing the timer expiration on guest initiated write
  KVM: x86/mmu: Skip !MMU-present SPTEs when removing SP in exclusive mode
  KVM: kvmclock: Fix vCPUs > 64 can't be online/hotpluged
  kvm: x86: annotate RCU pointers
  KVM: arm64: Fix exclusive limit for IPA size
  KVM: arm64: Reject VM creation when the default IPA size is unsupported
  KVM: arm64: Ensure I-cache isolation between vcpus of a same VM
  KVM: arm64: Don't use cbz/adr with external symbols
  KVM: arm64: Fix range alignment when walking page tables
  KVM: arm64: Workaround firmware wrongly advertising GICv2-on-v3 compatibility
  KVM: arm64: Rename __vgic_v3_get_ich_vtr_el2() to __vgic_v3_get_gic_config()
  KVM: arm64: Don't access PMSELR_EL0/PMUSERENR_EL0 when no PMU is available
  KVM: arm64: Turn kvm_arm_support_pmu_v3() into a static key
  KVM: arm64: Fix nVHE hyp panic host context restore
  KVM: arm64: Avoid corrupting vCPU context register in guest exit
  KVM: arm64: nvhe: Save the SPE context early
  kvm: x86: use NULL instead of using plain integer as pointer
  KVM: SVM: Connect 'npt' module param to KVM's internal 'npt_enabled'
  KVM: x86: Ensure deadline timer has truly expired before posting its IRQ

arch/x86/include/asm/kvm_host.h

@@ -963,7 +963,7 @@ struct kvm_arch {
 	struct kvm_pit *vpit;
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
-	struct kvm_apic_map *apic_map;
+	struct kvm_apic_map __rcu *apic_map;
 	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
@@ -1036,7 +1036,7 @@ struct kvm_arch {
 
 	bool bus_lock_detection_enabled;
 
-	struct kvm_pmu_event_filter *pmu_event_filter;
+	struct kvm_pmu_event_filter __rcu *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 
 #ifdef CONFIG_X86_64

arch/x86/kernel/kvmclock.c

@@ -268,21 +268,20 @@ static void __init kvmclock_init_mem(void)
 
 static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-#ifdef CONFIG_X86_64
-	u8 flags;
-
-	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
-		return 0;
-
-	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
-		return 0;
-
-	kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
-#endif
-
 	kvmclock_init_mem();
 
+#ifdef CONFIG_X86_64
+	if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) {
+		u8 flags;
+
+		flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+		if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+			return 0;
+
+		kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+	}
+#endif
+
 	return 0;
 }
 early_initcall(kvm_setup_vsyscall_timeinfo);

arch/x86/kvm/lapic.c

@@ -1642,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
-		kvm_wait_lapic_expire(vcpu);
+		/*
+		 * Ensure the guest's timer has truly expired before posting an
+		 * interrupt.  Open code the relevant checks to avoid querying
+		 * lapic_timer_int_injected(), which will be false since the
+		 * interrupt isn't yet injected.  Waiting until after injecting
+		 * is not an option since that won't help a posted interrupt.
+		 */
+		if (vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+		    vcpu->arch.apic->lapic_timer.timer_advance_ns)
+			__kvm_wait_lapic_expire(vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;
 	}
@@ -2595,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic->lapic_timer.expired_tscdeadline = 0;
 	apic_update_lvtt(apic);
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 	update_divide_count(apic);

arch/x86/kvm/mmu/tdp_mmu.c

@@ -337,7 +337,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
 				cpu_relax();
 			}
 		} else {
+			/*
+			 * If the SPTE is not MMU-present, there is no backing
+			 * page associated with the SPTE and so no side effects
+			 * that need to be recorded, and exclusive ownership of
+			 * mmu_lock ensures the SPTE can't be made present.
+			 * Note, zapping MMIO SPTEs is also unnecessary as they
+			 * are guarded by the memslots generation, not by being
+			 * unreachable.
+			 */
 			old_child_spte = READ_ONCE(*sptep);
+			if (!is_shadow_present_pte(old_child_spte))
+				continue;
 
 			/*
 			 * Marking the SPTE as a removed SPTE is not

arch/x86/kvm/svm/svm.c

@@ -115,13 +115,6 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_INVALID,				.always = false },
 };
 
-/* enable NPT for AMD64 and X86 with PAE */
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-bool npt_enabled = true;
-#else
-bool npt_enabled;
-#endif
-
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * pause_filter_count: On processors that support Pause filtering(indicated
@@ -170,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444);
 static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
 module_param(pause_filter_count_max, ushort, 0444);
 
-/* allow nested paging (virtualized MMU) for all guests */
-static int npt = true;
-module_param(npt, int, S_IRUGO);
+/*
+ * Use nested page tables by default.  Note, NPT may get forced off by
+ * svm_hardware_setup() if it's unsupported by hardware or the host kernel.
+ */
+bool npt_enabled = true;
+module_param_named(npt, npt_enabled, bool, 0444);
 
 /* allow nested virtualization in KVM/SVM */
 static int nested = true;
@@ -988,10 +984,15 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	if (!boot_cpu_has(X86_FEATURE_NPT))
+	/*
+	 * KVM's MMU doesn't support using 2-level paging for itself, and thus
+	 * NPT isn't supported if the host is using 2-level paging since host
+	 * CR4 is unchanged on VMRUN.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
 		npt_enabled = false;
 
-	if (npt_enabled && !npt)
+	if (!boot_cpu_has(X86_FEATURE_NPT))
 		npt_enabled = false;
 
 	kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);

arch/x86/kvm/x86.c

@@ -10601,7 +10601,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
-			return 0;
+			return NULL;
 
 		old_npages = slot->npages;
 		hva = slot->userspace_addr;