Merge tag 'v5.12-rc3' into x86/cleanups, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 37 insertions, 15 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 45d40bfacb7c..cc369b9ad8f1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/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);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index c926c6b899a1..d78915019b08 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/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
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index baee91c1e936..58a45bb139f8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/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);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50810d471462..32cf8287d4a7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6580,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 	int i, nr_msrs;
 	struct perf_guest_switch_msr *msrs;
 
+	/* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */
 	msrs = perf_guest_get_msrs(&nr_msrs);
-
 	if (!msrs)
 		return;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c020499efe47..edf96b3650c5 100644
--- a/arch/x86/kvm/x86.c
+++ b/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;