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

Pull more kvm updates from Paolo Bonzini:
 "Generic:

   - selftest compilation fix for non-x86

   - KVM: avoid warning on s390 in mark_page_dirty

 x86:

   - fix page write-protection bug and improve comments

   - use binary search to lookup the PMU event filter, add test

   - enable_pmu module parameter support for Intel CPUs

   - switch blocked_vcpu_on_cpu_lock to raw spinlock

   - cleanups of blocked vCPU logic

   - partially allow KVM_SET_CPUID{,2} after KVM_RUN (5.16 regression)

   - various small fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (46 commits)
  docs: kvm: fix WARNINGs from api.rst
  selftests: kvm/x86: Fix the warning in lib/x86_64/processor.c
  selftests: kvm/x86: Fix the warning in pmu_event_filter_test.c
  kvm: selftests: Do not indent with spaces
  kvm: selftests: sync uapi/linux/kvm.h with Linux header
  selftests: kvm: add amx_test to .gitignore
  KVM: SVM: Nullify vcpu_(un)blocking() hooks if AVIC is disabled
  KVM: SVM: Move svm_hardware_setup() and its helpers below svm_x86_ops
  KVM: SVM: Drop AVIC's intermediate avic_set_running() helper
  KVM: VMX: Don't do full kick when handling posted interrupt wakeup
  KVM: VMX: Fold fallback path into triggering posted IRQ helper
  KVM: VMX: Pass desired vector instead of bool for triggering posted IRQ
  KVM: VMX: Don't do full kick when triggering posted interrupt "fails"
  KVM: SVM: Skip AVIC and IRTE updates when loading blocking vCPU
  KVM: SVM: Use kvm_vcpu_is_blocking() in AVIC load to handle preemption
  KVM: SVM: Remove unnecessary APICv/AVIC update in vCPU unblocking path
  KVM: SVM: Don't bother checking for "running" AVIC when kicking for IPIs
  KVM: SVM: Signal AVIC doorbell iff vCPU is in guest mode
  KVM: x86: Remove defunct pre_block/post_block kvm_x86_ops hooks
  KVM: x86: Unexport LAPIC's switch_to_{hv,sw}_timer() helpers
  ...

1 files changed, 40 insertions, 30 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 76b4803dd3bd..9e43d756312f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -187,6 +187,11 @@ module_param(force_emulation_prefix, bool, S_IRUGO);
 int __read_mostly pi_inject_timer = -1;
 module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
 
+/* Enable/disable PMU virtualization */
+bool __read_mostly enable_pmu = true;
+EXPORT_SYMBOL_GPL(enable_pmu);
+module_param(enable_pmu, bool, 0444);
+
 /*
  * Restoring the host value for MSRs that are only consumed when running in
  * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
@@ -5230,17 +5235,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
 
-		/*
-		 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
-		 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
-		 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
-		 * faults due to reusing SPs/SPTEs.  In practice no sane VMM mucks with
-		 * the core vCPU model on the fly, so fail.
-		 */
-		r = -EINVAL;
-		if (vcpu->arch.last_vmentry_cpu != -1)
-			goto out;
-
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5251,14 +5245,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
-		/*
-		 * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
-		 * KVM_SET_CPUID case above.
-		 */
-		r = -EINVAL;
-		if (vcpu->arch.last_vmentry_cpu != -1)
-			goto out;
-
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -9945,10 +9931,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	smp_mb__after_srcu_read_unlock();
 
 	/*
-	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.  Assigned devices can
-	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
-	 * so do it even if APICv is disabled on this vCPU.
+	 * Process pending posted interrupts to handle the case where the
+	 * notification IRQ arrived in the host, or was never sent (because the
+	 * target vCPU wasn't running).  Do this regardless of the vCPU's APICv
+	 * status, KVM doesn't update assigned devices when APICv is inhibited,
+	 * i.e. they can post interrupts even if APICv is temporarily disabled.
 	 */
 	if (kvm_lapic_enabled(vcpu))
 		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
@@ -10113,8 +10100,20 @@ out:
 
 static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 {
-	if (!kvm_arch_vcpu_runnable(vcpu) &&
-	    (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) {
+	bool hv_timer;
+
+	if (!kvm_arch_vcpu_runnable(vcpu)) {
+		/*
+		 * Switch to the software timer before halt-polling/blocking as
+		 * the guest's timer may be a break event for the vCPU, and the
+		 * hypervisor timer runs only when the CPU is in guest mode.
+		 * Switch before halt-polling so that KVM recognizes an expired
+		 * timer before blocking.
+		 */
+		hv_timer = kvm_lapic_hv_timer_in_use(vcpu);
+		if (hv_timer)
+			kvm_lapic_switch_to_sw_timer(vcpu);
+
 		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 		if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
 			kvm_vcpu_halt(vcpu);
@@ -10122,8 +10121,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 			kvm_vcpu_block(vcpu);
 		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 
-		if (kvm_x86_ops.post_block)
-			static_call(kvm_x86_post_block)(vcpu);
+		if (hv_timer)
+			kvm_lapic_switch_to_hv_timer(vcpu);
 
 		if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
 			return 1;
@@ -10316,6 +10315,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			r = -EINTR;
 			goto out;
 		}
+		/*
+		 * It should be impossible for the hypervisor timer to be in
+		 * use before KVM has ever run the vCPU.
+		 */
+		WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu));
 		kvm_vcpu_block(vcpu);
 		if (kvm_apic_accept_events(vcpu) < 0) {
 			r = 0;
@@ -10360,10 +10364,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
-	if (kvm_run->immediate_exit)
+	if (kvm_run->immediate_exit) {
 		r = -EINTR;
-	else
-		r = vcpu_run(vcpu);
+		goto out;
+	}
+
+	r = static_call(kvm_x86_vcpu_pre_run)(vcpu);
+	if (r <= 0)
+		goto out;
+
+	r = vcpu_run(vcpu);
 
 out:
 	kvm_put_guest_fpu(vcpu);