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

Pull kvm fixes from Paolo Bonzini:

- Fixes for s390 interrupt delivery

- Fixes for Xen emulator bugs showing up as debug kernel WARNs

- Fix another issue with SEV/ES string I/O VMGEXITs

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86: Take srcu lock in post_kvm_run_save()
KVM: SEV-ES: fix another issue with string I/O VMGEXITs
KVM: x86/xen: Fix kvm_xen_has_interrupt() sleeping in kvm_vcpu_block()
KVM: x86: switch pvclock_gtod_sync_lock to a raw spinlock
KVM: s390: preserve deliverable_mask in __airqs_kick_single_vcpu
KVM: s390: clear kicked_mask before sleeping again

arch/s390/kvm/interrupt.c

···
 	int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
 	struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
 	struct kvm_vcpu *vcpu;
+	u8 vcpu_isc_mask;
 
 	for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
 		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
 		if (psw_ioint_disabled(vcpu))
 			continue;
-		deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
-		if (deliverable_mask) {
+		vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+		if (deliverable_mask & vcpu_isc_mask) {
 			/* lately kicked but not yet running */
 			if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
 				return;

arch/s390/kvm/kvm-s390.c

···
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
 	return kvm_s390_vcpu_has_irq(vcpu, 0);
 }
 

arch/x86/include/asm/kvm_host.h

···
 	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
 
-	spinlock_t pvclock_gtod_sync_lock;
+	raw_spinlock_t pvclock_gtod_sync_lock;
 	bool use_master_clock;
 	u64 master_kernel_ns;
 	u64 master_cycle_now;

arch/x86/kvm/svm/sev.c

···
 
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 {
-	if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+	int count;
+	int bytes;
+
+	if (svm->vmcb->control.exit_info_2 > INT_MAX)
 		return -EINVAL;
 
-	return kvm_sev_es_string_io(&svm->vcpu, size, port,
-				    svm->ghcb_sa, svm->ghcb_sa_len / size, in);
+	count = svm->vmcb->control.exit_info_2;
+	if (unlikely(check_mul_overflow(count, size, &bytes)))
+		return -EINVAL;
+
+	if (!setup_vmgexit_scratch(svm, in, bytes))
+		return -EINVAL;
+
+	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
 }
 
 void sev_es_init_vmcb(struct vcpu_svm *svm)

arch/x86/kvm/x86.c

···
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
-	spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
 	if (!matched) {
 		kvm->arch.nr_vcpus_matched_tsc = 0;
 	} else if (!already_matched) {
···
 	}
 
 	kvm_track_tsc_matching(vcpu);
-	spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
 }
 
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
···
 	kvm_make_mclock_inprogress_request(kvm);
 
 	/* no guest entries from this point */
-	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	pvclock_update_vm_gtod_copy(kvm);
-	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
···
 	unsigned long flags;
 	u64 ret;
 
-	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	if (!ka->use_master_clock) {
-		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+		raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 		return get_kvmclock_base_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
-	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
 	get_cpu();
···
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
 	 */
-	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	use_master_clock = ka->use_master_clock;
 	if (use_master_clock) {
 		host_tsc = ka->master_cycle_now;
 		kernel_ns = ka->master_kernel_ns;
 	}
-	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
···
 		 * is slightly ahead) here we risk going negative on unsigned
 		 * 'system_time' when 'user_ns.clock' is very small.
 		 */
-		spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+		raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock);
 		if (kvm->arch.use_master_clock)
 			now_ns = ka->master_kernel_ns;
 		else
 			now_ns = get_kvmclock_base_ns();
 		ka->kvmclock_offset = user_ns.clock - now_ns;
-		spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+		raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
 
 		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
 		break;
···
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		struct kvm_arch *ka = &kvm->arch;
 
-		spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+		raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 		pvclock_update_vm_gtod_copy(kvm);
-		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+		raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
···
 
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
+
+	/*
+	 * The call to kvm_ready_for_interrupt_injection() may end up in
+	 * kvm_xen_has_interrupt() which may require the srcu lock to be
+	 * held, to protect against changes in the vcpu_info address.
+	 */
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	kvm_run->ready_for_interrupt_injection =
 		pic_in_kernel(vcpu->kvm) ||
 		kvm_vcpu_ready_for_interrupt_injection(vcpu);
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 
 	if (is_smm(vcpu))
 		kvm_run->flags |= KVM_RUN_X86_SMM;
···
 
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
-	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+	raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
 	kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
 	pvclock_update_vm_gtod_copy(kvm);

arch/x86/kvm/xen.c

···
 
 int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
 {
+	int err;
 	u8 rc = 0;
 
 	/*
···
 	if (likely(slots->generation == ghc->generation &&
 		   !kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
 		/* Fast path */
-		__get_user(rc, (u8 __user *)ghc->hva + offset);
-	} else {
-		/* Slow path */
-		kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
-					     sizeof(rc));
+		pagefault_disable();
+		err = __get_user(rc, (u8 __user *)ghc->hva + offset);
+		pagefault_enable();
+		if (!err)
+			return rc;
 	}
+
+	/* Slow path */
+
+	/*
+	 * This function gets called from kvm_vcpu_block() after setting the
+	 * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
+	 * from a HLT. So we really mustn't sleep. If the page ended up absent
+	 * at that point, just return 1 in order to trigger an immediate wake,
+	 * and we'll end up getting called again from a context where we *can*
+	 * fault in the page and wait for it.
+	 */
+	if (in_atomic() || !task_is_running(current))
+		return 1;
+
+	kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+				     sizeof(rc));
 
 	return rc;
 }