Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Avi Kivity:
 "Changes include additional instruction emulation, page-crossing MMIO,
  faster dirty logging, preventing the watchdog from killing a stopped
  guest, module autoload, a new MSI ABI, and some minor optimizations
  and fixes.  Outside x86 we have a small s390 and a very large ppc
  update.

  Regarding the new (for kvm) rebaseless workflow, some of the patches
  that were merged before we switch trees had to be rebased, while
  others are true pulls.  In either case the signoffs should be correct
  now."

Fix up trivial conflicts in Documentation/feature-removal-schedule.txt
arch/powerpc/kvm/book3s_segment.S and arch/x86/include/asm/kvm_para.h.

I suspect the kvm_para.h resolution ends up doing the "do I have cpuid"
check effectively twice (it was done differently in two different
commits), but better safe than sorry ;)

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (125 commits)
  KVM: make asm-generic/kvm_para.h have an ifdef __KERNEL__ block
  KVM: s390: onereg for timer related registers
  KVM: s390: epoch difference and TOD programmable field
  KVM: s390: KVM_GET/SET_ONEREG for s390
  KVM: s390: add capability indicating COW support
  KVM: Fix mmu_reload() clash with nested vmx event injection
  KVM: MMU: Don't use RCU for lockless shadow walking
  KVM: VMX: Optimize %ds, %es reload
  KVM: VMX: Fix %ds/%es clobber
  KVM: x86 emulator: convert bsf/bsr instructions to emulate_2op_SrcV_nobyte()
  KVM: VMX: unlike vmcs on fail path
  KVM: PPC: Emulator: clean up SPR reads and writes
  KVM: PPC: Emulator: clean up instruction parsing
  kvm/powerpc: Add new ioctl to retreive server MMU infos
  kvm/book3s: Make kernel emulated H_PUT_TCE available for "PR" KVM
  KVM: PPC: bookehv: Fix r8/r13 storing in level exception handler
  KVM: PPC: Book3S: Enable IRQs during exit handling
  KVM: PPC: Fix PR KVM on POWER7 bare metal
  KVM: PPC: Fix stbux emulation
  KVM: PPC: bookehv: Use lwz/stw instead of PPC_LL/PPC_STL for 32-bit fields
  ...

5 files changed, 112 insertions, 48 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index f63ccb0..28694f4 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -18,3 +18,6 @@ config KVM_MMIO
 
 config KVM_ASYNC_PF
        bool
+
+config HAVE_KVM_MSI
+       bool
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index dcaf272c26..26fd54d 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -254,13 +254,17 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 	}
 }
 
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	smp_rmb();
+	return test_bit(vector, ioapic->handled_vectors);
+}
+
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
-	smp_rmb();
-	if (!test_bit(vector, ioapic->handled_vectors))
-		return;
 	spin_lock(&ioapic->lock);
 	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
 	spin_unlock(&ioapic->lock);
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 0b190c3..32872a0 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -71,6 +71,7 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 		int short_hand, int dest, int dest_mode);
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
 int kvm_ioapic_init(struct kvm *kvm);
 void kvm_ioapic_destroy(struct kvm *kvm);
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 9f614b4..a6a0365 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -138,6 +138,20 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+	struct kvm_kernel_irq_routing_entry route;
+
+	if (!irqchip_in_kernel(kvm) || msi->flags != 0)
+		return -EINVAL;
+
+	route.msi.address_lo = msi->address_lo;
+	route.msi.address_hi = msi->address_hi;
+	route.msi.data = msi->data;
+
+	return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
+}
+
 /*
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9739b53..7e14068 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -522,12 +522,11 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 		return;
 
 	if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)
-		vfree(memslot->dirty_bitmap_head);
+		vfree(memslot->dirty_bitmap);
 	else
-		kfree(memslot->dirty_bitmap_head);
+		kfree(memslot->dirty_bitmap);
 
 	memslot->dirty_bitmap = NULL;
-	memslot->dirty_bitmap_head = NULL;
 }
 
 /*
@@ -611,8 +610,7 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 
 /*
  * Allocation size is twice as large as the actual dirty bitmap size.
- * This makes it possible to do double buffering: see x86's
- * kvm_vm_ioctl_get_dirty_log().
+ * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed.
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
@@ -627,8 +625,6 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
-	memslot->dirty_bitmap_head = memslot->dirty_bitmap;
-	memslot->nr_dirty_pages = 0;
 #endif /* !CONFIG_S390 */
 	return 0;
 }
@@ -1477,8 +1473,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 
-		if (!test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap))
-			memslot->nr_dirty_pages++;
+		/* TODO: introduce set_bit_le() and use it */
+		test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 
@@ -1515,6 +1511,30 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	finish_wait(&vcpu->wq, &wait);
 }
 
+#ifndef CONFIG_S390
+/*
+ * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
+ */
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	int me;
+	int cpu = vcpu->cpu;
+	wait_queue_head_t *wqp;
+
+	wqp = kvm_arch_vcpu_wq(vcpu);
+	if (waitqueue_active(wqp)) {
+		wake_up_interruptible(wqp);
+		++vcpu->stat.halt_wakeup;
+	}
+
+	me = get_cpu();
+	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
+		if (kvm_arch_vcpu_should_kick(vcpu))
+			smp_send_reschedule(cpu);
+	put_cpu();
+}
+#endif /* !CONFIG_S390 */
+
 void kvm_resched(struct kvm_vcpu *vcpu)
 {
 	if (!need_resched())
@@ -1523,6 +1543,31 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
+{
+	struct pid *pid;
+	struct task_struct *task = NULL;
+
+	rcu_read_lock();
+	pid = rcu_dereference(target->pid);
+	if (pid)
+		task = get_pid_task(target->pid, PIDTYPE_PID);
+	rcu_read_unlock();
+	if (!task)
+		return false;
+	if (task->flags & PF_VCPU) {
+		put_task_struct(task);
+		return false;
+	}
+	if (yield_to(task, 1)) {
+		put_task_struct(task);
+		return true;
+	}
+	put_task_struct(task);
+	return false;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
@@ -1541,8 +1586,6 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	 */
 	for (pass = 0; pass < 2 && !yielded; pass++) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			struct task_struct *task = NULL;
-			struct pid *pid;
 			if (!pass && i < last_boosted_vcpu) {
 				i = last_boosted_vcpu;
 				continue;
@@ -1552,24 +1595,11 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (waitqueue_active(&vcpu->wq))
 				continue;
-			rcu_read_lock();
-			pid = rcu_dereference(vcpu->pid);
-			if (pid)
-				task = get_pid_task(vcpu->pid, PIDTYPE_PID);
-			rcu_read_unlock();
-			if (!task)
-				continue;
-			if (task->flags & PF_VCPU) {
-				put_task_struct(task);
-				continue;
-			}
-			if (yield_to(task, 1)) {
-				put_task_struct(task);
+			if (kvm_vcpu_yield_to(vcpu)) {
 				kvm->last_boosted_vcpu = i;
 				yielded = 1;
 				break;
 			}
-			put_task_struct(task);
 		}
 	}
 }
@@ -2040,6 +2070,17 @@ static long kvm_vm_ioctl(struct file *filp,
 		mutex_unlock(&kvm->lock);
 		break;
 #endif
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_SIGNAL_MSI: {
+		struct kvm_msi msi;
+
+		r = -EFAULT;
+		if (copy_from_user(&msi, argp, sizeof msi))
+			goto out;
+		r = kvm_send_userspace_msi(kvm, &msi);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)
@@ -2168,6 +2209,9 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 	case KVM_CAP_SET_BOOT_CPU_ID:
 #endif
 	case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_CAP_SIGNAL_MSI:
+#endif
 		return 1;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQ_ROUTING:
@@ -2394,9 +2438,6 @@ int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 			  gpa_t addr, int len)
 {
-	if (bus->dev_count == NR_IOBUS_DEVS)
-		return -ENOSPC;
-
 	bus->range[bus->dev_count++] = (struct kvm_io_range) {
 		.addr = addr,
 		.len = len,
@@ -2496,12 +2537,15 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-	if (bus->dev_count > NR_IOBUS_DEVS-1)
+	if (bus->dev_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
 
-	new_bus = kmemdup(bus, sizeof(struct kvm_io_bus), GFP_KERNEL);
+	new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) *
+			  sizeof(struct kvm_io_range)), GFP_KERNEL);
 	if (!new_bus)
 		return -ENOMEM;
+	memcpy(new_bus, bus, sizeof(*bus) + (bus->dev_count *
+	       sizeof(struct kvm_io_range)));
 	kvm_io_bus_insert_dev(new_bus, dev, addr, len);
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
@@ -2518,27 +2562,25 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-
-	new_bus = kmemdup(bus, sizeof(*bus), GFP_KERNEL);
-	if (!new_bus)
-		return -ENOMEM;
-
 	r = -ENOENT;
-	for (i = 0; i < new_bus->dev_count; i++)
-		if (new_bus->range[i].dev == dev) {
+	for (i = 0; i < bus->dev_count; i++)
+		if (bus->range[i].dev == dev) {
 			r = 0;
-			new_bus->dev_count--;
-			new_bus->range[i] = new_bus->range[new_bus->dev_count];
-			sort(new_bus->range, new_bus->dev_count,
-			     sizeof(struct kvm_io_range),
-			     kvm_io_bus_sort_cmp, NULL);
 			break;
 		}
 
-	if (r) {
-		kfree(new_bus);
+	if (r)
 		return r;
-	}
+
+	new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count - 1) *
+			  sizeof(struct kvm_io_range)), GFP_KERNEL);
+	if (!new_bus)
+		return -ENOMEM;
+
+	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));
 
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);