DEFINE_SPINLOCK(kvm_lock);
LIST_HEAD(vm_list);
-static cpumask_t cpus_hardware_enabled;
+static cpumask_var_t cpus_hardware_enabled;
struct kmem_cache *kvm_vcpu_cache;
EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
KVM_ASSIGNED_DEV_GUEST_MSI) {
assigned_device_msi_dispatch(assigned_dev);
enable_irq(assigned_dev->host_irq);
+ assigned_dev->host_irq_disabled = false;
}
mutex_unlock(&assigned_dev->kvm->lock);
- kvm_put_kvm(assigned_dev->kvm);
}
static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
struct kvm_assigned_dev_kernel *assigned_dev =
(struct kvm_assigned_dev_kernel *) dev_id;
- kvm_get_kvm(assigned_dev->kvm);
schedule_work(&assigned_dev->interrupt_work);
+
disable_irq_nosync(irq);
+ assigned_dev->host_irq_disabled = true;
+
return IRQ_HANDLED;
}
dev = container_of(kian, struct kvm_assigned_dev_kernel,
ack_notifier);
+
kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
- enable_irq(dev->host_irq);
+
+ /* The guest irq may be shared so this ack may be
+ * from another device.
+ */
+ if (dev->host_irq_disabled) {
+ enable_irq(dev->host_irq);
+ dev->host_irq_disabled = false;
+ }
}
-static void kvm_free_assigned_device(struct kvm *kvm,
- struct kvm_assigned_dev_kernel
- *assigned_dev)
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void kvm_free_assigned_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
{
- if (irqchip_in_kernel(kvm) && assigned_dev->irq_requested_type)
- free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+ if (!irqchip_in_kernel(kvm))
+ return;
+
+ kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
+
+ if (assigned_dev->irq_source_id != -1)
+ kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
+ assigned_dev->irq_source_id = -1;
+
+ if (!assigned_dev->irq_requested_type)
+ return;
+
+ /*
+ * In kvm_free_device_irq, cancel_work_sync return true if:
+ * 1. work is scheduled, and then cancelled.
+ * 2. work callback is executed.
+ *
+ * The first one ensured that the irq is disabled and no more events
+ * would happen. But for the second one, the irq may be enabled (e.g.
+ * for MSI). So we disable irq here to prevent further events.
+ *
+ * Notice this maybe result in nested disable if the interrupt type is
+ * INTx, but it's OK for we are going to free it.
+ *
+ * If this function is a part of VM destroy, please ensure that till
+ * now, the kvm state is still legal for probably we also have to wait
+ * interrupt_work done.
+ */
+ disable_irq_nosync(assigned_dev->host_irq);
+ cancel_work_sync(&assigned_dev->interrupt_work);
+
+ free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+
if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
pci_disable_msi(assigned_dev->dev);
- kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
- kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
+ assigned_dev->irq_requested_type = 0;
+}
- if (cancel_work_sync(&assigned_dev->interrupt_work))
- /* We had pending work. That means we will have to take
- * care of kvm_put_kvm.
- */
- kvm_put_kvm(kvm);
+
+static void kvm_free_assigned_device(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel
+ *assigned_dev)
+{
+ kvm_free_assigned_irq(kvm, assigned_dev);
pci_reset_function(assigned_dev->dev);
if (irqchip_in_kernel(kvm)) {
if (!msi2intx &&
- adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) {
- free_irq(adev->host_irq, (void *)kvm);
+ (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) {
+ free_irq(adev->host_irq, (void *)adev);
pci_disable_msi(adev->dev);
}
struct kvm_assigned_dev_kernel *match;
struct pci_dev *dev;
+ down_read(&kvm->slots_lock);
mutex_lock(&kvm->lock);
match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
match->assigned_dev_id = assigned_dev->assigned_dev_id;
match->host_busnr = assigned_dev->busnr;
match->host_devfn = assigned_dev->devfn;
+ match->flags = assigned_dev->flags;
match->dev = dev;
-
+ match->irq_source_id = -1;
match->kvm = kvm;
list_add(&match->list, &kvm->arch.assigned_dev_head);
if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
- r = kvm_iommu_map_guest(kvm, match);
+ if (!kvm->arch.iommu_domain) {
+ r = kvm_iommu_map_guest(kvm);
+ if (r)
+ goto out_list_del;
+ }
+ r = kvm_assign_device(kvm, match);
if (r)
goto out_list_del;
}
out:
mutex_unlock(&kvm->lock);
+ up_read(&kvm->slots_lock);
return r;
out_list_del:
list_del(&match->list);
out_free:
kfree(match);
mutex_unlock(&kvm->lock);
+ up_read(&kvm->slots_lock);
+ return r;
+}
+#endif
+
+#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
+static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
+ struct kvm_assigned_pci_dev *assigned_dev)
+{
+ int r = 0;
+ struct kvm_assigned_dev_kernel *match;
+
+ mutex_lock(&kvm->lock);
+
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_dev->assigned_dev_id);
+ if (!match) {
+ printk(KERN_INFO "%s: device hasn't been assigned before, "
+ "so cannot be deassigned\n", __func__);
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
+ kvm_deassign_device(kvm, match);
+
+ kvm_free_assigned_device(kvm, match);
+
+out:
+ mutex_unlock(&kvm->lock);
return r;
}
#endif
{
}
-void kvm_flush_remote_tlbs(struct kvm *kvm)
+static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
int i, cpu, me;
- cpumask_t cpus;
+ cpumask_var_t cpus;
+ bool called = true;
struct kvm_vcpu *vcpu;
+ if (alloc_cpumask_var(&cpus, GFP_ATOMIC))
+ cpumask_clear(cpus);
+
me = get_cpu();
- cpus_clear(cpus);
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
vcpu = kvm->vcpus[i];
if (!vcpu)
continue;
- if (test_and_set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+ if (test_and_set_bit(req, &vcpu->requests))
continue;
cpu = vcpu->cpu;
- if (cpu != -1 && cpu != me)
- cpu_set(cpu, cpus);
+ if (cpus != NULL && cpu != -1 && cpu != me)
+ cpumask_set_cpu(cpu, cpus);
}
- if (cpus_empty(cpus))
- goto out;
- ++kvm->stat.remote_tlb_flush;
- smp_call_function_mask(cpus, ack_flush, NULL, 1);
-out:
+ if (unlikely(cpus == NULL))
+ smp_call_function_many(cpu_online_mask, ack_flush, NULL, 1);
+ else if (!cpumask_empty(cpus))
+ smp_call_function_many(cpus, ack_flush, NULL, 1);
+ else
+ called = false;
put_cpu();
+ free_cpumask_var(cpus);
+ return called;
}
-void kvm_reload_remote_mmus(struct kvm *kvm)
+void kvm_flush_remote_tlbs(struct kvm *kvm)
{
- int i, cpu, me;
- cpumask_t cpus;
- struct kvm_vcpu *vcpu;
-
- me = get_cpu();
- cpus_clear(cpus);
- for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- vcpu = kvm->vcpus[i];
- if (!vcpu)
- continue;
- if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
- continue;
- cpu = vcpu->cpu;
- if (cpu != -1 && cpu != me)
- cpu_set(cpu, cpus);
- }
- if (cpus_empty(cpus))
- goto out;
- smp_call_function_mask(cpus, ack_flush, NULL, 1);
-out:
- put_cpu();
+ if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
+ ++kvm->stat.remote_tlb_flush;
}
+void kvm_reload_remote_mmus(struct kvm *kvm)
+{
+ make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
+}
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
{
return young;
}
+static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
+ struct mm_struct *mm)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ kvm_arch_flush_shadow(kvm);
+}
+
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
.invalidate_page = kvm_mmu_notifier_invalidate_page,
.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
+ .release = kvm_mmu_notifier_release,
};
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
{
struct mm_struct *mm = kvm->mm;
+ kvm_arch_sync_events(kvm);
spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
goto out_free;
}
- kvm_free_physmem_slot(&old, &new);
+ kvm_free_physmem_slot(&old, npages ? &new : NULL);
+ /* Slot deletion case: we have to update the current slot */
+ if (!npages)
+ *memslot = old;
#ifdef CONFIG_DMAR
/* map the pages in iommu page table */
r = kvm_iommu_map_pages(kvm, base_gfn, npages);
return 0;
}
-static const struct file_operations kvm_vcpu_fops = {
+static struct file_operations kvm_vcpu_fops = {
.release = kvm_vcpu_release,
.unlocked_ioctl = kvm_vcpu_ioctl,
.compat_ioctl = kvm_vcpu_ioctl,
break;
}
#endif
+#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
+ case KVM_DEASSIGN_PCI_DEVICE: {
+ struct kvm_assigned_pci_dev assigned_dev;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+ goto out;
+ r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
+ if (r)
+ goto out;
+ break;
+ }
+#endif
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
return 0;
}
-static const struct file_operations kvm_vm_fops = {
+static struct file_operations kvm_vm_fops = {
.release = kvm_vm_release,
.unlocked_ioctl = kvm_vm_ioctl,
.compat_ioctl = kvm_vm_ioctl,
return fd;
}
+static long kvm_dev_ioctl_check_extension_generic(long arg)
+{
+ switch (arg) {
+ case KVM_CAP_USER_MEMORY:
+ case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+ return 1;
+ default:
+ break;
+ }
+ return kvm_dev_ioctl_check_extension(arg);
+}
+
static long kvm_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = kvm_dev_ioctl_create_vm();
break;
case KVM_CHECK_EXTENSION:
- r = kvm_dev_ioctl_check_extension(arg);
+ r = kvm_dev_ioctl_check_extension_generic(arg);
break;
case KVM_GET_VCPU_MMAP_SIZE:
r = -EINVAL;
{
int cpu = raw_smp_processor_id();
- if (cpu_isset(cpu, cpus_hardware_enabled))
+ if (cpumask_test_cpu(cpu, cpus_hardware_enabled))
return;
- cpu_set(cpu, cpus_hardware_enabled);
+ cpumask_set_cpu(cpu, cpus_hardware_enabled);
kvm_arch_hardware_enable(NULL);
}
{
int cpu = raw_smp_processor_id();
- if (!cpu_isset(cpu, cpus_hardware_enabled))
+ if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
return;
- cpu_clear(cpu, cpus_hardware_enabled);
+ cpumask_clear_cpu(cpu, cpus_hardware_enabled);
kvm_arch_hardware_disable(NULL);
}
bad_pfn = page_to_pfn(bad_page);
+ if (!alloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
+ r = -ENOMEM;
+ goto out_free_0;
+ }
+
r = kvm_arch_hardware_setup();
if (r < 0)
- goto out_free_0;
+ goto out_free_0a;
for_each_online_cpu(cpu) {
smp_call_function_single(cpu,
}
kvm_chardev_ops.owner = module;
+ kvm_vm_fops.owner = module;
+ kvm_vcpu_fops.owner = module;
r = misc_register(&kvm_dev);
if (r) {
on_each_cpu(hardware_disable, NULL, 1);
out_free_1:
kvm_arch_hardware_unsetup();
+out_free_0a:
+ free_cpumask_var(cpus_hardware_enabled);
out_free_0:
__free_page(bad_page);
out:
kvm_arch_hardware_unsetup();
kvm_arch_exit();
kvm_exit_debug();
+ free_cpumask_var(cpus_hardware_enabled);
__free_page(bad_page);
}
EXPORT_SYMBOL_GPL(kvm_exit);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff