#include <linux/pagemap.h>
#include <linux/mman.h>
#include <linux/swap.h>
-#include <linux/intel-iommu.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
#include <asm/processor.h>
#include <asm/io.h>
#include "coalesced_mmio.h"
#endif
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include "irq.h"
+#endif
+
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
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);
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
-bool kvm_rebooting;
+static bool kvm_rebooting;
+
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
+ int assigned_dev_id)
+{
+ struct list_head *ptr;
+ struct kvm_assigned_dev_kernel *match;
+
+ list_for_each(ptr, head) {
+ match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
+ if (match->assigned_dev_id == assigned_dev_id)
+ return match;
+ }
+ return NULL;
+}
+
+static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
+ *assigned_dev, int irq)
+{
+ int i, index;
+ struct msix_entry *host_msix_entries;
+
+ host_msix_entries = assigned_dev->host_msix_entries;
+
+ index = -1;
+ for (i = 0; i < assigned_dev->entries_nr; i++)
+ if (irq == host_msix_entries[i].vector) {
+ index = i;
+ break;
+ }
+ if (index < 0) {
+ printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+ return 0;
+ }
+
+ return index;
+}
+
+static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev;
+ struct kvm *kvm;
+ int irq, i;
+
+ assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
+ interrupt_work);
+ kvm = assigned_dev->kvm;
+
+ /* This is taken to safely inject irq inside the guest. When
+ * the interrupt injection (or the ioapic code) uses a
+ * finer-grained lock, update this
+ */
+ mutex_lock(&kvm->lock);
+ spin_lock_irq(&assigned_dev->assigned_dev_lock);
+ if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+ struct kvm_guest_msix_entry *guest_entries =
+ assigned_dev->guest_msix_entries;
+ for (i = 0; i < assigned_dev->entries_nr; i++) {
+ if (!(guest_entries[i].flags &
+ KVM_ASSIGNED_MSIX_PENDING))
+ continue;
+ guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
+ kvm_set_irq(assigned_dev->kvm,
+ assigned_dev->irq_source_id,
+ guest_entries[i].vector, 1);
+ irq = assigned_dev->host_msix_entries[i].vector;
+ if (irq != 0)
+ enable_irq(irq);
+ assigned_dev->host_irq_disabled = false;
+ }
+ } else {
+ kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+ assigned_dev->guest_irq, 1);
+ if (assigned_dev->irq_requested_type &
+ KVM_DEV_IRQ_GUEST_MSI) {
+ enable_irq(assigned_dev->host_irq);
+ assigned_dev->host_irq_disabled = false;
+ }
+ }
+
+ spin_unlock_irq(&assigned_dev->assigned_dev_lock);
+ mutex_unlock(&assigned_dev->kvm->lock);
+}
+
+static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
+{
+ unsigned long flags;
+ struct kvm_assigned_dev_kernel *assigned_dev =
+ (struct kvm_assigned_dev_kernel *) dev_id;
+
+ spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
+ if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+ int index = find_index_from_host_irq(assigned_dev, irq);
+ if (index < 0)
+ goto out;
+ assigned_dev->guest_msix_entries[index].flags |=
+ KVM_ASSIGNED_MSIX_PENDING;
+ }
+
+ schedule_work(&assigned_dev->interrupt_work);
+
+ disable_irq_nosync(irq);
+ assigned_dev->host_irq_disabled = true;
+
+out:
+ spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
+ return IRQ_HANDLED;
+}
+
+/* Ack the irq line for an assigned device */
+static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
+{
+ struct kvm_assigned_dev_kernel *dev;
+ unsigned long flags;
+
+ if (kian->gsi == -1)
+ return;
+
+ dev = container_of(kian, struct kvm_assigned_dev_kernel,
+ ack_notifier);
+
+ kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0);
+
+ /* The guest irq may be shared so this ack may be
+ * from another device.
+ */
+ spin_lock_irqsave(&dev->assigned_dev_lock, flags);
+ if (dev->host_irq_disabled) {
+ enable_irq(dev->host_irq);
+ dev->host_irq_disabled = false;
+ }
+ spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
+}
+
+static void deassign_guest_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
+{
+ kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
+ assigned_dev->ack_notifier.gsi = -1;
+
+ if (assigned_dev->irq_source_id != -1)
+ kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
+ assigned_dev->irq_source_id = -1;
+ assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
+}
+
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void deassign_host_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
+{
+ /*
+ * 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.
+ */
+ if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+ int i;
+ for (i = 0; i < assigned_dev->entries_nr; i++)
+ disable_irq_nosync(assigned_dev->
+ host_msix_entries[i].vector);
+
+ cancel_work_sync(&assigned_dev->interrupt_work);
+
+ for (i = 0; i < assigned_dev->entries_nr; i++)
+ free_irq(assigned_dev->host_msix_entries[i].vector,
+ (void *)assigned_dev);
+
+ assigned_dev->entries_nr = 0;
+ kfree(assigned_dev->host_msix_entries);
+ kfree(assigned_dev->guest_msix_entries);
+ pci_disable_msix(assigned_dev->dev);
+ } else {
+ /* Deal with MSI and INTx */
+ 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_DEV_IRQ_HOST_MSI)
+ pci_disable_msi(assigned_dev->dev);
+ }
+
+ assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
+}
+
+static int kvm_deassign_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev,
+ unsigned long irq_requested_type)
+{
+ unsigned long guest_irq_type, host_irq_type;
+
+ if (!irqchip_in_kernel(kvm))
+ return -EINVAL;
+ /* no irq assignment to deassign */
+ if (!assigned_dev->irq_requested_type)
+ return -ENXIO;
+
+ host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
+ guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
+
+ if (host_irq_type)
+ deassign_host_irq(kvm, assigned_dev);
+ if (guest_irq_type)
+ deassign_guest_irq(kvm, assigned_dev);
+
+ return 0;
+}
+
+static void kvm_free_assigned_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
+{
+ kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
+}
+
+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);
+
+ pci_release_regions(assigned_dev->dev);
+ pci_disable_device(assigned_dev->dev);
+ pci_dev_put(assigned_dev->dev);
+
+ list_del(&assigned_dev->list);
+ kfree(assigned_dev);
+}
+
+void kvm_free_all_assigned_devices(struct kvm *kvm)
+{
+ struct list_head *ptr, *ptr2;
+ struct kvm_assigned_dev_kernel *assigned_dev;
+
+ list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
+ assigned_dev = list_entry(ptr,
+ struct kvm_assigned_dev_kernel,
+ list);
+
+ kvm_free_assigned_device(kvm, assigned_dev);
+ }
+}
+
+static int assigned_device_enable_host_intx(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev)
+{
+ dev->host_irq = dev->dev->irq;
+ /* Even though this is PCI, we don't want to use shared
+ * interrupts. Sharing host devices with guest-assigned devices
+ * on the same interrupt line is not a happy situation: there
+ * are going to be long delays in accepting, acking, etc.
+ */
+ if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
+ 0, "kvm_assigned_intx_device", (void *)dev))
+ return -EIO;
+ return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_host_msi(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev)
+{
+ int r;
+
+ if (!dev->dev->msi_enabled) {
+ r = pci_enable_msi(dev->dev);
+ if (r)
+ return r;
+ }
+
+ dev->host_irq = dev->dev->irq;
+ if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
+ "kvm_assigned_msi_device", (void *)dev)) {
+ pci_disable_msi(dev->dev);
+ return -EIO;
+ }
+
+ return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_host_msix(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev)
+{
+ int i, r = -EINVAL;
+
+ /* host_msix_entries and guest_msix_entries should have been
+ * initialized */
+ if (dev->entries_nr == 0)
+ return r;
+
+ r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
+ if (r)
+ return r;
+
+ for (i = 0; i < dev->entries_nr; i++) {
+ r = request_irq(dev->host_msix_entries[i].vector,
+ kvm_assigned_dev_intr, 0,
+ "kvm_assigned_msix_device",
+ (void *)dev);
+ /* FIXME: free requested_irq's on failure */
+ if (r)
+ return r;
+ }
+
+ return 0;
+}
+
+#endif
+
+static int assigned_device_enable_guest_intx(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq)
+{
+ dev->guest_irq = irq->guest_irq;
+ dev->ack_notifier.gsi = irq->guest_irq;
+ return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_guest_msi(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq)
+{
+ dev->guest_irq = irq->guest_irq;
+ dev->ack_notifier.gsi = -1;
+ return 0;
+}
+#endif
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_guest_msix(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq)
+{
+ dev->guest_irq = irq->guest_irq;
+ dev->ack_notifier.gsi = -1;
+ return 0;
+}
+#endif
+
+static int assign_host_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ __u32 host_irq_type)
+{
+ int r = -EEXIST;
+
+ if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
+ return r;
+
+ switch (host_irq_type) {
+ case KVM_DEV_IRQ_HOST_INTX:
+ r = assigned_device_enable_host_intx(kvm, dev);
+ break;
+#ifdef __KVM_HAVE_MSI
+ case KVM_DEV_IRQ_HOST_MSI:
+ r = assigned_device_enable_host_msi(kvm, dev);
+ break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+ case KVM_DEV_IRQ_HOST_MSIX:
+ r = assigned_device_enable_host_msix(kvm, dev);
+ break;
+#endif
+ default:
+ r = -EINVAL;
+ }
+
+ if (!r)
+ dev->irq_requested_type |= host_irq_type;
+
+ return r;
+}
+
+static int assign_guest_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq,
+ unsigned long guest_irq_type)
+{
+ int id;
+ int r = -EEXIST;
+
+ if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
+ return r;
+
+ id = kvm_request_irq_source_id(kvm);
+ if (id < 0)
+ return id;
+
+ dev->irq_source_id = id;
+
+ switch (guest_irq_type) {
+ case KVM_DEV_IRQ_GUEST_INTX:
+ r = assigned_device_enable_guest_intx(kvm, dev, irq);
+ break;
+#ifdef __KVM_HAVE_MSI
+ case KVM_DEV_IRQ_GUEST_MSI:
+ r = assigned_device_enable_guest_msi(kvm, dev, irq);
+ break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+ case KVM_DEV_IRQ_GUEST_MSIX:
+ r = assigned_device_enable_guest_msix(kvm, dev, irq);
+ break;
+#endif
+ default:
+ r = -EINVAL;
+ }
+
+ if (!r) {
+ dev->irq_requested_type |= guest_irq_type;
+ kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+ } else
+ kvm_free_irq_source_id(kvm, dev->irq_source_id);
+
+ return r;
+}
+
+/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
+static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
+ struct kvm_assigned_irq *assigned_irq)
+{
+ int r = -EINVAL;
+ struct kvm_assigned_dev_kernel *match;
+ unsigned long host_irq_type, guest_irq_type;
+
+ if (!capable(CAP_SYS_RAWIO))
+ return -EPERM;
+
+ if (!irqchip_in_kernel(kvm))
+ return r;
+
+ mutex_lock(&kvm->lock);
+ r = -ENODEV;
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_irq->assigned_dev_id);
+ if (!match)
+ goto out;
+
+ host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
+ guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
+
+ r = -EINVAL;
+ /* can only assign one type at a time */
+ if (hweight_long(host_irq_type) > 1)
+ goto out;
+ if (hweight_long(guest_irq_type) > 1)
+ goto out;
+ if (host_irq_type == 0 && guest_irq_type == 0)
+ goto out;
+
+ r = 0;
+ if (host_irq_type)
+ r = assign_host_irq(kvm, match, host_irq_type);
+ if (r)
+ goto out;
+
+ if (guest_irq_type)
+ r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
+ struct kvm_assigned_irq
+ *assigned_irq)
+{
+ int r = -ENODEV;
+ struct kvm_assigned_dev_kernel *match;
+
+ mutex_lock(&kvm->lock);
+
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_irq->assigned_dev_id);
+ if (!match)
+ goto out;
+
+ r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
+ struct kvm_assigned_pci_dev *assigned_dev)
+{
+ int r = 0;
+ 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,
+ assigned_dev->assigned_dev_id);
+ if (match) {
+ /* device already assigned */
+ r = -EEXIST;
+ goto out;
+ }
+
+ match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
+ if (match == NULL) {
+ printk(KERN_INFO "%s: Couldn't allocate memory\n",
+ __func__);
+ r = -ENOMEM;
+ goto out;
+ }
+ dev = pci_get_bus_and_slot(assigned_dev->busnr,
+ assigned_dev->devfn);
+ if (!dev) {
+ printk(KERN_INFO "%s: host device not found\n", __func__);
+ r = -EINVAL;
+ goto out_free;
+ }
+ if (pci_enable_device(dev)) {
+ printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
+ r = -EBUSY;
+ goto out_put;
+ }
+ r = pci_request_regions(dev, "kvm_assigned_device");
+ if (r) {
+ printk(KERN_INFO "%s: Could not get access to device regions\n",
+ __func__);
+ goto out_disable;
+ }
+
+ pci_reset_function(dev);
+
+ 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;
+ spin_lock_init(&match->assigned_dev_lock);
+ match->irq_source_id = -1;
+ match->kvm = kvm;
+ match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+ INIT_WORK(&match->interrupt_work,
+ kvm_assigned_dev_interrupt_work_handler);
+
+ list_add(&match->list, &kvm->arch.assigned_dev_head);
+
+ if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
+ 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);
+ pci_release_regions(dev);
+out_disable:
+ pci_disable_device(dev);
+out_put:
+ pci_dev_put(dev);
+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 (match->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
static inline int valid_vcpu(int n)
{
return likely(n >= 0 && n < KVM_MAX_VCPUS);
}
-inline int is_mmio_pfn(pfn_t pfn)
+inline int kvm_is_mmio_pfn(pfn_t pfn)
{
- if (pfn_valid(pfn))
- return PageReserved(pfn_to_page(pfn));
+ if (pfn_valid(pfn)) {
+ struct page *page = compound_head(pfn_to_page(pfn));
+ return PageReserved(page);
+ }
return true;
}
{
}
-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 */
if (IS_ERR(kvm))
goto out;
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+ INIT_LIST_HEAD(&kvm->irq_routing);
+ INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+#endif
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
{
struct mm_struct *mm = kvm->mm;
+ kvm_arch_sync_events(kvm);
spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
+ kvm_free_irq_routing(kvm);
kvm_io_bus_destroy(&kvm->pio_bus);
kvm_io_bus_destroy(&kvm->mmio_bus);
#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
#endif
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
+#else
+ kvm_arch_flush_shadow(kvm);
#endif
kvm_arch_destroy_vm(kvm);
mmdrop(mm);
{
int r;
gfn_t base_gfn;
- unsigned long npages;
+ unsigned long npages, ugfn;
+ int largepages;
unsigned long i;
struct kvm_memory_slot *memslot;
struct kvm_memory_slot old, new;
goto out;
if (mem->guest_phys_addr & (PAGE_SIZE - 1))
goto out;
+ if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1)))
+ goto out;
if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
goto out;
if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
struct kvm_memory_slot *s = &kvm->memslots[i];
- if (s == memslot)
+ if (s == memslot || !s->npages)
continue;
if (!((base_gfn + npages <= s->base_gfn) ||
(base_gfn >= s->base_gfn + s->npages)))
new.userspace_addr = 0;
}
if (npages && !new.lpage_info) {
- int largepages = npages / KVM_PAGES_PER_HPAGE;
- if (npages % KVM_PAGES_PER_HPAGE)
- largepages++;
- if (base_gfn % KVM_PAGES_PER_HPAGE)
- largepages++;
+ largepages = 1 + (base_gfn + npages - 1) / KVM_PAGES_PER_HPAGE;
+ largepages -= base_gfn / KVM_PAGES_PER_HPAGE;
new.lpage_info = vmalloc(largepages * sizeof(*new.lpage_info));
new.lpage_info[0].write_count = 1;
if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
new.lpage_info[largepages-1].write_count = 1;
+ ugfn = new.userspace_addr >> PAGE_SHIFT;
+ /*
+ * If the gfn and userspace address are not aligned wrt each
+ * other, disable large page support for this slot
+ */
+ if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1))
+ for (i = 0; i < largepages; ++i)
+ new.lpage_info[i].write_count = 1;
}
/* Allocate page dirty bitmap if needed */
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 */
+ spin_lock(&kvm->mmu_lock);
+ if (!npages)
+ *memslot = old;
+ spin_unlock(&kvm->mmu_lock);
+#ifdef CONFIG_DMAR
/* map the pages in iommu page table */
r = kvm_iommu_map_pages(kvm, base_gfn, npages);
if (r)
goto out;
-
+#endif
return 0;
out_free:
}
EXPORT_SYMBOL_GPL(kvm_is_error_hva);
-static struct kvm_memory_slot *__gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
{
int i;
}
return NULL;
}
+EXPORT_SYMBOL_GPL(gfn_to_memslot_unaliased);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
gfn = unalias_gfn(kvm, gfn);
- return __gfn_to_memslot(kvm, gfn);
+ return gfn_to_memslot_unaliased(kvm, gfn);
}
int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
struct kvm_memory_slot *slot;
gfn = unalias_gfn(kvm, gfn);
- slot = __gfn_to_memslot(kvm, gfn);
+ slot = gfn_to_memslot_unaliased(kvm, gfn);
if (!slot)
return bad_hva();
return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
up_read(¤t->mm->mmap_sem);
- BUG_ON(!is_mmio_pfn(pfn));
+ BUG_ON(!kvm_is_mmio_pfn(pfn));
} else
pfn = page_to_pfn(page[0]);
pfn_t pfn;
pfn = gfn_to_pfn(kvm, gfn);
- if (!is_mmio_pfn(pfn))
+ if (!kvm_is_mmio_pfn(pfn))
return pfn_to_page(pfn);
- WARN_ON(is_mmio_pfn(pfn));
+ WARN_ON(kvm_is_mmio_pfn(pfn));
get_page(bad_page);
return bad_page;
void kvm_release_pfn_clean(pfn_t pfn)
{
- if (!is_mmio_pfn(pfn))
+ if (!kvm_is_mmio_pfn(pfn))
put_page(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
void kvm_set_pfn_dirty(pfn_t pfn)
{
- if (!is_mmio_pfn(pfn)) {
+ if (!kvm_is_mmio_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
if (!PageReserved(page))
SetPageDirty(page);
void kvm_set_pfn_accessed(pfn_t pfn)
{
- if (!is_mmio_pfn(pfn))
+ if (!kvm_is_mmio_pfn(pfn))
mark_page_accessed(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
void kvm_get_pfn(pfn_t pfn)
{
- if (!is_mmio_pfn(pfn))
+ if (!kvm_is_mmio_pfn(pfn))
get_page(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_get_pfn);
struct kvm_memory_slot *memslot;
gfn = unalias_gfn(kvm, gfn);
- memslot = __gfn_to_memslot(kvm, gfn);
+ memslot = gfn_to_memslot_unaliased(kvm, gfn);
if (memslot && memslot->dirty_bitmap) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
for (;;) {
prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
- if (kvm_cpu_has_interrupt(vcpu) ||
- kvm_cpu_has_pending_timer(vcpu) ||
- kvm_arch_vcpu_runnable(vcpu)) {
+ if ((kvm_arch_interrupt_allowed(vcpu) &&
+ kvm_cpu_has_interrupt(vcpu)) ||
+ kvm_arch_vcpu_runnable(vcpu)) {
set_bit(KVM_REQ_UNHALT, &vcpu->requests);
break;
}
+ if (kvm_cpu_has_pending_timer(vcpu))
+ break;
if (signal_pending(current))
break;
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,
return 0;
}
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+ struct kvm_assigned_msix_nr *entry_nr)
+{
+ int r = 0;
+ struct kvm_assigned_dev_kernel *adev;
+
+ mutex_lock(&kvm->lock);
+
+ adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ entry_nr->assigned_dev_id);
+ if (!adev) {
+ r = -EINVAL;
+ goto msix_nr_out;
+ }
+
+ if (adev->entries_nr == 0) {
+ adev->entries_nr = entry_nr->entry_nr;
+ if (adev->entries_nr == 0 ||
+ adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
+ r = -EINVAL;
+ goto msix_nr_out;
+ }
+
+ adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+ entry_nr->entry_nr,
+ GFP_KERNEL);
+ if (!adev->host_msix_entries) {
+ r = -ENOMEM;
+ goto msix_nr_out;
+ }
+ adev->guest_msix_entries = kzalloc(
+ sizeof(struct kvm_guest_msix_entry) *
+ entry_nr->entry_nr, GFP_KERNEL);
+ if (!adev->guest_msix_entries) {
+ kfree(adev->host_msix_entries);
+ r = -ENOMEM;
+ goto msix_nr_out;
+ }
+ } else /* Not allowed set MSI-X number twice */
+ r = -EINVAL;
+msix_nr_out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+ struct kvm_assigned_msix_entry *entry)
+{
+ int r = 0, i;
+ struct kvm_assigned_dev_kernel *adev;
+
+ mutex_lock(&kvm->lock);
+
+ adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ entry->assigned_dev_id);
+
+ if (!adev) {
+ r = -EINVAL;
+ goto msix_entry_out;
+ }
+
+ for (i = 0; i < adev->entries_nr; i++)
+ if (adev->guest_msix_entries[i].vector == 0 ||
+ adev->guest_msix_entries[i].entry == entry->entry) {
+ adev->guest_msix_entries[i].entry = entry->entry;
+ adev->guest_msix_entries[i].vector = entry->gsi;
+ adev->host_msix_entries[i].entry = entry->entry;
+ break;
+ }
+ if (i == adev->entries_nr) {
+ r = -ENOSPC;
+ goto msix_entry_out;
+ }
+
+msix_entry_out:
+ mutex_unlock(&kvm->lock);
+
+ return r;
+}
+#endif
+
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = 0;
break;
}
- case KVM_DEBUG_GUEST: {
- struct kvm_debug_guest dbg;
+ case KVM_SET_GUEST_DEBUG: {
+ struct kvm_guest_debug dbg;
r = -EFAULT;
if (copy_from_user(&dbg, argp, sizeof dbg))
goto out;
- r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg);
+ r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
if (r)
goto out;
r = 0;
break;
}
#endif
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+ case KVM_ASSIGN_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_assign_device(kvm, &assigned_dev);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_ASSIGN_IRQ: {
+ r = -EOPNOTSUPP;
+ break;
+ }
+#ifdef KVM_CAP_ASSIGN_DEV_IRQ
+ case KVM_ASSIGN_DEV_IRQ: {
+ struct kvm_assigned_irq assigned_irq;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+ goto out;
+ r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_DEASSIGN_DEV_IRQ: {
+ struct kvm_assigned_irq assigned_irq;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+ goto out;
+ r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
+ if (r)
+ goto out;
+ break;
+ }
+#endif
+#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
+#ifdef KVM_CAP_IRQ_ROUTING
+ case KVM_SET_GSI_ROUTING: {
+ struct kvm_irq_routing routing;
+ struct kvm_irq_routing __user *urouting;
+ struct kvm_irq_routing_entry *entries;
+
+ r = -EFAULT;
+ if (copy_from_user(&routing, argp, sizeof(routing)))
+ goto out;
+ r = -EINVAL;
+ if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+ goto out;
+ if (routing.flags)
+ goto out;
+ r = -ENOMEM;
+ entries = vmalloc(routing.nr * sizeof(*entries));
+ if (!entries)
+ goto out;
+ r = -EFAULT;
+ urouting = argp;
+ if (copy_from_user(entries, urouting->entries,
+ routing.nr * sizeof(*entries)))
+ goto out_free_irq_routing;
+ r = kvm_set_irq_routing(kvm, entries, routing.nr,
+ routing.flags);
+ out_free_irq_routing:
+ vfree(entries);
+ break;
+ }
+#ifdef __KVM_HAVE_MSIX
+ case KVM_ASSIGN_SET_MSIX_NR: {
+ struct kvm_assigned_msix_nr entry_nr;
+ r = -EFAULT;
+ if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+ goto out;
+ r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_ASSIGN_SET_MSIX_ENTRY: {
+ struct kvm_assigned_msix_entry entry;
+ r = -EFAULT;
+ if (copy_from_user(&entry, argp, sizeof entry))
+ goto out;
+ r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+ if (r)
+ goto out;
+ break;
+ }
+#endif
+#endif /* KVM_CAP_IRQ_ROUTING */
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:
+ case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
+ return 1;
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+ case KVM_CAP_IRQ_ROUTING:
+ return KVM_MAX_IRQ_ROUTES;
+#endif
+ 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);
}
static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
void *v)
{
- if (val == SYS_RESTART) {
- /*
- * Some (well, at least mine) BIOSes hang on reboot if
- * in vmx root mode.
- */
- printk(KERN_INFO "kvm: exiting hardware virtualization\n");
- kvm_rebooting = true;
- on_each_cpu(hardware_disable, NULL, 1);
- }
+ /*
+ * Some (well, at least mine) BIOSes hang on reboot if
+ * in vmx root mode.
+ *
+ * And Intel TXT required VMX off for all cpu when system shutdown.
+ */
+ printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+ kvm_rebooting = true;
+ on_each_cpu(hardware_disable, NULL, 1);
return NOTIFY_OK;
}
bad_pfn = page_to_pfn(bad_page);
+ if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
+ r = -ENOMEM;
+ goto out_free_0;
+ }
+ cpumask_clear(cpus_hardware_enabled);
+
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