Merge branch 'kvm-updates/2.6.30' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.30' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (113 commits)
  KVM: VMX: Don't allow uninhibited access to EFER on i386
  KVM: Correct deassign device ioctl to IOW
  KVM: ppc: e500: Fix the bug that KVM is unstable in SMP
  KVM: ppc: e500: Fix the bug that mas0 update to wrong value when read TLB entry
  KVM: Fix missing smp tlb flush in invlpg
  KVM: Get support IRQ routing entry counts
  KVM: fix sparse warnings: Should it be static?
  KVM: fix sparse warnings: context imbalance
  KVM: is_long_mode() should check for EFER.LMA
  KVM: VMX: Update necessary state when guest enters long mode
  KVM: ia64: Fix the build errors due to lack of macros related to MSI.
  ia64: Move the macro definitions related to MSI to one header file.
  KVM: fix kvm_vm_ioctl_deassign_device
  KVM: define KVM_CAP_DEVICE_DEASSIGNMENT
  KVM: ppc: Add emulation of E500 register mmucsr0
  KVM: Report IRQ injection status for MSI delivered interrupts
  KVM: MMU: Fix another largepage memory leak
  KVM: SVM: set accessed bit for VMCB segment selectors
  KVM: Report IRQ injection status to userspace.
  KVM: MMU: remove assertion in kvm_mmu_alloc_page
  ...

1 files changed, 68 insertions, 73 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29a667ce35b0..605697e9c4dd 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -47,10 +47,6 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
-#ifdef CONFIG_X86
-#include <asm/msidef.h>
-#endif
-
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 #include "coalesced_mmio.h"
 #endif
@@ -85,57 +81,6 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 static bool kvm_rebooting;
 
 #ifdef KVM_CAP_DEVICE_ASSIGNMENT
-
-#ifdef CONFIG_X86
-static void assigned_device_msi_dispatch(struct kvm_assigned_dev_kernel *dev)
-{
-        int vcpu_id;
-        struct kvm_vcpu *vcpu;
-        struct kvm_ioapic *ioapic = ioapic_irqchip(dev->kvm);
-        int dest_id = (dev->guest_msi.address_lo & MSI_ADDR_DEST_ID_MASK)
-                        >> MSI_ADDR_DEST_ID_SHIFT;
-        int vector = (dev->guest_msi.data & MSI_DATA_VECTOR_MASK)
-                        >> MSI_DATA_VECTOR_SHIFT;
-        int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT,
-                                (unsigned long *)&dev->guest_msi.address_lo);
-        int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT,
-                                (unsigned long *)&dev->guest_msi.data);
-        int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT,
-                                (unsigned long *)&dev->guest_msi.data);
-        u32 deliver_bitmask;
-
-        BUG_ON(!ioapic);
-
-        deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic,
-                                dest_id, dest_mode);
-        /* IOAPIC delivery mode value is the same as MSI here */
-        switch (delivery_mode) {
-        case IOAPIC_LOWEST_PRIORITY:
-                vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
-                                deliver_bitmask);
-                if (vcpu != NULL)
-                        kvm_apic_set_irq(vcpu, vector, trig_mode);
-                else
-                        printk(KERN_INFO "kvm: null lowest priority vcpu!\n");
-                break;
-        case IOAPIC_FIXED:
-                for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
-                        if (!(deliver_bitmask & (1 << vcpu_id)))
-                                continue;
-                        deliver_bitmask &= ~(1 << vcpu_id);
-                        vcpu = ioapic->kvm->vcpus[vcpu_id];
-                        if (vcpu)
-                                kvm_apic_set_irq(vcpu, vector, trig_mode);
-                }
-                break;
-        default:
-                printk(KERN_INFO "kvm: unsupported MSI delivery mode\n");
-        }
-}
-#else
-static void assigned_device_msi_dispatch(struct kvm_assigned_dev_kernel *dev) {}
-#endif
-
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
                                                       int assigned_dev_id)
 {
@@ -162,13 +107,10 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
          * finer-grained lock, update this
          */
         mutex_lock(&assigned_dev->kvm->lock);
-        if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_INTX)
-                kvm_set_irq(assigned_dev->kvm,
-                            assigned_dev->irq_source_id,
-                            assigned_dev->guest_irq, 1);
-        else if (assigned_dev->irq_requested_type &
-                                KVM_ASSIGNED_DEV_GUEST_MSI) {
-                assigned_device_msi_dispatch(assigned_dev);
+        kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+                    assigned_dev->guest_irq, 1);
+
+        if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) {
                 enable_irq(assigned_dev->host_irq);
                 assigned_dev->host_irq_disabled = false;
         }
@@ -331,18 +273,24 @@ static int assigned_device_update_msi(struct kvm *kvm,
 {
         int r;
 
+        adev->guest_irq = airq->guest_irq;
         if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) {
                 /* x86 don't care upper address of guest msi message addr */
                 adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI;
                 adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX;
-                adev->guest_msi.address_lo = airq->guest_msi.addr_lo;
-                adev->guest_msi.data = airq->guest_msi.data;
                 adev->ack_notifier.gsi = -1;
         } else if (msi2intx) {
                 adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX;
                 adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI;
-                adev->guest_irq = airq->guest_irq;
                 adev->ack_notifier.gsi = airq->guest_irq;
+        } else {
+                /*
+                 * Guest require to disable device MSI, we disable MSI and
+                 * re-enable INTx by default again. Notice it's only for
+                 * non-msi2intx.
+                 */
+                assigned_device_update_intx(kvm, adev, airq);
+                return 0;
         }
 
         if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
@@ -379,6 +327,7 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
 {
         int r = 0;
         struct kvm_assigned_dev_kernel *match;
+        u32 current_flags = 0, changed_flags;
 
         mutex_lock(&kvm->lock);
 
@@ -416,8 +365,13 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
                 }
         }
 
-        if ((!msi2intx &&
-             (assigned_irq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI)) ||
+        if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) &&
+                 (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI))
+                current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI;
+
+        changed_flags = assigned_irq->flags ^ current_flags;
+
+        if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) ||
             (msi2intx && match->dev->msi_enabled)) {
 #ifdef CONFIG_X86
                 r = assigned_device_update_msi(kvm, match, assigned_irq);
@@ -563,7 +517,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
                 goto out;
         }
 
-        if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
+        if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
                 kvm_deassign_device(kvm, match);
 
         kvm_free_assigned_device(kvm, match);
@@ -581,8 +535,10 @@ static inline int valid_vcpu(int n)
 
 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;
 }
@@ -828,6 +784,10 @@ static struct kvm *kvm_create_vm(void)
 
         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);
@@ -909,6 +869,7 @@ static void kvm_destroy_vm(struct kvm *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
@@ -1755,13 +1716,13 @@ out_free2:
                 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;
@@ -1929,6 +1890,36 @@ static long kvm_vm_ioctl(struct file *filp,
                 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;
+        }
+#endif
         default:
                 r = kvm_arch_vm_ioctl(filp, ioctl, arg);
         }
@@ -1995,6 +1986,10 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
         case KVM_CAP_USER_MEMORY:
         case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
                 return 1;
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+        case KVM_CAP_IRQ_ROUTING:
+                return KVM_MAX_IRQ_ROUTES;
+#endif
         default:
                 break;
         }