KVM: Introduce a 'release' method for KVM devices

When a P9 sPAPR VM boots, the CAS negotiation process determines which
interrupt mode to use (XICS legacy or XIVE native) and invokes a
machine reset to activate the chosen mode.

To be able to switch from one interrupt mode to another, we introduce
the capability to release a KVM device without destroying the VM. The
KVM device interface is extended with a new 'release' method which is
called when the file descriptor of the device is closed.

Once 'release' is called, the 'destroy' method will not be called
anymore as the device is removed from the device list of the VM.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 831d963451d8c55811506c4ab784b17a56b13fe6..722692e2f7454d6f261cc9b4eef0ac033bbadf79 100644 (file)
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1240,6 +1240,15 @@ struct kvm_device_ops {
         */
        void (*destroy)(struct kvm_device *dev);
 
+       /*
+        * Release is an alternative method to free the device. It is
+        * called when the device file descriptor is closed. Once
+        * release is called, the destroy method will not be called
+        * anymore as the device is removed from the device list of
+        * the VM. kvm->lock is held.
+        */
+       void (*release)(struct kvm_device *dev);
+
        int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
        int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);
        int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr);

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ea2018ae1cd729bfa302758a135099481711d1cf..ea2619d5ca984f1a7ab6f7733387b923fcc320e1 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2938,6 +2938,19 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
        struct kvm_device *dev = filp->private_data;
        struct kvm *kvm = dev->kvm;
 
+       if (!dev)
+               return -ENODEV;
+
+       if (dev->kvm != kvm)
+               return -EPERM;
+
+       if (dev->ops->release) {
+               mutex_lock(&kvm->lock);
+               list_del(&dev->vm_node);
+               dev->ops->release(dev);
+               mutex_unlock(&kvm->lock);
+       }
+
        kvm_put_kvm(kvm);
        return 0;
 }