diff mbox series

[1/2] KVM: introduce a 'release' method for KVM devices

Message ID 20190411135302.27509-2-clg@kaod.org
State Superseded
Headers show
Series KVM: PPC: Book3S HV: add XIVE native exploitation mode (v5 errata) | expand

Commit Message

Cédric Le Goater April 11, 2019, 1:53 p.m. UTC
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>
---
 include/linux/kvm_host.h |  9 +++++++++
 virt/kvm/kvm_main.c      | 13 +++++++++++++
 2 files changed, 22 insertions(+)

Comments

David Gibson April 12, 2019, 6:32 a.m. UTC | #1
On Thu, Apr 11, 2019 at 03:53:01PM +0200, Cédric Le Goater wrote:
> 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>

Kind of a hack, but a better way to solve this that doesn't involve
inordinate amounts of work doesn't occur to me.

> ---
>  include/linux/kvm_host.h |  9 +++++++++
>  virt/kvm/kvm_main.c      | 13 +++++++++++++
>  2 files changed, 22 insertions(+)
> 
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 831d963451d8..722692e2f745 100644
> --- 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 ea2018ae1cd7..ea2619d5ca98 100644
> --- 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;
>  }
diff mbox series

Patch

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 831d963451d8..722692e2f745 100644
--- 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 ea2018ae1cd7..ea2619d5ca98 100644
--- 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;
 }