Merge tag 'vfio-for-linus' of git://github.com/awilliam/linux-vfio
Pull vfio fixes from Alex Williamson:
"VFIO doc update and virqfd race fix"
* tag 'vfio-for-linus' of git://github.com/awilliam/linux-vfio:
vfio: Fix virqfd release race
vfio: Trivial Documentation correction
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index 0cb6685..8eda363 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -133,7 +133,7 @@
$ lspci -n -s 0000:06:0d.0
06:0d.0 0401: 1102:0002 (rev 08)
# echo 0000:06:0d.0 > /sys/bus/pci/devices/0000:06:0d.0/driver/unbind
-# echo 1102 0002 > /sys/bus/pci/drivers/vfio/new_id
+# echo 1102 0002 > /sys/bus/pci/drivers/vfio-pci/new_id
Now we need to look at what other devices are in the group to free
it for use by VFIO:
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 211a492..d8dedc7 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -76,9 +76,24 @@
schedule_work(&virqfd->inject);
}
- if (flags & POLLHUP)
- /* The eventfd is closing, detach from VFIO */
- virqfd_deactivate(virqfd);
+ if (flags & POLLHUP) {
+ unsigned long flags;
+ spin_lock_irqsave(&virqfd->vdev->irqlock, flags);
+
+ /*
+ * The eventfd is closing, if the virqfd has not yet been
+ * queued for release, as determined by testing whether the
+ * vdev pointer to it is still valid, queue it now. As
+ * with kvm irqfds, we know we won't race against the virqfd
+ * going away because we hold wqh->lock to get here.
+ */
+ if (*(virqfd->pvirqfd) == virqfd) {
+ *(virqfd->pvirqfd) = NULL;
+ virqfd_deactivate(virqfd);
+ }
+
+ spin_unlock_irqrestore(&virqfd->vdev->irqlock, flags);
+ }
return 0;
}
@@ -93,7 +108,6 @@
static void virqfd_shutdown(struct work_struct *work)
{
struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
- struct virqfd **pvirqfd = virqfd->pvirqfd;
u64 cnt;
eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
@@ -101,7 +115,6 @@
eventfd_ctx_put(virqfd->eventfd);
kfree(virqfd);
- *pvirqfd = NULL;
}
static void virqfd_inject(struct work_struct *work)
@@ -122,15 +135,11 @@
int ret = 0;
unsigned int events;
- if (*pvirqfd)
- return -EBUSY;
-
virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
if (!virqfd)
return -ENOMEM;
virqfd->pvirqfd = pvirqfd;
- *pvirqfd = virqfd;
virqfd->vdev = vdev;
virqfd->handler = handler;
virqfd->thread = thread;
@@ -154,6 +163,23 @@
virqfd->eventfd = ctx;
/*
+ * virqfds can be released by closing the eventfd or directly
+ * through ioctl. These are both done through a workqueue, so
+ * we update the pointer to the virqfd under lock to avoid
+ * pushing multiple jobs to release the same virqfd.
+ */
+ spin_lock_irq(&vdev->irqlock);
+
+ if (*pvirqfd) {
+ spin_unlock_irq(&vdev->irqlock);
+ ret = -EBUSY;
+ goto fail;
+ }
+ *pvirqfd = virqfd;
+
+ spin_unlock_irq(&vdev->irqlock);
+
+ /*
* Install our own custom wake-up handling so we are notified via
* a callback whenever someone signals the underlying eventfd.
*/
@@ -187,19 +213,29 @@
fput(file);
kfree(virqfd);
- *pvirqfd = NULL;
return ret;
}
-static void virqfd_disable(struct virqfd *virqfd)
+static void virqfd_disable(struct vfio_pci_device *vdev,
+ struct virqfd **pvirqfd)
{
- if (!virqfd)
- return;
+ unsigned long flags;
- virqfd_deactivate(virqfd);
+ spin_lock_irqsave(&vdev->irqlock, flags);
- /* Block until we know all outstanding shutdown jobs have completed. */
+ if (*pvirqfd) {
+ virqfd_deactivate(*pvirqfd);
+ *pvirqfd = NULL;
+ }
+
+ spin_unlock_irqrestore(&vdev->irqlock, flags);
+
+ /*
+ * Block until we know all outstanding shutdown jobs have completed.
+ * Even if we don't queue the job, flush the wq to be sure it's
+ * been released.
+ */
flush_workqueue(vfio_irqfd_cleanup_wq);
}
@@ -392,8 +428,8 @@
static void vfio_intx_disable(struct vfio_pci_device *vdev)
{
vfio_intx_set_signal(vdev, -1);
- virqfd_disable(vdev->ctx[0].unmask);
- virqfd_disable(vdev->ctx[0].mask);
+ virqfd_disable(vdev, &vdev->ctx[0].unmask);
+ virqfd_disable(vdev, &vdev->ctx[0].mask);
vdev->irq_type = VFIO_PCI_NUM_IRQS;
vdev->num_ctx = 0;
kfree(vdev->ctx);
@@ -539,8 +575,8 @@
vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
for (i = 0; i < vdev->num_ctx; i++) {
- virqfd_disable(vdev->ctx[i].unmask);
- virqfd_disable(vdev->ctx[i].mask);
+ virqfd_disable(vdev, &vdev->ctx[i].unmask);
+ virqfd_disable(vdev, &vdev->ctx[i].mask);
}
if (msix) {
@@ -577,7 +613,7 @@
vfio_send_intx_eventfd, NULL,
&vdev->ctx[0].unmask, fd);
- virqfd_disable(vdev->ctx[0].unmask);
+ virqfd_disable(vdev, &vdev->ctx[0].unmask);
}
return 0;