virtio: disable notification hardening by default

We try to harden virtio device notifications in 8b4ec69d ("virtio:
harden vring IRQ"). It works with the assumption that the driver or
core can properly call virtio_device_ready() at the right
place. Unfortunately, this seems to be not true and uncover various
bugs of the existing drivers, mainly the issue of using
virtio_device_ready() incorrectly.

So let's add a Kconfig option and disable it by default. It gives
us time to fix the drivers and then we can consider re-enabling it.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220622012940.21441-1-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>

drivers/s390/virtio/virtio_ccw.c

@@ -1136,8 +1136,13 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
 			vcdev->err = -EIO;
 	}
 	virtio_ccw_check_activity(vcdev, activity);
-	/* Interrupts are disabled here */
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	/*
+	 * Paired with virtio_ccw_synchronize_cbs() and interrupts are
+	 * disabled here.
+	 */
 	read_lock(&vcdev->irq_lock);
+#endif
 	for_each_set_bit(i, indicators(vcdev),
 			 sizeof(*indicators(vcdev)) * BITS_PER_BYTE) {
 		/* The bit clear must happen before the vring kick. */
@@ -1146,7 +1151,9 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
 		vq = virtio_ccw_vq_by_ind(vcdev, i);
 		vring_interrupt(0, vq);
 	}
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
 	read_unlock(&vcdev->irq_lock);
+#endif
 	if (test_bit(0, indicators2(vcdev))) {
 		virtio_config_changed(&vcdev->vdev);
 		clear_bit(0, indicators2(vcdev));

drivers/virtio/Kconfig

@@ -29,6 +29,19 @@ menuconfig VIRTIO_MENU
 
 if VIRTIO_MENU
 
+config VIRTIO_HARDEN_NOTIFICATION
+        bool "Harden virtio notification"
+        help
+          Enable this to harden the device notifications and suppress
+          those that happen at a time where notifications are illegal.
+
+          Experimental: Note that several drivers still have bugs that
+          may cause crashes or hangs when correct handling of
+          notifications is enforced; depending on the subset of
+          drivers and devices you use, this may or may not work.
+
+          If unsure, say N.
+
 config VIRTIO_PCI
 	tristate "PCI driver for virtio devices"
 	depends on PCI

drivers/virtio/virtio.c

@@ -219,6 +219,7 @@ static int virtio_features_ok(struct virtio_device *dev)
  * */
 void virtio_reset_device(struct virtio_device *dev)
 {
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
 	/*
 	 * The below virtio_synchronize_cbs() guarantees that any
 	 * interrupt for this line arriving after
@@ -227,6 +228,7 @@ void virtio_reset_device(struct virtio_device *dev)
 	 */
 	virtio_break_device(dev);
 	virtio_synchronize_cbs(dev);
+#endif
 
 	dev->config->reset(dev);
 }

drivers/virtio/virtio_ring.c

@@ -1708,7 +1708,11 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	vq->we_own_ring = true;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
 	vq->broken = true;
+#else
+	vq->broken = false;
+#endif
 	vq->last_used_idx = 0 | (1 << VRING_PACKED_EVENT_F_WRAP_CTR);
 	vq->event_triggered = false;
 	vq->num_added = 0;
@@ -2154,9 +2158,13 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 	}
 
 	if (unlikely(vq->broken)) {
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
 		dev_warn_once(&vq->vq.vdev->dev,
 			      "virtio vring IRQ raised before DRIVER_OK");
 		return IRQ_NONE;
+#else
+		return IRQ_HANDLED;
+#endif
 	}
 
 	/* Just a hint for performance: so it's ok that this can be racy! */
@@ -2199,7 +2207,11 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->we_own_ring = false;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
 	vq->broken = true;
+#else
+	vq->broken = false;
+#endif
 	vq->last_used_idx = 0;
 	vq->event_triggered = false;
 	vq->num_added = 0;

include/linux/virtio_config.h

@@ -257,6 +257,7 @@ void virtio_device_ready(struct virtio_device *dev)
 
 	WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
 
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
 	/*
 	 * The virtio_synchronize_cbs() makes sure vring_interrupt()
 	 * will see the driver specific setup if it sees vq->broken
@@ -264,6 +265,7 @@ void virtio_device_ready(struct virtio_device *dev)
 	 */
 	virtio_synchronize_cbs(dev);
 	__virtio_unbreak_device(dev);
+#endif
 	/*
 	 * The transport should ensure the visibility of vq->broken
 	 * before setting DRIVER_OK. See the comments for the transport