virtio_pci: support VIRTIO_F_RING_RESET

This patch implements virtio pci support for QUEUE RESET.

Performing reset on a queue is divided into these steps:

 1. notify the device to reset the queue
 2. recycle the buffer submitted
 3. reset the vring (may re-alloc)
 4. mmap vring to device, and enable the queue

This patch implements virtio_reset_vq(), virtio_enable_resetq() in the
pci scenario.

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220801063902.129329-33-xuanzhuo@linux.alibaba.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

2 files changed, 97 insertions, 3 deletions

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index ca51fcc9daabb..ad258a9d3b9f4 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -214,9 +214,15 @@ static void vp_del_vq(struct virtqueue *vq)
 	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
 	unsigned long flags;
 
-	spin_lock_irqsave(&vp_dev->lock, flags);
-	list_del(&info->node);
-	spin_unlock_irqrestore(&vp_dev->lock, flags);
+	/*
+	 * If it fails during re-enable reset vq. This way we won't rejoin
+	 * info->node to the queue. Prevent unexpected irqs.
+	 */
+	if (!vq->reset) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		list_del(&info->node);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	}
 
 	vp_dev->del_vq(info);
 	kfree(info);
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 9041d9a41b7d2..c3b9f27618497 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -34,6 +34,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 	if ((features & BIT_ULL(VIRTIO_F_SR_IOV)) &&
 			pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV))
 		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);
+
+	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
+		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
 }
 
 /* virtio config->finalize_features() implementation */
@@ -199,6 +202,87 @@ static int vp_active_vq(struct virtqueue *vq, u16 msix_vec)
 	return 0;
 }
 
+static int vp_modern_disable_vq_and_reset(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_vq_info *info;
+	unsigned long flags;
+
+	if (!virtio_has_feature(vq->vdev, VIRTIO_F_RING_RESET))
+		return -ENOENT;
+
+	vp_modern_set_queue_reset(mdev, vq->index);
+
+	info = vp_dev->vqs[vq->index];
+
+	/* delete vq from irq handler */
+	spin_lock_irqsave(&vp_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+	INIT_LIST_HEAD(&info->node);
+
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	__virtqueue_break(vq);
+#endif
+
+	/* For the case where vq has an exclusive irq, call synchronize_irq() to
+	 * wait for completion.
+	 *
+	 * note: We can't use disable_irq() since it conflicts with the affinity
+	 * managed IRQ that is used by some drivers.
+	 */
+	if (vp_dev->per_vq_vectors && info->msix_vector != VIRTIO_MSI_NO_VECTOR)
+		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, info->msix_vector));
+
+	vq->reset = true;
+
+	return 0;
+}
+
+static int vp_modern_enable_vq_after_reset(struct virtqueue *vq)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
+	struct virtio_pci_vq_info *info;
+	unsigned long flags, index;
+	int err;
+
+	if (!vq->reset)
+		return -EBUSY;
+
+	index = vq->index;
+	info = vp_dev->vqs[index];
+
+	if (vp_modern_get_queue_reset(mdev, index))
+		return -EBUSY;
+
+	if (vp_modern_get_queue_enable(mdev, index))
+		return -EBUSY;
+
+	err = vp_active_vq(vq, info->msix_vector);
+	if (err)
+		return err;
+
+	if (vq->callback) {
+		spin_lock_irqsave(&vp_dev->lock, flags);
+		list_add(&info->node, &vp_dev->virtqueues);
+		spin_unlock_irqrestore(&vp_dev->lock, flags);
+	} else {
+		INIT_LIST_HEAD(&info->node);
+	}
+
+#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
+	__virtqueue_unbreak(vq);
+#endif
+
+	vp_modern_set_queue_enable(&vp_dev->mdev, index, true);
+	vq->reset = false;
+
+	return 0;
+}
+
 static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
 {
 	return vp_modern_config_vector(&vp_dev->mdev, vector);
@@ -413,6 +497,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
 	.get_shm_region  = vp_get_shm_region,
+	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
+	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -431,6 +517,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
 	.get_shm_region  = vp_get_shm_region,
+	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
+	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
 };
 
 /* the PCI probing function */