vhost: new device IOTLB API

This patch tries to implement an device IOTLB for vhost. This could be
used with userspace(qemu) implementation of DMA remapping
to emulate an IOMMU for the guest.

The idea is simple, cache the translation in a software device IOTLB
(which is implemented as an interval tree) in vhost and use vhost_net
file descriptor for reporting IOTLB miss and IOTLB
update/invalidation. When vhost meets an IOTLB miss, the fault
address, size and access can be read from the file. After userspace
finishes the translation, it writes the translated address to the
vhost_net file to update the device IOTLB.

When device IOTLB is enabled by setting VIRTIO_F_IOMMU_PLATFORM all vq
addresses set by ioctl are treated as iova instead of virtual address and
the accessing can only be done through IOTLB instead of direct userspace
memory access. Before each round or vq processing, all vq metadata is
prefetched in device IOTLB to make sure no translation fault happens
during vq processing.

In most cases, virtqueues are contiguous even in virtual address space.
The IOTLB translation for virtqueue itself may make it a little
slower. We might add fast path cache on top of this patch.

Signed-off-by: Jason Wang <jasowang@redhat.com>
[mst: use virtio feature bit: VHOST_F_DEVICE_IOTLB -> VIRTIO_F_IOMMU_PLATFORM ]
[mst: fix build warnings ]
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
[ weiyj.lk: missing unlock on error ]
Signed-off-by: Wei Yongjun <weiyj.lk@gmail.com>

1 files changed, 53 insertions, 6 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index a6b270aff9ef..0965f869dc57 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -61,7 +61,8 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
 enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
-			 (1ULL << VIRTIO_NET_F_MRG_RXBUF)
+			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
 };
 
 enum {
@@ -308,7 +309,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 {
 	unsigned long uninitialized_var(endtime);
 	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
-				    out_num, in_num, NULL, NULL);
+				  out_num, in_num, NULL, NULL);
 
 	if (r == vq->num && vq->busyloop_timeout) {
 		preempt_disable();
@@ -318,7 +319,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 			cpu_relax_lowlatency();
 		preempt_enable();
 		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
-					out_num, in_num, NULL, NULL);
+				      out_num, in_num, NULL, NULL);
 	}
 
 	return r;
@@ -351,6 +352,9 @@ static void handle_tx(struct vhost_net *net)
 	if (!sock)
 		goto out;
 
+	if (!vq_iotlb_prefetch(vq))
+		goto out;
+
 	vhost_disable_notify(&net->dev, vq);
 
 	hdr_size = nvq->vhost_hlen;
@@ -612,6 +616,10 @@ static void handle_rx(struct vhost_net *net)
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
+
+	if (!vq_iotlb_prefetch(vq))
+		goto out;
+
 	vhost_disable_notify(&net->dev, vq);
 
 	vhost_hlen = nvq->vhost_hlen;
@@ -1080,10 +1088,14 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	}
 	mutex_lock(&n->dev.mutex);
 	if ((features & (1 << VHOST_F_LOG_ALL)) &&
-	    !vhost_log_access_ok(&n->dev)) {
-		mutex_unlock(&n->dev.mutex);
-		return -EFAULT;
+	    !vhost_log_access_ok(&n->dev))
+		goto out_unlock;
+
+	if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) {
+		if (vhost_init_device_iotlb(&n->dev, true))
+			goto out_unlock;
 	}
+
 	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
 		mutex_lock(&n->vqs[i].vq.mutex);
 		n->vqs[i].vq.acked_features = features;
@@ -1093,6 +1105,10 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	}
 	mutex_unlock(&n->dev.mutex);
 	return 0;
+
+out_unlock:
+	mutex_unlock(&n->dev.mutex);
+	return -EFAULT;
 }
 
 static long vhost_net_set_owner(struct vhost_net *n)
@@ -1166,9 +1182,40 @@ static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
 }
 #endif
 
+static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_net *n = file->private_data;
+	struct vhost_dev *dev = &n->dev;
+	int noblock = file->f_flags & O_NONBLOCK;
+
+	return vhost_chr_read_iter(dev, to, noblock);
+}
+
+static ssize_t vhost_net_chr_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_net *n = file->private_data;
+	struct vhost_dev *dev = &n->dev;
+
+	return vhost_chr_write_iter(dev, from);
+}
+
+static unsigned int vhost_net_chr_poll(struct file *file, poll_table *wait)
+{
+	struct vhost_net *n = file->private_data;
+	struct vhost_dev *dev = &n->dev;
+
+	return vhost_chr_poll(file, dev, wait);
+}
+
 static const struct file_operations vhost_net_fops = {
 	.owner          = THIS_MODULE,
 	.release        = vhost_net_release,
+	.read_iter      = vhost_net_chr_read_iter,
+	.write_iter     = vhost_net_chr_write_iter,
+	.poll           = vhost_net_chr_poll,
 	.unlocked_ioctl = vhost_net_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = vhost_net_compat_ioctl,