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, 31 insertions, 1 deletions

diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index eaaf6df72218..78f3c5fc02e4 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -65,13 +65,15 @@ struct vhost_umem_node {
 	__u64 last;
 	__u64 size;
 	__u64 userspace_addr;
-	__u64 flags_padding;
+	__u32 perm;
+	__u32 flags_padding;
 	__u64 __subtree_last;
 };
 
 struct vhost_umem {
 	struct rb_root umem_tree;
 	struct list_head umem_list;
+	int numem;
 };
 
 /* The virtqueue structure describes a queue attached to a device. */
@@ -119,10 +121,12 @@ struct vhost_virtqueue {
 	u64 log_addr;
 
 	struct iovec iov[UIO_MAXIOV];
+	struct iovec iotlb_iov[64];
 	struct iovec *indirect;
 	struct vring_used_elem *heads;
 	/* Protected by virtqueue mutex. */
 	struct vhost_umem *umem;
+	struct vhost_umem *iotlb;
 	void *private_data;
 	u64 acked_features;
 	/* Log write descriptors */
@@ -139,6 +143,12 @@ struct vhost_virtqueue {
 	u32 busyloop_timeout;
 };
 
+struct vhost_msg_node {
+  struct vhost_msg msg;
+  struct vhost_virtqueue *vq;
+  struct list_head node;
+};
+
 struct vhost_dev {
 	struct mm_struct *mm;
 	struct mutex mutex;
@@ -149,6 +159,11 @@ struct vhost_dev {
 	struct llist_head work_list;
 	struct task_struct *worker;
 	struct vhost_umem *umem;
+	struct vhost_umem *iotlb;
+	spinlock_t iotlb_lock;
+	struct list_head read_list;
+	struct list_head pending_list;
+	wait_queue_head_t wait;
 };
 
 void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
@@ -185,6 +200,21 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		    unsigned int log_num, u64 len);
+int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
+
+struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
+void vhost_enqueue_msg(struct vhost_dev *dev,
+		       struct list_head *head,
+		       struct vhost_msg_node *node);
+struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
+					 struct list_head *head);
+unsigned int vhost_chr_poll(struct file *file, struct vhost_dev *dev,
+			    poll_table *wait);
+ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
+			    int noblock);
+ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
+			     struct iov_iter *from);
+int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
 
 #define vq_err(vq, fmt, ...) do {                                  \
 		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \