vhost_net: a kernel-level virtio server

What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.

There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
  migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)

common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear.  I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.

What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.

How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device.  Backend is also configured by userspace, including vlan/mac
etc.

Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.

Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use

Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item.  The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.

(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)

Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 161 insertions, 0 deletions

diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
new file mode 100644
index 000000000000..44591ba9b07a
--- /dev/null
+++ b/drivers/vhost/vhost.h
@@ -0,0 +1,161 @@
+#ifndef _VHOST_H
+#define _VHOST_H
+
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/skbuff.h>
+#include <linux/uio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_device;
+
+enum {
+	/* Enough place for all fragments, head, and virtio net header. */
+	VHOST_NET_MAX_SG = MAX_SKB_FRAGS + 2,
+};
+
+/* Poll a file (eventfd or socket) */
+/* Note: there's nothing vhost specific about this structure. */
+struct vhost_poll {
+	poll_table                table;
+	wait_queue_head_t        *wqh;
+	wait_queue_t              wait;
+	/* struct which will handle all actual work. */
+	struct work_struct        work;
+	unsigned long		  mask;
+};
+
+void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
+		     unsigned long mask);
+void vhost_poll_start(struct vhost_poll *poll, struct file *file);
+void vhost_poll_stop(struct vhost_poll *poll);
+void vhost_poll_flush(struct vhost_poll *poll);
+void vhost_poll_queue(struct vhost_poll *poll);
+
+struct vhost_log {
+	u64 addr;
+	u64 len;
+};
+
+/* The virtqueue structure describes a queue attached to a device. */
+struct vhost_virtqueue {
+	struct vhost_dev *dev;
+
+	/* The actual ring of buffers. */
+	struct mutex mutex;
+	unsigned int num;
+	struct vring_desc __user *desc;
+	struct vring_avail __user *avail;
+	struct vring_used __user *used;
+	struct file *kick;
+	struct file *call;
+	struct file *error;
+	struct eventfd_ctx *call_ctx;
+	struct eventfd_ctx *error_ctx;
+	struct eventfd_ctx *log_ctx;
+
+	struct vhost_poll poll;
+
+	/* The routine to call when the Guest pings us, or timeout. */
+	work_func_t handle_kick;
+
+	/* Last available index we saw. */
+	u16 last_avail_idx;
+
+	/* Caches available index value from user. */
+	u16 avail_idx;
+
+	/* Last index we used. */
+	u16 last_used_idx;
+
+	/* Used flags */
+	u16 used_flags;
+
+	/* Log writes to used structure. */
+	bool log_used;
+	u64 log_addr;
+
+	struct iovec indirect[VHOST_NET_MAX_SG];
+	struct iovec iov[VHOST_NET_MAX_SG];
+	struct iovec hdr[VHOST_NET_MAX_SG];
+	size_t hdr_size;
+	/* We use a kind of RCU to access private pointer.
+	 * All readers access it from workqueue, which makes it possible to
+	 * flush the workqueue instead of synchronize_rcu. Therefore readers do
+	 * not need to call rcu_read_lock/rcu_read_unlock: the beginning of
+	 * work item execution acts instead of rcu_read_lock() and the end of
+	 * work item execution acts instead of rcu_read_lock().
+	 * Writers use virtqueue mutex. */
+	void *private_data;
+	/* Log write descriptors */
+	void __user *log_base;
+	struct vhost_log log[VHOST_NET_MAX_SG];
+};
+
+struct vhost_dev {
+	/* Readers use RCU to access memory table pointer
+	 * log base pointer and features.
+	 * Writers use mutex below.*/
+	struct vhost_memory *memory;
+	struct mm_struct *mm;
+	struct mutex mutex;
+	unsigned acked_features;
+	struct vhost_virtqueue *vqs;
+	int nvqs;
+	struct file *log_file;
+	struct eventfd_ctx *log_ctx;
+};
+
+long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
+long vhost_dev_check_owner(struct vhost_dev *);
+long vhost_dev_reset_owner(struct vhost_dev *);
+void vhost_dev_cleanup(struct vhost_dev *);
+long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, unsigned long arg);
+int vhost_vq_access_ok(struct vhost_virtqueue *vq);
+int vhost_log_access_ok(struct vhost_dev *);
+
+unsigned vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *,
+			   struct iovec iov[], unsigned int iov_count,
+			   unsigned int *out_num, unsigned int *in_num,
+			   struct vhost_log *log, unsigned int *log_num);
+void vhost_discard_vq_desc(struct vhost_virtqueue *);
+
+int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
+void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
+void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
+			       unsigned int head, int len);
+void vhost_disable_notify(struct vhost_virtqueue *);
+bool vhost_enable_notify(struct vhost_virtqueue *);
+
+int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
+		    unsigned int log_num, u64 len);
+
+int vhost_init(void);
+void vhost_cleanup(void);
+
+#define vq_err(vq, fmt, ...) do {                                  \
+		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
+		if ((vq)->error_ctx)                               \
+				eventfd_signal((vq)->error_ctx, 1);\
+	} while (0)
+
+enum {
+	VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
+			 (1 << VIRTIO_RING_F_INDIRECT_DESC) |
+			 (1 << VHOST_F_LOG_ALL) |
+			 (1 << VHOST_NET_F_VIRTIO_NET_HDR),
+};
+
+static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
+{
+	unsigned acked_features = rcu_dereference(dev->acked_features);
+	return acked_features & (1 << bit);
+}
+
+#endif