vhost: replace vhost_workqueue with per-vhost kthread

Replace vhost_workqueue with per-vhost kthread.  Other than callback
argument change from struct work_struct * to struct vhost_work *,
there's no visible change to vhost_poll_*() interface.

This conversion is to make each vhost use a dedicated kthread so that
resource control via cgroup can be applied.

Partially based on Sridhar Samudrala's patch.

* Updated to use sub structure vhost_work instead of directly using
  vhost_poll at Michael's suggestion.

* Added flusher wake_up() optimization at Michael's suggestion.

Changes by MST:
* Converted atomics/barrier use to a spinlock.
* Create thread on SET_OWNER
* Fix flushing

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Sridhar Samudrala <samudrala.sridhar@gmail.com>

1 files changed, 25 insertions, 13 deletions

diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 11ee13dba0f..3693327549b 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -5,13 +5,13 @@
 #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>
+#include <asm/atomic.h>
 
 struct vhost_device;
 
@@ -20,19 +20,31 @@ enum {
 	VHOST_NET_MAX_SG = MAX_SKB_FRAGS + 2,
 };
 
+struct vhost_work;
+typedef void (*vhost_work_fn_t)(struct vhost_work *work);
+
+struct vhost_work {
+	struct list_head	  node;
+	vhost_work_fn_t		  fn;
+	wait_queue_head_t	  done;
+	int			  flushing;
+	unsigned		  queue_seq;
+	unsigned		  done_seq;
+};
+
 /* 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;
+	struct vhost_work	  work;
 	unsigned long		  mask;
+	struct vhost_dev	 *dev;
 };
 
-void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
-		     unsigned long mask);
+void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
+		     unsigned long mask, struct vhost_dev *dev);
 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);
@@ -63,7 +75,7 @@ struct vhost_virtqueue {
 	struct vhost_poll poll;
 
 	/* The routine to call when the Guest pings us, or timeout. */
-	work_func_t handle_kick;
+	vhost_work_fn_t handle_kick;
 
 	/* Last available index we saw. */
 	u16 last_avail_idx;
@@ -86,11 +98,11 @@ struct vhost_virtqueue {
 	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
+	 * All readers access it from worker, which makes it possible to
+	 * flush the vhost_work 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().
+	 * vhost_work execution acts instead of rcu_read_lock() and the end of
+	 * vhost_work execution acts instead of rcu_read_lock().
 	 * Writers use virtqueue mutex. */
 	void *private_data;
 	/* Log write descriptors */
@@ -110,6 +122,9 @@ struct vhost_dev {
 	int nvqs;
 	struct file *log_file;
 	struct eventfd_ctx *log_ctx;
+	spinlock_t work_lock;
+	struct list_head work_list;
+	struct task_struct *worker;
 };
 
 long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
@@ -136,9 +151,6 @@ 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)                               \