Merge branch 'vhost-net-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

drivers/vhost/vhost.c

@@ -17,12 +17,13 @@
 #include <linux/mm.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
 #include <linux/rcupdate.h>
 #include <linux/poll.h>
 #include <linux/file.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/cgroup.h>
 
 #include <linux/net.h>
 #include <linux/if_packet.h>
@@ -37,8 +38,6 @@ enum {
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
-static struct workqueue_struct *vhost_workqueue;
-
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -52,23 +51,31 @@ static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
 			     void *key)
 {
-	struct vhost_poll *poll;
-	poll = container_of(wait, struct vhost_poll, wait);
+	struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);
+
 	if (!((unsigned long)key & poll->mask))
 		return 0;
 
-	queue_work(vhost_workqueue, &poll->work);
+	vhost_poll_queue(poll);
 	return 0;
 }
 
 /* Init poll structure */
-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)
 {
-	INIT_WORK(&poll->work, func);
+	struct vhost_work *work = &poll->work;
+
 	init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
 	init_poll_funcptr(&poll->table, vhost_poll_func);
 	poll->mask = mask;
+	poll->dev = dev;
+
+	INIT_LIST_HEAD(&work->node);
+	work->fn = fn;
+	init_waitqueue_head(&work->done);
+	work->flushing = 0;
+	work->queue_seq = work->done_seq = 0;
 }
 
 /* Start polling a file. We add ourselves to file's wait queue. The caller must
@@ -92,12 +99,40 @@ void vhost_poll_stop(struct vhost_poll *poll)
  * locks that are also used by the callback. */
 void vhost_poll_flush(struct vhost_poll *poll)
 {
-	flush_work(&poll->work);
+	struct vhost_work *work = &poll->work;
+	unsigned seq;
+	int left;
+	int flushing;
+
+	spin_lock_irq(&poll->dev->work_lock);
+	seq = work->queue_seq;
+	work->flushing++;
+	spin_unlock_irq(&poll->dev->work_lock);
+	wait_event(work->done, ({
+		   spin_lock_irq(&poll->dev->work_lock);
+		   left = seq - work->done_seq <= 0;
+		   spin_unlock_irq(&poll->dev->work_lock);
+		   left;
+	}));
+	spin_lock_irq(&poll->dev->work_lock);
+	flushing = --work->flushing;
+	spin_unlock_irq(&poll->dev->work_lock);
+	BUG_ON(flushing < 0);
 }
 
 void vhost_poll_queue(struct vhost_poll *poll)
 {
-	queue_work(vhost_workqueue, &poll->work);
+	struct vhost_dev *dev = poll->dev;
+	struct vhost_work *work = &poll->work;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->work_lock, flags);
+	if (list_empty(&work->node)) {
+		list_add_tail(&work->node, &dev->work_list);
+		work->queue_seq++;
+		wake_up_process(dev->worker);
+	}
+	spin_unlock_irqrestore(&dev->work_lock, flags);
 }
 
 static void vhost_vq_reset(struct vhost_dev *dev,
@@ -114,7 +149,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->used_flags = 0;
 	vq->log_used = false;
 	vq->log_addr = -1ull;
-	vq->hdr_size = 0;
+	vq->vhost_hlen = 0;
+	vq->sock_hlen = 0;
 	vq->private_data = NULL;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
@@ -125,10 +161,51 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_ctx = NULL;
 }
 
+static int vhost_worker(void *data)
+{
+	struct vhost_dev *dev = data;
+	struct vhost_work *work = NULL;
+	unsigned uninitialized_var(seq);
+
+	for (;;) {
+		/* mb paired w/ kthread_stop */
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		spin_lock_irq(&dev->work_lock);
+		if (work) {
+			work->done_seq = seq;
+			if (work->flushing)
+				wake_up_all(&work->done);
+		}
+
+		if (kthread_should_stop()) {
+			spin_unlock_irq(&dev->work_lock);
+			__set_current_state(TASK_RUNNING);
+			return 0;
+		}
+		if (!list_empty(&dev->work_list)) {
+			work = list_first_entry(&dev->work_list,
+						struct vhost_work, node);
+			list_del_init(&work->node);
+			seq = work->queue_seq;
+		} else
+			work = NULL;
+		spin_unlock_irq(&dev->work_lock);
+
+		if (work) {
+			__set_current_state(TASK_RUNNING);
+			work->fn(work);
+		} else
+			schedule();
+
+	}
+}
+
 long vhost_dev_init(struct vhost_dev *dev,
 		    struct vhost_virtqueue *vqs, int nvqs)
 {
 	int i;
+
 	dev->vqs = vqs;
 	dev->nvqs = nvqs;
 	mutex_init(&dev->mutex);
@@ -136,6 +213,9 @@ long vhost_dev_init(struct vhost_dev *dev,
 	dev->log_file = NULL;
 	dev->memory = NULL;
 	dev->mm = NULL;
+	spin_lock_init(&dev->work_lock);
+	INIT_LIST_HEAD(&dev->work_list);
+	dev->worker = NULL;
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		dev->vqs[i].dev = dev;
@@ -143,9 +223,9 @@ long vhost_dev_init(struct vhost_dev *dev,
 		vhost_vq_reset(dev, dev->vqs + i);
 		if (dev->vqs[i].handle_kick)
 			vhost_poll_init(&dev->vqs[i].poll,
-					dev->vqs[i].handle_kick,
-					POLLIN);
+					dev->vqs[i].handle_kick, POLLIN, dev);
 	}
+
 	return 0;
 }
 
@@ -159,12 +239,36 @@ long vhost_dev_check_owner(struct vhost_dev *dev)
 /* Caller should have device mutex */
 static long vhost_dev_set_owner(struct vhost_dev *dev)
 {
+	struct task_struct *worker;
+	int err;
 	/* Is there an owner already? */
-	if (dev->mm)
-		return -EBUSY;
+	if (dev->mm) {
+		err = -EBUSY;
+		goto err_mm;
+	}
 	/* No owner, become one */
 	dev->mm = get_task_mm(current);
+	worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
+	if (IS_ERR(worker)) {
+		err = PTR_ERR(worker);
+		goto err_worker;
+	}
+
+	dev->worker = worker;
+	err = cgroup_attach_task_current_cg(worker);
+	if (err)
+		goto err_cgroup;
+	wake_up_process(worker);	/* avoid contributing to loadavg */
+
 	return 0;
+err_cgroup:
+	kthread_stop(worker);
+err_worker:
+	if (dev->mm)
+		mmput(dev->mm);
+	dev->mm = NULL;
+err_mm:
+	return err;
 }
 
 /* Caller should have device mutex */
@@ -217,6 +321,9 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 	if (dev->mm)
 		mmput(dev->mm);
 	dev->mm = NULL;
+
+	WARN_ON(!list_empty(&dev->work_list));
+	kthread_stop(dev->worker);
 }
 
 static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
@@ -995,9 +1102,9 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 }
 
 /* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
-void vhost_discard_vq_desc(struct vhost_virtqueue *vq)
+void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
 {
-	vq->last_avail_idx--;
+	vq->last_avail_idx -= n;
 }
 
 /* After we've used one of their buffers, we tell them about it.  We'll then
@@ -1042,6 +1149,67 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
 	return 0;
 }
 
+static int __vhost_add_used_n(struct vhost_virtqueue *vq,
+			    struct vring_used_elem *heads,
+			    unsigned count)
+{
+	struct vring_used_elem __user *used;
+	int start;
+
+	start = vq->last_used_idx % vq->num;
+	used = vq->used->ring + start;
+	if (copy_to_user(used, heads, count * sizeof *used)) {
+		vq_err(vq, "Failed to write used");
+		return -EFAULT;
+	}
+	if (unlikely(vq->log_used)) {
+		/* Make sure data is seen before log. */
+		smp_wmb();
+		/* Log used ring entry write. */
+		log_write(vq->log_base,
+			  vq->log_addr +
+			   ((void __user *)used - (void __user *)vq->used),
+			  count * sizeof *used);
+	}
+	vq->last_used_idx += count;
+	return 0;
+}
+
+/* After we've used one of their buffers, we tell them about it.  We'll then
+ * want to notify the guest, using eventfd. */
+int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
+		     unsigned count)
+{
+	int start, n, r;
+
+	start = vq->last_used_idx % vq->num;
+	n = vq->num - start;
+	if (n < count) {
+		r = __vhost_add_used_n(vq, heads, n);
+		if (r < 0)
+			return r;
+		heads += n;
+		count -= n;
+	}
+	r = __vhost_add_used_n(vq, heads, count);
+
+	/* Make sure buffer is written before we update index. */
+	smp_wmb();
+	if (put_user(vq->last_used_idx, &vq->used->idx)) {
+		vq_err(vq, "Failed to increment used idx");
+		return -EFAULT;
+	}
+	if (unlikely(vq->log_used)) {
+		/* Log used index update. */
+		log_write(vq->log_base,
+			  vq->log_addr + offsetof(struct vring_used, idx),
+			  sizeof vq->used->idx);
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
+	}
+	return r;
+}
+
 /* This actually signals the guest, using eventfd. */
 void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
@@ -1076,6 +1244,15 @@ void vhost_add_used_and_signal(struct vhost_dev *dev,
 	vhost_signal(dev, vq);
 }
 
+/* multi-buffer version of vhost_add_used_and_signal */
+void vhost_add_used_and_signal_n(struct vhost_dev *dev,
+				 struct vhost_virtqueue *vq,
+				 struct vring_used_elem *heads, unsigned count)
+{
+	vhost_add_used_n(vq, heads, count);
+	vhost_signal(dev, vq);
+}
+
 /* OK, now we need to know about added descriptors. */
 bool vhost_enable_notify(struct vhost_virtqueue *vq)
 {
@@ -1100,7 +1277,7 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 		return false;
 	}
 
-	return avail_idx != vq->last_avail_idx;
+	return avail_idx != vq->avail_idx;
 }
 
 /* We don't need to be notified again. */
@@ -1115,16 +1292,3 @@ void vhost_disable_notify(struct vhost_virtqueue *vq)
 		vq_err(vq, "Failed to enable notification at %p: %d\n",
 		       &vq->used->flags, r);
 }
-
-int vhost_init(void)
-{
-	vhost_workqueue = create_singlethread_workqueue("vhost");
-	if (!vhost_workqueue)
-		return -ENOMEM;
-	return 0;
-}
-
-void vhost_cleanup(void)
-{
-	destroy_workqueue(vhost_workqueue);
-}

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;
@@ -84,13 +96,15 @@ struct vhost_virtqueue {
 	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;
+	size_t vhost_hlen;
+	size_t sock_hlen;
+	struct vring_used_elem heads[VHOST_NET_MAX_SG];
 	/* 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 +124,9 @@ 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);
@@ -124,21 +141,22 @@ int 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 *);
+void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
 
 int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
-void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
+int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
+		     unsigned count);
 void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
-			       unsigned int head, int len);
+			       unsigned int id, int len);
+void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
+			       struct vring_used_elem *heads, unsigned count);
+void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
 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)                               \
@@ -149,7 +167,8 @@ 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),
+			 (1 << VHOST_NET_F_VIRTIO_NET_HDR) |
+			 (1 << VIRTIO_NET_F_MRG_RXBUF),
 };
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)

include/linux/cgroup.h

@@ -570,6 +570,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task(struct cgroup *, struct task_struct *);
+int cgroup_attach_task_current_cg(struct task_struct *);
 
 /*
  * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
@@ -626,6 +627,12 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 	return -EINVAL;
 }
 
+/* No cgroups - nothing to do */
+static inline int cgroup_attach_task_current_cg(struct task_struct *t)
+{
+	return 0;
+}
+
 #endif /* !CONFIG_CGROUPS */
 
 #endif /* _LINUX_CGROUP_H */

kernel/cgroup.c

@@ -1788,6 +1788,29 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	return retval;
 }
 
+/**
+ * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup
+ * @tsk: the task to be attached
+ */
+int cgroup_attach_task_current_cg(struct task_struct *tsk)
+{
+	struct cgroupfs_root *root;
+	struct cgroup *cur_cg;
+	int retval = 0;
+
+	cgroup_lock();
+	for_each_active_root(root) {
+		cur_cg = task_cgroup_from_root(current, root);
+		retval = cgroup_attach_task(cur_cg, tsk);
+		if (retval)
+			break;
+	}
+	cgroup_unlock();
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg);
+
 /*
  * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
  * held. May take task_lock of task