path: root/drivers/vhost/vhost.c

/* Copyright (C) 2009 Red Hat, Inc.
 * Copyright (C) 2006 Rusty Russell IBM Corporation
 *
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *
 * Inspiration, some code, and most witty comments come from
 * Documentation/virtual/lguest/lguest.c, by Rusty Russell
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 *
 * Generic code for virtio server in host kernel.
 */

#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/uio.h>
#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
#include <linux/mutex.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/module.h>

#include "vhost.h"

enum {
	VHOST_MEMORY_MAX_NREGIONS = 64,
	VHOST_MEMORY_F_LOG = 0x1,
};

#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])

static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
			    poll_table *pt)
{
	struct vhost_poll *poll;

	poll = container_of(pt, struct vhost_poll, table);
	poll->wqh = wqh;
	add_wait_queue(wqh, &poll->wait);
}

static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
			     void *key)
{
	struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);

	if (!((unsigned long)key & poll->mask))
		return 0;

	vhost_poll_queue(poll);
	return 0;
}

void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn)
{
	INIT_LIST_HEAD(&work->node);
	work->fn = fn;
	init_waitqueue_head(&work->done);
	work->flushing = 0;
	work->queue_seq = work->done_seq = 0;
}
EXPORT_SYMBOL_GPL(vhost_work_init);

/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
		     unsigned long mask, struct vhost_dev *dev)
{
	init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
	init_poll_funcptr(&poll->table, vhost_poll_func);
	poll->mask = mask;
	poll->dev = dev;
	poll->wqh = NULL;

	vhost_work_init(&poll->work, fn);
}
EXPORT_SYMBOL_GPL(vhost_poll_init);

/* Start polling a file. We add ourselves to file's wait queue. The caller must
 * keep a reference to a file until after vhost_poll_stop is called. */
int vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
	unsigned long mask;
	int ret = 0;

	if (poll->wqh)
		return 0;

	mask = file->f_op->poll(file, &poll->table);
	if (mask)
		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
	if (mask & POLLERR) {
		if (poll->wqh)
			remove_wait_queue(poll->wqh, &poll->wait);
		ret = -EINVAL;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(vhost_poll_start);

/* Stop polling a file. After this function returns, it becomes safe to drop the
 * file reference. You must also flush afterwards. */
void vhost_poll_stop(struct vhost_poll *poll)
{
	if (poll->wqh) {
		remove_wait_queue(poll->wqh, &poll->wait);
		poll->wqh = NULL;
	}
}
EXPORT_SYMBOL_GPL(vhost_poll_stop);

static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work,
				unsigned seq)
{
	int left;

	spin_lock_irq(&dev->work_lock);
	left = seq - work->done_seq;
	spin_unlock_irq(&dev->work_lock);
	return left <= 0;
}

void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work)
{
	unsigned seq;
	int flushing;

	spin_lock_irq(&dev->work_lock);
	seq = work->queue_seq;
	work->flushing++;
	spin_unlock_irq(&dev->work_lock);
	wait_event(work->done, vhost_work_seq_done(dev, work, seq));
	spin_lock_irq(&dev->work_lock);
	flushing = --work->flushing;
	spin_unlock_irq(&dev->work_lock);
	BUG_ON(flushing < 0);
}
EXPORT_SYMBOL_GPL(vhost_work_flush);

/* Flush any work that has been scheduled. When calling this, don't hold any
 * locks that are also used by the callback. */
void vhost_poll_flush(struct vhost_poll *poll)
{
	vhost_work_flush(poll->dev, &poll->work);
}
EXPORT_SYMBOL_GPL(vhost_poll_flush);

void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *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++;
		spin_unlock_irqrestore(&dev->work_lock, flags);
		wake_up_process(dev->worker);
	} else {
		spin_unlock_irqrestore(&dev->work_lock, flags);
	}
}
EXPORT_SYMBOL_GPL(vhost_work_queue);

void vhost_poll_queue(struct vhost_poll *poll)
{
	vhost_work_queue(poll->dev, &poll->work);
}
EXPORT_SYMBOL_GPL(vhost_poll_queue);

static void vhost_vq_reset(struct vhost_dev *dev,
			   struct vhost_virtqueue *vq)
{
	vq->num = 1;
	vq->desc = NULL;
	vq->avail = NULL;
	vq->used = NULL;
	vq->last_avail_idx = 0;
	vq->avail_idx = 0;
	vq->last_used_idx = 0;
	vq->signalled_used = 0;
	vq->signalled_used_valid = false;
	vq->used_flags = 0;
	vq->log_used = false;
	vq->log_addr = -1ull;
	vq->private_data = NULL;
	vq->acked_features = 0;
	vq->log_base = NULL;
	vq->error_ctx = NULL;
	vq->error = NULL;
	vq->kick = NULL;
	vq->call_ctx = NULL;
	vq->call = NULL;
	vq->log_ctx = NULL;
	vq->memory = NULL;
}

static int vhost_worker(void *data)
{
	struct vhost_dev *dev = data;
	struct vhost_work *work = NULL;
	unsigned uninitialized_var(seq);
	mm_segment_t oldfs = get_fs();

	set_fs(USER_DS);
	use_mm(dev->mm);

	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);
			break;
		}
		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);
			if (need_resched())
				schedule();
		} else
			schedule();

	}
	unuse_mm(dev->mm);
	set_fs(oldfs);
	return 0;
}

static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
{
	kfree(vq->indirect);
	vq->indirect = NULL