path: root/drivers/vhost/net.c

/* Copyright (C) 2009 Red Hat, Inc.
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 *
 * virtio-net server in host kernel.
 */

#include <linux/compat.h>
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/rcupdate.h>
#include <linux/file.h>
#include <linux/slab.h>

#include <linux/net.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>
#include <linux/if_tun.h>
#include <linux/if_macvlan.h>
#include <linux/if_vlan.h>

#include <net/sock.h>

#include "vhost.h"

static int experimental_zcopytx = 1;
module_param(experimental_zcopytx, int, 0444);
MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
		                       " 1 -Enable; 0 - Disable");

/* Max number of bytes transferred before requeueing the job.
 * Using this limit prevents one virtqueue from starving others. */
#define VHOST_NET_WEIGHT 0x80000

/* MAX number of TX used buffers for outstanding zerocopy */
#define VHOST_MAX_PEND 128
#define VHOST_GOODCOPY_LEN 256

/*
 * For transmit, used buffer len is unused; we override it to track buffer
 * status internally; used for zerocopy tx only.
 */
/* Lower device DMA failed */
#define VHOST_DMA_FAILED_LEN	3
/* Lower device DMA done */
#define VHOST_DMA_DONE_LEN	2
/* Lower device DMA in progress */
#define VHOST_DMA_IN_PROGRESS	1
/* Buffer unused */
#define VHOST_DMA_CLEAR_LEN	0

#define VHOST_DMA_IS_DONE(len) ((len) >= VHOST_DMA_DONE_LEN)

enum {
	VHOST_NET_FEATURES = VHOST_FEATURES |
			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
			 (1ULL << VIRTIO_NET_F_MRG_RXBUF),
};

enum {
	VHOST_NET_VQ_RX = 0,
	VHOST_NET_VQ_TX = 1,
	VHOST_NET_VQ_MAX = 2,
};

struct vhost_net_ubuf_ref {
	struct kref kref;
	wait_queue_head_t wait;
	struct vhost_virtqueue *vq;
};

struct vhost_net_virtqueue {
	struct vhost_virtqueue vq;
	/* hdr is used to store the virtio header.
	 * Since each iovec has >= 1 byte length, we never need more than
	 * header length entries to store the header. */
	struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)];
	size_t vhost_hlen;
	size_t sock_hlen;
	/* vhost zerocopy support fields below: */
	/* last used idx for outstanding DMA zerocopy buffers */
	int upend_idx;
	/* first used idx for DMA done zerocopy buffers */
	int done_idx;
	/* an array of userspace buffers info */
	struct ubuf_info *ubuf_info;
	/* Reference counting for outstanding ubufs.
	 * Protected by vq mutex. Writers must also take device mutex. */
	struct vhost_net_ubuf_ref *ubufs;
};

struct vhost_net {
	struct vhost_dev dev;
	struct vhost_net_virtqueue vqs[VHOST_NET_VQ_MAX];
	struct vhost_poll poll[VHOST_NET_VQ_MAX];
	/* Number of TX recently submitted.
	 * Protected by tx vq lock. */
	unsigned tx_packets;
	/* Number of times zerocopy TX recently failed.
	 * Protected by tx vq lock. */
	unsigned tx_zcopy_err;
	/* Flush in progress. Protected by tx vq lock. */
	bool tx_flush;
};

static unsigned vhost_net_zcopy_mask __read_mostly;

static void vhost_net_enable_zcopy(int vq)
{
	vhost_net_zcopy_mask |= 0x1 << vq;
}

static void vhost_net_zerocopy_done_signal(struct kref *kref)
{
	struct vhost_net_ubuf_ref *ubufs;

	ubufs = container_of(kref, struct vhost_net_ubuf_ref, kref);
	wake_up(&ubufs->wait);
}

static struct vhost_net_ubuf_ref *
vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
{
	struct vhost_net_ubuf_ref *ubufs;
	/* No zero copy backend? Nothing to count. */
	if (!zcopy)
		return NULL;
	ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL);
	if (!ubufs)
		return ERR_PTR(-ENOMEM);
	kref_init(&ubufs->kref);
	init_waitqueue_head(&ubufs->wait);
	ubufs->vq = vq;
	return ubufs;
}

static void vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
{
	kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
}

static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
{
	kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
	wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
}

static void vhost_net_ubuf_put_wait_and_free(struct