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_VQ_RX = 0,
	VHOST_NET_VQ_TX = 1,
	VHOST_NET_VQ_MAX = 2,
};

enum vhost_net_poll_state {
	VHOST_NET_POLL_DISABLED = 0,
	VHOST_NET_POLL_STARTED = 1,
	VHOST_NET_POLL_STOPPED = 2,
};

struct vhost_net {
	struct vhost_dev dev;
	struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
	struct vhost_poll poll[VHOST_NET_VQ_MAX];
	/* Tells us whether we are polling a socket for TX.
	 * We only do this when socket buffer fills up.
	 * Protected by tx vq lock. */
	enum vhost_net_poll_state tx_poll_state;
	/* 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 void vhost_net_tx_packet(struct vhost_net *net)
{
	++net->tx_packets;
	if (net->tx_packets < 1024)
		return;
	net->tx_packets = 0;
	net->tx_zcopy_err = 0;
}

static void vhost_net_tx_err(struct vhost_net *net)
{
	++net->tx_zcopy_err;
}

static bool vhost_net_tx_select_zcopy(struct vhost_net *net)
{
	/* TX flush waits for outstanding DMAs to be done.
	 * Don't start new DMAs.
	 */
	return !net->tx_flush &&
		net->tx_packets / 64 >= net->tx_zcopy_err;
}

static bool vhost_sock_zcopy(struct socket *sock)
{
	return unlikely(experimental_zcopytx) &&
		sock_flag(sock->sk, SOCK_ZEROCOPY);
}

/* Pop first len bytes from iovec. Return number of segments used. */
static int move_iovec_hdr(struct iovec *from, struct iovec *to,
			  size_t len, int iov_count)
{
	int seg = 0;
	size_t size;

	while (len && seg < iov_count) {
		size = min(from->iov_len, len);
		to->iov_base = from->iov_base;
		to->iov_len = size;
		from->iov_len -= size;
		from->iov_base += size;
		len -= size;
		++from;
		++to;
		++seg;
	}
	return seg;
}
/* Copy iovec entries for len bytes from iovec. */
static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
			   size_t len, int iovcount)
{
	int seg = 0;
	size_t size;

	while (len && seg < iovcount) {
		size = min(from->iov_len, len);
		to->iov_base = from->iov_base;
		to->iov_len = size;
		len -= size;
		++from;
		++to;
		++seg;
	}
}

/* Caller must have TX VQ lock */
static void tx_poll_stop(struct vhost_net *net)
{
	if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
		return;
	vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
	net->tx_poll_state = VHOST_NET_POLL_STOPPED;
}

/* Caller must have TX VQ lock */
static int tx_poll_start(struct vhost_net *net, struct socket *sock)
{
	int ret;

	if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
		return 0;
	ret = vhost_poll_start(net->poll + VHOST_NET_V