lguest.c

linux 内核源代码

		(void)convert(&iov[0], struct virtio_net_hdr);
		len = writev(vq->dev->fd, iov+1, out-1);
		add_used_and_trigger(fd, vq, head, len);
	}
}

/* This is where we handle a packet coming in from the tun device to our
 * Guest. */
static bool handle_tun_input(int fd, struct device *dev)
{
	unsigned int head, in_num, out_num;
	int len;
	struct iovec iov[dev->vq->vring.num];
	struct virtio_net_hdr *hdr;

	/* First we need a network buffer from the Guests's recv virtqueue. */
	head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
	if (head == dev->vq->vring.num) {
		/* Now, it's expected that if we try to send a packet too
		 * early, the Guest won't be ready yet.  Wait until the device
		 * status says it's ready. */
		/* FIXME: Actually want DRIVER_ACTIVE here. */
		if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK)
			warn("network: no dma buffer!");
		/* We'll turn this back on if input buffers are registered. */
		return false;
	} else if (out_num)
		errx(1, "Output buffers in network recv queue?");

	/* First element is the header: we set it to 0 (no features). */
	hdr = convert(&iov[0], struct virtio_net_hdr);
	hdr->flags = 0;
	hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;

	/* Read the packet from the device directly into the Guest's buffer. */
	len = readv(dev->fd, iov+1, in_num-1);
	if (len <= 0)
		err(1, "reading network");

	/* Tell the Guest about the new packet. */
	add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);

	verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
		((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
		head != dev->vq->vring.num ? "sent" : "discarded");

	/* All good. */
	return true;
}

/*L:215 This is the callback attached to the network and console input
 * virtqueues: it ensures we try again, in case we stopped console or net
 * delivery because Guest didn't have any buffers. */
static void enable_fd(int fd, struct virtqueue *vq)
{
	add_device_fd(vq->dev->fd);
	/* Tell waker to listen to it again */
	write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
}

/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */
static void handle_output(int fd, unsigned long addr)
{
	struct device *i;
	struct virtqueue *vq;

	/* Check each virtqueue. */
	for (i = devices.dev; i; i = i->next) {
		for (vq = i->vq; vq; vq = vq->next) {
			if (vq->config.pfn == addr/getpagesize()
			    && vq->handle_output) {
				verbose("Output to %s\n", vq->dev->name);
				vq->handle_output(fd, vq);
				return;
			}
		}
	}

	/* Early console write is done using notify on a nul-terminated string
	 * in Guest memory. */
	if (addr >= guest_limit)
		errx(1, "Bad NOTIFY %#lx", addr);

	write(STDOUT_FILENO, from_guest_phys(addr),
	      strnlen(from_guest_phys(addr), guest_limit - addr));
}

/* This is called when the Waker wakes us up: check for incoming file
 * descriptors. */
static void handle_input(int fd)
{
	/* select() wants a zeroed timeval to mean "don't wait". */
	struct timeval poll = { .tv_sec = 0, .tv_usec = 0 };

	for (;;) {
		struct device *i;
		fd_set fds = devices.infds;

		/* If nothing is ready, we're done. */
		if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0)
			break;

		/* Otherwise, call the device(s) which have readable
		 * file descriptors and a method of handling them.  */
		for (i = devices.dev; i; i = i->next) {
			if (i->handle_input && FD_ISSET(i->fd, &fds)) {
				int dev_fd;
				if (i->handle_input(fd, i))
					continue;

				/* If handle_input() returns false, it means we
				 * should no longer service it.  Networking and
				 * console do this when there's no input
				 * buffers to deliver into.  Console also uses
				 * it when it discovers that stdin is
				 * closed. */
				FD_CLR(i->fd, &devices.infds);
				/* Tell waker to ignore it too, by sending a
				 * negative fd number (-1, since 0 is a valid
				 * FD number). */
				dev_fd = -i->fd - 1;
				write(waker_fd, &dev_fd, sizeof(dev_fd));
			}
		}
	}
}

/*L:190
 * Device Setup
 *
 * All devices need a descriptor so the Guest knows it exists, and a "struct
 * device" so the Launcher can keep track of it.  We have common helper
 * routines to allocate them.
 *
 * This routine allocates a new "struct lguest_device_desc" from descriptor
 * table just above the Guest's normal memory.  It returns a pointer to that
 * descriptor. */
static struct lguest_device_desc *new_dev_desc(u16 type)
{
	struct lguest_device_desc *d;

	/* We only have one page for all the descriptors. */
	if (devices.desc_used + sizeof(*d) > getpagesize())
		errx(1, "Too many devices");

	/* We don't need to set config_len or status: page is 0 already. */
	d = (void *)devices.descpage + devices.desc_used;
	d->type = type;
	devices.desc_used += sizeof(*d);

	return d;
}

/* Each device descriptor is followed by some configuration information.
 * Each configuration field looks like: u8 type, u8 len, [... len bytes...].
 *
 * This routine adds a new field to an existing device's descriptor.  It only
 * works for the last device, but that's OK because that's how we use it. */
static void add_desc_field(struct device *dev, u8 type, u8 len, const void *c)
{
	/* This is the last descriptor, right? */
	assert(devices.descpage + devices.desc_used
	       == (u8 *)(dev->desc + 1) + dev->desc->config_len);

	/* We only have one page of device descriptions. */
	if (devices.desc_used + 2 + len > getpagesize())
		errx(1, "Too many devices");

	/* Copy in the new config header: type then length. */
	devices.descpage[devices.desc_used++] = type;
	devices.descpage[devices.desc_used++] = len;
	memcpy(devices.descpage + devices.desc_used, c, len);
	devices.desc_used += len;

	/* Update the device descriptor length: two byte head then data. */
	dev->desc->config_len += 2 + len;
}

/* This routine adds a virtqueue to a device.  We specify how many descriptors
 * the virtqueue is to have. */
static void add_virtqueue(struct device *dev, unsigned int num_descs,
			  void (*handle_output)(int fd, struct virtqueue *me))
{
	unsigned int pages;
	struct virtqueue **i, *vq = malloc(sizeof(*vq));
	void *p;

	/* First we need some pages for this virtqueue. */
	pages = (vring_size(num_descs, getpagesize()) + getpagesize() - 1)
		/ getpagesize();
	p = get_pages(pages);

	/* Initialize the virtqueue */
	vq->next = NULL;
	vq->last_avail_idx = 0;
	vq->dev = dev;

	/* Initialize the configuration. */
	vq->config.num = num_descs;
	vq->config.irq = devices.next_irq++;
	vq->config.pfn = to_guest_phys(p) / getpagesize();

	/* Initialize the vring. */
	vring_init(&vq->vring, num_descs, p, getpagesize());

	/* Add the configuration information to this device's descriptor. */
	add_desc_field(dev, VIRTIO_CONFIG_F_VIRTQUEUE,
		       sizeof(vq->config), &vq->config);

	/* Add to tail of list, so dev->vq is first vq, dev->vq->next is
	 * second.  */
	for (i = &dev->vq; *i; i = &(*i)->next);
	*i = vq;

	/* Set the routine to call when the Guest does something to this
	 * virtqueue. */
	vq->handle_output = handle_output;

	/* Set the "Don't Notify Me" flag if we don't have a handler */
	if (!handle_output)
		vq->vring.used->flags = VRING_USED_F_NO_NOTIFY;
}

/* This routine does all the creation and setup of a new device, including
 * calling new_dev_desc() to allocate the descriptor and device memory. */
static struct device *new_device(const char *name, u16 type, int fd,
				 bool (*handle_input)(int, struct device *))
{
	struct device *dev = malloc(sizeof(*dev));

	/* Append to device list.  Prepending to a single-linked list is
	 * easier, but the user expects the devices to be arranged on the bus
	 * in command-line order.  The first network device on the command line
	 * is eth0, the first block device /dev/vda, etc. */
	*devices.lastdev = dev;
	dev->next = NULL;
	devices.lastdev = &dev->next;

	/* Now we populate the fields one at a time. */
	dev->fd = fd;
	/* If we have an input handler for this file descriptor, then we add it
	 * to the device_list's fdset and maxfd. */
	if (handle_input)
		add_device_fd(dev->fd);
	dev->desc = new_dev_desc(type);
	dev->handle_input = handle_input;
	dev->name = name;
	dev->vq = NULL;
	return dev;
}

/* Our first setup routine is the console.  It's a fairly simple device, but
 * UNIX tty handling makes it uglier than it could be. */
static void setup_console(void)
{
	struct device *dev;

	/* If we can save the initial standard input settings... */
	if (tcgetattr(STDIN_FILENO, &orig_term) == 0) {
		struct termios term = orig_term;
		/* Then we turn off echo, line buffering and ^C etc.  We want a
		 * raw input stream to the Guest. */
		term.c_lflag &= ~(ISIG|ICANON|ECHO);
		tcsetattr(STDIN_FILENO, TCSANOW, &term);
		/* If we exit gracefully, the original settings will be
		 * restored so the user can see what they're typing. */
		atexit(restore_term);
	}

	dev = new_device("console", VIRTIO_ID_CONSOLE,
			 STDIN_FILENO, handle_console_input);
	/* We store the console state in dev->priv, and initialize it. */
	dev->priv = malloc(sizeof(struct console_abort));
	((struct console_abort *)dev->priv)->count = 0;

	/* The console needs two virtqueues: the input then the output.  When
	 * they put something the input queue, we make sure we're listening to
	 * stdin.  When they put something in the output queue, we write it to
	 * stdout. */
	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
	add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);

	verbose("device %u: console\n", devices.device_num++);
}
/*:*/

/*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
 * --sharenet=<name> option which opens or creates a named pipe.  This can be
 * used to send packets to another guest in a 1:1 manner.
 *
 * More sopisticated is to use one of the tools developed for project like UML
 * to do networking.
 *
 * Faster is to do virtio bonding in kernel.  Doing this 1:1 would be
 * completely generic ("here's my vring, attach to your vring") and would work
 * for any traffic.  Of course, namespace and permissions issues need to be
 * dealt with.  A more sophisticated "multi-channel" virtio_net.c could hide
 * multiple inter-guest channels behind one interface, although it would
 * require some manner of hotplugging new virtio channels.
 *
 * Finally, we could implement a virtio network switch in the kernel. :*/

static u32 str2ip(const char *ipaddr)
{
	unsigned int byte[4];

	sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
	return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
}

/* This code is "adapted" from libbridge: it attaches the Host end of the
 * network device to the bridge device specified by the command line.
 *
 * This is yet another James Morris contribution (I'm an IP-level guy, so I
 * dislike bridging), and I just try not to break it. */
static void add_to_bridge(int fd, const char *if_name, const char *br_name)
{
	int ifidx;
	struct ifreq ifr;

	if (!*br_name)
		errx(1, "must specify bridge name");

	ifidx = if_nametoindex(if_name);
	if (!ifidx)
		errx(1, "interface %s does not exist!", if_name);

	strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
	ifr.ifr_ifindex = ifidx;
	if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
		err(1, "can't add %s to bridge %s", if_name, br_name);
}

/* This sets up the Host end of the network device with an IP address, brings
 * it up so packets will flow, the copies the MAC address into the hwaddr
 * pointer. */
static void configure_device(int fd, const char *devname, u32 ipaddr,
			     unsigned char hwaddr[6])
{
	struct ifreq ifr;
	struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;

	/* Don't read these incantations.  Just cut & paste them like I did! */
	memset(&ifr, 0, sizeof(ifr));
	strcpy(ifr.ifr_name, devname);
	sin->sin_family = AF_INET;
	sin->sin_addr.s_addr = htonl(ipaddr);
	if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
		err(1, "Setting %s interface address", devname);
	ifr.ifr_flags = IFF_UP;
	if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
		err(1, "Bringing interface %s up", devname);

	/* SIOC stands for Socket I/O Control.  G means Get (vs S for Set
	 * above).  IF means Interface, and HWADDR is hardware address.
	 * Simple! */
	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
		err(1, "getting hw address for %s", devname);
	memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
}

/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
 * routing, but the principle is the same: it uses the "tun" device to inject
 * packets into the Host as if they came in from a normal network card.  We
 * just shunt packets between the Guest and the tun device. */
static void setup_tun_net(const char *arg)
{
	struct device *dev;
	struct ifreq ifr;
	int netfd, ipfd;
	u32 ip;
	const char *br_name = NULL;
	u8 hwaddr[6];

	/* We open the /dev/net/tun device and tell it we want a tap device.  A
	 * tap device is like a tun device, only somehow different.  To tell
	 * the truth, I completely blundered my way through this code, but it
	 * works now! */
	netfd = open_or_die("/dev/net/tun", O_RDWR);
	memset(&ifr, 0, sizeof(ifr));
	ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
	strcpy(ifr.ifr_name, "tap%d");
	if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
		err(1, "configuring /dev/net/tun");
	/* We don't need checksums calculated for packets coming in this
	 * device: trust us! */
	ioctl(netfd, TUNSETNOCSUM, 1);

	/* First we create a new network device. */
	dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);

	/* Network devices need a receive and a send queue, just like
	 * console. */
	add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
	add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);

	/* We need a socket to perform the magic network ioctls to bring up the
	 * tap interface, connect to the bridge etc.  Any socket will do! */
	ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
	if (ipfd < 0)
		err(1, "opening IP socket");

	/* If the command line was --tunnet=bridge:<name> do bridging. */
	if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
		ip = INADDR_ANY;
		br_name = arg + strlen(BRIDGE_PFX);
		add_to_bridge(ipfd, ifr.ifr_name, br_name);
	} else /* It is an IP address to set up the device with */
		ip = str2ip(arg);

	/* Set up the tun device, and get the mac address for the interface. */
	configure_device(ipfd, ifr.ifr_name, ip, hwaddr);

	/* Tell Guest what MAC address to use. */
	add_desc_field(dev, VIRTIO_CONFIG_NET_MAC_F, sizeof(hwaddr), hwaddr);

	/* We don't seed the socket any more; setup is done. */
	close(ipfd);

	verbose("device %u: tun net %u.%u.%u.%u\n",
		devices.device_num++,
		(u8)(ip>>24),(u8)(ip>>16),(u8)(ip>>8),(u8)ip);
	if (br_name)
		verbose("attached to bridge: %s\n", br_name);
}