summaryrefslogtreecommitdiff
path: root/Documentation/lguest/lguest.c
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/lguest/lguest.c')
-rw-r--r--Documentation/lguest/lguest.c387
1 files changed, 323 insertions, 64 deletions
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 82fafe0429fe..35c8c69ceb72 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -36,11 +36,13 @@
#include <sched.h>
#include <limits.h>
#include <stddef.h>
+#include <signal.h>
#include "linux/lguest_launcher.h"
#include "linux/virtio_config.h"
#include "linux/virtio_net.h"
#include "linux/virtio_blk.h"
#include "linux/virtio_console.h"
+#include "linux/virtio_rng.h"
#include "linux/virtio_ring.h"
#include "asm-x86/bootparam.h"
/*L:110 We can ignore the 39 include files we need for this program, but I do
@@ -64,8 +66,8 @@ typedef uint8_t u8;
#endif
/* We can have up to 256 pages for devices. */
#define DEVICE_PAGES 256
-/* This will occupy 2 pages: it must be a power of 2. */
-#define VIRTQUEUE_NUM 128
+/* This will occupy 4 pages: it must be a power of 2. */
+#define VIRTQUEUE_NUM 512
/*L:120 verbose is both a global flag and a macro. The C preprocessor allows
* this, and although I wouldn't recommend it, it works quite nicely here. */
@@ -80,6 +82,8 @@ static int waker_fd;
static void *guest_base;
/* The maximum guest physical address allowed, and maximum possible. */
static unsigned long guest_limit, guest_max;
+/* The pipe for signal hander to write to. */
+static int timeoutpipe[2];
/* a per-cpu variable indicating whose vcpu is currently running */
static unsigned int __thread cpu_id;
@@ -152,16 +156,18 @@ struct virtqueue
/* The actual ring of buffers. */
struct vring vring;
- /* Last available index we saw. */
- u16 last_avail_idx;
-
/* The routine to call when the Guest pings us. */
void (*handle_output)(int fd, struct virtqueue *me);
/* Outstanding buffers */
unsigned int inflight;
+
+ /* Is this blocked awaiting a timer? */
+ bool blocked;
};
+static unsigned int net_xmit_notify, net_recv_notify, net_timeout;
+
/* Remember the arguments to the program so we can "reboot" */
static char **main_args;
@@ -199,6 +205,33 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
#define le32_to_cpu(v32) (v32)
#define le64_to_cpu(v64) (v64)
+/* Is this iovec empty? */
+static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
+{
+ unsigned int i;
+
+ for (i = 0; i < num_iov; i++)
+ if (iov[i].iov_len)
+ return false;
+ return true;
+}
+
+/* Take len bytes from the front of this iovec. */
+static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
+{
+ unsigned int i;
+
+ for (i = 0; i < num_iov; i++) {
+ unsigned int used;
+
+ used = iov[i].iov_len < len ? iov[i].iov_len : len;
+ iov[i].iov_base += used;
+ iov[i].iov_len -= used;
+ len -= used;
+ }
+ assert(len == 0);
+}
+
/* The device virtqueue descriptors are followed by feature bitmasks. */
static u8 *get_feature_bits(struct device *dev)
{
@@ -254,6 +287,7 @@ static void *map_zeroed_pages(unsigned int num)
PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
if (addr == MAP_FAILED)
err(1, "Mmaping %u pages of /dev/zero", num);
+ close(fd);
return addr;
}
@@ -661,19 +695,22 @@ static unsigned get_vq_desc(struct virtqueue *vq,
unsigned int *out_num, unsigned int *in_num)
{
unsigned int i, head;
+ u16 last_avail;
/* Check it isn't doing very strange things with descriptor numbers. */
- if ((u16)(vq->vring.avail->idx - vq->last_avail_idx) > vq->vring.num)
+ last_avail = vring_last_avail(&vq->vring);
+ if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
errx(1, "Guest moved used index from %u to %u",
- vq->last_avail_idx, vq->vring.avail->idx);
+ last_avail, vq->vring.avail->idx);
/* If there's nothing new since last we looked, return invalid. */
- if (vq->vring.avail->idx == vq->last_avail_idx)
+ if (vq->vring.avail->idx == last_avail)
return vq->vring.num;
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
- head = vq->vring.avail->ring[vq->last_avail_idx++ % vq->vring.num];
+ head = vq->vring.avail->ring[last_avail % vq->vring.num];
+ vring_last_avail(&vq->vring)++;
/* If their number is silly, that's a fatal mistake. */
if (head >= vq->vring.num)
@@ -825,6 +862,9 @@ static bool handle_console_input(int fd, struct device *dev)
/* Just in case waker is blocked in BREAK, send
* unbreak now. */
write(fd, args, sizeof(args));
+ printf("network xmit %u recv %u timeout %u\n",
+ net_xmit_notify, net_recv_notify,
+ net_timeout);
exit(2);
}
abort->count = 0;
@@ -854,6 +894,21 @@ static void handle_console_output(int fd, struct virtqueue *vq)
}
}
+static void block_vq(struct virtqueue *vq)
+{
+ struct itimerval itm;
+
+ vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+ vq->blocked = true;
+
+ itm.it_interval.tv_sec = 0;
+ itm.it_interval.tv_usec = 0;
+ itm.it_value.tv_sec = 0;
+ itm.it_value.tv_usec = 250;
+
+ setitimer(ITIMER_REAL, &itm, NULL);
+}
+
/*
* The Network
*
@@ -863,21 +918,26 @@ static void handle_console_output(int fd, struct virtqueue *vq)
*/
static void handle_net_output(int fd, struct virtqueue *vq)
{
- unsigned int head, out, in;
+ unsigned int head, out, in, num = 0;
int len;
struct iovec iov[vq->vring.num];
+ net_xmit_notify++;
+
/* Keep getting output buffers from the Guest until we run out. */
while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
if (in)
errx(1, "Input buffers in output queue?");
- /* Check header, but otherwise ignore it (we told the Guest we
- * supported no features, so it shouldn't have anything
- * interesting). */
- (void)convert(&iov[0], struct virtio_net_hdr);
- len = writev(vq->dev->fd, iov+1, out-1);
+ len = writev(vq->dev->fd, iov, out);
+ if (len < 0)
+ err(1, "Writing network packet to tun");
add_used_and_trigger(fd, vq, head, len);
+ num++;
}
+
+ /* Block further kicks, and set up a timer if we saw anything. */
+ if (num)
+ block_vq(vq);
}
/* This is where we handle a packet coming in from the tun device to our
@@ -887,7 +947,6 @@ 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);
@@ -896,25 +955,23 @@ static bool handle_tun_input(int fd, struct device *dev)
* 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!");
+
+ /* Now tell it we want to know if new things appear. */
+ dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+ wmb();
+
/* 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);
+ len = readv(dev->fd, iov, in_num);
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);
+ add_used_and_trigger(fd, dev->vq, head, len);
verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
@@ -934,6 +991,16 @@ static void enable_fd(int fd, struct virtqueue *vq)
write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
}
+static void net_enable_fd(int fd, struct virtqueue *vq)
+{
+ /* We don't need to know again when Guest refills receive buffer. */
+ vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+ net_recv_notify++;
+ add_device_fd(vq->dev->fd);
+ /* Tell waker to listen to it again */
+ write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+}
+
/* When the Guest tells us they updated the status field, we handle it. */
static void update_device_status(struct device *dev)
{
@@ -951,7 +1018,7 @@ static void update_device_status(struct device *dev)
for (vq = dev->vq; vq; vq = vq->next) {
memset(vq->vring.desc, 0,
vring_size(vq->config.num, getpagesize()));
- vq->last_avail_idx = 0;
+ vring_last_avail(&vq->vring) = 0;
}
} else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
warnx("Device %s configuration FAILED", dev->name);
@@ -1014,6 +1081,29 @@ static void handle_output(int fd, unsigned long addr)
strnlen(from_guest_phys(addr), guest_limit - addr));
}
+static void handle_timeout(int fd)
+{
+ char buf[32];
+ struct device *i;
+ struct virtqueue *vq;
+
+ /* Clear the pipe */
+ read(timeoutpipe[0], buf, sizeof(buf));
+
+ /* Check each device and virtqueue: flush blocked ones. */
+ for (i = devices.dev; i; i = i->next) {
+ for (vq = i->vq; vq; vq = vq->next) {
+ if (!vq->blocked)
+ continue;
+
+ vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+ vq->blocked = false;
+ if (vq->handle_output)
+ vq->handle_output(fd, vq);
+ }
+ }
+}
+
/* This is called when the Waker wakes us up: check for incoming file
* descriptors. */
static void handle_input(int fd)
@@ -1024,9 +1114,14 @@ static void handle_input(int fd)
for (;;) {
struct device *i;
fd_set fds = devices.infds;
+ int num;
+ num = select(devices.max_infd+1, &fds, NULL, NULL, &poll);
+ /* Could get interrupted */
+ if (num < 0)
+ continue;
/* If nothing is ready, we're done. */
- if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0)
+ if (num == 0)
break;
/* Otherwise, call the device(s) which have readable file
@@ -1050,6 +1145,10 @@ static void handle_input(int fd)
write(waker_fd, &dev_fd, sizeof(dev_fd));
}
}
+
+ /* Is this the timeout fd? */
+ if (FD_ISSET(timeoutpipe[0], &fds))
+ handle_timeout(fd);
}
}
@@ -1111,9 +1210,9 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
/* Initialize the virtqueue */
vq->next = NULL;
- vq->last_avail_idx = 0;
vq->dev = dev;
vq->inflight = 0;
+ vq->blocked = false;
/* Initialize the configuration. */
vq->config.num = num_descs;
@@ -1168,6 +1267,10 @@ static void add_feature(struct device *dev, unsigned bit)
* how we use it. */
static void set_config(struct device *dev, unsigned len, const void *conf)
{
+ /* We always set the VIRTIO_RING_F_PUBLISH_INDICES feature
+ * bit, so now is a good time to do that. */
+ add_feature(dev, VIRTIO_RING_F_PUBLISH_INDICES);
+
/* Check we haven't overflowed our single page. */
if (device_config(dev) + len > devices.descpage + getpagesize())
errx(1, "Too many devices");
@@ -1242,10 +1345,31 @@ static void setup_console(void)
add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
add_virtqueue(dev, VIRTQUEUE_NUM, handle_console_output);
+ /* Every device should set this bit. */
+ add_feature(dev, VIRTIO_RING_F_PUBLISH_INDICES);
verbose("device %u: console\n", devices.device_num++);
}
/*:*/
+static void timeout_alarm(int sig)
+{
+ net_timeout++;
+ write(timeoutpipe[1], "", 1);
+}
+
+static void setup_timeout(void)
+{
+ if (pipe(timeoutpipe) != 0)
+ err(1, "Creating timeout pipe");
+
+ if (fcntl(timeoutpipe[1], F_SETFL,
+ fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0)
+ err(1, "Making timeout pipe nonblocking");
+
+ add_device_fd(timeoutpipe[0]);
+ signal(SIGALRM, timeout_alarm);
+}
+
/*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.
@@ -1264,10 +1388,25 @@ static void setup_console(void)
static u32 str2ip(const char *ipaddr)
{
- unsigned int byte[4];
+ unsigned int b[4];
+
+ if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
+ errx(1, "Failed to parse IP address '%s'", ipaddr);
+ return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
+}
- 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];
+static void str2mac(const char *macaddr, unsigned char mac[6])
+{
+ unsigned int m[6];
+ if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x",
+ &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6)
+ errx(1, "Failed to parse mac address '%s'", mac);
+ mac[0] = m[0];
+ mac[1] = m[1];
+ mac[2] = m[2];
+ mac[3] = m[3];
+ mac[4] = m[4];
+ mac[5] = m[5];
}
/* This code is "adapted" from libbridge: it attaches the Host end of the
@@ -1288,6 +1427,7 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
errx(1, "interface %s does not exist!", if_name);
strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
+ ifr.ifr_name[IFNAMSIZ-1] = '\0';
ifr.ifr_ifindex = ifidx;
if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
err(1, "can't add %s to bridge %s", if_name, br_name);
@@ -1296,64 +1436,90 @@ static void add_to_bridge(int fd, const char *if_name, const char *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])
+static void configure_device(int fd, const char *tapif, u32 ipaddr)
{
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);
+ strcpy(ifr.ifr_name, tapif);
+
+ /* Don't read these incantations. Just cut & paste them like I did! */
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);
+ err(1, "Setting %s interface address", tapif);
ifr.ifr_flags = IFF_UP;
if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
- err(1, "Bringing interface %s up", devname);
+ err(1, "Bringing interface %s up", tapif);
+}
+
+static void get_mac(int fd, const char *tapif, unsigned char hwaddr[6])
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, tapif);
/* 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);
+ err(1, "getting hw address for %s", tapif);
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)
+static int get_tun_device(char tapif[IFNAMSIZ])
{
- struct device *dev;
struct ifreq ifr;
- int netfd, ipfd;
- u32 ip;
- const char *br_name = NULL;
- struct virtio_net_config conf;
+ int netfd;
+
+ /* Start with this zeroed. Messy but sure. */
+ memset(&ifr, 0, sizeof(ifr));
/* 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;
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
strcpy(ifr.ifr_name, "tap%d");
if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
err(1, "configuring /dev/net/tun");
+
+ if (ioctl(netfd, TUNSETFEATURES,
+ TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
+ err(1, "Could not set features for tun device");
+
/* We don't need checksums calculated for packets coming in this
* device: trust us! */
ioctl(netfd, TUNSETNOCSUM, 1);
+ memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
+ return netfd;
+}
+
+/*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(char *arg)
+{
+ struct device *dev;
+ int netfd, ipfd;
+ u32 ip = INADDR_ANY;
+ bool bridging = false;
+ char tapif[IFNAMSIZ], *p;
+ struct virtio_net_config conf;
+
+ netfd = get_tun_device(tapif);
+
/* 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, net_enable_fd);
add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);
/* We need a socket to perform the magic network ioctls to bring up the
@@ -1364,28 +1530,56 @@ static void setup_tun_net(const char *arg)
/* 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 */
+ arg += strlen(BRIDGE_PFX);
+ bridging = true;
+ }
+
+ /* A mac address may follow the bridge name or IP address */
+ p = strchr(arg, ':');
+ if (p) {
+ str2mac(p+1, conf.mac);
+ *p = '\0';
+ } else {
+ p = arg + strlen(arg);
+ /* None supplied; query the randomly assigned mac. */
+ get_mac(ipfd, tapif, conf.mac);
+ }
+
+ /* arg is now either an IP address or a bridge name */
+ if (bridging)
+ add_to_bridge(ipfd, tapif, arg);
+ else
ip = str2ip(arg);
- /* Set up the tun device, and get the mac address for the interface. */
- configure_device(ipfd, ifr.ifr_name, ip, conf.mac);
+ /* Set up the tun device. */
+ configure_device(ipfd, tapif, ip);
/* Tell Guest what MAC address to use. */
add_feature(dev, VIRTIO_NET_F_MAC);
add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
+ /* Expect Guest to handle everything except UFO */
+ add_feature(dev, VIRTIO_NET_F_CSUM);
+ add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
+ add_feature(dev, VIRTIO_NET_F_MAC);
+ add_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
+ add_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
+ add_feature(dev, VIRTIO_NET_F_GUEST_ECN);
+ add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
+ add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
+ add_feature(dev, VIRTIO_NET_F_HOST_ECN);
set_config(dev, sizeof(conf), &conf);
/* We don't need 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);
+ devices.device_num++;
+
+ if (bridging)
+ verbose("device %u: tun %s attached to bridge: %s\n",
+ devices.device_num, tapif, arg);
+ else
+ verbose("device %u: tun %s: %s\n",
+ devices.device_num, tapif, arg);
}
/* Our block (disk) device should be really simple: the Guest asks for a block
@@ -1621,6 +1815,64 @@ static void setup_block_file(const char *filename)
verbose("device %u: virtblock %llu sectors\n",
devices.device_num, le64_to_cpu(conf.capacity));
}
+
+/* Our random number generator device reads from /dev/random into the Guest's
+ * input buffers. The usual case is that the Guest doesn't want random numbers
+ * and so has no buffers although /dev/random is still readable, whereas
+ * console is the reverse.
+ *
+ * The same logic applies, however. */
+static bool handle_rng_input(int fd, struct device *dev)
+{
+ int len;
+ unsigned int head, in_num, out_num, totlen = 0;
+ struct iovec iov[dev->vq->vring.num];
+
+ /* First we need a buffer from the Guests's virtqueue. */
+ head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
+
+ /* If they're not ready for input, stop listening to this file
+ * descriptor. We'll start again once they add an input buffer. */
+ if (head == dev->vq->vring.num)
+ return false;
+
+ if (out_num)
+ errx(1, "Output buffers in rng?");
+
+ /* This is why we convert to iovecs: the readv() call uses them, and so
+ * it reads straight into the Guest's buffer. We loop to make sure we
+ * fill it. */
+ while (!iov_empty(iov, in_num)) {
+ len = readv(dev->fd, iov, in_num);
+ if (len <= 0)
+ err(1, "Read from /dev/random gave %i", len);
+ iov_consume(iov, in_num, len);
+ totlen += len;
+ }
+
+ /* Tell the Guest about the new input. */
+ add_used_and_trigger(fd, dev->vq, head, totlen);
+
+ /* Everything went OK! */
+ return true;
+}
+
+/* And this creates a "hardware" random number device for the Guest. */
+static void setup_rng(void)
+{
+ struct device *dev;
+ int fd;
+
+ fd = open_or_die("/dev/random", O_RDONLY);
+
+ /* The device responds to return from I/O thread. */
+ dev = new_device("rng", VIRTIO_ID_RNG, fd, handle_rng_input);
+
+ /* The device has one virtqueue, where the Guest places inbufs. */
+ add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+
+ verbose("device %u: rng\n", devices.device_num++);
+}
/* That's the end of device setup. */
/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */
@@ -1663,7 +1915,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
/* ERESTART means that we need to reboot the guest */
} else if (errno == ERESTART) {
restart_guest();
- /* EAGAIN means the Waker wanted us to look at some input.
+ /* EAGAIN means a signal (timeout).
* Anything else means a bug or incompatible change. */
} else if (errno != EAGAIN)
err(1, "Running guest failed");
@@ -1691,13 +1943,14 @@ static struct option opts[] = {
{ "verbose", 0, NULL, 'v' },
{ "tunnet", 1, NULL, 't' },
{ "block", 1, NULL, 'b' },
+ { "rng", 0, NULL, 'r' },
{ "initrd", 1, NULL, 'i' },
{ NULL },
};
static void usage(void)
{
errx(1, "Usage: lguest [--verbose] "
- "[--tunnet=(<ipaddr>|bridge:<bridgename>)\n"
+ "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\n"
"|--block=<filename>|--initrd=<filename>]...\n"
"<mem-in-mb> vmlinux [args...]");
}
@@ -1765,6 +2018,9 @@ int main(int argc, char *argv[])
case 'b':
setup_block_file(optarg);
break;
+ case 'r':
+ setup_rng();
+ break;
case 'i':
initrd_name = optarg;
break;
@@ -1783,6 +2039,9 @@ int main(int argc, char *argv[])
/* We always have a console device */
setup_console();
+ /* We can timeout waiting for Guest network transmit. */
+ setup_timeout();
+
/* Now we load the kernel */
start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));