Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
lguest: turn Waker into a thread, not a process
lguest: Enlarge virtio rings
lguest: Use GSO/IFF_VNET_HDR extensions on tun/tap
lguest: Remove 'network: no dma buffer!' warning
lguest: Adaptive timeout
lguest: Tell Guest net not to notify us on every packet xmit
lguest: net block unneeded receive queue update notifications
lguest: wrap last_avail accesses.
lguest: use cpu capability accessors
lguest: virtio-rng support
lguest: Support assigning a MAC address
lguest: Don't leak /dev/zero fd
lguest: fix verbose printing of device features.
lguest: fix switcher_page leak on unload
lguest: Guest int3 fix
lguest: set max_pfn_mapped, growl loudly at Yinghai Lu
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 82fafe0..b88b0ea 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 @@
#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 3 pages: it must be a power of 2. */
+#define VIRTQUEUE_NUM 256
/*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. */
@@ -74,12 +76,19 @@
do { if (verbose) printf(args); } while(0)
/*:*/
-/* The pipe to send commands to the waker process */
-static int waker_fd;
+/* File descriptors for the Waker. */
+struct {
+ int pipe[2];
+ int lguest_fd;
+} waker_fds;
+
/* The pointer to the start of guest memory. */
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];
+static unsigned int timeout_usec = 500;
/* a per-cpu variable indicating whose vcpu is currently running */
static unsigned int __thread cpu_id;
@@ -155,11 +164,14 @@
/* 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);
+ /* The routine to call when the Guest pings us, or timeout. */
+ void (*handle_output)(int fd, struct virtqueue *me, bool timeout);
/* Outstanding buffers */
unsigned int inflight;
+
+ /* Is this blocked awaiting a timer? */
+ bool blocked;
};
/* Remember the arguments to the program so we can "reboot" */
@@ -190,6 +202,9 @@
return iov->iov_base;
}
+/* Wrapper for the last available index. Makes it easier to change. */
+#define lg_last_avail(vq) ((vq)->last_avail_idx)
+
/* The virtio configuration space is defined to be little-endian. x86 is
* little-endian too, but it's nice to be explicit so we have these helpers. */
#define cpu_to_le16(v16) (v16)
@@ -199,6 +214,33 @@
#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 +296,7 @@
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;
}
@@ -540,69 +583,64 @@
* watch, but handing a file descriptor mask through to the kernel is fairly
* icky.
*
- * Instead, we fork off a process which watches the file descriptors and writes
+ * Instead, we clone off a thread which watches the file descriptors and writes
* the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host
* stop running the Guest. This causes the Launcher to return from the
* /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
* the LHREQ_BREAK and wake us up again.
*
* This, of course, is merely a different *kind* of icky.
+ *
+ * Given my well-known antipathy to threads, I'd prefer to use processes. But
+ * it's easier to share Guest memory with threads, and trivial to share the
+ * devices.infds as the Launcher changes it.
*/
-static void wake_parent(int pipefd, int lguest_fd)
+static int waker(void *unused)
{
- /* Add the pipe from the Launcher to the fdset in the device_list, so
- * we watch it, too. */
- add_device_fd(pipefd);
+ /* Close the write end of the pipe: only the Launcher has it open. */
+ close(waker_fds.pipe[1]);
for (;;) {
fd_set rfds = devices.infds;
unsigned long args[] = { LHREQ_BREAK, 1 };
+ unsigned int maxfd = devices.max_infd;
+
+ /* We also listen to the pipe from the Launcher. */
+ FD_SET(waker_fds.pipe[0], &rfds);
+ if (waker_fds.pipe[0] > maxfd)
+ maxfd = waker_fds.pipe[0];
/* Wait until input is ready from one of the devices. */
- select(devices.max_infd+1, &rfds, NULL, NULL, NULL);
- /* Is it a message from the Launcher? */
- if (FD_ISSET(pipefd, &rfds)) {
- int fd;
- /* If read() returns 0, it means the Launcher has
- * exited. We silently follow. */
- if (read(pipefd, &fd, sizeof(fd)) == 0)
- exit(0);
- /* Otherwise it's telling us to change what file
- * descriptors we're to listen to. Positive means
- * listen to a new one, negative means stop
- * listening. */
- if (fd >= 0)
- FD_SET(fd, &devices.infds);
- else
- FD_CLR(-fd - 1, &devices.infds);
- } else /* Send LHREQ_BREAK command. */
- pwrite(lguest_fd, args, sizeof(args), cpu_id);
+ select(maxfd+1, &rfds, NULL, NULL, NULL);
+
+ /* Message from Launcher? */
+ if (FD_ISSET(waker_fds.pipe[0], &rfds)) {
+ char c;
+ /* If this fails, then assume Launcher has exited.
+ * Don't do anything on exit: we're just a thread! */
+ if (read(waker_fds.pipe[0], &c, 1) != 1)
+ _exit(0);
+ continue;
+ }
+
+ /* Send LHREQ_BREAK command to snap the Launcher out of it. */
+ pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id);
}
+ return 0;
}
/* This routine just sets up a pipe to the Waker process. */
-static int setup_waker(int lguest_fd)
+static void setup_waker(int lguest_fd)
{
- int pipefd[2], child;
+ /* This pipe is closed when Launcher dies, telling Waker. */
+ if (pipe(waker_fds.pipe) != 0)
+ err(1, "Creating pipe for Waker");
- /* We create a pipe to talk to the Waker, and also so it knows when the
- * Launcher dies (and closes pipe). */
- pipe(pipefd);
- child = fork();
- if (child == -1)
- err(1, "forking");
+ /* Waker also needs to know the lguest fd */
+ waker_fds.lguest_fd = lguest_fd;
- if (child == 0) {
- /* We are the Waker: close the "writing" end of our copy of the
- * pipe and start waiting for input. */
- close(pipefd[1]);
- wake_parent(pipefd[0], lguest_fd);
- }
- /* Close the reading end of our copy of the pipe. */
- close(pipefd[0]);
-
- /* Here is the fd used to talk to the waker. */
- return pipefd[1];
+ if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1)
+ err(1, "Creating Waker");
}
/*
@@ -661,19 +699,22 @@
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 = lg_last_avail(vq);
+ 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];
+ lg_last_avail(vq)++;
/* If their number is silly, that's a fatal mistake. */
if (head >= vq->vring.num)
@@ -821,8 +862,8 @@
unsigned long args[] = { LHREQ_BREAK, 0 };
/* Close the fd so Waker will know it has to
* exit. */
- close(waker_fd);
- /* Just in case waker is blocked in BREAK, send
+ close(waker_fds.pipe[1]);
+ /* Just in case Waker is blocked in BREAK, send
* unbreak now. */
write(fd, args, sizeof(args));
exit(2);
@@ -839,7 +880,7 @@
/* Handling output for console is simple: we just get all the output buffers
* and write them to stdout. */
-static void handle_console_output(int fd, struct virtqueue *vq)
+static void handle_console_output(int fd, struct virtqueue *vq, bool timeout)
{
unsigned int head, out, in;
int len;
@@ -854,6 +895,21 @@
}
}
+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 = timeout_usec;
+
+ setitimer(ITIMER_REAL, &itm, NULL);
+}
+
/*
* The Network
*
@@ -861,22 +917,34 @@
* and write them (ignoring the first element) to this device's file descriptor
* (/dev/net/tun).
*/
-static void handle_net_output(int fd, struct virtqueue *vq)
+static void handle_net_output(int fd, struct virtqueue *vq, bool timeout)
{
- unsigned int head, out, in;
+ unsigned int head, out, in, num = 0;
int len;
struct iovec iov[vq->vring.num];
+ static int last_timeout_num;
/* 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 (!timeout && num)
+ block_vq(vq);
+
+ if (timeout) {
+ if (num < last_timeout_num)
+ timeout_usec += 10;
+ else if (timeout_usec > 1)
+ timeout_usec--;
+ last_timeout_num = num;
}
}
@@ -887,7 +955,6 @@
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 +963,23 @@
* 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],
@@ -927,11 +992,18 @@
/*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)
+static void enable_fd(int fd, struct virtqueue *vq, bool timeout)
{
add_device_fd(vq->dev->fd);
- /* Tell waker to listen to it again */
- write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+ /* Snap the Waker out of its select loop. */
+ write(waker_fds.pipe[1], "", 1);
+}
+
+static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout)
+{
+ /* We don't need to know again when Guest refills receive buffer. */
+ vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+ enable_fd(fd, vq, timeout);
}
/* When the Guest tells us they updated the status field, we handle it. */
@@ -951,7 +1023,7 @@
for (vq = dev->vq; vq; vq = vq->next) {
memset(vq->vring.desc, 0,
vring_size(vq->config.num, getpagesize()));
- vq->last_avail_idx = 0;
+ lg_last_avail(vq) = 0;
}
} else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
warnx("Device %s configuration FAILED", dev->name);
@@ -960,10 +1032,10 @@
verbose("Device %s OK: offered", dev->name);
for (i = 0; i < dev->desc->feature_len; i++)
- verbose(" %08x", get_feature_bits(dev)[i]);
+ verbose(" %02x", get_feature_bits(dev)[i]);
verbose(", accepted");
for (i = 0; i < dev->desc->feature_len; i++)
- verbose(" %08x", get_feature_bits(dev)
+ verbose(" %02x", get_feature_bits(dev)
[dev->desc->feature_len+i]);
if (dev->ready)
@@ -1000,7 +1072,7 @@
if (strcmp(vq->dev->name, "console") != 0)
verbose("Output to %s\n", vq->dev->name);
if (vq->handle_output)
- vq->handle_output(fd, vq);
+ vq->handle_output(fd, vq, false);
return;
}
}
@@ -1014,6 +1086,29 @@
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, true);
+ }
+ }
+}
+
/* This is called when the Waker wakes us up: check for incoming file
* descriptors. */
static void handle_input(int fd)
@@ -1024,16 +1119,20 @@
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
* 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;
@@ -1043,13 +1142,12 @@
* 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));
}
}
+
+ /* Is this the timeout fd? */
+ if (FD_ISSET(timeoutpipe[0], &fds))
+ handle_timeout(fd);
}
}
@@ -1098,7 +1196,7 @@
/* Each device descriptor is followed by the description of its virtqueues. 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))
+ void (*handle_output)(int, struct virtqueue *, bool))
{
unsigned int pages;
struct virtqueue **i, *vq = malloc(sizeof(*vq));
@@ -1114,6 +1212,7 @@
vq->last_avail_idx = 0;
vq->dev = dev;
vq->inflight = 0;
+ vq->blocked = false;
/* Initialize the configuration. */
vq->config.num = num_descs;
@@ -1246,6 +1345,24 @@
}
/*:*/
+static void timeout_alarm(int sig)
+{
+ 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 +1381,25 @@
static u32 str2ip(const char *ipaddr)
{
- unsigned int byte[4];
+ unsigned int b[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];
+ 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];
+}
+
+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'", macaddr);
+ 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 +1420,7 @@
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 +1429,90 @@
/* 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, TUNSETOFFLOAD,
+ 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 +1523,56 @@
/* 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
@@ -1550,7 +1737,7 @@
}
/* When the Guest submits some I/O, we just need to wake the I/O thread. */
-static void handle_virtblk_output(int fd, struct virtqueue *vq)
+static void handle_virtblk_output(int fd, struct virtqueue *vq, bool timeout)
{
struct vblk_info *vblk = vq->dev->priv;
char c = 0;
@@ -1621,6 +1808,64 @@
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. */
@@ -1628,11 +1873,12 @@
{
unsigned int i;
- /* Closing pipes causes the Waker thread and io_threads to die, and
- * closing /dev/lguest cleans up the Guest. Since we don't track all
- * open fds, we simply close everything beyond stderr. */
+ /* Since we don't track all open fds, we simply close everything beyond
+ * stderr. */
for (i = 3; i < FD_SETSIZE; i++)
close(i);
+
+ /* The exec automatically gets rid of the I/O and Waker threads. */
execv(main_args[0], main_args);
err(1, "Could not exec %s", main_args[0]);
}
@@ -1663,7 +1909,7 @@
/* 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 +1937,14 @@
{ "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 +2012,9 @@
case 'b':
setup_block_file(optarg);
break;
+ case 'r':
+ setup_rng();
+ break;
case 'i':
initrd_name = optarg;
break;
@@ -1783,6 +2033,9 @@
/* 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));
@@ -1826,10 +2079,10 @@
* /dev/lguest file descriptor. */
lguest_fd = tell_kernel(pgdir, start);
- /* We fork off a child process, which wakes the Launcher whenever one
- * of the input file descriptors needs attention. We call this the
- * Waker, and we'll cover it in a moment. */
- waker_fd = setup_waker(lguest_fd);
+ /* We clone off a thread, which wakes the Launcher whenever one of the
+ * input file descriptors needs attention. We call this the Waker, and
+ * we'll cover it in a moment. */
+ setup_waker(lguest_fd);
/* Finally, run the Guest. This doesn't return. */
run_guest(lguest_fd);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 0313a5e..d9249a8 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1014,6 +1014,9 @@
init_pg_tables_start = __pa(pg0);
init_pg_tables_end = __pa(pg0);
+ /* As described in head_32.S, we map the first 128M of memory. */
+ max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;
+
/* Load the %fs segment register (the per-cpu segment register) with
* the normal data segment to get through booting. */
asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory");
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 5eea435..90663e0 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -135,6 +135,7 @@
/* Now we just need to free the pages we copied the switcher into */
for (i = 0; i < TOTAL_SWITCHER_PAGES; i++)
__free_pages(switcher_page[i], 0);
+ kfree(switcher_page);
}
/*H:032
diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c
index 0414ddf..a103906 100644
--- a/drivers/lguest/interrupts_and_traps.c
+++ b/drivers/lguest/interrupts_and_traps.c
@@ -406,7 +406,8 @@
* deliver_trap() to bounce it back into the Guest. */
static void default_idt_entry(struct desc_struct *idt,
int trap,
- const unsigned long handler)
+ const unsigned long handler,
+ const struct desc_struct *base)
{
/* A present interrupt gate. */
u32 flags = 0x8e00;
@@ -415,6 +416,10 @@
* the Guest to use the "int" instruction to trigger it. */
if (trap == LGUEST_TRAP_ENTRY)
flags |= (GUEST_PL << 13);
+ else if (base)
+ /* Copy priv. level from what Guest asked for. This allows
+ * debug (int 3) traps from Guest userspace, for example. */
+ flags |= (base->b & 0x6000);
/* Now pack it into the IDT entry in its weird format. */
idt->a = (LGUEST_CS<<16) | (handler&0x0000FFFF);
@@ -428,7 +433,7 @@
unsigned int i;
for (i = 0; i < ARRAY_SIZE(state->guest_idt); i++)
- default_idt_entry(&state->guest_idt[i], i, def[i]);
+ default_idt_entry(&state->guest_idt[i], i, def[i], NULL);
}
/*H:240 We don't use the IDT entries in the "struct lguest" directly, instead
@@ -442,6 +447,8 @@
/* We can simply copy the direct traps, otherwise we use the default
* ones in the Switcher: they will return to the Host. */
for (i = 0; i < ARRAY_SIZE(cpu->arch.idt); i++) {
+ const struct desc_struct *gidt = &cpu->arch.idt[i];
+
/* If no Guest can ever override this trap, leave it alone. */
if (!direct_trap(i))
continue;
@@ -449,12 +456,15 @@
/* Only trap gates (type 15) can go direct to the Guest.
* Interrupt gates (type 14) disable interrupts as they are
* entered, which we never let the Guest do. Not present
- * entries (type 0x0) also can't go direct, of course. */
- if (idt_type(cpu->arch.idt[i].a, cpu->arch.idt[i].b) == 0xF)
- idt[i] = cpu->arch.idt[i];
+ * entries (type 0x0) also can't go direct, of course.
+ *
+ * If it can't go direct, we still need to copy the priv. level:
+ * they might want to give userspace access to a software
+ * interrupt. */
+ if (idt_type(gidt->a, gidt->b) == 0xF)
+ idt[i] = *gidt;
else
- /* Reset it to the default. */
- default_idt_entry(&idt[i], i, def[i]);
+ default_idt_entry(&idt[i], i, def[i], gidt);
}
}
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 95dfda5..bf79423 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -480,7 +480,7 @@
* bit on its CPU, depending on the argument (0 == unset). */
on_each_cpu(adjust_pge, (void *)0, 1);
/* Turn off the feature in the global feature set. */
- clear_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability);
+ clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
}
put_online_cpus();
};
@@ -491,7 +491,7 @@
/* If we had PGE before we started, turn it back on now. */
get_online_cpus();
if (cpu_had_pge) {
- set_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability);
+ set_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
/* adjust_pge's argument "1" means set PGE. */
on_each_cpu(adjust_pge, (void *)1, 1);
}
