Add support for net bridge

The most common use of -net tap is to connect a tap device to a bridge.  This
requires the use of a script and running qemu as root in order to allocate a
tap device to pass to the script.

This model is great for portability and flexibility but it's incredibly
difficult to eliminate the need to run qemu as root.  The only really viable
mechanism is to use tunctl to create a tap device, attach it to a bridge as
root, and then hand that tap device to qemu.  The problem with this mechanism
is that it requires administrator intervention whenever a user wants to create
a guest.

By essentially writing a helper that implements the most common qemu-ifup
script that can be safely given cap_net_admin, we can dramatically simplify
things for non-privileged users.  We still support existing -net tap options
as a mechanism for advanced users and backwards compatibility.

Currently, this is very Linux centric but there's really no reason why it
couldn't be extended for other Unixes.

A typical invocation would be similar to one of the following:

  qemu linux.img -net bridge -net nic,model=virtio

  qemu linux.img -net tap,helper="/usr/local/libexec/qemu-bridge-helper"
                 -net nic,model=virtio

  qemu linux.img -netdev bridge,id=hn0
                 -device virtio-net-pci,netdev=hn0,id=nic1

  qemu linux.img -netdev tap,helper="/usr/local/libexec/qemu-bridge-helper",id=hn0
                 -device virtio-net-pci,netdev=hn0,id=nic1

The default bridge that we attach to is br0.  The thinking is that a distro
could preconfigure such an interface to allow out-of-the-box bridged networking.

Alternatively, if a user wants to use a different bridge, a typical invocation
would be simliar to one of the following:

  qemu linux.img -net bridge,br=qemubr0 -net nic,model=virtio

  qemu linux.img -net tap,helper="/usr/local/libexec/qemu-bridge-helper --br=qemubr0"
                 -net nic,model=virtio

  qemu linux.img -netdev bridge,br=qemubr0,id=hn0
                 -device virtio-net-pci,netdev=hn0,id=nic1

  qemu linux.img -netdev tap,helper="/usr/local/libexec/qemu-bridge-helper --br=qemubr0",id=hn0
                 -device virtio-net-pci,netdev=hn0,id=nic1

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Richa Marwaha <rmarwah@linux.vnet.ibm.com>
Signed-off-by: Corey Bryant <coreyb@linux.vnet.ibm.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

2 files changed, 204 insertions, 3 deletions

diff --git a/net/tap.c b/net/tap.c
index 6c27a94..f240028 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -382,6 +382,171 @@ static int launch_script(const char *setup_script, const char *ifname, int fd)
     return -1;
 }
 
+static int recv_fd(int c)
+{
+    int fd;
+    uint8_t msgbuf[CMSG_SPACE(sizeof(fd))];
+    struct msghdr msg = {
+        .msg_control = msgbuf,
+        .msg_controllen = sizeof(msgbuf),
+    };
+    struct cmsghdr *cmsg;
+    struct iovec iov;
+    uint8_t req[1];
+    ssize_t len;
+
+    cmsg = CMSG_FIRSTHDR(&msg);
+    cmsg->cmsg_level = SOL_SOCKET;
+    cmsg->cmsg_type = SCM_RIGHTS;
+    cmsg->cmsg_len = CMSG_LEN(sizeof(fd));
+    msg.msg_controllen = cmsg->cmsg_len;
+
+    iov.iov_base = req;
+    iov.iov_len = sizeof(req);
+
+    msg.msg_iov = &iov;
+    msg.msg_iovlen = 1;
+
+    len = recvmsg(c, &msg, 0);
+    if (len > 0) {
+        memcpy(&fd, CMSG_DATA(cmsg), sizeof(fd));
+        return fd;
+    }
+
+    return len;
+}
+
+static int net_bridge_run_helper(const char *helper, const char *bridge)
+{
+    sigset_t oldmask, mask;
+    int pid, status;
+    char *args[5];
+    char **parg;
+    int sv[2];
+
+    sigemptyset(&mask);
+    sigaddset(&mask, SIGCHLD);
+    sigprocmask(SIG_BLOCK, &mask, &oldmask);
+
+    if (socketpair(PF_UNIX, SOCK_STREAM, 0, sv) == -1) {
+        return -1;
+    }
+
+    /* try to launch bridge helper */
+    pid = fork();
+    if (pid == 0) {
+        int open_max = sysconf(_SC_OPEN_MAX), i;
+        char fd_buf[6+10];
+        char br_buf[6+IFNAMSIZ] = {0};
+        char helper_cmd[PATH_MAX + sizeof(fd_buf) + sizeof(br_buf) + 15];
+
+        for (i = 0; i < open_max; i++) {
+            if (i != STDIN_FILENO &&
+                i != STDOUT_FILENO &&
+                i != STDERR_FILENO &&
+                i != sv[1]) {
+                close(i);
+            }
+        }
+
+        snprintf(fd_buf, sizeof(fd_buf), "%s%d", "--fd=", sv[1]);
+
+        if (strrchr(helper, ' ') || strrchr(helper, '\t')) {
+            /* assume helper is a command */
+
+            if (strstr(helper, "--br=") == NULL) {
+                snprintf(br_buf, sizeof(br_buf), "%s%s", "--br=", bridge);
+            }
+
+            snprintf(helper_cmd, sizeof(helper_cmd), "%s %s %s %s",
+                     helper, "--use-vnet", fd_buf, br_buf);
+
+            parg = args;
+            *parg++ = (char *)"sh";
+            *parg++ = (char *)"-c";
+            *parg++ = helper_cmd;
+            *parg++ = NULL;
+
+            execv("/bin/sh", args);
+        } else {
+            /* assume helper is just the executable path name */
+
+            snprintf(br_buf, sizeof(br_buf), "%s%s", "--br=", bridge);
+
+            parg = args;
+            *parg++ = (char *)helper;
+            *parg++ = (char *)"--use-vnet";
+            *parg++ = fd_buf;
+            *parg++ = br_buf;
+            *parg++ = NULL;
+
+            execv(helper, args);
+        }
+        _exit(1);
+
+    } else if (pid > 0) {
+        int fd;
+
+        close(sv[1]);
+
+        do {
+            fd = recv_fd(sv[0]);
+        } while (fd == -1 && errno == EINTR);
+
+        close(sv[0]);
+
+        while (waitpid(pid, &status, 0) != pid) {
+            /* loop */
+        }
+        sigprocmask(SIG_SETMASK, &oldmask, NULL);
+        if (fd < 0) {
+            fprintf(stderr, "failed to recv file descriptor\n");
+            return -1;
+        }
+
+        if (WIFEXITED(status) && WEXITSTATUS(status) == 0) {
+            return fd;
+        }
+    }
+    fprintf(stderr, "failed to launch bridge helper\n");
+    return -1;
+}
+
+int net_init_bridge(QemuOpts *opts, Monitor *mon, const char *name,
+                    VLANState *vlan)
+{
+    TAPState *s;
+    int fd, vnet_hdr;
+
+    if (!qemu_opt_get(opts, "br")) {
+        qemu_opt_set(opts, "br", DEFAULT_BRIDGE_INTERFACE);
+    }
+    if (!qemu_opt_get(opts, "helper")) {
+        qemu_opt_set(opts, "helper", DEFAULT_BRIDGE_HELPER);
+    }
+
+    fd = net_bridge_run_helper(qemu_opt_get(opts, "helper"),
+                               qemu_opt_get(opts, "br"));
+    if (fd == -1) {
+        return -1;
+    }
+
+    fcntl(fd, F_SETFL, O_NONBLOCK);
+
+    vnet_hdr = tap_probe_vnet_hdr(fd);
+
+    s = net_tap_fd_init(vlan, "bridge", name, fd, vnet_hdr);
+    if (!s) {
+        close(fd);
+        return -1;
+    }
+
+    snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s,br=%s",
+             qemu_opt_get(opts, "helper"), qemu_opt_get(opts, "br"));
+
+    return 0;
+}
+
 static int net_tap_init(QemuOpts *opts, int *vnet_hdr)
 {
     int fd, vnet_hdr_required;
@@ -422,13 +587,16 @@ int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan
 {
     TAPState *s;
     int fd, vnet_hdr = 0;
+    const char *model;
 
     if (qemu_opt_get(opts, "fd")) {
         if (qemu_opt_get(opts, "ifname") ||
             qemu_opt_get(opts, "script") ||
             qemu_opt_get(opts, "downscript") ||
-            qemu_opt_get(opts, "vnet_hdr")) {
-            error_report("ifname=, script=, downscript= and vnet_hdr= is invalid with fd=");
+            qemu_opt_get(opts, "vnet_hdr") ||
+            qemu_opt_get(opts, "helper")) {
+            error_report("ifname=, script=, downscript=, vnet_hdr=, "
+                         "and helper= are invalid with fd=");
             return -1;
         }
 
@@ -440,6 +608,31 @@ int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan
         fcntl(fd, F_SETFL, O_NONBLOCK);
 
         vnet_hdr = tap_probe_vnet_hdr(fd);
+
+        model = "tap";
+
+    } else if (qemu_opt_get(opts, "helper")) {
+        if (qemu_opt_get(opts, "ifname") ||
+            qemu_opt_get(opts, "script") ||
+            qemu_opt_get(opts, "downscript") ||
+            qemu_opt_get(opts, "vnet_hdr")) {
+            error_report("ifname=, script=, downscript=, and vnet_hdr= "
+                         "are invalid with helper=");
+            return -1;
+        }
+
+        fd = net_bridge_run_helper(qemu_opt_get(opts, "helper"),
+                                   DEFAULT_BRIDGE_INTERFACE);
+        if (fd == -1) {
+            return -1;
+        }
+
+        fcntl(fd, F_SETFL, O_NONBLOCK);
+
+        vnet_hdr = tap_probe_vnet_hdr(fd);
+
+        model = "bridge";
+
     } else {
         if (!qemu_opt_get(opts, "script")) {
             qemu_opt_set(opts, "script", DEFAULT_NETWORK_SCRIPT);
@@ -453,9 +646,11 @@ int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan
         if (fd == -1) {
             return -1;
         }
+
+        model = "tap";
     }
 
-    s = net_tap_fd_init(vlan, "tap", name, fd, vnet_hdr);
+    s = net_tap_fd_init(vlan, model, name, fd, vnet_hdr);
     if (!s) {
         close(fd);
         return -1;
@@ -467,6 +662,9 @@ int net_init_tap(QemuOpts *opts, Monitor *mon, const char *name, VLANState *vlan
 
     if (qemu_opt_get(opts, "fd")) {
         snprintf(s->nc.info_str, sizeof(s->nc.info_str), "fd=%d", fd);
+    } else if (qemu_opt_get(opts, "helper")) {
+        snprintf(s->nc.info_str, sizeof(s->nc.info_str),
+                 "helper=%s", qemu_opt_get(opts, "helper"));
     } else {
         const char *ifname, *script, *downscript;
 
diff --git a/net/tap.h b/net/tap.h
index e44bd2b..56c591f 100644
--- a/net/tap.h
+++ b/net/tap.h
@@ -57,4 +57,7 @@ int tap_get_fd(VLANClientState *vc);
 struct vhost_net;
 struct vhost_net *tap_get_vhost_net(VLANClientState *vc);
 
+int net_init_bridge(QemuOpts *opts, Monitor *mon, const char *name,
+                    VLANState *vlan);
+
 #endif /* QEMU_NET_TAP_H */