aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorCorey Bryant <coreyb@linux.vnet.ibm.com>2012-01-26 09:42:24 -0500
committerAnthony Liguori <aliguori@us.ibm.com>2012-02-01 16:24:38 -0600
commit7b93fadf3a38d1ed65ea5536a52efc2772c6e3b8 (patch)
tree748cdb705ee503951593ad246f78f4e35211fd6f
parent069ab0eb8a46bc4ff6f4d4d81bf037d3441347da (diff)
downloadqemu-7b93fadf3a38d1ed65ea5536a52efc2772c6e3b8.zip
qemu-7b93fadf3a38d1ed65ea5536a52efc2772c6e3b8.tar.gz
qemu-7b93fadf3a38d1ed65ea5536a52efc2772c6e3b8.tar.bz2
Add basic version of bridge helper
This patch adds a helper that can be used to create a tap device attached to a bridge device. Since this helper is minimal in what it does, it can be given CAP_NET_ADMIN which allows qemu to avoid running as root while still satisfying the majority of what users tend to want to do with tap devices. The way this all works is that qemu launches this helper passing a bridge name and the name of an inherited file descriptor. The descriptor is one end of a socketpair() of domain sockets. This domain socket is used to transmit a file descriptor of the opened tap device from the helper to qemu. The helper can then exit and let qemu use the tap device. 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>
-rw-r--r--Makefile12
-rwxr-xr-xconfigure1
-rw-r--r--qemu-bridge-helper.c221
3 files changed, 232 insertions, 2 deletions
diff --git a/Makefile b/Makefile
index 2560b59..47acf3d 100644
--- a/Makefile
+++ b/Makefile
@@ -36,6 +36,8 @@ $(call set-vpath, $(SRC_PATH):$(SRC_PATH)/hw)
LIBS+=-lz $(LIBS_TOOLS)
+HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)
+
ifdef BUILD_DOCS
DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 QMP/qmp-commands.txt
DOCS+=fsdev/virtfs-proxy-helper.1
@@ -77,7 +79,7 @@ defconfig:
-include config-all-devices.mak
-build-all: $(DOCS) $(TOOLS) recurse-all
+build-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
config-host.h: config-host.h-timestamp
config-host.h-timestamp: config-host.mak
@@ -158,6 +160,8 @@ qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y)
qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y)
qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y)
+qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
+
fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o oslib-posix.o $(trace-obj-y)
fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
@@ -207,7 +211,7 @@ clean:
# avoid old build problems by removing potentially incorrect old files
rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
rm -f qemu-options.def
- rm -f *.o *.d *.a *.lo $(TOOLS) qemu-ga TAGS cscope.* *.pod *~ */*~
+ rm -f *.o *.d *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
rm -Rf .libs
rm -f slirp/*.o slirp/*.d audio/*.o audio/*.d block/*.o block/*.d net/*.o net/*.d fsdev/*.o fsdev/*.d ui/*.o ui/*.d qapi/*.o qapi/*.d qga/*.o qga/*.d
rm -f qemu-img-cmds.h
@@ -281,6 +285,10 @@ install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig
ifneq ($(TOOLS),)
$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
endif
+ifneq ($(HELPERS-y),)
+ $(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
+ $(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
+endif
ifneq ($(BLOBS),)
$(INSTALL_DIR) "$(DESTDIR)$(datadir)"
set -e; for x in $(BLOBS); do \
diff --git a/configure b/configure
index 3b0b300..b7e5ca6 100755
--- a/configure
+++ b/configure
@@ -2910,6 +2910,7 @@ echo "datadir=$datadir" >> $config_host_mak
echo "sysconfdir=$sysconfdir" >> $config_host_mak
echo "docdir=$docdir" >> $config_host_mak
echo "confdir=$confdir" >> $config_host_mak
+echo "libexecdir=\${prefix}/libexec" >> $config_host_mak
echo "ARCH=$ARCH" >> $config_host_mak
if test "$debug_tcg" = "yes" ; then
diff --git a/qemu-bridge-helper.c b/qemu-bridge-helper.c
new file mode 100644
index 0000000..48c5e22
--- /dev/null
+++ b/qemu-bridge-helper.c
@@ -0,0 +1,221 @@
+/*
+ * QEMU Bridge Helper
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ * Richa Marwaha <rmarwah@linux.vnet.ibm.com>
+ * Corey Bryant <coreyb@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "config-host.h"
+
+#include <stdio.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <ctype.h>
+
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/prctl.h>
+
+#include <net/if.h>
+
+#include <linux/sockios.h>
+
+#include "net/tap-linux.h"
+
+static void usage(void)
+{
+ fprintf(stderr,
+ "Usage: qemu-bridge-helper [--use-vnet] --br=bridge --fd=unixfd\n");
+}
+
+static bool has_vnet_hdr(int fd)
+{
+ unsigned int features = 0;
+
+ if (ioctl(fd, TUNGETFEATURES, &features) == -1) {
+ return false;
+ }
+
+ if (!(features & IFF_VNET_HDR)) {
+ return false;
+ }
+
+ return true;
+}
+
+static void prep_ifreq(struct ifreq *ifr, const char *ifname)
+{
+ memset(ifr, 0, sizeof(*ifr));
+ snprintf(ifr->ifr_name, IFNAMSIZ, "%s", ifname);
+}
+
+static int send_fd(int c, int fd)
+{
+ char msgbuf[CMSG_SPACE(sizeof(fd))];
+ struct msghdr msg = {
+ .msg_control = msgbuf,
+ .msg_controllen = sizeof(msgbuf),
+ };
+ struct cmsghdr *cmsg;
+ struct iovec iov;
+ char req[1] = { 0x00 };
+
+ 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;
+ memcpy(CMSG_DATA(cmsg), &fd, sizeof(fd));
+
+ return sendmsg(c, &msg, 0);
+}
+
+int main(int argc, char **argv)
+{
+ struct ifreq ifr;
+ int fd, ctlfd, unixfd = -1;
+ int use_vnet = 0;
+ int mtu;
+ const char *bridge = NULL;
+ char iface[IFNAMSIZ];
+ int index;
+ int ret = EXIT_SUCCESS;
+
+ /* parse arguments */
+ for (index = 1; index < argc; index++) {
+ if (strcmp(argv[index], "--use-vnet") == 0) {
+ use_vnet = 1;
+ } else if (strncmp(argv[index], "--br=", 5) == 0) {
+ bridge = &argv[index][5];
+ } else if (strncmp(argv[index], "--fd=", 5) == 0) {
+ unixfd = atoi(&argv[index][5]);
+ } else {
+ usage();
+ return EXIT_FAILURE;
+ }
+ }
+
+ if (bridge == NULL || unixfd == -1) {
+ usage();
+ return EXIT_FAILURE;
+ }
+
+ /* open a socket to use to control the network interfaces */
+ ctlfd = socket(AF_INET, SOCK_STREAM, 0);
+ if (ctlfd == -1) {
+ fprintf(stderr, "failed to open control socket: %s\n", strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* open the tap device */
+ fd = open("/dev/net/tun", O_RDWR);
+ if (fd == -1) {
+ fprintf(stderr, "failed to open /dev/net/tun: %s\n", strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* request a tap device, disable PI, and add vnet header support if
+ * requested and it's available. */
+ prep_ifreq(&ifr, "tap%d");
+ ifr.ifr_flags = IFF_TAP|IFF_NO_PI;
+ if (use_vnet && has_vnet_hdr(fd)) {
+ ifr.ifr_flags |= IFF_VNET_HDR;
+ }
+
+ if (ioctl(fd, TUNSETIFF, &ifr) == -1) {
+ fprintf(stderr, "failed to create tun device: %s\n", strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* save tap device name */
+ snprintf(iface, sizeof(iface), "%s", ifr.ifr_name);
+
+ /* get the mtu of the bridge */
+ prep_ifreq(&ifr, bridge);
+ if (ioctl(ctlfd, SIOCGIFMTU, &ifr) == -1) {
+ fprintf(stderr, "failed to get mtu of bridge `%s': %s\n",
+ bridge, strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* save mtu */
+ mtu = ifr.ifr_mtu;
+
+ /* set the mtu of the interface based on the bridge */
+ prep_ifreq(&ifr, iface);
+ ifr.ifr_mtu = mtu;
+ if (ioctl(ctlfd, SIOCSIFMTU, &ifr) == -1) {
+ fprintf(stderr, "failed to set mtu of device `%s' to %d: %s\n",
+ iface, mtu, strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* add the interface to the bridge */
+ prep_ifreq(&ifr, bridge);
+ ifr.ifr_ifindex = if_nametoindex(iface);
+
+ if (ioctl(ctlfd, SIOCBRADDIF, &ifr) == -1) {
+ fprintf(stderr, "failed to add interface `%s' to bridge `%s': %s\n",
+ iface, bridge, strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* bring the interface up */
+ prep_ifreq(&ifr, iface);
+ if (ioctl(ctlfd, SIOCGIFFLAGS, &ifr) == -1) {
+ fprintf(stderr, "failed to get interface flags for `%s': %s\n",
+ iface, strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ ifr.ifr_flags |= IFF_UP;
+ if (ioctl(ctlfd, SIOCSIFFLAGS, &ifr) == -1) {
+ fprintf(stderr, "failed to bring up interface `%s': %s\n",
+ iface, strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* write fd to the domain socket */
+ if (send_fd(unixfd, fd) == -1) {
+ fprintf(stderr, "failed to write fd to unix socket: %s\n",
+ strerror(errno));
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* ... */
+
+ /* profit! */
+
+cleanup:
+
+ return ret;
+}