* [Qemu-devel] [PATCH v7 1/4] Add basic version of bridge helper
2012-01-04 17:18 [Qemu-devel] [PATCH v7 0/4] -net bridge: rootless bridge support for qemu Corey Bryant
@ 2012-01-04 17:18 ` Corey Bryant
2012-01-04 17:18 ` [Qemu-devel] [PATCH v7 2/4] Add access control support to qemu " Corey Bryant
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Corey Bryant @ 2012-01-04 17:18 UTC (permalink / raw)
To: qemu-devel; +Cc: aliguori, rmarwah
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>
---
Makefile | 12 +++-
configure | 1 +
qemu-bridge-helper.c | 221 ++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 232 insertions(+), 2 deletions(-)
create mode 100644 qemu-bridge-helper.c
diff --git a/Makefile b/Makefile
index 0838bc4..78824f9 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
else
@@ -76,7 +78,7 @@ defconfig:
-include config-all-devices.mak
-build-all: $(DOCS) $(TOOLS) $(CHECKS) recurse-all
+build-all: $(DOCS) $(TOOLS) $(CHECKS) $(HELPERS-y) recurse-all
config-host.h: config-host.h-timestamp
config-host.h-timestamp: config-host.mak
@@ -155,6 +157,8 @@ qemu-img$(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
+
qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@," GEN $@")
@@ -227,7 +231,7 @@ 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) $(CHECKS) qemu-ga TAGS cscope.* *.pod *~ */*~
+ rm -f *.o *.d *.a *.lo $(TOOLS) $(CHECKS) $(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
@@ -296,6 +300,10 @@ 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 $(BLOBS); do \
diff --git a/configure b/configure
index 640e815..71774f4 100755
--- a/configure
+++ b/configure
@@ -2902,6 +2902,7 @@ echo "datadir=$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" >> $config_host_mak
case "$cpu" in
i386|x86_64|alpha|arm|cris|hppa|ia64|lm32|m68k|microblaze|mips|mips64|ppc|ppc64|s390|s390x|sparc|sparc64|unicore32)
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;
+}
--
1.7.3.4
^ permalink raw reply related [flat|nested] 6+ messages in thread* [Qemu-devel] [PATCH v7 2/4] Add access control support to qemu bridge helper
2012-01-04 17:18 [Qemu-devel] [PATCH v7 0/4] -net bridge: rootless bridge support for qemu Corey Bryant
2012-01-04 17:18 ` [Qemu-devel] [PATCH v7 1/4] Add basic version of bridge helper Corey Bryant
@ 2012-01-04 17:18 ` Corey Bryant
2012-01-04 17:19 ` [Qemu-devel] [PATCH v7 3/4] Add cap reduction support to enable use as SUID Corey Bryant
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Corey Bryant @ 2012-01-04 17:18 UTC (permalink / raw)
To: qemu-devel; +Cc: aliguori, rmarwah
We go to great lengths to restrict ourselves to just cap_net_admin as an OS
enforced security mechanism. However, we further restrict what we allow users
to do to simply adding a tap device to a bridge interface by virtue of the fact
that this is the only functionality we expose.
This is not good enough though. An administrator is likely to want to restrict
the bridges that an unprivileged user can access, in particular, to restrict
an unprivileged user from putting a guest on what should be isolated networks.
This patch implements an ACL mechanism that is enforced by qemu-bridge-helper.
The ACLs are fairly simple whitelist/blacklist mechanisms with a wildcard of
'all'. All users are blacklisted by default, and deny takes precedence over
allow.
An interesting feature of this ACL mechanism is that you can include external
ACL files. The main reason to support this is so that you can set different
file system permissions on those external ACL files. This allows an
administrator to implement rather sophisticated ACL policies based on
user/group policies via the file system.
As an example:
/etc/qemu/bridge.conf root:qemu 0640
allow br0
include /etc/qemu/alice.conf
include /etc/qemu/bob.conf
include /etc/qemu/charlie.conf
/etc/qemu/alice.conf root:alice 0640
allow br1
/etc/qemu/bob.conf root:bob 0640
allow br2
/etc/qemu/charlie.conf root:charlie 0640
deny all
This ACL pattern allows any user in the qemu group to get a tap device
connected to br0 (which is bridged to the physical network).
Users in the alice group can additionally get a tap device connected to br1.
This allows br1 to act as a private bridge for the alice group.
Users in the bob group can additionally get a tap device connected to br2.
This allows br2 to act as a private bridge for the bob group.
Users in the charlie group cannot get a tap device connected to any bridge.
Under no circumstance can the bob group get access to br1 or can the alice
group get access to br2. And under no cicumstance can the charlie group
get access to any bridge.
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>
---
qemu-bridge-helper.c | 153 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 153 insertions(+), 0 deletions(-)
diff --git a/qemu-bridge-helper.c b/qemu-bridge-helper.c
index 48c5e22..01eeb38 100644
--- a/qemu-bridge-helper.c
+++ b/qemu-bridge-helper.c
@@ -23,6 +23,7 @@
#include <stdlib.h>
#include <stdbool.h>
#include <ctype.h>
+#include <glib.h>
#include <sys/types.h>
#include <sys/ioctl.h>
@@ -34,14 +35,116 @@
#include <linux/sockios.h>
+#include "qemu-queue.h"
+
#include "net/tap-linux.h"
+#define DEFAULT_ACL_FILE CONFIG_QEMU_CONFDIR "/bridge.conf"
+
+enum {
+ ACL_ALLOW = 0,
+ ACL_ALLOW_ALL,
+ ACL_DENY,
+ ACL_DENY_ALL,
+};
+
+typedef struct ACLRule {
+ int type;
+ char iface[IFNAMSIZ];
+ QSIMPLEQ_ENTRY(ACLRule) entry;
+} ACLRule;
+
+typedef QSIMPLEQ_HEAD(ACLList, ACLRule) ACLList;
+
static void usage(void)
{
fprintf(stderr,
"Usage: qemu-bridge-helper [--use-vnet] --br=bridge --fd=unixfd\n");
}
+static int parse_acl_file(const char *filename, ACLList *acl_list)
+{
+ FILE *f;
+ char line[4096];
+ ACLRule *acl_rule;
+
+ f = fopen(filename, "r");
+ if (f == NULL) {
+ return -1;
+ }
+
+ while (fgets(line, sizeof(line), f) != NULL) {
+ char *ptr = line;
+ char *cmd, *arg, *argend;
+
+ while (isspace(*ptr)) {
+ ptr++;
+ }
+
+ /* skip comments and empty lines */
+ if (*ptr == '#' || *ptr == 0) {
+ continue;
+ }
+
+ cmd = ptr;
+ arg = strchr(cmd, ' ');
+ if (arg == NULL) {
+ arg = strchr(cmd, '\t');
+ }
+
+ if (arg == NULL) {
+ fprintf(stderr, "Invalid config line:\n %s\n", line);
+ fclose(f);
+ errno = EINVAL;
+ return -1;
+ }
+
+ *arg = 0;
+ arg++;
+ while (isspace(*arg)) {
+ arg++;
+ }
+
+ argend = arg + strlen(arg);
+ while (arg != argend && isspace(*(argend - 1))) {
+ argend--;
+ }
+ *argend = 0;
+
+ if (strcmp(cmd, "deny") == 0) {
+ acl_rule = g_malloc(sizeof(*acl_rule));
+ if (strcmp(arg, "all") == 0) {
+ acl_rule->type = ACL_DENY_ALL;
+ } else {
+ acl_rule->type = ACL_DENY;
+ snprintf(acl_rule->iface, IFNAMSIZ, "%s", arg);
+ }
+ QSIMPLEQ_INSERT_TAIL(acl_list, acl_rule, entry);
+ } else if (strcmp(cmd, "allow") == 0) {
+ acl_rule = g_malloc(sizeof(*acl_rule));
+ if (strcmp(arg, "all") == 0) {
+ acl_rule->type = ACL_ALLOW_ALL;
+ } else {
+ acl_rule->type = ACL_ALLOW;
+ snprintf(acl_rule->iface, IFNAMSIZ, "%s", arg);
+ }
+ QSIMPLEQ_INSERT_TAIL(acl_list, acl_rule, entry);
+ } else if (strcmp(cmd, "include") == 0) {
+ /* ignore errors */
+ parse_acl_file(arg, acl_list);
+ } else {
+ fprintf(stderr, "Unknown command `%s'\n", cmd);
+ fclose(f);
+ errno = EINVAL;
+ return -1;
+ }
+ }
+
+ fclose(f);
+
+ return 0;
+}
+
static bool has_vnet_hdr(int fd)
{
unsigned int features = 0;
@@ -99,6 +202,9 @@ int main(int argc, char **argv)
const char *bridge = NULL;
char iface[IFNAMSIZ];
int index;
+ ACLRule *acl_rule;
+ ACLList acl_list;
+ int access_allowed, access_denied;
int ret = EXIT_SUCCESS;
/* parse arguments */
@@ -120,6 +226,48 @@ int main(int argc, char **argv)
return EXIT_FAILURE;
}
+ /* parse default acl file */
+ QSIMPLEQ_INIT(&acl_list);
+ if (parse_acl_file(DEFAULT_ACL_FILE, &acl_list) == -1) {
+ fprintf(stderr, "failed to parse default acl file `%s'\n",
+ DEFAULT_ACL_FILE);
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
+ /* validate bridge against acl -- default policy is to deny
+ * according acl policy if we have a deny and allow both
+ * then deny should always win over allow
+ */
+ access_allowed = 0;
+ access_denied = 0;
+ QSIMPLEQ_FOREACH(acl_rule, &acl_list, entry) {
+ switch (acl_rule->type) {
+ case ACL_ALLOW_ALL:
+ access_allowed = 1;
+ break;
+ case ACL_ALLOW:
+ if (strcmp(bridge, acl_rule->iface) == 0) {
+ access_allowed = 1;
+ }
+ break;
+ case ACL_DENY_ALL:
+ access_denied = 1;
+ break;
+ case ACL_DENY:
+ if (strcmp(bridge, acl_rule->iface) == 0) {
+ access_denied = 1;
+ }
+ break;
+ }
+ }
+
+ if ((access_allowed == 0) || (access_denied == 1)) {
+ fprintf(stderr, "access denied by acl file\n");
+ ret = EXIT_FAILURE;
+ goto cleanup;
+ }
+
/* open a socket to use to control the network interfaces */
ctlfd = socket(AF_INET, SOCK_STREAM, 0);
if (ctlfd == -1) {
@@ -217,5 +365,10 @@ int main(int argc, char **argv)
cleanup:
+ while ((acl_rule = QSIMPLEQ_FIRST(&acl_list)) != NULL) {
+ QSIMPLEQ_REMOVE_HEAD(&acl_list, entry);
+ g_free(acl_rule);
+ }
+
return ret;
}
--
1.7.3.4
^ permalink raw reply related [flat|nested] 6+ messages in thread* [Qemu-devel] [PATCH v7 4/4] Add support for net bridge
2012-01-04 17:18 [Qemu-devel] [PATCH v7 0/4] -net bridge: rootless bridge support for qemu Corey Bryant
` (2 preceding siblings ...)
2012-01-04 17:19 ` [Qemu-devel] [PATCH v7 3/4] Add cap reduction support to enable use as SUID Corey Bryant
@ 2012-01-04 17:19 ` Corey Bryant
2012-01-04 17:49 ` [Qemu-devel] [PATCH v7 0/4] -net bridge: rootless bridge support for qemu Lutz Vieweg
4 siblings, 0 replies; 6+ messages in thread
From: Corey Bryant @ 2012-01-04 17:19 UTC (permalink / raw)
To: qemu-devel; +Cc: aliguori, rmarwah
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>
---
configure | 2 +
net.c | 25 +++++++-
net.h | 3 +
net/tap.c | 204 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
net/tap.h | 3 +
qemu-options.hx | 73 ++++++++++++++++----
6 files changed, 293 insertions(+), 17 deletions(-)
diff --git a/configure b/configure
index 3357fa6..bca27d0 100755
--- a/configure
+++ b/configure
@@ -2934,6 +2934,8 @@ echo "sysconfdir=$sysconfdir" >> $config_host_mak
echo "docdir=$docdir" >> $config_host_mak
echo "confdir=$confdir" >> $config_host_mak
echo "libexecdir=\${prefix}/libexec" >> $config_host_mak
+echo "CONFIG_QEMU_SHAREDIR=\"$prefix$datasuffix\"" >> $config_host_mak
+echo "CONFIG_QEMU_HELPERDIR=\"$prefix/libexec\"" >> $config_host_mak
case "$cpu" in
i386|x86_64|alpha|arm|cris|hppa|ia64|lm32|m68k|microblaze|mips|mips64|ppc|ppc64|s390|s390x|sparc|sparc64|unicore32)
diff --git a/net.c b/net.c
index f7bebf8..b42d405 100644
--- a/net.c
+++ b/net.c
@@ -952,6 +952,10 @@ static const struct {
.type = QEMU_OPT_STRING,
.help = "script to shut down the interface",
}, {
+ .name = "helper",
+ .type = QEMU_OPT_STRING,
+ .help = "command to execute to configure bridge",
+ }, {
.name = "sndbuf",
.type = QEMU_OPT_SIZE,
.help = "send buffer limit"
@@ -1049,6 +1053,23 @@ static const struct {
{ /* end of list */ }
},
},
+ [NET_CLIENT_TYPE_BRIDGE] = {
+ .type = "bridge",
+ .init = net_init_bridge,
+ .desc = {
+ NET_COMMON_PARAMS_DESC,
+ {
+ .name = "br",
+ .type = QEMU_OPT_STRING,
+ .help = "bridge name",
+ }, {
+ .name = "helper",
+ .type = QEMU_OPT_STRING,
+ .help = "command to execute to configure bridge",
+ },
+ { /* end of list */ }
+ },
+ },
};
int net_client_init(Monitor *mon, QemuOpts *opts, int is_netdev)
@@ -1071,7 +1092,8 @@ int net_client_init(Monitor *mon, QemuOpts *opts, int is_netdev)
#ifdef CONFIG_VDE
strcmp(type, "vde") != 0 &&
#endif
- strcmp(type, "socket") != 0) {
+ strcmp(type, "socket") != 0 &&
+ strcmp(type, "bridge") != 0) {
qerror_report(QERR_INVALID_PARAMETER_VALUE, "type",
"a netdev backend type");
return -1;
@@ -1141,6 +1163,7 @@ static int net_host_check_device(const char *device)
#ifdef CONFIG_VDE
,"vde"
#endif
+ , "bridge"
};
for (i = 0; i < sizeof(valid_param_list) / sizeof(char *); i++) {
if (!strncmp(valid_param_list[i], device,
diff --git a/net.h b/net.h
index c6b4190..0fd7e23 100644
--- a/net.h
+++ b/net.h
@@ -36,6 +36,7 @@ typedef enum {
NET_CLIENT_TYPE_SOCKET,
NET_CLIENT_TYPE_VDE,
NET_CLIENT_TYPE_DUMP,
+ NET_CLIENT_TYPE_BRIDGE,
NET_CLIENT_TYPE_MAX
} net_client_type;
@@ -173,6 +174,8 @@ int do_netdev_del(Monitor *mon, const QDict *qdict, QObject **ret_data);
#define DEFAULT_NETWORK_SCRIPT "/etc/qemu-ifup"
#define DEFAULT_NETWORK_DOWN_SCRIPT "/etc/qemu-ifdown"
+#define DEFAULT_BRIDGE_HELPER CONFIG_QEMU_HELPERDIR "/qemu-bridge-helper"
+#define DEFAULT_BRIDGE_INTERFACE "br0"
void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd);
diff --git a/net/tap.c b/net/tap.c
index 6c27a94..9d82470 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 */
diff --git a/qemu-options.hx b/qemu-options.hx
index a60191f..b0faf9e 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -1205,11 +1205,14 @@ DEF("net", HAS_ARG, QEMU_OPTION_net,
"-net tap[,vlan=n][,name=str],ifname=name\n"
" connect the host TAP network interface to VLAN 'n'\n"
#else
- "-net tap[,vlan=n][,name=str][,fd=h][,ifname=name][,script=file][,downscript=dfile][,sndbuf=nbytes][,vnet_hdr=on|off][,vhost=on|off][,vhostfd=h][,vhostforce=on|off]\n"
- " connect the host TAP network interface to VLAN 'n' and use the\n"
- " network scripts 'file' (default=" DEFAULT_NETWORK_SCRIPT ")\n"
- " and 'dfile' (default=" DEFAULT_NETWORK_DOWN_SCRIPT ")\n"
+ "-net tap[,vlan=n][,name=str][,fd=h][,ifname=name][,script=file][,downscript=dfile][,helper=helper][,sndbuf=nbytes][,vnet_hdr=on|off][,vhost=on|off][,vhostfd=h][,vhostforce=on|off]\n"
+ " connect the host TAP network interface to VLAN 'n' \n"
+ " use network scripts 'file' (default=" DEFAULT_NETWORK_SCRIPT ")\n"
+ " to configure it and 'dfile' (default=" DEFAULT_NETWORK_DOWN_SCRIPT ")\n"
+ " to deconfigure it\n"
" use '[down]script=no' to disable script execution\n"
+ " use network helper 'helper' (default=" DEFAULT_BRIDGE_HELPER ") to\n"
+ " configure it\n"
" use 'fd=h' to connect to an already opened TAP interface\n"
" use 'sndbuf=nbytes' to limit the size of the send buffer (the\n"
" default is disabled 'sndbuf=0' to enable flow control set 'sndbuf=1048576')\n"
@@ -1219,6 +1222,10 @@ DEF("net", HAS_ARG, QEMU_OPTION_net,
" (only has effect for virtio guests which use MSIX)\n"
" use vhostforce=on to force vhost on for non-MSIX virtio guests\n"
" use 'vhostfd=h' to connect to an already opened vhost net device\n"
+ "-net bridge[,vlan=n][,name=str][,br=bridge][,helper=helper]\n"
+ " connects a host TAP network interface to a host bridge device 'br'\n"
+ " (default=" DEFAULT_BRIDGE_INTERFACE ") using the program 'helper'\n"
+ " (default=" DEFAULT_BRIDGE_HELPER ")\n"
#endif
"-net socket[,vlan=n][,name=str][,fd=h][,listen=[host]:port][,connect=host:port]\n"
" connect the vlan 'n' to another VLAN using a socket connection\n"
@@ -1242,6 +1249,7 @@ DEF("netdev", HAS_ARG, QEMU_OPTION_netdev,
"user|"
#endif
"tap|"
+ "bridge|"
#ifdef CONFIG_VDE
"vde|"
#endif
@@ -1378,26 +1386,65 @@ processed and applied to -net user. Mixing them with the new configuration
syntax gives undefined results. Their use for new applications is discouraged
as they will be removed from future versions.
-@item -net tap[,vlan=@var{n}][,name=@var{name}][,fd=@var{h}][,ifname=@var{name}] [,script=@var{file}][,downscript=@var{dfile}]
-Connect the host TAP network interface @var{name} to VLAN @var{n}, use
-the network script @var{file} to configure it and the network script
+@item -net tap[,vlan=@var{n}][,name=@var{name}][,fd=@var{h}][,ifname=@var{name}][,script=@var{file}][,downscript=@var{dfile}][,helper=@var{helper}]
+Connect the host TAP network interface @var{name} to VLAN @var{n}.
+
+Use the network script @var{file} to configure it and the network script
@var{dfile} to deconfigure it. If @var{name} is not provided, the OS
-automatically provides one. @option{fd}=@var{h} can be used to specify
-the handle of an already opened host TAP interface. The default network
-configure script is @file{/etc/qemu-ifup} and the default network
-deconfigure script is @file{/etc/qemu-ifdown}. Use @option{script=no}
-or @option{downscript=no} to disable script execution. Example:
+automatically provides one. The default network configure script is
+@file{/etc/qemu-ifup} and the default network deconfigure script is
+@file{/etc/qemu-ifdown}. Use @option{script=no} or @option{downscript=no}
+to disable script execution.
+
+If running QEMU as an unprivileged user, use the network helper
+@var{helper} to configure the TAP interface. The default network
+helper executable is @file{/usr/local/libexec/qemu-bridge-helper}.
+
+@option{fd}=@var{h} can be used to specify the handle of an already
+opened host TAP interface.
+
+Examples:
@example
+#launch a QEMU instance with the default network script
qemu linux.img -net nic -net tap
@end example
-More complicated example (two NICs, each one connected to a TAP device)
@example
+#launch a QEMU instance with two NICs, each one connected
+#to a TAP device
qemu linux.img -net nic,vlan=0 -net tap,vlan=0,ifname=tap0 \
-net nic,vlan=1 -net tap,vlan=1,ifname=tap1
@end example
+@example
+#launch a QEMU instance with the default network helper to
+#connect a TAP device to bridge br0
+qemu linux.img -net nic -net tap,"helper=/usr/local/libexec/qemu-bridge-helper"
+@end example
+
+@item -net bridge[,vlan=@var{n}][,name=@var{name}][,br=@var{bridge}][,helper=@var{helper}]
+Connect a host TAP network interface to a host bridge device.
+
+Use the network helper @var{helper} to configure the TAP interface and
+attach it to the bridge. The default network helper executable is
+@file{/usr/local/libexec/qemu-bridge-helper} and the default bridge
+device is @file{br0}.
+
+Examples:
+
+@example
+#launch a QEMU instance with the default network helper to
+#connect a TAP device to bridge br0
+qemu linux.img -net bridge -net nic,model=virtio
+@end example
+
+@example
+#launch a QEMU instance with the default network helper to
+#connect a TAP device to bridge qemubr0
+qemu linux.img -net bridge,br=qemubr0 -net nic,model=virtio
+@end example
+
@item -net socket[,vlan=@var{n}][,name=@var{name}][,fd=@var{h}] [,listen=[@var{host}]:@var{port}][,connect=@var{host}:@var{port}]
Connect the VLAN @var{n} to a remote VLAN in another QEMU virtual
--
1.7.3.4
^ permalink raw reply related [flat|nested] 6+ messages in thread