/**
* virNetDevIPAddrDel:
* @ifname: the interface name
* @addr: the IP address (IPv4 or IPv6)
* @prefix: number of 1 bits in the netmask
*
* Delete an IP address from an interface.
*
* Returns 0 in case of success or -1 in case of error.
*/
int
virNetDevIPAddrDel(const char *ifname,
virSocketAddr *addr,
unsigned int prefix)
{
int ret = -1;
struct nl_msg *nlmsg = NULL;
struct nlmsghdr *resp = NULL;
unsigned int recvbuflen;
if (!(nlmsg = virNetDevCreateNetlinkAddressMessage(RTM_DELADDR, ifname,
addr, prefix,
NULL, NULL)))
goto cleanup;
if (virNetlinkCommand(nlmsg, &resp, &recvbuflen, 0, 0,
NETLINK_ROUTE, 0) < 0)
goto cleanup;
if (virNetlinkGetErrorCode(resp, recvbuflen) < 0) {
virReportError(VIR_ERR_SYSTEM_ERROR,
_("Error removing IP address from %s"), ifname);
goto cleanup;
}
ret = 0;
cleanup:
nlmsg_free(nlmsg);
VIR_FREE(resp);
return ret;
}
/* return after DAD finishes for all known IPv6 addresses or an error */
int
virNetDevIPWaitDadFinish(virSocketAddrPtr *addrs, size_t count)
{
struct nl_msg *nlmsg = NULL;
struct ifaddrmsg ifa;
struct nlmsghdr *resp = NULL;
unsigned int recvbuflen;
int ret = -1;
bool dad = true;
time_t max_time = time(NULL) + VIR_DAD_WAIT_TIMEOUT;
if (!(nlmsg = nlmsg_alloc_simple(RTM_GETADDR,
NLM_F_REQUEST | NLM_F_DUMP))) {
virReportOOMError();
return -1;
}
memset(&ifa, 0, sizeof(ifa));
/* DAD is for IPv6 adresses only. */
ifa.ifa_family = AF_INET6;
if (nlmsg_append(nlmsg, &ifa, sizeof(ifa), NLMSG_ALIGNTO) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("allocated netlink buffer is too small"));
goto cleanup;
}
/* Periodically query netlink until DAD finishes on all known addresses. */
while (dad && time(NULL) < max_time) {
if (virNetlinkCommand(nlmsg, &resp, &recvbuflen, 0, 0,
NETLINK_ROUTE, 0) < 0)
goto cleanup;
if (virNetlinkGetErrorCode(resp, recvbuflen) < 0) {
virReportError(VIR_ERR_SYSTEM_ERROR, "%s",
_("error reading DAD state information"));
goto cleanup;
}
/* Parse response. */
dad = virNetDevIPParseDadStatus(resp, recvbuflen, addrs, count);
if (dad)
usleep(1000 * 10);
VIR_FREE(resp);
}
/* Check timeout. */
if (dad) {
virReportError(VIR_ERR_SYSTEM_ERROR,
_("Duplicate Address Detection "
"not finished in %d seconds"), VIR_DAD_WAIT_TIMEOUT);
} else {
ret = 0;
}
cleanup:
VIR_FREE(resp);
nlmsg_free(nlmsg);
return ret;
}
/**
* virNetDevMacVLanCreate:
*
* @ifname: The name the interface is supposed to have; optional parameter
* @type: The type of device, i.e., "macvtap", "macvlan"
* @macaddress: The MAC address of the device
* @srcdev: The name of the 'link' device
* @macvlan_mode: The macvlan mode to use
* @retry: Pointer to integer that will be '1' upon return if an interface
* with the same name already exists and it is worth to try
* again with a different name
*
* Create a macvtap device with the given properties.
*
* Returns 0 on success, -1 on fatal error.
*/
int
virNetDevMacVLanCreate(const char *ifname,
const char *type,
const unsigned char *macaddress,
const char *srcdev,
uint32_t macvlan_mode,
int *retry)
{
int rc = -1;
struct nlmsghdr *resp;
struct nlmsgerr *err;
struct ifinfomsg ifinfo = { .ifi_family = AF_UNSPEC };
int ifindex;
unsigned char *recvbuf = NULL;
unsigned int recvbuflen;
struct nl_msg *nl_msg;
struct nlattr *linkinfo, *info_data;
if (virNetDevGetIndex(srcdev, &ifindex) < 0)
return -1;
*retry = 0;
nl_msg = nlmsg_alloc_simple(RTM_NEWLINK,
NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL);
if (!nl_msg) {
virReportOOMError();
return -1;
}
if (nlmsg_append(nl_msg, &ifinfo, sizeof(ifinfo), NLMSG_ALIGNTO) < 0)
goto buffer_too_small;
if (nla_put_u32(nl_msg, IFLA_LINK, ifindex) < 0)
goto buffer_too_small;
if (nla_put(nl_msg, IFLA_ADDRESS, VIR_MAC_BUFLEN, macaddress) < 0)
goto buffer_too_small;
if (ifname &&
nla_put(nl_msg, IFLA_IFNAME, strlen(ifname)+1, ifname) < 0)
goto buffer_too_small;
if (!(linkinfo = nla_nest_start(nl_msg, IFLA_LINKINFO)))
goto buffer_too_small;
if (nla_put(nl_msg, IFLA_INFO_KIND, strlen(type), type) < 0)
goto buffer_too_small;
if (macvlan_mode > 0) {
if (!(info_data = nla_nest_start(nl_msg, IFLA_INFO_DATA)))
goto buffer_too_small;
if (nla_put(nl_msg, IFLA_MACVLAN_MODE, sizeof(macvlan_mode),
&macvlan_mode) < 0)
goto buffer_too_small;
nla_nest_end(nl_msg, info_data);
}
nla_nest_end(nl_msg, linkinfo);
if (virNetlinkCommand(nl_msg, &recvbuf, &recvbuflen, 0) < 0) {
goto cleanup;
}
if (recvbuflen < NLMSG_LENGTH(0) || recvbuf == NULL)
goto malformed_resp;
resp = (struct nlmsghdr *)recvbuf;
switch (resp->nlmsg_type) {
case NLMSG_ERROR:
err = (struct nlmsgerr *)NLMSG_DATA(resp);
if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
goto malformed_resp;
switch (err->error) {
case 0:
break;
case -EEXIST:
*retry = 1;
goto cleanup;
default:
virReportSystemError(-err->error,
_("error creating %s type of interface"),
type);
goto cleanup;
}
break;
case NLMSG_DONE:
break;
default:
goto malformed_resp;
}
rc = 0;
cleanup:
nlmsg_free(nl_msg);
VIR_FREE(recvbuf);
return rc;
malformed_resp:
virNetDevError(VIR_ERR_INTERNAL_ERROR, "%s",
_("malformed netlink response message"));
goto cleanup;
buffer_too_small:
virNetDevError(VIR_ERR_INTERNAL_ERROR, "%s",
_("allocated netlink buffer is too small"));
goto cleanup;
}
/**
* virNetDevMacVLanDelete:
*
* @ifname: Name of the interface
*
* Tear down an interface with the given name.
*
* Returns 0 on success, -1 on fatal error.
*/
int virNetDevMacVLanDelete(const char *ifname)
{
int rc = -1;
struct nlmsghdr *resp;
struct nlmsgerr *err;
struct ifinfomsg ifinfo = { .ifi_family = AF_UNSPEC };
unsigned char *recvbuf = NULL;
unsigned int recvbuflen;
struct nl_msg *nl_msg;
nl_msg = nlmsg_alloc_simple(RTM_DELLINK,
NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL);
if (!nl_msg) {
virReportOOMError();
return -1;
}
if (nlmsg_append(nl_msg, &ifinfo, sizeof(ifinfo), NLMSG_ALIGNTO) < 0)
goto buffer_too_small;
if (nla_put(nl_msg, IFLA_IFNAME, strlen(ifname)+1, ifname) < 0)
goto buffer_too_small;
if (virNetlinkCommand(nl_msg, &recvbuf, &recvbuflen, 0) < 0) {
goto cleanup;
}
if (recvbuflen < NLMSG_LENGTH(0) || recvbuf == NULL)
goto malformed_resp;
resp = (struct nlmsghdr *)recvbuf;
switch (resp->nlmsg_type) {
case NLMSG_ERROR:
err = (struct nlmsgerr *)NLMSG_DATA(resp);
if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
goto malformed_resp;
if (err->error) {
virReportSystemError(-err->error,
_("error destroying %s interface"),
ifname);
goto cleanup;
}
break;
case NLMSG_DONE:
break;
default:
goto malformed_resp;
}
rc = 0;
cleanup:
nlmsg_free(nl_msg);
VIR_FREE(recvbuf);
return rc;
malformed_resp:
virNetDevError(VIR_ERR_INTERNAL_ERROR, "%s",
_("malformed netlink response message"));
goto cleanup;
buffer_too_small:
virNetDevError(VIR_ERR_INTERNAL_ERROR, "%s",
_("allocated netlink buffer is too small"));
goto cleanup;
}
/**
* virNetlinkCommand:
* @nlmsg: pointer to netlink message
* @respbuf: pointer to pointer where response buffer will be allocated
* @respbuflen: pointer to integer holding the size of the response buffer
* on return of the function.
* @src_pid: the pid of the process to send a message
* @dst_pid: the pid of the process to talk to, i.e., pid = 0 for kernel
* @protocol: netlink protocol
* @groups: the group identifier
*
* Send the given message to the netlink layer and receive response.
* Returns 0 on success, -1 on error. In case of error, no response
* buffer will be returned.
*/
int virNetlinkCommand(struct nl_msg *nl_msg,
struct nlmsghdr **resp, unsigned int *respbuflen,
uint32_t src_pid, uint32_t dst_pid,
unsigned int protocol, unsigned int groups)
{
int ret = -1;
struct sockaddr_nl nladdr = {
.nl_family = AF_NETLINK,
.nl_pid = dst_pid,
.nl_groups = 0,
};
ssize_t nbytes;
struct pollfd fds[1];
int fd;
int n;
struct nlmsghdr *nlmsg = nlmsg_hdr(nl_msg);
virNetlinkHandle *nlhandle = NULL;
int len = 0;
if (protocol >= MAX_LINKS) {
virReportSystemError(EINVAL,
_("invalid protocol argument: %d"), protocol);
goto cleanup;
}
if (!(nlhandle = virNetlinkCreateSocket(protocol)))
goto cleanup;
fd = nl_socket_get_fd(nlhandle);
if (fd < 0) {
virReportSystemError(errno,
"%s", _("cannot get netlink socket fd"));
goto cleanup;
}
if (groups && nl_socket_add_membership(nlhandle, groups) < 0) {
virReportSystemError(errno,
"%s", _("cannot add netlink membership"));
goto cleanup;
}
nlmsg_set_dst(nl_msg, &nladdr);
nlmsg->nlmsg_pid = src_pid ? src_pid : getpid();
nbytes = nl_send_auto_complete(nlhandle, nl_msg);
if (nbytes < 0) {
virReportSystemError(errno,
"%s", _("cannot send to netlink socket"));
goto cleanup;
}
memset(fds, 0, sizeof(fds));
fds[0].fd = fd;
fds[0].events = POLLIN;
n = poll(fds, ARRAY_CARDINALITY(fds), NETLINK_ACK_TIMEOUT_S);
if (n <= 0) {
if (n < 0)
virReportSystemError(errno, "%s",
_("error in poll call"));
if (n == 0)
virReportSystemError(ETIMEDOUT, "%s",
_("no valid netlink response was received"));
goto cleanup;
}
len = nl_recv(nlhandle, &nladdr, (unsigned char **)resp, NULL);
if (len == 0) {
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("nl_recv failed - returned 0 bytes"));
goto cleanup;
}
if (len < 0) {
virReportSystemError(errno, "%s", _("nl_recv failed"));
goto cleanup;
}
ret = 0;
*respbuflen = len;
cleanup:
if (ret < 0) {
*resp = NULL;
*respbuflen = 0;
}
virNetlinkFree(nlhandle);
return ret;
}
/**
* virNetlinkDumpLink:
*
* @ifname: The name of the interface; only use if ifindex <= 0
* @ifindex: The interface index; may be <= 0 if ifname is given
* @data: Gets a pointer to the raw data from netlink.
MUST BE FREED BY CALLER!
* @nlattr: Pointer to a pointer of netlink attributes that will contain
* the results
* @src_pid: pid used for nl_pid of the local end of the netlink message
* (0 == "use getpid()")
* @dst_pid: pid of destination nl_pid if the kernel
* is not the target of the netlink message but it is to be
* sent to another process (0 if sending to the kernel)
*
* Get information from netlink about an interface given its name or index.
*
* Returns 0 on success, -1 on fatal error.
*/
int
virNetlinkDumpLink(const char *ifname, int ifindex,
void **nlData, struct nlattr **tb,
uint32_t src_pid, uint32_t dst_pid)
{
int rc = -1;
struct nlmsghdr *resp = NULL;
struct nlmsgerr *err;
struct ifinfomsg ifinfo = {
.ifi_family = AF_UNSPEC,
.ifi_index = ifindex
};
unsigned int recvbuflen;
struct nl_msg *nl_msg;
if (ifname && ifindex <= 0 && virNetDevGetIndex(ifname, &ifindex) < 0)
return -1;
ifinfo.ifi_index = ifindex;
nl_msg = nlmsg_alloc_simple(RTM_GETLINK, NLM_F_REQUEST);
if (!nl_msg) {
virReportOOMError();
return -1;
}
if (nlmsg_append(nl_msg, &ifinfo, sizeof(ifinfo), NLMSG_ALIGNTO) < 0)
goto buffer_too_small;
if (ifname) {
if (nla_put(nl_msg, IFLA_IFNAME, strlen(ifname)+1, ifname) < 0)
goto buffer_too_small;
}
# ifdef RTEXT_FILTER_VF
/* if this filter exists in the kernel's netlink implementation,
* we need to set it, otherwise the response message will not
* contain the IFLA_VFINFO_LIST that we're looking for.
*/
{
uint32_t ifla_ext_mask = RTEXT_FILTER_VF;
if (nla_put(nl_msg, IFLA_EXT_MASK,
sizeof(ifla_ext_mask), &ifla_ext_mask) < 0) {
goto buffer_too_small;
}
}
# endif
if (virNetlinkCommand(nl_msg, &resp, &recvbuflen,
src_pid, dst_pid, NETLINK_ROUTE, 0) < 0)
goto cleanup;
if (recvbuflen < NLMSG_LENGTH(0) || resp == NULL)
goto malformed_resp;
switch (resp->nlmsg_type) {
case NLMSG_ERROR:
err = (struct nlmsgerr *)NLMSG_DATA(resp);
if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err)))
goto malformed_resp;
if (err->error) {
virReportSystemError(-err->error,
_("error dumping %s (%d) interface"),
ifname, ifindex);
goto cleanup;
}
break;
case GENL_ID_CTRL:
case NLMSG_DONE:
rc = nlmsg_parse(resp, sizeof(struct ifinfomsg),
tb, IFLA_MAX, NULL);
if (rc < 0)
goto malformed_resp;
break;
default:
goto malformed_resp;
}
rc = 0;
cleanup:
nlmsg_free(nl_msg);
if (rc < 0)
VIR_FREE(resp);
*nlData = resp;
return rc;
malformed_resp:
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("malformed netlink response message"));
goto cleanup;
buffer_too_small:
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("allocated netlink buffer is too small"));
goto cleanup;
}
/**
* virNetDevIPRouteAdd:
* @ifname: the interface name
* @addr: the IP network address (IPv4 or IPv6)
* @prefix: number of 1 bits in the netmask
* @gateway: via address for route (same as @addr)
*
* Add a route for a network IP address to an interface. This function
* *does not* remove any previously added IP static routes.
*
* Returns 0 in case of success or -1 in case of error.
*/
int
virNetDevIPRouteAdd(const char *ifname,
virSocketAddrPtr addr,
unsigned int prefix,
virSocketAddrPtr gateway,
unsigned int metric)
{
int ret = -1;
struct nl_msg *nlmsg = NULL;
struct nlmsghdr *resp = NULL;
unsigned int recvbuflen;
unsigned int ifindex;
struct rtmsg rtmsg;
void *gatewayData = NULL;
void *addrData = NULL;
size_t addrDataLen;
int errCode;
virSocketAddr defaultAddr;
virSocketAddrPtr actualAddr;
char *toStr = NULL;
char *viaStr = NULL;
actualAddr = addr;
/* If we have no valid network address, then use the default one */
if (!addr || !VIR_SOCKET_ADDR_VALID(addr)) {
VIR_DEBUG("computing default address");
int family = VIR_SOCKET_ADDR_FAMILY(gateway);
if (family == AF_INET) {
if (virSocketAddrParseIPv4(&defaultAddr, VIR_SOCKET_ADDR_IPV4_ALL) < 0)
goto cleanup;
} else {
if (virSocketAddrParseIPv6(&defaultAddr, VIR_SOCKET_ADDR_IPV6_ALL) < 0)
goto cleanup;
}
actualAddr = &defaultAddr;
}
toStr = virSocketAddrFormat(actualAddr);
viaStr = virSocketAddrFormat(gateway);
VIR_DEBUG("Adding route %s/%d via %s", toStr, prefix, viaStr);
if (virNetDevGetIPAddressBinary(actualAddr, &addrData, &addrDataLen) < 0 ||
virNetDevGetIPAddressBinary(gateway, &gatewayData, &addrDataLen) < 0)
goto cleanup;
/* Get the interface index */
if ((ifindex = if_nametoindex(ifname)) == 0)
goto cleanup;
if (!(nlmsg = nlmsg_alloc_simple(RTM_NEWROUTE,
NLM_F_REQUEST | NLM_F_CREATE |
NLM_F_EXCL))) {
virReportOOMError();
goto cleanup;
}
memset(&rtmsg, 0, sizeof(rtmsg));
rtmsg.rtm_family = VIR_SOCKET_ADDR_FAMILY(gateway);
rtmsg.rtm_table = RT_TABLE_MAIN;
rtmsg.rtm_scope = RT_SCOPE_UNIVERSE;
rtmsg.rtm_protocol = RTPROT_BOOT;
rtmsg.rtm_type = RTN_UNICAST;
rtmsg.rtm_dst_len = prefix;
if (nlmsg_append(nlmsg, &rtmsg, sizeof(rtmsg), NLMSG_ALIGNTO) < 0)
goto buffer_too_small;
if (prefix > 0 && nla_put(nlmsg, RTA_DST, addrDataLen, addrData) < 0)
goto buffer_too_small;
if (nla_put(nlmsg, RTA_GATEWAY, addrDataLen, gatewayData) < 0)
goto buffer_too_small;
if (nla_put_u32(nlmsg, RTA_OIF, ifindex) < 0)
goto buffer_too_small;
if (metric > 0 && nla_put_u32(nlmsg, RTA_PRIORITY, metric) < 0)
goto buffer_too_small;
if (virNetlinkCommand(nlmsg, &resp, &recvbuflen, 0, 0,
NETLINK_ROUTE, 0) < 0)
goto cleanup;
if ((errCode = virNetlinkGetErrorCode(resp, recvbuflen)) < 0) {
virReportSystemError(errCode, _("Error adding route to %s"), ifname);
goto cleanup;
}
ret = 0;
cleanup:
VIR_FREE(toStr);
VIR_FREE(viaStr);
nlmsg_free(nlmsg);
return ret;
buffer_too_small:
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("allocated netlink buffer is too small"));
goto cleanup;
}
/**
* virNetDevIPAddrAdd:
* @ifname: the interface name
* @addr: the IP address (IPv4 or IPv6)
* @peer: The IP address of peer (IPv4 or IPv6)
* @prefix: number of 1 bits in the netmask
*
* Add an IP address to an interface. This function *does not* remove
* any previously added IP addresses - that must be done separately with
* virNetDevIPAddrClear.
*
* Returns 0 in case of success or -1 in case of error.
*/
int
virNetDevIPAddrAdd(const char *ifname,
virSocketAddr *addr,
virSocketAddr *peer,
unsigned int prefix)
{
virSocketAddr *broadcast = NULL;
int ret = -1;
struct nl_msg *nlmsg = NULL;
struct nlmsghdr *resp = NULL;
unsigned int recvbuflen;
char *ipStr = NULL;
char *peerStr = NULL;
char *bcastStr = NULL;
ipStr = virSocketAddrFormat(addr);
if (peer && VIR_SOCKET_ADDR_VALID(peer))
peerStr = virSocketAddrFormat(peer);
/* The caller needs to provide a correct address */
if (VIR_SOCKET_ADDR_FAMILY(addr) == AF_INET &&
!(peer && VIR_SOCKET_ADDR_VALID(peer))) {
/* compute a broadcast address if this is IPv4 */
if (VIR_ALLOC(broadcast) < 0)
goto cleanup;
if (virSocketAddrBroadcastByPrefix(addr, prefix, broadcast) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Failed to determine broadcast address for '%s/%d'"),
ipStr, prefix);
goto cleanup;
}
bcastStr = virSocketAddrFormat(broadcast);
}
VIR_DEBUG("Adding IP address %s/%d%s%s%s%s to %s",
NULLSTR(ipStr), prefix,
peerStr ? " peer " : "", peerStr ? peerStr : "",
bcastStr ? " bcast " : "", bcastStr ? bcastStr : "",
ifname);
if (!(nlmsg = virNetDevCreateNetlinkAddressMessage(RTM_NEWADDR, ifname,
addr, prefix,
broadcast, peer)))
goto cleanup;
if (virNetlinkCommand(nlmsg, &resp, &recvbuflen,
0, 0, NETLINK_ROUTE, 0) < 0)
goto cleanup;
if (virNetlinkGetErrorCode(resp, recvbuflen) < 0) {
virReportError(VIR_ERR_SYSTEM_ERROR,
_("Failed to add IP address %s/%d%s%s%s%s to %s"),
ipStr, prefix,
peerStr ? " peer " : "", peerStr ? peerStr : "",
bcastStr ? " bcast " : "", bcastStr ? bcastStr : "",
ifname);
goto cleanup;
}
ret = 0;
cleanup:
VIR_FREE(ipStr);
VIR_FREE(peerStr);
VIR_FREE(bcastStr);
nlmsg_free(nlmsg);
VIR_FREE(resp);
VIR_FREE(broadcast);
return ret;
}
