/**
* virNetDevMacVLanTapOpen:
* @ifname: Name of the macvtap interface
* @tapfd: array of file descriptor return value for the new macvtap device
* @tapfdSize: number of file descriptors in @tapfd
* @retries : Number of retries in case udev for example may need to be
* waited for to create the tap chardev
*
* Open the macvtap's tap device, possibly multiple times if @tapfdSize > 1.
*
* Returns 0 on success, -1 otherwise.
*/
static int
virNetDevMacVLanTapOpen(const char *ifname,
int *tapfd,
size_t tapfdSize,
int retries)
{
int ret = -1;
int ifindex;
char *tapname = NULL;
size_t i = 0;
if (virNetDevGetIndex(ifname, &ifindex) < 0)
return -1;
if (virAsprintf(&tapname, "/dev/tap%d", ifindex) < 0)
goto cleanup;
for (i = 0; i < tapfdSize; i++) {
int fd = -1;
while (fd < 0) {
if ((fd = open(tapname, O_RDWR)) >= 0) {
tapfd[i] = fd;
} else if (retries-- > 0) {
/* may need to wait for udev to be done */
usleep(20000);
} else {
/* However, if haven't succeeded, quit. */
virReportSystemError(errno,
_("cannot open macvtap tap device %s"),
tapname);
goto cleanup;
}
}
}
ret = 0;
cleanup:
if (ret < 0) {
while (i--)
VIR_FORCE_CLOSE(tapfd[i]);
}
VIR_FREE(tapname);
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;
}
/**
* 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;
}
