/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned uninitialized_var(in), log;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr_mrg_rxbuf hdr = {
.hdr.flags = 0,
.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t total_len = 0;
int err, mergeable;
s16 headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
/* TODO: check that we are running from vhost_worker? */
struct socket *sock = rcu_dereference_check(vq->private_data, 1);
if (!sock)
return;
mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
vhost_hlen = vq->vhost_hlen;
sock_hlen = vq->sock_hlen;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
mergeable = vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF);
while ((sock_len = peek_head_len(sock->sk))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
headcount = get_rx_bufs(vq, vq->heads, vhost_len,
&in, vq_log, &log,
likely(mergeable) ? UIO_MAXIOV : 1);
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(&net->dev, vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (unlikely((vhost_hlen)))
/* Skip header. TODO: support TSO. */
move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
else
/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
* needed because recvmsg can modify msg_iov. */
copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
msg.msg_iovlen = in;
err = sock->ops->recvmsg(NULL, sock, &msg,
sock_len, MSG_DONTWAIT | MSG_TRUNC);
/* Userspace might have consumed the packet meanwhile:
* it's not supposed to do this usually, but might be hard
* to prevent. Discard data we got (if any) and keep going. */
if (unlikely(err != sock_len)) {
pr_debug("Discarded rx packet: "
" len %d, expected %zd\n", err, sock_len);
vhost_discard_vq_desc(vq, headcount);
continue;
}
if (unlikely(vhost_hlen) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&hdr, 0,
vhost_hlen)) {
vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
vq->iov->iov_base);
break;
}
/* TODO: Should check and handle checksum. */
if (likely(mergeable) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
offsetof(typeof(hdr), num_buffers),
sizeof hdr.num_buffers)) {
vq_err(vq, "Failed num_buffers write");
vhost_discard_vq_desc(vq, headcount);
break;
}
vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
headcount);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
}
static void handle_tx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_tx(net);
}
static void handle_rx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_rx(net);
}
static void handle_tx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_TX].work);
handle_tx(net);
}
static void handle_rx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_RX].work);
handle_rx(net);
}
static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
struct vhost_dev *dev;
int r;
if (!n)
return -ENOMEM;
dev = &n->dev;
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX);
if (r < 0) {
kfree(n);
return r;
}
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
f->private_data = n;
return 0;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
if (!vq->private_data)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
tx_poll_stop(n);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
} else
vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
}
static void vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (!sock)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
n->tx_poll_state = VHOST_NET_POLL_STOPPED;
tx_poll_start(n, sock);
} else
vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
mutex_lock(&vq->mutex);
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, NULL);
mutex_unlock(&vq->mutex);
return sock;
}
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->dev.vqs[index].poll);
}
static int do_ip_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
bool needs_rtnl = getsockopt_needs_rtnl(optname);
int val, err = 0;
int len;
if (level != SOL_IP)
return -EOPNOTSUPP;
if (ip_mroute_opt(optname))
return ip_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
unsigned char optbuf[sizeof(struct ip_options)+40];
struct ip_options *opt = (struct ip_options *)optbuf;
struct ip_options_rcu *inet_opt;
inet_opt = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
opt->optlen = 0;
if (inet_opt)
memcpy(optbuf, &inet_opt->opt,
sizeof(struct ip_options) +
inet_opt->opt.optlen);
release_sock(sk);
if (opt->optlen == 0)
return put_user(0, optlen);
ip_options_undo(opt);
len = min_t(unsigned int, len, opt->optlen);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, opt->__data, len))
return -EFAULT;
return 0;
}
case IP_PKTINFO:
val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0;
break;
case IP_RECVTTL:
val = (inet->cmsg_flags & IP_CMSG_TTL) != 0;
break;
case IP_RECVTOS:
val = (inet->cmsg_flags & IP_CMSG_TOS) != 0;
break;
case IP_RECVOPTS:
val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
break;
case IP_RETOPTS:
val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
break;
case IP_PASSSEC:
val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0;
break;
case IP_RECVORIGDSTADDR:
val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
break;
case IP_CHECKSUM:
val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
break;
case IP_RECVFRAGSIZE:
val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0;
break;
case IP_TOS:
val = inet->tos;
break;
case IP_TTL:
{
struct net *net = sock_net(sk);
val = (inet->uc_ttl == -1 ?
net->ipv4.sysctl_ip_default_ttl :
inet->uc_ttl);
break;
}
case IP_HDRINCL:
val = inet->hdrincl;
break;
case IP_NODEFRAG:
val = inet->nodefrag;
break;
case IP_BIND_ADDRESS_NO_PORT:
val = inet->bind_address_no_port;
break;
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;
case IP_MTU:
{
struct dst_entry *dst;
val = 0;
dst = sk_dst_get(sk);
if (dst) {
val = dst_mtu(dst);
dst_release(dst);
}
if (!val) {
release_sock(sk);
return -ENOTCONN;
}
break;
}
case IP_RECVERR:
val = inet->recverr;
break;
case IP_MULTICAST_TTL:
val = inet->mc_ttl;
break;
case IP_MULTICAST_LOOP:
val = inet->mc_loop;
break;
case IP_UNICAST_IF:
val = (__force int)htonl((__u32) inet->uc_index);
break;
case IP_MULTICAST_IF:
{
struct in_addr addr;
len = min_t(unsigned int, len, sizeof(struct in_addr));
addr.s_addr = inet->mc_addr;
release_sock(sk);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &addr, len))
return -EFAULT;
return 0;
}
case IP_MSFILTER:
{
struct ip_msfilter msf;
if (len < IP_MSFILTER_SIZE(0)) {
err = -EINVAL;
goto out;
}
if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
err = -EFAULT;
goto out;
}
err = ip_mc_msfget(sk, &msf,
(struct ip_msfilter __user *)optval, optlen);
goto out;
}
case MCAST_MSFILTER:
{
struct group_filter gsf;
if (len < GROUP_FILTER_SIZE(0)) {
err = -EINVAL;
goto out;
}
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) {
err = -EFAULT;
goto out;
}
err = ip_mc_gsfget(sk, &gsf,
(struct group_filter __user *)optval,
optlen);
goto out;
}
case IP_MULTICAST_ALL:
val = inet->mc_all;
break;
case IP_PKTOPTIONS:
{
struct msghdr msg;
release_sock(sk);
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = (__force void *) optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
struct in_pktinfo info;
info.ipi_addr.s_addr = inet->inet_rcv_saddr;
info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr;
info.ipi_ifindex = inet->mc_index;
put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
if (inet->cmsg_flags & IP_CMSG_TTL) {
int hlim = inet->mc_ttl;
put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
}
if (inet->cmsg_flags & IP_CMSG_TOS) {
int tos = inet->rcv_tos;
put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IP_FREEBIND:
val = inet->freebind;
break;
case IP_TRANSPARENT:
val = inet->transparent;
break;
case IP_MINTTL:
val = inet->min_ttl;
break;
default:
release_sock(sk);
return -ENOPROTOOPT;
}
release_sock(sk);
if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) {
unsigned char ucval = (unsigned char)val;
len = 1;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &ucval, 1))
return -EFAULT;
} else {
len = min_t(unsigned int, sizeof(int), len);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &val, len))
return -EFAULT;
}
return 0;
out:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return err;
}
static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
u_int16_t subsys_id)
{
struct sk_buff *nskb, *oskb = skb;
struct net *net = sock_net(skb->sk);
const struct nfnetlink_subsystem *ss;
const struct nfnl_callback *nc;
bool success = true, done = false;
int err;
if (subsys_id >= NFNL_SUBSYS_COUNT)
return netlink_ack(skb, nlh, -EINVAL);
replay:
nskb = netlink_skb_clone(oskb, GFP_KERNEL);
if (!nskb)
return netlink_ack(oskb, nlh, -ENOMEM);
nskb->sk = oskb->sk;
skb = nskb;
nfnl_lock(subsys_id);
ss = rcu_dereference_protected(table[subsys_id].subsys,
lockdep_is_held(&table[subsys_id].mutex));
if (!ss) {
#ifdef CONFIG_MODULES
nfnl_unlock(subsys_id);
request_module("nfnetlink-subsys-%d", subsys_id);
nfnl_lock(subsys_id);
ss = rcu_dereference_protected(table[subsys_id].subsys,
lockdep_is_held(&table[subsys_id].mutex));
if (!ss)
#endif
{
nfnl_unlock(subsys_id);
netlink_ack(skb, nlh, -EOPNOTSUPP);
return kfree_skb(nskb);
}
}
if (!ss->commit || !ss->abort) {
nfnl_unlock(subsys_id);
netlink_ack(skb, nlh, -EOPNOTSUPP);
return kfree_skb(skb);
}
while (skb->len >= nlmsg_total_size(0)) {
int msglen, type;
nlh = nlmsg_hdr(skb);
err = 0;
if (nlh->nlmsg_len < NLMSG_HDRLEN) {
err = -EINVAL;
goto ack;
}
/* Only requests are handled by the kernel */
if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) {
err = -EINVAL;
goto ack;
}
type = nlh->nlmsg_type;
if (type == NFNL_MSG_BATCH_BEGIN) {
/* Malformed: Batch begin twice */
success = false;
goto done;
} else if (type == NFNL_MSG_BATCH_END) {
done = true;
goto done;
} else if (type < NLMSG_MIN_TYPE) {
err = -EINVAL;
goto ack;
}
/* We only accept a batch with messages for the same
* subsystem.
*/
if (NFNL_SUBSYS_ID(type) != subsys_id) {
err = -EINVAL;
goto ack;
}
nc = nfnetlink_find_client(type, ss);
if (!nc) {
err = -EINVAL;
goto ack;
}
{
int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type);
struct nlattr *cda[ss->cb[cb_id].attr_count + 1];
struct nlattr *attr = (void *)nlh + min_len;
int attrlen = nlh->nlmsg_len - min_len;
err = nla_parse(cda, ss->cb[cb_id].attr_count,
attr, attrlen, ss->cb[cb_id].policy);
if (err < 0)
goto ack;
if (nc->call_batch) {
err = nc->call_batch(net->nfnl, skb, nlh,
(const struct nlattr **)cda);
}
/* The lock was released to autoload some module, we
* have to abort and start from scratch using the
* original skb.
*/
if (err == -EAGAIN) {
ss->abort(skb);
nfnl_unlock(subsys_id);
kfree_skb(nskb);
goto replay;
}
}
ack:
if (nlh->nlmsg_flags & NLM_F_ACK || err) {
/* We don't stop processing the batch on errors, thus,
* userspace gets all the errors that the batch
* triggers.
*/
netlink_ack(skb, nlh, err);
if (err)
success = false;
}
msglen = NLMSG_ALIGN(nlh->nlmsg_len);
if (msglen > skb->len)
msglen = skb->len;
skb_pull(skb, msglen);
}
done:
if (success && done)
ss->commit(skb);
else
ss->abort(skb);
nfnl_unlock(subsys_id);
kfree_skb(nskb);
}
e->missed &= ~missed;
spin_unlock_bh(&ct->lock);
out_unlock:
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events);
int nf_conntrack_register_notifier(struct net *net,
struct nf_ct_event_notifier *new)
{
int ret;
struct nf_ct_event_notifier *notify;
mutex_lock(&nf_ct_ecache_mutex);
notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
lockdep_is_held(&nf_ct_ecache_mutex));
if (notify != NULL) {
ret = -EBUSY;
goto out_unlock;
}
rcu_assign_pointer(net->ct.nf_conntrack_event_cb, new);
ret = 0;
out_unlock:
mutex_unlock(&nf_ct_ecache_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier);
void nf_conntrack_unregister_notifier(struct net *net,
struct nf_ct_event_notifier *new)
static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned int flags)
{
struct ipv6_pinfo *np = inet6_sk(sk);
int len;
int val;
if (ip6_mroute_opt(optname))
return ip6_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
case IPV6_ADDRFORM:
if (sk->sk_protocol != IPPROTO_UDP &&
sk->sk_protocol != IPPROTO_UDPLITE &&
sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
if (sk->sk_state != TCP_ESTABLISHED)
return -ENOTCONN;
val = sk->sk_family;
break;
case MCAST_MSFILTER:
{
struct group_filter gsf;
int err;
if (len < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
return -EFAULT;
if (gsf.gf_group.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
lock_sock(sk);
err = ip6_mc_msfget(sk, &gsf,
(struct group_filter __user *)optval, optlen);
release_sock(sk);
return err;
}
case IPV6_2292PKTOPTIONS:
{
struct msghdr msg;
struct sk_buff *skb;
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
lock_sock(sk);
skb = np->pktoptions;
if (skb)
ip6_datagram_recv_ctl(sk, &msg, skb);
release_sock(sk);
if (!skb) {
if (np->rxopt.bits.rxinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr;
put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxhlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxtclass) {
int tclass = (int)ip6_tclass(np->rcv_flowinfo);
put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
}
if (np->rxopt.bits.rxoinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr :
np->sticky_pktinfo.ipi6_addr;
put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxflow) {
__be32 flowinfo = np->rcv_flowinfo;
put_cmsg(&msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo);
}
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IPV6_MTU:
{
struct dst_entry *dst;
val = 0;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = dst_mtu(dst);
rcu_read_unlock();
if (!val)
return -ENOTCONN;
break;
}
case IPV6_V6ONLY:
val = sk->sk_ipv6only;
break;
case IPV6_RECVPKTINFO:
val = np->rxopt.bits.rxinfo;
break;
case IPV6_2292PKTINFO:
val = np->rxopt.bits.rxoinfo;
break;
case IPV6_RECVHOPLIMIT:
val = np->rxopt.bits.rxhlim;
break;
case IPV6_2292HOPLIMIT:
val = np->rxopt.bits.rxohlim;
break;
case IPV6_RECVRTHDR:
val = np->rxopt.bits.srcrt;
break;
case IPV6_2292RTHDR:
val = np->rxopt.bits.osrcrt;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
lock_sock(sk);
opt = rcu_dereference_protected(np->opt,
lockdep_sock_is_held(sk));
len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
return len;
return put_user(len, optlen);
}
case IPV6_RECVHOPOPTS:
val = np->rxopt.bits.hopopts;
break;
case IPV6_2292HOPOPTS:
val = np->rxopt.bits.ohopopts;
break;
case IPV6_RECVDSTOPTS:
val = np->rxopt.bits.dstopts;
break;
case IPV6_2292DSTOPTS:
val = np->rxopt.bits.odstopts;
break;
case IPV6_TCLASS:
val = np->tclass;
break;
case IPV6_RECVTCLASS:
val = np->rxopt.bits.rxtclass;
break;
case IPV6_FLOWINFO:
val = np->rxopt.bits.rxflow;
break;
case IPV6_RECVPATHMTU:
val = np->rxopt.bits.rxpmtu;
break;
case IPV6_PATHMTU:
{
struct dst_entry *dst;
struct ip6_mtuinfo mtuinfo;
if (len < sizeof(mtuinfo))
return -EINVAL;
len = sizeof(mtuinfo);
memset(&mtuinfo, 0, sizeof(mtuinfo));
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
mtuinfo.ip6m_mtu = dst_mtu(dst);
rcu_read_unlock();
if (!mtuinfo.ip6m_mtu)
return -ENOTCONN;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &mtuinfo, len))
return -EFAULT;
return 0;
}
case IPV6_TRANSPARENT:
val = inet_sk(sk)->transparent;
break;
case IPV6_RECVORIGDSTADDR:
val = np->rxopt.bits.rxorigdstaddr;
break;
case IPV6_UNICAST_HOPS:
case IPV6_MULTICAST_HOPS:
{
struct dst_entry *dst;
if (optname == IPV6_UNICAST_HOPS)
val = np->hop_limit;
else
val = np->mcast_hops;
if (val < 0) {
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = ip6_dst_hoplimit(dst);
rcu_read_unlock();
}
if (val < 0)
val = sock_net(sk)->ipv6.devconf_all->hop_limit;
break;
}
case IPV6_MULTICAST_LOOP:
val = np->mc_loop;
break;
case IPV6_MULTICAST_IF:
val = np->mcast_oif;
break;
case IPV6_UNICAST_IF:
val = (__force int)htonl((__u32) np->ucast_oif);
break;
case IPV6_MTU_DISCOVER:
val = np->pmtudisc;
break;
case IPV6_RECVERR:
val = np->recverr;
break;
case IPV6_FLOWINFO_SEND:
val = np->sndflow;
break;
case IPV6_FLOWLABEL_MGR:
{
struct in6_flowlabel_req freq;
int flags;
if (len < sizeof(freq))
return -EINVAL;
if (copy_from_user(&freq, optval, sizeof(freq)))
return -EFAULT;
if (freq.flr_action != IPV6_FL_A_GET)
return -EINVAL;
len = sizeof(freq);
flags = freq.flr_flags;
memset(&freq, 0, sizeof(freq));
val = ipv6_flowlabel_opt_get(sk, &freq, flags);
if (val < 0)
return val;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &freq, len))
return -EFAULT;
return 0;
}
case IPV6_ADDR_PREFERENCES:
val = 0;
if (np->srcprefs & IPV6_PREFER_SRC_TMP)
val |= IPV6_PREFER_SRC_TMP;
else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC)
val |= IPV6_PREFER_SRC_PUBLIC;
else {
/* XXX: should we return system default? */
val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT;
}
if (np->srcprefs & IPV6_PREFER_SRC_COA)
val |= IPV6_PREFER_SRC_COA;
else
val |= IPV6_PREFER_SRC_HOME;
break;
case IPV6_MINHOPCOUNT:
val = np->min_hopcount;
break;
case IPV6_DONTFRAG:
val = np->dontfrag;
break;
case IPV6_AUTOFLOWLABEL:
val = np->autoflowlabel;
break;
case IPV6_RECVFRAGSIZE:
val = np->rxopt.bits.recvfragsize;
break;
default:
return -ENOPROTOOPT;
}
len = min_t(unsigned int, sizeof(int), len);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
/*
* Update a cell's VL server address list from the DNS.
*/
static void afs_update_cell(struct afs_cell *cell)
{
struct afs_vlserver_list *vllist, *old;
unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl);
unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl);
time64_t now, expiry = 0;
_enter("%s", cell->name);
vllist = afs_dns_query(cell, &expiry);
now = ktime_get_real_seconds();
if (min_ttl > max_ttl)
max_ttl = min_ttl;
if (expiry < now + min_ttl)
expiry = now + min_ttl;
else if (expiry > now + max_ttl)
expiry = now + max_ttl;
if (IS_ERR(vllist)) {
switch (PTR_ERR(vllist)) {
case -ENODATA:
case -EDESTADDRREQ:
/* The DNS said that the cell does not exist or there
* weren't any addresses to be had.
*/
set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = expiry;
break;
case -EAGAIN:
case -ECONNREFUSED:
default:
set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
cell->dns_expiry = now + 10;
break;
}
cell->error = -EDESTADDRREQ;
} else {
clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags);
clear_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags);
/* Exclusion on changing vl_addrs is achieved by a
* non-reentrant work item.
*/
old = rcu_dereference_protected(cell->vl_servers, true);
rcu_assign_pointer(cell->vl_servers, vllist);
cell->dns_expiry = expiry;
if (old)
afs_put_vlserverlist(cell->net, old);
}
if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags))
wake_up_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET);
now = ktime_get_real_seconds();
afs_set_cell_timer(cell->net, cell->dns_expiry - now);
_leave("");
}
static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int orig_size, size;
int ret, i;
struct ctl_table tmp = {
.data = &size,
.maxlen = sizeof(size),
.mode = table->mode
};
struct rps_sock_flow_table *orig_sock_table, *sock_table;
static DEFINE_MUTEX(sock_flow_mutex);
mutex_lock(&sock_flow_mutex);
orig_sock_table = rcu_dereference_protected(rps_sock_flow_table,
lockdep_is_held(&sock_flow_mutex));
size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0;
ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
if (write) {
if (size) {
if (size > 1<<29) {
/* Enforce limit to prevent overflow */
mutex_unlock(&sock_flow_mutex);
return -EINVAL;
}
size = roundup_pow_of_two(size);
if (size != orig_size) {
sock_table =
vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size));
if (!sock_table) {
mutex_unlock(&sock_flow_mutex);
return -ENOMEM;
}
rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1;
sock_table->mask = size - 1;
} else
sock_table = orig_sock_table;
for (i = 0; i < size; i++)
sock_table->ents[i] = RPS_NO_CPU;
} else
sock_table = NULL;
if (sock_table != orig_sock_table) {
rcu_assign_pointer(rps_sock_flow_table, sock_table);
if (sock_table) {
static_key_slow_inc(&rps_needed);
static_key_slow_inc(&rfs_needed);
}
if (orig_sock_table) {
static_key_slow_dec(&rps_needed);
static_key_slow_dec(&rfs_needed);
synchronize_rcu();
vfree(orig_sock_table);
}
}
}
mutex_unlock(&sock_flow_mutex);
return ret;
}
#endif /* CONFIG_RPS */
#ifdef CONFIG_NET_FLOW_LIMIT
static DEFINE_MUTEX(flow_limit_update_mutex);
static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct sd_flow_limit *cur;
struct softnet_data *sd;
cpumask_var_t mask;
int i, len, ret = 0;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
if (write) {
ret = cpumask_parse_user(buffer, *lenp, mask);
if (ret)
goto done;
mutex_lock(&flow_limit_update_mutex);
len = sizeof(*cur) + netdev_flow_limit_table_len;
for_each_possible_cpu(i) {
sd = &per_cpu(softnet_data, i);
cur = rcu_dereference_protected(sd->flow_limit,
lockdep_is_held(&flow_limit_update_mutex));
if (cur && !cpumask_test_cpu(i, mask)) {
RCU_INIT_POINTER(sd->flow_limit, NULL);
synchronize_rcu();
kfree(cur);
} else if (!cur && cpumask_test_cpu(i, mask)) {
cur = kzalloc_node(len, GFP_KERNEL,
cpu_to_node(i));
if (!cur) {
/* not unwinding previous changes */
ret = -ENOMEM;
goto write_unlock;
}
cur->num_buckets = netdev_flow_limit_table_len;
rcu_assign_pointer(sd->flow_limit, cur);
}
}
write_unlock:
mutex_unlock(&flow_limit_update_mutex);
} else {
char kbuf[128];
if (*ppos || !*lenp) {
*lenp = 0;
goto done;
}
cpumask_clear(mask);
rcu_read_lock();
for_each_possible_cpu(i) {
sd = &per_cpu(softnet_data, i);
if (rcu_dereference(sd->flow_limit))
cpumask_set_cpu(i, mask);
}
rcu_read_unlock();
len = min(sizeof(kbuf) - 1, *lenp);
len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask));
if (!len) {
*lenp = 0;
goto done;
}
if (len < *lenp)
kbuf[len++] = '\n';
if (copy_to_user(buffer, kbuf, len)) {
ret = -EFAULT;
goto done;
}
*lenp = len;
*ppos += len;
}
done:
free_cpumask_var(mask);
return ret;
}
static void dccp_v4_reqsk_destructor(struct request_sock *req)
{
dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
}
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
struct vhost_ubuf_ref *ubufs, *oldubufs = NULL;
int r;
mutex_lock(&n->dev.mutex);
r = vhost_dev_check_owner(&n->dev);
if (r)
goto err;
if (index >= VHOST_NET_VQ_MAX) {
r = -ENOBUFS;
goto err;
}
vq = n->vqs + index;
mutex_lock(&vq->mutex);
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
goto err_vq;
}
sock = get_socket(fd);
if (IS_ERR(sock)) {
r = PTR_ERR(sock);
goto err_vq;
}
/* start polling new socket */
oldsock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (sock != oldsock) {
ubufs = vhost_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock));
if (IS_ERR(ubufs)) {
r = PTR_ERR(ubufs);
goto err_ubufs;
}
oldubufs = vq->ubufs;
vq->ubufs = ubufs;
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, sock);
vhost_net_enable_vq(n, vq);
r = vhost_init_used(vq);
if (r)
goto err_vq;
n->tx_packets = 0;
n->tx_zcopy_err = 0;
n->tx_flush = false;
}
mutex_unlock(&vq->mutex);
if (oldubufs) {
vhost_ubuf_put_and_wait(oldubufs);
mutex_lock(&vq->mutex);
vhost_zerocopy_signal_used(n, vq);
mutex_unlock(&vq->mutex);
}
if (oldsock) {
vhost_net_flush_vq(n, index);
fput(oldsock->file);
}
mutex_unlock(&n->dev.mutex);
return 0;
err_ubufs:
fput(sock->file);
err_vq:
mutex_unlock(&vq->mutex);
err:
mutex_unlock(&n->dev.mutex);
return r;
}
static ssize_t sta_tx_latency_stat_write(struct file *file,
const char __user *userbuf,
size_t count, loff_t *ppos)
{
struct ieee80211_local *local = file->private_data;
char buf[128] = {};
char *bins = buf;
char *token;
int buf_size, i, alloc_size;
int prev_bin = 0;
int n_ranges = 0;
int ret = count;
struct ieee80211_tx_latency_bin_ranges *tx_latency;
if (sizeof(buf) <= count)
return -EINVAL;
buf_size = count;
if (copy_from_user(buf, userbuf, buf_size))
return -EFAULT;
mutex_lock(&local->sta_mtx);
/* cannot change config once we have stations */
if (local->num_sta)
goto unlock;
tx_latency =
rcu_dereference_protected(local->tx_latency,
lockdep_is_held(&local->sta_mtx));
/* disable Tx statistics */
if (!strcmp(buf, TX_LATENCY_DISABLED)) {
if (!tx_latency)
goto unlock;
RCU_INIT_POINTER(local->tx_latency, NULL);
synchronize_rcu();
kfree(tx_latency);
goto unlock;
}
/* Tx latency already enabled */
if (tx_latency)
goto unlock;
if (strcmp(TX_LATENCY_BINS_DISABLED, buf)) {
/* check how many bins and between what ranges user requested */
token = buf;
while (*token != '\0') {
if (*token == TX_LATENCY_BIN_DELIMTER_C)
n_ranges++;
token++;
}
n_ranges++;
}
alloc_size = sizeof(struct ieee80211_tx_latency_bin_ranges) +
n_ranges * sizeof(u32);
tx_latency = kzalloc(alloc_size, GFP_ATOMIC);
if (!tx_latency) {
ret = -ENOMEM;
goto unlock;
}
tx_latency->n_ranges = n_ranges;
for (i = 0; i < n_ranges; i++) { /* setting bin ranges */
token = strsep(&bins, TX_LATENCY_BIN_DELIMTER_S);
sscanf(token, "%d", &tx_latency->ranges[i]);
/* bins values should be in ascending order */
if (prev_bin >= tx_latency->ranges[i]) {
ret = -EINVAL;
kfree(tx_latency);
goto unlock;
}
prev_bin = tx_latency->ranges[i];
}
rcu_assign_pointer(local->tx_latency, tx_latency);
unlock:
mutex_unlock(&local->sta_mtx);
return ret;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
__be16 orig_sport, orig_dport;
__be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
struct ip_options_rcu *inet_opt;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
inet_opt = rcu_dereference_protected(inet->inet_opt,
sock_owned_by_user(sk));
if (inet_opt != NULL && inet_opt->opt.srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet_opt->opt.faddr;
}
orig_sport = inet->inet_sport;
orig_dport = usin->sin_port;
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
orig_sport, orig_dport, sk, true);
if (IS_ERR(rt))
return PTR_ERR(rt);
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet_opt == NULL || !inet_opt->opt.srr)
daddr = fl4->daddr;
if (inet->inet_saddr == 0)
inet->inet_saddr = fl4->saddr;
inet->inet_rcv_saddr = inet->inet_saddr;
inet->inet_dport = usin->sin_port;
inet->inet_daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
if (IS_ERR(rt)) {
<<<<<<< HEAD
err = PTR_ERR(rt);
=======
<<<<<<< HEAD
int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
{
int uninitialized_var(err);
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
struct ipv6_fl_socklist *sfl1 = NULL;
struct ipv6_fl_socklist *sfl;
struct ipv6_fl_socklist __rcu **sflp;
struct ip6_flowlabel *fl, *fl1 = NULL;
if (optlen < sizeof(freq))
return -EINVAL;
if (copy_from_user(&freq, optval, sizeof(freq)))
return -EFAULT;
switch (freq.flr_action) {
case IPV6_FL_A_PUT:
if (freq.flr_flags & IPV6_FL_F_REFLECT) {
if (sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
if (!np->repflow)
return -ESRCH;
np->flow_label = 0;
np->repflow = 0;
return 0;
}
spin_lock_bh(&ip6_sk_fl_lock);
for (sflp = &np->ipv6_fl_list;
(sfl = rcu_dereference_protected(*sflp,
lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
sflp = &sfl->next) {
if (sfl->fl->label == freq.flr_label) {
if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
np->flow_label &= ~IPV6_FLOWLABEL_MASK;
*sflp = sfl->next;
spin_unlock_bh(&ip6_sk_fl_lock);
fl_release(sfl->fl);
kfree_rcu(sfl, rcu);
return 0;
}
}
spin_unlock_bh(&ip6_sk_fl_lock);
return -ESRCH;
case IPV6_FL_A_RENEW:
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
if (sfl->fl->label == freq.flr_label) {
err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires);
rcu_read_unlock_bh();
return err;
}
}
rcu_read_unlock_bh();
if (freq.flr_share == IPV6_FL_S_NONE &&
ns_capable(net->user_ns, CAP_NET_ADMIN)) {
fl = fl_lookup(net, freq.flr_label);
if (fl) {
err = fl6_renew(fl, freq.flr_linger, freq.flr_expires);
fl_release(fl);
return err;
}
}
return -ESRCH;
case IPV6_FL_A_GET:
if (freq.flr_flags & IPV6_FL_F_REFLECT) {
struct net *net = sock_net(sk);
if (net->ipv6.sysctl.flowlabel_consistency) {
net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n");
return -EPERM;
}
if (sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
np->repflow = 1;
return 0;
}
if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
return -EINVAL;
if (net->ipv6.sysctl.flowlabel_state_ranges &&
(freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
return -ERANGE;
fl = fl_create(net, sk, &freq, optval, optlen, &err);
if (!fl)
return err;
sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
if (freq.flr_label) {
err = -EEXIST;
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
if (sfl->fl->label == freq.flr_label) {
if (freq.flr_flags&IPV6_FL_F_EXCL) {
rcu_read_unlock_bh();
goto done;
}
fl1 = sfl->fl;
atomic_inc(&fl1->users);
break;
}
}
rcu_read_unlock_bh();
if (!fl1)
fl1 = fl_lookup(net, freq.flr_label);
if (fl1) {
recheck:
err = -EEXIST;
if (freq.flr_flags&IPV6_FL_F_EXCL)
goto release;
err = -EPERM;
if (fl1->share == IPV6_FL_S_EXCL ||
fl1->share != fl->share ||
((fl1->share == IPV6_FL_S_PROCESS) &&
(fl1->owner.pid == fl->owner.pid)) ||
((fl1->share == IPV6_FL_S_USER) &&
uid_eq(fl1->owner.uid, fl->owner.uid)))
goto release;
err = -ENOMEM;
if (!sfl1)
goto release;
if (fl->linger > fl1->linger)
fl1->linger = fl->linger;
if ((long)(fl->expires - fl1->expires) > 0)
fl1->expires = fl->expires;
fl_link(np, sfl1, fl1);
fl_free(fl);
return 0;
release:
fl_release(fl1);
goto done;
}
}
err = -ENOENT;
if (!(freq.flr_flags&IPV6_FL_F_CREATE))
goto done;
err = -ENOMEM;
if (!sfl1)
goto done;
err = mem_check(sk);
if (err != 0)
goto done;
fl1 = fl_intern(net, fl, freq.flr_label);
if (fl1)
goto recheck;
if (!freq.flr_label) {
if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label,
&fl->label, sizeof(fl->label))) {
/* Intentionally ignore fault. */
}
}
fl_link(np, sfl1, fl);
return 0;
default:
return -EINVAL;
}
/*
* Probe all of a vlserver's addresses to find out the best route and to
* query its capabilities.
*/
static bool afs_do_probe_vlserver(struct afs_net *net,
struct afs_vlserver *server,
struct key *key,
unsigned int server_index,
struct afs_error *_e)
{
struct afs_addr_cursor ac = {
.index = 0,
};
struct afs_call *call;
bool in_progress = false;
_enter("%s", server->name);
read_lock(&server->lock);
ac.alist = rcu_dereference_protected(server->addresses,
lockdep_is_held(&server->lock));
read_unlock(&server->lock);
atomic_set(&server->probe_outstanding, ac.alist->nr_addrs);
memset(&server->probe, 0, sizeof(server->probe));
server->probe.rtt = UINT_MAX;
for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
call = afs_vl_get_capabilities(net, &ac, key, server,
server_index);
if (!IS_ERR(call)) {
afs_put_call(call);
in_progress = true;
} else {
afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code);
}
}
if (!in_progress)
afs_vl_probe_done(server);
return in_progress;
}
/*
* Send off probes to all unprobed servers.
*/
int afs_send_vl_probes(struct afs_net *net, struct key *key,
struct afs_vlserver_list *vllist)
{
struct afs_vlserver *server;
struct afs_error e;
bool in_progress = false;
int i;
e.error = 0;
e.responded = false;
for (i = 0; i < vllist->nr_servers; i++) {
server = vllist->servers[i].server;
if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags))
continue;
if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags) &&
afs_do_probe_vlserver(net, server, key, i, &e))
in_progress = true;
}
return in_progress ? 0 : e.error;
}
/*
* Wait for the first as-yet untried server to respond.
*/
int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
unsigned long untried)
{
struct wait_queue_entry *waits;
struct afs_vlserver *server;
unsigned int rtt = UINT_MAX;
bool have_responders = false;
int pref = -1, i;
_enter("%u,%lx", vllist->nr_servers, untried);
/* Only wait for servers that have a probe outstanding. */
for (i = 0; i < vllist->nr_servers; i++) {
if (test_bit(i, &untried)) {
server = vllist->servers[i].server;
if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
__clear_bit(i, &untried);
if (server->probe.responded)
have_responders = true;
}
}
if (have_responders || !untried)
return 0;
waits = kmalloc(array_size(vllist->nr_servers, sizeof(*waits)), GFP_KERNEL);
if (!waits)
return -ENOMEM;
for (i = 0; i < vllist->nr_servers; i++) {
if (test_bit(i, &untried)) {
server = vllist->servers[i].server;
init_waitqueue_entry(&waits[i], current);
add_wait_queue(&server->probe_wq, &waits[i]);
}
}
for (;;) {
bool still_probing = false;
set_current_state(TASK_INTERRUPTIBLE);
for (i = 0; i < vllist->nr_servers; i++) {
if (test_bit(i, &untried)) {
server = vllist->servers[i].server;
if (server->probe.responded)
goto stop;
if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
still_probing = true;
}
}
if (!still_probing || signal_pending(current))
goto stop;
schedule();
}
stop:
set_current_state(TASK_RUNNING);
for (i = 0; i < vllist->nr_servers; i++) {
if (test_bit(i, &untried)) {
server = vllist->servers[i].server;
if (server->probe.responded &&
server->probe.rtt < rtt) {
pref = i;
rtt = server->probe.rtt;
}
remove_wait_queue(&server->probe_wq, &waits[i]);
}
}
kfree(waits);
if (pref == -1 && signal_pending(current))
return -ERESTARTSYS;
if (pref >= 0)
vllist->preferred = pref;
_leave(" = 0 [%u]", pref);
return 0;
}
static int do_ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
int val = 0, err;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
switch (optname) {
case IP_PKTINFO:
case IP_RECVTTL:
case IP_RECVOPTS:
case IP_RECVTOS:
case IP_RETOPTS:
case IP_TOS:
case IP_TTL:
case IP_HDRINCL:
case IP_MTU_DISCOVER:
case IP_RECVERR:
case IP_ROUTER_ALERT:
case IP_FREEBIND:
case IP_PASSSEC:
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
case IP_BIND_ADDRESS_NO_PORT:
case IP_UNICAST_IF:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
case IP_RECVFRAGSIZE:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else if (optlen >= sizeof(char)) {
unsigned char ucval;
if (get_user(ucval, (unsigned char __user *) optval))
return -EFAULT;
val = (int) ucval;
}
}
/* If optlen==0, it is equivalent to val == 0 */
if (optname == IP_ROUTER_ALERT)
return ip_ra_control(sk, val ? 1 : 0, NULL);
if (ip_mroute_opt(optname))
return ip_mroute_setsockopt(sk, optname, optval, optlen);
err = 0;
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
struct ip_options_rcu *old, *opt = NULL;
if (optlen > 40)
goto e_inval;
err = ip_options_get_from_user(sock_net(sk), &opt,
optval, optlen);
if (err)
break;
old = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
if (inet->is_icsk) {
struct inet_connection_sock *icsk = inet_csk(sk);
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
(TCPF_LISTEN | TCPF_CLOSE)) &&
inet->inet_daddr != LOOPBACK4_IPV6)) {
#endif
if (old)
icsk->icsk_ext_hdr_len -= old->opt.optlen;
if (opt)
icsk->icsk_ext_hdr_len += opt->opt.optlen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if IS_ENABLED(CONFIG_IPV6)
}
#endif
}
rcu_assign_pointer(inet->inet_opt, opt);
if (old)
kfree_rcu(old, rcu);
break;
}
case IP_PKTINFO:
if (val)
inet->cmsg_flags |= IP_CMSG_PKTINFO;
else
inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
break;
case IP_RECVTTL:
if (val)
inet->cmsg_flags |= IP_CMSG_TTL;
else
inet->cmsg_flags &= ~IP_CMSG_TTL;
break;
case IP_RECVTOS:
if (val)
inet->cmsg_flags |= IP_CMSG_TOS;
else
inet->cmsg_flags &= ~IP_CMSG_TOS;
break;
case IP_RECVOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RECVOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
break;
case IP_RETOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RETOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
break;
case IP_PASSSEC:
if (val)
inet->cmsg_flags |= IP_CMSG_PASSSEC;
else
inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
break;
case IP_RECVORIGDSTADDR:
if (val)
inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
else
inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
break;
case IP_CHECKSUM:
if (val) {
if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
inet_inc_convert_csum(sk);
inet->cmsg_flags |= IP_CMSG_CHECKSUM;
}
} else {
if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
inet_dec_convert_csum(sk);
inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
}
}
break;
case IP_RECVFRAGSIZE:
if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
goto e_inval;
if (val)
inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE;
else
inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE;
break;
case IP_TOS: /* This sets both TOS and Precedence */
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= inet->tos & INET_ECN_MASK;
}
if (inet->tos != val) {
inet->tos = val;
sk->sk_priority = rt_tos2priority(val);
sk_dst_reset(sk);
}
break;
case IP_TTL:
if (optlen < 1)
goto e_inval;
if (val != -1 && (val < 1 || val > 255))
goto e_inval;
inet->uc_ttl = val;
break;
case IP_HDRINCL:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->hdrincl = val ? 1 : 0;
break;
case IP_NODEFRAG:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->nodefrag = val ? 1 : 0;
break;
case IP_BIND_ADDRESS_NO_PORT:
inet->bind_address_no_port = val ? 1 : 0;
break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
inet->pmtudisc = val;
break;
case IP_RECVERR:
inet->recverr = !!val;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
break;
case IP_MULTICAST_TTL:
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
if (optlen < 1)
goto e_inval;
if (val == -1)
val = 1;
if (val < 0 || val > 255)
goto e_inval;
inet->mc_ttl = val;
break;
case IP_MULTICAST_LOOP:
if (optlen < 1)
goto e_inval;
inet->mc_loop = !!val;
break;
case IP_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
int midx;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
inet->uc_index = 0;
err = 0;
break;
}
dev = dev_get_by_index(sock_net(sk), ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
midx = l3mdev_master_ifindex(dev);
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
(!midx || midx != sk->sk_bound_dev_if))
break;
inet->uc_index = ifindex;
err = 0;
break;
}
case IP_MULTICAST_IF:
{
struct ip_mreqn mreq;
struct net_device *dev = NULL;
int midx;
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
/*
* Check the arguments are allowable
*/
if (optlen < sizeof(struct in_addr))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (optlen >= sizeof(struct ip_mreq)) {
if (copy_from_user(&mreq, optval,
sizeof(struct ip_mreq)))
break;
} else if (optlen >= sizeof(struct in_addr)) {
if (copy_from_user(&mreq.imr_address, optval,
sizeof(struct in_addr)))
break;
}
}
if (!mreq.imr_ifindex) {
if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) {
inet->mc_index = 0;
inet->mc_addr = 0;
err = 0;
break;
}
dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
if (dev)
mreq.imr_ifindex = dev->ifindex;
} else
dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
midx = l3mdev_master_ifindex(dev);
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if &&
(!midx || midx != sk->sk_bound_dev_if))
break;
inet->mc_index = mreq.imr_ifindex;
inet->mc_addr = mreq.imr_address.s_addr;
err = 0;
break;
}
case IP_ADD_MEMBERSHIP:
case IP_DROP_MEMBERSHIP:
{
struct ip_mreqn mreq;
err = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
if (optlen < sizeof(struct ip_mreq))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq)))
break;
}
if (optname == IP_ADD_MEMBERSHIP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case IP_MSFILTER:
{
struct ip_msfilter *msf;
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
msf = memdup_user(optval, optlen);
if (IS_ERR(msf)) {
err = PTR_ERR(msf);
break;
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
kfree(msf);
err = -ENOBUFS;
break;
}
if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) {
kfree(msf);
err = -EINVAL;
break;
}
err = ip_mc_msfilter(sk, msf, 0);
kfree(msf);
break;
}
case IP_BLOCK_SOURCE:
case IP_UNBLOCK_SOURCE:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
{
struct ip_mreq_source mreqs;
int omode, add;
if (optlen != sizeof(struct ip_mreq_source))
goto e_inval;
if (copy_from_user(&mreqs, optval, sizeof(mreqs))) {
err = -EFAULT;
break;
}
if (optname == IP_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == IP_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == IP_ADD_SOURCE_MEMBERSHIP) {
struct ip_mreqn mreq;
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* IP_DROP_SOURCE_MEMBERSHIP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs, 0);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in *psin;
struct ip_mreqn mreq;
if (optlen < sizeof(struct group_req))
goto e_inval;
err = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(greq)))
break;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
goto e_inval;
memset(&mreq, 0, sizeof(mreq));
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add;
if (optlen != sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
err = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET ||
greqs.gsr_source.ss_family != AF_INET) {
err = -EADDRNOTAVAIL;
break;
}
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct ip_mreqn mreq;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs,
greqs.gsr_interface);
break;
}
case MCAST_MSFILTER:
{
struct sockaddr_in *psin;
struct ip_msfilter *msf = NULL;
struct group_filter *gsf = NULL;
int msize, i, ifindex;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
gsf = memdup_user(optval, optlen);
if (IS_ERR(gsf)) {
err = PTR_ERR(gsf);
break;
}
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
err = -EINVAL;
goto mc_msf_out;
}
msize = IP_MSFILTER_SIZE(gsf->gf_numsrc);
msf = kmalloc(msize, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
ifindex = gsf->gf_interface;
psin = (struct sockaddr_in *)&gsf->gf_group;
if (psin->sin_family != AF_INET) {
err = -EADDRNOTAVAIL;
goto mc_msf_out;
}
msf->imsf_multiaddr = psin->sin_addr.s_addr;
msf->imsf_interface = 0;
msf->imsf_fmode = gsf->gf_fmode;
msf->imsf_numsrc = gsf->gf_numsrc;
err = -EADDRNOTAVAIL;
for (i = 0; i < gsf->gf_numsrc; ++i) {
psin = (struct sockaddr_in *)&gsf->gf_slist[i];
if (psin->sin_family != AF_INET)
goto mc_msf_out;
msf->imsf_slist[i] = psin->sin_addr.s_addr;
}
kfree(gsf);
gsf = NULL;
err = ip_mc_msfilter(sk, msf, ifindex);
mc_msf_out:
kfree(msf);
kfree(gsf);
break;
}
case IP_MULTICAST_ALL:
if (optlen < 1)
goto e_inval;
if (val != 0 && val != 1)
goto e_inval;
inet->mc_all = val;
break;
case IP_FREEBIND:
if (optlen < 1)
goto e_inval;
inet->freebind = !!val;
break;
case IP_IPSEC_POLICY:
case IP_XFRM_POLICY:
err = -EPERM;
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
break;
err = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IP_TRANSPARENT:
if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
err = -EPERM;
break;
}
if (optlen < 1)
goto e_inval;
inet->transparent = !!val;
break;
case IP_MINTTL:
if (optlen < 1)
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
inet->min_ttl = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return err;
e_inval:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return -EINVAL;
}
/* Called from syscall or from eBPF program */
static int trie_update_elem(struct bpf_map *map,
void *_key, void *value, u64 flags)
{
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL;
struct lpm_trie_node __rcu **slot;
struct bpf_lpm_trie_key *key = _key;
unsigned long irq_flags;
unsigned int next_bit;
size_t matchlen = 0;
int ret = 0;
if (unlikely(flags > BPF_EXIST))
return -EINVAL;
if (key->prefixlen > trie->max_prefixlen)
return -EINVAL;
raw_spin_lock_irqsave(&trie->lock, irq_flags);
/* Allocate and fill a new node */
if (trie->n_entries == trie->map.max_entries) {
ret = -ENOSPC;
goto out;
}
new_node = lpm_trie_node_alloc(trie, value);
if (!new_node) {
ret = -ENOMEM;
goto out;
}
trie->n_entries++;
new_node->prefixlen = key->prefixlen;
RCU_INIT_POINTER(new_node->child[0], NULL);
RCU_INIT_POINTER(new_node->child[1], NULL);
memcpy(new_node->data, key->data, trie->data_size);
/* Now find a slot to attach the new node. To do that, walk the tree
* from the root and match as many bits as possible for each node until
* we either find an empty slot or a slot that needs to be replaced by
* an intermediate node.
*/
slot = &trie->root;
while ((node = rcu_dereference_protected(*slot,
lockdep_is_held(&trie->lock)))) {
matchlen = longest_prefix_match(trie, node, key);
if (node->prefixlen != matchlen ||
node->prefixlen == key->prefixlen ||
node->prefixlen == trie->max_prefixlen)
break;
next_bit = extract_bit(key->data, node->prefixlen);
slot = &node->child[next_bit];
}
/* If the slot is empty (a free child pointer or an empty root),
* simply assign the @new_node to that slot and be done.
*/
if (!node) {
rcu_assign_pointer(*slot, new_node);
goto out;
}
/* If the slot we picked already exists, replace it with @new_node
* which already has the correct data array set.
*/
if (node->prefixlen == matchlen) {
new_node->child[0] = node->child[0];
new_node->child[1] = node->child[1];
if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
trie->n_entries--;
rcu_assign_pointer(*slot, new_node);
kfree_rcu(node, rcu);
goto out;
}
/* If the new node matches the prefix completely, it must be inserted
* as an ancestor. Simply insert it between @node and *@slot.
*/
if (matchlen == key->prefixlen) {
next_bit = extract_bit(node->data, matchlen);
rcu_assign_pointer(new_node->child[next_bit], node);
rcu_assign_pointer(*slot, new_node);
goto out;
}
im_node = lpm_trie_node_alloc(trie, NULL);
if (!im_node) {
ret = -ENOMEM;
goto out;
}
im_node->prefixlen = matchlen;
im_node->flags |= LPM_TREE_NODE_FLAG_IM;
memcpy(im_node->data, node->data, trie->data_size);
/* Now determine which child to install in which slot */
if (extract_bit(key->data, matchlen)) {
rcu_assign_pointer(im_node->child[0], node);
rcu_assign_pointer(im_node->child[1], new_node);
} else {
rcu_assign_pointer(im_node->child[0], new_node);
rcu_assign_pointer(im_node->child[1], node);
}
/* Finally, assign the intermediate node to the determined spot */
rcu_assign_pointer(*slot, im_node);
out:
if (ret) {
if (new_node)
trie->n_entries--;
kfree(new_node);
kfree(im_node);
}
raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
return ret;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
__be16 orig_sport, orig_dport;
__be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
struct ip_options_rcu *inet_opt;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
inet_opt = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
if (inet_opt != NULL && inet_opt->opt.srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet_opt->opt.faddr;
}
orig_sport = inet->inet_sport;
orig_dport = usin->sin_port;
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
orig_sport, orig_dport, sk);
if (IS_ERR(rt))
return PTR_ERR(rt);
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet_opt == NULL || !inet_opt->opt.srr)
daddr = fl4->daddr;
if (inet->inet_saddr == 0)
inet->inet_saddr = fl4->saddr;
sk_rcv_saddr_set(sk, inet->inet_saddr);
inet->inet_dport = usin->sin_port;
sk_daddr_set(sk, daddr);
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto failure;
}
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
inet->inet_id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
goto out;
}
static ssize_t iwl_dbgfs_mac_params_read(struct file *file,
char __user *user_buf,
size_t count, loff_t *ppos)
{
struct ieee80211_vif *vif = file->private_data;
struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
struct iwl_mvm *mvm = mvmvif->mvm;
u8 ap_sta_id;
struct ieee80211_chanctx_conf *chanctx_conf;
char buf[512];
int bufsz = sizeof(buf);
int pos = 0;
int i;
mutex_lock(&mvm->mutex);
ap_sta_id = mvmvif->ap_sta_id;
switch (ieee80211_vif_type_p2p(vif)) {
case NL80211_IFTYPE_ADHOC:
pos += scnprintf(buf+pos, bufsz-pos, "type: ibss\n");
break;
case NL80211_IFTYPE_STATION:
pos += scnprintf(buf+pos, bufsz-pos, "type: bss\n");
break;
case NL80211_IFTYPE_AP:
pos += scnprintf(buf+pos, bufsz-pos, "type: ap\n");
break;
case NL80211_IFTYPE_P2P_CLIENT:
pos += scnprintf(buf+pos, bufsz-pos, "type: p2p client\n");
break;
case NL80211_IFTYPE_P2P_GO:
pos += scnprintf(buf+pos, bufsz-pos, "type: p2p go\n");
break;
case NL80211_IFTYPE_P2P_DEVICE:
pos += scnprintf(buf+pos, bufsz-pos, "type: p2p dev\n");
break;
default:
break;
}
pos += scnprintf(buf+pos, bufsz-pos, "mac id/color: %d / %d\n",
mvmvif->id, mvmvif->color);
pos += scnprintf(buf+pos, bufsz-pos, "bssid: %pM\n",
vif->bss_conf.bssid);
pos += scnprintf(buf+pos, bufsz-pos, "QoS:\n");
for (i = 0; i < ARRAY_SIZE(mvmvif->queue_params); i++)
pos += scnprintf(buf+pos, bufsz-pos,
"\t%d: txop:%d - cw_min:%d - cw_max = %d - aifs = %d upasd = %d\n",
i, mvmvif->queue_params[i].txop,
mvmvif->queue_params[i].cw_min,
mvmvif->queue_params[i].cw_max,
mvmvif->queue_params[i].aifs,
mvmvif->queue_params[i].uapsd);
if (vif->type == NL80211_IFTYPE_STATION &&
ap_sta_id != IWL_MVM_STATION_COUNT) {
struct ieee80211_sta *sta;
sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[ap_sta_id],
lockdep_is_held(&mvm->mutex));
if (!IS_ERR_OR_NULL(sta)) {
struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
pos += scnprintf(buf+pos, bufsz-pos,
"ap_sta_id %d - reduced Tx power %d\n",
ap_sta_id,
mvm_sta->bt_reduced_txpower);
}
}
rcu_read_lock();
chanctx_conf = rcu_dereference(vif->chanctx_conf);
if (chanctx_conf)
pos += scnprintf(buf+pos, bufsz-pos,
"idle rx chains %d, active rx chains: %d\n",
chanctx_conf->rx_chains_static,
chanctx_conf->rx_chains_dynamic);
rcu_read_unlock();
mutex_unlock(&mvm->mutex);
return simple_read_from_buffer(user_buf, count, ppos, buf, pos);
}
static inline struct sta_info *
next_hop_deref_protected(struct mesh_path *mpath)
{
return rcu_dereference_protected(mpath->next_hop,
lockdep_is_held(&mpath->state_lock));
}
static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
usin->sin6_addr = flowlabel->dst;
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
np->daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
* DCCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &dccp_ipv6_mapped;
sk->sk_backlog_rcv = dccp_v4_do_rcv;
err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &dccp_ipv6_af_ops;
sk->sk_backlog_rcv = dccp_v6_do_rcv;
goto failure;
}
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr);
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = np->daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
np->rcv_saddr = *saddr;
}
/* set the source address */
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet6_hash_connect(&dccp_death_row, sk);
if (err)
goto late_failure;
dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
err = dccp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
int val, valbool;
int retv = -ENOPROTOOPT;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
if (!optval)
val = 0;
else {
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else
val = 0;
}
valbool = (val != 0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IPV6_ADDRFORM:
if (optlen < sizeof(int))
goto e_inval;
if (val == PF_INET) {
struct ipv6_txoptions *opt;
struct sk_buff *pktopt;
if (sk->sk_type == SOCK_RAW)
break;
if (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_UDPLITE) {
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET6) {
retv = -EBUSY;
break;
}
} else if (sk->sk_protocol != IPPROTO_TCP)
break;
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
}
if (ipv6_only_sock(sk) ||
!ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
retv = -EADDRNOTAVAIL;
break;
}
fl6_free_socklist(sk);
__ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
* remove it from the refcnt debug socks count in the
* original family...
*/
sk_refcnt_debug_dec(sk);
if (sk->sk_protocol == IPPROTO_TCP) {
struct inet_connection_sock *icsk = inet_csk(sk);
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);
local_bh_enable();
sk->sk_prot = &tcp_prot;
icsk->icsk_af_ops = &ipv4_specific;
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
if (sk->sk_protocol == IPPROTO_UDPLITE)
prot = &udplite_prot;
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);
local_bh_enable();
sk->sk_prot = prot;
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
opt = xchg((__force struct ipv6_txoptions **)&np->opt,
NULL);
if (opt) {
atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
txopt_put(opt);
}
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
sk->sk_destruct = inet_sock_destruct;
/*
* ... and add it to the refcnt debug socks count
* in the new family. -acme
*/
sk_refcnt_debug_inc(sk);
module_put(THIS_MODULE);
retv = 0;
break;
}
goto e_inval;
case IPV6_V6ONLY:
if (optlen < sizeof(int) ||
inet_sk(sk)->inet_num)
goto e_inval;
sk->sk_ipv6only = valbool;
retv = 0;
break;
case IPV6_RECVPKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxinfo = valbool;
retv = 0;
break;
case IPV6_2292PKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxoinfo = valbool;
retv = 0;
break;
case IPV6_RECVHOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxhlim = valbool;
retv = 0;
break;
case IPV6_2292HOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxohlim = valbool;
retv = 0;
break;
case IPV6_RECVRTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.srcrt = valbool;
retv = 0;
break;
case IPV6_2292RTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.osrcrt = valbool;
retv = 0;
break;
case IPV6_RECVHOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.hopopts = valbool;
retv = 0;
break;
case IPV6_2292HOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.ohopopts = valbool;
retv = 0;
break;
case IPV6_RECVDSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.dstopts = valbool;
retv = 0;
break;
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.odstopts = valbool;
retv = 0;
break;
case IPV6_TCLASS:
if (optlen < sizeof(int))
goto e_inval;
if (val < -1 || val > 0xff)
goto e_inval;
/* RFC 3542, 6.5: default traffic class of 0x0 */
if (val == -1)
val = 0;
np->tclass = val;
retv = 0;
break;
case IPV6_RECVTCLASS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxtclass = valbool;
retv = 0;
break;
case IPV6_FLOWINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxflow = valbool;
retv = 0;
break;
case IPV6_RECVPATHMTU:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxpmtu = valbool;
retv = 0;
break;
case IPV6_TRANSPARENT:
if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
!ns_capable(net->user_ns, CAP_NET_RAW)) {
retv = -EPERM;
break;
}
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
inet_sk(sk)->transparent = valbool;
retv = 0;
break;
case IPV6_RECVORIGDSTADDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxorigdstaddr = valbool;
retv = 0;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
/* remove any sticky options header with a zero option
* length, per RFC3542.
*/
if (optlen == 0)
optval = NULL;
else if (!optval)
goto e_inval;
else if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 || optlen > 8 * 255)
goto e_inval;
/* hop-by-hop / destination options are privileged option */
retv = -EPERM;
if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
break;
opt = rcu_dereference_protected(np->opt,
lockdep_sock_is_held(sk));
opt = ipv6_renew_options(sk, opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
}
/* routing header option needs extra check */
retv = -EINVAL;
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
goto sticky_done;
break;
#endif
case IPV6_SRCRT_TYPE_4:
{
struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)
opt->srcrt;
if (!seg6_validate_srh(srh, optlen))
goto sticky_done;
break;
}
default:
goto sticky_done;
}
}
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
if (opt) {
atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
txopt_put(opt);
}
break;
}
case IPV6_PKTINFO:
{
struct in6_pktinfo pkt;
if (optlen == 0)
goto e_inval;
else if (optlen < sizeof(struct in6_pktinfo) || !optval)
goto e_inval;
if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
retv = -EFAULT;
break;
}
if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
retv = 0;
break;
}
case IPV6_2292PKTOPTIONS:
{
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
struct sockcm_cookie sockc_junk;
struct ipcm6_cookie ipc6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
if (optlen == 0)
goto update;
/* 1K is probably excessive
* 1K is surely not enough, 2K per standard header is 16K.
*/
retv = -EINVAL;
if (optlen > 64*1024)
break;
opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
retv = -ENOBUFS;
if (!opt)
break;
memset(opt, 0, sizeof(*opt));
atomic_set(&opt->refcnt, 1);
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
goto done;
msg.msg_controllen = optlen;
msg.msg_control = (void *)(opt+1);
ipc6.opt = opt;
retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6, &sockc_junk);
if (retv)
goto done;
update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
if (opt) {
atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
txopt_put(opt);
}
break;
}
case IPV6_UNICAST_HOPS:
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->hop_limit = val;
retv = 0;
break;
case IPV6_MULTICAST_HOPS:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
retv = 0;
break;
case IPV6_MULTICAST_LOOP:
if (optlen < sizeof(int))
goto e_inval;
if (val != valbool)
goto e_inval;
np->mc_loop = valbool;
retv = 0;
break;
case IPV6_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
np->ucast_oif = 0;
retv = 0;
break;
}
dev = dev_get_by_index(net, ifindex);
retv = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
retv = -EINVAL;
if (sk->sk_bound_dev_if)
break;
np->ucast_oif = ifindex;
retv = 0;
break;
}
case IPV6_MULTICAST_IF:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val) {
struct net_device *dev;
int midx;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, val);
if (!dev) {
rcu_read_unlock();
retv = -ENODEV;
break;
}
midx = l3mdev_master_ifindex_rcu(dev);
rcu_read_unlock();
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != val &&
(!midx || midx != sk->sk_bound_dev_if))
goto e_inval;
}
np->mcast_oif = val;
retv = 0;
break;
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_ADD_MEMBERSHIP)
retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
else
retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
break;
}
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_JOIN_ANYCAST)
retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
else
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in6 *psin6;
if (optlen < sizeof(struct group_req))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(struct group_req)))
break;
if (greq.gr_group.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
psin6 = (struct sockaddr_in6 *)&greq.gr_group;
if (optname == MCAST_JOIN_GROUP)
retv = ipv6_sock_mc_join(sk, greq.gr_interface,
&psin6->sin6_addr);
else
retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
&psin6->sin6_addr);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
int omode, add;
if (optlen < sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
retv = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET6 ||
greqs.gsr_source.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
&psin6->sin6_addr);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
retv = ip6_mc_source(add, omode, sk, &greqs);
break;
}
case MCAST_MSFILTER:
{
struct group_filter *gsf;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
retv = -ENOBUFS;
break;
}
gsf = kmalloc(optlen, GFP_KERNEL);
if (!gsf) {
retv = -ENOBUFS;
break;
}
retv = -EFAULT;
if (copy_from_user(gsf, optval, optlen)) {
kfree(gsf);
break;
}
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffffU ||
gsf->gf_numsrc > sysctl_mld_max_msf) {
kfree(gsf);
retv = -ENOBUFS;
break;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
kfree(gsf);
retv = -EINVAL;
break;
}
retv = ip6_mc_msfilter(sk, gsf);
kfree(gsf);
break;
}
case IPV6_ROUTER_ALERT:
if (optlen < sizeof(int))
goto e_inval;
retv = ip6_ra_control(sk, val);
break;
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
goto e_inval;
if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
goto e_inval;
np->pmtudisc = val;
retv = 0;
break;
case IPV6_MTU:
if (optlen < sizeof(int))
goto e_inval;
if (val && val < IPV6_MIN_MTU)
goto e_inval;
np->frag_size = val;
retv = 0;
break;
case IPV6_RECVERR:
if (optlen < sizeof(int))
goto e_inval;
np->recverr = valbool;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
retv = 0;
break;
case IPV6_FLOWINFO_SEND:
if (optlen < sizeof(int))
goto e_inval;
np->sndflow = valbool;
retv = 0;
break;
case IPV6_FLOWLABEL_MGR:
retv = ipv6_flowlabel_opt(sk, optval, optlen);
break;
case IPV6_IPSEC_POLICY:
case IPV6_XFRM_POLICY:
retv = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IPV6_ADDR_PREFERENCES:
{
unsigned int pref = 0;
unsigned int prefmask = ~0;
if (optlen < sizeof(int))
goto e_inval;
retv = -EINVAL;
/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
switch (val & (IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP|
IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
case IPV6_PREFER_SRC_PUBLIC:
pref |= IPV6_PREFER_SRC_PUBLIC;
break;
case IPV6_PREFER_SRC_TMP:
pref |= IPV6_PREFER_SRC_TMP;
break;
case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
break;
case 0:
goto pref_skip_pubtmp;
default:
goto e_inval;
}
prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP);
pref_skip_pubtmp:
/* check HOME/COA conflicts */
switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
case IPV6_PREFER_SRC_HOME:
break;
case IPV6_PREFER_SRC_COA:
pref |= IPV6_PREFER_SRC_COA;
case 0:
goto pref_skip_coa;
default:
goto e_inval;
}
prefmask &= ~IPV6_PREFER_SRC_COA;
pref_skip_coa:
/* check CGA/NONCGA conflicts */
switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
case IPV6_PREFER_SRC_CGA:
case IPV6_PREFER_SRC_NONCGA:
case 0:
break;
default:
goto e_inval;
}
np->srcprefs = (np->srcprefs & prefmask) | pref;
retv = 0;
break;
}
case IPV6_MINHOPCOUNT:
if (optlen < sizeof(int))
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
np->min_hopcount = val;
retv = 0;
break;
case IPV6_DONTFRAG:
np->dontfrag = valbool;
retv = 0;
break;
case IPV6_AUTOFLOWLABEL:
np->autoflowlabel = valbool;
retv = 0;
break;
case IPV6_RECVFRAGSIZE:
np->rxopt.bits.recvfragsize = valbool;
retv = 0;
break;
}
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return retv;
e_inval:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return -EINVAL;
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx_big(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned out, in, log, s;
int head;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr hdr = {
.flags = 0,
.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
return;
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
hdr_size = vq->vhost_hlen;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
vq_log, &log);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* OK, now we need to know about added descriptors. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (out) {
vq_err(vq, "Unexpected descriptor format for RX: "
"out %d, int %d\n",
out, in);
break;
}
/* Skip header. TODO: support TSO/mergeable rx buffers. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
msg.msg_iovlen = in;
len = iov_length(vq->iov, in);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for RX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
break;
}
err = sock->ops->recvmsg(NULL, sock, &msg,
len, MSG_DONTWAIT | MSG_TRUNC);
/* TODO: Check specific error and bomb out unless EAGAIN? */
if (err < 0) {
vhost_discard_vq_desc(vq, 1);
break;
}
/* TODO: Should check and handle checksum. */
if (err > len) {
pr_debug("Discarded truncated rx packet: "
" len %d > %zd\n", err, len);
vhost_discard_vq_desc(vq, 1);
continue;
}
len = err;
err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
if (err) {
vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
vq->iov->iov_base, err);
break;
}
len += hdr_size;
vhost_add_used_and_signal(&net->dev, vq, head, len);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, len);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_rx_mergeable(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
unsigned uninitialized_var(in), log;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
.msg_controllen = 0,
.msg_iov = vq->iov,
.msg_flags = MSG_DONTWAIT,
};
struct virtio_net_hdr_mrg_rxbuf hdr = {
.hdr.flags = 0,
.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
};
size_t total_len = 0;
int err, headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
struct socket *sock = rcu_dereference(vq->private_data);
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
return;
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
vhost_hlen = vq->vhost_hlen;
sock_hlen = vq->sock_hlen;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
while ((sock_len = peek_head_len(sock->sk))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
headcount = get_rx_bufs(vq, vq->heads, vhost_len,
&in, vq_log, &log);
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
vhost_disable_notify(vq);
continue;
}
/* Nothing new? Wait for eventfd to tell us
* they refilled. */
break;
}
/* We don't need to be notified again. */
if (unlikely((vhost_hlen)))
/* Skip header. TODO: support TSO. */
move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
else
/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
* needed because sendmsg can modify msg_iov. */
copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
msg.msg_iovlen = in;
err = sock->ops->recvmsg(NULL, sock, &msg,
sock_len, MSG_DONTWAIT | MSG_TRUNC);
/* Userspace might have consumed the packet meanwhile:
* it's not supposed to do this usually, but might be hard
* to prevent. Discard data we got (if any) and keep going. */
if (unlikely(err != sock_len)) {
pr_debug("Discarded rx packet: "
" len %d, expected %zd\n", err, sock_len);
vhost_discard_vq_desc(vq, headcount);
continue;
}
if (unlikely(vhost_hlen) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&hdr, 0,
vhost_hlen)) {
vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
vq->iov->iov_base);
break;
}
/* TODO: Should check and handle checksum. */
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
offsetof(typeof(hdr), num_buffers),
sizeof hdr.num_buffers)) {
vq_err(vq, "Failed num_buffers write");
vhost_discard_vq_desc(vq, headcount);
break;
}
vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
headcount);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
static void handle_rx(struct vhost_net *net)
{
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF))
handle_rx_mergeable(net);
else
handle_rx_big(net);
}
static void handle_tx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_tx(net);
}
static void handle_rx_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
handle_rx(net);
}
static void handle_tx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_TX].work);
handle_tx(net);
}
static void handle_rx_net(struct vhost_work *work)
{
struct vhost_net *net = container_of(work, struct vhost_net,
poll[VHOST_NET_VQ_RX].work);
handle_rx(net);
}
static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
struct vhost_dev *dev;
int r;
if (!n)
return -ENOMEM;
dev = &n->dev;
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX);
if (r < 0) {
kfree(n);
return r;
}
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
f->private_data = n;
return 0;
}
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
if (!vq->private_data)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
tx_poll_stop(n);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
} else
vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
}
static void vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (!sock)
return;
if (vq == n->vqs + VHOST_NET_VQ_TX) {
n->tx_poll_state = VHOST_NET_POLL_STOPPED;
tx_poll_start(n, sock);
} else
vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct socket *sock;
mutex_lock(&vq->mutex);
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, NULL);
mutex_unlock(&vq->mutex);
return sock;
}
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->dev.vqs[index].poll);
}
static void vhost_net_flush(struct vhost_net *n)
{
vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
}
static int vhost_net_release(struct inode *inode, struct file *f)
{
struct vhost_net *n = f->private_data;
struct socket *tx_sock;
struct socket *rx_sock;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
vhost_dev_cleanup(&n->dev);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
kfree(n);
return 0;
}
static struct socket *get_raw_socket(int fd)
{
struct {
struct sockaddr_ll sa;
char buf[MAX_ADDR_LEN];
} uaddr;
int uaddr_len = sizeof uaddr, r;
struct socket *sock = sockfd_lookup(fd, &r);
if (!sock)
return ERR_PTR(-ENOTSOCK);
/* Parameter checking */
if (sock->sk->sk_type != SOCK_RAW) {
r = -ESOCKTNOSUPPORT;
goto err;
}
r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
&uaddr_len, 0);
if (r)
goto err;
if (uaddr.sa.sll_family != AF_PACKET) {
r = -EPFNOSUPPORT;
goto err;
}
return sock;
err:
fput(sock->file);
return ERR_PTR(r);
}
static struct socket *get_tap_socket(int fd)
{
struct file *file = fget(fd);
struct socket *sock;
if (!file)
return ERR_PTR(-EBADF);
sock = tun_get_socket(file);
if (!IS_ERR(sock))
return sock;
sock = macvtap_get_socket(file);
if (IS_ERR(sock))
fput(file);
return sock;
}
static struct socket *get_socket(int fd)
{
struct socket *sock;
/* special case to disable backend */
if (fd == -1)
return NULL;
sock = get_raw_socket(fd);
if (!IS_ERR(sock))
return sock;
sock = get_tap_socket(fd);
if (!IS_ERR(sock))
return sock;
return ERR_PTR(-ENOTSOCK);
}
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
int r;
mutex_lock(&n->dev.mutex);
r = vhost_dev_check_owner(&n->dev);
if (r)
goto err;
if (index >= VHOST_NET_VQ_MAX) {
r = -ENOBUFS;
goto err;
}
vq = n->vqs + index;
mutex_lock(&vq->mutex);
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
goto err_vq;
}
sock = get_socket(fd);
if (IS_ERR(sock)) {
r = PTR_ERR(sock);
goto err_vq;
}
/* start polling new socket */
oldsock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (sock != oldsock) {
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, sock);
vhost_net_enable_vq(n, vq);
}
mutex_unlock(&vq->mutex);
if (oldsock) {
vhost_net_flush_vq(n, index);
fput(oldsock->file);
}
mutex_unlock(&n->dev.mutex);
return 0;
err_vq:
mutex_unlock(&vq->mutex);
err:
mutex_unlock(&n->dev.mutex);
return r;
}
static long vhost_net_reset_owner(struct vhost_net *n)
{
struct socket *tx_sock = NULL;
struct socket *rx_sock = NULL;
long err;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
err = vhost_dev_reset_owner(&n->dev);
done:
mutex_unlock(&n->dev.mutex);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
fput(rx_sock->file);
return err;
}
static int vhost_net_set_features(struct vhost_net *n, u64 features)
{
size_t vhost_hlen, sock_hlen, hdr_len;
int i;
hdr_len = (features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ?
sizeof(struct virtio_net_hdr_mrg_rxbuf) :
sizeof(struct virtio_net_hdr);
if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
/* vhost provides vnet_hdr */
vhost_hlen = hdr_len;
sock_hlen = 0;
} else {
/* socket provides vnet_hdr */
vhost_hlen = 0;
sock_hlen = hdr_len;
}
mutex_lock(&n->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&n->dev)) {
mutex_unlock(&n->dev.mutex);
return -EFAULT;
}
n->dev.acked_features = features;
smp_wmb();
for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
mutex_lock(&n->vqs[i].mutex);
n->vqs[i].vhost_hlen = vhost_hlen;
n->vqs[i].sock_hlen = sock_hlen;
mutex_unlock(&n->vqs[i].mutex);
}
vhost_net_flush(n);
mutex_unlock(&n->dev.mutex);
return 0;
}
/* Process one complete nfnetlink message. */
static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
const struct nfnl_callback *nc;
const struct nfnetlink_subsystem *ss;
int type, err;
/* All the messages must at least contain nfgenmsg */
if (nlmsg_len(nlh) < sizeof(struct nfgenmsg))
return 0;
type = nlh->nlmsg_type;
replay:
rcu_read_lock();
ss = nfnetlink_get_subsys(type);
if (!ss) {
#ifdef CONFIG_MODULES
rcu_read_unlock();
request_module("nfnetlink-subsys-%d", NFNL_SUBSYS_ID(type));
rcu_read_lock();
ss = nfnetlink_get_subsys(type);
if (!ss)
#endif
{
rcu_read_unlock();
return -EINVAL;
}
}
nc = nfnetlink_find_client(type, ss);
if (!nc) {
rcu_read_unlock();
return -EINVAL;
}
{
int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type);
struct nlattr *cda[ss->cb[cb_id].attr_count + 1];
struct nlattr *attr = (void *)nlh + min_len;
int attrlen = nlh->nlmsg_len - min_len;
__u8 subsys_id = NFNL_SUBSYS_ID(type);
err = nla_parse(cda, ss->cb[cb_id].attr_count,
attr, attrlen, ss->cb[cb_id].policy);
if (err < 0) {
rcu_read_unlock();
return err;
}
if (nc->call_rcu) {
err = nc->call_rcu(net->nfnl, skb, nlh,
(const struct nlattr **)cda);
rcu_read_unlock();
} else {
rcu_read_unlock();
nfnl_lock(subsys_id);
if (rcu_dereference_protected(table[subsys_id].subsys,
lockdep_is_held(&table[subsys_id].mutex)) != ss ||
nfnetlink_find_client(type, ss) != nc)
err = -EAGAIN;
else if (nc->call)
err = nc->call(net->nfnl, skb, nlh,
(const struct nlattr **)cda);
else
err = -EINVAL;
nfnl_unlock(subsys_id);
}
if (err == -EAGAIN)
goto replay;
return err;
}
}
/**
* dns_query - Query the DNS
* @type: Query type (or NULL for straight host->IP lookup)
* @name: Name to look up
* @namelen: Length of name
* @options: Request options (or NULL if no options)
* @_result: Where to place the returned data.
* @_expiry: Where to store the result expiry time (or NULL)
*
* The data will be returned in the pointer at *result, and the caller is
* responsible for freeing it.
*
* The description should be of the form "[<query_type>:]<domain_name>", and
* the options need to be appropriate for the query type requested. If no
* query_type is given, then the query is a straight hostname to IP address
* lookup.
*
* The DNS resolution lookup is performed by upcalling to userspace by way of
* requesting a key of type dns_resolver.
*
* Returns the size of the result on success, -ve error code otherwise.
*/
int dns_query(const char *type, const char *name, size_t namelen,
const char *options, char **_result, time_t *_expiry)
{
struct key *rkey;
struct user_key_payload *upayload;
const struct cred *saved_cred;
size_t typelen, desclen;
char *desc, *cp;
int ret, len;
kenter("%s,%*.*s,%zu,%s",
type, (int)namelen, (int)namelen, name, namelen, options);
if (!name || namelen == 0 || !_result)
return -EINVAL;
/* construct the query key description as "[<type>:]<name>" */
typelen = 0;
desclen = 0;
if (type) {
typelen = strlen(type);
if (typelen < 1)
return -EINVAL;
desclen += typelen + 1;
}
if (!namelen)
namelen = strnlen(name, 256);
if (namelen < 3 || namelen > 255)
return -EINVAL;
desclen += namelen + 1;
desc = kmalloc(desclen, GFP_KERNEL);
if (!desc)
return -ENOMEM;
cp = desc;
if (type) {
memcpy(cp, type, typelen);
cp += typelen;
*cp++ = ':';
}
memcpy(cp, name, namelen);
cp += namelen;
*cp = '\0';
if (!options)
options = "";
kdebug("call request_key(,%s,%s)", desc, options);
/* make the upcall, using special credentials to prevent the use of
* add_key() to preinstall malicious redirections
*/
saved_cred = override_creds(dns_resolver_cache);
rkey = request_key(&key_type_dns_resolver, desc, options);
revert_creds(saved_cred);
kfree(desc);
if (IS_ERR(rkey)) {
ret = PTR_ERR(rkey);
goto out;
}
down_read(&rkey->sem);
set_bit(KEY_FLAG_ROOT_CAN_INVAL, &rkey->flags);
rkey->perm |= KEY_USR_VIEW;
ret = key_validate(rkey);
if (ret < 0)
goto put;
/* If the DNS server gave an error, return that to the caller */
ret = rkey->type_data.x[0];
if (ret)
goto put;
upayload = rcu_dereference_protected(rkey->payload.data,
lockdep_is_held(&rkey->sem));
len = upayload->datalen;
ret = -ENOMEM;
*_result = kmalloc(len + 1, GFP_KERNEL);
if (!*_result)
goto put;
memcpy(*_result, upayload->data, len);
(*_result)[len] = '\0';
if (_expiry)
*_expiry = rkey->expiry;
ret = len;
put:
up_read(&rkey->sem);
key_put(rkey);
out:
kleave(" = %d", ret);
return ret;
}
/*
* connection-level Rx packet processor
*/
static int rxrpc_process_event(struct rxrpc_connection *conn,
struct sk_buff *skb,
u32 *_abort_code)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
__be32 wtmp;
u32 abort_code;
int loop, ret;
if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
_leave(" = -ECONNABORTED [%u]", conn->state);
return -ECONNABORTED;
}
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
case RXRPC_PACKET_TYPE_ACK:
rxrpc_conn_retransmit_call(conn, skb,
sp->hdr.cid & RXRPC_CHANNELMASK);
return 0;
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
return 0;
case RXRPC_PACKET_TYPE_ABORT:
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&wtmp, sizeof(wtmp)) < 0) {
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
tracepoint_string("bad_abort"));
return -EPROTO;
}
abort_code = ntohl(wtmp);
_proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code);
conn->error = -ECONNABORTED;
conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
return conn->security->respond_to_challenge(conn, skb,
_abort_code);
case RXRPC_PACKET_TYPE_RESPONSE:
ret = conn->security->verify_response(conn, skb, _abort_code);
if (ret < 0)
return ret;
ret = conn->security->init_connection_security(conn);
if (ret < 0)
return ret;
ret = conn->security->prime_packet_security(conn);
if (ret < 0)
return ret;
spin_lock(&conn->channel_lock);
spin_lock(&conn->state_lock);
if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
conn->state = RXRPC_CONN_SERVICE;
spin_unlock(&conn->state_lock);
for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
rxrpc_call_is_secure(
rcu_dereference_protected(
conn->channels[loop].call,
lockdep_is_held(&conn->channel_lock)));
} else {
spin_unlock(&conn->state_lock);
}
spin_unlock(&conn->channel_lock);
return 0;
default:
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
tracepoint_string("bad_conn_pkt"));
return -EPROTO;
}
}
static int rps_sock_flow_sysctl(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int orig_size, size;
int ret, i;
ctl_table tmp = {
.data = &size,
.maxlen = sizeof(size),
.mode = table->mode
};
struct rps_sock_flow_table *orig_sock_table, *sock_table;
static DEFINE_MUTEX(sock_flow_mutex);
mutex_lock(&sock_flow_mutex);
orig_sock_table = rcu_dereference_protected(rps_sock_flow_table,
lockdep_is_held(&sock_flow_mutex));
size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0;
ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
if (write) {
if (size) {
if (size > 1<<30) {
/* Enforce limit to prevent overflow */
mutex_unlock(&sock_flow_mutex);
return -EINVAL;
}
size = roundup_pow_of_two(size);
if (size != orig_size) {
sock_table =
vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size));
if (!sock_table) {
mutex_unlock(&sock_flow_mutex);
return -ENOMEM;
}
sock_table->mask = size - 1;
} else
sock_table = orig_sock_table;
for (i = 0; i < size; i++)
sock_table->ents[i] = RPS_NO_CPU;
} else
sock_table = NULL;
if (sock_table != orig_sock_table) {
rcu_assign_pointer(rps_sock_flow_table, sock_table);
if (sock_table)
static_key_slow_inc(&rps_needed);
if (orig_sock_table) {
static_key_slow_dec(&rps_needed);
synchronize_rcu();
vfree(orig_sock_table);
}
}
}
mutex_unlock(&sock_flow_mutex);
return ret;
}
#endif /* CONFIG_RPS */
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
.procname = "wmem_max",
.data = &sysctl_wmem_max,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "rmem_max",