/*
* N.B. The flags may be moved into the flowi at some future stage.
*/
static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *flp, int flags)
{
unsigned hash = dn_hash(flp->fld_src, flp->fld_dst);
struct dn_route *rt = NULL;
if (!(flags & MSG_TRYHARD)) {
rcu_read_lock_bh();
for(rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt;
rt = rcu_dereference(rt->u.rt_next)) {
if ((flp->fld_dst == rt->fl.fld_dst) &&
(flp->fld_src == rt->fl.fld_src) &&
#ifdef CONFIG_DECNET_ROUTE_FWMARK
(flp->fld_fwmark == rt->fl.fld_fwmark) &&
#endif
(rt->fl.iif == 0) &&
(rt->fl.oif == flp->oif)) {
rt->u.dst.lastuse = jiffies;
dst_hold(&rt->u.dst);
rt->u.dst.__use++;
rcu_read_unlock_bh();
*pprt = &rt->u.dst;
return 0;
}
}
rcu_read_unlock_bh();
}
return dn_route_output_slow(pprt, flp, flags);
}
/* modelled after ip6_finish_output2 */
static int vrf_finish_output6(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct neighbour *neigh;
struct in6_addr *nexthop;
int ret;
skb->protocol = htons(ETH_P_IPV6);
skb->dev = dev;
rcu_read_lock_bh();
nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
if (!IS_ERR(neigh)) {
ret = dst_neigh_output(dst, neigh, skb);
rcu_read_unlock_bh();
return ret;
}
rcu_read_unlock_bh();
IP6_INC_STATS(dev_net(dst->dev),
ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
int flush_bytes_array(void)
{
struct bytes *tmp, *old;
rcu_read_lock_bh();
if (!(rcu_dereference_bh(bytes_to_skip)->array)) {
log_info("Byte array list is empty nothing to flush");
rcu_read_unlock_bh();
return 0;
}
rcu_read_unlock_bh();
tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
if (!tmp) {
log_err("Could not allocate struct bytes.");
return -ENOMEM;
}
old = bytes_to_skip;
*tmp = *bytes_to_skip;
/* Delete. */
tmp->array = NULL;
tmp->count = 0;
rcu_assign_pointer(bytes_to_skip, tmp);
synchronize_rcu_bh();
if (old->array)
kfree(old->array);
kfree(old);
return 0;
}
int display_bytes_array(void)
{
struct bytes tmp;
int i;
rcu_read_lock_bh();
tmp = *rcu_dereference(bytes_to_skip);
if (!tmp.count) {
log_info("Byte array list is empty");
goto end;
}
for (i = 0; i < tmp.count; i++) {
if (i + 1 != tmp.count)
printk("%u, ", tmp.array[i]);
else
printk("%u\n", tmp.array[i]);
}
log_info("Array length: %d", tmp.count);
end:
rcu_read_unlock_bh();
return 0;
}
/**
* llc_lookup_dgram - Finds dgram socket for the local sap/mac
* @sap: SAP
* @laddr: address of local LLC (MAC + SAP)
*
* Search socket list of the SAP and finds connection using the local
* mac, and local sap. Returns pointer for socket found, %NULL otherwise.
*/
static struct sock *llc_lookup_dgram(struct llc_sap *sap,
const struct llc_addr *laddr)
{
struct sock *rc;
struct hlist_nulls_node *node;
int slot = llc_sk_laddr_hashfn(sap, laddr);
struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot];
rcu_read_lock_bh();
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_dgram_match(sap, laddr, rc)) {
/* Extra checks required by SLAB_DESTROY_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
!llc_dgram_match(sap, laddr, rc))) {
sock_put(rc);
continue;
}
goto found;
}
}
rc = NULL;
/*
* if the nulls value we got at the end of this lookup is
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
if (unlikely(get_nulls_value(node) != slot))
goto again;
found:
rcu_read_unlock_bh();
return rc;
}
static int pcrypt_do_parallel(struct padata_priv *padata, unsigned int *cb_cpu,
struct padata_pcrypt *pcrypt)
{
unsigned int cpu_index, cpu, i;
struct pcrypt_cpumask *cpumask;
cpu = *cb_cpu;
rcu_read_lock_bh();
cpumask = rcu_dereference(pcrypt->cb_cpumask);
if (cpumask_test_cpu(cpu, cpumask->mask))
goto out;
if (!cpumask_weight(cpumask->mask))
goto out;
cpu_index = cpu % cpumask_weight(cpumask->mask);
cpu = cpumask_first(cpumask->mask);
for (i = 0; i < cpu_index; i++)
cpu = cpumask_next(cpu, cpumask->mask);
*cb_cpu = cpu;
out:
rcu_read_unlock_bh();
return padata_do_parallel(pcrypt->pinst, padata, cpu);
}
/**
* Copies this module's current configuration to "clone".
*
* @param[out] clone a copy of the current config will be placed here. Must be already allocated.
* @return zero on success, nonzero on failure.
*/
int filtering_clone_config(struct filtering_config *clone)
{
rcu_read_lock_bh();
*clone = *rcu_dereference_bh(config);
rcu_read_unlock_bh();
return 0;
}
static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
{
struct vhost_net_ubuf_ref *ubufs = ubuf->ctx;
struct vhost_virtqueue *vq = ubufs->vq;
int cnt;
rcu_read_lock_bh();
/* set len to mark this desc buffers done DMA */
vq->heads[ubuf->desc].len = success ?
VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
cnt = vhost_net_ubuf_put(ubufs);
/*
* Trigger polling thread if guest stopped submitting new buffers:
* in this case, the refcount after decrement will eventually reach 1.
* We also trigger polling periodically after each 16 packets
* (the value 16 here is more or less arbitrary, it's tuned to trigger
* less than 10% of times).
*/
if (cnt <= 1 || !(cnt % 16))
vhost_poll_queue(&vq->poll);
rcu_read_unlock_bh();
}
/* modelled after ip_finish_output2 */
static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
u32 nexthop;
int ret = -EINVAL;
nf_reset(skb);
/* Be paranoid, rather than too clever. */
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
struct sk_buff *skb2;
skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
if (!skb2) {
ret = -ENOMEM;
goto err;
}
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
consume_skb(skb);
skb = skb2;
}
rcu_read_lock_bh();
nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
if (!IS_ERR(neigh)) {
sock_confirm_neigh(skb, neigh);
ret = neigh_output(neigh, skb);
rcu_read_unlock_bh();
return ret;
}
rcu_read_unlock_bh();
err:
vrf_tx_error(skb->dev, skb);
return ret;
}
/**
* Use this function to safely obtain the configuration value which dictates whether IPv4 nodes
* should be allowed to initiate conversations with IPv6 nodes.
*
* @return whether IPv4 nodes should be allowed to initiate conversations with IPv6 nodes.
*/
static bool drop_external_connections(void)
{
bool result;
rcu_read_lock_bh();
result = rcu_dereference_bh(config)->drop_external_tcp;
rcu_read_unlock_bh();
return result;
}
/**
* Use this function to safely obtain the configuration value which dictates whether Jool should
* drop all informational ICMP packets that are traveling from IPv6 to IPv4.
*
* @return whether Jool should drop all ICMPv6 info packets.
*/
static bool filter_icmpv6_info(void)
{
bool result;
rcu_read_lock_bh();
result = rcu_dereference_bh(config)->drop_icmp6_info;
rcu_read_unlock_bh();
return result;
}
/**
* Use this function to safely obtain the configuration value which dictates whether Jool should
* be applying "address-dependent filtering" (Look that up in the RFC).
*
* @return whether Jool should apply "address-dependent filtering".
*/
static bool address_dependent_filtering(void)
{
bool result;
rcu_read_lock_bh();
result = rcu_dereference_bh(config)->drop_by_addr;
rcu_read_unlock_bh();
return result;
}
/*
* For routers, this is called from dn_fib_dump, but for endnodes its
* called directly from the rtnetlink dispatch table.
*/
int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct dn_route *rt;
int h, s_h;
int idx, s_idx;
if (NLMSG_PAYLOAD(cb->nlh, 0) < sizeof(struct rtmsg))
return -EINVAL;
if (!(((struct rtmsg *)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED))
return 0;
s_h = cb->args[0];
s_idx = idx = cb->args[1];
for(h = 0; h <= dn_rt_hash_mask; h++) {
if (h < s_h)
continue;
if (h > s_h)
s_idx = 0;
rcu_read_lock_bh();
for(rt = rcu_dereference(dn_rt_hash_table[h].chain), idx = 0;
rt;
rt = rcu_dereference(rt->u.rt_next), idx++) {
if (idx < s_idx)
continue;
skb->dst = dst_clone(&rt->u.dst);
if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
dst_release(xchg(&skb->dst, NULL));
rcu_read_unlock_bh();
goto done;
}
dst_release(xchg(&skb->dst, NULL));
}
rcu_read_unlock_bh();
}
done:
cb->args[0] = h;
cb->args[1] = idx;
return skb->len;
}
struct llc_sap *llc_sap_find(unsigned char sap_value)
{
struct llc_sap *sap;
rcu_read_lock_bh();
sap = __llc_sap_find(sap_value);
if (sap)
llc_sap_hold(sap);
rcu_read_unlock_bh();
return sap;
}
struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
{
struct ipv6_fl_socklist *sfl;
struct ipv6_pinfo *np = inet6_sk(sk);
label &= IPV6_FLOWLABEL_MASK;
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
struct ip6_flowlabel *fl = sfl->fl;
if (fl->label == label) {
fl->lastuse = jiffies;
atomic_inc(&fl->users);
rcu_read_unlock_bh();
return fl;
}
}
rcu_read_unlock_bh();
return NULL;
}
static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
{
struct ip6_flowlabel *fl;
rcu_read_lock_bh();
fl = __fl_lookup(net, label);
if (fl && !atomic_inc_not_zero(&fl->users))
fl = NULL;
rcu_read_unlock_bh();
return fl;
}
static struct nfulnl_instance *
instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num)
{
struct nfulnl_instance *inst;
rcu_read_lock_bh();
inst = __instance_lookup(log, group_num);
if (inst && !refcount_inc_not_zero(&inst->use))
inst = NULL;
rcu_read_unlock_bh();
return inst;
}
static struct nfulnl_instance *
instance_lookup_get(u_int16_t group_num)
{
struct nfulnl_instance *inst;
rcu_read_lock_bh();
inst = __instance_lookup(group_num);
if (inst && !atomic_inc_not_zero(&inst->use))
inst = NULL;
rcu_read_unlock_bh();
return inst;
}
/**
* padata_do_parallel - padata parallelization function
*
* @pinst: padata instance
* @padata: object to be parallelized
* @cb_cpu: cpu the serialization callback function will run on,
* must be in the serial cpumask of padata(i.e. cpumask.cbcpu).
*
* The parallelization callback function will run with BHs off.
* Note: Every object which is parallelized by padata_do_parallel
* must be seen by padata_do_serial.
*/
int padata_do_parallel(struct padata_instance *pinst,
struct padata_priv *padata, int cb_cpu)
{
int target_cpu, err;
struct padata_parallel_queue *queue;
struct parallel_data *pd;
rcu_read_lock_bh();
pd = rcu_dereference(pinst->pd);
err = -EINVAL;
if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID)
goto out;
if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu))
goto out;
err = -EBUSY;
if ((pinst->flags & PADATA_RESET))
goto out;
if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
goto out;
err = 0;
atomic_inc(&pd->refcnt);
padata->pd = pd;
padata->cb_cpu = cb_cpu;
if (unlikely(atomic_read(&pd->seq_nr) == pd->max_seq_nr))
atomic_set(&pd->seq_nr, -1);
padata->seq_nr = atomic_inc_return(&pd->seq_nr);
target_cpu = padata_cpu_hash(padata);
queue = per_cpu_ptr(pd->pqueue, target_cpu);
spin_lock(&queue->parallel.lock);
list_add_tail(&padata->list, &queue->parallel.list);
spin_unlock(&queue->parallel.lock);
queue_work_on(target_cpu, pinst->wq, &queue->work);
out:
rcu_read_unlock_bh();
return err;
}
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
struct sk_filter *filter;
rcu_read_lock_bh();
filter = rcu_dereference_bh(sk->sk_filter);
if (filter) {
rcu_assign_pointer(sk->sk_filter, NULL);
sk_filter_delayed_uncharge(sk, filter);
ret = 0;
}
rcu_read_unlock_bh();
return ret;
}
int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
int flags)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_fl_socklist *sfl;
if (flags & IPV6_FL_F_REMOTE) {
freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK;
return 0;
}
if (np->repflow) {
freq->flr_label = np->flow_label;
return 0;
}
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) {
spin_lock_bh(&ip6_fl_lock);
freq->flr_label = sfl->fl->label;
freq->flr_dst = sfl->fl->dst;
freq->flr_share = sfl->fl->share;
freq->flr_expires = (sfl->fl->expires - jiffies) / HZ;
freq->flr_linger = sfl->fl->linger / HZ;
spin_unlock_bh(&ip6_fl_lock);
rcu_read_unlock_bh();
return 0;
}
}
rcu_read_unlock_bh();
return -ENOENT;
}
void ieee80211_requeue(struct ieee80211_local *local, int queue)
{
struct netdev_queue *txq = netdev_get_tx_queue(local->mdev, queue);
struct sk_buff_head list;
spinlock_t *root_lock;
struct Qdisc *qdisc;
u32 len;
rcu_read_lock_bh();
qdisc = rcu_dereference(txq->qdisc);
if (!qdisc || !qdisc->dequeue)
goto out_unlock;
skb_queue_head_init(&list);
root_lock = qdisc_root_lock(qdisc);
spin_lock(root_lock);
for (len = qdisc->q.qlen; len > 0; len--) {
struct sk_buff *skb = qdisc->dequeue(qdisc);
if (skb)
__skb_queue_tail(&list, skb);
}
spin_unlock(root_lock);
for (len = list.qlen; len > 0; len--) {
struct sk_buff *skb = __skb_dequeue(&list);
u16 new_queue;
BUG_ON(!skb);
new_queue = ieee80211_select_queue(local->mdev, skb);
skb_set_queue_mapping(skb, new_queue);
txq = netdev_get_tx_queue(local->mdev, new_queue);
qdisc = rcu_dereference(txq->qdisc);
root_lock = qdisc_root_lock(qdisc);
spin_lock(root_lock);
qdisc_enqueue_root(skb, qdisc);
spin_unlock(root_lock);
}
out_unlock:
rcu_read_unlock_bh();
}
/**
* sk_filter - run a packet through a socket filter
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
*
* Run the filter code and then cut skb->data to correct size returned by
* sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
* wrapper to sk_run_filter. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
int sk_filter(struct sock *sk, struct sk_buff *skb)
{
int err;
struct sk_filter *filter;
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
rcu_read_lock_bh();
filter = rcu_dereference_bh(sk->sk_filter);
if (filter) {
unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
rcu_read_unlock_bh();
return err;
}
bool skb_compare(struct sk_buff *expected, struct sk_buff *actual)
{
struct bytes *skip_byte;
unsigned char *expected_ptr, *actual_ptr;
unsigned int i, min_len, skip_count;
int errors = 0;
if (expected->len != actual->len) {
print_error_table_hdr(errors);
log_info(" Length\t%d\t %d", expected->len, actual->len);
errors++;
}
expected_ptr = skb_network_header(expected);
actual_ptr = skb_network_header(actual);
min_len = (expected->len < actual->len) ? expected->len : actual->len;
rcu_read_lock_bh();
skip_byte = rcu_dereference_bh(bytes_to_skip);
skip_count = 0;
for (i = 0; i < min_len; i++) {
if (skip_count < skip_byte->count && skip_byte->array[skip_count] == i) {
skip_count++;
continue;
}
if (expected_ptr[i] != actual_ptr[i]) {
print_error_table_hdr(errors);
log_info(" byte %u\t0x%x\t 0x%x", i,
expected_ptr[i], actual_ptr[i]);
errors++;
if (errors >= 8)
break;
}
}
rcu_read_unlock_bh();
return !errors;
}
/**
* sk_attach_filter - attach a socket filter
* @fprog: the filter program
* @sk: the socket to use
*
* Attach the user's filter code. We first run some sanity checks on
* it to make sure it does not explode on us later. If an error
* occurs or there is insufficient memory for the filter a negative
* errno code is returned. On success the return is zero.
*/
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
struct sk_filter *fp, *old_fp;
unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
return -EINVAL;
fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL);
if (!fp)
return -ENOMEM;
if (copy_from_user(fp->insns, fprog->filter, fsize)) {
sock_kfree_s(sk, fp, fsize+sizeof(*fp));
return -EFAULT;
}
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
fp->bpf_func = sk_run_filter;
err = sk_chk_filter(fp->insns, fp->len);
if (err) {
sk_filter_uncharge(sk, fp);
return err;
}
bpf_jit_compile(fp);
rcu_read_lock_bh();
old_fp = rcu_dereference_bh(sk->sk_filter);
rcu_assign_pointer(sk->sk_filter, fp);
rcu_read_unlock_bh();
if (old_fp)
sk_filter_delayed_uncharge(sk, old_fp);
return 0;
}
static struct neighbour *hwaddr_neighbour(struct rtable *rt,
struct hwaddr_entry *entry)
{
#if LINUX_VERSION_CODE < KERNEL_VERSION(3,1,0)
struct neighbour *neigh = rt->dst.neighbour;
#else
struct neighbour *neigh = NULL;
__be32 next = 0;
rcu_read_lock_bh();
next = rt_nexthop(rt, entry->h_remote);
neigh = __ipv4_neigh_lookup_noref(rt->dst.dev, next);
if (IS_ERR_OR_NULL(neigh))
neigh = __neigh_create(&arp_tbl, &next, rt->dst.dev, false);
rcu_read_unlock_bh();
#endif
if (IS_ERR(neigh))
return NULL;
return neigh;
}
static int vrf_finish_direct(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct net_device *vrf_dev = skb->dev;
if (!list_empty(&vrf_dev->ptype_all) &&
likely(skb_headroom(skb) >= ETH_HLEN)) {
struct ethhdr *eth = skb_push(skb, ETH_HLEN);
ether_addr_copy(eth->h_source, vrf_dev->dev_addr);
eth_zero_addr(eth->h_dest);
eth->h_proto = skb->protocol;
rcu_read_lock_bh();
dev_queue_xmit_nit(skb, vrf_dev);
rcu_read_unlock_bh();
skb_pull(skb, ETH_HLEN);
}
return 1;
}
static int mem_check(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_fl_socklist *sfl;
int room = FL_MAX_SIZE - atomic_read(&fl_size);
int count = 0;
if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
return 0;
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl)
count++;
rcu_read_unlock_bh();
if (room <= 0 ||
((count >= FL_MAX_PER_SOCK ||
(count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) &&
!capable(CAP_NET_ADMIN)))
return -ENOBUFS;
return 0;
}
/**
* sk_filter - run a packet through a socket filter
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
*
* Run the filter code and then cut skb->data to correct size returned by
* sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
* wrapper to sk_run_filter. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
int sk_filter(struct sock *sk, struct sk_buff *skb)
{
int err;
struct sk_filter *filter;
err = security_sock_rcv_skb(sk, skb);
if (err)
return err;
err = provenance_sock_rcv_skb(sk, skb);
if (err)
return err;
rcu_read_lock_bh();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
unsigned int pkt_len = sk_run_filter(skb, filter->insns,
filter->len);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
rcu_read_unlock_bh();
return err;
}
int sock_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, int optlen)
{
struct sock *sk=sock->sk;
struct sk_filter *filter;
int val;
int valbool;
struct linger ling;
int ret = 0;
/*
* Options without arguments
*/
#ifdef SO_DONTLINGER /* Compatibility item... */
if (optname == SO_DONTLINGER) {
lock_sock(sk);
sock_reset_flag(sk, SOCK_LINGER);
release_sock(sk);
return 0;
}
#endif
if(optlen<sizeof(int))
return(-EINVAL);
if (get_user(val, (int __user *)optval))
return -EFAULT;
valbool = val?1:0;
lock_sock(sk);
switch(optname)
{
case SO_DEBUG:
if(val && !capable(CAP_NET_ADMIN))
{
ret = -EACCES;
}
else if (valbool)
sock_set_flag(sk, SOCK_DBG);
else
sock_reset_flag(sk, SOCK_DBG);
break;
case SO_REUSEADDR:
sk->sk_reuse = valbool;
break;
case SO_TYPE:
case SO_ERROR:
ret = -ENOPROTOOPT;
break;
case SO_DONTROUTE:
if (valbool)
sock_set_flag(sk, SOCK_LOCALROUTE);
else
sock_reset_flag(sk, SOCK_LOCALROUTE);
break;
case SO_BROADCAST:
sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
break;
case SO_SNDBUF:
/* Don't error on this BSD doesn't and if you think
about it this is right. Otherwise apps have to
play 'guess the biggest size' games. RCVBUF/SNDBUF
are treated in BSD as hints */
if (val > sysctl_wmem_max)
val = sysctl_wmem_max;
set_sndbuf:
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
if ((val * 2) < SOCK_MIN_SNDBUF)
sk->sk_sndbuf = SOCK_MIN_SNDBUF;
else
sk->sk_sndbuf = val * 2;
/*
* Wake up sending tasks if we
* upped the value.
*/
sk->sk_write_space(sk);
break;
case SO_SNDBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
goto set_sndbuf;
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
about it this is right. Otherwise apps have to
play 'guess the biggest size' games. RCVBUF/SNDBUF
are treated in BSD as hints */
if (val > sysctl_rmem_max)
val = sysctl_rmem_max;
set_rcvbuf:
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
/*
* We double it on the way in to account for
* "struct sk_buff" etc. overhead. Applications
* assume that the SO_RCVBUF setting they make will
* allow that much actual data to be received on that
* socket.
*
* Applications are unaware that "struct sk_buff" and
* other overheads allocate from the receive buffer
* during socket buffer allocation.
*
* And after considering the possible alternatives,
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
if ((val * 2) < SOCK_MIN_RCVBUF)
sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
else
sk->sk_rcvbuf = val * 2;
break;
case SO_RCVBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
goto set_rcvbuf;
case SO_KEEPALIVE:
#ifdef CONFIG_INET
if (sk->sk_protocol == IPPROTO_TCP)
tcp_set_keepalive(sk, valbool);
#endif
sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
break;
case SO_OOBINLINE:
sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
break;
case SO_NO_CHECK:
sk->sk_no_check = valbool;
break;
case SO_PRIORITY:
if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN))
sk->sk_priority = val;
else
ret = -EPERM;
break;
case SO_LINGER:
if(optlen<sizeof(ling)) {
ret = -EINVAL; /* 1003.1g */
break;
}
if (copy_from_user(&ling,optval,sizeof(ling))) {
ret = -EFAULT;
break;
}
if (!ling.l_onoff)
sock_reset_flag(sk, SOCK_LINGER);
else {
#if (BITS_PER_LONG == 32)
if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
else
#endif
sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
sock_set_flag(sk, SOCK_LINGER);
}
break;
case SO_BSDCOMPAT:
sock_warn_obsolete_bsdism("setsockopt");
break;
case SO_PASSCRED:
if (valbool)
set_bit(SOCK_PASSCRED, &sock->flags);
else
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_TIMESTAMP:
if (valbool) {
sock_set_flag(sk, SOCK_RCVTSTAMP);
sock_enable_timestamp(sk);
} else
sock_reset_flag(sk, SOCK_RCVTSTAMP);
break;
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
sk->sk_rcvlowat = val ? : 1;
break;
case SO_RCVTIMEO:
ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
break;
case SO_SNDTIMEO:
ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
break;
#ifdef CONFIG_NETDEVICES
case SO_BINDTODEVICE:
{
char devname[IFNAMSIZ];
/* Sorry... */
if (!capable(CAP_NET_RAW)) {
ret = -EPERM;
break;
}
/* Bind this socket to a particular device like "eth0",
* as specified in the passed interface name. If the
* name is "" or the option length is zero the socket
* is not bound.
*/
if (!valbool) {
sk->sk_bound_dev_if = 0;
} else {
if (optlen > IFNAMSIZ - 1)
optlen = IFNAMSIZ - 1;
memset(devname, 0, sizeof(devname));
if (copy_from_user(devname, optval, optlen)) {
ret = -EFAULT;
break;
}
/* Remove any cached route for this socket. */
sk_dst_reset(sk);
if (devname[0] == '\0') {
sk->sk_bound_dev_if = 0;
} else {
struct net_device *dev = dev_get_by_name(devname);
if (!dev) {
ret = -ENODEV;
break;
}
sk->sk_bound_dev_if = dev->ifindex;
dev_put(dev);
}
}
break;
}
#endif
case SO_ATTACH_FILTER:
ret = -EINVAL;
if (optlen == sizeof(struct sock_fprog)) {
struct sock_fprog fprog;
ret = -EFAULT;
if (copy_from_user(&fprog, optval, sizeof(fprog)))
break;
ret = sk_attach_filter(&fprog, sk);
}
break;
case SO_DETACH_FILTER:
rcu_read_lock_bh();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
rcu_assign_pointer(sk->sk_filter, NULL);
sk_filter_release(sk, filter);
rcu_read_unlock_bh();
break;
}
rcu_read_unlock_bh();
ret = -ENONET;
break;
case SO_PASSSEC:
if (valbool)
set_bit(SOCK_PASSSEC, &sock->flags);
else
clear_bit(SOCK_PASSSEC, &sock->flags);
break;
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
default:
ret = -ENOPROTOOPT;
break;
}
release_sock(sk);
return ret;
}