atomic_t udp_memory_allocated;
EXPORT_SYMBOL(udp_memory_allocated);
+#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE)
+
static int udp_lib_lport_inuse(struct net *net, __u16 num,
const struct udp_hslot *hslot,
+ unsigned long *bitmap,
struct sock *sk,
int (*saddr_comp)(const struct sock *sk1,
const struct sock *sk2))
{
struct sock *sk2;
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
- sk_for_each(sk2, node, &hslot->head)
+ sk_nulls_for_each(sk2, node, &hslot->head)
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
- sk2->sk_hash == num &&
+ (bitmap || sk2->sk_hash == num) &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
|| sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
- (*saddr_comp)(sk, sk2))
- return 1;
+ (*saddr_comp)(sk, sk2)) {
+ if (bitmap)
+ __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE,
+ bitmap);
+ else
+ return 1;
+ }
return 0;
}
if (!snum) {
int low, high, remaining;
unsigned rand;
- unsigned short first;
+ unsigned short first, last;
+ DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
inet_get_local_port_range(&low, &high);
remaining = (high - low) + 1;
rand = net_random();
- snum = first = rand % remaining + low;
- rand |= 1;
- for (;;) {
- hslot = &udptable->hash[udp_hashfn(net, snum)];
+ first = (((u64)rand * remaining) >> 32) + low;
+ /*
+ * force rand to be an odd multiple of UDP_HTABLE_SIZE
+ */
+ rand = (rand | 1) * UDP_HTABLE_SIZE;
+ for (last = first + UDP_HTABLE_SIZE; first != last; first++) {
+ hslot = &udptable->hash[udp_hashfn(net, first)];
+ bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
- if (!udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp))
- break;
- spin_unlock_bh(&hslot->lock);
+ udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
+ saddr_comp);
+
+ snum = first;
+ /*
+ * Iterate on all possible values of snum for this hash.
+ * Using steps of an odd multiple of UDP_HTABLE_SIZE
+ * give us randomization and full range coverage.
+ */
do {
- snum = snum + rand;
- } while (snum < low || snum > high);
- if (snum == first)
- goto fail;
+ if (low <= snum && snum <= high &&
+ !test_bit(snum / UDP_HTABLE_SIZE, bitmap))
+ goto found;
+ snum += rand;
+ } while (snum != first);
+ spin_unlock_bh(&hslot->lock);
}
+ goto fail;
} else {
hslot = &udptable->hash[udp_hashfn(net, snum)];
spin_lock_bh(&hslot->lock);
- if (udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp))
+ if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp))
goto fail_unlock;
}
+found:
inet_sk(sk)->num = snum;
sk->sk_hash = snum;
if (sk_unhashed(sk)) {
- sk_add_node_rcu(sk, &hslot->head);
+ sk_nulls_add_node_rcu(sk, &hslot->head);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
}
error = 0;
int dif, struct udp_table *udptable)
{
struct sock *sk, *result;
- struct hlist_node *node, *next;
+ struct hlist_nulls_node *node;
unsigned short hnum = ntohs(dport);
unsigned int hash = udp_hashfn(net, hnum);
struct udp_hslot *hslot = &udptable->hash[hash];
begin:
result = NULL;
badness = -1;
- sk_for_each_rcu_safenext(sk, node, &hslot->head, next) {
- /*
- * lockless reader, and SLAB_DESTROY_BY_RCU items:
- * We must check this item was not moved to another chain
- */
- if (udp_hashfn(net, sk->sk_hash) != hash)
- goto begin;
+ sk_nulls_for_each_rcu(sk, node, &hslot->head) {
score = compute_score(sk, net, saddr, hnum, sport,
daddr, dport, dif);
if (score > badness) {
badness = score;
}
}
+ /*
+ * 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 (get_nulls_value(node) != hash)
+ goto begin;
+
if (result) {
if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
result = NULL;
}
EXPORT_SYMBOL_GPL(udp4_lib_lookup);
-static inline struct sock *udp_v4_mcast_next(struct sock *sk,
+static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif)
{
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
struct sock *s = sk;
unsigned short hnum = ntohs(loc_port);
- sk_for_each_from(s, node) {
+ sk_nulls_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
- if (s->sk_hash != hnum ||
+ if (!net_eq(sock_net(s), net) ||
+ s->sk_hash != hnum ||
(inet->daddr && inet->daddr != rmt_addr) ||
(inet->dport != rmt_port && inet->dport) ||
(inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
return -EOPNOTSUPP;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (up->pending) {
/*
ipc.addr = inet->saddr;
ipc.oif = sk->sk_bound_dev_if;
+ err = sock_tx_timestamp(msg, sk, &ipc.shtx);
+ if (err)
+ return err;
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc);
if (err)
.saddr = saddr,
.tos = tos } },
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = { .ports =
{ .sport = inet->sport,
.dport = dport } } };
up->len += ulen;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
err = ip_append_data(sk, getfrag, msg->msg_iov, ulen,
- sizeof(struct udphdr), &ipc, rt,
+ sizeof(struct udphdr), &ipc, &rt,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
if (err)
udp_flush_pending_frames(sk);
void udp_lib_unhash(struct sock *sk)
{
- struct udp_table *udptable = sk->sk_prot->h.udp_table;
- unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash);
- struct udp_hslot *hslot = &udptable->hash[hash];
+ if (sk_hashed(sk)) {
+ struct udp_table *udptable = sk->sk_prot->h.udp_table;
+ unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash);
+ struct udp_hslot *hslot = &udptable->hash[hash];
- spin_lock_bh(&hslot->lock);
- if (sk_del_node_init_rcu(sk)) {
- inet_sk(sk)->num = 0;
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ spin_lock_bh(&hslot->lock);
+ if (sk_nulls_del_node_init_rcu(sk)) {
+ inet_sk(sk)->num = 0;
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ }
+ spin_unlock_bh(&hslot->lock);
}
- spin_unlock_bh(&hslot->lock);
}
EXPORT_SYMBOL(udp_lib_unhash);
if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
- if (rc == -ENOMEM)
+ if (rc == -ENOMEM) {
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
+ atomic_inc(&sk->sk_drops);
+ }
goto drop;
}
int dif;
spin_lock(&hslot->lock);
- sk = sk_head(&hslot->head);
+ sk = sk_nulls_head(&hslot->head);
dif = skb->dev->ifindex;
- sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
+ sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
if (sk) {
struct sock *sknext = NULL;
do {
struct sk_buff *skb1 = skb;
- sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
- uh->source, saddr, dif);
+ sknext = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest,
+ daddr, uh->source, saddr,
+ dif);
if (sknext)
skb1 = skb_clone(skb, GFP_ATOMIC);
sk = sknext;
} while (sknext);
} else
- kfree_skb(skb);
+ consume_skb(skb);
spin_unlock(&hslot->lock);
return 0;
}
int proto)
{
struct sock *sk;
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh;
unsigned short ulen;
struct rtable *rt = (struct rtable*)skb->dst;
- __be32 saddr = ip_hdr(skb)->saddr;
- __be32 daddr = ip_hdr(skb)->daddr;
+ __be32 saddr, daddr;
struct net *net = dev_net(skb->dev);
/*
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto drop; /* No space for header. */
+ uh = udp_hdr(skb);
ulen = ntohs(uh->len);
if (ulen > skb->len)
goto short_packet;
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
+ saddr = ip_hdr(skb)->saddr;
+ daddr = ip_hdr(skb)->daddr;
+
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
return __udp4_lib_mcast_deliver(net, skb, uh,
saddr, daddr, udptable);
struct net *net = seq_file_net(seq);
for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
spin_lock_bh(&hslot->lock);
- sk_for_each(sk, node, &hslot->head) {
+ sk_nulls_for_each(sk, node, &hslot->head) {
if (!net_eq(sock_net(sk), net))
continue;
if (sk->sk_family == state->family)
struct net *net = seq_file_net(seq);
do {
- sk = sk_next(sk);
+ sk = sk_nulls_next(sk);
} while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family));
if (!sk) {
- spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
+ if (state->bucket < UDP_HTABLE_SIZE)
+ spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
return udp_get_first(seq, state->bucket + 1);
}
return sk;
static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
+ struct udp_iter_state *state = seq->private;
+ state->bucket = UDP_HTABLE_SIZE;
+
return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
int i;
for (i = 0; i < UDP_HTABLE_SIZE; i++) {
- INIT_HLIST_HEAD(&table->hash[i].head);
+ INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i);
spin_lock_init(&table->hash[i].lock);
}
}