#include <net/xfrm.h>
#include "udp_impl.h"
-struct udp_table udp_table;
+struct udp_table udp_table __read_mostly;
EXPORT_SYMBOL(udp_table);
int sysctl_udp_mem[3] __read_mostly;
-int sysctl_udp_rmem_min __read_mostly;
-int sysctl_udp_wmem_min __read_mostly;
-
EXPORT_SYMBOL(sysctl_udp_mem);
+
+int sysctl_udp_rmem_min __read_mostly;
EXPORT_SYMBOL(sysctl_udp_rmem_min);
+
+int sysctl_udp_wmem_min __read_mostly;
EXPORT_SYMBOL(sysctl_udp_wmem_min);
atomic_t udp_memory_allocated;
EXPORT_SYMBOL(udp_memory_allocated);
+#define MAX_UDP_PORTS 65536
+#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN)
+
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))
+ const struct sock *sk2),
+ unsigned int log)
{
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 >> log, bitmap);
+ else
+ return 1;
+ }
return 0;
}
*/
int udp_lib_get_port(struct sock *sk, unsigned short snum,
int (*saddr_comp)(const struct sock *sk1,
- const struct sock *sk2 ) )
+ const struct sock *sk2))
{
struct udp_hslot *hslot;
struct udp_table *udptable = sk->sk_prot->h.udp_table;
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) * (udptable->mask + 1);
+ for (last = first + udptable->mask + 1;
+ first != last;
+ first++) {
+ hslot = udp_hashslot(udptable, 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, udptable->log);
+
+ 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 >> udptable->log, bitmap))
+ goto found;
+ snum += rand;
+ } while (snum != first);
+ spin_unlock_bh(&hslot->lock);
}
+ goto fail;
} else {
- hslot = &udptable->hash[udp_hashfn(net, snum)];
+ hslot = udp_hashslot(udptable, 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, 0))
goto fail_unlock;
}
- inet_sk(sk)->num = snum;
+found:
+ inet_sk(sk)->inet_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;
fail:
return error;
}
+EXPORT_SYMBOL(udp_lib_get_port);
static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
{
struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
- return ( !ipv6_only_sock(sk2) &&
- (!inet1->rcv_saddr || !inet2->rcv_saddr ||
- inet1->rcv_saddr == inet2->rcv_saddr ));
+ return (!ipv6_only_sock(sk2) &&
+ (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr ||
+ inet1->inet_rcv_saddr == inet2->inet_rcv_saddr));
}
int udp_v4_get_port(struct sock *sk, unsigned short snum)
struct inet_sock *inet = inet_sk(sk);
score = (sk->sk_family == PF_INET ? 1 : 0);
- if (inet->rcv_saddr) {
- if (inet->rcv_saddr != daddr)
+ if (inet->inet_rcv_saddr) {
+ if (inet->inet_rcv_saddr != daddr)
return -1;
score += 2;
}
- if (inet->daddr) {
- if (inet->daddr != saddr)
+ if (inet->inet_daddr) {
+ if (inet->inet_daddr != saddr)
return -1;
score += 2;
}
- if (inet->dport) {
- if (inet->dport != sport)
+ if (inet->inet_dport) {
+ if (inet->inet_dport != sport)
return -1;
score += 2;
}
int dif, struct udp_table *udptable)
{
struct sock *sk, *result;
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
unsigned short hnum = ntohs(dport);
- unsigned int hash = udp_hashfn(net, hnum);
+ unsigned int hash = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot = &udptable->hash[hash];
int score, badness;
begin:
result = NULL;
badness = -1;
- sk_for_each_rcu(sk, node, &hslot->head) {
- /*
- * 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;
if (unlikely(sk = skb_steal_sock(skb)))
return sk;
else
- return __udp4_lib_lookup(dev_net(skb->dst->dev), iph->saddr, sport,
+ return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
udptable);
}
}
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 ||
- (inet->daddr && inet->daddr != rmt_addr) ||
- (inet->dport != rmt_port && inet->dport) ||
- (inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
+ if (!net_eq(sock_net(s), net) ||
+ s->sk_hash != hnum ||
+ (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
+ (inet->inet_dport != rmt_port && inet->inet_dport) ||
+ (inet->inet_rcv_saddr &&
+ inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(s) ||
(s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
continue;
void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
{
struct inet_sock *inet;
- struct iphdr *iph = (struct iphdr*)skb->data;
- struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
+ struct iphdr *iph = (struct iphdr *)skb->data;
+ struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct sock *sk;
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
- ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1));
+ ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1));
}
sk->sk_err = err;
sk->sk_error_report(sk);
* (checksum field must be zeroed out)
*/
static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
- __be32 src, __be32 dst, int len )
+ __be32 src, __be32 dst, int len)
{
unsigned int offset;
struct udphdr *uh = udp_hdr(skb);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
- udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len);
+ udp4_hwcsum_outgoing(sk, skb, fl->fl4_src, fl->fl4_dst, up->len);
goto send;
} else /* `normal' UDP */
/* add protocol-dependent pseudo-header */
uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len,
- sk->sk_protocol, csum );
+ sk->sk_protocol, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
send:
err = ip_push_pending_frames(sk);
+ if (err) {
+ if (err == -ENOBUFS && !inet->recverr) {
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_SNDBUFERRORS, is_udplite);
+ err = 0;
+ }
+ } else
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_OUTDATAGRAMS, is_udplite);
out:
up->len = 0;
up->pending = 0;
- if (!err)
- UDP_INC_STATS_USER(sock_net(sk),
- UDP_MIB_OUTDATAGRAMS, is_udplite);
return err;
}
* Check the flags.
*/
- if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */
+ if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */
return -EOPNOTSUPP;
ipc.opt = NULL;
+ ipc.shtx.flags = 0;
if (up->pending) {
/*
* Get and verify the address.
*/
if (msg->msg_name) {
- struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
+ struct sockaddr_in * usin = (struct sockaddr_in *)msg->msg_name;
if (msg->msg_namelen < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET) {
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
- daddr = inet->daddr;
- dport = inet->dport;
+ daddr = inet->inet_daddr;
+ dport = inet->inet_dport;
/* Open fast path for connected socket.
Route will not be used, if at least one option is set.
*/
connected = 1;
}
- ipc.addr = inet->saddr;
+ ipc.addr = inet->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)
}
if (connected)
- rt = (struct rtable*)sk_dst_check(sk, 0);
+ rt = (struct rtable *)sk_dst_check(sk, 0);
if (rt == NULL) {
struct flowi fl = { .oif = ipc.oif,
+ .mark = sk->sk_mark,
.nl_u = { .ip4_u =
{ .daddr = faddr,
.saddr = saddr,
.tos = tos } },
.proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
.uli_u = { .ports =
- { .sport = inet->sport,
+ { .sport = inet->inet_sport,
.dport = dport } } };
struct net *net = sock_net(sk);
inet->cork.fl.fl4_dst = daddr;
inet->cork.fl.fl_ip_dport = dport;
inet->cork.fl.fl4_src = saddr;
- inet->cork.fl.fl_ip_sport = inet->sport;
+ inet->cork.fl.fl_ip_sport = inet->inet_sport;
up->pending = AF_INET;
do_append_data:
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);
err = 0;
goto out;
}
+EXPORT_SYMBOL(udp_sendmsg);
int udp_sendpage(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
return ret;
}
+
+/**
+ * first_packet_length - return length of first packet in receive queue
+ * @sk: socket
+ *
+ * Drops all bad checksum frames, until a valid one is found.
+ * Returns the length of found skb, or 0 if none is found.
+ */
+static unsigned int first_packet_length(struct sock *sk)
+{
+ struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue;
+ struct sk_buff *skb;
+ unsigned int res;
+
+ __skb_queue_head_init(&list_kill);
+
+ spin_lock_bh(&rcvq->lock);
+ while ((skb = skb_peek(rcvq)) != NULL &&
+ udp_lib_checksum_complete(skb)) {
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
+ IS_UDPLITE(sk));
+ __skb_unlink(skb, rcvq);
+ __skb_queue_tail(&list_kill, skb);
+ }
+ res = skb ? skb->len : 0;
+ spin_unlock_bh(&rcvq->lock);
+
+ if (!skb_queue_empty(&list_kill)) {
+ lock_sock(sk);
+ __skb_queue_purge(&list_kill);
+ sk_mem_reclaim_partial(sk);
+ release_sock(sk);
+ }
+ return res;
+}
+
/*
* IOCTL requests applicable to the UDP protocol
*/
switch (cmd) {
case SIOCOUTQ:
{
- int amount = atomic_read(&sk->sk_wmem_alloc);
+ int amount = sk_wmem_alloc_get(sk);
+
return put_user(amount, (int __user *)arg);
}
case SIOCINQ:
{
- struct sk_buff *skb;
- unsigned long amount;
+ unsigned int amount = first_packet_length(sk);
- amount = 0;
- spin_lock_bh(&sk->sk_receive_queue.lock);
- skb = skb_peek(&sk->sk_receive_queue);
- if (skb != NULL) {
+ if (amount)
/*
* We will only return the amount
* of this packet since that is all
* that will be read.
*/
- amount = skb->len - sizeof(struct udphdr);
- }
- spin_unlock_bh(&sk->sk_receive_queue.lock);
+ amount -= sizeof(struct udphdr);
+
return put_user(amount, (int __user *)arg);
}
return 0;
}
+EXPORT_SYMBOL(udp_ioctl);
/*
* This should be easy, if there is something there we
* Check any passed addresses
*/
if (addr_len)
- *addr_len=sizeof(*sin);
+ *addr_len = sizeof(*sin);
if (flags & MSG_ERRQUEUE)
return ip_recv_error(sk, msg, len);
if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
- msg->msg_iov, copied );
+ msg->msg_iov, copied);
else {
- err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
+ err = skb_copy_and_csum_datagram_iovec(skb,
+ sizeof(struct udphdr),
+ msg->msg_iov);
if (err == -EINVAL)
goto csum_copy_err;
UDP_INC_STATS_USER(sock_net(sk),
UDP_MIB_INDATAGRAMS, is_udplite);
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
/* Copy the address. */
- if (sin)
- {
+ if (sin) {
sin->sin_family = AF_INET;
sin->sin_port = udp_hdr(skb)->source;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
*/
sk->sk_state = TCP_CLOSE;
- inet->daddr = 0;
- inet->dport = 0;
+ inet->inet_daddr = 0;
+ inet->inet_dport = 0;
sk->sk_bound_dev_if = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
sk->sk_prot->unhash(sk);
- inet->sport = 0;
+ inet->inet_sport = 0;
}
sk_dst_reset(sk);
return 0;
}
+EXPORT_SYMBOL(udp_disconnect);
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;
+ struct udp_hslot *hslot = udp_hashslot(udptable, sock_net(sk),
+ sk->sk_hash);
- spin_lock(&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)->inet_num = 0;
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ }
+ spin_unlock_bh(&hslot->lock);
}
- spin_unlock(&hslot->lock);
}
EXPORT_SYMBOL(udp_lib_unhash);
static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
- int is_udplite = IS_UDPLITE(sk);
- int rc;
+ int rc = sock_queue_rcv_skb(sk, skb);
+
+ if (rc < 0) {
+ int is_udplite = IS_UDPLITE(sk);
- if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM)
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
- goto drop;
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
+ return -1;
}
return 0;
-drop:
- UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
- kfree_skb(skb);
- return -1;
}
/* returns:
* Note that in the success and error cases, the skb is assumed to
* have either been requeued or freed.
*/
-int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
+int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int rc;
struct udp_table *udptable)
{
struct sock *sk;
- struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))];
+ struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest));
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;
}
if (uh->check == 0) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
- if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
proto, skb->csum))
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
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;
+ struct rtable *rt = skb_rtable(skb);
+ __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);
return 0;
short_packet:
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From " NIPQUAD_FMT ":%u %d/%d to " NIPQUAD_FMT ":%u\n",
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
- NIPQUAD(saddr),
+ &saddr,
ntohs(uh->source),
ulen,
skb->len,
- NIPQUAD(daddr),
+ &daddr,
ntohs(uh->dest));
goto drop;
* RFC1122: OK. Discards the bad packet silently (as far as
* the network is concerned, anyway) as per 4.1.3.4 (MUST).
*/
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From " NIPQUAD_FMT ":%u to " NIPQUAD_FMT ":%u ulen %d\n",
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
- NIPQUAD(saddr),
+ &saddr,
ntohs(uh->source),
- NIPQUAD(daddr),
+ &daddr,
ntohs(uh->dest),
ulen);
drop:
* Socket option code for UDP
*/
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen,
+ char __user *optval, unsigned int optlen,
int (*push_pending_frames)(struct sock *))
{
struct udp_sock *up = udp_sk(sk);
int err = 0;
int is_udplite = IS_UDPLITE(sk);
- if (optlen<sizeof(int))
+ if (optlen < sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
return err;
}
+EXPORT_SYMBOL(udp_lib_setsockopt);
int udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
return udp_lib_setsockopt(sk, level, optname, optval, optlen,
#ifdef CONFIG_COMPAT
int compat_udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
return udp_lib_setsockopt(sk, level, optname, optval, optlen,
struct udp_sock *up = udp_sk(sk);
int val, len;
- if (get_user(len,optlen))
+ if (get_user(len, optlen))
return -EFAULT;
len = min_t(unsigned int, len, sizeof(int));
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval, &val,len))
+ if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
+EXPORT_SYMBOL(udp_lib_getsockopt);
int udp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
unsigned int mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
- int is_lite = IS_UDPLITE(sk);
/* Check for false positives due to checksum errors */
- if ( (mask & POLLRDNORM) &&
- !(file->f_flags & O_NONBLOCK) &&
- !(sk->sk_shutdown & RCV_SHUTDOWN)){
- struct sk_buff_head *rcvq = &sk->sk_receive_queue;
- struct sk_buff *skb;
-
- spin_lock_bh(&rcvq->lock);
- while ((skb = skb_peek(rcvq)) != NULL &&
- udp_lib_checksum_complete(skb)) {
- UDP_INC_STATS_BH(sock_net(sk),
- UDP_MIB_INERRORS, is_lite);
- __skb_unlink(skb, rcvq);
- kfree_skb(skb);
- }
- spin_unlock_bh(&rcvq->lock);
-
- /* nothing to see, move along */
- if (skb == NULL)
- mask &= ~(POLLIN | POLLRDNORM);
- }
+ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
+ !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
+ mask &= ~(POLLIN | POLLRDNORM);
return mask;
}
+EXPORT_SYMBOL(udp_poll);
struct proto udp_prot = {
.name = "UDP",
.compat_getsockopt = compat_udp_getsockopt,
#endif
};
+EXPORT_SYMBOL(udp_prot);
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
- for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
- struct hlist_node *node;
+ for (state->bucket = start; state->bucket <= state->udp_table->mask;
+ ++state->bucket) {
+ struct hlist_nulls_node *node;
struct udp_hslot *hslot = &state->udp_table->hash[state->bucket];
+
+ if (hlist_nulls_empty(&hslot->head))
+ continue;
+
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(&state->udp_table->hash[state->bucket].lock);
+ if (state->bucket <= state->udp_table->mask)
+ 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 = MAX_UDP_PORTS;
+
return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
{
struct udp_iter_state *state = seq->private;
- if (state->bucket < UDP_HTABLE_SIZE)
+ if (state->bucket <= state->udp_table->mask)
spin_unlock_bh(&state->udp_table->hash[state->bucket].lock);
}
rc = -ENOMEM;
return rc;
}
+EXPORT_SYMBOL(udp_proc_register);
void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
{
proc_net_remove(net, afinfo->name);
}
+EXPORT_SYMBOL(udp_proc_unregister);
/* ------------------------------------------------------------------------ */
static void udp4_format_sock(struct sock *sp, struct seq_file *f,
int bucket, int *len)
{
struct inet_sock *inet = inet_sk(sp);
- __be32 dest = inet->daddr;
- __be32 src = inet->rcv_saddr;
- __u16 destp = ntohs(inet->dport);
- __u16 srcp = ntohs(inet->sport);
+ __be32 dest = inet->inet_daddr;
+ __be32 src = inet->inet_rcv_saddr;
+ __u16 destp = ntohs(inet->inet_dport);
+ __u16 srcp = ntohs(inet->inet_sport);
- seq_printf(f, "%4d: %08X:%04X %08X:%04X"
+ seq_printf(f, "%5d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n",
bucket, src, srcp, dest, destp, sp->sk_state,
- atomic_read(&sp->sk_wmem_alloc),
- atomic_read(&sp->sk_rmem_alloc),
+ sk_wmem_alloc_get(sp),
+ sk_rmem_alloc_get(sp),
0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
atomic_read(&sp->sk_refcnt), sp,
atomic_read(&sp->sk_drops), len);
int len;
udp4_format_sock(v, seq, state->bucket, &len);
- seq_printf(seq, "%*s\n", 127 - len ,"");
+ seq_printf(seq, "%*s\n", 127 - len, "");
}
return 0;
}
}
#endif /* CONFIG_PROC_FS */
-void __init udp_table_init(struct udp_table *table)
+static __initdata unsigned long uhash_entries;
+static int __init set_uhash_entries(char *str)
{
- int i;
+ if (!str)
+ return 0;
+ uhash_entries = simple_strtoul(str, &str, 0);
+ if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN)
+ uhash_entries = UDP_HTABLE_SIZE_MIN;
+ return 1;
+}
+__setup("uhash_entries=", set_uhash_entries);
- for (i = 0; i < UDP_HTABLE_SIZE; i++) {
- INIT_HLIST_HEAD(&table->hash[i].head);
+void __init udp_table_init(struct udp_table *table, const char *name)
+{
+ unsigned int i;
+
+ if (!CONFIG_BASE_SMALL)
+ table->hash = alloc_large_system_hash(name,
+ sizeof(struct udp_hslot),
+ uhash_entries,
+ 21, /* one slot per 2 MB */
+ 0,
+ &table->log,
+ &table->mask,
+ 64 * 1024);
+ /*
+ * Make sure hash table has the minimum size
+ */
+ if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) {
+ table->hash = kmalloc(UDP_HTABLE_SIZE_MIN *
+ sizeof(struct udp_hslot), GFP_KERNEL);
+ if (!table->hash)
+ panic(name);
+ table->log = ilog2(UDP_HTABLE_SIZE_MIN);
+ table->mask = UDP_HTABLE_SIZE_MIN - 1;
+ }
+ for (i = 0; i <= table->mask; i++) {
+ INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i);
spin_lock_init(&table->hash[i].lock);
}
}
{
unsigned long nr_pages, limit;
- udp_table_init(&udp_table);
+ udp_table_init(&udp_table, "UDP");
/* Set the pressure threshold up by the same strategy of TCP. It is a
* fraction of global memory that is up to 1/2 at 256 MB, decreasing
* toward zero with the amount of memory, with a floor of 128 pages.
sysctl_udp_wmem_min = SK_MEM_QUANTUM;
}
-EXPORT_SYMBOL(udp_disconnect);
-EXPORT_SYMBOL(udp_ioctl);
-EXPORT_SYMBOL(udp_prot);
-EXPORT_SYMBOL(udp_sendmsg);
-EXPORT_SYMBOL(udp_lib_getsockopt);
-EXPORT_SYMBOL(udp_lib_setsockopt);
-EXPORT_SYMBOL(udp_poll);
-EXPORT_SYMBOL(udp_lib_get_port);
+int udp4_ufo_send_check(struct sk_buff *skb)
+{
+ const struct iphdr *iph;
+ struct udphdr *uh;
+
+ if (!pskb_may_pull(skb, sizeof(*uh)))
+ return -EINVAL;
+
+ iph = ip_hdr(skb);
+ uh = udp_hdr(skb);
+
+ uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ IPPROTO_UDP, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ return 0;
+}
+
+struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int mss;
+ int offset;
+ __wsum csum;
+
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
+ if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+ /* Packet is from an untrusted source, reset gso_segs. */
+ int type = skb_shinfo(skb)->gso_type;
+
+ if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) ||
+ !(type & (SKB_GSO_UDP))))
+ goto out;
+
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+ segs = NULL;
+ goto out;
+ }
+
+ /* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+ * do checksum of UDP packets sent as multiple IP fragments.
+ */
+ offset = skb->csum_start - skb_headroom(skb);
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ offset += skb->csum_offset;
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+
+ /* Fragment the skb. IP headers of the fragments are updated in
+ * inet_gso_segment()
+ */
+ segs = skb_segment(skb, features);
+out:
+ return segs;
+}
-#ifdef CONFIG_PROC_FS
-EXPORT_SYMBOL(udp_proc_register);
-EXPORT_SYMBOL(udp_proc_unregister);
-#endif