* be incorporated into the next SCTP release.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/init.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
#include <linux/bootmem.h>
+#include <linux/highmem.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
/* Global data structures. */
struct sctp_globals sctp_globals __read_mostly;
-struct proc_dir_entry *proc_net_sctp;
DEFINE_SNMP_STAT(struct sctp_mib, sctp_statistics) __read_mostly;
+#ifdef CONFIG_PROC_FS
+struct proc_dir_entry *proc_net_sctp;
+#endif
+
struct idr sctp_assocs_id;
DEFINE_SPINLOCK(sctp_assocs_id_lock);
* the Out-of-the-blue (OOTB) packets. A control sock will be created
* for this socket at the initialization time.
*/
-static struct socket *sctp_ctl_socket;
+static struct sock *sctp_ctl_sock;
static struct sctp_pf *sctp_pf_inet6_specific;
static struct sctp_pf *sctp_pf_inet_specific;
struct kmem_cache *sctp_chunk_cachep __read_mostly;
struct kmem_cache *sctp_bucket_cachep __read_mostly;
-int sysctl_sctp_mem[3];
+long sysctl_sctp_mem[3];
int sysctl_sctp_rmem[3];
int sysctl_sctp_wmem[3];
/* Return the address of the control sock. */
struct sock *sctp_get_ctl_sock(void)
{
- return sctp_ctl_socket->sk;
+ return sctp_ctl_sock;
}
/* Set up the proc fs entry for the SCTP protocol. */
static __init int sctp_proc_init(void)
{
+ if (percpu_counter_init(&sctp_sockets_allocated, 0))
+ goto out_nomem;
+#ifdef CONFIG_PROC_FS
if (!proc_net_sctp) {
- struct proc_dir_entry *ent;
- ent = proc_mkdir("sctp", init_net.proc_net);
- if (ent) {
- ent->owner = THIS_MODULE;
- proc_net_sctp = ent;
- } else
- goto out_nomem;
+ proc_net_sctp = proc_mkdir("sctp", init_net.proc_net);
+ if (!proc_net_sctp)
+ goto out_free_percpu;
}
if (sctp_snmp_proc_init())
- goto out_nomem;
+ goto out_snmp_proc_init;
if (sctp_eps_proc_init())
- goto out_nomem;
+ goto out_eps_proc_init;
if (sctp_assocs_proc_init())
- goto out_nomem;
+ goto out_assocs_proc_init;
+ if (sctp_remaddr_proc_init())
+ goto out_remaddr_proc_init;
+
+ return 0;
+out_remaddr_proc_init:
+ sctp_assocs_proc_exit();
+out_assocs_proc_init:
+ sctp_eps_proc_exit();
+out_eps_proc_init:
+ sctp_snmp_proc_exit();
+out_snmp_proc_init:
+ if (proc_net_sctp) {
+ proc_net_sctp = NULL;
+ remove_proc_entry("sctp", init_net.proc_net);
+ }
+out_free_percpu:
+ percpu_counter_destroy(&sctp_sockets_allocated);
+#else
return 0;
+#endif /* CONFIG_PROC_FS */
out_nomem:
return -ENOMEM;
*/
static void sctp_proc_exit(void)
{
+#ifdef CONFIG_PROC_FS
sctp_snmp_proc_exit();
sctp_eps_proc_exit();
sctp_assocs_proc_exit();
+ sctp_remaddr_proc_exit();
if (proc_net_sctp) {
proc_net_sctp = NULL;
remove_proc_entry("sctp", init_net.proc_net);
}
+#endif
+ percpu_counter_destroy(&sctp_sockets_allocated);
}
/* Private helper to extract ipv4 address and stash them in
addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
addr->valid = 1;
INIT_LIST_HEAD(&addr->list);
- INIT_RCU_HEAD(&addr->rcu);
list_add_tail(&addr->list, addrlist);
}
}
struct list_head *pos;
struct sctp_af *af;
- read_lock(&dev_base_lock);
- for_each_netdev(&init_net, dev) {
+ rcu_read_lock();
+ for_each_netdev_rcu(&init_net, dev) {
__list_for_each(pos, &sctp_address_families) {
af = list_entry(pos, struct sctp_af, list);
af->copy_addrlist(&sctp_local_addr_list, dev);
}
}
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
}
/* Free the existing local addresses. */
}
}
-void sctp_local_addr_free(struct rcu_head *head)
-{
- struct sctp_sockaddr_entry *e = container_of(head,
- struct sctp_sockaddr_entry, rcu);
- kfree(e);
-}
-
/* Copy the local addresses which are valid for 'scope' into 'bp'. */
int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
gfp_t gfp, int copy_flags)
{
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = 0;
- addr->v4.sin_addr.s_addr = inet_sk(sk)->rcv_saddr;
+ addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
}
/* Initialize sk->sk_rcv_saddr from sctp_addr. */
static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
{
- inet_sk(sk)->rcv_saddr = addr->v4.sin_addr.s_addr;
+ inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr;
}
/* Initialize sk->sk_daddr from sctp_addr. */
static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
{
- inet_sk(sk)->daddr = addr->v4.sin_addr.s_addr;
+ inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr;
}
/* Initialize a sctp_addr from an address parameter. */
}
/* Initialize a sctp_addr from a dst_entry. */
-static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct dst_entry *dst,
+static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
__be16 port)
{
- struct rtable *rt = (struct rtable *)dst;
saddr->v4.sin_family = AF_INET;
saddr->v4.sin_port = port;
- saddr->v4.sin_addr.s_addr = rt->rt_src;
+ saddr->v4.sin_addr.s_addr = fl4->saddr;
}
/* Compare two addresses exactly. */
struct sctp_sock *sp,
const struct sk_buff *skb)
{
+ /* IPv4 addresses not allowed */
+ if (sp && ipv6_only_sock(sctp_opt2sk(sp)))
+ return 0;
+
/* Is this a non-unicast address or a unusable SCTP address? */
if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr))
return 0;
/* Is this a broadcast address? */
- if (skb && skb->rtable->rt_flags & RTCF_BROADCAST)
+ if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST)
return 0;
return 1;
!sysctl_ip_nonlocal_bind)
return 0;
+ if (ipv6_only_sock(sctp_opt2sk(sp)))
+ return 0;
+
return 1;
}
* of requested destination address, sender and receiver
* SHOULD include all of its addresses with level greater
* than or equal to L.
+ *
+ * IPv4 scoping can be controlled through sysctl option
+ * net.sctp.addr_scope_policy
*/
static sctp_scope_t sctp_v4_scope(union sctp_addr *addr)
{
sctp_scope_t retval;
- /* Should IPv4 scoping be a sysctl configurable option
- * so users can turn it off (default on) for certain
- * unconventional networking environments?
- */
-
/* Check for unusable SCTP addresses. */
if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_UNUSABLE;
* addresses. If an association is passed, trys to get a dst entry with a
* source address that matches an address in the bind address list.
*/
-static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
- union sctp_addr *daddr,
- union sctp_addr *saddr)
+static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
+ struct flowi *fl, struct sock *sk)
{
+ struct sctp_association *asoc = t->asoc;
struct rtable *rt;
- struct flowi fl;
+ struct flowi4 *fl4 = &fl->u.ip4;
struct sctp_bind_addr *bp;
struct sctp_sockaddr_entry *laddr;
struct dst_entry *dst = NULL;
+ union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
- memset(&fl, 0x0, sizeof(struct flowi));
- fl.fl4_dst = daddr->v4.sin_addr.s_addr;
- fl.proto = IPPROTO_SCTP;
+ memset(fl4, 0x0, sizeof(struct flowi4));
+ fl4->daddr = daddr->v4.sin_addr.s_addr;
+ fl4->fl4_dport = daddr->v4.sin_port;
+ fl4->flowi4_proto = IPPROTO_SCTP;
if (asoc) {
- fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk);
- fl.oif = asoc->base.sk->sk_bound_dev_if;
+ fl4->flowi4_tos = RT_CONN_FLAGS(asoc->base.sk);
+ fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
+ fl4->fl4_sport = htons(asoc->base.bind_addr.port);
+ }
+ if (saddr) {
+ fl4->saddr = saddr->v4.sin_addr.s_addr;
+ fl4->fl4_sport = saddr->v4.sin_port;
}
- if (saddr)
- fl.fl4_src = saddr->v4.sin_addr.s_addr;
- SCTP_DEBUG_PRINTK("%s: DST:%u.%u.%u.%u, SRC:%u.%u.%u.%u - ",
- __func__, NIPQUAD(fl.fl4_dst),
- NIPQUAD(fl.fl4_src));
+ SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ",
+ __func__, &fl4->daddr, &fl4->saddr);
- if (!ip_route_output_key(&init_net, &rt, &fl)) {
- dst = &rt->u.dst;
- }
+ rt = ip_route_output_key(&init_net, fl4);
+ if (!IS_ERR(rt))
+ dst = &rt->dst;
/* If there is no association or if a source address is passed, no
* more validation is required.
/* Walk through the bind address list and look for a bind
* address that matches the source address of the returned dst.
*/
+ sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port));
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC))
continue;
- sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
goto out_unlock;
}
continue;
if ((laddr->state == SCTP_ADDR_SRC) &&
(AF_INET == laddr->a.sa.sa_family)) {
- fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
- if (!ip_route_output_key(&init_net, &rt, &fl)) {
- dst = &rt->u.dst;
+ fl4->saddr = laddr->a.v4.sin_addr.s_addr;
+ fl4->fl4_sport = laddr->a.v4.sin_port;
+ rt = ip_route_output_key(&init_net, fl4);
+ if (!IS_ERR(rt)) {
+ dst = &rt->dst;
goto out_unlock;
}
}
out_unlock:
rcu_read_unlock();
out:
+ t->dst = dst;
if (dst)
- SCTP_DEBUG_PRINTK("rt_dst:%u.%u.%u.%u, rt_src:%u.%u.%u.%u\n",
- NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_src));
+ SCTP_DEBUG_PRINTK("rt_dst:%pI4, rt_src:%pI4\n",
+ &fl4->daddr, &fl4->saddr);
else
SCTP_DEBUG_PRINTK("NO ROUTE\n");
-
- return dst;
}
/* For v4, the source address is cached in the route entry(dst). So no need
* to cache it separately and hence this is an empty routine.
*/
-static void sctp_v4_get_saddr(struct sctp_association *asoc,
- struct dst_entry *dst,
- union sctp_addr *daddr,
- union sctp_addr *saddr)
+static void sctp_v4_get_saddr(struct sctp_sock *sk,
+ struct sctp_transport *t,
+ struct flowi *fl)
{
- struct rtable *rt = (struct rtable *)dst;
-
- if (!asoc)
- return;
+ union sctp_addr *saddr = &t->saddr;
+ struct rtable *rt = (struct rtable *)t->dst;
if (rt) {
saddr->v4.sin_family = AF_INET;
- saddr->v4.sin_port = htons(asoc->base.bind_addr.port);
- saddr->v4.sin_addr.s_addr = rt->rt_src;
+ saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr;
}
}
/* What interface did this skb arrive on? */
static int sctp_v4_skb_iif(const struct sk_buff *skb)
{
- return skb->rtable->rt_iif;
+ return skb_rtable(skb)->rt_iif;
}
/* Was this packet marked by Explicit Congestion Notification? */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
struct sctp_association *asoc)
{
- struct inet_sock *inet = inet_sk(sk);
- struct inet_sock *newinet;
- struct sock *newsk = sk_alloc(sk->sk_net, PF_INET, GFP_KERNEL,
+ struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
sk->sk_prot);
+ struct inet_sock *newinet;
if (!newsk)
goto out;
sock_init_data(NULL, newsk);
- newsk->sk_type = SOCK_STREAM;
-
- newsk->sk_no_check = sk->sk_no_check;
- newsk->sk_reuse = sk->sk_reuse;
- newsk->sk_shutdown = sk->sk_shutdown;
-
- newsk->sk_destruct = inet_sock_destruct;
- newsk->sk_family = PF_INET;
- newsk->sk_protocol = IPPROTO_SCTP;
- newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
+ sctp_copy_sock(newsk, sk, asoc);
sock_reset_flag(newsk, SOCK_ZAPPED);
newinet = inet_sk(newsk);
- /* Initialize sk's sport, dport, rcv_saddr and daddr for
- * getsockname() and getpeername()
- */
- newinet->sport = inet->sport;
- newinet->saddr = inet->saddr;
- newinet->rcv_saddr = inet->rcv_saddr;
- newinet->dport = htons(asoc->peer.port);
- newinet->daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;
- newinet->pmtudisc = inet->pmtudisc;
- newinet->id = asoc->next_tsn ^ jiffies;
-
- newinet->uc_ttl = -1;
- newinet->mc_loop = 1;
- newinet->mc_ttl = 1;
- newinet->mc_index = 0;
- newinet->mc_list = NULL;
+ newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;
sk_refcnt_debug_inc(newsk);
/* Dump the v4 addr to the seq file. */
static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
{
- seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr));
+ seq_printf(seq, "%pI4 ", &addr->v4.sin_addr);
+}
+
+static void sctp_v4_ecn_capable(struct sock *sk)
+{
+ INET_ECN_xmit(sk);
+}
+
+void sctp_addr_wq_timeout_handler(unsigned long arg)
+{
+ struct sctp_sockaddr_entry *addrw, *temp;
+ struct sctp_sock *sp;
+
+ spin_lock_bh(&sctp_addr_wq_lock);
+
+ list_for_each_entry_safe(addrw, temp, &sctp_addr_waitq, list) {
+ SCTP_DEBUG_PRINTK_IPADDR("sctp_addrwq_timo_handler: the first ent in wq %p is ",
+ " for cmd %d at entry %p\n", &sctp_addr_waitq, &addrw->a, addrw->state,
+ addrw);
+
+ /* Now we send an ASCONF for each association */
+ /* Note. we currently don't handle link local IPv6 addressees */
+ if (addrw->a.sa.sa_family == AF_INET6) {
+ struct in6_addr *in6;
+
+ if (ipv6_addr_type(&addrw->a.v6.sin6_addr) &
+ IPV6_ADDR_LINKLOCAL)
+ goto free_next;
+
+ in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr;
+ if (ipv6_chk_addr(&init_net, in6, NULL, 0) == 0 &&
+ addrw->state == SCTP_ADDR_NEW) {
+ unsigned long timeo_val;
+
+ SCTP_DEBUG_PRINTK("sctp_timo_handler: this is on DAD, trying %d sec later\n",
+ SCTP_ADDRESS_TICK_DELAY);
+ timeo_val = jiffies;
+ timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
+ mod_timer(&sctp_addr_wq_timer, timeo_val);
+ break;
+ }
+ }
+
+ list_for_each_entry(sp, &sctp_auto_asconf_splist, auto_asconf_list) {
+ struct sock *sk;
+
+ sk = sctp_opt2sk(sp);
+ /* ignore bound-specific endpoints */
+ if (!sctp_is_ep_boundall(sk))
+ continue;
+ sctp_bh_lock_sock(sk);
+ if (sctp_asconf_mgmt(sp, addrw) < 0)
+ SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n");
+ sctp_bh_unlock_sock(sk);
+ }
+free_next:
+ list_del(&addrw->list);
+ kfree(addrw);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
+}
+
+static void sctp_free_addr_wq(void)
+{
+ struct sctp_sockaddr_entry *addrw;
+ struct sctp_sockaddr_entry *temp;
+
+ spin_lock_bh(&sctp_addr_wq_lock);
+ del_timer(&sctp_addr_wq_timer);
+ list_for_each_entry_safe(addrw, temp, &sctp_addr_waitq, list) {
+ list_del(&addrw->list);
+ kfree(addrw);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
+}
+
+/* lookup the entry for the same address in the addr_waitq
+ * sctp_addr_wq MUST be locked
+ */
+static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct sctp_sockaddr_entry *addr)
+{
+ struct sctp_sockaddr_entry *addrw;
+
+ list_for_each_entry(addrw, &sctp_addr_waitq, list) {
+ if (addrw->a.sa.sa_family != addr->a.sa.sa_family)
+ continue;
+ if (addrw->a.sa.sa_family == AF_INET) {
+ if (addrw->a.v4.sin_addr.s_addr ==
+ addr->a.v4.sin_addr.s_addr)
+ return addrw;
+ } else if (addrw->a.sa.sa_family == AF_INET6) {
+ if (ipv6_addr_equal(&addrw->a.v6.sin6_addr,
+ &addr->a.v6.sin6_addr))
+ return addrw;
+ }
+ }
+ return NULL;
+}
+
+void sctp_addr_wq_mgmt(struct sctp_sockaddr_entry *addr, int cmd)
+{
+ struct sctp_sockaddr_entry *addrw;
+ unsigned long timeo_val;
+
+ /* first, we check if an opposite message already exist in the queue.
+ * If we found such message, it is removed.
+ * This operation is a bit stupid, but the DHCP client attaches the
+ * new address after a couple of addition and deletion of that address
+ */
+
+ spin_lock_bh(&sctp_addr_wq_lock);
+ /* Offsets existing events in addr_wq */
+ addrw = sctp_addr_wq_lookup(addr);
+ if (addrw) {
+ if (addrw->state != cmd) {
+ SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt offsets existing entry for %d ",
+ " in wq %p\n", addrw->state, &addrw->a,
+ &sctp_addr_waitq);
+ list_del(&addrw->list);
+ kfree(addrw);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
+ return;
+ }
+
+ /* OK, we have to add the new address to the wait queue */
+ addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
+ if (addrw == NULL) {
+ spin_unlock_bh(&sctp_addr_wq_lock);
+ return;
+ }
+ addrw->state = cmd;
+ list_add_tail(&addrw->list, &sctp_addr_waitq);
+ SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt add new entry for cmd:%d ",
+ " in wq %p\n", addrw->state, &addrw->a, &sctp_addr_waitq);
+
+ if (!timer_pending(&sctp_addr_wq_timer)) {
+ timeo_val = jiffies;
+ timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
+ mod_timer(&sctp_addr_wq_timer, timeo_val);
+ }
+ spin_unlock_bh(&sctp_addr_wq_lock);
}
/* Event handler for inet address addition/deletion events.
struct sctp_sockaddr_entry *temp;
int found = 0;
- if (ifa->ifa_dev->dev->nd_net != &init_net)
+ if (!net_eq(dev_net(ifa->ifa_dev->dev), &init_net))
return NOTIFY_DONE;
switch (ev) {
addr->valid = 1;
spin_lock_bh(&sctp_local_addr_lock);
list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
+ sctp_addr_wq_mgmt(addr, SCTP_ADDR_NEW);
spin_unlock_bh(&sctp_local_addr_lock);
}
break;
spin_lock_bh(&sctp_local_addr_lock);
list_for_each_entry_safe(addr, temp,
&sctp_local_addr_list, list) {
- if (addr->a.v4.sin_addr.s_addr == ifa->ifa_local) {
+ if (addr->a.sa.sa_family == AF_INET &&
+ addr->a.v4.sin_addr.s_addr ==
+ ifa->ifa_local) {
+ sctp_addr_wq_mgmt(addr, SCTP_ADDR_DEL);
found = 1;
addr->valid = 0;
list_del_rcu(&addr->list);
}
spin_unlock_bh(&sctp_local_addr_lock);
if (found)
- call_rcu(&addr->rcu, sctp_local_addr_free);
+ kfree_rcu(addr, rcu);
break;
}
static int sctp_ctl_sock_init(void)
{
int err;
- sa_family_t family;
+ sa_family_t family = PF_INET;
if (sctp_get_pf_specific(PF_INET6))
family = PF_INET6;
- else
- family = PF_INET;
- err = sock_create_kern(family, SOCK_SEQPACKET, IPPROTO_SCTP,
- &sctp_ctl_socket);
+ err = inet_ctl_sock_create(&sctp_ctl_sock, family,
+ SOCK_SEQPACKET, IPPROTO_SCTP, &init_net);
+
+ /* If IPv6 socket could not be created, try the IPv4 socket */
+ if (err < 0 && family == PF_INET6)
+ err = inet_ctl_sock_create(&sctp_ctl_sock, AF_INET,
+ SOCK_SEQPACKET, IPPROTO_SCTP,
+ &init_net);
+
if (err < 0) {
- printk(KERN_ERR
- "SCTP: Failed to create the SCTP control socket.\n");
+ pr_err("Failed to create the SCTP control socket\n");
return err;
}
- sctp_ctl_socket->sk->sk_allocation = GFP_ATOMIC;
- inet_sk(sctp_ctl_socket->sk)->uc_ttl = -1;
-
return 0;
}
static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp)
{
/* PF_INET only supports AF_INET addresses. */
- return (AF_INET == family);
+ return AF_INET == family;
}
/* Address matching with wildcards allowed. */
/* Wrapper routine that calls the ip transmit routine. */
static inline int sctp_v4_xmit(struct sk_buff *skb,
- struct sctp_transport *transport, int ipfragok)
+ struct sctp_transport *transport)
{
- SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, "
- "src:%u.%u.%u.%u, dst:%u.%u.%u.%u\n",
+ struct inet_sock *inet = inet_sk(skb->sk);
+
+ SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n",
__func__, skb, skb->len,
- NIPQUAD(skb->rtable->rt_src),
- NIPQUAD(skb->rtable->rt_dst));
+ &transport->fl.u.ip4.saddr,
+ &transport->fl.u.ip4.daddr);
+
+ inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
+ IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
- return ip_queue_xmit(skb, ipfragok);
+ return ip_queue_xmit(skb, &transport->fl);
}
static struct sctp_af sctp_af_inet;
.protocol = IPPROTO_SCTP,
.prot = &sctp_prot,
.ops = &inet_seqpacket_ops,
- .capability = -1,
.no_check = 0,
.flags = SCTP_PROTOSW_FLAG
};
.protocol = IPPROTO_SCTP,
.prot = &sctp_prot,
.ops = &inet_seqpacket_ops,
- .capability = -1,
.no_check = 0,
.flags = SCTP_PROTOSW_FLAG
};
/* Register with IP layer. */
-static struct net_protocol sctp_protocol = {
+static const struct net_protocol sctp_protocol = {
.handler = sctp_rcv,
.err_handler = sctp_v4_err,
.no_policy = 1,
.to_sk_daddr = sctp_v4_to_sk_daddr,
.from_addr_param = sctp_v4_from_addr_param,
.to_addr_param = sctp_v4_to_addr_param,
- .dst_saddr = sctp_v4_dst_saddr,
.cmp_addr = sctp_v4_cmp_addr,
.addr_valid = sctp_v4_addr_valid,
.inaddr_any = sctp_v4_inaddr_any,
.skb_iif = sctp_v4_skb_iif,
.is_ce = sctp_v4_is_ce,
.seq_dump_addr = sctp_v4_seq_dump_addr,
+ .ecn_capable = sctp_v4_ecn_capable,
.net_header_len = sizeof(struct iphdr),
.sockaddr_len = sizeof(struct sockaddr_in),
#ifdef CONFIG_COMPAT
return 1;
}
-static int __init init_sctp_mibs(void)
+static inline int init_sctp_mibs(void)
{
- sctp_statistics[0] = alloc_percpu(struct sctp_mib);
- if (!sctp_statistics[0])
- return -ENOMEM;
- sctp_statistics[1] = alloc_percpu(struct sctp_mib);
- if (!sctp_statistics[1]) {
- free_percpu(sctp_statistics[0]);
- return -ENOMEM;
- }
+ return snmp_mib_init((void __percpu **)sctp_statistics,
+ sizeof(struct sctp_mib),
+ __alignof__(struct sctp_mib));
+}
+
+static inline void cleanup_sctp_mibs(void)
+{
+ snmp_mib_free((void __percpu **)sctp_statistics);
+}
+
+static void sctp_v4_pf_init(void)
+{
+ /* Initialize the SCTP specific PF functions. */
+ sctp_register_pf(&sctp_pf_inet, PF_INET);
+ sctp_register_af(&sctp_af_inet);
+}
+
+static void sctp_v4_pf_exit(void)
+{
+ list_del(&sctp_af_inet.list);
+}
+
+static int sctp_v4_protosw_init(void)
+{
+ int rc;
+
+ rc = proto_register(&sctp_prot, 1);
+ if (rc)
+ return rc;
+
+ /* Register SCTP(UDP and TCP style) with socket layer. */
+ inet_register_protosw(&sctp_seqpacket_protosw);
+ inet_register_protosw(&sctp_stream_protosw);
+
return 0;
+}
+
+static void sctp_v4_protosw_exit(void)
+{
+ inet_unregister_protosw(&sctp_stream_protosw);
+ inet_unregister_protosw(&sctp_seqpacket_protosw);
+ proto_unregister(&sctp_prot);
+}
+
+static int sctp_v4_add_protocol(void)
+{
+ /* Register notifier for inet address additions/deletions. */
+ register_inetaddr_notifier(&sctp_inetaddr_notifier);
+
+ /* Register SCTP with inet layer. */
+ if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0)
+ return -EAGAIN;
+ return 0;
}
-static void cleanup_sctp_mibs(void)
+static void sctp_v4_del_protocol(void)
{
- free_percpu(sctp_statistics[0]);
- free_percpu(sctp_statistics[1]);
+ inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
+ unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
}
/* Initialize the universe into something sensible. */
int status = -EINVAL;
unsigned long goal;
unsigned long limit;
+ unsigned long nr_pages;
int max_share;
int order;
/* Initialize object count debugging. */
sctp_dbg_objcnt_init();
- /* Initialize the SCTP specific PF functions. */
- sctp_register_pf(&sctp_pf_inet, PF_INET);
/*
* 14. Suggested SCTP Protocol Parameter Values
*/
/* Set the pressure threshold to be 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.
- * Note this initalizes the data in sctpv6_prot too
+ * Note this initializes the data in sctpv6_prot too
* Unabashedly stolen from tcp_init
*/
- limit = min(num_physpages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
- limit = (limit * (num_physpages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
+ nr_pages = totalram_pages - totalhigh_pages;
+ limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
+ limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
limit = max(limit, 128UL);
sysctl_sctp_mem[0] = limit / 4 * 3;
sysctl_sctp_mem[1] = limit;
limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7);
max_share = min(4UL*1024*1024, limit);
- sysctl_sctp_rmem[0] = PAGE_SIZE; /* give each asoc 1 page min */
+ sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */
sysctl_sctp_rmem[1] = (1500 *(sizeof(struct sk_buff) + 1));
sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share);
/* Size and allocate the association hash table.
* The methodology is similar to that of the tcp hash tables.
*/
- if (num_physpages >= (128 * 1024))
- goal = num_physpages >> (22 - PAGE_SHIFT);
+ if (totalram_pages >= (128 * 1024))
+ goal = totalram_pages >> (22 - PAGE_SHIFT);
else
- goal = num_physpages >> (24 - PAGE_SHIFT);
+ goal = totalram_pages >> (24 - PAGE_SHIFT);
for (order = 0; (1UL << order) < goal; order++)
;
if ((sctp_assoc_hashsize > (64 * 1024)) && order > 0)
continue;
sctp_assoc_hashtable = (struct sctp_hashbucket *)
- __get_free_pages(GFP_ATOMIC, order);
+ __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order);
} while (!sctp_assoc_hashtable && --order > 0);
if (!sctp_assoc_hashtable) {
- printk(KERN_ERR "SCTP: Failed association hash alloc.\n");
+ pr_err("Failed association hash alloc\n");
status = -ENOMEM;
goto err_ahash_alloc;
}
sctp_ep_hashtable = (struct sctp_hashbucket *)
kmalloc(64 * sizeof(struct sctp_hashbucket), GFP_KERNEL);
if (!sctp_ep_hashtable) {
- printk(KERN_ERR "SCTP: Failed endpoint_hash alloc.\n");
+ pr_err("Failed endpoint_hash alloc\n");
status = -ENOMEM;
goto err_ehash_alloc;
}
if ((sctp_port_hashsize > (64 * 1024)) && order > 0)
continue;
sctp_port_hashtable = (struct sctp_bind_hashbucket *)
- __get_free_pages(GFP_ATOMIC, order);
+ __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order);
} while (!sctp_port_hashtable && --order > 0);
if (!sctp_port_hashtable) {
- printk(KERN_ERR "SCTP: Failed bind hash alloc.");
+ pr_err("Failed bind hash alloc\n");
status = -ENOMEM;
goto err_bhash_alloc;
}
INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
}
- printk(KERN_INFO "SCTP: Hash tables configured "
- "(established %d bind %d)\n",
+ pr_info("Hash tables configured (established %d bind %d)\n",
sctp_assoc_hashsize, sctp_port_hashsize);
/* Disable ADDIP by default. */
sctp_addip_enable = 0;
sctp_addip_noauth = 0;
+ sctp_default_auto_asconf = 0;
/* Enable PR-SCTP by default. */
sctp_prsctp_enable = 1;
/* Disable AUTH by default. */
sctp_auth_enable = 0;
+ /* Set SCOPE policy to enabled */
+ sctp_scope_policy = SCTP_SCOPE_POLICY_ENABLE;
+
+ /* Set the default rwnd update threshold */
+ sctp_rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT;
+
sctp_sysctl_register();
INIT_LIST_HEAD(&sctp_address_families);
- sctp_register_af(&sctp_af_inet);
+ sctp_v4_pf_init();
+ sctp_v6_pf_init();
- status = proto_register(&sctp_prot, 1);
- if (status)
- goto err_proto_register;
+ /* Initialize the local address list. */
+ INIT_LIST_HEAD(&sctp_local_addr_list);
+ spin_lock_init(&sctp_local_addr_lock);
+ sctp_get_local_addr_list();
- /* Register SCTP(UDP and TCP style) with socket layer. */
- inet_register_protosw(&sctp_seqpacket_protosw);
- inet_register_protosw(&sctp_stream_protosw);
+ /* Initialize the address event list */
+ INIT_LIST_HEAD(&sctp_addr_waitq);
+ INIT_LIST_HEAD(&sctp_auto_asconf_splist);
+ spin_lock_init(&sctp_addr_wq_lock);
+ sctp_addr_wq_timer.expires = 0;
+ setup_timer(&sctp_addr_wq_timer, sctp_addr_wq_timeout_handler, 0);
+
+ status = sctp_v4_protosw_init();
+
+ if (status)
+ goto err_protosw_init;
- status = sctp_v6_init();
+ status = sctp_v6_protosw_init();
if (status)
- goto err_v6_init;
+ goto err_v6_protosw_init;
/* Initialize the control inode/socket for handling OOTB packets. */
if ((status = sctp_ctl_sock_init())) {
- printk (KERN_ERR
- "SCTP: Failed to initialize the SCTP control sock.\n");
+ pr_err("Failed to initialize the SCTP control sock\n");
goto err_ctl_sock_init;
}
- /* Initialize the local address list. */
- INIT_LIST_HEAD(&sctp_local_addr_list);
- spin_lock_init(&sctp_local_addr_lock);
- sctp_get_local_addr_list();
-
- /* Register notifier for inet address additions/deletions. */
- register_inetaddr_notifier(&sctp_inetaddr_notifier);
-
- /* Register SCTP with inet layer. */
- if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) {
- status = -EAGAIN;
+ status = sctp_v4_add_protocol();
+ if (status)
goto err_add_protocol;
- }
/* Register SCTP with inet6 layer. */
status = sctp_v6_add_protocol();
out:
return status;
err_v6_add_protocol:
- inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
- unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
+ sctp_v4_del_protocol();
err_add_protocol:
- sctp_free_local_addr_list();
- sock_release(sctp_ctl_socket);
+ inet_ctl_sock_destroy(sctp_ctl_sock);
err_ctl_sock_init:
- sctp_v6_exit();
-err_v6_init:
- inet_unregister_protosw(&sctp_stream_protosw);
- inet_unregister_protosw(&sctp_seqpacket_protosw);
- proto_unregister(&sctp_prot);
-err_proto_register:
+ sctp_v6_protosw_exit();
+err_v6_protosw_init:
+ sctp_v4_protosw_exit();
+err_protosw_init:
+ sctp_free_local_addr_list();
+ sctp_v4_pf_exit();
+ sctp_v6_pf_exit();
sctp_sysctl_unregister();
- list_del(&sctp_af_inet.list);
free_pages((unsigned long)sctp_port_hashtable,
get_order(sctp_port_hashsize *
sizeof(struct sctp_bind_hashbucket)));
/* Unregister with inet6/inet layers. */
sctp_v6_del_protocol();
- inet_del_protocol(&sctp_protocol, IPPROTO_SCTP);
+ sctp_v4_del_protocol();
+ sctp_free_addr_wq();
- /* Unregister notifier for inet address additions/deletions. */
- unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
+ /* Free the control endpoint. */
+ inet_ctl_sock_destroy(sctp_ctl_sock);
+
+ /* Free protosw registrations */
+ sctp_v6_protosw_exit();
+ sctp_v4_protosw_exit();
/* Free the local address list. */
sctp_free_local_addr_list();
- /* Free the control endpoint. */
- sock_release(sctp_ctl_socket);
-
- /* Cleanup v6 initializations. */
- sctp_v6_exit();
-
/* Unregister with socket layer. */
- inet_unregister_protosw(&sctp_stream_protosw);
- inet_unregister_protosw(&sctp_seqpacket_protosw);
+ sctp_v6_pf_exit();
+ sctp_v4_pf_exit();
sctp_sysctl_unregister();
- list_del(&sctp_af_inet.list);
free_pages((unsigned long)sctp_assoc_hashtable,
get_order(sctp_assoc_hashsize *
sctp_proc_exit();
cleanup_sctp_mibs();
+ rcu_barrier(); /* Wait for completion of call_rcu()'s */
+
kmem_cache_destroy(sctp_chunk_cachep);
kmem_cache_destroy(sctp_bucket_cachep);
-
- proto_unregister(&sctp_prot);
}
module_init(sctp_init);
MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132");
MODULE_AUTHOR("Linux Kernel SCTP developers <lksctp-developers@lists.sourceforge.net>");
MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)");
+module_param_named(no_checksums, sctp_checksum_disable, bool, 0644);
+MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification");
MODULE_LICENSE("GPL");