* published by the Free Software Foundation.
*/
+#include <linux/config.h>
#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/random.h>
#include <net/checksum.h>
+#include <net/inet_common.h>
#include <net/inet_sock.h>
+#include <net/protocol.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include "ccid.h"
#include "dccp.h"
-#include "feat.h"
DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
EXPORT_SYMBOL_GPL(dccp_orphan_count);
-struct inet_hashinfo __cacheline_aligned dccp_hashinfo = {
- .lhash_lock = RW_LOCK_UNLOCKED,
- .lhash_users = ATOMIC_INIT(0),
- .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait),
+static struct net_protocol dccp_protocol = {
+ .handler = dccp_v4_rcv,
+ .err_handler = dccp_v4_err,
+ .no_policy = 1,
};
-EXPORT_SYMBOL_GPL(dccp_hashinfo);
-
-void dccp_set_state(struct sock *sk, const int state)
-{
- const int oldstate = sk->sk_state;
-
- dccp_pr_debug("%s(%p) %-10.10s -> %s\n",
- dccp_role(sk), sk,
- dccp_state_name(oldstate), dccp_state_name(state));
- WARN_ON(state == oldstate);
-
- switch (state) {
- case DCCP_OPEN:
- if (oldstate != DCCP_OPEN)
- DCCP_INC_STATS(DCCP_MIB_CURRESTAB);
- break;
-
- case DCCP_CLOSED:
- if (oldstate == DCCP_CLOSING || oldstate == DCCP_OPEN)
- DCCP_INC_STATS(DCCP_MIB_ESTABRESETS);
-
- sk->sk_prot->unhash(sk);
- if (inet_csk(sk)->icsk_bind_hash != NULL &&
- !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
- inet_put_port(&dccp_hashinfo, sk);
- /* fall through */
- default:
- if (oldstate == DCCP_OPEN)
- DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
- }
-
- /* Change state AFTER socket is unhashed to avoid closed
- * socket sitting in hash tables.
- */
- sk->sk_state = state;
-}
-
-EXPORT_SYMBOL_GPL(dccp_set_state);
-
-void dccp_done(struct sock *sk)
-{
- dccp_set_state(sk, DCCP_CLOSED);
- dccp_clear_xmit_timers(sk);
-
- sk->sk_shutdown = SHUTDOWN_MASK;
-
- if (!sock_flag(sk, SOCK_DEAD))
- sk->sk_state_change(sk);
- else
- inet_csk_destroy_sock(sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_done);
-
const char *dccp_packet_name(const int type)
{
static const char *dccp_packet_names[] = {
EXPORT_SYMBOL_GPL(dccp_state_name);
-void dccp_hash(struct sock *sk)
-{
- inet_hash(&dccp_hashinfo, sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_hash);
-
-void dccp_unhash(struct sock *sk)
-{
- inet_unhash(&dccp_hashinfo, sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_unhash);
-
-int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
-{
- struct dccp_sock *dp = dccp_sk(sk);
- struct dccp_minisock *dmsk = dccp_msk(sk);
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- dccp_minisock_init(&dp->dccps_minisock);
- do_gettimeofday(&dp->dccps_epoch);
-
- /*
- * FIXME: We're hardcoding the CCID, and doing this at this point makes
- * the listening (master) sock get CCID control blocks, which is not
- * necessary, but for now, to not mess with the test userspace apps,
- * lets leave it here, later the real solution is to do this in a
- * setsockopt(CCIDs-I-want/accept). -acme
- */
- if (likely(ctl_sock_initialized)) {
- int rc = dccp_feat_init(dmsk);
-
- if (rc)
- return rc;
-
- if (dmsk->dccpms_send_ack_vector) {
- dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL);
- if (dp->dccps_hc_rx_ackvec == NULL)
- return -ENOMEM;
- }
- dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid,
- sk, GFP_KERNEL);
- dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid,
- sk, GFP_KERNEL);
- if (unlikely(dp->dccps_hc_rx_ccid == NULL ||
- dp->dccps_hc_tx_ccid == NULL)) {
- ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
- ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
- if (dmsk->dccpms_send_ack_vector) {
- dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
- dp->dccps_hc_rx_ackvec = NULL;
- }
- dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
- return -ENOMEM;
- }
- } else {
- /* control socket doesn't need feat nego */
- INIT_LIST_HEAD(&dmsk->dccpms_pending);
- INIT_LIST_HEAD(&dmsk->dccpms_conf);
- }
-
- dccp_init_xmit_timers(sk);
- icsk->icsk_rto = DCCP_TIMEOUT_INIT;
- sk->sk_state = DCCP_CLOSED;
- sk->sk_write_space = dccp_write_space;
- icsk->icsk_sync_mss = dccp_sync_mss;
- dp->dccps_mss_cache = 536;
- dp->dccps_role = DCCP_ROLE_UNDEFINED;
- dp->dccps_service = DCCP_SERVICE_INVALID_VALUE;
- dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1;
-
- return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_init_sock);
-
-int dccp_destroy_sock(struct sock *sk)
-{
- struct dccp_sock *dp = dccp_sk(sk);
- struct dccp_minisock *dmsk = dccp_msk(sk);
-
- /*
- * DCCP doesn't use sk_write_queue, just sk_send_head
- * for retransmissions
- */
- if (sk->sk_send_head != NULL) {
- kfree_skb(sk->sk_send_head);
- sk->sk_send_head = NULL;
- }
-
- /* Clean up a referenced DCCP bind bucket. */
- if (inet_csk(sk)->icsk_bind_hash != NULL)
- inet_put_port(&dccp_hashinfo, sk);
-
- kfree(dp->dccps_service_list);
- dp->dccps_service_list = NULL;
-
- if (dmsk->dccpms_send_ack_vector) {
- dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
- dp->dccps_hc_rx_ackvec = NULL;
- }
- ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
- ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
- dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
-
- /* clean up feature negotiation state */
- dccp_feat_clean(dmsk);
-
- return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_destroy_sock);
-
static inline int dccp_listen_start(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
mask |= POLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLIN | POLLRDNORM | POLLRDHUP;
+ mask |= POLLIN | POLLRDNORM;
/* Connected? */
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
EXPORT_SYMBOL_GPL(dccp_ioctl);
-static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
+static int dccp_setsockopt_service(struct sock *sk, const u32 service,
char __user *optval, int optlen)
{
struct dccp_sock *dp = dccp_sk(sk);
return 0;
}
-/* byte 1 is feature. the rest is the preference list */
-static int dccp_setsockopt_change(struct sock *sk, int type,
- struct dccp_so_feat __user *optval)
-{
- struct dccp_so_feat opt;
- u8 *val;
- int rc;
-
- if (copy_from_user(&opt, optval, sizeof(opt)))
- return -EFAULT;
-
- val = kmalloc(opt.dccpsf_len, GFP_KERNEL);
- if (!val)
- return -ENOMEM;
-
- if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) {
- rc = -EFAULT;
- goto out_free_val;
- }
-
- rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat,
- val, opt.dccpsf_len, GFP_KERNEL);
- if (rc)
- goto out_free_val;
-
-out:
- return rc;
-
-out_free_val:
- kfree(val);
- goto out;
-}
-
-static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+int dccp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
{
struct dccp_sock *dp;
int err;
int val;
+ if (level != SOL_DCCP)
+ return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
+ optname, optval,
+ optlen);
+
if (optlen < sizeof(int))
return -EINVAL;
case DCCP_SOCKOPT_PACKET_SIZE:
dp->dccps_packet_size = val;
break;
-
- case DCCP_SOCKOPT_CHANGE_L:
- if (optlen != sizeof(struct dccp_so_feat))
- err = -EINVAL;
- else
- err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L,
- (struct dccp_so_feat __user *)
- optval);
- break;
-
- case DCCP_SOCKOPT_CHANGE_R:
- if (optlen != sizeof(struct dccp_so_feat))
- err = -EINVAL;
- else
- err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R,
- (struct dccp_so_feat __user *)
- optval);
- break;
-
default:
err = -ENOPROTOOPT;
break;
return err;
}
-int dccp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
-{
- if (level != SOL_DCCP)
- return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
- optname, optval,
- optlen);
- return do_dccp_setsockopt(sk, level, optname, optval, optlen);
-}
-
EXPORT_SYMBOL_GPL(dccp_setsockopt);
-#ifdef CONFIG_COMPAT
-int compat_dccp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
-{
- if (level != SOL_DCCP)
- return inet_csk_compat_setsockopt(sk, level, optname,
- optval, optlen);
- return do_dccp_setsockopt(sk, level, optname, optval, optlen);
-}
-
-EXPORT_SYMBOL_GPL(compat_dccp_setsockopt);
-#endif
-
static int dccp_getsockopt_service(struct sock *sk, int len,
- __be32 __user *optval,
+ u32 __user *optval,
int __user *optlen)
{
const struct dccp_sock *dp = dccp_sk(sk);
return err;
}
-static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
+int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct dccp_sock *dp;
int val, len;
+ if (level != SOL_DCCP)
+ return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
+ optname, optval,
+ optlen);
if (get_user(len, optlen))
return -EFAULT;
break;
case DCCP_SOCKOPT_SERVICE:
return dccp_getsockopt_service(sk, len,
- (__be32 __user *)optval, optlen);
+ (u32 __user *)optval, optlen);
case 128 ... 191:
return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
return 0;
}
-int dccp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level != SOL_DCCP)
- return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
- optname, optval,
- optlen);
- return do_dccp_getsockopt(sk, level, optname, optval, optlen);
-}
-
EXPORT_SYMBOL_GPL(dccp_getsockopt);
-#ifdef CONFIG_COMPAT
-int compat_dccp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level != SOL_DCCP)
- return inet_csk_compat_getsockopt(sk, level, optname,
- optval, optlen);
- return do_dccp_getsockopt(sk, level, optname, optval, optlen);
-}
-
-EXPORT_SYMBOL_GPL(compat_dccp_getsockopt);
-#endif
-
int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
}
dccp_pr_debug("packet_type=%s\n",
dccp_packet_name(dh->dccph_type));
- sk_eat_skb(sk, skb, 0);
+ sk_eat_skb(sk, skb);
verify_sock_status:
if (sock_flag(sk, SOCK_DONE)) {
len = 0;
}
found_fin_ok:
if (!(flags & MSG_PEEK))
- sk_eat_skb(sk, skb, 0);
+ sk_eat_skb(sk, skb);
break;
} while (1);
out:
void dccp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
- int state;
lock_sock(sk);
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
- state = sk->sk_state;
- sock_hold(sk);
- sock_orphan(sk);
- atomic_inc(sk->sk_prot->orphan_count);
-
/*
* It is the last release_sock in its life. It will remove backlog.
*/
bh_lock_sock(sk);
BUG_TRAP(!sock_owned_by_user(sk));
- /* Have we already been destroyed by a softirq or backlog? */
- if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
- goto out;
+ sock_hold(sk);
+ sock_orphan(sk);
/*
* The last release_sock may have processed the CLOSE or RESET
#endif
}
+ atomic_inc(sk->sk_prot->orphan_count);
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
-out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
EXPORT_SYMBOL_GPL(dccp_shutdown);
-static int __init dccp_mib_init(void)
+static const struct proto_ops inet_dccp_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = inet_release,
+ .bind = inet_bind,
+ .connect = inet_stream_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = inet_accept,
+ .getname = inet_getname,
+ /* FIXME: work on tcp_poll to rename it to inet_csk_poll */
+ .poll = dccp_poll,
+ .ioctl = inet_ioctl,
+ /* FIXME: work on inet_listen to rename it to sock_common_listen */
+ .listen = inet_dccp_listen,
+ .shutdown = inet_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = sock_common_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = sock_no_sendpage,
+};
+
+extern struct net_proto_family inet_family_ops;
+
+static struct inet_protosw dccp_v4_protosw = {
+ .type = SOCK_DCCP,
+ .protocol = IPPROTO_DCCP,
+ .prot = &dccp_prot,
+ .ops = &inet_dccp_ops,
+ .capability = -1,
+ .no_check = 0,
+ .flags = INET_PROTOSW_ICSK,
+};
+
+/*
+ * This is the global socket data structure used for responding to
+ * the Out-of-the-blue (OOTB) packets. A control sock will be created
+ * for this socket at the initialization time.
+ */
+struct socket *dccp_ctl_socket;
+
+static char dccp_ctl_socket_err_msg[] __initdata =
+ KERN_ERR "DCCP: Failed to create the control socket.\n";
+
+static int __init dccp_ctl_sock_init(void)
+{
+ int rc = sock_create_kern(PF_INET, SOCK_DCCP, IPPROTO_DCCP,
+ &dccp_ctl_socket);
+ if (rc < 0)
+ printk(dccp_ctl_socket_err_msg);
+ else {
+ dccp_ctl_socket->sk->sk_allocation = GFP_ATOMIC;
+ inet_sk(dccp_ctl_socket->sk)->uc_ttl = -1;
+
+ /* Unhash it so that IP input processing does not even
+ * see it, we do not wish this socket to see incoming
+ * packets.
+ */
+ dccp_ctl_socket->sk->sk_prot->unhash(dccp_ctl_socket->sk);
+ }
+
+ return rc;
+}
+
+#ifdef CONFIG_IP_DCCP_UNLOAD_HACK
+void dccp_ctl_sock_exit(void)
+{
+ if (dccp_ctl_socket != NULL) {
+ sock_release(dccp_ctl_socket);
+ dccp_ctl_socket = NULL;
+ }
+}
+
+EXPORT_SYMBOL_GPL(dccp_ctl_sock_exit);
+#endif
+
+static int __init init_dccp_v4_mibs(void)
{
int rc = -ENOMEM;
}
-static void dccp_mib_exit(void)
-{
- free_percpu(dccp_statistics[0]);
- free_percpu(dccp_statistics[1]);
- dccp_statistics[0] = dccp_statistics[1] = NULL;
-}
-
static int thash_entries;
module_param(thash_entries, int, 0444);
MODULE_PARM_DESC(thash_entries, "Number of ehash buckets");
{
unsigned long goal;
int ehash_order, bhash_order, i;
- int rc = -ENOBUFS;
+ int rc = proto_register(&dccp_prot, 1);
+
+ if (rc)
+ goto out;
dccp_hashinfo.bind_bucket_cachep =
kmem_cache_create("dccp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
SLAB_HWCACHE_ALIGN, NULL, NULL);
if (!dccp_hashinfo.bind_bucket_cachep)
- goto out;
+ goto out_proto_unregister;
/*
* Size and allocate the main established and bind bucket
INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
}
- rc = dccp_mib_init();
- if (rc)
+ if (init_dccp_v4_mibs())
goto out_free_dccp_bhash;
- rc = dccp_ackvec_init();
- if (rc)
- goto out_free_dccp_mib;
+ rc = -EAGAIN;
+ if (inet_add_protocol(&dccp_protocol, IPPROTO_DCCP))
+ goto out_free_dccp_v4_mibs;
- rc = dccp_sysctl_init();
+ inet_register_protosw(&dccp_v4_protosw);
+
+ rc = dccp_ctl_sock_init();
if (rc)
- goto out_ackvec_exit;
+ goto out_unregister_protosw;
out:
return rc;
-out_ackvec_exit:
- dccp_ackvec_exit();
-out_free_dccp_mib:
- dccp_mib_exit();
+out_unregister_protosw:
+ inet_unregister_protosw(&dccp_v4_protosw);
+ inet_del_protocol(&dccp_protocol, IPPROTO_DCCP);
+out_free_dccp_v4_mibs:
+ free_percpu(dccp_statistics[0]);
+ free_percpu(dccp_statistics[1]);
+ dccp_statistics[0] = dccp_statistics[1] = NULL;
out_free_dccp_bhash:
free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
dccp_hashinfo.bhash = NULL;
out_free_bind_bucket_cachep:
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
dccp_hashinfo.bind_bucket_cachep = NULL;
+out_proto_unregister:
+ proto_unregister(&dccp_prot);
goto out;
}
+static const char dccp_del_proto_err_msg[] __exitdata =
+ KERN_ERR "can't remove dccp net_protocol\n";
+
static void __exit dccp_fini(void)
{
- dccp_mib_exit();
+ inet_unregister_protosw(&dccp_v4_protosw);
+
+ if (inet_del_protocol(&dccp_protocol, IPPROTO_DCCP) < 0)
+ printk(dccp_del_proto_err_msg);
+
+ free_percpu(dccp_statistics[0]);
+ free_percpu(dccp_statistics[1]);
free_pages((unsigned long)dccp_hashinfo.bhash,
get_order(dccp_hashinfo.bhash_size *
sizeof(struct inet_bind_hashbucket)));
get_order(dccp_hashinfo.ehash_size *
sizeof(struct inet_ehash_bucket)));
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
- dccp_ackvec_exit();
- dccp_sysctl_exit();
+ proto_unregister(&dccp_prot);
}
module_init(dccp_init);
module_exit(dccp_fini);
+/*
+ * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33)
+ * values directly, Also cover the case where the protocol is not specified,
+ * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP
+ */
+MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-33-type-6");
+MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-0-type-6");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>");
MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");
git://git.onelab.eu / linux-2.6.git / blobdiff