* request_sock handling and moved
* most of it into the af independent code.
* Added tail drop and some other bugfixes.
- * Added new listen sematics.
+ * Added new listen semantics.
* Mike McLagan : Routing by source
* Juan Jose Ciarlante: ip_dynaddr bits
* Andi Kleen: various fixes.
* a single port at the same time.
*/
-#include <linux/config.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
+#include <net/transp_v6.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
+#include <net/timewait_sock.h>
#include <net/xfrm.h>
+#include <net/netdma.h>
#include <linux/inet.h>
#include <linux/ipv6.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
-extern int sysctl_ip_dynaddr;
-int sysctl_tcp_tw_reuse;
-int sysctl_tcp_low_latency;
+int sysctl_tcp_tw_reuse __read_mostly;
+int sysctl_tcp_low_latency __read_mostly;
/* Check TCP sequence numbers in ICMP packets. */
#define ICMP_MIN_LENGTH 8
/* Socket used for sending RSTs */
static struct socket *tcp_socket;
-void tcp_v4_send_check(struct sock *sk, struct tcphdr *th, int len,
- struct sk_buff *skb);
+void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb);
struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
- .lhash_lock = RW_LOCK_UNLOCKED,
+ .lhash_lock = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock),
.lhash_users = ATOMIC_INIT(0),
.lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
- .portalloc_lock = SPIN_LOCK_UNLOCKED,
- .port_rover = 1024 - 1,
};
-/*
- * This array holds the first and last local port number.
- * For high-usage systems, use sysctl to change this to
- * 32768-61000
- */
-int sysctl_local_port_range[2] = { 1024, 4999 };
-
-static inline int tcp_bind_conflict(struct sock *sk, struct inet_bind_bucket *tb)
-{
- const u32 sk_rcv_saddr = tcp_v4_rcv_saddr(sk);
- struct sock *sk2;
- struct hlist_node *node;
- int reuse = sk->sk_reuse;
-
- sk_for_each_bound(sk2, node, &tb->owners) {
- if (sk != sk2 &&
- !tcp_v6_ipv6only(sk2) &&
- (!sk->sk_bound_dev_if ||
- !sk2->sk_bound_dev_if ||
- sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
- if (!reuse || !sk2->sk_reuse ||
- sk2->sk_state == TCP_LISTEN) {
- const u32 sk2_rcv_saddr = tcp_v4_rcv_saddr(sk2);
- if (!sk2_rcv_saddr || !sk_rcv_saddr ||
- sk2_rcv_saddr == sk_rcv_saddr)
- break;
- }
- }
- }
- return node != NULL;
-}
-
-/* Obtain a reference to a local port for the given sock,
- * if snum is zero it means select any available local port.
- */
static int tcp_v4_get_port(struct sock *sk, unsigned short snum)
{
- struct inet_bind_hashbucket *head;
- struct hlist_node *node;
- struct inet_bind_bucket *tb;
- int ret;
-
- local_bh_disable();
- if (!snum) {
- int low = sysctl_local_port_range[0];
- int high = sysctl_local_port_range[1];
- int remaining = (high - low) + 1;
- int rover;
-
- spin_lock(&tcp_hashinfo.portalloc_lock);
- if (tcp_hashinfo.port_rover < low)
- rover = low;
- else
- rover = tcp_hashinfo.port_rover;
- do {
- rover++;
- if (rover > high)
- rover = low;
- head = &tcp_hashinfo.bhash[inet_bhashfn(rover, tcp_hashinfo.bhash_size)];
- spin_lock(&head->lock);
- inet_bind_bucket_for_each(tb, node, &head->chain)
- if (tb->port == rover)
- goto next;
- break;
- next:
- spin_unlock(&head->lock);
- } while (--remaining > 0);
- tcp_hashinfo.port_rover = rover;
- spin_unlock(&tcp_hashinfo.portalloc_lock);
-
- /* Exhausted local port range during search? It is not
- * possible for us to be holding one of the bind hash
- * locks if this test triggers, because if 'remaining'
- * drops to zero, we broke out of the do/while loop at
- * the top level, not from the 'break;' statement.
- */
- ret = 1;
- if (unlikely(remaining <= 0))
- goto fail;
-
- /* OK, here is the one we will use. HEAD is
- * non-NULL and we hold it's mutex.
- */
- snum = rover;
- } else {
- head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)];
- spin_lock(&head->lock);
- inet_bind_bucket_for_each(tb, node, &head->chain)
- if (tb->port == snum)
- goto tb_found;
- }
- tb = NULL;
- goto tb_not_found;
-tb_found:
- if (!hlist_empty(&tb->owners)) {
- if (sk->sk_reuse > 1)
- goto success;
- if (tb->fastreuse > 0 &&
- sk->sk_reuse && sk->sk_state != TCP_LISTEN) {
- goto success;
- } else {
- ret = 1;
- if (tcp_bind_conflict(sk, tb))
- goto fail_unlock;
- }
- }
-tb_not_found:
- ret = 1;
- if (!tb && (tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, snum)) == NULL)
- goto fail_unlock;
- if (hlist_empty(&tb->owners)) {
- if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
- tb->fastreuse = 1;
- else
- tb->fastreuse = 0;
- } else if (tb->fastreuse &&
- (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
- tb->fastreuse = 0;
-success:
- if (!inet_sk(sk)->bind_hash)
- inet_bind_hash(sk, tb, snum);
- BUG_TRAP(inet_sk(sk)->bind_hash == tb);
- ret = 0;
-
-fail_unlock:
- spin_unlock(&head->lock);
-fail:
- local_bh_enable();
- return ret;
+ return inet_csk_get_port(&tcp_hashinfo, sk, snum,
+ inet_csk_bind_conflict);
}
static void tcp_v4_hash(struct sock *sk)
{
- if (sk->sk_state != TCP_CLOSE) {
- local_bh_disable();
- __inet_hash(&tcp_hashinfo, sk, 1);
- local_bh_enable();
- }
+ inet_hash(&tcp_hashinfo, sk);
}
void tcp_unhash(struct sock *sk)
{
- rwlock_t *lock;
-
- if (sk_unhashed(sk))
- goto ende;
-
- if (sk->sk_state == TCP_LISTEN) {
- local_bh_disable();
- inet_listen_wlock(&tcp_hashinfo);
- lock = &tcp_hashinfo.lhash_lock;
- } else {
- struct inet_ehash_bucket *head = &tcp_hashinfo.ehash[sk->sk_hashent];
- lock = &head->lock;
- write_lock_bh(&head->lock);
- }
-
- if (__sk_del_node_init(sk))
- sock_prot_dec_use(sk->sk_prot);
- write_unlock_bh(lock);
-
- ende:
- if (sk->sk_state == TCP_LISTEN)
- wake_up(&tcp_hashinfo.lhash_wait);
-}
-
-/* Don't inline this cruft. Here are some nice properties to
- * exploit here. The BSD API does not allow a listening TCP
- * to specify the remote port nor the remote address for the
- * connection. So always assume those are both wildcarded
- * during the search since they can never be otherwise.
- */
-static struct sock *__tcp_v4_lookup_listener(struct hlist_head *head,
- const u32 daddr,
- const unsigned short hnum,
- const int dif)
-{
- struct sock *result = NULL, *sk;
- struct hlist_node *node;
- int score, hiscore;
-
- hiscore=-1;
- sk_for_each(sk, node, head) {
- struct inet_sock *inet = inet_sk(sk);
-
- if (inet->num == hnum && !ipv6_only_sock(sk)) {
- __u32 rcv_saddr = inet->rcv_saddr;
-
- score = (sk->sk_family == PF_INET ? 1 : 0);
- if (rcv_saddr) {
- if (rcv_saddr != daddr)
- continue;
- score+=2;
- }
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- continue;
- score+=2;
- }
- if (score == 5)
- return sk;
- if (score > hiscore) {
- hiscore = score;
- result = sk;
- }
- }
- }
- return result;
-}
-
-/* Optimize the common listener case. */
-static inline struct sock *tcp_v4_lookup_listener(const u32 daddr,
- const unsigned short hnum,
- const int dif)
-{
- struct sock *sk = NULL;
- struct hlist_head *head;
-
- read_lock(&tcp_hashinfo.lhash_lock);
- head = &tcp_hashinfo.listening_hash[inet_lhashfn(hnum)];
- if (!hlist_empty(head)) {
- struct inet_sock *inet = inet_sk((sk = __sk_head(head)));
-
- if (inet->num == hnum && !sk->sk_node.next &&
- (!inet->rcv_saddr || inet->rcv_saddr == daddr) &&
- (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) &&
- !sk->sk_bound_dev_if)
- goto sherry_cache;
- sk = __tcp_v4_lookup_listener(head, daddr, hnum, dif);
- }
- if (sk) {
-sherry_cache:
- sock_hold(sk);
- }
- read_unlock(&tcp_hashinfo.lhash_lock);
- return sk;
-}
-
-/* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
- * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
- *
- * Local BH must be disabled here.
- */
-
-static inline struct sock *__tcp_v4_lookup_established(const u32 saddr,
- const u16 sport,
- const u32 daddr,
- const u16 hnum,
- const int dif)
-{
- struct inet_ehash_bucket *head;
- TCP_V4_ADDR_COOKIE(acookie, saddr, daddr)
- __u32 ports = TCP_COMBINED_PORTS(sport, hnum);
- struct sock *sk;
- struct hlist_node *node;
- /* Optimize here for direct hit, only listening connections can
- * have wildcards anyways.
- */
- const int hash = inet_ehashfn(daddr, hnum, saddr, sport, tcp_hashinfo.ehash_size);
- head = &tcp_hashinfo.ehash[hash];
- read_lock(&head->lock);
- sk_for_each(sk, node, &head->chain) {
- if (TCP_IPV4_MATCH(sk, acookie, saddr, daddr, ports, dif))
- goto hit; /* You sunk my battleship! */
- }
-
- /* Must check for a TIME_WAIT'er before going to listener hash. */
- sk_for_each(sk, node, &(head + tcp_hashinfo.ehash_size)->chain) {
- if (TCP_IPV4_TW_MATCH(sk, acookie, saddr, daddr, ports, dif))
- goto hit;
- }
- sk = NULL;
-out:
- read_unlock(&head->lock);
- return sk;
-hit:
- sock_hold(sk);
- goto out;
-}
-
-static inline struct sock *__tcp_v4_lookup(u32 saddr, u16 sport,
- u32 daddr, u16 hnum, int dif)
-{
- struct sock *sk = __tcp_v4_lookup_established(saddr, sport,
- daddr, hnum, dif);
-
- return sk ? : tcp_v4_lookup_listener(daddr, hnum, dif);
-}
-
-inline struct sock *tcp_v4_lookup(u32 saddr, u16 sport, u32 daddr,
- u16 dport, int dif)
-{
- struct sock *sk;
-
- local_bh_disable();
- sk = __tcp_v4_lookup(saddr, sport, daddr, ntohs(dport), dif);
- local_bh_enable();
-
- return sk;
+ inet_unhash(&tcp_hashinfo, sk);
}
-EXPORT_SYMBOL_GPL(tcp_v4_lookup);
-
static inline __u32 tcp_v4_init_sequence(struct sock *sk, struct sk_buff *skb)
{
return secure_tcp_sequence_number(skb->nh.iph->daddr,
skb->h.th->source);
}
-/* called with local bh disabled */
-static int __tcp_v4_check_established(struct sock *sk, __u16 lport,
- struct tcp_tw_bucket **twp)
+int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
- struct inet_sock *inet = inet_sk(sk);
- u32 daddr = inet->rcv_saddr;
- u32 saddr = inet->daddr;
- int dif = sk->sk_bound_dev_if;
- TCP_V4_ADDR_COOKIE(acookie, saddr, daddr)
- __u32 ports = TCP_COMBINED_PORTS(inet->dport, lport);
- const int hash = inet_ehashfn(daddr, lport, saddr, inet->dport, tcp_hashinfo.ehash_size);
- struct inet_ehash_bucket *head = &tcp_hashinfo.ehash[hash];
- struct sock *sk2;
- struct hlist_node *node;
- struct tcp_tw_bucket *tw;
-
- write_lock(&head->lock);
-
- /* Check TIME-WAIT sockets first. */
- sk_for_each(sk2, node, &(head + tcp_hashinfo.ehash_size)->chain) {
- tw = (struct tcp_tw_bucket *)sk2;
-
- if (TCP_IPV4_TW_MATCH(sk2, acookie, saddr, daddr, ports, dif)) {
- struct tcp_sock *tp = tcp_sk(sk);
-
- /* With PAWS, it is safe from the viewpoint
- of data integrity. Even without PAWS it
- is safe provided sequence spaces do not
- overlap i.e. at data rates <= 80Mbit/sec.
-
- Actually, the idea is close to VJ's one,
- only timestamp cache is held not per host,
- but per port pair and TW bucket is used
- as state holder.
+ const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
+ struct tcp_sock *tp = tcp_sk(sk);
- If TW bucket has been already destroyed we
- fall back to VJ's scheme and use initial
- timestamp retrieved from peer table.
- */
- if (tw->tw_ts_recent_stamp &&
- (!twp || (sysctl_tcp_tw_reuse &&
- xtime.tv_sec -
- tw->tw_ts_recent_stamp > 1))) {
- if ((tp->write_seq =
- tw->tw_snd_nxt + 65535 + 2) == 0)
- tp->write_seq = 1;
- tp->rx_opt.ts_recent = tw->tw_ts_recent;
- tp->rx_opt.ts_recent_stamp = tw->tw_ts_recent_stamp;
- sock_hold(sk2);
- goto unique;
- } else
- goto not_unique;
- }
- }
- tw = NULL;
+ /* With PAWS, it is safe from the viewpoint
+ of data integrity. Even without PAWS it is safe provided sequence
+ spaces do not overlap i.e. at data rates <= 80Mbit/sec.
- /* And established part... */
- sk_for_each(sk2, node, &head->chain) {
- if (TCP_IPV4_MATCH(sk2, acookie, saddr, daddr, ports, dif))
- goto not_unique;
- }
+ Actually, the idea is close to VJ's one, only timestamp cache is
+ held not per host, but per port pair and TW bucket is used as state
+ holder.
-unique:
- /* Must record num and sport now. Otherwise we will see
- * in hash table socket with a funny identity. */
- inet->num = lport;
- inet->sport = htons(lport);
- sk->sk_hashent = hash;
- BUG_TRAP(sk_unhashed(sk));
- __sk_add_node(sk, &head->chain);
- sock_prot_inc_use(sk->sk_prot);
- write_unlock(&head->lock);
-
- if (twp) {
- *twp = tw;
- NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
- } else if (tw) {
- /* Silly. Should hash-dance instead... */
- tcp_tw_deschedule(tw);
- NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
-
- tcp_tw_put(tw);
+ If TW bucket has been already destroyed we fall back to VJ's scheme
+ and use initial timestamp retrieved from peer table.
+ */
+ if (tcptw->tw_ts_recent_stamp &&
+ (twp == NULL || (sysctl_tcp_tw_reuse &&
+ xtime.tv_sec - tcptw->tw_ts_recent_stamp > 1))) {
+ tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
+ if (tp->write_seq == 0)
+ tp->write_seq = 1;
+ tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
+ tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+ sock_hold(sktw);
+ return 1;
}
return 0;
-
-not_unique:
- write_unlock(&head->lock);
- return -EADDRNOTAVAIL;
-}
-
-static inline u32 connect_port_offset(const struct sock *sk)
-{
- const struct inet_sock *inet = inet_sk(sk);
-
- return secure_tcp_port_ephemeral(inet->rcv_saddr, inet->daddr,
- inet->dport);
}
-/*
- * Bind a port for a connect operation and hash it.
- */
-static inline int tcp_v4_hash_connect(struct sock *sk)
-{
- const unsigned short snum = inet_sk(sk)->num;
- struct inet_bind_hashbucket *head;
- struct inet_bind_bucket *tb;
- int ret;
-
- if (!snum) {
- int low = sysctl_local_port_range[0];
- int high = sysctl_local_port_range[1];
- int range = high - low;
- int i;
- int port;
- static u32 hint;
- u32 offset = hint + connect_port_offset(sk);
- struct hlist_node *node;
- struct tcp_tw_bucket *tw = NULL;
-
- local_bh_disable();
- for (i = 1; i <= range; i++) {
- port = low + (i + offset) % range;
- head = &tcp_hashinfo.bhash[inet_bhashfn(port, tcp_hashinfo.bhash_size)];
- spin_lock(&head->lock);
-
- /* Does not bother with rcv_saddr checks,
- * because the established check is already
- * unique enough.
- */
- inet_bind_bucket_for_each(tb, node, &head->chain) {
- if (tb->port == port) {
- BUG_TRAP(!hlist_empty(&tb->owners));
- if (tb->fastreuse >= 0)
- goto next_port;
- if (!__tcp_v4_check_established(sk,
- port,
- &tw))
- goto ok;
- goto next_port;
- }
- }
-
- tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, port);
- if (!tb) {
- spin_unlock(&head->lock);
- break;
- }
- tb->fastreuse = -1;
- goto ok;
-
- next_port:
- spin_unlock(&head->lock);
- }
- local_bh_enable();
-
- return -EADDRNOTAVAIL;
-
-ok:
- hint += i;
-
- /* Head lock still held and bh's disabled */
- inet_bind_hash(sk, tb, port);
- if (sk_unhashed(sk)) {
- inet_sk(sk)->sport = htons(port);
- __inet_hash(&tcp_hashinfo, sk, 0);
- }
- spin_unlock(&head->lock);
-
- if (tw) {
- tcp_tw_deschedule(tw);
- tcp_tw_put(tw);
- }
-
- ret = 0;
- goto out;
- }
-
- head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)];
- tb = inet_sk(sk)->bind_hash;
- spin_lock_bh(&head->lock);
- if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- __inet_hash(&tcp_hashinfo, sk, 0);
- spin_unlock_bh(&head->lock);
- return 0;
- } else {
- spin_unlock(&head->lock);
- /* No definite answer... Walk to established hash table */
- ret = __tcp_v4_check_established(sk, snum, NULL);
-out:
- local_bh_enable();
- return ret;
- }
-}
+EXPORT_SYMBOL_GPL(tcp_twsk_unique);
/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
tp->write_seq = 0;
}
- if (sysctl_tcp_tw_recycle &&
+ if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
struct inet_peer *peer = rt_get_peer(rt);
inet->dport = usin->sin_port;
inet->daddr = daddr;
- tp->ext_header_len = 0;
+ inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt)
- tp->ext_header_len = inet->opt->optlen;
+ inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
tp->rx_opt.mss_clamp = 536;
* complete initialization after this.
*/
tcp_set_state(sk, TCP_SYN_SENT);
- err = tcp_v4_hash_connect(sk);
+ err = inet_hash_connect(&tcp_death_row, sk);
if (err)
goto failure;
- err = ip_route_newports(&rt, inet->sport, inet->dport, sk);
+ err = ip_route_newports(&rt, IPPROTO_TCP, inet->sport, inet->dport, sk);
if (err)
goto failure;
/* OK, now commit destination to socket. */
+ sk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(sk, &rt->u.dst);
if (!tp->write_seq)
return err;
}
-static __inline__ int tcp_v4_iif(struct sk_buff *skb)
-{
- return ((struct rtable *)skb->dst)->rt_iif;
-}
-
-static __inline__ u32 tcp_v4_synq_hash(u32 raddr, u16 rport, u32 rnd)
-{
- return (jhash_2words(raddr, (u32) rport, rnd) & (TCP_SYNQ_HSIZE - 1));
-}
-
-static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp,
- struct request_sock ***prevp,
- __u16 rport,
- __u32 raddr, __u32 laddr)
-{
- struct listen_sock *lopt = tp->accept_queue.listen_opt;
- struct request_sock *req, **prev;
-
- for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)];
- (req = *prev) != NULL;
- prev = &req->dl_next) {
- const struct inet_request_sock *ireq = inet_rsk(req);
-
- if (ireq->rmt_port == rport &&
- ireq->rmt_addr == raddr &&
- ireq->loc_addr == laddr &&
- TCP_INET_FAMILY(req->rsk_ops->family)) {
- BUG_TRAP(!req->sk);
- *prevp = prev;
- break;
- }
- }
-
- return req;
-}
-
-static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct listen_sock *lopt = tp->accept_queue.listen_opt;
- u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd);
-
- reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT);
- tcp_synq_added(sk);
-}
-
-
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
-static inline void do_pmtu_discovery(struct sock *sk, struct iphdr *iph,
- u32 mtu)
+static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
- struct tcp_sock *tp = tcp_sk(sk);
/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
* send out by Linux are always <576bytes so they should go through
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
- tp->pmtu_cookie > mtu) {
+ inet_csk(sk)->icsk_pmtu_cookie > mtu) {
tcp_sync_mss(sk, mtu);
/* Resend the TCP packet because it's
return;
}
- sk = tcp_v4_lookup(iph->daddr, th->dest, iph->saddr,
- th->source, tcp_v4_iif(skb));
+ sk = inet_lookup(&tcp_hashinfo, iph->daddr, th->dest, iph->saddr,
+ th->source, inet_iif(skb));
if (!sk) {
ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
- tcp_tw_put((struct tcp_tw_bucket *)sk);
+ inet_twsk_put((struct inet_timewait_sock *)sk);
return;
}
if (sock_owned_by_user(sk))
goto out;
- req = tcp_v4_search_req(tp, &prev, th->dest,
- iph->daddr, iph->saddr);
+ req = inet_csk_search_req(sk, &prev, th->dest,
+ iph->daddr, iph->saddr);
if (!req)
goto out;
* created socket, and POSIX does not want network
* errors returned from accept().
*/
- tcp_synq_drop(sk, req, prev);
+ inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
It can f.e. if SYNs crossed.
*/
if (!sock_owned_by_user(sk)) {
- TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
sk->sk_error_report(sk);
}
/* This routine computes an IPv4 TCP checksum. */
-void tcp_v4_send_check(struct sock *sk, struct tcphdr *th, int len,
- struct sk_buff *skb)
+void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
{
struct inet_sock *inet = inet_sk(sk);
+ struct tcphdr *th = skb->h.th;
- if (skb->ip_summed == CHECKSUM_HW) {
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
th->check = ~tcp_v4_check(th, len, inet->saddr, inet->daddr, 0);
skb->csum = offsetof(struct tcphdr, check);
} else {
}
}
+int tcp_v4_gso_send_check(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ struct tcphdr *th;
+
+ if (!pskb_may_pull(skb, sizeof(*th)))
+ return -EINVAL;
+
+ iph = skb->nh.iph;
+ th = skb->h.th;
+
+ th->check = 0;
+ th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0);
+ skb->csum = offsetof(struct tcphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ return 0;
+}
+
/*
* This routine will send an RST to the other tcp.
*
static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
- struct tcp_tw_bucket *tw = (struct tcp_tw_bucket *)sk;
+ struct inet_timewait_sock *tw = inet_twsk(sk);
+ const struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(skb, tw->tw_snd_nxt, tw->tw_rcv_nxt,
- tw->tw_rcv_wnd >> tw->tw_rcv_wscale, tw->tw_ts_recent);
+ tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcptw->tw_ts_recent);
- tcp_tw_put(tw);
+ inet_twsk_put(tw);
}
static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
req->ts_recent);
}
-static struct dst_entry* tcp_v4_route_req(struct sock *sk,
- struct request_sock *req)
-{
- struct rtable *rt;
- const struct inet_request_sock *ireq = inet_rsk(req);
- struct ip_options *opt = inet_rsk(req)->opt;
- struct flowi fl = { .oif = sk->sk_bound_dev_if,
- .nl_u = { .ip4_u =
- { .daddr = ((opt && opt->srr) ?
- opt->faddr :
- ireq->rmt_addr),
- .saddr = ireq->loc_addr,
- .tos = RT_CONN_FLAGS(sk) } },
- .proto = IPPROTO_TCP,
- .uli_u = { .ports =
- { .sport = inet_sk(sk)->sport,
- .dport = ireq->rmt_port } } };
-
- if (ip_route_output_flow(&rt, &fl, sk, 0)) {
- IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
- return NULL;
- }
- if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) {
- ip_rt_put(rt);
- IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
- return NULL;
- }
- return &rt->u.dst;
-}
-
/*
* Send a SYN-ACK after having received an ACK.
* This still operates on a request_sock only, not on a big
struct sk_buff * skb;
/* First, grab a route. */
- if (!dst && (dst = tcp_v4_route_req(sk, req)) == NULL)
+ if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
goto out;
skb = tcp_make_synack(sk, dst, req);
*/
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
- if (inet_rsk(req)->opt)
- kfree(inet_rsk(req)->opt);
+ kfree(inet_rsk(req)->opt);
}
-static inline void syn_flood_warning(struct sk_buff *skb)
+#ifdef CONFIG_SYN_COOKIES
+static void syn_flood_warning(struct sk_buff *skb)
{
static unsigned long warntime;
ntohs(skb->h.th->dest));
}
}
+#endif
/*
* Save and compile IPv4 options into the request_sock if needed.
*/
-static inline struct ip_options *tcp_v4_save_options(struct sock *sk,
- struct sk_buff *skb)
+static struct ip_options *tcp_v4_save_options(struct sock *sk,
+ struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
struct ip_options *dopt = NULL;
.send_reset = tcp_v4_send_reset,
};
+static struct timewait_sock_ops tcp_timewait_sock_ops = {
+ .twsk_obj_size = sizeof(struct tcp_timewait_sock),
+ .twsk_unique = tcp_twsk_unique,
+};
+
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct inet_request_sock *ireq;
* limitations, they conserve resources and peer is
* evidently real one.
*/
- if (tcp_synq_is_full(sk) && !isn) {
+ if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
#ifdef CONFIG_SYN_COOKIES
if (sysctl_tcp_syncookies) {
want_cookie = 1;
* clogging syn queue with openreqs with exponentially increasing
* timeout.
*/
- if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1)
+ if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
goto drop;
req = reqsk_alloc(&tcp_request_sock_ops);
tcp_openreq_init(req, &tmp_opt, skb);
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
ireq = inet_rsk(req);
ireq->loc_addr = daddr;
ireq->rmt_addr = saddr;
* are made in the function processing timewait state.
*/
if (tmp_opt.saw_tstamp &&
- sysctl_tcp_tw_recycle &&
- (dst = tcp_v4_route_req(sk, req)) != NULL &&
+ tcp_death_row.sysctl_tw_recycle &&
+ (dst = inet_csk_route_req(sk, req)) != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
if (xtime.tv_sec < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
}
/* Kill the following clause, if you dislike this way. */
else if (!sysctl_tcp_syncookies &&
- (sysctl_max_syn_backlog - tcp_synq_len(sk) <
+ (sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(sysctl_max_syn_backlog >> 2)) &&
(!peer || !peer->tcp_ts_stamp) &&
(!dst || !dst_metric(dst, RTAX_RTT))) {
* to destinations, already remembered
* to the moment of synflood.
*/
- LIMIT_NETDEBUG(printk(KERN_DEBUG "TCP: drop open "
- "request from %u.%u."
- "%u.%u/%u\n",
- NIPQUAD(saddr),
- ntohs(skb->h.th->source)));
+ LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open "
+ "request from %u.%u.%u.%u/%u\n",
+ NIPQUAD(saddr),
+ ntohs(skb->h.th->source));
dst_release(dst);
goto drop_and_free;
}
if (want_cookie) {
reqsk_free(req);
} else {
- tcp_v4_synq_add(sk, req);
+ inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
}
return 0;
drop_and_free:
reqsk_free(req);
drop:
- TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
return 0;
}
if (sk_acceptq_is_full(sk))
goto exit_overflow;
- if (!dst && (dst = tcp_v4_route_req(sk, req)) == NULL)
+ if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
goto exit;
newsk = tcp_create_openreq_child(sk, req, skb);
if (!newsk)
goto exit;
+ newsk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(newsk, dst);
newtp = tcp_sk(newsk);
newinet->saddr = ireq->loc_addr;
newinet->opt = ireq->opt;
ireq->opt = NULL;
- newinet->mc_index = tcp_v4_iif(skb);
+ newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = skb->nh.iph->ttl;
- newtp->ext_header_len = 0;
+ inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newinet->opt)
- newtp->ext_header_len = newinet->opt->optlen;
+ inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
newinet->id = newtp->write_seq ^ jiffies;
+ tcp_mtup_init(newsk);
tcp_sync_mss(newsk, dst_mtu(dst));
newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
tcp_initialize_rcv_mss(newsk);
{
struct tcphdr *th = skb->h.th;
struct iphdr *iph = skb->nh.iph;
- struct tcp_sock *tp = tcp_sk(sk);
struct sock *nsk;
struct request_sock **prev;
/* Find possible connection requests. */
- struct request_sock *req = tcp_v4_search_req(tp, &prev, th->source,
- iph->saddr, iph->daddr);
+ struct request_sock *req = inet_csk_search_req(sk, &prev, th->source,
+ iph->saddr, iph->daddr);
if (req)
return tcp_check_req(sk, skb, req, prev);
- nsk = __tcp_v4_lookup_established(skb->nh.iph->saddr,
- th->source,
- skb->nh.iph->daddr,
- ntohs(th->dest),
- tcp_v4_iif(skb));
+ nsk = inet_lookup_established(&tcp_hashinfo, skb->nh.iph->saddr,
+ th->source, skb->nh.iph->daddr,
+ th->dest, inet_iif(skb));
if (nsk) {
if (nsk->sk_state != TCP_TIME_WAIT) {
bh_lock_sock(nsk);
return nsk;
}
- tcp_tw_put((struct tcp_tw_bucket *)nsk);
+ inet_twsk_put((struct inet_timewait_sock *)nsk);
return NULL;
}
static int tcp_v4_checksum_init(struct sk_buff *skb)
{
- if (skb->ip_summed == CHECKSUM_HW) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
if (!tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr,
- skb->nh.iph->daddr, skb->csum))
+ skb->nh.iph->daddr, skb->csum)) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
return 0;
-
- LIMIT_NETDEBUG(printk(KERN_DEBUG "hw tcp v4 csum failed\n"));
- skb->ip_summed = CHECKSUM_NONE;
+ }
}
+
+ skb->csum = csum_tcpudp_nofold(skb->nh.iph->saddr, skb->nh.iph->daddr,
+ skb->len, IPPROTO_TCP, 0);
+
if (skb->len <= 76) {
- if (tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr,
- skb->nh.iph->daddr,
- skb_checksum(skb, 0, skb->len, 0)))
- return -1;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- } else {
- skb->csum = ~tcp_v4_check(skb->h.th, skb->len,
- skb->nh.iph->saddr,
- skb->nh.iph->daddr, 0);
+ return __skb_checksum_complete(skb);
}
return 0;
}
/* An explanation is required here, I think.
* Packet length and doff are validated by header prediction,
- * provided case of th->doff==0 is elimineted.
+ * provided case of th->doff==0 is eliminated.
* So, we defer the checks. */
if ((skb->ip_summed != CHECKSUM_UNNECESSARY &&
- tcp_v4_checksum_init(skb) < 0))
+ tcp_v4_checksum_init(skb)))
goto bad_packet;
th = skb->h.th;
TCP_SKB_CB(skb)->flags = skb->nh.iph->tos;
TCP_SKB_CB(skb)->sacked = 0;
- sk = __tcp_v4_lookup(skb->nh.iph->saddr, th->source,
- skb->nh.iph->daddr, ntohs(th->dest),
- tcp_v4_iif(skb));
+ sk = __inet_lookup(&tcp_hashinfo, skb->nh.iph->saddr, th->source,
+ skb->nh.iph->daddr, th->dest,
+ inet_iif(skb));
if (!sk)
goto no_tcp_socket;
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
+ nf_reset(skb);
if (sk_filter(sk, skb, 0))
goto discard_and_relse;
skb->dev = NULL;
- bh_lock_sock(sk);
+ bh_lock_sock_nested(sk);
ret = 0;
if (!sock_owned_by_user(sk)) {
- if (!tcp_prequeue(sk, skb))
+#ifdef CONFIG_NET_DMA
+ struct tcp_sock *tp = tcp_sk(sk);
+ if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
+ tp->ucopy.dma_chan = get_softnet_dma();
+ if (tp->ucopy.dma_chan)
+ ret = tcp_v4_do_rcv(sk, skb);
+ else
+#endif
+ {
+ if (!tcp_prequeue(sk, skb))
ret = tcp_v4_do_rcv(sk, skb);
+ }
} else
sk_add_backlog(sk, skb);
bh_unlock_sock(sk);
do_time_wait:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- tcp_tw_put((struct tcp_tw_bucket *) sk);
+ inet_twsk_put((struct inet_timewait_sock *) sk);
goto discard_it;
}
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
TCP_INC_STATS_BH(TCP_MIB_INERRS);
- tcp_tw_put((struct tcp_tw_bucket *) sk);
+ inet_twsk_put((struct inet_timewait_sock *) sk);
goto discard_it;
}
- switch (tcp_timewait_state_process((struct tcp_tw_bucket *)sk,
- skb, th, skb->len)) {
+ switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk,
+ skb, th)) {
case TCP_TW_SYN: {
- struct sock *sk2 = tcp_v4_lookup_listener(skb->nh.iph->daddr,
- ntohs(th->dest),
- tcp_v4_iif(skb));
+ struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo,
+ skb->nh.iph->daddr,
+ th->dest,
+ inet_iif(skb));
if (sk2) {
- tcp_tw_deschedule((struct tcp_tw_bucket *)sk);
- tcp_tw_put((struct tcp_tw_bucket *)sk);
+ inet_twsk_deschedule((struct inet_timewait_sock *)sk,
+ &tcp_death_row);
+ inet_twsk_put((struct inet_timewait_sock *)sk);
sk = sk2;
goto process;
}
goto discard_it;
}
-static void v4_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
-{
- struct sockaddr_in *sin = (struct sockaddr_in *) uaddr;
- struct inet_sock *inet = inet_sk(sk);
-
- sin->sin_family = AF_INET;
- sin->sin_addr.s_addr = inet->daddr;
- sin->sin_port = inet->dport;
-}
-
/* VJ's idea. Save last timestamp seen from this destination
* and hold it at least for normal timewait interval to use for duplicate
* segment detection in subsequent connections, before they enter synchronized
return 0;
}
-int tcp_v4_tw_remember_stamp(struct tcp_tw_bucket *tw)
+int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw)
{
- struct inet_peer *peer = NULL;
-
- peer = inet_getpeer(tw->tw_daddr, 1);
+ struct inet_peer *peer = inet_getpeer(tw->tw_daddr, 1);
if (peer) {
- if ((s32)(peer->tcp_ts - tw->tw_ts_recent) <= 0 ||
+ const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+
+ if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
(peer->tcp_ts_stamp + TCP_PAWS_MSL < xtime.tv_sec &&
- peer->tcp_ts_stamp <= tw->tw_ts_recent_stamp)) {
- peer->tcp_ts_stamp = tw->tw_ts_recent_stamp;
- peer->tcp_ts = tw->tw_ts_recent;
+ peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) {
+ peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp;
+ peer->tcp_ts = tcptw->tw_ts_recent;
}
inet_putpeer(peer);
return 1;
return 0;
}
-struct tcp_func ipv4_specific = {
- .queue_xmit = ip_queue_xmit,
- .send_check = tcp_v4_send_check,
- .rebuild_header = inet_sk_rebuild_header,
- .conn_request = tcp_v4_conn_request,
- .syn_recv_sock = tcp_v4_syn_recv_sock,
- .remember_stamp = tcp_v4_remember_stamp,
- .net_header_len = sizeof(struct iphdr),
- .setsockopt = ip_setsockopt,
- .getsockopt = ip_getsockopt,
- .addr2sockaddr = v4_addr2sockaddr,
- .sockaddr_len = sizeof(struct sockaddr_in),
+struct inet_connection_sock_af_ops ipv4_specific = {
+ .queue_xmit = ip_queue_xmit,
+ .send_check = tcp_v4_send_check,
+ .rebuild_header = inet_sk_rebuild_header,
+ .conn_request = tcp_v4_conn_request,
+ .syn_recv_sock = tcp_v4_syn_recv_sock,
+ .remember_stamp = tcp_v4_remember_stamp,
+ .net_header_len = sizeof(struct iphdr),
+ .setsockopt = ip_setsockopt,
+ .getsockopt = ip_getsockopt,
+ .addr2sockaddr = inet_csk_addr2sockaddr,
+ .sockaddr_len = sizeof(struct sockaddr_in),
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_ip_setsockopt,
+ .compat_getsockopt = compat_ip_getsockopt,
+#endif
};
/* NOTE: A lot of things set to zero explicitly by call to
*/
static int tcp_v4_init_sock(struct sock *sk)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
skb_queue_head_init(&tp->out_of_order_queue);
tcp_init_xmit_timers(sk);
tcp_prequeue_init(tp);
- tp->rto = TCP_TIMEOUT_INIT;
+ icsk->icsk_rto = TCP_TIMEOUT_INIT;
tp->mdev = TCP_TIMEOUT_INIT;
/* So many TCP implementations out there (incorrectly) count the
tp->mss_cache = 536;
tp->reordering = sysctl_tcp_reordering;
- tp->ca_ops = &tcp_init_congestion_ops;
+ icsk->icsk_ca_ops = &tcp_init_congestion_ops;
sk->sk_state = TCP_CLOSE;
sk->sk_write_space = sk_stream_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
- tp->af_specific = &ipv4_specific;
+ icsk->icsk_af_ops = &ipv4_specific;
+ icsk->icsk_sync_mss = tcp_sync_mss;
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
tcp_clear_xmit_timers(sk);
- tcp_cleanup_congestion_control(tp);
+ tcp_cleanup_congestion_control(sk);
/* Cleanup up the write buffer. */
sk_stream_writequeue_purge(sk);
/* Cleans up our, hopefully empty, out_of_order_queue. */
__skb_queue_purge(&tp->out_of_order_queue);
+#ifdef CONFIG_NET_DMA
+ /* Cleans up our sk_async_wait_queue */
+ __skb_queue_purge(&sk->sk_async_wait_queue);
+#endif
+
/* Clean prequeue, it must be empty really */
__skb_queue_purge(&tp->ucopy.prequeue);
/* Clean up a referenced TCP bind bucket. */
- if (inet_sk(sk)->bind_hash)
+ if (inet_csk(sk)->icsk_bind_hash)
inet_put_port(&tcp_hashinfo, sk);
/*
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */
-static inline struct tcp_tw_bucket *tw_head(struct hlist_head *head)
+static inline struct inet_timewait_sock *tw_head(struct hlist_head *head)
{
return hlist_empty(head) ? NULL :
- list_entry(head->first, struct tcp_tw_bucket, tw_node);
+ list_entry(head->first, struct inet_timewait_sock, tw_node);
}
-static inline struct tcp_tw_bucket *tw_next(struct tcp_tw_bucket *tw)
+static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
{
return tw->tw_node.next ?
hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
static void *listening_get_next(struct seq_file *seq, void *cur)
{
- struct tcp_sock *tp;
+ struct inet_connection_sock *icsk;
struct hlist_node *node;
struct sock *sk = cur;
struct tcp_iter_state* st = seq->private;
if (st->state == TCP_SEQ_STATE_OPENREQ) {
struct request_sock *req = cur;
- tp = tcp_sk(st->syn_wait_sk);
+ icsk = inet_csk(st->syn_wait_sk);
req = req->dl_next;
while (1) {
while (req) {
if (++st->sbucket >= TCP_SYNQ_HSIZE)
break;
get_req:
- req = tp->accept_queue.listen_opt->syn_table[st->sbucket];
+ req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
}
sk = sk_next(st->syn_wait_sk);
st->state = TCP_SEQ_STATE_LISTENING;
- read_unlock_bh(&tp->accept_queue.syn_wait_lock);
+ read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
} else {
- tp = tcp_sk(sk);
- read_lock_bh(&tp->accept_queue.syn_wait_lock);
- if (reqsk_queue_len(&tp->accept_queue))
+ icsk = inet_csk(sk);
+ read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+ if (reqsk_queue_len(&icsk->icsk_accept_queue))
goto start_req;
- read_unlock_bh(&tp->accept_queue.syn_wait_lock);
+ read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
sk = sk_next(sk);
}
get_sk:
cur = sk;
goto out;
}
- tp = tcp_sk(sk);
- read_lock_bh(&tp->accept_queue.syn_wait_lock);
- if (reqsk_queue_len(&tp->accept_queue)) {
+ icsk = inet_csk(sk);
+ read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
+ if (reqsk_queue_len(&icsk->icsk_accept_queue)) {
start_req:
st->uid = sock_i_uid(sk);
st->syn_wait_sk = sk;
st->sbucket = 0;
goto get_req;
}
- read_unlock_bh(&tp->accept_queue.syn_wait_lock);
+ read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
}
if (++st->bucket < INET_LHTABLE_SIZE) {
sk = sk_head(&tcp_hashinfo.listening_hash[st->bucket]);
for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) {
struct sock *sk;
struct hlist_node *node;
- struct tcp_tw_bucket *tw;
+ struct inet_timewait_sock *tw;
/* We can reschedule _before_ having picked the target: */
cond_resched_softirq();
goto out;
}
st->state = TCP_SEQ_STATE_TIME_WAIT;
- tw_for_each(tw, node,
- &tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain) {
+ inet_twsk_for_each(tw, node,
+ &tcp_hashinfo.ehash[st->bucket + tcp_hashinfo.ehash_size].chain) {
if (tw->tw_family != st->family) {
continue;
}
static void *established_get_next(struct seq_file *seq, void *cur)
{
struct sock *sk = cur;
- struct tcp_tw_bucket *tw;
+ struct inet_timewait_sock *tw;
struct hlist_node *node;
struct tcp_iter_state* st = seq->private;
switch (st->state) {
case TCP_SEQ_STATE_OPENREQ:
if (v) {
- struct tcp_sock *tp = tcp_sk(st->syn_wait_sk);
- read_unlock_bh(&tp->accept_queue.syn_wait_lock);
+ struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk);
+ read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
}
case TCP_SEQ_STATE_LISTENING:
if (v != SEQ_START_TOKEN)
if (unlikely(afinfo == NULL))
return -EINVAL;
- s = kmalloc(sizeof(*s), GFP_KERNEL);
+ s = kzalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
- memset(s, 0, sizeof(*s));
s->family = afinfo->family;
s->seq_ops.start = tcp_seq_start;
s->seq_ops.next = tcp_seq_next;
int timer_active;
unsigned long timer_expires;
struct tcp_sock *tp = tcp_sk(sp);
+ const struct inet_connection_sock *icsk = inet_csk(sp);
struct inet_sock *inet = inet_sk(sp);
unsigned int dest = inet->daddr;
unsigned int src = inet->rcv_saddr;
__u16 destp = ntohs(inet->dport);
__u16 srcp = ntohs(inet->sport);
- if (tp->pending == TCP_TIME_RETRANS) {
+ if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
timer_active = 1;
- timer_expires = tp->timeout;
- } else if (tp->pending == TCP_TIME_PROBE0) {
+ timer_expires = icsk->icsk_timeout;
+ } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
- timer_expires = tp->timeout;
+ timer_expires = icsk->icsk_timeout;
} else if (timer_pending(&sp->sk_timer)) {
timer_active = 2;
timer_expires = sp->sk_timer.expires;
sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
"%08X %5d %8d %lu %d %p %u %u %u %u %d",
i, src, srcp, dest, destp, sp->sk_state,
- tp->write_seq - tp->snd_una, tp->rcv_nxt - tp->copied_seq,
+ tp->write_seq - tp->snd_una,
+ (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq),
timer_active,
jiffies_to_clock_t(timer_expires - jiffies),
- tp->retransmits,
+ icsk->icsk_retransmits,
sock_i_uid(sp),
- tp->probes_out,
+ icsk->icsk_probes_out,
sock_i_ino(sp),
atomic_read(&sp->sk_refcnt), sp,
- tp->rto, tp->ack.ato, (tp->ack.quick << 1) | tp->ack.pingpong,
+ icsk->icsk_rto,
+ icsk->icsk_ack.ato,
+ (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
tp->snd_cwnd,
tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh);
}
-static void get_timewait4_sock(struct tcp_tw_bucket *tw, char *tmpbuf, int i)
+static void get_timewait4_sock(struct inet_timewait_sock *tw, char *tmpbuf, int i)
{
unsigned int dest, src;
__u16 destp, srcp;
.close = tcp_close,
.connect = tcp_v4_connect,
.disconnect = tcp_disconnect,
- .accept = tcp_accept,
+ .accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v4_init_sock,
.destroy = tcp_v4_destroy_sock,
.get_port = tcp_v4_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.sockets_allocated = &tcp_sockets_allocated,
+ .orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
.sysctl_mem = sysctl_tcp_mem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
+ .twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_tcp_setsockopt,
+ .compat_getsockopt = compat_tcp_getsockopt,
+#endif
};
-
-
void __init tcp_v4_init(struct net_proto_family *ops)
{
- int err = sock_create_kern(PF_INET, SOCK_RAW, IPPROTO_TCP, &tcp_socket);
- if (err < 0)
+ if (inet_csk_ctl_sock_create(&tcp_socket, PF_INET, SOCK_RAW, IPPROTO_TCP) < 0)
panic("Failed to create the TCP control socket.\n");
- tcp_socket->sk->sk_allocation = GFP_ATOMIC;
- inet_sk(tcp_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.
- */
- tcp_socket->sk->sk_prot->unhash(tcp_socket->sk);
}
EXPORT_SYMBOL(ipv4_specific);
-EXPORT_SYMBOL(inet_bind_bucket_create);
EXPORT_SYMBOL(tcp_hashinfo);
EXPORT_SYMBOL(tcp_prot);
EXPORT_SYMBOL(tcp_unhash);
#endif
EXPORT_SYMBOL(sysctl_local_port_range);
EXPORT_SYMBOL(sysctl_tcp_low_latency);
-EXPORT_SYMBOL(sysctl_tcp_tw_reuse);