#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
+#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
+#include <net/tcp_states.h>
+
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
#include <linux/ipv6.h>
#endif
#include <linux/seq_file.h>
-/* This is for all connections with a full identity, no wildcards.
- * New scheme, half the table is for TIME_WAIT, the other half is
- * for the rest. I'll experiment with dynamic table growth later.
- */
-struct tcp_ehash_bucket {
- rwlock_t lock;
- struct hlist_head chain;
-} __attribute__((__aligned__(8)));
-
-/* This is for listening sockets, thus all sockets which possess wildcards. */
-#define TCP_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */
-
-/* There are a few simple rules, which allow for local port reuse by
- * an application. In essence:
- *
- * 1) Sockets bound to different interfaces may share a local port.
- * Failing that, goto test 2.
- * 2) If all sockets have sk->sk_reuse set, and none of them are in
- * TCP_LISTEN state, the port may be shared.
- * Failing that, goto test 3.
- * 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
- * address, and none of them are the same, the port may be
- * shared.
- * Failing this, the port cannot be shared.
- *
- * The interesting point, is test #2. This is what an FTP server does
- * all day. To optimize this case we use a specific flag bit defined
- * below. As we add sockets to a bind bucket list, we perform a
- * check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
- * As long as all sockets added to a bind bucket pass this test,
- * the flag bit will be set.
- * The resulting situation is that tcp_v[46]_verify_bind() can just check
- * for this flag bit, if it is set and the socket trying to bind has
- * sk->sk_reuse set, we don't even have to walk the owners list at all,
- * we return that it is ok to bind this socket to the requested local port.
- *
- * Sounds like a lot of work, but it is worth it. In a more naive
- * implementation (ie. current FreeBSD etc.) the entire list of ports
- * must be walked for each data port opened by an ftp server. Needless
- * to say, this does not scale at all. With a couple thousand FTP
- * users logged onto your box, isn't it nice to know that new data
- * ports are created in O(1) time? I thought so. ;-) -DaveM
- */
-struct tcp_bind_bucket {
- unsigned short port;
- signed short fastreuse;
- struct hlist_node node;
- struct hlist_head owners;
-};
-
-#define tb_for_each(tb, node, head) hlist_for_each_entry(tb, node, head, node)
-
-struct tcp_bind_hashbucket {
- spinlock_t lock;
- struct hlist_head chain;
-};
-
-static inline struct tcp_bind_bucket *__tb_head(struct tcp_bind_hashbucket *head)
-{
- return hlist_entry(head->chain.first, struct tcp_bind_bucket, node);
-}
-
-static inline struct tcp_bind_bucket *tb_head(struct tcp_bind_hashbucket *head)
-{
- return hlist_empty(&head->chain) ? NULL : __tb_head(head);
-}
-
-extern struct tcp_hashinfo {
- /* This is for sockets with full identity only. Sockets here will
- * always be without wildcards and will have the following invariant:
- *
- * TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
- *
- * First half of the table is for sockets not in TIME_WAIT, second half
- * is for TIME_WAIT sockets only.
- */
- struct tcp_ehash_bucket *__tcp_ehash;
-
- /* Ok, let's try this, I give up, we do need a local binding
- * TCP hash as well as the others for fast bind/connect.
- */
- struct tcp_bind_hashbucket *__tcp_bhash;
-
- int __tcp_bhash_size;
- int __tcp_ehash_size;
-
- /* All sockets in TCP_LISTEN state will be in here. This is the only
- * table where wildcard'd TCP sockets can exist. Hash function here
- * is just local port number.
- */
- struct hlist_head __tcp_listening_hash[TCP_LHTABLE_SIZE];
-
- /* All the above members are written once at bootup and
- * never written again _or_ are predominantly read-access.
- *
- * Now align to a new cache line as all the following members
- * are often dirty.
- */
- rwlock_t __tcp_lhash_lock ____cacheline_aligned;
- atomic_t __tcp_lhash_users;
- wait_queue_head_t __tcp_lhash_wait;
- spinlock_t __tcp_portalloc_lock;
-} tcp_hashinfo;
-
-#define tcp_ehash (tcp_hashinfo.__tcp_ehash)
-#define tcp_bhash (tcp_hashinfo.__tcp_bhash)
-#define tcp_ehash_size (tcp_hashinfo.__tcp_ehash_size)
-#define tcp_bhash_size (tcp_hashinfo.__tcp_bhash_size)
-#define tcp_listening_hash (tcp_hashinfo.__tcp_listening_hash)
-#define tcp_lhash_lock (tcp_hashinfo.__tcp_lhash_lock)
-#define tcp_lhash_users (tcp_hashinfo.__tcp_lhash_users)
-#define tcp_lhash_wait (tcp_hashinfo.__tcp_lhash_wait)
-#define tcp_portalloc_lock (tcp_hashinfo.__tcp_portalloc_lock)
-
-extern kmem_cache_t *tcp_bucket_cachep;
-extern struct tcp_bind_bucket *tcp_bucket_create(struct tcp_bind_hashbucket *head,
- unsigned short snum);
-extern void tcp_bucket_destroy(struct tcp_bind_bucket *tb);
-extern void tcp_bucket_unlock(struct sock *sk);
-extern int tcp_port_rover;
-
-/* These are AF independent. */
-static __inline__ int tcp_bhashfn(__u16 lport)
-{
- return (lport & (tcp_bhash_size - 1));
-}
-
-extern void tcp_bind_hash(struct sock *sk, struct tcp_bind_bucket *tb,
- unsigned short snum);
+extern struct inet_hashinfo tcp_hashinfo;
#if (BITS_PER_LONG == 64)
#define TCP_ADDRCMP_ALIGN_BYTES 8
__u32 tw_ts_recent;
long tw_ts_recent_stamp;
unsigned long tw_ttd;
- struct tcp_bind_bucket *tw_tb;
+ struct inet_bind_bucket *tw_tb;
struct hlist_node tw_death_node;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
struct in6_addr tw_v6_daddr;
static inline void tcp_tw_put(struct tcp_tw_bucket *tw)
{
if (atomic_dec_and_test(&tw->tw_refcnt)) {
-#ifdef INET_REFCNT_DEBUG
+#ifdef SOCK_REFCNT_DEBUG
printk(KERN_DEBUG "tw_bucket %p released\n", tw);
#endif
kmem_cache_free(tcp_timewait_cachep, tw);
ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
-/* These can have wildcards, don't try too hard. */
-static __inline__ int tcp_lhashfn(unsigned short num)
-{
- return num & (TCP_LHTABLE_SIZE - 1);
-}
-
-static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
-{
- return tcp_lhashfn(inet_sk(sk)->num);
-}
-
#define MAX_TCP_HEADER (128 + MAX_HEADER)
/*
#define TCP_ADD_STATS_BH(field, val) SNMP_ADD_STATS_BH(tcp_statistics, field, val)
#define TCP_ADD_STATS_USER(field, val) SNMP_ADD_STATS_USER(tcp_statistics, field, val)
-extern void tcp_put_port(struct sock *sk);
-extern void tcp_inherit_port(struct sock *sk, struct sock *child);
-
extern void tcp_v4_err(struct sk_buff *skb, u32);
extern void tcp_shutdown (struct sock *sk, int how);
* TCP v4 functions exported for the inet6 API
*/
-extern int tcp_v4_rebuild_header(struct sock *sk);
-
-extern int tcp_v4_build_header(struct sock *sk,
- struct sk_buff *skb);
-
extern void tcp_v4_send_check(struct sock *sk,
struct tcphdr *th, int len,
struct sk_buff *skb);
/* tcp_output.c */
-extern int tcp_write_xmit(struct sock *, int nonagle);
+extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
+ unsigned int cur_mss, int nonagle);
+extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp);
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
extern void tcp_xmit_retransmit_queue(struct sock *);
extern void tcp_simple_retransmit(struct sock *);
extern void tcp_send_partial(struct sock *);
extern int tcp_write_wakeup(struct sock *);
extern void tcp_send_fin(struct sock *sk);
-extern void tcp_send_active_reset(struct sock *sk, int priority);
+extern void tcp_send_active_reset(struct sock *sk,
+ unsigned int __nocast priority);
extern int tcp_send_synack(struct sock *);
-extern void tcp_push_one(struct sock *, unsigned mss_now);
+extern void tcp_push_one(struct sock *, unsigned int mss_now);
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);
+/* tcp_input.c */
+extern void tcp_cwnd_application_limited(struct sock *sk);
+
/* tcp_timer.c */
extern void tcp_init_xmit_timers(struct sock *);
extern void tcp_clear_xmit_timers(struct sock *);
static inline void tcp_initialize_rcv_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
- unsigned int hint = min(tp->advmss, tp->mss_cache_std);
+ unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
hint = min(hint, tp->rcv_wnd/2);
hint = min(hint, TCP_MIN_RCVMSS);
static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp)
{
- if (skb_queue_len(&tp->out_of_order_queue) == 0 &&
+ if (skb_queue_empty(&tp->out_of_order_queue) &&
tp->rcv_wnd &&
atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
!tp->urg_data)
tp->left_out = tp->sacked_out + tp->lost_out;
}
-extern void tcp_cwnd_application_limited(struct sock *sk);
-
-/* Congestion window validation. (RFC2861) */
-
-static inline void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
-{
- __u32 packets_out = tp->packets_out;
-
- if (packets_out >= tp->snd_cwnd) {
- /* Network is feed fully. */
- tp->snd_cwnd_used = 0;
- tp->snd_cwnd_stamp = tcp_time_stamp;
- } else {
- /* Network starves. */
- if (tp->packets_out > tp->snd_cwnd_used)
- tp->snd_cwnd_used = tp->packets_out;
-
- if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= tp->rto)
- tcp_cwnd_application_limited(sk);
- }
-}
-
-/* Set slow start threshould and cwnd not falling to slow start */
+/* Set slow start threshold and cwnd not falling to slow start */
static inline void __tcp_enter_cwr(struct tcp_sock *tp)
{
tp->undo_marker = 0;
return 3;
}
-static __inline__ int tcp_minshall_check(const struct tcp_sock *tp)
-{
- return after(tp->snd_sml,tp->snd_una) &&
- !after(tp->snd_sml, tp->snd_nxt);
-}
-
static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss,
const struct sk_buff *skb)
{
tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
}
-/* Return 0, if packet can be sent now without violation Nagle's rules:
- 1. It is full sized.
- 2. Or it contains FIN.
- 3. Or TCP_NODELAY was set.
- 4. Or TCP_CORK is not set, and all sent packets are ACKed.
- With Minshall's modification: all sent small packets are ACKed.
- */
-
-static __inline__ int
-tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb,
- unsigned mss_now, int nonagle)
-{
- return (skb->len < mss_now &&
- !(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
- ((nonagle&TCP_NAGLE_CORK) ||
- (!nonagle &&
- tp->packets_out &&
- tcp_minshall_check(tp))));
-}
-
-extern void tcp_set_skb_tso_segs(struct sock *, struct sk_buff *);
-
-/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
- * should be put on the wire right now.
- */
-static __inline__ int tcp_snd_test(struct sock *sk,
- struct sk_buff *skb,
- unsigned cur_mss, int nonagle)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- int pkts = tcp_skb_pcount(skb);
-
- if (!pkts) {
- tcp_set_skb_tso_segs(sk, skb);
- pkts = tcp_skb_pcount(skb);
- }
-
- /* RFC 1122 - section 4.2.3.4
- *
- * We must queue if
- *
- * a) The right edge of this frame exceeds the window
- * b) There are packets in flight and we have a small segment
- * [SWS avoidance and Nagle algorithm]
- * (part of SWS is done on packetization)
- * Minshall version sounds: there are no _small_
- * segments in flight. (tcp_nagle_check)
- * c) We have too many packets 'in flight'
- *
- * Don't use the nagle rule for urgent data (or
- * for the final FIN -DaveM).
- *
- * Also, Nagle rule does not apply to frames, which
- * sit in the middle of queue (they have no chances
- * to get new data) and if room at tail of skb is
- * not enough to save something seriously (<32 for now).
- */
-
- /* Don't be strict about the congestion window for the
- * final FIN frame. -DaveM
- */
- return (((nonagle&TCP_NAGLE_PUSH) || tp->urg_mode
- || !tcp_nagle_check(tp, skb, cur_mss, nonagle)) &&
- (((tcp_packets_in_flight(tp) + (pkts-1)) < tp->snd_cwnd) ||
- (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)) &&
- !after(TCP_SKB_CB(skb)->end_seq, tp->snd_una + tp->snd_wnd));
-}
-
static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
{
if (!tp->packets_out && !tp->pending)
tcp_reset_xmit_timer(sk, TCP_TIME_PROBE0, tp->rto);
}
-static __inline__ int tcp_skb_is_last(const struct sock *sk,
- const struct sk_buff *skb)
-{
- return skb->next == (struct sk_buff *)&sk->sk_write_queue;
-}
-
-/* Push out any pending frames which were held back due to
- * TCP_CORK or attempt at coalescing tiny packets.
- * The socket must be locked by the caller.
- */
-static __inline__ void __tcp_push_pending_frames(struct sock *sk,
- struct tcp_sock *tp,
- unsigned cur_mss,
- int nonagle)
-{
- struct sk_buff *skb = sk->sk_send_head;
-
- if (skb) {
- if (!tcp_skb_is_last(sk, skb))
- nonagle = TCP_NAGLE_PUSH;
- if (!tcp_snd_test(sk, skb, cur_mss, nonagle) ||
- tcp_write_xmit(sk, nonagle))
- tcp_check_probe_timer(sk, tp);
- }
- tcp_cwnd_validate(sk, tp);
-}
-
static __inline__ void tcp_push_pending_frames(struct sock *sk,
struct tcp_sock *tp)
{
__tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle);
}
-static __inline__ int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
-{
- struct sk_buff *skb = sk->sk_send_head;
-
- return (skb &&
- tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
- tcp_skb_is_last(sk, skb) ? TCP_NAGLE_PUSH : tp->nonagle));
-}
-
static __inline__ void tcp_init_wl(struct tcp_sock *tp, u32 ack, u32 seq)
{
tp->snd_wl1 = seq;
TCP_INC_STATS(TCP_MIB_ESTABRESETS);
sk->sk_prot->unhash(sk);
- if (tcp_sk(sk)->bind_hash &&
+ if (inet_sk(sk)->bind_hash &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
- tcp_put_port(sk);
+ inet_put_port(&tcp_hashinfo, sk);
/* fall through */
default:
if (oldstate==TCP_ESTABLISHED)
extern void tcp_enter_memory_pressure(void);
-extern void tcp_listen_wlock(void);
-
-/* - We may sleep inside this lock.
- * - If sleeping is not required (or called from BH),
- * use plain read_(un)lock(&tcp_lhash_lock).
- */
-
-static inline void tcp_listen_lock(void)
-{
- /* read_lock synchronizes to candidates to writers */
- read_lock(&tcp_lhash_lock);
- atomic_inc(&tcp_lhash_users);
- read_unlock(&tcp_lhash_lock);
-}
-
-static inline void tcp_listen_unlock(void)
-{
- if (atomic_dec_and_test(&tcp_lhash_users))
- wake_up(&tcp_lhash_wait);
-}
-
static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
return tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl;
return 1;
}
-static inline void tcp_v4_setup_caps(struct sock *sk, struct dst_entry *dst)
-{
- sk->sk_route_caps = dst->dev->features;
- if (sk->sk_route_caps & NETIF_F_TSO) {
- if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
- sk->sk_route_caps &= ~NETIF_F_TSO;
- }
-}
-
#define TCP_CHECK_TIMER(sk) do { } while (0)
static inline int tcp_use_frto(const struct sock *sk)