diff options
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/inet_hashtables.c | 24 | ||||
| -rw-r--r-- | net/ipv4/inet_timewait_sock.c | 61 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 5 | ||||
| -rw-r--r-- | net/ipv4/tcp_input.c | 35 | ||||
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 2 | ||||
| -rw-r--r-- | net/ipv4/tcp_timer.c | 29 |
6 files changed, 122 insertions, 34 deletions
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 21e5e32d8c6..2b79377b468 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -351,12 +351,13 @@ static inline u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -void __inet_hash_nolisten(struct sock *sk) +int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; spinlock_t *lock; struct inet_ehash_bucket *head; + int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); @@ -367,8 +368,13 @@ void __inet_hash_nolisten(struct sock *sk) spin_lock(lock); __sk_nulls_add_node_rcu(sk, list); + if (tw) { + WARN_ON(sk->sk_hash != tw->tw_hash); + twrefcnt = inet_twsk_unhash(tw); + } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + return twrefcnt; } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); @@ -378,7 +384,7 @@ static void __inet_hash(struct sock *sk) struct inet_listen_hashbucket *ilb; if (sk->sk_state != TCP_LISTEN) { - __inet_hash_nolisten(sk); + __inet_hash_nolisten(sk, NULL); return; } @@ -427,7 +433,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **), - void (*hash)(struct sock *sk)) + int (*hash)(struct sock *sk, struct inet_timewait_sock *twp)) { struct inet_hashinfo *hinfo = death_row->hashinfo; const unsigned short snum = inet_sk(sk)->inet_num; @@ -435,6 +441,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; int ret; struct net *net = sock_net(sk); + int twrefcnt = 1; if (!snum) { int i, remaining, low, high, port; @@ -493,13 +500,18 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - hash(sk); + twrefcnt += hash(sk, tw); } + if (tw) + twrefcnt += inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head->lock); if (tw) { inet_twsk_deschedule(tw, death_row); - inet_twsk_put(tw); + while (twrefcnt) { + twrefcnt--; + inet_twsk_put(tw); + } } ret = 0; @@ -510,7 +522,7 @@ ok: tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - hash(sk); + hash(sk, NULL); spin_unlock_bh(&head->lock); return 0; } else { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 0fdf45e4c90..cc94cc2d8b2 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -15,9 +15,13 @@ #include <net/ip.h> -/* - * unhash a timewait socket from established hash - * lock must be hold by caller +/** + * inet_twsk_unhash - unhash a timewait socket from established hash + * @tw: timewait socket + * + * unhash a timewait socket from established hash, if hashed. + * ehash lock must be held by caller. + * Returns 1 if caller should call inet_twsk_put() after lock release. */ int inet_twsk_unhash(struct inet_timewait_sock *tw) { @@ -26,6 +30,37 @@ int inet_twsk_unhash(struct inet_timewait_sock *tw) hlist_nulls_del_rcu(&tw->tw_node); sk_nulls_node_init(&tw->tw_node); + /* + * We cannot call inet_twsk_put() ourself under lock, + * caller must call it for us. + */ + return 1; +} + +/** + * inet_twsk_bind_unhash - unhash a timewait socket from bind hash + * @tw: timewait socket + * @hashinfo: hashinfo pointer + * + * unhash a timewait socket from bind hash, if hashed. + * bind hash lock must be held by caller. + * Returns 1 if caller should call inet_twsk_put() after lock release. + */ +int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, + struct inet_hashinfo *hashinfo) +{ + struct inet_bind_bucket *tb = tw->tw_tb; + + if (!tb) + return 0; + + __hlist_del(&tw->tw_bind_node); + tw->tw_tb = NULL; + inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + /* + * We cannot call inet_twsk_put() ourself under lock, + * caller must call it for us. + */ return 1; } @@ -34,7 +69,6 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_hashbucket *bhead; - struct inet_bind_bucket *tb; int refcnt; /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); @@ -46,15 +80,11 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, /* Disassociate with bind bucket. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, hashinfo->bhash_size)]; + spin_lock(&bhead->lock); - tb = tw->tw_tb; - if (tb) { - __hlist_del(&tw->tw_bind_node); - tw->tw_tb = NULL; - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - refcnt++; - } + refcnt += inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); + #ifdef SOCK_REFCNT_DEBUG if (atomic_read(&tw->tw_refcnt) != 1) { printk(KERN_DEBUG "%s timewait_sock %p refcnt=%d\n", @@ -126,7 +156,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, /* * Notes : - * - We initially set tw_refcnt to 0 in inet_twsk_alloc() + * - We initially set tw_refcnt to 0 in inet_twsk_alloc() * - We add one reference for the bhash link * - We add one reference for the ehash link * - We want this refcnt update done before allowing other @@ -136,7 +166,6 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_unlock(lock); } - EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state) @@ -177,7 +206,6 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat return tw; } - EXPORT_SYMBOL_GPL(inet_twsk_alloc); /* Returns non-zero if quota exceeded. */ @@ -256,7 +284,6 @@ void inet_twdr_hangman(unsigned long data) out: spin_unlock(&twdr->death_lock); } - EXPORT_SYMBOL_GPL(inet_twdr_hangman); void inet_twdr_twkill_work(struct work_struct *work) @@ -287,7 +314,6 @@ void inet_twdr_twkill_work(struct work_struct *work) spin_unlock_bh(&twdr->death_lock); } } - EXPORT_SYMBOL_GPL(inet_twdr_twkill_work); /* These are always called from BH context. See callers in @@ -307,7 +333,6 @@ void inet_twsk_deschedule(struct inet_timewait_sock *tw, spin_unlock(&twdr->death_lock); __inet_twsk_kill(tw, twdr->hashinfo); } - EXPORT_SYMBOL(inet_twsk_deschedule); void inet_twsk_schedule(struct inet_timewait_sock *tw, @@ -388,7 +413,6 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, mod_timer(&twdr->tw_timer, jiffies + twdr->period); spin_unlock(&twdr->death_lock); } - EXPORT_SYMBOL_GPL(inet_twsk_schedule); void inet_twdr_twcal_tick(unsigned long data) @@ -449,7 +473,6 @@ out: #endif spin_unlock(&twdr->death_lock); } - EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick); void inet_twsk_purge(struct inet_hashinfo *hashinfo, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c8666b70cde..b0a26bb25e2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2540,11 +2540,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level, ctd.tcpct_cookie_desired = cvp->cookie_desired; ctd.tcpct_s_data_desired = cvp->s_data_desired; - /* Cookie(s) saved, return as nonce */ - if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) { - /* impossible? */ - return -EINVAL; - } memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0], cvp->cookie_pair_size); ctd.tcpct_used = cvp->cookie_pair_size; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 57ae96a0422..12cab7d74db 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2717,6 +2717,35 @@ static void tcp_try_undo_dsack(struct sock *sk) } } +/* We can clear retrans_stamp when there are no retransmissions in the + * window. It would seem that it is trivially available for us in + * tp->retrans_out, however, that kind of assumptions doesn't consider + * what will happen if errors occur when sending retransmission for the + * second time. ...It could the that such segment has only + * TCPCB_EVER_RETRANS set at the present time. It seems that checking + * the head skb is enough except for some reneging corner cases that + * are not worth the effort. + * + * Main reason for all this complexity is the fact that connection dying + * time now depends on the validity of the retrans_stamp, in particular, + * that successive retransmissions of a segment must not advance + * retrans_stamp under any conditions. + */ +static int tcp_any_retrans_done(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + + if (tp->retrans_out) + return 1; + + skb = tcp_write_queue_head(sk); + if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) + return 1; + + return 0; +} + /* Undo during fast recovery after partial ACK. */ static int tcp_try_undo_partial(struct sock *sk, int acked) @@ -2729,7 +2758,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked) /* Plain luck! Hole if filled with delayed * packet, rather than with a retransmit. */ - if (tp->retrans_out == 0) + if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1); @@ -2788,7 +2817,7 @@ static void tcp_try_keep_open(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); int state = TCP_CA_Open; - if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) + if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker) state = TCP_CA_Disorder; if (inet_csk(sk)->icsk_ca_state != state) { @@ -2803,7 +2832,7 @@ static void tcp_try_to_open(struct sock *sk, int flag) tcp_verify_left_out(tp); - if (!tp->frto_counter && tp->retrans_out == 0) + if (!tp->frto_counter && !tcp_any_retrans_done(sk)) tp->retrans_stamp = 0; if (flag & FLAG_ECE) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 29002ab26e0..15e96030ce4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1464,7 +1464,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif - __inet_hash_nolisten(newsk); + __inet_hash_nolisten(newsk, NULL); __inet_inherit_port(sk, newsk); return newsk; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8353a538cd4..8816a20c259 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -132,6 +132,35 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } } +/* This function calculates a "timeout" which is equivalent to the timeout of a + * TCP connection after "boundary" unsucessful, exponentially backed-off + * retransmissions with an initial RTO of TCP_RTO_MIN. + */ +static bool retransmits_timed_out(struct sock *sk, + unsigned int boundary) +{ + unsigned int timeout, linear_backoff_thresh; + unsigned int start_ts; + + if (!inet_csk(sk)->icsk_retransmits) + return false; + + if (unlikely(!tcp_sk(sk)->retrans_stamp)) + start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when; + else + start_ts = tcp_sk(sk)->retrans_stamp; + + linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN); + + if (boundary <= linear_backoff_thresh) + timeout = ((2 << boundary) - 1) * TCP_RTO_MIN; + else + timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN + + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + + return (tcp_time_stamp - start_ts) >= timeout; +} + /* A write timeout has occurred. Process the after effects. */ static int tcp_write_timeout(struct sock *sk) { |