diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/atm/common.c | 22 | ||||
-rw-r--r-- | net/bluetooth/l2cap.c | 5 | ||||
-rw-r--r-- | net/core/dev.c | 26 | ||||
-rw-r--r-- | net/core/skbuff.c | 2 | ||||
-rw-r--r-- | net/core/sock.c | 50 | ||||
-rw-r--r-- | net/core/stream.c | 10 | ||||
-rw-r--r-- | net/dccp/output.c | 10 | ||||
-rw-r--r-- | net/ethernet/eth.c | 2 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 16 | ||||
-rw-r--r-- | net/ipv6/addrconf.c | 16 | ||||
-rw-r--r-- | net/ipv6/inet6_connection_sock.c | 15 | ||||
-rw-r--r-- | net/iucv/af_iucv.c | 11 | ||||
-rw-r--r-- | net/phonet/pep.c | 8 | ||||
-rw-r--r-- | net/phonet/socket.c | 2 | ||||
-rw-r--r-- | net/rxrpc/af_rxrpc.c | 10 | ||||
-rw-r--r-- | net/sched/sch_generic.c | 2 | ||||
-rw-r--r-- | net/sctp/associola.c | 6 | ||||
-rw-r--r-- | net/sctp/endpointola.c | 1 | ||||
-rw-r--r-- | net/sctp/probe.c | 1 | ||||
-rw-r--r-- | net/sctp/sm_make_chunk.c | 94 | ||||
-rw-r--r-- | net/sctp/sm_sideeffect.c | 26 | ||||
-rw-r--r-- | net/sctp/sm_statefuns.c | 8 | ||||
-rw-r--r-- | net/sctp/socket.c | 19 | ||||
-rw-r--r-- | net/socket.c | 47 | ||||
-rw-r--r-- | net/unix/af_unix.c | 17 | ||||
-rw-r--r-- | net/unix/garbage.c | 13 |
26 files changed, 281 insertions, 158 deletions
diff --git a/net/atm/common.c b/net/atm/common.c index e3e10e6f862..b43feb1a399 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -90,10 +90,13 @@ static void vcc_sock_destruct(struct sock *sk) static void vcc_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up(sk_sleep(sk)); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up(&wq->wait); + rcu_read_unlock(); } static inline int vcc_writable(struct sock *sk) @@ -106,16 +109,19 @@ static inline int vcc_writable(struct sock *sk) static void vcc_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); if (vcc_writable(sk)) { - if (sk_has_sleeper(sk)) - wake_up_interruptible(sk_sleep(sk)); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static struct proto vcc_proto = { diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index c1e60eed5a9..864c76f4a67 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1626,7 +1626,10 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms /* Connectionless channel */ if (sk->sk_type == SOCK_DGRAM) { skb = l2cap_create_connless_pdu(sk, msg, len); - err = l2cap_do_send(sk, skb); + if (IS_ERR(skb)) + err = PTR_ERR(skb); + else + err = l2cap_do_send(sk, skb); goto done; } diff --git a/net/core/dev.c b/net/core/dev.c index 100dcbd2973..36d53be4fca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2205,8 +2205,6 @@ int netdev_max_backlog __read_mostly = 1000; int netdev_budget __read_mostly = 300; int weight_p __read_mostly = 64; /* old backlog weight */ -DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; - #ifdef CONFIG_RPS /* One global table that all flow-based protocols share. */ @@ -2366,7 +2364,7 @@ static void rps_trigger_softirq(void *data) struct softnet_data *sd = data; __napi_schedule(&sd->backlog); - __get_cpu_var(netdev_rx_stat).received_rps++; + sd->received_rps++; } #endif /* CONFIG_RPS */ @@ -2405,7 +2403,6 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, sd = &per_cpu(softnet_data, cpu); local_irq_save(flags); - __get_cpu_var(netdev_rx_stat).total++; rps_lock(sd); if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) { @@ -2429,9 +2426,9 @@ enqueue: goto enqueue; } + sd->dropped++; rps_unlock(sd); - __get_cpu_var(netdev_rx_stat).dropped++; local_irq_restore(flags); kfree_skb(skb); @@ -2806,7 +2803,7 @@ static int __netif_receive_skb(struct sk_buff *skb) skb->dev = master; } - __get_cpu_var(netdev_rx_stat).total++; + __get_cpu_var(softnet_data).processed++; skb_reset_network_header(skb); skb_reset_transport_header(skb); @@ -3490,7 +3487,7 @@ out: return; softnet_break: - __get_cpu_var(netdev_rx_stat).time_squeeze++; + sd->time_squeeze++; __raise_softirq_irqoff(NET_RX_SOFTIRQ); goto out; } @@ -3691,17 +3688,17 @@ static int dev_seq_show(struct seq_file *seq, void *v) return 0; } -static struct netif_rx_stats *softnet_get_online(loff_t *pos) +static struct softnet_data *softnet_get_online(loff_t *pos) { - struct netif_rx_stats *rc = NULL; + struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { - rc = &per_cpu(netdev_rx_stat, *pos); + sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; - return rc; + return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) @@ -3721,12 +3718,12 @@ static void softnet_seq_stop(struct seq_file *seq, void *v) static int softnet_seq_show(struct seq_file *seq, void *v) { - struct netif_rx_stats *s = v; + struct softnet_data *sd = v; seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", - s->total, s->dropped, s->time_squeeze, 0, + sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision, s->received_rps); + sd->cpu_collision, sd->received_rps); return 0; } @@ -5869,6 +5866,7 @@ static int __init net_dev_init(void) for_each_possible_cpu(i) { struct softnet_data *sd = &per_cpu(softnet_data, i); + memset(sd, 0, sizeof(*sd)); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); sd->completion_queue = NULL; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4218ff49bf1..8b9c109166a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1051,7 +1051,7 @@ EXPORT_SYMBOL(skb_push); */ unsigned char *skb_pull(struct sk_buff *skb, unsigned int len) { - return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); + return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); diff --git a/net/core/sock.c b/net/core/sock.c index 51041759517..94c4affdda9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1211,7 +1211,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); - newsk->sk_sleep = NULL; + newsk->sk_wq = NULL; if (newsk->sk_prot->sockets_allocated) percpu_counter_inc(newsk->sk_prot->sockets_allocated); @@ -1800,41 +1800,53 @@ EXPORT_SYMBOL(sock_no_sendpage); static void sock_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk_sleep(sk)); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_poll(sk_sleep(sk), POLLERR); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_readable(struct sock *sk, int len) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN | + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ @@ -1842,7 +1854,7 @@ static void sock_def_write_space(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) @@ -1896,10 +1908,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) if (sock) { sk->sk_type = sock->type; - sk->sk_sleep = &sock->wait; + sk->sk_wq = sock->wq; sock->sk = sk; } else - sk->sk_sleep = NULL; + sk->sk_wq = NULL; spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); diff --git a/net/core/stream.c b/net/core/stream.c index 7b3c3f30b10..cc196f42b8d 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -28,15 +28,19 @@ void sk_stream_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; + struct socket_wq *wq; if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); - if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); - if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) + if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); + rcu_read_unlock(); } } diff --git a/net/dccp/output.c b/net/dccp/output.c index 2d3dcb39851..aadbdb58758 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -195,15 +195,17 @@ EXPORT_SYMBOL_GPL(dccp_sync_mss); void dccp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; - if (sk_has_sleeper(sk)) - wake_up_interruptible(sk_sleep(sk)); + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /** diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 0c0d272a988..61ec0329316 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -162,7 +162,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - skb_pull(skb, ETH_HLEN); + skb_pull_inline(skb, ETH_HLEN); eth = eth_hdr(skb); if (unlikely(is_multicast_ether_addr(eth->h_dest))) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 78cbc39f56c..e0a3e3537b1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -70,17 +70,13 @@ int inet_csk_bind_conflict(const struct sock *sk, (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { - const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); - if (!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) { + const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr || sk2_rcv_saddr == sk_rcv_saddr) break; - } else if (reuse && sk2->sk_reuse && - sk2_rcv_saddr && - sk2_rcv_saddr == sk_rcv_saddr) - break; + } } } return node != NULL; @@ -124,11 +120,9 @@ again: smallest_size = tb->num_owners; smallest_rover = rover; if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) { - if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) { - spin_unlock(&head->lock); - snum = smallest_rover; - goto have_snum; - } + spin_unlock(&head->lock); + snum = smallest_rover; + goto have_snum; } } goto next; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 34d2d649e39..3984f52181f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1346,7 +1346,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add struct hlist_node *node; rcu_read_lock_bh(); - hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -2959,7 +2959,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { struct hlist_node *n; - hlist_for_each_entry_rcu(ifa, n, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; @@ -2974,12 +2974,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct hlist_node *n = &ifa->addr_lst; - hlist_for_each_entry_continue_rcu(ifa, n, addr_lst) + hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; while (++state->bucket < IN6_ADDR_HSIZE) { - hlist_for_each_entry(ifa, n, + hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], addr_lst) { if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; @@ -3000,7 +3000,7 @@ static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu) + __acquires(rcu_bh) { rcu_read_lock_bh(); return if6_get_idx(seq, *pos); @@ -3016,7 +3016,7 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void if6_seq_stop(struct seq_file *seq, void *v) - __releases(rcu) + __releases(rcu_bh) { rcu_read_unlock_bh(); } @@ -3093,7 +3093,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) unsigned int hash = ipv6_addr_hash(addr); rcu_read_lock_bh(); - hlist_for_each_entry_rcu(ifp, n, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -3127,7 +3127,7 @@ static void addrconf_verify(unsigned long foo) for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu(ifp, node, + hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[i], addr_lst) { unsigned long age; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 9ca1efc923a..0c5e3c3b7fd 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -42,16 +42,11 @@ int inet6_csk_bind_conflict(const struct sock *sk, if (sk != sk2 && (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { - if ((!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; - else if (sk->sk_reuse && sk2->sk_reuse && - !ipv6_addr_any(inet6_rcv_saddr(sk)) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; - } + sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && + (!sk->sk_reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + ipv6_rcv_saddr_equal(sk, sk2)) + break; } return node != NULL; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 9636b7d27b4..8be324fe08b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -305,11 +305,14 @@ static inline int iucv_below_msglim(struct sock *sk) */ static void iucv_sock_wake_msglim(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk_sleep(sk)); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /* Timers */ diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e2a95762abd..af4d38bc3b2 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -664,12 +664,12 @@ static int pep_wait_connreq(struct sock *sk, int noblock) if (signal_pending(tsk)) return sock_intr_errno(timeo); - prepare_to_wait_exclusive(&sk->sk_socket->wait, &wait, + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); - finish_wait(&sk->sk_socket->wait, &wait); + finish_wait(sk_sleep(sk), &wait); } return 0; @@ -910,10 +910,10 @@ disabled: goto out; } - prepare_to_wait(&sk->sk_socket->wait, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits)); - finish_wait(&sk->sk_socket->wait, &wait); + finish_wait(sk_sleep(sk), &wait); if (sk->sk_state != TCP_ESTABLISHED) goto disabled; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index c785bfd0744..6e9848bf037 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -265,7 +265,7 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock, struct pep_sock *pn = pep_sk(sk); unsigned int mask = 0; - poll_wait(file, &sock->wait, wait); + poll_wait(file, sk_sleep(sk), wait); switch (sk->sk_state) { case TCP_LISTEN: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index c432d76f415..0b9bb2085ce 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -62,13 +62,15 @@ static inline int rxrpc_writable(struct sock *sk) static void rxrpc_write_space(struct sock *sk) { _enter("%p", sk); - read_lock(&sk->sk_callback_lock); + rcu_read_lock(); if (rxrpc_writable(sk)) { - if (sk_has_sleeper(sk)) - wake_up_interruptible(sk_sleep(sk)); + struct socket_wq *wq = rcu_dereference(sk->sk_wq); + + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /* diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index aeddabfb8e4..a969b111bd7 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -94,7 +94,7 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, * Another cpu is holding lock, requeue & delay xmits for * some time. */ - __get_cpu_var(netdev_rx_stat).cpu_collision++; + __get_cpu_var(softnet_data).cpu_collision++; ret = dev_requeue_skb(skb, q); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 65f9a7cdf46..3912420cedc 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1192,8 +1192,10 @@ void sctp_assoc_update(struct sctp_association *asoc, /* Remove any peer addresses not present in the new association. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { trans = list_entry(pos, struct sctp_transport, transports); - if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) - sctp_assoc_del_peer(asoc, &trans->ipaddr); + if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) { + sctp_assoc_rm_peer(asoc, trans); + continue; + } if (asoc->state >= SCTP_STATE_ESTABLISHED) sctp_transport_reset(trans); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 2f8763bae9e..e10acc01c75 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -142,6 +142,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Use SCTP specific send buffer space queues. */ ep->sndbuf_policy = sctp_sndbuf_policy; + sk->sk_data_ready = sctp_data_ready; sk->sk_write_space = sctp_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); diff --git a/net/sctp/probe.c b/net/sctp/probe.c index 8f025d5831a..db3a42b8b34 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -27,6 +27,7 @@ #include <linux/socket.h> #include <linux/sctp.h> #include <linux/proc_fs.h> +#include <linux/vmalloc.h> #include <linux/module.h> #include <linux/kfifo.h> #include <linux/time.h> diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 24effdf471e..d8261f3d771 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -108,7 +108,7 @@ static const struct sctp_paramhdr prsctp_param = { cpu_to_be16(sizeof(struct sctp_paramhdr)), }; -/* A helper to initialize to initialize an op error inside a +/* A helper to initialize an op error inside a * provided chunk, as most cause codes will be embedded inside an * abort chunk. */ @@ -125,6 +125,29 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(sctp_errhdr_t), &err); } +/* A helper to initialize an op error inside a + * provided chunk, as most cause codes will be embedded inside an + * abort chunk. Differs from sctp_init_cause in that it won't oops + * if there isn't enough space in the op error chunk + */ +int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, + size_t paylen) +{ + sctp_errhdr_t err; + __u16 len; + + /* Cause code constants are now defined in network order. */ + err.cause = cause_code; + len = sizeof(sctp_errhdr_t) + paylen; + err.length = htons(len); + + if (skb_tailroom(chunk->skb) > len) + return -ENOSPC; + chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk, + sizeof(sctp_errhdr_t), + &err); + return 0; +} /* 3.3.2 Initiation (INIT) (1) * * This chunk is used to initiate a SCTP association between two @@ -208,7 +231,8 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sp = sctp_sk(asoc->base.sk); num_types = sp->pf->supported_addrs(sp, types); - chunksize = sizeof(init) + addrs_len + SCTP_SAT_LEN(num_types); + chunksize = sizeof(init) + addrs_len; + chunksize += WORD_ROUND(SCTP_SAT_LEN(num_types)); chunksize += sizeof(ecap_param); if (sctp_prsctp_enable) @@ -238,14 +262,14 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, /* Add HMACS parameter length if any were defined */ auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; if (auth_hmacs->length) - chunksize += ntohs(auth_hmacs->length); + chunksize += WORD_ROUND(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; /* Add CHUNKS parameter length */ auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; if (auth_chunks->length) - chunksize += ntohs(auth_chunks->length); + chunksize += WORD_ROUND(ntohs(auth_chunks->length)); else auth_chunks = NULL; @@ -255,7 +279,8 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, /* If we have any extensions to report, account for that */ if (num_ext) - chunksize += sizeof(sctp_supported_ext_param_t) + num_ext; + chunksize += WORD_ROUND(sizeof(sctp_supported_ext_param_t) + + num_ext); /* RFC 2960 3.3.2 Initiation (INIT) (1) * @@ -397,13 +422,13 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; if (auth_hmacs->length) - chunksize += ntohs(auth_hmacs->length); + chunksize += WORD_ROUND(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; if (auth_chunks->length) - chunksize += ntohs(auth_chunks->length); + chunksize += WORD_ROUND(ntohs(auth_chunks->length)); else auth_chunks = NULL; @@ -412,7 +437,8 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, } if (num_ext) - chunksize += sizeof(sctp_supported_ext_param_t) + num_ext; + chunksize += WORD_ROUND(sizeof(sctp_supported_ext_param_t) + + num_ext); /* Now allocate and fill out the chunk. */ retval = sctp_make_chunk(asoc, SCTP_CID_INIT_ACK, 0, chunksize); @@ -1124,6 +1150,24 @@ nodata: return retval; } +/* Create an Operation Error chunk of a fixed size, + * specifically, max(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) + * This is a helper function to allocate an error chunk for + * for those invalid parameter codes in which we may not want + * to report all the errors, if the incomming chunk is large + */ +static inline struct sctp_chunk *sctp_make_op_error_fixed( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk) +{ + size_t size = asoc ? asoc->pathmtu : 0; + + if (!size) + size = SCTP_DEFAULT_MAXSEGMENT; + + return sctp_make_op_error_space(asoc, chunk, size); +} + /* Create an Operation Error chunk. */ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, @@ -1365,6 +1409,18 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) return target; } +/* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient + * space in the chunk + */ +void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, + int len, const void *data) +{ + if (skb_tailroom(chunk->skb) > len) + return sctp_addto_chunk(chunk, len, data); + else + return NULL; +} + /* Append bytes from user space to the end of a chunk. Will panic if * chunk is not big enough. * Returns a kernel err value. @@ -1968,13 +2024,12 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, * returning multiple unknown parameters. */ if (NULL == *errp) - *errp = sctp_make_op_error_space(asoc, chunk, - ntohs(chunk->chunk_hdr->length)); + *errp = sctp_make_op_error_fixed(asoc, chunk); if (*errp) { - sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, + sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, WORD_ROUND(ntohs(param.p->length))); - sctp_addto_chunk(*errp, + sctp_addto_chunk_fixed(*errp, WORD_ROUND(ntohs(param.p->length)), param.v); } else { @@ -3309,21 +3364,6 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, sctp_chunk_free(asconf); asoc->addip_last_asconf = NULL; - /* Send the next asconf chunk from the addip chunk queue. */ - if (!list_empty(&asoc->addip_chunk_list)) { - struct list_head *entry = asoc->addip_chunk_list.next; - asconf = list_entry(entry, struct sctp_chunk, list); - - list_del_init(entry); - - /* Hold the chunk until an ASCONF_ACK is received. */ - sctp_chunk_hold(asconf); - if (sctp_primitive_ASCONF(asoc, asconf)) - sctp_chunk_free(asconf); - else - asoc->addip_last_asconf = asconf; - } - return retval; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 49fb9acece6..3b7230ef77c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -966,6 +966,29 @@ static int sctp_cmd_send_msg(struct sctp_association *asoc, } +/* Sent the next ASCONF packet currently stored in the association. + * This happens after the ASCONF_ACK was succeffully processed. + */ +static void sctp_cmd_send_asconf(struct sctp_association *asoc) +{ + /* Send the next asconf chunk from the addip chunk + * queue. + */ + if (!list_empty(&asoc->addip_chunk_list)) { + struct list_head *entry = asoc->addip_chunk_list.next; + struct sctp_chunk *asconf = list_entry(entry, + struct sctp_chunk, list); + list_del_init(entry); + + /* Hold the chunk until an ASCONF_ACK is received. */ + sctp_chunk_hold(asconf); + if (sctp_primitive_ASCONF(asoc, asconf)) + sctp_chunk_free(asconf); + else + asoc->addip_last_asconf = asconf; + } +} + /* These three macros allow us to pull the debugging code out of the * main flow of sctp_do_sm() to keep attention focused on the real @@ -1621,6 +1644,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, } error = sctp_cmd_send_msg(asoc, cmd->obj.msg); break; + case SCTP_CMD_SEND_NEXT_ASCONF: + sctp_cmd_send_asconf(asoc); + break; default: printk(KERN_WARNING "Impossible command: %u, %p\n", cmd->verb, cmd->obj.ptr); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index abf601a1b84..24b2cd55563 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3676,8 +3676,14 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); if (!sctp_process_asconf_ack((struct sctp_association *)asoc, - asconf_ack)) + asconf_ack)) { + /* Successfully processed ASCONF_ACK. We can + * release the next asconf if we have one. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF, + SCTP_NULL()); return SCTP_DISPOSITION_CONSUME; + } abort = sctp_make_abort(asoc, asconf_ack, sizeof(sctp_errhdr_t)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1282a0ed855..ba1add0b13c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3719,9 +3719,9 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->hmac = NULL; SCTP_DBG_OBJCNT_INC(sock); - percpu_counter_inc(&sctp_sockets_allocated); local_bh_disable(); + percpu_counter_inc(&sctp_sockets_allocated); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); local_bh_enable(); @@ -3738,8 +3738,8 @@ SCTP_STATIC void sctp_destroy_sock(struct sock *sk) /* Release our hold on the endpoint. */ ep = sctp_sk(sk)->ep; sctp_endpoint_free(ep); - percpu_counter_dec(&sctp_sockets_allocated); local_bh_disable(); + percpu_counter_dec(&sctp_sockets_allocated); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); } @@ -6065,7 +6065,7 @@ static void __sctp_write_space(struct sctp_association *asoc) * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ - if (sock->fasync_list && + if (sock->wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); @@ -6185,6 +6185,19 @@ do_nonblock: goto out; } +void sctp_data_ready(struct sock *sk, int len) +{ + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | + POLLRDNORM | POLLRDBAND); + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + rcu_read_unlock(); +} + /* If socket sndbuf has changed, wake up all per association waiters. */ void sctp_write_space(struct sock *sk) { diff --git a/net/socket.c b/net/socket.c index cb7c1f6c0d6..dae8c6b84a0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -252,9 +252,14 @@ static struct inode *sock_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; - init_waitqueue_head(&ei->socket.wait); + ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL); + if (!ei->socket.wq) { + kmem_cache_free(sock_inode_cachep, ei); + return NULL; + } + init_waitqueue_head(&ei->socket.wq->wait); + ei->socket.wq->fasync_list = NULL; - ei->socket.fasync_list = NULL; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; @@ -264,10 +269,21 @@ static struct inode *sock_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } + +static void wq_free_rcu(struct rcu_head *head) +{ + struct socket_wq *wq = container_of(head, struct socket_wq, rcu); + + kfree(wq); +} + static void sock_destroy_inode(struct inode *inode) { - kmem_cache_free(sock_inode_cachep, - container_of(inode, struct socket_alloc, vfs_inode)); + struct socket_alloc *ei; + + ei = container_of(inode, struct socket_alloc, vfs_inode); + call_rcu(&ei->socket.wq->rcu, wq_free_rcu); + kmem_cache_free(sock_inode_cachep, ei); } static void init_once(void *foo) @@ -513,7 +529,7 @@ void sock_release(struct socket *sock) module_put(owner); } - if (sock->fasync_list) + if (sock->wq->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); percpu_sub(sockets_in_use, 1); @@ -1080,9 +1096,9 @@ static int sock_fasync(int fd, struct file *filp, int on) lock_sock(sk); - fasync_helper(fd, filp, on, &sock->fasync_list); + fasync_helper(fd, filp, on, &sock->wq->fasync_list); - if (!sock->fasync_list) + if (!sock->wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); @@ -1091,12 +1107,20 @@ static int sock_fasync(int fd, struct file *filp, int on) return 0; } -/* This function may be called only under socket lock or callback_lock */ +/* This function may be called only under socket lock or callback_lock or rcu_lock */ int sock_wake_async(struct socket *sock, int how, int band) { - if (!sock || !sock->fasync_list) + struct socket_wq *wq; + + if (!sock) return -1; + rcu_read_lock(); + wq = rcu_dereference(sock->wq); + if (!wq || !wq->fasync_list) { + rcu_read_unlock(); + return -1; + } switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags)) @@ -1108,11 +1132,12 @@ int sock_wake_async(struct socket *sock, int how, int band) /* fall through */ case SOCK_WAKE_IO: call_kill: - kill_fasync(&sock->fasync_list, SIGIO, band); + kill_fasync(&wq->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: - kill_fasync(&sock->fasync_list, SIGURG, band); + kill_fasync(&wq->fasync_list, SIGURG, band); } + rcu_read_unlock(); return 0; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 87c0360eaa2..fef2cc5e9d2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -313,13 +313,16 @@ static inline int unix_writable(struct sock *sk) static void unix_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); if (unix_writable(sk)) { - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync(sk_sleep(sk)); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /* When dgram socket disconnects (or changes its peer), we clear its receive @@ -406,9 +409,7 @@ static int unix_release_sock(struct sock *sk, int embrion) skpair->sk_err = ECONNRESET; unix_state_unlock(skpair); skpair->sk_state_change(skpair); - read_lock(&skpair->sk_callback_lock); sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP); - read_unlock(&skpair->sk_callback_lock); } sock_put(skpair); /* It may now die */ unix_peer(sk) = NULL; @@ -1142,7 +1143,7 @@ restart: newsk->sk_peercred.pid = task_tgid_vnr(current); current_euid_egid(&newsk->sk_peercred.uid, &newsk->sk_peercred.gid); newu = unix_sk(newsk); - newsk->sk_sleep = &newu->peer_wait; + newsk->sk_wq = &newu->peer_wq; otheru = unix_sk(other); /* copy address information from listening to new sock*/ @@ -1931,12 +1932,10 @@ static int unix_shutdown(struct socket *sock, int mode) other->sk_shutdown |= peer_mode; unix_state_unlock(other); other->sk_state_change(other); - read_lock(&other->sk_callback_lock); if (peer_mode == SHUTDOWN_MASK) sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); else if (peer_mode & RCV_SHUTDOWN) sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); - read_unlock(&other->sk_callback_lock); } if (other) sock_put(other); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 14c22c3768d..c8df6fda0b1 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -153,15 +153,6 @@ void unix_notinflight(struct file *fp) } } -static inline struct sk_buff *sock_queue_head(struct sock *sk) -{ - return (struct sk_buff *)&sk->sk_receive_queue; -} - -#define receive_queue_for_each_skb(sk, next, skb) \ - for (skb = sock_queue_head(sk)->next, next = skb->next; \ - skb != sock_queue_head(sk); skb = next, next = skb->next) - static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { @@ -169,7 +160,7 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff *next; spin_lock(&x->sk_receive_queue.lock); - receive_queue_for_each_skb(x, next, skb) { + skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { /* * Do we have file descriptors ? */ @@ -225,7 +216,7 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), * and perform a scan on them as well. */ spin_lock(&x->sk_receive_queue.lock); - receive_queue_for_each_skb(x, next, skb) { + skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { u = unix_sk(skb->sk); /* |