diff options
Diffstat (limited to 'net/tipc')
| -rw-r--r-- | net/tipc/core.c | 16 | ||||
| -rw-r--r-- | net/tipc/core.h | 6 | ||||
| -rw-r--r-- | net/tipc/discover.c | 4 | ||||
| -rw-r--r-- | net/tipc/link.c | 2 | ||||
| -rw-r--r-- | net/tipc/msg.c | 53 | ||||
| -rw-r--r-- | net/tipc/msg.h | 26 | ||||
| -rw-r--r-- | net/tipc/name_distr.c | 2 | ||||
| -rw-r--r-- | net/tipc/node.c | 155 | ||||
| -rw-r--r-- | net/tipc/node.h | 12 | ||||
| -rw-r--r-- | net/tipc/socket.c | 127 |
10 files changed, 369 insertions, 34 deletions
diff --git a/net/tipc/core.c b/net/tipc/core.c index 23cb379a93d6..ab648dd150ee 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -105,6 +105,15 @@ static void __net_exit tipc_exit_net(struct net *net) tipc_sk_rht_destroy(net); } +static void __net_exit tipc_pernet_pre_exit(struct net *net) +{ + tipc_node_pre_cleanup_net(net); +} + +static struct pernet_operations tipc_pernet_pre_exit_ops = { + .pre_exit = tipc_pernet_pre_exit, +}; + static struct pernet_operations tipc_net_ops = { .init = tipc_init_net, .exit = tipc_exit_net, @@ -151,6 +160,10 @@ static int __init tipc_init(void) if (err) goto out_pernet_topsrv; + err = register_pernet_subsys(&tipc_pernet_pre_exit_ops); + if (err) + goto out_register_pernet_subsys; + err = tipc_bearer_setup(); if (err) goto out_bearer; @@ -158,6 +171,8 @@ static int __init tipc_init(void) pr_info("Started in single node mode\n"); return 0; out_bearer: + unregister_pernet_subsys(&tipc_pernet_pre_exit_ops); +out_register_pernet_subsys: unregister_pernet_device(&tipc_topsrv_net_ops); out_pernet_topsrv: tipc_socket_stop(); @@ -177,6 +192,7 @@ out_netlink: static void __exit tipc_exit(void) { tipc_bearer_cleanup(); + unregister_pernet_subsys(&tipc_pernet_pre_exit_ops); unregister_pernet_device(&tipc_topsrv_net_ops); tipc_socket_stop(); unregister_pernet_device(&tipc_net_ops); diff --git a/net/tipc/core.h b/net/tipc/core.h index 60d829581068..8776d32a4a47 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -59,6 +59,7 @@ #include <net/netns/generic.h> #include <linux/rhashtable.h> #include <net/genetlink.h> +#include <net/netns/hash.h> struct tipc_node; struct tipc_bearer; @@ -185,6 +186,11 @@ static inline int in_range(u16 val, u16 min, u16 max) return !less(val, min) && !more(val, max); } +static inline u32 tipc_net_hash_mixes(struct net *net, int tn_rand) +{ + return net_hash_mix(&init_net) ^ net_hash_mix(net) ^ tn_rand; +} + #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index c138d68e8a69..b043e8c6397a 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -94,6 +94,7 @@ static void tipc_disc_init_msg(struct net *net, struct sk_buff *skb, msg_set_dest_domain(hdr, dest_domain); msg_set_bc_netid(hdr, tn->net_id); b->media->addr2msg(msg_media_addr(hdr), &b->addr); + msg_set_peer_net_hash(hdr, tipc_net_hash_mixes(net, tn->random)); msg_set_node_id(hdr, tipc_own_id(net)); } @@ -242,7 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, if (!tipc_in_scope(legacy, b->domain, src)) return; tipc_node_check_dest(net, src, peer_id, b, caps, signature, - &maddr, &respond, &dupl_addr); + msg_peer_net_hash(hdr), &maddr, &respond, + &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) diff --git a/net/tipc/link.c b/net/tipc/link.c index 999eab592de8..7d7a66178607 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1873,7 +1873,7 @@ void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl, tipc_link_create_dummy_tnl_msg(tnl, xmitq); - /* This failover link enpoint was never established before, + /* This failover link endpoint was never established before, * so it has not received anything from peer. * Otherwise, it must be a normal failover situation or the * node has entered SELF_DOWN_PEER_LEAVING and both peer nodes diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 922d262e153f..973795a1a968 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -190,6 +190,59 @@ err: return 0; } +/** + * tipc_msg_append(): Append data to tail of an existing buffer queue + * @hdr: header to be used + * @m: the data to be appended + * @mss: max allowable size of buffer + * @dlen: size of data to be appended + * @txq: queue to appand to + * Returns the number og 1k blocks appended or errno value + */ +int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen, + int mss, struct sk_buff_head *txq) +{ + struct sk_buff *skb, *prev; + int accounted, total, curr; + int mlen, cpy, rem = dlen; + struct tipc_msg *hdr; + + skb = skb_peek_tail(txq); + accounted = skb ? msg_blocks(buf_msg(skb)) : 0; + total = accounted; + + while (rem) { + if (!skb || skb->len >= mss) { + prev = skb; + skb = tipc_buf_acquire(mss, GFP_KERNEL); + if (unlikely(!skb)) + return -ENOMEM; + skb_orphan(skb); + skb_trim(skb, MIN_H_SIZE); + hdr = buf_msg(skb); + skb_copy_to_linear_data(skb, _hdr, MIN_H_SIZE); + msg_set_hdr_sz(hdr, MIN_H_SIZE); + msg_set_size(hdr, MIN_H_SIZE); + __skb_queue_tail(txq, skb); + total += 1; + if (prev) + msg_set_ack_required(buf_msg(prev), 0); + msg_set_ack_required(hdr, 1); + } + hdr = buf_msg(skb); + curr = msg_blocks(hdr); + mlen = msg_size(hdr); + cpy = min_t(int, rem, mss - mlen); + if (cpy != copy_from_iter(skb->data + mlen, cpy, &m->msg_iter)) + return -EFAULT; + msg_set_size(hdr, mlen + cpy); + skb_put(skb, cpy); + rem -= cpy; + total += msg_blocks(hdr) - curr; + } + return total - accounted; +} + /* tipc_msg_validate - validate basic format of received message * * This routine ensures a TIPC message has an acceptable header, and at least diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 0daa6f04ca81..0435dda4b90c 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -290,6 +290,16 @@ static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d) msg_set_bits(m, 0, 18, 1, d); } +static inline int msg_ack_required(struct tipc_msg *m) +{ + return msg_bits(m, 0, 18, 1); +} + +static inline void msg_set_ack_required(struct tipc_msg *m, u32 d) +{ + msg_set_bits(m, 0, 18, 1, d); +} + static inline bool msg_is_rcast(struct tipc_msg *m) { return msg_bits(m, 0, 18, 0x1); @@ -1026,6 +1036,20 @@ static inline bool msg_is_reset(struct tipc_msg *hdr) return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG); } +/* Word 13 + */ +static inline void msg_set_peer_net_hash(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 13, n); +} + +static inline u32 msg_peer_net_hash(struct tipc_msg *m) +{ + return msg_word(m, 13); +} + +/* Word 14 + */ static inline u32 msg_sugg_node_addr(struct tipc_msg *m) { return msg_word(m, 14); @@ -1065,6 +1089,8 @@ int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, int pktmax, struct sk_buff_head *frags); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); +int tipc_msg_append(struct tipc_msg *hdr, struct msghdr *m, int dlen, + int mss, struct sk_buff_head *txq); bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); bool tipc_msg_assemble(struct sk_buff_head *list); bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq); diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 836e629e8f4a..5feaf3b67380 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -146,7 +146,7 @@ static void named_distribute(struct net *net, struct sk_buff_head *list, struct publication *publ; struct sk_buff *skb = NULL; struct distr_item *item = NULL; - u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) / + u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0, false) - INT_H_SIZE) / ITEM_SIZE) * ITEM_SIZE; u32 msg_rem = msg_dsz; diff --git a/net/tipc/node.c b/net/tipc/node.c index f2e3cf70c922..4b60928049ea 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -126,6 +126,8 @@ struct tipc_node { struct timer_list timer; struct rcu_head rcu; unsigned long delete_at; + struct net *peer_net; + u32 peer_hash_mix; }; /* Node FSM states and events: @@ -184,7 +186,7 @@ static struct tipc_link *node_active_link(struct tipc_node *n, int sel) return n->links[bearer_id].link; } -int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) +int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel, bool connected) { struct tipc_node *n; int bearer_id; @@ -194,6 +196,14 @@ int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) if (unlikely(!n)) return mtu; + /* Allow MAX_MSG_SIZE when building connection oriented message + * if they are in the same core network + */ + if (n->peer_net && connected) { + tipc_node_put(n); + return mtu; + } + bearer_id = n->active_links[sel & 1]; if (likely(bearer_id != INVALID_BEARER_ID)) mtu = n->links[bearer_id].mtu; @@ -360,8 +370,37 @@ static void tipc_node_write_unlock(struct tipc_node *n) } } +static void tipc_node_assign_peer_net(struct tipc_node *n, u32 hash_mixes) +{ + int net_id = tipc_netid(n->net); + struct tipc_net *tn_peer; + struct net *tmp; + u32 hash_chk; + + if (n->peer_net) + return; + + for_each_net_rcu(tmp) { + tn_peer = tipc_net(tmp); + if (!tn_peer) + continue; + /* Integrity checking whether node exists in namespace or not */ + if (tn_peer->net_id != net_id) + continue; + if (memcmp(n->peer_id, tn_peer->node_id, NODE_ID_LEN)) + continue; + hash_chk = tipc_net_hash_mixes(tmp, tn_peer->random); + if (hash_mixes ^ hash_chk) + continue; + n->peer_net = tmp; + n->peer_hash_mix = hash_mixes; + break; + } +} + static struct tipc_node *tipc_node_create(struct net *net, u32 addr, - u8 *peer_id, u16 capabilities) + u8 *peer_id, u16 capabilities, + u32 signature, u32 hash_mixes) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *n, *temp_node; @@ -372,6 +411,8 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, spin_lock_bh(&tn->node_list_lock); n = tipc_node_find(net, addr); if (n) { + if (n->peer_hash_mix ^ hash_mixes) + tipc_node_assign_peer_net(n, hash_mixes); if (n->capabilities == capabilities) goto exit; /* Same node may come back with new capabilities */ @@ -389,6 +430,7 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, list_for_each_entry_rcu(temp_node, &tn->node_list, list) { tn->capabilities &= temp_node->capabilities; } + goto exit; } n = kzalloc(sizeof(*n), GFP_ATOMIC); @@ -399,6 +441,10 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, n->addr = addr; memcpy(&n->peer_id, peer_id, 16); n->net = net; + n->peer_net = NULL; + n->peer_hash_mix = 0; + /* Assign kernel local namespace if exists */ + tipc_node_assign_peer_net(n, hash_mixes); n->capabilities = capabilities; kref_init(&n->kref); rwlock_init(&n->lock); @@ -426,6 +472,10 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, tipc_bc_sndlink(net), &n->bc_entry.link)) { pr_warn("Broadcast rcv link creation failed, no memory\n"); + if (n->peer_net) { + n->peer_net = NULL; + n->peer_hash_mix = 0; + } kfree(n); n = NULL; goto exit; @@ -979,7 +1029,7 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) void tipc_node_check_dest(struct net *net, u32 addr, u8 *peer_id, struct tipc_bearer *b, - u16 capabilities, u32 signature, + u16 capabilities, u32 signature, u32 hash_mixes, struct tipc_media_addr *maddr, bool *respond, bool *dupl_addr) { @@ -998,7 +1048,8 @@ void tipc_node_check_dest(struct net *net, u32 addr, *dupl_addr = false; *respond = false; - n = tipc_node_create(net, addr, peer_id, capabilities); + n = tipc_node_create(net, addr, peer_id, capabilities, signature, + hash_mixes); if (!n) return; @@ -1343,6 +1394,10 @@ static void node_lost_contact(struct tipc_node *n, /* Notify publications from this node */ n->action_flags |= TIPC_NOTIFY_NODE_DOWN; + if (n->peer_net) { + n->peer_net = NULL; + n->peer_hash_mix = 0; + } /* Notify sockets connected to node */ list_for_each_entry_safe(conn, safe, conns, list) { skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, @@ -1424,6 +1479,56 @@ msg_full: return -EMSGSIZE; } +static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list) +{ + struct tipc_msg *hdr = buf_msg(skb_peek(list)); + struct sk_buff_head inputq; + + switch (msg_user(hdr)) { + case TIPC_LOW_IMPORTANCE: + case TIPC_MEDIUM_IMPORTANCE: + case TIPC_HIGH_IMPORTANCE: + case TIPC_CRITICAL_IMPORTANCE: + if (msg_connected(hdr) || msg_named(hdr)) { + tipc_loopback_trace(peer_net, list); + spin_lock_init(&list->lock); + tipc_sk_rcv(peer_net, list); + return; + } + if (msg_mcast(hdr)) { + tipc_loopback_trace(peer_net, list); + skb_queue_head_init(&inputq); + tipc_sk_mcast_rcv(peer_net, list, &inputq); + __skb_queue_purge(list); + skb_queue_purge(&inputq); + return; + } + return; + case MSG_FRAGMENTER: + if (tipc_msg_assemble(list)) { + tipc_loopback_trace(peer_net, list); + skb_queue_head_init(&inputq); + tipc_sk_mcast_rcv(peer_net, list, &inputq); + __skb_queue_purge(list); + skb_queue_purge(&inputq); + } + return; + case GROUP_PROTOCOL: + case CONN_MANAGER: + tipc_loopback_trace(peer_net, list); + spin_lock_init(&list->lock); + tipc_sk_rcv(peer_net, list); + return; + case LINK_PROTOCOL: + case NAME_DISTRIBUTOR: + case TUNNEL_PROTOCOL: + case BCAST_PROTOCOL: + return; + default: + return; + }; +} + /** * tipc_node_xmit() is the general link level function for message sending * @net: the applicable net namespace @@ -1439,6 +1544,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, struct tipc_link_entry *le = NULL; struct tipc_node *n; struct sk_buff_head xmitq; + bool node_up = false; int bearer_id; int rc; @@ -1456,6 +1562,17 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, } tipc_node_read_lock(n); + node_up = node_is_up(n); + if (node_up && n->peer_net && check_net(n->peer_net)) { + /* xmit inner linux container */ + tipc_lxc_xmit(n->peer_net, list); + if (likely(skb_queue_empty(list))) { + tipc_node_read_unlock(n); + tipc_node_put(n); + return 0; + } + } + bearer_id = n->active_links[selector & 1]; if (unlikely(bearer_id == INVALID_BEARER_ID)) { tipc_node_read_unlock(n); @@ -2587,3 +2704,33 @@ int tipc_node_dump(struct tipc_node *n, bool more, char *buf) return i; } + +void tipc_node_pre_cleanup_net(struct net *exit_net) +{ + struct tipc_node *n; + struct tipc_net *tn; + struct net *tmp; + + rcu_read_lock(); + for_each_net_rcu(tmp) { + if (tmp == exit_net) + continue; + tn = tipc_net(tmp); + if (!tn) + continue; + spin_lock_bh(&tn->node_list_lock); + list_for_each_entry_rcu(n, &tn->node_list, list) { + if (!n->peer_net) + continue; + if (n->peer_net != exit_net) + continue; + tipc_node_write_lock(n); + n->peer_net = NULL; + n->peer_hash_mix = 0; + tipc_node_write_unlock_fast(n); + break; + } + spin_unlock_bh(&tn->node_list_lock); + } + rcu_read_unlock(); +} diff --git a/net/tipc/node.h b/net/tipc/node.h index 291d0ecd4101..c39cd861c07d 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -54,7 +54,8 @@ enum { TIPC_LINK_PROTO_SEQNO = (1 << 6), TIPC_MCAST_RBCTL = (1 << 7), TIPC_GAP_ACK_BLOCK = (1 << 8), - TIPC_TUNNEL_ENHANCED = (1 << 9) + TIPC_TUNNEL_ENHANCED = (1 << 9), + TIPC_NAGLE = (1 << 10) }; #define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \ @@ -66,7 +67,9 @@ enum { TIPC_LINK_PROTO_SEQNO | \ TIPC_MCAST_RBCTL | \ TIPC_GAP_ACK_BLOCK | \ - TIPC_TUNNEL_ENHANCED) + TIPC_TUNNEL_ENHANCED | \ + TIPC_NAGLE) + #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); @@ -75,7 +78,7 @@ u32 tipc_node_get_addr(struct tipc_node *node); u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr); void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128, struct tipc_bearer *bearer, - u16 capabilities, u32 signature, + u16 capabilities, u32 signature, u32 hash_mixes, struct tipc_media_addr *maddr, bool *respond, bool *dupl_addr); void tipc_node_delete_links(struct net *net, int bearer_id); @@ -92,7 +95,7 @@ void tipc_node_unsubscribe(struct net *net, struct list_head *subscr, u32 addr); void tipc_node_broadcast(struct net *net, struct sk_buff *skb); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); -int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel); +int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel, bool connected); bool tipc_node_is_up(struct net *net, u32 addr); u16 tipc_node_get_capabilities(struct net *net, u32 addr); int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); @@ -107,4 +110,5 @@ int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb, struct netlink_callback *cb); +void tipc_node_pre_cleanup_net(struct net *exit_net); #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 35e32ffc2b90..5d7859aac78e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -75,6 +75,7 @@ struct sockaddr_pair { * @conn_instance: TIPC instance used when connection was established * @published: non-zero if port has one or more associated names * @max_pkt: maximum packet size "hint" used when building messages sent by port + * @maxnagle: maximum size of msg which can be subject to nagle * @portid: unique port identity in TIPC socket hash table * @phdr: preformatted message header used when sending messages * #cong_links: list of congested links @@ -97,6 +98,7 @@ struct tipc_sock { u32 conn_instance; int published; u32 max_pkt; + u32 maxnagle; u32 portid; struct tipc_msg phdr; struct list_head cong_links; @@ -116,6 +118,10 @@ struct tipc_sock { struct tipc_mc_method mc_method; struct rcu_head rcu; struct tipc_group *group; + u32 oneway; + u16 snd_backlog; + bool expect_ack; + bool nodelay; bool group_is_open; }; @@ -137,6 +143,7 @@ static int tipc_sk_insert(struct tipc_sock *tsk); static void tipc_sk_remove(struct tipc_sock *tsk); static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz); static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); +static void tipc_sk_push_backlog(struct tipc_sock *tsk); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -227,6 +234,26 @@ static u16 tsk_inc(struct tipc_sock *tsk, int msglen) return 1; } +/* tsk_set_nagle - enable/disable nagle property by manipulating maxnagle + */ +static void tsk_set_nagle(struct tipc_sock *tsk) +{ + struct sock *sk = &tsk->sk; + + tsk->maxnagle = 0; + if (sk->sk_type != SOCK_STREAM) + return; + if (tsk->nodelay) + return; + if (!(tsk->peer_caps & TIPC_NAGLE)) + return; + /* Limit node local buffer size to avoid receive queue overflow */ + if (tsk->max_pkt == MAX_MSG_SIZE) + tsk->maxnagle = 1500; + else + tsk->maxnagle = tsk->max_pkt; +} + /** * tsk_advance_rx_queue - discard first buffer in socket receive queue * @@ -446,6 +473,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk = tipc_sk(sk); tsk->max_pkt = MAX_PKT_DEFAULT; + tsk->maxnagle = 0; INIT_LIST_HEAD(&tsk->publications); INIT_LIST_HEAD(&tsk->cong_links); msg = &tsk->phdr; @@ -512,8 +540,12 @@ static void __tipc_shutdown(struct socket *sock, int error) tipc_wait_for_cond(sock, &timeout, (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))); - /* Remove any pending SYN message */ - __skb_queue_purge(&sk->sk_write_queue); + /* Push out unsent messages or remove if pending SYN */ + skb = skb_peek(&sk->sk_write_queue); + if (skb && !msg_is_syn(buf_msg(skb))) + tipc_sk_push_backlog(tsk); + else + __skb_queue_purge(&sk->sk_write_queue); /* Reject all unreceived messages, except on an active connection * (which disconnects locally & sends a 'FIN+' to peer). @@ -740,7 +772,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, /* fall through */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) revents |= EPOLLIN | EPOLLRDNORM; break; case TIPC_OPEN: @@ -748,7 +780,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, revents |= EPOLLOUT; if (!tipc_sk_type_connectionless(sk)) break; - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) break; revents |= EPOLLIN | EPOLLRDNORM; break; @@ -854,7 +886,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, /* Build message as chain of buffers */ __skb_queue_head_init(&pkts); - mtu = tipc_node_get_mtu(net, dnode, tsk->portid); + mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) return rc; @@ -1208,6 +1240,27 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, tipc_sk_rcv(net, inputq); } +/* tipc_sk_push_backlog(): send accumulated buffers in socket write queue + * when socket is in Nagle mode + */ +static void tipc_sk_push_backlog(struct tipc_sock *tsk) +{ + struct sk_buff_head *txq = &tsk->sk.sk_write_queue; + struct net *net = sock_net(&tsk->sk); + u32 dnode = tsk_peer_node(tsk); + int rc; + + if (skb_queue_empty(txq) || tsk->cong_link_cnt) + return; + + tsk->snt_unacked += tsk->snd_backlog; + tsk->snd_backlog = 0; + tsk->expect_ack = true; + rc = tipc_node_xmit(net, txq, dnode, tsk->portid); + if (rc == -ELINKCONG) + tsk->cong_link_cnt = 1; +} + /** * tipc_sk_conn_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket @@ -1221,7 +1274,7 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, u32 onode = tsk_own_node(tsk); struct sock *sk = &tsk->sk; int mtyp = msg_type(hdr); - bool conn_cong; + bool was_cong; /* Ignore if connection cannot be validated: */ if (!tsk_peer_msg(tsk, hdr)) { @@ -1254,11 +1307,13 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, __skb_queue_tail(xmitq, skb); return; } else if (mtyp == CONN_ACK) { - conn_cong = tsk_conn_cong(tsk); + was_cong = tsk_conn_cong(tsk); + tsk->expect_ack = false; + tipc_sk_push_backlog(tsk); tsk->snt_unacked -= msg_conn_ack(hdr); if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL) tsk->snd_win = msg_adv_win(hdr); - if (conn_cong) + if (was_cong && !tsk_conn_cong(tsk)) sk->sk_write_space(sk); } else if (mtyp != CONN_PROBE_REPLY) { pr_warn("Received unknown CONN_PROTO msg\n"); @@ -1388,7 +1443,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return rc; __skb_queue_head_init(&pkts); - mtu = tipc_node_get_mtu(net, dnode, tsk->portid); + mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) return rc; @@ -1437,15 +1492,15 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); + struct sk_buff_head *txq = &sk->sk_write_queue; struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = &tsk->phdr; struct net *net = sock_net(sk); - struct sk_buff_head pkts; u32 dnode = tsk_peer_node(tsk); + int maxnagle = tsk->maxnagle; + int maxpkt = tsk->max_pkt; int send, sent = 0; - int rc = 0; - - __skb_queue_head_init(&pkts); + int blocks, rc = 0; if (unlikely(dlen > INT_MAX)) return -EMSGSIZE; @@ -1467,21 +1522,35 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) tipc_sk_connected(sk))); if (unlikely(rc)) break; - send = min_t(size_t, dlen - sent, TIPC_MAX_USER_MSG_SIZE); - rc = tipc_msg_build(hdr, m, sent, send, tsk->max_pkt, &pkts); - if (unlikely(rc != send)) - break; - - trace_tipc_sk_sendstream(sk, skb_peek(&pkts), + blocks = tsk->snd_backlog; + if (tsk->oneway++ >= 4 && send <= maxnagle) { + rc = tipc_msg_append(hdr, m, send, maxnagle, txq); + if (unlikely(rc < 0)) + break; + blocks += rc; + if (blocks <= 64 && tsk->expect_ack) { + tsk->snd_backlog = blocks; + sent += send; + break; + } + tsk->expect_ack = true; + } else { + rc = tipc_msg_build(hdr, m, sent, send, maxpkt, txq); + if (unlikely(rc != send)) + break; + blocks += tsk_inc(tsk, send + MIN_H_SIZE); + } + trace_tipc_sk_sendstream(sk, skb_peek(txq), TIPC_DUMP_SK_SNDQ, " "); - rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); + rc = tipc_node_xmit(net, txq, dnode, tsk->portid); if (unlikely(rc == -ELINKCONG)) { tsk->cong_link_cnt = 1; rc = 0; } if (likely(!rc)) { - tsk->snt_unacked += tsk_inc(tsk, send + MIN_H_SIZE); + tsk->snt_unacked += blocks; + tsk->snd_backlog = 0; sent += send; } } while (sent < dlen && !rc); @@ -1526,8 +1595,9 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV); tipc_set_sk_state(sk, TIPC_ESTABLISHED); tipc_node_add_conn(net, peer_node, tsk->portid, peer_port); - tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid); + tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid, true); tsk->peer_caps = tipc_node_get_capabilities(net, peer_node); + tsk_set_nagle(tsk); __skb_queue_purge(&sk->sk_write_queue); if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL) return; @@ -1848,6 +1918,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, bool peek = flags & MSG_PEEK; int offset, required, copy, copied = 0; int hlen, dlen, err, rc; + bool ack = false; long timeout; /* Catch invalid receive attempts */ @@ -1892,6 +1963,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Copy data if msg ok, otherwise return error/partial data */ if (likely(!err)) { + ack = msg_ack_required(hdr); offset = skb_cb->bytes_read; copy = min_t(int, dlen - offset, buflen - copied); rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); @@ -1919,7 +1991,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); - if (unlikely(tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)) + if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); /* Exit if all requested data or FIN/error received */ @@ -1990,6 +2062,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, smp_wmb(); tsk->cong_link_cnt--; wakeup = true; + tipc_sk_push_backlog(tsk); break; case GROUP_PROTOCOL: tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq); @@ -2029,6 +2102,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) if (unlikely(msg_mcast(hdr))) return false; + tsk->oneway = 0; switch (sk->sk_state) { case TIPC_CONNECTING: @@ -2074,6 +2148,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) return true; return false; case TIPC_ESTABLISHED: + if (!skb_queue_empty(&sk->sk_write_queue)) + tipc_sk_push_backlog(tsk); /* Accept only connection-based messages sent by peer */ if (likely(con_msg && !err && pport == oport && pnode == onode)) return true; @@ -2959,6 +3035,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, case TIPC_SRC_DROPPABLE: case TIPC_DEST_DROPPABLE: case TIPC_CONN_TIMEOUT: + case TIPC_NODELAY: if (ol < sizeof(value)) return -EINVAL; if (get_user(value, (u32 __user *)ov)) @@ -3007,6 +3084,10 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, case TIPC_GROUP_LEAVE: res = tipc_sk_leave(tsk); break; + case TIPC_NODELAY: + tsk->nodelay = !!value; + tsk_set_nagle(tsk); + break; default: res = -EINVAL; } |