diff options
Diffstat (limited to 'net/tipc')
-rw-r--r-- | net/tipc/bcast.c | 39 | ||||
-rw-r--r-- | net/tipc/core.c | 6 | ||||
-rw-r--r-- | net/tipc/discover.c | 8 | ||||
-rw-r--r-- | net/tipc/eth_media.c | 48 | ||||
-rw-r--r-- | net/tipc/link.c | 25 | ||||
-rw-r--r-- | net/tipc/name_table.c | 48 | ||||
-rw-r--r-- | net/tipc/net.c | 1 | ||||
-rw-r--r-- | net/tipc/node.c | 22 | ||||
-rw-r--r-- | net/tipc/node.h | 2 | ||||
-rw-r--r-- | net/tipc/port.c | 19 | ||||
-rw-r--r-- | net/tipc/socket.c | 81 |
11 files changed, 187 insertions, 112 deletions
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a008c66..b11248c 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -143,6 +143,19 @@ static void bcbuf_decr_acks(struct sk_buff *buf) } +static void bclink_set_last_sent(void) +{ + if (bcl->next_out) + bcl->fsm_msg_cnt = mod(buf_seqno(bcl->next_out) - 1); + else + bcl->fsm_msg_cnt = mod(bcl->next_out_no - 1); +} + +u32 tipc_bclink_get_last_sent(void) +{ + return bcl->fsm_msg_cnt; +} + /** * bclink_set_gap - set gap according to contents of current deferred pkt queue * @@ -237,8 +250,10 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) /* Try resolving broadcast link congestion, if necessary */ - if (unlikely(bcl->next_out)) + if (unlikely(bcl->next_out)) { tipc_link_push_queue(bcl); + bclink_set_last_sent(); + } if (unlikely(released && !list_empty(&bcl->waiting_ports))) tipc_link_wakeup_ports(bcl, 0); spin_unlock_bh(&bc_lock); @@ -395,7 +410,7 @@ int tipc_bclink_send_msg(struct sk_buff *buf) if (unlikely(res == -ELINKCONG)) buf_discard(buf); else - bcl->stats.sent_info++; + bclink_set_last_sent(); if (bcl->out_queue_size > bcl->stats.max_queue_sz) bcl->stats.max_queue_sz = bcl->out_queue_size; @@ -529,15 +544,6 @@ receive: tipc_node_unlock(node); } -u32 tipc_bclink_get_last_sent(void) -{ - u32 last_sent = mod(bcl->next_out_no - 1); - - if (bcl->next_out) - last_sent = mod(buf_seqno(bcl->next_out) - 1); - return last_sent; -} - u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) { return (n_ptr->bclink.supported && @@ -570,6 +576,7 @@ static int tipc_bcbearer_send(struct sk_buff *buf, msg = buf_msg(buf); msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tipc_net_id); + bcl->stats.sent_info++; } /* Send buffer over bearers until all targets reached */ @@ -609,11 +616,13 @@ static int tipc_bcbearer_send(struct sk_buff *buf, bcbearer->remains = bcbearer->remains_new; } - /* Unable to reach all targets */ + /* + * Unable to reach all targets (indicate success, since currently + * there isn't code in place to properly block & unblock the + * pseudo-bearer used by the broadcast link) + */ - bcbearer->bearer.publ.blocked = 1; - bcl->stats.bearer_congs++; - return 1; + return TIPC_OK; } /** diff --git a/net/tipc/core.c b/net/tipc/core.c index 6964681..466b861 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -169,6 +169,7 @@ void tipc_core_stop(void) tipc_nametbl_stop(); tipc_ref_table_stop(); tipc_socket_stop(); + tipc_log_resize(0); } /** @@ -203,7 +204,9 @@ static int __init tipc_init(void) { int res; - tipc_log_resize(CONFIG_TIPC_LOG); + if (tipc_log_resize(CONFIG_TIPC_LOG) != 0) + warn("Unable to create log buffer\n"); + info("Activated (version " TIPC_MOD_VER " compiled " __DATE__ " " __TIME__ ")\n"); @@ -230,7 +233,6 @@ static void __exit tipc_exit(void) tipc_core_stop_net(); tipc_core_stop(); info("Deactivated\n"); - tipc_log_resize(0); } module_init(tipc_init); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index fc1fcf5..f28d1ae 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -203,6 +203,14 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) return; } spin_lock_bh(&n_ptr->lock); + + /* Don't talk to neighbor during cleanup after last session */ + + if (n_ptr->cleanup_required) { + spin_unlock_bh(&n_ptr->lock); + return; + } + link = n_ptr->links[b_ptr->identity]; if (!link) { dbg("creating link\n"); diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 6230d16..6e988ba 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -72,17 +72,26 @@ static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, { struct sk_buff *clone; struct net_device *dev; + int delta; clone = skb_clone(buf, GFP_ATOMIC); - if (clone) { - skb_reset_network_header(clone); - dev = ((struct eth_bearer *)(tb_ptr->usr_handle))->dev; - clone->dev = dev; - dev_hard_header(clone, dev, ETH_P_TIPC, - &dest->dev_addr.eth_addr, - dev->dev_addr, clone->len); - dev_queue_xmit(clone); + if (!clone) + return 0; + + dev = ((struct eth_bearer *)(tb_ptr->usr_handle))->dev; + delta = dev->hard_header_len - skb_headroom(buf); + + if ((delta > 0) && + pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(clone); + return 0; } + + skb_reset_network_header(clone); + clone->dev = dev; + dev_hard_header(clone, dev, ETH_P_TIPC, &dest->dev_addr.eth_addr, + dev->dev_addr, clone->len); + dev_queue_xmit(clone); return 0; } @@ -92,15 +101,12 @@ static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, * Accept only packets explicitly sent to this node, or broadcast packets; * ignores packets sent using Ethernet multicast, and traffic sent to other * nodes (which can happen if interface is running in promiscuous mode). - * Routine truncates any Ethernet padding/CRC appended to the message, - * and ensures message size matches actual length */ static int recv_msg(struct sk_buff *buf, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct eth_bearer *eb_ptr = (struct eth_bearer *)pt->af_packet_priv; - u32 size; if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(buf); @@ -109,13 +115,9 @@ static int recv_msg(struct sk_buff *buf, struct net_device *dev, if (likely(eb_ptr->bearer)) { if (likely(buf->pkt_type <= PACKET_BROADCAST)) { - size = msg_size((struct tipc_msg *)buf->data); - skb_trim(buf, size); - if (likely(buf->len == size)) { - buf->next = NULL; - tipc_recv_msg(buf, eb_ptr->bearer); - return 0; - } + buf->next = NULL; + tipc_recv_msg(buf, eb_ptr->bearer); + return 0; } } kfree_skb(buf); @@ -133,6 +135,16 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) struct eth_bearer *eb_ptr = ð_bearers[0]; struct eth_bearer *stop = ð_bearers[MAX_ETH_BEARERS]; char *driver_name = strchr((const char *)tb_ptr->name, ':') + 1; + int pending_dev = 0; + + /* Find unused Ethernet bearer structure */ + + while (eb_ptr->dev) { + if (!eb_ptr->bearer) + pending_dev++; + if (++eb_ptr == stop) + return pending_dev ? -EAGAIN : -EDQUOT; + } /* Find device with specified name */ diff --git a/net/tipc/link.c b/net/tipc/link.c index a3616b9..a6a3102 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1802,6 +1802,15 @@ static int link_recv_buf_validate(struct sk_buff *buf) return pskb_may_pull(buf, hdr_size); } +/** + * tipc_recv_msg - process TIPC messages arriving from off-node + * @head: pointer to message buffer chain + * @tb_ptr: pointer to bearer message arrived on + * + * Invoked with no locks held. Bearer pointer must point to a valid bearer + * structure (i.e. cannot be NULL), but bearer can be inactive. + */ + void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *tb_ptr) { read_lock_bh(&tipc_net_lock); @@ -1819,6 +1828,11 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *tb_ptr) head = head->next; + /* Ensure bearer is still enabled */ + + if (unlikely(!b_ptr->active)) + goto cont; + /* Ensure message is well-formed */ if (unlikely(!link_recv_buf_validate(buf))) @@ -1855,13 +1869,22 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *tb_ptr) goto cont; } - /* Locate unicast link endpoint that should handle message */ + /* Locate neighboring node that sent message */ n_ptr = tipc_node_find(msg_prevnode(msg)); if (unlikely(!n_ptr)) goto cont; tipc_node_lock(n_ptr); + /* Don't talk to neighbor during cleanup after last session */ + + if (n_ptr->cleanup_required) { + tipc_node_unlock(n_ptr); + goto cont; + } + + /* Locate unicast link endpoint that should handle message */ + l_ptr = n_ptr->links[b_ptr->identity]; if (unlikely(!l_ptr)) { tipc_node_unlock(n_ptr); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 8ba7962..c13c2c7 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -613,8 +613,7 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, } /* - * tipc_nametbl_translate(): Translate tipc_name -> tipc_portid. - * Very time-critical. + * tipc_nametbl_translate - translate name to port id * * Note: on entry 'destnode' is the search domain used during translation; * on exit it passes back the node address of the matching port (if any) @@ -685,7 +684,6 @@ found: } spin_unlock_bh(&seq->lock); not_found: - *destnode = 0; read_unlock_bh(&tipc_nametbl_lock); return 0; } @@ -877,7 +875,7 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, u32 index) { char portIdStr[27]; - char *scopeStr; + const char *scope_str[] = {"", " zone", " cluster", " node"}; struct publication *publ = sseq->zone_list; tipc_printf(buf, "%-10u %-10u ", sseq->lower, sseq->upper); @@ -893,15 +891,8 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, tipc_node(publ->node), publ->ref); tipc_printf(buf, "%-26s ", portIdStr); if (depth > 3) { - if (publ->node != tipc_own_addr) - scopeStr = ""; - else if (publ->scope == TIPC_NODE_SCOPE) - scopeStr = "node"; - else if (publ->scope == TIPC_CLUSTER_SCOPE) - scopeStr = "cluster"; - else - scopeStr = "zone"; - tipc_printf(buf, "%-10u %s", publ->key, scopeStr); + tipc_printf(buf, "%-10u %s", publ->key, + scope_str[publ->scope]); } publ = publ->zone_list_next; @@ -951,24 +942,19 @@ static void nameseq_list(struct name_seq *seq, struct print_buf *buf, u32 depth, static void nametbl_header(struct print_buf *buf, u32 depth) { - tipc_printf(buf, "Type "); - - if (depth > 1) - tipc_printf(buf, "Lower Upper "); - if (depth > 2) - tipc_printf(buf, "Port Identity "); - if (depth > 3) - tipc_printf(buf, "Publication"); - - tipc_printf(buf, "\n-----------"); - - if (depth > 1) - tipc_printf(buf, "--------------------- "); - if (depth > 2) - tipc_printf(buf, "-------------------------- "); - if (depth > 3) - tipc_printf(buf, "------------------"); - + const char *header[] = { + "Type ", + "Lower Upper ", + "Port Identity ", + "Publication Scope" + }; + + int i; + + if (depth > 4) + depth = 4; + for (i = 0; i < depth; i++) + tipc_printf(buf, header[i]); tipc_printf(buf, "\n"); } diff --git a/net/tipc/net.c b/net/tipc/net.c index f61b769..7e05af4 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -248,6 +248,7 @@ void tipc_net_route_msg(struct sk_buff *buf) /* Handle message for another node */ msg_dbg(msg, "NET>SEND>: "); + skb_trim(buf, msg_size(msg)); tipc_link_send(buf, dnode, msg_link_selector(msg)); } diff --git a/net/tipc/node.c b/net/tipc/node.c index b634942..b702c7b 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -237,8 +237,7 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct link *l_ptr) int tipc_node_has_active_links(struct tipc_node *n_ptr) { - return (n_ptr && - ((n_ptr->active_links[0]) || (n_ptr->active_links[1]))); + return n_ptr->active_links[0] != NULL; } int tipc_node_has_redundant_links(struct tipc_node *n_ptr) @@ -384,6 +383,20 @@ static void node_established_contact(struct tipc_node *n_ptr) tipc_highest_allowed_slave); } +static void node_cleanup_finished(unsigned long node_addr) +{ + struct tipc_node *n_ptr; + + read_lock_bh(&tipc_net_lock); + n_ptr = tipc_node_find(node_addr); + if (n_ptr) { + tipc_node_lock(n_ptr); + n_ptr->cleanup_required = 0; + tipc_node_unlock(n_ptr); + } + read_unlock_bh(&tipc_net_lock); +} + static void node_lost_contact(struct tipc_node *n_ptr) { struct cluster *c_ptr; @@ -458,6 +471,11 @@ static void node_lost_contact(struct tipc_node *n_ptr) tipc_k_signal((Handler)ns->handle_node_down, (unsigned long)ns->usr_handle); } + + /* Prevent re-contact with node until all cleanup is done */ + + n_ptr->cleanup_required = 1; + tipc_k_signal((Handler)node_cleanup_finished, n_ptr->addr); } /** diff --git a/net/tipc/node.h b/net/tipc/node.h index 6f990da..45f3db3 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -52,6 +52,7 @@ * @active_links: pointers to active links to node * @links: pointers to all links to node * @working_links: number of working links to node (both active and standby) + * @cleanup_required: non-zero if cleaning up after a prior loss of contact * @link_cnt: number of links to node * @permit_changeover: non-zero if node has redundant links to this system * @routers: bitmap (used for multicluster communication) @@ -78,6 +79,7 @@ struct tipc_node { struct link *links[MAX_BEARERS]; int link_cnt; int working_links; + int cleanup_required; int permit_changeover; u32 routers[512/32]; int last_router; diff --git a/net/tipc/port.c b/net/tipc/port.c index 0737680..d760336 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -588,19 +588,10 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) if (!p_ptr) { err = TIPC_ERR_NO_PORT; } else if (p_ptr->publ.connected) { - if (port_peernode(p_ptr) != msg_orignode(msg)) + if ((port_peernode(p_ptr) != msg_orignode(msg)) || + (port_peerport(p_ptr) != msg_origport(msg))) { err = TIPC_ERR_NO_PORT; - if (port_peerport(p_ptr) != msg_origport(msg)) - err = TIPC_ERR_NO_PORT; - if (!err && msg_routed(msg)) { - u32 seqno = msg_transp_seqno(msg); - u32 myno = ++p_ptr->last_in_seqno; - if (seqno != myno) { - err = TIPC_ERR_NO_PORT; - abort_buf = port_build_self_abort_msg(p_ptr, err); - } - } - if (msg_type(msg) == CONN_ACK) { + } else if (msg_type(msg) == CONN_ACK) { int wakeup = tipc_port_congested(p_ptr) && p_ptr->publ.congested && p_ptr->wakeup; @@ -1473,7 +1464,7 @@ int tipc_forward2name(u32 ref, msg_set_destnode(msg, destnode); msg_set_destport(msg, destport); - if (likely(destport || destnode)) { + if (likely(destport)) { p_ptr->sent++; if (likely(destnode == tipc_own_addr)) return tipc_port_recv_sections(p_ptr, num_sect, msg_sect); @@ -1551,7 +1542,7 @@ int tipc_forward_buf2name(u32 ref, skb_push(buf, LONG_H_SIZE); skb_copy_to_linear_data(buf, msg, LONG_H_SIZE); msg_dbg(buf_msg(buf),"PREP:"); - if (likely(destport || destnode)) { + if (likely(destport)) { p_ptr->sent++; if (destnode == tipc_own_addr) return tipc_port_recv_msg(buf); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 66e889b..f7ac94d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -64,6 +64,7 @@ struct tipc_sock { struct sock sk; struct tipc_port *p; struct tipc_portid peer_name; + long conn_timeout; }; #define tipc_sk(sk) ((struct tipc_sock *)(sk)) @@ -240,9 +241,9 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, sock->state = state; sock_init_data(sock, sk); - sk->sk_rcvtimeo = msecs_to_jiffies(CONN_TIMEOUT_DEFAULT); sk->sk_backlog_rcv = backlog_rcv; tipc_sk(sk)->p = tp_ptr; + tipc_sk(sk)->conn_timeout = msecs_to_jiffies(CONN_TIMEOUT_DEFAULT); spin_unlock_bh(tp_ptr->lock); @@ -429,36 +430,55 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, * to handle any preventable race conditions, so TIPC will do the same ... * * TIPC sets the returned events as follows: - * a) POLLRDNORM and POLLIN are set if the socket's receive queue is non-empty - * or if a connection-oriented socket is does not have an active connection - * (i.e. a read operation will not block). - * b) POLLOUT is set except when a socket's connection has been terminated - * (i.e. a write operation will not block). - * c) POLLHUP is set when a socket's connection has been terminated. - * - * IMPORTANT: The fact that a read or write operation will not block does NOT - * imply that the operation will succeed! + * + * socket state flags set + * ------------ --------- + * unconnected no read flags + * no write flags + * + * connecting POLLIN/POLLRDNORM if ACK/NACK in rx queue + * no write flags + * + * connected POLLIN/POLLRDNORM if data in rx queue + * POLLOUT if port is not congested + * + * disconnecting POLLIN/POLLRDNORM/POLLHUP + * no write flags + * + * listening POLLIN if SYN in rx queue + * no write flags + * + * ready POLLIN/POLLRDNORM if data in rx queue + * [connectionless] POLLOUT (since port cannot be congested) + * + * IMPORTANT: The fact that a read or write operation is indicated does NOT + * imply that the operation will succeed, merely that it should be performed + * and will not block. */ static unsigned int poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; - u32 mask; + u32 mask = 0; poll_wait(file, sk_sleep(sk), wait); - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sock->state == SS_UNCONNECTED) || - (sock->state == SS_DISCONNECTING)) - mask = (POLLRDNORM | POLLIN); - else - mask = 0; - - if (sock->state == SS_DISCONNECTING) - mask |= POLLHUP; - else - mask |= POLLOUT; + switch ((int)sock->state) { + case SS_READY: + case SS_CONNECTED: + if (!tipc_sk_port(sk)->congested) + mask |= POLLOUT; + /* fall thru' */ + case SS_CONNECTING: + case SS_LISTENING: + if (!skb_queue_empty(&sk->sk_receive_queue)) + mask |= (POLLIN | POLLRDNORM); + break; + case SS_DISCONNECTING: + mask = (POLLIN | POLLRDNORM | POLLHUP); + break; + } return mask; } @@ -1026,9 +1046,8 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, struct sk_buff *buf; struct tipc_msg *msg; unsigned int sz; - int sz_to_copy; + int sz_to_copy, target, needed; int sz_copied = 0; - int needed; char __user *crs = m->msg_iov->iov_base; unsigned char *buf_crs; u32 err; @@ -1050,6 +1069,8 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, goto exit; } + target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); + restart: /* Look for a message in receive queue; wait if necessary */ @@ -1138,7 +1159,7 @@ restart: if ((sz_copied < buf_len) && /* didn't get all requested data */ (!skb_queue_empty(&sk->sk_receive_queue) || - (flags & MSG_WAITALL)) && /* and more is ready or required */ + (sz_copied < target)) && /* and more is ready or required */ (!(flags & MSG_PEEK)) && /* and aren't just peeking at data */ (!err)) /* and haven't reached a FIN */ goto restart; @@ -1365,6 +1386,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, struct msghdr m = {NULL,}; struct sk_buff *buf; struct tipc_msg *msg; + long timeout; int res; lock_sock(sk); @@ -1379,7 +1401,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, /* For now, TIPC does not support the non-blocking form of connect() */ if (flags & O_NONBLOCK) { - res = -EWOULDBLOCK; + res = -EOPNOTSUPP; goto exit; } @@ -1425,11 +1447,12 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ + timeout = tipc_sk(sk)->conn_timeout; release_sock(sk); res = wait_event_interruptible_timeout(*sk_sleep(sk), (!skb_queue_empty(&sk->sk_receive_queue) || (sock->state != SS_CONNECTING)), - sk->sk_rcvtimeo); + timeout ? timeout : MAX_SCHEDULE_TIMEOUT); lock_sock(sk); if (res > 0) { @@ -1692,7 +1715,7 @@ static int setsockopt(struct socket *sock, res = tipc_set_portunreturnable(tport->ref, value); break; case TIPC_CONN_TIMEOUT: - sk->sk_rcvtimeo = msecs_to_jiffies(value); + tipc_sk(sk)->conn_timeout = msecs_to_jiffies(value); /* no need to set "res", since already 0 at this point */ break; default: @@ -1747,7 +1770,7 @@ static int getsockopt(struct socket *sock, res = tipc_portunreturnable(tport->ref, &value); break; case TIPC_CONN_TIMEOUT: - value = jiffies_to_msecs(sk->sk_rcvtimeo); + value = jiffies_to_msecs(tipc_sk(sk)->conn_timeout); /* no need to set "res", since already 0 at this point */ break; case TIPC_NODE_RECVQ_DEPTH: |