diff options
Diffstat (limited to 'net/tipc')
-rw-r--r-- | net/tipc/bcast.c | 6 | ||||
-rw-r--r-- | net/tipc/bearer.c | 12 | ||||
-rw-r--r-- | net/tipc/diag.c | 2 | ||||
-rw-r--r-- | net/tipc/group.c | 41 | ||||
-rw-r--r-- | net/tipc/group.h | 1 | ||||
-rw-r--r-- | net/tipc/link.c | 176 | ||||
-rw-r--r-- | net/tipc/link.h | 5 | ||||
-rw-r--r-- | net/tipc/monitor.c | 3 | ||||
-rw-r--r-- | net/tipc/msg.c | 35 | ||||
-rw-r--r-- | net/tipc/name_table.c | 12 | ||||
-rw-r--r-- | net/tipc/name_table.h | 9 | ||||
-rw-r--r-- | net/tipc/net.c | 4 | ||||
-rw-r--r-- | net/tipc/netlink.c | 2 | ||||
-rw-r--r-- | net/tipc/netlink_compat.c | 5 | ||||
-rw-r--r-- | net/tipc/node.c | 101 | ||||
-rw-r--r-- | net/tipc/node.h | 14 | ||||
-rw-r--r-- | net/tipc/socket.c | 100 | ||||
-rw-r--r-- | net/tipc/socket.h | 3 | ||||
-rw-r--r-- | net/tipc/topsrv.c | 4 |
19 files changed, 382 insertions, 153 deletions
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index f3711176be45..d8026543bf4c 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -51,12 +51,12 @@ const char tipc_bclink_name[] = "broadcast-link"; * struct tipc_bc_base - base structure for keeping broadcast send state * @link: broadcast send link structure * @inputq: data input queue; will only carry SOCK_WAKEUP messages - * @dest: array keeping number of reachable destinations per bearer + * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast * @rcast_support: indicates if all peer nodes support replicast * @rc_ratio: dest count as percentage of cluster size where send method changes - * @bc_threshold: calculated drom rc_ratio; if dests > threshold use broadcast + * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; @@ -512,7 +512,7 @@ int tipc_bcast_init(struct net *net) struct tipc_bc_base *bb = NULL; struct tipc_link *l = NULL; - bb = kzalloc(sizeof(*bb), GFP_ATOMIC); + bb = kzalloc(sizeof(*bb), GFP_KERNEL); if (!bb) goto enomem; tn->bcbase = bb; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 2dfb492a7c94..645c16052052 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -395,6 +395,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, tipc_net_init(net, node_id, 0); } if (!tipc_own_id(net)) { + dev_put(dev); pr_warn("Failed to obtain node identity\n"); return -EINVAL; } @@ -608,15 +609,18 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, switch (evt) { case NETDEV_CHANGE: - if (netif_carrier_ok(dev)) + if (netif_carrier_ok(dev) && netif_oper_up(dev)) { + test_and_set_bit_lock(0, &b->up); break; - case NETDEV_UP: - test_and_set_bit_lock(0, &b->up); - break; + } + /* fall through */ case NETDEV_GOING_DOWN: clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); break; + case NETDEV_UP: + test_and_set_bit_lock(0, &b->up); + break; case NETDEV_CHANGEMTU: if (tipc_mtu_bad(dev, 0)) { bearer_disable(net, b); diff --git a/net/tipc/diag.c b/net/tipc/diag.c index aaabb0b776dd..73137f4aeb68 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -84,7 +84,9 @@ static int tipc_sock_diag_handler_dump(struct sk_buff *skb, if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = tipc_dump_start, .dump = tipc_diag_dump, + .done = tipc_dump_done, }; netlink_dump_start(net->diag_nlsk, skb, h, &c); return 0; diff --git a/net/tipc/group.c b/net/tipc/group.c index d7a7befeddd4..e82f13cb2dc5 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -159,11 +159,6 @@ u32 tipc_group_exclude(struct tipc_group *grp) return 0; } -int tipc_group_size(struct tipc_group *grp) -{ - return grp->member_cnt; -} - struct tipc_group *tipc_group_create(struct net *net, u32 portid, struct tipc_group_req *mreq, bool *group_is_open) @@ -232,8 +227,8 @@ void tipc_group_delete(struct net *net, struct tipc_group *grp) kfree(grp); } -struct tipc_member *tipc_group_find_member(struct tipc_group *grp, - u32 node, u32 port) +static struct tipc_member *tipc_group_find_member(struct tipc_group *grp, + u32 node, u32 port) { struct rb_node *n = grp->members.rb_node; u64 nkey, key = (u64)node << 32 | port; @@ -918,3 +913,35 @@ void tipc_group_member_evt(struct tipc_group *grp, } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } + +int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) +{ + struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP); + + if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID, + grp->type) || + nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE, + grp->instance) || + nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, + grp->bc_snd_nxt)) + goto group_msg_cancel; + + if (grp->scope == TIPC_NODE_SCOPE) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE)) + goto group_msg_cancel; + + if (grp->scope == TIPC_CLUSTER_SCOPE) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE)) + goto group_msg_cancel; + + if (*grp->open) + if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN)) + goto group_msg_cancel; + + nla_nest_end(skb, group); + return 0; + +group_msg_cancel: + nla_nest_cancel(skb, group); + return -1; +} diff --git a/net/tipc/group.h b/net/tipc/group.h index 5996af6e9f1d..76b4e5a7b39d 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -72,4 +72,5 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); void tipc_group_update_member(struct tipc_member *m, int len); +int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index 695acb783969..4ed650ce6e61 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -106,7 +106,8 @@ struct tipc_stats { * @backlogq: queue for messages waiting to be sent * @snt_nxt: next sequence number to use for outbound messages * @last_retransmitted: sequence number of most recently retransmitted message - * @stale_count: # of identical retransmit requests made by peer + * @stale_cnt: counter for number of identical retransmit attempts + * @stale_limit: time when repeated identical retransmits must force link reset * @ackers: # of peers that needs to ack each packet before it can be released * @acked: # last packet acked by a certain peer. Used for broadcast. * @rcv_nxt: next sequence number to expect for inbound messages @@ -127,14 +128,17 @@ struct tipc_link { struct net *net; /* Management and link supervision data */ - u32 peer_session; - u32 session; + u16 peer_session; + u16 session; + u16 snd_nxt_state; + u16 rcv_nxt_state; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; u32 abort_limit; u32 state; u16 peer_caps; + bool in_session; bool active; u32 silent_intv_cnt; char if_name[TIPC_MAX_IF_NAME]; @@ -161,7 +165,8 @@ struct tipc_link { u16 snd_nxt; u16 last_retransm; u16 window; - u32 stale_count; + u16 stale_cnt; + unsigned long stale_limit; /* Reception */ u16 rcv_nxt; @@ -212,11 +217,6 @@ enum { */ #define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) -/* Wildcard value for link session numbers. When it is known that - * peer endpoint is down, any session number must be accepted. - */ -#define ANY_SESSION 0x10000 - /* Link FSM states: */ enum { @@ -297,11 +297,6 @@ static bool link_is_bc_rcvlink(struct tipc_link *l) return ((l->bc_rcvlink == l) && !link_is_bc_sndlink(l)); } -int tipc_link_is_active(struct tipc_link *l) -{ - return l->active; -} - void tipc_link_set_active(struct tipc_link *l, bool active) { l->active = active; @@ -337,6 +332,11 @@ char tipc_link_plane(struct tipc_link *l) return l->net_plane; } +void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) +{ + l->peer_caps = capabilities; +} + void tipc_link_add_bc_peer(struct tipc_link *snd_l, struct tipc_link *uc_l, struct sk_buff_head *xmitq) @@ -373,7 +373,7 @@ int tipc_link_bc_peers(struct tipc_link *l) return l->ackers; } -u16 link_bc_rcv_gap(struct tipc_link *l) +static u16 link_bc_rcv_gap(struct tipc_link *l) { struct sk_buff *skb = skb_peek(&l->deferdq); u16 gap = 0; @@ -410,6 +410,11 @@ char *tipc_link_name(struct tipc_link *l) return l->name; } +u32 tipc_link_state(struct tipc_link *l) +{ + return l->state; +} + /** * tipc_link_create - create a new link * @n: pointer to associated node @@ -469,7 +474,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, l->addr = peer; l->peer_caps = peer_caps; l->net = net; - l->peer_session = ANY_SESSION; + l->in_session = false; l->bearer_id = bearer_id; l->tolerance = tolerance; l->net_plane = net_plane; @@ -820,7 +825,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) * Wake up a number of waiting users, as permitted by available space * in the send queue */ -void link_prepare_wakeup(struct tipc_link *l) +static void link_prepare_wakeup(struct tipc_link *l) { struct sk_buff *skb, *tmp; int imp, i = 0; @@ -838,12 +843,17 @@ void link_prepare_wakeup(struct tipc_link *l) void tipc_link_reset(struct tipc_link *l) { - l->peer_session = ANY_SESSION; + l->in_session = false; l->session++; l->mtu = l->advertised_mtu; + spin_lock_bh(&l->wakeupq.lock); + spin_lock_bh(&l->inputq->lock); + skb_queue_splice_init(&l->wakeupq, l->inputq); + spin_unlock_bh(&l->inputq->lock); + spin_unlock_bh(&l->wakeupq.lock); + __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); - skb_queue_splice_init(&l->wakeupq, l->inputq); __skb_queue_purge(&l->backlogq); l->backlog[TIPC_LOW_IMPORTANCE].len = 0; l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; @@ -857,10 +867,12 @@ void tipc_link_reset(struct tipc_link *l) l->rcv_unacked = 0; l->snd_nxt = 1; l->rcv_nxt = 1; + l->snd_nxt_state = 1; + l->rcv_nxt_state = 1; l->acked = 0; l->silent_intv_cnt = 0; l->rst_cnt = 0; - l->stale_count = 0; + l->stale_cnt = 0; l->bc_peer_is_up = false; memset(&l->mon_state, 0, sizeof(l->mon_state)); tipc_link_reset_stats(l); @@ -954,7 +966,8 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return rc; } -void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) +static void tipc_link_advance_backlog(struct tipc_link *l, + struct sk_buff_head *xmitq) { struct sk_buff *skb, *_skb; struct tipc_msg *hdr; @@ -997,39 +1010,41 @@ static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb) msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr)); } -int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker, - u16 from, u16 to, struct sk_buff_head *xmitq) +/* tipc_link_retrans() - retransmit one or more packets + * @l: the link to transmit on + * @r: the receiving link ordering the retransmit. Same as l if unicast + * @from: retransmit from (inclusive) this sequence number + * @to: retransmit to (inclusive) this sequence number + * xmitq: queue for accumulating the retransmitted packets + */ +static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, + u16 from, u16 to, struct sk_buff_head *xmitq) { struct sk_buff *_skb, *skb = skb_peek(&l->transmq); - struct tipc_msg *hdr; - u16 ack = l->rcv_nxt - 1; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u16 ack = l->rcv_nxt - 1; + struct tipc_msg *hdr; if (!skb) return 0; /* Detect repeated retransmit failures on same packet */ - if (nacker->last_retransm != buf_seqno(skb)) { - nacker->last_retransm = buf_seqno(skb); - nacker->stale_count = 1; - } else if (++nacker->stale_count > 100) { + if (r->last_retransm != buf_seqno(skb)) { + r->last_retransm = buf_seqno(skb); + r->stale_limit = jiffies + msecs_to_jiffies(l->tolerance); + } else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) { link_retransmit_failure(l, skb); - nacker->stale_count = 0; if (link_is_bc_sndlink(l)) return TIPC_LINK_DOWN_EVT; return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } - /* Move forward to where retransmission should start */ skb_queue_walk(&l->transmq, skb) { - if (!less(buf_seqno(skb), from)) - break; - } - - skb_queue_walk_from(&l->transmq, skb) { - if (more(buf_seqno(skb), to)) - break; hdr = buf_msg(skb); + if (less(msg_seqno(hdr), from)) + continue; + if (more(msg_seqno(hdr), to)) + break; _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC); if (!_skb) return 0; @@ -1063,6 +1078,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, skb_queue_tail(mc_inputq, skb); return true; } + /* else: fall through */ case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; @@ -1271,6 +1287,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, /* Forward queues and wake up waiting users */ if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) { + l->stale_cnt = 0; tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); @@ -1347,6 +1364,8 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2); if (mtyp == STATE_MSG) { + if (l->peer_caps & TIPC_LINK_PROTO_SEQNO) + msg_set_seqno(hdr, l->snd_nxt_state++); msg_set_seq_gap(hdr, rcvgap); msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); msg_set_probe(hdr, probe); @@ -1371,6 +1390,36 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, __skb_queue_tail(xmitq, skb); } +void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + u32 onode = tipc_own_addr(l->net); + struct tipc_msg *hdr, *ihdr; + struct sk_buff_head tnlq; + struct sk_buff *skb; + u32 dnode = l->addr; + + skb_queue_head_init(&tnlq); + skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, + INT_H_SIZE, BASIC_H_SIZE, + dnode, onode, 0, 0, 0); + if (!skb) { + pr_warn("%sunable to create tunnel packet\n", link_co_err); + return; + } + + hdr = buf_msg(skb); + msg_set_msgcnt(hdr, 1); + msg_set_bearer_id(hdr, l->peer_bearer_id); + + ihdr = (struct tipc_msg *)msg_data(hdr); + tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, + BASIC_H_SIZE, dnode); + msg_set_errcode(ihdr, TIPC_ERR_NO_PORT); + __skb_queue_tail(&tnlq, skb); + tipc_link_xmit(l, &tnlq, xmitq); +} + /* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets * with contents of the link's transmit and backlog queues. */ @@ -1438,6 +1487,44 @@ tnl: } } +/* tipc_link_validate_msg(): validate message against current link state + * Returns true if message should be accepted, otherwise false + */ +bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) +{ + u16 curr_session = l->peer_session; + u16 session = msg_session(hdr); + int mtyp = msg_type(hdr); + + if (msg_user(hdr) != LINK_PROTOCOL) + return true; + + switch (mtyp) { + case RESET_MSG: + if (!l->in_session) + return true; + /* Accept only RESET with new session number */ + return more(session, curr_session); + case ACTIVATE_MSG: + if (!l->in_session) + return true; + /* Accept only ACTIVATE with new or current session number */ + return !less(session, curr_session); + case STATE_MSG: + /* Accept only STATE with current session number */ + if (!l->in_session) + return false; + if (session != curr_session) + return false; + if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) + return true; + /* Accept only STATE with new sequence number */ + return !less(msg_seqno(hdr), l->rcv_nxt_state); + default: + return false; + } +} + /* tipc_link_proto_rcv(): receive link level protocol message : * Note that network plane id propagates through the network, and may * change at any time. The node with lowest numerical id determines @@ -1471,17 +1558,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, hdr = buf_msg(skb); data = msg_data(hdr); + if (!tipc_link_validate_msg(l, hdr)) + goto exit; + switch (mtyp) { case RESET_MSG: - - /* Ignore duplicate RESET with old session number */ - if ((less_eq(msg_session(hdr), l->peer_session)) && - (l->peer_session != ANY_SESSION)) - break; - /* fall thru' */ - case ACTIVATE_MSG: - /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -1509,12 +1591,14 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); + l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); if (l->mtu > msg_max_pkt(hdr)) l->mtu = msg_max_pkt(hdr); break; case STATE_MSG: + l->rcv_nxt_state = msg_seqno(hdr) + 1; /* Update own tolerance if peer indicates a non-zero value */ if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) diff --git a/net/tipc/link.h b/net/tipc/link.h index ec59348a81e8..90488c538a4e 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -88,6 +88,8 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, struct tipc_link **link); void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq); +void tipc_link_create_dummy_tnl_msg(struct tipc_link *tnl, + struct sk_buff_head *xmitq); void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq); int tipc_link_fsm_evt(struct tipc_link *l, int evt); bool tipc_link_is_up(struct tipc_link *l); @@ -107,9 +109,12 @@ u16 tipc_link_rcv_nxt(struct tipc_link *l); u16 tipc_link_acked(struct tipc_link *l); u32 tipc_link_id(struct tipc_link *l); char *tipc_link_name(struct tipc_link *l); +u32 tipc_link_state(struct tipc_link *l); char tipc_link_plane(struct tipc_link *l); int tipc_link_prio(struct tipc_link *l); int tipc_link_window(struct tipc_link *l); +void tipc_link_update_caps(struct tipc_link *l, u16 capabilities); +bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr); unsigned long tipc_link_tolerance(struct tipc_link *l); void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 5453e564da82..67f69389ec17 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -684,7 +684,8 @@ int tipc_nl_monitor_get_threshold(struct net *net) return tn->mon_threshold; } -int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, struct tipc_nl_msg *msg) +static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, + struct tipc_nl_msg *msg) { struct tipc_mon_domain *dom = peer->domain; struct nlattr *attrs; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index b6c45dccba3d..b61891054709 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -416,26 +416,31 @@ bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu) */ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) { - struct tipc_msg *msg; - int imsz, offset; + struct tipc_msg *hdr, *ihdr; + int imsz; *iskb = NULL; if (unlikely(skb_linearize(skb))) goto none; - msg = buf_msg(skb); - offset = msg_hdr_sz(msg) + *pos; - if (unlikely(offset > (msg_size(msg) - MIN_H_SIZE))) + hdr = buf_msg(skb); + if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE))) goto none; - *iskb = skb_clone(skb, GFP_ATOMIC); - if (unlikely(!*iskb)) + ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos); + imsz = msg_size(ihdr); + + if ((*pos + imsz) > msg_data_sz(hdr)) goto none; - skb_pull(*iskb, offset); - imsz = msg_size(buf_msg(*iskb)); - skb_trim(*iskb, imsz); + + *iskb = tipc_buf_acquire(imsz, GFP_ATOMIC); + if (!*iskb) + goto none; + + skb_copy_to_linear_data(*iskb, ihdr, imsz); if (unlikely(!tipc_msg_validate(iskb))) goto none; + *pos += align(imsz); return true; none: @@ -531,12 +536,6 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) msg_set_hdr_sz(hdr, BASIC_H_SIZE); } - if (skb_cloned(_skb) && - pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) - goto exit; - - /* reassign after skb header modifications */ - hdr = buf_msg(_skb); /* Now reverse the concerned fields */ msg_set_errcode(hdr, err); msg_set_non_seq(hdr, 0); @@ -595,10 +594,6 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) if (!skb_cloned(skb)) return true; - /* Unclone buffer in case it was bundled */ - if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) - return false; - return true; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bebe88cae07b..66d5b2c5987a 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -735,7 +735,7 @@ int tipc_nametbl_init(struct net *net) struct name_table *nt; int i; - nt = kzalloc(sizeof(*nt), GFP_ATOMIC); + nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return -ENOMEM; @@ -980,20 +980,17 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; list_for_each_entry(dst, l, list) { - if (dst->value != value) - continue; - return dst; + if (dst->node == node && dst->port == port) + return dst; } return NULL; } bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; if (tipc_dest_find(l, node, port)) @@ -1002,7 +999,8 @@ bool tipc_dest_push(struct list_head *l, u32 node, u32 port) dst = kmalloc(sizeof(*dst), GFP_ATOMIC); if (unlikely(!dst)) return false; - dst->value = value; + dst->node = node; + dst->port = port; list_add(&dst->list, l); return true; } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 0febba41da86..892bd750b85f 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -133,13 +133,8 @@ void tipc_nametbl_stop(struct net *net); struct tipc_dest { struct list_head list; - union { - struct { - u32 port; - u32 node; - }; - u64 value; - }; + u32 port; + u32 node; }; struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); diff --git a/net/tipc/net.c b/net/tipc/net.c index a7f6964c3a4b..62199cf5a56c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -123,15 +123,13 @@ void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); - spin_lock_bh(&tn->node_list_lock); - if (!tipc_own_addr(net)) { + if (!cmpxchg(&tn->node_addr, 0, addr)) { tipc_set_node_addr(net, addr); tipc_named_reinit(net); tipc_sk_reinit(net); tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, TIPC_CLUSTER_SCOPE, 0, addr); } - spin_unlock_bh(&tn->node_list_lock); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 6ff2254088f6..99ee419210ba 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -167,7 +167,9 @@ static const struct genl_ops tipc_genl_v2_ops[] = { }, { .cmd = TIPC_NL_SOCK_GET, + .start = tipc_dump_start, .dumpit = tipc_nl_sk_dump, + .done = tipc_dump_done, .policy = tipc_nl_policy, }, { diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index a2f76743c73a..6376467e78f8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -185,6 +185,10 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; buf->sk = msg->dst_sk; + if (__tipc_dump_start(&cb, msg->net)) { + kfree_skb(buf); + return -ENOMEM; + } do { int rem; @@ -216,6 +220,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, err = 0; err_out: + tipc_dump_done(&cb); kfree_skb(buf); if (err == -EMSGSIZE) { diff --git a/net/tipc/node.c b/net/tipc/node.c index 0453bd451ce8..b0ee25f1f2e6 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -45,6 +45,7 @@ #include "netlink.h" #define INVALID_NODE_SIG 0x10000 +#define NODE_CLEANUP_AFTER 300000 /* Flags used to take different actions according to flag type * TIPC_NOTIFY_NODE_DOWN: notify node is down @@ -96,6 +97,7 @@ struct tipc_bclink_entry { * @link_id: local and remote bearer ids of changing link, if any * @publ_list: list of publications * @rcu: rcu struct for tipc_node + * @delete_at: indicates the time for deleting a down node */ struct tipc_node { u32 addr; @@ -109,6 +111,7 @@ struct tipc_node { int action_flags; struct list_head list; int state; + bool failover_sent; u16 sync_point; int link_cnt; u16 working_links; @@ -121,6 +124,7 @@ struct tipc_node { unsigned long keepalive_intv; struct timer_list timer; struct rcu_head rcu; + unsigned long delete_at; }; /* Node FSM states and events: @@ -160,6 +164,7 @@ static struct tipc_node *tipc_node_find(struct net *net, u32 addr); static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id); static void tipc_node_put(struct tipc_node *node); static bool node_is_up(struct tipc_node *n); +static void tipc_node_delete_from_list(struct tipc_node *node); struct tipc_sock_conn { u32 port; @@ -359,13 +364,24 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *n, *temp_node; + struct tipc_link *l; + int bearer_id; int i; spin_lock_bh(&tn->node_list_lock); n = tipc_node_find(net, addr); if (n) { + if (n->capabilities == capabilities) + goto exit; /* Same node may come back with new capabilities */ + write_lock_bh(&n->lock); n->capabilities = capabilities; + for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + l = n->links[bearer_id].link; + if (l) + tipc_link_update_caps(l, capabilities); + } + write_unlock_bh(&n->lock); goto exit; } n = kzalloc(sizeof(*n), GFP_ATOMIC); @@ -390,6 +406,7 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, for (i = 0; i < MAX_BEARERS; i++) spin_lock_init(&n->links[i].lock); n->state = SELF_DOWN_PEER_LEAVING; + n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER); n->signature = INVALID_NODE_SIG; n->active_links[0] = INVALID_BEARER_ID; n->active_links[1] = INVALID_BEARER_ID; @@ -433,11 +450,16 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) tipc_link_set_abort_limit(l, tol / n->keepalive_intv); } -static void tipc_node_delete(struct tipc_node *node) +static void tipc_node_delete_from_list(struct tipc_node *node) { list_del_rcu(&node->list); hlist_del_rcu(&node->hash); tipc_node_put(node); +} + +static void tipc_node_delete(struct tipc_node *node) +{ + tipc_node_delete_from_list(node); del_timer_sync(&node->timer); tipc_node_put(node); @@ -544,6 +566,42 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) tipc_node_put(node); } +static void tipc_node_clear_links(struct tipc_node *node) +{ + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + struct tipc_link_entry *le = &node->links[i]; + + if (le->link) { + kfree(le->link); + le->link = NULL; + node->link_cnt--; + } + } +} + +/* tipc_node_cleanup - delete nodes that does not + * have active links for NODE_CLEANUP_AFTER time + */ +static int tipc_node_cleanup(struct tipc_node *peer) +{ + struct tipc_net *tn = tipc_net(peer->net); + bool deleted = false; + + spin_lock_bh(&tn->node_list_lock); + tipc_node_write_lock(peer); + + if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) { + tipc_node_clear_links(peer); + tipc_node_delete_from_list(peer); + deleted = true; + } + tipc_node_write_unlock(peer); + spin_unlock_bh(&tn->node_list_lock); + return deleted; +} + /* tipc_node_timeout - handle expiration of node timer */ static void tipc_node_timeout(struct timer_list *t) @@ -551,21 +609,29 @@ static void tipc_node_timeout(struct timer_list *t) struct tipc_node *n = from_timer(n, t, timer); struct tipc_link_entry *le; struct sk_buff_head xmitq; + int remains = n->link_cnt; int bearer_id; int rc = 0; + if (!node_is_up(n) && tipc_node_cleanup(n)) { + /*Removing the reference of Timer*/ + tipc_node_put(n); + return; + } + __skb_queue_head_init(&xmitq); - for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) { tipc_node_read_lock(n); le = &n->links[bearer_id]; - spin_lock_bh(&le->lock); if (le->link) { + spin_lock_bh(&le->lock); /* Link tolerance may change asynchronously: */ tipc_node_calculate_timer(n, le->link); rc = tipc_link_timeout(le->link, &xmitq); + spin_unlock_bh(&le->lock); + remains--; } - spin_unlock_bh(&le->lock); tipc_node_read_unlock(n); tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr); if (rc & TIPC_LINK_DOWN_EVT) @@ -615,6 +681,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, *slot0 = bearer_id; *slot1 = bearer_id; tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT); + n->failover_sent = false; n->action_flags |= TIPC_NOTIFY_NODE_UP; tipc_link_set_active(nl, true); tipc_bcast_add_peer(n->net, nl, xmitq); @@ -1174,6 +1241,7 @@ static void node_lost_contact(struct tipc_node *n, uint i; pr_debug("Lost contact with %x\n", n->addr); + n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER); /* Clean up broadcast state */ tipc_bcast_remove_peer(n->net, n->bc_entry.link); @@ -1481,7 +1549,7 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id * tipc_node_check_state - check and if necessary update node state * @skb: TIPC packet * @bearer_id: identity of bearer delivering the packet - * Returns true if state is ok, otherwise consumes buffer and returns false + * Returns true if state and msg are ok, otherwise false */ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, int bearer_id, struct sk_buff_head *xmitq) @@ -1515,6 +1583,9 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, } } + if (!tipc_link_validate_msg(l, hdr)) + return false; + /* Check and update node accesibility if applicable */ if (state == SELF_UP_PEER_COMING) { if (!tipc_link_is_up(l)) @@ -1546,6 +1617,15 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl), tipc_link_inputq(l)); } + /* If parallel link was already down, and this happened before + * the tunnel link came up, FAILOVER was never sent. Ensure that + * FAILOVER is sent to get peer out of NODE_FAILINGOVER state. + */ + if (n->state != NODE_FAILINGOVER && !n->failover_sent) { + tipc_link_create_dummy_tnl_msg(l, xmitq); + n->failover_sent = true; + } + /* If pkts arrive out of order, use lowest calculated syncpt */ if (less(syncpt, n->sync_point)) n->sync_point = syncpt; @@ -1743,7 +1823,6 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) struct tipc_node *peer; u32 addr; int err; - int i; /* We identify the peer by its net */ if (!info->attrs[TIPC_NLA_NET]) @@ -1778,15 +1857,7 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) goto err_out; } - for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link_entry *le = &peer->links[i]; - - if (le->link) { - kfree(le->link); - le->link = NULL; - peer->link_cnt--; - } - } + tipc_node_clear_links(peer); tipc_node_write_unlock(peer); tipc_node_delete(peer); diff --git a/net/tipc/node.h b/net/tipc/node.h index 846c8f240872..48b3298a248d 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -49,14 +49,16 @@ enum { TIPC_BCAST_STATE_NACK = (1 << 2), TIPC_BLOCK_FLOWCTL = (1 << 3), TIPC_BCAST_RCAST = (1 << 4), - TIPC_NODE_ID128 = (1 << 5) + TIPC_NODE_ID128 = (1 << 5), + TIPC_LINK_PROTO_SEQNO = (1 << 6) }; -#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ - TIPC_BCAST_STATE_NACK | \ - TIPC_BCAST_RCAST | \ - TIPC_BLOCK_FLOWCTL | \ - TIPC_NODE_ID128) +#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ + TIPC_BCAST_STATE_NACK | \ + TIPC_BCAST_RCAST | \ + TIPC_BLOCK_FLOWCTL | \ + TIPC_NODE_ID128 | \ + TIPC_LINK_PROTO_SEQNO) #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 930852c54d7a..b6f99b021d09 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -411,7 +411,6 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, int kern) { - struct tipc_net *tn; const struct proto_ops *ops; struct sock *sk; struct tipc_sock *tsk; @@ -446,7 +445,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, INIT_LIST_HEAD(&tsk->publications); INIT_LIST_HEAD(&tsk->cong_links); msg = &tsk->phdr; - tn = net_generic(sock_net(sk), tipc_net_id); /* Finish initializing socket data structures */ sock->ops = ops; @@ -578,6 +576,7 @@ static int tipc_release(struct socket *sock) sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); + sock_orphan(sk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); tipc_dest_list_purge(&tsk->cong_links); @@ -716,7 +715,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, struct tipc_sock *tsk = tipc_sk(sk); __poll_t revents = 0; - sock_poll_wait(file, sk_sleep(sk), wait); + sock_poll_wait(file, wait); if (sk->sk_shutdown & RCV_SHUTDOWN) revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; @@ -1117,7 +1116,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, u32 self = tipc_own_addr(net); u32 type, lower, upper, scope; struct sk_buff *skb, *_skb; - u32 portid, oport, onode; + u32 portid, onode; struct sk_buff_head tmpq; struct list_head dports; struct tipc_msg *hdr; @@ -1133,7 +1132,6 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, user = msg_user(hdr); mtyp = msg_type(hdr); hlen = skb_headroom(skb) + msg_hdr_sz(hdr); - oport = msg_origport(hdr); onode = msg_orignode(hdr); type = msg_nametype(hdr); @@ -1421,8 +1419,10 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) /* Handle implicit connection setup */ if (unlikely(dest)) { rc = __tipc_sendmsg(sock, m, dlen); - if (dlen && (dlen == rc)) + if (dlen && dlen == rc) { + tsk->peer_caps = tipc_node_get_capabilities(net, dnode); tsk->snt_unacked = tsk_inc(tsk, dlen + msg_hdr_sz(hdr)); + } return rc; } @@ -2675,6 +2675,8 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_stop(&iter); } while (tsk == ERR_PTR(-EAGAIN)); + + rhashtable_walk_exit(&iter); } static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) @@ -3230,45 +3232,74 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)) { - struct net *net = sock_net(skb->sk); - struct tipc_net *tn = tipc_net(net); - const struct bucket_table *tbl; - u32 prev_portid = cb->args[1]; - u32 tbl_id = cb->args[0]; - struct rhash_head *pos; + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_sock *tsk; int err; - rcu_read_lock(); - tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); - for (; tbl_id < tbl->size; tbl_id++) { - rht_for_each_entry_rcu(tsk, pos, tbl, tbl_id, node) { - spin_lock_bh(&tsk->sk.sk_lock.slock); - if (prev_portid && prev_portid != tsk->portid) { - spin_unlock_bh(&tsk->sk.sk_lock.slock); + rhashtable_walk_start(iter); + while ((tsk = rhashtable_walk_next(iter)) != NULL) { + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + if (err == -EAGAIN) { + err = 0; continue; } + break; + } - err = skb_handler(skb, cb, tsk); - if (err) { - prev_portid = tsk->portid; - spin_unlock_bh(&tsk->sk.sk_lock.slock); - goto out; - } - - prev_portid = 0; - spin_unlock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(iter); + lock_sock(&tsk->sk); + err = skb_handler(skb, cb, tsk); + if (err) { + release_sock(&tsk->sk); + sock_put(&tsk->sk); + goto out; } + release_sock(&tsk->sk); + rhashtable_walk_start(iter); + sock_put(&tsk->sk); } + rhashtable_walk_stop(iter); out: - rcu_read_unlock(); - cb->args[0] = tbl_id; - cb->args[1] = prev_portid; - return skb->len; } EXPORT_SYMBOL(tipc_nl_sk_walk); +int tipc_dump_start(struct netlink_callback *cb) +{ + return __tipc_dump_start(cb, sock_net(cb->skb->sk)); +} +EXPORT_SYMBOL(tipc_dump_start); + +int __tipc_dump_start(struct netlink_callback *cb, struct net *net) +{ + /* tipc_nl_name_table_dump() uses cb->args[0...3]. */ + struct rhashtable_iter *iter = (void *)cb->args[4]; + struct tipc_net *tn = tipc_net(net); + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[4] = (long)iter; + } + + rhashtable_walk_enter(&tn->sk_rht, iter); + return 0; +} + +int tipc_dump_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *hti = (void *)cb->args[4]; + + rhashtable_walk_exit(hti); + kfree(hti); + return 0; +} +EXPORT_SYMBOL(tipc_dump_done); + int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk, u32 sk_filter_state, u64 (*tipc_diag_gen_cookie)(struct sock *sk)) @@ -3320,6 +3351,11 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, goto stat_msg_cancel; nla_nest_end(skb, stat); + + if (tsk->group) + if (tipc_group_fill_sock_diag(tsk->group, skb)) + goto stat_msg_cancel; + nla_nest_end(skb, attrs); return 0; diff --git a/net/tipc/socket.h b/net/tipc/socket.h index aff9b2ae5a1f..5e575f205afe 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -68,4 +68,7 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, int (*skb_handler)(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk)); +int tipc_dump_start(struct netlink_callback *cb); +int __tipc_dump_start(struct netlink_callback *cb, struct net *net); +int tipc_dump_done(struct netlink_callback *cb); #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index c8e34ef22c30..2627b5d812e9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -313,8 +313,8 @@ static void tipc_conn_send_work(struct work_struct *work) conn_put(con); } -/* tipc_conn_queue_evt() - interrupt level call from a subscription instance - * The queued work is launched into tipc_send_work()->tipc_send_to_sock() +/* tipc_topsrv_queue_evt() - interrupt level call from a subscription instance + * The queued work is launched into tipc_conn_send_work()->tipc_conn_send_to_sock() */ void tipc_topsrv_queue_evt(struct net *net, int conid, u32 event, struct tipc_event *evt) |