diff options
Diffstat (limited to 'net/tipc/link.c')
| -rw-r--r-- | net/tipc/link.c | 1347 |
1 files changed, 975 insertions, 372 deletions
diff --git a/net/tipc/link.c b/net/tipc/link.c index ac306d17f8ad..931f55f781a1 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -44,6 +44,7 @@ #include "netlink.h" #include "monitor.h" #include "trace.h" +#include "crypto.h" #include <linux/pkt_sched.h> @@ -81,10 +82,7 @@ struct tipc_stats { * struct tipc_link - TIPC link data structure * @addr: network address of link's peer node * @name: link name character string - * @media_addr: media address to use when sending messages over link - * @timer: link timer * @net: pointer to namespace struct - * @refcnt: reference counter for permanent references (owner node & timer) * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link @@ -93,35 +91,48 @@ struct tipc_stats { * @state: current state of link FSM * @peer_caps: bitmap describing capabilities of peer node * @silent_intv_cnt: # of timer intervals without any reception from peer - * @proto_msg: template for control messages generated by link - * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') * @mon_state: cookie with information needed by link monitor - * @backlog_limit: backlog queue congestion thresholds (indexed by importance) - * @exp_msg_count: # of tunnelled messages expected during link changeover - * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset * @mtu: current maximum packet size for this link * @advertised_mtu: advertised own mtu when link is being established - * @transmitq: queue for sent, non-acked messages * @backlogq: queue for messages waiting to be sent - * @snt_nxt: next sequence number to use for outbound messages - * @prev_from: sequence number of most previous retransmission request - * @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 - * @deferred_queue: deferred queue saved OOS b'cast message received from node - * @unacked_window: # of inbound messages rx'd without ack'ing back to peer * @inputq: buffer queue for messages to be delivered upwards * @namedq: buffer queue for name table messages to be delivered upwards - * @next_out: ptr to first unsent outbound message in queue * @wakeupq: linked list of wakeup msgs waiting for link congestion to abate - * @long_msg_seq_no: next identifier to use for outbound fragmented messages * @reasm_buf: head of partially reassembled inbound message fragments - * @bc_rcvr: marks that this is a broadcast receiver link * @stats: collects statistics regarding link activity + * @session: session to be used by link + * @snd_nxt_state: next send seq number + * @rcv_nxt_state: next rcv seq number + * @in_session: have received ACTIVATE_MSG from peer + * @active: link is active + * @if_name: associated interface name + * @rst_cnt: link reset counter + * @drop_point: seq number for failover handling (FIXME) + * @failover_reasm_skb: saved failover msg ptr (FIXME) + * @failover_deferdq: deferred message queue for failover processing (FIXME) + * @transmq: the link's transmit queue + * @backlog: link's backlog by priority (importance) + * @snd_nxt: next sequence number to be used + * @rcv_unacked: # messages read by user, but not yet acked back to peer + * @deferdq: deferred receive queue + * @window: sliding window size for congestion handling + * @min_win: minimal send window to be used by link + * @ssthresh: slow start threshold for congestion handling + * @max_win: maximal send window to be used by link + * @cong_acks: congestion acks for congestion avoidance (FIXME) + * @checkpoint: seq number for congestion window size handling + * @reasm_tnlmsg: fragmentation/reassembly area for tunnel protocol message + * @last_gap: last gap ack blocks for bcast (FIXME) + * @last_ga: ptr to gap ack blocks + * @bc_rcvlink: the peer specific link used for broadcast reception + * @bc_sndlink: the namespace global link used for broadcast sending + * @nack_state: bcast nack state + * @bc_peer_is_up: peer has acked the bcast init msg */ struct tipc_link { u32 addr; @@ -151,6 +162,7 @@ struct tipc_link { /* Failover/synch */ u16 drop_point; struct sk_buff *failover_reasm_skb; + struct sk_buff_head failover_deferdq; /* Max packet negotiation */ u16 mtu; @@ -162,12 +174,9 @@ struct tipc_link { struct { u16 len; u16 limit; + struct sk_buff *target_bskb; } backlog[5]; u16 snd_nxt; - u16 prev_from; - u16 window; - u16 stale_cnt; - unsigned long stale_limit; /* Reception */ u16 rcv_nxt; @@ -178,13 +187,22 @@ struct tipc_link { /* Congestion handling */ struct sk_buff_head wakeupq; + u16 window; + u16 min_win; + u16 ssthresh; + u16 max_win; + u16 cong_acks; + u16 checkpoint; /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; + struct sk_buff *reasm_tnlmsg; /* Broadcast */ u16 ackers; u16 acked; + u16 last_gap; + struct tipc_gap_ack_blks *last_ga; struct tipc_link *bc_rcvlink; struct tipc_link *bc_sndlink; u8 nack_state; @@ -208,12 +226,8 @@ enum { BC_NACK_SND_SUPPRESS, }; -#define TIPC_BC_RETR_LIM msecs_to_jiffies(10) /* [ms] */ - -/* - * Interval between NACKs when packets arrive out of order - */ -#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) +#define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) +#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) /* Link FSM states: */ @@ -227,13 +241,6 @@ enum { LINK_SYNCHING = 0xc << 24 }; -/* Link FSM state checking routines - */ -static int link_is_up(struct tipc_link *l) -{ - return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); -} - static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, @@ -245,14 +252,22 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq); -static bool tipc_link_release_pkts(struct tipc_link *l, u16 to); - +static u8 __tipc_build_gap_ack_blks(struct tipc_gap_ack_blks *ga, + struct tipc_link *l, u8 start_index); +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr); +static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r, + u16 acked, u16 gap, + struct tipc_gap_ack_blks *ga, + struct sk_buff_head *xmitq, + bool *retransmitted, int *rc); +static void tipc_link_update_cwin(struct tipc_link *l, int released, + bool retransmitted); /* * Simple non-static link routines (i.e. referenced outside this file) */ bool tipc_link_is_up(struct tipc_link *l) { - return link_is_up(l); + return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); } bool tipc_link_peer_is_down(struct tipc_link *l) @@ -305,9 +320,14 @@ u32 tipc_link_id(struct tipc_link *l) return l->peer_bearer_id << 16 | l->bearer_id; } -int tipc_link_window(struct tipc_link *l) +int tipc_link_min_win(struct tipc_link *l) { - return l->window; + return l->min_win; +} + +int tipc_link_max_win(struct tipc_link *l) +{ + return l->max_win; } int tipc_link_prio(struct tipc_link *l) @@ -330,6 +350,11 @@ char tipc_link_plane(struct tipc_link *l) return l->net_plane; } +struct net *tipc_link_net(struct tipc_link *l) +{ + return l->net; +} + void tipc_link_update_caps(struct tipc_link *l, u16 capabilities) { l->peer_caps = capabilities; @@ -356,7 +381,7 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l, snd_l->ackers--; rcv_l->bc_peer_is_up = true; rcv_l->state = LINK_ESTABLISHED; - tipc_link_bc_ack_rcv(rcv_l, ack, xmitq); + tipc_link_bc_ack_rcv(rcv_l, ack, 0, NULL, xmitq, NULL); trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!"); tipc_link_reset(rcv_l); rcv_l->state = LINK_RESET; @@ -395,6 +420,15 @@ int tipc_link_mtu(struct tipc_link *l) return l->mtu; } +int tipc_link_mss(struct tipc_link *l) +{ +#ifdef CONFIG_TIPC_CRYPTO + return l->mtu - INT_H_SIZE - EMSG_OVERHEAD; +#else + return l->mtu - INT_H_SIZE; +#endif +} + u16 tipc_link_rcv_nxt(struct tipc_link *l) { return l->rcv_nxt; @@ -417,16 +451,16 @@ u32 tipc_link_state(struct tipc_link *l) /** * tipc_link_create - create a new link - * @n: pointer to associated node + * @net: pointer to associated network namespace * @if_name: associated interface name * @bearer_id: id (index) of associated bearer * @tolerance: link tolerance to be used by link * @net_plane: network plane (A,B,c..) this link belongs to * @mtu: mtu to be advertised by link * @priority: priority to be used by link - * @window: send window to be used by link + * @min_win: minimal send window to be used by link + * @max_win: maximal send window to be used by link * @session: session to be used by link - * @ownnode: identity of own node * @peer: node id of peer node * @peer_caps: bitmap describing peer node capabilities * @bc_sndlink: the namespace global link used for broadcast sending @@ -434,12 +468,14 @@ u32 tipc_link_state(struct tipc_link *l) * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link + * @self: local unicast link id + * @peer_id: 128-bit ID of peer * - * Returns true if link was created, otherwise false + * Return: true if link was created, otherwise false */ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, int tolerance, char net_plane, u32 mtu, int priority, - int window, u32 session, u32 self, + u32 min_win, u32 max_win, u32 session, u32 self, u32 peer, u8 *peer_id, u16 peer_caps, struct tipc_link *bc_sndlink, struct tipc_link *bc_rcvlink, @@ -459,11 +495,9 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, /* Set link name for unicast links only */ if (peer_id) { - tipc_nodeid2string(self_str, tipc_own_id(net)); - if (strlen(self_str) > 16) + if (tipc_nodeid2string(self_str, tipc_own_id(net)) > NODE_ID_LEN) sprintf(self_str, "%x", self); - tipc_nodeid2string(peer_str, peer_id); - if (strlen(peer_str) > 16) + if (tipc_nodeid2string(peer_str, peer_id) > NODE_ID_LEN) sprintf(peer_str, "%x", peer); } /* Peer i/f name will be completed by reset/activate message */ @@ -483,7 +517,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, l->advertised_mtu = mtu; l->mtu = mtu; l->priority = priority; - tipc_link_set_queue_limits(l, window); + tipc_link_set_queue_limits(l, min_win, max_win); l->ackers = 1; l->bc_sndlink = bc_sndlink; l->bc_rcvlink = bc_rcvlink; @@ -493,6 +527,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, __skb_queue_head_init(&l->transmq); __skb_queue_head_init(&l->backlogq); __skb_queue_head_init(&l->deferdq); + __skb_queue_head_init(&l->failover_deferdq); skb_queue_head_init(&l->wakeupq); skb_queue_head_init(l->inputq); return true; @@ -500,17 +535,23 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, /** * tipc_link_bc_create - create new link to be used for broadcast - * @n: pointer to associated node + * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers - * @window: send window to be used + * @min_win: minimal send window to be used by link + * @max_win: maximal send window to be used by link * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link + * @ownnode: identity of own node + * @peer: node id of peer node + * @peer_id: 128-bit ID of peer + * @peer_caps: bitmap describing peer node capabilities + * @bc_sndlink: the namespace global link used for broadcast sending * - * Returns true if link was created, otherwise false + * Return: true if link was created, otherwise false */ -bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, - int mtu, int window, u16 peer_caps, +bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, + int mtu, u32 min_win, u32 max_win, u16 peer_caps, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link *bc_sndlink, @@ -518,13 +559,23 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, { struct tipc_link *l; - if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, window, - 0, ownnode, peer, NULL, peer_caps, bc_sndlink, - NULL, inputq, namedq, link)) + if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, min_win, + max_win, 0, ownnode, peer, NULL, peer_caps, + bc_sndlink, NULL, inputq, namedq, link)) return false; l = *link; - strcpy(l->name, tipc_bclink_name); + if (peer_id) { + char peer_str[NODE_ID_STR_LEN] = {0,}; + + if (tipc_nodeid2string(peer_str, peer_id) > NODE_ID_LEN) + sprintf(peer_str, "%x", peer); + /* Broadcast receiver link name: "broadcast-link:<peer>" */ + snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, + peer_str); + } else { + strcpy(l->name, tipc_bclink_name); + } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); l->state = LINK_RESET; @@ -537,7 +588,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, /* Disable replicast if even a single peer doesn't support it */ if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST)) - tipc_bcast_disable_rcast(net); + tipc_bcast_toggle_rcast(net, false); return true; } @@ -578,6 +629,7 @@ int tipc_link_fsm_evt(struct tipc_link *l, int evt) break; case LINK_FAILOVER_BEGIN_EVT: l->state = LINK_FAILINGOVER; + break; case LINK_FAILURE_EVT: case LINK_RESET_EVT: case LINK_ESTABLISH_EVT: @@ -727,7 +779,7 @@ static void link_profile_stats(struct tipc_link *l) if (msg_user(msg) == MSG_FRAGMENTER) { if (msg_type(msg) != FIRST_FRAGMENT) return; - length = msg_size(msg_get_wrapped(msg)); + length = msg_size(msg_inner_hdr(msg)); } l->stats.msg_lengths_total += length; l->stats.msg_length_counts++; @@ -751,7 +803,7 @@ static void link_profile_stats(struct tipc_link *l) * tipc_link_too_silent - check if link is "too silent" * @l: tipc link to be checked * - * Returns true if the link 'silent_intv_cnt' is about to reach the + * Return: true if the link 'silent_intv_cnt' is about to reach the * 'abort_limit' value, otherwise false */ bool tipc_link_too_silent(struct tipc_link *l) @@ -786,11 +838,16 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) state |= l->bc_rcvlink->rcv_unacked; state |= l->rcv_unacked; state |= !skb_queue_empty(&l->transmq); - state |= !skb_queue_empty(&l->deferdq); probe = mstate->probing; probe |= l->silent_intv_cnt; if (probe || mstate->monitoring) l->silent_intv_cnt++; + probe |= !skb_queue_empty(&l->deferdq); + if (l->snd_nxt == l->checkpoint) { + tipc_link_update_cwin(l, 0, 0); + probe = true; + } + l->checkpoint = l->snd_nxt; break; case LINK_RESET: setup = l->rst_cnt++ <= 4; @@ -848,27 +905,58 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) */ static void link_prepare_wakeup(struct tipc_link *l) { + struct sk_buff_head *wakeupq = &l->wakeupq; + struct sk_buff_head *inputq = l->inputq; struct sk_buff *skb, *tmp; - int imp, i = 0; + struct sk_buff_head tmpq; + int avail[5] = {0,}; + int imp = 0; + + __skb_queue_head_init(&tmpq); - skb_queue_walk_safe(&l->wakeupq, skb, tmp) { + for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) + avail[imp] = l->backlog[imp].limit - l->backlog[imp].len; + + skb_queue_walk_safe(wakeupq, skb, tmp) { imp = TIPC_SKB_CB(skb)->chain_imp; - if (l->backlog[imp].len < l->backlog[imp].limit) { - skb_unlink(skb, &l->wakeupq); - skb_queue_tail(l->inputq, skb); - } else if (i++ > 10) { - break; - } + if (avail[imp] <= 0) + continue; + avail[imp]--; + __skb_unlink(skb, wakeupq); + __skb_queue_tail(&tmpq, skb); } + + spin_lock_bh(&inputq->lock); + skb_queue_splice_tail(&tmpq, inputq); + spin_unlock_bh(&inputq->lock); + +} + +/** + * tipc_link_set_skb_retransmit_time - set the time at which retransmission of + * the given skb should be next attempted + * @skb: skb to set a future retransmission time for + * @l: link the skb will be transmitted on + */ +static void tipc_link_set_skb_retransmit_time(struct sk_buff *skb, + struct tipc_link *l) +{ + if (link_is_bc_sndlink(l)) + TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + else + TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; } void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; + u32 imp; __skb_queue_head_init(&list); l->in_session = false; + /* Force re-synch of peer session number before establishing */ + l->peer_session--; l->session++; l->mtu = l->advertised_mtu; @@ -883,14 +971,16 @@ void tipc_link_reset(struct tipc_link *l) __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); __skb_queue_purge(&l->backlogq); - l->backlog[TIPC_LOW_IMPORTANCE].len = 0; - l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; - l->backlog[TIPC_HIGH_IMPORTANCE].len = 0; - l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; - l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; + __skb_queue_purge(&l->failover_deferdq); + for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) { + l->backlog[imp].len = 0; + l->backlog[imp].target_bskb = NULL; + } kfree_skb(l->reasm_buf); + kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); l->reasm_buf = NULL; + l->reasm_tnlmsg = NULL; l->failover_reasm_skb = NULL; l->rcv_unacked = 0; l->snd_nxt = 1; @@ -898,9 +988,11 @@ void tipc_link_reset(struct tipc_link *l) l->snd_nxt_state = 1; l->rcv_nxt_state = 1; l->acked = 0; + l->last_gap = 0; + kfree(l->last_ga); + l->last_ga = NULL; l->silent_intv_cnt = 0; l->rst_cnt = 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); @@ -908,39 +1000,50 @@ void tipc_link_reset(struct tipc_link *l) /** * tipc_link_xmit(): enqueue buffer list according to queue situation - * @link: link to use + * @l: link to use * @list: chain of buffers containing message * @xmitq: returned list of packets to be sent by caller * * Consumes the buffer chain. - * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) { - struct tipc_msg *hdr = buf_msg(skb_peek(list)); - unsigned int maxwin = l->window; - int imp = msg_importance(hdr); - unsigned int mtu = l->mtu; + struct sk_buff_head *backlogq = &l->backlogq; + struct sk_buff_head *transmq = &l->transmq; + struct sk_buff *skb, *_skb; + u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; u16 seqno = l->snd_nxt; - u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; - struct sk_buff_head *transmq = &l->transmq; - struct sk_buff_head *backlogq = &l->backlogq; - struct sk_buff *skb, *_skb, *bskb; int pkt_cnt = skb_queue_len(list); + unsigned int mss = tipc_link_mss(l); + unsigned int cwin = l->window; + unsigned int mtu = l->mtu; + struct tipc_msg *hdr; + bool new_bundle; int rc = 0; + int imp; + if (pkt_cnt <= 0) + return 0; + + hdr = buf_msg(skb_peek(list)); if (unlikely(msg_size(hdr) > mtu)) { - skb_queue_purge(list); + pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n", + skb_queue_len(list), msg_user(hdr), + msg_type(hdr), msg_size(hdr), mtu); + __skb_queue_purge(list); return -EMSGSIZE; } + imp = msg_importance(hdr); /* Allow oversubscription of one data msg per source at congestion */ if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) { if (imp == TIPC_SYSTEM_IMPORTANCE) { pr_warn("%s<%s>, link overflow", link_rst_msg, l->name); + __skb_queue_purge(list); return -ENOBUFS; } rc = link_schedule_user(l, hdr); @@ -952,25 +1055,20 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, } /* Prepare each packet for sending, and add to relevant queue: */ - while (skb_queue_len(list)) { - skb = skb_peek(list); - hdr = buf_msg(skb); - msg_set_seqno(hdr, seqno); - msg_set_ack(hdr, ack); - msg_set_bcast_ack(hdr, bc_ack); - - if (likely(skb_queue_len(transmq) < maxwin)) { + while ((skb = __skb_dequeue(list))) { + if (likely(skb_queue_len(transmq) < cwin)) { + hdr = buf_msg(skb); + msg_set_seqno(hdr, seqno); + msg_set_ack(hdr, ack); + msg_set_bcast_ack(hdr, bc_ack); _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) { - skb_queue_purge(list); + kfree_skb(skb); + __skb_queue_purge(list); return -ENOBUFS; } - __skb_dequeue(list); __skb_queue_tail(transmq, skb); - /* next retransmit attempt */ - if (link_is_bc_sndlink(l)) - TIPC_SKB_CB(skb)->nxt_retr = - jiffies + TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; @@ -978,36 +1076,86 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, seqno++; continue; } - if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) { - kfree_skb(__skb_dequeue(list)); - l->stats.sent_bundled++; - continue; - } - if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) { - kfree_skb(__skb_dequeue(list)); - __skb_queue_tail(backlogq, bskb); - l->backlog[msg_importance(buf_msg(bskb))].len++; - l->stats.sent_bundled++; - l->stats.sent_bundles++; + if (tipc_msg_try_bundle(l->backlog[imp].target_bskb, &skb, + mss, l->addr, &new_bundle)) { + if (skb) { + /* Keep a ref. to the skb for next try */ + l->backlog[imp].target_bskb = skb; + l->backlog[imp].len++; + __skb_queue_tail(backlogq, skb); + } else { + if (new_bundle) { + l->stats.sent_bundles++; + l->stats.sent_bundled++; + } + l->stats.sent_bundled++; + } continue; } - l->backlog[imp].len += skb_queue_len(list); + l->backlog[imp].target_bskb = NULL; + l->backlog[imp].len += (1 + skb_queue_len(list)); + __skb_queue_tail(backlogq, skb); skb_queue_splice_tail_init(list, backlogq); } l->snd_nxt = seqno; return rc; } +static void tipc_link_update_cwin(struct tipc_link *l, int released, + bool retransmitted) +{ + int bklog_len = skb_queue_len(&l->backlogq); + struct sk_buff_head *txq = &l->transmq; + int txq_len = skb_queue_len(txq); + u16 cwin = l->window; + + /* Enter fast recovery */ + if (unlikely(retransmitted)) { + l->ssthresh = max_t(u16, l->window / 2, 300); + l->window = min_t(u16, l->ssthresh, l->window); + return; + } + /* Enter slow start */ + if (unlikely(!released)) { + l->ssthresh = max_t(u16, l->window / 2, 300); + l->window = l->min_win; + return; + } + /* Don't increase window if no pressure on the transmit queue */ + if (txq_len + bklog_len < cwin) + return; + + /* Don't increase window if there are holes the transmit queue */ + if (txq_len && l->snd_nxt - buf_seqno(skb_peek(txq)) != txq_len) + return; + + l->cong_acks += released; + + /* Slow start */ + if (cwin <= l->ssthresh) { + l->window = min_t(u16, cwin + released, l->max_win); + return; + } + /* Congestion avoidance */ + if (l->cong_acks < cwin) + return; + l->window = min_t(u16, ++cwin, l->max_win); + l->cong_acks = 0; +} + static void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) { + u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + struct sk_buff_head *txq = &l->transmq; struct sk_buff *skb, *_skb; - struct tipc_msg *hdr; - u16 seqno = l->snd_nxt; u16 ack = l->rcv_nxt - 1; - u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u16 seqno = l->snd_nxt; + struct tipc_msg *hdr; + u16 cwin = l->window; + u32 imp; - while (skb_queue_len(&l->transmq) < l->window) { + while (skb_queue_len(txq) < cwin) { skb = skb_peek(&l->backlogq); if (!skb) break; @@ -1016,11 +1164,12 @@ static void tipc_link_advance_backlog(struct tipc_link *l, break; __skb_dequeue(&l->backlogq); hdr = buf_msg(skb); - l->backlog[msg_importance(hdr)].len--; + imp = msg_importance(hdr); + l->backlog[imp].len--; + if (unlikely(skb == l->backlog[imp].target_bskb)) + l->backlog[imp].target_bskb = NULL; __skb_queue_tail(&l->transmq, skb); - /* next retransmit attempt */ - if (link_is_bc_sndlink(l)) - TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; @@ -1034,76 +1183,57 @@ static void tipc_link_advance_backlog(struct tipc_link *l, l->snd_nxt = seqno; } -static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb) -{ - struct tipc_msg *hdr = buf_msg(skb); - - pr_warn("Retransmission failure on link <%s>\n", l->name); - link_print(l, "State of link "); - pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", - msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr)); - pr_info("sqno %u, prev: %x, src: %x\n", - msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr)); -} - -/* 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 +/** + * link_retransmit_failure() - Detect repeated retransmit failures + * @l: tipc link sender + * @r: tipc link receiver (= l in case of unicast) + * @rc: returned code + * + * Return: true if the repeated retransmit failures happens, otherwise + * false */ -static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, - u16 from, u16 to, struct sk_buff_head *xmitq) +static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r, + int *rc) { - struct sk_buff *_skb, *skb = skb_peek(&l->transmq); - u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; - u16 ack = l->rcv_nxt - 1; + struct sk_buff *skb = skb_peek(&l->transmq); struct tipc_msg *hdr; if (!skb) - return 0; - if (less(to, from)) - return 0; + return false; - trace_tipc_link_retrans(r, from, to, &l->transmq); - /* Detect repeated retransmit failures on same packet */ - if (r->prev_from != from) { - r->prev_from = from; - r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance); - r->stale_cnt = 0; - } else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) { - link_retransmit_failure(l, skb); - trace_tipc_list_dump(&l->transmq, true, "retrans failure!"); - trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!"); - trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!"); - if (link_is_bc_sndlink(l)) - return TIPC_LINK_DOWN_EVT; - return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - } + if (!TIPC_SKB_CB(skb)->retr_cnt) + return false; - skb_queue_walk(&l->transmq, skb) { - hdr = buf_msg(skb); - if (less(msg_seqno(hdr), from)) - continue; - if (more(msg_seqno(hdr), to)) - break; - if (link_is_bc_sndlink(l)) { - if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) - continue; - TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM; - } - _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC); - if (!_skb) - return 0; - hdr = buf_msg(_skb); - msg_set_ack(hdr, ack); - msg_set_bcast_ack(hdr, bc_ack); - _skb->priority = TC_PRIO_CONTROL; - __skb_queue_tail(xmitq, _skb); - l->stats.retransmitted++; + if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp + + msecs_to_jiffies(r->tolerance * 10))) + return false; + + hdr = buf_msg(skb); + if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr))) + return false; + + pr_warn("Retransmission failure on link <%s>\n", l->name); + link_print(l, "State of link "); + pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", + msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr)); + pr_info("sqno %u, prev: %x, dest: %x\n", + msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr)); + pr_info("retr_stamp %d, retr_cnt %d\n", + jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp), + TIPC_SKB_CB(skb)->retr_cnt); + + trace_tipc_list_dump(&l->transmq, true, "retrans failure!"); + trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!"); + trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!"); + + if (link_is_bc_sndlink(l)) { + r->state = LINK_RESET; + *rc |= TIPC_LINK_DOWN_EVT; + } else { + *rc |= tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } - return 0; + + return true; } /* tipc_data_input - deliver data and name distr msgs to upper layer @@ -1126,7 +1256,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, skb_queue_tail(mc_inputq, skb); return true; } - /* fall through */ + fallthrough; case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; @@ -1142,11 +1272,20 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case MSG_FRAGMENTER: case BCAST_PROTOCOL: return false; +#ifdef CONFIG_TIPC_CRYPTO + case MSG_CRYPTO: + if (sysctl_tipc_key_exchange_enabled && + TIPC_SKB_CB(skb)->decrypted) { + tipc_crypto_msg_rcv(l->net, skb); + return true; + } + fallthrough; +#endif default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); - return false; - }; + return true; + } } /* tipc_link_input - process packet that has passed link protocol check @@ -1154,34 +1293,14 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, * Consumes buffer */ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, - struct sk_buff_head *inputq) + struct sk_buff_head *inputq, + struct sk_buff **reasm_skb) { struct tipc_msg *hdr = buf_msg(skb); - struct sk_buff **reasm_skb = &l->reasm_buf; struct sk_buff *iskb; struct sk_buff_head tmpq; int usr = msg_user(hdr); - int rc = 0; int pos = 0; - int ipos = 0; - - if (unlikely(usr == TUNNEL_PROTOCOL)) { - if (msg_type(hdr) == SYNCH_MSG) { - __skb_queue_purge(&l->deferdq); - goto drop; - } - if (!tipc_msg_extract(skb, &iskb, &ipos)) - return rc; - kfree_skb(skb); - skb = iskb; - hdr = buf_msg(skb); - if (less(msg_seqno(hdr), l->drop_point)) - goto drop; - if (tipc_data_input(l, skb, inputq)) - return rc; - usr = msg_user(hdr); - reasm_skb = &l->failover_reasm_skb; - } if (usr == MSG_BUNDLER) { skb_queue_head_init(&tmpq); @@ -1206,24 +1325,359 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, tipc_link_bc_init_rcv(l->bc_rcvlink, hdr); tipc_bcast_unlock(l->net); } -drop: + kfree_skb(skb); return 0; } -static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) +/* tipc_link_tnl_rcv() - receive TUNNEL_PROTOCOL message, drop or process the + * inner message along with the ones in the old link's + * deferdq + * @l: tunnel link + * @skb: TUNNEL_PROTOCOL message + * @inputq: queue to put messages ready for delivery + */ +static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *inputq) { - bool released = false; - struct sk_buff *skb, *tmp; + struct sk_buff **reasm_skb = &l->failover_reasm_skb; + struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg; + struct sk_buff_head *fdefq = &l->failover_deferdq; + struct tipc_msg *hdr = buf_msg(skb); + struct sk_buff *iskb; + int ipos = 0; + int rc = 0; + u16 seqno; - skb_queue_walk_safe(&l->transmq, skb, tmp) { - if (more(buf_seqno(skb), acked)) - break; - __skb_unlink(skb, &l->transmq); + if (msg_type(hdr) == SYNCH_MSG) { + kfree_skb(skb); + return 0; + } + + /* Not a fragment? */ + if (likely(!msg_nof_fragms(hdr))) { + if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) { + pr_warn_ratelimited("Unable to extract msg, defq: %d\n", + skb_queue_len(fdefq)); + return 0; + } kfree_skb(skb); - released = true; + } else { + /* Set fragment type for buf_append */ + if (msg_fragm_no(hdr) == 1) + msg_set_type(hdr, FIRST_FRAGMENT); + else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr)) + msg_set_type(hdr, FRAGMENT); + else + msg_set_type(hdr, LAST_FRAGMENT); + + if (!tipc_buf_append(reasm_tnlmsg, &skb)) { + /* Successful but non-complete reassembly? */ + if (*reasm_tnlmsg || link_is_bc_rcvlink(l)) + return 0; + pr_warn_ratelimited("Unable to reassemble tunnel msg\n"); + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + iskb = skb; + } + + do { + seqno = buf_seqno(iskb); + if (unlikely(less(seqno, l->drop_point))) { + kfree_skb(iskb); + continue; + } + if (unlikely(seqno != l->drop_point)) { + __tipc_skb_queue_sorted(fdefq, seqno, iskb); + continue; + } + + l->drop_point++; + if (!tipc_data_input(l, iskb, inputq)) + rc |= tipc_link_input(l, iskb, inputq, reasm_skb); + if (unlikely(rc)) + break; + } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point))); + + return rc; +} + +/** + * tipc_get_gap_ack_blks - get Gap ACK blocks from PROTOCOL/STATE_MSG + * @ga: returned pointer to the Gap ACK blocks if any + * @l: the tipc link + * @hdr: the PROTOCOL/STATE_MSG header + * @uc: desired Gap ACK blocks type, i.e. unicast (= 1) or broadcast (= 0) + * + * Return: the total Gap ACK blocks size + */ +u16 tipc_get_gap_ack_blks(struct tipc_gap_ack_blks **ga, struct tipc_link *l, + struct tipc_msg *hdr, bool uc) +{ + struct tipc_gap_ack_blks *p; + u16 sz = 0; + + /* Does peer support the Gap ACK blocks feature? */ + if (l->peer_caps & TIPC_GAP_ACK_BLOCK) { + p = (struct tipc_gap_ack_blks *)msg_data(hdr); + sz = ntohs(p->len); + /* Sanity check */ + if (sz == struct_size(p, gacks, size_add(p->ugack_cnt, p->bgack_cnt))) { + /* Good, check if the desired type exists */ + if ((uc && p->ugack_cnt) || (!uc && p->bgack_cnt)) + goto ok; + /* Backward compatible: peer might not support bc, but uc? */ + } else if (uc && sz == struct_size(p, gacks, p->ugack_cnt)) { + if (p->ugack_cnt) { + p->bgack_cnt = 0; + goto ok; + } + } + } + /* Other cases: ignore! */ + p = NULL; + +ok: + *ga = p; + return sz; +} + +static u8 __tipc_build_gap_ack_blks(struct tipc_gap_ack_blks *ga, + struct tipc_link *l, u8 start_index) +{ + struct tipc_gap_ack *gacks = &ga->gacks[start_index]; + struct sk_buff *skb = skb_peek(&l->deferdq); + u16 expect, seqno = 0; + u8 n = 0; + + if (!skb) + return 0; + + expect = buf_seqno(skb); + skb_queue_walk(&l->deferdq, skb) { + seqno = buf_seqno(skb); + if (unlikely(more(seqno, expect))) { + gacks[n].ack = htons(expect - 1); + gacks[n].gap = htons(seqno - expect); + if (++n >= MAX_GAP_ACK_BLKS / 2) { + pr_info_ratelimited("Gacks on %s: %d, ql: %d!\n", + l->name, n, + skb_queue_len(&l->deferdq)); + return n; + } + } else if (unlikely(less(seqno, expect))) { + pr_warn("Unexpected skb in deferdq!\n"); + continue; + } + expect = seqno + 1; + } + + /* last block */ + gacks[n].ack = htons(seqno); + gacks[n].gap = 0; + n++; + return n; +} + +/* tipc_build_gap_ack_blks - build Gap ACK blocks + * @l: tipc unicast link + * @hdr: the tipc message buffer to store the Gap ACK blocks after built + * + * The function builds Gap ACK blocks for both the unicast & broadcast receiver + * links of a certain peer, the buffer after built has the network data format + * as found at the struct tipc_gap_ack_blks definition. + * + * returns the actual allocated memory size + */ +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, struct tipc_msg *hdr) +{ + struct tipc_link *bcl = l->bc_rcvlink; + struct tipc_gap_ack_blks *ga; + u16 len; + + ga = (struct tipc_gap_ack_blks *)msg_data(hdr); + + /* Start with broadcast link first */ + tipc_bcast_lock(bcl->net); + msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1); + msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); + ga->bgack_cnt = __tipc_build_gap_ack_blks(ga, bcl, 0); + tipc_bcast_unlock(bcl->net); + + /* Now for unicast link, but an explicit NACK only (???) */ + ga->ugack_cnt = (msg_seq_gap(hdr)) ? + __tipc_build_gap_ack_blks(ga, l, ga->bgack_cnt) : 0; + + /* Total len */ + len = struct_size(ga, gacks, size_add(ga->bgack_cnt, ga->ugack_cnt)); + ga->len = htons(len); + return len; +} + +/* tipc_link_advance_transmq - advance TIPC link transmq queue by releasing + * acked packets, also doing retransmissions if + * gaps found + * @l: tipc link with transmq queue to be advanced + * @r: tipc link "receiver" i.e. in case of broadcast (= "l" if unicast) + * @acked: seqno of last packet acked by peer without any gaps before + * @gap: # of gap packets + * @ga: buffer pointer to Gap ACK blocks from peer + * @xmitq: queue for accumulating the retransmitted packets if any + * @retransmitted: returned boolean value if a retransmission is really issued + * @rc: returned code e.g. TIPC_LINK_DOWN_EVT if a repeated retransmit failures + * happens (- unlikely case) + * + * Return: the number of packets released from the link transmq + */ +static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r, + u16 acked, u16 gap, + struct tipc_gap_ack_blks *ga, + struct sk_buff_head *xmitq, + bool *retransmitted, int *rc) +{ + struct tipc_gap_ack_blks *last_ga = r->last_ga, *this_ga = NULL; + struct tipc_gap_ack *gacks = NULL; + struct sk_buff *skb, *_skb, *tmp; + struct tipc_msg *hdr; + u32 qlen = skb_queue_len(&l->transmq); + u16 nacked = acked, ngap = gap, gack_cnt = 0; + u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u16 ack = l->rcv_nxt - 1; + u16 seqno, n = 0; + u16 end = r->acked, start = end, offset = r->last_gap; + u16 si = (last_ga) ? last_ga->start_index : 0; + bool is_uc = !link_is_bc_sndlink(l); + bool bc_has_acked = false; + + trace_tipc_link_retrans(r, acked + 1, acked + gap, &l->transmq); + + /* Determine Gap ACK blocks if any for the particular link */ + if (ga && is_uc) { + /* Get the Gap ACKs, uc part */ + gack_cnt = ga->ugack_cnt; + gacks = &ga->gacks[ga->bgack_cnt]; + } else if (ga) { + /* Copy the Gap ACKs, bc part, for later renewal if needed */ + this_ga = kmemdup(ga, struct_size(ga, gacks, ga->bgack_cnt), + GFP_ATOMIC); + if (likely(this_ga)) { + this_ga->start_index = 0; + /* Start with the bc Gap ACKs */ + gack_cnt = this_ga->bgack_cnt; + gacks = &this_ga->gacks[0]; + } else { + /* Hmm, we can get in trouble..., simply ignore it */ + pr_warn_ratelimited("Ignoring bc Gap ACKs, no memory\n"); + } + } + + /* Advance the link transmq */ + skb_queue_walk_safe(&l->transmq, skb, tmp) { + seqno = buf_seqno(skb); + +next_gap_ack: + if (less_eq(seqno, nacked)) { + if (is_uc) + goto release; + /* Skip packets peer has already acked */ + if (!more(seqno, r->acked)) + continue; + /* Get the next of last Gap ACK blocks */ + while (more(seqno, end)) { + if (!last_ga || si >= last_ga->bgack_cnt) + break; + start = end + offset + 1; + end = ntohs(last_ga->gacks[si].ack); + offset = ntohs(last_ga->gacks[si].gap); + si++; + WARN_ONCE(more(start, end) || + (!offset && + si < last_ga->bgack_cnt) || + si > MAX_GAP_ACK_BLKS, + "Corrupted Gap ACK: %d %d %d %d %d\n", + start, end, offset, si, + last_ga->bgack_cnt); + } + /* Check against the last Gap ACK block */ + if (tipc_in_range(seqno, start, end)) + continue; + /* Update/release the packet peer is acking */ + bc_has_acked = true; + if (--TIPC_SKB_CB(skb)->ackers) + continue; +release: + /* release skb */ + __skb_unlink(skb, &l->transmq); + kfree_skb(skb); + } else if (less_eq(seqno, nacked + ngap)) { + /* First gap: check if repeated retrans failures? */ + if (unlikely(seqno == acked + 1 && + link_retransmit_failure(l, r, rc))) { + /* Ignore this bc Gap ACKs if any */ + kfree(this_ga); + this_ga = NULL; + break; + } + /* retransmit skb if unrestricted*/ + if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) + continue; + tipc_link_set_skb_retransmit_time(skb, l); + _skb = pskb_copy(skb, GFP_ATOMIC); + if (!_skb) + continue; + hdr = buf_msg(_skb); + msg_set_ack(hdr, ack); + msg_set_bcast_ack(hdr, bc_ack); + _skb->priority = TC_PRIO_CONTROL; + __skb_queue_tail(xmitq, _skb); + l->stats.retransmitted++; + if (!is_uc) + r->stats.retransmitted++; + *retransmitted = true; + /* Increase actual retrans counter & mark first time */ + if (!TIPC_SKB_CB(skb)->retr_cnt++) + TIPC_SKB_CB(skb)->retr_stamp = jiffies; + } else { + /* retry with Gap ACK blocks if any */ + if (n >= gack_cnt) + break; + nacked = ntohs(gacks[n].ack); + ngap = ntohs(gacks[n].gap); + n++; + goto next_gap_ack; + } } - return released; + + /* Renew last Gap ACK blocks for bc if needed */ + if (bc_has_acked) { + if (this_ga) { + kfree(last_ga); + r->last_ga = this_ga; + r->last_gap = gap; + } else if (last_ga) { + if (less(acked, start)) { + si--; + offset = start - acked - 1; + } else if (less(acked, end)) { + acked = end; + } + if (si < last_ga->bgack_cnt) { + last_ga->start_index = si; + r->last_gap = offset; + } else { + kfree(last_ga); + r->last_ga = NULL; + r->last_gap = 0; + } + } else { + r->last_gap = 0; + } + r->acked = acked; + } else { + kfree(this_ga); + } + + return qlen - skb_queue_len(&l->transmq); } /* tipc_link_build_state_msg: prepare link state message for transmission @@ -1246,7 +1700,6 @@ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq) l->snd_nxt = l->rcv_nxt; return TIPC_LINK_SND_STATE; } - /* Unicast ACK */ l->rcv_unacked = 0; l->stats.sent_acks++; @@ -1280,6 +1733,8 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 def_cnt = ++l->stats.deferred_recv; + struct sk_buff_head *dfq = &l->deferdq; + u32 defq_len = skb_queue_len(dfq); int match1, match2; if (link_is_bc_rcvlink(l)) { @@ -1290,8 +1745,12 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, return 0; } - if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV)) - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); + if (defq_len >= 3 && !((defq_len - 3) % 16)) { + u16 rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; + + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, + rcvgap, 0, 0, xmitq); + } return 0; } @@ -1304,46 +1763,44 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct sk_buff_head *defq = &l->deferdq; - struct tipc_msg *hdr; + struct tipc_msg *hdr = buf_msg(skb); u16 seqno, rcv_nxt, win_lim; + int released = 0; int rc = 0; + /* Verify and update link state */ + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) + return tipc_link_proto_rcv(l, skb, xmitq); + + /* Don't send probe at next timeout expiration */ + l->silent_intv_cnt = 0; + do { hdr = buf_msg(skb); seqno = msg_seqno(hdr); rcv_nxt = l->rcv_nxt; win_lim = rcv_nxt + TIPC_MAX_LINK_WIN; - /* Verify and update link state */ - if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) - return tipc_link_proto_rcv(l, skb, xmitq); - - if (unlikely(!link_is_up(l))) { + if (unlikely(!tipc_link_is_up(l))) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; - goto drop; + kfree_skb(skb); + break; } - /* Don't send probe at next timeout expiration */ - l->silent_intv_cnt = 0; - /* Drop if outside receive window */ if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) { l->stats.duplicates++; - goto drop; - } - - /* 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); + kfree_skb(skb); + break; } + released += tipc_link_advance_transmq(l, l, msg_ack(hdr), 0, + NULL, NULL, NULL, NULL); /* Defer delivery if sequence gap */ if (unlikely(seqno != rcv_nxt)) { - __tipc_skb_queue_sorted(defq, seqno, skb); + if (!__tipc_skb_queue_sorted(defq, seqno, skb)) + l->stats.duplicates++; rc |= tipc_link_build_nack_msg(l, xmitq); break; } @@ -1351,17 +1808,24 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, /* Deliver packet */ l->rcv_nxt++; l->stats.recv_pkts++; - if (!tipc_data_input(l, skb, l->inputq)) - rc |= tipc_link_input(l, skb, l->inputq); + + if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL)) + rc |= tipc_link_tnl_rcv(l, skb, l->inputq); + else if (!tipc_data_input(l, skb, l->inputq)) + rc |= tipc_link_input(l, skb, l->inputq, &l->reasm_buf); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) rc |= tipc_link_build_state_msg(l, xmitq); if (unlikely(rc & ~TIPC_LINK_SND_STATE)) break; - } while ((skb = __skb_dequeue(defq))); + } while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt))); - return rc; -drop: - kfree_skb(skb); + /* Forward queues and wake up waiting users */ + if (released) { + tipc_link_update_cwin(l, released, 0); + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + } return rc; } @@ -1370,12 +1834,13 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, int tolerance, int priority, struct sk_buff_head *xmitq) { + struct tipc_mon_state *mstate = &l->mon_state; + struct sk_buff_head *dfq = &l->deferdq; struct tipc_link *bcl = l->bc_rcvlink; - struct sk_buff *skb; struct tipc_msg *hdr; - struct sk_buff_head *dfq = &l->deferdq; - bool node_up = link_is_up(bcl); - struct tipc_mon_state *mstate = &l->mon_state; + struct sk_buff *skb; + bool node_up = tipc_link_is_up(bcl); + u16 glen = 0, bc_rcvgap = 0; int dlen = 0; void *data; @@ -1386,12 +1851,12 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, if (!tipc_link_is_up(l) && (mtyp == STATE_MSG)) return; - if (!skb_queue_empty(dfq)) + if ((probe || probe_reply) && !skb_queue_empty(dfq)) rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE, - tipc_max_domain_size, l->addr, - tipc_own_addr(l->net), 0, 0, 0); + tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ, + l->addr, tipc_own_addr(l->net), 0, 0, 0); if (!skb) return; @@ -1415,16 +1880,23 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, 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)); + bc_rcvgap = link_bc_rcv_gap(bcl); + msg_set_bc_gap(hdr, bc_rcvgap); msg_set_probe(hdr, probe); msg_set_is_keepalive(hdr, probe || probe_reply); - tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id); - msg_set_size(hdr, INT_H_SIZE + dlen); - skb_trim(skb, INT_H_SIZE + dlen); + if (l->peer_caps & TIPC_GAP_ACK_BLOCK) + glen = tipc_build_gap_ack_blks(l, hdr); + tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id); + msg_set_size(hdr, INT_H_SIZE + glen + dlen); + skb_trim(skb, INT_H_SIZE + glen + dlen); l->stats.sent_states++; l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ + if (mtyp == ACTIVATE_MSG) { + msg_set_dest_session_valid(hdr, 1); + msg_set_dest_session(hdr, l->peer_session); + } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); @@ -1434,6 +1906,8 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, l->stats.sent_probes++; if (rcvgap) l->stats.sent_nacks++; + if (bc_rcvgap) + bcl->stats.sent_nacks++; skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, skb); trace_tipc_proto_build(skb, false, l->name); @@ -1448,7 +1922,7 @@ void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, struct sk_buff *skb; u32 dnode = l->addr; - skb_queue_head_init(&tnlq); + __skb_queue_head_init(&tnlq); skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, INT_H_SIZE, BASIC_H_SIZE, dnode, onode, 0, 0, 0); @@ -1478,15 +1952,43 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, struct sk_buff *skb, *tnlskb; struct tipc_msg *hdr, tnlhdr; struct sk_buff_head *queue = &l->transmq; - struct sk_buff_head tmpxq, tnlq; + struct sk_buff_head tmpxq, tnlq, frags; u16 pktlen, pktcnt, seqno = l->snd_nxt; + bool pktcnt_need_update = false; + u16 syncpt; + int rc; if (!tnl) return; - skb_queue_head_init(&tnlq); - skb_queue_head_init(&tmpxq); + __skb_queue_head_init(&tnlq); + /* Link Synching: + * From now on, send only one single ("dummy") SYNCH message + * to peer. The SYNCH message does not contain any data, just + * a header conveying the synch point to the peer. + */ + if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { + tnlskb = tipc_msg_create(TUNNEL_PROTOCOL, SYNCH_MSG, + INT_H_SIZE, 0, l->addr, + tipc_own_addr(l->net), + 0, 0, 0); + if (!tnlskb) { + pr_warn("%sunable to create dummy SYNCH_MSG\n", + link_co_err); + return; + } + + hdr = buf_msg(tnlskb); + syncpt = l->snd_nxt + skb_queue_len(&l->backlogq) - 1; + msg_set_syncpt(hdr, syncpt); + msg_set_bearer_id(hdr, l->peer_bearer_id); + __skb_queue_tail(&tnlq, tnlskb); + tipc_link_xmit(tnl, &tnlq, xmitq); + return; + } + __skb_queue_head_init(&tmpxq); + __skb_queue_head_init(&frags); /* At least one packet required for safe algorithm => add dummy */ skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, BASIC_H_SIZE, 0, l->addr, tipc_own_addr(l->net), @@ -1495,14 +1997,18 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, pr_warn("%sunable to create tunnel packet\n", link_co_err); return; } - skb_queue_tail(&tnlq, skb); + __skb_queue_tail(&tnlq, skb); tipc_link_xmit(l, &tnlq, &tmpxq); __skb_queue_purge(&tmpxq); /* Initialize reusable tunnel packet header */ tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL, mtyp, INT_H_SIZE, l->addr); - pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq); + if (mtyp == SYNCH_MSG) + pktcnt = l->snd_nxt - buf_seqno(skb_peek(&l->transmq)); + else + pktcnt = skb_queue_len(&l->transmq); + pktcnt += skb_queue_len(&l->backlogq); msg_set_msgcnt(&tnlhdr, pktcnt); msg_set_bearer_id(&tnlhdr, l->peer_bearer_id); tnl: @@ -1512,6 +2018,39 @@ tnl: if (queue == &l->backlogq) msg_set_seqno(hdr, seqno++); pktlen = msg_size(hdr); + + /* Tunnel link MTU is not large enough? This could be + * due to: + * 1) Link MTU has just changed or set differently; + * 2) Or FAILOVER on the top of a SYNCH message + * + * The 2nd case should not happen if peer supports + * TIPC_TUNNEL_ENHANCED + */ + if (pktlen > tnl->mtu - INT_H_SIZE) { + if (mtyp == FAILOVER_MSG && + (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { + rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu, + &frags); + if (rc) { + pr_warn("%sunable to frag msg: rc %d\n", + link_co_err, rc); + return; + } + pktcnt += skb_queue_len(&frags) - 1; + pktcnt_need_update = true; + skb_queue_splice_tail_init(&frags, &tnlq); + continue; + } + /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED + * => Just warn it and return! + */ + pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n", + link_co_err, msg_user(hdr), + msg_type(hdr), msg_size(hdr)); + return; + } + msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC); if (!tnlskb) { @@ -1527,12 +2066,62 @@ tnl: goto tnl; } + if (pktcnt_need_update) + skb_queue_walk(&tnlq, skb) { + hdr = buf_msg(skb); + msg_set_msgcnt(hdr, pktcnt); + } + tipc_link_xmit(tnl, &tnlq, xmitq); if (mtyp == FAILOVER_MSG) { + struct sk_buff_head *fdefq = &tnl->failover_deferdq; + tnl->drop_point = l->rcv_nxt; tnl->failover_reasm_skb = l->reasm_buf; l->reasm_buf = NULL; + + /* Failover the link's deferdq */ + if (unlikely(!skb_queue_empty(fdefq))) { + pr_warn("Link failover deferdq not empty: %d!\n", + skb_queue_len(fdefq)); + __skb_queue_purge(fdefq); + } + skb_queue_splice_init(&l->deferdq, fdefq); + } +} + +/** + * tipc_link_failover_prepare() - prepare tnl for link failover + * + * This is a special version of the precursor - tipc_link_tnl_prepare(), + * see the tipc_node_link_failover() for details + * + * @l: failover link + * @tnl: tunnel link + * @xmitq: queue for messages to be xmited + */ +void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl, + struct sk_buff_head *xmitq) +{ + struct sk_buff_head *fdefq = &tnl->failover_deferdq; + + tipc_link_create_dummy_tnl_msg(tnl, xmitq); + + /* 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 + * would have to start over from scratch instead. + */ + tnl->drop_point = 1; + tnl->failover_reasm_skb = NULL; + + /* Initiate the link's failover deferdq */ + if (unlikely(!skb_queue_empty(fdefq))) { + pr_warn("Link failover deferdq not empty: %d!\n", + skb_queue_len(fdefq)); + __skb_queue_purge(fdefq); } } @@ -1566,7 +2155,7 @@ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) if (session != curr_session) return false; /* Extra sanity check */ - if (!link_is_up(l) && msg_ack(hdr)) + if (!tipc_link_is_up(l) && msg_ack(hdr)) return false; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) return true; @@ -1586,28 +2175,35 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); - u16 rcvgap = 0; - u16 ack = msg_ack(hdr); - u16 gap = msg_seq_gap(hdr); + struct tipc_gap_ack_blks *ga = NULL; + bool reply = msg_probe(hdr), retransmitted = false; + u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); + u16 gap = msg_seq_gap(hdr); + u16 ack = msg_ack(hdr); u16 rcv_nxt = l->rcv_nxt; - u16 dlen = msg_data_sz(hdr); + u16 rcvgap = 0; int mtyp = msg_type(hdr); - bool reply = msg_probe(hdr); - void *data; + int rc = 0, released; char *if_name; - int rc = 0; + void *data; trace_tipc_proto_rcv(skb, false, l->name); + + if (dlen > U16_MAX) + goto exit; + if (tipc_link_is_blocked(l) || !xmitq) goto exit; if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); - skb_linearize(skb); + if (skb_linearize(skb)) + goto exit; + hdr = buf_msg(skb); data = msg_data(hdr); @@ -1620,21 +2216,24 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: + msg_max = msg_max_pkt(hdr); + if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) + break; /* 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) break; if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME) break; - strncpy(if_name, data, TIPC_MAX_IF_NAME); + strscpy(if_name, data, TIPC_MAX_IF_NAME); /* Update own tolerance if peer indicates a non-zero value */ - if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { + if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; l->bc_rcvlink->tolerance = peers_tol; } /* Update own priority if peer's priority is higher */ - if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) + if (tipc_in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; /* If peer is going down we want full re-establish cycle */ @@ -1642,8 +2241,19 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } + + /* If this endpoint was re-created while peer was ESTABLISHING + * it doesn't know current session number. Force re-synch. + */ + if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && + l->session != msg_dest_session(hdr)) { + if (less(l->session, msg_dest_session(hdr))) + l->session = msg_dest_session(hdr) + 1; + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (mtyp == RESET_MSG || !link_is_up(l)) + if (mtyp == RESET_MSG || !tipc_link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ @@ -1653,21 +2263,26 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, 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); + if (l->mtu > msg_max) + l->mtu = msg_max; break; case STATE_MSG: + /* Validate Gap ACK blocks, drop if invalid */ + glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); + if (glen > dlen) + break; + 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)) { + if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) { l->tolerance = peers_tol; l->bc_rcvlink->tolerance = peers_tol; } /* Update own prio if peer indicates a different value */ if ((peers_prio != l->priority) && - in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { + tipc_in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) { l->priority = peers_prio; rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } @@ -1677,29 +2292,33 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (msg_probe(hdr)) l->stats.recv_probes++; - if (!link_is_up(l)) { + if (!tipc_link_is_up(l)) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; break; } - tipc_mon_rcv(l->net, data, dlen, l->addr, + + tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr, &l->mon_state, l->bearer_id); /* Send NACK if peer has sent pkts we haven't received yet */ - if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l)) + if ((reply || msg_is_keepalive(hdr)) && + more(peers_snd_nxt, rcv_nxt) && + !tipc_link_is_synching(l) && + skb_queue_empty(&l->deferdq)) rcvgap = peers_snd_nxt - l->rcv_nxt; if (rcvgap || reply) tipc_link_build_proto_msg(l, STATE_MSG, 0, reply, rcvgap, 0, 0, xmitq); - tipc_link_release_pkts(l, ack); - /* If NACK, retransmit will now start at right position */ - if (gap) { - rc = tipc_link_retrans(l, l, ack + 1, ack + gap, xmitq); + released = tipc_link_advance_transmq(l, l, ack, gap, ga, xmitq, + &retransmitted, &rc); + if (gap) l->stats.recv_nacks++; - } - - tipc_link_advance_backlog(l, xmitq); + if (released || retransmitted) + tipc_link_update_cwin(l, released, retransmitted); + if (released) + tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); } @@ -1760,7 +2379,7 @@ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr) int mtyp = msg_type(hdr); u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); - if (link_is_up(l)) + if (tipc_link_is_up(l)) return; if (msg_user(hdr) == BCAST_PROTOCOL) { @@ -1785,33 +2404,26 @@ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr) int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, struct sk_buff_head *xmitq) { - struct tipc_link *snd_l = l->bc_sndlink; u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); - u16 from = msg_bcast_ack(hdr) + 1; - u16 to = from + msg_bc_gap(hdr) - 1; int rc = 0; - if (!link_is_up(l)) + if (!tipc_link_is_up(l)) return rc; if (!msg_peer_node_is_up(hdr)) return rc; - /* Open when peer ackowledges our bcast init msg (pkt #1) */ + /* Open when peer acknowledges our bcast init msg (pkt #1) */ if (msg_ack(hdr)) l->bc_peer_is_up = true; if (!l->bc_peer_is_up) return rc; - l->stats.recv_nacks++; - /* Ignore if peers_snd_nxt goes beyond receive window */ if (more(peers_snd_nxt, l->rcv_nxt + l->window)) return rc; - rc = tipc_link_retrans(snd_l, l, from, to, xmitq); - l->snd_nxt = peers_snd_nxt; if (link_bc_rcv_gap(l)) rc |= TIPC_LINK_SND_STATE; @@ -1846,38 +2458,34 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, return 0; } -void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked, - struct sk_buff_head *xmitq) +int tipc_link_bc_ack_rcv(struct tipc_link *r, u16 acked, u16 gap, + struct tipc_gap_ack_blks *ga, + struct sk_buff_head *xmitq, + struct sk_buff_head *retrq) { - struct sk_buff *skb, *tmp; - struct tipc_link *snd_l = l->bc_sndlink; - - if (!link_is_up(l) || !l->bc_peer_is_up) - return; + struct tipc_link *l = r->bc_sndlink; + bool unused = false; + int rc = 0; - if (!more(acked, l->acked)) - return; + if (!tipc_link_is_up(r) || !r->bc_peer_is_up) + return 0; - trace_tipc_link_bc_ack(l, l->acked, acked, &snd_l->transmq); - /* Skip over packets peer has already acked */ - skb_queue_walk(&snd_l->transmq, skb) { - if (more(buf_seqno(skb), l->acked)) - break; + if (gap) { + l->stats.recv_nacks++; + r->stats.recv_nacks++; } - /* Update/release the packets peer is acking now */ - skb_queue_walk_from_safe(&snd_l->transmq, skb, tmp) { - if (more(buf_seqno(skb), acked)) - break; - if (!--TIPC_SKB_CB(skb)->ackers) { - __skb_unlink(skb, &snd_l->transmq); - kfree_skb(skb); - } - } - l->acked = acked; - tipc_link_advance_backlog(snd_l, xmitq); - if (unlikely(!skb_queue_empty(&snd_l->wakeupq))) - link_prepare_wakeup(snd_l); + if (less(acked, r->acked) || (acked == r->acked && !gap && !ga)) + return 0; + + trace_tipc_link_bc_ack(r, acked, gap, &l->transmq); + tipc_link_advance_transmq(l, r, acked, gap, ga, retrq, &unused, &rc); + + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + + return rc; } /* tipc_link_bc_nack_rcv(): receive broadcast nack message @@ -1905,8 +2513,8 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, return 0; if (dnode == tipc_own_addr(l->net)) { - tipc_link_bc_ack_rcv(l, acked, xmitq); - rc = tipc_link_retrans(l->bc_sndlink, l, from, to, xmitq); + rc = tipc_link_bc_ack_rcv(l, acked, to - acked, NULL, xmitq, + xmitq); l->stats.recv_nacks++; return rc; } @@ -1918,20 +2526,23 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, return 0; } -void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) +void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win) { int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE); - l->window = win; - l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win); - l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = max_t(u16, 100, win * 2); - l->backlog[TIPC_HIGH_IMPORTANCE].limit = max_t(u16, 150, win * 3); - l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = max_t(u16, 200, win * 4); + l->min_win = min_win; + l->ssthresh = max_win; + l->max_win = max_win; + l->window = min_win; + l->backlog[TIPC_LOW_IMPORTANCE].limit = min_win * 2; + l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = min_win * 4; + l->backlog[TIPC_HIGH_IMPORTANCE].limit = min_win * 6; + l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = min_win * 8; l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } /** - * link_reset_stats - reset link statistics + * tipc_link_reset_stats - reset link statistics * @l: pointer to link */ void tipc_link_reset_stats(struct tipc_link *l) @@ -1957,8 +2568,8 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]) { int err; - err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop, - tipc_nl_prop_policy, NULL); + err = nla_parse_nested_deprecated(props, TIPC_NLA_PROP_MAX, prop, + tipc_nl_prop_policy, NULL); if (err) return err; @@ -1979,10 +2590,10 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]) } if (props[TIPC_NLA_PROP_WIN]) { - u32 win; + u32 max_win; - win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); - if ((win < TIPC_MIN_LINK_WIN) || (win > TIPC_MAX_LINK_WIN)) + max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (max_win < TIPC_DEF_LINK_WIN || max_win > TIPC_MAX_LINK_WIN) return -EINVAL; } @@ -2037,7 +2648,7 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) (s->accu_queue_sz / s->queue_sz_counts) : 0} }; - stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS); + stats = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!stats) return -EMSGSIZE; @@ -2069,7 +2680,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; @@ -2091,7 +2702,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority)) @@ -2158,7 +2769,7 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, (stats->accu_queue_sz / stats->queue_sz_counts) : 0} }; - nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS); + nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS); if (!nest) return -EMSGSIZE; @@ -2175,14 +2786,15 @@ msg_full: return -EMSGSIZE; } -int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) +int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg, + struct tipc_link *bcl) { int err; void *hdr; struct nlattr *attrs; struct nlattr *prop; - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_link *bcl = tn->bcl; + u32 bc_mode = tipc_bcast_get_mode(net); + u32 bc_ratio = tipc_bcast_get_broadcast_ratio(net); if (!bcl) return 0; @@ -2196,7 +2808,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) return -EMSGSIZE; } - attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK); if (!attrs) goto msg_full; @@ -2213,11 +2825,17 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window)) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->max_win)) + goto prop_msg_full; + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST, bc_mode)) goto prop_msg_full; + if (bc_mode & BCLINK_MODE_SEL) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST_RATIO, + bc_ratio)) + goto prop_msg_full; nla_nest_end(msg->skb, prop); err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats); @@ -2247,7 +2865,7 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, l->tolerance = tol; if (l->bc_rcvlink) l->bc_rcvlink->tolerance = tol; - if (link_is_up(l)) + if (tipc_link_is_up(l)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } @@ -2263,21 +2881,6 @@ void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit) l->abort_limit = limit; } -char *tipc_link_name_ext(struct tipc_link *l, char *buf) -{ - if (!l) - scnprintf(buf, TIPC_MAX_LINK_NAME, "null"); - else if (link_is_bc_sndlink(l)) - scnprintf(buf, TIPC_MAX_LINK_NAME, "broadcast-sender"); - else if (link_is_bc_rcvlink(l)) - scnprintf(buf, TIPC_MAX_LINK_NAME, - "broadcast-receiver, peer %x", l->addr); - else - memcpy(buf, l->name, TIPC_MAX_LINK_NAME); - - return buf; -} - /** * tipc_link_dump - dump TIPC link data * @l: tipc link to be dumped @@ -2316,8 +2919,8 @@ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf) i += scnprintf(buf + i, sz - i, " %x", l->peer_caps); i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt); i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt); - i += scnprintf(buf + i, sz - i, " %u", l->prev_from); - i += scnprintf(buf + i, sz - i, " %u", l->stale_cnt); + i += scnprintf(buf + i, sz - i, " %u", 0); + i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", l->acked); list = &l->transmq; |