diff options
Diffstat (limited to 'net/tipc/link.c')
| -rw-r--r-- | net/tipc/link.c | 674 |
1 files changed, 527 insertions, 147 deletions
diff --git a/net/tipc/link.c b/net/tipc/link.c index 341ecd796aa4..24d4d10756d3 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> @@ -106,9 +107,6 @@ struct tipc_stats { * @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 @@ -151,6 +149,7 @@ 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 +161,10 @@ 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; @@ -181,6 +178,7 @@ struct tipc_link { /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; + struct sk_buff *reasm_tnlmsg; /* Broadcast */ u16 ackers; @@ -208,7 +206,8 @@ enum { BC_NACK_SND_SUPPRESS, }; -#define TIPC_BC_RETR_LIM msecs_to_jiffies(10) /* [ms] */ +#define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) +#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) /* * Interval between NACKs when packets arrive out of order @@ -246,6 +245,10 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, 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 u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data); +static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap, + struct tipc_gap_ack_blks *ga, + struct sk_buff_head *xmitq); /* * Simple non-static link routines (i.e. referenced outside this file) @@ -395,6 +398,15 @@ 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; @@ -493,6 +505,7 @@ 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; @@ -537,7 +550,7 @@ 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; } @@ -727,7 +740,7 @@ 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++; @@ -848,27 +861,43 @@ 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); + + for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) + avail[imp] = l->backlog[imp].limit - l->backlog[imp].len; - skb_queue_walk_safe(&l->wakeupq, skb, tmp) { + 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); + } 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 +912,16 @@ 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; @@ -900,7 +931,6 @@ void tipc_link_reset(struct tipc_link *l) l->acked = 0; 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); @@ -920,20 +950,25 @@ 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); + int imp = msg_importance(hdr); + unsigned int mss = tipc_link_mss(l); + unsigned int maxwin = l->window; + unsigned int mtu = l->mtu; + bool new_bundle; int rc = 0; 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; } @@ -952,25 +987,22 @@ 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); - + while ((skb = __skb_dequeue(list))) { if (likely(skb_queue_len(transmq) < maxwin)) { + 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_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; @@ -978,20 +1010,25 @@ 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; @@ -1006,6 +1043,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l, u16 seqno = l->snd_nxt; u16 ack = l->rcv_nxt - 1; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u32 imp; while (skb_queue_len(&l->transmq) < l->window) { skb = skb_peek(&l->backlogq); @@ -1016,11 +1054,14 @@ 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_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; @@ -1034,32 +1075,74 @@ 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) +/** + * 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 bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r, + int *rc) { - struct tipc_msg *hdr = buf_msg(skb); + struct sk_buff *skb = skb_peek(&l->transmq); + struct tipc_msg *hdr; + + if (!skb) + return false; + + if (!TIPC_SKB_CB(skb)->retr_cnt) + return false; + + 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, src: %x\n", - msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(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 true; } -/* tipc_link_retrans() - retransmit one or more packets +/* tipc_link_bc_retrans() - retransmit zero 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) +static int tipc_link_bc_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); u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; struct tipc_msg *hdr; + int rc = 0; if (!skb) return 0; @@ -1067,20 +1150,9 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, return 0; 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 (link_retransmit_failure(l, r, &rc)) + return rc; skb_queue_walk(&l->transmq, skb) { hdr = buf_msg(skb); @@ -1088,12 +1160,11 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, 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 (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) + continue; + TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) return 0; hdr = buf_msg(_skb); @@ -1102,6 +1173,10 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r, _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; + + /* Increase actual retrans counter & mark first time */ + if (!TIPC_SKB_CB(skb)->retr_cnt++) + TIPC_SKB_CB(skb)->retr_stamp = jiffies; } return 0; } @@ -1154,34 +1229,14 @@ 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); @@ -1206,11 +1261,83 @@ 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; } +/* 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) +{ + 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; + + 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); + } 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; +} + static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) { bool released = false; @@ -1226,6 +1353,120 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) return released; } +/* tipc_build_gap_ack_blks - build Gap ACK blocks + * @l: tipc link that data have come with gaps in sequence if any + * @data: data buffer to store the Gap ACK blocks after built + * + * returns the actual allocated memory size + */ +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data) +{ + struct sk_buff *skb = skb_peek(&l->deferdq); + struct tipc_gap_ack_blks *ga = data; + u16 len, expect, seqno = 0; + u8 n = 0; + + if (!skb) + goto exit; + + expect = buf_seqno(skb); + skb_queue_walk(&l->deferdq, skb) { + seqno = buf_seqno(skb); + if (unlikely(more(seqno, expect))) { + ga->gacks[n].ack = htons(expect - 1); + ga->gacks[n].gap = htons(seqno - expect); + if (++n >= MAX_GAP_ACK_BLKS) { + pr_info_ratelimited("Too few Gap ACK blocks!\n"); + goto exit; + } + } else if (unlikely(less(seqno, expect))) { + pr_warn("Unexpected skb in deferdq!\n"); + continue; + } + expect = seqno + 1; + } + + /* last block */ + ga->gacks[n].ack = htons(seqno); + ga->gacks[n].gap = 0; + n++; + +exit: + len = tipc_gap_ack_blks_sz(n); + ga->len = htons(len); + ga->gack_cnt = n; + 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 + * @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 + * + * In case of a repeated retransmit failures, the call will return shortly + * with a returned code (e.g. TIPC_LINK_DOWN_EVT) + */ +static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap, + struct tipc_gap_ack_blks *ga, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb, *_skb, *tmp; + struct tipc_msg *hdr; + u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u16 ack = l->rcv_nxt - 1; + bool passed = false; + u16 seqno, n = 0; + int rc = 0; + + skb_queue_walk_safe(&l->transmq, skb, tmp) { + seqno = buf_seqno(skb); + +next_gap_ack: + if (less_eq(seqno, acked)) { + /* release skb */ + __skb_unlink(skb, &l->transmq); + kfree_skb(skb); + } else if (less_eq(seqno, acked + gap)) { + /* First, check if repeated retrans failures occurs? */ + if (!passed && link_retransmit_failure(l, l, &rc)) + return rc; + passed = true; + + /* retransmit skb if unrestricted*/ + if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) + continue; + TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; + _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++; + + /* 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 (!ga || n >= ga->gack_cnt) + break; + acked = ntohs(ga->gacks[n].ack); + gap = ntohs(ga->gacks[n].gap); + n++; + goto next_gap_ack; + } + } + + return 0; +} + /* tipc_link_build_state_msg: prepare link state message for transmission * * Note that sending of broadcast ack is coordinated among nodes, to reduce @@ -1280,6 +1521,7 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 def_cnt = ++l->stats.deferred_recv; + u32 defq_len = skb_queue_len(&l->deferdq); int match1, match2; if (link_is_bc_rcvlink(l)) { @@ -1290,7 +1532,7 @@ 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)) + if (defq_len >= 3 && !((defq_len - 3) % 16)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); return 0; } @@ -1304,29 +1546,29 @@ 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 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 (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; goto drop; } - /* 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++; @@ -1335,7 +1577,6 @@ 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); @@ -1351,13 +1592,16 @@ 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: @@ -1378,6 +1622,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, struct tipc_mon_state *mstate = &l->mon_state; int dlen = 0; void *data; + u16 glen = 0; /* Don't send protocol message during reset or link failover */ if (tipc_link_is_blocked(l)) @@ -1390,8 +1635,8 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, 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; @@ -1418,9 +1663,11 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); 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, data); + 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 { @@ -1452,7 +1699,7 @@ 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); @@ -1479,18 +1726,47 @@ void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq) { + struct sk_buff_head *fdefq = &tnl->failover_deferdq; 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), @@ -1499,14 +1775,18 @@ 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: @@ -1516,6 +1796,39 @@ 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) { @@ -1531,12 +1844,60 @@ 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) { 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); } } @@ -1590,6 +1951,7 @@ 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); + struct tipc_gap_ack_blks *ga = NULL; u16 rcvgap = 0; u16 ack = msg_ack(hdr); u16 gap = msg_seq_gap(hdr); @@ -1600,6 +1962,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, u16 dlen = msg_data_sz(hdr); int mtyp = msg_type(hdr); bool reply = msg_probe(hdr); + u16 glen = 0; void *data; char *if_name; int rc = 0; @@ -1697,7 +2060,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = TIPC_LINK_UP_EVT; break; } - tipc_mon_rcv(l->net, data, dlen, l->addr, + + /* Receive Gap ACK blocks from peer if any */ + if (l->peer_caps & TIPC_GAP_ACK_BLOCK) { + ga = (struct tipc_gap_ack_blks *)data; + glen = ntohs(ga->len); + /* sanity check: if failed, ignore Gap ACK blocks */ + if (glen != tipc_gap_ack_blks_sz(ga->gack_cnt)) + ga = NULL; + } + + 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 */ @@ -1706,13 +2079,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (rcvgap || reply) tipc_link_build_proto_msg(l, STATE_MSG, 0, reply, rcvgap, 0, 0, xmitq); - tipc_link_release_pkts(l, ack); + + rc |= tipc_link_advance_transmq(l, ack, gap, ga, xmitq); /* If NACK, retransmit will now start at right position */ - if (gap) { - rc = tipc_link_retrans(l, l, ack + 1, ack + gap, xmitq); + if (gap) l->stats.recv_nacks++; - } tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) @@ -1825,7 +2197,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, if (more(peers_snd_nxt, l->rcv_nxt + l->window)) return rc; - rc = tipc_link_retrans(snd_l, l, from, to, xmitq); + rc = tipc_link_bc_retrans(snd_l, l, from, to, xmitq); l->snd_nxt = peers_snd_nxt; if (link_bc_rcv_gap(l)) @@ -1921,7 +2293,7 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, 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_retrans(l->bc_sndlink, l, from, to, xmitq); l->stats.recv_nacks++; return rc; } @@ -1972,8 +2344,8 @@ 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; @@ -2052,7 +2424,7 @@ 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; @@ -2084,7 +2456,7 @@ 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; @@ -2106,7 +2478,7 @@ 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)) @@ -2173,7 +2545,7 @@ 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; @@ -2197,6 +2569,8 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) struct nlattr *attrs; struct nlattr *prop; struct tipc_net *tn = net_generic(net, tipc_net_id); + u32 bc_mode = tipc_bcast_get_broadcast_mode(net); + u32 bc_ratio = tipc_bcast_get_broadcast_ratio(net); struct tipc_link *bcl = tn->bcl; if (!bcl) @@ -2211,7 +2585,7 @@ 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; @@ -2228,11 +2602,17 @@ 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)) 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); @@ -2331,8 +2711,8 @@ 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; |
