From: Jon Paul Maloy Date: Mon, 21 Aug 2017 15:59:30 +0000 (+0200) Subject: tipc: don't reset stale broadcast send link X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=40501f90ed5d992176ba504910d512d9dd1b2668;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git tipc: don't reset stale broadcast send link When the broadcast send link after 100 attempts has failed to transfer a packet to all peers, we consider it stale, and reset it. Thereafter it needs to re-synchronize with the peers, something currently done by just resetting and re-establishing all links to all peers. This has turned out to be overkill, with potentially unwanted consequences for the remaining cluster. A closer analysis reveals that this can be done much simpler. When this kind of failure happens, for reasons that may lie outside the TIPC protocol, it is typically only one peer which is failing to receive and acknowledge packets. It is hence sufficient to identify and reset the links only to that peer to resolve the situation, without having to reset the broadcast link at all. This solution entails a much lower risk of negative consequences for the own node as well as for the overall cluster. We implement this change in this commit. Reviewed-by: Parthasarathy Bhuvaragan Acked-by: Ying Xue Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 767e0537dde5..d49598f6002b 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -365,30 +365,6 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) return 0; } -/* tipc_bearer_reset_all - reset all links on all bearers - */ -void tipc_bearer_reset_all(struct net *net) -{ - struct tipc_bearer *b; - int i; - - for (i = 0; i < MAX_BEARERS; i++) { - b = bearer_get(net, i); - if (b) - clear_bit_unlock(0, &b->up); - } - for (i = 0; i < MAX_BEARERS; i++) { - b = bearer_get(net, i); - if (b) - tipc_reset_bearer(net, b); - } - for (i = 0; i < MAX_BEARERS; i++) { - b = bearer_get(net, i); - if (b) - test_and_set_bit_lock(0, &b->up); - } -} - /** * bearer_disable * diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 635c9086e19a..865cb0901a20 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -210,7 +210,6 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id); struct tipc_media *tipc_media_find(const char *name); -void tipc_bearer_reset_all(struct net *net); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); diff --git a/net/tipc/link.c b/net/tipc/link.c index 60820dc35a08..ac0144f532aa 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -978,15 +978,15 @@ 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, "Resetting link "); + 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)); } -int tipc_link_retrans(struct tipc_link *l, u16 from, u16 to, - struct sk_buff_head *xmitq) +int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker, + u16 from, u16 to, struct sk_buff_head *xmitq) { struct sk_buff *_skb, *skb = skb_peek(&l->transmq); struct tipc_msg *hdr; @@ -997,11 +997,14 @@ int tipc_link_retrans(struct tipc_link *l, u16 from, u16 to, return 0; /* Detect repeated retransmit failures on same packet */ - if (likely(l->last_retransm != buf_seqno(skb))) { - l->last_retransm = buf_seqno(skb); - l->stale_count = 1; - } else if (++l->stale_count > 100) { + if (nacker->last_retransm != buf_seqno(skb)) { + nacker->last_retransm = buf_seqno(skb); + nacker->stale_count = 1; + } else if (++nacker->stale_count > 100) { link_retransmit_failure(l, skb); + nacker->stale_count = 0; + if (link_is_bc_sndlink(l)) + return TIPC_LINK_DOWN_EVT; return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } @@ -1528,7 +1531,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, /* If NACK, retransmit will now start at right position */ if (gap) { - rc = tipc_link_retrans(l, ack + 1, ack + gap, xmitq); + rc = tipc_link_retrans(l, l, ack + 1, ack + gap, xmitq); l->stats.recv_nacks++; } @@ -1680,7 +1683,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, return rc; if (link_bc_retr_eval(snd_l, &from, &to)) - rc = tipc_link_retrans(snd_l, from, to, xmitq); + rc = tipc_link_retrans(snd_l, l, from, to, xmitq); l->snd_nxt = peers_snd_nxt; if (link_bc_rcv_gap(l)) @@ -1775,7 +1778,7 @@ 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, from, to, xmitq); + rc = tipc_link_retrans(l->bc_sndlink, l, from, to, xmitq); l->stats.recv_nacks++; return rc; } diff --git a/net/tipc/node.c b/net/tipc/node.c index 9b4dcb6a16b5..eb728397c810 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1284,7 +1284,7 @@ static void tipc_node_bc_sync_rcv(struct tipc_node *n, struct tipc_msg *hdr, rc = tipc_bcast_sync_rcv(n->net, n->bc_entry.link, hdr); if (rc & TIPC_LINK_DOWN_EVT) { - tipc_bearer_reset_all(n->net); + tipc_node_reset_links(n); return; } @@ -1351,15 +1351,9 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id if (!skb_queue_empty(&be->inputq1)) tipc_node_mcast_rcv(n); - if (rc & TIPC_LINK_DOWN_EVT) { - /* Reception reassembly failure => reset all links to peer */ - if (!tipc_link_is_up(be->link)) - tipc_node_reset_links(n); - - /* Retransmission failure => reset all links to all peers */ - if (!tipc_link_is_up(tipc_bc_sndlink(net))) - tipc_bearer_reset_all(net); - } + /* If reassembly or retransmission failure => reset all links to peer */ + if (rc & TIPC_LINK_DOWN_EVT) + tipc_node_reset_links(n); tipc_node_put(n); }