diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-08 08:03:58 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-08 08:03:58 +0300 |
commit | 80f232121b69cc69a31ccb2b38c1665d770b0710 (patch) | |
tree | 106263eac4ff03b899df695e00dd11e593e74fe2 /net/tipc | |
parent | 82efe439599439a5e1e225ce5740e6cfb777a7dd (diff) | |
parent | a9e41a529681b38087c91ebc0bb91e12f510ca2d (diff) | |
download | linux-80f232121b69cc69a31ccb2b38c1665d770b0710.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.
2) Add fib_sync_mem to control the amount of dirty memory we allow to
queue up between synchronize RCU calls, from David Ahern.
3) Make flow classifier more lockless, from Vlad Buslov.
4) Add PHY downshift support to aquantia driver, from Heiner
Kallweit.
5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
contention on SLAB spinlocks in heavy RPC workloads.
6) Partial GSO offload support in XFRM, from Boris Pismenny.
7) Add fast link down support to ethtool, from Heiner Kallweit.
8) Use siphash for IP ID generator, from Eric Dumazet.
9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
entries, from David Ahern.
10) Move skb->xmit_more into a per-cpu variable, from Florian
Westphal.
11) Improve eBPF verifier speed and increase maximum program size,
from Alexei Starovoitov.
12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
spinlocks. From Neil Brown.
13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.
14) Improve link partner cap detection in generic PHY code, from
Heiner Kallweit.
15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
Maguire.
16) Remove SKB list implementation assumptions in SCTP, your's truly.
17) Various cleanups, optimizations, and simplifications in r8169
driver. From Heiner Kallweit.
18) Add memory accounting on TX and RX path of SCTP, from Xin Long.
19) Switch PHY drivers over to use dynamic featue detection, from
Heiner Kallweit.
20) Support flow steering without masking in dpaa2-eth, from Ioana
Ciocoi.
21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
Pirko.
22) Increase the strict parsing of current and future netlink
attributes, also export such policies to userspace. From Johannes
Berg.
23) Allow DSA tag drivers to be modular, from Andrew Lunn.
24) Remove legacy DSA probing support, also from Andrew Lunn.
25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
Haabendal.
26) Add a generic tracepoint for TX queue timeouts to ease debugging,
from Cong Wang.
27) More indirect call optimizations, from Paolo Abeni"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
cxgb4: Fix error path in cxgb4_init_module
net: phy: improve pause mode reporting in phy_print_status
dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
net: macb: Change interrupt and napi enable order in open
net: ll_temac: Improve error message on error IRQ
net/sched: remove block pointer from common offload structure
net: ethernet: support of_get_mac_address new ERR_PTR error
net: usb: smsc: fix warning reported by kbuild test robot
staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
net: dsa: support of_get_mac_address new ERR_PTR error
net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
vrf: sit mtu should not be updated when vrf netdev is the link
net: dsa: Fix error cleanup path in dsa_init_module
l2tp: Fix possible NULL pointer dereference
taprio: add null check on sched_nest to avoid potential null pointer dereference
net: mvpp2: cls: fix less than zero check on a u32 variable
net_sched: sch_fq: handle non connected flows
net_sched: sch_fq: do not assume EDT packets are ordered
net: hns3: use devm_kcalloc when allocating desc_cb
net: hns3: some cleanup for struct hns3_enet_ring
...
Diffstat (limited to 'net/tipc')
-rw-r--r-- | net/tipc/bcast.c | 275 | ||||
-rw-r--r-- | net/tipc/bcast.h | 12 | ||||
-rw-r--r-- | net/tipc/bearer.c | 50 | ||||
-rw-r--r-- | net/tipc/core.c | 2 | ||||
-rw-r--r-- | net/tipc/core.h | 3 | ||||
-rw-r--r-- | net/tipc/group.c | 2 | ||||
-rw-r--r-- | net/tipc/link.c | 325 | ||||
-rw-r--r-- | net/tipc/link.h | 2 | ||||
-rw-r--r-- | net/tipc/monitor.c | 4 | ||||
-rw-r--r-- | net/tipc/msg.h | 62 | ||||
-rw-r--r-- | net/tipc/name_table.c | 4 | ||||
-rw-r--r-- | net/tipc/net.c | 8 | ||||
-rw-r--r-- | net/tipc/netlink.c | 51 | ||||
-rw-r--r-- | net/tipc/netlink_compat.c | 88 | ||||
-rw-r--r-- | net/tipc/node.c | 119 | ||||
-rw-r--r-- | net/tipc/node.h | 8 | ||||
-rw-r--r-- | net/tipc/socket.c | 25 | ||||
-rw-r--r-- | net/tipc/udp_media.c | 27 |
18 files changed, 853 insertions, 214 deletions
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index d8026543bf4c..6c997d4a6218 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -54,7 +54,9 @@ const char tipc_bclink_name[] = "broadcast-link"; * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast + * @force_bcast: forces broadcast for multicast traffic * @rcast_support: indicates if all peer nodes support replicast + * @force_rcast: forces replicast for multicast traffic * @rc_ratio: dest count as percentage of cluster size where send method changes * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ @@ -64,7 +66,9 @@ struct tipc_bc_base { int dests[MAX_BEARERS]; int primary_bearer; bool bcast_support; + bool force_bcast; bool rcast_support; + bool force_rcast; int rc_ratio; int bc_threshold; }; @@ -216,9 +220,24 @@ static void tipc_bcast_select_xmit_method(struct net *net, int dests, } /* Can current method be changed ? */ method->expires = jiffies + TIPC_METHOD_EXPIRE; - if (method->mandatory || time_before(jiffies, exp)) + if (method->mandatory) return; + if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL) && + time_before(jiffies, exp)) + return; + + /* Configuration as force 'broadcast' method */ + if (bb->force_bcast) { + method->rcast = false; + return; + } + /* Configuration as force 'replicast' method */ + if (bb->force_rcast) { + method->rcast = true; + return; + } + /* Configuration as 'autoselect' or default method */ /* Determine method to use now */ method->rcast = dests <= bb->bc_threshold; } @@ -281,6 +300,63 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, return 0; } +/* tipc_mcast_send_sync - deliver a dummy message with SYN bit + * @net: the applicable net namespace + * @skb: socket buffer to copy + * @method: send method to be used + * @dests: destination nodes for message. + * @cong_link_cnt: returns number of encountered congested destination links + * Returns 0 if success, otherwise errno + */ +static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, + struct tipc_mc_method *method, + struct tipc_nlist *dests, + u16 *cong_link_cnt) +{ + struct tipc_msg *hdr, *_hdr; + struct sk_buff_head tmpq; + struct sk_buff *_skb; + + /* Is a cluster supporting with new capabilities ? */ + if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) + return 0; + + hdr = buf_msg(skb); + if (msg_user(hdr) == MSG_FRAGMENTER) + hdr = msg_get_wrapped(hdr); + if (msg_type(hdr) != TIPC_MCAST_MSG) + return 0; + + /* Allocate dummy message */ + _skb = tipc_buf_acquire(MCAST_H_SIZE, GFP_KERNEL); + if (!_skb) + return -ENOMEM; + + /* Preparing for 'synching' header */ + msg_set_syn(hdr, 1); + + /* Copy skb's header into a dummy header */ + skb_copy_to_linear_data(_skb, hdr, MCAST_H_SIZE); + skb_orphan(_skb); + + /* Reverse method for dummy message */ + _hdr = buf_msg(_skb); + msg_set_size(_hdr, MCAST_H_SIZE); + msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + + skb_queue_head_init(&tmpq); + __skb_queue_tail(&tmpq, _skb); + if (method->rcast) + tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + else + tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + + /* This queue should normally be empty by now */ + __skb_queue_purge(&tmpq); + + return 0; +} + /* tipc_mcast_xmit - deliver message to indicated destination nodes * and to identified node local sockets * @net: the applicable net namespace @@ -296,6 +372,9 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, u16 *cong_link_cnt) { struct sk_buff_head inputq, localq; + bool rcast = method->rcast; + struct tipc_msg *hdr; + struct sk_buff *skb; int rc = 0; skb_queue_head_init(&inputq); @@ -309,6 +388,18 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, /* Send according to determined transmit method */ if (dests->remote) { tipc_bcast_select_xmit_method(net, dests->remote, method); + + skb = skb_peek(pkts); + hdr = buf_msg(skb); + if (msg_user(hdr) == MSG_FRAGMENTER) + hdr = msg_get_wrapped(hdr); + msg_set_is_rcast(hdr, method->rcast); + + /* Switch method ? */ + if (rcast != method->rcast) + tipc_mcast_send_sync(net, skb, method, + dests, cong_link_cnt); + if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); else @@ -485,10 +576,63 @@ static int tipc_bc_link_set_queue_limits(struct net *net, u32 limit) return 0; } +static int tipc_bc_link_set_broadcast_mode(struct net *net, u32 bc_mode) +{ + struct tipc_bc_base *bb = tipc_bc_base(net); + + switch (bc_mode) { + case BCLINK_MODE_BCAST: + if (!bb->bcast_support) + return -ENOPROTOOPT; + + bb->force_bcast = true; + bb->force_rcast = false; + break; + case BCLINK_MODE_RCAST: + if (!bb->rcast_support) + return -ENOPROTOOPT; + + bb->force_bcast = false; + bb->force_rcast = true; + break; + case BCLINK_MODE_SEL: + if (!bb->bcast_support || !bb->rcast_support) + return -ENOPROTOOPT; + + bb->force_bcast = false; + bb->force_rcast = false; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int tipc_bc_link_set_broadcast_ratio(struct net *net, u32 bc_ratio) +{ + struct tipc_bc_base *bb = tipc_bc_base(net); + + if (!bb->bcast_support || !bb->rcast_support) + return -ENOPROTOOPT; + + if (bc_ratio > 100 || bc_ratio <= 0) + return -EINVAL; + + bb->rc_ratio = bc_ratio; + tipc_bcast_lock(net); + tipc_bcbase_calc_bc_threshold(net); + tipc_bcast_unlock(net); + + return 0; +} + int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]) { int err; u32 win; + u32 bc_mode; + u32 bc_ratio; struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; if (!attrs[TIPC_NLA_LINK_PROP]) @@ -498,12 +642,28 @@ int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]) if (err) return err; - if (!props[TIPC_NLA_PROP_WIN]) + if (!props[TIPC_NLA_PROP_WIN] && + !props[TIPC_NLA_PROP_BROADCAST] && + !props[TIPC_NLA_PROP_BROADCAST_RATIO]) { return -EOPNOTSUPP; + } + + if (props[TIPC_NLA_PROP_BROADCAST]) { + bc_mode = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST]); + err = tipc_bc_link_set_broadcast_mode(net, bc_mode); + } + + if (!err && props[TIPC_NLA_PROP_BROADCAST_RATIO]) { + bc_ratio = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST_RATIO]); + err = tipc_bc_link_set_broadcast_ratio(net, bc_ratio); + } - win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (!err && props[TIPC_NLA_PROP_WIN]) { + win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + err = tipc_bc_link_set_queue_limits(net, win); + } - return tipc_bc_link_set_queue_limits(net, win); + return err; } int tipc_bcast_init(struct net *net) @@ -529,7 +689,7 @@ int tipc_bcast_init(struct net *net) goto enomem; bb->link = l; tn->bcl = l; - bb->rc_ratio = 25; + bb->rc_ratio = 10; bb->rcast_support = true; return 0; enomem: @@ -576,3 +736,108 @@ void tipc_nlist_purge(struct tipc_nlist *nl) nl->remote = 0; nl->local = false; } + +u32 tipc_bcast_get_broadcast_mode(struct net *net) +{ + struct tipc_bc_base *bb = tipc_bc_base(net); + + if (bb->force_bcast) + return BCLINK_MODE_BCAST; + + if (bb->force_rcast) + return BCLINK_MODE_RCAST; + + if (bb->bcast_support && bb->rcast_support) + return BCLINK_MODE_SEL; + + return 0; +} + +u32 tipc_bcast_get_broadcast_ratio(struct net *net) +{ + struct tipc_bc_base *bb = tipc_bc_base(net); + + return bb->rc_ratio; +} + +void tipc_mcast_filter_msg(struct net *net, struct sk_buff_head *defq, + struct sk_buff_head *inputq) +{ + struct sk_buff *skb, *_skb, *tmp; + struct tipc_msg *hdr, *_hdr; + bool match = false; + u32 node, port; + + skb = skb_peek(inputq); + if (!skb) + return; + + hdr = buf_msg(skb); + + if (likely(!msg_is_syn(hdr) && skb_queue_empty(defq))) + return; + + node = msg_orignode(hdr); + if (node == tipc_own_addr(net)) + return; + + port = msg_origport(hdr); + + /* Has the twin SYN message already arrived ? */ + skb_queue_walk(defq, _skb) { + _hdr = buf_msg(_skb); + if (msg_orignode(_hdr) != node) + continue; + if (msg_origport(_hdr) != port) + continue; + match = true; + break; + } + + if (!match) { + if (!msg_is_syn(hdr)) + return; + __skb_dequeue(inputq); + __skb_queue_tail(defq, skb); + return; + } + + /* Deliver non-SYN message from other link, otherwise queue it */ + if (!msg_is_syn(hdr)) { + if (msg_is_rcast(hdr) != msg_is_rcast(_hdr)) + return; + __skb_dequeue(inputq); + __skb_queue_tail(defq, skb); + return; + } + + /* Queue non-SYN/SYN message from same link */ + if (msg_is_rcast(hdr) == msg_is_rcast(_hdr)) { + __skb_dequeue(inputq); + __skb_queue_tail(defq, skb); + return; + } + + /* Matching SYN messages => return the one with data, if any */ + __skb_unlink(_skb, defq); + if (msg_data_sz(hdr)) { + kfree_skb(_skb); + } else { + __skb_dequeue(inputq); + kfree_skb(skb); + __skb_queue_tail(inputq, _skb); + } + + /* Deliver subsequent non-SYN messages from same peer */ + skb_queue_walk_safe(defq, _skb, tmp) { + _hdr = buf_msg(_skb); + if (msg_orignode(_hdr) != node) + continue; + if (msg_origport(_hdr) != port) + continue; + if (msg_is_syn(_hdr)) + break; + __skb_unlink(_skb, defq); + __skb_queue_tail(inputq, _skb); + } +} diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 751530ab0c49..dadad953e2be 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -48,6 +48,10 @@ extern const char tipc_bclink_name[]; #define TIPC_METHOD_EXPIRE msecs_to_jiffies(5000) +#define BCLINK_MODE_BCAST 0x1 +#define BCLINK_MODE_RCAST 0x2 +#define BCLINK_MODE_SEL 0x4 + struct tipc_nlist { struct list_head list; u32 self; @@ -63,11 +67,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node); /* Cookie to be used between socket and broadcast layer * @rcast: replicast (instead of broadcast) was used at previous xmit * @mandatory: broadcast/replicast indication was set by user + * @deferredq: defer queue to make message in order * @expires: re-evaluate non-mandatory transmit method if we are past this */ struct tipc_mc_method { bool rcast; bool mandatory; + struct sk_buff_head deferredq; unsigned long expires; }; @@ -92,6 +98,12 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]); int tipc_bclink_reset_stats(struct net *net); +u32 tipc_bcast_get_broadcast_mode(struct net *net); +u32 tipc_bcast_get_broadcast_ratio(struct net *net); + +void tipc_mcast_filter_msg(struct net *net, struct sk_buff_head *defq, + struct sk_buff_head *inputq); + static inline void tipc_bcast_lock(struct net *net) { spin_lock_bh(&tipc_net(net)->bclock); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index d27f30a9a01d..2bed6589f41e 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -687,14 +687,14 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_BEARER); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_BEARER_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority)) @@ -776,9 +776,9 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, - info->attrs[TIPC_NLA_BEARER], - tipc_nl_bearer_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy, info->extack); if (err) return err; @@ -825,9 +825,9 @@ int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, - info->attrs[TIPC_NLA_BEARER], - tipc_nl_bearer_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy, info->extack); if (err) return err; @@ -870,9 +870,9 @@ int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, - info->attrs[TIPC_NLA_BEARER], - tipc_nl_bearer_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy, info->extack); if (err) return err; @@ -921,9 +921,9 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, - info->attrs[TIPC_NLA_BEARER], - tipc_nl_bearer_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy, info->extack); if (err) return err; @@ -964,9 +964,9 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, - info->attrs[TIPC_NLA_BEARER], - tipc_nl_bearer_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy, info->extack); if (err) return err; @@ -1033,14 +1033,14 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MEDIA); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA); if (!attrs) goto msg_full; if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name)) goto attr_msg_full; - prop = nla_nest_start(msg->skb, TIPC_NLA_MEDIA_PROP); + prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP); if (!prop) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority)) @@ -1107,9 +1107,9 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX, - info->attrs[TIPC_NLA_MEDIA], - tipc_nl_media_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX, + info->attrs[TIPC_NLA_MEDIA], + tipc_nl_media_policy, info->extack); if (err) return err; @@ -1155,9 +1155,9 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX, - info->attrs[TIPC_NLA_MEDIA], - tipc_nl_media_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX, + info->attrs[TIPC_NLA_MEDIA], + tipc_nl_media_policy, info->extack); if (!attrs[TIPC_NLA_MEDIA_NAME]) return -EINVAL; diff --git a/net/tipc/core.c b/net/tipc/core.c index 5b38f5164281..27cccd101ef6 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -43,6 +43,7 @@ #include "net.h" #include "socket.h" #include "bcast.h" +#include "node.h" #include <linux/module.h> @@ -59,6 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->node_addr = 0; tn->trial_addr = 0; tn->addr_trial_end = 0; + tn->capabilities = TIPC_NODE_CAPABILITIES; memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; diff --git a/net/tipc/core.h b/net/tipc/core.h index 8020a6c360ff..7a68e1b6a066 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -122,6 +122,9 @@ struct tipc_net { /* Topology subscription server */ struct tipc_topsrv *topsrv; atomic_t subscription_count; + + /* Cluster capabilities */ + u16 capabilities; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/group.c b/net/tipc/group.c index 63f39201e41e..992be6113676 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -917,7 +917,7 @@ void tipc_group_member_evt(struct tipc_group *grp, int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) { - struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP); + struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP); if (!group) return -EMSGSIZE; diff --git a/net/tipc/link.c b/net/tipc/link.c index 131aa2f0fd27..f5cd986e1e50 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -151,6 +151,7 @@ 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; @@ -209,6 +210,7 @@ enum { }; #define TIPC_BC_RETR_LIM msecs_to_jiffies(10) /* [ms] */ +#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) /* * Interval between NACKs when packets arrive out of order @@ -246,6 +248,10 @@ 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 void 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) @@ -493,6 +499,7 @@ 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; @@ -885,6 +892,7 @@ void tipc_link_reset(struct tipc_link *l) __skb_queue_purge(&l->transmq); __skb_queue_purge(&l->deferdq); __skb_queue_purge(&l->backlogq); + __skb_queue_purge(&l->failover_deferdq); l->backlog[TIPC_LOW_IMPORTANCE].len = 0; l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0; l->backlog[TIPC_HIGH_IMPORTANCE].len = 0; @@ -1156,34 +1164,14 @@ 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); @@ -1208,11 +1196,66 @@ 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_head *fdefq = &l->failover_deferdq; + struct tipc_msg *hdr = buf_msg(skb); + struct sk_buff *iskb; + int ipos = 0; + int rc = 0; + u16 seqno; + + /* SYNCH_MSG */ + if (msg_type(hdr) == SYNCH_MSG) + goto drop; + + /* FAILOVER_MSG */ + if (!tipc_msg_extract(skb, &iskb, &ipos)) { + pr_warn_ratelimited("Cannot extract FAILOVER_MSG, defq: %d\n", + skb_queue_len(fdefq)); + return rc; + } + + 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))); + +drop: + kfree_skb(skb); + return rc; +} + static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) { bool released = false; @@ -1228,6 +1271,106 @@ 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 + */ +static void 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; + u16 seqno; + u16 n = 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)) { + /* retransmit skb */ + 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, MIN_H_SIZE, 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++; + } 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; + } + } +} + /* tipc_link_build_state_msg: prepare link state message for transmission * * Note that sending of broadcast ack is coordinated among nodes, to reduce @@ -1282,6 +1425,7 @@ 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)) { @@ -1292,7 +1436,7 @@ 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; } @@ -1306,29 +1450,29 @@ 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++; @@ -1353,13 +1497,16 @@ 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: @@ -1380,6 +1527,7 @@ 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)) @@ -1392,8 +1540,8 @@ 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; @@ -1420,9 +1568,11 @@ 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 { @@ -1481,6 +1631,7 @@ 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; @@ -1508,7 +1659,11 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, /* 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: @@ -1539,6 +1694,49 @@ tnl: 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 enpoint 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. + */ + WARN_ON(l && tipc_link_is_up(l)); + 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); } } @@ -1592,6 +1790,7 @@ 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); @@ -1602,6 +1801,7 @@ 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; @@ -1699,7 +1899,17 @@ 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 */ @@ -1708,13 +1918,12 @@ 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); + + 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))) @@ -1974,8 +2183,8 @@ 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; @@ -2054,7 +2263,7 @@ 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; @@ -2086,7 +2295,7 @@ 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; @@ -2108,7 +2317,7 @@ 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)) @@ -2175,7 +2384,7 @@ 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; @@ -2199,6 +2408,8 @@ 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) @@ -2213,7 +2424,7 @@ 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; @@ -2230,11 +2441,17 @@ 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); diff --git a/net/tipc/link.h b/net/tipc/link.h index 8439e0ee53a8..adcad65e761c 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -90,6 +90,8 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, int mtyp, struct sk_buff_head *xmitq); void tipc_link_create_dummy_tnl_msg(struct tipc_link *tnl, struct sk_buff_head *xmitq); +void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl, + struct sk_buff_head *xmitq); void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq); int tipc_link_fsm_evt(struct tipc_link *l, int evt); bool tipc_link_is_up(struct tipc_link *l); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 67f69389ec17..6a6eae88442f 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -696,7 +696,7 @@ static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MON_PEER); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER); if (!attrs) goto msg_full; @@ -785,7 +785,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MON); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON); if (!attrs) goto msg_full; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index d7e4b8b93f9d..8de02ad6e352 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -117,6 +117,37 @@ struct tipc_msg { __be32 hdr[15]; }; +/* struct tipc_gap_ack - TIPC Gap ACK block + * @ack: seqno of the last consecutive packet in link deferdq + * @gap: number of gap packets since the last ack + * + * E.g: + * link deferdq: 1 2 3 4 10 11 13 14 15 20 + * --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0> + */ +struct tipc_gap_ack { + __be16 ack; + __be16 gap; +}; + +/* struct tipc_gap_ack_blks + * @len: actual length of the record + * @gack_cnt: number of Gap ACK blocks in the record + * @gacks: array of Gap ACK blocks + */ +struct tipc_gap_ack_blks { + __be16 len; + u8 gack_cnt; + u8 reserved; + struct tipc_gap_ack gacks[]; +}; + +#define tipc_gap_ack_blks_sz(n) (sizeof(struct tipc_gap_ack_blks) + \ + sizeof(struct tipc_gap_ack) * (n)) + +#define MAX_GAP_ACK_BLKS 32 +#define MAX_GAP_ACK_BLKS_SZ tipc_gap_ack_blks_sz(MAX_GAP_ACK_BLKS) + static inline struct tipc_msg *buf_msg(struct sk_buff *skb) { return (struct tipc_msg *)skb->data; @@ -257,6 +288,16 @@ static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d) msg_set_bits(m, 0, 18, 1, d); } +static inline bool msg_is_rcast(struct tipc_msg *m) +{ + return msg_bits(m, 0, 18, 0x1); +} + +static inline void msg_set_is_rcast(struct tipc_msg *m, bool d) +{ + msg_set_bits(m, 0, 18, 0x1, d); +} + static inline void msg_set_size(struct tipc_msg *m, u32 sz) { m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz); @@ -1110,4 +1151,25 @@ static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list, tipc_skb_queue_splice_tail(&tmp, head); } +/* __tipc_skb_dequeue() - dequeue the head skb according to expected seqno + * @list: list to be dequeued from + * @seqno: seqno of the expected msg + * + * returns skb dequeued from the list if its seqno is less than or equal to + * the expected one, otherwise the skb is still hold + * + * Note: must be used with appropriate locks held only + */ +static inline struct sk_buff *__tipc_skb_dequeue(struct sk_buff_head *list, + u16 seqno) +{ + struct sk_buff *skb = skb_peek(list); + + if (skb && less_eq(buf_seqno(skb), seqno)) { + __skb_unlink(skb, list); + return skb; + } + return NULL; +} + #endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 89993afe0fbd..66a65c2cdb23 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -829,11 +829,11 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE); if (!attrs) goto msg_full; - b = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); + b = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE_PUBL); if (!b) goto attr_msg_full; diff --git a/net/tipc/net.c b/net/tipc/net.c index 7ce1e86b024f..85707c185360 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -187,7 +187,7 @@ static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; @@ -245,9 +245,9 @@ int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_NET]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX, - info->attrs[TIPC_NLA_NET], tipc_nl_net_policy, - info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX, + info->attrs[TIPC_NLA_NET], + tipc_nl_net_policy, info->extack); if (err) return err; diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 99ee419210ba..99bd166bccec 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -110,7 +110,9 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { [TIPC_NLA_PROP_UNSPEC] = { .type = NLA_UNSPEC }, [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, - [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 } + [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_BROADCAST] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_BROADCAST_RATIO] = { .type = NLA_U32 } }; const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = { @@ -141,115 +143,115 @@ const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { static const struct genl_ops tipc_genl_v2_ops[] = { { .cmd = TIPC_NL_BEARER_DISABLE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_bearer_disable, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_ENABLE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_bearer_enable, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_bearer_get, .dumpit = tipc_nl_bearer_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_ADD, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_bearer_add, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_BEARER_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_bearer_set, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_SOCK_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .start = tipc_dump_start, .dumpit = tipc_nl_sk_dump, .done = tipc_dump_done, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_PUBL_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = tipc_nl_publ_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_LINK_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_node_get_link, .dumpit = tipc_nl_node_dump_link, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_LINK_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_node_set_link, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_LINK_RESET_STATS, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_node_reset_link_stats, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MEDIA_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_media_get, .dumpit = tipc_nl_media_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MEDIA_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_media_set, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NODE_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = tipc_nl_node_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NET_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = tipc_nl_net_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NET_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_net_set, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_NAME_TABLE_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = tipc_nl_name_table_dump, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MON_SET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_node_set_monitor, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MON_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_node_get_monitor, .dumpit = tipc_nl_node_dump_monitor, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_MON_PEER_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = tipc_nl_node_dump_monitor_peer, - .policy = tipc_nl_policy, }, { .cmd = TIPC_NL_PEER_REMOVE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_peer_rm, - .policy = tipc_nl_policy, }, #ifdef CONFIG_TIPC_MEDIA_UDP { .cmd = TIPC_NL_UDP_GET_REMOTEIP, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = tipc_udp_nl_dump_remoteip, - .policy = tipc_nl_policy, }, #endif }; @@ -259,6 +261,7 @@ struct genl_family tipc_genl_family __ro_after_init = { .version = TIPC_GENL_V2_VERSION, .hdrsize = 0, .maxattr = TIPC_NLA_MAX, + .policy = tipc_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = tipc_genl_v2_ops, @@ -273,8 +276,8 @@ int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr) if (!*attr) return -EOPNOTSUPP; - return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy, - NULL); + return nlmsg_parse_deprecated(nlh, GENL_HDRLEN, *attr, maxattr, + tipc_nl_policy, NULL); } int __init tipc_netlink_start(void) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 340a6e7c43a7..c6a04c09d075 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -328,9 +328,9 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, if (err) goto doit_out; - err = nla_parse(attrbuf, tipc_genl_family.maxattr, - (const struct nlattr *)trans_buf->data, - trans_buf->len, NULL, NULL); + err = nla_parse_deprecated(attrbuf, tipc_genl_family.maxattr, + (const struct nlattr *)trans_buf->data, + trans_buf->len, NULL, NULL); if (err) goto doit_out; @@ -378,8 +378,8 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, - attrs[TIPC_NLA_BEARER], NULL, NULL); + err = nla_parse_nested_deprecated(bearer, TIPC_NLA_BEARER_MAX, + attrs[TIPC_NLA_BEARER], NULL, NULL); if (err) return err; @@ -399,7 +399,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, b = (struct tipc_bearer_config *)TLV_DATA(msg->req); - bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER); if (!bearer) return -EMSGSIZE; @@ -419,7 +419,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, return -EMSGSIZE; if (ntohl(b->priority) <= TIPC_MAX_LINK_PRI) { - prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP); if (!prop) return -EMSGSIZE; if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(b->priority))) @@ -441,7 +441,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, name = (char *)TLV_DATA(msg->req); - bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER); if (!bearer) return -EMSGSIZE; @@ -514,24 +514,26 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_LINK]) return -EINVAL; - err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], - NULL, NULL); + err = nla_parse_nested_deprecated(link, TIPC_NLA_LINK_MAX, + attrs[TIPC_NLA_LINK], NULL, NULL); if (err) return err; if (!link[TIPC_NLA_LINK_PROP]) return -EINVAL; - err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX, - link[TIPC_NLA_LINK_PROP], NULL, NULL); + err = nla_parse_nested_deprecated(prop, TIPC_NLA_PROP_MAX, + link[TIPC_NLA_LINK_PROP], NULL, + NULL); if (err) return err; if (!link[TIPC_NLA_LINK_STATS]) return -EINVAL; - err = nla_parse_nested(stats, TIPC_NLA_STATS_MAX, - link[TIPC_NLA_LINK_STATS], NULL, NULL); + err = nla_parse_nested_deprecated(stats, TIPC_NLA_STATS_MAX, + link[TIPC_NLA_LINK_STATS], NULL, + NULL); if (err) return err; @@ -645,8 +647,8 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_LINK]) return -EINVAL; - err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], - NULL, NULL); + err = nla_parse_nested_deprecated(link, TIPC_NLA_LINK_MAX, + attrs[TIPC_NLA_LINK], NULL, NULL); if (err) return err; @@ -685,7 +687,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - media = nla_nest_start(skb, TIPC_NLA_MEDIA); + media = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA); if (!media) return -EMSGSIZE; @@ -696,7 +698,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name)) return -EMSGSIZE; - prop = nla_nest_start(skb, TIPC_NLA_MEDIA_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA_PROP); if (!prop) return -EMSGSIZE; @@ -717,7 +719,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - bearer = nla_nest_start(skb, TIPC_NLA_BEARER); + bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER); if (!bearer) return -EMSGSIZE; @@ -728,7 +730,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name)) return -EMSGSIZE; - prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP); if (!prop) return -EMSGSIZE; @@ -748,14 +750,14 @@ static int __tipc_nl_compat_link_set(struct sk_buff *skb, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - link = nla_nest_start(skb, TIPC_NLA_LINK); + link = nla_nest_start_noflag(skb, TIPC_NLA_LINK); if (!link) return -EMSGSIZE; if (nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name)) return -EMSGSIZE; - prop = nla_nest_start(skb, TIPC_NLA_LINK_PROP); + prop = nla_nest_start_noflag(skb, TIPC_NLA_LINK_PROP); if (!prop) return -EMSGSIZE; @@ -811,7 +813,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, name = (char *)TLV_DATA(msg->req); - link = nla_nest_start(skb, TIPC_NLA_LINK); + link = nla_nest_start_noflag(skb, TIPC_NLA_LINK); if (!link) return -EMSGSIZE; @@ -869,16 +871,18 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_NAME_TABLE]) return -EINVAL; - err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX, - attrs[TIPC_NLA_NAME_TABLE], NULL, NULL); + err = nla_parse_nested_deprecated(nt, TIPC_NLA_NAME_TABLE_MAX, + attrs[TIPC_NLA_NAME_TABLE], NULL, + NULL); if (err) return err; if (!nt[TIPC_NLA_NAME_TABLE_PUBL]) return -EINVAL; - err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, - nt[TIPC_NLA_NAME_TABLE_PUBL], NULL, NULL); + err = nla_parse_nested_deprecated(publ, TIPC_NLA_PUBL_MAX, + nt[TIPC_NLA_NAME_TABLE_PUBL], NULL, + NULL); if (err) return err; @@ -937,8 +941,8 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_PUBL]) return -EINVAL; - err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL], - NULL, NULL); + err = nla_parse_nested_deprecated(publ, TIPC_NLA_PUBL_MAX, + attrs[TIPC_NLA_PUBL], NULL, NULL); if (err) return err; @@ -973,7 +977,7 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock) return -EMSGSIZE; } - nest = nla_nest_start(args, TIPC_NLA_SOCK); + nest = nla_nest_start_noflag(args, TIPC_NLA_SOCK); if (!nest) { kfree_skb(args); return -EMSGSIZE; @@ -1007,8 +1011,8 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_SOCK]) return -EINVAL; - err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], - NULL, NULL); + err = nla_parse_nested_deprecated(sock, TIPC_NLA_SOCK_MAX, + attrs[TIPC_NLA_SOCK], NULL, NULL); if (err) return err; @@ -1019,8 +1023,9 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg, u32 node; struct nlattr *con[TIPC_NLA_CON_MAX + 1]; - err = nla_parse_nested(con, TIPC_NLA_CON_MAX, - sock[TIPC_NLA_SOCK_CON], NULL, NULL); + err = nla_parse_nested_deprecated(con, TIPC_NLA_CON_MAX, + sock[TIPC_NLA_SOCK_CON], + NULL, NULL); if (err) return err; @@ -1059,8 +1064,8 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_MEDIA]) return -EINVAL; - err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, - attrs[TIPC_NLA_MEDIA], NULL, NULL); + err = nla_parse_nested_deprecated(media, TIPC_NLA_MEDIA_MAX, + attrs[TIPC_NLA_MEDIA], NULL, NULL); if (err) return err; @@ -1079,8 +1084,8 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_NODE]) return -EINVAL; - err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE], - NULL, NULL); + err = nla_parse_nested_deprecated(node, TIPC_NLA_NODE_MAX, + attrs[TIPC_NLA_NODE], NULL, NULL); if (err) return err; @@ -1100,7 +1105,7 @@ static int tipc_nl_compat_net_set(struct tipc_nl_compat_cmd_doit *cmd, val = ntohl(*(__be32 *)TLV_DATA(msg->req)); - net = nla_nest_start(skb, TIPC_NLA_NET); + net = nla_nest_start_noflag(skb, TIPC_NLA_NET); if (!net) return -EMSGSIZE; @@ -1126,8 +1131,8 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg, if (!attrs[TIPC_NLA_NET]) return -EINVAL; - err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET], - NULL, NULL); + err = nla_parse_nested_deprecated(net, TIPC_NLA_NET_MAX, + attrs[TIPC_NLA_NET], NULL, NULL); if (err) return err; @@ -1300,6 +1305,7 @@ send: static const struct genl_ops tipc_genl_compat_ops[] = { { .cmd = TIPC_GENL_CMD, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = tipc_nl_compat_recv, }, }; diff --git a/net/tipc/node.c b/net/tipc/node.c index dd3b6dc17662..9e106d3ed187 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -375,14 +375,20 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, if (n->capabilities == capabilities) goto exit; /* Same node may come back with new capabilities */ - write_lock_bh(&n->lock); + tipc_node_write_lock(n); n->capabilities = capabilities; for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { l = n->links[bearer_id].link; if (l) tipc_link_update_caps(l, capabilities); } - write_unlock_bh(&n->lock); + tipc_node_write_unlock_fast(n); + + /* Calculate cluster capabilities */ + tn->capabilities = TIPC_NODE_CAPABILITIES; + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + tn->capabilities &= temp_node->capabilities; + } goto exit; } n = kzalloc(sizeof(*n), GFP_ATOMIC); @@ -433,6 +439,11 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr, break; } list_add_tail_rcu(&n->list, &temp_node->list); + /* Calculate cluster capabilities */ + tn->capabilities = TIPC_NODE_CAPABILITIES; + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + tn->capabilities &= temp_node->capabilities; + } trace_tipc_node_create(n, true, " "); exit: spin_unlock_bh(&tn->node_list_lock); @@ -589,6 +600,7 @@ static void tipc_node_clear_links(struct tipc_node *node) */ static bool tipc_node_cleanup(struct tipc_node *peer) { + struct tipc_node *temp_node; struct tipc_net *tn = tipc_net(peer->net); bool deleted = false; @@ -604,6 +616,13 @@ static bool tipc_node_cleanup(struct tipc_node *peer) deleted = true; } tipc_node_write_unlock(peer); + + /* Calculate cluster capabilities */ + tn->capabilities = TIPC_NODE_CAPABILITIES; + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + tn->capabilities &= temp_node->capabilities; + } + spin_unlock_bh(&tn->node_list_lock); return deleted; } @@ -695,7 +714,6 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, *slot0 = bearer_id; *slot1 = bearer_id; tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT); - n->failover_sent = false; n->action_flags |= TIPC_NOTIFY_NODE_UP; tipc_link_set_active(nl, true); tipc_bcast_add_peer(n->net, nl, xmitq); @@ -738,6 +756,45 @@ static void tipc_node_link_up(struct tipc_node *n, int bearer_id, } /** + * tipc_node_link_failover() - start failover in case "half-failover" + * + * This function is only called in a very special situation where link + * failover can be already started on peer node but not on this node. + * This can happen when e.g. + * 1. Both links <1A-2A>, <1B-2B> down + * 2. Link endpoint 2A up, but 1A still down (e.g. due to network + * disturbance, wrong session, etc.) + * 3. Link <1B-2B> up + * 4. Link endpoint 2A down (e.g. due to link tolerance timeout) + * 5. Node B starts failover onto link <1B-2B> + * + * ==> Node A does never start link/node failover! + * + * @n: tipc node structure + * @l: link peer endpoint failingover (- can be NULL) + * @tnl: tunnel link + * @xmitq: queue for messages to be xmited on tnl link later + */ +static void tipc_node_link_failover(struct tipc_node *n, struct tipc_link *l, + struct tipc_link *tnl, + struct sk_buff_head *xmitq) +{ + /* Avoid to be "self-failover" that can never end */ + if (!tipc_link_is_up(tnl)) + return; + + tipc_link_fsm_evt(tnl, LINK_SYNCH_END_EVT); + tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT); + + n->sync_point = tipc_link_rcv_nxt(tnl) + (U16_MAX / 2 - 1); + tipc_link_failover_prepare(l, tnl, xmitq); + + if (l) + tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT); +} + +/** * __tipc_node_link_down - handle loss of link */ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, @@ -1340,7 +1397,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node) if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NODE); if (!attrs) goto msg_full; @@ -1656,14 +1713,16 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl), tipc_link_inputq(l)); } + /* If parallel link was already down, and this happened before - * the tunnel link came up, FAILOVER was never sent. Ensure that - * FAILOVER is sent to get peer out of NODE_FAILINGOVER state. + * the tunnel link came up, node failover was never started. + * Ensure that a FAILOVER_MSG is sent to get peer out of + * NODE_FAILINGOVER state, also this node must accept + * TUNNEL_MSGs from peer. */ - if (n->state != NODE_FAILINGOVER && !n->failover_sent) { - tipc_link_create_dummy_tnl_msg(l, xmitq); - n->failover_sent = true; - } + if (n->state != NODE_FAILINGOVER) + tipc_node_link_failover(n, pl, l, xmitq); + /* If pkts arrive out of order, use lowest calculated syncpt */ if (less(syncpt, n->sync_point)) n->sync_point = syncpt; @@ -1866,9 +1925,9 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_NET]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX, - info->attrs[TIPC_NLA_NET], tipc_nl_net_policy, - info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX, + info->attrs[TIPC_NLA_NET], + tipc_nl_net_policy, info->extack); if (err) return err; @@ -2024,9 +2083,9 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX, - info->attrs[TIPC_NLA_LINK], - tipc_nl_link_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX, + info->attrs[TIPC_NLA_LINK], + tipc_nl_link_policy, info->extack); if (err) return err; @@ -2100,9 +2159,9 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX, - info->attrs[TIPC_NLA_LINK], - tipc_nl_link_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX, + info->attrs[TIPC_NLA_LINK], + tipc_nl_link_policy, info->extack); if (err) return err; @@ -2165,9 +2224,9 @@ int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX, - info->attrs[TIPC_NLA_LINK], - tipc_nl_link_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX, + info->attrs[TIPC_NLA_LINK], + tipc_nl_link_policy, info->extack); if (err) return err; @@ -2305,9 +2364,10 @@ int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[TIPC_NLA_MON]) return -EINVAL; - err = nla_parse_nested(attrs, TIPC_NLA_MON_MAX, - info->attrs[TIPC_NLA_MON], - tipc_nl_monitor_policy, info->extack); + err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MON_MAX, + info->attrs[TIPC_NLA_MON], + tipc_nl_monitor_policy, + info->extack); if (err) return err; @@ -2334,7 +2394,7 @@ static int __tipc_nl_add_monitor_prop(struct net *net, struct tipc_nl_msg *msg) if (!hdr) return -EMSGSIZE; - attrs = nla_nest_start(msg->skb, TIPC_NLA_MON); + attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON); if (!attrs) goto msg_full; @@ -2425,9 +2485,10 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb, if (!attrs[TIPC_NLA_MON]) return -EINVAL; - err = nla_parse_nested(mon, TIPC_NLA_MON_MAX, - attrs[TIPC_NLA_MON], - tipc_nl_monitor_policy, NULL); + err = nla_parse_nested_deprecated(mon, TIPC_NLA_MON_MAX, + attrs[TIPC_NLA_MON], + tipc_nl_monitor_policy, + NULL); if (err) return err; diff --git a/net/tipc/node.h b/net/tipc/node.h index 4f59a30e989a..c0bf49ea3de4 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -51,7 +51,9 @@ enum { TIPC_BLOCK_FLOWCTL = (1 << 3), TIPC_BCAST_RCAST = (1 << 4), TIPC_NODE_ID128 = (1 << 5), - TIPC_LINK_PROTO_SEQNO = (1 << 6) + TIPC_LINK_PROTO_SEQNO = (1 << 6), + TIPC_MCAST_RBCTL = (1 << 7), + TIPC_GAP_ACK_BLOCK = (1 << 8) }; #define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \ @@ -60,7 +62,9 @@ enum { TIPC_BCAST_RCAST | \ TIPC_BLOCK_FLOWCTL | \ TIPC_NODE_ID128 | \ - TIPC_LINK_PROTO_SEQNO) + TIPC_LINK_PROTO_SEQNO | \ + TIPC_MCAST_RBCTL | \ + TIPC_GAP_ACK_BLOCK) #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b542f14ed444..145e4decb0c9 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -485,6 +485,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk_set_unreturnable(tsk, true); if (sock->type == SOCK_DGRAM) tsk_set_unreliable(tsk, true); + __skb_queue_head_init(&tsk->mc_method.deferredq); } trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " "); @@ -582,6 +583,7 @@ static int tipc_release(struct socket *sock) sk->sk_shutdown = SHUTDOWN_MASK; tipc_sk_leave(tsk); tipc_sk_withdraw(tsk, 0, NULL); + __skb_queue_purge(&tsk->mc_method.deferredq); sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); @@ -2149,6 +2151,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct net *net = sock_net(sk); struct sk_buff_head inputq; + int mtyp = msg_type(hdr); int limit, err = TIPC_OK; trace_tipc_sk_filter_rcv(sk, skb, TIPC_DUMP_ALL, " "); @@ -2162,6 +2165,9 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, if (unlikely(grp)) tipc_group_filter_msg(grp, &inputq, xmitq); + if (unlikely(!grp) && mtyp == TIPC_MCAST_MSG) + tipc_mcast_filter_msg(net, &tsk->mc_method.deferredq, &inputq); + /* Validate and add to receive buffer if there is space */ while ((skb = __skb_dequeue(&inputq))) { hdr = buf_msg(skb); @@ -3064,6 +3070,9 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); break; + case TIPC_SOCK_RECVQ_USED: + value = sk_rmem_alloc_get(sk); + break; case TIPC_GROUP_JOIN: seq.type = 0; if (tsk->group) @@ -3264,7 +3273,7 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) peer_node = tsk_peer_node(tsk); peer_port = tsk_peer_port(tsk); - nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON); + nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON); if (!nest) return -EMSGSIZE; @@ -3323,7 +3332,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb, if (!hdr) goto msg_cancel; - attrs = nla_nest_start(skb, TIPC_NLA_SOCK); + attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK); if (!attrs) goto genlmsg_cancel; @@ -3428,7 +3437,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, if (!(sk_filter_state & (1 << sk->sk_state))) return 0; - attrs = nla_nest_start(skb, TIPC_NLA_SOCK); + attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK); if (!attrs) goto msg_cancel; @@ -3446,7 +3455,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, TIPC_NLA_SOCK_PAD)) goto attr_msg_cancel; - stat = nla_nest_start(skb, TIPC_NLA_SOCK_STAT); + stat = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_STAT); if (!stat) goto attr_msg_cancel; @@ -3503,7 +3512,7 @@ static int __tipc_nl_add_sk_publ(struct sk_buff *skb, if (!hdr) goto msg_cancel; - attrs = nla_nest_start(skb, TIPC_NLA_PUBL); + attrs = nla_nest_start_noflag(skb, TIPC_NLA_PUBL); if (!attrs) goto genlmsg_cancel; @@ -3590,9 +3599,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!attrs[TIPC_NLA_SOCK]) return -EINVAL; - err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, - attrs[TIPC_NLA_SOCK], - tipc_nl_sock_policy, NULL); + err = nla_parse_nested_deprecated(sock, TIPC_NLA_SOCK_MAX, + attrs[TIPC_NLA_SOCK], + tipc_nl_sock_policy, NULL); if (err) return err; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 4d85d71f16e2..7fc02d84c4f1 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -44,7 +44,7 @@ #include <net/sock.h> #include <net/ip.h> #include <net/udp_tunnel.h> -#include <net/addrconf.h> +#include <net/ipv6_stubs.h> #include <linux/tipc_netlink.h> #include "core.h" #include "addr.h" @@ -354,25 +354,21 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) skb_pull(skb, sizeof(struct udphdr)); hdr = buf_msg(skb); - rcu_read_lock(); - b = rcu_dereference_rtnl(ub->bearer); + b = rcu_dereference(ub->bearer); if (!b) - goto rcu_out; + goto out; if (b && test_bit(0, &b->up)) { tipc_rcv(sock_net(sk), skb, b); - rcu_read_unlock(); return 0; } if (unlikely(msg_user(hdr) == LINK_CONFIG)) { err = tipc_udp_rcast_disc(b, skb); if (err) - goto rcu_out; + goto out; } -rcu_out: - rcu_read_unlock(); out: kfree_skb(skb); return 0; @@ -451,9 +447,9 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) if (!attrs[TIPC_NLA_BEARER]) return -EINVAL; - err = nla_parse_nested(battrs, TIPC_NLA_BEARER_MAX, - attrs[TIPC_NLA_BEARER], - tipc_nl_bearer_policy, NULL); + err = nla_parse_nested_deprecated(battrs, TIPC_NLA_BEARER_MAX, + attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy, NULL); if (err) return err; @@ -527,7 +523,7 @@ int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b) if (!ub) return -ENODEV; - nest = nla_nest_start(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); + nest = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); if (!nest) goto msg_full; @@ -605,8 +601,7 @@ int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr) struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; struct udp_media_addr *dst; - if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr, - tipc_nl_udp_policy, NULL)) + if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy, NULL)) return -EINVAL; if (!opts[TIPC_NLA_UDP_REMOTE]) @@ -659,9 +654,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) goto err; - if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, - attrs[TIPC_NLA_BEARER_UDP_OPTS], - tipc_nl_udp_policy, NULL)) + if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attrs[TIPC_NLA_BEARER_UDP_OPTS], tipc_nl_udp_policy, NULL)) goto err; if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) { |