Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig
index e450212..b83e16a 100644
--- a/net/tipc/Kconfig
+++ b/net/tipc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# TIPC configuration
#
@@ -16,7 +17,7 @@
This protocol support is also available as a module ( = code which
can be inserted in and removed from the running kernel whenever you
want). The module will be called tipc. If you want to compile it
- as a module, say M here and read <file:Documentation/kbuild/modules.txt>.
+ as a module, say M here and read <file:Documentation/kbuild/modules.rst>.
If in doubt, say N.
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index aca168f..c86aba0 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -9,7 +9,9 @@
core.o link.o discover.o msg.o \
name_distr.o subscr.o monitor.o name_table.o net.o \
netlink.o netlink_compat.o node.o socket.o eth_media.o \
- topsrv.o socket.o group.o
+ topsrv.o socket.o group.o trace.o
+
+CFLAGS_trace.o += -I$(src)
tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o
tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o
diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index b88d48d..0f1eaed 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -75,6 +75,7 @@
tipc_set_node_id(net, node_id);
}
tn->trial_addr = addr;
+ tn->addr_trial_end = jiffies;
pr_info("32-bit node address hash set to %x\n", addr);
}
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index d802654..6ef1abd 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -54,7 +54,9 @@
* @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 @@
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;
};
@@ -181,7 +185,7 @@
}
/* We have to transmit across all bearers */
- skb_queue_head_init(&_xmitq);
+ __skb_queue_head_init(&_xmitq);
for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
if (!bb->dests[bearer_id])
continue;
@@ -216,9 +220,24 @@
}
/* 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;
}
@@ -237,7 +256,7 @@
struct sk_buff_head xmitq;
int rc = 0;
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
tipc_bcast_lock(net);
if (tipc_link_bc_peers(l))
rc = tipc_link_xmit(l, pkts, &xmitq);
@@ -267,7 +286,7 @@
u32 dnode, selector;
selector = msg_link_selector(buf_msg(skb_peek(pkts)));
- skb_queue_head_init(&_pkts);
+ __skb_queue_head_init(&_pkts);
list_for_each_entry_safe(dst, tmp, &dests->list, list) {
dnode = dst->node;
@@ -281,6 +300,63 @@
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_inner_hdr(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
@@ -296,10 +372,13 @@
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);
- skb_queue_head_init(&localq);
+ __skb_queue_head_init(&localq);
/* Clone packets before they are consumed by next call */
if (dests->local && !tipc_msg_reassemble(pkts, &localq)) {
@@ -309,14 +388,28 @@
/* 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_inner_hdr(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
rc = tipc_bcast_xmit(net, pkts, cong_link_cnt);
}
- if (dests->local)
+ if (dests->local) {
+ tipc_loopback_trace(net, &localq);
tipc_sk_mcast_rcv(net, &localq, &inputq);
+ }
exit:
/* This queue should normally be empty by now */
__skb_queue_purge(pkts);
@@ -485,10 +578,63 @@
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 +644,28 @@
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;
+ }
- win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ 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);
+ }
- return tipc_bc_link_set_queue_limits(net, win);
+ 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);
+ }
+
+ 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 err;
}
int tipc_bcast_init(struct net *net)
@@ -529,7 +691,7 @@
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 +738,108 @@
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 751530a..dadad95 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -48,6 +48,10 @@
#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 @@
/* 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_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 645c160..0214aa1 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -43,6 +43,7 @@
#include "bcast.h"
#include "netlink.h"
#include "udp_media.h"
+#include "trace.h"
#define MAX_ADDR_STR 60
@@ -61,7 +62,7 @@
{
struct tipc_net *tn = tipc_net(net);
- return rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
+ return rcu_dereference(tn->bearer_list[bearer_id]);
}
static void bearer_disable(struct net *net, struct tipc_bearer *b);
@@ -99,7 +100,7 @@
/**
* tipc_media_addr_printf - record media address in print buffer
*/
-void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
+int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
{
char addr_str[MAX_ADDR_STR];
struct tipc_media *m;
@@ -114,9 +115,10 @@
ret = scnprintf(buf, len, "UNKNOWN(%u)", a->media_id);
for (i = 0; i < sizeof(a->value); i++)
- ret += scnprintf(buf - ret, len + ret,
- "-%02x", a->value[i]);
+ ret += scnprintf(buf + ret, len - ret,
+ "-%x", a->value[i]);
}
+ return ret;
}
/**
@@ -208,7 +210,7 @@
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
+ b = rcu_dereference(tn->bearer_list[bearer_id]);
if (b)
tipc_disc_add_dest(b->disc);
rcu_read_unlock();
@@ -220,7 +222,7 @@
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
+ b = rcu_dereference(tn->bearer_list[bearer_id]);
if (b)
tipc_disc_remove_dest(b->disc);
rcu_read_unlock();
@@ -317,7 +319,6 @@
res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
if (res) {
bearer_disable(net, b);
- kfree(b);
errstr = "failed to create discoverer";
goto rejected;
}
@@ -388,6 +389,11 @@
dev_put(dev);
return -EINVAL;
}
+ if (dev == net->loopback_dev) {
+ dev_put(dev);
+ pr_info("Enabling <%s> not permitted\n", b->name);
+ return -EINVAL;
+ }
/* Autoconfigure own node identity if needed */
if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) {
@@ -443,7 +449,7 @@
struct net_device *dev;
int delta;
- dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr);
+ dev = (struct net_device *)rcu_dereference(b->media_ptr);
if (!dev)
return 0;
@@ -480,7 +486,7 @@
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(tipc_net(net)->bearer_list[bearer_id]);
+ b = rcu_dereference(tipc_net(net)->bearer_list[bearer_id]);
if (b)
mtu = b->mtu;
rcu_read_unlock();
@@ -573,11 +579,11 @@
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(dev->tipc_ptr) ?:
- rcu_dereference_rtnl(orig_dev->tipc_ptr);
+ b = rcu_dereference(dev->tipc_ptr) ?:
+ rcu_dereference(orig_dev->tipc_ptr);
if (likely(b && test_bit(0, &b->up) &&
(skb->pkt_type <= PACKET_MULTICAST))) {
- skb->next = NULL;
+ skb_mark_not_on_list(skb);
tipc_rcv(dev_net(b->pt.dev), skb, b);
rcu_read_unlock();
return NET_RX_SUCCESS;
@@ -607,6 +613,7 @@
if (!b)
return NOTIFY_DONE;
+ trace_tipc_l2_device_event(dev, b, evt);
switch (evt) {
case NETDEV_CHANGE:
if (netif_carrier_ok(dev) && netif_oper_up(dev)) {
@@ -672,6 +679,65 @@
}
}
+void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts)
+{
+ struct net_device *dev = net->loopback_dev;
+ struct sk_buff *skb, *_skb;
+ int exp;
+
+ skb_queue_walk(pkts, _skb) {
+ skb = pskb_copy(_skb, GFP_ATOMIC);
+ if (!skb)
+ continue;
+
+ exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb));
+ if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ continue;
+ }
+
+ skb_reset_network_header(skb);
+ dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr,
+ dev->dev_addr, skb->len);
+ skb->dev = dev;
+ skb->pkt_type = PACKET_HOST;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->protocol = eth_type_trans(skb, dev);
+ netif_rx_ni(skb);
+ }
+}
+
+static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt, struct net_device *od)
+{
+ consume_skb(skb);
+ return NET_RX_SUCCESS;
+}
+
+int tipc_attach_loopback(struct net *net)
+{
+ struct net_device *dev = net->loopback_dev;
+ struct tipc_net *tn = tipc_net(net);
+
+ if (!dev)
+ return -ENODEV;
+
+ dev_hold(dev);
+ tn->loopback_pt.dev = dev;
+ tn->loopback_pt.type = htons(ETH_P_TIPC);
+ tn->loopback_pt.func = tipc_loopback_rcv_pkt;
+ dev_add_pack(&tn->loopback_pt);
+ return 0;
+}
+
+void tipc_detach_loopback(struct net *net)
+{
+ struct tipc_net *tn = tipc_net(net);
+
+ dev_remove_pack(&tn->loopback_pt);
+ dev_put(net->loopback_dev);
+}
+
/* Caller should hold rtnl_lock to protect the bearer */
static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
struct tipc_bearer *bearer, int nlflags)
@@ -685,14 +751,14 @@
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))
@@ -774,9 +840,9 @@
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;
@@ -823,9 +889,9 @@
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;
@@ -868,9 +934,9 @@
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;
@@ -919,9 +985,9 @@
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;
@@ -962,9 +1028,9 @@
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;
@@ -1031,14 +1097,14 @@
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))
@@ -1105,9 +1171,9 @@
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;
@@ -1153,9 +1219,9 @@
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/bearer.h b/net/tipc/bearer.h
index 394290c..ea0f3c4 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -207,7 +207,7 @@
int tipc_media_set_priority(const char *name, u32 new_value);
int tipc_media_set_window(const char *name, u32 new_value);
-void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
+int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
struct nlattr *attrs[]);
void tipc_disable_l2_media(struct tipc_bearer *b);
@@ -232,6 +232,16 @@
struct tipc_media_addr *dst);
void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq);
+void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts);
+int tipc_attach_loopback(struct net *net);
+void tipc_detach_loopback(struct net *net);
+
+static inline void tipc_loopback_trace(struct net *net,
+ struct sk_buff_head *pkts)
+{
+ if (unlikely(dev_nit_active(net->loopback_dev)))
+ tipc_clone_to_loopback(net, pkts);
+}
/* check if device MTU is too low for tipc headers */
static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve)
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5b38f51..8f35060 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -34,8 +34,6 @@
* POSSIBILITY OF SUCH DAMAGE.
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include "core.h"
#include "name_table.h"
#include "subscr.h"
@@ -43,6 +41,7 @@
#include "net.h"
#include "socket.h"
#include "bcast.h"
+#include "node.h"
#include <linux/module.h>
@@ -59,6 +58,7 @@
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;
@@ -75,19 +75,18 @@
goto out_nametbl;
INIT_LIST_HEAD(&tn->dist_queue);
- err = tipc_topsrv_start(net);
- if (err)
- goto out_subscr;
err = tipc_bcast_init(net);
if (err)
goto out_bclink;
+ err = tipc_attach_loopback(net);
+ if (err)
+ goto out_bclink;
+
return 0;
out_bclink:
- tipc_bcast_stop(net);
-out_subscr:
tipc_nametbl_stop(net);
out_nametbl:
tipc_sk_rht_destroy(net);
@@ -97,7 +96,7 @@
static void __net_exit tipc_exit_net(struct net *net)
{
- tipc_topsrv_stop(net);
+ tipc_detach_loopback(net);
tipc_net_stop(net);
tipc_bcast_stop(net);
tipc_nametbl_stop(net);
@@ -111,6 +110,11 @@
.size = sizeof(struct tipc_net),
};
+static struct pernet_operations tipc_topsrv_net_ops = {
+ .init = tipc_topsrv_init_net,
+ .exit = tipc_topsrv_exit_net,
+};
+
static int __init tipc_init(void)
{
int err;
@@ -129,18 +133,22 @@
if (err)
goto out_netlink_compat;
- err = tipc_socket_init();
- if (err)
- goto out_socket;
-
err = tipc_register_sysctl();
if (err)
goto out_sysctl;
- err = register_pernet_subsys(&tipc_net_ops);
+ err = register_pernet_device(&tipc_net_ops);
if (err)
goto out_pernet;
+ err = tipc_socket_init();
+ if (err)
+ goto out_socket;
+
+ err = register_pernet_device(&tipc_topsrv_net_ops);
+ if (err)
+ goto out_pernet_topsrv;
+
err = tipc_bearer_setup();
if (err)
goto out_bearer;
@@ -148,12 +156,14 @@
pr_info("Started in single node mode\n");
return 0;
out_bearer:
- unregister_pernet_subsys(&tipc_net_ops);
+ unregister_pernet_device(&tipc_topsrv_net_ops);
+out_pernet_topsrv:
+ tipc_socket_stop();
+out_socket:
+ unregister_pernet_device(&tipc_net_ops);
out_pernet:
tipc_unregister_sysctl();
out_sysctl:
- tipc_socket_stop();
-out_socket:
tipc_netlink_compat_stop();
out_netlink_compat:
tipc_netlink_stop();
@@ -165,10 +175,11 @@
static void __exit tipc_exit(void)
{
tipc_bearer_cleanup();
- unregister_pernet_subsys(&tipc_net_ops);
+ unregister_pernet_device(&tipc_topsrv_net_ops);
+ tipc_socket_stop();
+ unregister_pernet_device(&tipc_net_ops);
tipc_netlink_stop();
tipc_netlink_compat_stop();
- tipc_socket_stop();
tipc_unregister_sysctl();
pr_info("Deactivated\n");
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 8020a6c..3042f65 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -60,6 +60,12 @@
#include <linux/rhashtable.h>
#include <net/genetlink.h>
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
struct tipc_node;
struct tipc_bearer;
struct tipc_bc_base;
@@ -122,6 +128,12 @@
/* Topology subscription server */
struct tipc_topsrv *topsrv;
atomic_t subscription_count;
+
+ /* Cluster capabilities */
+ u16 capabilities;
+
+ /* Tracing of node internal messages */
+ struct packet_type loopback_pt;
};
static inline struct tipc_net *tipc_net(struct net *net)
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 06fee14..89257e2 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -199,7 +199,7 @@
struct tipc_member *m, *tmp;
struct sk_buff_head xmitq;
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, &xmitq);
tipc_group_update_member(m, 0);
@@ -218,6 +218,7 @@
rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
+ __skb_queue_purge(&m->deferredq);
list_del(&m->list);
kfree(m);
}
@@ -434,7 +435,7 @@
return true;
if (state == MBR_PENDING && adv == ADV_IDLE)
return true;
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq);
tipc_node_distr_xmit(grp->net, &xmitq);
return true;
@@ -917,7 +918,10 @@
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;
if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID,
grp->type) ||
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 836727e..999eab5 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -43,6 +43,7 @@
#include "discover.h"
#include "netlink.h"
#include "monitor.h"
+#include "trace.h"
#include <linux/pkt_sched.h>
@@ -105,9 +106,6 @@
* @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
- * @last_retransmitted: sequence number of most recently retransmitted message
- * @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
@@ -150,6 +148,7 @@
/* Failover/synch */
u16 drop_point;
struct sk_buff *failover_reasm_skb;
+ struct sk_buff_head failover_deferdq;
/* Max packet negotiation */
u16 mtu;
@@ -161,12 +160,10 @@
struct {
u16 len;
u16 limit;
+ struct sk_buff *target_bskb;
} backlog[5];
u16 snd_nxt;
- u16 last_retransm;
u16 window;
- u16 stale_cnt;
- unsigned long stale_limit;
/* Reception */
u16 rcv_nxt;
@@ -180,15 +177,13 @@
/* Fragmentation/reassembly */
struct sk_buff *reasm_buf;
+ struct sk_buff *reasm_tnlmsg;
/* Broadcast */
u16 ackers;
u16 acked;
struct tipc_link *bc_rcvlink;
struct tipc_link *bc_sndlink;
- unsigned long prev_retr;
- u16 prev_from;
- u16 prev_to;
u8 nack_state;
bool bc_peer_is_up;
@@ -210,7 +205,8 @@
BC_NACK_SND_SUPPRESS,
};
-#define TIPC_BC_RETR_LIMIT 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
@@ -248,6 +244,10 @@
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)
@@ -359,9 +359,11 @@
rcv_l->bc_peer_is_up = true;
rcv_l->state = LINK_ESTABLISHED;
tipc_link_bc_ack_rcv(rcv_l, ack, xmitq);
+ trace_tipc_link_reset(rcv_l, TIPC_DUMP_ALL, "bclink removed!");
tipc_link_reset(rcv_l);
rcv_l->state = LINK_RESET;
if (!snd_l->ackers) {
+ trace_tipc_link_reset(snd_l, TIPC_DUMP_ALL, "zero ackers!");
tipc_link_reset(snd_l);
snd_l->state = LINK_RESET;
__skb_queue_purge(xmitq);
@@ -493,6 +495,7 @@
__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;
@@ -525,6 +528,7 @@
l = *link;
strcpy(l->name, tipc_bclink_name);
+ trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!");
tipc_link_reset(l);
l->state = LINK_RESET;
l->ackers = 0;
@@ -549,6 +553,7 @@
int tipc_link_fsm_evt(struct tipc_link *l, int evt)
{
int rc = 0;
+ int old_state = l->state;
switch (l->state) {
case LINK_RESETTING:
@@ -695,10 +700,12 @@
default:
pr_err("Unknown FSM state %x in %s\n", l->state, l->name);
}
+ trace_tipc_link_fsm(l->name, old_state, l->state, evt);
return rc;
illegal_evt:
pr_err("Illegal FSM event %x in state %x on link %s\n",
evt, l->state, l->name);
+ trace_tipc_link_fsm(l->name, old_state, l->state, evt);
return rc;
}
@@ -723,7 +730,7 @@
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++;
@@ -743,6 +750,18 @@
l->stats.msg_length_profile[6]++;
}
+/**
+ * tipc_link_too_silent - check if link is "too silent"
+ * @l: tipc link to be checked
+ *
+ * Returns true if the link 'silent_intv_cnt' is about to reach the
+ * 'abort_limit' value, otherwise false
+ */
+bool tipc_link_too_silent(struct tipc_link *l)
+{
+ return (l->silent_intv_cnt + 2 > l->abort_limit);
+}
+
/* tipc_link_timeout - perform periodic task as instructed from node timeout
*/
int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
@@ -756,6 +775,8 @@
u16 bc_acked = l->bc_rcvlink->acked;
struct tipc_mon_state *mstate = &l->mon_state;
+ trace_tipc_link_timeout(l, TIPC_DUMP_NONE, " ");
+ trace_tipc_link_too_silent(l, TIPC_DUMP_ALL, " ");
switch (l->state) {
case LINK_ESTABLISHED:
case LINK_SYNCHING:
@@ -818,6 +839,7 @@
TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
skb_queue_tail(&l->wakeupq, skb);
l->stats.link_congs++;
+ trace_tipc_link_conges(l, TIPC_DUMP_ALL, "wakeup scheduled!");
return -ELINKCONG;
}
@@ -829,27 +851,43 @@
*/
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_walk_safe(&l->wakeupq, skb, tmp) {
+ __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(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;
@@ -864,14 +902,16 @@
__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;
@@ -881,7 +921,6 @@
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);
@@ -909,12 +948,15 @@
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;
+ struct sk_buff *skb, *_skb, **tskb;
int pkt_cnt = skb_queue_len(list);
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;
}
@@ -943,11 +985,14 @@
if (likely(skb_queue_len(transmq) < maxwin)) {
_skb = skb_clone(skb, GFP_ATOMIC);
if (!_skb) {
- skb_queue_purge(list);
+ __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 = TIPC_BC_RETR_LIM;
__skb_queue_tail(xmitq, _skb);
TIPC_SKB_CB(skb)->ackers = l->ackers;
l->rcv_unacked = 0;
@@ -955,19 +1000,21 @@
seqno++;
continue;
}
- if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) {
+ tskb = &l->backlog[imp].target_bskb;
+ if (tipc_msg_bundle(*tskb, hdr, mtu)) {
kfree_skb(__skb_dequeue(list));
l->stats.sent_bundled++;
continue;
}
- if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) {
+ if (tipc_msg_make_bundle(tskb, hdr, mtu, l->addr)) {
kfree_skb(__skb_dequeue(list));
- __skb_queue_tail(backlogq, bskb);
- l->backlog[msg_importance(buf_msg(bskb))].len++;
+ __skb_queue_tail(backlogq, *tskb);
+ l->backlog[imp].len++;
l->stats.sent_bundled++;
l->stats.sent_bundles++;
continue;
}
+ l->backlog[imp].target_bskb = NULL;
l->backlog[imp].len += skb_queue_len(list);
skb_queue_splice_tail_init(list, backlogq);
}
@@ -983,6 +1030,7 @@
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);
@@ -993,8 +1041,15 @@
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 = TIPC_BC_RETR_LIM;
+
__skb_queue_tail(xmitq, _skb);
TIPC_SKB_CB(skb)->ackers = l->ackers;
msg_set_seqno(hdr, seqno);
@@ -1007,47 +1062,84 @@
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)))
+ 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;
+ if (less(to, from))
+ return 0;
- /* Detect repeated retransmit failures on same packet */
- if (r->last_retransm != buf_seqno(skb)) {
- r->last_retransm = buf_seqno(skb);
- 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);
- if (link_is_bc_sndlink(l))
- return TIPC_LINK_DOWN_EVT;
- return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
- }
+ trace_tipc_link_retrans(r, from, to, &l->transmq);
+
+ if (link_retransmit_failure(l, r, &rc))
+ return rc;
skb_queue_walk(&l->transmq, skb) {
hdr = buf_msg(skb);
@@ -1055,7 +1147,11 @@
continue;
if (more(msg_seqno(hdr), to))
break;
- _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, LL_MAX_HEADER + MIN_H_SIZE, GFP_ATOMIC);
if (!_skb)
return 0;
hdr = buf_msg(_skb);
@@ -1064,6 +1160,10 @@
_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;
}
@@ -1088,7 +1188,7 @@
skb_queue_tail(mc_inputq, skb);
return true;
}
- /* else: fall through */
+ /* fall through */
case CONN_MANAGER:
skb_queue_tail(inputq, skb);
return true;
@@ -1107,7 +1207,7 @@
default:
pr_warn("Dropping received illegal msg type\n");
kfree_skb(skb);
- return false;
+ return true;
};
}
@@ -1116,34 +1216,14 @@
* 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);
@@ -1168,11 +1248,83 @@
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;
@@ -1188,6 +1340,121 @@
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, LL_MAX_HEADER + 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++;
+
+ /* 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
@@ -1242,6 +1509,7 @@
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)) {
@@ -1252,7 +1520,7 @@
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;
}
@@ -1266,29 +1534,29 @@
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++;
@@ -1297,7 +1565,6 @@
/* 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);
@@ -1313,13 +1580,16 @@
/* 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:
@@ -1340,6 +1610,7 @@
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))
@@ -1352,8 +1623,8 @@
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;
@@ -1380,13 +1651,19 @@
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 {
/* RESET_MSG or ACTIVATE_MSG */
+ if (mtyp == ACTIVATE_MSG) {
+ msg_set_dest_session_valid(hdr, 1);
+ msg_set_dest_session(hdr, l->peer_session);
+ }
msg_set_max_pkt(hdr, l->advertised_mtu);
strcpy(data, l->if_name);
msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
@@ -1398,6 +1675,7 @@
l->stats.sent_nacks++;
skb->priority = TC_PRIO_CONTROL;
__skb_queue_tail(xmitq, skb);
+ trace_tipc_proto_build(skb, false, l->name);
}
void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
@@ -1409,7 +1687,7 @@
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);
@@ -1436,17 +1714,22 @@
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);
+ __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,
@@ -1456,14 +1739,43 @@
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);
+ /* 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;
+ }
+
/* 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:
@@ -1473,6 +1785,39 @@
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) {
@@ -1488,12 +1833,60 @@
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 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.
+ */
+ 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);
}
}
@@ -1547,6 +1940,7 @@
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);
@@ -1557,10 +1951,12 @@
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;
+ trace_tipc_proto_rcv(skb, false, l->name);
if (tipc_link_is_blocked(l) || !xmitq)
goto exit;
@@ -1571,8 +1967,11 @@
hdr = buf_msg(skb);
data = msg_data(hdr);
- if (!tipc_link_validate_msg(l, hdr))
+ if (!tipc_link_validate_msg(l, hdr)) {
+ trace_tipc_skb_dump(skb, false, "PROTO invalid (1)!");
+ trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (1)!");
goto exit;
+ }
switch (mtyp) {
case RESET_MSG:
@@ -1599,6 +1998,17 @@
rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
break;
}
+
+ /* If this endpoint was re-created while peer was ESTABLISHING
+ * it doesn't know current session number. Force re-synch.
+ */
+ if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) &&
+ l->session != msg_dest_session(hdr)) {
+ if (less(l->session, msg_dest_session(hdr)))
+ l->session = msg_dest_session(hdr) + 1;
+ break;
+ }
+
/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
if (mtyp == RESET_MSG || !link_is_up(l))
rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
@@ -1639,7 +2049,17 @@
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 */
@@ -1648,13 +2068,12 @@
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)))
@@ -1737,42 +2156,6 @@
l->rcv_nxt = peers_snd_nxt;
}
-/* link_bc_retr eval()- check if the indicated range can be retransmitted now
- * - Adjust permitted range if there is overlap with previous retransmission
- */
-static bool link_bc_retr_eval(struct tipc_link *l, u16 *from, u16 *to)
-{
- unsigned long elapsed = jiffies_to_msecs(jiffies - l->prev_retr);
-
- if (less(*to, *from))
- return false;
-
- /* New retransmission request */
- if ((elapsed > TIPC_BC_RETR_LIMIT) ||
- less(*to, l->prev_from) || more(*from, l->prev_to)) {
- l->prev_from = *from;
- l->prev_to = *to;
- l->prev_retr = jiffies;
- return true;
- }
-
- /* Inside range of previous retransmit */
- if (!less(*from, l->prev_from) && !more(*to, l->prev_to))
- return false;
-
- /* Fully or partially outside previous range => exclude overlap */
- if (less(*from, l->prev_from)) {
- *to = l->prev_from - 1;
- l->prev_from = *from;
- }
- if (more(*to, l->prev_to)) {
- *from = l->prev_to + 1;
- l->prev_to = *to;
- }
- l->prev_retr = jiffies;
- return true;
-}
-
/* tipc_link_bc_sync_rcv - update rcv link according to peer's send state
*/
int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
@@ -1803,8 +2186,7 @@
if (more(peers_snd_nxt, l->rcv_nxt + l->window))
return rc;
- if (link_bc_retr_eval(snd_l, &from, &to))
- 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))
@@ -1852,6 +2234,7 @@
if (!more(acked, l->acked))
return;
+ trace_tipc_link_bc_ack(l, l->acked, acked, &snd_l->transmq);
/* Skip over packets peer has already acked */
skb_queue_walk(&snd_l->transmq, skb) {
if (more(buf_seqno(skb), l->acked))
@@ -1899,7 +2282,7 @@
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;
}
@@ -1950,8 +2333,8 @@
{
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;
@@ -2030,7 +2413,7 @@
(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;
@@ -2062,7 +2445,7 @@
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;
@@ -2084,7 +2467,7 @@
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))
@@ -2151,7 +2534,7 @@
(stats->accu_queue_sz / stats->queue_sz_counts) : 0}
};
- nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+ nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS);
if (!nest)
return -EMSGSIZE;
@@ -2175,6 +2558,8 @@
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)
@@ -2189,7 +2574,7 @@
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;
@@ -2206,11 +2591,17 @@
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);
@@ -2255,3 +2646,122 @@
{
l->abort_limit = limit;
}
+
+char *tipc_link_name_ext(struct tipc_link *l, char *buf)
+{
+ if (!l)
+ scnprintf(buf, TIPC_MAX_LINK_NAME, "null");
+ else if (link_is_bc_sndlink(l))
+ scnprintf(buf, TIPC_MAX_LINK_NAME, "broadcast-sender");
+ else if (link_is_bc_rcvlink(l))
+ scnprintf(buf, TIPC_MAX_LINK_NAME,
+ "broadcast-receiver, peer %x", l->addr);
+ else
+ memcpy(buf, l->name, TIPC_MAX_LINK_NAME);
+
+ return buf;
+}
+
+/**
+ * tipc_link_dump - dump TIPC link data
+ * @l: tipc link to be dumped
+ * @dqueues: bitmask to decide if any link queue to be dumped?
+ * - TIPC_DUMP_NONE: don't dump link queues
+ * - TIPC_DUMP_TRANSMQ: dump link transmq queue
+ * - TIPC_DUMP_BACKLOGQ: dump link backlog queue
+ * - TIPC_DUMP_DEFERDQ: dump link deferd queue
+ * - TIPC_DUMP_INPUTQ: dump link input queue
+ * - TIPC_DUMP_WAKEUP: dump link wakeup queue
+ * - TIPC_DUMP_ALL: dump all the link queues above
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
+{
+ int i = 0;
+ size_t sz = (dqueues) ? LINK_LMAX : LINK_LMIN;
+ struct sk_buff_head *list;
+ struct sk_buff *hskb, *tskb;
+ u32 len;
+
+ if (!l) {
+ i += scnprintf(buf, sz, "link data: (null)\n");
+ return i;
+ }
+
+ i += scnprintf(buf, sz, "link data: %x", l->addr);
+ i += scnprintf(buf + i, sz - i, " %x", l->state);
+ i += scnprintf(buf + i, sz - i, " %u", l->in_session);
+ i += scnprintf(buf + i, sz - i, " %u", l->session);
+ i += scnprintf(buf + i, sz - i, " %u", l->peer_session);
+ i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt);
+ i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt);
+ i += scnprintf(buf + i, sz - i, " %u", l->snd_nxt_state);
+ i += scnprintf(buf + i, sz - i, " %u", l->rcv_nxt_state);
+ 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", 0);
+ i += scnprintf(buf + i, sz - i, " %u", 0);
+ i += scnprintf(buf + i, sz - i, " %u", l->acked);
+
+ list = &l->transmq;
+ len = skb_queue_len(list);
+ hskb = skb_peek(list);
+ tskb = skb_peek_tail(list);
+ i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+ (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+ (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+ list = &l->deferdq;
+ len = skb_queue_len(list);
+ hskb = skb_peek(list);
+ tskb = skb_peek_tail(list);
+ i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+ (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+ (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+ list = &l->backlogq;
+ len = skb_queue_len(list);
+ hskb = skb_peek(list);
+ tskb = skb_peek_tail(list);
+ i += scnprintf(buf + i, sz - i, " | %u %u %u", len,
+ (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+ (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+ list = l->inputq;
+ len = skb_queue_len(list);
+ hskb = skb_peek(list);
+ tskb = skb_peek_tail(list);
+ i += scnprintf(buf + i, sz - i, " | %u %u %u\n", len,
+ (hskb) ? msg_seqno(buf_msg(hskb)) : 0,
+ (tskb) ? msg_seqno(buf_msg(tskb)) : 0);
+
+ if (dqueues & TIPC_DUMP_TRANSMQ) {
+ i += scnprintf(buf + i, sz - i, "transmq: ");
+ i += tipc_list_dump(&l->transmq, false, buf + i);
+ }
+ if (dqueues & TIPC_DUMP_BACKLOGQ) {
+ i += scnprintf(buf + i, sz - i,
+ "backlogq: <%u %u %u %u %u>, ",
+ l->backlog[TIPC_LOW_IMPORTANCE].len,
+ l->backlog[TIPC_MEDIUM_IMPORTANCE].len,
+ l->backlog[TIPC_HIGH_IMPORTANCE].len,
+ l->backlog[TIPC_CRITICAL_IMPORTANCE].len,
+ l->backlog[TIPC_SYSTEM_IMPORTANCE].len);
+ i += tipc_list_dump(&l->backlogq, false, buf + i);
+ }
+ if (dqueues & TIPC_DUMP_DEFERDQ) {
+ i += scnprintf(buf + i, sz - i, "deferdq: ");
+ i += tipc_list_dump(&l->deferdq, false, buf + i);
+ }
+ if (dqueues & TIPC_DUMP_INPUTQ) {
+ i += scnprintf(buf + i, sz - i, "inputq: ");
+ i += tipc_list_dump(l->inputq, false, buf + i);
+ }
+ if (dqueues & TIPC_DUMP_WAKEUP) {
+ i += scnprintf(buf + i, sz - i, "wakeup: ");
+ i += tipc_list_dump(&l->wakeupq, false, buf + i);
+ }
+
+ return i;
+}
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 90488c5..adcad65 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -90,6 +90,8 @@
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);
@@ -109,6 +111,7 @@
u16 tipc_link_acked(struct tipc_link *l);
u32 tipc_link_id(struct tipc_link *l);
char *tipc_link_name(struct tipc_link *l);
+char *tipc_link_name_ext(struct tipc_link *l, char *buf);
u32 tipc_link_state(struct tipc_link *l);
char tipc_link_plane(struct tipc_link *l);
int tipc_link_prio(struct tipc_link *l);
@@ -147,4 +150,5 @@
struct sk_buff_head *xmitq);
int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *xmitq);
+bool tipc_link_too_silent(struct tipc_link *l);
#endif
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 67f6938..6a6eae8 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -696,7 +696,7 @@
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 @@
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.c b/net/tipc/msg.c
index b618910..922d262 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -244,6 +244,65 @@
}
/**
+ * tipc_msg_fragment - build a fragment skb list for TIPC message
+ *
+ * @skb: TIPC message skb
+ * @hdr: internal msg header to be put on the top of the fragments
+ * @pktmax: max size of a fragment incl. the header
+ * @frags: returned fragment skb list
+ *
+ * Returns 0 if the fragmentation is successful, otherwise: -EINVAL
+ * or -ENOMEM
+ */
+int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
+ int pktmax, struct sk_buff_head *frags)
+{
+ int pktno, nof_fragms, dsz, dmax, eat;
+ struct tipc_msg *_hdr;
+ struct sk_buff *_skb;
+ u8 *data;
+
+ /* Non-linear buffer? */
+ if (skb_linearize(skb))
+ return -ENOMEM;
+
+ data = (u8 *)skb->data;
+ dsz = msg_size(buf_msg(skb));
+ dmax = pktmax - INT_H_SIZE;
+ if (dsz <= dmax || !dmax)
+ return -EINVAL;
+
+ nof_fragms = dsz / dmax + 1;
+ for (pktno = 1; pktno <= nof_fragms; pktno++) {
+ if (pktno < nof_fragms)
+ eat = dmax;
+ else
+ eat = dsz % dmax;
+ /* Allocate a new fragment */
+ _skb = tipc_buf_acquire(INT_H_SIZE + eat, GFP_ATOMIC);
+ if (!_skb)
+ goto error;
+ skb_orphan(_skb);
+ __skb_queue_tail(frags, _skb);
+ /* Copy header & data to the fragment */
+ skb_copy_to_linear_data(_skb, hdr, INT_H_SIZE);
+ skb_copy_to_linear_data_offset(_skb, INT_H_SIZE, data, eat);
+ data += eat;
+ /* Update the fragment's header */
+ _hdr = buf_msg(_skb);
+ msg_set_fragm_no(_hdr, pktno);
+ msg_set_nof_fragms(_hdr, nof_fragms);
+ msg_set_size(_hdr, INT_H_SIZE + eat);
+ }
+ return 0;
+
+error:
+ __skb_queue_purge(frags);
+ __skb_queue_head_init(frags);
+ return -ENOMEM;
+}
+
+/**
* tipc_msg_build - create buffer chain containing specified header and data
* @mhdr: Message header, to be prepended to data
* @m: User message
@@ -484,10 +543,7 @@
bmsg = buf_msg(_skb);
tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
INT_H_SIZE, dnode);
- if (msg_isdata(msg))
- msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE);
- else
- msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE);
+ msg_set_importance(bmsg, msg_importance(msg));
msg_set_seqno(bmsg, msg_seqno(msg));
msg_set_ack(bmsg, msg_ack(msg));
msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
@@ -499,54 +555,56 @@
/**
* tipc_msg_reverse(): swap source and destination addresses and add error code
* @own_node: originating node id for reversed message
- * @skb: buffer containing message to be reversed; may be replaced.
+ * @skb: buffer containing message to be reversed; will be consumed
* @err: error code to be set in message, if any
- * Consumes buffer at failure
+ * Replaces consumed buffer with new one when successful
* Returns true if success, otherwise false
*/
bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err)
{
struct sk_buff *_skb = *skb;
- struct tipc_msg *hdr;
- struct tipc_msg ohdr;
- int dlen;
+ struct tipc_msg *_hdr, *hdr;
+ int hlen, dlen;
if (skb_linearize(_skb))
goto exit;
- hdr = buf_msg(_skb);
- dlen = min_t(uint, msg_data_sz(hdr), MAX_FORWARD_SIZE);
- if (msg_dest_droppable(hdr))
+ _hdr = buf_msg(_skb);
+ dlen = min_t(uint, msg_data_sz(_hdr), MAX_FORWARD_SIZE);
+ hlen = msg_hdr_sz(_hdr);
+
+ if (msg_dest_droppable(_hdr))
goto exit;
- if (msg_errcode(hdr))
+ if (msg_errcode(_hdr))
goto exit;
- /* Take a copy of original header before altering message */
- memcpy(&ohdr, hdr, msg_hdr_sz(hdr));
+ /* Never return SHORT header */
+ if (hlen == SHORT_H_SIZE)
+ hlen = BASIC_H_SIZE;
- /* Never return SHORT header; expand by replacing buffer if necessary */
- if (msg_short(hdr)) {
- *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen, GFP_ATOMIC);
- if (!*skb)
- goto exit;
- memcpy((*skb)->data + BASIC_H_SIZE, msg_data(hdr), dlen);
- kfree_skb(_skb);
- _skb = *skb;
- hdr = buf_msg(_skb);
- memcpy(hdr, &ohdr, BASIC_H_SIZE);
- msg_set_hdr_sz(hdr, BASIC_H_SIZE);
- }
+ /* Don't return data along with SYN+, - sender has a clone */
+ if (msg_is_syn(_hdr) && err == TIPC_ERR_OVERLOAD)
+ dlen = 0;
- /* Now reverse the concerned fields */
+ /* Allocate new buffer to return */
+ *skb = tipc_buf_acquire(hlen + dlen, GFP_ATOMIC);
+ if (!*skb)
+ goto exit;
+ memcpy((*skb)->data, _skb->data, msg_hdr_sz(_hdr));
+ memcpy((*skb)->data + hlen, msg_data(_hdr), dlen);
+
+ /* Build reverse header in new buffer */
+ hdr = buf_msg(*skb);
+ msg_set_hdr_sz(hdr, hlen);
msg_set_errcode(hdr, err);
msg_set_non_seq(hdr, 0);
- msg_set_origport(hdr, msg_destport(&ohdr));
- msg_set_destport(hdr, msg_origport(&ohdr));
- msg_set_destnode(hdr, msg_prevnode(&ohdr));
+ msg_set_origport(hdr, msg_destport(_hdr));
+ msg_set_destport(hdr, msg_origport(_hdr));
+ msg_set_destnode(hdr, msg_prevnode(_hdr));
msg_set_prevnode(hdr, own_node);
msg_set_orignode(hdr, own_node);
- msg_set_size(hdr, msg_hdr_sz(hdr) + dlen);
- skb_trim(_skb, msg_size(hdr));
+ msg_set_size(hdr, hlen + dlen);
skb_orphan(_skb);
+ kfree_skb(_skb);
return true;
exit:
kfree_skb(_skb);
@@ -554,6 +612,22 @@
return false;
}
+bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy)
+{
+ struct sk_buff *skb, *_skb;
+
+ skb_queue_walk(msg, skb) {
+ _skb = skb_clone(skb, GFP_ATOMIC);
+ if (!_skb) {
+ __skb_queue_purge(cpy);
+ pr_err_ratelimited("Failed to clone buffer chain\n");
+ return false;
+ }
+ __skb_queue_tail(cpy, _skb);
+ }
+ return true;
+}
+
/**
* tipc_msg_lookup_dest(): try to find new destination for named message
* @skb: the buffer containing the message.
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index a4e944d..0daa6f0 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -102,12 +102,15 @@
#define TIPC_MEDIA_INFO_OFFSET 5
struct tipc_skb_cb {
+ struct sk_buff *tail;
+ unsigned long nxt_retr;
+ unsigned long retr_stamp;
u32 bytes_read;
u32 orig_member;
- struct sk_buff *tail;
- bool validated;
u16 chain_imp;
u16 ackers;
+ u16 retr_cnt;
+ bool validated;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
@@ -116,6 +119,37 @@
__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;
@@ -216,6 +250,16 @@
msg_set_bits(m, 0, 20, 1, n);
}
+static inline int msg_is_syn(struct tipc_msg *m)
+{
+ return msg_bits(m, 0, 17, 1);
+}
+
+static inline void msg_set_syn(struct tipc_msg *m, u32 d)
+{
+ msg_set_bits(m, 0, 17, 1, d);
+}
+
static inline int msg_dest_droppable(struct tipc_msg *m)
{
return msg_bits(m, 0, 19, 1);
@@ -246,6 +290,16 @@
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);
@@ -256,7 +310,7 @@
return ((unchar *)m) + msg_hdr_sz(m);
}
-static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
+static inline struct tipc_msg *msg_inner_hdr(struct tipc_msg *m)
{
return (struct tipc_msg *)msg_data(m);
}
@@ -349,6 +403,28 @@
msg_set_bits(m, 1, 0, 0xffff, n);
}
+/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch
+ * link peer session number
+ */
+static inline bool msg_dest_session_valid(struct tipc_msg *m)
+{
+ return msg_bits(m, 1, 16, 0x1);
+}
+
+static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid)
+{
+ msg_set_bits(m, 1, 16, 0x1, valid);
+}
+
+static inline u16 msg_dest_session(struct tipc_msg *m)
+{
+ return msg_bits(m, 1, 0, 0xffff);
+}
+
+static inline void msg_set_dest_session(struct tipc_msg *m, u16 n)
+{
+ msg_set_bits(m, 1, 0, 0xffff, n);
+}
/*
* Word 2
@@ -412,7 +488,7 @@
static inline u32 msg_origport(struct tipc_msg *m)
{
if (msg_user(m) == MSG_FRAGMENTER)
- m = msg_get_wrapped(m);
+ m = msg_inner_hdr(m);
return msg_word(m, 4);
}
@@ -647,12 +723,26 @@
msg_set_bits(m, 4, 16, 0xffff, n);
}
+static inline u32 msg_nof_fragms(struct tipc_msg *m)
+{
+ return msg_bits(m, 4, 0, 0xffff);
+}
+
+static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n)
+{
+ msg_set_bits(m, 4, 0, 0xffff, n);
+}
+
+static inline u32 msg_fragm_no(struct tipc_msg *m)
+{
+ return msg_bits(m, 4, 16, 0xffff);
+}
+
static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 4, 16, 0xffff, n);
}
-
static inline u16 msg_next_sent(struct tipc_msg *m)
{
return msg_bits(m, 4, 0, 0xffff);
@@ -803,6 +893,16 @@
msg_set_bits(m, 9, 16, 0xffff, n);
}
+static inline u16 msg_syncpt(struct tipc_msg *m)
+{
+ return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_syncpt(struct tipc_msg *m, u16 n)
+{
+ msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
static inline u32 msg_conn_ack(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff);
@@ -961,6 +1061,8 @@
bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg,
u32 mtu, u32 dnode);
bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos);
+int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
+ int pktmax, struct sk_buff_head *frags);
int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
int offset, int dsz, int mtu, struct sk_buff_head *list);
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err);
@@ -970,6 +1072,7 @@
struct sk_buff_head *cpy);
void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
struct sk_buff *skb);
+bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy);
static inline u16 buf_seqno(struct sk_buff *skb)
{
@@ -1076,4 +1179,25 @@
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_distr.c b/net/tipc/name_distr.c
index 3cfeb9d..836e629 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -94,8 +94,9 @@
list_add_tail_rcu(&publ->binding_node, &nt->node_scope);
return NULL;
}
- list_add_tail_rcu(&publ->binding_node, &nt->cluster_scope);
-
+ write_lock_bh(&nt->cluster_scope_lock);
+ list_add_tail(&publ->binding_node, &nt->cluster_scope);
+ write_unlock_bh(&nt->cluster_scope_lock);
skb = named_prepare_buf(net, PUBLICATION, ITEM_SIZE, 0);
if (!skb) {
pr_warn("Publication distribution failure\n");
@@ -112,11 +113,13 @@
*/
struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ)
{
+ struct name_table *nt = tipc_name_table(net);
struct sk_buff *buf;
struct distr_item *item;
- list_del_rcu(&publ->binding_node);
-
+ write_lock_bh(&nt->cluster_scope_lock);
+ list_del(&publ->binding_node);
+ write_unlock_bh(&nt->cluster_scope_lock);
if (publ->scope == TIPC_NODE_SCOPE)
return NULL;
@@ -147,7 +150,7 @@
ITEM_SIZE) * ITEM_SIZE;
u32 msg_rem = msg_dsz;
- list_for_each_entry_rcu(publ, pls, binding_node) {
+ list_for_each_entry(publ, pls, binding_node) {
/* Prepare next buffer: */
if (!skb) {
skb = named_prepare_buf(net, PUBLICATION, msg_rem,
@@ -189,11 +192,10 @@
__skb_queue_head_init(&head);
- rcu_read_lock();
+ read_lock_bh(&nt->cluster_scope_lock);
named_distribute(net, &head, dnode, &nt->cluster_scope);
- rcu_read_unlock();
-
tipc_node_xmit(net, &head, dnode, 0);
+ read_unlock_bh(&nt->cluster_scope_lock);
}
/**
@@ -221,7 +223,8 @@
publ->key);
}
- kfree_rcu(p, rcu);
+ if (p)
+ kfree_rcu(p, rcu);
}
/**
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 66d5b2c..66a65c2 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -744,6 +744,7 @@
INIT_LIST_HEAD(&nt->node_scope);
INIT_LIST_HEAD(&nt->cluster_scope);
+ rwlock_init(&nt->cluster_scope_lock);
tn->nametbl = nt;
spin_lock_init(&tn->nametbl_lock);
return 0;
@@ -828,11 +829,11 @@
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;
@@ -908,7 +909,8 @@
for (; i < TIPC_NAMETBL_SIZE; i++) {
head = &tn->nametbl->services[i];
- if (*last_type) {
+ if (*last_type ||
+ (!i && *last_key && (*last_lower == *last_key))) {
service = tipc_service_find(net, *last_type);
if (!service)
return -EPIPE;
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 892bd75..f790663 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -100,6 +100,7 @@
struct hlist_head services[TIPC_NAMETBL_SIZE];
struct list_head node_scope;
struct list_head cluster_scope;
+ rwlock_t cluster_scope_lock;
u32 local_publ_count;
};
diff --git a/net/tipc/net.c b/net/tipc/net.c
index f076edb..85707c1 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -163,12 +163,9 @@
void tipc_net_stop(struct net *net)
{
- u32 self = tipc_own_addr(net);
-
- if (!self)
+ if (!tipc_own_id(net))
return;
- tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self);
rtnl_lock();
tipc_bearer_stop(net);
tipc_node_stop(net);
@@ -190,7 +187,7 @@
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;
@@ -248,9 +245,9 @@
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 99ee419..d6165ad 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -110,7 +110,9 @@
[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 @@
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 @@
.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 @@
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 6376467..d4d2928 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -55,6 +55,7 @@
int rep_type;
int rep_size;
int req_type;
+ int req_size;
struct net *net;
struct sk_buff *rep;
struct tlv_desc *req;
@@ -87,6 +88,11 @@
return limit;
}
+static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv)
+{
+ return TLV_GET_LEN(tlv) - TLV_SPACE(0);
+}
+
static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
{
struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb);
@@ -166,6 +172,11 @@
return buf;
}
+static inline bool string_is_valid(char *s, int len)
+{
+ return memchr(s, '\0', len) ? true : false;
+}
+
static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
struct tipc_nl_compat_msg *msg,
struct sk_buff *arg)
@@ -247,7 +258,8 @@
int err;
struct sk_buff *arg;
- if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+ if (msg->req_type && (!msg->req_size ||
+ !TLV_CHECK_TYPE(msg->req, msg->req_type)))
return -EINVAL;
msg->rep = tipc_tlv_alloc(msg->rep_size);
@@ -257,8 +269,14 @@
if (msg->rep_type)
tipc_tlv_init(msg->rep, msg->rep_type);
- if (cmd->header)
- (*cmd->header)(msg);
+ if (cmd->header) {
+ err = (*cmd->header)(msg);
+ if (err) {
+ kfree_skb(msg->rep);
+ msg->rep = NULL;
+ return err;
+ }
+ }
arg = nlmsg_new(0, GFP_KERNEL);
if (!arg) {
@@ -312,9 +330,9 @@
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;
@@ -338,7 +356,8 @@
{
int err;
- if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+ if (msg->req_type && (!msg->req_size ||
+ !TLV_CHECK_TYPE(msg->req, msg->req_type)))
return -EINVAL;
err = __tipc_nl_compat_doit(cmd, msg);
@@ -362,8 +381,8 @@
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;
@@ -379,13 +398,23 @@
struct nlattr *prop;
struct nlattr *bearer;
struct tipc_bearer_config *b;
+ int len;
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;
+ len = TLV_GET_DATA_LEN(msg->req);
+ len -= offsetof(struct tipc_bearer_config, name);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_BEARER_NAME);
+ if (!string_is_valid(b->name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name))
return -EMSGSIZE;
@@ -393,7 +422,7 @@
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)))
@@ -411,13 +440,22 @@
{
char *name;
struct nlattr *bearer;
+ int len;
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;
+ len = TLV_GET_DATA_LEN(msg->req);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_BEARER_NAME);
+ if (!string_is_valid(name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name))
return -EMSGSIZE;
@@ -478,32 +516,44 @@
struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
int err;
+ int len;
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;
name = (char *)TLV_DATA(msg->req);
+
+ len = TLV_GET_DATA_LEN(msg->req);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
+ if (!string_is_valid(name, len))
+ return -EINVAL;
+
if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
return 0;
@@ -608,8 +658,8 @@
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;
@@ -647,14 +697,14 @@
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;
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;
@@ -674,14 +724,14 @@
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;
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;
@@ -701,14 +751,14 @@
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;
@@ -726,9 +776,19 @@
struct tipc_link_config *lc;
struct tipc_bearer *bearer;
struct tipc_media *media;
+ int len;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
+ len = TLV_GET_DATA_LEN(msg->req);
+ len -= offsetof(struct tipc_link_config, name);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
+ if (!string_is_valid(lc->name, len))
+ return -EINVAL;
+
media = tipc_media_find(lc->name);
if (media) {
cmd->doit = &__tipc_nl_media_set;
@@ -750,13 +810,22 @@
{
char *name;
struct nlattr *link;
+ int len;
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;
+ len = TLV_GET_DATA_LEN(msg->req);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
+ if (!string_is_valid(name, len))
+ return -EINVAL;
+
if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name))
return -EMSGSIZE;
@@ -778,6 +847,8 @@
};
ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
+ if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query))
+ return -EINVAL;
depth = ntohl(ntq->depth);
@@ -805,16 +876,18 @@
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;
@@ -873,8 +946,8 @@
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;
@@ -904,8 +977,12 @@
hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI,
TIPC_NL_PUBL_GET);
+ if (!hdr) {
+ kfree_skb(args);
+ 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;
@@ -939,8 +1016,8 @@
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;
@@ -951,8 +1028,12 @@
u32 node;
struct nlattr *con[TIPC_NLA_CON_MAX + 1];
- 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;
node = nla_get_u32(con[TIPC_NLA_CON_NODE]);
tipc_tlv_sprintf(msg->rep, " connected to <%u.%u.%u:%u>",
@@ -988,8 +1069,8 @@
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;
@@ -1008,8 +1089,8 @@
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;
@@ -1029,7 +1110,7 @@
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;
@@ -1055,8 +1136,8 @@
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;
@@ -1200,8 +1281,8 @@
goto send;
}
- len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
- if (len && !TLV_OK(msg.req, len)) {
+ msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+ if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) {
msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
err = -EOPNOTSUPP;
goto send;
@@ -1229,6 +1310,7 @@
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 4880197..c8f6177 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -43,6 +43,7 @@
#include "monitor.h"
#include "discover.h"
#include "netlink.h"
+#include "trace.h"
#define INVALID_NODE_SIG 0x10000
#define NODE_CLEANUP_AFTER 300000
@@ -374,14 +375,20 @@
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);
@@ -432,6 +439,12 @@
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);
return n;
@@ -459,6 +472,7 @@
static void tipc_node_delete(struct tipc_node *node)
{
+ trace_tipc_node_delete(node, true, " ");
tipc_node_delete_from_list(node);
del_timer_sync(&node->timer);
@@ -586,6 +600,7 @@
*/
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;
@@ -601,6 +616,13 @@
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;
}
@@ -616,6 +638,7 @@
int bearer_id;
int rc = 0;
+ trace_tipc_node_timeout(n, false, " ");
if (!node_is_up(n) && tipc_node_cleanup(n)) {
/*Removing the reference of Timer*/
tipc_node_put(n);
@@ -624,6 +647,12 @@
__skb_queue_head_init(&xmitq);
+ /* Initial node interval to value larger (10 seconds), then it will be
+ * recalculated with link lowest tolerance
+ */
+ tipc_node_read_lock(n);
+ n->keepalive_intv = 10000;
+ tipc_node_read_unlock(n);
for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
tipc_node_read_lock(n);
le = &n->links[bearer_id];
@@ -675,6 +704,7 @@
pr_debug("Established link <%s> on network plane %c\n",
tipc_link_name(nl), tipc_link_plane(nl));
+ trace_tipc_node_link_up(n, true, " ");
/* Ensure that a STATE message goes first */
tipc_link_build_state_msg(nl, xmitq);
@@ -684,7 +714,6 @@
*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);
@@ -727,6 +756,49 @@
}
/**
+ * 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 2 starts failover onto link <1B-2B>
+ *
+ * ==> Node 1 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;
+
+ /* Don't rush, failure link may be in the process of resetting */
+ if (l && !tipc_link_is_reset(l))
+ 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,
@@ -777,6 +849,7 @@
if (tipc_link_peer_is_down(l))
tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
+ trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link down!");
tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_reset(l);
tipc_link_build_reset_msg(l, xmitq);
@@ -794,6 +867,7 @@
tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT);
n->sync_point = tipc_link_rcv_nxt(tnl) + (U16_MAX / 2 - 1);
tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq);
+ trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link down -> failover!");
tipc_link_reset(l);
tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
@@ -804,10 +878,10 @@
static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
{
struct tipc_link_entry *le = &n->links[bearer_id];
+ struct tipc_media_addr *maddr = NULL;
struct tipc_link *l = le->link;
- struct tipc_media_addr *maddr;
- struct sk_buff_head xmitq;
int old_bearer_id = bearer_id;
+ struct sk_buff_head xmitq;
if (!l)
return;
@@ -817,19 +891,22 @@
tipc_node_write_lock(n);
if (!tipc_link_is_establishing(l)) {
__tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
- if (delete) {
- kfree(l);
- le->link = NULL;
- n->link_cnt--;
- }
} else {
/* Defuse pending tipc_node_link_up() */
+ tipc_link_reset(l);
tipc_link_fsm_evt(l, LINK_RESET_EVT);
}
+ if (delete) {
+ kfree(l);
+ le->link = NULL;
+ n->link_cnt--;
+ }
+ trace_tipc_node_link_down(n, true, "node link down or deleted!");
tipc_node_write_unlock(n);
if (delete)
tipc_mon_remove_peer(n->net, n->addr, old_bearer_id);
- tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
+ if (!skb_queue_empty(&xmitq))
+ tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
tipc_sk_rcv(n->net, &le->inputq);
}
@@ -1015,6 +1092,7 @@
*respond = false;
goto exit;
}
+ trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link created!");
tipc_link_reset(l);
tipc_link_fsm_evt(l, LINK_RESET_EVT);
if (n->state == NODE_FAILINGOVER)
@@ -1054,6 +1132,7 @@
pr_warn("Resetting all links to %x\n", n->addr);
+ trace_tipc_node_reset_links(n, true, " ");
for (i = 0; i < MAX_BEARERS; i++) {
tipc_node_link_down(n, i, false);
}
@@ -1229,11 +1308,13 @@
pr_err("Unknown node fsm state %x\n", state);
break;
}
+ trace_tipc_node_fsm(n->peer_id, n->state, state, evt);
n->state = state;
return;
illegal_evt:
pr_err("Illegal node fsm evt %x in state %x\n", evt, state);
+ trace_tipc_node_fsm(n->peer_id, n->state, state, evt);
}
static void node_lost_contact(struct tipc_node *n,
@@ -1247,6 +1328,7 @@
pr_debug("Lost contact with %x\n", n->addr);
n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
+ trace_tipc_node_lost_contact(n, true, " ");
/* Clean up broadcast state */
tipc_bcast_remove_peer(n->net, n->bc_entry.link);
@@ -1319,7 +1401,7 @@
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;
@@ -1361,13 +1443,15 @@
int rc;
if (in_own_node(net, dnode)) {
+ tipc_loopback_trace(net, list);
+ spin_lock_init(&list->lock);
tipc_sk_rcv(net, list);
return 0;
}
n = tipc_node_find(net, dnode);
if (unlikely(!n)) {
- skb_queue_purge(list);
+ __skb_queue_purge(list);
return -EHOSTUNREACH;
}
@@ -1376,7 +1460,7 @@
if (unlikely(bearer_id == INVALID_BEARER_ID)) {
tipc_node_read_unlock(n);
tipc_node_put(n);
- skb_queue_purge(list);
+ __skb_queue_purge(list);
return -EHOSTUNREACH;
}
@@ -1408,7 +1492,7 @@
{
struct sk_buff_head head;
- skb_queue_head_init(&head);
+ __skb_queue_head_init(&head);
__skb_queue_tail(&head, skb);
tipc_node_xmit(net, &head, dnode, selector);
return 0;
@@ -1543,6 +1627,10 @@
if (!skb_queue_empty(&be->inputq1))
tipc_node_mcast_rcv(n);
+ /* Handle NAME_DISTRIBUTOR messages sent from 1.7 nodes */
+ if (!skb_queue_empty(&n->bc_entry.namedq))
+ tipc_named_rcv(net, &n->bc_entry.namedq);
+
/* If reassembly or retransmission failure => reset all links to peer */
if (rc & TIPC_LINK_DOWN_EVT)
tipc_node_reset_links(n);
@@ -1563,7 +1651,6 @@
int usr = msg_user(hdr);
int mtyp = msg_type(hdr);
u16 oseqno = msg_seqno(hdr);
- u16 iseqno = msg_seqno(msg_get_wrapped(hdr));
u16 exp_pkts = msg_msgcnt(hdr);
u16 rcv_nxt, syncpt, dlv_nxt, inputq_len;
int state = n->state;
@@ -1571,6 +1658,10 @@
struct tipc_media_addr *maddr;
int pb_id;
+ if (trace_tipc_node_check_state_enabled()) {
+ trace_tipc_skb_dump(skb, false, "skb for node state check");
+ trace_tipc_node_check_state(n, true, " ");
+ }
l = n->links[bearer_id].link;
if (!l)
return false;
@@ -1588,8 +1679,11 @@
}
}
- if (!tipc_link_validate_msg(l, hdr))
+ if (!tipc_link_validate_msg(l, hdr)) {
+ trace_tipc_skb_dump(skb, false, "PROTO invalid (2)!");
+ trace_tipc_link_dump(l, TIPC_DUMP_NONE, "PROTO invalid (2)!");
return false;
+ }
/* Check and update node accesibility if applicable */
if (state == SELF_UP_PEER_COMING) {
@@ -1617,19 +1711,23 @@
/* Initiate or update failover mode if applicable */
if ((usr == TUNNEL_PROTOCOL) && (mtyp == FAILOVER_MSG)) {
syncpt = oseqno + exp_pkts - 1;
- if (pl && tipc_link_is_up(pl)) {
+ if (pl && !tipc_link_is_reset(pl)) {
__tipc_node_link_down(n, &pb_id, xmitq, &maddr);
+ trace_tipc_node_link_down(n, true,
+ "node link down <- failover!");
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;
@@ -1651,7 +1749,10 @@
/* Initiate synch mode if applicable */
if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) {
- syncpt = iseqno + exp_pkts - 1;
+ if (n->capabilities & TIPC_TUNNEL_ENHANCED)
+ syncpt = msg_syncpt(hdr);
+ else
+ syncpt = msg_seqno(msg_inner_hdr(hdr)) + exp_pkts - 1;
if (!tipc_link_is_up(l))
__tipc_node_link_up(n, bearer_id, xmitq);
if (n->state == SELF_UP_PEER_UP) {
@@ -1710,6 +1811,7 @@
__skb_queue_head_init(&xmitq);
/* Ensure message is well-formed before touching the header */
+ TIPC_SKB_CB(skb)->validated = false;
if (unlikely(!tipc_msg_validate(&skb)))
goto discard;
hdr = buf_msg(skb);
@@ -1832,9 +1934,9 @@
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;
@@ -1990,9 +2092,9 @@
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;
@@ -2066,9 +2168,9 @@
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;
@@ -2131,9 +2233,9 @@
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;
@@ -2271,9 +2373,10 @@
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;
@@ -2300,7 +2403,7 @@
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;
@@ -2391,9 +2494,10 @@
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;
@@ -2425,3 +2529,65 @@
return skb->len;
}
+
+u32 tipc_node_get_addr(struct tipc_node *node)
+{
+ return (node) ? node->addr : 0;
+}
+
+/**
+ * tipc_node_dump - dump TIPC node data
+ * @n: tipc node to be dumped
+ * @more: dump more?
+ * - false: dump only tipc node data
+ * - true: dump node link data as well
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_node_dump(struct tipc_node *n, bool more, char *buf)
+{
+ int i = 0;
+ size_t sz = (more) ? NODE_LMAX : NODE_LMIN;
+
+ if (!n) {
+ i += scnprintf(buf, sz, "node data: (null)\n");
+ return i;
+ }
+
+ i += scnprintf(buf, sz, "node data: %x", n->addr);
+ i += scnprintf(buf + i, sz - i, " %x", n->state);
+ i += scnprintf(buf + i, sz - i, " %d", n->active_links[0]);
+ i += scnprintf(buf + i, sz - i, " %d", n->active_links[1]);
+ i += scnprintf(buf + i, sz - i, " %x", n->action_flags);
+ i += scnprintf(buf + i, sz - i, " %u", n->failover_sent);
+ i += scnprintf(buf + i, sz - i, " %u", n->sync_point);
+ i += scnprintf(buf + i, sz - i, " %d", n->link_cnt);
+ i += scnprintf(buf + i, sz - i, " %u", n->working_links);
+ i += scnprintf(buf + i, sz - i, " %x", n->capabilities);
+ i += scnprintf(buf + i, sz - i, " %lu\n", n->keepalive_intv);
+
+ if (!more)
+ return i;
+
+ i += scnprintf(buf + i, sz - i, "link_entry[0]:\n");
+ i += scnprintf(buf + i, sz - i, " mtu: %u\n", n->links[0].mtu);
+ i += scnprintf(buf + i, sz - i, " media: ");
+ i += tipc_media_addr_printf(buf + i, sz - i, &n->links[0].maddr);
+ i += scnprintf(buf + i, sz - i, "\n");
+ i += tipc_link_dump(n->links[0].link, TIPC_DUMP_NONE, buf + i);
+ i += scnprintf(buf + i, sz - i, " inputq: ");
+ i += tipc_list_dump(&n->links[0].inputq, false, buf + i);
+
+ i += scnprintf(buf + i, sz - i, "link_entry[1]:\n");
+ i += scnprintf(buf + i, sz - i, " mtu: %u\n", n->links[1].mtu);
+ i += scnprintf(buf + i, sz - i, " media: ");
+ i += tipc_media_addr_printf(buf + i, sz - i, &n->links[1].maddr);
+ i += scnprintf(buf + i, sz - i, "\n");
+ i += tipc_link_dump(n->links[1].link, TIPC_DUMP_NONE, buf + i);
+ i += scnprintf(buf + i, sz - i, " inputq: ");
+ i += tipc_list_dump(&n->links[1].inputq, false, buf + i);
+
+ i += scnprintf(buf + i, sz - i, "bclink:\n ");
+ i += tipc_link_dump(n->bc_entry.link, TIPC_DUMP_NONE, buf + i);
+
+ return i;
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 48b3298..291d0ec 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -45,24 +45,33 @@
/* Optional capabilities supported by this code version
*/
enum {
+ TIPC_SYN_BIT = (1),
TIPC_BCAST_SYNCH = (1 << 1),
TIPC_BCAST_STATE_NACK = (1 << 2),
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),
+ TIPC_TUNNEL_ENHANCED = (1 << 9)
};
-#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \
- TIPC_BCAST_STATE_NACK | \
- TIPC_BCAST_RCAST | \
- TIPC_BLOCK_FLOWCTL | \
- TIPC_NODE_ID128 | \
- TIPC_LINK_PROTO_SEQNO)
+#define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \
+ TIPC_BCAST_SYNCH | \
+ TIPC_BCAST_STATE_NACK | \
+ TIPC_BCAST_RCAST | \
+ TIPC_BLOCK_FLOWCTL | \
+ TIPC_NODE_ID128 | \
+ TIPC_LINK_PROTO_SEQNO | \
+ TIPC_MCAST_RBCTL | \
+ TIPC_GAP_ACK_BLOCK | \
+ TIPC_TUNNEL_ENHANCED)
#define INVALID_BEARER_ID -1
void tipc_node_stop(struct net *net);
bool tipc_node_get_id(struct net *net, u32 addr, u8 *id);
+u32 tipc_node_get_addr(struct tipc_node *node);
u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr);
void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128,
struct tipc_bearer *bearer,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 366ce0b..4b92b19 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -46,8 +46,9 @@
#include "bcast.h"
#include "netlink.h"
#include "group.h"
+#include "trace.h"
-#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
+#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */
#define TIPC_FWD_MSG 1
#define TIPC_MAX_PORT 0xffffffff
@@ -80,7 +81,6 @@
* @publications: list of publications for port
* @blocking_link: address of the congested link we are currently sleeping on
* @pub_count: total # of publications port has made during its lifetime
- * @probing_state:
* @conn_timeout: the time we can wait for an unresponded setup request
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
* @cong_link_cnt: number of congested links
@@ -102,8 +102,8 @@
struct list_head cong_links;
struct list_head publications;
u32 pub_count;
- uint conn_timeout;
atomic_t dupl_rcvcnt;
+ u16 conn_timeout;
bool probe_unacked;
u16 cong_link_cnt;
u16 snt_unacked;
@@ -234,6 +234,7 @@
*/
static void tsk_advance_rx_queue(struct sock *sk)
{
+ trace_tipc_sk_advance_rx(sk, NULL, TIPC_DUMP_SK_RCVQ, " ");
kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
}
@@ -248,6 +249,7 @@
if (!tipc_msg_reverse(onode, &skb, err))
return;
+ trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_NONE, "@sk_respond!");
dnode = msg_destnode(buf_msg(skb));
selector = msg_origport(buf_msg(skb));
tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
@@ -377,16 +379,18 @@
#define tipc_wait_for_cond(sock_, timeo_, condition_) \
({ \
+ DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
struct sock *sk_; \
int rc_; \
\
while ((rc_ = !(condition_))) { \
- DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
+ /* coupled with smp_wmb() in tipc_sk_proto_rcv() */ \
+ smp_rmb(); \
sk_ = (sock_)->sk; \
rc_ = tipc_sk_sock_err((sock_), timeo_); \
if (rc_) \
break; \
- prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \
+ add_wait_queue(sk_sleep(sk_), &wait_); \
release_sock(sk_); \
*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
sched_annotate_sleep(); \
@@ -482,7 +486,8 @@
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, " ");
return 0;
}
@@ -507,6 +512,9 @@
tipc_wait_for_cond(sock, &timeout, (!tsk->cong_link_cnt &&
!tsk_conn_cong(tsk)));
+ /* Remove any pending SYN message */
+ __skb_queue_purge(&sk->sk_write_queue);
+
/* Reject all unreceived messages, except on an active connection
* (which disconnects locally & sends a 'FIN+' to peer).
*/
@@ -569,10 +577,12 @@
tsk = tipc_sk(sk);
lock_sock(sk);
+ trace_tipc_sk_release(sk, NULL, TIPC_DUMP_ALL, " ");
__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
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);
@@ -716,6 +726,7 @@
__poll_t revents = 0;
sock_poll_wait(file, sock, wait);
+ trace_tipc_sk_poll(sk, NULL, TIPC_DUMP_ALL, " ");
if (sk->sk_shutdown & RCV_SHUTDOWN)
revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
@@ -724,12 +735,12 @@
switch (sk->sk_state) {
case TIPC_ESTABLISHED:
- case TIPC_CONNECTING:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
revents |= EPOLLOUT;
- /* fall thru' */
+ /* fall through */
case TIPC_LISTEN:
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ case TIPC_CONNECTING:
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
revents |= EPOLLIN | EPOLLRDNORM;
break;
case TIPC_OPEN:
@@ -737,7 +748,7 @@
revents |= EPOLLOUT;
if (!tipc_sk_type_connectionless(sk))
break;
- if (skb_queue_empty(&sk->sk_receive_queue))
+ if (skb_queue_empty_lockless(&sk->sk_receive_queue))
break;
revents |= EPOLLIN | EPOLLRDNORM;
break;
@@ -798,13 +809,16 @@
msg_set_nameupper(hdr, seq->upper);
/* Build message as chain of buffers */
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts);
/* Send message if build was successful */
- if (unlikely(rc == dlen))
+ if (unlikely(rc == dlen)) {
+ trace_tipc_sk_sendmcast(sk, skb_peek(&pkts),
+ TIPC_DUMP_SK_SNDQ, " ");
rc = tipc_mcast_xmit(net, &pkts, method, &dsts,
&tsk->cong_link_cnt);
+ }
tipc_nlist_purge(&dsts);
@@ -839,7 +853,7 @@
msg_set_grp_bc_seqno(hdr, bc_snd_nxt);
/* Build message as chain of buffers */
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
if (unlikely(rc != dlen))
@@ -878,7 +892,6 @@
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
int blks = tsk_blocks(GROUP_H_SIZE + dlen);
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_group *grp = tsk->group;
struct net *net = sock_net(sk);
struct tipc_member *mb = NULL;
u32 node, port;
@@ -892,7 +905,9 @@
/* Block or return if destination link or member is congested */
rc = tipc_wait_for_cond(sock, &timeout,
!tipc_dest_find(&tsk->cong_links, node, 0) &&
- !tipc_group_cong(grp, node, port, blks, &mb));
+ tsk->group &&
+ !tipc_group_cong(tsk->group, node, port, blks,
+ &mb));
if (unlikely(rc))
return rc;
@@ -922,7 +937,6 @@
struct tipc_sock *tsk = tipc_sk(sk);
struct list_head *cong_links = &tsk->cong_links;
int blks = tsk_blocks(GROUP_H_SIZE + dlen);
- struct tipc_group *grp = tsk->group;
struct tipc_msg *hdr = &tsk->phdr;
struct tipc_member *first = NULL;
struct tipc_member *mbr = NULL;
@@ -939,9 +953,10 @@
type = msg_nametype(hdr);
inst = dest->addr.name.name.instance;
scope = msg_lookup_scope(hdr);
- exclude = tipc_group_exclude(grp);
while (++lookups < 4) {
+ exclude = tipc_group_exclude(tsk->group);
+
first = NULL;
/* Look for a non-congested destination member, if any */
@@ -950,7 +965,8 @@
&dstcnt, exclude, false))
return -EHOSTUNREACH;
tipc_dest_pop(&dsts, &node, &port);
- cong = tipc_group_cong(grp, node, port, blks, &mbr);
+ cong = tipc_group_cong(tsk->group, node, port, blks,
+ &mbr);
if (!cong)
break;
if (mbr == first)
@@ -969,7 +985,8 @@
/* Block or return if destination link or member is congested */
rc = tipc_wait_for_cond(sock, &timeout,
!tipc_dest_find(cong_links, node, 0) &&
- !tipc_group_cong(grp, node, port,
+ tsk->group &&
+ !tipc_group_cong(tsk->group, node, port,
blks, &mbr));
if (unlikely(rc))
return rc;
@@ -1004,8 +1021,7 @@
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_group *grp = tsk->group;
- struct tipc_nlist *dsts = tipc_group_dests(grp);
+ struct tipc_nlist *dsts;
struct tipc_mc_method *method = &tsk->mc_method;
bool ack = method->mandatory && method->rcast;
int blks = tsk_blocks(MCAST_H_SIZE + dlen);
@@ -1014,15 +1030,17 @@
struct sk_buff_head pkts;
int rc = -EHOSTUNREACH;
- if (!dsts->local && !dsts->remote)
- return -EHOSTUNREACH;
-
/* Block or return if any destination link or member is congested */
- rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt &&
- !tipc_group_bc_cong(grp, blks));
+ rc = tipc_wait_for_cond(sock, &timeout,
+ !tsk->cong_link_cnt && tsk->group &&
+ !tipc_group_bc_cong(tsk->group, blks));
if (unlikely(rc))
return rc;
+ dsts = tipc_group_dests(tsk->group);
+ if (!dsts->local && !dsts->remote)
+ return -EHOSTUNREACH;
+
/* Complete message header */
if (dest) {
msg_set_type(hdr, TIPC_GRP_MCAST_MSG);
@@ -1034,13 +1052,13 @@
msg_set_hdr_sz(hdr, GROUP_H_SIZE);
msg_set_destport(hdr, 0);
msg_set_destnode(hdr, 0);
- msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp));
+ msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(tsk->group));
/* Avoid getting stuck with repeated forced replicasts */
msg_set_grp_bc_ack_req(hdr, ack);
/* Build message as chain of buffers */
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
if (unlikely(rc != dlen))
return rc;
@@ -1206,8 +1224,10 @@
bool conn_cong;
/* Ignore if connection cannot be validated: */
- if (!tsk_peer_msg(tsk, hdr))
+ if (!tsk_peer_msg(tsk, hdr)) {
+ trace_tipc_sk_drop_msg(sk, skb, TIPC_DUMP_NONE, "@proto_rcv!");
goto exit;
+ }
if (unlikely(msg_errcode(hdr))) {
tipc_set_sk_state(sk, TIPC_DISCONNECTING);
@@ -1314,7 +1334,7 @@
if (unlikely(!dest)) {
dest = &tsk->peer;
- if (!syn || dest->family != AF_TIPC)
+ if (!syn && dest->family != AF_TIPC)
return -EDESTADDRREQ;
}
@@ -1329,6 +1349,7 @@
tsk->conn_type = dest->addr.name.name.type;
tsk->conn_instance = dest->addr.name.name.instance;
}
+ msg_set_syn(hdr, 1);
}
seq = &dest->addr.nameseq;
@@ -1366,12 +1387,15 @@
if (unlikely(rc))
return rc;
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
if (unlikely(rc != dlen))
return rc;
+ if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue)))
+ return -ENOMEM;
+ trace_tipc_sk_sendmsg(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " ");
rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
if (unlikely(rc == -ELINKCONG)) {
tipc_dest_push(clinks, dnode, 0);
@@ -1421,7 +1445,7 @@
int send, sent = 0;
int rc = 0;
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
if (unlikely(dlen > INT_MAX))
return -EMSGSIZE;
@@ -1449,6 +1473,8 @@
if (unlikely(rc != send))
break;
+ trace_tipc_sk_sendstream(sk, skb_peek(&pkts),
+ TIPC_DUMP_SK_SNDQ, " ");
rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
if (unlikely(rc == -ELINKCONG)) {
tsk->cong_link_cnt = 1;
@@ -1490,6 +1516,7 @@
struct net *net = sock_net(sk);
struct tipc_msg *msg = &tsk->phdr;
+ msg_set_syn(msg, 0);
msg_set_destnode(msg, peer_node);
msg_set_destport(msg, peer_port);
msg_set_type(msg, TIPC_CONN_MSG);
@@ -1501,6 +1528,7 @@
tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
+ __skb_queue_purge(&sk->sk_write_queue);
if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
return;
@@ -1652,7 +1680,7 @@
static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
{
struct sock *sk = sock->sk;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
long timeo = *timeop;
int err = sock_error(sk);
@@ -1660,15 +1688,17 @@
return err;
for (;;) {
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
if (sk->sk_shutdown & RCV_SHUTDOWN) {
err = -ENOTCONN;
break;
}
+ add_wait_queue(sk_sleep(sk), &wait);
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
+ sched_annotate_sleep();
lock_sock(sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -1684,7 +1714,6 @@
if (err)
break;
}
- finish_wait(sk_sleep(sk), &wait);
*timeop = timeo;
return err;
}
@@ -1776,7 +1805,7 @@
/* Send group flow control advertisement when applicable */
if (tsk->group && msg_in_group(hdr) && !grp_evt) {
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen),
msg_orignode(hdr), msg_origport(hdr),
&xmitq);
@@ -1957,6 +1986,8 @@
return;
case SOCK_WAKEUP:
tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);
+ /* coupled with smp_rmb() in tipc_wait_for_cond() */
+ smp_wmb();
tsk->cong_link_cnt--;
wakeup = true;
break;
@@ -1978,91 +2009,90 @@
}
/**
- * tipc_filter_connect - Handle incoming message for a connection-based socket
+ * tipc_sk_filter_connect - check incoming message for a connection-based socket
* @tsk: TIPC socket
- * @skb: pointer to message buffer. Set to NULL if buffer is consumed
- *
- * Returns true if everything ok, false otherwise
+ * @skb: pointer to message buffer.
+ * Returns true if message should be added to receive queue, false otherwise
*/
static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
{
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
struct tipc_msg *hdr = buf_msg(skb);
- u32 pport = msg_origport(hdr);
- u32 pnode = msg_orignode(hdr);
+ bool con_msg = msg_connected(hdr);
+ u32 pport = tsk_peer_port(tsk);
+ u32 pnode = tsk_peer_node(tsk);
+ u32 oport = msg_origport(hdr);
+ u32 onode = msg_orignode(hdr);
+ int err = msg_errcode(hdr);
+ unsigned long delay;
if (unlikely(msg_mcast(hdr)))
return false;
switch (sk->sk_state) {
case TIPC_CONNECTING:
- /* Accept only ACK or NACK message */
- if (unlikely(!msg_connected(hdr))) {
- if (pport != tsk_peer_port(tsk) ||
- pnode != tsk_peer_node(tsk))
- return false;
-
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- sk->sk_err = ECONNREFUSED;
+ /* Setup ACK */
+ if (likely(con_msg)) {
+ if (err)
+ break;
+ tipc_sk_finish_conn(tsk, oport, onode);
+ msg_set_importance(&tsk->phdr, msg_importance(hdr));
+ /* ACK+ message with data is added to receive queue */
+ if (msg_data_sz(hdr))
+ return true;
+ /* Empty ACK-, - wake up sleeping connect() and drop */
sk->sk_state_change(sk);
- return true;
+ msg_set_dest_droppable(hdr, 1);
+ return false;
}
-
- if (unlikely(msg_errcode(hdr))) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- sk->sk_err = ECONNREFUSED;
- sk->sk_state_change(sk);
- return true;
- }
-
- if (unlikely(!msg_isdata(hdr))) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- sk->sk_err = EINVAL;
- sk->sk_state_change(sk);
- return true;
- }
-
- tipc_sk_finish_conn(tsk, msg_origport(hdr), msg_orignode(hdr));
- msg_set_importance(&tsk->phdr, msg_importance(hdr));
-
- /* If 'ACK+' message, add to socket receive queue */
- if (msg_data_sz(hdr))
- return true;
-
- /* If empty 'ACK-' message, wake up sleeping connect() */
- sk->sk_data_ready(sk);
-
- /* 'ACK-' message is neither accepted nor rejected: */
- msg_set_dest_droppable(hdr, 1);
- return false;
-
- case TIPC_OPEN:
- case TIPC_DISCONNECTING:
- break;
- case TIPC_LISTEN:
- /* Accept only SYN message */
- if (!msg_connected(hdr) && !(msg_errcode(hdr)))
- return true;
- break;
- case TIPC_ESTABLISHED:
- /* Accept only connection-based messages sent by peer */
- if (unlikely(!tsk_peer_msg(tsk, hdr)))
+ /* Ignore connectionless message if not from listening socket */
+ if (oport != pport || onode != pnode)
return false;
- if (unlikely(msg_errcode(hdr))) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- /* Let timer expire on it's own */
- tipc_node_remove_conn(net, tsk_peer_node(tsk),
- tsk->portid);
- sk->sk_state_change(sk);
- }
+ /* Rejected SYN */
+ if (err != TIPC_ERR_OVERLOAD)
+ break;
+
+ /* Prepare for new setup attempt if we have a SYN clone */
+ if (skb_queue_empty(&sk->sk_write_queue))
+ break;
+ get_random_bytes(&delay, 2);
+ delay %= (tsk->conn_timeout / 4);
+ delay = msecs_to_jiffies(delay + 100);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + delay);
+ return false;
+ case TIPC_OPEN:
+ case TIPC_DISCONNECTING:
+ return false;
+ case TIPC_LISTEN:
+ /* Accept only SYN message */
+ if (!msg_is_syn(hdr) &&
+ tipc_node_get_capabilities(net, onode) & TIPC_SYN_BIT)
+ return false;
+ if (!con_msg && !err)
+ return true;
+ return false;
+ case TIPC_ESTABLISHED:
+ /* Accept only connection-based messages sent by peer */
+ if (likely(con_msg && !err && pport == oport && pnode == onode))
+ return true;
+ if (!tsk_peer_msg(tsk, hdr))
+ return false;
+ if (!err)
+ return true;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(net, pnode, tsk->portid);
+ sk->sk_state_change(sk);
return true;
default:
pr_err("Unknown sk_state %u\n", sk->sk_state);
}
-
- return false;
+ /* Abort connection setup attempt */
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ sk->sk_err = ECONNREFUSED;
+ sk->sk_state_change(sk);
+ return true;
}
/**
@@ -2089,13 +2119,13 @@
struct tipc_msg *hdr = buf_msg(skb);
if (unlikely(msg_in_group(hdr)))
- return sk->sk_rcvbuf;
+ return READ_ONCE(sk->sk_rcvbuf);
if (unlikely(!msg_connected(hdr)))
- return sk->sk_rcvbuf << msg_importance(hdr);
+ return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr);
if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
- return sk->sk_rcvbuf;
+ return READ_ONCE(sk->sk_rcvbuf);
return FLOWCTL_MSG_LIM;
}
@@ -2120,8 +2150,10 @@
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, " ");
TIPC_SKB_CB(skb)->bytes_read = 0;
__skb_queue_head_init(&inputq);
__skb_queue_tail(&inputq, skb);
@@ -2132,6 +2164,9 @@
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);
@@ -2141,17 +2176,25 @@
(!grp && msg_in_group(hdr)))
err = TIPC_ERR_NO_PORT;
else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) {
+ trace_tipc_sk_dump(sk, skb, TIPC_DUMP_ALL,
+ "err_overload2!");
atomic_inc(&sk->sk_drops);
err = TIPC_ERR_OVERLOAD;
}
if (unlikely(err)) {
- tipc_skb_reject(net, err, skb, xmitq);
+ if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) {
+ trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_NONE,
+ "@filter_rcv!");
+ __skb_queue_tail(xmitq, skb);
+ }
err = TIPC_OK;
continue;
}
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
+ trace_tipc_sk_overlimit2(sk, skb, TIPC_DUMP_ALL,
+ "rcvq >90% allocated!");
sk->sk_data_ready(sk);
}
}
@@ -2217,14 +2260,21 @@
if (!sk->sk_backlog.len)
atomic_set(dcnt, 0);
lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
- if (likely(!sk_add_backlog(sk, skb, lim)))
+ if (likely(!sk_add_backlog(sk, skb, lim))) {
+ trace_tipc_sk_overlimit1(sk, skb, TIPC_DUMP_ALL,
+ "bklg & rcvq >90% allocated!");
continue;
+ }
+ trace_tipc_sk_dump(sk, skb, TIPC_DUMP_ALL, "err_overload!");
/* Overload => reject message back to sender */
onode = tipc_own_addr(sock_net(sk));
atomic_inc(&sk->sk_drops);
- if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
+ if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD)) {
+ trace_tipc_sk_rej_msg(sk, skb, TIPC_DUMP_ALL,
+ "@sk_enqueue!");
__skb_queue_tail(xmitq, skb);
+ }
break;
}
}
@@ -2273,6 +2323,8 @@
/* Prepare for message rejection */
if (!tipc_msg_reverse(tipc_own_addr(net), &skb, err))
continue;
+
+ trace_tipc_sk_rej_msg(NULL, skb, TIPC_DUMP_NONE, "@sk_rcv!");
xmit:
dnode = msg_destnode(buf_msg(skb));
tipc_node_xmit_skb(net, skb, dnode, dport);
@@ -2302,6 +2354,16 @@
return 0;
}
+static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr)
+{
+ if (addr->family != AF_TIPC)
+ return false;
+ if (addr->addrtype == TIPC_SERVICE_RANGE)
+ return (addr->addr.nameseq.lower <= addr->addr.nameseq.upper);
+ return (addr->addrtype == TIPC_SERVICE_ADDR ||
+ addr->addrtype == TIPC_SOCKET_ADDR);
+}
+
/**
* tipc_connect - establish a connection to another TIPC port
* @sock: socket structure
@@ -2337,18 +2399,18 @@
if (!tipc_sk_type_connectionless(sk))
res = -EINVAL;
goto exit;
- } else if (dst->family != AF_TIPC) {
- res = -EINVAL;
}
- if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
+ if (!tipc_sockaddr_is_sane(dst)) {
res = -EINVAL;
- if (res)
goto exit;
-
+ }
/* DGRAM/RDM connect(), just save the destaddr */
if (tipc_sk_type_connectionless(sk)) {
memcpy(&tsk->peer, dest, destlen);
goto exit;
+ } else if (dst->addrtype == TIPC_SERVICE_RANGE) {
+ res = -EINVAL;
+ goto exit;
}
previous = sk->sk_state;
@@ -2374,7 +2436,7 @@
* case is EINPROGRESS, rather than EALREADY.
*/
res = -EINPROGRESS;
- /* fall thru' */
+ /* fall through */
case TIPC_CONNECTING:
if (!timeout) {
if (previous == TIPC_CONNECTING)
@@ -2546,6 +2608,7 @@
lock_sock(sk);
+ trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
sk->sk_shutdown = SEND_SHUTDOWN;
@@ -2564,43 +2627,78 @@
return res;
}
+static void tipc_sk_check_probing_state(struct sock *sk,
+ struct sk_buff_head *list)
+{
+ struct tipc_sock *tsk = tipc_sk(sk);
+ u32 pnode = tsk_peer_node(tsk);
+ u32 pport = tsk_peer_port(tsk);
+ u32 self = tsk_own_node(tsk);
+ u32 oport = tsk->portid;
+ struct sk_buff *skb;
+
+ if (tsk->probe_unacked) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ sk->sk_err = ECONNABORTED;
+ tipc_node_remove_conn(sock_net(sk), pnode, pport);
+ sk->sk_state_change(sk);
+ return;
+ }
+ /* Prepare new probe */
+ skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0,
+ pnode, self, pport, oport, TIPC_OK);
+ if (skb)
+ __skb_queue_tail(list, skb);
+ tsk->probe_unacked = true;
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
+}
+
+static void tipc_sk_retry_connect(struct sock *sk, struct sk_buff_head *list)
+{
+ struct tipc_sock *tsk = tipc_sk(sk);
+
+ /* Try again later if dest link is congested */
+ if (tsk->cong_link_cnt) {
+ sk_reset_timer(sk, &sk->sk_timer, msecs_to_jiffies(100));
+ return;
+ }
+ /* Prepare SYN for retransmit */
+ tipc_msg_skb_clone(&sk->sk_write_queue, list);
+}
+
static void tipc_sk_timeout(struct timer_list *t)
{
struct sock *sk = from_timer(sk, t, sk_timer);
struct tipc_sock *tsk = tipc_sk(sk);
- u32 peer_port = tsk_peer_port(tsk);
- u32 peer_node = tsk_peer_node(tsk);
- u32 own_node = tsk_own_node(tsk);
- u32 own_port = tsk->portid;
- struct net *net = sock_net(sk);
- struct sk_buff *skb = NULL;
+ u32 pnode = tsk_peer_node(tsk);
+ struct sk_buff_head list;
+ int rc = 0;
+ __skb_queue_head_init(&list);
bh_lock_sock(sk);
- if (!tipc_sk_connected(sk))
- goto exit;
/* Try again later if socket is busy */
if (sock_owned_by_user(sk)) {
sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20);
- goto exit;
+ bh_unlock_sock(sk);
+ return;
}
- if (tsk->probe_unacked) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- tipc_node_remove_conn(net, peer_node, peer_port);
- sk->sk_state_change(sk);
- goto exit;
- }
- /* Send new probe */
- skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0,
- peer_node, own_node, peer_port, own_port,
- TIPC_OK);
- tsk->probe_unacked = true;
- sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
-exit:
+ if (sk->sk_state == TIPC_ESTABLISHED)
+ tipc_sk_check_probing_state(sk, &list);
+ else if (sk->sk_state == TIPC_CONNECTING)
+ tipc_sk_retry_connect(sk, &list);
+
bh_unlock_sock(sk);
- if (skb)
- tipc_node_xmit_skb(net, skb, peer_node, own_port);
+
+ if (!skb_queue_empty(&list))
+ rc = tipc_node_xmit(sock_net(sk), &list, pnode, tsk->portid);
+
+ /* SYN messages may cause link congestion */
+ if (rc == -ELINKCONG) {
+ tipc_dest_push(&tsk->cong_links, pnode, 0);
+ tsk->cong_link_cnt = 1;
+ }
sock_put(sk);
}
@@ -2683,11 +2781,15 @@
rhashtable_walk_start(&iter);
while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
- spin_lock_bh(&tsk->sk.sk_lock.slock);
+ sock_hold(&tsk->sk);
+ rhashtable_walk_stop(&iter);
+ lock_sock(&tsk->sk);
msg = &tsk->phdr;
msg_set_prevnode(msg, tipc_own_addr(net));
msg_set_orignode(msg, tipc_own_addr(net));
- spin_unlock_bh(&tsk->sk.sk_lock.slock);
+ release_sock(&tsk->sk);
+ rhashtable_walk_start(&iter);
+ sock_put(&tsk->sk);
}
rhashtable_walk_stop(&iter);
@@ -2967,6 +3069,9 @@
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)
@@ -3167,7 +3272,9 @@
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;
if (nla_put_u32(skb, TIPC_NLA_CON_NODE, peer_node))
goto msg_full;
@@ -3224,7 +3331,7 @@
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;
@@ -3329,7 +3436,7 @@
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;
@@ -3347,7 +3454,7 @@
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;
@@ -3404,7 +3511,7 @@
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;
@@ -3491,9 +3598,9 @@
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;
@@ -3523,3 +3630,187 @@
return skb->len;
}
+
+/**
+ * tipc_sk_filtering - check if a socket should be traced
+ * @sk: the socket to be examined
+ * @sysctl_tipc_sk_filter[]: the socket tuple for filtering,
+ * (portid, sock type, name type, name lower, name upper)
+ *
+ * Returns true if the socket meets the socket tuple data
+ * (value 0 = 'any') or when there is no tuple set (all = 0),
+ * otherwise false
+ */
+bool tipc_sk_filtering(struct sock *sk)
+{
+ struct tipc_sock *tsk;
+ struct publication *p;
+ u32 _port, _sktype, _type, _lower, _upper;
+ u32 type = 0, lower = 0, upper = 0;
+
+ if (!sk)
+ return true;
+
+ tsk = tipc_sk(sk);
+
+ _port = sysctl_tipc_sk_filter[0];
+ _sktype = sysctl_tipc_sk_filter[1];
+ _type = sysctl_tipc_sk_filter[2];
+ _lower = sysctl_tipc_sk_filter[3];
+ _upper = sysctl_tipc_sk_filter[4];
+
+ if (!_port && !_sktype && !_type && !_lower && !_upper)
+ return true;
+
+ if (_port)
+ return (_port == tsk->portid);
+
+ if (_sktype && _sktype != sk->sk_type)
+ return false;
+
+ if (tsk->published) {
+ p = list_first_entry_or_null(&tsk->publications,
+ struct publication, binding_sock);
+ if (p) {
+ type = p->type;
+ lower = p->lower;
+ upper = p->upper;
+ }
+ }
+
+ if (!tipc_sk_type_connectionless(sk)) {
+ type = tsk->conn_type;
+ lower = tsk->conn_instance;
+ upper = tsk->conn_instance;
+ }
+
+ if ((_type && _type != type) || (_lower && _lower != lower) ||
+ (_upper && _upper != upper))
+ return false;
+
+ return true;
+}
+
+u32 tipc_sock_get_portid(struct sock *sk)
+{
+ return (sk) ? (tipc_sk(sk))->portid : 0;
+}
+
+/**
+ * tipc_sk_overlimit1 - check if socket rx queue is about to be overloaded,
+ * both the rcv and backlog queues are considered
+ * @sk: tipc sk to be checked
+ * @skb: tipc msg to be checked
+ *
+ * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ */
+
+bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb)
+{
+ atomic_t *dcnt = &tipc_sk(sk)->dupl_rcvcnt;
+ unsigned int lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt);
+ unsigned int qsize = sk->sk_backlog.len + sk_rmem_alloc_get(sk);
+
+ return (qsize > lim * 90 / 100);
+}
+
+/**
+ * tipc_sk_overlimit2 - check if socket rx queue is about to be overloaded,
+ * only the rcv queue is considered
+ * @sk: tipc sk to be checked
+ * @skb: tipc msg to be checked
+ *
+ * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ */
+
+bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb)
+{
+ unsigned int lim = rcvbuf_limit(sk, skb);
+ unsigned int qsize = sk_rmem_alloc_get(sk);
+
+ return (qsize > lim * 90 / 100);
+}
+
+/**
+ * tipc_sk_dump - dump TIPC socket
+ * @sk: tipc sk to be dumped
+ * @dqueues: bitmask to decide if any socket queue to be dumped?
+ * - TIPC_DUMP_NONE: don't dump socket queues
+ * - TIPC_DUMP_SK_SNDQ: dump socket send queue
+ * - TIPC_DUMP_SK_RCVQ: dump socket rcv queue
+ * - TIPC_DUMP_SK_BKLGQ: dump socket backlog queue
+ * - TIPC_DUMP_ALL: dump all the socket queues above
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
+{
+ int i = 0;
+ size_t sz = (dqueues) ? SK_LMAX : SK_LMIN;
+ struct tipc_sock *tsk;
+ struct publication *p;
+ bool tsk_connected;
+
+ if (!sk) {
+ i += scnprintf(buf, sz, "sk data: (null)\n");
+ return i;
+ }
+
+ tsk = tipc_sk(sk);
+ tsk_connected = !tipc_sk_type_connectionless(sk);
+
+ i += scnprintf(buf, sz, "sk data: %u", sk->sk_type);
+ i += scnprintf(buf + i, sz - i, " %d", sk->sk_state);
+ i += scnprintf(buf + i, sz - i, " %x", tsk_own_node(tsk));
+ i += scnprintf(buf + i, sz - i, " %u", tsk->portid);
+ i += scnprintf(buf + i, sz - i, " | %u", tsk_connected);
+ if (tsk_connected) {
+ i += scnprintf(buf + i, sz - i, " %x", tsk_peer_node(tsk));
+ i += scnprintf(buf + i, sz - i, " %u", tsk_peer_port(tsk));
+ i += scnprintf(buf + i, sz - i, " %u", tsk->conn_type);
+ i += scnprintf(buf + i, sz - i, " %u", tsk->conn_instance);
+ }
+ i += scnprintf(buf + i, sz - i, " | %u", tsk->published);
+ if (tsk->published) {
+ p = list_first_entry_or_null(&tsk->publications,
+ struct publication, binding_sock);
+ i += scnprintf(buf + i, sz - i, " %u", (p) ? p->type : 0);
+ i += scnprintf(buf + i, sz - i, " %u", (p) ? p->lower : 0);
+ i += scnprintf(buf + i, sz - i, " %u", (p) ? p->upper : 0);
+ }
+ i += scnprintf(buf + i, sz - i, " | %u", tsk->snd_win);
+ i += scnprintf(buf + i, sz - i, " %u", tsk->rcv_win);
+ i += scnprintf(buf + i, sz - i, " %u", tsk->max_pkt);
+ i += scnprintf(buf + i, sz - i, " %x", tsk->peer_caps);
+ i += scnprintf(buf + i, sz - i, " %u", tsk->cong_link_cnt);
+ i += scnprintf(buf + i, sz - i, " %u", tsk->snt_unacked);
+ i += scnprintf(buf + i, sz - i, " %u", tsk->rcv_unacked);
+ i += scnprintf(buf + i, sz - i, " %u", atomic_read(&tsk->dupl_rcvcnt));
+ i += scnprintf(buf + i, sz - i, " %u", sk->sk_shutdown);
+ i += scnprintf(buf + i, sz - i, " | %d", sk_wmem_alloc_get(sk));
+ i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf);
+ i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk));
+ i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf);
+ i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len));
+
+ if (dqueues & TIPC_DUMP_SK_SNDQ) {
+ i += scnprintf(buf + i, sz - i, "sk_write_queue: ");
+ i += tipc_list_dump(&sk->sk_write_queue, false, buf + i);
+ }
+
+ if (dqueues & TIPC_DUMP_SK_RCVQ) {
+ i += scnprintf(buf + i, sz - i, "sk_receive_queue: ");
+ i += tipc_list_dump(&sk->sk_receive_queue, false, buf + i);
+ }
+
+ if (dqueues & TIPC_DUMP_SK_BKLGQ) {
+ i += scnprintf(buf + i, sz - i, "sk_backlog:\n head ");
+ i += tipc_skb_dump(sk->sk_backlog.head, false, buf + i);
+ if (sk->sk_backlog.tail != sk->sk_backlog.head) {
+ i += scnprintf(buf + i, sz - i, " tail ");
+ i += tipc_skb_dump(sk->sk_backlog.tail, false,
+ buf + i);
+ }
+ }
+
+ return i;
+}
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 5e575f2..235b967 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -71,4 +71,8 @@
int tipc_dump_start(struct netlink_callback *cb);
int __tipc_dump_start(struct netlink_callback *cb, struct net *net);
int tipc_dump_done(struct netlink_callback *cb);
+u32 tipc_sock_get_portid(struct sock *sk);
+bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb);
+bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb);
+
#endif
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index d793b43..aa015c2 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -77,8 +77,9 @@
u32 found_lower, u32 found_upper,
u32 event, u32 port, u32 node,
u32 scope, int must);
-int tipc_topsrv_start(struct net *net);
-void tipc_topsrv_stop(struct net *net);
+
+int __net_init tipc_topsrv_init_net(struct net *net);
+void __net_exit tipc_topsrv_exit_net(struct net *net);
void tipc_sub_put(struct tipc_subscription *subscription);
void tipc_sub_get(struct tipc_subscription *subscription);
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 1a779b1..6159d32 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -34,6 +34,7 @@
*/
#include "core.h"
+#include "trace.h"
#include <linux/sysctl.h>
@@ -45,14 +46,23 @@
.data = &sysctl_tipc_rmem,
.maxlen = sizeof(sysctl_tipc_rmem),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ONE,
},
{
.procname = "named_timeout",
.data = &sysctl_tipc_named_timeout,
.maxlen = sizeof(sysctl_tipc_named_timeout),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
+ {
+ .procname = "sk_filter",
+ .data = &sysctl_tipc_sk_filter,
+ .maxlen = sizeof(sysctl_tipc_sk_filter),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
},
{}
};
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index b84c005..3a12fc1 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -40,6 +40,7 @@
#include "socket.h"
#include "addr.h"
#include "msg.h"
+#include "bearer.h"
#include <net/sock.h>
#include <linux/module.h>
@@ -57,16 +58,11 @@
* @idr_lock: protect the connection identifier set
* @idr_in_use: amount of allocated identifier entry
* @net: network namspace instance
- * @rcvbuf_cache: memory cache of server receive buffer
+ * @awork: accept work item
* @rcv_wq: receive workqueue
* @send_wq: send workqueue
- * @max_rcvbuf_size: maximum permitted receive message length
- * @tipc_conn_new: callback will be called when new connection is incoming
- * @tipc_conn_release: callback will be called before releasing the connection
- * @tipc_conn_recvmsg: callback will be called when message arrives
+ * @listener: topsrv listener socket
* @name: server name
- * @imp: message importance
- * @type: socket type
*/
struct tipc_topsrv {
struct idr conn_idr;
@@ -76,7 +72,6 @@
struct work_struct awork;
struct workqueue_struct *rcv_wq;
struct workqueue_struct *send_wq;
- int max_rcvbuf_size;
struct socket *listener;
char name[TIPC_SERVER_NAME_LEN];
};
@@ -90,9 +85,7 @@
* @server: pointer to connected server
* @sub_list: lsit to all pertaing subscriptions
* @sub_lock: lock protecting the subscription list
- * @outqueue_lock: control access to the outqueue
* @rwork: receive work item
- * @rx_action: what to do when connection socket is active
* @outqueue: pointer to first outbound message in queue
* @outqueue_lock: control access to the outqueue
* @swork: send work item
@@ -371,6 +364,7 @@
struct tipc_subscription *sub;
if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) {
+ s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL);
tipc_conn_delete_sub(con, s);
return 0;
}
@@ -400,11 +394,11 @@
iov.iov_base = &s;
iov.iov_len = sizeof(s);
msg.msg_name = NULL;
- iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len);
+ iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len);
ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
if (ret == -EWOULDBLOCK)
return -EWOULDBLOCK;
- if (ret > 0) {
+ if (ret == sizeof(s)) {
read_lock_bh(&sk->sk_callback_lock);
ret = tipc_conn_rcv_sub(srv, con, &s);
read_unlock_bh(&sk->sk_callback_lock);
@@ -483,7 +477,7 @@
}
}
-/* tipc_toprsv_listener_data_ready - interrupt callback with connection request
+/* tipc_topsrv_listener_data_ready - interrupt callback with connection request
* The queued job is launched into tipc_topsrv_accept()
*/
static void tipc_topsrv_listener_data_ready(struct sock *sk)
@@ -615,6 +609,7 @@
memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt));
skb_queue_head_init(&evtq);
__skb_queue_tail(&evtq, skb);
+ tipc_loopback_trace(net, &evtq);
tipc_sk_rcv(net, &evtq);
}
@@ -642,7 +637,7 @@
destroy_workqueue(s->send_wq);
}
-int tipc_topsrv_start(struct net *net)
+static int tipc_topsrv_start(struct net *net)
{
struct tipc_net *tn = tipc_net(net);
const char name[] = "topology_server";
@@ -654,7 +649,6 @@
return -ENOMEM;
srv->net = net;
- srv->max_rcvbuf_size = sizeof(struct tipc_subscr);
INIT_WORK(&srv->awork, tipc_topsrv_accept);
strscpy(srv->name, name, sizeof(srv->name));
@@ -676,7 +670,7 @@
return ret;
}
-void tipc_topsrv_stop(struct net *net)
+static void tipc_topsrv_stop(struct net *net)
{
struct tipc_topsrv *srv = tipc_topsrv(net);
struct socket *lsock = srv->listener;
@@ -701,3 +695,13 @@
idr_destroy(&srv->conn_idr);
kfree(srv);
}
+
+int __net_init tipc_topsrv_init_net(struct net *net)
+{
+ return tipc_topsrv_start(net);
+}
+
+void __net_exit tipc_topsrv_exit_net(struct net *net)
+{
+ tipc_topsrv_stop(net);
+}
diff --git a/net/tipc/trace.c b/net/tipc/trace.c
new file mode 100644
index 0000000..265f6a2
--- /dev/null
+++ b/net/tipc/trace.c
@@ -0,0 +1,206 @@
+/*
+ * net/tipc/trace.c: TIPC tracepoints code
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+/**
+ * socket tuples for filtering in socket traces:
+ * (portid, sock type, name type, name lower, name upper)
+ */
+unsigned long sysctl_tipc_sk_filter[5] __read_mostly = {0, };
+
+/**
+ * tipc_skb_dump - dump TIPC skb data
+ * @skb: skb to be dumped
+ * @more: dump more?
+ * - false: dump only tipc msg data
+ * - true: dump kernel-related skb data and tipc cb[] array as well
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf)
+{
+ int i = 0;
+ size_t sz = (more) ? SKB_LMAX : SKB_LMIN;
+ struct tipc_msg *hdr;
+ struct tipc_skb_cb *skbcb;
+
+ if (!skb) {
+ i += scnprintf(buf, sz, "msg: (null)\n");
+ return i;
+ }
+
+ hdr = buf_msg(skb);
+ skbcb = TIPC_SKB_CB(skb);
+
+ /* tipc msg data section */
+ i += scnprintf(buf, sz, "msg: %u", msg_user(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_type(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_hdr_sz(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_data_sz(hdr));
+ i += scnprintf(buf + i, sz - i, " %x", msg_orignode(hdr));
+ i += scnprintf(buf + i, sz - i, " %x", msg_destnode(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_seqno(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_ack(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_bcast_ack(hdr));
+ switch (msg_user(hdr)) {
+ case LINK_PROTOCOL:
+ i += scnprintf(buf + i, sz - i, " %c", msg_net_plane(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_probe(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_peer_stopping(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_session(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_next_sent(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_seq_gap(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_bc_snd_nxt(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_bc_gap(hdr));
+ break;
+ case TIPC_LOW_IMPORTANCE:
+ case TIPC_MEDIUM_IMPORTANCE:
+ case TIPC_HIGH_IMPORTANCE:
+ case TIPC_CRITICAL_IMPORTANCE:
+ case CONN_MANAGER:
+ case SOCK_WAKEUP:
+ i += scnprintf(buf + i, sz - i, " | %u", msg_origport(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_destport(hdr));
+ switch (msg_type(hdr)) {
+ case TIPC_NAMED_MSG:
+ i += scnprintf(buf + i, sz - i, " %u",
+ msg_nametype(hdr));
+ i += scnprintf(buf + i, sz - i, " %u",
+ msg_nameinst(hdr));
+ break;
+ case TIPC_MCAST_MSG:
+ i += scnprintf(buf + i, sz - i, " %u",
+ msg_nametype(hdr));
+ i += scnprintf(buf + i, sz - i, " %u",
+ msg_namelower(hdr));
+ i += scnprintf(buf + i, sz - i, " %u",
+ msg_nameupper(hdr));
+ break;
+ default:
+ break;
+ }
+ i += scnprintf(buf + i, sz - i, " | %u",
+ msg_src_droppable(hdr));
+ i += scnprintf(buf + i, sz - i, " %u",
+ msg_dest_droppable(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_errcode(hdr));
+ i += scnprintf(buf + i, sz - i, " %u", msg_reroute_cnt(hdr));
+ break;
+ default:
+ /* need more? */
+ break;
+ }
+
+ i += scnprintf(buf + i, sz - i, "\n");
+ if (!more)
+ return i;
+
+ /* kernel-related skb data section */
+ i += scnprintf(buf + i, sz - i, "skb: %s",
+ (skb->dev) ? skb->dev->name : "n/a");
+ i += scnprintf(buf + i, sz - i, " %u", skb->len);
+ i += scnprintf(buf + i, sz - i, " %u", skb->data_len);
+ i += scnprintf(buf + i, sz - i, " %u", skb->hdr_len);
+ i += scnprintf(buf + i, sz - i, " %u", skb->truesize);
+ i += scnprintf(buf + i, sz - i, " %u", skb_cloned(skb));
+ i += scnprintf(buf + i, sz - i, " %p", skb->sk);
+ i += scnprintf(buf + i, sz - i, " %u", skb_shinfo(skb)->nr_frags);
+ i += scnprintf(buf + i, sz - i, " %llx",
+ ktime_to_ms(skb_get_ktime(skb)));
+ i += scnprintf(buf + i, sz - i, " %llx\n",
+ ktime_to_ms(skb_hwtstamps(skb)->hwtstamp));
+
+ /* tipc skb cb[] data section */
+ i += scnprintf(buf + i, sz - i, "cb[]: %u", skbcb->bytes_read);
+ i += scnprintf(buf + i, sz - i, " %u", skbcb->orig_member);
+ i += scnprintf(buf + i, sz - i, " %u",
+ jiffies_to_msecs(skbcb->nxt_retr));
+ i += scnprintf(buf + i, sz - i, " %u", skbcb->validated);
+ i += scnprintf(buf + i, sz - i, " %u", skbcb->chain_imp);
+ i += scnprintf(buf + i, sz - i, " %u\n", skbcb->ackers);
+
+ return i;
+}
+
+/**
+ * tipc_list_dump - dump TIPC skb list/queue
+ * @list: list of skbs to be dumped
+ * @more: dump more?
+ * - false: dump only the head & tail skbs
+ * - true: dump the first & last 5 skbs
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf)
+{
+ int i = 0;
+ size_t sz = (more) ? LIST_LMAX : LIST_LMIN;
+ u32 count, len;
+ struct sk_buff *hskb, *tskb, *skb, *tmp;
+
+ if (!list) {
+ i += scnprintf(buf, sz, "(null)\n");
+ return i;
+ }
+
+ len = skb_queue_len(list);
+ i += scnprintf(buf, sz, "len = %d\n", len);
+
+ if (!len)
+ return i;
+
+ if (!more) {
+ hskb = skb_peek(list);
+ i += scnprintf(buf + i, sz - i, " head ");
+ i += tipc_skb_dump(hskb, false, buf + i);
+ if (len > 1) {
+ tskb = skb_peek_tail(list);
+ i += scnprintf(buf + i, sz - i, " tail ");
+ i += tipc_skb_dump(tskb, false, buf + i);
+ }
+ } else {
+ count = 0;
+ skb_queue_walk_safe(list, skb, tmp) {
+ count++;
+ if (count == 6)
+ i += scnprintf(buf + i, sz - i, " .\n .\n");
+ if (count > 5 && count <= len - 5)
+ continue;
+ i += scnprintf(buf + i, sz - i, " #%d ", count);
+ i += tipc_skb_dump(skb, false, buf + i);
+ }
+ }
+ return i;
+}
diff --git a/net/tipc/trace.h b/net/tipc/trace.h
new file mode 100644
index 0000000..4d8e004
--- /dev/null
+++ b/net/tipc/trace.h
@@ -0,0 +1,431 @@
+/*
+ * net/tipc/trace.h: TIPC tracepoints
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tipc
+
+#if !defined(_TIPC_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TIPC_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "core.h"
+#include "link.h"
+#include "socket.h"
+#include "node.h"
+
+#define SKB_LMIN (100)
+#define SKB_LMAX (SKB_LMIN * 2)
+#define LIST_LMIN (SKB_LMIN * 3)
+#define LIST_LMAX (SKB_LMIN * 11)
+#define SK_LMIN (SKB_LMIN * 2)
+#define SK_LMAX (SKB_LMIN * 11)
+#define LINK_LMIN (SKB_LMIN)
+#define LINK_LMAX (SKB_LMIN * 16)
+#define NODE_LMIN (SKB_LMIN)
+#define NODE_LMAX (SKB_LMIN * 11)
+
+#ifndef __TIPC_TRACE_ENUM
+#define __TIPC_TRACE_ENUM
+enum {
+ TIPC_DUMP_NONE = 0,
+
+ TIPC_DUMP_TRANSMQ = 1,
+ TIPC_DUMP_BACKLOGQ = (1 << 1),
+ TIPC_DUMP_DEFERDQ = (1 << 2),
+ TIPC_DUMP_INPUTQ = (1 << 3),
+ TIPC_DUMP_WAKEUP = (1 << 4),
+
+ TIPC_DUMP_SK_SNDQ = (1 << 8),
+ TIPC_DUMP_SK_RCVQ = (1 << 9),
+ TIPC_DUMP_SK_BKLGQ = (1 << 10),
+ TIPC_DUMP_ALL = 0xffffu
+};
+#endif
+
+/* Link & Node FSM states: */
+#define state_sym(val) \
+ __print_symbolic(val, \
+ {(0xe), "ESTABLISHED" },\
+ {(0xe << 4), "ESTABLISHING" },\
+ {(0x1 << 8), "RESET" },\
+ {(0x2 << 12), "RESETTING" },\
+ {(0xd << 16), "PEER_RESET" },\
+ {(0xf << 20), "FAILINGOVER" },\
+ {(0xc << 24), "SYNCHING" },\
+ {(0xdd), "SELF_DOWN_PEER_DOWN" },\
+ {(0xaa), "SELF_UP_PEER_UP" },\
+ {(0xd1), "SELF_DOWN_PEER_LEAVING" },\
+ {(0xac), "SELF_UP_PEER_COMING" },\
+ {(0xca), "SELF_COMING_PEER_UP" },\
+ {(0x1d), "SELF_LEAVING_PEER_DOWN" },\
+ {(0xf0), "FAILINGOVER" },\
+ {(0xcc), "SYNCHING" })
+
+/* Link & Node FSM events: */
+#define evt_sym(val) \
+ __print_symbolic(val, \
+ {(0xec1ab1e), "ESTABLISH_EVT" },\
+ {(0x9eed0e), "PEER_RESET_EVT" },\
+ {(0xfa110e), "FAILURE_EVT" },\
+ {(0x10ca1d0e), "RESET_EVT" },\
+ {(0xfa110bee), "FAILOVER_BEGIN_EVT" },\
+ {(0xfa110ede), "FAILOVER_END_EVT" },\
+ {(0xc1ccbee), "SYNCH_BEGIN_EVT" },\
+ {(0xc1ccede), "SYNCH_END_EVT" },\
+ {(0xece), "SELF_ESTABL_CONTACT_EVT" },\
+ {(0x1ce), "SELF_LOST_CONTACT_EVT" },\
+ {(0x9ece), "PEER_ESTABL_CONTACT_EVT" },\
+ {(0x91ce), "PEER_LOST_CONTACT_EVT" },\
+ {(0xfbe), "FAILOVER_BEGIN_EVT" },\
+ {(0xfee), "FAILOVER_END_EVT" },\
+ {(0xcbe), "SYNCH_BEGIN_EVT" },\
+ {(0xcee), "SYNCH_END_EVT" })
+
+/* Bearer, net device events: */
+#define dev_evt_sym(val) \
+ __print_symbolic(val, \
+ {(NETDEV_CHANGE), "NETDEV_CHANGE" },\
+ {(NETDEV_GOING_DOWN), "NETDEV_GOING_DOWN" },\
+ {(NETDEV_UP), "NETDEV_UP" },\
+ {(NETDEV_CHANGEMTU), "NETDEV_CHANGEMTU" },\
+ {(NETDEV_CHANGEADDR), "NETDEV_CHANGEADDR" },\
+ {(NETDEV_UNREGISTER), "NETDEV_UNREGISTER" },\
+ {(NETDEV_CHANGENAME), "NETDEV_CHANGENAME" })
+
+extern unsigned long sysctl_tipc_sk_filter[5] __read_mostly;
+
+int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
+int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf);
+int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf);
+int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf);
+int tipc_node_dump(struct tipc_node *n, bool more, char *buf);
+bool tipc_sk_filtering(struct sock *sk);
+
+DECLARE_EVENT_CLASS(tipc_skb_class,
+
+ TP_PROTO(struct sk_buff *skb, bool more, const char *header),
+
+ TP_ARGS(skb, more, header),
+
+ TP_STRUCT__entry(
+ __string(header, header)
+ __dynamic_array(char, buf, (more) ? SKB_LMAX : SKB_LMIN)
+ ),
+
+ TP_fast_assign(
+ __assign_str(header, header);
+ tipc_skb_dump(skb, more, __get_str(buf));
+ ),
+
+ TP_printk("%s\n%s", __get_str(header), __get_str(buf))
+)
+
+#define DEFINE_SKB_EVENT(name) \
+DEFINE_EVENT(tipc_skb_class, name, \
+ TP_PROTO(struct sk_buff *skb, bool more, const char *header), \
+ TP_ARGS(skb, more, header))
+DEFINE_SKB_EVENT(tipc_skb_dump);
+DEFINE_SKB_EVENT(tipc_proto_build);
+DEFINE_SKB_EVENT(tipc_proto_rcv);
+
+DECLARE_EVENT_CLASS(tipc_list_class,
+
+ TP_PROTO(struct sk_buff_head *list, bool more, const char *header),
+
+ TP_ARGS(list, more, header),
+
+ TP_STRUCT__entry(
+ __string(header, header)
+ __dynamic_array(char, buf, (more) ? LIST_LMAX : LIST_LMIN)
+ ),
+
+ TP_fast_assign(
+ __assign_str(header, header);
+ tipc_list_dump(list, more, __get_str(buf));
+ ),
+
+ TP_printk("%s\n%s", __get_str(header), __get_str(buf))
+);
+
+#define DEFINE_LIST_EVENT(name) \
+DEFINE_EVENT(tipc_list_class, name, \
+ TP_PROTO(struct sk_buff_head *list, bool more, const char *header), \
+ TP_ARGS(list, more, header))
+DEFINE_LIST_EVENT(tipc_list_dump);
+
+DECLARE_EVENT_CLASS(tipc_sk_class,
+
+ TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues,
+ const char *header),
+
+ TP_ARGS(sk, skb, dqueues, header),
+
+ TP_STRUCT__entry(
+ __string(header, header)
+ __field(u32, portid)
+ __dynamic_array(char, buf, (dqueues) ? SK_LMAX : SK_LMIN)
+ __dynamic_array(char, skb_buf, (skb) ? SKB_LMIN : 1)
+ ),
+
+ TP_fast_assign(
+ __assign_str(header, header);
+ __entry->portid = tipc_sock_get_portid(sk);
+ tipc_sk_dump(sk, dqueues, __get_str(buf));
+ if (skb)
+ tipc_skb_dump(skb, false, __get_str(skb_buf));
+ else
+ *(__get_str(skb_buf)) = '\0';
+ ),
+
+ TP_printk("<%u> %s\n%s%s", __entry->portid, __get_str(header),
+ __get_str(skb_buf), __get_str(buf))
+);
+
+#define DEFINE_SK_EVENT_FILTER(name) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
+ TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+ const char *header), \
+ TP_ARGS(sk, skb, dqueues, header), \
+ TP_CONDITION(tipc_sk_filtering(sk)))
+DEFINE_SK_EVENT_FILTER(tipc_sk_dump);
+DEFINE_SK_EVENT_FILTER(tipc_sk_create);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmcast);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmsg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendstream);
+DEFINE_SK_EVENT_FILTER(tipc_sk_poll);
+DEFINE_SK_EVENT_FILTER(tipc_sk_filter_rcv);
+DEFINE_SK_EVENT_FILTER(tipc_sk_advance_rx);
+DEFINE_SK_EVENT_FILTER(tipc_sk_rej_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_drop_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_release);
+DEFINE_SK_EVENT_FILTER(tipc_sk_shutdown);
+
+#define DEFINE_SK_EVENT_FILTER_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
+ TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+ const char *header), \
+ TP_ARGS(sk, skb, dqueues, header), \
+ TP_CONDITION(tipc_sk_filtering(sk) && (cond)))
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit1, tipc_sk_overlimit1(sk, skb));
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit2, tipc_sk_overlimit2(sk, skb));
+
+DECLARE_EVENT_CLASS(tipc_link_class,
+
+ TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header),
+
+ TP_ARGS(l, dqueues, header),
+
+ TP_STRUCT__entry(
+ __string(header, header)
+ __array(char, name, TIPC_MAX_LINK_NAME)
+ __dynamic_array(char, buf, (dqueues) ? LINK_LMAX : LINK_LMIN)
+ ),
+
+ TP_fast_assign(
+ __assign_str(header, header);
+ tipc_link_name_ext(l, __entry->name);
+ tipc_link_dump(l, dqueues, __get_str(buf));
+ ),
+
+ TP_printk("<%s> %s\n%s", __entry->name, __get_str(header),
+ __get_str(buf))
+);
+
+#define DEFINE_LINK_EVENT(name) \
+DEFINE_EVENT(tipc_link_class, name, \
+ TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
+ TP_ARGS(l, dqueues, header))
+DEFINE_LINK_EVENT(tipc_link_dump);
+DEFINE_LINK_EVENT(tipc_link_conges);
+DEFINE_LINK_EVENT(tipc_link_timeout);
+DEFINE_LINK_EVENT(tipc_link_reset);
+
+#define DEFINE_LINK_EVENT_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_link_class, name, \
+ TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
+ TP_ARGS(l, dqueues, header), \
+ TP_CONDITION(cond))
+DEFINE_LINK_EVENT_COND(tipc_link_too_silent, tipc_link_too_silent(l));
+
+DECLARE_EVENT_CLASS(tipc_link_transmq_class,
+
+ TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+
+ TP_ARGS(r, f, t, tq),
+
+ TP_STRUCT__entry(
+ __array(char, name, TIPC_MAX_LINK_NAME)
+ __field(u16, from)
+ __field(u16, to)
+ __field(u32, len)
+ __field(u16, fseqno)
+ __field(u16, lseqno)
+ ),
+
+ TP_fast_assign(
+ tipc_link_name_ext(r, __entry->name);
+ __entry->from = f;
+ __entry->to = t;
+ __entry->len = skb_queue_len(tq);
+ __entry->fseqno = msg_seqno(buf_msg(skb_peek(tq)));
+ __entry->lseqno = msg_seqno(buf_msg(skb_peek_tail(tq)));
+ ),
+
+ TP_printk("<%s> retrans req: [%u-%u] transmq: %u [%u-%u]\n",
+ __entry->name, __entry->from, __entry->to,
+ __entry->len, __entry->fseqno, __entry->lseqno)
+);
+
+DEFINE_EVENT(tipc_link_transmq_class, tipc_link_retrans,
+ TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+ TP_ARGS(r, f, t, tq)
+);
+
+DEFINE_EVENT_PRINT(tipc_link_transmq_class, tipc_link_bc_ack,
+ TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+ TP_ARGS(r, f, t, tq),
+ TP_printk("<%s> acked: [%u-%u] transmq: %u [%u-%u]\n",
+ __entry->name, __entry->from, __entry->to,
+ __entry->len, __entry->fseqno, __entry->lseqno)
+);
+
+DECLARE_EVENT_CLASS(tipc_node_class,
+
+ TP_PROTO(struct tipc_node *n, bool more, const char *header),
+
+ TP_ARGS(n, more, header),
+
+ TP_STRUCT__entry(
+ __string(header, header)
+ __field(u32, addr)
+ __dynamic_array(char, buf, (more) ? NODE_LMAX : NODE_LMIN)
+ ),
+
+ TP_fast_assign(
+ __assign_str(header, header);
+ __entry->addr = tipc_node_get_addr(n);
+ tipc_node_dump(n, more, __get_str(buf));
+ ),
+
+ TP_printk("<%x> %s\n%s", __entry->addr, __get_str(header),
+ __get_str(buf))
+);
+
+#define DEFINE_NODE_EVENT(name) \
+DEFINE_EVENT(tipc_node_class, name, \
+ TP_PROTO(struct tipc_node *n, bool more, const char *header), \
+ TP_ARGS(n, more, header))
+DEFINE_NODE_EVENT(tipc_node_dump);
+DEFINE_NODE_EVENT(tipc_node_create);
+DEFINE_NODE_EVENT(tipc_node_delete);
+DEFINE_NODE_EVENT(tipc_node_lost_contact);
+DEFINE_NODE_EVENT(tipc_node_timeout);
+DEFINE_NODE_EVENT(tipc_node_link_up);
+DEFINE_NODE_EVENT(tipc_node_link_down);
+DEFINE_NODE_EVENT(tipc_node_reset_links);
+DEFINE_NODE_EVENT(tipc_node_check_state);
+
+DECLARE_EVENT_CLASS(tipc_fsm_class,
+
+ TP_PROTO(const char *name, u32 os, u32 ns, int evt),
+
+ TP_ARGS(name, os, ns, evt),
+
+ TP_STRUCT__entry(
+ __string(name, name)
+ __field(u32, os)
+ __field(u32, ns)
+ __field(u32, evt)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, name);
+ __entry->os = os;
+ __entry->ns = ns;
+ __entry->evt = evt;
+ ),
+
+ TP_printk("<%s> %s--(%s)->%s\n", __get_str(name),
+ state_sym(__entry->os), evt_sym(__entry->evt),
+ state_sym(__entry->ns))
+);
+
+#define DEFINE_FSM_EVENT(fsm_name) \
+DEFINE_EVENT(tipc_fsm_class, fsm_name, \
+ TP_PROTO(const char *name, u32 os, u32 ns, int evt), \
+ TP_ARGS(name, os, ns, evt))
+DEFINE_FSM_EVENT(tipc_link_fsm);
+DEFINE_FSM_EVENT(tipc_node_fsm);
+
+TRACE_EVENT(tipc_l2_device_event,
+
+ TP_PROTO(struct net_device *dev, struct tipc_bearer *b,
+ unsigned long evt),
+
+ TP_ARGS(dev, b, evt),
+
+ TP_STRUCT__entry(
+ __string(dev_name, dev->name)
+ __string(b_name, b->name)
+ __field(unsigned long, evt)
+ __field(u8, b_up)
+ __field(u8, carrier)
+ __field(u8, oper)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev_name, dev->name);
+ __assign_str(b_name, b->name);
+ __entry->evt = evt;
+ __entry->b_up = test_bit(0, &b->up);
+ __entry->carrier = netif_carrier_ok(dev);
+ __entry->oper = netif_oper_up(dev);
+ ),
+
+ TP_printk("%s on: <%s>/<%s> oper: %s carrier: %s bearer: %s\n",
+ dev_evt_sym(__entry->evt), __get_str(dev_name),
+ __get_str(b_name), (__entry->oper) ? "up" : "down",
+ (__entry->carrier) ? "ok" : "notok",
+ (__entry->b_up) ? "up" : "down")
+);
+
+#endif /* _TIPC_TRACE_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 9783101..287df68 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"
@@ -76,6 +76,7 @@
/* struct udp_replicast - container for UDP remote addresses */
struct udp_replicast {
struct udp_media_addr addr;
+ struct dst_cache dst_cache;
struct rcu_head rcu;
struct list_head list;
};
@@ -158,47 +159,52 @@
/* tipc_send_msg - enqueue a send request */
static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
struct udp_bearer *ub, struct udp_media_addr *src,
- struct udp_media_addr *dst)
+ struct udp_media_addr *dst, struct dst_cache *cache)
{
+ struct dst_entry *ndst = dst_cache_get(cache);
int ttl, err = 0;
- struct rtable *rt;
if (dst->proto == htons(ETH_P_IP)) {
- struct flowi4 fl = {
- .daddr = dst->ipv4.s_addr,
- .saddr = src->ipv4.s_addr,
- .flowi4_mark = skb->mark,
- .flowi4_proto = IPPROTO_UDP
- };
- rt = ip_route_output_key(net, &fl);
- if (IS_ERR(rt)) {
- err = PTR_ERR(rt);
- goto tx_error;
+ struct rtable *rt = (struct rtable *)ndst;
+
+ if (!rt) {
+ struct flowi4 fl = {
+ .daddr = dst->ipv4.s_addr,
+ .saddr = src->ipv4.s_addr,
+ .flowi4_mark = skb->mark,
+ .flowi4_proto = IPPROTO_UDP
+ };
+ rt = ip_route_output_key(net, &fl);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ goto tx_error;
+ }
+ dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
}
- skb->dev = rt->dst.dev;
ttl = ip4_dst_hoplimit(&rt->dst);
udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr,
dst->ipv4.s_addr, 0, ttl, 0, src->port,
dst->port, false, true);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- struct dst_entry *ndst;
- struct flowi6 fl6 = {
- .flowi6_oif = ub->ifindex,
- .daddr = dst->ipv6,
- .saddr = src->ipv6,
- .flowi6_proto = IPPROTO_UDP
- };
- err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, &ndst,
- &fl6);
- if (err)
- goto tx_error;
+ if (!ndst) {
+ struct flowi6 fl6 = {
+ .flowi6_oif = ub->ifindex,
+ .daddr = dst->ipv6,
+ .saddr = src->ipv6,
+ .flowi6_proto = IPPROTO_UDP
+ };
+ err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk,
+ &ndst, &fl6);
+ if (err)
+ goto tx_error;
+ dst_cache_set_ip6(cache, ndst, &fl6.saddr);
+ }
ttl = ip6_dst_hoplimit(ndst);
- err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb,
- ndst->dev, &src->ipv6,
- &dst->ipv6, 0, ttl, 0, src->port,
- dst->port, false);
+ err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL,
+ &src->ipv6, &dst->ipv6, 0, ttl, 0,
+ src->port, dst->port, false);
#endif
}
return err;
@@ -225,14 +231,15 @@
}
skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rcu_dereference(b->media_ptr);
if (!ub) {
err = -ENODEV;
goto out;
}
if (addr->broadcast != TIPC_REPLICAST_SUPPORT)
- return tipc_udp_xmit(net, skb, ub, src, dst);
+ return tipc_udp_xmit(net, skb, ub, src, dst,
+ &ub->rcast.dst_cache);
/* Replicast, send an skb to each configured IP address */
list_for_each_entry_rcu(rcast, &ub->rcast.list, list) {
@@ -244,11 +251,10 @@
goto out;
}
- err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr);
- if (err) {
- kfree_skb(_skb);
+ err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr,
+ &rcast->dst_cache);
+ if (err)
goto out;
- }
}
err = 0;
out:
@@ -290,6 +296,11 @@
if (!rcast)
return -ENOMEM;
+ if (dst_cache_init(&rcast->dst_cache, GFP_ATOMIC)) {
+ kfree(rcast);
+ return -ENOMEM;
+ }
+
memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr));
if (ntohs(addr->proto) == ETH_P_IP)
@@ -356,25 +367,21 @@
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;
@@ -453,9 +460,9 @@
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;
@@ -483,7 +490,7 @@
}
}
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rtnl_dereference(b->media_ptr);
if (!ub) {
rtnl_unlock();
return -EINVAL;
@@ -525,11 +532,11 @@
struct udp_bearer *ub;
struct nlattr *nest;
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rtnl_dereference(b->media_ptr);
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;
@@ -607,8 +614,7 @@
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])
@@ -650,6 +656,7 @@
struct udp_tunnel_sock_cfg tuncfg = {NULL};
struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
u8 node_id[NODE_ID_LEN] = {0,};
+ int rmcast = 0;
ub = kzalloc(sizeof(*ub), GFP_ATOMIC);
if (!ub)
@@ -660,9 +667,7 @@
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]) {
@@ -680,6 +685,14 @@
if (err)
goto err;
+ if (remote.proto != local.proto) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ /* Checking remote ip address */
+ rmcast = tipc_udp_is_mcast_addr(&remote);
+
/* Autoconfigure own node identity if needed */
if (!tipc_own_id(net)) {
memcpy(node_id, local.ipv6.in6_u.u6_addr8, 16);
@@ -705,7 +718,12 @@
goto err;
}
udp_conf.family = AF_INET;
- udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+
+ /* Switch to use ANY to receive packets from group */
+ if (rmcast)
+ udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+ else
+ udp_conf.local_ip.s_addr = local.ipv4.s_addr;
udp_conf.use_udp_checksums = false;
ub->ifindex = dev->ifindex;
if (tipc_mtu_bad(dev, sizeof(struct iphdr) +
@@ -719,7 +737,10 @@
udp_conf.family = AF_INET6;
udp_conf.use_udp6_tx_checksums = true;
udp_conf.use_udp6_rx_checksums = true;
- udp_conf.local_ip6 = in6addr_any;
+ if (rmcast)
+ udp_conf.local_ip6 = in6addr_any;
+ else
+ udp_conf.local_ip6 = local.ipv6;
b->mtu = 1280;
#endif
} else {
@@ -736,22 +757,28 @@
tuncfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg);
+ err = dst_cache_init(&ub->rcast.dst_cache, GFP_ATOMIC);
+ if (err)
+ goto free;
+
/**
* The bcast media address port is used for all peers and the ip
* is used if it's a multicast address.
*/
memcpy(&b->bcast_addr.value, &remote, sizeof(remote));
- if (tipc_udp_is_mcast_addr(&remote))
+ if (rmcast)
err = enable_mcast(ub, &remote);
else
err = tipc_udp_rcast_add(b, &remote);
if (err)
- goto err;
+ goto free;
return 0;
+
+free:
+ dst_cache_destroy(&ub->rcast.dst_cache);
+ udp_tunnel_sock_release(ub->ubsock);
err:
- if (ub->ubsock)
- udp_tunnel_sock_release(ub->ubsock);
kfree(ub);
return err;
}
@@ -763,12 +790,13 @@
struct udp_replicast *rcast, *tmp;
list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) {
+ dst_cache_destroy(&rcast->dst_cache);
list_del_rcu(&rcast->list);
kfree_rcu(rcast, rcu);
}
- if (ub->ubsock)
- udp_tunnel_sock_release(ub->ubsock);
+ dst_cache_destroy(&ub->rcast.dst_cache);
+ udp_tunnel_sock_release(ub->ubsock);
synchronize_net();
kfree(ub);
}
@@ -778,13 +806,12 @@
{
struct udp_bearer *ub;
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rtnl_dereference(b->media_ptr);
if (!ub) {
pr_err("UDP bearer instance not found\n");
return;
}
- if (ub->ubsock)
- sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
+ sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
RCU_INIT_POINTER(ub->bearer, NULL);
/* sock_release need to be done outside of rtnl lock */