summaryrefslogtreecommitdiff
path: root/net/tipc
diff options
context:
space:
mode:
Diffstat (limited to 'net/tipc')
-rw-r--r--net/tipc/Makefile2
-rw-r--r--net/tipc/addr.h6
-rw-r--r--net/tipc/bearer.c147
-rw-r--r--net/tipc/bearer.h19
-rw-r--r--net/tipc/core.c10
-rw-r--r--net/tipc/core.h18
-rw-r--r--net/tipc/discover.c12
-rw-r--r--net/tipc/discover.h2
-rw-r--r--net/tipc/link.c105
-rw-r--r--net/tipc/link.h2
-rw-r--r--net/tipc/monitor.c803
-rw-r--r--net/tipc/monitor.h82
-rw-r--r--net/tipc/msg.c6
-rw-r--r--net/tipc/msg.h40
-rw-r--r--net/tipc/name_distr.c35
-rw-r--r--net/tipc/netlink.c27
-rw-r--r--net/tipc/netlink.h1
-rw-r--r--net/tipc/netlink_compat.c116
-rw-r--r--net/tipc/node.c260
-rw-r--r--net/tipc/node.h11
-rw-r--r--net/tipc/server.c30
-rw-r--r--net/tipc/server.h4
-rw-r--r--net/tipc/socket.c203
-rw-r--r--net/tipc/socket.h17
-rw-r--r--net/tipc/subscr.c7
-rw-r--r--net/tipc/udp_media.c24
26 files changed, 1702 insertions, 287 deletions
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 57e460be4692..31b9f9c52974 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -6,7 +6,7 @@ obj-$(CONFIG_TIPC) := tipc.o
tipc-y += addr.o bcast.o bearer.o \
core.o link.o discover.o msg.o \
- name_distr.o subscr.o name_table.o net.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 \
server.o socket.o
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 93f7c983be33..bebb347803ce 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -43,9 +43,6 @@
#include <net/netns/generic.h>
#include "core.h"
-#define TIPC_ZONE_MASK 0xff000000u
-#define TIPC_CLUSTER_MASK 0xfffff000u
-
static inline u32 tipc_own_addr(struct net *net)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
@@ -60,7 +57,7 @@ static inline u32 tipc_zone_mask(u32 addr)
static inline u32 tipc_cluster_mask(u32 addr)
{
- return addr & TIPC_CLUSTER_MASK;
+ return addr & TIPC_ZONE_CLUSTER_MASK;
}
u32 tipc_own_addr(struct net *net);
@@ -73,4 +70,5 @@ int tipc_addr_node_valid(u32 addr);
int tipc_in_scope(u32 domain, u32 addr);
int tipc_addr_scope(u32 domain);
char *tipc_addr_string_fill(char *string, u32 addr);
+
#endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 27a5406213c6..65b1bbf133bd 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1,7 +1,7 @@
/*
* net/tipc/bearer.c: TIPC bearer code
*
- * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
* Copyright (c) 2004-2006, 2010-2013, Wind River Systems
* All rights reserved.
*
@@ -39,6 +39,7 @@
#include "bearer.h"
#include "link.h"
#include "discover.h"
+#include "monitor.h"
#include "bcast.h"
#include "netlink.h"
@@ -170,6 +171,27 @@ struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
return NULL;
}
+/* tipc_bearer_get_name - get the bearer name from its id.
+ * @net: network namespace
+ * @name: a pointer to the buffer where the name will be stored.
+ * @bearer_id: the id to get the name from.
+ */
+int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id)
+{
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_bearer *b;
+
+ if (bearer_id >= MAX_BEARERS)
+ return -EINVAL;
+
+ b = rtnl_dereference(tn->bearer_list[bearer_id]);
+ if (!b)
+ return -EINVAL;
+
+ strcpy(name, b->name);
+ return 0;
+}
+
void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
@@ -205,6 +227,7 @@ static int tipc_enable_bearer(struct net *net, const char *name,
struct tipc_bearer *b;
struct tipc_media *m;
struct tipc_bearer_names b_names;
+ struct sk_buff *skb;
char addr_string[16];
u32 bearer_id;
u32 with_this_prio;
@@ -223,7 +246,7 @@ static int tipc_enable_bearer(struct net *net, const char *name,
if (tipc_addr_domain_valid(disc_domain) &&
(disc_domain != tn->own_addr)) {
if (tipc_in_scope(disc_domain, tn->own_addr)) {
- disc_domain = tn->own_addr & TIPC_CLUSTER_MASK;
+ disc_domain = tn->own_addr & TIPC_ZONE_CLUSTER_MASK;
res = 0; /* accept any node in own cluster */
} else if (in_own_cluster_exact(net, disc_domain))
res = 0; /* accept specified node in own cluster */
@@ -301,7 +324,7 @@ restart:
b->net_plane = bearer_id + 'A';
b->priority = priority;
- res = tipc_disc_create(net, b, &b->bcast_addr);
+ res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
if (res) {
bearer_disable(net, b);
pr_warn("Bearer <%s> rejected, discovery object creation failed\n",
@@ -310,6 +333,11 @@ restart:
}
rcu_assign_pointer(tn->bearer_list[bearer_id], b);
+ if (skb)
+ tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
+
+ if (tipc_mon_create(net, bearer_id))
+ return -ENOMEM;
pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
name,
@@ -328,6 +356,21 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b)
return 0;
}
+/* tipc_bearer_reset_all - reset all links on all bearers
+ */
+void tipc_bearer_reset_all(struct net *net)
+{
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_bearer *b;
+ int i;
+
+ for (i = 0; i < MAX_BEARERS; i++) {
+ b = rcu_dereference_rtnl(tn->bearer_list[i]);
+ if (b)
+ tipc_reset_bearer(net, b);
+ }
+}
+
/**
* bearer_disable
*
@@ -335,24 +378,18 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b)
*/
static void bearer_disable(struct net *net, struct tipc_bearer *b)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- u32 i;
+ struct tipc_net *tn = tipc_net(net);
+ int bearer_id = b->identity;
pr_info("Disabling bearer <%s>\n", b->name);
b->media->disable_media(b);
-
- tipc_node_delete_links(net, b->identity);
+ tipc_node_delete_links(net, bearer_id);
RCU_INIT_POINTER(b->media_ptr, NULL);
if (b->link_req)
tipc_disc_delete(b->link_req);
-
- for (i = 0; i < MAX_BEARERS; i++) {
- if (b == rtnl_dereference(tn->bearer_list[i])) {
- RCU_INIT_POINTER(tn->bearer_list[i], NULL);
- break;
- }
- }
+ RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL);
kfree_rcu(b, rcu);
+ tipc_mon_delete(net, bearer_id);
}
int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
@@ -394,7 +431,7 @@ void tipc_disable_l2_media(struct tipc_bearer *b)
/**
* tipc_l2_send_msg - send a TIPC packet out over an L2 interface
- * @buf: the packet to be sent
+ * @skb: the packet to be sent
* @b: the bearer through which the packet is to be sent
* @dest: peer destination address
*/
@@ -403,17 +440,21 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb,
{
struct net_device *dev;
int delta;
+ void *tipc_ptr;
dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr);
if (!dev)
return 0;
+ /* Send RESET message even if bearer is detached from device */
+ tipc_ptr = rcu_dereference_rtnl(dev->tipc_ptr);
+ if (unlikely(!tipc_ptr && !msg_is_reset(buf_msg(skb))))
+ goto drop;
+
delta = dev->hard_header_len - skb_headroom(skb);
if ((delta > 0) &&
- pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
- kfree_skb(skb);
- return 0;
- }
+ pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC))
+ goto drop;
skb_reset_network_header(skb);
skb->dev = dev;
@@ -422,6 +463,9 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb,
dev->dev_addr, skb->len);
dev_queue_xmit(skb);
return 0;
+drop:
+ kfree_skb(skb);
+ return 0;
}
int tipc_bearer_mtu(struct net *net, u32 bearer_id)
@@ -450,6 +494,8 @@ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id,
b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
if (likely(b))
b->media->send_msg(net, skb, b, dest);
+ else
+ kfree_skb(skb);
rcu_read_unlock();
}
@@ -468,11 +514,11 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id,
rcu_read_lock();
b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
- if (likely(b)) {
- skb_queue_walk_safe(xmitq, skb, tmp) {
- __skb_dequeue(xmitq);
- b->media->send_msg(net, skb, b, dst);
- }
+ if (unlikely(!b))
+ __skb_queue_purge(xmitq);
+ skb_queue_walk_safe(xmitq, skb, tmp) {
+ __skb_dequeue(xmitq);
+ b->media->send_msg(net, skb, b, dst);
}
rcu_read_unlock();
}
@@ -490,14 +536,14 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
rcu_read_lock();
b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
- if (likely(b)) {
- skb_queue_walk_safe(xmitq, skb, tmp) {
- hdr = buf_msg(skb);
- msg_set_non_seq(hdr, 1);
- msg_set_mc_netid(hdr, net_id);
- __skb_dequeue(xmitq);
- b->media->send_msg(net, skb, b, &b->bcast_addr);
- }
+ if (unlikely(!b))
+ __skb_queue_purge(xmitq);
+ skb_queue_walk_safe(xmitq, skb, tmp) {
+ hdr = buf_msg(skb);
+ msg_set_non_seq(hdr, 1);
+ msg_set_mc_netid(hdr, net_id);
+ __skb_dequeue(xmitq);
+ b->media->send_msg(net, skb, b, &b->bcast_addr);
}
rcu_read_unlock();
}
@@ -513,24 +559,21 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
* ignores packets sent using interface multicast, and traffic sent to other
* nodes (which can happen if interface is running in promiscuous mode).
*/
-static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev,
+static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct tipc_bearer *b;
rcu_read_lock();
b = rcu_dereference_rtnl(dev->tipc_ptr);
- if (likely(b)) {
- if (likely(buf->pkt_type <= PACKET_BROADCAST)) {
- buf->next = NULL;
- tipc_rcv(dev_net(dev), buf, b);
- rcu_read_unlock();
- return NET_RX_SUCCESS;
- }
+ if (likely(b && (skb->pkt_type <= PACKET_BROADCAST))) {
+ skb->next = NULL;
+ tipc_rcv(dev_net(dev), skb, b);
+ rcu_read_unlock();
+ return NET_RX_SUCCESS;
}
rcu_read_unlock();
-
- kfree_skb(buf);
+ kfree_skb(skb);
return NET_RX_DROP;
}
@@ -548,9 +591,18 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
+ struct tipc_net *tn = tipc_net(net);
struct tipc_bearer *b;
+ int i;
b = rtnl_dereference(dev->tipc_ptr);
+ if (!b) {
+ for (i = 0; i < MAX_BEARERS; b = NULL, i++) {
+ b = rtnl_dereference(tn->bearer_list[i]);
+ if (b && (b->media_ptr == dev))
+ break;
+ }
+ }
if (!b)
return NOTIFY_DONE;
@@ -560,13 +612,20 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
case NETDEV_CHANGE:
if (netif_carrier_ok(dev))
break;
+ case NETDEV_UP:
+ rcu_assign_pointer(dev->tipc_ptr, b);
+ break;
case NETDEV_GOING_DOWN:
+ RCU_INIT_POINTER(dev->tipc_ptr, NULL);
+ synchronize_net();
+ tipc_reset_bearer(net, b);
+ break;
case NETDEV_CHANGEMTU:
tipc_reset_bearer(net, b);
break;
case NETDEV_CHANGEADDR:
b->media->raw2addr(b, &b->addr,
- (char *)dev->dev_addr);
+ (char *)dev->dev_addr);
tipc_reset_bearer(net, b);
break;
case NETDEV_UNREGISTER:
@@ -794,7 +853,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
u32 prio;
prio = TIPC_MEDIA_LINK_PRI;
- domain = tn->own_addr & TIPC_CLUSTER_MASK;
+ domain = tn->own_addr & TIPC_ZONE_CLUSTER_MASK;
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index e31820516774..43757f1f9cb3 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -1,7 +1,7 @@
/*
* net/tipc/bearer.h: Include file for TIPC bearer code
*
- * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
* Copyright (c) 2005, 2010-2011, Wind River Systems
* All rights reserved.
*
@@ -42,8 +42,6 @@
#include <net/genetlink.h>
#define MAX_MEDIA 3
-#define MAX_NODES 4096
-#define WSIZE 32
/* Identifiers associated with TIPC message header media address info
* - address info field is 32 bytes long
@@ -62,16 +60,6 @@
#define TIPC_MEDIA_TYPE_UDP 3
/**
- * struct tipc_node_map - set of node identifiers
- * @count: # of nodes in set
- * @map: bitmap of node identifiers that are in the set
- */
-struct tipc_node_map {
- u32 count;
- u32 map[MAX_NODES / WSIZE];
-};
-
-/**
* struct tipc_media_addr - destination address used by TIPC bearers
* @value: address info (format defined by media)
* @media_id: TIPC media type identifier
@@ -142,7 +130,6 @@ struct tipc_media {
* @identity: array index of this bearer within TIPC bearer array
* @link_req: ptr to (optional) structure making periodic link setup requests
* @net_plane: network plane ('A' through 'H') currently associated with bearer
- * @nodes: indicates which nodes in cluster can be reached through bearer
*
* Note: media-specific code is responsible for initialization of the fields
* indicated below when a bearer is enabled; TIPC's generic bearer code takes
@@ -163,8 +150,6 @@ struct tipc_bearer {
u32 identity;
struct tipc_link_req *link_req;
char net_plane;
- int node_cnt;
- struct tipc_node_map nodes;
};
struct tipc_bearer_names {
@@ -212,7 +197,9 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *buf,
void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest);
void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest);
struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name);
+int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id);
struct tipc_media *tipc_media_find(const char *name);
+void tipc_bearer_reset_all(struct net *net);
int tipc_bearer_setup(void);
void tipc_bearer_cleanup(void);
void tipc_bearer_stop(struct net *net);
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 03a842870c52..236b043a4156 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -57,6 +57,7 @@ static int __net_init tipc_init_net(struct net *net)
tn->net_id = 4711;
tn->own_addr = 0;
+ tn->mon_threshold = TIPC_DEF_MON_THRESHOLD;
get_random_bytes(&tn->random, sizeof(int));
INIT_LIST_HEAD(&tn->node_list);
spin_lock_init(&tn->node_list_lock);
@@ -69,6 +70,7 @@ static int __net_init tipc_init_net(struct net *net)
if (err)
goto out_nametbl;
+ INIT_LIST_HEAD(&tn->dist_queue);
err = tipc_topsrv_start(net);
if (err)
goto out_subscr;
@@ -111,11 +113,9 @@ static int __init tipc_init(void)
pr_info("Activated (version " TIPC_MOD_VER ")\n");
- sysctl_tipc_rmem[0] = TIPC_CONN_OVERLOAD_LIMIT >> 4 <<
- TIPC_LOW_IMPORTANCE;
- sysctl_tipc_rmem[1] = TIPC_CONN_OVERLOAD_LIMIT >> 4 <<
- TIPC_CRITICAL_IMPORTANCE;
- sysctl_tipc_rmem[2] = TIPC_CONN_OVERLOAD_LIMIT;
+ sysctl_tipc_rmem[0] = RCVBUF_MIN;
+ sysctl_tipc_rmem[1] = RCVBUF_DEF;
+ sysctl_tipc_rmem[2] = RCVBUF_MAX;
err = tipc_netlink_start();
if (err)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 5504d63503df..a1845fb27d80 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -66,11 +66,13 @@ struct tipc_bc_base;
struct tipc_link;
struct tipc_name_table;
struct tipc_server;
+struct tipc_monitor;
#define TIPC_MOD_VER "2.0.0"
-#define NODE_HTABLE_SIZE 512
-#define MAX_BEARERS 3
+#define NODE_HTABLE_SIZE 512
+#define MAX_BEARERS 3
+#define TIPC_DEF_MON_THRESHOLD 32
extern int tipc_net_id __read_mostly;
extern int sysctl_tipc_rmem[3] __read_mostly;
@@ -88,6 +90,10 @@ struct tipc_net {
u32 num_nodes;
u32 num_links;
+ /* Neighbor monitoring list */
+ struct tipc_monitor *monitors[MAX_BEARERS];
+ int mon_threshold;
+
/* Bearer list */
struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
@@ -103,6 +109,9 @@ struct tipc_net {
spinlock_t nametbl_lock;
struct name_table *nametbl;
+ /* Name dist queue */
+ struct list_head dist_queue;
+
/* Topology subscription server */
struct tipc_server *topsrv;
atomic_t subscription_count;
@@ -123,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net)
return &tipc_net(net)->node_list;
}
+static inline unsigned int tipc_hashfn(u32 addr)
+{
+ return addr & (NODE_HTABLE_SIZE - 1);
+}
+
static inline u16 mod(u16 x)
{
return x & 0xffffu;
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index f1e738e80535..6b109a808d4c 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -135,9 +135,12 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
u16 caps = msg_node_capabilities(hdr);
bool respond = false;
bool dupl_addr = false;
+ int err;
- bearer->media->msg2addr(bearer, &maddr, msg_media_addr(hdr));
+ err = bearer->media->msg2addr(bearer, &maddr, msg_media_addr(hdr));
kfree_skb(skb);
+ if (err)
+ return;
/* Ensure message from node is valid and communication is permitted */
if (net_id != tn->net_id)
@@ -268,10 +271,9 @@ exit:
* Returns 0 if successful, otherwise -errno.
*/
int tipc_disc_create(struct net *net, struct tipc_bearer *b,
- struct tipc_media_addr *dest)
+ struct tipc_media_addr *dest, struct sk_buff **skb)
{
struct tipc_link_req *req;
- struct sk_buff *skb;
req = kmalloc(sizeof(*req), GFP_ATOMIC);
if (!req)
@@ -293,9 +295,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,
setup_timer(&req->timer, disc_timeout, (unsigned long)req);
mod_timer(&req->timer, jiffies + req->timer_intv);
b->link_req = req;
- skb = skb_clone(req->buf, GFP_ATOMIC);
- if (skb)
- tipc_bearer_xmit_skb(net, req->bearer_id, skb, &req->dest);
+ *skb = skb_clone(req->buf, GFP_ATOMIC);
return 0;
}
diff --git a/net/tipc/discover.h b/net/tipc/discover.h
index c9b12770c5ed..b80a335389c0 100644
--- a/net/tipc/discover.h
+++ b/net/tipc/discover.h
@@ -40,7 +40,7 @@
struct tipc_link_req;
int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr,
- struct tipc_media_addr *dest);
+ struct tipc_media_addr *dest, struct sk_buff **skb);
void tipc_disc_delete(struct tipc_link_req *req);
void tipc_disc_reset(struct net *net, struct tipc_bearer *b_ptr);
void tipc_disc_add_dest(struct tipc_link_req *req);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 7d2bb3e70baa..877d94f34814 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -42,6 +42,7 @@
#include "name_distr.h"
#include "discover.h"
#include "netlink.h"
+#include "monitor.h"
#include <linux/pkt_sched.h>
@@ -87,7 +88,6 @@ struct tipc_stats {
* @peer_bearer_id: bearer id used by link's peer endpoint
* @bearer_id: local bearer id used by link
* @tolerance: minimum link continuity loss needed to reset link [in ms]
- * @keepalive_intv: link keepalive timer interval
* @abort_limit: # of unacknowledged continuity probes needed to reset link
* @state: current state of link FSM
* @peer_caps: bitmap describing capabilities of peer node
@@ -96,6 +96,7 @@ struct tipc_stats {
* @pmsg: convenience pointer to "proto_msg" field
* @priority: current link priority
* @net_plane: current link network plane ('A' through 'H')
+ * @mon_state: cookie with information needed by link monitor
* @backlog_limit: backlog queue congestion thresholds (indexed by importance)
* @exp_msg_count: # of tunnelled messages expected during link changeover
* @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset
@@ -131,7 +132,6 @@ struct tipc_link {
u32 peer_bearer_id;
u32 bearer_id;
u32 tolerance;
- unsigned long keepalive_intv;
u32 abort_limit;
u32 state;
u16 peer_caps;
@@ -140,6 +140,8 @@ struct tipc_link {
char if_name[TIPC_MAX_IF_NAME];
u32 priority;
char net_plane;
+ struct tipc_mon_state mon_state;
+ u16 rst_cnt;
/* Failover/synch */
u16 drop_point;
@@ -348,6 +350,8 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
u16 ack = snd_l->snd_nxt - 1;
snd_l->ackers--;
+ rcv_l->bc_peer_is_up = true;
+ rcv_l->state = LINK_ESTABLISHED;
tipc_link_bc_ack_rcv(rcv_l, ack, xmitq);
tipc_link_reset(rcv_l);
rcv_l->state = LINK_RESET;
@@ -701,40 +705,42 @@ static void link_profile_stats(struct tipc_link *l)
/* tipc_link_timeout - perform periodic task as instructed from node timeout
*/
-/* tipc_link_timeout - perform periodic task as instructed from node timeout
- */
int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
{
+ int mtyp = 0;
int rc = 0;
- int mtyp = STATE_MSG;
- bool xmit = false;
- bool prb = false;
+ bool state = false;
+ bool probe = false;
+ bool setup = false;
u16 bc_snt = l->bc_sndlink->snd_nxt - 1;
u16 bc_acked = l->bc_rcvlink->acked;
- bool bc_up = link_is_up(l->bc_rcvlink);
-
- link_profile_stats(l);
+ struct tipc_mon_state *mstate = &l->mon_state;
switch (l->state) {
case LINK_ESTABLISHED:
case LINK_SYNCHING:
- if (!l->silent_intv_cnt) {
- if (bc_up && (bc_acked != bc_snt))
- xmit = true;
- } else if (l->silent_intv_cnt <= l->abort_limit) {
- xmit = true;
- prb = true;
- } else {
- rc |= tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
- }
- l->silent_intv_cnt++;
+ mtyp = STATE_MSG;
+ link_profile_stats(l);
+ tipc_mon_get_state(l->net, l->addr, mstate, l->bearer_id);
+ if (mstate->reset || (l->silent_intv_cnt > l->abort_limit))
+ return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
+ state = bc_acked != bc_snt;
+ state |= l->bc_rcvlink->rcv_unacked;
+ state |= l->rcv_unacked;
+ state |= !skb_queue_empty(&l->transmq);
+ state |= !skb_queue_empty(&l->deferdq);
+ probe = mstate->probing;
+ probe |= l->silent_intv_cnt;
+ if (probe || mstate->monitoring)
+ l->silent_intv_cnt++;
break;
case LINK_RESET:
- xmit = true;
+ setup = l->rst_cnt++ <= 4;
+ setup |= !(l->rst_cnt % 16);
mtyp = RESET_MSG;
break;
case LINK_ESTABLISHING:
- xmit = true;
+ setup = true;
mtyp = ACTIVATE_MSG;
break;
case LINK_PEER_RESET:
@@ -745,8 +751,8 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
break;
}
- if (xmit)
- tipc_link_build_proto_msg(l, mtyp, prb, 0, 0, 0, xmitq);
+ if (state || probe || setup)
+ tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, xmitq);
return rc;
}
@@ -833,9 +839,11 @@ void tipc_link_reset(struct tipc_link *l)
l->rcv_nxt = 1;
l->acked = 0;
l->silent_intv_cnt = 0;
+ l->rst_cnt = 0;
l->stats.recv_info = 0;
l->stale_count = 0;
l->bc_peer_is_up = false;
+ memset(&l->mon_state, 0, sizeof(l->mon_state));
tipc_link_reset_stats(l);
}
@@ -1110,12 +1118,12 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
return released;
}
-/* tipc_link_build_ack_msg: prepare link acknowledge message for transmission
+/* tipc_link_build_state_msg: prepare link state message for transmission
*
* Note that sending of broadcast ack is coordinated among nodes, to reduce
* risk of ack storms towards the sender
*/
-int tipc_link_build_ack_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
+int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
{
if (!l)
return 0;
@@ -1140,11 +1148,17 @@ int tipc_link_build_ack_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
{
int mtyp = RESET_MSG;
+ struct sk_buff *skb;
if (l->state == LINK_ESTABLISHING)
mtyp = ACTIVATE_MSG;
tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, xmitq);
+
+ /* Inform peer that this endpoint is going down if applicable */
+ skb = skb_peek_tail(xmitq);
+ if (skb && (l->state == LINK_RESET))
+ msg_set_peer_stopping(buf_msg(skb), 1);
}
/* tipc_link_build_nack_msg: prepare link nack message for transmission
@@ -1219,7 +1233,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
if (!tipc_data_input(l, skb, l->inputq))
rc |= tipc_link_input(l, skb, l->inputq);
if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN))
- rc |= tipc_link_build_ack_msg(l, xmitq);
+ rc |= tipc_link_build_state_msg(l, xmitq);
if (unlikely(rc & ~TIPC_LINK_SND_BC_ACK))
break;
} while ((skb = __skb_dequeue(defq)));
@@ -1238,6 +1252,9 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
struct tipc_msg *hdr;
struct sk_buff_head *dfq = &l->deferdq;
bool node_up = link_is_up(l->bc_rcvlink);
+ struct tipc_mon_state *mstate = &l->mon_state;
+ int dlen = 0;
+ void *data;
/* Don't send protocol message during reset or link failover */
if (tipc_link_is_blocked(l))
@@ -1250,12 +1267,13 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
- TIPC_MAX_IF_NAME, l->addr,
+ tipc_max_domain_size, l->addr,
tipc_own_addr(l->net), 0, 0, 0);
if (!skb)
return;
hdr = buf_msg(skb);
+ data = msg_data(hdr);
msg_set_session(hdr, l->session);
msg_set_bearer_id(hdr, l->bearer_id);
msg_set_net_plane(hdr, l->net_plane);
@@ -1271,14 +1289,18 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
if (mtyp == STATE_MSG) {
msg_set_seq_gap(hdr, rcvgap);
- msg_set_size(hdr, INT_H_SIZE);
msg_set_probe(hdr, probe);
+ 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);
l->stats.sent_states++;
l->rcv_unacked = 0;
} else {
/* RESET_MSG or ACTIVATE_MSG */
msg_set_max_pkt(hdr, l->advertised_mtu);
- strcpy(msg_data(hdr), l->if_name);
+ strcpy(data, l->if_name);
+ msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
+ skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME);
}
if (probe)
l->stats.sent_probes++;
@@ -1371,7 +1393,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
u16 peers_tol = msg_link_tolerance(hdr);
u16 peers_prio = msg_linkprio(hdr);
u16 rcv_nxt = l->rcv_nxt;
+ u16 dlen = msg_data_sz(hdr);
int mtyp = msg_type(hdr);
+ void *data;
char *if_name;
int rc = 0;
@@ -1381,6 +1405,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
if (tipc_own_addr(l->net) > msg_prevnode(hdr))
l->net_plane = msg_net_plane(hdr);
+ skb_linearize(skb);
+ hdr = buf_msg(skb);
+ data = msg_data(hdr);
+
switch (mtyp) {
case RESET_MSG:
@@ -1391,8 +1419,6 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
/* fall thru' */
case ACTIVATE_MSG:
- skb_linearize(skb);
- hdr = buf_msg(skb);
/* Complete own link name with peer's interface name */
if_name = strrchr(l->name, ':') + 1;
@@ -1400,7 +1426,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
break;
if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME)
break;
- strncpy(if_name, msg_data(hdr), TIPC_MAX_IF_NAME);
+ strncpy(if_name, data, TIPC_MAX_IF_NAME);
/* Update own tolerance if peer indicates a non-zero value */
if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
@@ -1411,7 +1437,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
l->priority = peers_prio;
/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
- if ((mtyp == RESET_MSG) || !link_is_up(l))
+ if (msg_peer_stopping(hdr))
+ rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
+ else if ((mtyp == RESET_MSG) || !link_is_up(l))
rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
/* ACTIVATE_MSG takes up link if it was already locally reset */
@@ -1446,6 +1474,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
rc = TIPC_LINK_UP_EVT;
break;
}
+ tipc_mon_rcv(l->net, data, dlen, l->addr,
+ &l->mon_state, l->bearer_id);
/* Send NACK if peer has sent pkts we haven't received yet */
if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))
@@ -1554,7 +1584,12 @@ void tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
if (!msg_peer_node_is_up(hdr))
return;
- l->bc_peer_is_up = true;
+ /* Open when peer ackowledges our bcast init msg (pkt #1) */
+ if (msg_ack(hdr))
+ l->bc_peer_is_up = true;
+
+ if (!l->bc_peer_is_up)
+ return;
/* Ignore if peers_snd_nxt goes beyond receive window */
if (more(peers_snd_nxt, l->rcv_nxt + l->window))
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 6a94175ee20a..d7e9d42fcb2d 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -123,7 +123,7 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq);
int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *xmitq);
-int tipc_link_build_ack_msg(struct tipc_link *l, struct sk_buff_head *xmitq);
+int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq);
void tipc_link_add_bc_peer(struct tipc_link *snd_l,
struct tipc_link *uc_l,
struct sk_buff_head *xmitq);
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
new file mode 100644
index 000000000000..b62caa1c770c
--- /dev/null
+++ b/net/tipc/monitor.c
@@ -0,0 +1,803 @@
+/*
+ * net/tipc/monitor.c
+ *
+ * Copyright (c) 2016, 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 "AS IS"
+ * 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.
+ */
+
+#include <net/genetlink.h>
+#include "core.h"
+#include "addr.h"
+#include "monitor.h"
+#include "bearer.h"
+
+#define MAX_MON_DOMAIN 64
+#define MON_TIMEOUT 120000
+#define MAX_PEER_DOWN_EVENTS 4
+
+/* struct tipc_mon_domain: domain record to be transferred between peers
+ * @len: actual size of domain record
+ * @gen: current generation of sender's domain
+ * @ack_gen: most recent generation of self's domain acked by peer
+ * @member_cnt: number of domain member nodes described in this record
+ * @up_map: bit map indicating which of the members the sender considers up
+ * @members: identity of the domain members
+ */
+struct tipc_mon_domain {
+ u16 len;
+ u16 gen;
+ u16 ack_gen;
+ u16 member_cnt;
+ u64 up_map;
+ u32 members[MAX_MON_DOMAIN];
+};
+
+/* struct tipc_peer: state of a peer node and its domain
+ * @addr: tipc node identity of peer
+ * @head_map: shows which other nodes currently consider peer 'up'
+ * @domain: most recent domain record from peer
+ * @hash: position in hashed lookup list
+ * @list: position in linked list, in circular ascending order by 'addr'
+ * @applied: number of reported domain members applied on this monitor list
+ * @is_up: peer is up as seen from this node
+ * @is_head: peer is assigned domain head as seen from this node
+ * @is_local: peer is in local domain and should be continuously monitored
+ * @down_cnt: - numbers of other peers which have reported this on lost
+ */
+struct tipc_peer {
+ u32 addr;
+ struct tipc_mon_domain *domain;
+ struct hlist_node hash;
+ struct list_head list;
+ u8 applied;
+ u8 down_cnt;
+ bool is_up;
+ bool is_head;
+ bool is_local;
+};
+
+struct tipc_monitor {
+ struct hlist_head peers[NODE_HTABLE_SIZE];
+ int peer_cnt;
+ struct tipc_peer *self;
+ rwlock_t lock;
+ struct tipc_mon_domain cache;
+ u16 list_gen;
+ u16 dom_gen;
+ struct net *net;
+ struct timer_list timer;
+ unsigned long timer_intv;
+};
+
+static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id)
+{
+ return tipc_net(net)->monitors[bearer_id];
+}
+
+const int tipc_max_domain_size = sizeof(struct tipc_mon_domain);
+
+/* dom_rec_len(): actual length of domain record for transport
+ */
+static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt)
+{
+ return ((void *)&dom->members - (void *)dom) + (mcnt * sizeof(u32));
+}
+
+/* dom_size() : calculate size of own domain based on number of peers
+ */
+static int dom_size(int peers)
+{
+ int i = 0;
+
+ while ((i * i) < peers)
+ i++;
+ return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN;
+}
+
+static void map_set(u64 *up_map, int i, unsigned int v)
+{
+ *up_map &= ~(1ULL << i);
+ *up_map |= ((u64)v << i);
+}
+
+static int map_get(u64 up_map, int i)
+{
+ return (up_map & (1 << i)) >> i;
+}
+
+static struct tipc_peer *peer_prev(struct tipc_peer *peer)
+{
+ return list_last_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_nxt(struct tipc_peer *peer)
+{
+ return list_first_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_head(struct tipc_peer *peer)
+{
+ while (!peer->is_head)
+ peer = peer_prev(peer);
+ return peer;
+}
+
+static struct tipc_peer *get_peer(struct tipc_monitor *mon, u32 addr)
+{
+ struct tipc_peer *peer;
+ unsigned int thash = tipc_hashfn(addr);
+
+ hlist_for_each_entry(peer, &mon->peers[thash], hash) {
+ if (peer->addr == addr)
+ return peer;
+ }
+ return NULL;
+}
+
+static struct tipc_peer *get_self(struct net *net, int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+
+ return mon->self;
+}
+
+static inline bool tipc_mon_is_active(struct net *net, struct tipc_monitor *mon)
+{
+ struct tipc_net *tn = tipc_net(net);
+
+ return mon->peer_cnt > tn->mon_threshold;
+}
+
+/* mon_identify_lost_members() : - identify amd mark potentially lost members
+ */
+static void mon_identify_lost_members(struct tipc_peer *peer,
+ struct tipc_mon_domain *dom_bef,
+ int applied_bef)
+{
+ struct tipc_peer *member = peer;
+ struct tipc_mon_domain *dom_aft = peer->domain;
+ int applied_aft = peer->applied;
+ int i;
+
+ for (i = 0; i < applied_bef; i++) {
+ member = peer_nxt(member);
+
+ /* Do nothing if self or peer already see member as down */
+ if (!member->is_up || !map_get(dom_bef->up_map, i))
+ continue;
+
+ /* Loss of local node must be detected by active probing */
+ if (member->is_local)
+ continue;
+
+ /* Start probing if member was removed from applied domain */
+ if (!applied_aft || (applied_aft < i)) {
+ member->down_cnt = 1;
+ continue;
+ }
+
+ /* Member loss is confirmed if it is still in applied domain */
+ if (!map_get(dom_aft->up_map, i))
+ member->down_cnt++;
+ }
+}
+
+/* mon_apply_domain() : match a peer's domain record against monitor list
+ */
+static void mon_apply_domain(struct tipc_monitor *mon,
+ struct tipc_peer *peer)
+{
+ struct tipc_mon_domain *dom = peer->domain;
+ struct tipc_peer *member;
+ u32 addr;
+ int i;
+
+ if (!dom || !peer->is_up)
+ return;
+
+ /* Scan across domain members and match against monitor list */
+ peer->applied = 0;
+ member = peer_nxt(peer);
+ for (i = 0; i < dom->member_cnt; i++) {
+ addr = dom->members[i];
+ if (addr != member->addr)
+ return;
+ peer->applied++;
+ member = peer_nxt(member);
+ }
+}
+
+/* mon_update_local_domain() : update after peer addition/removal/up/down
+ */
+static void mon_update_local_domain(struct tipc_monitor *mon)
+{
+ struct tipc_peer *self = mon->self;
+ struct tipc_mon_domain *cache = &mon->cache;
+ struct tipc_mon_domain *dom = self->domain;
+ struct tipc_peer *peer = self;
+ u64 prev_up_map = dom->up_map;
+ u16 member_cnt, i;
+ bool diff;
+
+ /* Update local domain size based on current size of cluster */
+ member_cnt = dom_size(mon->peer_cnt) - 1;
+ self->applied = member_cnt;
+
+ /* Update native and cached outgoing local domain records */
+ dom->len = dom_rec_len(dom, member_cnt);
+ diff = dom->member_cnt != member_cnt;
+ dom->member_cnt = member_cnt;
+ for (i = 0; i < member_cnt; i++) {
+ peer = peer_nxt(peer);
+ diff |= dom->members[i] != peer->addr;
+ dom->members[i] = peer->addr;
+ map_set(&dom->up_map, i, peer->is_up);
+ cache->members[i] = htonl(peer->addr);
+ }
+ diff |= dom->up_map != prev_up_map;
+ if (!diff)
+ return;
+ dom->gen = ++mon->dom_gen;
+ cache->len = htons(dom->len);
+ cache->gen = htons(dom->gen);
+ cache->member_cnt = htons(member_cnt);
+ cache->up_map = cpu_to_be64(dom->up_map);
+ mon_apply_domain(mon, self);
+}
+
+/* mon_update_neighbors() : update preceding neighbors of added/removed peer
+ */
+static void mon_update_neighbors(struct tipc_monitor *mon,
+ struct tipc_peer *peer)
+{
+ int dz, i;
+
+ dz = dom_size(mon->peer_cnt);
+ for (i = 0; i < dz; i++) {
+ mon_apply_domain(mon, peer);
+ peer = peer_prev(peer);
+ }
+}
+
+/* mon_assign_roles() : reassign peer roles after a network change
+ * The monitor list is consistent at this stage; i.e., each peer is monitoring
+ * a set of domain members as matched between domain record and the monitor list
+ */
+static void mon_assign_roles(struct tipc_monitor *mon, struct tipc_peer *head)
+{
+ struct tipc_peer *peer = peer_nxt(head);
+ struct tipc_peer *self = mon->self;
+ int i = 0;
+
+ for (; peer != self; peer = peer_nxt(peer)) {
+ peer->is_local = false;
+
+ /* Update domain member */
+ if (i++ < head->applied) {
+ peer->is_head = false;
+ if (head == self)
+ peer->is_local = true;
+ continue;
+ }
+ /* Assign next domain head */
+ if (!peer->is_up)
+ continue;
+ if (peer->is_head)
+ break;
+ head = peer;
+ head->is_head = true;
+ i = 0;
+ }
+ mon->list_gen++;
+}
+
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_peer *self = get_self(net, bearer_id);
+ struct tipc_peer *peer, *prev, *head;
+
+ write_lock_bh(&mon->lock);
+ peer = get_peer(mon, addr);
+ if (!peer)
+ goto exit;
+ prev = peer_prev(peer);
+ list_del(&peer->list);
+ hlist_del(&peer->hash);
+ kfree(peer->domain);
+ kfree(peer);
+ mon->peer_cnt--;
+ head = peer_head(prev);
+ if (head == self)
+ mon_update_local_domain(mon);
+ mon_update_neighbors(mon, prev);
+
+ /* Revert to full-mesh monitoring if we reach threshold */
+ if (!tipc_mon_is_active(net, mon)) {
+ list_for_each_entry(peer, &self->list, list) {
+ kfree(peer->domain);
+ peer->domain = NULL;
+ peer->applied = 0;
+ }
+ }
+ mon_assign_roles(mon, head);
+exit:
+ write_unlock_bh(&mon->lock);
+}
+
+static bool tipc_mon_add_peer(struct tipc_monitor *mon, u32 addr,
+ struct tipc_peer **peer)
+{
+ struct tipc_peer *self = mon->self;
+ struct tipc_peer *cur, *prev, *p;
+
+ p = kzalloc(sizeof(*p), GFP_ATOMIC);
+ *peer = p;
+ if (!p)
+ return false;
+ p->addr = addr;
+
+ /* Add new peer to lookup list */
+ INIT_LIST_HEAD(&p->list);
+ hlist_add_head(&p->hash, &mon->peers[tipc_hashfn(addr)]);
+
+ /* Sort new peer into iterator list, in ascending circular order */
+ prev = self;
+ list_for_each_entry(cur, &self->list, list) {
+ if ((addr > prev->addr) && (addr < cur->addr))
+ break;
+ if (((addr < cur->addr) || (addr > prev->addr)) &&
+ (prev->addr > cur->addr))
+ break;
+ prev = cur;
+ }
+ list_add_tail(&p->list, &cur->list);
+ mon->peer_cnt++;
+ mon_update_neighbors(mon, p);
+ return true;
+}
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_peer *self = get_self(net, bearer_id);
+ struct tipc_peer *peer, *head;
+
+ write_lock_bh(&mon->lock);
+ peer = get_peer(mon, addr);
+ if (!peer && !tipc_mon_add_peer(mon, addr, &peer))
+ goto exit;
+ peer->is_up = true;
+ head = peer_head(peer);
+ if (head == self)
+ mon_update_local_domain(mon);
+ mon_assign_roles(mon, head);
+exit:
+ write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_peer *self = get_self(net, bearer_id);
+ struct tipc_peer *peer, *head;
+ struct tipc_mon_domain *dom;
+ int applied;
+
+ write_lock_bh(&mon->lock);
+ peer = get_peer(mon, addr);
+ if (!peer) {
+ pr_warn("Mon: unknown link %x/%u DOWN\n", addr, bearer_id);
+ goto exit;
+ }
+ applied = peer->applied;
+ peer->applied = 0;
+ dom = peer->domain;
+ peer->domain = NULL;
+ if (peer->is_head)
+ mon_identify_lost_members(peer, dom, applied);
+ kfree(dom);
+ peer->is_up = false;
+ peer->is_head = false;
+ peer->is_local = false;
+ peer->down_cnt = 0;
+ head = peer_head(peer);
+ if (head == self)
+ mon_update_local_domain(mon);
+ mon_assign_roles(mon, head);
+exit:
+ write_unlock_bh(&mon->lock);
+}
+
+/* tipc_mon_rcv - process monitor domain event message
+ */
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+ struct tipc_mon_state *state, int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_mon_domain *arrv_dom = data;
+ struct tipc_mon_domain dom_bef;
+ struct tipc_mon_domain *dom;
+ struct tipc_peer *peer;
+ u16 new_member_cnt = ntohs(arrv_dom->member_cnt);
+ int new_dlen = dom_rec_len(arrv_dom, new_member_cnt);
+ u16 new_gen = ntohs(arrv_dom->gen);
+ u16 acked_gen = ntohs(arrv_dom->ack_gen);
+ bool probing = state->probing;
+ int i, applied_bef;
+
+ state->probing = false;
+ if (!dlen)
+ return;
+
+ /* Sanity check received domain record */
+ if ((dlen < new_dlen) || ntohs(arrv_dom->len) != new_dlen) {
+ pr_warn_ratelimited("Received illegal domain record\n");
+ return;
+ }
+
+ /* Synch generation numbers with peer if link just came up */
+ if (!state->synched) {
+ state->peer_gen = new_gen - 1;
+ state->acked_gen = acked_gen;
+ state->synched = true;
+ }
+
+ if (more(acked_gen, state->acked_gen))
+ state->acked_gen = acked_gen;
+
+ /* Drop duplicate unless we are waiting for a probe response */
+ if (!more(new_gen, state->peer_gen) && !probing)
+ return;
+
+ write_lock_bh(&mon->lock);
+ peer = get_peer(mon, addr);
+ if (!peer || !peer->is_up)
+ goto exit;
+
+ /* Peer is confirmed, stop any ongoing probing */
+ peer->down_cnt = 0;
+
+ /* Task is done for duplicate record */
+ if (!more(new_gen, state->peer_gen))
+ goto exit;
+
+ state->peer_gen = new_gen;
+
+ /* Cache current domain record for later use */
+ dom_bef.member_cnt = 0;
+ dom = peer->domain;
+ if (dom)
+ memcpy(&dom_bef, dom, dom->len);
+
+ /* Transform and store received domain record */
+ if (!dom || (dom->len < new_dlen)) {
+ kfree(dom);
+ dom = kmalloc(new_dlen, GFP_ATOMIC);
+ peer->domain = dom;
+ if (!dom)
+ goto exit;
+ }
+ dom->len = new_dlen;
+ dom->gen = new_gen;
+ dom->member_cnt = new_member_cnt;
+ dom->up_map = be64_to_cpu(arrv_dom->up_map);
+ for (i = 0; i < new_member_cnt; i++)
+ dom->members[i] = ntohl(arrv_dom->members[i]);
+
+ /* Update peers affected by this domain record */
+ applied_bef = peer->applied;
+ mon_apply_domain(mon, peer);
+ mon_identify_lost_members(peer, &dom_bef, applied_bef);
+ mon_assign_roles(mon, peer_head(peer));
+exit:
+ write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+ struct tipc_mon_state *state, int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_mon_domain *dom = data;
+ u16 gen = mon->dom_gen;
+ u16 len;
+
+ if (!tipc_mon_is_active(net, mon))
+ return;
+
+ /* Send only a dummy record with ack if peer has acked our last sent */
+ if (likely(state->acked_gen == gen)) {
+ len = dom_rec_len(dom, 0);
+ *dlen = len;
+ dom->len = htons(len);
+ dom->gen = htons(gen);
+ dom->ack_gen = htons(state->peer_gen);
+ dom->member_cnt = 0;
+ return;
+ }
+ /* Send the full record */
+ read_lock_bh(&mon->lock);
+ len = ntohs(mon->cache.len);
+ *dlen = len;
+ memcpy(data, &mon->cache, len);
+ read_unlock_bh(&mon->lock);
+ dom->ack_gen = htons(state->peer_gen);
+}
+
+void tipc_mon_get_state(struct net *net, u32 addr,
+ struct tipc_mon_state *state,
+ int bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_peer *peer;
+
+ /* Used cached state if table has not changed */
+ if (!state->probing &&
+ (state->list_gen == mon->list_gen) &&
+ (state->acked_gen == mon->dom_gen))
+ return;
+
+ read_lock_bh(&mon->lock);
+ peer = get_peer(mon, addr);
+ if (peer) {
+ state->probing = state->acked_gen != mon->dom_gen;
+ state->probing |= peer->down_cnt;
+ state->reset |= peer->down_cnt >= MAX_PEER_DOWN_EVENTS;
+ state->monitoring = peer->is_local;
+ state->monitoring |= peer->is_head;
+ state->list_gen = mon->list_gen;
+ }
+ read_unlock_bh(&mon->lock);
+}
+
+static void mon_timeout(unsigned long m)
+{
+ struct tipc_monitor *mon = (void *)m;
+ struct tipc_peer *self;
+ int best_member_cnt = dom_size(mon->peer_cnt) - 1;
+
+ write_lock_bh(&mon->lock);
+ self = mon->self;
+ if (self && (best_member_cnt != self->applied)) {
+ mon_update_local_domain(mon);
+ mon_assign_roles(mon, self);
+ }
+ write_unlock_bh(&mon->lock);
+ mod_timer(&mon->timer, jiffies + mon->timer_intv);
+}
+
+int tipc_mon_create(struct net *net, int bearer_id)
+{
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_monitor *mon;
+ struct tipc_peer *self;
+ struct tipc_mon_domain *dom;
+
+ if (tn->monitors[bearer_id])
+ return 0;
+
+ mon = kzalloc(sizeof(*mon), GFP_ATOMIC);
+ self = kzalloc(sizeof(*self), GFP_ATOMIC);
+ dom = kzalloc(sizeof(*dom), GFP_ATOMIC);
+ if (!mon || !self || !dom) {
+ kfree(mon);
+ kfree(self);
+ kfree(dom);
+ return -ENOMEM;
+ }
+ tn->monitors[bearer_id] = mon;
+ rwlock_init(&mon->lock);
+ mon->net = net;
+ mon->peer_cnt = 1;
+ mon->self = self;
+ self->domain = dom;
+ self->addr = tipc_own_addr(net);
+ self->is_up = true;
+ self->is_head = true;
+ INIT_LIST_HEAD(&self->list);
+ setup_timer(&mon->timer, mon_timeout, (unsigned long)mon);
+ mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff));
+ mod_timer(&mon->timer, jiffies + mon->timer_intv);
+ return 0;
+}
+
+void tipc_mon_delete(struct net *net, int bearer_id)
+{
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_peer *self = get_self(net, bearer_id);
+ struct tipc_peer *peer, *tmp;
+
+ write_lock_bh(&mon->lock);
+ tn->monitors[bearer_id] = NULL;
+ list_for_each_entry_safe(peer, tmp, &self->list, list) {
+ list_del(&peer->list);
+ hlist_del(&peer->hash);
+ kfree(peer->domain);
+ kfree(peer);
+ }
+ mon->self = NULL;
+ write_unlock_bh(&mon->lock);
+ del_timer_sync(&mon->timer);
+ kfree(self->domain);
+ kfree(self);
+ kfree(mon);
+}
+
+int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size)
+{
+ struct tipc_net *tn = tipc_net(net);
+
+ if (cluster_size > TIPC_CLUSTER_SIZE)
+ return -EINVAL;
+
+ tn->mon_threshold = cluster_size;
+
+ return 0;
+}
+
+int tipc_nl_monitor_get_threshold(struct net *net)
+{
+ struct tipc_net *tn = tipc_net(net);
+
+ return tn->mon_threshold;
+}
+
+int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, struct tipc_nl_msg *msg)
+{
+ struct tipc_mon_domain *dom = peer->domain;
+ struct nlattr *attrs;
+ void *hdr;
+
+ hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+ NLM_F_MULTI, TIPC_NL_MON_PEER_GET);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ attrs = nla_nest_start(msg->skb, TIPC_NLA_MON_PEER);
+ if (!attrs)
+ goto msg_full;
+
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_ADDR, peer->addr))
+ goto attr_msg_full;
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_APPLIED, peer->applied))
+ goto attr_msg_full;
+
+ if (peer->is_up)
+ if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_UP))
+ goto attr_msg_full;
+ if (peer->is_local)
+ if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_LOCAL))
+ goto attr_msg_full;
+ if (peer->is_head)
+ if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_HEAD))
+ goto attr_msg_full;
+
+ if (dom) {
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_DOMGEN, dom->gen))
+ goto attr_msg_full;
+ if (nla_put_u64_64bit(msg->skb, TIPC_NLA_MON_PEER_UPMAP,
+ dom->up_map, TIPC_NLA_MON_PEER_PAD))
+ goto attr_msg_full;
+ if (nla_put(msg->skb, TIPC_NLA_MON_PEER_MEMBERS,
+ dom->member_cnt * sizeof(u32), &dom->members))
+ goto attr_msg_full;
+ }
+
+ nla_nest_end(msg->skb, attrs);
+ genlmsg_end(msg->skb, hdr);
+ return 0;
+
+attr_msg_full:
+ nla_nest_cancel(msg->skb, attrs);
+msg_full:
+ genlmsg_cancel(msg->skb, hdr);
+
+ return -EMSGSIZE;
+}
+
+int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg,
+ u32 bearer_id, u32 *prev_node)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ struct tipc_peer *peer = mon->self;
+
+ if (!mon)
+ return -EINVAL;
+
+ read_lock_bh(&mon->lock);
+ do {
+ if (*prev_node) {
+ if (peer->addr == *prev_node)
+ *prev_node = 0;
+ else
+ continue;
+ }
+ if (__tipc_nl_add_monitor_peer(peer, msg)) {
+ *prev_node = peer->addr;
+ read_unlock_bh(&mon->lock);
+ return -EMSGSIZE;
+ }
+ } while ((peer = peer_nxt(peer)) != mon->self);
+ read_unlock_bh(&mon->lock);
+
+ return 0;
+}
+
+int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
+ u32 bearer_id)
+{
+ struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+ char bearer_name[TIPC_MAX_BEARER_NAME];
+ struct nlattr *attrs;
+ void *hdr;
+ int ret;
+
+ ret = tipc_bearer_get_name(net, bearer_name, bearer_id);
+ if (ret || !mon)
+ return -EINVAL;
+
+ hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+ NLM_F_MULTI, TIPC_NL_MON_GET);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ attrs = nla_nest_start(msg->skb, TIPC_NLA_MON);
+ if (!attrs)
+ goto msg_full;
+
+ read_lock_bh(&mon->lock);
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_REF, bearer_id))
+ goto attr_msg_full;
+ if (tipc_mon_is_active(net, mon))
+ if (nla_put_flag(msg->skb, TIPC_NLA_MON_ACTIVE))
+ goto attr_msg_full;
+ if (nla_put_string(msg->skb, TIPC_NLA_MON_BEARER_NAME, bearer_name))
+ goto attr_msg_full;
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEERCNT, mon->peer_cnt))
+ goto attr_msg_full;
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_LISTGEN, mon->list_gen))
+ goto attr_msg_full;
+
+ read_unlock_bh(&mon->lock);
+ nla_nest_end(msg->skb, attrs);
+ genlmsg_end(msg->skb, hdr);
+
+ return 0;
+
+attr_msg_full:
+ read_unlock_bh(&mon->lock);
+ nla_nest_cancel(msg->skb, attrs);
+msg_full:
+ genlmsg_cancel(msg->skb, hdr);
+
+ return -EMSGSIZE;
+}
diff --git a/net/tipc/monitor.h b/net/tipc/monitor.h
new file mode 100644
index 000000000000..2a21b93e0d04
--- /dev/null
+++ b/net/tipc/monitor.h
@@ -0,0 +1,82 @@
+/*
+ * net/tipc/monitor.h
+ *
+ * Copyright (c) 2015, 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 "AS IS"
+ * 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.
+ */
+
+#ifndef _TIPC_MONITOR_H
+#define _TIPC_MONITOR_H
+
+#include "netlink.h"
+
+/* struct tipc_mon_state: link instance's cache of monitor list and domain state
+ * @list_gen: current generation of this node's monitor list
+ * @gen: current generation of this node's local domain
+ * @peer_gen: most recent domain generation received from peer
+ * @acked_gen: most recent generation of self's domain acked by peer
+ * @monitoring: this peer endpoint should continuously monitored
+ * @probing: peer endpoint should be temporarily probed for potential loss
+ * @synched: domain record's generation has been synched with peer after reset
+ */
+struct tipc_mon_state {
+ u16 list_gen;
+ u16 peer_gen;
+ u16 acked_gen;
+ bool monitoring :1;
+ bool probing :1;
+ bool reset :1;
+ bool synched :1;
+};
+
+int tipc_mon_create(struct net *net, int bearer_id);
+void tipc_mon_delete(struct net *net, int bearer_id);
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+ struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+ struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_get_state(struct net *net, u32 addr,
+ struct tipc_mon_state *state,
+ int bearer_id);
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id);
+
+int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size);
+int tipc_nl_monitor_get_threshold(struct net *net);
+int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
+ u32 bearer_id);
+int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg,
+ u32 bearer_id, u32 *prev_node);
+
+extern const int tipc_max_domain_size;
+#endif
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 8740930f0787..17201aa8423d 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -41,6 +41,8 @@
#include "name_table.h"
#define MAX_FORWARD_SIZE 1024
+#define BUF_HEADROOM (LL_MAX_HEADER + 48)
+#define BUF_TAILROOM 16
static unsigned int align(unsigned int i)
{
@@ -505,6 +507,10 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err)
msg_set_hdr_sz(hdr, BASIC_H_SIZE);
}
+ if (skb_cloned(_skb) &&
+ pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL))
+ goto exit;
+
/* Now reverse the concerned fields */
msg_set_errcode(hdr, err);
msg_set_origport(hdr, msg_destport(&ohdr));
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 55778a0aebf3..7cf52fb39bee 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -94,17 +94,6 @@ struct plist;
#define TIPC_MEDIA_INFO_OFFSET 5
-/**
- * TIPC message buffer code
- *
- * TIPC message buffer headroom reserves space for the worst-case
- * link-level device header (in case the message is sent off-node).
- *
- * Note: Headroom should be a multiple of 4 to ensure the TIPC header fields
- * are word aligned for quicker access
- */
-#define BUF_HEADROOM (LL_MAX_HEADER + 48)
-
struct tipc_skb_cb {
void *handle;
struct sk_buff *tail;
@@ -715,6 +704,16 @@ static inline void msg_set_redundant_link(struct tipc_msg *m, u32 r)
msg_set_bits(m, 5, 12, 0x1, r);
}
+static inline u32 msg_peer_stopping(struct tipc_msg *m)
+{
+ return msg_bits(m, 5, 13, 0x1);
+}
+
+static inline void msg_set_peer_stopping(struct tipc_msg *m, u32 s)
+{
+ msg_set_bits(m, 5, 13, 0x1, s);
+}
+
static inline char *msg_media_addr(struct tipc_msg *m)
{
return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET];
@@ -733,16 +732,26 @@ static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n)
msg_set_bits(m, 9, 16, 0xffff, n);
}
-static inline u32 msg_bcast_tag(struct tipc_msg *m)
+static inline u32 msg_conn_ack(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff);
}
-static inline void msg_set_bcast_tag(struct tipc_msg *m, u32 n)
+static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 9, 16, 0xffff, n);
}
+static inline u32 msg_adv_win(struct tipc_msg *m)
+{
+ return msg_bits(m, 9, 0, 0xffff);
+}
+
+static inline void msg_set_adv_win(struct tipc_msg *m, u32 n)
+{
+ msg_set_bits(m, 9, 0, 0xffff, n);
+}
+
static inline u32 msg_max_pkt(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff) * 4;
@@ -779,6 +788,11 @@ static inline bool msg_peer_node_is_up(struct tipc_msg *m)
return msg_redundant_link(m);
}
+static inline bool msg_is_reset(struct tipc_msg *hdr)
+{
+ return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG);
+}
+
struct sk_buff *tipc_buf_acquire(u32 size);
bool tipc_msg_validate(struct sk_buff *skb);
bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err);
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index ebe9d0ff6e9e..6b626a64b517 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -40,11 +40,6 @@
int sysctl_tipc_named_timeout __read_mostly = 2000;
-/**
- * struct tipc_dist_queue - queue holding deferred name table updates
- */
-static struct list_head tipc_dist_queue = LIST_HEAD_INIT(tipc_dist_queue);
-
struct distr_queue_item {
struct distr_item i;
u32 dtype;
@@ -229,12 +224,31 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
kfree_rcu(p, rcu);
}
+/**
+ * tipc_dist_queue_purge - remove deferred updates from a node that went down
+ */
+static void tipc_dist_queue_purge(struct net *net, u32 addr)
+{
+ struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct distr_queue_item *e, *tmp;
+
+ spin_lock_bh(&tn->nametbl_lock);
+ list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
+ if (e->node != addr)
+ continue;
+ list_del(&e->next);
+ kfree(e);
+ }
+ spin_unlock_bh(&tn->nametbl_lock);
+}
+
void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr)
{
struct publication *publ, *tmp;
list_for_each_entry_safe(publ, tmp, nsub_list, nodesub_list)
tipc_publ_purge(net, publ, addr);
+ tipc_dist_queue_purge(net, addr);
}
/**
@@ -279,9 +293,11 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
* tipc_named_add_backlog - add a failed name table update to the backlog
*
*/
-static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
+static void tipc_named_add_backlog(struct net *net, struct distr_item *i,
+ u32 type, u32 node)
{
struct distr_queue_item *e;
+ struct tipc_net *tn = net_generic(net, tipc_net_id);
unsigned long now = get_jiffies_64();
e = kzalloc(sizeof(*e), GFP_ATOMIC);
@@ -291,7 +307,7 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
e->node = node;
e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout);
memcpy(e, i, sizeof(*i));
- list_add_tail(&e->next, &tipc_dist_queue);
+ list_add_tail(&e->next, &tn->dist_queue);
}
/**
@@ -301,10 +317,11 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
void tipc_named_process_backlog(struct net *net)
{
struct distr_queue_item *e, *tmp;
+ struct tipc_net *tn = net_generic(net, tipc_net_id);
char addr[16];
unsigned long now = get_jiffies_64();
- list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) {
+ list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
if (time_after(e->expires, now)) {
if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype))
continue;
@@ -344,7 +361,7 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq)
node = msg_orignode(msg);
while (count--) {
if (!tipc_update_nametbl(net, item, node, mtype))
- tipc_named_add_backlog(item, mtype, node);
+ tipc_named_add_backlog(net, item, mtype, node);
item++;
}
kfree_skb(skb);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 56935df2167a..a84daec0afe9 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -52,7 +52,8 @@ static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
[TIPC_NLA_MEDIA] = { .type = NLA_NESTED, },
[TIPC_NLA_NODE] = { .type = NLA_NESTED, },
[TIPC_NLA_NET] = { .type = NLA_NESTED, },
- [TIPC_NLA_NAME_TABLE] = { .type = NLA_NESTED, }
+ [TIPC_NLA_NAME_TABLE] = { .type = NLA_NESTED, },
+ [TIPC_NLA_MON] = { .type = NLA_NESTED, },
};
const struct nla_policy
@@ -61,6 +62,12 @@ tipc_nl_name_table_policy[TIPC_NLA_NAME_TABLE_MAX + 1] = {
[TIPC_NLA_NAME_TABLE_PUBL] = { .type = NLA_NESTED }
};
+const struct nla_policy tipc_nl_monitor_policy[TIPC_NLA_MON_MAX + 1] = {
+ [TIPC_NLA_MON_UNSPEC] = { .type = NLA_UNSPEC },
+ [TIPC_NLA_MON_REF] = { .type = NLA_U32 },
+ [TIPC_NLA_MON_ACTIVATION_THRESHOLD] = { .type = NLA_U32 },
+};
+
const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
[TIPC_NLA_SOCK_UNSPEC] = { .type = NLA_UNSPEC },
[TIPC_NLA_SOCK_ADDR] = { .type = NLA_U32 },
@@ -214,7 +221,23 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
.cmd = TIPC_NL_NAME_TABLE_GET,
.dumpit = tipc_nl_name_table_dump,
.policy = tipc_nl_policy,
- }
+ },
+ {
+ .cmd = TIPC_NL_MON_SET,
+ .doit = tipc_nl_node_set_monitor,
+ .policy = tipc_nl_policy,
+ },
+ {
+ .cmd = TIPC_NL_MON_GET,
+ .doit = tipc_nl_node_get_monitor,
+ .dumpit = tipc_nl_node_dump_monitor,
+ .policy = tipc_nl_policy,
+ },
+ {
+ .cmd = TIPC_NL_MON_PEER_GET,
+ .dumpit = tipc_nl_node_dump_monitor_peer,
+ .policy = tipc_nl_policy,
+ },
};
int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr)
diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h
index ed1dbcb4afbd..4ba0ad422110 100644
--- a/net/tipc/netlink.h
+++ b/net/tipc/netlink.h
@@ -55,6 +55,7 @@ extern const struct nla_policy tipc_nl_prop_policy[];
extern const struct nla_policy tipc_nl_bearer_policy[];
extern const struct nla_policy tipc_nl_media_policy[];
extern const struct nla_policy tipc_nl_udp_policy[];
+extern const struct nla_policy tipc_nl_monitor_policy[];
int tipc_netlink_start(void);
int tipc_netlink_compat_start(void);
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index d7d050f44fc1..1fd464764765 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -346,9 +346,15 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
struct nlattr **attrs)
{
struct nlattr *bearer[TIPC_NLA_BEARER_MAX + 1];
+ int err;
+
+ if (!attrs[TIPC_NLA_BEARER])
+ return -EINVAL;
- nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, attrs[TIPC_NLA_BEARER],
- NULL);
+ err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX,
+ attrs[TIPC_NLA_BEARER], NULL);
+ if (err)
+ return err;
return tipc_add_tlv(msg->rep, TIPC_TLV_BEARER_NAME,
nla_data(bearer[TIPC_NLA_BEARER_NAME]),
@@ -460,14 +466,31 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
+ int err;
- nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+ if (!attrs[TIPC_NLA_LINK])
+ return -EINVAL;
- nla_parse_nested(prop, TIPC_NLA_PROP_MAX, link[TIPC_NLA_LINK_PROP],
- NULL);
+ err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
+ NULL);
+ if (err)
+ return err;
+
+ if (!link[TIPC_NLA_LINK_PROP])
+ return -EINVAL;
- nla_parse_nested(stats, TIPC_NLA_STATS_MAX, link[TIPC_NLA_LINK_STATS],
- NULL);
+ err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX,
+ link[TIPC_NLA_LINK_PROP], 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);
+ if (err)
+ return err;
name = (char *)TLV_DATA(msg->req);
if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
@@ -569,12 +592,20 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
{
struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
struct tipc_link_info link_info;
+ int err;
- nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+ if (!attrs[TIPC_NLA_LINK])
+ return -EINVAL;
+
+ err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
+ NULL);
+ if (err)
+ return err;
link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
- strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+ nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+ TIPC_MAX_LINK_NAME);
return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
&link_info, sizeof(link_info));
@@ -758,12 +789,23 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
u32 node, depth, type, lowbound, upbound;
static const char * const scope_str[] = {"", " zone", " cluster",
" node"};
+ int err;
- nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
- attrs[TIPC_NLA_NAME_TABLE], NULL);
+ if (!attrs[TIPC_NLA_NAME_TABLE])
+ return -EINVAL;
- nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, nt[TIPC_NLA_NAME_TABLE_PUBL],
- NULL);
+ err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
+ attrs[TIPC_NLA_NAME_TABLE], 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);
+ if (err)
+ return err;
ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req);
@@ -802,7 +844,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
goto out;
tipc_tlv_sprintf(msg->rep, "%-10u %s",
- nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+ nla_get_u32(publ[TIPC_NLA_PUBL_KEY]),
scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
out:
tipc_tlv_sprintf(msg->rep, "\n");
@@ -815,8 +857,15 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg,
{
u32 type, lower, upper;
struct nlattr *publ[TIPC_NLA_PUBL_MAX + 1];
+ int err;
- nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL], NULL);
+ if (!attrs[TIPC_NLA_PUBL])
+ return -EINVAL;
+
+ err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL],
+ NULL);
+ if (err)
+ return err;
type = nla_get_u32(publ[TIPC_NLA_PUBL_TYPE]);
lower = nla_get_u32(publ[TIPC_NLA_PUBL_LOWER]);
@@ -876,7 +925,13 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
u32 sock_ref;
struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
- nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], NULL);
+ if (!attrs[TIPC_NLA_SOCK])
+ return -EINVAL;
+
+ err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK],
+ NULL);
+ if (err)
+ return err;
sock_ref = nla_get_u32(sock[TIPC_NLA_SOCK_REF]);
tipc_tlv_sprintf(msg->rep, "%u:", sock_ref);
@@ -917,9 +972,15 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg,
struct nlattr **attrs)
{
struct nlattr *media[TIPC_NLA_MEDIA_MAX + 1];
+ int err;
+
+ if (!attrs[TIPC_NLA_MEDIA])
+ return -EINVAL;
- nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA],
- NULL);
+ err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX, attrs[TIPC_NLA_MEDIA],
+ NULL);
+ if (err)
+ return err;
return tipc_add_tlv(msg->rep, TIPC_TLV_MEDIA_NAME,
nla_data(media[TIPC_NLA_MEDIA_NAME]),
@@ -931,8 +992,15 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg,
{
struct tipc_node_info node_info;
struct nlattr *node[TIPC_NLA_NODE_MAX + 1];
+ int err;
- nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE], NULL);
+ if (!attrs[TIPC_NLA_NODE])
+ return -EINVAL;
+
+ err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE],
+ NULL);
+ if (err)
+ return err;
node_info.addr = htonl(nla_get_u32(node[TIPC_NLA_NODE_ADDR]));
node_info.up = htonl(nla_get_flag(node[TIPC_NLA_NODE_UP]));
@@ -971,8 +1039,16 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg,
{
__be32 id;
struct nlattr *net[TIPC_NLA_NET_MAX + 1];
+ int err;
+
+ if (!attrs[TIPC_NLA_NET])
+ return -EINVAL;
+
+ err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET],
+ NULL);
+ if (err)
+ return err;
- nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET], NULL);
id = htonl(nla_get_u32(net[TIPC_NLA_NET_ID]));
return tipc_add_tlv(msg->rep, TIPC_TLV_UNSIGNED, &id, sizeof(id));
diff --git a/net/tipc/node.c b/net/tipc/node.c
index ace178fd3850..21974191e425 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1,7 +1,7 @@
/*
* net/tipc/node.c: TIPC node management routines
*
- * Copyright (c) 2000-2006, 2012-2015, Ericsson AB
+ * Copyright (c) 2000-2006, 2012-2016, Ericsson AB
* Copyright (c) 2005-2006, 2010-2014, Wind River Systems
* All rights reserved.
*
@@ -40,6 +40,7 @@
#include "name_distr.h"
#include "socket.h"
#include "bcast.h"
+#include "monitor.h"
#include "discover.h"
#include "netlink.h"
@@ -191,15 +192,18 @@ int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel)
tipc_node_put(n);
return mtu;
}
-/*
- * A trivial power-of-two bitmask technique is used for speed, since this
- * operation is done for every incoming TIPC packet. The number of hash table
- * entries has been chosen so that no hash chain exceeds 8 nodes and will
- * usually be much smaller (typically only a single node).
- */
-static unsigned int tipc_hashfn(u32 addr)
+
+u16 tipc_node_get_capabilities(struct net *net, u32 addr)
{
- return addr & (NODE_HTABLE_SIZE - 1);
+ struct tipc_node *n;
+ u16 caps;
+
+ n = tipc_node_find(net, addr);
+ if (unlikely(!n))
+ return TIPC_NODE_CAPABILITIES;
+ caps = n->capabilities;
+ tipc_node_put(n);
+ return caps;
}
static void tipc_node_kref_release(struct kref *kref)
@@ -265,6 +269,7 @@ static void tipc_node_write_unlock(struct tipc_node *n)
u32 addr = 0;
u32 flags = n->action_flags;
u32 link_id = 0;
+ u32 bearer_id;
struct list_head *publ_list;
if (likely(!flags)) {
@@ -274,6 +279,7 @@ static void tipc_node_write_unlock(struct tipc_node *n)
addr = n->addr;
link_id = n->link_id;
+ bearer_id = link_id & 0xffff;
publ_list = &n->publ_list;
n->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
@@ -287,13 +293,16 @@ static void tipc_node_write_unlock(struct tipc_node *n)
if (flags & TIPC_NOTIFY_NODE_UP)
tipc_named_node_up(net, addr);
- if (flags & TIPC_NOTIFY_LINK_UP)
+ if (flags & TIPC_NOTIFY_LINK_UP) {
+ tipc_mon_peer_up(net, addr, bearer_id);
tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
TIPC_NODE_SCOPE, link_id, addr);
-
- if (flags & TIPC_NOTIFY_LINK_DOWN)
+ }
+ if (flags & TIPC_NOTIFY_LINK_DOWN) {
+ tipc_mon_peer_down(net, addr, bearer_id);
tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
link_id, addr);
+ }
}
struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
@@ -304,8 +313,11 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
spin_lock_bh(&tn->node_list_lock);
n = tipc_node_find(net, addr);
- if (n)
+ if (n) {
+ /* Same node may come back with new capabilities */
+ n->capabilities = capabilities;
goto exit;
+ }
n = kzalloc(sizeof(*n), GFP_ATOMIC);
if (!n) {
pr_warn("Node creation failed, no memory\n");
@@ -361,14 +373,13 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l)
{
unsigned long tol = tipc_link_tolerance(l);
unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4;
- unsigned long keepalive_intv = msecs_to_jiffies(intv);
/* Link with lowest tolerance determines timer interval */
- if (keepalive_intv < n->keepalive_intv)
- n->keepalive_intv = keepalive_intv;
+ if (intv < n->keepalive_intv)
+ n->keepalive_intv = intv;
- /* Ensure link's abort limit corresponds to current interval */
- tipc_link_set_abort_limit(l, tol / jiffies_to_msecs(n->keepalive_intv));
+ /* Ensure link's abort limit corresponds to current tolerance */
+ tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
}
static void tipc_node_delete(struct tipc_node *node)
@@ -509,7 +520,7 @@ static void tipc_node_timeout(unsigned long data)
if (rc & TIPC_LINK_DOWN_EVT)
tipc_node_link_down(n, bearer_id, false);
}
- mod_timer(&n->timer, jiffies + n->keepalive_intv);
+ mod_timer(&n->timer, jiffies + msecs_to_jiffies(n->keepalive_intv));
}
/**
@@ -525,7 +536,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
struct tipc_link *ol = node_active_link(n, 0);
struct tipc_link *nl = n->links[bearer_id].link;
- if (!nl)
+ if (!nl || tipc_link_is_up(nl))
return;
tipc_link_fsm_evt(nl, LINK_ESTABLISH_EVT);
@@ -545,12 +556,16 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
pr_debug("Established link <%s> on network plane %c\n",
tipc_link_name(nl), tipc_link_plane(nl));
+ /* Ensure that a STATE message goes first */
+ tipc_link_build_state_msg(nl, xmitq);
+
/* First link? => give it both slots */
if (!ol) {
*slot0 = bearer_id;
*slot1 = bearer_id;
tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT);
n->action_flags |= TIPC_NOTIFY_NODE_UP;
+ tipc_link_set_active(nl, true);
tipc_bcast_add_peer(n->net, nl, xmitq);
return;
}
@@ -581,8 +596,12 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
static void tipc_node_link_up(struct tipc_node *n, int bearer_id,
struct sk_buff_head *xmitq)
{
+ struct tipc_media_addr *maddr;
+
tipc_node_write_lock(n);
__tipc_node_link_up(n, bearer_id, xmitq);
+ maddr = &n->links[bearer_id].maddr;
+ tipc_bearer_xmit(n->net, bearer_id, xmitq, maddr);
tipc_node_write_unlock(n);
}
@@ -667,6 +686,7 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
struct tipc_link *l = le->link;
struct tipc_media_addr *maddr;
struct sk_buff_head xmitq;
+ int old_bearer_id = bearer_id;
if (!l)
return;
@@ -686,6 +706,8 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
tipc_link_fsm_evt(l, LINK_RESET_EVT);
}
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);
tipc_sk_rcv(n->net, &le->inputq);
}
@@ -710,6 +732,7 @@ void tipc_node_check_dest(struct net *net, u32 onode,
bool accept_addr = false;
bool reset = true;
char *if_name;
+ unsigned long intv;
*dupl_addr = false;
*respond = false;
@@ -815,9 +838,11 @@ void tipc_node_check_dest(struct net *net, u32 onode,
le->link = l;
n->link_cnt++;
tipc_node_calculate_timer(n, l);
- if (n->link_cnt == 1)
- if (!mod_timer(&n->timer, jiffies + n->keepalive_intv))
+ if (n->link_cnt == 1) {
+ intv = jiffies + msecs_to_jiffies(n->keepalive_intv);
+ if (!mod_timer(&n->timer, intv))
tipc_node_get(n);
+ }
}
memcpy(&le->maddr, maddr, sizeof(*maddr));
exit:
@@ -925,7 +950,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
state = SELF_UP_PEER_UP;
break;
case SELF_LOST_CONTACT_EVT:
- state = SELF_DOWN_PEER_LEAVING;
+ state = SELF_DOWN_PEER_DOWN;
break;
case SELF_ESTABL_CONTACT_EVT:
case PEER_LOST_CONTACT_EVT:
@@ -944,7 +969,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
state = SELF_UP_PEER_UP;
break;
case PEER_LOST_CONTACT_EVT:
- state = SELF_LEAVING_PEER_DOWN;
+ state = SELF_DOWN_PEER_DOWN;
break;
case SELF_LOST_CONTACT_EVT:
case PEER_ESTABL_CONTACT_EVT:
@@ -1272,14 +1297,10 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
rc = tipc_bcast_rcv(net, be->link, skb);
- /* Broadcast link reset may happen at reassembly failure */
- if (rc & TIPC_LINK_DOWN_EVT)
- tipc_node_reset_links(n);
-
/* Broadcast ACKs are sent on a unicast link */
if (rc & TIPC_LINK_SND_BC_ACK) {
tipc_node_read_lock(n);
- tipc_link_build_ack_msg(le->link, &xmitq);
+ tipc_link_build_state_msg(le->link, &xmitq);
tipc_node_read_unlock(n);
}
@@ -1295,6 +1316,17 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
spin_unlock_bh(&be->inputq2.lock);
tipc_sk_mcast_rcv(net, &be->arrvq, &be->inputq2);
}
+
+ if (rc & TIPC_LINK_DOWN_EVT) {
+ /* Reception reassembly failure => reset all links to peer */
+ if (!tipc_link_is_up(be->link))
+ tipc_node_reset_links(n);
+
+ /* Retransmission failure => reset all links to all peers */
+ if (!tipc_link_is_up(tipc_bc_sndlink(net)))
+ tipc_bearer_reset_all(net);
+ }
+
tipc_node_put(n);
}
@@ -1444,6 +1476,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
int bearer_id = b->identity;
struct tipc_link_entry *le;
u16 bc_ack = msg_bcast_ack(hdr);
+ u32 self = tipc_own_addr(net);
int rc = 0;
__skb_queue_head_init(&xmitq);
@@ -1460,6 +1493,10 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
return tipc_node_bc_rcv(net, skb, bearer_id);
}
+ /* Discard unicast link messages destined for another node */
+ if (unlikely(!msg_short(hdr) && (msg_destnode(hdr) != self)))
+ goto discard;
+
/* Locate neighboring node that sent packet */
n = tipc_node_find(net, msg_prevnode(hdr));
if (unlikely(!n))
@@ -1891,3 +1928,168 @@ out:
return skb->len;
}
+
+int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr *attrs[TIPC_NLA_MON_MAX + 1];
+ struct net *net = sock_net(skb->sk);
+ int err;
+
+ 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);
+ if (err)
+ return err;
+
+ if (attrs[TIPC_NLA_MON_ACTIVATION_THRESHOLD]) {
+ u32 val;
+
+ val = nla_get_u32(attrs[TIPC_NLA_MON_ACTIVATION_THRESHOLD]);
+ err = tipc_nl_monitor_set_threshold(net, val);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int __tipc_nl_add_monitor_prop(struct net *net, struct tipc_nl_msg *msg)
+{
+ struct nlattr *attrs;
+ void *hdr;
+ u32 val;
+
+ hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+ 0, TIPC_NL_MON_GET);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ attrs = nla_nest_start(msg->skb, TIPC_NLA_MON);
+ if (!attrs)
+ goto msg_full;
+
+ val = tipc_nl_monitor_get_threshold(net);
+
+ if (nla_put_u32(msg->skb, TIPC_NLA_MON_ACTIVATION_THRESHOLD, val))
+ goto attr_msg_full;
+
+ nla_nest_end(msg->skb, attrs);
+ genlmsg_end(msg->skb, hdr);
+
+ return 0;
+
+attr_msg_full:
+ nla_nest_cancel(msg->skb, attrs);
+msg_full:
+ genlmsg_cancel(msg->skb, hdr);
+
+ return -EMSGSIZE;
+}
+
+int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = sock_net(skb->sk);
+ struct tipc_nl_msg msg;
+ int err;
+
+ msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ msg.portid = info->snd_portid;
+ msg.seq = info->snd_seq;
+
+ err = __tipc_nl_add_monitor_prop(net, &msg);
+ if (err) {
+ nlmsg_free(msg.skb);
+ return err;
+ }
+
+ return genlmsg_reply(msg.skb, info);
+}
+
+int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ u32 prev_bearer = cb->args[0];
+ struct tipc_nl_msg msg;
+ int err;
+ int i;
+
+ if (prev_bearer == MAX_BEARERS)
+ return 0;
+
+ msg.skb = skb;
+ msg.portid = NETLINK_CB(cb->skb).portid;
+ msg.seq = cb->nlh->nlmsg_seq;
+
+ rtnl_lock();
+ for (i = prev_bearer; i < MAX_BEARERS; i++) {
+ prev_bearer = i;
+ err = __tipc_nl_add_monitor(net, &msg, prev_bearer);
+ if (err)
+ goto out;
+ }
+
+out:
+ rtnl_unlock();
+ cb->args[0] = prev_bearer;
+
+ return skb->len;
+}
+
+int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ u32 prev_node = cb->args[1];
+ u32 bearer_id = cb->args[2];
+ int done = cb->args[0];
+ struct tipc_nl_msg msg;
+ int err;
+
+ if (!prev_node) {
+ struct nlattr **attrs;
+ struct nlattr *mon[TIPC_NLA_MON_MAX + 1];
+
+ err = tipc_nlmsg_parse(cb->nlh, &attrs);
+ if (err)
+ return err;
+
+ if (!attrs[TIPC_NLA_MON])
+ return -EINVAL;
+
+ err = nla_parse_nested(mon, TIPC_NLA_MON_MAX,
+ attrs[TIPC_NLA_MON],
+ tipc_nl_monitor_policy);
+ if (err)
+ return err;
+
+ if (!mon[TIPC_NLA_MON_REF])
+ return -EINVAL;
+
+ bearer_id = nla_get_u32(mon[TIPC_NLA_MON_REF]);
+
+ if (bearer_id >= MAX_BEARERS)
+ return -EINVAL;
+ }
+
+ if (done)
+ return 0;
+
+ msg.skb = skb;
+ msg.portid = NETLINK_CB(cb->skb).portid;
+ msg.seq = cb->nlh->nlmsg_seq;
+
+ rtnl_lock();
+ err = tipc_nl_add_monitor_peer(net, &msg, bearer_id, &prev_node);
+ if (!err)
+ done = 1;
+
+ rtnl_unlock();
+ cb->args[0] = done;
+ cb->args[1] = prev_node;
+ cb->args[2] = bearer_id;
+
+ return skb->len;
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index f39d9d06e8bb..d69fdfcc0ec9 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -45,10 +45,11 @@
/* Optional capabilities supported by this code version
*/
enum {
- TIPC_BCAST_SYNCH = (1 << 1)
+ TIPC_BCAST_SYNCH = (1 << 1),
+ TIPC_BLOCK_FLOWCTL = (2 << 1)
};
-#define TIPC_NODE_CAPABILITIES TIPC_BCAST_SYNCH
+#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | TIPC_BLOCK_FLOWCTL)
#define INVALID_BEARER_ID -1
void tipc_node_stop(struct net *net);
@@ -70,10 +71,16 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb);
int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port);
void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port);
int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel);
+u16 tipc_node_get_capabilities(struct net *net, u32 addr);
int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb);
int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info);
int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info);
int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
+ struct netlink_callback *cb);
#endif
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 2446bfbaa309..215849ce453d 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -86,6 +86,7 @@ struct outqueue_entry {
static void tipc_recv_work(struct work_struct *work);
static void tipc_send_work(struct work_struct *work);
static void tipc_clean_outqueues(struct tipc_conn *con);
+static void tipc_sock_release(struct tipc_conn *con);
static void tipc_conn_kref_release(struct kref *kref)
{
@@ -102,6 +103,7 @@ static void tipc_conn_kref_release(struct kref *kref)
}
saddr->scope = -TIPC_NODE_SCOPE;
kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
+ tipc_sock_release(con);
sock_release(sock);
con->sock = NULL;
}
@@ -136,28 +138,28 @@ static void sock_data_ready(struct sock *sk)
{
struct tipc_conn *con;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (con && test_bit(CF_CONNECTED, &con->flags)) {
conn_get(con);
if (!queue_work(con->server->rcv_wq, &con->rwork))
conn_put(con);
}
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void sock_write_space(struct sock *sk)
{
struct tipc_conn *con;
- read_lock(&sk->sk_callback_lock);
+ read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (con && test_bit(CF_CONNECTED, &con->flags)) {
conn_get(con);
if (!queue_work(con->server->send_wq, &con->swork))
conn_put(con);
}
- read_unlock(&sk->sk_callback_lock);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static void tipc_register_callbacks(struct socket *sock, struct tipc_conn *con)
@@ -184,26 +186,31 @@ static void tipc_unregister_callbacks(struct tipc_conn *con)
write_unlock_bh(&sk->sk_callback_lock);
}
+static void tipc_sock_release(struct tipc_conn *con)
+{
+ struct tipc_server *s = con->server;
+
+ if (con->conid)
+ s->tipc_conn_release(con->conid, con->usr_data);
+
+ tipc_unregister_callbacks(con);
+}
+
static void tipc_close_conn(struct tipc_conn *con)
{
struct tipc_server *s = con->server;
if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
- if (con->conid)
- s->tipc_conn_shutdown(con->conid, con->usr_data);
spin_lock_bh(&s->idr_lock);
idr_remove(&s->conn_idr, con->conid);
s->idr_in_use--;
spin_unlock_bh(&s->idr_lock);
- tipc_unregister_callbacks(con);
-
/* We shouldn't flush pending works as we may be in the
* thread. In fact the races with pending rx/tx work structs
* are harmless for us here as we have already deleted this
- * connection from server connection list and set
- * sk->sk_user_data to 0 before releasing connection object.
+ * connection from server connection list.
*/
kernel_sock_shutdown(con->sock, SHUT_RDWR);
@@ -411,13 +418,12 @@ static struct outqueue_entry *tipc_alloc_entry(void *data, int len)
if (!entry)
return NULL;
- buf = kmalloc(len, GFP_ATOMIC);
+ buf = kmemdup(data, len, GFP_ATOMIC);
if (!buf) {
kfree(entry);
return NULL;
}
- memcpy(buf, data, len);
entry->iov.iov_base = buf;
entry->iov.iov_len = len;
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 9015faedb1b0..34f8055afa3b 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -53,7 +53,7 @@
* @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_shutdown: callback will be called when connection is shut down
+ * @tipc_conn_release: callback will be called before releasing the connection
* @tipc_conn_recvmsg: callback will be called when message arrives
* @saddr: TIPC server address
* @name: server name
@@ -70,7 +70,7 @@ struct tipc_server {
struct workqueue_struct *send_wq;
int max_rcvbuf_size;
void *(*tipc_conn_new)(int conid);
- void (*tipc_conn_shutdown)(int conid, void *usr_data);
+ void (*tipc_conn_release)(int conid, void *usr_data);
void (*tipc_conn_recvmsg)(struct net *net, int conid,
struct sockaddr_tipc *addr, void *usr_data,
void *buf, size_t len);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3eeb50a27b89..c49b8df438cb 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -96,8 +96,11 @@ struct tipc_sock {
uint conn_timeout;
atomic_t dupl_rcvcnt;
bool link_cong;
- uint sent_unacked;
- uint rcv_unacked;
+ u16 snt_unacked;
+ u16 snd_win;
+ u16 peer_caps;
+ u16 rcv_unacked;
+ u16 rcv_win;
struct sockaddr_tipc remote;
struct rhash_head node;
struct rcu_head rcu;
@@ -227,9 +230,29 @@ static struct tipc_sock *tipc_sk(const struct sock *sk)
return container_of(sk, struct tipc_sock, sk);
}
-static int tsk_conn_cong(struct tipc_sock *tsk)
+static bool tsk_conn_cong(struct tipc_sock *tsk)
{
- return tsk->sent_unacked >= TIPC_FLOWCTRL_WIN;
+ return tsk->snt_unacked >= tsk->snd_win;
+}
+
+/* tsk_blocks(): translate a buffer size in bytes to number of
+ * advertisable blocks, taking into account the ratio truesize(len)/len
+ * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ
+ */
+static u16 tsk_adv_blocks(int len)
+{
+ return len / FLOWCTL_BLK_SZ / 4;
+}
+
+/* tsk_inc(): increment counter for sent or received data
+ * - If block based flow control is not supported by peer we
+ * fall back to message based ditto, incrementing the counter
+ */
+static u16 tsk_inc(struct tipc_sock *tsk, int msglen)
+{
+ if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
+ return ((msglen / FLOWCTL_BLK_SZ) + 1);
+ return 1;
}
/**
@@ -366,7 +389,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
sock->state = state;
sock_init_data(sock, sk);
if (tipc_sk_insert(tsk)) {
- pr_warn("Socket create failed; port numbrer exhausted\n");
+ pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
msg_set_origport(msg, tsk->portid);
@@ -377,9 +400,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
sk->sk_write_space = tipc_write_space;
sk->sk_destruct = tipc_sock_destruct;
tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
- tsk->sent_unacked = 0;
atomic_set(&tsk->dupl_rcvcnt, 0);
+ /* Start out with safe limits until we receive an advertised window */
+ tsk->snd_win = tsk_adv_blocks(RCVBUF_MIN);
+ tsk->rcv_win = tsk->snd_win;
+
if (sock->state == SS_READY) {
tsk_set_unreturnable(tsk, true);
if (sock->type == SOCK_DGRAM)
@@ -770,12 +796,14 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
* @tsk: receiving socket
* @skb: pointer to message buffer.
*/
-static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
+static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
struct sock *sk = &tsk->sk;
+ u32 onode = tsk_own_node(tsk);
struct tipc_msg *hdr = buf_msg(skb);
int mtyp = msg_type(hdr);
- int conn_cong;
+ bool conn_cong;
/* Ignore if connection cannot be validated: */
if (!tsk_peer_msg(tsk, hdr))
@@ -785,11 +813,14 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb)
if (mtyp == CONN_PROBE) {
msg_set_type(hdr, CONN_PROBE_REPLY);
- tipc_sk_respond(sk, skb, TIPC_OK);
+ if (tipc_msg_reverse(onode, &skb, TIPC_OK))
+ __skb_queue_tail(xmitq, skb);
return;
} else if (mtyp == CONN_ACK) {
conn_cong = tsk_conn_cong(tsk);
- tsk->sent_unacked -= msg_msgcnt(hdr);
+ tsk->snt_unacked -= msg_conn_ack(hdr);
+ if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
+ tsk->snd_win = msg_adv_win(hdr);
if (conn_cong)
sk->sk_write_space(sk);
} else if (mtyp != CONN_PROBE_REPLY) {
@@ -1020,12 +1051,14 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
u32 dnode;
uint mtu, send, sent = 0;
struct iov_iter save;
+ int hlen = MIN_H_SIZE;
/* Handle implied connection establishment */
if (unlikely(dest)) {
rc = __tipc_sendmsg(sock, m, dsz);
+ hlen = msg_hdr_sz(mhdr);
if (dsz && (dsz == rc))
- tsk->sent_unacked = 1;
+ tsk->snt_unacked = tsk_inc(tsk, dsz + hlen);
return rc;
}
if (dsz > (uint)INT_MAX)
@@ -1054,7 +1087,7 @@ next:
if (likely(!tsk_conn_cong(tsk))) {
rc = tipc_node_xmit(net, &pktchain, dnode, portid);
if (likely(!rc)) {
- tsk->sent_unacked++;
+ tsk->snt_unacked += tsk_inc(tsk, send + hlen);
sent += send;
if (sent == dsz)
return dsz;
@@ -1118,6 +1151,13 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
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);
+ if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
+ return;
+
+ /* Fall back to message based flow control */
+ tsk->rcv_win = FLOWCTL_MSG_WIN;
+ tsk->snd_win = FLOWCTL_MSG_WIN;
}
/**
@@ -1214,7 +1254,7 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
return 0;
}
-static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack)
+static void tipc_sk_send_ack(struct tipc_sock *tsk)
{
struct net *net = sock_net(&tsk->sk);
struct sk_buff *skb = NULL;
@@ -1230,7 +1270,14 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack)
if (!skb)
return;
msg = buf_msg(skb);
- msg_set_msgcnt(msg, ack);
+ msg_set_conn_ack(msg, tsk->rcv_unacked);
+ tsk->rcv_unacked = 0;
+
+ /* Adjust to and advertize the correct window limit */
+ if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL) {
+ tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf);
+ msg_set_adv_win(msg, tsk->rcv_win);
+ }
tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg));
}
@@ -1288,7 +1335,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
long timeo;
unsigned int sz;
u32 err;
- int res;
+ int res, hlen;
/* Catch invalid receive requests */
if (unlikely(!buf_len))
@@ -1313,6 +1360,7 @@ restart:
buf = skb_peek(&sk->sk_receive_queue);
msg = buf_msg(buf);
sz = msg_data_sz(msg);
+ hlen = msg_hdr_sz(msg);
err = msg_errcode(msg);
/* Discard an empty non-errored message & try again */
@@ -1335,7 +1383,7 @@ restart:
sz = buf_len;
m->msg_flags |= MSG_TRUNC;
}
- res = skb_copy_datagram_msg(buf, msg_hdr_sz(msg), m, sz);
+ res = skb_copy_datagram_msg(buf, hlen, m, sz);
if (res)
goto exit;
res = sz;
@@ -1347,15 +1395,15 @@ restart:
res = -ECONNRESET;
}
- /* Consume received message (optional) */
- if (likely(!(flags & MSG_PEEK))) {
- if ((sock->state != SS_READY) &&
- (++tsk->rcv_unacked >= TIPC_CONNACK_INTV)) {
- tipc_sk_send_ack(tsk, tsk->rcv_unacked);
- tsk->rcv_unacked = 0;
- }
- tsk_advance_rx_queue(sk);
+ if (unlikely(flags & MSG_PEEK))
+ goto exit;
+
+ if (likely(sock->state != SS_READY)) {
+ tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
+ if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
+ tipc_sk_send_ack(tsk);
}
+ tsk_advance_rx_queue(sk);
exit:
release_sock(sk);
return res;
@@ -1384,7 +1432,7 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
int sz_to_copy, target, needed;
int sz_copied = 0;
u32 err;
- int res = 0;
+ int res = 0, hlen;
/* Catch invalid receive attempts */
if (unlikely(!buf_len))
@@ -1410,6 +1458,7 @@ restart:
buf = skb_peek(&sk->sk_receive_queue);
msg = buf_msg(buf);
sz = msg_data_sz(msg);
+ hlen = msg_hdr_sz(msg);
err = msg_errcode(msg);
/* Discard an empty non-errored message & try again */
@@ -1434,8 +1483,7 @@ restart:
needed = (buf_len - sz_copied);
sz_to_copy = (sz <= needed) ? sz : needed;
- res = skb_copy_datagram_msg(buf, msg_hdr_sz(msg) + offset,
- m, sz_to_copy);
+ res = skb_copy_datagram_msg(buf, hlen + offset, m, sz_to_copy);
if (res)
goto exit;
@@ -1457,20 +1505,18 @@ restart:
res = -ECONNRESET;
}
- /* Consume received message (optional) */
- if (likely(!(flags & MSG_PEEK))) {
- if (unlikely(++tsk->rcv_unacked >= TIPC_CONNACK_INTV)) {
- tipc_sk_send_ack(tsk, tsk->rcv_unacked);
- tsk->rcv_unacked = 0;
- }
- tsk_advance_rx_queue(sk);
- }
+ if (unlikely(flags & MSG_PEEK))
+ goto exit;
+
+ tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
+ if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
+ tipc_sk_send_ack(tsk);
+ tsk_advance_rx_queue(sk);
/* Loop around if more data is required */
if ((sz_copied < buf_len) && /* didn't get all requested data */
(!skb_queue_empty(&sk->sk_receive_queue) ||
(sz_copied < target)) && /* and more is ready or required */
- (!(flags & MSG_PEEK)) && /* and aren't just peeking at data */
(!err)) /* and haven't reached a FIN */
goto restart;
@@ -1602,30 +1648,33 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
/**
* rcvbuf_limit - get proper overload limit of socket receive queue
* @sk: socket
- * @buf: message
+ * @skb: message
*
- * For all connection oriented messages, irrespective of importance,
- * the default overload value (i.e. 67MB) is set as limit.
+ * For connection oriented messages, irrespective of importance,
+ * default queue limit is 2 MB.
*
- * For all connectionless messages, by default new queue limits are
- * as belows:
+ * For connectionless messages, queue limits are based on message
+ * importance as follows:
*
- * TIPC_LOW_IMPORTANCE (4 MB)
- * TIPC_MEDIUM_IMPORTANCE (8 MB)
- * TIPC_HIGH_IMPORTANCE (16 MB)
- * TIPC_CRITICAL_IMPORTANCE (32 MB)
+ * TIPC_LOW_IMPORTANCE (2 MB)
+ * TIPC_MEDIUM_IMPORTANCE (4 MB)
+ * TIPC_HIGH_IMPORTANCE (8 MB)
+ * TIPC_CRITICAL_IMPORTANCE (16 MB)
*
* Returns overload limit according to corresponding message importance
*/
-static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
+static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
{
- struct tipc_msg *msg = buf_msg(buf);
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct tipc_msg *hdr = buf_msg(skb);
+
+ if (unlikely(!msg_connected(hdr)))
+ return sk->sk_rcvbuf << msg_importance(hdr);
- if (msg_connected(msg))
- return sysctl_tipc_rmem[2];
+ if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
+ return sk->sk_rcvbuf;
- return sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE <<
- msg_importance(msg);
+ return FLOWCTL_MSG_LIM;
}
/**
@@ -1640,7 +1689,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
*
* Returns true if message was added to socket receive queue, otherwise false
*/
-static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
+static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
+ struct sk_buff_head *xmitq)
{
struct socket *sock = sk->sk_socket;
struct tipc_sock *tsk = tipc_sk(sk);
@@ -1650,7 +1700,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
int usr = msg_user(hdr);
if (unlikely(msg_user(hdr) == CONN_MANAGER)) {
- tipc_sk_proto_rcv(tsk, skb);
+ tipc_sk_proto_rcv(tsk, skb, xmitq);
return false;
}
@@ -1693,7 +1743,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb)
return true;
reject:
- tipc_sk_respond(sk, skb, err);
+ if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err))
+ __skb_queue_tail(xmitq, skb);
return false;
}
@@ -1709,9 +1760,24 @@ reject:
static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
unsigned int truesize = skb->truesize;
+ struct sk_buff_head xmitq;
+ u32 dnode, selector;
- if (likely(filter_rcv(sk, skb)))
+ __skb_queue_head_init(&xmitq);
+
+ if (likely(filter_rcv(sk, skb, &xmitq))) {
atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt);
+ return 0;
+ }
+
+ if (skb_queue_empty(&xmitq))
+ return 0;
+
+ /* Send response/rejected message */
+ skb = __skb_dequeue(&xmitq);
+ dnode = msg_destnode(buf_msg(skb));
+ selector = msg_origport(buf_msg(skb));
+ tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
return 0;
}
@@ -1725,12 +1791,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb)
* Caller must hold socket lock
*/
static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
- u32 dport)
+ u32 dport, struct sk_buff_head *xmitq)
{
+ unsigned long time_limit = jiffies + 2;
+ struct sk_buff *skb;
unsigned int lim;
atomic_t *dcnt;
- struct sk_buff *skb;
- unsigned long time_limit = jiffies + 2;
+ u32 onode;
while (skb_queue_len(inputq)) {
if (unlikely(time_after_eq(jiffies, time_limit)))
@@ -1742,20 +1809,22 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
/* Add message directly to receive queue if possible */
if (!sock_owned_by_user(sk)) {
- filter_rcv(sk, skb);
+ filter_rcv(sk, skb, xmitq);
continue;
}
/* Try backlog, compensating for double-counted bytes */
dcnt = &tipc_sk(sk)->dupl_rcvcnt;
- if (sk->sk_backlog.len)
+ 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)))
continue;
/* Overload => reject message back to sender */
- tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD);
+ onode = tipc_own_addr(sock_net(sk));
+ if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD))
+ __skb_queue_tail(xmitq, skb);
break;
}
}
@@ -1768,12 +1837,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
*/
void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
{
+ struct sk_buff_head xmitq;
u32 dnode, dport = 0;
int err;
struct tipc_sock *tsk;
struct sock *sk;
struct sk_buff *skb;
+ __skb_queue_head_init(&xmitq);
while (skb_queue_len(inputq)) {
dport = tipc_skb_peek_port(inputq, dport);
tsk = tipc_sk_lookup(net, dport);
@@ -1781,9 +1852,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
if (likely(tsk)) {
sk = &tsk->sk;
if (likely(spin_trylock_bh(&sk->sk_lock.slock))) {
- tipc_sk_enqueue(inputq, sk, dport);
+ tipc_sk_enqueue(inputq, sk, dport, &xmitq);
spin_unlock_bh(&sk->sk_lock.slock);
}
+ /* Send pending response/rejected messages, if any */
+ while ((skb = __skb_dequeue(&xmitq))) {
+ dnode = msg_destnode(buf_msg(skb));
+ tipc_node_xmit_skb(net, skb, dnode, dport);
+ }
sock_put(sk);
continue;
}
@@ -2807,6 +2883,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (err)
return err;
+ if (!attrs[TIPC_NLA_SOCK])
+ return -EINVAL;
+
err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
attrs[TIPC_NLA_SOCK],
tipc_nl_sock_policy);
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 4241f22069dc..06fb5944cf76 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -1,6 +1,6 @@
/* net/tipc/socket.h: Include file for TIPC socket code
*
- * Copyright (c) 2014-2015, Ericsson AB
+ * Copyright (c) 2014-2016, Ericsson AB
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -38,10 +38,17 @@
#include <net/sock.h>
#include <net/genetlink.h>
-#define TIPC_CONNACK_INTV 256
-#define TIPC_FLOWCTRL_WIN (TIPC_CONNACK_INTV * 2)
-#define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \
- SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
+/* Compatibility values for deprecated message based flow control */
+#define FLOWCTL_MSG_WIN 512
+#define FLOWCTL_MSG_LIM ((FLOWCTL_MSG_WIN * 2 + 1) * SKB_TRUESIZE(MAX_MSG_SIZE))
+
+#define FLOWCTL_BLK_SZ 1024
+
+/* Socket receive buffer sizes */
+#define RCVBUF_MIN (FLOWCTL_BLK_SZ * 512)
+#define RCVBUF_DEF (FLOWCTL_BLK_SZ * 1024 * 2)
+#define RCVBUF_MAX (FLOWCTL_BLK_SZ * 1024 * 16)
+
int tipc_socket_init(void);
void tipc_socket_stop(void);
void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq);
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index e6cb386fbf34..0dd02244e21d 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -302,7 +302,7 @@ static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s,
}
/* Handle one termination request for the subscriber */
-static void tipc_subscrb_shutdown_cb(int conid, void *usr_data)
+static void tipc_subscrb_release_cb(int conid, void *usr_data)
{
tipc_subscrb_delete((struct tipc_subscriber *)usr_data);
}
@@ -326,8 +326,7 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid,
return tipc_subscrp_cancel(s, subscriber);
}
- if (s)
- tipc_subscrp_subscribe(net, s, subscriber, swap);
+ tipc_subscrp_subscribe(net, s, subscriber, swap);
}
/* Handle one request to establish a new subscriber */
@@ -365,7 +364,7 @@ int tipc_topsrv_start(struct net *net)
topsrv->max_rcvbuf_size = sizeof(struct tipc_subscr);
topsrv->tipc_conn_recvmsg = tipc_subscrb_rcv_cb;
topsrv->tipc_conn_new = tipc_subscrb_connect_cb;
- topsrv->tipc_conn_shutdown = tipc_subscrb_shutdown_cb;
+ topsrv->tipc_conn_release = tipc_subscrb_release_cb;
strncpy(topsrv->name, name, strlen(name) + 1);
tn->topsrv = topsrv;
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index c9cf2be3674a..b016c011970b 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -63,7 +63,7 @@
*/
struct udp_media_addr {
__be16 proto;
- __be16 udp_port;
+ __be16 port;
union {
struct in_addr ipv4;
struct in6_addr ipv6;
@@ -108,9 +108,9 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
struct udp_media_addr *ua = (struct udp_media_addr *)&a->value;
if (ntohs(ua->proto) == ETH_P_IP)
- snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->udp_port));
+ snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port));
else if (ntohs(ua->proto) == ETH_P_IPV6)
- snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->udp_port));
+ snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port));
else
pr_err("Invalid UDP media address\n");
return 0;
@@ -178,8 +178,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
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->udp_port,
- dst->udp_port, false, true);
+ dst->ipv4.s_addr, 0, ttl, 0, src->port,
+ dst->port, false, true);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct dst_entry *ndst;
@@ -196,8 +196,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
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->udp_port,
- dst->udp_port, false);
+ &dst->ipv6, 0, ttl, 0, src->port,
+ dst->port, false);
#endif
}
return err;
@@ -292,12 +292,12 @@ err:
ip4 = (struct sockaddr_in *)&sa_local;
local->proto = htons(ETH_P_IP);
- local->udp_port = ip4->sin_port;
+ local->port = ip4->sin_port;
local->ipv4.s_addr = ip4->sin_addr.s_addr;
ip4 = (struct sockaddr_in *)&sa_remote;
remote->proto = htons(ETH_P_IP);
- remote->udp_port = ip4->sin_port;
+ remote->port = ip4->sin_port;
remote->ipv4.s_addr = ip4->sin_addr.s_addr;
return 0;
@@ -312,13 +312,13 @@ err:
return -EINVAL;
local->proto = htons(ETH_P_IPV6);
- local->udp_port = ip6->sin6_port;
+ local->port = ip6->sin6_port;
memcpy(&local->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr));
ub->ifindex = ip6->sin6_scope_id;
ip6 = (struct sockaddr_in6 *)&sa_remote;
remote->proto = htons(ETH_P_IPV6);
- remote->udp_port = ip6->sin6_port;
+ remote->port = ip6->sin6_port;
memcpy(&remote->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr));
return 0;
#endif
@@ -386,7 +386,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
err = -EAFNOSUPPORT;
goto err;
}
- udp_conf.local_udp_port = local.udp_port;
+ udp_conf.local_udp_port = local.port;
err = udp_sock_create(net, &udp_conf, &ub->ubsock);
if (err)
goto err;
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-11 07:33:01 +0000