aboutsummaryrefslogtreecommitdiffstats
path: root/net/tipc
diff options
context:
space:
mode:
Diffstat (limited to 'net/tipc')
-rw-r--r--net/tipc/Makefile4
-rw-r--r--net/tipc/bcast.c35
-rw-r--r--net/tipc/bearer.c11
-rw-r--r--net/tipc/bearer.h6
-rw-r--r--net/tipc/crypto.c5
-rw-r--r--net/tipc/discover.c6
-rw-r--r--net/tipc/eth_media.c3
-rw-r--r--net/tipc/ib_media.c5
-rw-r--r--net/tipc/link.c199
-rw-r--r--net/tipc/link.h9
-rw-r--r--net/tipc/name_table.c279
-rw-r--r--net/tipc/net.c56
-rw-r--r--net/tipc/net.h1
-rw-r--r--net/tipc/netlink.c6
-rw-r--r--net/tipc/netlink_compat.c4
-rw-r--r--net/tipc/node.c16
-rw-r--r--net/tipc/socket.c89
-rw-r--r--net/tipc/udp_media.c3
18 files changed, 492 insertions, 245 deletions
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 11255e970dd4..ee49a9f1dd4f 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -9,7 +9,7 @@ tipc-y += addr.o bcast.o bearer.o \
core.o link.o discover.o msg.o \
name_distr.o subscr.o monitor.o name_table.o net.o \
netlink.o netlink_compat.o node.o socket.o eth_media.o \
- topsrv.o socket.o group.o trace.o
+ topsrv.o group.o trace.o
CFLAGS_trace.o += -I$(src)
@@ -20,5 +20,3 @@ tipc-$(CONFIG_TIPC_CRYPTO) += crypto.o
obj-$(CONFIG_TIPC_DIAG) += diag.o
-
-tipc_diag-y := diag.o
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 55aeba681cf4..4c20be08b9c4 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
* @skb: socket buffer to copy
* @method: send method to be used
* @dests: destination nodes for message.
- * @cong_link_cnt: returns number of encountered congested destination links
* Returns 0 if success, otherwise errno
*/
static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
struct tipc_mc_method *method,
- struct tipc_nlist *dests,
- u16 *cong_link_cnt)
+ struct tipc_nlist *dests)
{
struct tipc_msg *hdr, *_hdr;
struct sk_buff_head tmpq;
struct sk_buff *_skb;
+ u16 cong_link_cnt;
+ int rc = 0;
/* Is a cluster supporting with new capabilities ? */
if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL))
@@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
_hdr = buf_msg(_skb);
msg_set_size(_hdr, MCAST_H_SIZE);
msg_set_is_rcast(_hdr, !msg_is_rcast(hdr));
+ msg_set_errcode(_hdr, TIPC_ERR_NO_PORT);
__skb_queue_head_init(&tmpq);
__skb_queue_tail(&tmpq, _skb);
if (method->rcast)
- tipc_bcast_xmit(net, &tmpq, cong_link_cnt);
+ rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt);
else
- tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt);
+ rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt);
/* This queue should normally be empty by now */
__skb_queue_purge(&tmpq);
- return 0;
+ return rc;
}
/* tipc_mcast_xmit - deliver message to indicated destination nodes
@@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
msg_set_is_rcast(hdr, method->rcast);
/* Switch method ? */
- if (rcast != method->rcast)
- tipc_mcast_send_sync(net, skb, method,
- dests, cong_link_cnt);
+ if (rcast != method->rcast) {
+ rc = tipc_mcast_send_sync(net, skb, method, dests);
+ if (unlikely(rc)) {
+ pr_err("Unable to send SYN: method %d, rc %d\n",
+ rcast, rc);
+ goto exit;
+ }
+ }
if (method->rcast)
rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt);
@@ -562,18 +568,18 @@ int tipc_bclink_reset_stats(struct net *net)
return 0;
}
-static int tipc_bc_link_set_queue_limits(struct net *net, u32 limit)
+static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win)
{
struct tipc_link *l = tipc_bc_sndlink(net);
if (!l)
return -ENOPROTOOPT;
- if (limit < BCLINK_WIN_MIN)
- limit = BCLINK_WIN_MIN;
- if (limit > TIPC_MAX_LINK_WIN)
+ if (max_win < BCLINK_WIN_MIN)
+ max_win = BCLINK_WIN_MIN;
+ if (max_win > TIPC_MAX_LINK_WIN)
return -EINVAL;
tipc_bcast_lock(net);
- tipc_link_set_queue_limits(l, limit);
+ tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win);
tipc_bcast_unlock(net);
return 0;
}
@@ -683,6 +689,7 @@ int tipc_bcast_init(struct net *net)
if (!tipc_link_bc_create(net, 0, 0,
FB_MTU,
BCLINK_WIN_DEFAULT,
+ BCLINK_WIN_DEFAULT,
0,
&bb->inputq,
NULL,
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index d7ec26bd739d..34ca7b789eba 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -311,7 +311,8 @@ static int tipc_enable_bearer(struct net *net, const char *name,
b->identity = bearer_id;
b->tolerance = m->tolerance;
- b->window = m->window;
+ b->min_win = m->min_win;
+ b->max_win = m->max_win;
b->domain = disc_domain;
b->net_plane = bearer_id + 'A';
b->priority = prio;
@@ -796,7 +797,7 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance))
goto prop_msg_full;
- if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window))
+ if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->max_win))
goto prop_msg_full;
if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP)
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu))
@@ -1088,7 +1089,7 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
if (props[TIPC_NLA_PROP_PRIO])
b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
if (props[TIPC_NLA_PROP_WIN])
- b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ b->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
if (props[TIPC_NLA_PROP_MTU]) {
if (b->media->type_id != TIPC_MEDIA_TYPE_UDP)
return -EINVAL;
@@ -1142,7 +1143,7 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg,
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance))
goto prop_msg_full;
- if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window))
+ if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->max_win))
goto prop_msg_full;
if (media->type_id == TIPC_MEDIA_TYPE_UDP)
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu))
@@ -1275,7 +1276,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
if (props[TIPC_NLA_PROP_PRIO])
m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
if (props[TIPC_NLA_PROP_WIN])
- m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ m->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
if (props[TIPC_NLA_PROP_MTU]) {
if (m->type_id != TIPC_MEDIA_TYPE_UDP)
return -EINVAL;
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index d0c79cc6c0c2..bc0023119da2 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -119,7 +119,8 @@ struct tipc_media {
char *raw);
u32 priority;
u32 tolerance;
- u32 window;
+ u32 min_win;
+ u32 max_win;
u32 mtu;
u32 type_id;
u32 hwaddr_len;
@@ -158,7 +159,8 @@ struct tipc_bearer {
struct packet_type pt;
struct rcu_head rcu;
u32 priority;
- u32 window;
+ u32 min_win;
+ u32 max_win;
u32 tolerance;
u32 domain;
u32 identity;
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 990a872cec46..c8c47fc72653 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -257,9 +257,6 @@ static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
#define tipc_aead_rcu_ptr(rcu_ptr, lock) \
rcu_dereference_protected((rcu_ptr), lockdep_is_held(lock))
-#define tipc_aead_rcu_swap(rcu_ptr, ptr, lock) \
- rcu_swap_protected((rcu_ptr), (ptr), lockdep_is_held(lock))
-
#define tipc_aead_rcu_replace(rcu_ptr, ptr, lock) \
do { \
typeof(rcu_ptr) __tmp = rcu_dereference_protected((rcu_ptr), \
@@ -1189,7 +1186,7 @@ static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending)
/* Move passive key if any */
if (key.passive) {
- tipc_aead_rcu_swap(rx->aead[key.passive], tmp2, &rx->lock);
+ tmp2 = rcu_replace_pointer(rx->aead[key.passive], tmp2, lockdep_is_held(&rx->lock));
x = (key.passive - key.pending + new_pending) % KEY_MAX;
new_passive = (x <= 0) ? x + KEY_MAX : x;
}
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index b043e8c6397a..bfe43da127c0 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -194,6 +194,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
{
struct tipc_net *tn = tipc_net(net);
struct tipc_msg *hdr = buf_msg(skb);
+ u32 pnet_hash = msg_peer_net_hash(hdr);
u16 caps = msg_node_capabilities(hdr);
bool legacy = tn->legacy_addr_format;
u32 sugg = msg_sugg_node_addr(hdr);
@@ -242,9 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
return;
if (!tipc_in_scope(legacy, b->domain, src))
return;
- tipc_node_check_dest(net, src, peer_id, b, caps, signature,
- msg_peer_net_hash(hdr), &maddr, &respond,
- &dupl_addr);
+ tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash,
+ &maddr, &respond, &dupl_addr);
if (dupl_addr)
disc_dupl_alert(b, src, &maddr);
if (!respond)
diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c
index f69a2fde9f4a..8b0bb600602d 100644
--- a/net/tipc/eth_media.c
+++ b/net/tipc/eth_media.c
@@ -92,7 +92,8 @@ struct tipc_media eth_media_info = {
.raw2addr = tipc_eth_raw2addr,
.priority = TIPC_DEF_LINK_PRI,
.tolerance = TIPC_DEF_LINK_TOL,
- .window = TIPC_DEF_LINK_WIN,
+ .min_win = TIPC_DEF_LINK_WIN,
+ .max_win = TIPC_MAX_LINK_WIN,
.type_id = TIPC_MEDIA_TYPE_ETH,
.hwaddr_len = ETH_ALEN,
.name = "eth"
diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c
index e8c16718e3fa..7aa9ff88458d 100644
--- a/net/tipc/ib_media.c
+++ b/net/tipc/ib_media.c
@@ -42,6 +42,8 @@
#include "core.h"
#include "bearer.h"
+#define TIPC_MAX_IB_LINK_WIN 500
+
/* convert InfiniBand address (media address format) media address to string */
static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
int str_size)
@@ -94,7 +96,8 @@ struct tipc_media ib_media_info = {
.raw2addr = tipc_ib_raw2addr,
.priority = TIPC_DEF_LINK_PRI,
.tolerance = TIPC_DEF_LINK_TOL,
- .window = TIPC_DEF_LINK_WIN,
+ .min_win = TIPC_DEF_LINK_WIN,
+ .max_win = TIPC_MAX_IB_LINK_WIN,
.type_id = TIPC_MEDIA_TYPE_IB,
.hwaddr_len = INFINIBAND_ALEN,
.name = "ib"
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 24d4d10756d3..467c53a1fb5c 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -164,7 +164,6 @@ struct tipc_link {
struct sk_buff *target_bskb;
} backlog[5];
u16 snd_nxt;
- u16 window;
/* Reception */
u16 rcv_nxt;
@@ -175,6 +174,12 @@ struct tipc_link {
/* Congestion handling */
struct sk_buff_head wakeupq;
+ u16 window;
+ u16 min_win;
+ u16 ssthresh;
+ u16 max_win;
+ u16 cong_acks;
+ u16 checkpoint;
/* Fragmentation/reassembly */
struct sk_buff *reasm_buf;
@@ -244,12 +249,13 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
struct sk_buff_head *xmitq);
static void tipc_link_build_bc_init_msg(struct tipc_link *l,
struct sk_buff_head *xmitq);
-static bool tipc_link_release_pkts(struct tipc_link *l, u16 to);
-static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data);
+static int tipc_link_release_pkts(struct tipc_link *l, u16 to);
+static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap);
static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
struct tipc_gap_ack_blks *ga,
struct sk_buff_head *xmitq);
-
+static void tipc_link_update_cwin(struct tipc_link *l, int released,
+ bool retransmitted);
/*
* Simple non-static link routines (i.e. referenced outside this file)
*/
@@ -308,9 +314,14 @@ u32 tipc_link_id(struct tipc_link *l)
return l->peer_bearer_id << 16 | l->bearer_id;
}
-int tipc_link_window(struct tipc_link *l)
+int tipc_link_min_win(struct tipc_link *l)
{
- return l->window;
+ return l->min_win;
+}
+
+int tipc_link_max_win(struct tipc_link *l)
+{
+ return l->max_win;
}
int tipc_link_prio(struct tipc_link *l)
@@ -436,7 +447,8 @@ u32 tipc_link_state(struct tipc_link *l)
* @net_plane: network plane (A,B,c..) this link belongs to
* @mtu: mtu to be advertised by link
* @priority: priority to be used by link
- * @window: send window to be used by link
+ * @min_win: minimal send window to be used by link
+ * @max_win: maximal send window to be used by link
* @session: session to be used by link
* @ownnode: identity of own node
* @peer: node id of peer node
@@ -451,7 +463,7 @@ u32 tipc_link_state(struct tipc_link *l)
*/
bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
int tolerance, char net_plane, u32 mtu, int priority,
- int window, u32 session, u32 self,
+ u32 min_win, u32 max_win, u32 session, u32 self,
u32 peer, u8 *peer_id, u16 peer_caps,
struct tipc_link *bc_sndlink,
struct tipc_link *bc_rcvlink,
@@ -495,7 +507,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
l->advertised_mtu = mtu;
l->mtu = mtu;
l->priority = priority;
- tipc_link_set_queue_limits(l, window);
+ tipc_link_set_queue_limits(l, min_win, max_win);
l->ackers = 1;
l->bc_sndlink = bc_sndlink;
l->bc_rcvlink = bc_rcvlink;
@@ -523,7 +535,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
* Returns true if link was created, otherwise false
*/
bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
- int mtu, int window, u16 peer_caps,
+ int mtu, u32 min_win, u32 max_win, u16 peer_caps,
struct sk_buff_head *inputq,
struct sk_buff_head *namedq,
struct tipc_link *bc_sndlink,
@@ -531,9 +543,9 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
{
struct tipc_link *l;
- if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, window,
- 0, ownnode, peer, NULL, peer_caps, bc_sndlink,
- NULL, inputq, namedq, link))
+ if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, min_win,
+ max_win, 0, ownnode, peer, NULL, peer_caps,
+ bc_sndlink, NULL, inputq, namedq, link))
return false;
l = *link;
@@ -772,6 +784,8 @@ bool tipc_link_too_silent(struct tipc_link *l)
return (l->silent_intv_cnt + 2 > l->abort_limit);
}
+static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
+ u16 from, u16 to, struct sk_buff_head *xmitq);
/* tipc_link_timeout - perform periodic task as instructed from node timeout
*/
int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
@@ -804,6 +818,11 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
probe |= l->silent_intv_cnt;
if (probe || mstate->monitoring)
l->silent_intv_cnt++;
+ if (l->snd_nxt == l->checkpoint) {
+ tipc_link_update_cwin(l, 0, 0);
+ probe = true;
+ }
+ l->checkpoint = l->snd_nxt;
break;
case LINK_RESET:
setup = l->rst_cnt++ <= 4;
@@ -959,7 +978,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
int pkt_cnt = skb_queue_len(list);
int imp = msg_importance(hdr);
unsigned int mss = tipc_link_mss(l);
- unsigned int maxwin = l->window;
+ unsigned int cwin = l->window;
unsigned int mtu = l->mtu;
bool new_bundle;
int rc = 0;
@@ -988,7 +1007,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
/* Prepare each packet for sending, and add to relevant queue: */
while ((skb = __skb_dequeue(list))) {
- if (likely(skb_queue_len(transmq) < maxwin)) {
+ if (likely(skb_queue_len(transmq) < cwin)) {
hdr = buf_msg(skb);
msg_set_seqno(hdr, seqno);
msg_set_ack(hdr, ack);
@@ -1035,17 +1054,61 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
return rc;
}
+static void tipc_link_update_cwin(struct tipc_link *l, int released,
+ bool retransmitted)
+{
+ int bklog_len = skb_queue_len(&l->backlogq);
+ struct sk_buff_head *txq = &l->transmq;
+ int txq_len = skb_queue_len(txq);
+ u16 cwin = l->window;
+
+ /* Enter fast recovery */
+ if (unlikely(retransmitted)) {
+ l->ssthresh = max_t(u16, l->window / 2, 300);
+ l->window = l->ssthresh;
+ return;
+ }
+ /* Enter slow start */
+ if (unlikely(!released)) {
+ l->ssthresh = max_t(u16, l->window / 2, 300);
+ l->window = l->min_win;
+ return;
+ }
+ /* Don't increase window if no pressure on the transmit queue */
+ if (txq_len + bklog_len < cwin)
+ return;
+
+ /* Don't increase window if there are holes the transmit queue */
+ if (txq_len && l->snd_nxt - buf_seqno(skb_peek(txq)) != txq_len)
+ return;
+
+ l->cong_acks += released;
+
+ /* Slow start */
+ if (cwin <= l->ssthresh) {
+ l->window = min_t(u16, cwin + released, l->max_win);
+ return;
+ }
+ /* Congestion avoidance */
+ if (l->cong_acks < cwin)
+ return;
+ l->window = min_t(u16, ++cwin, l->max_win);
+ l->cong_acks = 0;
+}
+
static void tipc_link_advance_backlog(struct tipc_link *l,
struct sk_buff_head *xmitq)
{
+ u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ struct sk_buff_head *txq = &l->transmq;
struct sk_buff *skb, *_skb;
- struct tipc_msg *hdr;
- u16 seqno = l->snd_nxt;
u16 ack = l->rcv_nxt - 1;
- u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ u16 seqno = l->snd_nxt;
+ struct tipc_msg *hdr;
+ u16 cwin = l->window;
u32 imp;
- while (skb_queue_len(&l->transmq) < l->window) {
+ while (skb_queue_len(txq) < cwin) {
skb = skb_peek(&l->backlogq);
if (!skb)
break;
@@ -1141,6 +1204,7 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
u16 ack = l->rcv_nxt - 1;
+ int retransmitted = 0;
struct tipc_msg *hdr;
int rc = 0;
@@ -1160,7 +1224,6 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
continue;
if (more(msg_seqno(hdr), to))
break;
-
if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
continue;
TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
@@ -1173,11 +1236,12 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
_skb->priority = TC_PRIO_CONTROL;
__skb_queue_tail(xmitq, _skb);
l->stats.retransmitted++;
-
+ retransmitted++;
/* Increase actual retrans counter & mark first time */
if (!TIPC_SKB_CB(skb)->retr_cnt++)
TIPC_SKB_CB(skb)->retr_stamp = jiffies;
}
+ tipc_link_update_cwin(l, 0, retransmitted);
return 0;
}
@@ -1338,9 +1402,9 @@ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb,
return rc;
}
-static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
+static int tipc_link_release_pkts(struct tipc_link *l, u16 acked)
{
- bool released = false;
+ int released = 0;
struct sk_buff *skb, *tmp;
skb_queue_walk_safe(&l->transmq, skb, tmp) {
@@ -1348,7 +1412,7 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
break;
__skb_unlink(skb, &l->transmq);
kfree_skb(skb);
- released = true;
+ released++;
}
return released;
}
@@ -1359,14 +1423,14 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
*
* returns the actual allocated memory size
*/
-static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data)
+static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap)
{
struct sk_buff *skb = skb_peek(&l->deferdq);
struct tipc_gap_ack_blks *ga = data;
u16 len, expect, seqno = 0;
u8 n = 0;
- if (!skb)
+ if (!skb || !gap)
goto exit;
expect = buf_seqno(skb);
@@ -1417,8 +1481,10 @@ static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
struct sk_buff *skb, *_skb, *tmp;
struct tipc_msg *hdr;
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ bool retransmitted = false;
u16 ack = l->rcv_nxt - 1;
bool passed = false;
+ u16 released = 0;
u16 seqno, n = 0;
int rc = 0;
@@ -1430,6 +1496,7 @@ next_gap_ack:
/* release skb */
__skb_unlink(skb, &l->transmq);
kfree_skb(skb);
+ released++;
} else if (less_eq(seqno, acked + gap)) {
/* First, check if repeated retrans failures occurs? */
if (!passed && link_retransmit_failure(l, l, &rc))
@@ -1449,7 +1516,7 @@ next_gap_ack:
_skb->priority = TC_PRIO_CONTROL;
__skb_queue_tail(xmitq, _skb);
l->stats.retransmitted++;
-
+ retransmitted = true;
/* Increase actual retrans counter & mark first time */
if (!TIPC_SKB_CB(skb)->retr_cnt++)
TIPC_SKB_CB(skb)->retr_stamp = jiffies;
@@ -1463,7 +1530,10 @@ next_gap_ack:
goto next_gap_ack;
}
}
-
+ if (released || retransmitted)
+ tipc_link_update_cwin(l, released, retransmitted);
+ if (released)
+ tipc_link_advance_backlog(l, xmitq);
return 0;
}
@@ -1487,7 +1557,6 @@ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
l->snd_nxt = l->rcv_nxt;
return TIPC_LINK_SND_STATE;
}
-
/* Unicast ACK */
l->rcv_unacked = 0;
l->stats.sent_acks++;
@@ -1521,7 +1590,8 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
struct sk_buff_head *xmitq)
{
u32 def_cnt = ++l->stats.deferred_recv;
- u32 defq_len = skb_queue_len(&l->deferdq);
+ struct sk_buff_head *dfq = &l->deferdq;
+ u32 defq_len = skb_queue_len(dfq);
int match1, match2;
if (link_is_bc_rcvlink(l)) {
@@ -1532,8 +1602,12 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
return 0;
}
- if (defq_len >= 3 && !((defq_len - 3) % 16))
- tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq);
+ if (defq_len >= 3 && !((defq_len - 3) % 16)) {
+ u16 rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
+
+ tipc_link_build_proto_msg(l, STATE_MSG, 0, 0,
+ rcvgap, 0, 0, xmitq);
+ }
return 0;
}
@@ -1548,6 +1622,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *defq = &l->deferdq;
struct tipc_msg *hdr = buf_msg(skb);
u16 seqno, rcv_nxt, win_lim;
+ int released = 0;
int rc = 0;
/* Verify and update link state */
@@ -1566,21 +1641,17 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
if (unlikely(!link_is_up(l))) {
if (l->state == LINK_ESTABLISHING)
rc = TIPC_LINK_UP_EVT;
- goto drop;
+ kfree_skb(skb);
+ break;
}
/* Drop if outside receive window */
if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) {
l->stats.duplicates++;
- goto drop;
- }
-
- /* Forward queues and wake up waiting users */
- if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
- tipc_link_advance_backlog(l, xmitq);
- if (unlikely(!skb_queue_empty(&l->wakeupq)))
- link_prepare_wakeup(l);
+ kfree_skb(skb);
+ break;
}
+ released += tipc_link_release_pkts(l, msg_ack(hdr));
/* Defer delivery if sequence gap */
if (unlikely(seqno != rcv_nxt)) {
@@ -1603,9 +1674,13 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
break;
} while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt)));
- return rc;
-drop:
- kfree_skb(skb);
+ /* Forward queues and wake up waiting users */
+ if (released) {
+ tipc_link_update_cwin(l, released, 0);
+ tipc_link_advance_backlog(l, xmitq);
+ if (unlikely(!skb_queue_empty(&l->wakeupq)))
+ link_prepare_wakeup(l);
+ }
return rc;
}
@@ -1631,7 +1706,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
if (!tipc_link_is_up(l) && (mtyp == STATE_MSG))
return;
- if (!skb_queue_empty(dfq))
+ if ((probe || probe_reply) && !skb_queue_empty(dfq))
rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
@@ -1664,7 +1739,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
msg_set_probe(hdr, probe);
msg_set_is_keepalive(hdr, probe || probe_reply);
if (l->peer_caps & TIPC_GAP_ACK_BLOCK)
- glen = tipc_build_gap_ack_blks(l, data);
+ glen = tipc_build_gap_ack_blks(l, data, rcvgap);
tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id);
msg_set_size(hdr, INT_H_SIZE + glen + dlen);
skb_trim(skb, INT_H_SIZE + glen + dlen);
@@ -2074,19 +2149,18 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
&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))
+ if ((reply || msg_is_keepalive(hdr)) &&
+ more(peers_snd_nxt, rcv_nxt) &&
+ !tipc_link_is_synching(l) &&
+ skb_queue_empty(&l->deferdq))
rcvgap = peers_snd_nxt - l->rcv_nxt;
if (rcvgap || reply)
tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
rcvgap, 0, 0, xmitq);
rc |= tipc_link_advance_transmq(l, ack, gap, ga, xmitq);
-
- /* If NACK, retransmit will now start at right position */
if (gap)
l->stats.recv_nacks++;
-
- tipc_link_advance_backlog(l, xmitq);
if (unlikely(!skb_queue_empty(&l->wakeupq)))
link_prepare_wakeup(l);
}
@@ -2305,15 +2379,18 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
return 0;
}
-void tipc_link_set_queue_limits(struct tipc_link *l, u32 win)
+void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win)
{
int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE);
- l->window = win;
- l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win);
- l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = max_t(u16, 100, win * 2);
- l->backlog[TIPC_HIGH_IMPORTANCE].limit = max_t(u16, 150, win * 3);
- l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = max_t(u16, 200, win * 4);
+ l->min_win = min_win;
+ l->ssthresh = max_win;
+ l->max_win = max_win;
+ l->window = min_win;
+ l->backlog[TIPC_LOW_IMPORTANCE].limit = min_win * 2;
+ l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = min_win * 4;
+ l->backlog[TIPC_HIGH_IMPORTANCE].limit = min_win * 6;
+ l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = min_win * 8;
l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk;
}
@@ -2366,10 +2443,10 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
}
if (props[TIPC_NLA_PROP_WIN]) {
- u32 win;
+ u32 max_win;
- win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
- if ((win < TIPC_MIN_LINK_WIN) || (win > TIPC_MAX_LINK_WIN))
+ max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ if (max_win < TIPC_DEF_LINK_WIN || max_win > TIPC_MAX_LINK_WIN)
return -EINVAL;
}
@@ -2605,7 +2682,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP);
if (!prop)
goto attr_msg_full;
- if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window))
+ if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->max_win))
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST, bc_mode))
goto prop_msg_full;
diff --git a/net/tipc/link.h b/net/tipc/link.h
index c09e9d49d0a3..d3c1c3fc1659 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -73,7 +73,7 @@ enum {
bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
int tolerance, char net_plane, u32 mtu, int priority,
- int window, u32 session, u32 ownnode,
+ u32 min_win, u32 max_win, u32 session, u32 ownnode,
u32 peer, u8 *peer_id, u16 peer_caps,
struct tipc_link *bc_sndlink,
struct tipc_link *bc_rcvlink,
@@ -81,7 +81,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
struct sk_buff_head *namedq,
struct tipc_link **link);
bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
- int mtu, int window, u16 peer_caps,
+ int mtu, u32 min_win, u32 max_win, u16 peer_caps,
struct sk_buff_head *inputq,
struct sk_buff_head *namedq,
struct tipc_link *bc_sndlink,
@@ -115,7 +115,8 @@ char *tipc_link_name_ext(struct tipc_link *l, char *buf);
u32 tipc_link_state(struct tipc_link *l);
char tipc_link_plane(struct tipc_link *l);
int tipc_link_prio(struct tipc_link *l);
-int tipc_link_window(struct tipc_link *l);
+int tipc_link_min_win(struct tipc_link *l);
+int tipc_link_max_win(struct tipc_link *l);
void tipc_link_update_caps(struct tipc_link *l, u16 capabilities);
bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr);
unsigned long tipc_link_tolerance(struct tipc_link *l);
@@ -124,7 +125,7 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
void tipc_link_set_prio(struct tipc_link *l, u32 prio,
struct sk_buff_head *xmitq);
void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit);
-void tipc_link_set_queue_limits(struct tipc_link *l, u32 window);
+void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win);
int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
struct tipc_link *link, int nlflags);
int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 92d04dc2a44b..359b2bc888cf 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -36,6 +36,7 @@
#include <net/sock.h>
#include <linux/list_sort.h>
+#include <linux/rbtree_augmented.h>
#include "core.h"
#include "netlink.h"
#include "name_table.h"
@@ -51,6 +52,7 @@
* @lower: service range lower bound
* @upper: service range upper bound
* @tree_node: member of service range RB tree
+ * @max: largest 'upper' in this node subtree
* @local_publ: list of identical publications made from this node
* Used by closest_first lookup and multicast lookup algorithm
* @all_publ: all publications identical to this one, whatever node and scope
@@ -60,6 +62,7 @@ struct service_range {
u32 lower;
u32 upper;
struct rb_node tree_node;
+ u32 max;
struct list_head local_publ;
struct list_head all_publ;
};
@@ -84,6 +87,130 @@ struct tipc_service {
struct rcu_head rcu;
};
+#define service_range_upper(sr) ((sr)->upper)
+RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks,
+ struct service_range, tree_node, u32, max,
+ service_range_upper)
+
+#define service_range_entry(rbtree_node) \
+ (container_of(rbtree_node, struct service_range, tree_node))
+
+#define service_range_overlap(sr, start, end) \
+ ((sr)->lower <= (end) && (sr)->upper >= (start))
+
+/**
+ * service_range_foreach_match - iterate over tipc service rbtree for each
+ * range match
+ * @sr: the service range pointer as a loop cursor
+ * @sc: the pointer to tipc service which holds the service range rbtree
+ * @start, end: the range (end >= start) for matching
+ */
+#define service_range_foreach_match(sr, sc, start, end) \
+ for (sr = service_range_match_first((sc)->ranges.rb_node, \
+ start, \
+ end); \
+ sr; \
+ sr = service_range_match_next(&(sr)->tree_node, \
+ start, \
+ end))
+
+/**
+ * service_range_match_first - find first service range matching a range
+ * @n: the root node of service range rbtree for searching
+ * @start, end: the range (end >= start) for matching
+ *
+ * Return: the leftmost service range node in the rbtree that overlaps the
+ * specific range if any. Otherwise, returns NULL.
+ */
+static struct service_range *service_range_match_first(struct rb_node *n,
+ u32 start, u32 end)
+{
+ struct service_range *sr;
+ struct rb_node *l, *r;
+
+ /* Non overlaps in tree at all? */
+ if (!n || service_range_entry(n)->max < start)
+ return NULL;
+
+ while (n) {
+ l = n->rb_left;
+ if (l && service_range_entry(l)->max >= start) {
+ /* A leftmost overlap range node must be one in the left
+ * subtree. If not, it has lower > end, then nodes on
+ * the right side cannot satisfy the condition either.
+ */
+ n = l;
+ continue;
+ }
+
+ /* No one in the left subtree can match, return if this node is
+ * an overlap i.e. leftmost.
+ */
+ sr = service_range_entry(n);
+ if (service_range_overlap(sr, start, end))
+ return sr;
+
+ /* Ok, try to lookup on the right side */
+ r = n->rb_right;
+ if (sr->lower <= end &&
+ r && service_range_entry(r)->max >= start) {
+ n = r;
+ continue;
+ }
+ break;
+ }
+
+ return NULL;
+}
+
+/**
+ * service_range_match_next - find next service range matching a range
+ * @n: a node in service range rbtree from which the searching starts
+ * @start, end: the range (end >= start) for matching
+ *
+ * Return: the next service range node to the given node in the rbtree that
+ * overlaps the specific range if any. Otherwise, returns NULL.
+ */
+static struct service_range *service_range_match_next(struct rb_node *n,
+ u32 start, u32 end)
+{
+ struct service_range *sr;
+ struct rb_node *p, *r;
+
+ while (n) {
+ r = n->rb_right;
+ if (r && service_range_entry(r)->max >= start)
+ /* A next overlap range node must be one in the right
+ * subtree. If not, it has lower > end, then any next
+ * successor (- an ancestor) of this node cannot
+ * satisfy the condition either.
+ */
+ return service_range_match_first(r, start, end);
+
+ /* No one in the right subtree can match, go up to find an
+ * ancestor of this node which is parent of a left-hand child.
+ */
+ while ((p = rb_parent(n)) && n == p->rb_right)
+ n = p;
+ if (!p)
+ break;
+
+ /* Return if this ancestor is an overlap */
+ sr = service_range_entry(p);
+ if (service_range_overlap(sr, start, end))
+ return sr;
+
+ /* Ok, try to lookup more from this ancestor */
+ if (sr->lower <= end) {
+ n = p;
+ continue;
+ }
+ break;
+ }
+
+ return NULL;
+}
+
static int hash(int x)
{
return x & (TIPC_NAMETBL_SIZE - 1);
@@ -139,84 +266,51 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd)
return service;
}
-/**
- * tipc_service_first_range - find first service range in tree matching instance
- *
- * Very time-critical, so binary search through range rb tree
- */
-static struct service_range *tipc_service_first_range(struct tipc_service *sc,
- u32 instance)
-{
- struct rb_node *n = sc->ranges.rb_node;
- struct service_range *sr;
-
- while (n) {
- sr = container_of(n, struct service_range, tree_node);
- if (sr->lower > instance)
- n = n->rb_left;
- else if (sr->upper < instance)
- n = n->rb_right;
- else
- return sr;
- }
- return NULL;
-}
-
/* tipc_service_find_range - find service range matching publication parameters
*/
static struct service_range *tipc_service_find_range(struct tipc_service *sc,
u32 lower, u32 upper)
{
- struct rb_node *n = sc->ranges.rb_node;
struct service_range *sr;
- sr = tipc_service_first_range(sc, lower);
- if (!sr)
- return NULL;
-
- /* Look for exact match */
- for (n = &sr->tree_node; n; n = rb_next(n)) {
- sr = container_of(n, struct service_range, tree_node);
- if (sr->upper == upper)
- break;
+ service_range_foreach_match(sr, sc, lower, upper) {
+ /* Look for exact match */
+ if (sr->lower == lower && sr->upper == upper)
+ return sr;
}
- if (!n || sr->lower != lower || sr->upper != upper)
- return NULL;
- return sr;
+ return NULL;
}
static struct service_range *tipc_service_create_range(struct tipc_service *sc,
u32 lower, u32 upper)
{
struct rb_node **n, *parent = NULL;
- struct service_range *sr, *tmp;
+ struct service_range *sr;
n = &sc->ranges.rb_node;
while (*n) {
- tmp = container_of(*n, struct service_range, tree_node);
parent = *n;
- tmp = container_of(parent, struct service_range, tree_node);
- if (lower < tmp->lower)
- n = &(*n)->rb_left;
- else if (lower > tmp->lower)
- n = &(*n)->rb_right;
- else if (upper < tmp->upper)
- n = &(*n)->rb_left;
- else if (upper > tmp->upper)
- n = &(*n)->rb_right;
+ sr = service_range_entry(parent);
+ if (lower == sr->lower && upper == sr->upper)
+ return sr;
+ if (sr->max < upper)
+ sr->max = upper;
+ if (lower <= sr->lower)
+ n = &parent->rb_left;
else
- return tmp;
+ n = &parent->rb_right;
}
sr = kzalloc(sizeof(*sr), GFP_ATOMIC);
if (!sr)
return NULL;
sr->lower = lower;
sr->upper = upper;
+ sr->max = upper;
INIT_LIST_HEAD(&sr->local_publ);
INIT_LIST_HEAD(&sr->all_publ);
rb_link_node(&sr->tree_node, parent, n);
- rb_insert_color(&sr->tree_node, &sc->ranges);
+ rb_insert_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks);
return sr;
}
@@ -310,7 +404,6 @@ static void tipc_service_subscribe(struct tipc_service *service,
struct list_head publ_list;
struct service_range *sr;
struct tipc_name_seq ns;
- struct rb_node *n;
u32 filter;
ns.type = tipc_sub_read(sb, seq.type);
@@ -325,13 +418,7 @@ static void tipc_service_subscribe(struct tipc_service *service,
return;
INIT_LIST_HEAD(&publ_list);
- for (n = rb_first(&service->ranges); n; n = rb_next(n)) {
- sr = container_of(n, struct service_range, tree_node);
- if (sr->lower > ns.upper)
- break;
- if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper))
- continue;
-
+ service_range_foreach_match(sr, service, ns.lower, ns.upper) {
first = NULL;
list_for_each_entry(p, &sr->all_publ, all_publ) {
if (filter & TIPC_SUB_PORTS)
@@ -425,7 +512,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type,
/* Remove service range item if this was its last publication */
if (list_empty(&sr->all_publ)) {
- rb_erase(&sr->tree_node, &sc->ranges);
+ rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks);
kfree(sr);
}
@@ -473,34 +560,39 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode)
rcu_read_lock();
sc = tipc_service_find(net, type);
if (unlikely(!sc))
- goto not_found;
+ goto exit;
spin_lock_bh(&sc->lock);
- sr = tipc_service_first_range(sc, instance);
- if (unlikely(!sr))
- goto no_match;
-
- /* Select lookup algorithm: local, closest-first or round-robin */
- if (*dnode == self) {
- list = &sr->local_publ;
- if (list_empty(list))
- goto no_match;
- p = list_first_entry(list, struct publication, local_publ);
- list_move_tail(&p->local_publ, &sr->local_publ);
- } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) {
- list = &sr->local_publ;
- p = list_first_entry(list, struct publication, local_publ);
- list_move_tail(&p->local_publ, &sr->local_publ);
- } else {
- list = &sr->all_publ;
- p = list_first_entry(list, struct publication, all_publ);
- list_move_tail(&p->all_publ, &sr->all_publ);
+ service_range_foreach_match(sr, sc, instance, instance) {
+ /* Select lookup algo: local, closest-first or round-robin */
+ if (*dnode == self) {
+ list = &sr->local_publ;
+ if (list_empty(list))
+ continue;
+ p = list_first_entry(list, struct publication,
+ local_publ);
+ list_move_tail(&p->local_publ, &sr->local_publ);
+ } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) {
+ list = &sr->local_publ;
+ p = list_first_entry(list, struct publication,
+ local_publ);
+ list_move_tail(&p->local_publ, &sr->local_publ);
+ } else {
+ list = &sr->all_publ;
+ p = list_first_entry(list, struct publication,
+ all_publ);
+ list_move_tail(&p->all_publ, &sr->all_publ);
+ }
+ port = p->port;
+ node = p->node;
+ /* Todo: as for legacy, pick the first matching range only, a
+ * "true" round-robin will be performed as needed.
+ */
+ break;
}
- port = p->port;
- node = p->node;
-no_match:
spin_unlock_bh(&sc->lock);
-not_found:
+
+exit:
rcu_read_unlock();
*dnode = node;
return port;
@@ -523,7 +615,8 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope,
spin_lock_bh(&sc->lock);
- sr = tipc_service_first_range(sc, instance);
+ /* Todo: a full search i.e. service_range_foreach_match() instead? */
+ sr = service_range_match_first(sc->ranges.rb_node, instance, instance);
if (!sr)
goto no_match;
@@ -552,7 +645,6 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper,
struct service_range *sr;
struct tipc_service *sc;
struct publication *p;
- struct rb_node *n;
rcu_read_lock();
sc = tipc_service_find(net, type);
@@ -560,13 +652,7 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper,
goto exit;
spin_lock_bh(&sc->lock);
-
- for (n = rb_first(&sc->ranges); n; n = rb_next(n)) {
- sr = container_of(n, struct service_range, tree_node);
- if (sr->upper < lower)
- continue;
- if (sr->lower > upper)
- break;
+ service_range_foreach_match(sr, sc, lower, upper) {
list_for_each_entry(p, &sr->local_publ, local_publ) {
if (p->scope == scope || (!exact && p->scope < scope))
tipc_dest_push(dports, 0, p->port);
@@ -587,7 +673,6 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
struct service_range *sr;
struct tipc_service *sc;
struct publication *p;
- struct rb_node *n;
rcu_read_lock();
sc = tipc_service_find(net, type);
@@ -595,13 +680,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower,
goto exit;
spin_lock_bh(&sc->lock);
-
- for (n = rb_first(&sc->ranges); n; n = rb_next(n)) {
- sr = container_of(n, struct service_range, tree_node);
- if (sr->upper < lower)
- continue;
- if (sr->lower > upper)
- break;
+ service_range_foreach_match(sr, sc, lower, upper) {
list_for_each_entry(p, &sr->all_publ, all_publ) {
tipc_nlist_add(nodes, p->node);
}
@@ -799,7 +878,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc)
tipc_service_remove_publ(sr, p->node, p->key);
kfree_rcu(p, rcu);
}
- rb_erase(&sr->tree_node, &sc->ranges);
+ rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks);
kfree(sr);
}
hlist_del_init_rcu(&sc->service_list);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 2de3cec9929d..85400e4242de 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -302,3 +302,59 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
return err;
}
+
+static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg)
+{
+ struct tipc_net *tn = tipc_net(net);
+ struct nlattr *attrs;
+ void *hdr;
+
+ hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+ 0, TIPC_NL_ADDR_LEGACY_GET);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ attrs = nla_nest_start(msg->skb, TIPC_NLA_NET);
+ if (!attrs)
+ goto msg_full;
+
+ if (tn->legacy_addr_format)
+ if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY))
+ 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_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = sock_net(skb->sk);
+ struct tipc_nl_msg msg;
+ struct sk_buff *rep;
+ int err;
+
+ rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!rep)
+ return -ENOMEM;
+
+ msg.skb = rep;
+ msg.portid = info->snd_portid;
+ msg.seq = info->snd_seq;
+
+ err = __tipc_nl_addr_legacy_get(net, &msg);
+ if (err) {
+ nlmsg_free(msg.skb);
+ return err;
+ }
+
+ return genlmsg_reply(msg.skb, info);
+}
diff --git a/net/tipc/net.h b/net/tipc/net.h
index b7f2e364eb99..6740d97c706e 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -47,5 +47,6 @@ void tipc_net_stop(struct net *net);
int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info);
#endif
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index e53231bd23b4..7c35094c20b8 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -83,6 +83,7 @@ const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
[TIPC_NLA_NET_ADDR] = { .type = NLA_U32 },
[TIPC_NLA_NET_NODEID] = { .type = NLA_U64 },
[TIPC_NLA_NET_NODEID_W1] = { .type = NLA_U64 },
+ [TIPC_NLA_NET_ADDR_LEGACY] = { .type = NLA_FLAG }
};
const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
@@ -273,6 +274,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
.doit = tipc_nl_node_flush_key,
},
#endif
+ {
+ .cmd = TIPC_NL_ADDR_LEGACY_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .doit = tipc_nl_net_addr_legacy_get,
+ },
};
struct genl_family tipc_genl_family __ro_after_init = {
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 0254bb7e418b..217516357ef2 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -204,8 +204,8 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
return -ENOMEM;
}
- attrbuf = kmalloc_array(tipc_genl_family.maxattr + 1,
- sizeof(struct nlattr *), GFP_KERNEL);
+ attrbuf = kcalloc(tipc_genl_family.maxattr + 1,
+ sizeof(struct nlattr *), GFP_KERNEL);
if (!attrbuf) {
err = -ENOMEM;
goto err_out;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index ab04e00cb95b..99b28b69fc17 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1139,7 +1139,8 @@ void tipc_node_check_dest(struct net *net, u32 addr,
snd_l = tipc_bc_sndlink(net);
if (!tipc_link_bc_create(net, tipc_own_addr(net),
addr, U16_MAX,
- tipc_link_window(snd_l),
+ tipc_link_min_win(snd_l),
+ tipc_link_max_win(snd_l),
n->capabilities,
&n->bc_entry.inputq1,
&n->bc_entry.namedq, snd_l,
@@ -1233,7 +1234,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
get_random_bytes(&session, sizeof(u16));
if (!tipc_link_create(net, if_name, b->identity, b->tolerance,
b->net_plane, b->mtu, b->priority,
- b->window, session,
+ b->min_win, b->max_win, session,
tipc_own_addr(net), addr, peer_id,
n->capabilities,
tipc_bc_sndlink(n->net), n->bc_entry.link,
@@ -2360,8 +2361,7 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
if (attrs[TIPC_NLA_LINK_PROP]) {
struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
- err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP],
- props);
+ err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props);
if (err) {
res = err;
goto out;
@@ -2380,10 +2380,12 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
tipc_link_set_prio(link, prio, &xmitq);
}
if (props[TIPC_NLA_PROP_WIN]) {
- u32 win;
+ u32 max_win;
- win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
- tipc_link_set_queue_limits(link, win);
+ max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ tipc_link_set_queue_limits(link,
+ tipc_link_min_win(link),
+ max_win);
}
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 41688da233ab..f9b4fb92c0b1 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -287,12 +287,12 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
*
* Caller must hold socket lock
*/
-static void tsk_rej_rx_queue(struct sock *sk)
+static void tsk_rej_rx_queue(struct sock *sk, int error)
{
struct sk_buff *skb;
while ((skb = __skb_dequeue(&sk->sk_receive_queue)))
- tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
+ tipc_sk_respond(sk, skb, error);
}
static bool tipc_sk_connected(struct sock *sk)
@@ -545,34 +545,45 @@ static void __tipc_shutdown(struct socket *sock, int error)
/* Remove pending SYN */
__skb_queue_purge(&sk->sk_write_queue);
- /* Reject all unreceived messages, except on an active connection
- * (which disconnects locally & sends a 'FIN+' to peer).
- */
- while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
- if (TIPC_SKB_CB(skb)->bytes_read) {
- kfree_skb(skb);
- continue;
- }
- if (!tipc_sk_type_connectionless(sk) &&
- sk->sk_state != TIPC_DISCONNECTING) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
- tipc_sk_respond(sk, skb, error);
+ /* Remove partially received buffer if any */
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb && TIPC_SKB_CB(skb)->bytes_read) {
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ kfree_skb(skb);
}
- if (tipc_sk_type_connectionless(sk))
+ /* Reject all unreceived messages if connectionless */
+ if (tipc_sk_type_connectionless(sk)) {
+ tsk_rej_rx_queue(sk, error);
return;
+ }
- if (sk->sk_state != TIPC_DISCONNECTING) {
+ switch (sk->sk_state) {
+ case TIPC_CONNECTING:
+ case TIPC_ESTABLISHED:
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ /* Send a FIN+/- to its peer */
+ skb = __skb_dequeue(&sk->sk_receive_queue);
+ if (skb) {
+ __skb_queue_purge(&sk->sk_receive_queue);
+ tipc_sk_respond(sk, skb, error);
+ break;
+ }
skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
tsk_own_node(tsk), tsk_peer_port(tsk),
tsk->portid, error);
if (skb)
tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ break;
+ case TIPC_LISTEN:
+ /* Reject all SYN messages */
+ tsk_rej_rx_queue(sk, error);
+ break;
+ default:
+ __skb_queue_purge(&sk->sk_receive_queue);
+ break;
}
}
@@ -1364,8 +1375,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
struct tipc_msg *hdr = &tsk->phdr;
struct tipc_name_seq *seq;
struct sk_buff_head pkts;
- u32 dport, dnode = 0;
- u32 type, inst;
+ u32 dport = 0, dnode = 0;
+ u32 type = 0, inst = 0;
int mtu, rc;
if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE))
@@ -1418,23 +1429,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
type = dest->addr.name.name.type;
inst = dest->addr.name.name.instance;
dnode = dest->addr.name.domain;
- msg_set_type(hdr, TIPC_NAMED_MSG);
- msg_set_hdr_sz(hdr, NAMED_H_SIZE);
- msg_set_nametype(hdr, type);
- msg_set_nameinst(hdr, inst);
- msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
dport = tipc_nametbl_translate(net, type, inst, &dnode);
- msg_set_destnode(hdr, dnode);
- msg_set_destport(hdr, dport);
if (unlikely(!dport && !dnode))
return -EHOSTUNREACH;
} else if (dest->addrtype == TIPC_ADDR_ID) {
dnode = dest->addr.id.node;
- msg_set_type(hdr, TIPC_DIRECT_MSG);
- msg_set_lookup_scope(hdr, 0);
- msg_set_destnode(hdr, dnode);
- msg_set_destport(hdr, dest->addr.id.ref);
- msg_set_hdr_sz(hdr, BASIC_H_SIZE);
} else {
return -EINVAL;
}
@@ -1445,6 +1444,22 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (unlikely(rc))
return rc;
+ if (dest->addrtype == TIPC_ADDR_NAME) {
+ msg_set_type(hdr, TIPC_NAMED_MSG);
+ msg_set_hdr_sz(hdr, NAMED_H_SIZE);
+ msg_set_nametype(hdr, type);
+ msg_set_nameinst(hdr, inst);
+ msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
+ msg_set_destnode(hdr, dnode);
+ msg_set_destport(hdr, dport);
+ } else { /* TIPC_ADDR_ID */
+ msg_set_type(hdr, TIPC_DIRECT_MSG);
+ msg_set_lookup_scope(hdr, 0);
+ msg_set_destnode(hdr, dnode);
+ msg_set_destport(hdr, dest->addr.id.ref);
+ msg_set_hdr_sz(hdr, BASIC_H_SIZE);
+ }
+
__skb_queue_head_init(&pkts);
mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
@@ -2428,8 +2443,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
return sock_intr_errno(*timeo_p);
add_wait_queue(sk_sleep(sk), &wait);
- done = sk_wait_event(sk, timeo_p,
- sk->sk_state != TIPC_CONNECTING, &wait);
+ done = sk_wait_event(sk, timeo_p, tipc_sk_connected(sk),
+ &wait);
remove_wait_queue(sk_sleep(sk), &wait);
} while (!done);
return 0;
@@ -2639,7 +2654,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
* Reject any stray messages received by new socket
* before the socket lock was taken (very, very unlikely)
*/
- tsk_rej_rx_queue(new_sk);
+ tsk_rej_rx_queue(new_sk, TIPC_ERR_NO_PORT);
/* Connect new socket to it's peer */
tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index ed113735c019..d6620ad53546 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -828,7 +828,8 @@ struct tipc_media udp_media_info = {
.msg2addr = tipc_udp_msg2addr,
.priority = TIPC_DEF_LINK_PRI,
.tolerance = TIPC_DEF_LINK_TOL,
- .window = TIPC_DEF_LINK_WIN,
+ .min_win = TIPC_DEF_LINK_WIN,
+ .max_win = TIPC_DEF_LINK_WIN,
.mtu = TIPC_DEF_LINK_UDP_MTU,
.type_id = TIPC_MEDIA_TYPE_UDP,
.hwaddr_len = 0,
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.