summaryrefslogtreecommitdiff
path: root/net/tipc
diff options
context:
space:
mode:
Diffstat (limited to 'net/tipc')
-rw-r--r--net/tipc/Kconfig18
-rw-r--r--net/tipc/Makefile1
-rw-r--r--net/tipc/addr.c1
-rw-r--r--net/tipc/bcast.c293
-rw-r--r--net/tipc/bcast.h14
-rw-r--r--net/tipc/bearer.c177
-rw-r--r--net/tipc/bearer.h16
-rw-r--r--net/tipc/core.c75
-rw-r--r--net/tipc/core.h26
-rw-r--r--net/tipc/crypto.c1986
-rw-r--r--net/tipc/crypto.h167
-rw-r--r--net/tipc/discover.c4
-rw-r--r--net/tipc/group.c7
-rw-r--r--net/tipc/link.c674
-rw-r--r--net/tipc/link.h3
-rw-r--r--net/tipc/monitor.c19
-rw-r--r--net/tipc/monitor.h1
-rw-r--r--net/tipc/msg.c283
-rw-r--r--net/tipc/msg.h169
-rw-r--r--net/tipc/name_distr.c5
-rw-r--r--net/tipc/name_table.c58
-rw-r--r--net/tipc/name_table.h4
-rw-r--r--net/tipc/net.c10
-rw-r--r--net/tipc/netlink.c80
-rw-r--r--net/tipc/netlink.h1
-rw-r--r--net/tipc/netlink_compat.c155
-rw-r--r--net/tipc/node.c632
-rw-r--r--net/tipc/node.h31
-rw-r--r--net/tipc/socket.c193
-rw-r--r--net/tipc/subscr.h5
-rw-r--r--net/tipc/sysctl.c17
-rw-r--r--net/tipc/topsrv.c18
-rw-r--r--net/tipc/udp_media.c135
33 files changed, 4636 insertions, 642 deletions
diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig
index e450212121d2..716b61a701a8 100644
--- a/net/tipc/Kconfig
+++ b/net/tipc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# TIPC configuration
#
@@ -16,7 +17,7 @@ menuconfig TIPC
This protocol support is also available as a module ( = code which
can be inserted in and removed from the running kernel whenever you
want). The module will be called tipc. If you want to compile it
- as a module, say M here and read <file:Documentation/kbuild/modules.txt>.
+ as a module, say M here and read <file:Documentation/kbuild/modules.rst>.
If in doubt, say N.
@@ -34,6 +35,21 @@ config TIPC_MEDIA_UDP
Saying Y here will enable support for running TIPC over IP/UDP
bool
default y
+config TIPC_CRYPTO
+ bool "TIPC encryption support"
+ depends on TIPC
+ select CRYPTO
+ select CRYPTO_AES
+ select CRYPTO_GCM
+ help
+ Saying Y here will enable support for TIPC encryption.
+ All TIPC messages will be encrypted/decrypted by using the currently most
+ advanced algorithm: AEAD AES-GCM (like IPSec or TLS) before leaving/
+ entering the TIPC stack.
+ Key setting from user-space is performed via netlink by a user program
+ (e.g. the iproute2 'tipc' tool).
+ bool
+ default y
config TIPC_DIAG
tristate "TIPC: socket monitoring interface"
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index c86aba0282af..11255e970dd4 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -16,6 +16,7 @@ CFLAGS_trace.o += -I$(src)
tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o
tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o
tipc-$(CONFIG_SYSCTL) += sysctl.o
+tipc-$(CONFIG_TIPC_CRYPTO) += crypto.o
obj-$(CONFIG_TIPC_DIAG) += diag.o
diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index b88d48d00913..0f1eaed1bd1b 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -75,6 +75,7 @@ void tipc_set_node_addr(struct net *net, u32 addr)
tipc_set_node_id(net, node_id);
}
tn->trial_addr = addr;
+ tn->addr_trial_end = jiffies;
pr_info("32-bit node address hash set to %x\n", addr);
}
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index d8026543bf4c..55aeba681cf4 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -54,7 +54,9 @@ const char tipc_bclink_name[] = "broadcast-link";
* @dests: array keeping number of reachable destinations per bearer
* @primary_bearer: a bearer having links to all broadcast destinations, if any
* @bcast_support: indicates if primary bearer, if any, supports broadcast
+ * @force_bcast: forces broadcast for multicast traffic
* @rcast_support: indicates if all peer nodes support replicast
+ * @force_rcast: forces replicast for multicast traffic
* @rc_ratio: dest count as percentage of cluster size where send method changes
* @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast
*/
@@ -64,7 +66,9 @@ struct tipc_bc_base {
int dests[MAX_BEARERS];
int primary_bearer;
bool bcast_support;
+ bool force_bcast;
bool rcast_support;
+ bool force_rcast;
int rc_ratio;
int bc_threshold;
};
@@ -80,12 +84,12 @@ static struct tipc_bc_base *tipc_bc_base(struct net *net)
*/
int tipc_bcast_get_mtu(struct net *net)
{
- return tipc_link_mtu(tipc_bc_sndlink(net)) - INT_H_SIZE;
+ return tipc_link_mss(tipc_bc_sndlink(net));
}
-void tipc_bcast_disable_rcast(struct net *net)
+void tipc_bcast_toggle_rcast(struct net *net, bool supp)
{
- tipc_bc_base(net)->rcast_support = false;
+ tipc_bc_base(net)->rcast_support = supp;
}
static void tipc_bcbase_calc_bc_threshold(struct net *net)
@@ -181,7 +185,7 @@ static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq)
}
/* We have to transmit across all bearers */
- skb_queue_head_init(&_xmitq);
+ __skb_queue_head_init(&_xmitq);
for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
if (!bb->dests[bearer_id])
continue;
@@ -216,9 +220,24 @@ static void tipc_bcast_select_xmit_method(struct net *net, int dests,
}
/* Can current method be changed ? */
method->expires = jiffies + TIPC_METHOD_EXPIRE;
- if (method->mandatory || time_before(jiffies, exp))
+ if (method->mandatory)
return;
+ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL) &&
+ time_before(jiffies, exp))
+ return;
+
+ /* Configuration as force 'broadcast' method */
+ if (bb->force_bcast) {
+ method->rcast = false;
+ return;
+ }
+ /* Configuration as force 'replicast' method */
+ if (bb->force_rcast) {
+ method->rcast = true;
+ return;
+ }
+ /* Configuration as 'autoselect' or default method */
/* Determine method to use now */
method->rcast = dests <= bb->bc_threshold;
}
@@ -237,7 +256,7 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts,
struct sk_buff_head xmitq;
int rc = 0;
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
tipc_bcast_lock(net);
if (tipc_link_bc_peers(l))
rc = tipc_link_xmit(l, pkts, &xmitq);
@@ -267,7 +286,7 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
u32 dnode, selector;
selector = msg_link_selector(buf_msg(skb_peek(pkts)));
- skb_queue_head_init(&_pkts);
+ __skb_queue_head_init(&_pkts);
list_for_each_entry_safe(dst, tmp, &dests->list, list) {
dnode = dst->node;
@@ -281,6 +300,63 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
return 0;
}
+/* tipc_mcast_send_sync - deliver a dummy message with SYN bit
+ * @net: the applicable net namespace
+ * @skb: socket buffer to copy
+ * @method: send method to be used
+ * @dests: destination nodes for message.
+ * @cong_link_cnt: returns number of encountered congested destination links
+ * Returns 0 if success, otherwise errno
+ */
+static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
+ struct tipc_mc_method *method,
+ struct tipc_nlist *dests,
+ u16 *cong_link_cnt)
+{
+ struct tipc_msg *hdr, *_hdr;
+ struct sk_buff_head tmpq;
+ struct sk_buff *_skb;
+
+ /* Is a cluster supporting with new capabilities ? */
+ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL))
+ return 0;
+
+ hdr = buf_msg(skb);
+ if (msg_user(hdr) == MSG_FRAGMENTER)
+ hdr = msg_inner_hdr(hdr);
+ if (msg_type(hdr) != TIPC_MCAST_MSG)
+ return 0;
+
+ /* Allocate dummy message */
+ _skb = tipc_buf_acquire(MCAST_H_SIZE, GFP_KERNEL);
+ if (!_skb)
+ return -ENOMEM;
+
+ /* Preparing for 'synching' header */
+ msg_set_syn(hdr, 1);
+
+ /* Copy skb's header into a dummy header */
+ skb_copy_to_linear_data(_skb, hdr, MCAST_H_SIZE);
+ skb_orphan(_skb);
+
+ /* Reverse method for dummy message */
+ _hdr = buf_msg(_skb);
+ msg_set_size(_hdr, MCAST_H_SIZE);
+ msg_set_is_rcast(_hdr, !msg_is_rcast(hdr));
+
+ __skb_queue_head_init(&tmpq);
+ __skb_queue_tail(&tmpq, _skb);
+ if (method->rcast)
+ tipc_bcast_xmit(net, &tmpq, cong_link_cnt);
+ else
+ tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt);
+
+ /* This queue should normally be empty by now */
+ __skb_queue_purge(&tmpq);
+
+ return 0;
+}
+
/* tipc_mcast_xmit - deliver message to indicated destination nodes
* and to identified node local sockets
* @net: the applicable net namespace
@@ -296,10 +372,13 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
u16 *cong_link_cnt)
{
struct sk_buff_head inputq, localq;
+ bool rcast = method->rcast;
+ struct tipc_msg *hdr;
+ struct sk_buff *skb;
int rc = 0;
skb_queue_head_init(&inputq);
- skb_queue_head_init(&localq);
+ __skb_queue_head_init(&localq);
/* Clone packets before they are consumed by next call */
if (dests->local && !tipc_msg_reassemble(pkts, &localq)) {
@@ -309,14 +388,28 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
/* Send according to determined transmit method */
if (dests->remote) {
tipc_bcast_select_xmit_method(net, dests->remote, method);
+
+ skb = skb_peek(pkts);
+ hdr = buf_msg(skb);
+ if (msg_user(hdr) == MSG_FRAGMENTER)
+ hdr = msg_inner_hdr(hdr);
+ msg_set_is_rcast(hdr, method->rcast);
+
+ /* Switch method ? */
+ if (rcast != method->rcast)
+ tipc_mcast_send_sync(net, skb, method,
+ dests, cong_link_cnt);
+
if (method->rcast)
rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt);
else
rc = tipc_bcast_xmit(net, pkts, cong_link_cnt);
}
- if (dests->local)
+ if (dests->local) {
+ tipc_loopback_trace(net, &localq);
tipc_sk_mcast_rcv(net, &localq, &inputq);
+ }
exit:
/* This queue should normally be empty by now */
__skb_queue_purge(pkts);
@@ -485,10 +578,63 @@ static int tipc_bc_link_set_queue_limits(struct net *net, u32 limit)
return 0;
}
+static int tipc_bc_link_set_broadcast_mode(struct net *net, u32 bc_mode)
+{
+ struct tipc_bc_base *bb = tipc_bc_base(net);
+
+ switch (bc_mode) {
+ case BCLINK_MODE_BCAST:
+ if (!bb->bcast_support)
+ return -ENOPROTOOPT;
+
+ bb->force_bcast = true;
+ bb->force_rcast = false;
+ break;
+ case BCLINK_MODE_RCAST:
+ if (!bb->rcast_support)
+ return -ENOPROTOOPT;
+
+ bb->force_bcast = false;
+ bb->force_rcast = true;
+ break;
+ case BCLINK_MODE_SEL:
+ if (!bb->bcast_support || !bb->rcast_support)
+ return -ENOPROTOOPT;
+
+ bb->force_bcast = false;
+ bb->force_rcast = false;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int tipc_bc_link_set_broadcast_ratio(struct net *net, u32 bc_ratio)
+{
+ struct tipc_bc_base *bb = tipc_bc_base(net);
+
+ if (!bb->bcast_support || !bb->rcast_support)
+ return -ENOPROTOOPT;
+
+ if (bc_ratio > 100 || bc_ratio <= 0)
+ return -EINVAL;
+
+ bb->rc_ratio = bc_ratio;
+ tipc_bcast_lock(net);
+ tipc_bcbase_calc_bc_threshold(net);
+ tipc_bcast_unlock(net);
+
+ return 0;
+}
+
int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[])
{
int err;
u32 win;
+ u32 bc_mode;
+ u32 bc_ratio;
struct nlattr *props[TIPC_NLA_PROP_MAX + 1];
if (!attrs[TIPC_NLA_LINK_PROP])
@@ -498,12 +644,28 @@ int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[])
if (err)
return err;
- if (!props[TIPC_NLA_PROP_WIN])
+ if (!props[TIPC_NLA_PROP_WIN] &&
+ !props[TIPC_NLA_PROP_BROADCAST] &&
+ !props[TIPC_NLA_PROP_BROADCAST_RATIO]) {
return -EOPNOTSUPP;
+ }
+
+ if (props[TIPC_NLA_PROP_BROADCAST]) {
+ bc_mode = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST]);
+ err = tipc_bc_link_set_broadcast_mode(net, bc_mode);
+ }
+
+ if (!err && props[TIPC_NLA_PROP_BROADCAST_RATIO]) {
+ bc_ratio = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST_RATIO]);
+ err = tipc_bc_link_set_broadcast_ratio(net, bc_ratio);
+ }
- win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ if (!err && props[TIPC_NLA_PROP_WIN]) {
+ win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+ err = tipc_bc_link_set_queue_limits(net, win);
+ }
- return tipc_bc_link_set_queue_limits(net, win);
+ return err;
}
int tipc_bcast_init(struct net *net)
@@ -529,7 +691,7 @@ int tipc_bcast_init(struct net *net)
goto enomem;
bb->link = l;
tn->bcl = l;
- bb->rc_ratio = 25;
+ bb->rc_ratio = 10;
bb->rcast_support = true;
return 0;
enomem:
@@ -576,3 +738,108 @@ void tipc_nlist_purge(struct tipc_nlist *nl)
nl->remote = 0;
nl->local = false;
}
+
+u32 tipc_bcast_get_broadcast_mode(struct net *net)
+{
+ struct tipc_bc_base *bb = tipc_bc_base(net);
+
+ if (bb->force_bcast)
+ return BCLINK_MODE_BCAST;
+
+ if (bb->force_rcast)
+ return BCLINK_MODE_RCAST;
+
+ if (bb->bcast_support && bb->rcast_support)
+ return BCLINK_MODE_SEL;
+
+ return 0;
+}
+
+u32 tipc_bcast_get_broadcast_ratio(struct net *net)
+{
+ struct tipc_bc_base *bb = tipc_bc_base(net);
+
+ return bb->rc_ratio;
+}
+
+void tipc_mcast_filter_msg(struct net *net, struct sk_buff_head *defq,
+ struct sk_buff_head *inputq)
+{
+ struct sk_buff *skb, *_skb, *tmp;
+ struct tipc_msg *hdr, *_hdr;
+ bool match = false;
+ u32 node, port;
+
+ skb = skb_peek(inputq);
+ if (!skb)
+ return;
+
+ hdr = buf_msg(skb);
+
+ if (likely(!msg_is_syn(hdr) && skb_queue_empty(defq)))
+ return;
+
+ node = msg_orignode(hdr);
+ if (node == tipc_own_addr(net))
+ return;
+
+ port = msg_origport(hdr);
+
+ /* Has the twin SYN message already arrived ? */
+ skb_queue_walk(defq, _skb) {
+ _hdr = buf_msg(_skb);
+ if (msg_orignode(_hdr) != node)
+ continue;
+ if (msg_origport(_hdr) != port)
+ continue;
+ match = true;
+ break;
+ }
+
+ if (!match) {
+ if (!msg_is_syn(hdr))
+ return;
+ __skb_dequeue(inputq);
+ __skb_queue_tail(defq, skb);
+ return;
+ }
+
+ /* Deliver non-SYN message from other link, otherwise queue it */
+ if (!msg_is_syn(hdr)) {
+ if (msg_is_rcast(hdr) != msg_is_rcast(_hdr))
+ return;
+ __skb_dequeue(inputq);
+ __skb_queue_tail(defq, skb);
+ return;
+ }
+
+ /* Queue non-SYN/SYN message from same link */
+ if (msg_is_rcast(hdr) == msg_is_rcast(_hdr)) {
+ __skb_dequeue(inputq);
+ __skb_queue_tail(defq, skb);
+ return;
+ }
+
+ /* Matching SYN messages => return the one with data, if any */
+ __skb_unlink(_skb, defq);
+ if (msg_data_sz(hdr)) {
+ kfree_skb(_skb);
+ } else {
+ __skb_dequeue(inputq);
+ kfree_skb(skb);
+ __skb_queue_tail(inputq, _skb);
+ }
+
+ /* Deliver subsequent non-SYN messages from same peer */
+ skb_queue_walk_safe(defq, _skb, tmp) {
+ _hdr = buf_msg(_skb);
+ if (msg_orignode(_hdr) != node)
+ continue;
+ if (msg_origport(_hdr) != port)
+ continue;
+ if (msg_is_syn(_hdr))
+ break;
+ __skb_unlink(_skb, defq);
+ __skb_queue_tail(inputq, _skb);
+ }
+}
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index 751530ab0c49..9e847d9617d3 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -48,6 +48,10 @@ extern const char tipc_bclink_name[];
#define TIPC_METHOD_EXPIRE msecs_to_jiffies(5000)
+#define BCLINK_MODE_BCAST 0x1
+#define BCLINK_MODE_RCAST 0x2
+#define BCLINK_MODE_SEL 0x4
+
struct tipc_nlist {
struct list_head list;
u32 self;
@@ -63,11 +67,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node);
/* Cookie to be used between socket and broadcast layer
* @rcast: replicast (instead of broadcast) was used at previous xmit
* @mandatory: broadcast/replicast indication was set by user
+ * @deferredq: defer queue to make message in order
* @expires: re-evaluate non-mandatory transmit method if we are past this
*/
struct tipc_mc_method {
bool rcast;
bool mandatory;
+ struct sk_buff_head deferredq;
unsigned long expires;
};
@@ -79,7 +85,7 @@ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_bcl);
void tipc_bcast_inc_bearer_dst_cnt(struct net *net, int bearer_id);
void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id);
int tipc_bcast_get_mtu(struct net *net);
-void tipc_bcast_disable_rcast(struct net *net);
+void tipc_bcast_toggle_rcast(struct net *net, bool supp);
int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts,
struct tipc_mc_method *method, struct tipc_nlist *dests,
u16 *cong_link_cnt);
@@ -92,6 +98,12 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg);
int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]);
int tipc_bclink_reset_stats(struct net *net);
+u32 tipc_bcast_get_broadcast_mode(struct net *net);
+u32 tipc_bcast_get_broadcast_ratio(struct net *net);
+
+void tipc_mcast_filter_msg(struct net *net, struct sk_buff_head *defq,
+ struct sk_buff_head *inputq);
+
static inline void tipc_bcast_lock(struct net *net)
{
spin_lock_bh(&tipc_net(net)->bclock);
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index d27f30a9a01d..d7ec26bd739d 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -44,6 +44,7 @@
#include "netlink.h"
#include "udp_media.h"
#include "trace.h"
+#include "crypto.h"
#define MAX_ADDR_STR 60
@@ -62,7 +63,7 @@ static struct tipc_bearer *bearer_get(struct net *net, int bearer_id)
{
struct tipc_net *tn = tipc_net(net);
- return rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
+ return rcu_dereference(tn->bearer_list[bearer_id]);
}
static void bearer_disable(struct net *net, struct tipc_bearer *b);
@@ -210,7 +211,7 @@ void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
+ b = rcu_dereference(tn->bearer_list[bearer_id]);
if (b)
tipc_disc_add_dest(b->disc);
rcu_read_unlock();
@@ -222,7 +223,7 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest)
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]);
+ b = rcu_dereference(tn->bearer_list[bearer_id]);
if (b)
tipc_disc_remove_dest(b->disc);
rcu_read_unlock();
@@ -315,6 +316,7 @@ static int tipc_enable_bearer(struct net *net, const char *name,
b->net_plane = bearer_id + 'A';
b->priority = prio;
test_and_set_bit_lock(0, &b->up);
+ refcount_set(&b->refcnt, 1);
res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
if (res) {
@@ -351,6 +353,17 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b)
return 0;
}
+bool tipc_bearer_hold(struct tipc_bearer *b)
+{
+ return (b && refcount_inc_not_zero(&b->refcnt));
+}
+
+void tipc_bearer_put(struct tipc_bearer *b)
+{
+ if (b && refcount_dec_and_test(&b->refcnt))
+ kfree_rcu(b, rcu);
+}
+
/**
* bearer_disable
*
@@ -369,7 +382,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b)
if (b->disc)
tipc_disc_delete(b->disc);
RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL);
- kfree_rcu(b, rcu);
+ tipc_bearer_put(b);
tipc_mon_delete(net, bearer_id);
}
@@ -389,6 +402,11 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
dev_put(dev);
return -EINVAL;
}
+ if (dev == net->loopback_dev) {
+ dev_put(dev);
+ pr_info("Enabling <%s> not permitted\n", b->name);
+ return -EINVAL;
+ }
/* Autoconfigure own node identity if needed */
if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) {
@@ -444,7 +462,7 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb,
struct net_device *dev;
int delta;
- dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr);
+ dev = (struct net_device *)rcu_dereference(b->media_ptr);
if (!dev)
return 0;
@@ -481,7 +499,7 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id)
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(tipc_net(net)->bearer_list[bearer_id]);
+ b = rcu_dereference(tipc_net(net)->bearer_list[bearer_id]);
if (b)
mtu = b->mtu;
rcu_read_unlock();
@@ -499,10 +517,15 @@ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id,
rcu_read_lock();
b = bearer_get(net, bearer_id);
- if (likely(b && (test_bit(0, &b->up) || msg_is_reset(hdr))))
- b->media->send_msg(net, skb, b, dest);
- else
+ if (likely(b && (test_bit(0, &b->up) || msg_is_reset(hdr)))) {
+#ifdef CONFIG_TIPC_CRYPTO
+ tipc_crypto_xmit(net, &skb, b, dest, NULL);
+ if (skb)
+#endif
+ b->media->send_msg(net, skb, b, dest);
+ } else {
kfree_skb(skb);
+ }
rcu_read_unlock();
}
@@ -510,7 +533,8 @@ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id,
*/
void tipc_bearer_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq,
- struct tipc_media_addr *dst)
+ struct tipc_media_addr *dst,
+ struct tipc_node *__dnode)
{
struct tipc_bearer *b;
struct sk_buff *skb, *tmp;
@@ -524,10 +548,15 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id,
__skb_queue_purge(xmitq);
skb_queue_walk_safe(xmitq, skb, tmp) {
__skb_dequeue(xmitq);
- if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb))))
- b->media->send_msg(net, skb, b, dst);
- else
+ if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb)))) {
+#ifdef CONFIG_TIPC_CRYPTO
+ tipc_crypto_xmit(net, &skb, b, dst, __dnode);
+ if (skb)
+#endif
+ b->media->send_msg(net, skb, b, dst);
+ } else {
kfree_skb(skb);
+ }
}
rcu_read_unlock();
}
@@ -538,6 +567,7 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq)
{
struct tipc_net *tn = tipc_net(net);
+ struct tipc_media_addr *dst;
int net_id = tn->net_id;
struct tipc_bearer *b;
struct sk_buff *skb, *tmp;
@@ -552,7 +582,12 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
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);
+ dst = &b->bcast_addr;
+#ifdef CONFIG_TIPC_CRYPTO
+ tipc_crypto_xmit(net, &skb, b, dst, NULL);
+ if (skb)
+#endif
+ b->media->send_msg(net, skb, b, dst);
}
rcu_read_unlock();
}
@@ -574,11 +609,12 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev,
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference_rtnl(dev->tipc_ptr) ?:
- rcu_dereference_rtnl(orig_dev->tipc_ptr);
+ b = rcu_dereference(dev->tipc_ptr) ?:
+ rcu_dereference(orig_dev->tipc_ptr);
if (likely(b && test_bit(0, &b->up) &&
(skb->pkt_type <= PACKET_MULTICAST))) {
skb_mark_not_on_list(skb);
+ TIPC_SKB_CB(skb)->flags = 0;
tipc_rcv(dev_net(b->pt.dev), skb, b);
rcu_read_unlock();
return NET_RX_SUCCESS;
@@ -674,6 +710,65 @@ void tipc_bearer_stop(struct net *net)
}
}
+void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts)
+{
+ struct net_device *dev = net->loopback_dev;
+ struct sk_buff *skb, *_skb;
+ int exp;
+
+ skb_queue_walk(pkts, _skb) {
+ skb = pskb_copy(_skb, GFP_ATOMIC);
+ if (!skb)
+ continue;
+
+ exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb));
+ if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ continue;
+ }
+
+ skb_reset_network_header(skb);
+ dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr,
+ dev->dev_addr, skb->len);
+ skb->dev = dev;
+ skb->pkt_type = PACKET_HOST;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->protocol = eth_type_trans(skb, dev);
+ netif_rx_ni(skb);
+ }
+}
+
+static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt, struct net_device *od)
+{
+ consume_skb(skb);
+ return NET_RX_SUCCESS;
+}
+
+int tipc_attach_loopback(struct net *net)
+{
+ struct net_device *dev = net->loopback_dev;
+ struct tipc_net *tn = tipc_net(net);
+
+ if (!dev)
+ return -ENODEV;
+
+ dev_hold(dev);
+ tn->loopback_pt.dev = dev;
+ tn->loopback_pt.type = htons(ETH_P_TIPC);
+ tn->loopback_pt.func = tipc_loopback_rcv_pkt;
+ dev_add_pack(&tn->loopback_pt);
+ return 0;
+}
+
+void tipc_detach_loopback(struct net *net)
+{
+ struct tipc_net *tn = tipc_net(net);
+
+ dev_remove_pack(&tn->loopback_pt);
+ dev_put(net->loopback_dev);
+}
+
/* Caller should hold rtnl_lock to protect the bearer */
static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
struct tipc_bearer *bearer, int nlflags)
@@ -687,14 +782,14 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_BEARER);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER);
if (!attrs)
goto msg_full;
if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name))
goto attr_msg_full;
- prop = nla_nest_start(msg->skb, TIPC_NLA_BEARER_PROP);
+ prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP);
if (!prop)
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority))
@@ -776,9 +871,9 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
- info->attrs[TIPC_NLA_BEARER],
- tipc_nl_bearer_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+ info->attrs[TIPC_NLA_BEARER],
+ tipc_nl_bearer_policy, info->extack);
if (err)
return err;
@@ -825,9 +920,9 @@ int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
- info->attrs[TIPC_NLA_BEARER],
- tipc_nl_bearer_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+ info->attrs[TIPC_NLA_BEARER],
+ tipc_nl_bearer_policy, info->extack);
if (err)
return err;
@@ -870,9 +965,9 @@ int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
- info->attrs[TIPC_NLA_BEARER],
- tipc_nl_bearer_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+ info->attrs[TIPC_NLA_BEARER],
+ tipc_nl_bearer_policy, info->extack);
if (err)
return err;
@@ -921,9 +1016,9 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
- info->attrs[TIPC_NLA_BEARER],
- tipc_nl_bearer_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+ info->attrs[TIPC_NLA_BEARER],
+ tipc_nl_bearer_policy, info->extack);
if (err)
return err;
@@ -964,9 +1059,9 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
- info->attrs[TIPC_NLA_BEARER],
- tipc_nl_bearer_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+ info->attrs[TIPC_NLA_BEARER],
+ tipc_nl_bearer_policy, info->extack);
if (err)
return err;
@@ -1033,14 +1128,14 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg,
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_MEDIA);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA);
if (!attrs)
goto msg_full;
if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name))
goto attr_msg_full;
- prop = nla_nest_start(msg->skb, TIPC_NLA_MEDIA_PROP);
+ prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP);
if (!prop)
goto prop_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority))
@@ -1107,9 +1202,9 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_MEDIA])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
- info->attrs[TIPC_NLA_MEDIA],
- tipc_nl_media_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX,
+ info->attrs[TIPC_NLA_MEDIA],
+ tipc_nl_media_policy, info->extack);
if (err)
return err;
@@ -1155,9 +1250,9 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_MEDIA])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
- info->attrs[TIPC_NLA_MEDIA],
- tipc_nl_media_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX,
+ info->attrs[TIPC_NLA_MEDIA],
+ tipc_nl_media_policy, info->extack);
if (!attrs[TIPC_NLA_MEDIA_NAME])
return -EINVAL;
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 7f4c569594a5..d0c79cc6c0c2 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -165,6 +165,7 @@ struct tipc_bearer {
struct tipc_discoverer *disc;
char net_plane;
unsigned long up;
+ refcount_t refcnt;
};
struct tipc_bearer_names {
@@ -210,6 +211,8 @@ int tipc_media_set_window(const char *name, u32 new_value);
int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
struct nlattr *attrs[]);
+bool tipc_bearer_hold(struct tipc_bearer *b);
+void tipc_bearer_put(struct tipc_bearer *b);
void tipc_disable_l2_media(struct tipc_bearer *b);
int tipc_l2_send_msg(struct net *net, struct sk_buff *buf,
struct tipc_bearer *b, struct tipc_media_addr *dest);
@@ -229,9 +232,20 @@ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id,
struct tipc_media_addr *dest);
void tipc_bearer_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq,
- struct tipc_media_addr *dst);
+ struct tipc_media_addr *dst,
+ struct tipc_node *__dnode);
void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
struct sk_buff_head *xmitq);
+void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts);
+int tipc_attach_loopback(struct net *net);
+void tipc_detach_loopback(struct net *net);
+
+static inline void tipc_loopback_trace(struct net *net,
+ struct sk_buff_head *pkts)
+{
+ if (unlikely(dev_nit_active(net->loopback_dev)))
+ tipc_clone_to_loopback(net, pkts);
+}
/* check if device MTU is too low for tipc headers */
static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve)
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5b38f5164281..7532a00ac73d 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -34,8 +34,6 @@
* POSSIBILITY OF SUCH DAMAGE.
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
#include "core.h"
#include "name_table.h"
#include "subscr.h"
@@ -43,6 +41,8 @@
#include "net.h"
#include "socket.h"
#include "bcast.h"
+#include "node.h"
+#include "crypto.h"
#include <linux/module.h>
@@ -59,6 +59,7 @@ static int __net_init tipc_init_net(struct net *net)
tn->node_addr = 0;
tn->trial_addr = 0;
tn->addr_trial_end = 0;
+ tn->capabilities = TIPC_NODE_CAPABILITIES;
memset(tn->node_id, 0, sizeof(tn->node_id));
memset(tn->node_id_string, 0, sizeof(tn->node_id_string));
tn->mon_threshold = TIPC_DEF_MON_THRESHOLD;
@@ -66,6 +67,11 @@ static int __net_init tipc_init_net(struct net *net)
INIT_LIST_HEAD(&tn->node_list);
spin_lock_init(&tn->node_list_lock);
+#ifdef CONFIG_TIPC_CRYPTO
+ err = tipc_crypto_start(&tn->crypto_tx, net, NULL);
+ if (err)
+ goto out_crypto;
+#endif
err = tipc_sk_rht_init(net);
if (err)
goto out_sk_rht;
@@ -75,35 +81,51 @@ static int __net_init tipc_init_net(struct net *net)
goto out_nametbl;
INIT_LIST_HEAD(&tn->dist_queue);
- err = tipc_topsrv_start(net);
- if (err)
- goto out_subscr;
err = tipc_bcast_init(net);
if (err)
goto out_bclink;
+ err = tipc_attach_loopback(net);
+ if (err)
+ goto out_bclink;
+
return 0;
out_bclink:
- tipc_bcast_stop(net);
-out_subscr:
tipc_nametbl_stop(net);
out_nametbl:
tipc_sk_rht_destroy(net);
out_sk_rht:
+
+#ifdef CONFIG_TIPC_CRYPTO
+ tipc_crypto_stop(&tn->crypto_tx);
+out_crypto:
+#endif
return err;
}
static void __net_exit tipc_exit_net(struct net *net)
{
- tipc_topsrv_stop(net);
+ tipc_detach_loopback(net);
tipc_net_stop(net);
tipc_bcast_stop(net);
tipc_nametbl_stop(net);
tipc_sk_rht_destroy(net);
+#ifdef CONFIG_TIPC_CRYPTO
+ tipc_crypto_stop(&tipc_net(net)->crypto_tx);
+#endif
}
+static void __net_exit tipc_pernet_pre_exit(struct net *net)
+{
+ tipc_node_pre_cleanup_net(net);
+}
+
+static struct pernet_operations tipc_pernet_pre_exit_ops = {
+ .pre_exit = tipc_pernet_pre_exit,
+};
+
static struct pernet_operations tipc_net_ops = {
.init = tipc_init_net,
.exit = tipc_exit_net,
@@ -111,6 +133,11 @@ static struct pernet_operations tipc_net_ops = {
.size = sizeof(struct tipc_net),
};
+static struct pernet_operations tipc_topsrv_net_ops = {
+ .init = tipc_topsrv_init_net,
+ .exit = tipc_topsrv_exit_net,
+};
+
static int __init tipc_init(void)
{
int err;
@@ -129,17 +156,25 @@ static int __init tipc_init(void)
if (err)
goto out_netlink_compat;
+ err = tipc_register_sysctl();
+ if (err)
+ goto out_sysctl;
+
+ err = register_pernet_device(&tipc_net_ops);
+ if (err)
+ goto out_pernet;
+
err = tipc_socket_init();
if (err)
goto out_socket;
- err = tipc_register_sysctl();
+ err = register_pernet_device(&tipc_topsrv_net_ops);
if (err)
- goto out_sysctl;
+ goto out_pernet_topsrv;
- err = register_pernet_subsys(&tipc_net_ops);
+ err = register_pernet_subsys(&tipc_pernet_pre_exit_ops);
if (err)
- goto out_pernet;
+ goto out_register_pernet_subsys;
err = tipc_bearer_setup();
if (err)
@@ -148,12 +183,16 @@ static int __init tipc_init(void)
pr_info("Started in single node mode\n");
return 0;
out_bearer:
- unregister_pernet_subsys(&tipc_net_ops);
+ unregister_pernet_subsys(&tipc_pernet_pre_exit_ops);
+out_register_pernet_subsys:
+ unregister_pernet_device(&tipc_topsrv_net_ops);
+out_pernet_topsrv:
+ tipc_socket_stop();
+out_socket:
+ unregister_pernet_device(&tipc_net_ops);
out_pernet:
tipc_unregister_sysctl();
out_sysctl:
- tipc_socket_stop();
-out_socket:
tipc_netlink_compat_stop();
out_netlink_compat:
tipc_netlink_stop();
@@ -165,10 +204,12 @@ out_netlink:
static void __exit tipc_exit(void)
{
tipc_bearer_cleanup();
- unregister_pernet_subsys(&tipc_net_ops);
+ unregister_pernet_subsys(&tipc_pernet_pre_exit_ops);
+ unregister_pernet_device(&tipc_topsrv_net_ops);
+ tipc_socket_stop();
+ unregister_pernet_device(&tipc_net_ops);
tipc_netlink_stop();
tipc_netlink_compat_stop();
- tipc_socket_stop();
tipc_unregister_sysctl();
pr_info("Deactivated\n");
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 8020a6c360ff..631d83c9705f 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -59,6 +59,13 @@
#include <net/netns/generic.h>
#include <linux/rhashtable.h>
#include <net/genetlink.h>
+#include <net/netns/hash.h>
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
struct tipc_node;
struct tipc_bearer;
@@ -67,6 +74,9 @@ struct tipc_link;
struct tipc_name_table;
struct tipc_topsrv;
struct tipc_monitor;
+#ifdef CONFIG_TIPC_CRYPTO
+struct tipc_crypto;
+#endif
#define TIPC_MOD_VER "2.0.0"
@@ -122,6 +132,17 @@ struct tipc_net {
/* Topology subscription server */
struct tipc_topsrv *topsrv;
atomic_t subscription_count;
+
+ /* Cluster capabilities */
+ u16 capabilities;
+
+ /* Tracing of node internal messages */
+ struct packet_type loopback_pt;
+
+#ifdef CONFIG_TIPC_CRYPTO
+ /* TX crypto handler */
+ struct tipc_crypto *crypto_tx;
+#endif
};
static inline struct tipc_net *tipc_net(struct net *net)
@@ -179,6 +200,11 @@ static inline int in_range(u16 val, u16 min, u16 max)
return !less(val, min) && !more(val, max);
}
+static inline u32 tipc_net_hash_mixes(struct net *net, int tn_rand)
+{
+ return net_hash_mix(&init_net) ^ net_hash_mix(net) ^ tn_rand;
+}
+
#ifdef CONFIG_SYSCTL
int tipc_register_sysctl(void);
void tipc_unregister_sysctl(void);
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
new file mode 100644
index 000000000000..990a872cec46
--- /dev/null
+++ b/net/tipc/crypto.c
@@ -0,0 +1,1986 @@
+// SPDX-License-Identifier: GPL-2.0
+/**
+ * net/tipc/crypto.c: TIPC crypto for key handling & packet en/decryption
+ *
+ * Copyright (c) 2019, 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 <crypto/aead.h>
+#include <crypto/aes.h>
+#include "crypto.h"
+
+#define TIPC_TX_PROBE_LIM msecs_to_jiffies(1000) /* > 1s */
+#define TIPC_TX_LASTING_LIM msecs_to_jiffies(120000) /* 2 mins */
+#define TIPC_RX_ACTIVE_LIM msecs_to_jiffies(3000) /* 3s */
+#define TIPC_RX_PASSIVE_LIM msecs_to_jiffies(180000) /* 3 mins */
+#define TIPC_MAX_TFMS_DEF 10
+#define TIPC_MAX_TFMS_LIM 1000
+
+/**
+ * TIPC Key ids
+ */
+enum {
+ KEY_UNUSED = 0,
+ KEY_MIN,
+ KEY_1 = KEY_MIN,
+ KEY_2,
+ KEY_3,
+ KEY_MAX = KEY_3,
+};
+
+/**
+ * TIPC Crypto statistics
+ */
+enum {
+ STAT_OK,
+ STAT_NOK,
+ STAT_ASYNC,
+ STAT_ASYNC_OK,
+ STAT_ASYNC_NOK,
+ STAT_BADKEYS, /* tx only */
+ STAT_BADMSGS = STAT_BADKEYS, /* rx only */
+ STAT_NOKEYS,
+ STAT_SWITCHES,
+
+ MAX_STATS,
+};
+
+/* TIPC crypto statistics' header */
+static const char *hstats[MAX_STATS] = {"ok", "nok", "async", "async_ok",
+ "async_nok", "badmsgs", "nokeys",
+ "switches"};
+
+/* Max TFMs number per key */
+int sysctl_tipc_max_tfms __read_mostly = TIPC_MAX_TFMS_DEF;
+
+/**
+ * struct tipc_key - TIPC keys' status indicator
+ *
+ * 7 6 5 4 3 2 1 0
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ * key: | (reserved)|passive idx| active idx|pending idx|
+ * +-----+-----+-----+-----+-----+-----+-----+-----+
+ */
+struct tipc_key {
+#define KEY_BITS (2)
+#define KEY_MASK ((1 << KEY_BITS) - 1)
+ union {
+ struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ u8 pending:2,
+ active:2,
+ passive:2, /* rx only */
+ reserved:2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ u8 reserved:2,
+ passive:2, /* rx only */
+ active:2,
+ pending:2;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ } __packed;
+ u8 keys;
+ };
+};
+
+/**
+ * struct tipc_tfm - TIPC TFM structure to form a list of TFMs
+ */
+struct tipc_tfm {
+ struct crypto_aead *tfm;
+ struct list_head list;
+};
+
+/**
+ * struct tipc_aead - TIPC AEAD key structure
+ * @tfm_entry: per-cpu pointer to one entry in TFM list
+ * @crypto: TIPC crypto owns this key
+ * @cloned: reference to the source key in case cloning
+ * @users: the number of the key users (TX/RX)
+ * @salt: the key's SALT value
+ * @authsize: authentication tag size (max = 16)
+ * @mode: crypto mode is applied to the key
+ * @hint[]: a hint for user key
+ * @rcu: struct rcu_head
+ * @seqno: the key seqno (cluster scope)
+ * @refcnt: the key reference counter
+ */
+struct tipc_aead {
+#define TIPC_AEAD_HINT_LEN (5)
+ struct tipc_tfm * __percpu *tfm_entry;
+ struct tipc_crypto *crypto;
+ struct tipc_aead *cloned;
+ atomic_t users;
+ u32 salt;
+ u8 authsize;
+ u8 mode;
+ char hint[TIPC_AEAD_HINT_LEN + 1];
+ struct rcu_head rcu;
+
+ atomic64_t seqno ____cacheline_aligned;
+ refcount_t refcnt ____cacheline_aligned;
+
+} ____cacheline_aligned;
+
+/**
+ * struct tipc_crypto_stats - TIPC Crypto statistics
+ */
+struct tipc_crypto_stats {
+ unsigned int stat[MAX_STATS];
+};
+
+/**
+ * struct tipc_crypto - TIPC TX/RX crypto structure
+ * @net: struct net
+ * @node: TIPC node (RX)
+ * @aead: array of pointers to AEAD keys for encryption/decryption
+ * @peer_rx_active: replicated peer RX active key index
+ * @key: the key states
+ * @working: the crypto is working or not
+ * @stats: the crypto statistics
+ * @sndnxt: the per-peer sndnxt (TX)
+ * @timer1: general timer 1 (jiffies)
+ * @timer2: general timer 1 (jiffies)
+ * @lock: tipc_key lock
+ */
+struct tipc_crypto {
+ struct net *net;
+ struct tipc_node *node;
+ struct tipc_aead __rcu *aead[KEY_MAX + 1]; /* key[0] is UNUSED */
+ atomic_t peer_rx_active;
+ struct tipc_key key;
+ u8 working:1;
+ struct tipc_crypto_stats __percpu *stats;
+
+ atomic64_t sndnxt ____cacheline_aligned;
+ unsigned long timer1;
+ unsigned long timer2;
+ spinlock_t lock; /* crypto lock */
+
+} ____cacheline_aligned;
+
+/* struct tipc_crypto_tx_ctx - TX context for callbacks */
+struct tipc_crypto_tx_ctx {
+ struct tipc_aead *aead;
+ struct tipc_bearer *bearer;
+ struct tipc_media_addr dst;
+};
+
+/* struct tipc_crypto_rx_ctx - RX context for callbacks */
+struct tipc_crypto_rx_ctx {
+ struct tipc_aead *aead;
+ struct tipc_bearer *bearer;
+};
+
+static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead);
+static inline void tipc_aead_put(struct tipc_aead *aead);
+static void tipc_aead_free(struct rcu_head *rp);
+static int tipc_aead_users(struct tipc_aead __rcu *aead);
+static void tipc_aead_users_inc(struct tipc_aead __rcu *aead, int lim);
+static void tipc_aead_users_dec(struct tipc_aead __rcu *aead, int lim);
+static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val);
+static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead);
+static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey,
+ u8 mode);
+static int tipc_aead_clone(struct tipc_aead **dst, struct tipc_aead *src);
+static void *tipc_aead_mem_alloc(struct crypto_aead *tfm,
+ unsigned int crypto_ctx_size,
+ u8 **iv, struct aead_request **req,
+ struct scatterlist **sg, int nsg);
+static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
+ struct tipc_bearer *b,
+ struct tipc_media_addr *dst,
+ struct tipc_node *__dnode);
+static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err);
+static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
+ struct sk_buff *skb, struct tipc_bearer *b);
+static void tipc_aead_decrypt_done(struct crypto_async_request *base, int err);
+static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr);
+static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead,
+ u8 tx_key, struct sk_buff *skb,
+ struct tipc_crypto *__rx);
+static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
+ u8 new_passive,
+ u8 new_active,
+ u8 new_pending);
+static int tipc_crypto_key_attach(struct tipc_crypto *c,
+ struct tipc_aead *aead, u8 pos);
+static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending);
+static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
+ struct tipc_crypto *rx,
+ struct sk_buff *skb);
+static void tipc_crypto_key_synch(struct tipc_crypto *rx, u8 new_rx_active,
+ struct tipc_msg *hdr);
+static int tipc_crypto_key_revoke(struct net *net, u8 tx_key);
+static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
+ struct tipc_bearer *b,
+ struct sk_buff **skb, int err);
+static void tipc_crypto_do_cmd(struct net *net, int cmd);
+static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf);
+#ifdef TIPC_CRYPTO_DEBUG
+static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
+ char *buf);
+#endif
+
+#define key_next(cur) ((cur) % KEY_MAX + 1)
+
+#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), \
+ lockdep_is_held(lock)); \
+ rcu_assign_pointer((rcu_ptr), (ptr)); \
+ tipc_aead_put(__tmp); \
+} while (0)
+
+#define tipc_crypto_key_detach(rcu_ptr, lock) \
+ tipc_aead_rcu_replace((rcu_ptr), NULL, lock)
+
+/**
+ * tipc_aead_key_validate - Validate a AEAD user key
+ */
+int tipc_aead_key_validate(struct tipc_aead_key *ukey)
+{
+ int keylen;
+
+ /* Check if algorithm exists */
+ if (unlikely(!crypto_has_alg(ukey->alg_name, 0, 0))) {
+ pr_info("Not found cipher: \"%s\"!\n", ukey->alg_name);
+ return -ENODEV;
+ }
+
+ /* Currently, we only support the "gcm(aes)" cipher algorithm */
+ if (strcmp(ukey->alg_name, "gcm(aes)"))
+ return -ENOTSUPP;
+
+ /* Check if key size is correct */
+ keylen = ukey->keylen - TIPC_AES_GCM_SALT_SIZE;
+ if (unlikely(keylen != TIPC_AES_GCM_KEY_SIZE_128 &&
+ keylen != TIPC_AES_GCM_KEY_SIZE_192 &&
+ keylen != TIPC_AES_GCM_KEY_SIZE_256))
+ return -EINVAL;
+
+ return 0;
+}
+
+static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead)
+{
+ struct tipc_aead *tmp;
+
+ rcu_read_lock();
+ tmp = rcu_dereference(aead);
+ if (unlikely(!tmp || !refcount_inc_not_zero(&tmp->refcnt)))
+ tmp = NULL;
+ rcu_read_unlock();
+
+ return tmp;
+}
+
+static inline void tipc_aead_put(struct tipc_aead *aead)
+{
+ if (aead && refcount_dec_and_test(&aead->refcnt))
+ call_rcu(&aead->rcu, tipc_aead_free);
+}
+
+/**
+ * tipc_aead_free - Release AEAD key incl. all the TFMs in the list
+ * @rp: rcu head pointer
+ */
+static void tipc_aead_free(struct rcu_head *rp)
+{
+ struct tipc_aead *aead = container_of(rp, struct tipc_aead, rcu);
+ struct tipc_tfm *tfm_entry, *head, *tmp;
+
+ if (aead->cloned) {
+ tipc_aead_put(aead->cloned);
+ } else {
+ head = *this_cpu_ptr(aead->tfm_entry);
+ list_for_each_entry_safe(tfm_entry, tmp, &head->list, list) {
+ crypto_free_aead(tfm_entry->tfm);
+ list_del(&tfm_entry->list);
+ kfree(tfm_entry);
+ }
+ /* Free the head */
+ crypto_free_aead(head->tfm);
+ list_del(&head->list);
+ kfree(head);
+ }
+ free_percpu(aead->tfm_entry);
+ kfree(aead);
+}
+
+static int tipc_aead_users(struct tipc_aead __rcu *aead)
+{
+ struct tipc_aead *tmp;
+ int users = 0;
+
+ rcu_read_lock();
+ tmp = rcu_dereference(aead);
+ if (tmp)
+ users = atomic_read(&tmp->users);
+ rcu_read_unlock();
+
+ return users;
+}
+
+static void tipc_aead_users_inc(struct tipc_aead __rcu *aead, int lim)
+{
+ struct tipc_aead *tmp;
+
+ rcu_read_lock();
+ tmp = rcu_dereference(aead);
+ if (tmp)
+ atomic_add_unless(&tmp->users, 1, lim);
+ rcu_read_unlock();
+}
+
+static void tipc_aead_users_dec(struct tipc_aead __rcu *aead, int lim)
+{
+ struct tipc_aead *tmp;
+
+ rcu_read_lock();
+ tmp = rcu_dereference(aead);
+ if (tmp)
+ atomic_add_unless(&rcu_dereference(aead)->users, -1, lim);
+ rcu_read_unlock();
+}
+
+static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val)
+{
+ struct tipc_aead *tmp;
+ int cur;
+
+ rcu_read_lock();
+ tmp = rcu_dereference(aead);
+ if (tmp) {
+ do {
+ cur = atomic_read(&tmp->users);
+ if (cur == val)
+ break;
+ } while (atomic_cmpxchg(&tmp->users, cur, val) != cur);
+ }
+ rcu_read_unlock();
+}
+
+/**
+ * tipc_aead_tfm_next - Move TFM entry to the next one in list and return it
+ */
+static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead)
+{
+ struct tipc_tfm **tfm_entry = this_cpu_ptr(aead->tfm_entry);
+
+ *tfm_entry = list_next_entry(*tfm_entry, list);
+ return (*tfm_entry)->tfm;
+}
+
+/**
+ * tipc_aead_init - Initiate TIPC AEAD
+ * @aead: returned new TIPC AEAD key handle pointer
+ * @ukey: pointer to user key data
+ * @mode: the key mode
+ *
+ * Allocate a (list of) new cipher transformation (TFM) with the specific user
+ * key data if valid. The number of the allocated TFMs can be set via the sysfs
+ * "net/tipc/max_tfms" first.
+ * Also, all the other AEAD data are also initialized.
+ *
+ * Return: 0 if the initiation is successful, otherwise: < 0
+ */
+static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey,
+ u8 mode)
+{
+ struct tipc_tfm *tfm_entry, *head;
+ struct crypto_aead *tfm;
+ struct tipc_aead *tmp;
+ int keylen, err, cpu;
+ int tfm_cnt = 0;
+
+ if (unlikely(*aead))
+ return -EEXIST;
+
+ /* Allocate a new AEAD */
+ tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
+ if (unlikely(!tmp))
+ return -ENOMEM;
+
+ /* The key consists of two parts: [AES-KEY][SALT] */
+ keylen = ukey->keylen - TIPC_AES_GCM_SALT_SIZE;
+
+ /* Allocate per-cpu TFM entry pointer */
+ tmp->tfm_entry = alloc_percpu(struct tipc_tfm *);
+ if (!tmp->tfm_entry) {
+ kzfree(tmp);
+ return -ENOMEM;
+ }
+
+ /* Make a list of TFMs with the user key data */
+ do {
+ tfm = crypto_alloc_aead(ukey->alg_name, 0, 0);
+ if (IS_ERR(tfm)) {
+ err = PTR_ERR(tfm);
+ break;
+ }
+
+ if (unlikely(!tfm_cnt &&
+ crypto_aead_ivsize(tfm) != TIPC_AES_GCM_IV_SIZE)) {
+ crypto_free_aead(tfm);
+ err = -ENOTSUPP;
+ break;
+ }
+
+ err = crypto_aead_setauthsize(tfm, TIPC_AES_GCM_TAG_SIZE);
+ err |= crypto_aead_setkey(tfm, ukey->key, keylen);
+ if (unlikely(err)) {
+ crypto_free_aead(tfm);
+ break;
+ }
+
+ tfm_entry = kmalloc(sizeof(*tfm_entry), GFP_KERNEL);
+ if (unlikely(!tfm_entry)) {
+ crypto_free_aead(tfm);
+ err = -ENOMEM;
+ break;
+ }
+ INIT_LIST_HEAD(&tfm_entry->list);
+ tfm_entry->tfm = tfm;
+
+ /* First entry? */
+ if (!tfm_cnt) {
+ head = tfm_entry;
+ for_each_possible_cpu(cpu) {
+ *per_cpu_ptr(tmp->tfm_entry, cpu) = head;
+ }
+ } else {
+ list_add_tail(&tfm_entry->list, &head->list);
+ }
+
+ } while (++tfm_cnt < sysctl_tipc_max_tfms);
+
+ /* Not any TFM is allocated? */
+ if (!tfm_cnt) {
+ free_percpu(tmp->tfm_entry);
+ kzfree(tmp);
+ return err;
+ }
+
+ /* Copy some chars from the user key as a hint */
+ memcpy(tmp->hint, ukey->key, TIPC_AEAD_HINT_LEN);
+ tmp->hint[TIPC_AEAD_HINT_LEN] = '\0';
+
+ /* Initialize the other data */
+ tmp->mode = mode;
+ tmp->cloned = NULL;
+ tmp->authsize = TIPC_AES_GCM_TAG_SIZE;
+ memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE);
+ atomic_set(&tmp->users, 0);
+ atomic64_set(&tmp->seqno, 0);
+ refcount_set(&tmp->refcnt, 1);
+
+ *aead = tmp;
+ return 0;
+}
+
+/**
+ * tipc_aead_clone - Clone a TIPC AEAD key
+ * @dst: dest key for the cloning
+ * @src: source key to clone from
+ *
+ * Make a "copy" of the source AEAD key data to the dest, the TFMs list is
+ * common for the keys.
+ * A reference to the source is hold in the "cloned" pointer for the later
+ * freeing purposes.
+ *
+ * Note: this must be done in cluster-key mode only!
+ * Return: 0 in case of success, otherwise < 0
+ */
+static int tipc_aead_clone(struct tipc_aead **dst, struct tipc_aead *src)
+{
+ struct tipc_aead *aead;
+ int cpu;
+
+ if (!src)
+ return -ENOKEY;
+
+ if (src->mode != CLUSTER_KEY)
+ return -EINVAL;
+
+ if (unlikely(*dst))
+ return -EEXIST;
+
+ aead = kzalloc(sizeof(*aead), GFP_ATOMIC);
+ if (unlikely(!aead))
+ return -ENOMEM;
+
+ aead->tfm_entry = alloc_percpu_gfp(struct tipc_tfm *, GFP_ATOMIC);
+ if (unlikely(!aead->tfm_entry)) {
+ kzfree(aead);
+ return -ENOMEM;
+ }
+
+ for_each_possible_cpu(cpu) {
+ *per_cpu_ptr(aead->tfm_entry, cpu) =
+ *per_cpu_ptr(src->tfm_entry, cpu);
+ }
+
+ memcpy(aead->hint, src->hint, sizeof(src->hint));
+ aead->mode = src->mode;
+ aead->salt = src->salt;
+ aead->authsize = src->authsize;
+ atomic_set(&aead->users, 0);
+ atomic64_set(&aead->seqno, 0);
+ refcount_set(&aead->refcnt, 1);
+
+ WARN_ON(!refcount_inc_not_zero(&src->refcnt));
+ aead->cloned = src;
+
+ *dst = aead;
+ return 0;
+}
+
+/**
+ * tipc_aead_mem_alloc - Allocate memory for AEAD request operations
+ * @tfm: cipher handle to be registered with the request
+ * @crypto_ctx_size: size of crypto context for callback
+ * @iv: returned pointer to IV data
+ * @req: returned pointer to AEAD request data
+ * @sg: returned pointer to SG lists
+ * @nsg: number of SG lists to be allocated
+ *
+ * Allocate memory to store the crypto context data, AEAD request, IV and SG
+ * lists, the memory layout is as follows:
+ * crypto_ctx || iv || aead_req || sg[]
+ *
+ * Return: the pointer to the memory areas in case of success, otherwise NULL
+ */
+static void *tipc_aead_mem_alloc(struct crypto_aead *tfm,
+ unsigned int crypto_ctx_size,
+ u8 **iv, struct aead_request **req,
+ struct scatterlist **sg, int nsg)
+{
+ unsigned int iv_size, req_size;
+ unsigned int len;
+ u8 *mem;
+
+ iv_size = crypto_aead_ivsize(tfm);
+ req_size = sizeof(**req) + crypto_aead_reqsize(tfm);
+
+ len = crypto_ctx_size;
+ len += iv_size;
+ len += crypto_aead_alignmask(tfm) & ~(crypto_tfm_ctx_alignment() - 1);
+ len = ALIGN(len, crypto_tfm_ctx_alignment());
+ len += req_size;
+ len = ALIGN(len, __alignof__(struct scatterlist));
+ len += nsg * sizeof(**sg);
+
+ mem = kmalloc(len, GFP_ATOMIC);
+ if (!mem)
+ return NULL;
+
+ *iv = (u8 *)PTR_ALIGN(mem + crypto_ctx_size,
+ crypto_aead_alignmask(tfm) + 1);
+ *req = (struct aead_request *)PTR_ALIGN(*iv + iv_size,
+ crypto_tfm_ctx_alignment());
+ *sg = (struct scatterlist *)PTR_ALIGN((u8 *)*req + req_size,
+ __alignof__(struct scatterlist));
+
+ return (void *)mem;
+}
+
+/**
+ * tipc_aead_encrypt - Encrypt a message
+ * @aead: TIPC AEAD key for the message encryption
+ * @skb: the input/output skb
+ * @b: TIPC bearer where the message will be delivered after the encryption
+ * @dst: the destination media address
+ * @__dnode: TIPC dest node if "known"
+ *
+ * Return:
+ * 0 : if the encryption has completed
+ * -EINPROGRESS/-EBUSY : if a callback will be performed
+ * < 0 : the encryption has failed
+ */
+static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
+ struct tipc_bearer *b,
+ struct tipc_media_addr *dst,
+ struct tipc_node *__dnode)
+{
+ struct crypto_aead *tfm = tipc_aead_tfm_next(aead);
+ struct tipc_crypto_tx_ctx *tx_ctx;
+ struct aead_request *req;
+ struct sk_buff *trailer;
+ struct scatterlist *sg;
+ struct tipc_ehdr *ehdr;
+ int ehsz, len, tailen, nsg, rc;
+ void *ctx;
+ u32 salt;
+ u8 *iv;
+
+ /* Make sure message len at least 4-byte aligned */
+ len = ALIGN(skb->len, 4);
+ tailen = len - skb->len + aead->authsize;
+
+ /* Expand skb tail for authentication tag:
+ * As for simplicity, we'd have made sure skb having enough tailroom
+ * for authentication tag @skb allocation. Even when skb is nonlinear
+ * but there is no frag_list, it should be still fine!
+ * Otherwise, we must cow it to be a writable buffer with the tailroom.
+ */
+#ifdef TIPC_CRYPTO_DEBUG
+ SKB_LINEAR_ASSERT(skb);
+ if (tailen > skb_tailroom(skb)) {
+ pr_warn("TX: skb tailroom is not enough: %d, requires: %d\n",
+ skb_tailroom(skb), tailen);
+ }
+#endif
+
+ if (unlikely(!skb_cloned(skb) && tailen <= skb_tailroom(skb))) {
+ nsg = 1;
+ trailer = skb;
+ } else {
+ /* TODO: We could avoid skb_cow_data() if skb has no frag_list
+ * e.g. by skb_fill_page_desc() to add another page to the skb
+ * with the wanted tailen... However, page skbs look not often,
+ * so take it easy now!
+ * Cloned skbs e.g. from link_xmit() seems no choice though :(
+ */
+ nsg = skb_cow_data(skb, tailen, &trailer);
+ if (unlikely(nsg < 0)) {
+ pr_err("TX: skb_cow_data() returned %d\n", nsg);
+ return nsg;
+ }
+ }
+
+ pskb_put(skb, trailer, tailen);
+
+ /* Allocate memory for the AEAD operation */
+ ctx = tipc_aead_mem_alloc(tfm, sizeof(*tx_ctx), &iv, &req, &sg, nsg);
+ if (unlikely(!ctx))
+ return -ENOMEM;
+ TIPC_SKB_CB(skb)->crypto_ctx = ctx;
+
+ /* Map skb to the sg lists */
+ sg_init_table(sg, nsg);
+ rc = skb_to_sgvec(skb, sg, 0, skb->len);
+ if (unlikely(rc < 0)) {
+ pr_err("TX: skb_to_sgvec() returned %d, nsg %d!\n", rc, nsg);
+ goto exit;
+ }
+
+ /* Prepare IV: [SALT (4 octets)][SEQNO (8 octets)]
+ * In case we're in cluster-key mode, SALT is varied by xor-ing with
+ * the source address (or w0 of id), otherwise with the dest address
+ * if dest is known.
+ */
+ ehdr = (struct tipc_ehdr *)skb->data;
+ salt = aead->salt;
+ if (aead->mode == CLUSTER_KEY)
+ salt ^= ehdr->addr; /* __be32 */
+ else if (__dnode)
+ salt ^= tipc_node_get_addr(__dnode);
+ memcpy(iv, &salt, 4);
+ memcpy(iv + 4, (u8 *)&ehdr->seqno, 8);
+
+ /* Prepare request */
+ ehsz = tipc_ehdr_size(ehdr);
+ aead_request_set_tfm(req, tfm);
+ aead_request_set_ad(req, ehsz);
+ aead_request_set_crypt(req, sg, sg, len - ehsz, iv);
+
+ /* Set callback function & data */
+ aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ tipc_aead_encrypt_done, skb);
+ tx_ctx = (struct tipc_crypto_tx_ctx *)ctx;
+ tx_ctx->aead = aead;
+ tx_ctx->bearer = b;
+ memcpy(&tx_ctx->dst, dst, sizeof(*dst));
+
+ /* Hold bearer */
+ if (unlikely(!tipc_bearer_hold(b))) {
+ rc = -ENODEV;
+ goto exit;
+ }
+
+ /* Now, do encrypt */
+ rc = crypto_aead_encrypt(req);
+ if (rc == -EINPROGRESS || rc == -EBUSY)
+ return rc;
+
+ tipc_bearer_put(b);
+
+exit:
+ kfree(ctx);
+ TIPC_SKB_CB(skb)->crypto_ctx = NULL;
+ return rc;
+}
+
+static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err)
+{
+ struct sk_buff *skb = base->data;
+ struct tipc_crypto_tx_ctx *tx_ctx = TIPC_SKB_CB(skb)->crypto_ctx;
+ struct tipc_bearer *b = tx_ctx->bearer;
+ struct tipc_aead *aead = tx_ctx->aead;
+ struct tipc_crypto *tx = aead->crypto;
+ struct net *net = tx->net;
+
+ switch (err) {
+ case 0:
+ this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]);
+ if (likely(test_bit(0, &b->up)))
+ b->media->send_msg(net, skb, b, &tx_ctx->dst);
+ else
+ kfree_skb(skb);
+ break;
+ case -EINPROGRESS:
+ return;
+ default:
+ this_cpu_inc(tx->stats->stat[STAT_ASYNC_NOK]);
+ kfree_skb(skb);
+ break;
+ }
+
+ kfree(tx_ctx);
+ tipc_bearer_put(b);
+ tipc_aead_put(aead);
+}
+
+/**
+ * tipc_aead_decrypt - Decrypt an encrypted message
+ * @net: struct net
+ * @aead: TIPC AEAD for the message decryption
+ * @skb: the input/output skb
+ * @b: TIPC bearer where the message has been received
+ *
+ * Return:
+ * 0 : if the decryption has completed
+ * -EINPROGRESS/-EBUSY : if a callback will be performed
+ * < 0 : the decryption has failed
+ */
+static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
+ struct sk_buff *skb, struct tipc_bearer *b)
+{
+ struct tipc_crypto_rx_ctx *rx_ctx;
+ struct aead_request *req;
+ struct crypto_aead *tfm;
+ struct sk_buff *unused;
+ struct scatterlist *sg;
+ struct tipc_ehdr *ehdr;
+ int ehsz, nsg, rc;
+ void *ctx;
+ u32 salt;
+ u8 *iv;
+
+ if (unlikely(!aead))
+ return -ENOKEY;
+
+ /* Cow skb data if needed */
+ if (likely(!skb_cloned(skb) &&
+ (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) {
+ nsg = 1 + skb_shinfo(skb)->nr_frags;
+ } else {
+ nsg = skb_cow_data(skb, 0, &unused);
+ if (unlikely(nsg < 0)) {
+ pr_err("RX: skb_cow_data() returned %d\n", nsg);
+ return nsg;
+ }
+ }
+
+ /* Allocate memory for the AEAD operation */
+ tfm = tipc_aead_tfm_next(aead);
+ ctx = tipc_aead_mem_alloc(tfm, sizeof(*rx_ctx), &iv, &req, &sg, nsg);
+ if (unlikely(!ctx))
+ return -ENOMEM;
+ TIPC_SKB_CB(skb)->crypto_ctx = ctx;
+
+ /* Map skb to the sg lists */
+ sg_init_table(sg, nsg);
+ rc = skb_to_sgvec(skb, sg, 0, skb->len);
+ if (unlikely(rc < 0)) {
+ pr_err("RX: skb_to_sgvec() returned %d, nsg %d\n", rc, nsg);
+ goto exit;
+ }
+
+ /* Reconstruct IV: */
+ ehdr = (struct tipc_ehdr *)skb->data;
+ salt = aead->salt;
+ if (aead->mode == CLUSTER_KEY)
+ salt ^= ehdr->addr; /* __be32 */
+ else if (ehdr->destined)
+ salt ^= tipc_own_addr(net);
+ memcpy(iv, &salt, 4);
+ memcpy(iv + 4, (u8 *)&ehdr->seqno, 8);
+
+ /* Prepare request */
+ ehsz = tipc_ehdr_size(ehdr);
+ aead_request_set_tfm(req, tfm);
+ aead_request_set_ad(req, ehsz);
+ aead_request_set_crypt(req, sg, sg, skb->len - ehsz, iv);
+
+ /* Set callback function & data */
+ aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+ tipc_aead_decrypt_done, skb);
+ rx_ctx = (struct tipc_crypto_rx_ctx *)ctx;
+ rx_ctx->aead = aead;
+ rx_ctx->bearer = b;
+
+ /* Hold bearer */
+ if (unlikely(!tipc_bearer_hold(b))) {
+ rc = -ENODEV;
+ goto exit;
+ }
+
+ /* Now, do decrypt */
+ rc = crypto_aead_decrypt(req);
+ if (rc == -EINPROGRESS || rc == -EBUSY)
+ return rc;
+
+ tipc_bearer_put(b);
+
+exit:
+ kfree(ctx);
+ TIPC_SKB_CB(skb)->crypto_ctx = NULL;
+ return rc;
+}
+
+static void tipc_aead_decrypt_done(struct crypto_async_request *base, int err)
+{
+ struct sk_buff *skb = base->data;
+ struct tipc_crypto_rx_ctx *rx_ctx = TIPC_SKB_CB(skb)->crypto_ctx;
+ struct tipc_bearer *b = rx_ctx->bearer;
+ struct tipc_aead *aead = rx_ctx->aead;
+ struct tipc_crypto_stats __percpu *stats = aead->crypto->stats;
+ struct net *net = aead->crypto->net;
+
+ switch (err) {
+ case 0:
+ this_cpu_inc(stats->stat[STAT_ASYNC_OK]);
+ break;
+ case -EINPROGRESS:
+ return;
+ default:
+ this_cpu_inc(stats->stat[STAT_ASYNC_NOK]);
+ break;
+ }
+
+ kfree(rx_ctx);
+ tipc_crypto_rcv_complete(net, aead, b, &skb, err);
+ if (likely(skb)) {
+ if (likely(test_bit(0, &b->up)))
+ tipc_rcv(net, skb, b);
+ else
+ kfree_skb(skb);
+ }
+
+ tipc_bearer_put(b);
+}
+
+static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr)
+{
+ return (ehdr->user != LINK_CONFIG) ? EHDR_SIZE : EHDR_CFG_SIZE;
+}
+
+/**
+ * tipc_ehdr_validate - Validate an encryption message
+ * @skb: the message buffer
+ *
+ * Returns "true" if this is a valid encryption message, otherwise "false"
+ */
+bool tipc_ehdr_validate(struct sk_buff *skb)
+{
+ struct tipc_ehdr *ehdr;
+ int ehsz;
+
+ if (unlikely(!pskb_may_pull(skb, EHDR_MIN_SIZE)))
+ return false;
+
+ ehdr = (struct tipc_ehdr *)skb->data;
+ if (unlikely(ehdr->version != TIPC_EVERSION))
+ return false;
+ ehsz = tipc_ehdr_size(ehdr);
+ if (unlikely(!pskb_may_pull(skb, ehsz)))
+ return false;
+ if (unlikely(skb->len <= ehsz + TIPC_AES_GCM_TAG_SIZE))
+ return false;
+ if (unlikely(!ehdr->tx_key))
+ return false;
+
+ return true;
+}
+
+/**
+ * tipc_ehdr_build - Build TIPC encryption message header
+ * @net: struct net
+ * @aead: TX AEAD key to be used for the message encryption
+ * @tx_key: key id used for the message encryption
+ * @skb: input/output message skb
+ * @__rx: RX crypto handle if dest is "known"
+ *
+ * Return: the header size if the building is successful, otherwise < 0
+ */
+static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead,
+ u8 tx_key, struct sk_buff *skb,
+ struct tipc_crypto *__rx)
+{
+ struct tipc_msg *hdr = buf_msg(skb);
+ struct tipc_ehdr *ehdr;
+ u32 user = msg_user(hdr);
+ u64 seqno;
+ int ehsz;
+
+ /* Make room for encryption header */
+ ehsz = (user != LINK_CONFIG) ? EHDR_SIZE : EHDR_CFG_SIZE;
+ WARN_ON(skb_headroom(skb) < ehsz);
+ ehdr = (struct tipc_ehdr *)skb_push(skb, ehsz);
+
+ /* Obtain a seqno first:
+ * Use the key seqno (= cluster wise) if dest is unknown or we're in
+ * cluster key mode, otherwise it's better for a per-peer seqno!
+ */
+ if (!__rx || aead->mode == CLUSTER_KEY)
+ seqno = atomic64_inc_return(&aead->seqno);
+ else
+ seqno = atomic64_inc_return(&__rx->sndnxt);
+
+ /* Revoke the key if seqno is wrapped around */
+ if (unlikely(!seqno))
+ return tipc_crypto_key_revoke(net, tx_key);
+
+ /* Word 1-2 */
+ ehdr->seqno = cpu_to_be64(seqno);
+
+ /* Words 0, 3- */
+ ehdr->version = TIPC_EVERSION;
+ ehdr->user = 0;
+ ehdr->keepalive = 0;
+ ehdr->tx_key = tx_key;
+ ehdr->destined = (__rx) ? 1 : 0;
+ ehdr->rx_key_active = (__rx) ? __rx->key.active : 0;
+ ehdr->reserved_1 = 0;
+ ehdr->reserved_2 = 0;
+
+ switch (user) {
+ case LINK_CONFIG:
+ ehdr->user = LINK_CONFIG;
+ memcpy(ehdr->id, tipc_own_id(net), NODE_ID_LEN);
+ break;
+ default:
+ if (user == LINK_PROTOCOL && msg_type(hdr) == STATE_MSG) {
+ ehdr->user = LINK_PROTOCOL;
+ ehdr->keepalive = msg_is_keepalive(hdr);
+ }
+ ehdr->addr = hdr->hdr[3];
+ break;
+ }
+
+ return ehsz;
+}
+
+static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
+ u8 new_passive,
+ u8 new_active,
+ u8 new_pending)
+{
+#ifdef TIPC_CRYPTO_DEBUG
+ struct tipc_key old = c->key;
+ char buf[32];
+#endif
+
+ c->key.keys = ((new_passive & KEY_MASK) << (KEY_BITS * 2)) |
+ ((new_active & KEY_MASK) << (KEY_BITS)) |
+ ((new_pending & KEY_MASK));
+
+#ifdef TIPC_CRYPTO_DEBUG
+ pr_info("%s(%s): key changing %s ::%pS\n",
+ (c->node) ? "RX" : "TX",
+ (c->node) ? tipc_node_get_id_str(c->node) :
+ tipc_own_id_string(c->net),
+ tipc_key_change_dump(old, c->key, buf),
+ __builtin_return_address(0));
+#endif
+}
+
+/**
+ * tipc_crypto_key_init - Initiate a new user / AEAD key
+ * @c: TIPC crypto to which new key is attached
+ * @ukey: the user key
+ * @mode: the key mode (CLUSTER_KEY or PER_NODE_KEY)
+ *
+ * A new TIPC AEAD key will be allocated and initiated with the specified user
+ * key, then attached to the TIPC crypto.
+ *
+ * Return: new key id in case of success, otherwise: < 0
+ */
+int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
+ u8 mode)
+{
+ struct tipc_aead *aead = NULL;
+ int rc = 0;
+
+ /* Initiate with the new user key */
+ rc = tipc_aead_init(&aead, ukey, mode);
+
+ /* Attach it to the crypto */
+ if (likely(!rc)) {
+ rc = tipc_crypto_key_attach(c, aead, 0);
+ if (rc < 0)
+ tipc_aead_free(&aead->rcu);
+ }
+
+ pr_info("%s(%s): key initiating, rc %d!\n",
+ (c->node) ? "RX" : "TX",
+ (c->node) ? tipc_node_get_id_str(c->node) :
+ tipc_own_id_string(c->net),
+ rc);
+
+ return rc;
+}
+
+/**
+ * tipc_crypto_key_attach - Attach a new AEAD key to TIPC crypto
+ * @c: TIPC crypto to which the new AEAD key is attached
+ * @aead: the new AEAD key pointer
+ * @pos: desired slot in the crypto key array, = 0 if any!
+ *
+ * Return: new key id in case of success, otherwise: -EBUSY
+ */
+static int tipc_crypto_key_attach(struct tipc_crypto *c,
+ struct tipc_aead *aead, u8 pos)
+{
+ u8 new_pending, new_passive, new_key;
+ struct tipc_key key;
+ int rc = -EBUSY;
+
+ spin_lock_bh(&c->lock);
+ key = c->key;
+ if (key.active && key.passive)
+ goto exit;
+ if (key.passive && !tipc_aead_users(c->aead[key.passive]))
+ goto exit;
+ if (key.pending) {
+ if (pos)
+ goto exit;
+ if (tipc_aead_users(c->aead[key.pending]) > 0)
+ goto exit;
+ /* Replace it */
+ new_pending = key.pending;
+ new_passive = key.passive;
+ new_key = new_pending;
+ } else {
+ if (pos) {
+ if (key.active && pos != key_next(key.active)) {
+ new_pending = key.pending;
+ new_passive = pos;
+ new_key = new_passive;
+ goto attach;
+ } else if (!key.active && !key.passive) {
+ new_pending = pos;
+ new_passive = key.passive;
+ new_key = new_pending;
+ goto attach;
+ }
+ }
+ new_pending = key_next(key.active ?: key.passive);
+ new_passive = key.passive;
+ new_key = new_pending;
+ }
+
+attach:
+ aead->crypto = c;
+ tipc_crypto_key_set_state(c, new_passive, key.active, new_pending);
+ tipc_aead_rcu_replace(c->aead[new_key], aead, &c->lock);
+
+ c->working = 1;
+ c->timer1 = jiffies;
+ c->timer2 = jiffies;
+ rc = new_key;
+
+exit:
+ spin_unlock_bh(&c->lock);
+ return rc;
+}
+
+void tipc_crypto_key_flush(struct tipc_crypto *c)
+{
+ int k;
+
+ spin_lock_bh(&c->lock);
+ c->working = 0;
+ tipc_crypto_key_set_state(c, 0, 0, 0);
+ for (k = KEY_MIN; k <= KEY_MAX; k++)
+ tipc_crypto_key_detach(c->aead[k], &c->lock);
+ atomic_set(&c->peer_rx_active, 0);
+ atomic64_set(&c->sndnxt, 0);
+ spin_unlock_bh(&c->lock);
+}
+
+/**
+ * tipc_crypto_key_try_align - Align RX keys if possible
+ * @rx: RX crypto handle
+ * @new_pending: new pending slot if aligned (= TX key from peer)
+ *
+ * Peer has used an unknown key slot, this only happens when peer has left and
+ * rejoned, or we are newcomer.
+ * That means, there must be no active key but a pending key at unaligned slot.
+ * If so, we try to move the pending key to the new slot.
+ * Note: A potential passive key can exist, it will be shifted correspondingly!
+ *
+ * Return: "true" if key is successfully aligned, otherwise "false"
+ */
+static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending)
+{
+ struct tipc_aead *tmp1, *tmp2 = NULL;
+ struct tipc_key key;
+ bool aligned = false;
+ u8 new_passive = 0;
+ int x;
+
+ spin_lock(&rx->lock);
+ key = rx->key;
+ if (key.pending == new_pending) {
+ aligned = true;
+ goto exit;
+ }
+ if (key.active)
+ goto exit;
+ if (!key.pending)
+ goto exit;
+ if (tipc_aead_users(rx->aead[key.pending]) > 0)
+ goto exit;
+
+ /* Try to "isolate" this pending key first */
+ tmp1 = tipc_aead_rcu_ptr(rx->aead[key.pending], &rx->lock);
+ if (!refcount_dec_if_one(&tmp1->refcnt))
+ goto exit;
+ rcu_assign_pointer(rx->aead[key.pending], NULL);
+
+ /* Move passive key if any */
+ if (key.passive) {
+ tipc_aead_rcu_swap(rx->aead[key.passive], tmp2, &rx->lock);
+ x = (key.passive - key.pending + new_pending) % KEY_MAX;
+ new_passive = (x <= 0) ? x + KEY_MAX : x;
+ }
+
+ /* Re-allocate the key(s) */
+ tipc_crypto_key_set_state(rx, new_passive, 0, new_pending);
+ rcu_assign_pointer(rx->aead[new_pending], tmp1);
+ if (new_passive)
+ rcu_assign_pointer(rx->aead[new_passive], tmp2);
+ refcount_set(&tmp1->refcnt, 1);
+ aligned = true;
+ pr_info("RX(%s): key is aligned!\n", tipc_node_get_id_str(rx->node));
+
+exit:
+ spin_unlock(&rx->lock);
+ return aligned;
+}
+
+/**
+ * tipc_crypto_key_pick_tx - Pick one TX key for message decryption
+ * @tx: TX crypto handle
+ * @rx: RX crypto handle (can be NULL)
+ * @skb: the message skb which will be decrypted later
+ *
+ * This function looks up the existing TX keys and pick one which is suitable
+ * for the message decryption, that must be a cluster key and not used before
+ * on the same message (i.e. recursive).
+ *
+ * Return: the TX AEAD key handle in case of success, otherwise NULL
+ */
+static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
+ struct tipc_crypto *rx,
+ struct sk_buff *skb)
+{
+ struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(skb);
+ struct tipc_aead *aead = NULL;
+ struct tipc_key key = tx->key;
+ u8 k, i = 0;
+
+ /* Initialize data if not yet */
+ if (!skb_cb->tx_clone_deferred) {
+ skb_cb->tx_clone_deferred = 1;
+ memset(&skb_cb->tx_clone_ctx, 0, sizeof(skb_cb->tx_clone_ctx));
+ }
+
+ skb_cb->tx_clone_ctx.rx = rx;
+ if (++skb_cb->tx_clone_ctx.recurs > 2)
+ return NULL;
+
+ /* Pick one TX key */
+ spin_lock(&tx->lock);
+ do {
+ k = (i == 0) ? key.pending :
+ ((i == 1) ? key.active : key.passive);
+ if (!k)
+ continue;
+ aead = tipc_aead_rcu_ptr(tx->aead[k], &tx->lock);
+ if (!aead)
+ continue;
+ if (aead->mode != CLUSTER_KEY ||
+ aead == skb_cb->tx_clone_ctx.last) {
+ aead = NULL;
+ continue;
+ }
+ /* Ok, found one cluster key */
+ skb_cb->tx_clone_ctx.last = aead;
+ WARN_ON(skb->next);
+ skb->next = skb_clone(skb, GFP_ATOMIC);
+ if (unlikely(!skb->next))
+ pr_warn("Failed to clone skb for next round if any\n");
+ WARN_ON(!refcount_inc_not_zero(&aead->refcnt));
+ break;
+ } while (++i < 3);
+ spin_unlock(&tx->lock);
+
+ return aead;
+}
+
+/**
+ * tipc_crypto_key_synch: Synch own key data according to peer key status
+ * @rx: RX crypto handle
+ * @new_rx_active: latest RX active key from peer
+ * @hdr: TIPCv2 message
+ *
+ * This function updates the peer node related data as the peer RX active key
+ * has changed, so the number of TX keys' users on this node are increased and
+ * decreased correspondingly.
+ *
+ * The "per-peer" sndnxt is also reset when the peer key has switched.
+ */
+static void tipc_crypto_key_synch(struct tipc_crypto *rx, u8 new_rx_active,
+ struct tipc_msg *hdr)
+{
+ struct net *net = rx->net;
+ struct tipc_crypto *tx = tipc_net(net)->crypto_tx;
+ u8 cur_rx_active;
+
+ /* TX might be even not ready yet */
+ if (unlikely(!tx->key.active && !tx->key.pending))
+ return;
+
+ cur_rx_active = atomic_read(&rx->peer_rx_active);
+ if (likely(cur_rx_active == new_rx_active))
+ return;
+
+ /* Make sure this message destined for this node */
+ if (unlikely(msg_short(hdr) ||
+ msg_destnode(hdr) != tipc_own_addr(net)))
+ return;
+
+ /* Peer RX active key has changed, try to update owns' & TX users */
+ if (atomic_cmpxchg(&rx->peer_rx_active,
+ cur_rx_active,
+ new_rx_active) == cur_rx_active) {
+ if (new_rx_active)
+ tipc_aead_users_inc(tx->aead[new_rx_active], INT_MAX);
+ if (cur_rx_active)
+ tipc_aead_users_dec(tx->aead[cur_rx_active], 0);
+
+ atomic64_set(&rx->sndnxt, 0);
+ /* Mark the point TX key users changed */
+ tx->timer1 = jiffies;
+
+#ifdef TIPC_CRYPTO_DEBUG
+ pr_info("TX(%s): key users changed %d-- %d++, peer RX(%s)\n",
+ tipc_own_id_string(net), cur_rx_active,
+ new_rx_active, tipc_node_get_id_str(rx->node));
+#endif
+ }
+}
+
+static int tipc_crypto_key_revoke(struct net *net, u8 tx_key)
+{
+ struct tipc_crypto *tx = tipc_net(net)->crypto_tx;
+ struct tipc_key key;
+
+ spin_lock(&tx->lock);
+ key = tx->key;
+ WARN_ON(!key.active || tx_key != key.active);
+
+ /* Free the active key */
+ tipc_crypto_key_set_state(tx, key.passive, 0, key.pending);
+ tipc_crypto_key_detach(tx->aead[key.active], &tx->lock);
+ spin_unlock(&tx->lock);
+
+ pr_warn("TX(%s): key is revoked!\n", tipc_own_id_string(net));
+ return -EKEYREVOKED;
+}
+
+int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
+ struct tipc_node *node)
+{
+ struct tipc_crypto *c;
+
+ if (*crypto)
+ return -EEXIST;
+
+ /* Allocate crypto */
+ c = kzalloc(sizeof(*c), GFP_ATOMIC);
+ if (!c)
+ return -ENOMEM;
+
+ /* Allocate statistic structure */
+ c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC);
+ if (!c->stats) {
+ kzfree(c);
+ return -ENOMEM;
+ }
+
+ c->working = 0;
+ c->net = net;
+ c->node = node;
+ tipc_crypto_key_set_state(c, 0, 0, 0);
+ atomic_set(&c->peer_rx_active, 0);
+ atomic64_set(&c->sndnxt, 0);
+ c->timer1 = jiffies;
+ c->timer2 = jiffies;
+ spin_lock_init(&c->lock);
+ *crypto = c;
+
+ return 0;
+}
+
+void tipc_crypto_stop(struct tipc_crypto **crypto)
+{
+ struct tipc_crypto *c, *tx, *rx;
+ bool is_rx;
+ u8 k;
+
+ if (!*crypto)
+ return;
+
+ rcu_read_lock();
+ /* RX stopping? => decrease TX key users if any */
+ is_rx = !!((*crypto)->node);
+ if (is_rx) {
+ rx = *crypto;
+ tx = tipc_net(rx->net)->crypto_tx;
+ k = atomic_read(&rx->peer_rx_active);
+ if (k) {
+ tipc_aead_users_dec(tx->aead[k], 0);
+ /* Mark the point TX key users changed */
+ tx->timer1 = jiffies;
+ }
+ }
+
+ /* Release AEAD keys */
+ c = *crypto;
+ for (k = KEY_MIN; k <= KEY_MAX; k++)
+ tipc_aead_put(rcu_dereference(c->aead[k]));
+ rcu_read_unlock();
+
+ pr_warn("%s(%s) has been purged, node left!\n",
+ (is_rx) ? "RX" : "TX",
+ (is_rx) ? tipc_node_get_id_str((*crypto)->node) :
+ tipc_own_id_string((*crypto)->net));
+
+ /* Free this crypto statistics */
+ free_percpu(c->stats);
+
+ *crypto = NULL;
+ kzfree(c);
+}
+
+void tipc_crypto_timeout(struct tipc_crypto *rx)
+{
+ struct tipc_net *tn = tipc_net(rx->net);
+ struct tipc_crypto *tx = tn->crypto_tx;
+ struct tipc_key key;
+ u8 new_pending, new_passive;
+ int cmd;
+
+ /* TX key activating:
+ * The pending key (users > 0) -> active
+ * The active key if any (users == 0) -> free
+ */
+ spin_lock(&tx->lock);
+ key = tx->key;
+ if (key.active && tipc_aead_users(tx->aead[key.active]) > 0)
+ goto s1;
+ if (!key.pending || tipc_aead_users(tx->aead[key.pending]) <= 0)
+ goto s1;
+ if (time_before(jiffies, tx->timer1 + TIPC_TX_LASTING_LIM))
+ goto s1;
+
+ tipc_crypto_key_set_state(tx, key.passive, key.pending, 0);
+ if (key.active)
+ tipc_crypto_key_detach(tx->aead[key.active], &tx->lock);
+ this_cpu_inc(tx->stats->stat[STAT_SWITCHES]);
+ pr_info("TX(%s): key %d is activated!\n", tipc_own_id_string(tx->net),
+ key.pending);
+
+s1:
+ spin_unlock(&tx->lock);
+
+ /* RX key activating:
+ * The pending key (users > 0) -> active
+ * The active key if any -> passive, freed later
+ */
+ spin_lock(&rx->lock);
+ key = rx->key;
+ if (!key.pending || tipc_aead_users(rx->aead[key.pending]) <= 0)
+ goto s2;
+
+ new_pending = (key.passive &&
+ !tipc_aead_users(rx->aead[key.passive])) ?
+ key.passive : 0;
+ new_passive = (key.active) ?: ((new_pending) ? 0 : key.passive);
+ tipc_crypto_key_set_state(rx, new_passive, key.pending, new_pending);
+ this_cpu_inc(rx->stats->stat[STAT_SWITCHES]);
+ pr_info("RX(%s): key %d is activated!\n",
+ tipc_node_get_id_str(rx->node), key.pending);
+ goto s5;
+
+s2:
+ /* RX key "faulty" switching:
+ * The faulty pending key (users < -30) -> passive
+ * The passive key (users = 0) -> pending
+ * Note: This only happens after RX deactivated - s3!
+ */
+ key = rx->key;
+ if (!key.pending || tipc_aead_users(rx->aead[key.pending]) > -30)
+ goto s3;
+ if (!key.passive || tipc_aead_users(rx->aead[key.passive]) != 0)
+ goto s3;
+
+ new_pending = key.passive;
+ new_passive = key.pending;
+ tipc_crypto_key_set_state(rx, new_passive, key.active, new_pending);
+ goto s5;
+
+s3:
+ /* RX key deactivating:
+ * The passive key if any -> pending
+ * The active key -> passive (users = 0) / pending
+ * The pending key if any -> passive (users = 0)
+ */
+ key = rx->key;
+ if (!key.active)
+ goto s4;
+ if (time_before(jiffies, rx->timer1 + TIPC_RX_ACTIVE_LIM))
+ goto s4;
+
+ new_pending = (key.passive) ?: key.active;
+ new_passive = (key.passive) ? key.active : key.pending;
+ tipc_aead_users_set(rx->aead[new_pending], 0);
+ if (new_passive)
+ tipc_aead_users_set(rx->aead[new_passive], 0);
+ tipc_crypto_key_set_state(rx, new_passive, 0, new_pending);
+ pr_info("RX(%s): key %d is deactivated!\n",
+ tipc_node_get_id_str(rx->node), key.active);
+ goto s5;
+
+s4:
+ /* RX key passive -> freed: */
+ key = rx->key;
+ if (!key.passive || !tipc_aead_users(rx->aead[key.passive]))
+ goto s5;
+ if (time_before(jiffies, rx->timer2 + TIPC_RX_PASSIVE_LIM))
+ goto s5;
+
+ tipc_crypto_key_set_state(rx, 0, key.active, key.pending);
+ tipc_crypto_key_detach(rx->aead[key.passive], &rx->lock);
+ pr_info("RX(%s): key %d is freed!\n", tipc_node_get_id_str(rx->node),
+ key.passive);
+
+s5:
+ spin_unlock(&rx->lock);
+
+ /* Limit max_tfms & do debug commands if needed */
+ if (likely(sysctl_tipc_max_tfms <= TIPC_MAX_TFMS_LIM))
+ return;
+
+ cmd = sysctl_tipc_max_tfms;
+ sysctl_tipc_max_tfms = TIPC_MAX_TFMS_DEF;
+ tipc_crypto_do_cmd(rx->net, cmd);
+}
+
+/**
+ * tipc_crypto_xmit - Build & encrypt TIPC message for xmit
+ * @net: struct net
+ * @skb: input/output message skb pointer
+ * @b: bearer used for xmit later
+ * @dst: destination media address
+ * @__dnode: destination node for reference if any
+ *
+ * First, build an encryption message header on the top of the message, then
+ * encrypt the original TIPC message by using the active or pending TX key.
+ * If the encryption is successful, the encrypted skb is returned directly or
+ * via the callback.
+ * Otherwise, the skb is freed!
+ *
+ * Return:
+ * 0 : the encryption has succeeded (or no encryption)
+ * -EINPROGRESS/-EBUSY : the encryption is ongoing, a callback will be made
+ * -ENOKEK : the encryption has failed due to no key
+ * -EKEYREVOKED : the encryption has failed due to key revoked
+ * -ENOMEM : the encryption has failed due to no memory
+ * < 0 : the encryption has failed due to other reasons
+ */
+int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
+ struct tipc_bearer *b, struct tipc_media_addr *dst,
+ struct tipc_node *__dnode)
+{
+ struct tipc_crypto *__rx = tipc_node_crypto_rx(__dnode);
+ struct tipc_crypto *tx = tipc_net(net)->crypto_tx;
+ struct tipc_crypto_stats __percpu *stats = tx->stats;
+ struct tipc_key key = tx->key;
+ struct tipc_aead *aead = NULL;
+ struct sk_buff *probe;
+ int rc = -ENOKEY;
+ u8 tx_key;
+
+ /* No encryption? */
+ if (!tx->working)
+ return 0;
+
+ /* Try with the pending key if available and:
+ * 1) This is the only choice (i.e. no active key) or;
+ * 2) Peer has switched to this key (unicast only) or;
+ * 3) It is time to do a pending key probe;
+ */
+ if (unlikely(key.pending)) {
+ tx_key = key.pending;
+ if (!key.active)
+ goto encrypt;
+ if (__rx && atomic_read(&__rx->peer_rx_active) == tx_key)
+ goto encrypt;
+ if (TIPC_SKB_CB(*skb)->probe)
+ goto encrypt;
+ if (!__rx &&
+ time_after(jiffies, tx->timer2 + TIPC_TX_PROBE_LIM)) {
+ tx->timer2 = jiffies;
+ probe = skb_clone(*skb, GFP_ATOMIC);
+ if (probe) {
+ TIPC_SKB_CB(probe)->probe = 1;
+ tipc_crypto_xmit(net, &probe, b, dst, __dnode);
+ if (probe)
+ b->media->send_msg(net, probe, b, dst);
+ }
+ }
+ }
+ /* Else, use the active key if any */
+ if (likely(key.active)) {
+ tx_key = key.active;
+ goto encrypt;
+ }
+ goto exit;
+
+encrypt:
+ aead = tipc_aead_get(tx->aead[tx_key]);
+ if (unlikely(!aead))
+ goto exit;
+ rc = tipc_ehdr_build(net, aead, tx_key, *skb, __rx);
+ if (likely(rc > 0))
+ rc = tipc_aead_encrypt(aead, *skb, b, dst, __dnode);
+
+exit:
+ switch (rc) {
+ case 0:
+ this_cpu_inc(stats->stat[STAT_OK]);
+ break;
+ case -EINPROGRESS:
+ case -EBUSY:
+ this_cpu_inc(stats->stat[STAT_ASYNC]);
+ *skb = NULL;
+ return rc;
+ default:
+ this_cpu_inc(stats->stat[STAT_NOK]);
+ if (rc == -ENOKEY)
+ this_cpu_inc(stats->stat[STAT_NOKEYS]);
+ else if (rc == -EKEYREVOKED)
+ this_cpu_inc(stats->stat[STAT_BADKEYS]);
+ kfree_skb(*skb);
+ *skb = NULL;
+ break;
+ }
+
+ tipc_aead_put(aead);
+ return rc;
+}
+
+/**
+ * tipc_crypto_rcv - Decrypt an encrypted TIPC message from peer
+ * @net: struct net
+ * @rx: RX crypto handle
+ * @skb: input/output message skb pointer
+ * @b: bearer where the message has been received
+ *
+ * If the decryption is successful, the decrypted skb is returned directly or
+ * as the callback, the encryption header and auth tag will be trimed out
+ * before forwarding to tipc_rcv() via the tipc_crypto_rcv_complete().
+ * Otherwise, the skb will be freed!
+ * Note: RX key(s) can be re-aligned, or in case of no key suitable, TX
+ * cluster key(s) can be taken for decryption (- recursive).
+ *
+ * Return:
+ * 0 : the decryption has successfully completed
+ * -EINPROGRESS/-EBUSY : the decryption is ongoing, a callback will be made
+ * -ENOKEY : the decryption has failed due to no key
+ * -EBADMSG : the decryption has failed due to bad message
+ * -ENOMEM : the decryption has failed due to no memory
+ * < 0 : the decryption has failed due to other reasons
+ */
+int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
+ struct sk_buff **skb, struct tipc_bearer *b)
+{
+ struct tipc_crypto *tx = tipc_net(net)->crypto_tx;
+ struct tipc_crypto_stats __percpu *stats;
+ struct tipc_aead *aead = NULL;
+ struct tipc_key key;
+ int rc = -ENOKEY;
+ u8 tx_key = 0;
+
+ /* New peer?
+ * Let's try with TX key (i.e. cluster mode) & verify the skb first!
+ */
+ if (unlikely(!rx))
+ goto pick_tx;
+
+ /* Pick RX key according to TX key, three cases are possible:
+ * 1) The current active key (likely) or;
+ * 2) The pending (new or deactivated) key (if any) or;
+ * 3) The passive or old active key (i.e. users > 0);
+ */
+ tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key;
+ key = rx->key;
+ if (likely(tx_key == key.active))
+ goto decrypt;
+ if (tx_key == key.pending)
+ goto decrypt;
+ if (tx_key == key.passive) {
+ rx->timer2 = jiffies;
+ if (tipc_aead_users(rx->aead[key.passive]) > 0)
+ goto decrypt;
+ }
+
+ /* Unknown key, let's try to align RX key(s) */
+ if (tipc_crypto_key_try_align(rx, tx_key))
+ goto decrypt;
+
+pick_tx:
+ /* No key suitable? Try to pick one from TX... */
+ aead = tipc_crypto_key_pick_tx(tx, rx, *skb);
+ if (aead)
+ goto decrypt;
+ goto exit;
+
+decrypt:
+ rcu_read_lock();
+ if (!aead)
+ aead = tipc_aead_get(rx->aead[tx_key]);
+ rc = tipc_aead_decrypt(net, aead, *skb, b);
+ rcu_read_unlock();
+
+exit:
+ stats = ((rx) ?: tx)->stats;
+ switch (rc) {
+ case 0:
+ this_cpu_inc(stats->stat[STAT_OK]);
+ break;
+ case -EINPROGRESS:
+ case -EBUSY:
+ this_cpu_inc(stats->stat[STAT_ASYNC]);
+ *skb = NULL;
+ return rc;
+ default:
+ this_cpu_inc(stats->stat[STAT_NOK]);
+ if (rc == -ENOKEY) {
+ kfree_skb(*skb);
+ *skb = NULL;
+ if (rx)
+ tipc_node_put(rx->node);
+ this_cpu_inc(stats->stat[STAT_NOKEYS]);
+ return rc;
+ } else if (rc == -EBADMSG) {
+ this_cpu_inc(stats->stat[STAT_BADMSGS]);
+ }
+ break;
+ }
+
+ tipc_crypto_rcv_complete(net, aead, b, skb, rc);
+ return rc;
+}
+
+static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
+ struct tipc_bearer *b,
+ struct sk_buff **skb, int err)
+{
+ struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(*skb);
+ struct tipc_crypto *rx = aead->crypto;
+ struct tipc_aead *tmp = NULL;
+ struct tipc_ehdr *ehdr;
+ struct tipc_node *n;
+ u8 rx_key_active;
+ bool destined;
+
+ /* Is this completed by TX? */
+ if (unlikely(!rx->node)) {
+ rx = skb_cb->tx_clone_ctx.rx;
+#ifdef TIPC_CRYPTO_DEBUG
+ pr_info("TX->RX(%s): err %d, aead %p, skb->next %p, flags %x\n",
+ (rx) ? tipc_node_get_id_str(rx->node) : "-", err, aead,
+ (*skb)->next, skb_cb->flags);
+ pr_info("skb_cb [recurs %d, last %p], tx->aead [%p %p %p]\n",
+ skb_cb->tx_clone_ctx.recurs, skb_cb->tx_clone_ctx.last,
+ aead->crypto->aead[1], aead->crypto->aead[2],
+ aead->crypto->aead[3]);
+#endif
+ if (unlikely(err)) {
+ if (err == -EBADMSG && (*skb)->next)
+ tipc_rcv(net, (*skb)->next, b);
+ goto free_skb;
+ }
+
+ if (likely((*skb)->next)) {
+ kfree_skb((*skb)->next);
+ (*skb)->next = NULL;
+ }
+ ehdr = (struct tipc_ehdr *)(*skb)->data;
+ if (!rx) {
+ WARN_ON(ehdr->user != LINK_CONFIG);
+ n = tipc_node_create(net, 0, ehdr->id, 0xffffu, 0,
+ true);
+ rx = tipc_node_crypto_rx(n);
+ if (unlikely(!rx))
+ goto free_skb;
+ }
+
+ /* Skip cloning this time as we had a RX pending key */
+ if (rx->key.pending)
+ goto rcv;
+ if (tipc_aead_clone(&tmp, aead) < 0)
+ goto rcv;
+ if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key) < 0) {
+ tipc_aead_free(&tmp->rcu);
+ goto rcv;
+ }
+ tipc_aead_put(aead);
+ aead = tipc_aead_get(tmp);
+ }
+
+ if (unlikely(err)) {
+ tipc_aead_users_dec(aead, INT_MIN);
+ goto free_skb;
+ }
+
+ /* Set the RX key's user */
+ tipc_aead_users_set(aead, 1);
+
+rcv:
+ /* Mark this point, RX works */
+ rx->timer1 = jiffies;
+
+ /* Remove ehdr & auth. tag prior to tipc_rcv() */
+ ehdr = (struct tipc_ehdr *)(*skb)->data;
+ destined = ehdr->destined;
+ rx_key_active = ehdr->rx_key_active;
+ skb_pull(*skb, tipc_ehdr_size(ehdr));
+ pskb_trim(*skb, (*skb)->len - aead->authsize);
+
+ /* Validate TIPCv2 message */
+ if (unlikely(!tipc_msg_validate(skb))) {
+ pr_err_ratelimited("Packet dropped after decryption!\n");
+ goto free_skb;
+ }
+
+ /* Update peer RX active key & TX users */
+ if (destined)
+ tipc_crypto_key_synch(rx, rx_key_active, buf_msg(*skb));
+
+ /* Mark skb decrypted */
+ skb_cb->decrypted = 1;
+
+ /* Clear clone cxt if any */
+ if (likely(!skb_cb->tx_clone_deferred))
+ goto exit;
+ skb_cb->tx_clone_deferred = 0;
+ memset(&skb_cb->tx_clone_ctx, 0, sizeof(skb_cb->tx_clone_ctx));
+ goto exit;
+
+free_skb:
+ kfree_skb(*skb);
+ *skb = NULL;
+
+exit:
+ tipc_aead_put(aead);
+ if (rx)
+ tipc_node_put(rx->node);
+}
+
+static void tipc_crypto_do_cmd(struct net *net, int cmd)
+{
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_crypto *tx = tn->crypto_tx, *rx;
+ struct list_head *p;
+ unsigned int stat;
+ int i, j, cpu;
+ char buf[200];
+
+ /* Currently only one command is supported */
+ switch (cmd) {
+ case 0xfff1:
+ goto print_stats;
+ default:
+ return;
+ }
+
+print_stats:
+ /* Print a header */
+ pr_info("\n=============== TIPC Crypto Statistics ===============\n\n");
+
+ /* Print key status */
+ pr_info("Key status:\n");
+ pr_info("TX(%7.7s)\n%s", tipc_own_id_string(net),
+ tipc_crypto_key_dump(tx, buf));
+
+ rcu_read_lock();
+ for (p = tn->node_list.next; p != &tn->node_list; p = p->next) {
+ rx = tipc_node_crypto_rx_by_list(p);
+ pr_info("RX(%7.7s)\n%s", tipc_node_get_id_str(rx->node),
+ tipc_crypto_key_dump(rx, buf));
+ }
+ rcu_read_unlock();
+
+ /* Print crypto statistics */
+ for (i = 0, j = 0; i < MAX_STATS; i++)
+ j += scnprintf(buf + j, 200 - j, "|%11s ", hstats[i]);
+ pr_info("\nCounter %s", buf);
+
+ memset(buf, '-', 115);
+ buf[115] = '\0';
+ pr_info("%s\n", buf);
+
+ j = scnprintf(buf, 200, "TX(%7.7s) ", tipc_own_id_string(net));
+ for_each_possible_cpu(cpu) {
+ for (i = 0; i < MAX_STATS; i++) {
+ stat = per_cpu_ptr(tx->stats, cpu)->stat[i];
+ j += scnprintf(buf + j, 200 - j, "|%11d ", stat);
+ }
+ pr_info("%s", buf);
+ j = scnprintf(buf, 200, "%12s", " ");
+ }
+
+ rcu_read_lock();
+ for (p = tn->node_list.next; p != &tn->node_list; p = p->next) {
+ rx = tipc_node_crypto_rx_by_list(p);
+ j = scnprintf(buf, 200, "RX(%7.7s) ",
+ tipc_node_get_id_str(rx->node));
+ for_each_possible_cpu(cpu) {
+ for (i = 0; i < MAX_STATS; i++) {
+ stat = per_cpu_ptr(rx->stats, cpu)->stat[i];
+ j += scnprintf(buf + j, 200 - j, "|%11d ",
+ stat);
+ }
+ pr_info("%s", buf);
+ j = scnprintf(buf, 200, "%12s", " ");
+ }
+ }
+ rcu_read_unlock();
+
+ pr_info("\n======================== Done ========================\n");
+}
+
+static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf)
+{
+ struct tipc_key key = c->key;
+ struct tipc_aead *aead;
+ int k, i = 0;
+ char *s;
+
+ for (k = KEY_MIN; k <= KEY_MAX; k++) {
+ if (k == key.passive)
+ s = "PAS";
+ else if (k == key.active)
+ s = "ACT";
+ else if (k == key.pending)
+ s = "PEN";
+ else
+ s = "-";
+ i += scnprintf(buf + i, 200 - i, "\tKey%d: %s", k, s);
+
+ rcu_read_lock();
+ aead = rcu_dereference(c->aead[k]);
+ if (aead)
+ i += scnprintf(buf + i, 200 - i,
+ "{\"%s...\", \"%s\"}/%d:%d",
+ aead->hint,
+ (aead->mode == CLUSTER_KEY) ? "c" : "p",
+ atomic_read(&aead->users),
+ refcount_read(&aead->refcnt));
+ rcu_read_unlock();
+ i += scnprintf(buf + i, 200 - i, "\n");
+ }
+
+ if (c->node)
+ i += scnprintf(buf + i, 200 - i, "\tPeer RX active: %d\n",
+ atomic_read(&c->peer_rx_active));
+
+ return buf;
+}
+
+#ifdef TIPC_CRYPTO_DEBUG
+static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
+ char *buf)
+{
+ struct tipc_key *key = &old;
+ int k, i = 0;
+ char *s;
+
+ /* Output format: "[%s %s %s] -> [%s %s %s]", max len = 32 */
+again:
+ i += scnprintf(buf + i, 32 - i, "[");
+ for (k = KEY_MIN; k <= KEY_MAX; k++) {
+ if (k == key->passive)
+ s = "pas";
+ else if (k == key->active)
+ s = "act";
+ else if (k == key->pending)
+ s = "pen";
+ else
+ s = "-";
+ i += scnprintf(buf + i, 32 - i,
+ (k != KEY_MAX) ? "%s " : "%s", s);
+ }
+ if (key != &new) {
+ i += scnprintf(buf + i, 32 - i, "] -> ");
+ key = &new;
+ goto again;
+ }
+ i += scnprintf(buf + i, 32 - i, "]");
+ return buf;
+}
+#endif
diff --git a/net/tipc/crypto.h b/net/tipc/crypto.h
new file mode 100644
index 000000000000..c3de769f49e8
--- /dev/null
+++ b/net/tipc/crypto.h
@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+ * net/tipc/crypto.h: Include file for TIPC crypto
+ *
+ * Copyright (c) 2019, 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.
+ */
+#ifdef CONFIG_TIPC_CRYPTO
+#ifndef _TIPC_CRYPTO_H
+#define _TIPC_CRYPTO_H
+
+#include "core.h"
+#include "node.h"
+#include "msg.h"
+#include "bearer.h"
+
+#define TIPC_EVERSION 7
+
+/* AEAD aes(gcm) */
+#define TIPC_AES_GCM_KEY_SIZE_128 16
+#define TIPC_AES_GCM_KEY_SIZE_192 24
+#define TIPC_AES_GCM_KEY_SIZE_256 32
+
+#define TIPC_AES_GCM_SALT_SIZE 4
+#define TIPC_AES_GCM_IV_SIZE 12
+#define TIPC_AES_GCM_TAG_SIZE 16
+
+/**
+ * TIPC crypto modes:
+ * - CLUSTER_KEY:
+ * One single key is used for both TX & RX in all nodes in the cluster.
+ * - PER_NODE_KEY:
+ * Each nodes in the cluster has one TX key, for RX a node needs to know
+ * its peers' TX key for the decryption of messages from those nodes.
+ */
+enum {
+ CLUSTER_KEY = 1,
+ PER_NODE_KEY = (1 << 1),
+};
+
+extern int sysctl_tipc_max_tfms __read_mostly;
+
+/**
+ * TIPC encryption message format:
+ *
+ * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0
+ * 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * w0:|Ver=7| User |D|TX |RX |K| Rsvd |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * w1:| Seqno |
+ * w2:| (8 octets) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * w3:\ Prevnode \
+ * / (4 or 16 octets) /
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * \ \
+ * / Encrypted complete TIPC V2 header and user data /
+ * \ \
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | |
+ * | AuthTag |
+ * | (16 octets) |
+ * | |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Word0:
+ * Ver : = 7 i.e. TIPC encryption message version
+ * User : = 7 (for LINK_PROTOCOL); = 13 (for LINK_CONFIG) or = 0
+ * D : The destined bit i.e. the message's destination node is
+ * "known" or not at the message encryption
+ * TX : TX key used for the message encryption
+ * RX : Currently RX active key corresponding to the destination
+ * node's TX key (when the "D" bit is set)
+ * K : Keep-alive bit (for RPS, LINK_PROTOCOL/STATE_MSG only)
+ * Rsvd : Reserved bit, field
+ * Word1-2:
+ * Seqno : The 64-bit sequence number of the encrypted message, also
+ * part of the nonce used for the message encryption/decryption
+ * Word3-:
+ * Prevnode: The source node address, or ID in case LINK_CONFIG only
+ * AuthTag : The authentication tag for the message integrity checking
+ * generated by the message encryption
+ */
+struct tipc_ehdr {
+ union {
+ struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u8 destined:1,
+ user:4,
+ version:3;
+ __u8 reserved_1:3,
+ keepalive:1,
+ rx_key_active:2,
+ tx_key:2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u8 version:3,
+ user:4,
+ destined:1;
+ __u8 tx_key:2,
+ rx_key_active:2,
+ keepalive:1,
+ reserved_1:3;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ __be16 reserved_2;
+ } __packed;
+ __be32 w0;
+ };
+ __be64 seqno;
+ union {
+ __be32 addr;
+ __u8 id[NODE_ID_LEN]; /* For a LINK_CONFIG message only! */
+ };
+#define EHDR_SIZE (offsetof(struct tipc_ehdr, addr) + sizeof(__be32))
+#define EHDR_CFG_SIZE (sizeof(struct tipc_ehdr))
+#define EHDR_MIN_SIZE (EHDR_SIZE)
+#define EHDR_MAX_SIZE (EHDR_CFG_SIZE)
+#define EMSG_OVERHEAD (EHDR_SIZE + TIPC_AES_GCM_TAG_SIZE)
+} __packed;
+
+int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
+ struct tipc_node *node);
+void tipc_crypto_stop(struct tipc_crypto **crypto);
+void tipc_crypto_timeout(struct tipc_crypto *rx);
+int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
+ struct tipc_bearer *b, struct tipc_media_addr *dst,
+ struct tipc_node *__dnode);
+int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
+ struct sk_buff **skb, struct tipc_bearer *b);
+int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
+ u8 mode);
+void tipc_crypto_key_flush(struct tipc_crypto *c);
+int tipc_aead_key_validate(struct tipc_aead_key *ukey);
+bool tipc_ehdr_validate(struct sk_buff *skb);
+
+#endif /* _TIPC_CRYPTO_H */
+#endif
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index c138d68e8a69..b043e8c6397a 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -94,6 +94,7 @@ static void tipc_disc_init_msg(struct net *net, struct sk_buff *skb,
msg_set_dest_domain(hdr, dest_domain);
msg_set_bc_netid(hdr, tn->net_id);
b->media->addr2msg(msg_media_addr(hdr), &b->addr);
+ msg_set_peer_net_hash(hdr, tipc_net_hash_mixes(net, tn->random));
msg_set_node_id(hdr, tipc_own_id(net));
}
@@ -242,7 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
if (!tipc_in_scope(legacy, b->domain, src))
return;
tipc_node_check_dest(net, src, peer_id, b, caps, signature,
- &maddr, &respond, &dupl_addr);
+ msg_peer_net_hash(hdr), &maddr, &respond,
+ &dupl_addr);
if (dupl_addr)
disc_dupl_alert(b, src, &maddr);
if (!respond)
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 63f39201e41e..89257e2a980d 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -199,7 +199,7 @@ void tipc_group_join(struct net *net, struct tipc_group *grp, int *sk_rcvbuf)
struct tipc_member *m, *tmp;
struct sk_buff_head xmitq;
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, &xmitq);
tipc_group_update_member(m, 0);
@@ -218,6 +218,7 @@ void tipc_group_delete(struct net *net, struct tipc_group *grp)
rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
+ __skb_queue_purge(&m->deferredq);
list_del(&m->list);
kfree(m);
}
@@ -434,7 +435,7 @@ bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
return true;
if (state == MBR_PENDING && adv == ADV_IDLE)
return true;
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq);
tipc_node_distr_xmit(grp->net, &xmitq);
return true;
@@ -917,7 +918,7 @@ void tipc_group_member_evt(struct tipc_group *grp,
int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb)
{
- struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP);
+ struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP);
if (!group)
return -EMSGSIZE;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 341ecd796aa4..24d4d10756d3 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -44,6 +44,7 @@
#include "netlink.h"
#include "monitor.h"
#include "trace.h"
+#include "crypto.h"
#include <linux/pkt_sched.h>
@@ -106,9 +107,6 @@ struct tipc_stats {
* @transmitq: queue for sent, non-acked messages
* @backlogq: queue for messages waiting to be sent
* @snt_nxt: next sequence number to use for outbound messages
- * @prev_from: sequence number of most previous retransmission request
- * @stale_cnt: counter for number of identical retransmit attempts
- * @stale_limit: time when repeated identical retransmits must force link reset
* @ackers: # of peers that needs to ack each packet before it can be released
* @acked: # last packet acked by a certain peer. Used for broadcast.
* @rcv_nxt: next sequence number to expect for inbound messages
@@ -151,6 +149,7 @@ struct tipc_link {
/* Failover/synch */
u16 drop_point;
struct sk_buff *failover_reasm_skb;
+ struct sk_buff_head failover_deferdq;
/* Max packet negotiation */
u16 mtu;
@@ -162,12 +161,10 @@ struct tipc_link {
struct {
u16 len;
u16 limit;
+ struct sk_buff *target_bskb;
} backlog[5];
u16 snd_nxt;
- u16 prev_from;
u16 window;
- u16 stale_cnt;
- unsigned long stale_limit;
/* Reception */
u16 rcv_nxt;
@@ -181,6 +178,7 @@ struct tipc_link {
/* Fragmentation/reassembly */
struct sk_buff *reasm_buf;
+ struct sk_buff *reasm_tnlmsg;
/* Broadcast */
u16 ackers;
@@ -208,7 +206,8 @@ enum {
BC_NACK_SND_SUPPRESS,
};
-#define TIPC_BC_RETR_LIM msecs_to_jiffies(10) /* [ms] */
+#define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10))
+#define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1))
/*
* Interval between NACKs when packets arrive out of order
@@ -246,6 +245,10 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
static void tipc_link_build_bc_init_msg(struct tipc_link *l,
struct sk_buff_head *xmitq);
static bool tipc_link_release_pkts(struct tipc_link *l, u16 to);
+static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data);
+static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
+ struct tipc_gap_ack_blks *ga,
+ struct sk_buff_head *xmitq);
/*
* Simple non-static link routines (i.e. referenced outside this file)
@@ -395,6 +398,15 @@ int tipc_link_mtu(struct tipc_link *l)
return l->mtu;
}
+int tipc_link_mss(struct tipc_link *l)
+{
+#ifdef CONFIG_TIPC_CRYPTO
+ return l->mtu - INT_H_SIZE - EMSG_OVERHEAD;
+#else
+ return l->mtu - INT_H_SIZE;
+#endif
+}
+
u16 tipc_link_rcv_nxt(struct tipc_link *l)
{
return l->rcv_nxt;
@@ -493,6 +505,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
__skb_queue_head_init(&l->transmq);
__skb_queue_head_init(&l->backlogq);
__skb_queue_head_init(&l->deferdq);
+ __skb_queue_head_init(&l->failover_deferdq);
skb_queue_head_init(&l->wakeupq);
skb_queue_head_init(l->inputq);
return true;
@@ -537,7 +550,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
/* Disable replicast if even a single peer doesn't support it */
if (link_is_bc_rcvlink(l) && !(peer_caps & TIPC_BCAST_RCAST))
- tipc_bcast_disable_rcast(net);
+ tipc_bcast_toggle_rcast(net, false);
return true;
}
@@ -727,7 +740,7 @@ static void link_profile_stats(struct tipc_link *l)
if (msg_user(msg) == MSG_FRAGMENTER) {
if (msg_type(msg) != FIRST_FRAGMENT)
return;
- length = msg_size(msg_get_wrapped(msg));
+ length = msg_size(msg_inner_hdr(msg));
}
l->stats.msg_lengths_total += length;
l->stats.msg_length_counts++;
@@ -848,27 +861,43 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
*/
static void link_prepare_wakeup(struct tipc_link *l)
{
+ struct sk_buff_head *wakeupq = &l->wakeupq;
+ struct sk_buff_head *inputq = l->inputq;
struct sk_buff *skb, *tmp;
- int imp, i = 0;
+ struct sk_buff_head tmpq;
+ int avail[5] = {0,};
+ int imp = 0;
+
+ __skb_queue_head_init(&tmpq);
+
+ for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++)
+ avail[imp] = l->backlog[imp].limit - l->backlog[imp].len;
- skb_queue_walk_safe(&l->wakeupq, skb, tmp) {
+ skb_queue_walk_safe(wakeupq, skb, tmp) {
imp = TIPC_SKB_CB(skb)->chain_imp;
- if (l->backlog[imp].len < l->backlog[imp].limit) {
- skb_unlink(skb, &l->wakeupq);
- skb_queue_tail(l->inputq, skb);
- } else if (i++ > 10) {
- break;
- }
+ if (avail[imp] <= 0)
+ continue;
+ avail[imp]--;
+ __skb_unlink(skb, wakeupq);
+ __skb_queue_tail(&tmpq, skb);
}
+
+ spin_lock_bh(&inputq->lock);
+ skb_queue_splice_tail(&tmpq, inputq);
+ spin_unlock_bh(&inputq->lock);
+
}
void tipc_link_reset(struct tipc_link *l)
{
struct sk_buff_head list;
+ u32 imp;
__skb_queue_head_init(&list);
l->in_session = false;
+ /* Force re-synch of peer session number before establishing */
+ l->peer_session--;
l->session++;
l->mtu = l->advertised_mtu;
@@ -883,14 +912,16 @@ void tipc_link_reset(struct tipc_link *l)
__skb_queue_purge(&l->transmq);
__skb_queue_purge(&l->deferdq);
__skb_queue_purge(&l->backlogq);
- l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
- l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
- l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
- l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0;
- l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0;
+ __skb_queue_purge(&l->failover_deferdq);
+ for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) {
+ l->backlog[imp].len = 0;
+ l->backlog[imp].target_bskb = NULL;
+ }
kfree_skb(l->reasm_buf);
+ kfree_skb(l->reasm_tnlmsg);
kfree_skb(l->failover_reasm_skb);
l->reasm_buf = NULL;
+ l->reasm_tnlmsg = NULL;
l->failover_reasm_skb = NULL;
l->rcv_unacked = 0;
l->snd_nxt = 1;
@@ -900,7 +931,6 @@ void tipc_link_reset(struct tipc_link *l)
l->acked = 0;
l->silent_intv_cnt = 0;
l->rst_cnt = 0;
- l->stale_cnt = 0;
l->bc_peer_is_up = false;
memset(&l->mon_state, 0, sizeof(l->mon_state));
tipc_link_reset_stats(l);
@@ -920,20 +950,25 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
struct sk_buff_head *xmitq)
{
struct tipc_msg *hdr = buf_msg(skb_peek(list));
- unsigned int maxwin = l->window;
- int imp = msg_importance(hdr);
- unsigned int mtu = l->mtu;
+ struct sk_buff_head *backlogq = &l->backlogq;
+ struct sk_buff_head *transmq = &l->transmq;
+ struct sk_buff *skb, *_skb;
+ u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
u16 ack = l->rcv_nxt - 1;
u16 seqno = l->snd_nxt;
- u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
- struct sk_buff_head *transmq = &l->transmq;
- struct sk_buff_head *backlogq = &l->backlogq;
- struct sk_buff *skb, *_skb, *bskb;
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 mtu = l->mtu;
+ bool new_bundle;
int rc = 0;
if (unlikely(msg_size(hdr) > mtu)) {
- skb_queue_purge(list);
+ pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n",
+ skb_queue_len(list), msg_user(hdr),
+ msg_type(hdr), msg_size(hdr), mtu);
+ __skb_queue_purge(list);
return -EMSGSIZE;
}
@@ -952,25 +987,22 @@ 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_queue_len(list)) {
- skb = skb_peek(list);
- hdr = buf_msg(skb);
- msg_set_seqno(hdr, seqno);
- msg_set_ack(hdr, ack);
- msg_set_bcast_ack(hdr, bc_ack);
-
+ while ((skb = __skb_dequeue(list))) {
if (likely(skb_queue_len(transmq) < maxwin)) {
+ hdr = buf_msg(skb);
+ msg_set_seqno(hdr, seqno);
+ msg_set_ack(hdr, ack);
+ msg_set_bcast_ack(hdr, bc_ack);
_skb = skb_clone(skb, GFP_ATOMIC);
if (!_skb) {
- skb_queue_purge(list);
+ kfree_skb(skb);
+ __skb_queue_purge(list);
return -ENOBUFS;
}
- __skb_dequeue(list);
__skb_queue_tail(transmq, skb);
/* next retransmit attempt */
if (link_is_bc_sndlink(l))
- TIPC_SKB_CB(skb)->nxt_retr =
- jiffies + TIPC_BC_RETR_LIM;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
__skb_queue_tail(xmitq, _skb);
TIPC_SKB_CB(skb)->ackers = l->ackers;
l->rcv_unacked = 0;
@@ -978,20 +1010,25 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
seqno++;
continue;
}
- if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) {
- kfree_skb(__skb_dequeue(list));
- l->stats.sent_bundled++;
- continue;
- }
- if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) {
- kfree_skb(__skb_dequeue(list));
- __skb_queue_tail(backlogq, bskb);
- l->backlog[msg_importance(buf_msg(bskb))].len++;
- l->stats.sent_bundled++;
- l->stats.sent_bundles++;
+ if (tipc_msg_try_bundle(l->backlog[imp].target_bskb, &skb,
+ mss, l->addr, &new_bundle)) {
+ if (skb) {
+ /* Keep a ref. to the skb for next try */
+ l->backlog[imp].target_bskb = skb;
+ l->backlog[imp].len++;
+ __skb_queue_tail(backlogq, skb);
+ } else {
+ if (new_bundle) {
+ l->stats.sent_bundles++;
+ l->stats.sent_bundled++;
+ }
+ l->stats.sent_bundled++;
+ }
continue;
}
- l->backlog[imp].len += skb_queue_len(list);
+ l->backlog[imp].target_bskb = NULL;
+ l->backlog[imp].len += (1 + skb_queue_len(list));
+ __skb_queue_tail(backlogq, skb);
skb_queue_splice_tail_init(list, backlogq);
}
l->snd_nxt = seqno;
@@ -1006,6 +1043,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
u16 seqno = l->snd_nxt;
u16 ack = l->rcv_nxt - 1;
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ u32 imp;
while (skb_queue_len(&l->transmq) < l->window) {
skb = skb_peek(&l->backlogq);
@@ -1016,11 +1054,14 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
break;
__skb_dequeue(&l->backlogq);
hdr = buf_msg(skb);
- l->backlog[msg_importance(hdr)].len--;
+ imp = msg_importance(hdr);
+ l->backlog[imp].len--;
+ if (unlikely(skb == l->backlog[imp].target_bskb))
+ l->backlog[imp].target_bskb = NULL;
__skb_queue_tail(&l->transmq, skb);
/* next retransmit attempt */
if (link_is_bc_sndlink(l))
- TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
__skb_queue_tail(xmitq, _skb);
TIPC_SKB_CB(skb)->ackers = l->ackers;
@@ -1034,32 +1075,74 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
l->snd_nxt = seqno;
}
-static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb)
+/**
+ * link_retransmit_failure() - Detect repeated retransmit failures
+ * @l: tipc link sender
+ * @r: tipc link receiver (= l in case of unicast)
+ * @rc: returned code
+ *
+ * Return: true if the repeated retransmit failures happens, otherwise
+ * false
+ */
+static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r,
+ int *rc)
{
- struct tipc_msg *hdr = buf_msg(skb);
+ struct sk_buff *skb = skb_peek(&l->transmq);
+ struct tipc_msg *hdr;
+
+ if (!skb)
+ return false;
+
+ if (!TIPC_SKB_CB(skb)->retr_cnt)
+ return false;
+
+ if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp +
+ msecs_to_jiffies(r->tolerance * 10)))
+ return false;
+
+ hdr = buf_msg(skb);
+ if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr)))
+ return false;
pr_warn("Retransmission failure on link <%s>\n", l->name);
link_print(l, "State of link ");
pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr));
- pr_info("sqno %u, prev: %x, src: %x\n",
- msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
+ pr_info("sqno %u, prev: %x, dest: %x\n",
+ msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr));
+ pr_info("retr_stamp %d, retr_cnt %d\n",
+ jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp),
+ TIPC_SKB_CB(skb)->retr_cnt);
+
+ trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
+ trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
+ trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
+
+ if (link_is_bc_sndlink(l)) {
+ r->state = LINK_RESET;
+ *rc = TIPC_LINK_DOWN_EVT;
+ } else {
+ *rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
+ }
+
+ return true;
}
-/* tipc_link_retrans() - retransmit one or more packets
+/* tipc_link_bc_retrans() - retransmit zero or more packets
* @l: the link to transmit on
* @r: the receiving link ordering the retransmit. Same as l if unicast
* @from: retransmit from (inclusive) this sequence number
* @to: retransmit to (inclusive) this sequence number
* xmitq: queue for accumulating the retransmitted packets
*/
-static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
- u16 from, u16 to, struct sk_buff_head *xmitq)
+static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r,
+ u16 from, u16 to, struct sk_buff_head *xmitq)
{
struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
u16 ack = l->rcv_nxt - 1;
struct tipc_msg *hdr;
+ int rc = 0;
if (!skb)
return 0;
@@ -1067,20 +1150,9 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
return 0;
trace_tipc_link_retrans(r, from, to, &l->transmq);
- /* Detect repeated retransmit failures on same packet */
- if (r->prev_from != from) {
- r->prev_from = from;
- r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
- r->stale_cnt = 0;
- } else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
- link_retransmit_failure(l, skb);
- trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
- trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
- trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
- if (link_is_bc_sndlink(l))
- return TIPC_LINK_DOWN_EVT;
- return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
- }
+
+ if (link_retransmit_failure(l, r, &rc))
+ return rc;
skb_queue_walk(&l->transmq, skb) {
hdr = buf_msg(skb);
@@ -1088,12 +1160,11 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
continue;
if (more(msg_seqno(hdr), to))
break;
- if (link_is_bc_sndlink(l)) {
- if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
- continue;
- TIPC_SKB_CB(skb)->nxt_retr = jiffies + TIPC_BC_RETR_LIM;
- }
- _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
+
+ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
+ continue;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
+ _skb = pskb_copy(skb, GFP_ATOMIC);
if (!_skb)
return 0;
hdr = buf_msg(_skb);
@@ -1102,6 +1173,10 @@ static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
_skb->priority = TC_PRIO_CONTROL;
__skb_queue_tail(xmitq, _skb);
l->stats.retransmitted++;
+
+ /* Increase actual retrans counter & mark first time */
+ if (!TIPC_SKB_CB(skb)->retr_cnt++)
+ TIPC_SKB_CB(skb)->retr_stamp = jiffies;
}
return 0;
}
@@ -1154,34 +1229,14 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
* Consumes buffer
*/
static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb,
- struct sk_buff_head *inputq)
+ struct sk_buff_head *inputq,
+ struct sk_buff **reasm_skb)
{
struct tipc_msg *hdr = buf_msg(skb);
- struct sk_buff **reasm_skb = &l->reasm_buf;
struct sk_buff *iskb;
struct sk_buff_head tmpq;
int usr = msg_user(hdr);
- int rc = 0;
int pos = 0;
- int ipos = 0;
-
- if (unlikely(usr == TUNNEL_PROTOCOL)) {
- if (msg_type(hdr) == SYNCH_MSG) {
- __skb_queue_purge(&l->deferdq);
- goto drop;
- }
- if (!tipc_msg_extract(skb, &iskb, &ipos))
- return rc;
- kfree_skb(skb);
- skb = iskb;
- hdr = buf_msg(skb);
- if (less(msg_seqno(hdr), l->drop_point))
- goto drop;
- if (tipc_data_input(l, skb, inputq))
- return rc;
- usr = msg_user(hdr);
- reasm_skb = &l->failover_reasm_skb;
- }
if (usr == MSG_BUNDLER) {
skb_queue_head_init(&tmpq);
@@ -1206,11 +1261,83 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb,
tipc_link_bc_init_rcv(l->bc_rcvlink, hdr);
tipc_bcast_unlock(l->net);
}
-drop:
+
kfree_skb(skb);
return 0;
}
+/* tipc_link_tnl_rcv() - receive TUNNEL_PROTOCOL message, drop or process the
+ * inner message along with the ones in the old link's
+ * deferdq
+ * @l: tunnel link
+ * @skb: TUNNEL_PROTOCOL message
+ * @inputq: queue to put messages ready for delivery
+ */
+static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb,
+ struct sk_buff_head *inputq)
+{
+ struct sk_buff **reasm_skb = &l->failover_reasm_skb;
+ struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg;
+ struct sk_buff_head *fdefq = &l->failover_deferdq;
+ struct tipc_msg *hdr = buf_msg(skb);
+ struct sk_buff *iskb;
+ int ipos = 0;
+ int rc = 0;
+ u16 seqno;
+
+ if (msg_type(hdr) == SYNCH_MSG) {
+ kfree_skb(skb);
+ return 0;
+ }
+
+ /* Not a fragment? */
+ if (likely(!msg_nof_fragms(hdr))) {
+ if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) {
+ pr_warn_ratelimited("Unable to extract msg, defq: %d\n",
+ skb_queue_len(fdefq));
+ return 0;
+ }
+ kfree_skb(skb);
+ } else {
+ /* Set fragment type for buf_append */
+ if (msg_fragm_no(hdr) == 1)
+ msg_set_type(hdr, FIRST_FRAGMENT);
+ else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr))
+ msg_set_type(hdr, FRAGMENT);
+ else
+ msg_set_type(hdr, LAST_FRAGMENT);
+
+ if (!tipc_buf_append(reasm_tnlmsg, &skb)) {
+ /* Successful but non-complete reassembly? */
+ if (*reasm_tnlmsg || link_is_bc_rcvlink(l))
+ return 0;
+ pr_warn_ratelimited("Unable to reassemble tunnel msg\n");
+ return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
+ }
+ iskb = skb;
+ }
+
+ do {
+ seqno = buf_seqno(iskb);
+ if (unlikely(less(seqno, l->drop_point))) {
+ kfree_skb(iskb);
+ continue;
+ }
+ if (unlikely(seqno != l->drop_point)) {
+ __tipc_skb_queue_sorted(fdefq, seqno, iskb);
+ continue;
+ }
+
+ l->drop_point++;
+ if (!tipc_data_input(l, iskb, inputq))
+ rc |= tipc_link_input(l, iskb, inputq, reasm_skb);
+ if (unlikely(rc))
+ break;
+ } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point)));
+
+ return rc;
+}
+
static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
{
bool released = false;
@@ -1226,6 +1353,120 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
return released;
}
+/* tipc_build_gap_ack_blks - build Gap ACK blocks
+ * @l: tipc link that data have come with gaps in sequence if any
+ * @data: data buffer to store the Gap ACK blocks after built
+ *
+ * returns the actual allocated memory size
+ */
+static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data)
+{
+ struct sk_buff *skb = skb_peek(&l->deferdq);
+ struct tipc_gap_ack_blks *ga = data;
+ u16 len, expect, seqno = 0;
+ u8 n = 0;
+
+ if (!skb)
+ goto exit;
+
+ expect = buf_seqno(skb);
+ skb_queue_walk(&l->deferdq, skb) {
+ seqno = buf_seqno(skb);
+ if (unlikely(more(seqno, expect))) {
+ ga->gacks[n].ack = htons(expect - 1);
+ ga->gacks[n].gap = htons(seqno - expect);
+ if (++n >= MAX_GAP_ACK_BLKS) {
+ pr_info_ratelimited("Too few Gap ACK blocks!\n");
+ goto exit;
+ }
+ } else if (unlikely(less(seqno, expect))) {
+ pr_warn("Unexpected skb in deferdq!\n");
+ continue;
+ }
+ expect = seqno + 1;
+ }
+
+ /* last block */
+ ga->gacks[n].ack = htons(seqno);
+ ga->gacks[n].gap = 0;
+ n++;
+
+exit:
+ len = tipc_gap_ack_blks_sz(n);
+ ga->len = htons(len);
+ ga->gack_cnt = n;
+ return len;
+}
+
+/* tipc_link_advance_transmq - advance TIPC link transmq queue by releasing
+ * acked packets, also doing retransmissions if
+ * gaps found
+ * @l: tipc link with transmq queue to be advanced
+ * @acked: seqno of last packet acked by peer without any gaps before
+ * @gap: # of gap packets
+ * @ga: buffer pointer to Gap ACK blocks from peer
+ * @xmitq: queue for accumulating the retransmitted packets if any
+ *
+ * In case of a repeated retransmit failures, the call will return shortly
+ * with a returned code (e.g. TIPC_LINK_DOWN_EVT)
+ */
+static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap,
+ struct tipc_gap_ack_blks *ga,
+ struct sk_buff_head *xmitq)
+{
+ struct sk_buff *skb, *_skb, *tmp;
+ struct tipc_msg *hdr;
+ u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+ u16 ack = l->rcv_nxt - 1;
+ bool passed = false;
+ u16 seqno, n = 0;
+ int rc = 0;
+
+ skb_queue_walk_safe(&l->transmq, skb, tmp) {
+ seqno = buf_seqno(skb);
+
+next_gap_ack:
+ if (less_eq(seqno, acked)) {
+ /* release skb */
+ __skb_unlink(skb, &l->transmq);
+ kfree_skb(skb);
+ } else if (less_eq(seqno, acked + gap)) {
+ /* First, check if repeated retrans failures occurs? */
+ if (!passed && link_retransmit_failure(l, l, &rc))
+ return rc;
+ passed = true;
+
+ /* retransmit skb if unrestricted*/
+ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
+ continue;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME;
+ _skb = pskb_copy(skb, GFP_ATOMIC);
+ if (!_skb)
+ continue;
+ hdr = buf_msg(_skb);
+ msg_set_ack(hdr, ack);
+ msg_set_bcast_ack(hdr, bc_ack);
+ _skb->priority = TC_PRIO_CONTROL;
+ __skb_queue_tail(xmitq, _skb);
+ l->stats.retransmitted++;
+
+ /* Increase actual retrans counter & mark first time */
+ if (!TIPC_SKB_CB(skb)->retr_cnt++)
+ TIPC_SKB_CB(skb)->retr_stamp = jiffies;
+ } else {
+ /* retry with Gap ACK blocks if any */
+ if (!ga || n >= ga->gack_cnt)
+ break;
+ acked = ntohs(ga->gacks[n].ack);
+ gap = ntohs(ga->gacks[n].gap);
+ n++;
+ goto next_gap_ack;
+ }
+ }
+
+ return 0;
+}
+
/* tipc_link_build_state_msg: prepare link state message for transmission
*
* Note that sending of broadcast ack is coordinated among nodes, to reduce
@@ -1280,6 +1521,7 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
struct sk_buff_head *xmitq)
{
u32 def_cnt = ++l->stats.deferred_recv;
+ u32 defq_len = skb_queue_len(&l->deferdq);
int match1, match2;
if (link_is_bc_rcvlink(l)) {
@@ -1290,7 +1532,7 @@ static int tipc_link_build_nack_msg(struct tipc_link *l,
return 0;
}
- if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV))
+ if (defq_len >= 3 && !((defq_len - 3) % 16))
tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq);
return 0;
}
@@ -1304,29 +1546,29 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *xmitq)
{
struct sk_buff_head *defq = &l->deferdq;
- struct tipc_msg *hdr;
+ struct tipc_msg *hdr = buf_msg(skb);
u16 seqno, rcv_nxt, win_lim;
int rc = 0;
+ /* Verify and update link state */
+ if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
+ return tipc_link_proto_rcv(l, skb, xmitq);
+
+ /* Don't send probe at next timeout expiration */
+ l->silent_intv_cnt = 0;
+
do {
hdr = buf_msg(skb);
seqno = msg_seqno(hdr);
rcv_nxt = l->rcv_nxt;
win_lim = rcv_nxt + TIPC_MAX_LINK_WIN;
- /* Verify and update link state */
- if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
- return tipc_link_proto_rcv(l, skb, xmitq);
-
if (unlikely(!link_is_up(l))) {
if (l->state == LINK_ESTABLISHING)
rc = TIPC_LINK_UP_EVT;
goto drop;
}
- /* Don't send probe at next timeout expiration */
- l->silent_intv_cnt = 0;
-
/* Drop if outside receive window */
if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) {
l->stats.duplicates++;
@@ -1335,7 +1577,6 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
/* Forward queues and wake up waiting users */
if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
- l->stale_cnt = 0;
tipc_link_advance_backlog(l, xmitq);
if (unlikely(!skb_queue_empty(&l->wakeupq)))
link_prepare_wakeup(l);
@@ -1351,13 +1592,16 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
/* Deliver packet */
l->rcv_nxt++;
l->stats.recv_pkts++;
- if (!tipc_data_input(l, skb, l->inputq))
- rc |= tipc_link_input(l, skb, l->inputq);
+
+ if (unlikely(msg_user(hdr) == TUNNEL_PROTOCOL))
+ rc |= tipc_link_tnl_rcv(l, skb, l->inputq);
+ else if (!tipc_data_input(l, skb, l->inputq))
+ rc |= tipc_link_input(l, skb, l->inputq, &l->reasm_buf);
if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN))
rc |= tipc_link_build_state_msg(l, xmitq);
if (unlikely(rc & ~TIPC_LINK_SND_STATE))
break;
- } while ((skb = __skb_dequeue(defq)));
+ } while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt)));
return rc;
drop:
@@ -1378,6 +1622,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
struct tipc_mon_state *mstate = &l->mon_state;
int dlen = 0;
void *data;
+ u16 glen = 0;
/* Don't send protocol message during reset or link failover */
if (tipc_link_is_blocked(l))
@@ -1390,8 +1635,8 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
- tipc_max_domain_size, l->addr,
- tipc_own_addr(l->net), 0, 0, 0);
+ tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ,
+ l->addr, tipc_own_addr(l->net), 0, 0, 0);
if (!skb)
return;
@@ -1418,9 +1663,11 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
msg_set_probe(hdr, probe);
msg_set_is_keepalive(hdr, probe || probe_reply);
- tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id);
- msg_set_size(hdr, INT_H_SIZE + dlen);
- skb_trim(skb, INT_H_SIZE + dlen);
+ if (l->peer_caps & TIPC_GAP_ACK_BLOCK)
+ glen = tipc_build_gap_ack_blks(l, data);
+ tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id);
+ msg_set_size(hdr, INT_H_SIZE + glen + dlen);
+ skb_trim(skb, INT_H_SIZE + glen + dlen);
l->stats.sent_states++;
l->rcv_unacked = 0;
} else {
@@ -1452,7 +1699,7 @@ void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
struct sk_buff *skb;
u32 dnode = l->addr;
- skb_queue_head_init(&tnlq);
+ __skb_queue_head_init(&tnlq);
skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG,
INT_H_SIZE, BASIC_H_SIZE,
dnode, onode, 0, 0, 0);
@@ -1479,18 +1726,47 @@ void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
int mtyp, struct sk_buff_head *xmitq)
{
+ struct sk_buff_head *fdefq = &tnl->failover_deferdq;
struct sk_buff *skb, *tnlskb;
struct tipc_msg *hdr, tnlhdr;
struct sk_buff_head *queue = &l->transmq;
- struct sk_buff_head tmpxq, tnlq;
+ struct sk_buff_head tmpxq, tnlq, frags;
u16 pktlen, pktcnt, seqno = l->snd_nxt;
+ bool pktcnt_need_update = false;
+ u16 syncpt;
+ int rc;
if (!tnl)
return;
- skb_queue_head_init(&tnlq);
- skb_queue_head_init(&tmpxq);
+ __skb_queue_head_init(&tnlq);
+ /* Link Synching:
+ * From now on, send only one single ("dummy") SYNCH message
+ * to peer. The SYNCH message does not contain any data, just
+ * a header conveying the synch point to the peer.
+ */
+ if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) {
+ tnlskb = tipc_msg_create(TUNNEL_PROTOCOL, SYNCH_MSG,
+ INT_H_SIZE, 0, l->addr,
+ tipc_own_addr(l->net),
+ 0, 0, 0);
+ if (!tnlskb) {
+ pr_warn("%sunable to create dummy SYNCH_MSG\n",
+ link_co_err);
+ return;
+ }
+ hdr = buf_msg(tnlskb);
+ syncpt = l->snd_nxt + skb_queue_len(&l->backlogq) - 1;
+ msg_set_syncpt(hdr, syncpt);
+ msg_set_bearer_id(hdr, l->peer_bearer_id);
+ __skb_queue_tail(&tnlq, tnlskb);
+ tipc_link_xmit(tnl, &tnlq, xmitq);
+ return;
+ }
+
+ __skb_queue_head_init(&tmpxq);
+ __skb_queue_head_init(&frags);
/* At least one packet required for safe algorithm => add dummy */
skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG,
BASIC_H_SIZE, 0, l->addr, tipc_own_addr(l->net),
@@ -1499,14 +1775,18 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
pr_warn("%sunable to create tunnel packet\n", link_co_err);
return;
}
- skb_queue_tail(&tnlq, skb);
+ __skb_queue_tail(&tnlq, skb);
tipc_link_xmit(l, &tnlq, &tmpxq);
__skb_queue_purge(&tmpxq);
/* Initialize reusable tunnel packet header */
tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL,
mtyp, INT_H_SIZE, l->addr);
- pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq);
+ if (mtyp == SYNCH_MSG)
+ pktcnt = l->snd_nxt - buf_seqno(skb_peek(&l->transmq));
+ else
+ pktcnt = skb_queue_len(&l->transmq);
+ pktcnt += skb_queue_len(&l->backlogq);
msg_set_msgcnt(&tnlhdr, pktcnt);
msg_set_bearer_id(&tnlhdr, l->peer_bearer_id);
tnl:
@@ -1516,6 +1796,39 @@ tnl:
if (queue == &l->backlogq)
msg_set_seqno(hdr, seqno++);
pktlen = msg_size(hdr);
+
+ /* Tunnel link MTU is not large enough? This could be
+ * due to:
+ * 1) Link MTU has just changed or set differently;
+ * 2) Or FAILOVER on the top of a SYNCH message
+ *
+ * The 2nd case should not happen if peer supports
+ * TIPC_TUNNEL_ENHANCED
+ */
+ if (pktlen > tnl->mtu - INT_H_SIZE) {
+ if (mtyp == FAILOVER_MSG &&
+ (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) {
+ rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu,
+ &frags);
+ if (rc) {
+ pr_warn("%sunable to frag msg: rc %d\n",
+ link_co_err, rc);
+ return;
+ }
+ pktcnt += skb_queue_len(&frags) - 1;
+ pktcnt_need_update = true;
+ skb_queue_splice_tail_init(&frags, &tnlq);
+ continue;
+ }
+ /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED
+ * => Just warn it and return!
+ */
+ pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n",
+ link_co_err, msg_user(hdr),
+ msg_type(hdr), msg_size(hdr));
+ return;
+ }
+
msg_set_size(&tnlhdr, pktlen + INT_H_SIZE);
tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC);
if (!tnlskb) {
@@ -1531,12 +1844,60 @@ tnl:
goto tnl;
}
+ if (pktcnt_need_update)
+ skb_queue_walk(&tnlq, skb) {
+ hdr = buf_msg(skb);
+ msg_set_msgcnt(hdr, pktcnt);
+ }
+
tipc_link_xmit(tnl, &tnlq, xmitq);
if (mtyp == FAILOVER_MSG) {
tnl->drop_point = l->rcv_nxt;
tnl->failover_reasm_skb = l->reasm_buf;
l->reasm_buf = NULL;
+
+ /* Failover the link's deferdq */
+ if (unlikely(!skb_queue_empty(fdefq))) {
+ pr_warn("Link failover deferdq not empty: %d!\n",
+ skb_queue_len(fdefq));
+ __skb_queue_purge(fdefq);
+ }
+ skb_queue_splice_init(&l->deferdq, fdefq);
+ }
+}
+
+/**
+ * tipc_link_failover_prepare() - prepare tnl for link failover
+ *
+ * This is a special version of the precursor - tipc_link_tnl_prepare(),
+ * see the tipc_node_link_failover() for details
+ *
+ * @l: failover link
+ * @tnl: tunnel link
+ * @xmitq: queue for messages to be xmited
+ */
+void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl,
+ struct sk_buff_head *xmitq)
+{
+ struct sk_buff_head *fdefq = &tnl->failover_deferdq;
+
+ tipc_link_create_dummy_tnl_msg(tnl, xmitq);
+
+ /* This failover link endpoint was never established before,
+ * so it has not received anything from peer.
+ * Otherwise, it must be a normal failover situation or the
+ * node has entered SELF_DOWN_PEER_LEAVING and both peer nodes
+ * would have to start over from scratch instead.
+ */
+ tnl->drop_point = 1;
+ tnl->failover_reasm_skb = NULL;
+
+ /* Initiate the link's failover deferdq */
+ if (unlikely(!skb_queue_empty(fdefq))) {
+ pr_warn("Link failover deferdq not empty: %d!\n",
+ skb_queue_len(fdefq));
+ __skb_queue_purge(fdefq);
}
}
@@ -1590,6 +1951,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *xmitq)
{
struct tipc_msg *hdr = buf_msg(skb);
+ struct tipc_gap_ack_blks *ga = NULL;
u16 rcvgap = 0;
u16 ack = msg_ack(hdr);
u16 gap = msg_seq_gap(hdr);
@@ -1600,6 +1962,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
u16 dlen = msg_data_sz(hdr);
int mtyp = msg_type(hdr);
bool reply = msg_probe(hdr);
+ u16 glen = 0;
void *data;
char *if_name;
int rc = 0;
@@ -1697,7 +2060,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
rc = TIPC_LINK_UP_EVT;
break;
}
- tipc_mon_rcv(l->net, data, dlen, l->addr,
+
+ /* Receive Gap ACK blocks from peer if any */
+ if (l->peer_caps & TIPC_GAP_ACK_BLOCK) {
+ ga = (struct tipc_gap_ack_blks *)data;
+ glen = ntohs(ga->len);
+ /* sanity check: if failed, ignore Gap ACK blocks */
+ if (glen != tipc_gap_ack_blks_sz(ga->gack_cnt))
+ ga = NULL;
+ }
+
+ tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr,
&l->mon_state, l->bearer_id);
/* Send NACK if peer has sent pkts we haven't received yet */
@@ -1706,13 +2079,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
if (rcvgap || reply)
tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
rcvgap, 0, 0, xmitq);
- tipc_link_release_pkts(l, ack);
+
+ rc |= tipc_link_advance_transmq(l, ack, gap, ga, xmitq);
/* If NACK, retransmit will now start at right position */
- if (gap) {
- rc = tipc_link_retrans(l, l, ack + 1, ack + gap, xmitq);
+ if (gap)
l->stats.recv_nacks++;
- }
tipc_link_advance_backlog(l, xmitq);
if (unlikely(!skb_queue_empty(&l->wakeupq)))
@@ -1825,7 +2197,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
if (more(peers_snd_nxt, l->rcv_nxt + l->window))
return rc;
- rc = tipc_link_retrans(snd_l, l, from, to, xmitq);
+ rc = tipc_link_bc_retrans(snd_l, l, from, to, xmitq);
l->snd_nxt = peers_snd_nxt;
if (link_bc_rcv_gap(l))
@@ -1921,7 +2293,7 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
if (dnode == tipc_own_addr(l->net)) {
tipc_link_bc_ack_rcv(l, acked, xmitq);
- rc = tipc_link_retrans(l->bc_sndlink, l, from, to, xmitq);
+ rc = tipc_link_bc_retrans(l->bc_sndlink, l, from, to, xmitq);
l->stats.recv_nacks++;
return rc;
}
@@ -1972,8 +2344,8 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
{
int err;
- err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop,
- tipc_nl_prop_policy, NULL);
+ err = nla_parse_nested_deprecated(props, TIPC_NLA_PROP_MAX, prop,
+ tipc_nl_prop_policy, NULL);
if (err)
return err;
@@ -2052,7 +2424,7 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s)
(s->accu_queue_sz / s->queue_sz_counts) : 0}
};
- stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+ stats = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS);
if (!stats)
return -EMSGSIZE;
@@ -2084,7 +2456,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK);
if (!attrs)
goto msg_full;
@@ -2106,7 +2478,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE))
goto attr_msg_full;
- prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+ prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP);
if (!prop)
goto attr_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
@@ -2173,7 +2545,7 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb,
(stats->accu_queue_sz / stats->queue_sz_counts) : 0}
};
- nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+ nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS);
if (!nest)
return -EMSGSIZE;
@@ -2197,6 +2569,8 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
struct nlattr *attrs;
struct nlattr *prop;
struct tipc_net *tn = net_generic(net, tipc_net_id);
+ u32 bc_mode = tipc_bcast_get_broadcast_mode(net);
+ u32 bc_ratio = tipc_bcast_get_broadcast_ratio(net);
struct tipc_link *bcl = tn->bcl;
if (!bcl)
@@ -2211,7 +2585,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
return -EMSGSIZE;
}
- attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK);
if (!attrs)
goto msg_full;
@@ -2228,11 +2602,17 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0))
goto attr_msg_full;
- prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+ prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP);
if (!prop)
goto attr_msg_full;
if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window))
goto prop_msg_full;
+ if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST, bc_mode))
+ goto prop_msg_full;
+ if (bc_mode & BCLINK_MODE_SEL)
+ if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST_RATIO,
+ bc_ratio))
+ goto prop_msg_full;
nla_nest_end(msg->skb, prop);
err = __tipc_nl_add_bc_link_stat(msg->skb, &bcl->stats);
@@ -2331,8 +2711,8 @@ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
i += scnprintf(buf + i, sz - i, " %x", l->peer_caps);
i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt);
i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt);
- i += scnprintf(buf + i, sz - i, " %u", l->prev_from);
- i += scnprintf(buf + i, sz - i, " %u", l->stale_cnt);
+ i += scnprintf(buf + i, sz - i, " %u", 0);
+ i += scnprintf(buf + i, sz - i, " %u", 0);
i += scnprintf(buf + i, sz - i, " %u", l->acked);
list = &l->transmq;
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 8439e0ee53a8..c09e9d49d0a3 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -90,6 +90,8 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
int mtyp, struct sk_buff_head *xmitq);
void tipc_link_create_dummy_tnl_msg(struct tipc_link *tnl,
struct sk_buff_head *xmitq);
+void tipc_link_failover_prepare(struct tipc_link *l, struct tipc_link *tnl,
+ struct sk_buff_head *xmitq);
void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq);
int tipc_link_fsm_evt(struct tipc_link *l, int evt);
bool tipc_link_is_up(struct tipc_link *l);
@@ -139,6 +141,7 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
int tipc_link_bc_peers(struct tipc_link *l);
void tipc_link_set_mtu(struct tipc_link *l, int mtu);
int tipc_link_mtu(struct tipc_link *l);
+int tipc_link_mss(struct tipc_link *l);
void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked,
struct sk_buff_head *xmitq);
void tipc_link_build_bc_sync_msg(struct tipc_link *l,
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 67f69389ec17..58708b4c7719 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -665,6 +665,21 @@ void tipc_mon_delete(struct net *net, int bearer_id)
kfree(mon);
}
+void tipc_mon_reinit_self(struct net *net)
+{
+ struct tipc_monitor *mon;
+ int bearer_id;
+
+ for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+ mon = tipc_monitor(net, bearer_id);
+ if (!mon)
+ continue;
+ write_lock_bh(&mon->lock);
+ mon->self->addr = tipc_own_addr(net);
+ write_unlock_bh(&mon->lock);
+ }
+}
+
int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size)
{
struct tipc_net *tn = tipc_net(net);
@@ -696,7 +711,7 @@ static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer,
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_MON_PEER);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER);
if (!attrs)
goto msg_full;
@@ -785,7 +800,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_MON);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON);
if (!attrs)
goto msg_full;
diff --git a/net/tipc/monitor.h b/net/tipc/monitor.h
index 2a21b93e0d04..ed63d2e650b0 100644
--- a/net/tipc/monitor.h
+++ b/net/tipc/monitor.h
@@ -77,6 +77,7 @@ 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);
+void tipc_mon_reinit_self(struct net *net);
extern const int tipc_max_domain_size;
#endif
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index f48e5857210f..0d515d20b056 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -39,10 +39,16 @@
#include "msg.h"
#include "addr.h"
#include "name_table.h"
+#include "crypto.h"
#define MAX_FORWARD_SIZE 1024
+#ifdef CONFIG_TIPC_CRYPTO
+#define BUF_HEADROOM ALIGN(((LL_MAX_HEADER + 48) + EHDR_MAX_SIZE), 16)
+#define BUF_TAILROOM (TIPC_AES_GCM_TAG_SIZE)
+#else
#define BUF_HEADROOM (LL_MAX_HEADER + 48)
#define BUF_TAILROOM 16
+#endif
static unsigned int align(unsigned int i)
{
@@ -61,7 +67,11 @@ static unsigned int align(unsigned int i)
struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
{
struct sk_buff *skb;
+#ifdef CONFIG_TIPC_CRYPTO
+ unsigned int buf_size = (BUF_HEADROOM + size + BUF_TAILROOM + 3) & ~3u;
+#else
unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
+#endif
skb = alloc_skb_fclone(buf_size, gfp);
if (skb) {
@@ -173,7 +183,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
}
if (fragid == LAST_FRAGMENT) {
- TIPC_SKB_CB(head)->validated = false;
+ TIPC_SKB_CB(head)->validated = 0;
if (unlikely(!tipc_msg_validate(&head)))
goto err;
*buf = head;
@@ -190,6 +200,59 @@ err:
return 0;
}
+/**
+ * tipc_msg_append(): Append data to tail of an existing buffer queue
+ * @hdr: header to be used
+ * @m: the data to be appended
+ * @mss: max allowable size of buffer
+ * @dlen: size of data to be appended
+ * @txq: queue to appand to
+ * Returns the number og 1k blocks appended or errno value
+ */
+int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
+ int mss, struct sk_buff_head *txq)
+{
+ struct sk_buff *skb, *prev;
+ int accounted, total, curr;
+ int mlen, cpy, rem = dlen;
+ struct tipc_msg *hdr;
+
+ skb = skb_peek_tail(txq);
+ accounted = skb ? msg_blocks(buf_msg(skb)) : 0;
+ total = accounted;
+
+ while (rem) {
+ if (!skb || skb->len >= mss) {
+ prev = skb;
+ skb = tipc_buf_acquire(mss, GFP_KERNEL);
+ if (unlikely(!skb))
+ return -ENOMEM;
+ skb_orphan(skb);
+ skb_trim(skb, MIN_H_SIZE);
+ hdr = buf_msg(skb);
+ skb_copy_to_linear_data(skb, _hdr, MIN_H_SIZE);
+ msg_set_hdr_sz(hdr, MIN_H_SIZE);
+ msg_set_size(hdr, MIN_H_SIZE);
+ __skb_queue_tail(txq, skb);
+ total += 1;
+ if (prev)
+ msg_set_ack_required(buf_msg(prev), 0);
+ msg_set_ack_required(hdr, 1);
+ }
+ hdr = buf_msg(skb);
+ curr = msg_blocks(hdr);
+ mlen = msg_size(hdr);
+ cpy = min_t(int, rem, mss - mlen);
+ if (cpy != copy_from_iter(skb->data + mlen, cpy, &m->msg_iter))
+ return -EFAULT;
+ msg_set_size(hdr, mlen + cpy);
+ skb_put(skb, cpy);
+ rem -= cpy;
+ total += msg_blocks(hdr) - curr;
+ }
+ return total - accounted;
+}
+
/* tipc_msg_validate - validate basic format of received message
*
* This routine ensures a TIPC message has an acceptable header, and at least
@@ -218,6 +281,7 @@ bool tipc_msg_validate(struct sk_buff **_skb)
if (unlikely(TIPC_SKB_CB(skb)->validated))
return true;
+
if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE)))
return false;
@@ -239,11 +303,70 @@ bool tipc_msg_validate(struct sk_buff **_skb)
if (unlikely(skb->len < msz))
return false;
- TIPC_SKB_CB(skb)->validated = true;
+ TIPC_SKB_CB(skb)->validated = 1;
return true;
}
/**
+ * tipc_msg_fragment - build a fragment skb list for TIPC message
+ *
+ * @skb: TIPC message skb
+ * @hdr: internal msg header to be put on the top of the fragments
+ * @pktmax: max size of a fragment incl. the header
+ * @frags: returned fragment skb list
+ *
+ * Returns 0 if the fragmentation is successful, otherwise: -EINVAL
+ * or -ENOMEM
+ */
+int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
+ int pktmax, struct sk_buff_head *frags)
+{
+ int pktno, nof_fragms, dsz, dmax, eat;
+ struct tipc_msg *_hdr;
+ struct sk_buff *_skb;
+ u8 *data;
+
+ /* Non-linear buffer? */
+ if (skb_linearize(skb))
+ return -ENOMEM;
+
+ data = (u8 *)skb->data;
+ dsz = msg_size(buf_msg(skb));
+ dmax = pktmax - INT_H_SIZE;
+ if (dsz <= dmax || !dmax)
+ return -EINVAL;
+
+ nof_fragms = dsz / dmax + 1;
+ for (pktno = 1; pktno <= nof_fragms; pktno++) {
+ if (pktno < nof_fragms)
+ eat = dmax;
+ else
+ eat = dsz % dmax;
+ /* Allocate a new fragment */
+ _skb = tipc_buf_acquire(INT_H_SIZE + eat, GFP_ATOMIC);
+ if (!_skb)
+ goto error;
+ skb_orphan(_skb);
+ __skb_queue_tail(frags, _skb);
+ /* Copy header & data to the fragment */
+ skb_copy_to_linear_data(_skb, hdr, INT_H_SIZE);
+ skb_copy_to_linear_data_offset(_skb, INT_H_SIZE, data, eat);
+ data += eat;
+ /* Update the fragment's header */
+ _hdr = buf_msg(_skb);
+ msg_set_fragm_no(_hdr, pktno);
+ msg_set_nof_fragms(_hdr, nof_fragms);
+ msg_set_size(_hdr, INT_H_SIZE + eat);
+ }
+ return 0;
+
+error:
+ __skb_queue_purge(frags);
+ __skb_queue_head_init(frags);
+ return -ENOMEM;
+}
+
+/**
* tipc_msg_build - create buffer chain containing specified header and data
* @mhdr: Message header, to be prepended to data
* @m: User message
@@ -360,48 +483,98 @@ error:
}
/**
- * tipc_msg_bundle(): Append contents of a buffer to tail of an existing one
- * @skb: the buffer to append to ("bundle")
- * @msg: message to be appended
- * @mtu: max allowable size for the bundle buffer
- * Consumes buffer if successful
- * Returns true if bundling could be performed, otherwise false
+ * tipc_msg_bundle - Append contents of a buffer to tail of an existing one
+ * @bskb: the bundle buffer to append to
+ * @msg: message to be appended
+ * @max: max allowable size for the bundle buffer
+ *
+ * Returns "true" if bundling has been performed, otherwise "false"
*/
-bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu)
+static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg,
+ u32 max)
{
- struct tipc_msg *bmsg;
- unsigned int bsz;
- unsigned int msz = msg_size(msg);
- u32 start, pad;
- u32 max = mtu - INT_H_SIZE;
+ struct tipc_msg *bmsg = buf_msg(bskb);
+ u32 msz, bsz, offset, pad;
- if (likely(msg_user(msg) == MSG_FRAGMENTER))
- return false;
- if (!skb)
- return false;
- bmsg = buf_msg(skb);
+ msz = msg_size(msg);
bsz = msg_size(bmsg);
- start = align(bsz);
- pad = start - bsz;
+ offset = align(bsz);
+ pad = offset - bsz;
- if (unlikely(msg_user(msg) == TUNNEL_PROTOCOL))
+ if (unlikely(skb_tailroom(bskb) < (pad + msz)))
return false;
- if (unlikely(msg_user(msg) == BCAST_PROTOCOL))
+ if (unlikely(max < (offset + msz)))
return false;
- if (unlikely(msg_user(bmsg) != MSG_BUNDLER))
+
+ skb_put(bskb, pad + msz);
+ skb_copy_to_linear_data_offset(bskb, offset, msg, msz);
+ msg_set_size(bmsg, offset + msz);
+ msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1);
+ return true;
+}
+
+/**
+ * tipc_msg_try_bundle - Try to bundle a new message to the last one
+ * @tskb: the last/target message to which the new one will be appended
+ * @skb: the new message skb pointer
+ * @mss: max message size (header inclusive)
+ * @dnode: destination node for the message
+ * @new_bundle: if this call made a new bundle or not
+ *
+ * Return: "true" if the new message skb is potential for bundling this time or
+ * later, in the case a bundling has been done this time, the skb is consumed
+ * (the skb pointer = NULL).
+ * Otherwise, "false" if the skb cannot be bundled at all.
+ */
+bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss,
+ u32 dnode, bool *new_bundle)
+{
+ struct tipc_msg *msg, *inner, *outer;
+ u32 tsz;
+
+ /* First, check if the new buffer is suitable for bundling */
+ msg = buf_msg(*skb);
+ if (msg_user(msg) == MSG_FRAGMENTER)
return false;
- if (unlikely(skb_tailroom(skb) < (pad + msz)))
+ if (msg_user(msg) == TUNNEL_PROTOCOL)
return false;
- if (unlikely(max < (start + msz)))
+ if (msg_user(msg) == BCAST_PROTOCOL)
return false;
- if ((msg_importance(msg) < TIPC_SYSTEM_IMPORTANCE) &&
- (msg_importance(bmsg) == TIPC_SYSTEM_IMPORTANCE))
+ if (mss <= INT_H_SIZE + msg_size(msg))
return false;
- skb_put(skb, pad + msz);
- skb_copy_to_linear_data_offset(skb, start, msg, msz);
- msg_set_size(bmsg, start + msz);
- msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1);
+ /* Ok, but the last/target buffer can be empty? */
+ if (unlikely(!tskb))
+ return true;
+
+ /* Is it a bundle already? Try to bundle the new message to it */
+ if (msg_user(buf_msg(tskb)) == MSG_BUNDLER) {
+ *new_bundle = false;
+ goto bundle;
+ }
+
+ /* Make a new bundle of the two messages if possible */
+ tsz = msg_size(buf_msg(tskb));
+ if (unlikely(mss < align(INT_H_SIZE + tsz) + msg_size(msg)))
+ return true;
+ if (unlikely(pskb_expand_head(tskb, INT_H_SIZE, mss - tsz - INT_H_SIZE,
+ GFP_ATOMIC)))
+ return true;
+ inner = buf_msg(tskb);
+ skb_push(tskb, INT_H_SIZE);
+ outer = buf_msg(tskb);
+ tipc_msg_init(msg_prevnode(inner), outer, MSG_BUNDLER, 0, INT_H_SIZE,
+ dnode);
+ msg_set_importance(outer, msg_importance(inner));
+ msg_set_size(outer, INT_H_SIZE + tsz);
+ msg_set_msgcnt(outer, 1);
+ *new_bundle = true;
+
+bundle:
+ if (likely(tipc_msg_bundle(tskb, msg, mss))) {
+ consume_skb(*skb);
+ *skb = NULL;
+ }
return true;
}
@@ -451,52 +624,6 @@ none:
}
/**
- * tipc_msg_make_bundle(): Create bundle buf and append message to its tail
- * @list: the buffer chain, where head is the buffer to replace/append
- * @skb: buffer to be created, appended to and returned in case of success
- * @msg: message to be appended
- * @mtu: max allowable size for the bundle buffer, inclusive header
- * @dnode: destination node for message. (Not always present in header)
- * Returns true if success, otherwise false
- */
-bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg,
- u32 mtu, u32 dnode)
-{
- struct sk_buff *_skb;
- struct tipc_msg *bmsg;
- u32 msz = msg_size(msg);
- u32 max = mtu - INT_H_SIZE;
-
- if (msg_user(msg) == MSG_FRAGMENTER)
- return false;
- if (msg_user(msg) == TUNNEL_PROTOCOL)
- return false;
- if (msg_user(msg) == BCAST_PROTOCOL)
- return false;
- if (msz > (max / 2))
- return false;
-
- _skb = tipc_buf_acquire(max, GFP_ATOMIC);
- if (!_skb)
- return false;
-
- skb_trim(_skb, INT_H_SIZE);
- bmsg = buf_msg(_skb);
- tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
- INT_H_SIZE, dnode);
- if (msg_isdata(msg))
- msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE);
- else
- msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE);
- msg_set_seqno(bmsg, msg_seqno(msg));
- msg_set_ack(bmsg, msg_ack(msg));
- msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
- tipc_msg_bundle(_skb, msg, mtu);
- *skb = _skb;
- return true;
-}
-
-/**
* tipc_msg_reverse(): swap source and destination addresses and add error code
* @own_node: originating node id for reversed message
* @skb: buffer containing message to be reversed; will be consumed
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index d7e4b8b93f9d..6d466ebdb64f 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -102,14 +102,42 @@ struct plist;
#define TIPC_MEDIA_INFO_OFFSET 5
struct tipc_skb_cb {
- u32 bytes_read;
- u32 orig_member;
- struct sk_buff *tail;
- unsigned long nxt_retr;
- bool validated;
- u16 chain_imp;
- u16 ackers;
-};
+ union {
+ struct {
+ struct sk_buff *tail;
+ unsigned long nxt_retr;
+ unsigned long retr_stamp;
+ u32 bytes_read;
+ u32 orig_member;
+ u16 chain_imp;
+ u16 ackers;
+ u16 retr_cnt;
+ } __packed;
+#ifdef CONFIG_TIPC_CRYPTO
+ struct {
+ struct tipc_crypto *rx;
+ struct tipc_aead *last;
+ u8 recurs;
+ } tx_clone_ctx __packed;
+#endif
+ } __packed;
+ union {
+ struct {
+ u8 validated:1;
+#ifdef CONFIG_TIPC_CRYPTO
+ u8 encrypted:1;
+ u8 decrypted:1;
+ u8 probe:1;
+ u8 tx_clone_deferred:1;
+#endif
+ };
+ u8 flags;
+ };
+ u8 reserved;
+#ifdef CONFIG_TIPC_CRYPTO
+ void *crypto_ctx;
+#endif
+} __packed;
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
@@ -117,6 +145,37 @@ struct tipc_msg {
__be32 hdr[15];
};
+/* struct tipc_gap_ack - TIPC Gap ACK block
+ * @ack: seqno of the last consecutive packet in link deferdq
+ * @gap: number of gap packets since the last ack
+ *
+ * E.g:
+ * link deferdq: 1 2 3 4 10 11 13 14 15 20
+ * --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0>
+ */
+struct tipc_gap_ack {
+ __be16 ack;
+ __be16 gap;
+};
+
+/* struct tipc_gap_ack_blks
+ * @len: actual length of the record
+ * @gack_cnt: number of Gap ACK blocks in the record
+ * @gacks: array of Gap ACK blocks
+ */
+struct tipc_gap_ack_blks {
+ __be16 len;
+ u8 gack_cnt;
+ u8 reserved;
+ struct tipc_gap_ack gacks[];
+};
+
+#define tipc_gap_ack_blks_sz(n) (sizeof(struct tipc_gap_ack_blks) + \
+ sizeof(struct tipc_gap_ack) * (n))
+
+#define MAX_GAP_ACK_BLKS 32
+#define MAX_GAP_ACK_BLKS_SZ tipc_gap_ack_blks_sz(MAX_GAP_ACK_BLKS)
+
static inline struct tipc_msg *buf_msg(struct sk_buff *skb)
{
return (struct tipc_msg *)skb->data;
@@ -257,6 +316,26 @@ static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d)
msg_set_bits(m, 0, 18, 1, d);
}
+static inline int msg_ack_required(struct tipc_msg *m)
+{
+ return msg_bits(m, 0, 18, 1);
+}
+
+static inline void msg_set_ack_required(struct tipc_msg *m, u32 d)
+{
+ msg_set_bits(m, 0, 18, 1, d);
+}
+
+static inline bool msg_is_rcast(struct tipc_msg *m)
+{
+ return msg_bits(m, 0, 18, 0x1);
+}
+
+static inline void msg_set_is_rcast(struct tipc_msg *m, bool d)
+{
+ msg_set_bits(m, 0, 18, 0x1, d);
+}
+
static inline void msg_set_size(struct tipc_msg *m, u32 sz)
{
m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz);
@@ -267,7 +346,7 @@ static inline unchar *msg_data(struct tipc_msg *m)
return ((unchar *)m) + msg_hdr_sz(m);
}
-static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
+static inline struct tipc_msg *msg_inner_hdr(struct tipc_msg *m)
{
return (struct tipc_msg *)msg_data(m);
}
@@ -445,7 +524,7 @@ static inline void msg_set_prevnode(struct tipc_msg *m, u32 a)
static inline u32 msg_origport(struct tipc_msg *m)
{
if (msg_user(m) == MSG_FRAGMENTER)
- m = msg_get_wrapped(m);
+ m = msg_inner_hdr(m);
return msg_word(m, 4);
}
@@ -680,12 +759,26 @@ static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n)
msg_set_bits(m, 4, 16, 0xffff, n);
}
+static inline u32 msg_nof_fragms(struct tipc_msg *m)
+{
+ return msg_bits(m, 4, 0, 0xffff);
+}
+
+static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n)
+{
+ msg_set_bits(m, 4, 0, 0xffff, n);
+}
+
+static inline u32 msg_fragm_no(struct tipc_msg *m)
+{
+ return msg_bits(m, 4, 16, 0xffff);
+}
+
static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 4, 16, 0xffff, n);
}
-
static inline u16 msg_next_sent(struct tipc_msg *m)
{
return msg_bits(m, 4, 0, 0xffff);
@@ -836,6 +929,16 @@ static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n)
msg_set_bits(m, 9, 16, 0xffff, n);
}
+static inline u16 msg_syncpt(struct tipc_msg *m)
+{
+ return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_syncpt(struct tipc_msg *m, u16 n)
+{
+ msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
static inline u32 msg_conn_ack(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff);
@@ -959,6 +1062,20 @@ static inline bool msg_is_reset(struct tipc_msg *hdr)
return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG);
}
+/* Word 13
+ */
+static inline void msg_set_peer_net_hash(struct tipc_msg *m, u32 n)
+{
+ msg_set_word(m, 13, n);
+}
+
+static inline u32 msg_peer_net_hash(struct tipc_msg *m)
+{
+ return msg_word(m, 13);
+}
+
+/* Word 14
+ */
static inline u32 msg_sugg_node_addr(struct tipc_msg *m)
{
return msg_word(m, 14);
@@ -990,12 +1107,15 @@ struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
uint data_sz, u32 dnode, u32 onode,
u32 dport, u32 oport, int errcode);
int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf);
-bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu);
-bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg,
- u32 mtu, u32 dnode);
+bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss,
+ u32 dnode, bool *new_bundle);
bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos);
+int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
+ int pktmax, struct sk_buff_head *frags);
int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
int offset, int dsz, int mtu, struct sk_buff_head *list);
+int tipc_msg_append(struct tipc_msg *hdr, struct msghdr *m, int dlen,
+ int mss, struct sk_buff_head *txq);
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err);
bool tipc_msg_assemble(struct sk_buff_head *list);
bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq);
@@ -1110,4 +1230,25 @@ static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list,
tipc_skb_queue_splice_tail(&tmp, head);
}
+/* __tipc_skb_dequeue() - dequeue the head skb according to expected seqno
+ * @list: list to be dequeued from
+ * @seqno: seqno of the expected msg
+ *
+ * returns skb dequeued from the list if its seqno is less than or equal to
+ * the expected one, otherwise the skb is still hold
+ *
+ * Note: must be used with appropriate locks held only
+ */
+static inline struct sk_buff *__tipc_skb_dequeue(struct sk_buff_head *list,
+ u16 seqno)
+{
+ struct sk_buff *skb = skb_peek(list);
+
+ if (skb && less_eq(buf_seqno(skb), seqno)) {
+ __skb_unlink(skb, list);
+ return skb;
+ }
+ return NULL;
+}
+
#endif
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 61219f0b9677..5feaf3b67380 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -146,7 +146,7 @@ static void named_distribute(struct net *net, struct sk_buff_head *list,
struct publication *publ;
struct sk_buff *skb = NULL;
struct distr_item *item = NULL;
- u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) /
+ u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0, false) - INT_H_SIZE) /
ITEM_SIZE) * ITEM_SIZE;
u32 msg_rem = msg_dsz;
@@ -223,7 +223,8 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
publ->key);
}
- kfree_rcu(p, rcu);
+ if (p)
+ kfree_rcu(p, rcu);
}
/**
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bff241f03525..92d04dc2a44b 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -35,6 +35,7 @@
*/
#include <net/sock.h>
+#include <linux/list_sort.h>
#include "core.h"
#include "netlink.h"
#include "name_table.h"
@@ -66,6 +67,7 @@ struct service_range {
/**
* struct tipc_service - container for all published instances of a service type
* @type: 32 bit 'type' value for service
+ * @publ_cnt: increasing counter for publications in this service
* @ranges: rb tree containing all service ranges for this service
* @service_list: links to adjacent name ranges in hash chain
* @subscriptions: list of subscriptions for this service type
@@ -74,6 +76,7 @@ struct service_range {
*/
struct tipc_service {
u32 type;
+ u32 publ_cnt;
struct rb_root ranges;
struct hlist_node service_list;
struct list_head subscriptions;
@@ -109,6 +112,7 @@ static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper,
INIT_LIST_HEAD(&publ->binding_node);
INIT_LIST_HEAD(&publ->local_publ);
INIT_LIST_HEAD(&publ->all_publ);
+ INIT_LIST_HEAD(&publ->list);
return publ;
}
@@ -244,6 +248,8 @@ static struct publication *tipc_service_insert_publ(struct net *net,
p = tipc_publ_create(type, lower, upper, scope, node, port, key);
if (!p)
goto err;
+ /* Suppose there shouldn't be a huge gap btw publs i.e. >INT_MAX */
+ p->id = sc->publ_cnt++;
if (in_own_node(net, node))
list_add(&p->local_publ, &sr->local_publ);
list_add(&p->all_publ, &sr->all_publ);
@@ -278,6 +284,20 @@ static struct publication *tipc_service_remove_publ(struct service_range *sr,
}
/**
+ * Code reused: time_after32() for the same purpose
+ */
+#define publication_after(pa, pb) time_after32((pa)->id, (pb)->id)
+static int tipc_publ_sort(void *priv, struct list_head *a,
+ struct list_head *b)
+{
+ struct publication *pa, *pb;
+
+ pa = container_of(a, struct publication, list);
+ pb = container_of(b, struct publication, list);
+ return publication_after(pa, pb);
+}
+
+/**
* tipc_service_subscribe - attach a subscription, and optionally
* issue the prescribed number of events if there is any service
* range overlapping with the requested range
@@ -286,36 +306,51 @@ static void tipc_service_subscribe(struct tipc_service *service,
struct tipc_subscription *sub)
{
struct tipc_subscr *sb = &sub->evt.s;
+ struct publication *p, *first, *tmp;
+ struct list_head publ_list;
struct service_range *sr;
struct tipc_name_seq ns;
- struct publication *p;
struct rb_node *n;
- bool first;
+ u32 filter;
ns.type = tipc_sub_read(sb, seq.type);
ns.lower = tipc_sub_read(sb, seq.lower);
ns.upper = tipc_sub_read(sb, seq.upper);
+ filter = tipc_sub_read(sb, filter);
tipc_sub_get(sub);
list_add(&sub->service_list, &service->subscriptions);
- if (tipc_sub_read(sb, filter) & TIPC_SUB_NO_STATUS)
+ if (filter & TIPC_SUB_NO_STATUS)
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;
- first = true;
+ first = NULL;
list_for_each_entry(p, &sr->all_publ, all_publ) {
- tipc_sub_report_overlap(sub, sr->lower, sr->upper,
- TIPC_PUBLISHED, p->port,
- p->node, p->scope, first);
- first = false;
+ if (filter & TIPC_SUB_PORTS)
+ list_add_tail(&p->list, &publ_list);
+ else if (!first || publication_after(first, p))
+ /* Pick this range's *first* publication */
+ first = p;
}
+ if (first)
+ list_add_tail(&first->list, &publ_list);
+ }
+
+ /* Sort the publications before reporting */
+ list_sort(NULL, &publ_list, tipc_publ_sort);
+ list_for_each_entry_safe(p, tmp, &publ_list, list) {
+ tipc_sub_report_overlap(sub, p->lower, p->upper,
+ TIPC_PUBLISHED, p->port, p->node,
+ p->scope, true);
+ list_del_init(&p->list);
}
}
@@ -829,11 +864,11 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE);
if (!attrs)
goto msg_full;
- b = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
+ b = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
if (!b)
goto attr_msg_full;
@@ -909,7 +944,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg,
for (; i < TIPC_NAMETBL_SIZE; i++) {
head = &tn->nametbl->services[i];
- if (*last_type) {
+ if (*last_type ||
+ (!i && *last_key && (*last_lower == *last_key))) {
service = tipc_service_find(net, *last_type);
if (!service)
return -EPIPE;
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index f79066334cc8..728bc7016c38 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -58,6 +58,7 @@ struct tipc_group;
* @node: network address of publishing socket's node
* @port: publishing port
* @key: publication key, unique across the cluster
+ * @id: publication id
* @binding_node: all publications from the same node which bound this one
* - Remote publications: in node->publ_list
* Used by node/name distr to withdraw publications when node is lost
@@ -69,6 +70,7 @@ struct tipc_group;
* Used by closest_first and multicast receive lookup algorithms
* @all_publ: all publications identical to this one, whatever node and scope
* Used by round-robin lookup algorithm
+ * @list: to form a list of publications in temporal order
* @rcu: RCU callback head used for deferred freeing
*/
struct publication {
@@ -79,10 +81,12 @@ struct publication {
u32 node;
u32 port;
u32 key;
+ u32 id;
struct list_head binding_node;
struct list_head binding_sock;
struct list_head local_publ;
struct list_head all_publ;
+ struct list_head list;
struct rcu_head rcu;
};
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 7ce1e86b024f..2de3cec9929d 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -42,6 +42,7 @@
#include "node.h"
#include "bcast.h"
#include "netlink.h"
+#include "monitor.h"
/*
* The TIPC locking policy is designed to ensure a very fine locking
@@ -136,6 +137,7 @@ static void tipc_net_finalize(struct net *net, u32 addr)
tipc_set_node_addr(net, addr);
tipc_named_reinit(net);
tipc_sk_reinit(net);
+ tipc_mon_reinit_self(net);
tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
TIPC_CLUSTER_SCOPE, 0, addr);
}
@@ -187,7 +189,7 @@ static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg)
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_NET);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET);
if (!attrs)
goto msg_full;
@@ -245,9 +247,9 @@ int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_NET])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
- info->attrs[TIPC_NLA_NET], tipc_nl_net_policy,
- info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX,
+ info->attrs[TIPC_NLA_NET],
+ tipc_nl_net_policy, info->extack);
if (err)
return err;
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 99ee419210ba..e53231bd23b4 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -102,7 +102,11 @@ const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
[TIPC_NLA_NODE_UNSPEC] = { .type = NLA_UNSPEC },
[TIPC_NLA_NODE_ADDR] = { .type = NLA_U32 },
- [TIPC_NLA_NODE_UP] = { .type = NLA_FLAG }
+ [TIPC_NLA_NODE_UP] = { .type = NLA_FLAG },
+ [TIPC_NLA_NODE_ID] = { .type = NLA_BINARY,
+ .len = TIPC_NODEID_LEN},
+ [TIPC_NLA_NODE_KEY] = { .type = NLA_BINARY,
+ .len = TIPC_AEAD_KEY_SIZE_MAX},
};
/* Properties valid for media, bearer and link */
@@ -110,7 +114,9 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
[TIPC_NLA_PROP_UNSPEC] = { .type = NLA_UNSPEC },
[TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 },
[TIPC_NLA_PROP_TOL] = { .type = NLA_U32 },
- [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 }
+ [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 },
+ [TIPC_NLA_PROP_BROADCAST] = { .type = NLA_U32 },
+ [TIPC_NLA_PROP_BROADCAST_RATIO] = { .type = NLA_U32 }
};
const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = {
@@ -141,115 +147,130 @@ const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = {
static const struct genl_ops tipc_genl_v2_ops[] = {
{
.cmd = TIPC_NL_BEARER_DISABLE,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_bearer_disable,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_BEARER_ENABLE,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_bearer_enable,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_BEARER_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_bearer_get,
.dumpit = tipc_nl_bearer_dump,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_BEARER_ADD,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_bearer_add,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_BEARER_SET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_bearer_set,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_SOCK_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.start = tipc_dump_start,
.dumpit = tipc_nl_sk_dump,
.done = tipc_dump_done,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_PUBL_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = tipc_nl_publ_dump,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_LINK_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_node_get_link,
.dumpit = tipc_nl_node_dump_link,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_LINK_SET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_node_set_link,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_LINK_RESET_STATS,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_node_reset_link_stats,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_MEDIA_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_media_get,
.dumpit = tipc_nl_media_dump,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_MEDIA_SET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_media_set,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_NODE_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.dumpit = tipc_nl_node_dump,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_NET_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.dumpit = tipc_nl_net_dump,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_NET_SET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_net_set,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_NAME_TABLE_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.dumpit = tipc_nl_name_table_dump,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_MON_SET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_node_set_monitor,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_MON_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_node_get_monitor,
.dumpit = tipc_nl_node_dump_monitor,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_MON_PEER_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = tipc_nl_node_dump_monitor_peer,
- .policy = tipc_nl_policy,
},
{
.cmd = TIPC_NL_PEER_REMOVE,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_peer_rm,
- .policy = tipc_nl_policy,
},
#ifdef CONFIG_TIPC_MEDIA_UDP
{
.cmd = TIPC_NL_UDP_GET_REMOTEIP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = tipc_udp_nl_dump_remoteip,
- .policy = tipc_nl_policy,
+ },
+#endif
+#ifdef CONFIG_TIPC_CRYPTO
+ {
+ .cmd = TIPC_NL_KEY_SET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .doit = tipc_nl_node_set_key,
+ },
+ {
+ .cmd = TIPC_NL_KEY_FLUSH,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .doit = tipc_nl_node_flush_key,
},
#endif
};
@@ -259,24 +280,13 @@ struct genl_family tipc_genl_family __ro_after_init = {
.version = TIPC_GENL_V2_VERSION,
.hdrsize = 0,
.maxattr = TIPC_NLA_MAX,
+ .policy = tipc_nl_policy,
.netnsok = true,
.module = THIS_MODULE,
.ops = tipc_genl_v2_ops,
.n_ops = ARRAY_SIZE(tipc_genl_v2_ops),
};
-int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr)
-{
- u32 maxattr = tipc_genl_family.maxattr;
-
- *attr = genl_family_attrbuf(&tipc_genl_family);
- if (!*attr)
- return -EOPNOTSUPP;
-
- return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy,
- NULL);
-}
-
int __init tipc_netlink_start(void)
{
int res;
diff --git a/net/tipc/netlink.h b/net/tipc/netlink.h
index 4ba0ad422110..7cf777723e3e 100644
--- a/net/tipc/netlink.h
+++ b/net/tipc/netlink.h
@@ -38,7 +38,6 @@
#include <net/netlink.h>
extern struct genl_family tipc_genl_family;
-int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***buf);
struct tipc_nl_msg {
struct sk_buff *skb;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 340a6e7c43a7..0254bb7e418b 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -55,6 +55,7 @@ struct tipc_nl_compat_msg {
int rep_type;
int rep_size;
int req_type;
+ int req_size;
struct net *net;
struct sk_buff *rep;
struct tlv_desc *req;
@@ -180,15 +181,18 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
struct tipc_nl_compat_msg *msg,
struct sk_buff *arg)
{
+ struct genl_dumpit_info info;
int len = 0;
int err;
struct sk_buff *buf;
struct nlmsghdr *nlmsg;
struct netlink_callback cb;
+ struct nlattr **attrbuf;
memset(&cb, 0, sizeof(cb));
cb.nlh = (struct nlmsghdr *)arg->data;
cb.skb = arg;
+ cb.data = &info;
buf = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (!buf)
@@ -200,19 +204,35 @@ 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);
+ if (!attrbuf) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ info.attrs = attrbuf;
+ err = nlmsg_parse_deprecated(cb.nlh, GENL_HDRLEN, attrbuf,
+ tipc_genl_family.maxattr,
+ tipc_genl_family.policy, NULL);
+ if (err)
+ goto err_out;
+
do {
int rem;
len = (*cmd->dumpit)(buf, &cb);
nlmsg_for_each_msg(nlmsg, nlmsg_hdr(buf), len, rem) {
- struct nlattr **attrs;
-
- err = tipc_nlmsg_parse(nlmsg, &attrs);
+ err = nlmsg_parse_deprecated(nlmsg, GENL_HDRLEN,
+ attrbuf,
+ tipc_genl_family.maxattr,
+ tipc_genl_family.policy,
+ NULL);
if (err)
goto err_out;
- err = (*cmd->format)(msg, attrs);
+ err = (*cmd->format)(msg, attrbuf);
if (err)
goto err_out;
@@ -230,6 +250,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
err = 0;
err_out:
+ kfree(attrbuf);
tipc_dump_done(&cb);
kfree_skb(buf);
@@ -257,7 +278,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
int err;
struct sk_buff *arg;
- if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+ if (msg->req_type && (!msg->req_size ||
+ !TLV_CHECK_TYPE(msg->req, msg->req_type)))
return -EINVAL;
msg->rep = tipc_tlv_alloc(msg->rep_size);
@@ -328,9 +350,9 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
if (err)
goto doit_out;
- err = nla_parse(attrbuf, tipc_genl_family.maxattr,
- (const struct nlattr *)trans_buf->data,
- trans_buf->len, NULL, NULL);
+ err = nla_parse_deprecated(attrbuf, tipc_genl_family.maxattr,
+ (const struct nlattr *)trans_buf->data,
+ trans_buf->len, NULL, NULL);
if (err)
goto doit_out;
@@ -354,7 +376,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
{
int err;
- if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+ if (msg->req_type && (!msg->req_size ||
+ !TLV_CHECK_TYPE(msg->req, msg->req_type)))
return -EINVAL;
err = __tipc_nl_compat_doit(cmd, msg);
@@ -378,8 +401,8 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX,
- attrs[TIPC_NLA_BEARER], NULL, NULL);
+ err = nla_parse_nested_deprecated(bearer, TIPC_NLA_BEARER_MAX,
+ attrs[TIPC_NLA_BEARER], NULL, NULL);
if (err)
return err;
@@ -399,7 +422,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
b = (struct tipc_bearer_config *)TLV_DATA(msg->req);
- bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+ bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER);
if (!bearer)
return -EMSGSIZE;
@@ -419,7 +442,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
return -EMSGSIZE;
if (ntohl(b->priority) <= TIPC_MAX_LINK_PRI) {
- prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP);
+ prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP);
if (!prop)
return -EMSGSIZE;
if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(b->priority)))
@@ -441,11 +464,15 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
name = (char *)TLV_DATA(msg->req);
- bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+ bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER);
if (!bearer)
return -EMSGSIZE;
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_BEARER_NAME);
if (!string_is_valid(name, len))
return -EINVAL;
@@ -514,30 +541,36 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_LINK])
return -EINVAL;
- err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
- NULL, NULL);
+ err = nla_parse_nested_deprecated(link, TIPC_NLA_LINK_MAX,
+ attrs[TIPC_NLA_LINK], NULL, NULL);
if (err)
return err;
if (!link[TIPC_NLA_LINK_PROP])
return -EINVAL;
- err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX,
- link[TIPC_NLA_LINK_PROP], NULL, NULL);
+ err = nla_parse_nested_deprecated(prop, TIPC_NLA_PROP_MAX,
+ link[TIPC_NLA_LINK_PROP], NULL,
+ NULL);
if (err)
return err;
if (!link[TIPC_NLA_LINK_STATS])
return -EINVAL;
- err = nla_parse_nested(stats, TIPC_NLA_STATS_MAX,
- link[TIPC_NLA_LINK_STATS], NULL, NULL);
+ err = nla_parse_nested_deprecated(stats, TIPC_NLA_STATS_MAX,
+ link[TIPC_NLA_LINK_STATS], NULL,
+ NULL);
if (err)
return err;
name = (char *)TLV_DATA(msg->req);
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
if (!string_is_valid(name, len))
return -EINVAL;
@@ -645,8 +678,8 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_LINK])
return -EINVAL;
- err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
- NULL, NULL);
+ err = nla_parse_nested_deprecated(link, TIPC_NLA_LINK_MAX,
+ attrs[TIPC_NLA_LINK], NULL, NULL);
if (err)
return err;
@@ -681,22 +714,17 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
struct nlattr *prop;
struct nlattr *media;
struct tipc_link_config *lc;
- int len;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
- media = nla_nest_start(skb, TIPC_NLA_MEDIA);
+ media = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA);
if (!media)
return -EMSGSIZE;
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME);
- if (!string_is_valid(lc->name, len))
- return -EINVAL;
-
if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name))
return -EMSGSIZE;
- prop = nla_nest_start(skb, TIPC_NLA_MEDIA_PROP);
+ prop = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA_PROP);
if (!prop)
return -EMSGSIZE;
@@ -713,22 +741,17 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
struct nlattr *prop;
struct nlattr *bearer;
struct tipc_link_config *lc;
- int len;
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
- bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+ bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER);
if (!bearer)
return -EMSGSIZE;
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME);
- if (!string_is_valid(lc->name, len))
- return -EINVAL;
-
if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name))
return -EMSGSIZE;
- prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP);
+ prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP);
if (!prop)
return -EMSGSIZE;
@@ -748,14 +771,14 @@ static int __tipc_nl_compat_link_set(struct sk_buff *skb,
lc = (struct tipc_link_config *)TLV_DATA(msg->req);
- link = nla_nest_start(skb, TIPC_NLA_LINK);
+ link = nla_nest_start_noflag(skb, TIPC_NLA_LINK);
if (!link)
return -EMSGSIZE;
if (nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name))
return -EMSGSIZE;
- prop = nla_nest_start(skb, TIPC_NLA_LINK_PROP);
+ prop = nla_nest_start_noflag(skb, TIPC_NLA_LINK_PROP);
if (!prop)
return -EMSGSIZE;
@@ -811,11 +834,15 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
name = (char *)TLV_DATA(msg->req);
- link = nla_nest_start(skb, TIPC_NLA_LINK);
+ link = nla_nest_start_noflag(skb, TIPC_NLA_LINK);
if (!link)
return -EMSGSIZE;
- len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+ len = TLV_GET_DATA_LEN(msg->req);
+ if (len <= 0)
+ return -EINVAL;
+
+ len = min_t(int, len, TIPC_MAX_LINK_NAME);
if (!string_is_valid(name, len))
return -EINVAL;
@@ -869,16 +896,18 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_NAME_TABLE])
return -EINVAL;
- err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
- attrs[TIPC_NLA_NAME_TABLE], NULL, NULL);
+ err = nla_parse_nested_deprecated(nt, TIPC_NLA_NAME_TABLE_MAX,
+ attrs[TIPC_NLA_NAME_TABLE], NULL,
+ NULL);
if (err)
return err;
if (!nt[TIPC_NLA_NAME_TABLE_PUBL])
return -EINVAL;
- err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX,
- nt[TIPC_NLA_NAME_TABLE_PUBL], NULL, NULL);
+ err = nla_parse_nested_deprecated(publ, TIPC_NLA_PUBL_MAX,
+ nt[TIPC_NLA_NAME_TABLE_PUBL], NULL,
+ NULL);
if (err)
return err;
@@ -937,8 +966,8 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_PUBL])
return -EINVAL;
- err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL],
- NULL, NULL);
+ err = nla_parse_nested_deprecated(publ, TIPC_NLA_PUBL_MAX,
+ attrs[TIPC_NLA_PUBL], NULL, NULL);
if (err)
return err;
@@ -973,7 +1002,7 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock)
return -EMSGSIZE;
}
- nest = nla_nest_start(args, TIPC_NLA_SOCK);
+ nest = nla_nest_start_noflag(args, TIPC_NLA_SOCK);
if (!nest) {
kfree_skb(args);
return -EMSGSIZE;
@@ -1007,8 +1036,8 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_SOCK])
return -EINVAL;
- err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK],
- NULL, NULL);
+ err = nla_parse_nested_deprecated(sock, TIPC_NLA_SOCK_MAX,
+ attrs[TIPC_NLA_SOCK], NULL, NULL);
if (err)
return err;
@@ -1019,8 +1048,9 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
u32 node;
struct nlattr *con[TIPC_NLA_CON_MAX + 1];
- err = nla_parse_nested(con, TIPC_NLA_CON_MAX,
- sock[TIPC_NLA_SOCK_CON], NULL, NULL);
+ err = nla_parse_nested_deprecated(con, TIPC_NLA_CON_MAX,
+ sock[TIPC_NLA_SOCK_CON],
+ NULL, NULL);
if (err)
return err;
@@ -1059,8 +1089,8 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_MEDIA])
return -EINVAL;
- err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX,
- attrs[TIPC_NLA_MEDIA], NULL, NULL);
+ err = nla_parse_nested_deprecated(media, TIPC_NLA_MEDIA_MAX,
+ attrs[TIPC_NLA_MEDIA], NULL, NULL);
if (err)
return err;
@@ -1079,8 +1109,8 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_NODE])
return -EINVAL;
- err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE],
- NULL, NULL);
+ err = nla_parse_nested_deprecated(node, TIPC_NLA_NODE_MAX,
+ attrs[TIPC_NLA_NODE], NULL, NULL);
if (err)
return err;
@@ -1100,7 +1130,7 @@ static int tipc_nl_compat_net_set(struct tipc_nl_compat_cmd_doit *cmd,
val = ntohl(*(__be32 *)TLV_DATA(msg->req));
- net = nla_nest_start(skb, TIPC_NLA_NET);
+ net = nla_nest_start_noflag(skb, TIPC_NLA_NET);
if (!net)
return -EMSGSIZE;
@@ -1126,8 +1156,8 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg,
if (!attrs[TIPC_NLA_NET])
return -EINVAL;
- err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET],
- NULL, NULL);
+ err = nla_parse_nested_deprecated(net, TIPC_NLA_NET_MAX,
+ attrs[TIPC_NLA_NET], NULL, NULL);
if (err)
return err;
@@ -1271,8 +1301,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
goto send;
}
- len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
- if (!len || !TLV_OK(msg.req, len)) {
+ msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+ if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) {
msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
err = -EOPNOTSUPP;
goto send;
@@ -1300,6 +1330,7 @@ send:
static const struct genl_ops tipc_genl_compat_ops[] = {
{
.cmd = TIPC_GENL_CMD,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = tipc_nl_compat_recv,
},
};
diff --git a/net/tipc/node.c b/net/tipc/node.c
index dd3b6dc17662..ab04e00cb95b 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -44,6 +44,7 @@
#include "discover.h"
#include "netlink.h"
#include "trace.h"
+#include "crypto.h"
#define INVALID_NODE_SIG 0x10000
#define NODE_CLEANUP_AFTER 300000
@@ -89,6 +90,7 @@ struct tipc_bclink_entry {
* @links: array containing references to all links to node
* @action_flags: bit mask of different types of node actions
* @state: connectivity state vs peer node
+ * @preliminary: a preliminary node or not
* @sync_point: sequence number where synch/failover is finished
* @list: links to adjacent nodes in sorted list of cluster's nodes
* @working_links: number of working links to node (both active and standby)
@@ -99,6 +101,7 @@ struct tipc_bclink_entry {
* @publ_list: list of publications
* @rcu: rcu struct for tipc_node
* @delete_at: indicates the time for deleting a down node
+ * @crypto_rx: RX crypto handler
*/
struct tipc_node {
u32 addr;
@@ -112,6 +115,7 @@ struct tipc_node {
int action_flags;
struct list_head list;
int state;
+ bool preliminary;
bool failover_sent;
u16 sync_point;
int link_cnt;
@@ -120,12 +124,18 @@ struct tipc_node {
u32 signature;
u32 link_id;
u8 peer_id[16];
+ char peer_id_string[NODE_ID_STR_LEN];
struct list_head publ_list;
struct list_head conn_sks;
unsigned long keepalive_intv;
struct timer_list timer;
struct rcu_head rcu;
unsigned long delete_at;
+ struct net *peer_net;
+ u32 peer_hash_mix;
+#ifdef CONFIG_TIPC_CRYPTO
+ struct tipc_crypto *crypto_rx;
+#endif
};
/* Node FSM states and events:
@@ -163,7 +173,6 @@ static void tipc_node_timeout(struct timer_list *t);
static void tipc_node_fsm_evt(struct tipc_node *n, int evt);
static struct tipc_node *tipc_node_find(struct net *net, u32 addr);
static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id);
-static void tipc_node_put(struct tipc_node *node);
static bool node_is_up(struct tipc_node *n);
static void tipc_node_delete_from_list(struct tipc_node *node);
@@ -184,7 +193,7 @@ static struct tipc_link *node_active_link(struct tipc_node *n, int sel)
return n->links[bearer_id].link;
}
-int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel)
+int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel, bool connected)
{
struct tipc_node *n;
int bearer_id;
@@ -194,6 +203,14 @@ int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel)
if (unlikely(!n))
return mtu;
+ /* Allow MAX_MSG_SIZE when building connection oriented message
+ * if they are in the same core network
+ */
+ if (n->peer_net && connected) {
+ tipc_node_put(n);
+ return mtu;
+ }
+
bearer_id = n->active_links[sel & 1];
if (likely(bearer_id != INVALID_BEARER_ID))
mtu = n->links[bearer_id].mtu;
@@ -235,15 +252,51 @@ u16 tipc_node_get_capabilities(struct net *net, u32 addr)
return caps;
}
+u32 tipc_node_get_addr(struct tipc_node *node)
+{
+ return (node) ? node->addr : 0;
+}
+
+char *tipc_node_get_id_str(struct tipc_node *node)
+{
+ return node->peer_id_string;
+}
+
+#ifdef CONFIG_TIPC_CRYPTO
+/**
+ * tipc_node_crypto_rx - Retrieve crypto RX handle from node
+ * Note: node ref counter must be held first!
+ */
+struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n)
+{
+ return (__n) ? __n->crypto_rx : NULL;
+}
+
+struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos)
+{
+ return container_of(pos, struct tipc_node, list)->crypto_rx;
+}
+#endif
+
+void tipc_node_free(struct rcu_head *rp)
+{
+ struct tipc_node *n = container_of(rp, struct tipc_node, rcu);
+
+#ifdef CONFIG_TIPC_CRYPTO
+ tipc_crypto_stop(&n->crypto_rx);
+#endif
+ kfree(n);
+}
+
static void tipc_node_kref_release(struct kref *kref)
{
struct tipc_node *n = container_of(kref, struct tipc_node, kref);
kfree(n->bc_entry.link);
- kfree_rcu(n, rcu);
+ call_rcu(&n->rcu, tipc_node_free);
}
-static void tipc_node_put(struct tipc_node *node)
+void tipc_node_put(struct tipc_node *node)
{
kref_put(&node->kref, tipc_node_kref_release);
}
@@ -264,7 +317,7 @@ static struct tipc_node *tipc_node_find(struct net *net, u32 addr)
rcu_read_lock();
hlist_for_each_entry_rcu(node, &tn->node_htable[thash], hash) {
- if (node->addr != addr)
+ if (node->addr != addr || node->preliminary)
continue;
if (!kref_get_unless_zero(&node->kref))
node = NULL;
@@ -360,29 +413,92 @@ static void tipc_node_write_unlock(struct tipc_node *n)
}
}
-static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
- u8 *peer_id, u16 capabilities)
+static void tipc_node_assign_peer_net(struct tipc_node *n, u32 hash_mixes)
+{
+ int net_id = tipc_netid(n->net);
+ struct tipc_net *tn_peer;
+ struct net *tmp;
+ u32 hash_chk;
+
+ if (n->peer_net)
+ return;
+
+ for_each_net_rcu(tmp) {
+ tn_peer = tipc_net(tmp);
+ if (!tn_peer)
+ continue;
+ /* Integrity checking whether node exists in namespace or not */
+ if (tn_peer->net_id != net_id)
+ continue;
+ if (memcmp(n->peer_id, tn_peer->node_id, NODE_ID_LEN))
+ continue;
+ hash_chk = tipc_net_hash_mixes(tmp, tn_peer->random);
+ if (hash_mixes ^ hash_chk)
+ continue;
+ n->peer_net = tmp;
+ n->peer_hash_mix = hash_mixes;
+ break;
+ }
+}
+
+struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
+ u16 capabilities, u32 hash_mixes,
+ bool preliminary)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_node *n, *temp_node;
struct tipc_link *l;
+ unsigned long intv;
int bearer_id;
int i;
spin_lock_bh(&tn->node_list_lock);
- n = tipc_node_find(net, addr);
+ n = tipc_node_find(net, addr) ?:
+ tipc_node_find_by_id(net, peer_id);
if (n) {
+ if (!n->preliminary)
+ goto update;
+ if (preliminary)
+ goto exit;
+ /* A preliminary node becomes "real" now, refresh its data */
+ tipc_node_write_lock(n);
+ n->preliminary = false;
+ n->addr = addr;
+ hlist_del_rcu(&n->hash);
+ hlist_add_head_rcu(&n->hash,
+ &tn->node_htable[tipc_hashfn(addr)]);
+ list_del_rcu(&n->list);
+ list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+ if (n->addr < temp_node->addr)
+ break;
+ }
+ list_add_tail_rcu(&n->list, &temp_node->list);
+ tipc_node_write_unlock_fast(n);
+
+update:
+ if (n->peer_hash_mix ^ hash_mixes)
+ tipc_node_assign_peer_net(n, hash_mixes);
if (n->capabilities == capabilities)
goto exit;
/* Same node may come back with new capabilities */
- write_lock_bh(&n->lock);
+ tipc_node_write_lock(n);
n->capabilities = capabilities;
for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
l = n->links[bearer_id].link;
if (l)
tipc_link_update_caps(l, capabilities);
}
- write_unlock_bh(&n->lock);
+ tipc_node_write_unlock_fast(n);
+
+ /* Calculate cluster capabilities */
+ tn->capabilities = TIPC_NODE_CAPABILITIES;
+ list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+ tn->capabilities &= temp_node->capabilities;
+ }
+
+ tipc_bcast_toggle_rcast(net,
+ (tn->capabilities & TIPC_BCAST_RCAST));
+
goto exit;
}
n = kzalloc(sizeof(*n), GFP_ATOMIC);
@@ -390,9 +506,23 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
pr_warn("Node creation failed, no memory\n");
goto exit;
}
+ tipc_nodeid2string(n->peer_id_string, peer_id);
+#ifdef CONFIG_TIPC_CRYPTO
+ if (unlikely(tipc_crypto_start(&n->crypto_rx, net, n))) {
+ pr_warn("Failed to start crypto RX(%s)!\n", n->peer_id_string);
+ kfree(n);
+ n = NULL;
+ goto exit;
+ }
+#endif
n->addr = addr;
+ n->preliminary = preliminary;
memcpy(&n->peer_id, peer_id, 16);
n->net = net;
+ n->peer_net = NULL;
+ n->peer_hash_mix = 0;
+ /* Assign kernel local namespace if exists */
+ tipc_node_assign_peer_net(n, hash_mixes);
n->capabilities = capabilities;
kref_init(&n->kref);
rwlock_init(&n->lock);
@@ -411,28 +541,26 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
n->signature = INVALID_NODE_SIG;
n->active_links[0] = INVALID_BEARER_ID;
n->active_links[1] = INVALID_BEARER_ID;
- if (!tipc_link_bc_create(net, tipc_own_addr(net),
- addr, U16_MAX,
- tipc_link_window(tipc_bc_sndlink(net)),
- n->capabilities,
- &n->bc_entry.inputq1,
- &n->bc_entry.namedq,
- tipc_bc_sndlink(net),
- &n->bc_entry.link)) {
- pr_warn("Broadcast rcv link creation failed, no memory\n");
- kfree(n);
- n = NULL;
- goto exit;
- }
+ n->bc_entry.link = NULL;
tipc_node_get(n);
timer_setup(&n->timer, tipc_node_timeout, 0);
- n->keepalive_intv = U32_MAX;
+ /* Start a slow timer anyway, crypto needs it */
+ n->keepalive_intv = 10000;
+ intv = jiffies + msecs_to_jiffies(n->keepalive_intv);
+ if (!mod_timer(&n->timer, intv))
+ tipc_node_get(n);
hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
if (n->addr < temp_node->addr)
break;
}
list_add_tail_rcu(&n->list, &temp_node->list);
+ /* Calculate cluster capabilities */
+ tn->capabilities = TIPC_NODE_CAPABILITIES;
+ list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+ tn->capabilities &= temp_node->capabilities;
+ }
+ tipc_bcast_toggle_rcast(net, (tn->capabilities & TIPC_BCAST_RCAST));
trace_tipc_node_create(n, true, " ");
exit:
spin_unlock_bh(&tn->node_list_lock);
@@ -589,6 +717,7 @@ static void tipc_node_clear_links(struct tipc_node *node)
*/
static bool tipc_node_cleanup(struct tipc_node *peer)
{
+ struct tipc_node *temp_node;
struct tipc_net *tn = tipc_net(peer->net);
bool deleted = false;
@@ -604,6 +733,19 @@ static bool tipc_node_cleanup(struct tipc_node *peer)
deleted = true;
}
tipc_node_write_unlock(peer);
+
+ if (!deleted) {
+ spin_unlock_bh(&tn->node_list_lock);
+ return deleted;
+ }
+
+ /* Calculate cluster capabilities */
+ tn->capabilities = TIPC_NODE_CAPABILITIES;
+ list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+ tn->capabilities &= temp_node->capabilities;
+ }
+ tipc_bcast_toggle_rcast(peer->net,
+ (tn->capabilities & TIPC_BCAST_RCAST));
spin_unlock_bh(&tn->node_list_lock);
return deleted;
}
@@ -626,6 +768,10 @@ static void tipc_node_timeout(struct timer_list *t)
return;
}
+#ifdef CONFIG_TIPC_CRYPTO
+ /* Take any crypto key related actions first */
+ tipc_crypto_timeout(n->crypto_rx);
+#endif
__skb_queue_head_init(&xmitq);
/* Initial node interval to value larger (10 seconds), then it will be
@@ -646,7 +792,7 @@ static void tipc_node_timeout(struct timer_list *t)
remains--;
}
tipc_node_read_unlock(n);
- tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr);
+ tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr, n);
if (rc & TIPC_LINK_DOWN_EVT)
tipc_node_link_down(n, bearer_id, false);
}
@@ -678,7 +824,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
n->link_id = tipc_link_id(nl);
/* Leave room for tunnel header when returning 'mtu' to users: */
- n->links[bearer_id].mtu = tipc_link_mtu(nl) - INT_H_SIZE;
+ n->links[bearer_id].mtu = tipc_link_mss(nl);
tipc_bearer_add_dest(n->net, bearer_id, n->addr);
tipc_bcast_inc_bearer_dst_cnt(n->net, bearer_id);
@@ -695,7 +841,6 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
*slot0 = bearer_id;
*slot1 = bearer_id;
tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT);
- n->failover_sent = false;
n->action_flags |= TIPC_NOTIFY_NODE_UP;
tipc_link_set_active(nl, true);
tipc_bcast_add_peer(n->net, nl, xmitq);
@@ -733,11 +878,54 @@ static void tipc_node_link_up(struct tipc_node *n, int bearer_id,
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_bearer_xmit(n->net, bearer_id, xmitq, maddr, n);
tipc_node_write_unlock(n);
}
/**
+ * tipc_node_link_failover() - start failover in case "half-failover"
+ *
+ * This function is only called in a very special situation where link
+ * failover can be already started on peer node but not on this node.
+ * This can happen when e.g.
+ * 1. Both links <1A-2A>, <1B-2B> down
+ * 2. Link endpoint 2A up, but 1A still down (e.g. due to network
+ * disturbance, wrong session, etc.)
+ * 3. Link <1B-2B> up
+ * 4. Link endpoint 2A down (e.g. due to link tolerance timeout)
+ * 5. Node 2 starts failover onto link <1B-2B>
+ *
+ * ==> Node 1 does never start link/node failover!
+ *
+ * @n: tipc node structure
+ * @l: link peer endpoint failingover (- can be NULL)
+ * @tnl: tunnel link
+ * @xmitq: queue for messages to be xmited on tnl link later
+ */
+static void tipc_node_link_failover(struct tipc_node *n, struct tipc_link *l,
+ struct tipc_link *tnl,
+ struct sk_buff_head *xmitq)
+{
+ /* Avoid to be "self-failover" that can never end */
+ if (!tipc_link_is_up(tnl))
+ return;
+
+ /* Don't rush, failure link may be in the process of resetting */
+ if (l && !tipc_link_is_reset(l))
+ return;
+
+ tipc_link_fsm_evt(tnl, LINK_SYNCH_END_EVT);
+ tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT);
+
+ n->sync_point = tipc_link_rcv_nxt(tnl) + (U16_MAX / 2 - 1);
+ tipc_link_failover_prepare(l, tnl, xmitq);
+
+ if (l)
+ tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
+ tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT);
+}
+
+/**
* __tipc_node_link_down - handle loss of link
*/
static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
@@ -845,7 +1033,7 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
if (delete)
tipc_mon_remove_peer(n->net, n->addr, old_bearer_id);
if (!skb_queue_empty(&xmitq))
- tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
+ tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr, n);
tipc_sk_rcv(n->net, &le->inputq);
}
@@ -889,6 +1077,8 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
{
struct tipc_net *tn = tipc_net(net);
struct tipc_node *n;
+ bool preliminary;
+ u32 sugg_addr;
/* Suggest new address if some other peer is using this one */
n = tipc_node_find(net, addr);
@@ -904,9 +1094,11 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
/* Suggest previously used address if peer is known */
n = tipc_node_find_by_id(net, id);
if (n) {
- addr = n->addr;
+ sugg_addr = n->addr;
+ preliminary = n->preliminary;
tipc_node_put(n);
- return addr;
+ if (!preliminary)
+ return sugg_addr;
}
/* Even this node may be in conflict */
@@ -918,12 +1110,12 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
void tipc_node_check_dest(struct net *net, u32 addr,
u8 *peer_id, struct tipc_bearer *b,
- u16 capabilities, u32 signature,
+ u16 capabilities, u32 signature, u32 hash_mixes,
struct tipc_media_addr *maddr,
bool *respond, bool *dupl_addr)
{
struct tipc_node *n;
- struct tipc_link *l;
+ struct tipc_link *l, *snd_l;
struct tipc_link_entry *le;
bool addr_match = false;
bool sign_match = false;
@@ -937,11 +1129,27 @@ void tipc_node_check_dest(struct net *net, u32 addr,
*dupl_addr = false;
*respond = false;
- n = tipc_node_create(net, addr, peer_id, capabilities);
+ n = tipc_node_create(net, addr, peer_id, capabilities, hash_mixes,
+ false);
if (!n)
return;
tipc_node_write_lock(n);
+ if (unlikely(!n->bc_entry.link)) {
+ snd_l = tipc_bc_sndlink(net);
+ if (!tipc_link_bc_create(net, tipc_own_addr(net),
+ addr, U16_MAX,
+ tipc_link_window(snd_l),
+ n->capabilities,
+ &n->bc_entry.inputq1,
+ &n->bc_entry.namedq, snd_l,
+ &n->bc_entry.link)) {
+ pr_warn("Broadcast rcv link creation failed, no mem\n");
+ tipc_node_write_unlock_fast(n);
+ tipc_node_put(n);
+ return;
+ }
+ }
le = &n->links[b->identity];
@@ -956,6 +1164,9 @@ void tipc_node_check_dest(struct net *net, u32 addr,
if (sign_match && addr_match && link_up) {
/* All is fine. Do nothing. */
reset = false;
+ /* Peer node is not a container/local namespace */
+ if (!n->peer_hash_mix)
+ n->peer_hash_mix = hash_mixes;
} else if (sign_match && addr_match && !link_up) {
/* Respond. The link will come up in due time */
*respond = true;
@@ -1281,7 +1492,8 @@ static void node_lost_contact(struct tipc_node *n,
/* Notify publications from this node */
n->action_flags |= TIPC_NOTIFY_NODE_DOWN;
-
+ n->peer_net = NULL;
+ n->peer_hash_mix = 0;
/* Notify sockets connected to node */
list_for_each_entry_safe(conn, safe, conns, list) {
skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
@@ -1340,7 +1552,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NODE);
if (!attrs)
goto msg_full;
@@ -1363,6 +1575,56 @@ msg_full:
return -EMSGSIZE;
}
+static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list)
+{
+ struct tipc_msg *hdr = buf_msg(skb_peek(list));
+ struct sk_buff_head inputq;
+
+ switch (msg_user(hdr)) {
+ case TIPC_LOW_IMPORTANCE:
+ case TIPC_MEDIUM_IMPORTANCE:
+ case TIPC_HIGH_IMPORTANCE:
+ case TIPC_CRITICAL_IMPORTANCE:
+ if (msg_connected(hdr) || msg_named(hdr)) {
+ tipc_loopback_trace(peer_net, list);
+ spin_lock_init(&list->lock);
+ tipc_sk_rcv(peer_net, list);
+ return;
+ }
+ if (msg_mcast(hdr)) {
+ tipc_loopback_trace(peer_net, list);
+ skb_queue_head_init(&inputq);
+ tipc_sk_mcast_rcv(peer_net, list, &inputq);
+ __skb_queue_purge(list);
+ skb_queue_purge(&inputq);
+ return;
+ }
+ return;
+ case MSG_FRAGMENTER:
+ if (tipc_msg_assemble(list)) {
+ tipc_loopback_trace(peer_net, list);
+ skb_queue_head_init(&inputq);
+ tipc_sk_mcast_rcv(peer_net, list, &inputq);
+ __skb_queue_purge(list);
+ skb_queue_purge(&inputq);
+ }
+ return;
+ case GROUP_PROTOCOL:
+ case CONN_MANAGER:
+ tipc_loopback_trace(peer_net, list);
+ spin_lock_init(&list->lock);
+ tipc_sk_rcv(peer_net, list);
+ return;
+ case LINK_PROTOCOL:
+ case NAME_DISTRIBUTOR:
+ case TUNNEL_PROTOCOL:
+ case BCAST_PROTOCOL:
+ return;
+ default:
+ return;
+ };
+}
+
/**
* tipc_node_xmit() is the general link level function for message sending
* @net: the applicable net namespace
@@ -1378,26 +1640,40 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list,
struct tipc_link_entry *le = NULL;
struct tipc_node *n;
struct sk_buff_head xmitq;
+ bool node_up = false;
int bearer_id;
int rc;
if (in_own_node(net, dnode)) {
+ tipc_loopback_trace(net, list);
+ spin_lock_init(&list->lock);
tipc_sk_rcv(net, list);
return 0;
}
n = tipc_node_find(net, dnode);
if (unlikely(!n)) {
- skb_queue_purge(list);
+ __skb_queue_purge(list);
return -EHOSTUNREACH;
}
tipc_node_read_lock(n);
+ node_up = node_is_up(n);
+ if (node_up && n->peer_net && check_net(n->peer_net)) {
+ /* xmit inner linux container */
+ tipc_lxc_xmit(n->peer_net, list);
+ if (likely(skb_queue_empty(list))) {
+ tipc_node_read_unlock(n);
+ tipc_node_put(n);
+ return 0;
+ }
+ }
+
bearer_id = n->active_links[selector & 1];
if (unlikely(bearer_id == INVALID_BEARER_ID)) {
tipc_node_read_unlock(n);
tipc_node_put(n);
- skb_queue_purge(list);
+ __skb_queue_purge(list);
return -EHOSTUNREACH;
}
@@ -1411,7 +1687,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list,
if (unlikely(rc == -ENOBUFS))
tipc_node_link_down(n, bearer_id, false);
else
- tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr);
+ tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n);
tipc_node_put(n);
@@ -1429,7 +1705,7 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode,
{
struct sk_buff_head head;
- skb_queue_head_init(&head);
+ __skb_queue_head_init(&head);
__skb_queue_tail(&head, skb);
tipc_node_xmit(net, &head, dnode, selector);
return 0;
@@ -1559,7 +1835,7 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
}
if (!skb_queue_empty(&xmitq))
- tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr);
+ tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n);
if (!skb_queue_empty(&be->inputq1))
tipc_node_mcast_rcv(n);
@@ -1588,7 +1864,6 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
int usr = msg_user(hdr);
int mtyp = msg_type(hdr);
u16 oseqno = msg_seqno(hdr);
- u16 iseqno = msg_seqno(msg_get_wrapped(hdr));
u16 exp_pkts = msg_msgcnt(hdr);
u16 rcv_nxt, syncpt, dlv_nxt, inputq_len;
int state = n->state;
@@ -1649,21 +1924,23 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
/* Initiate or update failover mode if applicable */
if ((usr == TUNNEL_PROTOCOL) && (mtyp == FAILOVER_MSG)) {
syncpt = oseqno + exp_pkts - 1;
- if (pl && tipc_link_is_up(pl)) {
+ if (pl && !tipc_link_is_reset(pl)) {
__tipc_node_link_down(n, &pb_id, xmitq, &maddr);
trace_tipc_node_link_down(n, true,
"node link down <- failover!");
tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl),
tipc_link_inputq(l));
}
+
/* If parallel link was already down, and this happened before
- * the tunnel link came up, FAILOVER was never sent. Ensure that
- * FAILOVER is sent to get peer out of NODE_FAILINGOVER state.
+ * the tunnel link came up, node failover was never started.
+ * Ensure that a FAILOVER_MSG is sent to get peer out of
+ * NODE_FAILINGOVER state, also this node must accept
+ * TUNNEL_MSGs from peer.
*/
- if (n->state != NODE_FAILINGOVER && !n->failover_sent) {
- tipc_link_create_dummy_tnl_msg(l, xmitq);
- n->failover_sent = true;
- }
+ if (n->state != NODE_FAILINGOVER)
+ tipc_node_link_failover(n, pl, l, xmitq);
+
/* If pkts arrive out of order, use lowest calculated syncpt */
if (less(syncpt, n->sync_point))
n->sync_point = syncpt;
@@ -1685,7 +1962,10 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
/* Initiate synch mode if applicable */
if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) {
- syncpt = iseqno + exp_pkts - 1;
+ if (n->capabilities & TIPC_TUNNEL_ENHANCED)
+ syncpt = msg_syncpt(hdr);
+ else
+ syncpt = msg_seqno(msg_inner_hdr(hdr)) + exp_pkts - 1;
if (!tipc_link_is_up(l))
__tipc_node_link_up(n, bearer_id, xmitq);
if (n->state == SELF_UP_PEER_UP) {
@@ -1733,19 +2013,38 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
{
struct sk_buff_head xmitq;
- struct tipc_node *n;
+ struct tipc_link_entry *le;
struct tipc_msg *hdr;
+ struct tipc_node *n;
int bearer_id = b->identity;
- struct tipc_link_entry *le;
u32 self = tipc_own_addr(net);
int usr, rc = 0;
u16 bc_ack;
+#ifdef CONFIG_TIPC_CRYPTO
+ struct tipc_ehdr *ehdr;
- __skb_queue_head_init(&xmitq);
+ /* Check if message must be decrypted first */
+ if (TIPC_SKB_CB(skb)->decrypted || !tipc_ehdr_validate(skb))
+ goto rcv;
+ ehdr = (struct tipc_ehdr *)skb->data;
+ if (likely(ehdr->user != LINK_CONFIG)) {
+ n = tipc_node_find(net, ntohl(ehdr->addr));
+ if (unlikely(!n))
+ goto discard;
+ } else {
+ n = tipc_node_find_by_id(net, ehdr->id);
+ }
+ tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b);
+ if (!skb)
+ return;
+
+rcv:
+#endif
/* Ensure message is well-formed before touching the header */
if (unlikely(!tipc_msg_validate(&skb)))
goto discard;
+ __skb_queue_head_init(&xmitq);
hdr = buf_msg(skb);
usr = msg_user(hdr);
bc_ack = msg_bcast_ack(hdr);
@@ -1816,7 +2115,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
tipc_sk_rcv(net, &le->inputq);
if (!skb_queue_empty(&xmitq))
- tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr);
+ tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n);
tipc_node_put(n);
discard:
@@ -1847,7 +2146,7 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b,
tipc_link_set_mtu(e->link, b->mtu);
}
tipc_node_write_unlock(n);
- tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr);
+ tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL);
}
rcu_read_unlock();
@@ -1858,7 +2157,7 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
struct net *net = sock_net(skb->sk);
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct nlattr *attrs[TIPC_NLA_NET_MAX + 1];
- struct tipc_node *peer;
+ struct tipc_node *peer, *temp_node;
u32 addr;
int err;
@@ -1866,9 +2165,9 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_NET])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
- info->attrs[TIPC_NLA_NET], tipc_nl_net_policy,
- info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX,
+ info->attrs[TIPC_NLA_NET],
+ tipc_nl_net_policy, info->extack);
if (err)
return err;
@@ -1899,6 +2198,12 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
tipc_node_write_unlock(peer);
tipc_node_delete(peer);
+ /* Calculate cluster capabilities */
+ tn->capabilities = TIPC_NODE_CAPABILITIES;
+ list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+ tn->capabilities &= temp_node->capabilities;
+ }
+ tipc_bcast_toggle_rcast(net, (tn->capabilities & TIPC_BCAST_RCAST));
err = 0;
err_out:
tipc_node_put(peer);
@@ -1943,6 +2248,8 @@ int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb)
}
list_for_each_entry_rcu(node, &tn->node_list, list) {
+ if (node->preliminary)
+ continue;
if (last_addr) {
if (node->addr == last_addr)
last_addr = 0;
@@ -2024,9 +2331,9 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_LINK])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
- info->attrs[TIPC_NLA_LINK],
- tipc_nl_link_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX,
+ info->attrs[TIPC_NLA_LINK],
+ tipc_nl_link_policy, info->extack);
if (err)
return err;
@@ -2082,7 +2389,8 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
out:
tipc_node_read_unlock(node);
- tipc_bearer_xmit(net, bearer_id, &xmitq, &node->links[bearer_id].maddr);
+ tipc_bearer_xmit(net, bearer_id, &xmitq, &node->links[bearer_id].maddr,
+ NULL);
return res;
}
@@ -2100,9 +2408,9 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_LINK])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
- info->attrs[TIPC_NLA_LINK],
- tipc_nl_link_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX,
+ info->attrs[TIPC_NLA_LINK],
+ tipc_nl_link_policy, info->extack);
if (err)
return err;
@@ -2165,9 +2473,9 @@ int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_LINK])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
- info->attrs[TIPC_NLA_LINK],
- tipc_nl_link_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX,
+ info->attrs[TIPC_NLA_LINK],
+ tipc_nl_link_policy, info->extack);
if (err)
return err;
@@ -2305,9 +2613,10 @@ int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[TIPC_NLA_MON])
return -EINVAL;
- err = nla_parse_nested(attrs, TIPC_NLA_MON_MAX,
- info->attrs[TIPC_NLA_MON],
- tipc_nl_monitor_policy, info->extack);
+ err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MON_MAX,
+ info->attrs[TIPC_NLA_MON],
+ tipc_nl_monitor_policy,
+ info->extack);
if (err)
return err;
@@ -2334,7 +2643,7 @@ static int __tipc_nl_add_monitor_prop(struct net *net, struct tipc_nl_msg *msg)
if (!hdr)
return -EMSGSIZE;
- attrs = nla_nest_start(msg->skb, TIPC_NLA_MON);
+ attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON);
if (!attrs)
goto msg_full;
@@ -2415,19 +2724,16 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
int err;
if (!prev_node) {
- struct nlattr **attrs;
+ struct nlattr **attrs = genl_dumpit_info(cb)->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, NULL);
+ err = nla_parse_nested_deprecated(mon, TIPC_NLA_MON_MAX,
+ attrs[TIPC_NLA_MON],
+ tipc_nl_monitor_policy,
+ NULL);
if (err)
return err;
@@ -2460,10 +2766,140 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
return skb->len;
}
-u32 tipc_node_get_addr(struct tipc_node *node)
+#ifdef CONFIG_TIPC_CRYPTO
+static int tipc_nl_retrieve_key(struct nlattr **attrs,
+ struct tipc_aead_key **key)
{
- return (node) ? node->addr : 0;
+ struct nlattr *attr = attrs[TIPC_NLA_NODE_KEY];
+
+ if (!attr)
+ return -ENODATA;
+
+ *key = (struct tipc_aead_key *)nla_data(attr);
+ if (nla_len(attr) < tipc_aead_key_size(*key))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int tipc_nl_retrieve_nodeid(struct nlattr **attrs, u8 **node_id)
+{
+ struct nlattr *attr = attrs[TIPC_NLA_NODE_ID];
+
+ if (!attr)
+ return -ENODATA;
+
+ if (nla_len(attr) < TIPC_NODEID_LEN)
+ return -EINVAL;
+
+ *node_id = (u8 *)nla_data(attr);
+ return 0;
+}
+
+int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1];
+ struct net *net = sock_net(skb->sk);
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_node *n = NULL;
+ struct tipc_aead_key *ukey;
+ struct tipc_crypto *c;
+ u8 *id, *own_id;
+ int rc = 0;
+
+ if (!info->attrs[TIPC_NLA_NODE])
+ return -EINVAL;
+
+ rc = nla_parse_nested(attrs, TIPC_NLA_NODE_MAX,
+ info->attrs[TIPC_NLA_NODE],
+ tipc_nl_node_policy, info->extack);
+ if (rc)
+ goto exit;
+
+ own_id = tipc_own_id(net);
+ if (!own_id) {
+ rc = -EPERM;
+ goto exit;
+ }
+
+ rc = tipc_nl_retrieve_key(attrs, &ukey);
+ if (rc)
+ goto exit;
+
+ rc = tipc_aead_key_validate(ukey);
+ if (rc)
+ goto exit;
+
+ rc = tipc_nl_retrieve_nodeid(attrs, &id);
+ switch (rc) {
+ case -ENODATA:
+ /* Cluster key mode */
+ rc = tipc_crypto_key_init(tn->crypto_tx, ukey, CLUSTER_KEY);
+ break;
+ case 0:
+ /* Per-node key mode */
+ if (!memcmp(id, own_id, NODE_ID_LEN)) {
+ c = tn->crypto_tx;
+ } else {
+ n = tipc_node_find_by_id(net, id) ?:
+ tipc_node_create(net, 0, id, 0xffffu, 0, true);
+ if (unlikely(!n)) {
+ rc = -ENOMEM;
+ break;
+ }
+ c = n->crypto_rx;
+ }
+
+ rc = tipc_crypto_key_init(c, ukey, PER_NODE_KEY);
+ if (n)
+ tipc_node_put(n);
+ break;
+ default:
+ break;
+ }
+
+exit:
+ return (rc < 0) ? rc : 0;
+}
+
+int tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
+{
+ int err;
+
+ rtnl_lock();
+ err = __tipc_nl_node_set_key(skb, info);
+ rtnl_unlock();
+
+ return err;
+}
+
+int __tipc_nl_node_flush_key(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = sock_net(skb->sk);
+ struct tipc_net *tn = tipc_net(net);
+ struct tipc_node *n;
+
+ tipc_crypto_key_flush(tn->crypto_tx);
+ rcu_read_lock();
+ list_for_each_entry_rcu(n, &tn->node_list, list)
+ tipc_crypto_key_flush(n->crypto_rx);
+ rcu_read_unlock();
+
+ pr_info("All keys are flushed!\n");
+ return 0;
+}
+
+int tipc_nl_node_flush_key(struct sk_buff *skb, struct genl_info *info)
+{
+ int err;
+
+ rtnl_lock();
+ err = __tipc_nl_node_flush_key(skb, info);
+ rtnl_unlock();
+
+ return err;
}
+#endif
/**
* tipc_node_dump - dump TIPC node data
@@ -2521,3 +2957,33 @@ int tipc_node_dump(struct tipc_node *n, bool more, char *buf)
return i;
}
+
+void tipc_node_pre_cleanup_net(struct net *exit_net)
+{
+ struct tipc_node *n;
+ struct tipc_net *tn;
+ struct net *tmp;
+
+ rcu_read_lock();
+ for_each_net_rcu(tmp) {
+ if (tmp == exit_net)
+ continue;
+ tn = tipc_net(tmp);
+ if (!tn)
+ continue;
+ spin_lock_bh(&tn->node_list_lock);
+ list_for_each_entry_rcu(n, &tn->node_list, list) {
+ if (!n->peer_net)
+ continue;
+ if (n->peer_net != exit_net)
+ continue;
+ tipc_node_write_lock(n);
+ n->peer_net = NULL;
+ n->peer_hash_mix = 0;
+ tipc_node_write_unlock_fast(n);
+ break;
+ }
+ spin_unlock_bh(&tn->node_list_lock);
+ }
+ rcu_read_unlock();
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 4f59a30e989a..a6803b449a2c 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -51,7 +51,11 @@ enum {
TIPC_BLOCK_FLOWCTL = (1 << 3),
TIPC_BCAST_RCAST = (1 << 4),
TIPC_NODE_ID128 = (1 << 5),
- TIPC_LINK_PROTO_SEQNO = (1 << 6)
+ TIPC_LINK_PROTO_SEQNO = (1 << 6),
+ TIPC_MCAST_RBCTL = (1 << 7),
+ TIPC_GAP_ACK_BLOCK = (1 << 8),
+ TIPC_TUNNEL_ENHANCED = (1 << 9),
+ TIPC_NAGLE = (1 << 10)
};
#define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \
@@ -60,16 +64,30 @@ enum {
TIPC_BCAST_RCAST | \
TIPC_BLOCK_FLOWCTL | \
TIPC_NODE_ID128 | \
- TIPC_LINK_PROTO_SEQNO)
+ TIPC_LINK_PROTO_SEQNO | \
+ TIPC_MCAST_RBCTL | \
+ TIPC_GAP_ACK_BLOCK | \
+ TIPC_TUNNEL_ENHANCED | \
+ TIPC_NAGLE)
+
#define INVALID_BEARER_ID -1
void tipc_node_stop(struct net *net);
bool tipc_node_get_id(struct net *net, u32 addr, u8 *id);
u32 tipc_node_get_addr(struct tipc_node *node);
+char *tipc_node_get_id_str(struct tipc_node *node);
+void tipc_node_put(struct tipc_node *node);
+struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
+ u16 capabilities, u32 hash_mixes,
+ bool preliminary);
+#ifdef CONFIG_TIPC_CRYPTO
+struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n);
+struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos);
+#endif
u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr);
void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128,
struct tipc_bearer *bearer,
- u16 capabilities, u32 signature,
+ u16 capabilities, u32 signature, u32 hash_mixes,
struct tipc_media_addr *maddr,
bool *respond, bool *dupl_addr);
void tipc_node_delete_links(struct net *net, int bearer_id);
@@ -86,7 +104,7 @@ void tipc_node_unsubscribe(struct net *net, struct list_head *subscr, u32 addr);
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);
+int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel, bool connected);
bool tipc_node_is_up(struct net *net, u32 addr);
u16 tipc_node_get_capabilities(struct net *net, u32 addr);
int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb);
@@ -101,4 +119,9 @@ 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);
+#ifdef CONFIG_TIPC_CRYPTO
+int tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_flush_key(struct sk_buff *skb, struct genl_info *info);
+#endif
+void tipc_node_pre_cleanup_net(struct net *exit_net);
#endif
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b542f14ed444..41688da233ab 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -75,6 +75,7 @@ struct sockaddr_pair {
* @conn_instance: TIPC instance used when connection was established
* @published: non-zero if port has one or more associated names
* @max_pkt: maximum packet size "hint" used when building messages sent by port
+ * @maxnagle: maximum size of msg which can be subject to nagle
* @portid: unique port identity in TIPC socket hash table
* @phdr: preformatted message header used when sending messages
* #cong_links: list of congested links
@@ -97,6 +98,7 @@ struct tipc_sock {
u32 conn_instance;
int published;
u32 max_pkt;
+ u32 maxnagle;
u32 portid;
struct tipc_msg phdr;
struct list_head cong_links;
@@ -116,6 +118,10 @@ struct tipc_sock {
struct tipc_mc_method mc_method;
struct rcu_head rcu;
struct tipc_group *group;
+ u32 oneway;
+ u16 snd_backlog;
+ bool expect_ack;
+ bool nodelay;
bool group_is_open;
};
@@ -137,6 +143,7 @@ static int tipc_sk_insert(struct tipc_sock *tsk);
static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
+static void tipc_sk_push_backlog(struct tipc_sock *tsk);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
@@ -227,6 +234,26 @@ static u16 tsk_inc(struct tipc_sock *tsk, int msglen)
return 1;
}
+/* tsk_set_nagle - enable/disable nagle property by manipulating maxnagle
+ */
+static void tsk_set_nagle(struct tipc_sock *tsk)
+{
+ struct sock *sk = &tsk->sk;
+
+ tsk->maxnagle = 0;
+ if (sk->sk_type != SOCK_STREAM)
+ return;
+ if (tsk->nodelay)
+ return;
+ if (!(tsk->peer_caps & TIPC_NAGLE))
+ return;
+ /* Limit node local buffer size to avoid receive queue overflow */
+ if (tsk->max_pkt == MAX_MSG_SIZE)
+ tsk->maxnagle = 1500;
+ else
+ tsk->maxnagle = tsk->max_pkt;
+}
+
/**
* tsk_advance_rx_queue - discard first buffer in socket receive queue
*
@@ -446,6 +473,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
tsk = tipc_sk(sk);
tsk->max_pkt = MAX_PKT_DEFAULT;
+ tsk->maxnagle = 0;
INIT_LIST_HEAD(&tsk->publications);
INIT_LIST_HEAD(&tsk->cong_links);
msg = &tsk->phdr;
@@ -486,7 +514,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
if (sock->type == SOCK_DGRAM)
tsk_set_unreliable(tsk, true);
}
-
+ __skb_queue_head_init(&tsk->mc_method.deferredq);
trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " ");
return 0;
}
@@ -504,7 +532,7 @@ static void __tipc_shutdown(struct socket *sock, int error)
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct net *net = sock_net(sk);
- long timeout = CONN_TIMEOUT_DEFAULT;
+ long timeout = msecs_to_jiffies(CONN_TIMEOUT_DEFAULT);
u32 dnode = tsk_peer_node(tsk);
struct sk_buff *skb;
@@ -512,7 +540,9 @@ static void __tipc_shutdown(struct socket *sock, int error)
tipc_wait_for_cond(sock, &timeout, (!tsk->cong_link_cnt &&
!tsk_conn_cong(tsk)));
- /* Remove any pending SYN message */
+ /* Push out delayed messages if in Nagle mode */
+ tipc_sk_push_backlog(tsk);
+ /* Remove pending SYN */
__skb_queue_purge(&sk->sk_write_queue);
/* Reject all unreceived messages, except on an active connection
@@ -582,6 +612,7 @@ static int tipc_release(struct socket *sock)
sk->sk_shutdown = SHUTDOWN_MASK;
tipc_sk_leave(tsk);
tipc_sk_withdraw(tsk, 0, NULL);
+ __skb_queue_purge(&tsk->mc_method.deferredq);
sk_stop_timer(sk, &sk->sk_timer);
tipc_sk_remove(tsk);
@@ -734,12 +765,12 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
switch (sk->sk_state) {
case TIPC_ESTABLISHED:
- case TIPC_CONNECTING:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
revents |= EPOLLOUT;
/* fall through */
case TIPC_LISTEN:
- if (!skb_queue_empty(&sk->sk_receive_queue))
+ case TIPC_CONNECTING:
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
revents |= EPOLLIN | EPOLLRDNORM;
break;
case TIPC_OPEN:
@@ -747,7 +778,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
revents |= EPOLLOUT;
if (!tipc_sk_type_connectionless(sk))
break;
- if (skb_queue_empty(&sk->sk_receive_queue))
+ if (skb_queue_empty_lockless(&sk->sk_receive_queue))
break;
revents |= EPOLLIN | EPOLLRDNORM;
break;
@@ -808,7 +839,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
msg_set_nameupper(hdr, seq->upper);
/* Build message as chain of buffers */
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts);
/* Send message if build was successful */
@@ -852,8 +883,8 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
msg_set_grp_bc_seqno(hdr, bc_snd_nxt);
/* Build message as chain of buffers */
- skb_queue_head_init(&pkts);
- mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
+ __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);
if (unlikely(rc != dlen))
return rc;
@@ -1057,7 +1088,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
msg_set_grp_bc_ack_req(hdr, ack);
/* Build message as chain of buffers */
- skb_queue_head_init(&pkts);
+ __skb_queue_head_init(&pkts);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
if (unlikely(rc != dlen))
return rc;
@@ -1207,6 +1238,32 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
tipc_sk_rcv(net, inputq);
}
+/* tipc_sk_push_backlog(): send accumulated buffers in socket write queue
+ * when socket is in Nagle mode
+ */
+static void tipc_sk_push_backlog(struct tipc_sock *tsk)
+{
+ struct sk_buff_head *txq = &tsk->sk.sk_write_queue;
+ struct net *net = sock_net(&tsk->sk);
+ u32 dnode = tsk_peer_node(tsk);
+ struct sk_buff *skb = skb_peek(txq);
+ int rc;
+
+ if (!skb || tsk->cong_link_cnt)
+ return;
+
+ /* Do not send SYN again after congestion */
+ if (msg_is_syn(buf_msg(skb)))
+ return;
+
+ tsk->snt_unacked += tsk->snd_backlog;
+ tsk->snd_backlog = 0;
+ tsk->expect_ack = true;
+ rc = tipc_node_xmit(net, txq, dnode, tsk->portid);
+ if (rc == -ELINKCONG)
+ tsk->cong_link_cnt = 1;
+}
+
/**
* tipc_sk_conn_proto_rcv - receive a connection mng protocol message
* @tsk: receiving socket
@@ -1220,7 +1277,7 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
u32 onode = tsk_own_node(tsk);
struct sock *sk = &tsk->sk;
int mtyp = msg_type(hdr);
- bool conn_cong;
+ bool was_cong;
/* Ignore if connection cannot be validated: */
if (!tsk_peer_msg(tsk, hdr)) {
@@ -1253,11 +1310,13 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
__skb_queue_tail(xmitq, skb);
return;
} else if (mtyp == CONN_ACK) {
- conn_cong = tsk_conn_cong(tsk);
+ was_cong = tsk_conn_cong(tsk);
+ tsk->expect_ack = false;
+ tipc_sk_push_backlog(tsk);
tsk->snt_unacked -= msg_conn_ack(hdr);
if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
tsk->snd_win = msg_adv_win(hdr);
- if (conn_cong)
+ if (was_cong && !tsk_conn_cong(tsk))
sk->sk_write_space(sk);
} else if (mtyp != CONN_PROBE_REPLY) {
pr_warn("Received unknown CONN_PROTO msg\n");
@@ -1386,13 +1445,15 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
if (unlikely(rc))
return rc;
- skb_queue_head_init(&pkts);
- mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
+ __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);
if (unlikely(rc != dlen))
return rc;
- if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue)))
+ if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue))) {
+ __skb_queue_purge(&pkts);
return -ENOMEM;
+ }
trace_tipc_sk_sendmsg(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " ");
rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
@@ -1436,15 +1497,15 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
struct sock *sk = sock->sk;
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
+ struct sk_buff_head *txq = &sk->sk_write_queue;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *hdr = &tsk->phdr;
struct net *net = sock_net(sk);
- struct sk_buff_head pkts;
u32 dnode = tsk_peer_node(tsk);
+ int maxnagle = tsk->maxnagle;
+ int maxpkt = tsk->max_pkt;
int send, sent = 0;
- int rc = 0;
-
- skb_queue_head_init(&pkts);
+ int blocks, rc = 0;
if (unlikely(dlen > INT_MAX))
return -EMSGSIZE;
@@ -1466,21 +1527,35 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
tipc_sk_connected(sk)));
if (unlikely(rc))
break;
-
send = min_t(size_t, dlen - sent, TIPC_MAX_USER_MSG_SIZE);
- rc = tipc_msg_build(hdr, m, sent, send, tsk->max_pkt, &pkts);
- if (unlikely(rc != send))
- break;
-
- trace_tipc_sk_sendstream(sk, skb_peek(&pkts),
+ blocks = tsk->snd_backlog;
+ if (tsk->oneway++ >= 4 && send <= maxnagle) {
+ rc = tipc_msg_append(hdr, m, send, maxnagle, txq);
+ if (unlikely(rc < 0))
+ break;
+ blocks += rc;
+ if (blocks <= 64 && tsk->expect_ack) {
+ tsk->snd_backlog = blocks;
+ sent += send;
+ break;
+ }
+ tsk->expect_ack = true;
+ } else {
+ rc = tipc_msg_build(hdr, m, sent, send, maxpkt, txq);
+ if (unlikely(rc != send))
+ break;
+ blocks += tsk_inc(tsk, send + MIN_H_SIZE);
+ }
+ trace_tipc_sk_sendstream(sk, skb_peek(txq),
TIPC_DUMP_SK_SNDQ, " ");
- rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
+ rc = tipc_node_xmit(net, txq, dnode, tsk->portid);
if (unlikely(rc == -ELINKCONG)) {
tsk->cong_link_cnt = 1;
rc = 0;
}
if (likely(!rc)) {
- tsk->snt_unacked += tsk_inc(tsk, send + MIN_H_SIZE);
+ tsk->snt_unacked += blocks;
+ tsk->snd_backlog = 0;
sent += send;
}
} while (sent < dlen && !rc);
@@ -1525,8 +1600,9 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV);
tipc_set_sk_state(sk, TIPC_ESTABLISHED);
tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
- tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
+ tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid, true);
tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
+ tsk_set_nagle(tsk);
__skb_queue_purge(&sk->sk_write_queue);
if (tsk->peer_caps & TIPC_BLOCK_FLOWCTL)
return;
@@ -1804,7 +1880,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
/* Send group flow control advertisement when applicable */
if (tsk->group && msg_in_group(hdr) && !grp_evt) {
- skb_queue_head_init(&xmitq);
+ __skb_queue_head_init(&xmitq);
tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen),
msg_orignode(hdr), msg_origport(hdr),
&xmitq);
@@ -1847,6 +1923,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
bool peek = flags & MSG_PEEK;
int offset, required, copy, copied = 0;
int hlen, dlen, err, rc;
+ bool ack = false;
long timeout;
/* Catch invalid receive attempts */
@@ -1891,6 +1968,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
/* Copy data if msg ok, otherwise return error/partial data */
if (likely(!err)) {
+ ack = msg_ack_required(hdr);
offset = skb_cb->bytes_read;
copy = min_t(int, dlen - offset, buflen - copied);
rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy);
@@ -1918,7 +1996,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
/* Send connection flow control advertisement when applicable */
tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen);
- if (unlikely(tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE))
+ if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE)
tipc_sk_send_ack(tsk);
/* Exit if all requested data or FIN/error received */
@@ -1989,6 +2067,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
smp_wmb();
tsk->cong_link_cnt--;
wakeup = true;
+ tipc_sk_push_backlog(tsk);
break;
case GROUP_PROTOCOL:
tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq);
@@ -2028,6 +2107,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
if (unlikely(msg_mcast(hdr)))
return false;
+ tsk->oneway = 0;
switch (sk->sk_state) {
case TIPC_CONNECTING:
@@ -2041,7 +2121,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
if (msg_data_sz(hdr))
return true;
/* Empty ACK-, - wake up sleeping connect() and drop */
- sk->sk_data_ready(sk);
+ sk->sk_state_change(sk);
msg_set_dest_droppable(hdr, 1);
return false;
}
@@ -2073,6 +2153,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
return true;
return false;
case TIPC_ESTABLISHED:
+ if (!skb_queue_empty(&sk->sk_write_queue))
+ tipc_sk_push_backlog(tsk);
/* Accept only connection-based messages sent by peer */
if (likely(con_msg && !err && pport == oport && pnode == onode))
return true;
@@ -2118,13 +2200,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
struct tipc_msg *hdr = buf_msg(skb);
if (unlikely(msg_in_group(hdr)))
- return sk->sk_rcvbuf;
+ return READ_ONCE(sk->sk_rcvbuf);
if (unlikely(!msg_connected(hdr)))
- return sk->sk_rcvbuf << msg_importance(hdr);
+ return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr);
if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
- return sk->sk_rcvbuf;
+ return READ_ONCE(sk->sk_rcvbuf);
return FLOWCTL_MSG_LIM;
}
@@ -2149,6 +2231,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
struct tipc_msg *hdr = buf_msg(skb);
struct net *net = sock_net(sk);
struct sk_buff_head inputq;
+ int mtyp = msg_type(hdr);
int limit, err = TIPC_OK;
trace_tipc_sk_filter_rcv(sk, skb, TIPC_DUMP_ALL, " ");
@@ -2162,6 +2245,9 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
if (unlikely(grp))
tipc_group_filter_msg(grp, &inputq, xmitq);
+ if (unlikely(!grp) && mtyp == TIPC_MCAST_MSG)
+ tipc_mcast_filter_msg(net, &tsk->mc_method.deferredq, &inputq);
+
/* Validate and add to receive buffer if there is space */
while ((skb = __skb_dequeue(&inputq))) {
hdr = buf_msg(skb);
@@ -2669,13 +2755,14 @@ static void tipc_sk_timeout(struct timer_list *t)
struct sk_buff_head list;
int rc = 0;
- skb_queue_head_init(&list);
+ __skb_queue_head_init(&list);
bh_lock_sock(sk);
/* Try again later if socket is busy */
if (sock_owned_by_user(sk)) {
sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20);
bh_unlock_sock(sk);
+ sock_put(sk);
return;
}
@@ -2799,7 +2886,7 @@ static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
struct tipc_sock *tsk;
rcu_read_lock();
- tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params);
+ tsk = rhashtable_lookup(&tn->sk_rht, &portid, tsk_rht_params);
if (tsk)
sock_hold(&tsk->sk);
rcu_read_unlock();
@@ -2954,6 +3041,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
case TIPC_SRC_DROPPABLE:
case TIPC_DEST_DROPPABLE:
case TIPC_CONN_TIMEOUT:
+ case TIPC_NODELAY:
if (ol < sizeof(value))
return -EINVAL;
if (get_user(value, (u32 __user *)ov))
@@ -3002,6 +3090,10 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
case TIPC_GROUP_LEAVE:
res = tipc_sk_leave(tsk);
break;
+ case TIPC_NODELAY:
+ tsk->nodelay = !!value;
+ tsk_set_nagle(tsk);
+ break;
default:
res = -EINVAL;
}
@@ -3064,6 +3156,9 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
case TIPC_SOCK_RECVQ_DEPTH:
value = skb_queue_len(&sk->sk_receive_queue);
break;
+ case TIPC_SOCK_RECVQ_USED:
+ value = sk_rmem_alloc_get(sk);
+ break;
case TIPC_GROUP_JOIN:
seq.type = 0;
if (tsk->group)
@@ -3264,7 +3359,7 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
peer_node = tsk_peer_node(tsk);
peer_port = tsk_peer_port(tsk);
- nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON);
+ nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON);
if (!nest)
return -EMSGSIZE;
@@ -3323,7 +3418,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
if (!hdr)
goto msg_cancel;
- attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+ attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK);
if (!attrs)
goto genlmsg_cancel;
@@ -3428,7 +3523,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
if (!(sk_filter_state & (1 << sk->sk_state)))
return 0;
- attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+ attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK);
if (!attrs)
goto msg_cancel;
@@ -3446,7 +3541,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
TIPC_NLA_SOCK_PAD))
goto attr_msg_cancel;
- stat = nla_nest_start(skb, TIPC_NLA_SOCK_STAT);
+ stat = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_STAT);
if (!stat)
goto attr_msg_cancel;
@@ -3503,7 +3598,7 @@ static int __tipc_nl_add_sk_publ(struct sk_buff *skb,
if (!hdr)
goto msg_cancel;
- attrs = nla_nest_start(skb, TIPC_NLA_PUBL);
+ attrs = nla_nest_start_noflag(skb, TIPC_NLA_PUBL);
if (!attrs)
goto genlmsg_cancel;
@@ -3580,19 +3675,15 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct tipc_sock *tsk;
if (!tsk_portid) {
- struct nlattr **attrs;
+ struct nlattr **attrs = genl_dumpit_info(cb)->attrs;
struct nlattr *sock[TIPC_NLA_SOCK_MAX + 1];
- err = tipc_nlmsg_parse(cb->nlh, &attrs);
- 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, NULL);
+ err = nla_parse_nested_deprecated(sock, TIPC_NLA_SOCK_MAX,
+ attrs[TIPC_NLA_SOCK],
+ tipc_nl_sock_policy, NULL);
if (err)
return err;
@@ -3782,7 +3873,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf);
i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk));
i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf);
- i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len);
+ i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len));
if (dqueues & TIPC_DUMP_SK_SNDQ) {
i += scnprintf(buf + i, sz - i, "sk_write_queue: ");
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index d793b4343885..aa015c233898 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -77,8 +77,9 @@ void tipc_sub_report_overlap(struct tipc_subscription *sub,
u32 found_lower, u32 found_upper,
u32 event, u32 port, u32 node,
u32 scope, int must);
-int tipc_topsrv_start(struct net *net);
-void tipc_topsrv_stop(struct net *net);
+
+int __net_init tipc_topsrv_init_net(struct net *net);
+void __net_exit tipc_topsrv_exit_net(struct net *net);
void tipc_sub_put(struct tipc_subscription *subscription);
void tipc_sub_get(struct tipc_subscription *subscription);
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 3481e4906bd6..58ab3d6dcdce 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -35,6 +35,7 @@
#include "core.h"
#include "trace.h"
+#include "crypto.h"
#include <linux/sysctl.h>
@@ -46,14 +47,16 @@ static struct ctl_table tipc_table[] = {
.data = &sysctl_tipc_rmem,
.maxlen = sizeof(sysctl_tipc_rmem),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ONE,
},
{
.procname = "named_timeout",
.data = &sysctl_tipc_named_timeout,
.maxlen = sizeof(sysctl_tipc_named_timeout),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
},
{
.procname = "sk_filter",
@@ -62,6 +65,16 @@ static struct ctl_table tipc_table[] = {
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
+#ifdef CONFIG_TIPC_CRYPTO
+ {
+ .procname = "max_tfms",
+ .data = &sysctl_tipc_max_tfms,
+ .maxlen = sizeof(sysctl_tipc_max_tfms),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ONE,
+ },
+#endif
{}
};
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index b45932d78004..3a12fc18239b 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -40,6 +40,7 @@
#include "socket.h"
#include "addr.h"
#include "msg.h"
+#include "bearer.h"
#include <net/sock.h>
#include <linux/module.h>
@@ -476,7 +477,7 @@ static void tipc_topsrv_accept(struct work_struct *work)
}
}
-/* tipc_toprsv_listener_data_ready - interrupt callback with connection request
+/* tipc_topsrv_listener_data_ready - interrupt callback with connection request
* The queued job is launched into tipc_topsrv_accept()
*/
static void tipc_topsrv_listener_data_ready(struct sock *sk)
@@ -608,6 +609,7 @@ static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt)
memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt));
skb_queue_head_init(&evtq);
__skb_queue_tail(&evtq, skb);
+ tipc_loopback_trace(net, &evtq);
tipc_sk_rcv(net, &evtq);
}
@@ -635,7 +637,7 @@ static void tipc_topsrv_work_stop(struct tipc_topsrv *s)
destroy_workqueue(s->send_wq);
}
-int tipc_topsrv_start(struct net *net)
+static int tipc_topsrv_start(struct net *net)
{
struct tipc_net *tn = tipc_net(net);
const char name[] = "topology_server";
@@ -668,7 +670,7 @@ int tipc_topsrv_start(struct net *net)
return ret;
}
-void tipc_topsrv_stop(struct net *net)
+static void tipc_topsrv_stop(struct net *net)
{
struct tipc_topsrv *srv = tipc_topsrv(net);
struct socket *lsock = srv->listener;
@@ -693,3 +695,13 @@ void tipc_topsrv_stop(struct net *net)
idr_destroy(&srv->conn_idr);
kfree(srv);
}
+
+int __net_init tipc_topsrv_init_net(struct net *net)
+{
+ return tipc_topsrv_start(net);
+}
+
+void __net_exit tipc_topsrv_exit_net(struct net *net)
+{
+ tipc_topsrv_stop(net);
+}
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 4d85d71f16e2..86aaa4d3e781 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -44,7 +44,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/udp_tunnel.h>
-#include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
#include <linux/tipc_netlink.h>
#include "core.h"
#include "addr.h"
@@ -76,6 +76,7 @@ struct udp_media_addr {
/* struct udp_replicast - container for UDP remote addresses */
struct udp_replicast {
struct udp_media_addr addr;
+ struct dst_cache dst_cache;
struct rcu_head rcu;
struct list_head list;
};
@@ -158,47 +159,52 @@ static int tipc_udp_addr2msg(char *msg, struct tipc_media_addr *a)
/* tipc_send_msg - enqueue a send request */
static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
struct udp_bearer *ub, struct udp_media_addr *src,
- struct udp_media_addr *dst)
+ struct udp_media_addr *dst, struct dst_cache *cache)
{
+ struct dst_entry *ndst = dst_cache_get(cache);
int ttl, err = 0;
- struct rtable *rt;
if (dst->proto == htons(ETH_P_IP)) {
- struct flowi4 fl = {
- .daddr = dst->ipv4.s_addr,
- .saddr = src->ipv4.s_addr,
- .flowi4_mark = skb->mark,
- .flowi4_proto = IPPROTO_UDP
- };
- rt = ip_route_output_key(net, &fl);
- if (IS_ERR(rt)) {
- err = PTR_ERR(rt);
- goto tx_error;
+ struct rtable *rt = (struct rtable *)ndst;
+
+ if (!rt) {
+ struct flowi4 fl = {
+ .daddr = dst->ipv4.s_addr,
+ .saddr = src->ipv4.s_addr,
+ .flowi4_mark = skb->mark,
+ .flowi4_proto = IPPROTO_UDP
+ };
+ rt = ip_route_output_key(net, &fl);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ goto tx_error;
+ }
+ dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
}
- skb->dev = rt->dst.dev;
ttl = ip4_dst_hoplimit(&rt->dst);
udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr,
dst->ipv4.s_addr, 0, ttl, 0, src->port,
dst->port, false, true);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- struct dst_entry *ndst;
- struct flowi6 fl6 = {
- .flowi6_oif = ub->ifindex,
- .daddr = dst->ipv6,
- .saddr = src->ipv6,
- .flowi6_proto = IPPROTO_UDP
- };
- err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, &ndst,
- &fl6);
- if (err)
- goto tx_error;
+ if (!ndst) {
+ struct flowi6 fl6 = {
+ .flowi6_oif = ub->ifindex,
+ .daddr = dst->ipv6,
+ .saddr = src->ipv6,
+ .flowi6_proto = IPPROTO_UDP
+ };
+ err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk,
+ &ndst, &fl6);
+ if (err)
+ goto tx_error;
+ dst_cache_set_ip6(cache, ndst, &fl6.saddr);
+ }
ttl = ip6_dst_hoplimit(ndst);
- err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb,
- ndst->dev, &src->ipv6,
- &dst->ipv6, 0, ttl, 0, src->port,
- dst->port, false);
+ err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL,
+ &src->ipv6, &dst->ipv6, 0, ttl, 0,
+ src->port, dst->port, false);
#endif
}
return err;
@@ -225,14 +231,15 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
}
skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rcu_dereference(b->media_ptr);
if (!ub) {
err = -ENODEV;
goto out;
}
if (addr->broadcast != TIPC_REPLICAST_SUPPORT)
- return tipc_udp_xmit(net, skb, ub, src, dst);
+ return tipc_udp_xmit(net, skb, ub, src, dst,
+ &ub->rcast.dst_cache);
/* Replicast, send an skb to each configured IP address */
list_for_each_entry_rcu(rcast, &ub->rcast.list, list) {
@@ -244,7 +251,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
goto out;
}
- err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr);
+ err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr,
+ &rcast->dst_cache);
if (err)
goto out;
}
@@ -288,6 +296,11 @@ static int tipc_udp_rcast_add(struct tipc_bearer *b,
if (!rcast)
return -ENOMEM;
+ if (dst_cache_init(&rcast->dst_cache, GFP_ATOMIC)) {
+ kfree(rcast);
+ return -ENOMEM;
+ }
+
memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr));
if (ntohs(addr->proto) == ETH_P_IP)
@@ -354,25 +367,22 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
skb_pull(skb, sizeof(struct udphdr));
hdr = buf_msg(skb);
- rcu_read_lock();
- b = rcu_dereference_rtnl(ub->bearer);
+ b = rcu_dereference(ub->bearer);
if (!b)
- goto rcu_out;
+ goto out;
if (b && test_bit(0, &b->up)) {
+ TIPC_SKB_CB(skb)->flags = 0;
tipc_rcv(sock_net(sk), skb, b);
- rcu_read_unlock();
return 0;
}
if (unlikely(msg_user(hdr) == LINK_CONFIG)) {
err = tipc_udp_rcast_disc(b, skb);
if (err)
- goto rcu_out;
+ goto out;
}
-rcu_out:
- rcu_read_unlock();
out:
kfree_skb(skb);
return 0;
@@ -439,21 +449,17 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
int i;
if (!bid && !skip_cnt) {
+ struct nlattr **attrs = genl_dumpit_info(cb)->attrs;
struct net *net = sock_net(skb->sk);
struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1];
- struct nlattr **attrs;
char *bname;
- err = tipc_nlmsg_parse(cb->nlh, &attrs);
- if (err)
- return err;
-
if (!attrs[TIPC_NLA_BEARER])
return -EINVAL;
- err = nla_parse_nested(battrs, TIPC_NLA_BEARER_MAX,
- attrs[TIPC_NLA_BEARER],
- tipc_nl_bearer_policy, NULL);
+ err = nla_parse_nested_deprecated(battrs, TIPC_NLA_BEARER_MAX,
+ attrs[TIPC_NLA_BEARER],
+ tipc_nl_bearer_policy, NULL);
if (err)
return err;
@@ -481,7 +487,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
}
}
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rtnl_dereference(b->media_ptr);
if (!ub) {
rtnl_unlock();
return -EINVAL;
@@ -523,11 +529,11 @@ int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b)
struct udp_bearer *ub;
struct nlattr *nest;
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rtnl_dereference(b->media_ptr);
if (!ub)
return -ENODEV;
- nest = nla_nest_start(msg->skb, TIPC_NLA_BEARER_UDP_OPTS);
+ nest = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_UDP_OPTS);
if (!nest)
goto msg_full;
@@ -605,8 +611,7 @@ int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr)
struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
struct udp_media_addr *dst;
- if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr,
- tipc_nl_udp_policy, NULL))
+ if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy, NULL))
return -EINVAL;
if (!opts[TIPC_NLA_UDP_REMOTE])
@@ -659,9 +664,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
if (!attrs[TIPC_NLA_BEARER_UDP_OPTS])
goto err;
- if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX,
- attrs[TIPC_NLA_BEARER_UDP_OPTS],
- tipc_nl_udp_policy, NULL))
+ if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attrs[TIPC_NLA_BEARER_UDP_OPTS], tipc_nl_udp_policy, NULL))
goto err;
if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) {
@@ -751,6 +754,10 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
tuncfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg);
+ err = dst_cache_init(&ub->rcast.dst_cache, GFP_ATOMIC);
+ if (err)
+ goto free;
+
/**
* The bcast media address port is used for all peers and the ip
* is used if it's a multicast address.
@@ -761,12 +768,14 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
else
err = tipc_udp_rcast_add(b, &remote);
if (err)
- goto err;
+ goto free;
return 0;
+
+free:
+ dst_cache_destroy(&ub->rcast.dst_cache);
+ udp_tunnel_sock_release(ub->ubsock);
err:
- if (ub->ubsock)
- udp_tunnel_sock_release(ub->ubsock);
kfree(ub);
return err;
}
@@ -778,12 +787,13 @@ static void cleanup_bearer(struct work_struct *work)
struct udp_replicast *rcast, *tmp;
list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) {
+ dst_cache_destroy(&rcast->dst_cache);
list_del_rcu(&rcast->list);
kfree_rcu(rcast, rcu);
}
- if (ub->ubsock)
- udp_tunnel_sock_release(ub->ubsock);
+ dst_cache_destroy(&ub->rcast.dst_cache);
+ udp_tunnel_sock_release(ub->ubsock);
synchronize_net();
kfree(ub);
}
@@ -793,13 +803,12 @@ static void tipc_udp_disable(struct tipc_bearer *b)
{
struct udp_bearer *ub;
- ub = rcu_dereference_rtnl(b->media_ptr);
+ ub = rtnl_dereference(b->media_ptr);
if (!ub) {
pr_err("UDP bearer instance not found\n");
return;
}
- if (ub->ubsock)
- sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
+ sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
RCU_INIT_POINTER(ub->bearer, NULL);
/* sock_release need to be done outside of rtnl lock */
generated by cgit v1.2.3 (git 2.39.0) at 2025-12-17 00:42:42 +0300