Resguardo inicial

linux-7.2.3/net/tipc/Kconfig

@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# TIPC configuration
+#
+
+menuconfig TIPC
+	tristate "The TIPC Protocol"
+	depends on INET
+	help
+	  The Transparent Inter Process Communication (TIPC) protocol is
+	  specially designed for intra cluster communication. This protocol
+	  originates from Ericsson where it has been used in carrier grade
+	  cluster applications for many years.
+
+	  For more information about TIPC, see http://tipc.sourceforge.net.
+
+	  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.rst>.
+
+	  If in doubt, say N.
+
+config TIPC_MEDIA_IB
+	bool "InfiniBand media type support"
+	depends on TIPC && INFINIBAND_IPOIB
+	help
+	  Saying Y here will enable support for running TIPC on
+	  IP-over-InfiniBand devices.
+config TIPC_MEDIA_UDP
+	bool "IP/UDP media type support"
+	depends on TIPC
+	select NET_UDP_TUNNEL
+	default y
+	help
+	  Saying Y here will enable support for running TIPC over IP/UDP
+
+config TIPC_CRYPTO
+	bool "TIPC encryption support"
+	depends on TIPC
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_GCM
+	default y
+	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).
+
+config TIPC_DIAG
+	tristate "TIPC: socket monitoring interface"
+	depends on TIPC
+	default y
+	help
+	Support for TIPC socket monitoring interface used by ss tool.
+	If unsure, say Y.

linux-7.2.3/net/tipc/Makefile

@@ -0,0 +1,22 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux TIPC layer
+#
+
+obj-$(CONFIG_TIPC) := tipc.o
+
+tipc-y	+= addr.o bcast.o bearer.o \
+	   core.o link.o discover.o msg.o  \
+	   name_distr.o  subscr.o monitor.o name_table.o net.o  \
+	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
+	   topsrv.o group.o trace.o
+
+CFLAGS_trace.o += -I$(src)
+
+tipc-$(CONFIG_TIPC_MEDIA_UDP)	+= udp_media.o
+tipc-$(CONFIG_TIPC_MEDIA_IB)	+= ib_media.o
+tipc-$(CONFIG_SYSCTL)		+= sysctl.o
+tipc-$(CONFIG_TIPC_CRYPTO)	+= crypto.o
+
+obj-$(CONFIG_TIPC_DIAG)	+= tipc_diag.o
+tipc_diag-y	+= diag.o

linux-7.2.3/net/tipc/addr.c

@@ -0,0 +1,124 @@
+/*
+ * net/tipc/addr.c: TIPC address utility routines
+ *
+ * Copyright (c) 2000-2006, 2018, Ericsson AB
+ * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
+ * Copyright (c) 2020-2021, Red Hat Inc
+ * 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 "addr.h"
+#include "core.h"
+
+bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr)
+{
+	if (!domain || (domain == addr))
+		return true;
+	if (!legacy_format)
+		return false;
+	if (domain == tipc_cluster_mask(addr)) /* domain <Z.C.0> */
+		return true;
+	if (domain == (addr & TIPC_ZONE_CLUSTER_MASK)) /* domain <Z.C.0> */
+		return true;
+	if (domain == (addr & TIPC_ZONE_MASK)) /* domain <Z.0.0> */
+		return true;
+	return false;
+}
+
+void tipc_set_node_id(struct net *net, u8 *id)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	memcpy(tn->node_id, id, NODE_ID_LEN);
+	tipc_nodeid2string(tn->node_id_string, id);
+	tn->trial_addr = hash128to32(id);
+	pr_info("Node identity %s, cluster identity %u\n",
+		tipc_own_id_string(net), tn->net_id);
+}
+
+void tipc_set_node_addr(struct net *net, u32 addr)
+{
+	struct tipc_net *tn = tipc_net(net);
+	u8 node_id[NODE_ID_LEN] = {0,};
+
+	tn->node_addr = addr;
+	if (!tipc_own_id(net)) {
+		sprintf(node_id, "%x", addr);
+		tipc_set_node_id(net, node_id);
+	}
+	tn->trial_addr = addr;
+	tn->addr_trial_end = jiffies;
+	pr_info("Node number set to %u\n", addr);
+}
+
+int tipc_nodeid2string(char *str, u8 *id)
+{
+	int i;
+	u8 c;
+
+	/* Already a string ? */
+	for (i = 0; i < NODE_ID_LEN; i++) {
+		c = id[i];
+		if (c >= '0' && c <= '9')
+			continue;
+		if (c >= 'A' && c <= 'Z')
+			continue;
+		if (c >= 'a' && c <= 'z')
+			continue;
+		if (c == '.')
+			continue;
+		if (c == ':')
+			continue;
+		if (c == '_')
+			continue;
+		if (c == '-')
+			continue;
+		if (c == '@')
+			continue;
+		if (c != 0)
+			break;
+	}
+	if (i == NODE_ID_LEN) {
+		memcpy(str, id, NODE_ID_LEN);
+		str[NODE_ID_LEN] = 0;
+		return i;
+	}
+
+	/* Translate to hex string */
+	for (i = 0; i < NODE_ID_LEN; i++)
+		sprintf(&str[2 * i], "%02x", id[i]);
+
+	/* Strip off trailing zeroes */
+	for (i = NODE_ID_STR_LEN - 2; str[i] == '0'; i--)
+		str[i] = 0;
+
+	return i + 1;
+}

linux-7.2.3/net/tipc/addr.h

@@ -0,0 +1,135 @@
+/*
+ * net/tipc/addr.h: Include file for TIPC address utility routines
+ *
+ * Copyright (c) 2000-2006, 2018, Ericsson AB
+ * Copyright (c) 2004-2005, Wind River Systems
+ * Copyright (c) 2020-2021, Red Hat Inc
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_ADDR_H
+#define _TIPC_ADDR_H
+
+#include <linux/types.h>
+#include <linux/tipc.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include "core.h"
+
+/* Struct tipc_uaddr: internal version of struct sockaddr_tipc.
+ * Must be kept aligned both regarding field positions and size.
+ */
+struct tipc_uaddr {
+	unsigned short family;
+	unsigned char addrtype;
+	signed char scope;
+	union {
+		struct {
+			struct tipc_service_addr sa;
+			u32 lookup_node;
+		};
+		struct tipc_service_range sr;
+		struct tipc_socket_addr sk;
+	};
+};
+
+static inline void tipc_uaddr(struct tipc_uaddr *ua, u32 atype, u32 scope,
+			      u32 type, u32 lower, u32 upper)
+{
+	ua->family = AF_TIPC;
+	ua->addrtype = atype;
+	ua->scope = scope;
+	ua->sr.type = type;
+	ua->sr.lower = lower;
+	ua->sr.upper = upper;
+}
+
+static inline bool tipc_uaddr_valid(struct tipc_uaddr *ua, int len)
+{
+	u32 atype;
+
+	if (len < sizeof(struct sockaddr_tipc))
+		return false;
+	atype = ua->addrtype;
+	if (ua->family != AF_TIPC)
+		return false;
+	if (atype == TIPC_SERVICE_ADDR || atype == TIPC_SOCKET_ADDR)
+		return true;
+	if (atype == TIPC_SERVICE_RANGE)
+		return ua->sr.upper >= ua->sr.lower;
+	return false;
+}
+
+static inline u32 tipc_own_addr(struct net *net)
+{
+	return tipc_net(net)->node_addr;
+}
+
+static inline u8 *tipc_own_id(struct net *net)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	if (!strlen(tn->node_id_string))
+		return NULL;
+	return tn->node_id;
+}
+
+static inline char *tipc_own_id_string(struct net *net)
+{
+	return tipc_net(net)->node_id_string;
+}
+
+static inline u32 tipc_cluster_mask(u32 addr)
+{
+	return addr & TIPC_ZONE_CLUSTER_MASK;
+}
+
+static inline int tipc_node2scope(u32 node)
+{
+	return node ? TIPC_NODE_SCOPE : TIPC_CLUSTER_SCOPE;
+}
+
+static inline int tipc_scope2node(struct net *net, int sc)
+{
+	return sc != TIPC_NODE_SCOPE ? 0 : tipc_own_addr(net);
+}
+
+static inline int in_own_node(struct net *net, u32 addr)
+{
+	return addr == tipc_own_addr(net) || !addr;
+}
+
+bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr);
+void tipc_set_node_id(struct net *net, u8 *id);
+void tipc_set_node_addr(struct net *net, u32 addr);
+int tipc_nodeid2string(char *str, u8 *id);
+
+#endif

linux-7.2.3/net/tipc/bcast.c

@@ -0,0 +1,870 @@
+/*
+ * net/tipc/bcast.c: TIPC broadcast code
+ *
+ * Copyright (c) 2004-2006, 2014-2017, Ericsson AB
+ * Copyright (c) 2004, Intel Corporation.
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * 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 <linux/tipc_config.h>
+#include "socket.h"
+#include "msg.h"
+#include "bcast.h"
+#include "link.h"
+#include "name_table.h"
+
+#define BCLINK_WIN_DEFAULT  50	/* bcast link window size (default) */
+#define BCLINK_WIN_MIN      32	/* bcast minimum link window size */
+
+const char tipc_bclink_name[] = "broadcast-link";
+unsigned long sysctl_tipc_bc_retruni __read_mostly;
+
+/**
+ * struct tipc_bc_base - base structure for keeping broadcast send state
+ * @link: broadcast send link structure
+ * @inputq: data input queue; will only carry SOCK_WAKEUP messages
+ * @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
+ */
+struct tipc_bc_base {
+	struct tipc_link *link;
+	struct sk_buff_head inputq;
+	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;
+};
+
+static struct tipc_bc_base *tipc_bc_base(struct net *net)
+{
+	return tipc_net(net)->bcbase;
+}
+
+/* tipc_bcast_get_mtu(): -get the MTU currently used by broadcast link
+ * Note: the MTU is decremented to give room for a tunnel header, in
+ * case the message needs to be sent as replicast
+ */
+int tipc_bcast_get_mtu(struct net *net)
+{
+	return tipc_link_mss(tipc_bc_sndlink(net));
+}
+
+void tipc_bcast_toggle_rcast(struct net *net, bool supp)
+{
+	tipc_bc_base(net)->rcast_support = supp;
+}
+
+static void tipc_bcbase_calc_bc_threshold(struct net *net)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+	int cluster_size = tipc_link_bc_peers(tipc_bc_sndlink(net));
+
+	bb->bc_threshold = 1 + (cluster_size * bb->rc_ratio / 100);
+}
+
+/* tipc_bcbase_select_primary(): find a bearer with links to all destinations,
+ *                               if any, and make it primary bearer
+ */
+static void tipc_bcbase_select_primary(struct net *net)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+	int all_dests =  tipc_link_bc_peers(bb->link);
+	int max_win = tipc_link_max_win(bb->link);
+	int min_win = tipc_link_min_win(bb->link);
+	int i, mtu, prim;
+
+	bb->primary_bearer = INVALID_BEARER_ID;
+	bb->bcast_support = true;
+
+	if (!all_dests)
+		return;
+
+	for (i = 0; i < MAX_BEARERS; i++) {
+		if (!bb->dests[i])
+			continue;
+
+		mtu = tipc_bearer_mtu(net, i);
+		if (mtu < tipc_link_mtu(bb->link)) {
+			tipc_link_set_mtu(bb->link, mtu);
+			tipc_link_set_queue_limits(bb->link,
+						   min_win,
+						   max_win);
+		}
+		bb->bcast_support &= tipc_bearer_bcast_support(net, i);
+		if (bb->dests[i] < all_dests)
+			continue;
+
+		bb->primary_bearer = i;
+
+		/* Reduce risk that all nodes select same primary */
+		if ((i ^ tipc_own_addr(net)) & 1)
+			break;
+	}
+	prim = bb->primary_bearer;
+	if (prim != INVALID_BEARER_ID)
+		bb->bcast_support = tipc_bearer_bcast_support(net, prim);
+}
+
+void tipc_bcast_inc_bearer_dst_cnt(struct net *net, int bearer_id)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+
+	tipc_bcast_lock(net);
+	bb->dests[bearer_id]++;
+	tipc_bcbase_select_primary(net);
+	tipc_bcast_unlock(net);
+}
+
+void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+
+	tipc_bcast_lock(net);
+	bb->dests[bearer_id]--;
+	tipc_bcbase_select_primary(net);
+	tipc_bcast_unlock(net);
+}
+
+/* tipc_bcbase_xmit - broadcast a packet queue across one or more bearers
+ *
+ * Note that number of reachable destinations, as indicated in the dests[]
+ * array, may transitionally differ from the number of destinations indicated
+ * in each sent buffer. We can sustain this. Excess destination nodes will
+ * drop and never acknowledge the unexpected packets, and missing destinations
+ * will either require retransmission (if they are just about to be added to
+ * the bearer), or be removed from the buffer's 'ackers' counter (if they
+ * just went down)
+ */
+static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq)
+{
+	int bearer_id;
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+	struct sk_buff *skb, *_skb;
+	struct sk_buff_head _xmitq;
+
+	if (skb_queue_empty(xmitq))
+		return;
+
+	/* The typical case: at least one bearer has links to all nodes */
+	bearer_id = bb->primary_bearer;
+	if (bearer_id >= 0) {
+		tipc_bearer_bc_xmit(net, bearer_id, xmitq);
+		return;
+	}
+
+	/* We have to transmit across all bearers */
+	__skb_queue_head_init(&_xmitq);
+	for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+		if (!bb->dests[bearer_id])
+			continue;
+
+		skb_queue_walk(xmitq, skb) {
+			_skb = pskb_copy_for_clone(skb, GFP_ATOMIC);
+			if (!_skb)
+				break;
+			__skb_queue_tail(&_xmitq, _skb);
+		}
+		tipc_bearer_bc_xmit(net, bearer_id, &_xmitq);
+	}
+	__skb_queue_purge(xmitq);
+	__skb_queue_purge(&_xmitq);
+}
+
+static void tipc_bcast_select_xmit_method(struct net *net, int dests,
+					  struct tipc_mc_method *method)
+{
+	struct tipc_bc_base *bb = tipc_bc_base(net);
+	unsigned long exp = method->expires;
+
+	/* Broadcast supported by used bearer/bearers? */
+	if (!bb->bcast_support) {
+		method->rcast = true;
+		return;
+	}
+	/* Any destinations which don't support replicast ? */
+	if (!bb->rcast_support) {
+		method->rcast = false;
+		return;
+	}
+	/* Can current method be changed ? */
+	method->expires = jiffies + TIPC_METHOD_EXPIRE;
+	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;
+}
+
+/* tipc_bcast_xmit - broadcast the buffer chain to all external nodes
+ * @net: the applicable net namespace
+ * @pkts: chain of buffers containing message
+ * @cong_link_cnt: set to 1 if broadcast link is congested, otherwise 0
+ * Consumes the buffer chain.
+ * Returns 0 if success, otherwise errno: -EHOSTUNREACH,-EMSGSIZE
+ */
+int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts,
+		    u16 *cong_link_cnt)
+{
+	struct tipc_link *l = tipc_bc_sndlink(net);
+	struct sk_buff_head xmitq;
+	int rc = 0;
+
+	__skb_queue_head_init(&xmitq);
+	tipc_bcast_lock(net);
+	if (tipc_link_bc_peers(l))
+		rc = tipc_link_xmit(l, pkts, &xmitq);
+	tipc_bcast_unlock(net);
+	tipc_bcbase_xmit(net, &xmitq);
+	__skb_queue_purge(pkts);
+	if (rc == -ELINKCONG) {
+		*cong_link_cnt = 1;
+		rc = 0;
+	}
+	return rc;
+}
+
+/* tipc_rcast_xmit - replicate and send a message to given destination nodes
+ * @net: the applicable net namespace
+ * @pkts: chain of buffers containing message
+ * @dests: list of destination nodes
+ * @cong_link_cnt: returns number of congested links
+ * @cong_links: returns identities of congested links
+ * Returns 0 if success, otherwise errno
+ */
+static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts,
+			   struct tipc_nlist *dests, u16 *cong_link_cnt)
+{
+	struct tipc_dest *dst, *tmp;
+	struct sk_buff_head _pkts;
+	u32 dnode, selector;
+
+	selector = msg_link_selector(buf_msg(skb_peek(pkts)));
+	__skb_queue_head_init(&_pkts);
+
+	list_for_each_entry_safe(dst, tmp, &dests->list, list) {
+		dnode = dst->node;
+		if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts))
+			return -ENOMEM;
+
+		/* Any other return value than -ELINKCONG is ignored */
+		if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG)
+			(*cong_link_cnt)++;
+	}
+	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.
+ * 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)
+{
+	struct tipc_msg *hdr, *_hdr;
+	struct sk_buff_head tmpq;
+	u16 cong_link_cnt = 0;
+	struct sk_buff *_skb;
+	int rc = 0;
+
+	/* 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));
+	msg_set_errcode(_hdr, TIPC_ERR_NO_PORT);
+
+	__skb_queue_head_init(&tmpq);
+	__skb_queue_tail(&tmpq, _skb);
+	if (method->rcast)
+		rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt);
+	else
+		rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt);
+
+	/* This queue should normally be empty by now */
+	__skb_queue_purge(&tmpq);
+
+	return rc;
+}
+
+/* tipc_mcast_xmit - deliver message to indicated destination nodes
+ *                   and to identified node local sockets
+ * @net: the applicable net namespace
+ * @pkts: chain of buffers containing message
+ * @method: send method to be used
+ * @dests: destination nodes for message.
+ * @cong_link_cnt: returns number of encountered congested destination links
+ * Consumes buffer chain.
+ * Returns 0 if success, otherwise errno
+ */
+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)
+{
+	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);
+
+	/* Clone packets before they are consumed by next call */
+	if (dests->local && !tipc_msg_reassemble(pkts, &localq)) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+	/* 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) {
+			rc = tipc_mcast_send_sync(net, skb, method, dests);
+			if (unlikely(rc)) {
+				pr_err("Unable to send SYN: method %d, rc %d\n",
+				       rcast, rc);
+				goto exit;
+			}
+		}
+
+		if (method->rcast)
+			rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt);
+		else
+			rc = tipc_bcast_xmit(net, pkts, cong_link_cnt);
+	}
+
+	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);
+	return rc;
+}
+
+/* tipc_bcast_rcv - receive a broadcast packet, and deliver to rcv link
+ *
+ * RCU is locked, no other locks set
+ */
+int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb)
+{
+	struct tipc_msg *hdr = buf_msg(skb);
+	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
+	struct sk_buff_head xmitq;
+	int rc;
+
+	__skb_queue_head_init(&xmitq);
+
+	if (msg_mc_netid(hdr) != tipc_netid(net) || !tipc_link_is_up(l)) {
+		kfree_skb(skb);
+		return 0;
+	}
+
+	tipc_bcast_lock(net);
+	if (msg_user(hdr) == BCAST_PROTOCOL)
+		rc = tipc_link_bc_nack_rcv(l, skb, &xmitq);
+	else
+		rc = tipc_link_rcv(l, skb, NULL);
+	tipc_bcast_unlock(net);
+
+	tipc_bcbase_xmit(net, &xmitq);
+
+	/* Any socket wakeup messages ? */
+	if (!skb_queue_empty(inputq))
+		tipc_sk_rcv(net, inputq);
+
+	return rc;
+}
+
+/* tipc_bcast_ack_rcv - receive and handle a broadcast acknowledge
+ *
+ * RCU is locked, no other locks set
+ */
+void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
+			struct tipc_msg *hdr)
+{
+	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
+	u16 acked = msg_bcast_ack(hdr);
+	struct sk_buff_head xmitq;
+
+	/* Ignore bc acks sent by peer before bcast synch point was received */
+	if (msg_bc_ack_invalid(hdr))
+		return;
+
+	__skb_queue_head_init(&xmitq);
+
+	tipc_bcast_lock(net);
+	tipc_link_bc_ack_rcv(l, acked, 0, NULL, &xmitq, NULL);
+	tipc_bcast_unlock(net);
+
+	tipc_bcbase_xmit(net, &xmitq);
+
+	/* Any socket wakeup messages ? */
+	if (!skb_queue_empty(inputq))
+		tipc_sk_rcv(net, inputq);
+}
+
+/* tipc_bcast_synch_rcv -  check and update rcv link with peer's send state
+ *
+ * RCU is locked, no other locks set
+ */
+int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
+			struct tipc_msg *hdr,
+			struct sk_buff_head *retrq, bool *valid)
+{
+	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
+	struct tipc_gap_ack_blks *ga;
+	struct sk_buff_head xmitq;
+	int rc = 0;
+	u16 glen;
+
+	__skb_queue_head_init(&xmitq);
+
+	tipc_bcast_lock(net);
+	if (msg_type(hdr) != STATE_MSG) {
+		tipc_link_bc_init_rcv(l, hdr);
+	} else if (!msg_bc_ack_invalid(hdr)) {
+		glen = tipc_get_gap_ack_blks(&ga, l, hdr, false);
+		if (glen > msg_data_sz(hdr)) {
+			/* Malformed Gap ACK blocks; caller drops the msg */
+			*valid = false;
+		} else {
+			if (!sysctl_tipc_bc_retruni)
+				retrq = &xmitq;
+			rc = tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr),
+						  msg_bc_gap(hdr), ga, &xmitq,
+						  retrq);
+			rc |= tipc_link_bc_sync_rcv(l, hdr, &xmitq);
+		}
+	}
+	tipc_bcast_unlock(net);
+
+	tipc_bcbase_xmit(net, &xmitq);
+
+	/* Any socket wakeup messages ? */
+	if (!skb_queue_empty(inputq))
+		tipc_sk_rcv(net, inputq);
+	return rc;
+}
+
+/* tipc_bcast_add_peer - add a peer node to broadcast link and bearer
+ *
+ * RCU is locked, node lock is set
+ */
+void tipc_bcast_add_peer(struct net *net, struct tipc_link *uc_l,
+			 struct sk_buff_head *xmitq)
+{
+	struct tipc_link *snd_l = tipc_bc_sndlink(net);
+
+	tipc_bcast_lock(net);
+	tipc_link_add_bc_peer(snd_l, uc_l, xmitq);
+	tipc_bcbase_select_primary(net);
+	tipc_bcbase_calc_bc_threshold(net);
+	tipc_bcast_unlock(net);
+}
+
+/* tipc_bcast_remove_peer - remove a peer node from broadcast link and bearer
+ *
+ * RCU is locked, node lock is set
+ */
+void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_l)
+{
+	struct tipc_link *snd_l = tipc_bc_sndlink(net);
+	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
+	struct sk_buff_head xmitq;
+
+	__skb_queue_head_init(&xmitq);
+
+	tipc_bcast_lock(net);
+	tipc_link_remove_bc_peer(snd_l, rcv_l, &xmitq);
+	tipc_bcbase_select_primary(net);
+	tipc_bcbase_calc_bc_threshold(net);
+	tipc_bcast_unlock(net);
+
+	tipc_bcbase_xmit(net, &xmitq);
+
+	/* Any socket wakeup messages ? */
+	if (!skb_queue_empty(inputq))
+		tipc_sk_rcv(net, inputq);
+}
+
+int tipc_bclink_reset_stats(struct net *net, struct tipc_link *l)
+{
+	if (!l)
+		return -ENOPROTOOPT;
+
+	tipc_bcast_lock(net);
+	tipc_link_reset_stats(l);
+	tipc_bcast_unlock(net);
+	return 0;
+}
+
+static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win)
+{
+	struct tipc_link *l = tipc_bc_sndlink(net);
+
+	if (!l)
+		return -ENOPROTOOPT;
+	if (max_win < BCLINK_WIN_MIN)
+		max_win = BCLINK_WIN_MIN;
+	if (max_win > TIPC_MAX_LINK_WIN)
+		return -EINVAL;
+	tipc_bcast_lock(net);
+	tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win);
+	tipc_bcast_unlock(net);
+	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])
+		return -EINVAL;
+
+	err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props);
+	if (err)
+		return err;
+
+	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);
+	}
+
+	if (!err && props[TIPC_NLA_PROP_WIN]) {
+		win = nla_get_u32(props[TIPC_NLA_PROP_WIN]);
+		err = tipc_bc_link_set_queue_limits(net, win);
+	}
+
+	return err;
+}
+
+int tipc_bcast_init(struct net *net)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_bc_base *bb = NULL;
+	struct tipc_link *l = NULL;
+
+	bb = kzalloc_obj(*bb);
+	if (!bb)
+		goto enomem;
+	tn->bcbase = bb;
+	spin_lock_init(&tipc_net(net)->bclock);
+
+	if (!tipc_link_bc_create(net, 0, 0, NULL,
+				 one_page_mtu,
+				 BCLINK_WIN_DEFAULT,
+				 BCLINK_WIN_DEFAULT,
+				 0,
+				 &bb->inputq,
+				 NULL,
+				 NULL,
+				 &l))
+		goto enomem;
+	bb->link = l;
+	tn->bcl = l;
+	bb->rc_ratio = 10;
+	bb->rcast_support = true;
+	return 0;
+enomem:
+	kfree(bb);
+	kfree(l);
+	return -ENOMEM;
+}
+
+void tipc_bcast_stop(struct net *net)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+	synchronize_net();
+	kfree(tn->bcbase);
+	kfree(tn->bcl);
+}
+
+void tipc_nlist_init(struct tipc_nlist *nl, u32 self)
+{
+	memset(nl, 0, sizeof(*nl));
+	INIT_LIST_HEAD(&nl->list);
+	nl->self = self;
+}
+
+void tipc_nlist_add(struct tipc_nlist *nl, u32 node)
+{
+	if (node == nl->self)
+		nl->local = true;
+	else if (tipc_dest_push(&nl->list, node, 0))
+		nl->remote++;
+}
+
+void tipc_nlist_del(struct tipc_nlist *nl, u32 node)
+{
+	if (node == nl->self)
+		nl->local = false;
+	else if (tipc_dest_del(&nl->list, node, 0))
+		nl->remote--;
+}
+
+void tipc_nlist_purge(struct tipc_nlist *nl)
+{
+	tipc_dest_list_purge(&nl->list);
+	nl->remote = 0;
+	nl->local = false;
+}
+
+u32 tipc_bcast_get_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);
+	}
+}

linux-7.2.3/net/tipc/bcast.h

@@ -0,0 +1,127 @@
+/*
+ * net/tipc/bcast.h: Include file for TIPC broadcast code
+ *
+ * Copyright (c) 2003-2006, 2014-2015, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_BCAST_H
+#define _TIPC_BCAST_H
+
+#include "core.h"
+
+struct tipc_node;
+struct tipc_msg;
+struct tipc_nl_msg;
+struct tipc_nlist;
+struct tipc_nitem;
+extern const char tipc_bclink_name[];
+extern unsigned long sysctl_tipc_bc_retruni;
+
+#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;
+	u16 remote;
+	bool local;
+};
+
+void tipc_nlist_init(struct tipc_nlist *nl, u32 self);
+void tipc_nlist_purge(struct tipc_nlist *nl);
+void tipc_nlist_add(struct tipc_nlist *nl, u32 node);
+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;
+};
+
+int tipc_bcast_init(struct net *net);
+void tipc_bcast_stop(struct net *net);
+void tipc_bcast_add_peer(struct net *net, struct tipc_link *l,
+			 struct sk_buff_head *xmitq);
+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_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);
+int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts,
+		    u16 *cong_link_cnt);
+int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb);
+void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
+			struct tipc_msg *hdr);
+int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
+			struct tipc_msg *hdr,
+			struct sk_buff_head *retrq, bool *valid);
+int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg,
+			struct tipc_link *bcl);
+int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]);
+int tipc_bclink_reset_stats(struct net *net, struct tipc_link *l);
+
+u32 tipc_bcast_get_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);
+}
+
+static inline void tipc_bcast_unlock(struct net *net)
+{
+	spin_unlock_bh(&tipc_net(net)->bclock);
+}
+
+static inline struct tipc_link *tipc_bc_sndlink(struct net *net)
+{
+	return tipc_net(net)->bcl;
+}
+
+#endif

linux-7.2.3/net/tipc/bearer.h

@@ -0,0 +1,266 @@
+/*
+ * net/tipc/bearer.h: Include file for TIPC bearer code
+ *
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_BEARER_H
+#define _TIPC_BEARER_H
+
+#include "netlink.h"
+#include "core.h"
+#include "msg.h"
+#include <net/genetlink.h>
+
+#define MAX_MEDIA	3
+
+/* Identifiers associated with TIPC message header media address info
+ * - address info field is 32 bytes long
+ * - the field's actual content and length is defined per media
+ * - remaining unused bytes in the field are set to zero
+ */
+#define TIPC_MEDIA_INFO_SIZE	32
+#define TIPC_MEDIA_TYPE_OFFSET	3
+#define TIPC_MEDIA_ADDR_OFFSET	4
+
+/*
+ * Identifiers of supported TIPC media types
+ */
+#define TIPC_MEDIA_TYPE_ETH	1
+#define TIPC_MEDIA_TYPE_IB	2
+#define TIPC_MEDIA_TYPE_UDP	3
+
+/* Minimum bearer MTU */
+#define TIPC_MIN_BEARER_MTU	(MAX_H_SIZE + INT_H_SIZE)
+
+/* Identifiers for distinguishing between broadcast/multicast and replicast
+ */
+#define TIPC_BROADCAST_SUPPORT  1
+#define TIPC_REPLICAST_SUPPORT  2
+
+/**
+ * struct tipc_media_addr - destination address used by TIPC bearers
+ * @value: address info (format defined by media)
+ * @media_id: TIPC media type identifier
+ * @broadcast: non-zero if address is a broadcast address
+ */
+struct tipc_media_addr {
+	u8 value[TIPC_MEDIA_INFO_SIZE];
+	u8 media_id;
+	u8 broadcast;
+};
+
+struct tipc_bearer;
+
+/**
+ * struct tipc_media - Media specific info exposed to generic bearer layer
+ * @send_msg: routine which handles buffer transmission
+ * @enable_media: routine which enables a media
+ * @disable_media: routine which disables a media
+ * @addr2str: convert media address format to string
+ * @addr2msg: convert from media addr format to discovery msg addr format
+ * @msg2addr: convert from discovery msg addr format to media addr format
+ * @raw2addr: convert from raw addr format to media addr format
+ * @priority: default link (and bearer) priority
+ * @tolerance: default time (in ms) before declaring link failure
+ * @min_win: minimum window (in packets) before declaring link congestion
+ * @max_win: maximum window (in packets) before declaring link congestion
+ * @mtu: max packet size bearer can support for media type not dependent on
+ * underlying device MTU
+ * @type_id: TIPC media identifier
+ * @hwaddr_len: TIPC media address len
+ * @name: media name
+ */
+struct tipc_media {
+	int (*send_msg)(struct net *net, struct sk_buff *buf,
+			struct tipc_bearer *b,
+			struct tipc_media_addr *dest);
+	int (*enable_media)(struct net *net, struct tipc_bearer *b,
+			    struct nlattr *attr[]);
+	void (*disable_media)(struct tipc_bearer *b);
+	int (*addr2str)(struct tipc_media_addr *addr,
+			char *strbuf,
+			int bufsz);
+	int (*addr2msg)(char *msg, struct tipc_media_addr *addr);
+	int (*msg2addr)(struct tipc_bearer *b,
+			struct tipc_media_addr *addr,
+			char *msg);
+	int (*raw2addr)(struct tipc_bearer *b,
+			struct tipc_media_addr *addr,
+			const char *raw);
+	u32 priority;
+	u32 tolerance;
+	u32 min_win;
+	u32 max_win;
+	u32 mtu;
+	u32 type_id;
+	u32 hwaddr_len;
+	char name[TIPC_MAX_MEDIA_NAME];
+};
+
+/**
+ * struct tipc_bearer - Generic TIPC bearer structure
+ * @media_ptr: pointer to additional media-specific information about bearer
+ * @mtu: max packet size bearer can support
+ * @addr: media-specific address associated with bearer
+ * @name: bearer name (format = media:interface)
+ * @media: ptr to media structure associated with bearer
+ * @bcast_addr: media address used in broadcasting
+ * @pt: packet type for bearer
+ * @rcu: rcu struct for tipc_bearer
+ * @priority: default link priority for bearer
+ * @min_win: minimum window (in packets) before declaring link congestion
+ * @max_win: maximum window (in packets) before declaring link congestion
+ * @tolerance: default link tolerance for bearer
+ * @domain: network domain to which links can be established
+ * @identity: array index of this bearer within TIPC bearer array
+ * @disc: ptr to link setup request
+ * @net_plane: network plane ('A' through 'H') currently associated with bearer
+ * @encap_hlen: encap headers length
+ * @up: bearer up flag (bit 0)
+ * @refcnt: tipc_bearer reference counter
+ *
+ * Note: media-specific code is responsible for initialization of the fields
+ * indicated below when a bearer is enabled; TIPC's generic bearer code takes
+ * care of initializing all other fields.
+ */
+struct tipc_bearer {
+	void __rcu *media_ptr;			/* initialized by media */
+	u32 mtu;				/* initialized by media */
+	struct tipc_media_addr addr;		/* initialized by media */
+	char name[TIPC_MAX_BEARER_NAME];
+	struct tipc_media *media;
+	struct tipc_media_addr bcast_addr;
+	struct packet_type pt;
+	struct rcu_head rcu;
+	u32 priority;
+	u32 min_win;
+	u32 max_win;
+	u32 tolerance;
+	u32 domain;
+	u32 identity;
+	struct tipc_discoverer *disc;
+	char net_plane;
+	u16 encap_hlen;
+	unsigned long up;
+	refcount_t refcnt;
+};
+
+struct tipc_bearer_names {
+	char media_name[TIPC_MAX_MEDIA_NAME];
+	char if_name[TIPC_MAX_IF_NAME];
+};
+
+/*
+ * TIPC routines available to supported media types
+ */
+
+void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b);
+
+/*
+ * Routines made available to TIPC by supported media types
+ */
+extern struct tipc_media eth_media_info;
+
+#ifdef CONFIG_TIPC_MEDIA_IB
+extern struct tipc_media ib_media_info;
+#endif
+#ifdef CONFIG_TIPC_MEDIA_UDP
+extern struct tipc_media udp_media_info;
+#endif
+
+int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info);
+int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info);
+int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info);
+int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info);
+
+int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
+int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info);
+
+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);
+
+void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest);
+void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest);
+struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name);
+int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id);
+struct tipc_media *tipc_media_find(const char *name);
+int tipc_bearer_setup(void);
+void tipc_bearer_cleanup(void);
+void tipc_bearer_stop(struct net *net);
+int tipc_bearer_mtu(struct net *net, u32 bearer_id);
+int tipc_bearer_min_mtu(struct net *net, u32 bearer_id);
+bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id);
+void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id,
+			  struct sk_buff *skb,
+			  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_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)
+{
+	if (dev->mtu >= TIPC_MIN_BEARER_MTU)
+		return false;
+	netdev_warn(dev, "MTU too low for tipc bearer\n");
+	return true;
+}
+
+#endif	/* _TIPC_BEARER_H */

linux-7.2.3/net/tipc/core.c

@@ -0,0 +1,234 @@
+/*
+ * net/tipc/core.c: TIPC module code
+ *
+ * Copyright (c) 2003-2006, 2013, Ericsson AB
+ * Copyright (c) 2005-2006, 2010-2013, Wind River Systems
+ * 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 "core.h"
+#include "name_table.h"
+#include "subscr.h"
+#include "bearer.h"
+#include "net.h"
+#include "socket.h"
+#include "bcast.h"
+#include "node.h"
+#include "crypto.h"
+
+#include <linux/module.h>
+#include <linux/wait_bit.h>
+
+/* configurable TIPC parameters */
+unsigned int tipc_net_id __read_mostly;
+int sysctl_tipc_rmem[3] __read_mostly;	/* min/default/max */
+
+static int __net_init tipc_init_net(struct net *net)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	int err;
+
+	tn->net_id = 4711;
+	tn->node_addr = 0;
+	tn->trial_addr = 0;
+	tn->addr_trial_end = 0;
+	tn->capabilities = TIPC_NODE_CAPABILITIES;
+	INIT_WORK(&tn->work, tipc_net_finalize_work);
+	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;
+	get_random_bytes(&tn->random, sizeof(int));
+	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;
+
+	err = tipc_nametbl_init(net);
+	if (err)
+		goto out_nametbl;
+
+	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_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)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	tipc_detach_loopback(net);
+	tipc_net_stop(net);
+	/* Make sure the tipc_net_finalize_work() finished */
+	cancel_work_sync(&tn->work);
+	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
+	wait_var_event(&tn->wq_count, atomic_read(&tn->wq_count) == 0);
+}
+
+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,
+	.id   = &tipc_net_id,
+	.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;
+
+	pr_info("Activated (version " TIPC_MOD_VER ")\n");
+
+	sysctl_tipc_rmem[0] = RCVBUF_MIN;
+	sysctl_tipc_rmem[1] = RCVBUF_DEF;
+	sysctl_tipc_rmem[2] = RCVBUF_MAX;
+
+	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 = register_pernet_device(&tipc_topsrv_net_ops);
+	if (err)
+		goto out_pernet_topsrv;
+
+	err = register_pernet_subsys(&tipc_pernet_pre_exit_ops);
+	if (err)
+		goto out_register_pernet_subsys;
+
+	err = tipc_bearer_setup();
+	if (err)
+		goto out_bearer;
+
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_netlink_compat_start();
+	if (err)
+		goto out_netlink_compat;
+
+	pr_info("Started in single node mode\n");
+	return 0;
+
+out_netlink_compat:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_bearer_cleanup();
+out_bearer:
+	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:
+	pr_err("Unable to start in single node mode\n");
+	return err;
+}
+
+static void __exit tipc_exit(void)
+{
+	tipc_netlink_compat_stop();
+	tipc_netlink_stop();
+	tipc_bearer_cleanup();
+	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_unregister_sysctl();
+
+	/* TODO: Wait for all timers that called call_rcu() to finish before
+	 * calling rcu_barrier().
+	 */
+	rcu_barrier();
+
+	pr_info("Deactivated\n");
+}
+
+module_init(tipc_init);
+module_exit(tipc_exit);
+
+MODULE_DESCRIPTION("TIPC: Transparent Inter Process Communication");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(TIPC_MOD_VER);

linux-7.2.3/net/tipc/core.h

@@ -0,0 +1,228 @@
+/*
+ * net/tipc/core.h: Include file for TIPC global declarations
+ *
+ * Copyright (c) 2005-2006, 2013-2018 Ericsson AB
+ * Copyright (c) 2005-2007, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_CORE_H
+#define _TIPC_CORE_H
+
+#include <linux/tipc.h>
+#include <linux/tipc_config.h>
+#include <linux/tipc_netlink.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/hex.h>
+#include <linux/mm.h>
+#include <linux/timer.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/interrupt.h>
+#include <linux/atomic.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/rtnetlink.h>
+#include <linux/etherdevice.h>
+#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;
+struct tipc_bc_base;
+struct tipc_link;
+struct tipc_topsrv;
+struct tipc_monitor;
+#ifdef CONFIG_TIPC_CRYPTO
+struct tipc_crypto;
+#endif
+
+#define TIPC_MOD_VER "2.0.0"
+
+#define NODE_HTABLE_SIZE       512
+#define MAX_BEARERS	         3
+#define TIPC_DEF_MON_THRESHOLD  32
+#define NODE_ID_LEN             16
+#define NODE_ID_STR_LEN        (NODE_ID_LEN * 2 + 1)
+
+extern unsigned int tipc_net_id __read_mostly;
+extern int sysctl_tipc_rmem[3] __read_mostly;
+extern int sysctl_tipc_named_timeout __read_mostly;
+
+struct tipc_net {
+	u8  node_id[NODE_ID_LEN];
+	u32 node_addr;
+	u32 trial_addr;
+	unsigned long addr_trial_end;
+	char node_id_string[NODE_ID_STR_LEN];
+	int net_id;
+	int random;
+	bool legacy_addr_format;
+
+	/* Node table and node list */
+	spinlock_t node_list_lock;
+	struct hlist_head node_htable[NODE_HTABLE_SIZE];
+	struct list_head node_list;
+	u32 num_nodes;
+	u32 num_links;
+
+	/* Neighbor monitoring list */
+	struct tipc_monitor *monitors[MAX_BEARERS];
+	int mon_threshold;
+
+	/* Bearer list */
+	struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
+
+	/* Broadcast link */
+	spinlock_t bclock;
+	struct tipc_bc_base *bcbase;
+	struct tipc_link *bcl;
+
+	/* Socket hash table */
+	struct rhashtable sk_rht;
+
+	/* Name table */
+	spinlock_t nametbl_lock;
+	struct name_table *nametbl;
+
+	/* 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
+	/* Work item for net finalize */
+	struct work_struct work;
+	/* The numbers of work queues in schedule */
+	atomic_t wq_count;
+};
+
+static inline struct tipc_net *tipc_net(struct net *net)
+{
+	return net_generic(net, tipc_net_id);
+}
+
+static inline int tipc_netid(struct net *net)
+{
+	return tipc_net(net)->net_id;
+}
+
+static inline struct list_head *tipc_nodes(struct net *net)
+{
+	return &tipc_net(net)->node_list;
+}
+
+static inline struct name_table *tipc_name_table(struct net *net)
+{
+	return tipc_net(net)->nametbl;
+}
+
+static inline struct tipc_topsrv *tipc_topsrv(struct net *net)
+{
+	return tipc_net(net)->topsrv;
+}
+
+static inline unsigned int tipc_hashfn(u32 addr)
+{
+	return addr & (NODE_HTABLE_SIZE - 1);
+}
+
+static inline u16 mod(u16 x)
+{
+	return x & 0xffffu;
+}
+
+static inline int less_eq(u16 left, u16 right)
+{
+	return mod(right - left) < 32768u;
+}
+
+static inline int more(u16 left, u16 right)
+{
+	return !less_eq(left, right);
+}
+
+static inline int less(u16 left, u16 right)
+{
+	return less_eq(left, right) && (mod(right) != mod(left));
+}
+
+static inline int tipc_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;
+}
+
+static inline u32 hash128to32(char *bytes)
+{
+	__be32 *tmp = (__be32 *)bytes;
+	u32 res;
+
+	res = ntohl(tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3]);
+	if (likely(res))
+		return res;
+	return  ntohl(tmp[0] | tmp[1] | tmp[2] | tmp[3]);
+}
+
+#ifdef CONFIG_SYSCTL
+int tipc_register_sysctl(void);
+void tipc_unregister_sysctl(void);
+#else
+#define tipc_register_sysctl() 0
+#define tipc_unregister_sysctl()
+#endif
+#endif

linux-7.2.3/net/tipc/crypto.h

@@ -0,0 +1,200 @@
+/* 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;
+extern int sysctl_tipc_key_exchange_enabled __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|M|N|             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)
+ *	M       : Bit indicates if sender has master key
+ *	N	: Bit indicates if sender has no RX keys corresponding to the
+ *	          receiver's TX (when the "D" bit is set)
+ *	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_1:1,
+				rx_nokey:1,
+				master_key:1,
+				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,
+				master_key:1,
+				rx_nokey:1,
+				reserved_1:1;
+#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, bool master_key);
+void tipc_crypto_key_flush(struct tipc_crypto *c);
+int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key,
+			  struct tipc_node *dest);
+void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb);
+void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed,
+				u32 new_intv);
+int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info);
+bool tipc_ehdr_validate(struct sk_buff *skb);
+
+static inline u32 msg_key_gen(struct tipc_msg *m)
+{
+	return msg_bits(m, 4, 16, 0xffff);
+}
+
+static inline void msg_set_key_gen(struct tipc_msg *m, u32 gen)
+{
+	msg_set_bits(m, 4, 16, 0xffff, gen);
+}
+
+static inline u32 msg_key_mode(struct tipc_msg *m)
+{
+	return msg_bits(m, 4, 0, 0xf);
+}
+
+static inline void msg_set_key_mode(struct tipc_msg *m, u32 mode)
+{
+	msg_set_bits(m, 4, 0, 0xf, mode);
+}
+
+#endif /* _TIPC_CRYPTO_H */
+#endif

linux-7.2.3/net/tipc/diag.c

@@ -0,0 +1,118 @@
+/*
+ * net/tipc/diag.c: TIPC socket diag
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "core.h"
+#include "socket.h"
+#include <linux/sock_diag.h>
+#include <linux/tipc_sockets_diag.h>
+
+static u64 __tipc_diag_gen_cookie(struct sock *sk)
+{
+	u32 res[2];
+
+	sock_diag_save_cookie(sk, res);
+	return *((u64 *)res);
+}
+
+static int __tipc_add_sock_diag(struct sk_buff *skb,
+				struct netlink_callback *cb,
+				struct tipc_sock *tsk)
+{
+	struct tipc_sock_diag_req *req = nlmsg_data(cb->nlh);
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = nlmsg_put_answer(skb, cb, SOCK_DIAG_BY_FAMILY, 0,
+			       NLM_F_MULTI);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	err = tipc_sk_fill_sock_diag(skb, cb, tsk, req->tidiag_states,
+				     __tipc_diag_gen_cookie);
+	if (err)
+		return err;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+}
+
+static int tipc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return tipc_nl_sk_walk(skb, cb, __tipc_add_sock_diag);
+}
+
+static int tipc_sock_diag_handler_dump(struct sk_buff *skb,
+				       struct nlmsghdr *h)
+{
+	int hdrlen = sizeof(struct tipc_sock_diag_req);
+	struct net *net = sock_net(skb->sk);
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.start = tipc_dump_start,
+			.dump = tipc_diag_dump,
+			.done = tipc_dump_done,
+		};
+		netlink_dump_start(net->diag_nlsk, skb, h, &c);
+		return 0;
+	}
+	return -EOPNOTSUPP;
+}
+
+static const struct sock_diag_handler tipc_sock_diag_handler = {
+	.owner = THIS_MODULE,
+	.family = AF_TIPC,
+	.dump = tipc_sock_diag_handler_dump,
+};
+
+static int __init tipc_diag_init(void)
+{
+	return sock_diag_register(&tipc_sock_diag_handler);
+}
+
+static void __exit tipc_diag_exit(void)
+{
+	sock_diag_unregister(&tipc_sock_diag_handler);
+}
+
+module_init(tipc_diag_init);
+module_exit(tipc_diag_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("TIPC socket monitoring via SOCK_DIAG");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_TIPC);

linux-7.2.3/net/tipc/discover.c

@@ -0,0 +1,430 @@
+/*
+ * net/tipc/discover.c
+ *
+ * Copyright (c) 2003-2006, 2014-2018, Ericsson AB
+ * Copyright (c) 2005-2006, 2010-2011, Wind River Systems
+ * 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 "core.h"
+#include "node.h"
+#include "discover.h"
+
+/* min delay during bearer start up */
+#define TIPC_DISC_INIT	msecs_to_jiffies(125)
+/* max delay if bearer has no links */
+#define TIPC_DISC_FAST	msecs_to_jiffies(1000)
+/* max delay if bearer has links */
+#define TIPC_DISC_SLOW	msecs_to_jiffies(60000)
+/* indicates no timer in use */
+#define TIPC_DISC_INACTIVE	0xffffffff
+
+/**
+ * struct tipc_discoverer - information about an ongoing link setup request
+ * @bearer_id: identity of bearer issuing requests
+ * @net: network namespace instance
+ * @dest: destination address for request messages
+ * @domain: network domain to which links can be established
+ * @num_nodes: number of nodes currently discovered (i.e. with an active link)
+ * @lock: spinlock for controlling access to requests
+ * @skb: request message to be (repeatedly) sent
+ * @timer: timer governing period between requests
+ * @timer_intv: current interval between requests (in ms)
+ * @rcu: RCU head for deferred freeing
+ */
+struct tipc_discoverer {
+	u32 bearer_id;
+	struct tipc_media_addr dest;
+	struct net *net;
+	u32 domain;
+	int num_nodes;
+	spinlock_t lock;
+	struct sk_buff *skb;
+	struct timer_list timer;
+	unsigned long timer_intv;
+	struct rcu_head rcu;
+};
+
+/**
+ * tipc_disc_init_msg - initialize a link setup message
+ * @net: the applicable net namespace
+ * @skb: buffer containing message
+ * @mtyp: message type (request or response)
+ * @b: ptr to bearer issuing message
+ */
+static void tipc_disc_init_msg(struct net *net, struct sk_buff *skb,
+			       u32 mtyp,  struct tipc_bearer *b)
+{
+	struct tipc_net *tn = tipc_net(net);
+	u32 dest_domain = b->domain;
+	struct tipc_msg *hdr;
+
+	hdr = buf_msg(skb);
+	tipc_msg_init(tn->trial_addr, hdr, LINK_CONFIG, mtyp,
+		      MAX_H_SIZE, dest_domain);
+	msg_set_size(hdr, MAX_H_SIZE + NODE_ID_LEN);
+	msg_set_non_seq(hdr, 1);
+	msg_set_node_sig(hdr, tn->random);
+	msg_set_node_capabilities(hdr, TIPC_NODE_CAPABILITIES);
+	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));
+}
+
+static void tipc_disc_msg_xmit(struct net *net, u32 mtyp, u32 dst,
+			       u32 src, u32 sugg_addr,
+			       struct tipc_media_addr *maddr,
+			       struct tipc_bearer *b)
+{
+	struct tipc_msg *hdr;
+	struct sk_buff *skb;
+
+	skb = tipc_buf_acquire(MAX_H_SIZE + NODE_ID_LEN, GFP_ATOMIC);
+	if (!skb)
+		return;
+	hdr = buf_msg(skb);
+	tipc_disc_init_msg(net, skb, mtyp, b);
+	msg_set_sugg_node_addr(hdr, sugg_addr);
+	msg_set_dest_domain(hdr, dst);
+	tipc_bearer_xmit_skb(net, b->identity, skb, maddr);
+}
+
+/**
+ * disc_dupl_alert - issue node address duplication alert
+ * @b: pointer to bearer detecting duplication
+ * @node_addr: duplicated node address
+ * @media_addr: media address advertised by duplicated node
+ */
+static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr,
+			    struct tipc_media_addr *media_addr)
+{
+	char media_addr_str[64];
+
+	tipc_media_addr_printf(media_addr_str, sizeof(media_addr_str),
+			       media_addr);
+	pr_warn("Duplicate %x using %s seen on <%s>\n", node_addr,
+		media_addr_str, b->name);
+}
+
+/* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer
+ * Returns true if message should be dropped by caller, i.e., if it is a
+ * trial message or we are inside trial period. Otherwise false.
+ */
+static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
+				     struct tipc_media_addr *maddr,
+				     struct tipc_bearer *b,
+				     u32 dst, u32 src,
+				     u32 sugg_addr,
+				     u8 *peer_id,
+				     int mtyp)
+{
+	struct net *net = d->net;
+	struct tipc_net *tn = tipc_net(net);
+	u32 self = tipc_own_addr(net);
+	bool trial = time_before(jiffies, tn->addr_trial_end) && !self;
+
+	if (mtyp == DSC_TRIAL_FAIL_MSG) {
+		if (!trial)
+			return true;
+
+		/* Ignore if somebody else already gave new suggestion */
+		if (dst != tn->trial_addr)
+			return true;
+
+		/* Otherwise update trial address and restart trial period */
+		tn->trial_addr = sugg_addr;
+		msg_set_prevnode(buf_msg(d->skb), sugg_addr);
+		tn->addr_trial_end = jiffies + msecs_to_jiffies(1000);
+		return true;
+	}
+
+	/* Apply trial address if we just left trial period */
+	if (!trial && !self) {
+		schedule_work(&tn->work);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+	}
+
+	/* Accept regular link requests/responses only after trial period */
+	if (mtyp != DSC_TRIAL_MSG)
+		return trial;
+
+	sugg_addr = tipc_node_try_addr(net, peer_id, src);
+	if (sugg_addr)
+		tipc_disc_msg_xmit(net, DSC_TRIAL_FAIL_MSG, src,
+				   self, sugg_addr, maddr, b);
+	return true;
+}
+
+/**
+ * tipc_disc_rcv - handle incoming discovery message (request or response)
+ * @net: applicable net namespace
+ * @skb: buffer containing message
+ * @b: bearer that message arrived on
+ */
+void tipc_disc_rcv(struct net *net, struct sk_buff *skb,
+		   struct tipc_bearer *b)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_msg *hdr = buf_msg(skb);
+	u32 pnet_hash = msg_peer_net_hash(hdr);
+	u16 caps = msg_node_capabilities(hdr);
+	bool legacy = tn->legacy_addr_format;
+	u32 sugg = msg_sugg_node_addr(hdr);
+	u32 signature = msg_node_sig(hdr);
+	u8 peer_id[NODE_ID_LEN] = {0,};
+	u32 dst = msg_dest_domain(hdr);
+	u32 net_id = msg_bc_netid(hdr);
+	struct tipc_media_addr maddr;
+	u32 src = msg_prevnode(hdr);
+	u32 mtyp = msg_type(hdr);
+	bool dupl_addr = false;
+	bool respond = false;
+	u32 self;
+	int err;
+
+	if (skb_linearize(skb)) {
+		kfree_skb(skb);
+		return;
+	}
+	hdr = buf_msg(skb);
+
+	if (caps & TIPC_NODE_ID128)
+		memcpy(peer_id, msg_node_id(hdr), NODE_ID_LEN);
+	else
+		sprintf(peer_id, "%x", src);
+
+	err = b->media->msg2addr(b, &maddr, msg_media_addr(hdr));
+	kfree_skb(skb);
+	if (err || maddr.broadcast) {
+		pr_warn_ratelimited("Rcv corrupt discovery message\n");
+		return;
+	}
+	/* Ignore discovery messages from own node */
+	if (!memcmp(&maddr, &b->addr, sizeof(maddr)))
+		return;
+	if (net_id != tn->net_id)
+		return;
+	if (tipc_disc_addr_trial_msg(b->disc, &maddr, b, dst,
+				     src, sugg, peer_id, mtyp))
+		return;
+	self = tipc_own_addr(net);
+
+	/* Message from somebody using this node's address */
+	if (in_own_node(net, src)) {
+		disc_dupl_alert(b, self, &maddr);
+		return;
+	}
+	if (!tipc_in_scope(legacy, dst, self))
+		return;
+	if (!tipc_in_scope(legacy, b->domain, src))
+		return;
+	tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash,
+			     &maddr, &respond, &dupl_addr);
+	if (dupl_addr)
+		disc_dupl_alert(b, src, &maddr);
+	if (!respond)
+		return;
+	if (mtyp != DSC_REQ_MSG)
+		return;
+	tipc_disc_msg_xmit(net, DSC_RESP_MSG, src, self, 0, &maddr, b);
+}
+
+/* tipc_disc_add_dest - increment set of discovered nodes
+ */
+void tipc_disc_add_dest(struct tipc_discoverer *d)
+{
+	spin_lock_bh(&d->lock);
+	d->num_nodes++;
+	spin_unlock_bh(&d->lock);
+}
+
+/* tipc_disc_remove_dest - decrement set of discovered nodes
+ */
+void tipc_disc_remove_dest(struct tipc_discoverer *d)
+{
+	int intv, num;
+
+	spin_lock_bh(&d->lock);
+	d->num_nodes--;
+	num = d->num_nodes;
+	intv = d->timer_intv;
+	if (!num && (intv == TIPC_DISC_INACTIVE || intv > TIPC_DISC_FAST))  {
+		d->timer_intv = TIPC_DISC_INIT;
+		mod_timer(&d->timer, jiffies + d->timer_intv);
+	}
+	spin_unlock_bh(&d->lock);
+}
+
+/* tipc_disc_timeout - send a periodic link setup request
+ * Called whenever a link setup request timer associated with a bearer expires.
+ * - Keep doubling time between sent request until limit is reached;
+ * - Hold at fast polling rate if we don't have any associated nodes
+ * - Otherwise hold at slow polling rate
+ */
+static void tipc_disc_timeout(struct timer_list *t)
+{
+	struct tipc_discoverer *d = timer_container_of(d, t, timer);
+	struct tipc_net *tn = tipc_net(d->net);
+	struct tipc_media_addr maddr;
+	struct sk_buff *skb = NULL;
+	struct net *net = d->net;
+	u32 bearer_id;
+
+	spin_lock_bh(&d->lock);
+
+	/* Stop searching if only desired node has been found */
+	if (tipc_node(d->domain) && d->num_nodes) {
+		d->timer_intv = TIPC_DISC_INACTIVE;
+		goto exit;
+	}
+
+	/* Did we just leave trial period ? */
+	if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
+		mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
+		spin_unlock_bh(&d->lock);
+		schedule_work(&tn->work);
+		return;
+	}
+
+	/* Adjust timeout interval according to discovery phase */
+	if (time_before(jiffies, tn->addr_trial_end)) {
+		d->timer_intv = TIPC_DISC_INIT;
+	} else {
+		d->timer_intv *= 2;
+		if (d->num_nodes && d->timer_intv > TIPC_DISC_SLOW)
+			d->timer_intv = TIPC_DISC_SLOW;
+		else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST)
+			d->timer_intv = TIPC_DISC_FAST;
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
+	}
+
+	mod_timer(&d->timer, jiffies + d->timer_intv);
+	memcpy(&maddr, &d->dest, sizeof(maddr));
+	skb = skb_clone(d->skb, GFP_ATOMIC);
+	bearer_id = d->bearer_id;
+exit:
+	spin_unlock_bh(&d->lock);
+	if (skb)
+		tipc_bearer_xmit_skb(net, bearer_id, skb, &maddr);
+}
+
+/**
+ * tipc_disc_create - create object to send periodic link setup requests
+ * @net: the applicable net namespace
+ * @b: ptr to bearer issuing requests
+ * @dest: destination address for request messages
+ * @skb: pointer to created frame
+ *
+ * Return: 0 if successful, otherwise -errno.
+ */
+int tipc_disc_create(struct net *net, struct tipc_bearer *b,
+		     struct tipc_media_addr *dest, struct sk_buff **skb)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_discoverer *d;
+
+	d = kmalloc_obj(*d, GFP_ATOMIC);
+	if (!d)
+		return -ENOMEM;
+	d->skb = tipc_buf_acquire(MAX_H_SIZE + NODE_ID_LEN, GFP_ATOMIC);
+	if (!d->skb) {
+		kfree(d);
+		return -ENOMEM;
+	}
+	tipc_disc_init_msg(net, d->skb, DSC_REQ_MSG, b);
+
+	/* Do we need an address trial period first ? */
+	if (!tipc_own_addr(net)) {
+		tn->addr_trial_end = jiffies + msecs_to_jiffies(1000);
+		msg_set_type(buf_msg(d->skb), DSC_TRIAL_MSG);
+	}
+	memcpy(&d->dest, dest, sizeof(*dest));
+	d->net = net;
+	d->bearer_id = b->identity;
+	d->domain = b->domain;
+	d->num_nodes = 0;
+	d->timer_intv = TIPC_DISC_INIT;
+	spin_lock_init(&d->lock);
+	timer_setup(&d->timer, tipc_disc_timeout, 0);
+	mod_timer(&d->timer, jiffies + d->timer_intv);
+	b->disc = d;
+	*skb = skb_clone(d->skb, GFP_ATOMIC);
+	return 0;
+}
+
+static void tipc_disc_free_rcu(struct rcu_head *rp)
+{
+	struct tipc_discoverer *d = container_of(rp, struct tipc_discoverer,
+						 rcu);
+
+	kfree_skb(d->skb);
+	kfree(d);
+}
+
+/**
+ * tipc_disc_delete - destroy object sending periodic link setup requests
+ * @d: ptr to link dest structure
+ */
+void tipc_disc_delete(struct tipc_discoverer *d)
+{
+	timer_shutdown_sync(&d->timer);
+	call_rcu(&d->rcu, tipc_disc_free_rcu);
+}
+
+/**
+ * tipc_disc_reset - reset object to send periodic link setup requests
+ * @net: the applicable net namespace
+ * @b: ptr to bearer issuing requests
+ */
+void tipc_disc_reset(struct net *net, struct tipc_bearer *b)
+{
+	struct tipc_discoverer *d = b->disc;
+	struct tipc_media_addr maddr;
+	struct sk_buff *skb;
+
+	spin_lock_bh(&d->lock);
+	tipc_disc_init_msg(net, d->skb, DSC_REQ_MSG, b);
+	d->net = net;
+	d->bearer_id = b->identity;
+	d->domain = b->domain;
+	d->num_nodes = 0;
+	d->timer_intv = TIPC_DISC_INIT;
+	memcpy(&maddr, &d->dest, sizeof(maddr));
+	mod_timer(&d->timer, jiffies + d->timer_intv);
+	skb = skb_clone(d->skb, GFP_ATOMIC);
+	spin_unlock_bh(&d->lock);
+	if (skb)
+		tipc_bearer_xmit_skb(net, b->identity, skb, &maddr);
+}

linux-7.2.3/net/tipc/discover.h

@@ -0,0 +1,51 @@
+/*
+ * net/tipc/discover.h
+ *
+ * Copyright (c) 2003-2006, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_DISCOVER_H
+#define _TIPC_DISCOVER_H
+
+struct tipc_discoverer;
+
+int tipc_disc_create(struct net *net, struct tipc_bearer *b_ptr,
+		     struct tipc_media_addr *dest, struct sk_buff **skb);
+void tipc_disc_delete(struct tipc_discoverer *req);
+void tipc_disc_reset(struct net *net, struct tipc_bearer *b_ptr);
+void tipc_disc_add_dest(struct tipc_discoverer *req);
+void tipc_disc_remove_dest(struct tipc_discoverer *req);
+void tipc_disc_rcv(struct net *net, struct sk_buff *buf,
+		   struct tipc_bearer *b_ptr);
+
+#endif

linux-7.2.3/net/tipc/eth_media.c

@@ -0,0 +1,98 @@
+/*
+ * net/tipc/eth_media.c: Ethernet bearer support for TIPC
+ *
+ * Copyright (c) 2001-2007, 2013-2014, Ericsson AB
+ * Copyright (c) 2005-2008, 2011-2013, Wind River Systems
+ * 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 "core.h"
+#include "bearer.h"
+
+/* Convert Ethernet address (media address format) to string */
+static int tipc_eth_addr2str(struct tipc_media_addr *addr,
+			     char *strbuf, int bufsz)
+{
+	if (bufsz < 18)	/* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */
+		return 1;
+
+	sprintf(strbuf, "%pM", addr->value);
+	return 0;
+}
+
+/* Convert from media address format to discovery message addr format */
+static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr)
+{
+	memset(msg, 0, TIPC_MEDIA_INFO_SIZE);
+	msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
+	memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, addr->value, ETH_ALEN);
+	return 0;
+}
+
+/* Convert raw mac address format to media addr format */
+static int tipc_eth_raw2addr(struct tipc_bearer *b,
+			     struct tipc_media_addr *addr,
+			     const char *msg)
+{
+	memset(addr, 0, sizeof(*addr));
+	ether_addr_copy(addr->value, msg);
+	addr->media_id = TIPC_MEDIA_TYPE_ETH;
+	addr->broadcast = is_broadcast_ether_addr(addr->value);
+	return 0;
+}
+
+/* Convert discovery msg addr format to Ethernet media addr format */
+static int tipc_eth_msg2addr(struct tipc_bearer *b,
+			     struct tipc_media_addr *addr,
+			     char *msg)
+{
+	/* Skip past preamble: */
+	msg += TIPC_MEDIA_ADDR_OFFSET;
+	return tipc_eth_raw2addr(b, addr, msg);
+}
+
+/* Ethernet media registration info */
+struct tipc_media eth_media_info = {
+	.send_msg	= tipc_l2_send_msg,
+	.enable_media	= tipc_enable_l2_media,
+	.disable_media	= tipc_disable_l2_media,
+	.addr2str	= tipc_eth_addr2str,
+	.addr2msg	= tipc_eth_addr2msg,
+	.msg2addr	= tipc_eth_msg2addr,
+	.raw2addr	= tipc_eth_raw2addr,
+	.priority	= TIPC_DEF_LINK_PRI,
+	.tolerance	= TIPC_DEF_LINK_TOL,
+	.min_win	= TIPC_DEF_LINK_WIN,
+	.max_win	= TIPC_MAX_LINK_WIN,
+	.type_id	= TIPC_MEDIA_TYPE_ETH,
+	.hwaddr_len	= ETH_ALEN,
+	.name		= "eth"
+};

linux-7.2.3/net/tipc/group.c

@@ -0,0 +1,963 @@
+/*
+ * net/tipc/group.c: TIPC group messaging code
+ *
+ * Copyright (c) 2017, Ericsson AB
+ * Copyright (c) 2020, Red Hat Inc
+ * 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 "core.h"
+#include "addr.h"
+#include "group.h"
+#include "bcast.h"
+#include "topsrv.h"
+#include "msg.h"
+#include "socket.h"
+#include "node.h"
+#include "name_table.h"
+#include "subscr.h"
+
+#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1)
+#define ADV_IDLE ADV_UNIT
+#define ADV_ACTIVE (ADV_UNIT * 12)
+
+enum mbr_state {
+	MBR_JOINING,
+	MBR_PUBLISHED,
+	MBR_JOINED,
+	MBR_PENDING,
+	MBR_ACTIVE,
+	MBR_RECLAIMING,
+	MBR_REMITTED,
+	MBR_LEAVING
+};
+
+struct tipc_member {
+	struct rb_node tree_node;
+	struct list_head list;
+	struct list_head small_win;
+	struct sk_buff_head deferredq;
+	struct tipc_group *group;
+	u32 node;
+	u32 port;
+	u32 instance;
+	enum mbr_state state;
+	u16 advertised;
+	u16 window;
+	u16 bc_rcv_nxt;
+	u16 bc_syncpt;
+	u16 bc_acked;
+};
+
+struct tipc_group {
+	struct rb_root members;
+	struct list_head small_win;
+	struct list_head pending;
+	struct list_head active;
+	struct tipc_nlist dests;
+	struct net *net;
+	int subid;
+	u32 type;
+	u32 instance;
+	u32 scope;
+	u32 portid;
+	u16 member_cnt;
+	u16 active_cnt;
+	u16 max_active;
+	u16 bc_snd_nxt;
+	u16 bc_ackers;
+	bool *open;
+	bool loopback;
+	bool events;
+};
+
+static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
+				  int mtyp, struct sk_buff_head *xmitq);
+
+static void tipc_group_open(struct tipc_member *m, bool *wakeup)
+{
+	*wakeup = false;
+	if (list_empty(&m->small_win))
+		return;
+	list_del_init(&m->small_win);
+	*m->group->open = true;
+	*wakeup = true;
+}
+
+static void tipc_group_decr_active(struct tipc_group *grp,
+				   struct tipc_member *m)
+{
+	if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING ||
+	    m->state == MBR_REMITTED)
+		grp->active_cnt--;
+}
+
+static int tipc_group_rcvbuf_limit(struct tipc_group *grp)
+{
+	int max_active, active_pool, idle_pool;
+	int mcnt = grp->member_cnt + 1;
+
+	/* Limit simultaneous reception from other members */
+	max_active = min(mcnt / 8, 64);
+	max_active = max(max_active, 16);
+	grp->max_active = max_active;
+
+	/* Reserve blocks for active and idle members */
+	active_pool = max_active * ADV_ACTIVE;
+	idle_pool = (mcnt - max_active) * ADV_IDLE;
+
+	/* Scale to bytes, considering worst-case truesize/msgsize ratio */
+	return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4;
+}
+
+u16 tipc_group_bc_snd_nxt(struct tipc_group *grp)
+{
+	return grp->bc_snd_nxt;
+}
+
+static bool tipc_group_is_receiver(struct tipc_member *m)
+{
+	return m && m->state != MBR_JOINING && m->state != MBR_LEAVING;
+}
+
+static bool tipc_group_is_sender(struct tipc_member *m)
+{
+	return m && m->state != MBR_JOINING && m->state != MBR_PUBLISHED;
+}
+
+u32 tipc_group_exclude(struct tipc_group *grp)
+{
+	if (!grp->loopback)
+		return grp->portid;
+	return 0;
+}
+
+struct tipc_group *tipc_group_create(struct net *net, u32 portid,
+				     struct tipc_group_req *mreq,
+				     bool *group_is_open)
+{
+	u32 filter = TIPC_SUB_PORTS | TIPC_SUB_NO_STATUS;
+	bool global = mreq->scope != TIPC_NODE_SCOPE;
+	struct tipc_group *grp;
+	u32 type = mreq->type;
+
+	grp = kzalloc_obj(*grp, GFP_ATOMIC);
+	if (!grp)
+		return NULL;
+	tipc_nlist_init(&grp->dests, tipc_own_addr(net));
+	INIT_LIST_HEAD(&grp->small_win);
+	INIT_LIST_HEAD(&grp->active);
+	INIT_LIST_HEAD(&grp->pending);
+	grp->members = RB_ROOT;
+	grp->net = net;
+	grp->portid = portid;
+	grp->type = type;
+	grp->instance = mreq->instance;
+	grp->scope = mreq->scope;
+	grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK;
+	grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS;
+	grp->open = group_is_open;
+	*grp->open = false;
+	filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE;
+	if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0,
+				    filter, &grp->subid))
+		return grp;
+	kfree(grp);
+	return NULL;
+}
+
+void tipc_group_join(struct net *net, struct tipc_group *grp, int *sk_rcvbuf)
+{
+	struct rb_root *tree = &grp->members;
+	struct tipc_member *m, *tmp;
+	struct sk_buff_head 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);
+	}
+	tipc_node_distr_xmit(net, &xmitq);
+	*sk_rcvbuf = tipc_group_rcvbuf_limit(grp);
+}
+
+void tipc_group_delete(struct net *net, struct tipc_group *grp)
+{
+	struct rb_root *tree = &grp->members;
+	struct tipc_member *m, *tmp;
+	struct sk_buff_head xmitq;
+
+	__skb_queue_head_init(&xmitq);
+
+	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);
+	}
+	tipc_node_distr_xmit(net, &xmitq);
+	tipc_nlist_purge(&grp->dests);
+	tipc_topsrv_kern_unsubscr(net, grp->subid);
+	kfree(grp);
+}
+
+static struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
+						  u32 node, u32 port)
+{
+	struct rb_node *n = grp->members.rb_node;
+	u64 nkey, key = (u64)node << 32 | port;
+	struct tipc_member *m;
+
+	while (n) {
+		m = container_of(n, struct tipc_member, tree_node);
+		nkey = (u64)m->node << 32 | m->port;
+		if (key < nkey)
+			n = n->rb_left;
+		else if (key > nkey)
+			n = n->rb_right;
+		else
+			return m;
+	}
+	return NULL;
+}
+
+static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp,
+						u32 node, u32 port)
+{
+	struct tipc_member *m;
+
+	m = tipc_group_find_member(grp, node, port);
+	if (m && tipc_group_is_receiver(m))
+		return m;
+	return NULL;
+}
+
+static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
+						u32 node)
+{
+	struct tipc_member *m;
+	struct rb_node *n;
+
+	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
+		m = container_of(n, struct tipc_member, tree_node);
+		if (m->node == node)
+			return m;
+	}
+	return NULL;
+}
+
+static int tipc_group_add_to_tree(struct tipc_group *grp,
+				  struct tipc_member *m)
+{
+	u64 nkey, key = (u64)m->node << 32 | m->port;
+	struct rb_node **n, *parent = NULL;
+	struct tipc_member *tmp;
+
+	n = &grp->members.rb_node;
+	while (*n) {
+		tmp = container_of(*n, struct tipc_member, tree_node);
+		parent = *n;
+		tmp = container_of(parent, struct tipc_member, tree_node);
+		nkey = (u64)tmp->node << 32 | tmp->port;
+		if (key < nkey)
+			n = &(*n)->rb_left;
+		else if (key > nkey)
+			n = &(*n)->rb_right;
+		else
+			return -EEXIST;
+	}
+	rb_link_node(&m->tree_node, parent, n);
+	rb_insert_color(&m->tree_node, &grp->members);
+	return 0;
+}
+
+static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
+						    u32 node, u32 port,
+						    u32 instance, int state)
+{
+	struct tipc_member *m;
+	int ret;
+
+	m = kzalloc_obj(*m, GFP_ATOMIC);
+	if (!m)
+		return NULL;
+	INIT_LIST_HEAD(&m->list);
+	INIT_LIST_HEAD(&m->small_win);
+	__skb_queue_head_init(&m->deferredq);
+	m->group = grp;
+	m->node = node;
+	m->port = port;
+	m->instance = instance;
+	m->bc_acked = grp->bc_snd_nxt - 1;
+	ret = tipc_group_add_to_tree(grp, m);
+	if (ret < 0) {
+		kfree(m);
+		return NULL;
+	}
+	grp->member_cnt++;
+	tipc_nlist_add(&grp->dests, m->node);
+	m->state = state;
+	return m;
+}
+
+void tipc_group_add_member(struct tipc_group *grp, u32 node,
+			   u32 port, u32 instance)
+{
+	tipc_group_create_member(grp, node, port, instance, MBR_PUBLISHED);
+}
+
+static void tipc_group_delete_member(struct tipc_group *grp,
+				     struct tipc_member *m)
+{
+	rb_erase(&m->tree_node, &grp->members);
+	grp->member_cnt--;
+
+	/* Check if we were waiting for replicast ack from this member */
+	if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1))
+		grp->bc_ackers--;
+
+	list_del_init(&m->list);
+	list_del_init(&m->small_win);
+	tipc_group_decr_active(grp, m);
+
+	/* If last member on a node, remove node from dest list */
+	if (!tipc_group_find_node(grp, m->node))
+		tipc_nlist_del(&grp->dests, m->node);
+
+	kfree(m);
+}
+
+struct tipc_nlist *tipc_group_dests(struct tipc_group *grp)
+{
+	return &grp->dests;
+}
+
+void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq,
+		     int *scope)
+{
+	seq->type = grp->type;
+	seq->lower = grp->instance;
+	seq->upper = grp->instance;
+	*scope = grp->scope;
+}
+
+void tipc_group_update_member(struct tipc_member *m, int len)
+{
+	struct tipc_group *grp = m->group;
+	struct tipc_member *_m, *tmp;
+
+	if (!tipc_group_is_receiver(m))
+		return;
+
+	m->window -= len;
+
+	if (m->window >= ADV_IDLE)
+		return;
+
+	list_del_init(&m->small_win);
+
+	/* Sort member into small_window members' list */
+	list_for_each_entry_safe(_m, tmp, &grp->small_win, small_win) {
+		if (_m->window > m->window)
+			break;
+	}
+	list_add_tail(&m->small_win, &_m->small_win);
+}
+
+void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack)
+{
+	u16 prev = grp->bc_snd_nxt - 1;
+	struct tipc_member *m;
+	struct rb_node *n;
+	u16 ackers = 0;
+
+	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
+		m = container_of(n, struct tipc_member, tree_node);
+		if (tipc_group_is_receiver(m)) {
+			tipc_group_update_member(m, len);
+			m->bc_acked = prev;
+			ackers++;
+		}
+	}
+
+	/* Mark number of acknowledges to expect, if any */
+	if (ack)
+		grp->bc_ackers = ackers;
+	grp->bc_snd_nxt++;
+}
+
+bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
+		     int len, struct tipc_member **mbr)
+{
+	struct sk_buff_head xmitq;
+	struct tipc_member *m;
+	int adv, state;
+
+	m = tipc_group_find_dest(grp, dnode, dport);
+	if (!tipc_group_is_receiver(m)) {
+		*mbr = NULL;
+		return false;
+	}
+	*mbr = m;
+
+	if (m->window >= len)
+		return false;
+
+	*grp->open = false;
+
+	/* If not fully advertised, do it now to prevent mutual blocking */
+	adv = m->advertised;
+	state = m->state;
+	if (state == MBR_JOINED && adv == ADV_IDLE)
+		return true;
+	if (state == MBR_ACTIVE && adv == ADV_ACTIVE)
+		return true;
+	if (state == MBR_PENDING && adv == ADV_IDLE)
+		return true;
+	__skb_queue_head_init(&xmitq);
+	tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq);
+	tipc_node_distr_xmit(grp->net, &xmitq);
+	return true;
+}
+
+bool tipc_group_bc_cong(struct tipc_group *grp, int len)
+{
+	struct tipc_member *m = NULL;
+
+	/* If prev bcast was replicast, reject until all receivers have acked */
+	if (grp->bc_ackers) {
+		*grp->open = false;
+		return true;
+	}
+	if (list_empty(&grp->small_win))
+		return false;
+
+	m = list_first_entry(&grp->small_win, struct tipc_member, small_win);
+	if (m->window >= len)
+		return false;
+
+	return tipc_group_cong(grp, m->node, m->port, len, &m);
+}
+
+/* tipc_group_sort_msg() - sort msg into queue by bcast sequence number
+ */
+static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq)
+{
+	struct tipc_msg *_hdr, *hdr = buf_msg(skb);
+	u16 bc_seqno = msg_grp_bc_seqno(hdr);
+	struct sk_buff *_skb, *tmp;
+	int mtyp = msg_type(hdr);
+
+	/* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */
+	if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) {
+		skb_queue_walk_safe(defq, _skb, tmp) {
+			_hdr = buf_msg(_skb);
+			if (!less(bc_seqno, msg_grp_bc_seqno(_hdr)))
+				continue;
+			__skb_queue_before(defq, _skb, skb);
+			return;
+		}
+		/* Bcast was not bypassed, - add to tail */
+	}
+	/* Unicasts are never bypassed, - always add to tail */
+	__skb_queue_tail(defq, skb);
+}
+
+/* tipc_group_filter_msg() - determine if we should accept arriving message
+ */
+void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq)
+{
+	struct sk_buff *skb = __skb_dequeue(inputq);
+	bool ack, deliver, update, leave = false;
+	struct sk_buff_head *defq;
+	struct tipc_member *m;
+	struct tipc_msg *hdr;
+	u32 node, port;
+	int mtyp, blks;
+
+	if (!skb)
+		return;
+
+	hdr = buf_msg(skb);
+	node =  msg_orignode(hdr);
+	port = msg_origport(hdr);
+
+	if (!msg_in_group(hdr))
+		goto drop;
+
+	m = tipc_group_find_member(grp, node, port);
+	if (!tipc_group_is_sender(m))
+		goto drop;
+
+	if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt))
+		goto drop;
+
+	TIPC_SKB_CB(skb)->orig_member = m->instance;
+	defq = &m->deferredq;
+	tipc_group_sort_msg(skb, defq);
+
+	while ((skb = skb_peek(defq))) {
+		hdr = buf_msg(skb);
+		mtyp = msg_type(hdr);
+		blks = msg_blocks(hdr);
+		deliver = true;
+		ack = false;
+		update = false;
+
+		if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt))
+			break;
+
+		/* Decide what to do with message */
+		switch (mtyp) {
+		case TIPC_GRP_MCAST_MSG:
+			if (msg_nameinst(hdr) != grp->instance) {
+				update = true;
+				deliver = false;
+			}
+			fallthrough;
+		case TIPC_GRP_BCAST_MSG:
+			m->bc_rcv_nxt++;
+			ack = msg_grp_bc_ack_req(hdr);
+			break;
+		case TIPC_GRP_UCAST_MSG:
+			break;
+		case TIPC_GRP_MEMBER_EVT:
+			if (m->state == MBR_LEAVING)
+				leave = true;
+			if (!grp->events)
+				deliver = false;
+			break;
+		default:
+			break;
+		}
+
+		/* Execute decisions */
+		__skb_dequeue(defq);
+		if (deliver)
+			__skb_queue_tail(inputq, skb);
+		else
+			kfree_skb(skb);
+
+		if (ack)
+			tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq);
+
+		if (leave) {
+			__skb_queue_purge(defq);
+			tipc_group_delete_member(grp, m);
+			break;
+		}
+		if (!update)
+			continue;
+
+		tipc_group_update_rcv_win(grp, blks, node, port, xmitq);
+	}
+	return;
+drop:
+	kfree_skb(skb);
+}
+
+void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
+			       u32 port, struct sk_buff_head *xmitq)
+{
+	struct list_head *active = &grp->active;
+	int max_active = grp->max_active;
+	int reclaim_limit = max_active * 3 / 4;
+	int active_cnt = grp->active_cnt;
+	struct tipc_member *m, *rm, *pm;
+
+	m = tipc_group_find_member(grp, node, port);
+	if (!m)
+		return;
+
+	m->advertised -= blks;
+
+	switch (m->state) {
+	case MBR_JOINED:
+		/* First, decide if member can go active */
+		if (active_cnt <= max_active) {
+			m->state = MBR_ACTIVE;
+			list_add_tail(&m->list, active);
+			grp->active_cnt++;
+			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+		} else {
+			m->state = MBR_PENDING;
+			list_add_tail(&m->list, &grp->pending);
+		}
+
+		if (active_cnt < reclaim_limit)
+			break;
+
+		/* Reclaim from oldest active member, if possible */
+		if (!list_empty(active)) {
+			rm = list_first_entry(active, struct tipc_member, list);
+			rm->state = MBR_RECLAIMING;
+			list_del_init(&rm->list);
+			tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq);
+			break;
+		}
+		/* Nobody to reclaim from; - revert oldest pending to JOINED */
+		pm = list_first_entry(&grp->pending, struct tipc_member, list);
+		list_del_init(&pm->list);
+		pm->state = MBR_JOINED;
+		tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq);
+		break;
+	case MBR_ACTIVE:
+		if (!list_is_last(&m->list, &grp->active))
+			list_move_tail(&m->list, &grp->active);
+		if (m->advertised > (ADV_ACTIVE * 3 / 4))
+			break;
+		tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+		break;
+	case MBR_REMITTED:
+		if (m->advertised > ADV_IDLE)
+			break;
+		m->state = MBR_JOINED;
+		grp->active_cnt--;
+		if (m->advertised < ADV_IDLE) {
+			pr_warn_ratelimited("Rcv unexpected msg after REMIT\n");
+			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+		}
+
+		if (list_empty(&grp->pending))
+			return;
+
+		/* Set oldest pending member to active and advertise */
+		pm = list_first_entry(&grp->pending, struct tipc_member, list);
+		pm->state = MBR_ACTIVE;
+		list_move_tail(&pm->list, &grp->active);
+		grp->active_cnt++;
+		tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq);
+		break;
+	case MBR_RECLAIMING:
+	case MBR_JOINING:
+	case MBR_LEAVING:
+	default:
+		break;
+	}
+}
+
+static void tipc_group_create_event(struct tipc_group *grp,
+				    struct tipc_member *m,
+				    u32 event, u16 seqno,
+				    struct sk_buff_head *inputq)
+{	u32 dnode = tipc_own_addr(grp->net);
+	struct tipc_event evt;
+	struct sk_buff *skb;
+	struct tipc_msg *hdr;
+
+	memset(&evt, 0, sizeof(evt));
+	evt.event = event;
+	evt.found_lower = m->instance;
+	evt.found_upper = m->instance;
+	evt.port.ref = m->port;
+	evt.port.node = m->node;
+	evt.s.seq.type = grp->type;
+	evt.s.seq.lower = m->instance;
+	evt.s.seq.upper = m->instance;
+
+	skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_GRP_MEMBER_EVT,
+			      GROUP_H_SIZE, sizeof(evt), dnode, m->node,
+			      grp->portid, m->port, 0);
+	if (!skb)
+		return;
+
+	hdr = buf_msg(skb);
+	msg_set_nametype(hdr, grp->type);
+	msg_set_grp_evt(hdr, event);
+	msg_set_dest_droppable(hdr, true);
+	msg_set_grp_bc_seqno(hdr, seqno);
+	memcpy(msg_data(hdr), &evt, sizeof(evt));
+	TIPC_SKB_CB(skb)->orig_member = m->instance;
+	__skb_queue_tail(inputq, skb);
+}
+
+static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
+				  int mtyp, struct sk_buff_head *xmitq)
+{
+	struct tipc_msg *hdr;
+	struct sk_buff *skb;
+	int adv = 0;
+
+	skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0,
+			      m->node, tipc_own_addr(grp->net),
+			      m->port, grp->portid, 0);
+	if (!skb)
+		return;
+
+	if (m->state == MBR_ACTIVE)
+		adv = ADV_ACTIVE - m->advertised;
+	else if (m->state == MBR_JOINED || m->state == MBR_PENDING)
+		adv = ADV_IDLE - m->advertised;
+
+	hdr = buf_msg(skb);
+
+	if (mtyp == GRP_JOIN_MSG) {
+		msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt);
+		msg_set_adv_win(hdr, adv);
+		m->advertised += adv;
+	} else if (mtyp == GRP_LEAVE_MSG) {
+		msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt);
+	} else if (mtyp == GRP_ADV_MSG) {
+		msg_set_adv_win(hdr, adv);
+		m->advertised += adv;
+	} else if (mtyp == GRP_ACK_MSG) {
+		msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt);
+	} else if (mtyp == GRP_REMIT_MSG) {
+		msg_set_grp_remitted(hdr, m->window);
+	}
+	msg_set_dest_droppable(hdr, true);
+	__skb_queue_tail(xmitq, skb);
+}
+
+void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
+			  struct tipc_msg *hdr, struct sk_buff_head *inputq,
+			  struct sk_buff_head *xmitq)
+{
+	u32 node = msg_orignode(hdr);
+	u32 port = msg_origport(hdr);
+	struct tipc_member *m, *pm;
+	u16 remitted, in_flight;
+	u16 acked;
+
+	if (!grp)
+		return;
+
+	if (grp->scope == TIPC_NODE_SCOPE && node != tipc_own_addr(grp->net))
+		return;
+
+	m = tipc_group_find_member(grp, node, port);
+
+	switch (msg_type(hdr)) {
+	case GRP_JOIN_MSG:
+		if (!m)
+			m = tipc_group_create_member(grp, node, port,
+						     0, MBR_JOINING);
+		if (!m)
+			return;
+		m->bc_syncpt = msg_grp_bc_syncpt(hdr);
+		m->bc_rcv_nxt = m->bc_syncpt;
+		m->window += msg_adv_win(hdr);
+
+		/* Wait until PUBLISH event is received if necessary */
+		if (m->state != MBR_PUBLISHED)
+			return;
+
+		/* Member can be taken into service */
+		m->state = MBR_JOINED;
+		tipc_group_open(m, usr_wakeup);
+		tipc_group_update_member(m, 0);
+		tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
+		tipc_group_create_event(grp, m, TIPC_PUBLISHED,
+					m->bc_syncpt, inputq);
+		return;
+	case GRP_LEAVE_MSG:
+		if (!m)
+			return;
+		m->bc_syncpt = msg_grp_bc_syncpt(hdr);
+		list_del_init(&m->list);
+		tipc_group_open(m, usr_wakeup);
+		tipc_group_decr_active(grp, m);
+		m->state = MBR_LEAVING;
+		tipc_group_create_event(grp, m, TIPC_WITHDRAWN,
+					m->bc_syncpt, inputq);
+		return;
+	case GRP_ADV_MSG:
+		if (!m)
+			return;
+		m->window += msg_adv_win(hdr);
+		tipc_group_open(m, usr_wakeup);
+		return;
+	case GRP_ACK_MSG:
+		if (!m)
+			return;
+		acked = msg_grp_bc_acked(hdr);
+		if (less_eq(acked, m->bc_acked))
+			return;
+		m->bc_acked = acked;
+		if (--grp->bc_ackers)
+			return;
+		list_del_init(&m->small_win);
+		*m->group->open = true;
+		*usr_wakeup = true;
+		tipc_group_update_member(m, 0);
+		return;
+	case GRP_RECLAIM_MSG:
+		if (!m)
+			return;
+		tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq);
+		m->window = ADV_IDLE;
+		tipc_group_open(m, usr_wakeup);
+		return;
+	case GRP_REMIT_MSG:
+		if (!m || m->state != MBR_RECLAIMING)
+			return;
+
+		remitted = msg_grp_remitted(hdr);
+
+		/* Messages preceding the REMIT still in receive queue */
+		if (m->advertised > remitted) {
+			m->state = MBR_REMITTED;
+			in_flight = m->advertised - remitted;
+			m->advertised = ADV_IDLE + in_flight;
+			return;
+		}
+		/* This should never happen */
+		if (m->advertised < remitted)
+			pr_warn_ratelimited("Unexpected REMIT msg\n");
+
+		/* All messages preceding the REMIT have been read */
+		m->state = MBR_JOINED;
+		grp->active_cnt--;
+		m->advertised = ADV_IDLE;
+
+		/* Set oldest pending member to active and advertise */
+		if (list_empty(&grp->pending))
+			return;
+		pm = list_first_entry(&grp->pending, struct tipc_member, list);
+		pm->state = MBR_ACTIVE;
+		list_move_tail(&pm->list, &grp->active);
+		grp->active_cnt++;
+		if (pm->advertised <= (ADV_ACTIVE * 3 / 4))
+			tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq);
+		return;
+	default:
+		pr_warn("Received unknown GROUP_PROTO message\n");
+	}
+}
+
+/* tipc_group_member_evt() - receive and handle a member up/down event
+ */
+void tipc_group_member_evt(struct tipc_group *grp,
+			   bool *usr_wakeup,
+			   int *sk_rcvbuf,
+			   struct tipc_msg *hdr,
+			   struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq)
+{
+	struct tipc_event *evt = (void *)msg_data(hdr);
+	u32 instance = evt->found_lower;
+	u32 node = evt->port.node;
+	u32 port = evt->port.ref;
+	int event = evt->event;
+	struct tipc_member *m;
+	struct net *net;
+	u32 self;
+
+	if (!grp)
+		return;
+
+	net = grp->net;
+	self = tipc_own_addr(net);
+	if (!grp->loopback && node == self && port == grp->portid)
+		return;
+
+	m = tipc_group_find_member(grp, node, port);
+
+	switch (event) {
+	case TIPC_PUBLISHED:
+		/* Send and wait for arrival of JOIN message if necessary */
+		if (!m) {
+			m = tipc_group_create_member(grp, node, port, instance,
+						     MBR_PUBLISHED);
+			if (!m)
+				break;
+			tipc_group_update_member(m, 0);
+			tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
+			break;
+		}
+
+		if (m->state != MBR_JOINING)
+			break;
+
+		/* Member can be taken into service */
+		m->instance = instance;
+		m->state = MBR_JOINED;
+		tipc_group_open(m, usr_wakeup);
+		tipc_group_update_member(m, 0);
+		tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
+		tipc_group_create_event(grp, m, TIPC_PUBLISHED,
+					m->bc_syncpt, inputq);
+		break;
+	case TIPC_WITHDRAWN:
+		if (!m)
+			break;
+
+		tipc_group_decr_active(grp, m);
+		m->state = MBR_LEAVING;
+		list_del_init(&m->list);
+		tipc_group_open(m, usr_wakeup);
+
+		/* Only send event if no LEAVE message can be expected */
+		if (!tipc_node_is_up(net, node))
+			tipc_group_create_event(grp, m, TIPC_WITHDRAWN,
+						m->bc_rcv_nxt, inputq);
+		break;
+	default:
+		break;
+	}
+	*sk_rcvbuf = tipc_group_rcvbuf_limit(grp);
+}
+
+int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb)
+{
+	struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP);
+
+	if (!group)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID,
+			grp->type) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE,
+			grp->instance) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT,
+			grp->bc_snd_nxt))
+		goto group_msg_cancel;
+
+	if (grp->scope == TIPC_NODE_SCOPE)
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE))
+			goto group_msg_cancel;
+
+	if (grp->scope == TIPC_CLUSTER_SCOPE)
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE))
+			goto group_msg_cancel;
+
+	if (*grp->open)
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN))
+			goto group_msg_cancel;
+
+	nla_nest_end(skb, group);
+	return 0;
+
+group_msg_cancel:
+	nla_nest_cancel(skb, group);
+	return -1;
+}

linux-7.2.3/net/tipc/group.h

@@ -0,0 +1,77 @@
+/*
+ * net/tipc/group.h: Include file for TIPC group unicast/multicast functions
+ *
+ * Copyright (c) 2017, Ericsson AB
+ * Copyright (c) 2020, Red Hat Inc
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_GROUP_H
+#define _TIPC_GROUP_H
+
+#include "core.h"
+
+struct tipc_group;
+struct tipc_member;
+struct tipc_msg;
+
+struct tipc_group *tipc_group_create(struct net *net, u32 portid,
+				     struct tipc_group_req *mreq,
+				     bool *group_is_open);
+void tipc_group_join(struct net *net, struct tipc_group *grp, int *sk_rcv_buf);
+void tipc_group_delete(struct net *net, struct tipc_group *grp);
+void tipc_group_add_member(struct tipc_group *grp, u32 node,
+			   u32 port, u32 instance);
+struct tipc_nlist *tipc_group_dests(struct tipc_group *grp);
+void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq,
+		     int *scope);
+u32 tipc_group_exclude(struct tipc_group *grp);
+void tipc_group_filter_msg(struct tipc_group *grp,
+			   struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq);
+void tipc_group_member_evt(struct tipc_group *grp, bool *wakeup,
+			   int *sk_rcvbuf, struct tipc_msg *hdr,
+			   struct sk_buff_head *inputq,
+			   struct sk_buff_head *xmitq);
+void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup,
+			  struct tipc_msg *hdr,
+			  struct sk_buff_head *inputq,
+			  struct sk_buff_head *xmitq);
+void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack);
+bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport,
+		     int len, struct tipc_member **m);
+bool tipc_group_bc_cong(struct tipc_group *grp, int len);
+void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
+			       u32 port, struct sk_buff_head *xmitq);
+u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
+void tipc_group_update_member(struct tipc_member *m, int len);
+int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb);
+#endif

linux-7.2.3/net/tipc/ib_media.c

@@ -0,0 +1,104 @@
+/*
+ * net/tipc/ib_media.c: Infiniband bearer support for TIPC
+ *
+ * Copyright (c) 2013 Patrick McHardy <kaber@trash.net>
+ *
+ * Based on eth_media.c, which carries the following copyright notice:
+ *
+ * Copyright (c) 2001-2007, Ericsson AB
+ * Copyright (c) 2005-2008, 2011, Wind River Systems
+ * 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 <linux/if_infiniband.h>
+#include "core.h"
+#include "bearer.h"
+
+#define TIPC_MAX_IB_LINK_WIN 500
+
+/* convert InfiniBand address (media address format) media address to string */
+static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
+			    int str_size)
+{
+	if (str_size < 60)	/* 60 = 19 * strlen("xx:") + strlen("xx\0") */
+		return 1;
+
+	sprintf(str_buf, "%20phC", a->value);
+
+	return 0;
+}
+
+/* Convert from media address format to discovery message addr format */
+static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr)
+{
+	memset(msg, 0, TIPC_MEDIA_INFO_SIZE);
+	memcpy(msg, addr->value, INFINIBAND_ALEN);
+	return 0;
+}
+
+/* Convert raw InfiniBand address format to media addr format */
+static int tipc_ib_raw2addr(struct tipc_bearer *b,
+			    struct tipc_media_addr *addr,
+			    const char *msg)
+{
+	memset(addr, 0, sizeof(*addr));
+	memcpy(addr->value, msg, INFINIBAND_ALEN);
+	addr->media_id = TIPC_MEDIA_TYPE_IB;
+	addr->broadcast = !memcmp(msg, b->bcast_addr.value,
+				  INFINIBAND_ALEN);
+	return 0;
+}
+
+/* Convert discovery msg addr format to InfiniBand media addr format */
+static int tipc_ib_msg2addr(struct tipc_bearer *b,
+			    struct tipc_media_addr *addr,
+			    char *msg)
+{
+	return tipc_ib_raw2addr(b, addr, msg);
+}
+
+/* InfiniBand media registration info */
+struct tipc_media ib_media_info = {
+	.send_msg	= tipc_l2_send_msg,
+	.enable_media	= tipc_enable_l2_media,
+	.disable_media	= tipc_disable_l2_media,
+	.addr2str	= tipc_ib_addr2str,
+	.addr2msg	= tipc_ib_addr2msg,
+	.msg2addr	= tipc_ib_msg2addr,
+	.raw2addr	= tipc_ib_raw2addr,
+	.priority	= TIPC_DEF_LINK_PRI,
+	.tolerance	= TIPC_DEF_LINK_TOL,
+	.min_win	= TIPC_DEF_LINK_WIN,
+	.max_win	= TIPC_MAX_IB_LINK_WIN,
+	.type_id	= TIPC_MEDIA_TYPE_IB,
+	.hwaddr_len	= INFINIBAND_ALEN,
+	.name		= "ib"
+};

linux-7.2.3/net/tipc/link.h

@@ -0,0 +1,158 @@
+/*
+ * net/tipc/link.h: Include file for TIPC link code
+ *
+ * Copyright (c) 1995-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_LINK_H
+#define _TIPC_LINK_H
+
+#include <net/genetlink.h>
+#include "msg.h"
+#include "node.h"
+
+/* TIPC-specific error codes
+*/
+#define ELINKCONG EAGAIN	/* link congestion <=> resource unavailable */
+
+/* Link FSM events:
+ */
+enum {
+	LINK_ESTABLISH_EVT       = 0xec1ab1e,
+	LINK_PEER_RESET_EVT      = 0x9eed0e,
+	LINK_FAILURE_EVT         = 0xfa110e,
+	LINK_RESET_EVT           = 0x10ca1d0e,
+	LINK_FAILOVER_BEGIN_EVT  = 0xfa110bee,
+	LINK_FAILOVER_END_EVT    = 0xfa110ede,
+	LINK_SYNCH_BEGIN_EVT     = 0xc1ccbee,
+	LINK_SYNCH_END_EVT       = 0xc1ccede
+};
+
+/* Events returned from link at packet reception or at timeout
+ */
+enum {
+	TIPC_LINK_UP_EVT       = 1,
+	TIPC_LINK_DOWN_EVT     = (1 << 1),
+	TIPC_LINK_SND_STATE    = (1 << 2)
+};
+
+/* Starting value for maximum packet size negotiation on unicast links
+ * (unless bearer MTU is less)
+ */
+#define MAX_PKT_DEFAULT 1500
+
+bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
+		      int tolerance, char net_plane, u32 mtu, int priority,
+		      u32 min_win, u32 max_win, u32 session, u32 ownnode,
+		      u32 peer, u8 *peer_id, u16 peer_caps,
+		      struct tipc_link *bc_sndlink,
+		      struct tipc_link *bc_rcvlink,
+		      struct sk_buff_head *inputq,
+		      struct sk_buff_head *namedq,
+		      struct tipc_link **link);
+bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id,
+			 int mtu, u32 min_win, u32 max_win, u16 peer_caps,
+			 struct sk_buff_head *inputq,
+			 struct sk_buff_head *namedq,
+			 struct tipc_link *bc_sndlink,
+			 struct tipc_link **link);
+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);
+bool tipc_link_peer_is_down(struct tipc_link *l);
+bool tipc_link_is_reset(struct tipc_link *l);
+bool tipc_link_is_establishing(struct tipc_link *l);
+bool tipc_link_is_synching(struct tipc_link *l);
+bool tipc_link_is_failingover(struct tipc_link *l);
+bool tipc_link_is_blocked(struct tipc_link *l);
+void tipc_link_set_active(struct tipc_link *l, bool active);
+void tipc_link_reset(struct tipc_link *l);
+void tipc_link_reset_stats(struct tipc_link *l);
+int tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list,
+		   struct sk_buff_head *xmitq);
+struct sk_buff_head *tipc_link_inputq(struct tipc_link *l);
+u16 tipc_link_rcv_nxt(struct tipc_link *l);
+u16 tipc_link_acked(struct tipc_link *l);
+u32 tipc_link_id(struct tipc_link *l);
+char *tipc_link_name(struct tipc_link *l);
+u32 tipc_link_state(struct tipc_link *l);
+char tipc_link_plane(struct tipc_link *l);
+int tipc_link_prio(struct tipc_link *l);
+int tipc_link_min_win(struct tipc_link *l);
+int tipc_link_max_win(struct tipc_link *l);
+void tipc_link_update_caps(struct tipc_link *l, u16 capabilities);
+bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr);
+unsigned long tipc_link_tolerance(struct tipc_link *l);
+void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
+			     struct sk_buff_head *xmitq);
+void tipc_link_set_prio(struct tipc_link *l, u32 prio,
+			struct sk_buff_head *xmitq);
+void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit);
+void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win);
+int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
+		       struct tipc_link *link, int nlflags);
+int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
+int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq);
+int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
+		  struct sk_buff_head *xmitq);
+int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq);
+void tipc_link_add_bc_peer(struct tipc_link *snd_l,
+			   struct tipc_link *uc_l,
+			   struct sk_buff_head *xmitq);
+void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
+			      struct tipc_link *rcv_l,
+			      struct sk_buff_head *xmitq);
+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);
+u16 tipc_get_gap_ack_blks(struct tipc_gap_ack_blks **ga, struct tipc_link *l,
+			  struct tipc_msg *hdr, bool uc);
+int tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked, u16 gap,
+			 struct tipc_gap_ack_blks *ga,
+			 struct sk_buff_head *xmitq,
+			 struct sk_buff_head *retrq);
+void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr);
+int tipc_link_bc_sync_rcv(struct tipc_link *l,   struct tipc_msg *hdr,
+			  struct sk_buff_head *xmitq);
+int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb,
+			  struct sk_buff_head *xmitq);
+bool tipc_link_too_silent(struct tipc_link *l);
+struct net *tipc_link_net(struct tipc_link *l);
+#endif

linux-7.2.3/net/tipc/monitor.c

@@ -0,0 +1,875 @@
+/*
+ * net/tipc/monitor.c
+ *
+ * Copyright (c) 2016, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <net/genetlink.h>
+#include "core.h"
+#include "addr.h"
+#include "monitor.h"
+#include "bearer.h"
+
+#define MAX_MON_DOMAIN       64
+#define MON_TIMEOUT          120000
+#define MAX_PEER_DOWN_EVENTS 4
+
+/* struct tipc_mon_domain: domain record to be transferred between peers
+ * @len: actual size of domain record
+ * @gen: current generation of sender's domain
+ * @ack_gen: most recent generation of self's domain acked by peer
+ * @member_cnt: number of domain member nodes described in this record
+ * @up_map: bit map indicating which of the members the sender considers up
+ * @members: identity of the domain members
+ */
+struct tipc_mon_domain {
+	u16 len;
+	u16 gen;
+	u16 ack_gen;
+	u16 member_cnt;
+	u64 up_map;
+	u32 members[MAX_MON_DOMAIN];
+};
+
+/* struct tipc_peer: state of a peer node and its domain
+ * @addr: tipc node identity of peer
+ * @head_map: shows which other nodes currently consider peer 'up'
+ * @domain: most recent domain record from peer
+ * @hash: position in hashed lookup list
+ * @list: position in linked list, in circular ascending order by 'addr'
+ * @applied: number of reported domain members applied on this monitor list
+ * @is_up: peer is up as seen from this node
+ * @is_head: peer is assigned domain head as seen from this node
+ * @is_local: peer is in local domain and should be continuously monitored
+ * @down_cnt: - numbers of other peers which have reported this on lost
+ */
+struct tipc_peer {
+	u32 addr;
+	struct tipc_mon_domain *domain;
+	struct hlist_node hash;
+	struct list_head list;
+	u8 applied;
+	u8 down_cnt;
+	bool is_up;
+	bool is_head;
+	bool is_local;
+};
+
+struct tipc_monitor {
+	struct hlist_head peers[NODE_HTABLE_SIZE];
+	int peer_cnt;
+	struct tipc_peer *self;
+	rwlock_t lock;
+	struct tipc_mon_domain cache;
+	u16 list_gen;
+	u16 dom_gen;
+	struct net *net;
+	struct timer_list timer;
+	unsigned long timer_intv;
+};
+
+static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id)
+{
+	return tipc_net(net)->monitors[bearer_id];
+}
+
+const int tipc_max_domain_size = sizeof(struct tipc_mon_domain);
+
+static inline u16 mon_cpu_to_le16(u16 val)
+{
+	return (__force __u16)htons(val);
+}
+
+static inline u32 mon_cpu_to_le32(u32 val)
+{
+	return (__force __u32)htonl(val);
+}
+
+static inline u64 mon_cpu_to_le64(u64 val)
+{
+	return (__force __u64)cpu_to_be64(val);
+}
+
+static inline u16 mon_le16_to_cpu(u16 val)
+{
+	return ntohs((__force __be16)val);
+}
+
+static inline u32 mon_le32_to_cpu(u32 val)
+{
+	return ntohl((__force __be32)val);
+}
+
+static inline u64 mon_le64_to_cpu(u64 val)
+{
+	return be64_to_cpu((__force __be64)val);
+}
+
+/* dom_rec_len(): actual length of domain record for transport
+ */
+static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt)
+{
+	return (offsetof(struct tipc_mon_domain, members)) + (mcnt * sizeof(u32));
+}
+
+/* dom_size() : calculate size of own domain based on number of peers
+ */
+static int dom_size(int peers)
+{
+	int i = 0;
+
+	while ((i * i) < peers)
+		i++;
+	return min(i, MAX_MON_DOMAIN);
+}
+
+static void map_set(u64 *up_map, int i, unsigned int v)
+{
+	*up_map &= ~(1ULL << i);
+	*up_map |= ((u64)v << i);
+}
+
+static int map_get(u64 up_map, int i)
+{
+	return (up_map & (1ULL << i)) >> i;
+}
+
+static struct tipc_peer *peer_prev(struct tipc_peer *peer)
+{
+	return list_last_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_nxt(struct tipc_peer *peer)
+{
+	return list_first_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_head(struct tipc_peer *peer)
+{
+	while (!peer->is_head)
+		peer = peer_prev(peer);
+	return peer;
+}
+
+static struct tipc_peer *get_peer(struct tipc_monitor *mon, u32 addr)
+{
+	struct tipc_peer *peer;
+	unsigned int thash = tipc_hashfn(addr);
+
+	hlist_for_each_entry(peer, &mon->peers[thash], hash) {
+		if (peer->addr == addr)
+			return peer;
+	}
+	return NULL;
+}
+
+static struct tipc_peer *get_self(struct net *net, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+
+	return mon->self;
+}
+
+static inline bool tipc_mon_is_active(struct net *net, struct tipc_monitor *mon)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	return mon->peer_cnt > tn->mon_threshold;
+}
+
+/* mon_identify_lost_members() : - identify amd mark potentially lost members
+ */
+static void mon_identify_lost_members(struct tipc_peer *peer,
+				      struct tipc_mon_domain *dom_bef,
+				      int applied_bef)
+{
+	struct tipc_peer *member = peer;
+	struct tipc_mon_domain *dom_aft = peer->domain;
+	int applied_aft = peer->applied;
+	int i;
+
+	for (i = 0; i < applied_bef; i++) {
+		member = peer_nxt(member);
+
+		/* Do nothing if self or peer already see member as down */
+		if (!member->is_up || !map_get(dom_bef->up_map, i))
+			continue;
+
+		/* Loss of local node must be detected by active probing */
+		if (member->is_local)
+			continue;
+
+		/* Start probing if member was removed from applied domain */
+		if (!applied_aft || (applied_aft < i)) {
+			member->down_cnt = 1;
+			continue;
+		}
+
+		/* Member loss is confirmed if it is still in applied domain */
+		if (!map_get(dom_aft->up_map, i))
+			member->down_cnt++;
+	}
+}
+
+/* mon_apply_domain() : match a peer's domain record against monitor list
+ */
+static void mon_apply_domain(struct tipc_monitor *mon,
+			     struct tipc_peer *peer)
+{
+	struct tipc_mon_domain *dom = peer->domain;
+	struct tipc_peer *member;
+	u32 addr;
+	int i;
+
+	if (!dom || !peer->is_up)
+		return;
+
+	/* Scan across domain members and match against monitor list */
+	peer->applied = 0;
+	member = peer_nxt(peer);
+	for (i = 0; i < dom->member_cnt; i++) {
+		addr = dom->members[i];
+		if (addr != member->addr)
+			return;
+		peer->applied++;
+		member = peer_nxt(member);
+	}
+}
+
+/* mon_update_local_domain() : update after peer addition/removal/up/down
+ */
+static void mon_update_local_domain(struct tipc_monitor *mon)
+{
+	struct tipc_peer *self = mon->self;
+	struct tipc_mon_domain *cache = &mon->cache;
+	struct tipc_mon_domain *dom = self->domain;
+	struct tipc_peer *peer = self;
+	u64 prev_up_map = dom->up_map;
+	u16 member_cnt, i;
+	bool diff;
+
+	/* Update local domain size based on current size of cluster */
+	member_cnt = dom_size(mon->peer_cnt) - 1;
+	self->applied = member_cnt;
+
+	/* Update native and cached outgoing local domain records */
+	dom->len = dom_rec_len(dom, member_cnt);
+	diff = dom->member_cnt != member_cnt;
+	dom->member_cnt = member_cnt;
+	for (i = 0; i < member_cnt; i++) {
+		peer = peer_nxt(peer);
+		diff |= dom->members[i] != peer->addr;
+		dom->members[i] = peer->addr;
+		map_set(&dom->up_map, i, peer->is_up);
+		cache->members[i] = mon_cpu_to_le32(peer->addr);
+	}
+	diff |= dom->up_map != prev_up_map;
+	if (!diff)
+		return;
+	dom->gen = ++mon->dom_gen;
+	cache->len = mon_cpu_to_le16(dom->len);
+	cache->gen = mon_cpu_to_le16(dom->gen);
+	cache->member_cnt = mon_cpu_to_le16(member_cnt);
+	cache->up_map = mon_cpu_to_le64(dom->up_map);
+	mon_apply_domain(mon, self);
+}
+
+/* mon_update_neighbors() : update preceding neighbors of added/removed peer
+ */
+static void mon_update_neighbors(struct tipc_monitor *mon,
+				 struct tipc_peer *peer)
+{
+	int dz, i;
+
+	dz = dom_size(mon->peer_cnt);
+	for (i = 0; i < dz; i++) {
+		mon_apply_domain(mon, peer);
+		peer = peer_prev(peer);
+	}
+}
+
+/* mon_assign_roles() : reassign peer roles after a network change
+ * The monitor list is consistent at this stage; i.e., each peer is monitoring
+ * a set of domain members as matched between domain record and the monitor list
+ */
+static void mon_assign_roles(struct tipc_monitor *mon, struct tipc_peer *head)
+{
+	struct tipc_peer *peer = peer_nxt(head);
+	struct tipc_peer *self = mon->self;
+	int i = 0;
+
+	for (; peer != self; peer = peer_nxt(peer)) {
+		peer->is_local = false;
+
+		/* Update domain member */
+		if (i++ < head->applied) {
+			peer->is_head = false;
+			if (head == self)
+				peer->is_local = true;
+			continue;
+		}
+		/* Assign next domain head */
+		if (!peer->is_up)
+			continue;
+		if (peer->is_head)
+			break;
+		head = peer;
+		head->is_head = true;
+		i = 0;
+	}
+	mon->list_gen++;
+}
+
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self;
+	struct tipc_peer *peer, *prev, *head;
+
+	if (!mon)
+		return;
+
+	self = get_self(net, bearer_id);
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer)
+		goto exit;
+	prev = peer_prev(peer);
+	list_del(&peer->list);
+	hlist_del(&peer->hash);
+	kfree(peer->domain);
+	kfree(peer);
+	mon->peer_cnt--;
+	head = peer_head(prev);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_update_neighbors(mon, prev);
+
+	/* Revert to full-mesh monitoring if we reach threshold */
+	if (!tipc_mon_is_active(net, mon)) {
+		list_for_each_entry(peer, &self->list, list) {
+			kfree(peer->domain);
+			peer->domain = NULL;
+			peer->applied = 0;
+		}
+	}
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+static bool tipc_mon_add_peer(struct tipc_monitor *mon, u32 addr,
+			      struct tipc_peer **peer)
+{
+	struct tipc_peer *self = mon->self;
+	struct tipc_peer *cur, *prev, *p;
+
+	p = kzalloc_obj(*p, GFP_ATOMIC);
+	*peer = p;
+	if (!p)
+		return false;
+	p->addr = addr;
+
+	/* Add new peer to lookup list */
+	INIT_LIST_HEAD(&p->list);
+	hlist_add_head(&p->hash, &mon->peers[tipc_hashfn(addr)]);
+
+	/* Sort new peer into iterator list, in ascending circular order */
+	prev = self;
+	list_for_each_entry(cur, &self->list, list) {
+		if ((addr > prev->addr) && (addr < cur->addr))
+			break;
+		if (((addr < cur->addr) || (addr > prev->addr)) &&
+		    (prev->addr > cur->addr))
+			break;
+		prev = cur;
+	}
+	list_add_tail(&p->list, &cur->list);
+	mon->peer_cnt++;
+	mon_update_neighbors(mon, p);
+	return true;
+}
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *head;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer && !tipc_mon_add_peer(mon, addr, &peer))
+		goto exit;
+	peer->is_up = true;
+	head = peer_head(peer);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self;
+	struct tipc_peer *peer, *head;
+	struct tipc_mon_domain *dom;
+	int applied;
+
+	if (!mon)
+		return;
+
+	self = get_self(net, bearer_id);
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer) {
+		pr_warn("Mon: unknown link %x/%u DOWN\n", addr, bearer_id);
+		goto exit;
+	}
+	applied = peer->applied;
+	peer->applied = 0;
+	dom = peer->domain;
+	peer->domain = NULL;
+	if (peer->is_head)
+		mon_identify_lost_members(peer, dom, applied);
+	kfree(dom);
+	peer->is_up = false;
+	peer->is_head = false;
+	peer->is_local = false;
+	peer->down_cnt = 0;
+	head = peer_head(peer);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+/* tipc_mon_rcv - process monitor domain event message
+ */
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+		  struct tipc_mon_state *state, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_mon_domain *arrv_dom = data;
+	struct tipc_mon_domain dom_bef;
+	struct tipc_mon_domain *dom;
+	struct tipc_peer *peer;
+	u16 new_member_cnt = mon_le16_to_cpu(arrv_dom->member_cnt);
+	int new_dlen = dom_rec_len(arrv_dom, new_member_cnt);
+	u16 new_gen = mon_le16_to_cpu(arrv_dom->gen);
+	u16 acked_gen = mon_le16_to_cpu(arrv_dom->ack_gen);
+	u16 arrv_dlen = mon_le16_to_cpu(arrv_dom->len);
+	bool probing = state->probing;
+	int i, applied_bef;
+
+	state->probing = false;
+
+	/* Sanity check received domain record */
+	if (new_member_cnt > MAX_MON_DOMAIN)
+		return;
+	if (dlen < dom_rec_len(arrv_dom, 0))
+		return;
+	if (dlen != dom_rec_len(arrv_dom, new_member_cnt))
+		return;
+	if (dlen < new_dlen || arrv_dlen != new_dlen)
+		return;
+
+	/* Synch generation numbers with peer if link just came up */
+	if (!state->synched) {
+		state->peer_gen = new_gen - 1;
+		state->acked_gen = acked_gen;
+		state->synched = true;
+	}
+
+	if (more(acked_gen, state->acked_gen))
+		state->acked_gen = acked_gen;
+
+	/* Drop duplicate unless we are waiting for a probe response */
+	if (!more(new_gen, state->peer_gen) && !probing)
+		return;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer || !peer->is_up)
+		goto exit;
+
+	/* Peer is confirmed, stop any ongoing probing */
+	peer->down_cnt = 0;
+
+	/* Task is done for duplicate record */
+	if (!more(new_gen, state->peer_gen))
+		goto exit;
+
+	state->peer_gen = new_gen;
+
+	/* Cache current domain record for later use */
+	dom_bef.member_cnt = 0;
+	dom = peer->domain;
+	if (dom)
+		memcpy(&dom_bef, dom, dom->len);
+
+	/* Transform and store received domain record */
+	if (!dom || (dom->len < new_dlen)) {
+		kfree(dom);
+		dom = kmalloc(new_dlen, GFP_ATOMIC);
+		peer->domain = dom;
+		if (!dom)
+			goto exit;
+	}
+	dom->len = new_dlen;
+	dom->gen = new_gen;
+	dom->member_cnt = new_member_cnt;
+	dom->up_map = mon_le64_to_cpu(arrv_dom->up_map);
+	for (i = 0; i < new_member_cnt; i++)
+		dom->members[i] = mon_le32_to_cpu(arrv_dom->members[i]);
+
+	/* Update peers affected by this domain record */
+	applied_bef = peer->applied;
+	mon_apply_domain(mon, peer);
+	mon_identify_lost_members(peer, &dom_bef, applied_bef);
+	mon_assign_roles(mon, peer_head(peer));
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+		   struct tipc_mon_state *state, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_mon_domain *dom = data;
+	u16 gen = mon->dom_gen;
+	u16 len;
+
+	/* Send invalid record if not active */
+	if (!tipc_mon_is_active(net, mon)) {
+		dom->len = 0;
+		return;
+	}
+
+	/* Send only a dummy record with ack if peer has acked our last sent */
+	if (likely(state->acked_gen == gen)) {
+		len = dom_rec_len(dom, 0);
+		*dlen = len;
+		dom->len = mon_cpu_to_le16(len);
+		dom->gen = mon_cpu_to_le16(gen);
+		dom->ack_gen = mon_cpu_to_le16(state->peer_gen);
+		dom->member_cnt = 0;
+		return;
+	}
+	/* Send the full record */
+	read_lock_bh(&mon->lock);
+	len = mon_le16_to_cpu(mon->cache.len);
+	*dlen = len;
+	memcpy(data, &mon->cache, len);
+	read_unlock_bh(&mon->lock);
+	dom->ack_gen = mon_cpu_to_le16(state->peer_gen);
+}
+
+void tipc_mon_get_state(struct net *net, u32 addr,
+			struct tipc_mon_state *state,
+			int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *peer;
+
+	if (!tipc_mon_is_active(net, mon)) {
+		state->probing = false;
+		state->monitoring = true;
+		return;
+	}
+
+	/* Used cached state if table has not changed */
+	if (!state->probing &&
+	    (state->list_gen == mon->list_gen) &&
+	    (state->acked_gen == mon->dom_gen))
+		return;
+
+	read_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (peer) {
+		state->probing = state->acked_gen != mon->dom_gen;
+		state->probing |= peer->down_cnt;
+		state->reset |= peer->down_cnt >= MAX_PEER_DOWN_EVENTS;
+		state->monitoring = peer->is_local;
+		state->monitoring |= peer->is_head;
+		state->list_gen = mon->list_gen;
+	}
+	read_unlock_bh(&mon->lock);
+}
+
+static void mon_timeout(struct timer_list *t)
+{
+	struct tipc_monitor *mon = timer_container_of(mon, t, timer);
+	struct tipc_peer *self;
+	int best_member_cnt = dom_size(mon->peer_cnt) - 1;
+
+	write_lock_bh(&mon->lock);
+	self = mon->self;
+	if (self && (best_member_cnt != self->applied)) {
+		mon_update_local_domain(mon);
+		mon_assign_roles(mon, self);
+	}
+	write_unlock_bh(&mon->lock);
+	mod_timer(&mon->timer, jiffies + mon->timer_intv);
+}
+
+int tipc_mon_create(struct net *net, int bearer_id)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_monitor *mon;
+	struct tipc_peer *self;
+	struct tipc_mon_domain *dom;
+
+	if (tn->monitors[bearer_id])
+		return 0;
+
+	mon = kzalloc_obj(*mon, GFP_ATOMIC);
+	self = kzalloc_obj(*self, GFP_ATOMIC);
+	dom = kzalloc_obj(*dom, GFP_ATOMIC);
+	if (!mon || !self || !dom) {
+		kfree(mon);
+		kfree(self);
+		kfree(dom);
+		return -ENOMEM;
+	}
+	tn->monitors[bearer_id] = mon;
+	rwlock_init(&mon->lock);
+	mon->net = net;
+	mon->peer_cnt = 1;
+	mon->self = self;
+	self->domain = dom;
+	self->addr = tipc_own_addr(net);
+	self->is_up = true;
+	self->is_head = true;
+	INIT_LIST_HEAD(&self->list);
+	timer_setup(&mon->timer, mon_timeout, 0);
+	mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff));
+	mod_timer(&mon->timer, jiffies + mon->timer_intv);
+	return 0;
+}
+
+void tipc_mon_delete(struct net *net, int bearer_id)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self;
+	struct tipc_peer *peer, *tmp;
+
+	if (!mon)
+		return;
+
+	self = get_self(net, bearer_id);
+	write_lock_bh(&mon->lock);
+	tn->monitors[bearer_id] = NULL;
+	list_for_each_entry_safe(peer, tmp, &self->list, list) {
+		list_del(&peer->list);
+		hlist_del(&peer->hash);
+		kfree(peer->domain);
+		kfree(peer);
+	}
+	mon->self = NULL;
+	write_unlock_bh(&mon->lock);
+	timer_shutdown_sync(&mon->timer);
+	kfree(self->domain);
+	kfree(self);
+	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);
+		if (mon->self)
+			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);
+
+	if (cluster_size > TIPC_CLUSTER_SIZE)
+		return -EINVAL;
+
+	tn->mon_threshold = cluster_size;
+
+	return 0;
+}
+
+int tipc_nl_monitor_get_threshold(struct net *net)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	return tn->mon_threshold;
+}
+
+static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer,
+				      struct tipc_nl_msg *msg)
+{
+	struct tipc_mon_domain *dom = peer->domain;
+	struct nlattr *attrs;
+	void *hdr;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  NLM_F_MULTI, TIPC_NL_MON_PEER_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_ADDR, peer->addr))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_APPLIED, peer->applied))
+		goto attr_msg_full;
+
+	if (peer->is_up)
+		if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_UP))
+			goto attr_msg_full;
+	if (peer->is_local)
+		if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_LOCAL))
+			goto attr_msg_full;
+	if (peer->is_head)
+		if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_HEAD))
+			goto attr_msg_full;
+
+	if (dom) {
+		if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_DOMGEN, dom->gen))
+			goto attr_msg_full;
+		if (nla_put_u64_64bit(msg->skb, TIPC_NLA_MON_PEER_UPMAP,
+				      dom->up_map, TIPC_NLA_MON_PEER_PAD))
+			goto attr_msg_full;
+		if (nla_put(msg->skb, TIPC_NLA_MON_PEER_MEMBERS,
+			    dom->member_cnt * sizeof(u32), &dom->members))
+			goto attr_msg_full;
+	}
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg,
+			     u32 bearer_id, u32 *prev_node)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *peer;
+
+	if (!mon)
+		return -EINVAL;
+
+	read_lock_bh(&mon->lock);
+	peer = mon->self;
+	do {
+		if (*prev_node) {
+			if (peer->addr == *prev_node)
+				*prev_node = 0;
+			else
+				continue;
+		}
+		if (__tipc_nl_add_monitor_peer(peer, msg)) {
+			*prev_node = peer->addr;
+			read_unlock_bh(&mon->lock);
+			return -EMSGSIZE;
+		}
+	} while ((peer = peer_nxt(peer)) != mon->self);
+	read_unlock_bh(&mon->lock);
+
+	return 0;
+}
+
+int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
+			  u32 bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	char bearer_name[TIPC_MAX_BEARER_NAME];
+	struct nlattr *attrs;
+	void *hdr;
+	int ret;
+
+	ret = tipc_bearer_get_name(net, bearer_name, bearer_id);
+	if (ret || !mon)
+		return 0;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  NLM_F_MULTI, TIPC_NL_MON_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON);
+	if (!attrs)
+		goto msg_full;
+
+	read_lock_bh(&mon->lock);
+	if (nla_put_u32(msg->skb, TIPC_NLA_MON_REF, bearer_id))
+		goto attr_msg_full;
+	if (tipc_mon_is_active(net, mon))
+		if (nla_put_flag(msg->skb, TIPC_NLA_MON_ACTIVE))
+			goto attr_msg_full;
+	if (nla_put_string(msg->skb, TIPC_NLA_MON_BEARER_NAME, bearer_name))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEERCNT, mon->peer_cnt))
+		goto attr_msg_full;
+	if (nla_put_u32(msg->skb, TIPC_NLA_MON_LISTGEN, mon->list_gen))
+		goto attr_msg_full;
+
+	read_unlock_bh(&mon->lock);
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	read_unlock_bh(&mon->lock);
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}

linux-7.2.3/net/tipc/monitor.h

@@ -0,0 +1,83 @@
+/*
+ * net/tipc/monitor.h
+ *
+ * Copyright (c) 2015, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_MONITOR_H
+#define _TIPC_MONITOR_H
+
+#include "netlink.h"
+
+/* struct tipc_mon_state: link instance's cache of monitor list and domain state
+ * @list_gen: current generation of this node's monitor list
+ * @gen: current generation of this node's local domain
+ * @peer_gen: most recent domain generation received from peer
+ * @acked_gen: most recent generation of self's domain acked by peer
+ * @monitoring: this peer endpoint should continuously monitored
+ * @probing: peer endpoint should be temporarily probed for potential loss
+ * @synched: domain record's generation has been synched with peer after reset
+ */
+struct tipc_mon_state {
+	u16 list_gen;
+	u16 peer_gen;
+	u16 acked_gen;
+	bool monitoring :1;
+	bool probing    :1;
+	bool reset      :1;
+	bool synched    :1;
+};
+
+int tipc_mon_create(struct net *net, int bearer_id);
+void tipc_mon_delete(struct net *net, int bearer_id);
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+		   struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+		  struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_get_state(struct net *net, u32 addr,
+			struct tipc_mon_state *state,
+			int bearer_id);
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id);
+
+int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size);
+int tipc_nl_monitor_get_threshold(struct net *net);
+int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
+			  u32 bearer_id);
+int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg,
+			     u32 bearer_id, u32 *prev_node);
+void tipc_mon_reinit_self(struct net *net);
+
+extern const int tipc_max_domain_size;
+#endif

linux-7.2.3/net/tipc/msg.c

@@ -0,0 +1,867 @@
+/*
+ * net/tipc/msg.c: TIPC message header routines
+ *
+ * Copyright (c) 2000-2006, 2014-2015, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <net/sock.h>
+#include "core.h"
+#include "msg.h"
+#include "addr.h"
+#include "name_table.h"
+#include "crypto.h"
+
+#define BUF_ALIGN(x) ALIGN(x, 4)
+#define MAX_FORWARD_SIZE 1024
+#ifdef CONFIG_TIPC_CRYPTO
+#define BUF_HEADROOM ALIGN(((LL_MAX_HEADER + 48) + EHDR_MAX_SIZE), 16)
+#define BUF_OVERHEAD (BUF_HEADROOM + TIPC_AES_GCM_TAG_SIZE)
+#else
+#define BUF_HEADROOM (LL_MAX_HEADER + 48)
+#define BUF_OVERHEAD BUF_HEADROOM
+#endif
+
+const int one_page_mtu = PAGE_SIZE - SKB_DATA_ALIGN(BUF_OVERHEAD) -
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+/**
+ * tipc_buf_acquire - creates a TIPC message buffer
+ * @size: message size (including TIPC header)
+ * @gfp: memory allocation flags
+ *
+ * Return: a new buffer with data pointers set to the specified size.
+ *
+ * NOTE:
+ * Headroom is reserved to allow prepending of a data link header.
+ * There may also be unrequested tailroom present at the buffer's end.
+ */
+struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb_fclone(BUF_OVERHEAD + size, gfp);
+	if (skb) {
+		skb_reserve(skb, BUF_HEADROOM);
+		skb_put(skb, size);
+		skb->next = NULL;
+	}
+	return skb;
+}
+
+void tipc_msg_init(u32 own_node, struct tipc_msg *m, u32 user, u32 type,
+		   u32 hsize, u32 dnode)
+{
+	memset(m, 0, hsize);
+	msg_set_version(m);
+	msg_set_user(m, user);
+	msg_set_hdr_sz(m, hsize);
+	msg_set_size(m, hsize);
+	msg_set_prevnode(m, own_node);
+	msg_set_type(m, type);
+	if (hsize > SHORT_H_SIZE) {
+		msg_set_orignode(m, own_node);
+		msg_set_destnode(m, dnode);
+	}
+}
+
+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)
+{
+	struct tipc_msg *msg;
+	struct sk_buff *buf;
+
+	buf = tipc_buf_acquire(hdr_sz + data_sz, GFP_ATOMIC);
+	if (unlikely(!buf))
+		return NULL;
+
+	msg = buf_msg(buf);
+	tipc_msg_init(onode, msg, user, type, hdr_sz, dnode);
+	msg_set_size(msg, hdr_sz + data_sz);
+	msg_set_origport(msg, oport);
+	msg_set_destport(msg, dport);
+	msg_set_errcode(msg, errcode);
+	return buf;
+}
+
+/* tipc_buf_append(): Append a buffer to the fragment list of another buffer
+ * @*headbuf: in:  NULL for first frag, otherwise value returned from prev call
+ *            out: set when successful non-complete reassembly, otherwise NULL
+ * @*buf:     in:  the buffer to append. Always defined
+ *            out: head buf after successful complete reassembly, otherwise NULL
+ * Returns 1 when reassembly complete, otherwise 0
+ */
+int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
+{
+	struct sk_buff *head = *headbuf;
+	struct sk_buff *frag = *buf;
+	struct sk_buff *tail = NULL;
+	struct tipc_msg *msg;
+	u32 fragid;
+	int delta;
+	bool headstolen;
+
+	if (!frag)
+		goto err;
+
+	msg = buf_msg(frag);
+	fragid = msg_type(msg);
+	frag->next = NULL;
+	skb_pull(frag, msg_hdr_sz(msg));
+
+	if (fragid == FIRST_FRAGMENT) {
+		if (unlikely(head))
+			goto err;
+		if (skb_has_frag_list(frag) && __skb_linearize(frag))
+			goto err;
+		*buf = NULL;
+		frag = skb_unshare(frag, GFP_ATOMIC);
+		if (unlikely(!frag))
+			goto err;
+		head = *headbuf = frag;
+		TIPC_SKB_CB(head)->tail = NULL;
+		return 0;
+	}
+
+	if (!head)
+		goto err;
+
+	/* Either the input skb ownership is transferred to headskb
+	 * or the input skb is freed, clear the reference to avoid
+	 * bad access on error path.
+	 */
+	*buf = NULL;
+	if (skb_try_coalesce(head, frag, &headstolen, &delta)) {
+		kfree_skb_partial(frag, headstolen);
+	} else {
+		tail = TIPC_SKB_CB(head)->tail;
+		if (!skb_has_frag_list(head))
+			skb_shinfo(head)->frag_list = frag;
+		else
+			tail->next = frag;
+		head->truesize += frag->truesize;
+		head->data_len += frag->len;
+		head->len += frag->len;
+		TIPC_SKB_CB(head)->tail = frag;
+	}
+
+	if (fragid == LAST_FRAGMENT) {
+		TIPC_SKB_CB(head)->validated = 0;
+
+		/* If the reassembled skb has been freed in
+		 * tipc_msg_validate() because of an invalid truesize,
+		 * then head will point to a newly allocated reassembled
+		 * skb, while *headbuf points to freed reassembled skb.
+		 * In such cases, correct *headbuf for freeing the newly
+		 * allocated reassembled skb later.
+		 */
+		if (unlikely(!tipc_msg_validate(&head))) {
+			if (head != *headbuf)
+				*headbuf = head;
+			goto err;
+		}
+
+		*buf = head;
+		TIPC_SKB_CB(head)->tail = NULL;
+		*headbuf = NULL;
+		return 1;
+	}
+	return 0;
+err:
+	kfree_skb(*buf);
+	kfree_skb(*headbuf);
+	*buf = *headbuf = NULL;
+	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 append to
+ *
+ * Return: the number of 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;
+	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;
+
+	do {
+		if (!skb || skb->len >= mss) {
+			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;
+		}
+		hdr = buf_msg(skb);
+		curr = msg_blocks(hdr);
+		mlen = msg_size(hdr);
+		cpy = min_t(size_t, 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;
+	} while (rem > 0);
+	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
+ * as much data as the header indicates it should.  The routine also ensures
+ * that the entire message header is stored in the main fragment of the message
+ * buffer, to simplify future access to message header fields.
+ *
+ * Note: Having extra info present in the message header or data areas is OK.
+ * TIPC will ignore the excess, under the assumption that it is optional info
+ * introduced by a later release of the protocol.
+ */
+bool tipc_msg_validate(struct sk_buff **_skb)
+{
+	struct sk_buff *skb = *_skb;
+	struct tipc_msg *hdr;
+	int msz, hsz;
+
+	/* Ensure that flow control ratio condition is satisfied */
+	if (unlikely(skb->truesize / buf_roundup_len(skb) >= 4)) {
+		skb = skb_copy_expand(skb, BUF_HEADROOM, 0, GFP_ATOMIC);
+		if (!skb)
+			return false;
+		kfree_skb(*_skb);
+		*_skb = skb;
+	}
+
+	if (unlikely(TIPC_SKB_CB(skb)->validated))
+		return true;
+
+	if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE)))
+		return false;
+
+	hsz = msg_hdr_sz(buf_msg(skb));
+	if (unlikely(hsz < MIN_H_SIZE) || (hsz > MAX_H_SIZE))
+		return false;
+	if (unlikely(!pskb_may_pull(skb, hsz)))
+		return false;
+
+	hdr = buf_msg(skb);
+	if (unlikely(msg_version(hdr) != TIPC_VERSION))
+		return false;
+
+	msz = msg_size(hdr);
+	if (unlikely(msz < hsz))
+		return false;
+	if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE))
+		return false;
+	if (unlikely(skb->len < msz))
+		return false;
+
+	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
+ *
+ * Return: 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
+ * @offset: buffer offset for fragmented messages (FIXME)
+ * @dsz: Total length of user data
+ * @pktmax: Max packet size that can be used
+ * @list: Buffer or chain of buffers to be returned to caller
+ *
+ * Note that the recursive call we are making here is safe, since it can
+ * logically go only one further level down.
+ *
+ * Return: message data size or errno: -ENOMEM, -EFAULT
+ */
+int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
+		   int dsz, int pktmax, struct sk_buff_head *list)
+{
+	int mhsz = msg_hdr_sz(mhdr);
+	struct tipc_msg pkthdr;
+	int msz = mhsz + dsz;
+	int pktrem = pktmax;
+	struct sk_buff *skb;
+	int drem = dsz;
+	int pktno = 1;
+	char *pktpos;
+	int pktsz;
+	int rc;
+
+	msg_set_size(mhdr, msz);
+
+	/* No fragmentation needed? */
+	if (likely(msz <= pktmax)) {
+		skb = tipc_buf_acquire(msz, GFP_KERNEL);
+
+		/* Fall back to smaller MTU if node local message */
+		if (unlikely(!skb)) {
+			if (pktmax != MAX_MSG_SIZE)
+				return -ENOMEM;
+			rc = tipc_msg_build(mhdr, m, offset, dsz,
+					    one_page_mtu, list);
+			if (rc != dsz)
+				return rc;
+			if (tipc_msg_assemble(list))
+				return dsz;
+			return -ENOMEM;
+		}
+		skb_orphan(skb);
+		__skb_queue_tail(list, skb);
+		skb_copy_to_linear_data(skb, mhdr, mhsz);
+		pktpos = skb->data + mhsz;
+		if (copy_from_iter_full(pktpos, dsz, &m->msg_iter))
+			return dsz;
+		rc = -EFAULT;
+		goto error;
+	}
+
+	/* Prepare reusable fragment header */
+	tipc_msg_init(msg_prevnode(mhdr), &pkthdr, MSG_FRAGMENTER,
+		      FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr));
+	msg_set_size(&pkthdr, pktmax);
+	msg_set_fragm_no(&pkthdr, pktno);
+	msg_set_importance(&pkthdr, msg_importance(mhdr));
+
+	/* Prepare first fragment */
+	skb = tipc_buf_acquire(pktmax, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_orphan(skb);
+	__skb_queue_tail(list, skb);
+	pktpos = skb->data;
+	skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
+	pktpos += INT_H_SIZE;
+	pktrem -= INT_H_SIZE;
+	skb_copy_to_linear_data_offset(skb, INT_H_SIZE, mhdr, mhsz);
+	pktpos += mhsz;
+	pktrem -= mhsz;
+
+	do {
+		if (drem < pktrem)
+			pktrem = drem;
+
+		if (!copy_from_iter_full(pktpos, pktrem, &m->msg_iter)) {
+			rc = -EFAULT;
+			goto error;
+		}
+		drem -= pktrem;
+
+		if (!drem)
+			break;
+
+		/* Prepare new fragment: */
+		if (drem < (pktmax - INT_H_SIZE))
+			pktsz = drem + INT_H_SIZE;
+		else
+			pktsz = pktmax;
+		skb = tipc_buf_acquire(pktsz, GFP_KERNEL);
+		if (!skb) {
+			rc = -ENOMEM;
+			goto error;
+		}
+		skb_orphan(skb);
+		__skb_queue_tail(list, skb);
+		msg_set_type(&pkthdr, FRAGMENT);
+		msg_set_size(&pkthdr, pktsz);
+		msg_set_fragm_no(&pkthdr, ++pktno);
+		skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
+		pktpos = skb->data + INT_H_SIZE;
+		pktrem = pktsz - INT_H_SIZE;
+
+	} while (1);
+	msg_set_type(buf_msg(skb), LAST_FRAGMENT);
+	return dsz;
+error:
+	__skb_queue_purge(list);
+	__skb_queue_head_init(list);
+	return rc;
+}
+
+/**
+ * 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
+ *
+ * Return: "true" if bundling has been performed, otherwise "false"
+ */
+static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg,
+			    u32 max)
+{
+	struct tipc_msg *bmsg = buf_msg(bskb);
+	u32 msz, bsz, offset, pad;
+
+	msz = msg_size(msg);
+	bsz = msg_size(bmsg);
+	offset = BUF_ALIGN(bsz);
+	pad = offset - bsz;
+
+	if (unlikely(skb_tailroom(bskb) < (pad + msz)))
+		return false;
+	if (unlikely(max < (offset + msz)))
+		return false;
+
+	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 (msg_user(msg) == TUNNEL_PROTOCOL)
+		return false;
+	if (msg_user(msg) == BCAST_PROTOCOL)
+		return false;
+	if (mss <= INT_H_SIZE + msg_size(msg))
+		return false;
+
+	/* 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 < BUF_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;
+}
+
+/**
+ *  tipc_msg_extract(): extract bundled inner packet from buffer
+ *  @skb: buffer to be extracted from.
+ *  @iskb: extracted inner buffer, to be returned
+ *  @pos: position in outer message of msg to be extracted.
+ *  Returns position of next msg.
+ *  Consumes outer buffer when last packet extracted
+ *  Return: true when there is an extracted buffer, otherwise false
+ */
+bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
+{
+	struct tipc_msg *hdr, *ihdr;
+	int imsz;
+
+	*iskb = NULL;
+	if (unlikely(skb_linearize(skb)))
+		goto none;
+
+	hdr = buf_msg(skb);
+	if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE)))
+		goto none;
+
+	ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos);
+	imsz = msg_size(ihdr);
+
+	if ((*pos + imsz) > msg_data_sz(hdr))
+		goto none;
+
+	*iskb = tipc_buf_acquire(imsz, GFP_ATOMIC);
+	if (!*iskb)
+		goto none;
+
+	skb_copy_to_linear_data(*iskb, ihdr, imsz);
+	if (unlikely(!tipc_msg_validate(iskb)))
+		goto none;
+
+	*pos += BUF_ALIGN(imsz);
+	return true;
+none:
+	kfree_skb(skb);
+	kfree_skb(*iskb);
+	*iskb = NULL;
+	return false;
+}
+
+/**
+ * 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
+ * @err:  error code to be set in message, if any
+ * Replaces consumed buffer with new one when successful
+ * Return: true if success, otherwise false
+ */
+bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
+{
+	struct sk_buff *_skb = *skb;
+	struct tipc_msg *_hdr, *hdr;
+	int hlen, dlen;
+
+	if (skb_linearize(_skb))
+		goto exit;
+	_hdr = buf_msg(_skb);
+	dlen = min_t(uint, msg_data_sz(_hdr), MAX_FORWARD_SIZE);
+	hlen = msg_hdr_sz(_hdr);
+
+	if (msg_dest_droppable(_hdr))
+		goto exit;
+	if (msg_errcode(_hdr))
+		goto exit;
+
+	/* Never return SHORT header */
+	if (hlen == SHORT_H_SIZE)
+		hlen = BASIC_H_SIZE;
+
+	/* Don't return data along with SYN+, - sender has a clone */
+	if (msg_is_syn(_hdr) && err == TIPC_ERR_OVERLOAD)
+		dlen = 0;
+
+	/* Allocate new buffer to return */
+	*skb = tipc_buf_acquire(hlen + dlen, GFP_ATOMIC);
+	if (!*skb)
+		goto exit;
+	memcpy((*skb)->data, _skb->data, msg_hdr_sz(_hdr));
+	memcpy((*skb)->data + hlen, msg_data(_hdr), dlen);
+
+	/* Build reverse header in new buffer */
+	hdr = buf_msg(*skb);
+	msg_set_hdr_sz(hdr, hlen);
+	msg_set_errcode(hdr, err);
+	msg_set_non_seq(hdr, 0);
+	msg_set_origport(hdr, msg_destport(_hdr));
+	msg_set_destport(hdr, msg_origport(_hdr));
+	msg_set_destnode(hdr, msg_prevnode(_hdr));
+	msg_set_prevnode(hdr, own_node);
+	msg_set_orignode(hdr, own_node);
+	msg_set_size(hdr, hlen + dlen);
+	skb_orphan(_skb);
+	kfree_skb(_skb);
+	return true;
+exit:
+	kfree_skb(_skb);
+	*skb = NULL;
+	return false;
+}
+
+bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy)
+{
+	struct sk_buff *skb, *_skb;
+
+	skb_queue_walk(msg, skb) {
+		_skb = skb_clone(skb, GFP_ATOMIC);
+		if (!_skb) {
+			__skb_queue_purge(cpy);
+			pr_err_ratelimited("Failed to clone buffer chain\n");
+			return false;
+		}
+		__skb_queue_tail(cpy, _skb);
+	}
+	return true;
+}
+
+/**
+ * tipc_msg_lookup_dest(): try to find new destination for named message
+ * @net: pointer to associated network namespace
+ * @skb: the buffer containing the message.
+ * @err: error code to be used by caller if lookup fails
+ * Does not consume buffer
+ * Return: true if a destination is found, false otherwise
+ */
+bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
+{
+	struct tipc_msg *msg = buf_msg(skb);
+	u32 scope = msg_lookup_scope(msg);
+	u32 self = tipc_own_addr(net);
+	u32 inst = msg_nameinst(msg);
+	struct tipc_socket_addr sk;
+	struct tipc_uaddr ua;
+
+	if (!msg_isdata(msg))
+		return false;
+	if (!msg_named(msg))
+		return false;
+	if (msg_errcode(msg))
+		return false;
+	*err = TIPC_ERR_NO_NAME;
+	if (skb_linearize(skb))
+		return false;
+	msg = buf_msg(skb);
+	if (msg_reroute_cnt(msg))
+		return false;
+	tipc_uaddr(&ua, TIPC_SERVICE_RANGE, scope,
+		   msg_nametype(msg), inst, inst);
+	sk.node = tipc_scope2node(net, scope);
+	if (!tipc_nametbl_lookup_anycast(net, &ua, &sk))
+		return false;
+	msg_incr_reroute_cnt(msg);
+	if (sk.node != self)
+		msg_set_prevnode(msg, self);
+	msg_set_destnode(msg, sk.node);
+	msg_set_destport(msg, sk.ref);
+	*err = TIPC_OK;
+
+	return true;
+}
+
+/* tipc_msg_assemble() - assemble chain of fragments into one message
+ */
+bool tipc_msg_assemble(struct sk_buff_head *list)
+{
+	struct sk_buff *skb, *tmp = NULL;
+
+	if (skb_queue_len(list) == 1)
+		return true;
+
+	while ((skb = __skb_dequeue(list))) {
+		skb->next = NULL;
+		if (tipc_buf_append(&tmp, &skb)) {
+			__skb_queue_tail(list, skb);
+			return true;
+		}
+		if (!tmp)
+			break;
+	}
+	__skb_queue_purge(list);
+	__skb_queue_head_init(list);
+	pr_warn("Failed do assemble buffer\n");
+	return false;
+}
+
+/* tipc_msg_reassemble() - clone a buffer chain of fragments and
+ *                         reassemble the clones into one message
+ */
+bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq)
+{
+	struct sk_buff *skb, *_skb;
+	struct sk_buff *frag = NULL;
+	struct sk_buff *head = NULL;
+	int hdr_len;
+
+	/* Copy header if single buffer */
+	if (skb_queue_len(list) == 1) {
+		skb = skb_peek(list);
+		hdr_len = skb_headroom(skb) + msg_hdr_sz(buf_msg(skb));
+		_skb = __pskb_copy(skb, hdr_len, GFP_ATOMIC);
+		if (!_skb)
+			return false;
+		__skb_queue_tail(rcvq, _skb);
+		return true;
+	}
+
+	/* Clone all fragments and reassemble */
+	skb_queue_walk(list, skb) {
+		frag = skb_clone(skb, GFP_ATOMIC);
+		if (!frag)
+			goto error;
+		frag->next = NULL;
+		if (tipc_buf_append(&head, &frag))
+			break;
+		if (!head)
+			goto error;
+	}
+	__skb_queue_tail(rcvq, frag);
+	return true;
+error:
+	pr_warn("Failed do clone local mcast rcv buffer\n");
+	kfree_skb(head);
+	return false;
+}
+
+bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg,
+			struct sk_buff_head *cpy)
+{
+	struct sk_buff *skb, *_skb;
+
+	skb_queue_walk(msg, skb) {
+		_skb = pskb_copy(skb, GFP_ATOMIC);
+		if (!_skb) {
+			__skb_queue_purge(cpy);
+			return false;
+		}
+		msg_set_destnode(buf_msg(_skb), dst);
+		__skb_queue_tail(cpy, _skb);
+	}
+	return true;
+}
+
+/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number
+ * @list: list to be appended to
+ * @seqno: sequence number of buffer to add
+ * @skb: buffer to add
+ */
+bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
+			     struct sk_buff *skb)
+{
+	struct sk_buff *_skb, *tmp;
+
+	if (skb_queue_empty(list) || less(seqno, buf_seqno(skb_peek(list)))) {
+		__skb_queue_head(list, skb);
+		return true;
+	}
+
+	if (more(seqno, buf_seqno(skb_peek_tail(list)))) {
+		__skb_queue_tail(list, skb);
+		return true;
+	}
+
+	skb_queue_walk_safe(list, _skb, tmp) {
+		if (more(seqno, buf_seqno(_skb)))
+			continue;
+		if (seqno == buf_seqno(_skb))
+			break;
+		__skb_queue_before(list, _skb, skb);
+		return true;
+	}
+	kfree_skb(skb);
+	return false;
+}
+
+void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
+		     struct sk_buff_head *xmitq)
+{
+	if (tipc_msg_reverse(tipc_own_addr(net), &skb, err))
+		__skb_queue_tail(xmitq, skb);
+}

linux-7.2.3/net/tipc/name_distr.c

@@ -0,0 +1,420 @@
+/*
+ * net/tipc/name_distr.c: TIPC name distribution code
+ *
+ * Copyright (c) 2000-2006, 2014-2019, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * Copyright (c) 2020-2021, Red Hat Inc
+ * 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 "core.h"
+#include "link.h"
+#include "name_distr.h"
+
+int sysctl_tipc_named_timeout __read_mostly = 2000;
+
+/**
+ * publ_to_item - add publication info to a publication message
+ * @p: publication info
+ * @i: location of item in the message
+ */
+static void publ_to_item(struct distr_item *i, struct publication *p)
+{
+	i->type = htonl(p->sr.type);
+	i->lower = htonl(p->sr.lower);
+	i->upper = htonl(p->sr.upper);
+	i->port = htonl(p->sk.ref);
+	i->key = htonl(p->key);
+}
+
+/**
+ * named_prepare_buf - allocate & initialize a publication message
+ * @net: the associated network namespace
+ * @type: message type
+ * @size: payload size
+ * @dest: destination node
+ *
+ * The buffer returned is of size INT_H_SIZE + payload size
+ */
+static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
+					 u32 dest)
+{
+	struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC);
+	u32 self = tipc_own_addr(net);
+	struct tipc_msg *msg;
+
+	if (buf != NULL) {
+		msg = buf_msg(buf);
+		tipc_msg_init(self, msg, NAME_DISTRIBUTOR,
+			      type, INT_H_SIZE, dest);
+		msg_set_size(msg, INT_H_SIZE + size);
+	}
+	return buf;
+}
+
+/**
+ * tipc_named_publish - tell other nodes about a new publication by this node
+ * @net: the associated network namespace
+ * @p: the new publication
+ */
+struct sk_buff *tipc_named_publish(struct net *net, struct publication *p)
+{
+	struct name_table *nt = tipc_name_table(net);
+	struct distr_item *item;
+	struct sk_buff *skb;
+
+	if (p->scope == TIPC_NODE_SCOPE) {
+		list_add_tail_rcu(&p->binding_node, &nt->node_scope);
+		return NULL;
+	}
+	write_lock_bh(&nt->cluster_scope_lock);
+	list_add_tail(&p->binding_node, &nt->cluster_scope);
+	write_unlock_bh(&nt->cluster_scope_lock);
+	skb = named_prepare_buf(net, PUBLICATION, ITEM_SIZE, 0);
+	if (!skb) {
+		pr_warn("Publication distribution failure\n");
+		return NULL;
+	}
+	msg_set_named_seqno(buf_msg(skb), nt->snd_nxt++);
+	msg_set_non_legacy(buf_msg(skb));
+	item = (struct distr_item *)msg_data(buf_msg(skb));
+	publ_to_item(item, p);
+	return skb;
+}
+
+/**
+ * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node
+ * @net: the associated network namespace
+ * @p: the withdrawn publication
+ */
+struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *p)
+{
+	struct name_table *nt = tipc_name_table(net);
+	struct distr_item *item;
+	struct sk_buff *skb;
+
+	write_lock_bh(&nt->cluster_scope_lock);
+	list_del(&p->binding_node);
+	write_unlock_bh(&nt->cluster_scope_lock);
+	if (p->scope == TIPC_NODE_SCOPE)
+		return NULL;
+
+	skb = named_prepare_buf(net, WITHDRAWAL, ITEM_SIZE, 0);
+	if (!skb) {
+		pr_warn("Withdrawal distribution failure\n");
+		return NULL;
+	}
+	msg_set_named_seqno(buf_msg(skb), nt->snd_nxt++);
+	msg_set_non_legacy(buf_msg(skb));
+	item = (struct distr_item *)msg_data(buf_msg(skb));
+	publ_to_item(item, p);
+	return skb;
+}
+
+/**
+ * named_distribute - prepare name info for bulk distribution to another node
+ * @net: the associated network namespace
+ * @list: list of messages (buffers) to be returned from this function
+ * @dnode: node to be updated
+ * @pls: linked list of publication items to be packed into buffer chain
+ * @seqno: sequence number for this message
+ */
+static void named_distribute(struct net *net, struct sk_buff_head *list,
+			     u32 dnode, struct list_head *pls, u16 seqno)
+{
+	struct publication *publ;
+	struct sk_buff *skb = NULL;
+	struct distr_item *item = NULL;
+	u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0, false) - INT_H_SIZE) /
+			ITEM_SIZE) * ITEM_SIZE;
+	u32 msg_rem = msg_dsz;
+	struct tipc_msg *hdr;
+
+	list_for_each_entry(publ, pls, binding_node) {
+		/* Prepare next buffer: */
+		if (!skb) {
+			skb = named_prepare_buf(net, PUBLICATION, msg_rem,
+						dnode);
+			if (!skb) {
+				pr_warn("Bulk publication failure\n");
+				return;
+			}
+			hdr = buf_msg(skb);
+			msg_set_bc_ack_invalid(hdr, true);
+			msg_set_bulk(hdr);
+			msg_set_non_legacy(hdr);
+			item = (struct distr_item *)msg_data(hdr);
+		}
+
+		/* Pack publication into message: */
+		publ_to_item(item, publ);
+		item++;
+		msg_rem -= ITEM_SIZE;
+
+		/* Append full buffer to list: */
+		if (!msg_rem) {
+			__skb_queue_tail(list, skb);
+			skb = NULL;
+			msg_rem = msg_dsz;
+		}
+	}
+	if (skb) {
+		hdr = buf_msg(skb);
+		msg_set_size(hdr, INT_H_SIZE + (msg_dsz - msg_rem));
+		skb_trim(skb, INT_H_SIZE + (msg_dsz - msg_rem));
+		__skb_queue_tail(list, skb);
+	}
+	hdr = buf_msg(skb_peek_tail(list));
+	msg_set_last_bulk(hdr);
+	msg_set_named_seqno(hdr, seqno);
+}
+
+/**
+ * tipc_named_node_up - tell specified node about all publications by this node
+ * @net: the associated network namespace
+ * @dnode: destination node
+ * @capabilities: peer node's capabilities
+ */
+void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities)
+{
+	struct name_table *nt = tipc_name_table(net);
+	struct tipc_net *tn = tipc_net(net);
+	struct sk_buff_head head;
+	u16 seqno;
+
+	__skb_queue_head_init(&head);
+	spin_lock_bh(&tn->nametbl_lock);
+	if (!(capabilities & TIPC_NAMED_BCAST))
+		nt->rc_dests++;
+	seqno = nt->snd_nxt;
+	spin_unlock_bh(&tn->nametbl_lock);
+
+	read_lock_bh(&nt->cluster_scope_lock);
+	named_distribute(net, &head, dnode, &nt->cluster_scope, seqno);
+	tipc_node_xmit(net, &head, dnode, 0);
+	read_unlock_bh(&nt->cluster_scope_lock);
+}
+
+/**
+ * tipc_publ_purge - remove publication associated with a failed node
+ * @net: the associated network namespace
+ * @p: the publication to remove
+ * @addr: failed node's address
+ *
+ * Invoked for each publication issued by a newly failed node.
+ * Removes publication structure from name table & deletes it.
+ */
+static void tipc_publ_purge(struct net *net, struct publication *p, u32 addr)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct publication *_p;
+	struct tipc_uaddr ua;
+
+	tipc_uaddr(&ua, TIPC_SERVICE_RANGE, p->scope, p->sr.type,
+		   p->sr.lower, p->sr.upper);
+	spin_lock_bh(&tn->nametbl_lock);
+	_p = tipc_nametbl_remove_publ(net, &ua, &p->sk, p->key);
+	if (_p)
+		tipc_node_unsubscribe(net, &_p->binding_node, addr);
+	spin_unlock_bh(&tn->nametbl_lock);
+	if (_p)
+		kfree_rcu(_p, rcu);
+}
+
+void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
+		      u32 addr, u16 capabilities)
+{
+	struct name_table *nt = tipc_name_table(net);
+	struct tipc_net *tn = tipc_net(net);
+
+	struct publication *publ, *tmp;
+
+	list_for_each_entry_safe(publ, tmp, nsub_list, binding_node)
+		tipc_publ_purge(net, publ, addr);
+	spin_lock_bh(&tn->nametbl_lock);
+	if (!(capabilities & TIPC_NAMED_BCAST))
+		nt->rc_dests--;
+	spin_unlock_bh(&tn->nametbl_lock);
+}
+
+/**
+ * tipc_update_nametbl - try to process a nametable update and notify
+ *			 subscribers
+ * @net: the associated network namespace
+ * @i: location of item in the message
+ * @node: node address
+ * @dtype: name distributor message type
+ *
+ * tipc_nametbl_lock must be held.
+ * Return: the publication item if successful, otherwise NULL.
+ */
+static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
+				u32 node, u32 dtype)
+{
+	struct publication *p = NULL;
+	u32 lower = ntohl(i->lower);
+	u32 upper = ntohl(i->upper);
+	struct tipc_socket_addr sk;
+	u32 key = ntohl(i->key);
+	struct tipc_uaddr ua;
+
+	/* A peer-advertised binding with lower > upper can never be matched
+	 * or withdrawn and would leak the publication; the local bind path
+	 * rejects such ranges, so reject ranges learned from the network too.
+	 */
+	if (lower > upper)
+		return false;
+
+	tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE,
+		   ntohl(i->type), lower, upper);
+	sk.ref = ntohl(i->port);
+	sk.node = node;
+
+	if (dtype == PUBLICATION) {
+		p = tipc_nametbl_insert_publ(net, &ua, &sk, key);
+		if (p) {
+			tipc_node_subscribe(net, &p->binding_node, node);
+			return true;
+		}
+	} else if (dtype == WITHDRAWAL) {
+		p = tipc_nametbl_remove_publ(net, &ua, &sk, key);
+		if (p) {
+			tipc_node_unsubscribe(net, &p->binding_node, node);
+			kfree_rcu(p, rcu);
+			return true;
+		}
+		pr_warn_ratelimited("Failed to remove binding %u,%u from %u\n",
+				    ua.sr.type, ua.sr.lower, node);
+	} else {
+		pr_warn_ratelimited("Unknown name table message received\n");
+	}
+	return false;
+}
+
+static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq,
+					  u16 *rcv_nxt, bool *open)
+{
+	struct sk_buff *skb, *tmp;
+	struct tipc_msg *hdr;
+	u16 seqno;
+
+	spin_lock_bh(&namedq->lock);
+	skb_queue_walk_safe(namedq, skb, tmp) {
+		if (unlikely(skb_linearize(skb))) {
+			__skb_unlink(skb, namedq);
+			kfree_skb(skb);
+			continue;
+		}
+		hdr = buf_msg(skb);
+		seqno = msg_named_seqno(hdr);
+		if (msg_is_last_bulk(hdr)) {
+			*rcv_nxt = seqno;
+			*open = true;
+		}
+
+		if (msg_is_bulk(hdr) || msg_is_legacy(hdr)) {
+			__skb_unlink(skb, namedq);
+			spin_unlock_bh(&namedq->lock);
+			return skb;
+		}
+
+		if (*open && (*rcv_nxt == seqno)) {
+			(*rcv_nxt)++;
+			__skb_unlink(skb, namedq);
+			spin_unlock_bh(&namedq->lock);
+			return skb;
+		}
+
+		if (less(seqno, *rcv_nxt)) {
+			__skb_unlink(skb, namedq);
+			kfree_skb(skb);
+			continue;
+		}
+	}
+	spin_unlock_bh(&namedq->lock);
+	return NULL;
+}
+
+/**
+ * tipc_named_rcv - process name table update messages sent by another node
+ * @net: the associated network namespace
+ * @namedq: queue to receive from
+ * @rcv_nxt: store last received seqno here
+ * @open: last bulk msg was received (FIXME)
+ */
+void tipc_named_rcv(struct net *net, struct sk_buff_head *namedq,
+		    u16 *rcv_nxt, bool *open)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct distr_item *item;
+	struct tipc_msg *hdr;
+	struct sk_buff *skb;
+	u32 count, node;
+
+	spin_lock_bh(&tn->nametbl_lock);
+	while ((skb = tipc_named_dequeue(namedq, rcv_nxt, open))) {
+		hdr = buf_msg(skb);
+		node = msg_orignode(hdr);
+		item = (struct distr_item *)msg_data(hdr);
+		count = msg_data_sz(hdr) / ITEM_SIZE;
+		while (count--) {
+			tipc_update_nametbl(net, item, node, msg_type(hdr));
+			item++;
+		}
+		kfree_skb(skb);
+	}
+	spin_unlock_bh(&tn->nametbl_lock);
+}
+
+/**
+ * tipc_named_reinit - re-initialize local publications
+ * @net: the associated network namespace
+ *
+ * This routine is called whenever TIPC networking is enabled.
+ * All name table entries published by this node are updated to reflect
+ * the node's new network address.
+ */
+void tipc_named_reinit(struct net *net)
+{
+	struct name_table *nt = tipc_name_table(net);
+	struct tipc_net *tn = tipc_net(net);
+	struct publication *p;
+	u32 self = tipc_own_addr(net);
+
+	spin_lock_bh(&tn->nametbl_lock);
+
+	list_for_each_entry_rcu(p, &nt->node_scope, binding_node)
+		p->sk.node = self;
+	list_for_each_entry_rcu(p, &nt->cluster_scope, binding_node)
+		p->sk.node = self;
+	nt->rc_dests = 0;
+	spin_unlock_bh(&tn->nametbl_lock);
+}

linux-7.2.3/net/tipc/name_distr.h

@@ -0,0 +1,79 @@
+/*
+ * net/tipc/name_distr.h: Include file for TIPC name distribution code
+ *
+ * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2005, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_NAME_DISTR_H
+#define _TIPC_NAME_DISTR_H
+
+#include "name_table.h"
+
+#define ITEM_SIZE sizeof(struct distr_item)
+
+/**
+ * struct distr_item - publication info distributed to other nodes
+ * @type: name sequence type
+ * @lower: name sequence lower bound
+ * @upper: name sequence upper bound
+ * @port: publishing port reference
+ * @key: publication key
+ *
+ * ===> All fields are stored in network byte order. <===
+ *
+ * First 3 fields identify (name or) name sequence being published.
+ * Reference field uniquely identifies port that published name sequence.
+ * Key field uniquely identifies publication, in the event a port has
+ * multiple publications of the same name sequence.
+ *
+ * Note: There is no field that identifies the publishing node because it is
+ * the same for all items contained within a publication message.
+ */
+struct distr_item {
+	__be32 type;
+	__be32 lower;
+	__be32 upper;
+	__be32 port;
+	__be32 key;
+};
+
+struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ);
+struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ);
+void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities);
+void tipc_named_rcv(struct net *net, struct sk_buff_head *namedq,
+		    u16 *rcv_nxt, bool *open);
+void tipc_named_reinit(struct net *net);
+void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
+		      u32 addr, u16 capabilities);
+
+#endif

linux-7.2.3/net/tipc/name_table.h

@@ -0,0 +1,157 @@
+/*
+ * net/tipc/name_table.h: Include file for TIPC name table code
+ *
+ * Copyright (c) 2000-2006, 2014-2018, Ericsson AB
+ * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
+ * Copyright (c) 2020-2021, Red Hat Inc
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_NAME_TABLE_H
+#define _TIPC_NAME_TABLE_H
+
+struct tipc_subscription;
+struct tipc_plist;
+struct tipc_nlist;
+struct tipc_group;
+struct tipc_uaddr;
+
+/*
+ * TIPC name types reserved for internal TIPC use (both current and planned)
+ */
+#define TIPC_ZM_SRV		3	/* zone master service name type */
+#define TIPC_PUBL_SCOPE_NUM	(TIPC_NODE_SCOPE + 1)
+#define TIPC_NAMETBL_SIZE	1024	/* must be a power of 2 */
+
+#define TIPC_ANY_SCOPE 10      /* Both node and cluster scope will match */
+
+/**
+ * struct publication - info about a published service address or range
+ * @sr: service range represented by this publication
+ * @sk: address of socket bound to this publication
+ * @scope: scope of publication, TIPC_NODE_SCOPE or TIPC_CLUSTER_SCOPE
+ * @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
+ * - Local/node scope publications: in name_table->node_scope list
+ * - Local/cluster scope publications: in name_table->cluster_scope list
+ * @binding_sock: all publications from the same socket which bound this one
+ *   Used by socket to withdraw publications when socket is unbound/released
+ * @local_publ: list of identical publications made from this node
+ *   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 {
+	struct tipc_service_range sr;
+	struct tipc_socket_addr sk;
+	u16 scope;
+	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;
+};
+
+/**
+ * struct name_table - table containing all existing port name publications
+ * @rcu: RCU callback head used for deferred freeing
+ * @services: name sequence hash lists
+ * @node_scope: all local publications with node scope
+ *               - used by name_distr during re-init of name table
+ * @cluster_scope: all local publications with cluster scope
+ *               - used by name_distr to send bulk updates to new nodes
+ *               - used by name_distr during re-init of name table
+ * @cluster_scope_lock: lock for accessing @cluster_scope
+ * @local_publ_count: number of publications issued by this node
+ * @rc_dests: destination node counter
+ * @snd_nxt: next sequence number to be used
+ */
+struct name_table {
+	struct rcu_head rcu;
+	struct hlist_head services[TIPC_NAMETBL_SIZE];
+	struct list_head node_scope;
+	struct list_head cluster_scope;
+	rwlock_t cluster_scope_lock;
+	u32 local_publ_count;
+	u32 rc_dests;
+	u32 snd_nxt;
+};
+
+int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb);
+bool tipc_nametbl_lookup_anycast(struct net *net, struct tipc_uaddr *ua,
+				 struct tipc_socket_addr *sk);
+void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua,
+				       struct list_head *dports);
+void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua,
+				     struct tipc_nlist *nodes);
+bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua,
+			       struct list_head *dsts, int *dstcnt,
+			       u32 exclude, bool mcast);
+void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp,
+			      struct tipc_uaddr *ua);
+struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua,
+					 struct tipc_socket_addr *sk, u32 key);
+void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua,
+			   struct tipc_socket_addr *sk, u32 key);
+struct publication *tipc_nametbl_insert_publ(struct net *net,
+					     struct tipc_uaddr *ua,
+					     struct tipc_socket_addr *sk,
+					     u32 key);
+struct publication *tipc_nametbl_remove_publ(struct net *net,
+					     struct tipc_uaddr *ua,
+					     struct tipc_socket_addr *sk,
+					     u32 key);
+bool tipc_nametbl_subscribe(struct tipc_subscription *s);
+void tipc_nametbl_unsubscribe(struct tipc_subscription *s);
+int tipc_nametbl_init(struct net *net);
+void tipc_nametbl_stop(struct net *net);
+
+struct tipc_dest {
+	struct list_head list;
+	u32 port;
+	u32 node;
+};
+
+struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port);
+bool tipc_dest_push(struct list_head *l, u32 node, u32 port);
+bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port);
+bool tipc_dest_del(struct list_head *l, u32 node, u32 port);
+void tipc_dest_list_purge(struct list_head *l);
+
+#endif

linux-7.2.3/net/tipc/net.c

@@ -0,0 +1,347 @@
+/*
+ * net/tipc/net.c: TIPC network routing code
+ *
+ * Copyright (c) 1995-2006, 2014, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * 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 "core.h"
+#include "net.h"
+#include "name_distr.h"
+#include "subscr.h"
+#include "socket.h"
+#include "node.h"
+#include "bcast.h"
+#include "link.h"
+#include "netlink.h"
+#include "monitor.h"
+
+/*
+ * The TIPC locking policy is designed to ensure a very fine locking
+ * granularity, permitting complete parallel access to individual
+ * port and node/link instances. The code consists of four major
+ * locking domains, each protected with their own disjunct set of locks.
+ *
+ * 1: The bearer level.
+ *    RTNL lock is used to serialize the process of configuring bearer
+ *    on update side, and RCU lock is applied on read side to make
+ *    bearer instance valid on both paths of message transmission and
+ *    reception.
+ *
+ * 2: The node and link level.
+ *    All node instances are saved into two tipc_node_list and node_htable
+ *    lists. The two lists are protected by node_list_lock on write side,
+ *    and they are guarded with RCU lock on read side. Especially node
+ *    instance is destroyed only when TIPC module is removed, and we can
+ *    confirm that there has no any user who is accessing the node at the
+ *    moment. Therefore, Except for iterating the two lists within RCU
+ *    protection, it's no needed to hold RCU that we access node instance
+ *    in other places.
+ *
+ *    In addition, all members in node structure including link instances
+ *    are protected by node spin lock.
+ *
+ * 3: The transport level of the protocol.
+ *    This consists of the structures port, (and its user level
+ *    representations, such as user_port and tipc_sock), reference and
+ *    tipc_user (port.c, reg.c, socket.c).
+ *
+ *    This layer has four different locks:
+ *     - The tipc_port spin_lock. This is protecting each port instance
+ *       from parallel data access and removal. Since we can not place
+ *       this lock in the port itself, it has been placed in the
+ *       corresponding reference table entry, which has the same life
+ *       cycle as the module. This entry is difficult to access from
+ *       outside the TIPC core, however, so a pointer to the lock has
+ *       been added in the port instance, -to be used for unlocking
+ *       only.
+ *     - A read/write lock to protect the reference table itself (teg.c).
+ *       (Nobody is using read-only access to this, so it can just as
+ *       well be changed to a spin_lock)
+ *     - A spin lock to protect the registry of kernel/driver users (reg.c)
+ *     - A global spin_lock (tipc_port_lock), which only task is to ensure
+ *       consistency where more than one port is involved in an operation,
+ *       i.e., when a port is part of a linked list of ports.
+ *       There are two such lists; 'port_list', which is used for management,
+ *       and 'wait_list', which is used to queue ports during congestion.
+ *
+ *  4: The name table (name_table.c, name_distr.c, subscription.c)
+ *     - There is one big read/write-lock (tipc_nametbl_lock) protecting the
+ *       overall name table structure. Nothing must be added/removed to
+ *       this structure without holding write access to it.
+ *     - There is one local spin_lock per sub_sequence, which can be seen
+ *       as a sub-domain to the tipc_nametbl_lock domain. It is used only
+ *       for translation operations, and is needed because a translation
+ *       steps the root of the 'publication' linked list between each lookup.
+ *       This is always used within the scope of a tipc_nametbl_lock(read).
+ *     - A local spin_lock protecting the queue of subscriber events.
+*/
+
+static void tipc_net_finalize(struct net *net, u32 addr);
+
+int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
+{
+	if (tipc_own_id(net)) {
+		pr_info("Cannot configure node identity twice\n");
+		return -1;
+	}
+	pr_info("Started in network mode\n");
+
+	if (node_id)
+		tipc_set_node_id(net, node_id);
+	if (addr)
+		tipc_net_finalize(net, addr);
+	return 0;
+}
+
+static void tipc_net_finalize(struct net *net, u32 addr)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_socket_addr sk = {0, addr};
+	struct tipc_uaddr ua;
+
+	tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE,
+		   TIPC_NODE_STATE, addr, addr);
+
+	if (cmpxchg(&tn->node_addr, 0, addr))
+		return;
+	tipc_set_node_addr(net, addr);
+	tipc_named_reinit(net);
+	tipc_sk_reinit(net);
+	tipc_mon_reinit_self(net);
+	tipc_nametbl_publish(net, &ua, &sk, addr);
+}
+
+void tipc_net_finalize_work(struct work_struct *work)
+{
+	struct tipc_net *tn = container_of(work, struct tipc_net, work);
+
+	rtnl_lock();
+	tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr);
+	rtnl_unlock();
+}
+
+void tipc_net_stop(struct net *net)
+{
+	if (!tipc_own_id(net))
+		return;
+
+	rtnl_lock();
+	tipc_bearer_stop(net);
+	tipc_node_stop(net);
+	rtnl_unlock();
+
+	pr_info("Left network mode\n");
+}
+
+static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg)
+{
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	u64 *w0 = (u64 *)&tn->node_id[0];
+	u64 *w1 = (u64 *)&tn->node_id[8];
+	struct nlattr *attrs;
+	void *hdr;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  NLM_F_MULTI, TIPC_NL_NET_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET);
+	if (!attrs)
+		goto msg_full;
+
+	if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id))
+		goto attr_msg_full;
+	if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID, *w0, 0))
+		goto attr_msg_full;
+	if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID_W1, *w1, 0))
+		goto attr_msg_full;
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	int err;
+	int done = cb->args[0];
+	struct tipc_nl_msg msg;
+
+	if (done)
+		return 0;
+
+	msg.skb = skb;
+	msg.portid = NETLINK_CB(cb->skb).portid;
+	msg.seq = cb->nlh->nlmsg_seq;
+
+	err = __tipc_nl_add_net(net, &msg);
+	if (err)
+		goto out;
+
+	done = 1;
+out:
+	cb->args[0] = done;
+
+	return skb->len;
+}
+
+int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *attrs[TIPC_NLA_NET_MAX + 1];
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = tipc_net(net);
+	int err;
+
+	if (!info->attrs[TIPC_NLA_NET])
+		return -EINVAL;
+
+	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;
+
+	/* Can't change net id once TIPC has joined a network */
+	if (tipc_own_addr(net))
+		return -EPERM;
+
+	if (attrs[TIPC_NLA_NET_ID]) {
+		u32 val;
+
+		val = nla_get_u32(attrs[TIPC_NLA_NET_ID]);
+		if (val < 1 || val > 9999)
+			return -EINVAL;
+
+		tn->net_id = val;
+	}
+
+	if (attrs[TIPC_NLA_NET_ADDR]) {
+		u32 addr;
+
+		addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]);
+		if (!addr)
+			return -EINVAL;
+		tn->legacy_addr_format = true;
+		tipc_net_init(net, NULL, addr);
+	}
+
+	if (attrs[TIPC_NLA_NET_NODEID]) {
+		u8 node_id[NODE_ID_LEN];
+		u64 *w0 = (u64 *)&node_id[0];
+		u64 *w1 = (u64 *)&node_id[8];
+
+		if (!attrs[TIPC_NLA_NET_NODEID_W1])
+			return -EINVAL;
+		*w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]);
+		*w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]);
+		tipc_net_init(net, node_id, 0);
+	}
+	return 0;
+}
+
+int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+
+	rtnl_lock();
+	err = __tipc_nl_net_set(skb, info);
+	rtnl_unlock();
+
+	return err;
+}
+
+static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct nlattr *attrs;
+	void *hdr;
+
+	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
+			  0, TIPC_NL_ADDR_LEGACY_GET);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	attrs = nla_nest_start(msg->skb, TIPC_NLA_NET);
+	if (!attrs)
+		goto msg_full;
+
+	if (tn->legacy_addr_format)
+		if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY))
+			goto attr_msg_full;
+
+	nla_nest_end(msg->skb, attrs);
+	genlmsg_end(msg->skb, hdr);
+
+	return 0;
+
+attr_msg_full:
+	nla_nest_cancel(msg->skb, attrs);
+msg_full:
+	genlmsg_cancel(msg->skb, hdr);
+
+	return -EMSGSIZE;
+}
+
+int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = sock_net(skb->sk);
+	struct tipc_nl_msg msg;
+	struct sk_buff *rep;
+	int err;
+
+	rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	msg.skb = rep;
+	msg.portid = info->snd_portid;
+	msg.seq = info->snd_seq;
+
+	err = __tipc_nl_addr_legacy_get(net, &msg);
+	if (err) {
+		nlmsg_free(msg.skb);
+		return err;
+	}
+
+	return genlmsg_reply(msg.skb, info);
+}

linux-7.2.3/net/tipc/net.h

@@ -0,0 +1,52 @@
+/*
+ * net/tipc/net.h: Include file for TIPC network routing code
+ *
+ * Copyright (c) 1995-2006, 2014, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_NET_H
+#define _TIPC_NET_H
+
+#include <net/genetlink.h>
+
+extern const struct nla_policy tipc_nl_net_policy[];
+
+int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
+void tipc_net_finalize_work(struct work_struct *work);
+void tipc_net_stop(struct net *net);
+int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
+int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info);
+
+#endif

linux-7.2.3/net/tipc/netlink.c

@@ -0,0 +1,331 @@
+/*
+ * net/tipc/netlink.c: TIPC configuration handling
+ *
+ * Copyright (c) 2005-2006, 2014, Ericsson AB
+ * Copyright (c) 2005-2007, Wind River Systems
+ * 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 "core.h"
+#include "socket.h"
+#include "name_table.h"
+#include "bearer.h"
+#include "link.h"
+#include "node.h"
+#include "net.h"
+#include "udp_media.h"
+#include <net/genetlink.h>
+
+static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = {
+	[TIPC_NLA_UNSPEC]	= { .type = NLA_UNSPEC, },
+	[TIPC_NLA_BEARER]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_SOCK]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_PUBL]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_LINK]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_MEDIA]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_NODE]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_NET]		= { .type = NLA_NESTED, },
+	[TIPC_NLA_NAME_TABLE]	= { .type = NLA_NESTED, },
+	[TIPC_NLA_MON]		= { .type = NLA_NESTED, },
+};
+
+const struct nla_policy
+tipc_nl_name_table_policy[TIPC_NLA_NAME_TABLE_MAX + 1] = {
+	[TIPC_NLA_NAME_TABLE_UNSPEC]	= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NAME_TABLE_PUBL]	= { .type = NLA_NESTED }
+};
+
+const struct nla_policy tipc_nl_monitor_policy[TIPC_NLA_MON_MAX + 1] = {
+	[TIPC_NLA_MON_UNSPEC]			= { .type = NLA_UNSPEC },
+	[TIPC_NLA_MON_REF]			= { .type = NLA_U32 },
+	[TIPC_NLA_MON_ACTIVATION_THRESHOLD]	= { .type = NLA_U32 },
+};
+
+const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
+	[TIPC_NLA_SOCK_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_SOCK_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_SOCK_REF]		= { .type = NLA_U32 },
+	[TIPC_NLA_SOCK_CON]		= { .type = NLA_NESTED },
+	[TIPC_NLA_SOCK_HAS_PUBL]	= { .type = NLA_FLAG }
+};
+
+const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
+	[TIPC_NLA_NET_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 },
+	[TIPC_NLA_NET_ADDR]		= { .type = NLA_U32 },
+	[TIPC_NLA_NET_NODEID]		= { .type = NLA_U64 },
+	[TIPC_NLA_NET_NODEID_W1]	= { .type = NLA_U64 },
+	[TIPC_NLA_NET_ADDR_LEGACY]	= { .type = NLA_FLAG }
+};
+
+const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
+	[TIPC_NLA_LINK_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_LINK_NAME]		= { .type = NLA_NUL_STRING,
+					    .len = TIPC_MAX_LINK_NAME },
+	[TIPC_NLA_LINK_MTU]		= { .type = NLA_U32 },
+	[TIPC_NLA_LINK_BROADCAST]	= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_UP]		= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_ACTIVE]		= { .type = NLA_FLAG },
+	[TIPC_NLA_LINK_PROP]		= { .type = NLA_NESTED },
+	[TIPC_NLA_LINK_STATS]		= { .type = NLA_NESTED },
+	[TIPC_NLA_LINK_RX]		= { .type = NLA_U32 },
+	[TIPC_NLA_LINK_TX]		= { .type = NLA_U32 }
+};
+
+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_ID]		= { .type = NLA_BINARY,
+					    .len = TIPC_NODEID_LEN},
+	[TIPC_NLA_NODE_KEY]		= { .type = NLA_BINARY,
+					    .len = TIPC_AEAD_KEY_SIZE_MAX},
+	[TIPC_NLA_NODE_KEY_MASTER]	= { .type = NLA_FLAG },
+	[TIPC_NLA_NODE_REKEYING]	= { .type = NLA_U32 },
+};
+
+/* Properties valid for media, bearer and link */
+static const struct netlink_range_validation tipc_nl_mtu_range = {
+	.max = U16_MAX,
+};
+
+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_MTU]		= NLA_POLICY_FULL_RANGE(NLA_U32, &tipc_nl_mtu_range),
+	[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]	= {
+	[TIPC_NLA_BEARER_UNSPEC]	= { .type = NLA_UNSPEC },
+	[TIPC_NLA_BEARER_NAME]		= { .type = NLA_NUL_STRING,
+					    .len = TIPC_MAX_BEARER_NAME },
+	[TIPC_NLA_BEARER_PROP]		= { .type = NLA_NESTED },
+	[TIPC_NLA_BEARER_DOMAIN]	= { .type = NLA_U32 }
+};
+
+const struct nla_policy tipc_nl_media_policy[TIPC_NLA_MEDIA_MAX + 1] = {
+	[TIPC_NLA_MEDIA_UNSPEC]		= { .type = NLA_UNSPEC },
+	[TIPC_NLA_MEDIA_NAME]		= { .type = NLA_STRING },
+	[TIPC_NLA_MEDIA_PROP]		= { .type = NLA_NESTED }
+};
+
+const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = {
+	[TIPC_NLA_UDP_UNSPEC]	= {.type = NLA_UNSPEC},
+	[TIPC_NLA_UDP_LOCAL]	= {.type = NLA_BINARY,
+				   .len = sizeof(struct sockaddr_storage)},
+	[TIPC_NLA_UDP_REMOTE]	= {.type = NLA_BINARY,
+				   .len = sizeof(struct sockaddr_storage)},
+};
+
+/* Users of the legacy API (tipc-config) can't handle that we add operations,
+ * so we have a separate genl handling for the new API.
+ */
+static const struct genl_ops tipc_genl_v2_ops[] = {
+	{
+		.cmd	= TIPC_NL_BEARER_DISABLE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_bearer_disable,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_ENABLE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_bearer_enable,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= tipc_nl_bearer_get,
+		.dumpit	= tipc_nl_bearer_dump,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_ADD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_bearer_add,
+	},
+	{
+		.cmd	= TIPC_NL_BEARER_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_bearer_set,
+	},
+	{
+		.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,
+	},
+	{
+		.cmd	= TIPC_NL_PUBL_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT |
+			    GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit	= tipc_nl_publ_dump,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT,
+		.doit   = tipc_nl_node_get_link,
+		.dumpit	= tipc_nl_node_dump_link,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_node_set_link,
+	},
+	{
+		.cmd	= TIPC_NL_LINK_RESET_STATS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit   = tipc_nl_node_reset_link_stats,
+	},
+	{
+		.cmd	= TIPC_NL_MEDIA_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= tipc_nl_media_get,
+		.dumpit	= tipc_nl_media_dump,
+	},
+	{
+		.cmd	= TIPC_NL_MEDIA_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_media_set,
+	},
+	{
+		.cmd	= TIPC_NL_NODE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.dumpit	= tipc_nl_node_dump,
+	},
+	{
+		.cmd	= TIPC_NL_NET_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.dumpit	= tipc_nl_net_dump,
+	},
+	{
+		.cmd	= TIPC_NL_NET_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_net_set,
+	},
+	{
+		.cmd	= TIPC_NL_NAME_TABLE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.dumpit	= tipc_nl_name_table_dump,
+	},
+	{
+		.cmd	= TIPC_NL_MON_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_node_set_monitor,
+	},
+	{
+		.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,
+	},
+	{
+		.cmd	= TIPC_NL_MON_PEER_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT |
+			    GENL_DONT_VALIDATE_DUMP_STRICT,
+		.dumpit	= tipc_nl_node_dump_monitor_peer,
+	},
+	{
+		.cmd	= TIPC_NL_PEER_REMOVE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_peer_rm,
+	},
+#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,
+	},
+#endif
+#ifdef CONFIG_TIPC_CRYPTO
+	{
+		.cmd	= TIPC_NL_KEY_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_node_set_key,
+	},
+	{
+		.cmd	= TIPC_NL_KEY_FLUSH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= tipc_nl_node_flush_key,
+	},
+#endif
+	{
+		.cmd	= TIPC_NL_ADDR_LEGACY_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= tipc_nl_net_addr_legacy_get,
+	},
+};
+
+struct genl_family tipc_genl_family __ro_after_init = {
+	.name		= TIPC_GENL_V2_NAME,
+	.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),
+	.resv_start_op	= TIPC_NL_ADDR_LEGACY_GET + 1,
+};
+
+int __init tipc_netlink_start(void)
+{
+	int res;
+
+	res = genl_register_family(&tipc_genl_family);
+	if (res) {
+		pr_err("Failed to register netlink interface\n");
+		return res;
+	}
+	return 0;
+}
+
+void tipc_netlink_stop(void)
+{
+	genl_unregister_family(&tipc_genl_family);
+}

linux-7.2.3/net/tipc/netlink.h

@@ -0,0 +1,64 @@
+/*
+ * net/tipc/netlink.h: Include file for TIPC netlink code
+ *
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_NETLINK_H
+#define _TIPC_NETLINK_H
+#include <net/netlink.h>
+
+extern struct genl_family tipc_genl_family;
+
+struct tipc_nl_msg {
+	struct sk_buff *skb;
+	u32 portid;
+	u32 seq;
+};
+
+extern const struct nla_policy tipc_nl_name_table_policy[];
+extern const struct nla_policy tipc_nl_sock_policy[];
+extern const struct nla_policy tipc_nl_net_policy[];
+extern const struct nla_policy tipc_nl_link_policy[];
+extern const struct nla_policy tipc_nl_node_policy[];
+extern const struct nla_policy tipc_nl_prop_policy[];
+extern const struct nla_policy tipc_nl_bearer_policy[];
+extern const struct nla_policy tipc_nl_media_policy[];
+extern const struct nla_policy tipc_nl_udp_policy[];
+extern const struct nla_policy tipc_nl_monitor_policy[];
+
+int tipc_netlink_start(void);
+int tipc_netlink_compat_start(void);
+void tipc_netlink_stop(void);
+void tipc_netlink_compat_stop(void);
+
+#endif

linux-7.2.3/net/tipc/node.h

@@ -0,0 +1,131 @@
+/*
+ * net/tipc/node.h: Include file for TIPC node management routines
+ *
+ * Copyright (c) 2000-2006, 2014-2016, Ericsson AB
+ * Copyright (c) 2005, 2010-2014, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_NODE_H
+#define _TIPC_NODE_H
+
+#include "addr.h"
+#include "net.h"
+#include "bearer.h"
+#include "msg.h"
+
+/* Optional capabilities supported by this code version
+ */
+enum {
+	TIPC_SYN_BIT          = (1),
+	TIPC_BCAST_SYNCH      = (1 << 1),
+	TIPC_BCAST_STATE_NACK = (1 << 2),
+	TIPC_BLOCK_FLOWCTL    = (1 << 3),
+	TIPC_BCAST_RCAST      = (1 << 4),
+	TIPC_NODE_ID128       = (1 << 5),
+	TIPC_LINK_PROTO_SEQNO = (1 << 6),
+	TIPC_MCAST_RBCTL      = (1 << 7),
+	TIPC_GAP_ACK_BLOCK    = (1 << 8),
+	TIPC_TUNNEL_ENHANCED  = (1 << 9),
+	TIPC_NAGLE            = (1 << 10),
+	TIPC_NAMED_BCAST      = (1 << 11)
+};
+
+#define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT           |  \
+				TIPC_BCAST_SYNCH       |   \
+				TIPC_BCAST_STATE_NACK  |   \
+				TIPC_BCAST_RCAST       |   \
+				TIPC_BLOCK_FLOWCTL     |   \
+				TIPC_NODE_ID128        |   \
+				TIPC_LINK_PROTO_SEQNO  |   \
+				TIPC_MCAST_RBCTL       |   \
+				TIPC_GAP_ACK_BLOCK     |   \
+				TIPC_TUNNEL_ENHANCED   |   \
+				TIPC_NAGLE             |   \
+				TIPC_NAMED_BCAST)
+
+#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);
+void tipc_node_get(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);
+struct tipc_crypto *tipc_node_crypto_rx_by_addr(struct net *net, u32 addr);
+#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, u32 hash_mixes,
+			  struct tipc_media_addr *maddr,
+			  bool *respond, bool *dupl_addr);
+void tipc_node_delete_links(struct net *net, int bearer_id);
+void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, int prop);
+int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node,
+			   char *linkname, size_t len);
+int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode,
+		   int selector);
+int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *list);
+int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest,
+		       u32 selector);
+void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr);
+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 rc_dests);
+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, 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);
+int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info);
+
+int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info);
+int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
+				   struct netlink_callback *cb);
+#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

linux-7.2.3/net/tipc/socket.h

@@ -0,0 +1,80 @@
+/* net/tipc/socket.h: Include file for TIPC socket code
+ *
+ * Copyright (c) 2014-2016, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_SOCK_H
+#define _TIPC_SOCK_H
+
+#include <net/sock.h>
+#include <net/genetlink.h>
+
+/* Compatibility values for deprecated message based flow control */
+#define FLOWCTL_MSG_WIN 512
+#define FLOWCTL_MSG_LIM ((FLOWCTL_MSG_WIN * 2 + 1) * SKB_TRUESIZE(MAX_MSG_SIZE))
+
+#define FLOWCTL_BLK_SZ 1024
+
+/* Socket receive buffer sizes */
+#define RCVBUF_MIN  (FLOWCTL_BLK_SZ * 512)
+#define RCVBUF_DEF  (FLOWCTL_BLK_SZ * 1024 * 2)
+#define RCVBUF_MAX  (FLOWCTL_BLK_SZ * 1024 * 16)
+
+struct tipc_sock;
+
+int tipc_socket_init(void);
+void tipc_socket_stop(void);
+void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq);
+void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
+		       struct sk_buff_head *inputq);
+void tipc_sk_reinit(struct net *net);
+int tipc_sk_rht_init(struct net *net);
+void tipc_sk_rht_destroy(struct net *net);
+int tipc_nl_sk_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
+			   struct tipc_sock *tsk, u32 sk_filter_state,
+			   u64 (*tipc_diag_gen_cookie)(struct sock *sk));
+int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb,
+		    int (*skb_handler)(struct sk_buff *skb,
+				       struct netlink_callback *cb,
+				       struct tipc_sock *tsk));
+int tipc_dump_start(struct netlink_callback *cb);
+int __tipc_dump_start(struct netlink_callback *cb, struct net *net);
+int tipc_dump_done(struct netlink_callback *cb);
+u32 tipc_sock_get_portid(struct sock *sk);
+bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb);
+bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb);
+int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen);
+int tsk_set_importance(struct sock *sk, int imp);
+
+#endif

linux-7.2.3/net/tipc/subscr.c

@@ -0,0 +1,183 @@
+/*
+ * net/tipc/subscr.c: TIPC network topology service
+ *
+ * Copyright (c) 2000-2017, Ericsson AB
+ * Copyright (c) 2005-2007, 2010-2013, Wind River Systems
+ * Copyright (c) 2020-2021, Red Hat Inc
+ * 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 "core.h"
+#include "name_table.h"
+#include "subscr.h"
+
+static void tipc_sub_send_event(struct tipc_subscription *sub,
+				struct publication *p,
+				u32 event)
+{
+	struct tipc_subscr *s = &sub->evt.s;
+	struct tipc_event *evt = &sub->evt;
+
+	if (sub->inactive)
+		return;
+	tipc_evt_write(evt, event, event);
+	if (p) {
+		tipc_evt_write(evt, found_lower, p->sr.lower);
+		tipc_evt_write(evt, found_upper, p->sr.upper);
+		tipc_evt_write(evt, port.ref, p->sk.ref);
+		tipc_evt_write(evt, port.node, p->sk.node);
+	} else {
+		tipc_evt_write(evt, found_lower, s->seq.lower);
+		tipc_evt_write(evt, found_upper, s->seq.upper);
+		tipc_evt_write(evt, port.ref, 0);
+		tipc_evt_write(evt, port.node, 0);
+	}
+	tipc_topsrv_queue_evt(sub->net, sub->conid, event, evt);
+}
+
+/**
+ * tipc_sub_check_overlap - test for subscription overlap with the given values
+ * @subscribed: the service range subscribed for
+ * @found: the service range we are checking for match
+ *
+ * Returns true if there is overlap, otherwise false.
+ */
+static bool tipc_sub_check_overlap(struct tipc_service_range *subscribed,
+				   struct tipc_service_range *found)
+{
+	u32 found_lower = found->lower;
+	u32 found_upper = found->upper;
+
+	if (found_lower < subscribed->lower)
+		found_lower = subscribed->lower;
+	if (found_upper > subscribed->upper)
+		found_upper = subscribed->upper;
+	return found_lower <= found_upper;
+}
+
+void tipc_sub_report_overlap(struct tipc_subscription *sub,
+			     struct publication *p,
+			     u32 event, bool must)
+{
+	struct tipc_service_range *sr = &sub->s.seq;
+	u32 filter = sub->s.filter;
+
+	if (!tipc_sub_check_overlap(sr, &p->sr))
+		return;
+	if (!must && !(filter & TIPC_SUB_PORTS))
+		return;
+	if (filter & TIPC_SUB_CLUSTER_SCOPE && p->scope == TIPC_NODE_SCOPE)
+		return;
+	if (filter & TIPC_SUB_NODE_SCOPE && p->scope != TIPC_NODE_SCOPE)
+		return;
+	spin_lock(&sub->lock);
+	tipc_sub_send_event(sub, p, event);
+	spin_unlock(&sub->lock);
+}
+
+static void tipc_sub_timeout(struct timer_list *t)
+{
+	struct tipc_subscription *sub = timer_container_of(sub, t, timer);
+
+	spin_lock(&sub->lock);
+	tipc_sub_send_event(sub, NULL, TIPC_SUBSCR_TIMEOUT);
+	sub->inactive = true;
+	spin_unlock(&sub->lock);
+}
+
+static void tipc_sub_kref_release(struct kref *kref)
+{
+	kfree(container_of(kref, struct tipc_subscription, kref));
+}
+
+void tipc_sub_put(struct tipc_subscription *subscription)
+{
+	kref_put(&subscription->kref, tipc_sub_kref_release);
+}
+
+void tipc_sub_get(struct tipc_subscription *subscription)
+{
+	kref_get(&subscription->kref);
+}
+
+struct tipc_subscription *tipc_sub_subscribe(struct net *net,
+					     struct tipc_subscr *s,
+					     int conid)
+{
+	u32 lower = tipc_sub_read(s, seq.lower);
+	u32 upper = tipc_sub_read(s, seq.upper);
+	u32 filter = tipc_sub_read(s, filter);
+	struct tipc_subscription *sub;
+	u32 timeout;
+
+	if ((filter & TIPC_SUB_PORTS && filter & TIPC_SUB_SERVICE) ||
+	    lower > upper) {
+		pr_warn("Subscription rejected, illegal request\n");
+		return NULL;
+	}
+	sub = kmalloc_obj(*sub, GFP_ATOMIC);
+	if (!sub) {
+		pr_warn("Subscription rejected, no memory\n");
+		return NULL;
+	}
+	INIT_LIST_HEAD(&sub->service_list);
+	INIT_LIST_HEAD(&sub->sub_list);
+	sub->net = net;
+	sub->conid = conid;
+	sub->inactive = false;
+	memcpy(&sub->evt.s, s, sizeof(*s));
+	sub->s.seq.type = tipc_sub_read(s, seq.type);
+	sub->s.seq.lower = lower;
+	sub->s.seq.upper = upper;
+	sub->s.filter = filter;
+	sub->s.timeout = tipc_sub_read(s, timeout);
+	memcpy(sub->s.usr_handle, s->usr_handle, 8);
+	spin_lock_init(&sub->lock);
+	kref_init(&sub->kref);
+	if (!tipc_nametbl_subscribe(sub)) {
+		kfree(sub);
+		return NULL;
+	}
+	timer_setup(&sub->timer, tipc_sub_timeout, 0);
+	timeout = tipc_sub_read(&sub->evt.s, timeout);
+	if (timeout != TIPC_WAIT_FOREVER)
+		mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
+	return sub;
+}
+
+void tipc_sub_unsubscribe(struct tipc_subscription *sub)
+{
+	tipc_nametbl_unsubscribe(sub);
+	if (sub->evt.s.timeout != TIPC_WAIT_FOREVER)
+		timer_delete_sync(&sub->timer);
+	list_del(&sub->sub_list);
+	tipc_sub_put(sub);
+}

linux-7.2.3/net/tipc/subscr.h

@@ -0,0 +1,122 @@
+/*
+ * net/tipc/subscr.h: Include file for TIPC network topology service
+ *
+ * Copyright (c) 2003-2017, Ericsson AB
+ * Copyright (c) 2005-2007, 2012-2013, Wind River Systems
+ * Copyright (c) 2020-2021, Red Hat Inc
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_SUBSCR_H
+#define _TIPC_SUBSCR_H
+
+#include "topsrv.h"
+
+#define TIPC_MAX_SUBSCR         65535
+#define TIPC_MAX_PUBL           65535
+
+struct publication;
+struct tipc_subscription;
+struct tipc_conn;
+
+/**
+ * struct tipc_subscription - TIPC network topology subscription object
+ * @s: host-endian copy of the user subscription
+ * @evt: template for events generated by subscription
+ * @kref: reference count for this subscription
+ * @net: network namespace associated with subscription
+ * @timer: timer governing subscription duration (optional)
+ * @service_list: adjacent subscriptions in name sequence's subscription list
+ * @sub_list: adjacent subscriptions in subscriber's subscription list
+ * @conid: connection identifier of topology server
+ * @inactive: true if this subscription is inactive
+ * @lock: serialize up/down and timer events
+ */
+struct tipc_subscription {
+	struct tipc_subscr s;
+	struct tipc_event evt;
+	struct kref kref;
+	struct net *net;
+	struct timer_list timer;
+	struct list_head service_list;
+	struct list_head sub_list;
+	int conid;
+	bool inactive;
+	spinlock_t lock;
+};
+
+struct tipc_subscription *tipc_sub_subscribe(struct net *net,
+					     struct tipc_subscr *s,
+					     int conid);
+void tipc_sub_unsubscribe(struct tipc_subscription *sub);
+void tipc_sub_report_overlap(struct tipc_subscription *sub,
+			     struct publication *p,
+			     u32 event, bool must);
+
+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);
+
+#define TIPC_FILTER_MASK (TIPC_SUB_PORTS | TIPC_SUB_SERVICE | TIPC_SUB_CANCEL)
+
+/* tipc_sub_read - return field_ of struct sub_ in host endian format
+ */
+#define tipc_sub_read(sub_, field_)					\
+	({								\
+		struct tipc_subscr *sub__ = sub_;			\
+		u32 val__ = (sub__)->field_;				\
+		int swap_ = !((sub__)->filter & TIPC_FILTER_MASK);	\
+		(swap_ ? swab32(val__) : val__);			\
+	})
+
+/* tipc_sub_write - write val_ to field_ of struct sub_ in user endian format
+ */
+#define tipc_sub_write(sub_, field_, val_)				\
+	({								\
+		struct tipc_subscr *sub__ = sub_;			\
+		u32 val__ = val_;					\
+		int swap_ = !((sub__)->filter & TIPC_FILTER_MASK);	\
+		(sub__)->field_ = swap_ ? swab32(val__) : val__;	\
+	})
+
+/* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format
+ */
+#define tipc_evt_write(evt_, field_, val_)				\
+	({								\
+		struct tipc_event *evt__ = evt_;			\
+		u32 val__ = val_;					\
+		int swap_ = !((evt__)->s.filter & (TIPC_FILTER_MASK));	\
+		(evt__)->field_ = swap_ ? swab32(val__) : val__;	\
+	})
+
+#endif

linux-7.2.3/net/tipc/sysctl.c

@@ -0,0 +1,107 @@
+/*
+ * net/tipc/sysctl.c: sysctl interface to TIPC subsystem
+ *
+ * Copyright (c) 2013, Wind River Systems
+ * 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 "core.h"
+#include "trace.h"
+#include "crypto.h"
+#include "bcast.h"
+#include <linux/sysctl.h>
+
+static struct ctl_table_header *tipc_ctl_hdr;
+
+static struct ctl_table tipc_table[] = {
+	{
+		.procname	= "tipc_rmem",
+		.data		= &sysctl_tipc_rmem,
+		.maxlen		= sizeof(sysctl_tipc_rmem),
+		.mode		= 0644,
+		.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_minmax,
+		.extra1         = SYSCTL_ZERO,
+	},
+	{
+		.procname       = "sk_filter",
+		.data           = &sysctl_tipc_sk_filter,
+		.maxlen         = sizeof(sysctl_tipc_sk_filter),
+		.mode           = 0644,
+		.proc_handler   = proc_doulongvec_minmax,
+	},
+#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,
+	},
+	{
+		.procname	= "key_exchange_enabled",
+		.data		= &sysctl_tipc_key_exchange_enabled,
+		.maxlen		= sizeof(sysctl_tipc_key_exchange_enabled),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+#endif
+	{
+		.procname	= "bc_retruni",
+		.data		= &sysctl_tipc_bc_retruni,
+		.maxlen		= sizeof(sysctl_tipc_bc_retruni),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+};
+
+int tipc_register_sysctl(void)
+{
+	tipc_ctl_hdr = register_net_sysctl(&init_net, "net/tipc", tipc_table);
+	if (tipc_ctl_hdr == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void tipc_unregister_sysctl(void)
+{
+	unregister_net_sysctl_table(tipc_ctl_hdr);
+}

linux-7.2.3/net/tipc/topsrv.c

@@ -0,0 +1,733 @@
+/*
+ * net/tipc/server.c: TIPC server infrastructure
+ *
+ * Copyright (c) 2012-2013, Wind River Systems
+ * Copyright (c) 2017-2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "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 "subscr.h"
+#include "topsrv.h"
+#include "core.h"
+#include "socket.h"
+#include "addr.h"
+#include "msg.h"
+#include "bearer.h"
+#include <net/sock.h>
+#include <linux/module.h>
+#include <trace/events/sock.h>
+
+/* Number of messages to send before rescheduling */
+#define MAX_SEND_MSG_COUNT	25
+#define MAX_RECV_MSG_COUNT	25
+#define CF_CONNECTED		1
+
+#define TIPC_SERVER_NAME_LEN	32
+
+/**
+ * struct tipc_topsrv - TIPC server structure
+ * @conn_idr: identifier set of connection
+ * @idr_lock: protect the connection identifier set
+ * @idr_in_use: amount of allocated identifier entry
+ * @net: network namespace instance
+ * @awork: accept work item
+ * @rcv_wq: receive workqueue
+ * @send_wq: send workqueue
+ * @listener: topsrv listener socket
+ * @name: server name
+ */
+struct tipc_topsrv {
+	struct idr conn_idr;
+	spinlock_t idr_lock; /* for idr list */
+	int idr_in_use;
+	struct net *net;
+	struct work_struct awork;
+	struct workqueue_struct *rcv_wq;
+	struct workqueue_struct *send_wq;
+	struct socket *listener;
+	char name[TIPC_SERVER_NAME_LEN];
+};
+
+/**
+ * struct tipc_conn - TIPC connection structure
+ * @kref: reference counter to connection object
+ * @conid: connection identifier
+ * @sock: socket handler associated with connection
+ * @flags: indicates connection state
+ * @server: pointer to connected server
+ * @sub_list: list to all pertaining subscriptions
+ * @sub_lock: lock protecting the subscription list
+ * @rwork: receive work item
+ * @outqueue: pointer to first outbound message in queue
+ * @outqueue_lock: control access to the outqueue
+ * @swork: send work item
+ */
+struct tipc_conn {
+	struct kref kref;
+	int conid;
+	struct socket *sock;
+	unsigned long flags;
+	struct tipc_topsrv *server;
+	struct list_head sub_list;
+	spinlock_t sub_lock; /* for subscription list */
+	struct work_struct rwork;
+	struct list_head outqueue;
+	spinlock_t outqueue_lock; /* for outqueue */
+	struct work_struct swork;
+};
+
+/* An entry waiting to be sent */
+struct outqueue_entry {
+	bool inactive;
+	struct tipc_event evt;
+	struct list_head list;
+};
+
+static void tipc_conn_recv_work(struct work_struct *work);
+static void tipc_conn_send_work(struct work_struct *work);
+static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt);
+static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s);
+
+static bool connected(struct tipc_conn *con)
+{
+	return con && test_bit(CF_CONNECTED, &con->flags);
+}
+
+static void tipc_conn_kref_release(struct kref *kref)
+{
+	struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
+	struct tipc_topsrv *s = con->server;
+	struct outqueue_entry *e, *safe;
+
+	spin_lock_bh(&s->idr_lock);
+	idr_remove(&s->conn_idr, con->conid);
+	s->idr_in_use--;
+	spin_unlock_bh(&s->idr_lock);
+	if (con->sock)
+		sock_release(con->sock);
+
+	spin_lock_bh(&con->outqueue_lock);
+	list_for_each_entry_safe(e, safe, &con->outqueue, list) {
+		list_del(&e->list);
+		kfree(e);
+	}
+	spin_unlock_bh(&con->outqueue_lock);
+	kfree(con);
+}
+
+static void conn_put(struct tipc_conn *con)
+{
+	kref_put(&con->kref, tipc_conn_kref_release);
+}
+
+static void conn_get(struct tipc_conn *con)
+{
+	kref_get(&con->kref);
+}
+
+static void tipc_conn_close(struct tipc_conn *con)
+{
+	struct sock *sk = con->sock->sk;
+	bool disconnect = false;
+
+	write_lock_bh(&sk->sk_callback_lock);
+	disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags);
+
+	if (disconnect) {
+		sk->sk_user_data = NULL;
+		tipc_conn_delete_sub(con, NULL);
+	}
+	write_unlock_bh(&sk->sk_callback_lock);
+
+	/* Handle concurrent calls from sending and receiving threads */
+	if (!disconnect)
+		return;
+
+	/* Don't flush pending works, -just let them expire */
+	kernel_sock_shutdown(con->sock, SHUT_RDWR);
+
+	conn_put(con);
+}
+
+static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock)
+{
+	struct tipc_conn *con;
+	int ret;
+
+	con = kzalloc_obj(*con, GFP_ATOMIC);
+	if (!con)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&con->kref);
+	INIT_LIST_HEAD(&con->outqueue);
+	INIT_LIST_HEAD(&con->sub_list);
+	spin_lock_init(&con->outqueue_lock);
+	spin_lock_init(&con->sub_lock);
+	INIT_WORK(&con->swork, tipc_conn_send_work);
+	INIT_WORK(&con->rwork, tipc_conn_recv_work);
+
+	spin_lock_bh(&s->idr_lock);
+	ret = idr_alloc(&s->conn_idr, con, 0, 0, GFP_ATOMIC);
+	if (ret < 0) {
+		kfree(con);
+		spin_unlock_bh(&s->idr_lock);
+		return ERR_PTR(-ENOMEM);
+	}
+	con->conid = ret;
+	s->idr_in_use++;
+
+	set_bit(CF_CONNECTED, &con->flags);
+	con->server = s;
+	con->sock = sock;
+	conn_get(con);
+	spin_unlock_bh(&s->idr_lock);
+
+	return con;
+}
+
+static struct tipc_conn *tipc_conn_lookup(struct tipc_topsrv *s, int conid)
+{
+	struct tipc_conn *con;
+
+	spin_lock_bh(&s->idr_lock);
+	con = idr_find(&s->conn_idr, conid);
+	if (!connected(con) || !kref_get_unless_zero(&con->kref))
+		con = NULL;
+	spin_unlock_bh(&s->idr_lock);
+	return con;
+}
+
+/* tipc_conn_delete_sub - delete a specific or all subscriptions
+ * for a given subscriber
+ */
+static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s)
+{
+	struct tipc_net *tn = tipc_net(con->server->net);
+	struct list_head *sub_list = &con->sub_list;
+	struct tipc_subscription *sub, *tmp;
+
+	spin_lock_bh(&con->sub_lock);
+	list_for_each_entry_safe(sub, tmp, sub_list, sub_list) {
+		if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) {
+			tipc_sub_unsubscribe(sub);
+			atomic_dec(&tn->subscription_count);
+			if (s)
+				break;
+		}
+	}
+	spin_unlock_bh(&con->sub_lock);
+}
+
+static void tipc_conn_send_to_sock(struct tipc_conn *con)
+{
+	struct list_head *queue = &con->outqueue;
+	struct tipc_topsrv *srv = con->server;
+	struct outqueue_entry *e;
+	struct tipc_event *evt;
+	struct msghdr msg;
+	struct kvec iov;
+	int count = 0;
+	int ret;
+
+	spin_lock_bh(&con->outqueue_lock);
+
+	while (!list_empty(queue)) {
+		e = list_first_entry(queue, struct outqueue_entry, list);
+		evt = &e->evt;
+		spin_unlock_bh(&con->outqueue_lock);
+
+		if (e->inactive)
+			tipc_conn_delete_sub(con, &evt->s);
+
+		memset(&msg, 0, sizeof(msg));
+		msg.msg_flags = MSG_DONTWAIT;
+		iov.iov_base = evt;
+		iov.iov_len = sizeof(*evt);
+		msg.msg_name = NULL;
+
+		if (con->sock) {
+			ret = kernel_sendmsg(con->sock, &msg, &iov,
+					     1, sizeof(*evt));
+			if (ret == -EWOULDBLOCK || ret == 0) {
+				cond_resched();
+				return;
+			} else if (ret < 0) {
+				return tipc_conn_close(con);
+			}
+		} else {
+			tipc_topsrv_kern_evt(srv->net, evt);
+		}
+
+		/* Don't starve users filling buffers */
+		if (++count >= MAX_SEND_MSG_COUNT) {
+			cond_resched();
+			count = 0;
+		}
+		spin_lock_bh(&con->outqueue_lock);
+		list_del(&e->list);
+		kfree(e);
+	}
+	spin_unlock_bh(&con->outqueue_lock);
+}
+
+static void tipc_conn_send_work(struct work_struct *work)
+{
+	struct tipc_conn *con = container_of(work, struct tipc_conn, swork);
+
+	if (connected(con))
+		tipc_conn_send_to_sock(con);
+
+	conn_put(con);
+}
+
+/* tipc_topsrv_queue_evt() - interrupt level call from a subscription instance
+ * The queued work is launched into tipc_conn_send_work()->tipc_conn_send_to_sock()
+ */
+void tipc_topsrv_queue_evt(struct net *net, int conid,
+			   u32 event, struct tipc_event *evt)
+{
+	struct tipc_topsrv *srv = tipc_topsrv(net);
+	struct outqueue_entry *e;
+	struct tipc_conn *con;
+
+	con = tipc_conn_lookup(srv, conid);
+	if (!con)
+		return;
+
+	if (!connected(con))
+		goto err;
+
+	e = kmalloc_obj(*e, GFP_ATOMIC);
+	if (!e)
+		goto err;
+	e->inactive = (event == TIPC_SUBSCR_TIMEOUT);
+	memcpy(&e->evt, evt, sizeof(*evt));
+	spin_lock_bh(&con->outqueue_lock);
+	list_add_tail(&e->list, &con->outqueue);
+	spin_unlock_bh(&con->outqueue_lock);
+
+	if (queue_work(srv->send_wq, &con->swork))
+		return;
+err:
+	conn_put(con);
+}
+
+/* tipc_conn_write_space - interrupt callback after a sendmsg EAGAIN
+ * Indicates that there now is more space in the send buffer
+ * The queued work is launched into tipc_send_work()->tipc_conn_send_to_sock()
+ */
+static void tipc_conn_write_space(struct sock *sk)
+{
+	struct tipc_conn *con;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	con = sk->sk_user_data;
+	if (connected(con)) {
+		conn_get(con);
+		if (!queue_work(con->server->send_wq, &con->swork))
+			conn_put(con);
+	}
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int tipc_conn_rcv_sub(struct tipc_topsrv *srv,
+			     struct tipc_conn *con,
+			     struct tipc_subscr *s)
+{
+	struct tipc_net *tn = tipc_net(srv->net);
+	struct tipc_subscription *sub;
+	u32 s_filter = tipc_sub_read(s, filter);
+
+	if (s_filter & TIPC_SUB_CANCEL) {
+		tipc_sub_write(s, filter, s_filter & ~TIPC_SUB_CANCEL);
+		tipc_conn_delete_sub(con, s);
+		return 0;
+	}
+	if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCR) {
+		pr_warn("Subscription rejected, max (%u)\n", TIPC_MAX_SUBSCR);
+		return -1;
+	}
+	sub = tipc_sub_subscribe(srv->net, s, con->conid);
+	if (!sub)
+		return -1;
+	atomic_inc(&tn->subscription_count);
+	spin_lock_bh(&con->sub_lock);
+	list_add(&sub->sub_list, &con->sub_list);
+	spin_unlock_bh(&con->sub_lock);
+	return 0;
+}
+
+static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
+{
+	struct tipc_topsrv *srv = con->server;
+	struct sock *sk = con->sock->sk;
+	struct msghdr msg = {};
+	struct tipc_subscr s;
+	struct kvec iov;
+	int ret;
+
+	iov.iov_base = &s;
+	iov.iov_len = sizeof(s);
+	msg.msg_name = NULL;
+	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, iov.iov_len);
+	ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
+	if (ret == -EWOULDBLOCK)
+		return -EWOULDBLOCK;
+	if (ret == sizeof(s)) {
+		read_lock_bh(&sk->sk_callback_lock);
+		/* RACE: the connection can be closed in the meantime */
+		if (likely(connected(con)))
+			ret = tipc_conn_rcv_sub(srv, con, &s);
+		read_unlock_bh(&sk->sk_callback_lock);
+		if (!ret)
+			return 0;
+	}
+
+	tipc_conn_close(con);
+	return ret;
+}
+
+static void tipc_conn_recv_work(struct work_struct *work)
+{
+	struct tipc_conn *con = container_of(work, struct tipc_conn, rwork);
+	int count = 0;
+
+	while (connected(con)) {
+		if (tipc_conn_rcv_from_sock(con))
+			break;
+
+		/* Don't flood Rx machine */
+		if (++count >= MAX_RECV_MSG_COUNT) {
+			cond_resched();
+			count = 0;
+		}
+	}
+	conn_put(con);
+}
+
+/* tipc_conn_data_ready - interrupt callback indicating the socket has data
+ * The queued work is launched into tipc_recv_work()->tipc_conn_rcv_from_sock()
+ */
+static void tipc_conn_data_ready(struct sock *sk)
+{
+	struct tipc_conn *con;
+
+	trace_sk_data_ready(sk);
+
+	read_lock_bh(&sk->sk_callback_lock);
+	con = sk->sk_user_data;
+	if (connected(con)) {
+		conn_get(con);
+		if (!queue_work(con->server->rcv_wq, &con->rwork))
+			conn_put(con);
+	}
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void tipc_topsrv_accept(struct work_struct *work)
+{
+	struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork);
+	struct socket *newsock, *lsock;
+	struct tipc_conn *con;
+	struct sock *newsk;
+	int ret;
+
+	spin_lock_bh(&srv->idr_lock);
+	if (!srv->listener) {
+		spin_unlock_bh(&srv->idr_lock);
+		return;
+	}
+	lsock = srv->listener;
+	spin_unlock_bh(&srv->idr_lock);
+
+	while (1) {
+		ret = kernel_accept(lsock, &newsock, O_NONBLOCK);
+		if (ret < 0)
+			return;
+		con = tipc_conn_alloc(srv, newsock);
+		if (IS_ERR(con)) {
+			ret = PTR_ERR(con);
+			sock_release(newsock);
+			return;
+		}
+		/* Register callbacks */
+		newsk = newsock->sk;
+		write_lock_bh(&newsk->sk_callback_lock);
+		newsk->sk_data_ready = tipc_conn_data_ready;
+		newsk->sk_write_space = tipc_conn_write_space;
+		newsk->sk_user_data = con;
+		write_unlock_bh(&newsk->sk_callback_lock);
+
+		/* Wake up receive process in case of 'SYN+' message */
+		newsk->sk_data_ready(newsk);
+		conn_put(con);
+	}
+}
+
+/* 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)
+{
+	struct tipc_topsrv *srv;
+
+	trace_sk_data_ready(sk);
+
+	read_lock_bh(&sk->sk_callback_lock);
+	srv = sk->sk_user_data;
+	if (srv)
+		queue_work(srv->rcv_wq, &srv->awork);
+	read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int tipc_topsrv_create_listener(struct tipc_topsrv *srv)
+{
+	struct socket *lsock = NULL;
+	struct sockaddr_tipc saddr;
+	struct sock *sk;
+	int rc;
+
+	rc = sock_create_kern(srv->net, AF_TIPC, SOCK_SEQPACKET, 0, &lsock);
+	if (rc < 0)
+		return rc;
+
+	srv->listener = lsock;
+	sk = lsock->sk;
+	write_lock_bh(&sk->sk_callback_lock);
+	sk->sk_data_ready = tipc_topsrv_listener_data_ready;
+	sk->sk_user_data = srv;
+	write_unlock_bh(&sk->sk_callback_lock);
+
+	lock_sock(sk);
+	rc = tsk_set_importance(sk, TIPC_CRITICAL_IMPORTANCE);
+	release_sock(sk);
+	if (rc < 0)
+		goto err;
+
+	saddr.family	                = AF_TIPC;
+	saddr.addrtype		        = TIPC_SERVICE_RANGE;
+	saddr.addr.nameseq.type	= TIPC_TOP_SRV;
+	saddr.addr.nameseq.lower	= TIPC_TOP_SRV;
+	saddr.addr.nameseq.upper	= TIPC_TOP_SRV;
+	saddr.scope			= TIPC_NODE_SCOPE;
+
+	rc = tipc_sk_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
+	if (rc < 0)
+		goto err;
+	rc = kernel_listen(lsock, 0);
+	if (rc < 0)
+		goto err;
+
+	/* As server's listening socket owner and creator is the same module,
+	 * we have to decrease TIPC module reference count to guarantee that
+	 * it remains zero after the server socket is created, otherwise,
+	 * executing "rmmod" command is unable to make TIPC module deleted
+	 * after TIPC module is inserted successfully.
+	 *
+	 * However, the reference count is ever increased twice in
+	 * sock_create_kern(): one is to increase the reference count of owner
+	 * of TIPC socket's proto_ops struct; another is to increment the
+	 * reference count of owner of TIPC proto struct. Therefore, we must
+	 * decrement the module reference count twice to ensure that it keeps
+	 * zero after server's listening socket is created. Of course, we
+	 * must bump the module reference count twice as well before the socket
+	 * is closed.
+	 */
+	module_put(lsock->ops->owner);
+	module_put(sk->sk_prot_creator->owner);
+
+	return 0;
+err:
+	sock_release(lsock);
+	return -EINVAL;
+}
+
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower,
+			     u32 upper, u32 filter, int *conid)
+{
+	struct tipc_subscr sub;
+	struct tipc_conn *con;
+	int rc;
+
+	sub.seq.type = type;
+	sub.seq.lower = lower;
+	sub.seq.upper = upper;
+	sub.timeout = TIPC_WAIT_FOREVER;
+	sub.filter = filter;
+	*(u64 *)&sub.usr_handle = (u64)port;
+
+	con = tipc_conn_alloc(tipc_topsrv(net), NULL);
+	if (IS_ERR(con))
+		return false;
+
+	*conid = con->conid;
+	rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub);
+	if (rc)
+		conn_put(con);
+
+	conn_put(con);
+	return !rc;
+}
+
+void tipc_topsrv_kern_unsubscr(struct net *net, int conid)
+{
+	struct tipc_conn *con;
+
+	con = tipc_conn_lookup(tipc_topsrv(net), conid);
+	if (!con)
+		return;
+
+	test_and_clear_bit(CF_CONNECTED, &con->flags);
+	tipc_conn_delete_sub(con, NULL);
+	conn_put(con);
+	conn_put(con);
+}
+
+static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt)
+{
+	u32 port = *(u32 *)&evt->s.usr_handle;
+	u32 self = tipc_own_addr(net);
+	struct sk_buff_head evtq;
+	struct sk_buff *skb;
+
+	skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt),
+			      self, self, port, port, 0);
+	if (!skb)
+		return;
+	msg_set_dest_droppable(buf_msg(skb), true);
+	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);
+}
+
+static int tipc_topsrv_work_start(struct tipc_topsrv *s)
+{
+	s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0);
+	if (!s->rcv_wq) {
+		pr_err("can't start tipc receive workqueue\n");
+		return -ENOMEM;
+	}
+
+	s->send_wq = alloc_ordered_workqueue("tipc_send", 0);
+	if (!s->send_wq) {
+		pr_err("can't start tipc send workqueue\n");
+		destroy_workqueue(s->rcv_wq);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void tipc_topsrv_work_stop(struct tipc_topsrv *s)
+{
+	destroy_workqueue(s->rcv_wq);
+	destroy_workqueue(s->send_wq);
+}
+
+static int tipc_topsrv_start(struct net *net)
+{
+	struct tipc_net *tn = tipc_net(net);
+	const char name[] = "topology_server";
+	struct tipc_topsrv *srv;
+	int ret;
+
+	srv = kzalloc_obj(*srv, GFP_ATOMIC);
+	if (!srv)
+		return -ENOMEM;
+
+	srv->net = net;
+	INIT_WORK(&srv->awork, tipc_topsrv_accept);
+
+	strscpy(srv->name, name, sizeof(srv->name));
+	tn->topsrv = srv;
+	atomic_set(&tn->subscription_count, 0);
+
+	spin_lock_init(&srv->idr_lock);
+	idr_init(&srv->conn_idr);
+	srv->idr_in_use = 0;
+
+	ret = tipc_topsrv_work_start(srv);
+	if (ret < 0)
+		goto err_start;
+
+	ret = tipc_topsrv_create_listener(srv);
+	if (ret < 0)
+		goto err_create;
+
+	return 0;
+
+err_create:
+	tipc_topsrv_work_stop(srv);
+err_start:
+	kfree(srv);
+	return ret;
+}
+
+static void tipc_topsrv_stop(struct net *net)
+{
+	struct tipc_topsrv *srv = tipc_topsrv(net);
+	struct socket *lsock = srv->listener;
+	struct tipc_conn *con;
+	int id;
+
+	spin_lock_bh(&srv->idr_lock);
+	for (id = 0; srv->idr_in_use; id++) {
+		con = idr_find(&srv->conn_idr, id);
+		if (con) {
+			conn_get(con);
+			spin_unlock_bh(&srv->idr_lock);
+			tipc_conn_close(con);
+			conn_put(con);
+			spin_lock_bh(&srv->idr_lock);
+		}
+	}
+	__module_get(lsock->ops->owner);
+	__module_get(lsock->sk->sk_prot_creator->owner);
+	srv->listener = NULL;
+	spin_unlock_bh(&srv->idr_lock);
+
+	tipc_topsrv_work_stop(srv);
+	sock_release(lsock);
+	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);
+}

linux-7.2.3/net/tipc/topsrv.h

@@ -0,0 +1,54 @@
+/*
+ * net/tipc/server.h: Include file for TIPC server code
+ *
+ * Copyright (c) 2012-2013, Wind River Systems
+ * Copyright (c) 2017, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_SERVER_H
+#define _TIPC_SERVER_H
+
+#include "core.h"
+
+#define TIPC_SERVER_NAME_LEN	32
+#define TIPC_SUB_CLUSTER_SCOPE  0x20
+#define TIPC_SUB_NODE_SCOPE     0x40
+#define TIPC_SUB_NO_STATUS      0x80
+
+void tipc_topsrv_queue_evt(struct net *net, int conid,
+			   u32 event, struct tipc_event *evt);
+
+bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower,
+			     u32 upper, u32 filter, int *conid);
+void tipc_topsrv_kern_unsubscr(struct net *net, int conid);
+
+#endif

linux-7.2.3/net/tipc/trace.c

@@ -0,0 +1,206 @@
+/*
+ * net/tipc/trace.c: TIPC tracepoints code
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+/*
+ * socket tuples for filtering in socket traces:
+ * (portid, sock type, name type, name lower, name upper)
+ */
+unsigned long sysctl_tipc_sk_filter[5] __read_mostly = {0, };
+
+/**
+ * tipc_skb_dump - dump TIPC skb data
+ * @skb: skb to be dumped
+ * @more: dump more?
+ *        - false: dump only tipc msg data
+ *        - true: dump kernel-related skb data and tipc cb[] array as well
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf)
+{
+	int i = 0;
+	size_t sz = (more) ? SKB_LMAX : SKB_LMIN;
+	struct tipc_msg *hdr;
+	struct tipc_skb_cb *skbcb;
+
+	if (!skb) {
+		i += scnprintf(buf, sz, "msg: (null)\n");
+		return i;
+	}
+
+	hdr = buf_msg(skb);
+	skbcb = TIPC_SKB_CB(skb);
+
+	/* tipc msg data section */
+	i += scnprintf(buf, sz, "msg: %u", msg_user(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_type(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_hdr_sz(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_data_sz(hdr));
+	i += scnprintf(buf + i, sz - i, " %x", msg_orignode(hdr));
+	i += scnprintf(buf + i, sz - i, " %x", msg_destnode(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_seqno(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_ack(hdr));
+	i += scnprintf(buf + i, sz - i, " %u", msg_bcast_ack(hdr));
+	switch (msg_user(hdr)) {
+	case LINK_PROTOCOL:
+		i += scnprintf(buf + i, sz - i, " %c", msg_net_plane(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_probe(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_peer_stopping(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_session(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_next_sent(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_seq_gap(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_bc_snd_nxt(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_bc_gap(hdr));
+		break;
+	case TIPC_LOW_IMPORTANCE:
+	case TIPC_MEDIUM_IMPORTANCE:
+	case TIPC_HIGH_IMPORTANCE:
+	case TIPC_CRITICAL_IMPORTANCE:
+	case CONN_MANAGER:
+	case SOCK_WAKEUP:
+		i += scnprintf(buf + i, sz - i, " | %u", msg_origport(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_destport(hdr));
+		switch (msg_type(hdr)) {
+		case TIPC_NAMED_MSG:
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nametype(hdr));
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nameinst(hdr));
+			break;
+		case TIPC_MCAST_MSG:
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nametype(hdr));
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_namelower(hdr));
+			i += scnprintf(buf + i, sz - i, " %u",
+				       msg_nameupper(hdr));
+			break;
+		default:
+			break;
+		}
+		i += scnprintf(buf + i, sz - i, " | %u",
+			       msg_src_droppable(hdr));
+		i += scnprintf(buf + i, sz - i, " %u",
+			       msg_dest_droppable(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_errcode(hdr));
+		i += scnprintf(buf + i, sz - i, " %u", msg_reroute_cnt(hdr));
+		break;
+	default:
+		/* need more? */
+		break;
+	}
+
+	i += scnprintf(buf + i, sz - i, "\n");
+	if (!more)
+		return i;
+
+	/* kernel-related skb data section */
+	i += scnprintf(buf + i, sz - i, "skb: %s",
+		       (skb->dev) ? skb->dev->name : "n/a");
+	i += scnprintf(buf + i, sz - i, " %u", skb->len);
+	i += scnprintf(buf + i, sz - i, " %u", skb->data_len);
+	i += scnprintf(buf + i, sz - i, " %u", skb->hdr_len);
+	i += scnprintf(buf + i, sz - i, " %u", skb->truesize);
+	i += scnprintf(buf + i, sz - i, " %u", skb_cloned(skb));
+	i += scnprintf(buf + i, sz - i, " %p", skb->sk);
+	i += scnprintf(buf + i, sz - i, " %u", skb_shinfo(skb)->nr_frags);
+	i += scnprintf(buf + i, sz - i, " %llx",
+		       ktime_to_ms(skb_get_ktime(skb)));
+	i += scnprintf(buf + i, sz - i, " %llx\n",
+		       ktime_to_ms(skb_hwtstamps(skb)->hwtstamp));
+
+	/* tipc skb cb[] data section */
+	i += scnprintf(buf + i, sz - i, "cb[]: %u", skbcb->bytes_read);
+	i += scnprintf(buf + i, sz - i, " %u", skbcb->orig_member);
+	i += scnprintf(buf + i, sz - i, " %u",
+		       jiffies_to_msecs(skbcb->nxt_retr));
+	i += scnprintf(buf + i, sz - i, " %u", skbcb->validated);
+	i += scnprintf(buf + i, sz - i, " %u", skbcb->chain_imp);
+	i += scnprintf(buf + i, sz - i, " %u\n", skbcb->ackers);
+
+	return i;
+}
+
+/**
+ * tipc_list_dump - dump TIPC skb list/queue
+ * @list: list of skbs to be dumped
+ * @more: dump more?
+ *        - false: dump only the head & tail skbs
+ *        - true: dump the first & last 5 skbs
+ * @buf: returned buffer of dump data in format
+ */
+int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf)
+{
+	int i = 0;
+	size_t sz = (more) ? LIST_LMAX : LIST_LMIN;
+	u32 count, len;
+	struct sk_buff *hskb, *tskb, *skb, *tmp;
+
+	if (!list) {
+		i += scnprintf(buf, sz, "(null)\n");
+		return i;
+	}
+
+	len = skb_queue_len(list);
+	i += scnprintf(buf, sz, "len = %d\n", len);
+
+	if (!len)
+		return i;
+
+	if (!more) {
+		hskb = skb_peek(list);
+		i += scnprintf(buf + i, sz - i, "  head ");
+		i += tipc_skb_dump(hskb, false, buf + i);
+		if (len > 1) {
+			tskb = skb_peek_tail(list);
+			i += scnprintf(buf + i, sz - i, "  tail ");
+			i += tipc_skb_dump(tskb, false, buf + i);
+		}
+	} else {
+		count = 0;
+		skb_queue_walk_safe(list, skb, tmp) {
+			count++;
+			if (count == 6)
+				i += scnprintf(buf + i, sz - i, "  .\n  .\n");
+			if (count > 5 && count <= len - 5)
+				continue;
+			i += scnprintf(buf + i, sz - i, "  #%d ", count);
+			i += tipc_skb_dump(skb, false, buf + i);
+		}
+	}
+	return i;
+}

linux-7.2.3/net/tipc/trace.h

@@ -0,0 +1,434 @@
+/*
+ * net/tipc/trace.h: TIPC tracepoints
+ *
+ * Copyright (c) 2018, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "ASIS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tipc
+
+#if !defined(_TIPC_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TIPC_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "core.h"
+#include "link.h"
+#include "socket.h"
+#include "node.h"
+
+#define SKB_LMIN	(100)
+#define SKB_LMAX	(SKB_LMIN * 2)
+#define LIST_LMIN	(SKB_LMIN * 3)
+#define LIST_LMAX	(SKB_LMIN * 11)
+#define SK_LMIN		(SKB_LMIN * 2)
+#define SK_LMAX		(SKB_LMIN * 11)
+#define LINK_LMIN	(SKB_LMIN)
+#define LINK_LMAX	(SKB_LMIN * 16)
+#define NODE_LMIN	(SKB_LMIN)
+#define NODE_LMAX	(SKB_LMIN * 11)
+
+#ifndef __TIPC_TRACE_ENUM
+#define __TIPC_TRACE_ENUM
+enum {
+	TIPC_DUMP_NONE		= 0,
+
+	TIPC_DUMP_TRANSMQ	= 1,
+	TIPC_DUMP_BACKLOGQ	= (1 << 1),
+	TIPC_DUMP_DEFERDQ	= (1 << 2),
+	TIPC_DUMP_INPUTQ	= (1 << 3),
+	TIPC_DUMP_WAKEUP        = (1 << 4),
+
+	TIPC_DUMP_SK_SNDQ	= (1 << 8),
+	TIPC_DUMP_SK_RCVQ	= (1 << 9),
+	TIPC_DUMP_SK_BKLGQ	= (1 << 10),
+	TIPC_DUMP_ALL		= 0xffffu
+};
+#endif
+
+/* Link & Node FSM states: */
+#define state_sym(val)							  \
+	__print_symbolic(val,						  \
+			{(0xe),		"ESTABLISHED"			},\
+			{(0xe << 4),	"ESTABLISHING"			},\
+			{(0x1 << 8),	"RESET"				},\
+			{(0x2 << 12),	"RESETTING"			},\
+			{(0xd << 16),	"PEER_RESET"			},\
+			{(0xf << 20),	"FAILINGOVER"			},\
+			{(0xc << 24),	"SYNCHING"			},\
+			{(0xdd),	"SELF_DOWN_PEER_DOWN"		},\
+			{(0xaa),	"SELF_UP_PEER_UP"		},\
+			{(0xd1),	"SELF_DOWN_PEER_LEAVING"	},\
+			{(0xac),	"SELF_UP_PEER_COMING"		},\
+			{(0xca),	"SELF_COMING_PEER_UP"		},\
+			{(0x1d),	"SELF_LEAVING_PEER_DOWN"	},\
+			{(0xf0),	"FAILINGOVER"			},\
+			{(0xcc),	"SYNCHING"			})
+
+/* Link & Node FSM events: */
+#define evt_sym(val)							  \
+	__print_symbolic(val,						  \
+			{(0xec1ab1e),	"ESTABLISH_EVT"			},\
+			{(0x9eed0e),	"PEER_RESET_EVT"		},\
+			{(0xfa110e),	"FAILURE_EVT"			},\
+			{(0x10ca1d0e),	"RESET_EVT"			},\
+			{(0xfa110bee),	"FAILOVER_BEGIN_EVT"		},\
+			{(0xfa110ede),	"FAILOVER_END_EVT"		},\
+			{(0xc1ccbee),	"SYNCH_BEGIN_EVT"		},\
+			{(0xc1ccede),	"SYNCH_END_EVT"			},\
+			{(0xece),	"SELF_ESTABL_CONTACT_EVT"	},\
+			{(0x1ce),	"SELF_LOST_CONTACT_EVT"		},\
+			{(0x9ece),	"PEER_ESTABL_CONTACT_EVT"	},\
+			{(0x91ce),	"PEER_LOST_CONTACT_EVT"		},\
+			{(0xfbe),	"FAILOVER_BEGIN_EVT"		},\
+			{(0xfee),	"FAILOVER_END_EVT"		},\
+			{(0xcbe),	"SYNCH_BEGIN_EVT"		},\
+			{(0xcee),	"SYNCH_END_EVT"			})
+
+/* Bearer, net device events: */
+#define dev_evt_sym(val)						  \
+	__print_symbolic(val,						  \
+			{(NETDEV_CHANGE),	"NETDEV_CHANGE"		},\
+			{(NETDEV_GOING_DOWN),	"NETDEV_GOING_DOWN"	},\
+			{(NETDEV_UP),		"NETDEV_UP"		},\
+			{(NETDEV_CHANGEMTU),	"NETDEV_CHANGEMTU"	},\
+			{(NETDEV_CHANGEADDR),	"NETDEV_CHANGEADDR"	},\
+			{(NETDEV_UNREGISTER),	"NETDEV_UNREGISTER"	},\
+			{(NETDEV_CHANGENAME),	"NETDEV_CHANGENAME"	})
+
+extern unsigned long sysctl_tipc_sk_filter[5] __read_mostly;
+
+int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf);
+int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf);
+int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf);
+int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf);
+int tipc_node_dump(struct tipc_node *n, bool more, char *buf);
+bool tipc_sk_filtering(struct sock *sk);
+
+DECLARE_EVENT_CLASS(tipc_skb_class,
+
+	TP_PROTO(struct sk_buff *skb, bool more, const char *header),
+
+	TP_ARGS(skb, more, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__dynamic_array(char, buf, (more) ? SKB_LMAX : SKB_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header);
+		tipc_skb_dump(skb, more, __get_str(buf));
+	),
+
+	TP_printk("%s\n%s", __get_str(header), __get_str(buf))
+)
+
+#define DEFINE_SKB_EVENT(name) \
+DEFINE_EVENT(tipc_skb_class, name, \
+	TP_PROTO(struct sk_buff *skb, bool more, const char *header), \
+	TP_ARGS(skb, more, header))
+DEFINE_SKB_EVENT(tipc_skb_dump);
+DEFINE_SKB_EVENT(tipc_proto_build);
+DEFINE_SKB_EVENT(tipc_proto_rcv);
+
+DECLARE_EVENT_CLASS(tipc_list_class,
+
+	TP_PROTO(struct sk_buff_head *list, bool more, const char *header),
+
+	TP_ARGS(list, more, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__dynamic_array(char, buf, (more) ? LIST_LMAX : LIST_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header);
+		tipc_list_dump(list, more, __get_str(buf));
+	),
+
+	TP_printk("%s\n%s", __get_str(header), __get_str(buf))
+);
+
+#define DEFINE_LIST_EVENT(name) \
+DEFINE_EVENT(tipc_list_class, name, \
+	TP_PROTO(struct sk_buff_head *list, bool more, const char *header), \
+	TP_ARGS(list, more, header))
+DEFINE_LIST_EVENT(tipc_list_dump);
+
+DECLARE_EVENT_CLASS(tipc_sk_class,
+
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues,
+		 const char *header),
+
+	TP_ARGS(sk, skb, dqueues, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__field(u32, portid)
+		__dynamic_array(char, buf, (dqueues) ? SK_LMAX : SK_LMIN)
+		__dynamic_array(char, skb_buf, (skb) ? SKB_LMIN : 1)
+	),
+
+	TP_fast_assign(
+		__assign_str(header);
+		__entry->portid = tipc_sock_get_portid(sk);
+		tipc_sk_dump(sk, dqueues, __get_str(buf));
+		if (skb)
+			tipc_skb_dump(skb, false, __get_str(skb_buf));
+		else
+			*(__get_str(skb_buf)) = '\0';
+	),
+
+	TP_printk("<%u> %s\n%s%s", __entry->portid, __get_str(header),
+		  __get_str(skb_buf), __get_str(buf))
+);
+
+#define DEFINE_SK_EVENT_FILTER(name) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+		 const char *header), \
+	TP_ARGS(sk, skb, dqueues, header), \
+	TP_CONDITION(tipc_sk_filtering(sk)))
+DEFINE_SK_EVENT_FILTER(tipc_sk_dump);
+DEFINE_SK_EVENT_FILTER(tipc_sk_create);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmcast);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendmsg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_sendstream);
+DEFINE_SK_EVENT_FILTER(tipc_sk_poll);
+DEFINE_SK_EVENT_FILTER(tipc_sk_filter_rcv);
+DEFINE_SK_EVENT_FILTER(tipc_sk_advance_rx);
+DEFINE_SK_EVENT_FILTER(tipc_sk_rej_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_drop_msg);
+DEFINE_SK_EVENT_FILTER(tipc_sk_release);
+DEFINE_SK_EVENT_FILTER(tipc_sk_shutdown);
+
+#define DEFINE_SK_EVENT_FILTER_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_sk_class, name, \
+	TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \
+		 const char *header), \
+	TP_ARGS(sk, skb, dqueues, header), \
+	TP_CONDITION(tipc_sk_filtering(sk) && (cond)))
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit1, tipc_sk_overlimit1(sk, skb));
+DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit2, tipc_sk_overlimit2(sk, skb));
+
+DECLARE_EVENT_CLASS(tipc_link_class,
+
+	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header),
+
+	TP_ARGS(l, dqueues, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__array(char, name, TIPC_MAX_LINK_NAME)
+		__dynamic_array(char, buf, (dqueues) ? LINK_LMAX : LINK_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header);
+		memcpy(__entry->name, tipc_link_name(l), TIPC_MAX_LINK_NAME);
+		tipc_link_dump(l, dqueues, __get_str(buf));
+	),
+
+	TP_printk("<%s> %s\n%s", __entry->name, __get_str(header),
+		  __get_str(buf))
+);
+
+#define DEFINE_LINK_EVENT(name) \
+DEFINE_EVENT(tipc_link_class, name, \
+	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
+	TP_ARGS(l, dqueues, header))
+DEFINE_LINK_EVENT(tipc_link_dump);
+DEFINE_LINK_EVENT(tipc_link_conges);
+DEFINE_LINK_EVENT(tipc_link_timeout);
+DEFINE_LINK_EVENT(tipc_link_reset);
+
+#define DEFINE_LINK_EVENT_COND(name, cond) \
+DEFINE_EVENT_CONDITION(tipc_link_class, name, \
+	TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \
+	TP_ARGS(l, dqueues, header), \
+	TP_CONDITION(cond))
+DEFINE_LINK_EVENT_COND(tipc_link_too_silent, tipc_link_too_silent(l));
+
+DECLARE_EVENT_CLASS(tipc_link_transmq_class,
+
+	TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+
+	TP_ARGS(r, f, t, tq),
+
+	TP_STRUCT__entry(
+		__array(char, name, TIPC_MAX_LINK_NAME)
+		__field(u16, from)
+		__field(u16, to)
+		__field(u32, len)
+		__field(u16, fseqno)
+		__field(u16, lseqno)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->name, tipc_link_name(r), TIPC_MAX_LINK_NAME);
+		__entry->from = f;
+		__entry->to = t;
+		__entry->len = skb_queue_len(tq);
+		__entry->fseqno = __entry->len ?
+				  msg_seqno(buf_msg(skb_peek(tq))) : 0;
+		__entry->lseqno = __entry->len ?
+				  msg_seqno(buf_msg(skb_peek_tail(tq))) : 0;
+	),
+
+	TP_printk("<%s> retrans req: [%u-%u] transmq: %u [%u-%u]\n",
+		  __entry->name, __entry->from, __entry->to,
+		  __entry->len, __entry->fseqno, __entry->lseqno)
+);
+
+DEFINE_EVENT_CONDITION(tipc_link_transmq_class, tipc_link_retrans,
+	TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+	TP_ARGS(r, f, t, tq),
+	TP_CONDITION(less_eq(f, t))
+);
+
+DEFINE_EVENT_PRINT(tipc_link_transmq_class, tipc_link_bc_ack,
+	TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq),
+	TP_ARGS(r, f, t, tq),
+	TP_printk("<%s> acked: %u gap: %u transmq: %u [%u-%u]\n",
+		  __entry->name, __entry->from, __entry->to,
+		  __entry->len, __entry->fseqno, __entry->lseqno)
+);
+
+DECLARE_EVENT_CLASS(tipc_node_class,
+
+	TP_PROTO(struct tipc_node *n, bool more, const char *header),
+
+	TP_ARGS(n, more, header),
+
+	TP_STRUCT__entry(
+		__string(header, header)
+		__field(u32, addr)
+		__dynamic_array(char, buf, (more) ? NODE_LMAX : NODE_LMIN)
+	),
+
+	TP_fast_assign(
+		__assign_str(header);
+		__entry->addr = tipc_node_get_addr(n);
+		tipc_node_dump(n, more, __get_str(buf));
+	),
+
+	TP_printk("<%x> %s\n%s", __entry->addr, __get_str(header),
+		  __get_str(buf))
+);
+
+#define DEFINE_NODE_EVENT(name) \
+DEFINE_EVENT(tipc_node_class, name, \
+	TP_PROTO(struct tipc_node *n, bool more, const char *header), \
+	TP_ARGS(n, more, header))
+DEFINE_NODE_EVENT(tipc_node_dump);
+DEFINE_NODE_EVENT(tipc_node_create);
+DEFINE_NODE_EVENT(tipc_node_delete);
+DEFINE_NODE_EVENT(tipc_node_lost_contact);
+DEFINE_NODE_EVENT(tipc_node_timeout);
+DEFINE_NODE_EVENT(tipc_node_link_up);
+DEFINE_NODE_EVENT(tipc_node_link_down);
+DEFINE_NODE_EVENT(tipc_node_reset_links);
+DEFINE_NODE_EVENT(tipc_node_check_state);
+
+DECLARE_EVENT_CLASS(tipc_fsm_class,
+
+	TP_PROTO(const char *name, u32 os, u32 ns, int evt),
+
+	TP_ARGS(name, os, ns, evt),
+
+	TP_STRUCT__entry(
+		__string(name, name)
+		__field(u32, os)
+		__field(u32, ns)
+		__field(u32, evt)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__entry->os = os;
+		__entry->ns = ns;
+		__entry->evt = evt;
+	),
+
+	TP_printk("<%s> %s--(%s)->%s\n", __get_str(name),
+		  state_sym(__entry->os), evt_sym(__entry->evt),
+		  state_sym(__entry->ns))
+);
+
+#define DEFINE_FSM_EVENT(fsm_name) \
+DEFINE_EVENT(tipc_fsm_class, fsm_name, \
+	TP_PROTO(const char *name, u32 os, u32 ns, int evt), \
+	TP_ARGS(name, os, ns, evt))
+DEFINE_FSM_EVENT(tipc_link_fsm);
+DEFINE_FSM_EVENT(tipc_node_fsm);
+
+TRACE_EVENT(tipc_l2_device_event,
+
+	TP_PROTO(struct net_device *dev, struct tipc_bearer *b,
+		 unsigned long evt),
+
+	TP_ARGS(dev, b, evt),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev->name)
+		__string(b_name, b->name)
+		__field(unsigned long, evt)
+		__field(u8, b_up)
+		__field(u8, carrier)
+		__field(u8, oper)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__assign_str(b_name);
+		__entry->evt = evt;
+		__entry->b_up = test_bit(0, &b->up);
+		__entry->carrier = netif_carrier_ok(dev);
+		__entry->oper = netif_oper_up(dev);
+	),
+
+	TP_printk("%s on: <%s>/<%s> oper: %s carrier: %s bearer: %s\n",
+		  dev_evt_sym(__entry->evt), __get_str(dev_name),
+		  __get_str(b_name), (__entry->oper) ? "up" : "down",
+		  (__entry->carrier) ? "ok" : "notok",
+		  (__entry->b_up) ? "up" : "down")
+);
+
+#endif /* _TIPC_TRACE_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>

linux-7.2.3/net/tipc/udp_media.c

@@ -0,0 +1,871 @@
+/* net/tipc/udp_media.c: IP bearer support for TIPC
+ *
+ * Copyright (c) 2015, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/socket.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/inet.h>
+#include <linux/inetdevice.h>
+#include <linux/igmp.h>
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+#include <linux/wait_bit.h>
+#include <linux/list.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/udp_tunnel.h>
+#include <linux/tipc_netlink.h>
+#include "core.h"
+#include "addr.h"
+#include "net.h"
+#include "bearer.h"
+#include "netlink.h"
+#include "msg.h"
+#include "udp_media.h"
+
+/* IANA assigned UDP port */
+#define UDP_PORT_DEFAULT	6118
+
+#define UDP_MIN_HEADROOM        48
+
+/**
+ * struct udp_media_addr - IP/UDP addressing information
+ *
+ * This is the bearer level originating address used in neighbor discovery
+ * messages, and all fields should be in network byte order
+ *
+ * @proto: Ethernet protocol in use
+ * @port: port being used
+ * @ipv4: IPv4 address of neighbor
+ * @ipv6: IPv6 address of neighbor
+ */
+struct udp_media_addr {
+	__be16	proto;
+	__be16	port;
+	union {
+		struct in_addr ipv4;
+		struct in6_addr ipv6;
+	};
+};
+
+/* 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;
+};
+
+/**
+ * struct udp_bearer - ip/udp bearer data structure
+ * @bearer:	associated generic tipc bearer
+ * @sk:		bearer associated socket
+ * @ifindex:	local address scope
+ * @work:	used to schedule deferred work on a bearer
+ * @rcast:	associated udp_replicast container
+ * @rcast_lock:	serialize updates to @rcast.list against concurrent updaters
+ * @disabled:	bearer is being torn down; reject further @rcast.list additions
+ */
+struct udp_bearer {
+	struct tipc_bearer __rcu *bearer;
+	struct sock *sk;
+	u32 ifindex;
+	struct work_struct work;
+	struct udp_replicast rcast;
+	spinlock_t rcast_lock;
+	bool disabled;
+};
+
+static int tipc_udp_is_mcast_addr(struct udp_media_addr *addr)
+{
+	if (ntohs(addr->proto) == ETH_P_IP)
+		return ipv4_is_multicast(addr->ipv4.s_addr);
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		return ipv6_addr_is_multicast(&addr->ipv6);
+#endif
+	return 0;
+}
+
+/* udp_media_addr_set - convert a ip/udp address to a TIPC media address */
+static void tipc_udp_media_addr_set(struct tipc_media_addr *addr,
+				    struct udp_media_addr *ua)
+{
+	memset(addr, 0, sizeof(struct tipc_media_addr));
+	addr->media_id = TIPC_MEDIA_TYPE_UDP;
+	memcpy(addr->value, ua, sizeof(struct udp_media_addr));
+
+	if (tipc_udp_is_mcast_addr(ua))
+		addr->broadcast = TIPC_BROADCAST_SUPPORT;
+}
+
+/* tipc_udp_addr2str - convert ip/udp address to string */
+static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
+{
+	struct udp_media_addr *ua = (struct udp_media_addr *)&a->value;
+
+	if (ntohs(ua->proto) == ETH_P_IP)
+		snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port));
+	else if (ntohs(ua->proto) == ETH_P_IPV6)
+		snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port));
+	else {
+		pr_err("Invalid UDP media address\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+/* tipc_udp_msg2addr - extract an ip/udp address from a TIPC ndisc message */
+static int tipc_udp_msg2addr(struct tipc_bearer *b, struct tipc_media_addr *a,
+			     char *msg)
+{
+	struct udp_media_addr *ua;
+
+	ua = (struct udp_media_addr *) (msg + TIPC_MEDIA_ADDR_OFFSET);
+	if (msg[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_UDP)
+		return -EINVAL;
+	tipc_udp_media_addr_set(a, ua);
+	return 0;
+}
+
+/* tipc_udp_addr2msg - write an ip/udp address to a TIPC ndisc message */
+static int tipc_udp_addr2msg(char *msg, struct tipc_media_addr *a)
+{
+	memset(msg, 0, TIPC_MEDIA_INFO_SIZE);
+	msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_UDP;
+	memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, a->value,
+	       sizeof(struct udp_media_addr));
+	return 0;
+}
+
+/* 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 dst_cache *cache)
+{
+	struct dst_entry *ndst;
+	int ttl, err;
+
+	local_bh_disable();
+	ndst = dst_cache_get(cache);
+	if (dst->proto == htons(ETH_P_IP)) {
+		struct rtable *rt = dst_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);
+		}
+
+		ttl = ip4_dst_hoplimit(&rt->dst);
+		udp_tunnel_xmit_skb(rt, ub->sk, skb, src->ipv4.s_addr,
+				    dst->ipv4.s_addr, 0, ttl, 0, src->port,
+				    dst->port, false, true, 0);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		if (!ndst) {
+			struct flowi6 fl6 = {
+				.flowi6_oif = ub->ifindex,
+				.daddr = dst->ipv6,
+				.saddr = src->ipv6,
+				.flowi6_proto = IPPROTO_UDP
+			};
+			ndst = ip6_dst_lookup_flow(net, ub->sk,
+						   &fl6, NULL);
+			if (IS_ERR(ndst)) {
+				err = PTR_ERR(ndst);
+				goto tx_error;
+			}
+			dst_cache_set_ip6(cache, ndst, &fl6.saddr);
+		}
+		ttl = ip6_dst_hoplimit(ndst);
+		udp_tunnel6_xmit_skb(ndst, ub->sk, skb, NULL,
+				     &src->ipv6, &dst->ipv6, 0, ttl, 0,
+				     src->port, dst->port, false, 0);
+#endif
+	}
+	local_bh_enable();
+	return 0;
+
+tx_error:
+	local_bh_enable();
+	kfree_skb(skb);
+	return err;
+}
+
+static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
+			     struct tipc_bearer *b,
+			     struct tipc_media_addr *addr)
+{
+	struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
+	struct udp_media_addr *dst = (struct udp_media_addr *)&addr->value;
+	struct udp_replicast *rcast;
+	struct udp_bearer *ub;
+	int err = 0;
+
+	if (skb_headroom(skb) < UDP_MIN_HEADROOM) {
+		err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+		if (err)
+			goto out;
+	}
+
+	skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
+	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,
+				     &ub->rcast.dst_cache);
+
+	/* Replicast, send an skb to each configured IP address */
+	list_for_each_entry_rcu(rcast, &ub->rcast.list, list) {
+		struct sk_buff *_skb;
+
+		_skb = pskb_copy(skb, GFP_ATOMIC);
+		if (!_skb) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr,
+				    &rcast->dst_cache);
+		if (err)
+			goto out;
+	}
+	err = 0;
+out:
+	kfree_skb(skb);
+	return err;
+}
+
+static int tipc_udp_rcast_add(struct tipc_bearer *b,
+			      struct udp_media_addr *addr)
+{
+	struct udp_replicast *rcast;
+	struct udp_bearer *ub;
+
+	ub = rcu_dereference_rtnl(b->media_ptr);
+	if (!ub)
+		return -ENODEV;
+
+	spin_lock_bh(&ub->rcast_lock);
+	if (ub->disabled) {
+		spin_unlock_bh(&ub->rcast_lock);
+		return 0;
+	}
+	list_for_each_entry(rcast, &ub->rcast.list, list) {
+		if (!memcmp(&rcast->addr, addr, sizeof(*addr))) {
+			spin_unlock_bh(&ub->rcast_lock);
+			return 0;
+		}
+	}
+
+	rcast = kmalloc_obj(*rcast, GFP_ATOMIC);
+	if (!rcast) {
+		spin_unlock_bh(&ub->rcast_lock);
+		return -ENOMEM;
+	}
+
+	if (dst_cache_init(&rcast->dst_cache, GFP_ATOMIC)) {
+		spin_unlock_bh(&ub->rcast_lock);
+		kfree(rcast);
+		return -ENOMEM;
+	}
+
+	memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr));
+	list_add_rcu(&rcast->list, &ub->rcast.list);
+	b->bcast_addr.broadcast = TIPC_REPLICAST_SUPPORT;
+	spin_unlock_bh(&ub->rcast_lock);
+
+	if (ntohs(addr->proto) == ETH_P_IP)
+		pr_info("New replicast peer: %pI4\n", &rcast->addr.ipv4);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (ntohs(addr->proto) == ETH_P_IPV6)
+		pr_info("New replicast peer: %pI6\n", &rcast->addr.ipv6);
+#endif
+	return 0;
+}
+
+static int tipc_udp_rcast_disc(struct tipc_bearer *b, struct sk_buff *skb)
+{
+	struct udp_media_addr src = {0};
+	struct udp_media_addr *dst;
+
+	dst = (struct udp_media_addr *)&b->bcast_addr.value;
+	if (tipc_udp_is_mcast_addr(dst))
+		return 0;
+
+	src.port = udp_hdr(skb)->source;
+
+	if (ip_hdr(skb)->version == 4) {
+		struct iphdr *iphdr = ip_hdr(skb);
+
+		src.proto = htons(ETH_P_IP);
+		src.ipv4.s_addr = iphdr->saddr;
+		if (ipv4_is_multicast(iphdr->daddr))
+			return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (ip_hdr(skb)->version == 6) {
+		struct ipv6hdr *iphdr = ipv6_hdr(skb);
+
+		src.proto = htons(ETH_P_IPV6);
+		src.ipv6 = iphdr->saddr;
+		if (ipv6_addr_is_multicast(&iphdr->daddr))
+			return 0;
+#endif
+	} else {
+		return 0;
+	}
+
+	return tipc_udp_rcast_add(b, &src);
+}
+
+/* tipc_udp_recv - read data from bearer socket */
+static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct udp_bearer *ub;
+	struct tipc_bearer *b;
+	struct tipc_msg *hdr;
+	int err;
+
+	ub = rcu_dereference_sk_user_data(sk);
+	if (!ub) {
+		pr_err_ratelimited("Failed to get UDP bearer reference");
+		goto out;
+	}
+	skb_pull(skb, sizeof(struct udphdr));
+	hdr = buf_msg(skb);
+
+	b = rcu_dereference(ub->bearer);
+	if (!b)
+		goto out;
+
+	if (b && test_bit(0, &b->up)) {
+		TIPC_SKB_CB(skb)->flags = 0;
+		tipc_rcv(sock_net(sk), skb, b);
+		return 0;
+	}
+
+	if (unlikely(msg_user(hdr) == LINK_CONFIG)) {
+		err = tipc_udp_rcast_disc(b, skb);
+		if (err)
+			goto out;
+	}
+
+out:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote)
+{
+	struct sock *sk = ub->sk;
+	struct ip_mreqn mreqn;
+	int err = 0;
+
+	if (ntohs(remote->proto) == ETH_P_IP) {
+		mreqn.imr_multiaddr = remote->ipv4;
+		mreqn.imr_ifindex = ub->ifindex;
+		err = ip_mc_join_group(sk, &mreqn);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		lock_sock(sk);
+		err = ipv6_sock_mc_join(sk, ub->ifindex, &remote->ipv6);
+		release_sock(sk);
+#endif
+	}
+	return err;
+}
+
+static int __tipc_nl_add_udp_addr(struct sk_buff *skb,
+				  struct udp_media_addr *addr, int nla_t)
+{
+	if (ntohs(addr->proto) == ETH_P_IP) {
+		struct sockaddr_in ip4;
+
+		memset(&ip4, 0, sizeof(ip4));
+		ip4.sin_family = AF_INET;
+		ip4.sin_port = addr->port;
+		ip4.sin_addr.s_addr = addr->ipv4.s_addr;
+		if (nla_put(skb, nla_t, sizeof(ip4), &ip4))
+			return -EMSGSIZE;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (ntohs(addr->proto) == ETH_P_IPV6) {
+		struct sockaddr_in6 ip6;
+
+		memset(&ip6, 0, sizeof(ip6));
+		ip6.sin6_family = AF_INET6;
+		ip6.sin6_port  = addr->port;
+		memcpy(&ip6.sin6_addr, &addr->ipv6, sizeof(struct in6_addr));
+		if (nla_put(skb, nla_t, sizeof(ip6), &ip6))
+			return -EMSGSIZE;
+#endif
+	}
+
+	return 0;
+}
+
+int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	u32 bid = cb->args[0];
+	u32 skip_cnt = cb->args[1];
+	u32 portid = NETLINK_CB(cb->skb).portid;
+	struct udp_replicast *rcast, *tmp;
+	struct tipc_bearer *b;
+	struct udp_bearer *ub;
+	void *hdr;
+	int err;
+	int i;
+
+	if (!bid && !skip_cnt) {
+		struct nlattr **attrs = genl_dumpit_info(cb)->info.attrs;
+		struct net *net = sock_net(skb->sk);
+		struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1];
+		char *bname;
+
+		if (!attrs[TIPC_NLA_BEARER])
+			return -EINVAL;
+
+		err = nla_parse_nested_deprecated(battrs, TIPC_NLA_BEARER_MAX,
+						  attrs[TIPC_NLA_BEARER],
+						  tipc_nl_bearer_policy, NULL);
+		if (err)
+			return err;
+
+		if (!battrs[TIPC_NLA_BEARER_NAME])
+			return -EINVAL;
+
+		bname = nla_data(battrs[TIPC_NLA_BEARER_NAME]);
+
+		rtnl_lock();
+		b = tipc_bearer_find(net, bname);
+		if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
+			rtnl_unlock();
+			return -EINVAL;
+		}
+		bid = b->identity;
+	} else {
+		struct net *net = sock_net(skb->sk);
+		struct tipc_net *tn = net_generic(net, tipc_net_id);
+
+		rtnl_lock();
+		b = rtnl_dereference(tn->bearer_list[bid]);
+		if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
+			rtnl_unlock();
+			return -EINVAL;
+		}
+	}
+
+	ub = rtnl_dereference(b->media_ptr);
+	if (!ub) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	i = 0;
+	list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) {
+		if (i < skip_cnt)
+			goto count;
+
+		hdr = genlmsg_put(skb, portid, cb->nlh->nlmsg_seq,
+				  &tipc_genl_family, NLM_F_MULTI,
+				  TIPC_NL_BEARER_GET);
+		if (!hdr)
+			goto done;
+
+		err = __tipc_nl_add_udp_addr(skb, &rcast->addr,
+					     TIPC_NLA_UDP_REMOTE);
+		if (err) {
+			genlmsg_cancel(skb, hdr);
+			goto done;
+		}
+		genlmsg_end(skb, hdr);
+count:
+		i++;
+	}
+done:
+	rtnl_unlock();
+	cb->args[0] = bid;
+	cb->args[1] = i;
+
+	return skb->len;
+}
+
+int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b)
+{
+	struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
+	struct udp_media_addr *dst;
+	struct udp_bearer *ub;
+	struct nlattr *nest;
+
+	ub = rtnl_dereference(b->media_ptr);
+	if (!ub)
+		return -ENODEV;
+
+	nest = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_UDP_OPTS);
+	if (!nest)
+		goto msg_full;
+
+	if (__tipc_nl_add_udp_addr(msg->skb, src, TIPC_NLA_UDP_LOCAL))
+		goto msg_full;
+
+	dst = (struct udp_media_addr *)&b->bcast_addr.value;
+	if (__tipc_nl_add_udp_addr(msg->skb, dst, TIPC_NLA_UDP_REMOTE))
+		goto msg_full;
+
+	if (!list_empty(&ub->rcast.list)) {
+		if (nla_put_flag(msg->skb, TIPC_NLA_UDP_MULTI_REMOTEIP))
+			goto msg_full;
+	}
+
+	nla_nest_end(msg->skb, nest);
+	return 0;
+msg_full:
+	nla_nest_cancel(msg->skb, nest);
+	return -EMSGSIZE;
+}
+
+/**
+ * tipc_parse_udp_addr - build udp media address from netlink data
+ * @nla:	netlink attribute containing sockaddr storage aligned address
+ * @addr:	tipc media address to fill with address, port and protocol type
+ * @scope_id:	IPv6 scope id pointer, not NULL indicates it's required
+ */
+
+static int tipc_parse_udp_addr(struct nlattr *nla, struct udp_media_addr *addr,
+			       u32 *scope_id)
+{
+	struct sockaddr_storage sa;
+
+	nla_memcpy(&sa, nla, sizeof(sa));
+	if (sa.ss_family == AF_INET) {
+		struct sockaddr_in *ip4 = (struct sockaddr_in *)&sa;
+
+		addr->proto = htons(ETH_P_IP);
+		addr->port = ip4->sin_port;
+		addr->ipv4.s_addr = ip4->sin_addr.s_addr;
+		return 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (sa.ss_family == AF_INET6) {
+		struct sockaddr_in6 *ip6 = (struct sockaddr_in6 *)&sa;
+
+		addr->proto = htons(ETH_P_IPV6);
+		addr->port = ip6->sin6_port;
+		memcpy(&addr->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr));
+
+		/* Scope ID is only interesting for local addresses */
+		if (scope_id) {
+			int atype;
+
+			atype = ipv6_addr_type(&ip6->sin6_addr);
+			if (__ipv6_addr_needs_scope_id(atype) &&
+			    !ip6->sin6_scope_id) {
+				return -EINVAL;
+			}
+
+			*scope_id = ip6->sin6_scope_id ? : 0;
+		}
+
+		return 0;
+#endif
+	}
+	return -EADDRNOTAVAIL;
+}
+
+int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr)
+{
+	int err;
+	struct udp_media_addr addr = {0};
+	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
+	struct udp_media_addr *dst;
+
+	if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy, NULL))
+		return -EINVAL;
+
+	if (!opts[TIPC_NLA_UDP_REMOTE])
+		return -EINVAL;
+
+	err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &addr, NULL);
+	if (err)
+		return err;
+
+	dst = (struct udp_media_addr *)&b->bcast_addr.value;
+	if (tipc_udp_is_mcast_addr(dst)) {
+		pr_err("Can't add remote ip to TIPC UDP multicast bearer\n");
+		return -EINVAL;
+	}
+
+	return tipc_udp_rcast_add(b, &addr);
+}
+
+/**
+ * tipc_udp_enable - callback to create a new udp bearer instance
+ * @net:	network namespace
+ * @b:		pointer to generic tipc_bearer
+ * @attrs:	netlink bearer configuration
+ *
+ * validate the bearer parameters and initialize the udp bearer
+ * rtnl_lock should be held
+ */
+static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
+			   struct nlattr *attrs[])
+{
+	int err = -EINVAL;
+	struct udp_bearer *ub;
+	struct udp_media_addr remote = {0};
+	struct udp_media_addr local = {0};
+	struct udp_port_cfg udp_conf = {0};
+	struct udp_tunnel_sock_cfg tuncfg = {NULL};
+	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
+	u8 node_id[NODE_ID_LEN] = {0,};
+	struct net_device *dev;
+	struct socket *sock;
+	int rmcast = 0;
+
+	ub = kzalloc_obj(*ub, GFP_ATOMIC);
+	if (!ub)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ub->rcast.list);
+	spin_lock_init(&ub->rcast_lock);
+
+	if (!attrs[TIPC_NLA_BEARER_UDP_OPTS])
+		goto err;
+
+	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]) {
+		pr_err("Invalid UDP bearer configuration");
+		err = -EINVAL;
+		goto err;
+	}
+
+	err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_LOCAL], &local,
+				  &ub->ifindex);
+	if (err)
+		goto err;
+
+	err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &remote, NULL);
+	if (err)
+		goto err;
+
+	if (remote.proto != local.proto) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	/* Checking remote ip address */
+	rmcast = tipc_udp_is_mcast_addr(&remote);
+
+	/* Autoconfigure own node identity if needed */
+	if (!tipc_own_id(net)) {
+		memcpy(node_id, local.ipv6.in6_u.u6_addr8, 16);
+		tipc_net_init(net, node_id, 0);
+	}
+	if (!tipc_own_id(net)) {
+		pr_warn("Failed to set node id, please configure manually\n");
+		err = -EINVAL;
+		goto err;
+	}
+
+	b->bcast_addr.media_id = TIPC_MEDIA_TYPE_UDP;
+	b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT;
+	rcu_assign_pointer(b->media_ptr, ub);
+	rcu_assign_pointer(ub->bearer, b);
+	tipc_udp_media_addr_set(&b->addr, &local);
+	if (local.proto == htons(ETH_P_IP)) {
+		dev = __ip_dev_find(net, local.ipv4.s_addr, false);
+		if (!dev) {
+			err = -ENODEV;
+			goto err;
+		}
+		udp_conf.family = AF_INET;
+
+		/* Switch to use ANY to receive packets from group */
+		if (rmcast)
+			udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+		else
+			udp_conf.local_ip.s_addr = local.ipv4.s_addr;
+		udp_conf.use_udp_checksums = false;
+		ub->ifindex = dev->ifindex;
+		b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr);
+		b->mtu = b->media->mtu;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else if (local.proto == htons(ETH_P_IPV6)) {
+		dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL;
+		dev = ipv6_dev_find(net, &local.ipv6, dev);
+		if (!dev) {
+			err = -ENODEV;
+			goto err;
+		}
+		udp_conf.family = AF_INET6;
+		udp_conf.use_udp6_tx_checksums = true;
+		udp_conf.use_udp6_rx_checksums = true;
+		if (rmcast)
+			udp_conf.local_ip6 = in6addr_any;
+		else
+			udp_conf.local_ip6 = local.ipv6;
+		ub->ifindex = dev->ifindex;
+		b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr);
+		b->mtu = 1280;
+#endif
+	} else {
+		err = -EAFNOSUPPORT;
+		goto err;
+	}
+	udp_conf.local_udp_port = local.port;
+	err = udp_sock_create(net, &udp_conf, &sock);
+	if (err)
+		goto err;
+
+	ub->sk = sock->sk;
+	tuncfg.sk_user_data = ub;
+	tuncfg.encap_type = 1;
+	tuncfg.encap_rcv = tipc_udp_recv;
+	tuncfg.encap_destroy = NULL;
+	setup_udp_tunnel_sock(net, ub->sk, &tuncfg);
+
+	err = dst_cache_init(&ub->rcast.dst_cache, GFP_ATOMIC);
+	if (err)
+		goto free;
+
+	/*
+	 * The bcast media address port is used for all peers and the ip
+	 * is used if it's a multicast address.
+	 */
+	memcpy(&b->bcast_addr.value, &remote, sizeof(remote));
+	if (rmcast)
+		err = enable_mcast(ub, &remote);
+	else
+		err = tipc_udp_rcast_add(b, &remote);
+	if (err)
+		goto free;
+
+	return 0;
+
+free:
+	dst_cache_destroy(&ub->rcast.dst_cache);
+	udp_tunnel_sock_release(ub->sk);
+	synchronize_rcu();
+err:
+	kfree(ub);
+	return err;
+}
+
+static void rcast_free_rcu(struct rcu_head *rcu)
+{
+	struct udp_replicast *rcast = container_of(rcu, struct udp_replicast, rcu);
+
+	dst_cache_destroy(&rcast->dst_cache);
+	kfree(rcast);
+}
+
+/* cleanup_bearer - break the socket/bearer association */
+static void cleanup_bearer(struct work_struct *work)
+{
+	struct udp_bearer *ub = container_of(work, struct udp_bearer, work);
+	struct udp_replicast *rcast, *tmp;
+	struct tipc_net *tn;
+
+	spin_lock_bh(&ub->rcast_lock);
+	list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) {
+		list_del_rcu(&rcast->list);
+		call_rcu_hurry(&rcast->rcu, rcast_free_rcu);
+	}
+	ub->disabled = true;
+	spin_unlock_bh(&ub->rcast_lock);
+
+	tn = tipc_net(sock_net(ub->sk));
+
+	udp_tunnel_sock_release(ub->sk);
+
+	synchronize_net();
+
+	dst_cache_destroy(&ub->rcast.dst_cache);
+	if (atomic_dec_and_test(&tn->wq_count))
+		wake_up_var(&tn->wq_count);
+	kfree(ub);
+}
+
+/* tipc_udp_disable - detach bearer from socket */
+static void tipc_udp_disable(struct tipc_bearer *b)
+{
+	struct udp_bearer *ub;
+
+	ub = rtnl_dereference(b->media_ptr);
+	if (!ub) {
+		pr_err("UDP bearer instance not found\n");
+		return;
+	}
+	sock_set_flag(ub->sk, SOCK_DEAD);
+	RCU_INIT_POINTER(ub->bearer, NULL);
+
+	/* sock_release need to be done outside of rtnl lock */
+	atomic_inc(&tipc_net(sock_net(ub->sk))->wq_count);
+	INIT_WORK(&ub->work, cleanup_bearer);
+	schedule_work(&ub->work);
+}
+
+struct tipc_media udp_media_info = {
+	.send_msg	= tipc_udp_send_msg,
+	.enable_media	= tipc_udp_enable,
+	.disable_media	= tipc_udp_disable,
+	.addr2str	= tipc_udp_addr2str,
+	.addr2msg	= tipc_udp_addr2msg,
+	.msg2addr	= tipc_udp_msg2addr,
+	.priority	= TIPC_DEF_LINK_PRI,
+	.tolerance	= TIPC_DEF_LINK_TOL,
+	.min_win	= TIPC_DEF_LINK_WIN,
+	.max_win	= TIPC_DEF_LINK_WIN,
+	.mtu		= TIPC_DEF_LINK_UDP_MTU,
+	.type_id	= TIPC_MEDIA_TYPE_UDP,
+	.hwaddr_len	= 0,
+	.name		= "udp"
+};

linux-7.2.3/net/tipc/udp_media.h

@@ -0,0 +1,60 @@
+/*
+ * net/tipc/udp_media.h: Include file for UDP bearer media
+ *
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * 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_MEDIA_UDP
+#ifndef _TIPC_UDP_MEDIA_H
+#define _TIPC_UDP_MEDIA_H
+
+#include <linux/ip.h>
+#include <linux/udp.h>
+
+int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr);
+int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b);
+int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb);
+
+/* check if configured MTU is too low for tipc headers */
+static inline bool tipc_udp_mtu_bad(u32 mtu)
+{
+	if (mtu >= (TIPC_MIN_BEARER_MTU + sizeof(struct iphdr) +
+	    sizeof(struct udphdr)))
+		return false;
+
+	pr_warn("MTU too low for tipc bearer\n");
+	return true;
+}
+
+#endif
+#endif