Merge branch 'tipc-comm-groups'

Jon Maloy says:

====================
tipc: Introduce Communcation Group feature

With this commit series we introduce a 'Group Communication' feature in
order to resolve the datagram and multicast flow control problem. This
new feature makes it possible for a user to instantiate multiple private
virtual brokerless message buses by just creating and joining member
sockets.

The main features are as follows:
---------------------------------
- Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN.
  If it is the first socket of the group this implies creation of the
  group. This call takes four parameters: 'type' serves as group
  identifier, 'instance' serves as member identifier, and 'scope'
  indicates the visibility of the group (node/cluster/zone). Finally,
  'flags' indicates different options for the socket joining the group.
  For the time being, there are only two such flags: 1) 'LOOPBACK'
  indicates if the creator of the socket wants to receive a copy of
  broadcast or multicast messages it sends to the group, 2) EVENTS
  indicates if it wants to receive membership (JOINED/LEFT) events for
  the other members of the group.

- Groups are closed, i.e., sockets which have not joined a group will
  not be able to send messages to or receive messages from members of
  the group, and vice versa. A socket can only be member of one group
  at a time.

- There are four transmission modes.
  1: Unicast. The sender transmits a message using the port identity
     (node:port tuple) of the receiving socket.
  2: Anycast. The sender transmits a message using a port name (type:
     instance:scope) of one of the receiving sockets. If more than
     one member socket matches the given address a destination is
     selected according to a round-robin algorithm, but also considering
     the destination load (advertised window size) as an additional
     criteria.
  3: Multicast. The sender transmits a message using a port name
     (type:instance:scope) of one or more of the receiving sockets.
     All sockets in the group matching the given address will receive
     a copy of the message.
  4: Broadcast. The sender transmits a message using the primtive
     send(). All members of the group, irrespective of their member
     identity (instance) number receive a copy of the message.

- TIPC broadcast is used for carrying messages in mode 3 or 4 when
  this is deemed more efficient, i.e., depending on number of actual
  destinations.

- All transmission modes are flow controlled, so that messages never
  are dropped or rejected, just like we are used to from connection
  oriented communication. A special algorithm guarantees that this is
  true even for multipoint-to-point communication, i.e., at occasions
  where many source sockets may decide to send simultaneously towards
  the same  destination socket.

- Sequence order is always guaranteed, even between the different
  transmission modes.

- Member join/leave events are received in all other member sockets
  in guaranteed order. I.e., a 'JOINED' (an empty message with the OOB
  bit set) will always be received before the first data message from
  a new member, and a 'LEAVE' (like 'JOINED', but with EOR bit set) will
  always arrive after the last data message from a leaving member.

-----
v2: Reordered variable declarations in descending length order, as per
    feedback from David Miller. This was done as far as permitted by the
    the initialization order.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 110 insertions, 8 deletions

diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index c843fd2bc48d..cedf811317fb 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/msg.h: Include file for TIPC message header routines
  *
- * Copyright (c) 2000-2007, 2014-2015 Ericsson AB
+ * Copyright (c) 2000-2007, 2014-2017 Ericsson AB
  * Copyright (c) 2005-2008, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -61,10 +61,14 @@ struct plist;
 /*
  * Payload message types
  */
-#define TIPC_CONN_MSG		0
-#define TIPC_MCAST_MSG		1
-#define TIPC_NAMED_MSG		2
-#define TIPC_DIRECT_MSG		3
+#define TIPC_CONN_MSG           0
+#define TIPC_MCAST_MSG          1
+#define TIPC_NAMED_MSG          2
+#define TIPC_DIRECT_MSG         3
+#define TIPC_GRP_MEMBER_EVT     4
+#define TIPC_GRP_BCAST_MSG      5
+#define TIPC_GRP_MCAST_MSG      6
+#define TIPC_GRP_UCAST_MSG      7
 
 /*
  * Internal message users
@@ -73,11 +77,13 @@ struct plist;
 #define  MSG_BUNDLER          6
 #define  LINK_PROTOCOL        7
 #define  CONN_MANAGER         8
+#define  GROUP_PROTOCOL       9
 #define  TUNNEL_PROTOCOL      10
 #define  NAME_DISTRIBUTOR     11
 #define  MSG_FRAGMENTER       12
 #define  LINK_CONFIG          13
 #define  SOCK_WAKEUP          14       /* pseudo user */
+#define  TOP_SRV              15       /* pseudo user */
 
 /*
  * Message header sizes
@@ -86,6 +92,7 @@ struct plist;
 #define BASIC_H_SIZE              32	/* Basic payload message */
 #define NAMED_H_SIZE              40	/* Named payload message */
 #define MCAST_H_SIZE              44	/* Multicast payload message */
+#define GROUP_H_SIZE              44	/* Group payload message */
 #define INT_H_SIZE                40	/* Internal messages */
 #define MIN_H_SIZE                24	/* Smallest legal TIPC header size */
 #define MAX_H_SIZE                60	/* Largest possible TIPC header size */
@@ -96,6 +103,7 @@ struct plist;
 
 struct tipc_skb_cb {
 	u32 bytes_read;
+	u32 orig_member;
 	struct sk_buff *tail;
 	bool validated;
 	u16 chain_imp;
@@ -188,6 +196,11 @@ static inline u32 msg_size(struct tipc_msg *m)
 	return msg_bits(m, 0, 0, 0x1ffff);
 }
 
+static inline u32 msg_blocks(struct tipc_msg *m)
+{
+	return (msg_size(m) / 1024) + 1;
+}
+
 static inline u32 msg_data_sz(struct tipc_msg *m)
 {
 	return msg_size(m) - msg_hdr_sz(m);
@@ -251,6 +264,18 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 1, 29, 0x7, n);
 }
 
+static inline int msg_in_group(struct tipc_msg *m)
+{
+	int mtyp = msg_type(m);
+
+	return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG;
+}
+
+static inline bool msg_is_grp_evt(struct tipc_msg *m)
+{
+	return msg_type(m) == TIPC_GRP_MEMBER_EVT;
+}
+
 static inline u32 msg_named(struct tipc_msg *m)
 {
 	return msg_type(m) == TIPC_NAMED_MSG;
@@ -258,7 +283,10 @@ static inline u32 msg_named(struct tipc_msg *m)
 
 static inline u32 msg_mcast(struct tipc_msg *m)
 {
-	return msg_type(m) == TIPC_MCAST_MSG;
+	int mtyp = msg_type(m);
+
+	return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) ||
+		(mtyp == TIPC_GRP_MCAST_MSG));
 }
 
 static inline u32 msg_connected(struct tipc_msg *m)
@@ -514,6 +542,16 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
 #define DSC_RESP_MSG		1
 
 /*
+ * Group protocol message types
+ */
+#define GRP_JOIN_MSG         0
+#define GRP_LEAVE_MSG        1
+#define GRP_ADV_MSG          2
+#define GRP_ACK_MSG          3
+#define GRP_RECLAIM_MSG      4
+#define GRP_REMIT_MSG        5
+
+/*
  * Word 1
  */
 static inline u32 msg_seq_gap(struct tipc_msg *m)
@@ -764,12 +802,12 @@ static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 9, 16, 0xffff, n);
 }
 
-static inline u32 msg_adv_win(struct tipc_msg *m)
+static inline u16 msg_adv_win(struct tipc_msg *m)
 {
 	return msg_bits(m, 9, 0, 0xffff);
 }
 
-static inline void msg_set_adv_win(struct tipc_msg *m, u32 n)
+static inline void msg_set_adv_win(struct tipc_msg *m, u16 n)
 {
 	msg_set_bits(m, 9, 0, 0xffff, n);
 }
@@ -794,6 +832,68 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n)
 	msg_set_bits(m, 9, 0, 0xffff, n);
 }
 
+static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m)
+{
+	return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n)
+{
+	msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+static inline u16 msg_grp_bc_acked(struct tipc_msg *m)
+{
+	return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n)
+{
+	msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+static inline u16 msg_grp_remitted(struct tipc_msg *m)
+{
+	return msg_bits(m, 9, 16, 0xffff);
+}
+
+static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n)
+{
+	msg_set_bits(m, 9, 16, 0xffff, n);
+}
+
+/* Word 10
+ */
+static inline u16 msg_grp_evt(struct tipc_msg *m)
+{
+	return msg_bits(m, 10, 0, 0x3);
+}
+
+static inline void msg_set_grp_evt(struct tipc_msg *m, int n)
+{
+	msg_set_bits(m, 10, 0, 0x3, n);
+}
+
+static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m)
+{
+	return msg_bits(m, 10, 0, 0x1);
+}
+
+static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n)
+{
+	msg_set_bits(m, 10, 0, 0x1, n);
+}
+
+static inline u16 msg_grp_bc_seqno(struct tipc_msg *m)
+{
+	return msg_bits(m, 10, 16, 0xffff);
+}
+
+static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n)
+{
+	msg_set_bits(m, 10, 16, 0xffff, n);
+}
+
 static inline bool msg_peer_link_is_up(struct tipc_msg *m)
 {
 	if (likely(msg_user(m) != LINK_PROTOCOL))
@@ -818,6 +918,8 @@ static inline bool msg_is_reset(struct tipc_msg *hdr)
 struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp);
 bool tipc_msg_validate(struct sk_buff *skb);
 bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err);
+void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
+		     struct sk_buff_head *xmitq);
 void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type,
 		   u32 hsize, u32 destnode);
 struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,