linux_old1/net/tipc/msg.h

1204 lines
26 KiB
C
Raw Normal View History

/*
* net/tipc/msg.h: Include file for TIPC message header routines
*
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
* Copyright (c) 2000-2007, 2014-2017 Ericsson AB
* Copyright (c) 2005-2008, 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_MSG_H
#define _TIPC_MSG_H
#include <linux/tipc.h>
#include "core.h"
/*
* Constants and routines used to read and write TIPC payload message headers
*
* Note: Some items are also used with TIPC internal message headers
*/
#define TIPC_VERSION 2
tipc: resolve race problem at unicast message reception TIPC handles message cardinality and sequencing at the link layer, before passing messages upwards to the destination sockets. During the upcall from link to socket no locks are held. It is therefore possible, and we see it happen occasionally, that messages arriving in different threads and delivered in sequence still bypass each other before they reach the destination socket. This must not happen, since it violates the sequentiality guarantee. We solve this by adding a new input buffer queue to the link structure. Arriving messages are added safely to the tail of that queue by the link, while the head of the queue is consumed, also safely, by the receiving socket. Sequentiality is secured per socket by only allowing buffers to be dequeued inside the socket lock. Since there may be multiple simultaneous readers of the queue, we use a 'filter' parameter to reduce the risk that they peek the same buffer from the queue, hence also reducing the risk of contention on the receiving socket locks. This solves the sequentiality problem, and seems to cause no measurable performance degradation. A nice side effect of this change is that lock handling in the functions tipc_rcv() and tipc_bcast_rcv() now becomes uniform, something that will enable future simplifications of those functions. Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-05 21:36:41 +08:00
struct plist;
/*
* Payload message users are defined in TIPC's public API:
* - TIPC_LOW_IMPORTANCE
* - TIPC_MEDIUM_IMPORTANCE
* - TIPC_HIGH_IMPORTANCE
* - TIPC_CRITICAL_IMPORTANCE
*/
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
#define TIPC_SYSTEM_IMPORTANCE 4
/*
* Payload message types
*/
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
#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
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
/*
* Internal message users
*/
#define BCAST_PROTOCOL 5
#define MSG_BUNDLER 6
#define LINK_PROTOCOL 7
#define CONN_MANAGER 8
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
#define GROUP_PROTOCOL 9
#define TUNNEL_PROTOCOL 10
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
#define NAME_DISTRIBUTOR 11
#define MSG_FRAGMENTER 12
#define LINK_CONFIG 13
#define SOCK_WAKEUP 14 /* pseudo user */
#define TOP_SRV 15 /* pseudo user */
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
/*
* Message header sizes
*/
#define SHORT_H_SIZE 24 /* In-cluster basic payload message */
#define BASIC_H_SIZE 32 /* Basic payload message */
#define NAMED_H_SIZE 40 /* Named payload message */
#define MCAST_H_SIZE 44 /* Multicast payload message */
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
#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 */
#define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE)
#define FB_MTU 3744
#define TIPC_MEDIA_INFO_OFFSET 5
struct tipc_skb_cb {
struct sk_buff *tail;
unsigned long nxt_retr;
2019-08-15 11:24:08 +08:00
unsigned long retr_stamp;
u32 bytes_read;
u32 orig_member;
u16 chain_imp;
u16 ackers;
2019-08-15 11:24:08 +08:00
u16 retr_cnt;
bool validated;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
struct tipc_msg {
__be32 hdr[15];
};
tipc: improve TIPC throughput by Gap ACK blocks During unicast link transmission, it's observed very often that because of one or a few lost/dis-ordered packets, the sending side will fastly reach the send window limit and must wait for the packets to be arrived at the receiving side or in the worst case, a retransmission must be done first. The sending side cannot release a lot of subsequent packets in its transmq even though all of them might have already been received by the receiving side. That is, one or two packets dis-ordered/lost and dozens of packets have to wait, this obviously reduces the overall throughput! This commit introduces an algorithm to overcome this by using "Gap ACK blocks". Basically, a Gap ACK block will consist of <ack, gap> numbers that describes the link deferdq where packets have been got by the receiving side but with gaps, for example: link deferdq: [1 2 3 4 10 11 13 14 15 20] --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0> The Gap ACK blocks will be sent to the sending side along with the traditional ACK or NACK message. Immediately when receiving the message the sending side will now not only release from its transmq the packets ack-ed by the ACK but also by the Gap ACK blocks! So, more packets can be enqueued and transmitted. In addition, the sending side can now do "multi-retransmissions" according to the Gaps reported in the Gap ACK blocks. The new algorithm as verified helps greatly improve the TIPC throughput especially under packet loss condition. So far, a maximum of 32 blocks is quite enough without any "Too few Gap ACK blocks" reports with a 5.0% packet loss rate, however this number can be increased in the furture if needed. Also, the patch is backward compatible. Acked-by: Ying Xue <ying.xue@windriver.com> Acked-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-04 12:09:51 +08:00
/* struct tipc_gap_ack - TIPC Gap ACK block
* @ack: seqno of the last consecutive packet in link deferdq
* @gap: number of gap packets since the last ack
*
* E.g:
* link deferdq: 1 2 3 4 10 11 13 14 15 20
* --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0>
*/
struct tipc_gap_ack {
__be16 ack;
__be16 gap;
};
/* struct tipc_gap_ack_blks
* @len: actual length of the record
* @gack_cnt: number of Gap ACK blocks in the record
* @gacks: array of Gap ACK blocks
*/
struct tipc_gap_ack_blks {
__be16 len;
u8 gack_cnt;
u8 reserved;
struct tipc_gap_ack gacks[];
};
#define tipc_gap_ack_blks_sz(n) (sizeof(struct tipc_gap_ack_blks) + \
sizeof(struct tipc_gap_ack) * (n))
#define MAX_GAP_ACK_BLKS 32
#define MAX_GAP_ACK_BLKS_SZ tipc_gap_ack_blks_sz(MAX_GAP_ACK_BLKS)
static inline struct tipc_msg *buf_msg(struct sk_buff *skb)
{
return (struct tipc_msg *)skb->data;
}
static inline u32 msg_word(struct tipc_msg *m, u32 pos)
{
return ntohl(m->hdr[pos]);
}
static inline void msg_set_word(struct tipc_msg *m, u32 w, u32 val)
{
m->hdr[w] = htonl(val);
}
static inline u32 msg_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask)
{
return (msg_word(m, w) >> pos) & mask;
}
static inline void msg_set_bits(struct tipc_msg *m, u32 w,
u32 pos, u32 mask, u32 val)
{
val = (val & mask) << pos;
mask = mask << pos;
m->hdr[w] &= ~htonl(mask);
m->hdr[w] |= htonl(val);
}
static inline void msg_swap_words(struct tipc_msg *msg, u32 a, u32 b)
{
u32 temp = msg->hdr[a];
msg->hdr[a] = msg->hdr[b];
msg->hdr[b] = temp;
}
/*
* Word 0
*/
static inline u32 msg_version(struct tipc_msg *m)
{
return msg_bits(m, 0, 29, 7);
}
static inline void msg_set_version(struct tipc_msg *m)
{
msg_set_bits(m, 0, 29, 7, TIPC_VERSION);
}
static inline u32 msg_user(struct tipc_msg *m)
{
return msg_bits(m, 0, 25, 0xf);
}
static inline u32 msg_isdata(struct tipc_msg *m)
{
return msg_user(m) <= TIPC_CRITICAL_IMPORTANCE;
}
static inline void msg_set_user(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 0, 25, 0xf, n);
}
static inline u32 msg_hdr_sz(struct tipc_msg *m)
{
return msg_bits(m, 0, 21, 0xf) << 2;
}
static inline void msg_set_hdr_sz(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 0, 21, 0xf, n>>2);
}
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);
}
static inline int msg_non_seq(struct tipc_msg *m)
{
return msg_bits(m, 0, 20, 1);
}
static inline void msg_set_non_seq(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 0, 20, 1, n);
}
static inline int msg_is_syn(struct tipc_msg *m)
{
return msg_bits(m, 0, 17, 1);
}
static inline void msg_set_syn(struct tipc_msg *m, u32 d)
{
msg_set_bits(m, 0, 17, 1, d);
}
static inline int msg_dest_droppable(struct tipc_msg *m)
{
return msg_bits(m, 0, 19, 1);
}
static inline void msg_set_dest_droppable(struct tipc_msg *m, u32 d)
{
msg_set_bits(m, 0, 19, 1, d);
}
static inline int msg_is_keepalive(struct tipc_msg *m)
{
return msg_bits(m, 0, 19, 1);
}
static inline void msg_set_is_keepalive(struct tipc_msg *m, u32 d)
{
msg_set_bits(m, 0, 19, 1, d);
}
static inline int msg_src_droppable(struct tipc_msg *m)
{
return msg_bits(m, 0, 18, 1);
}
static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d)
{
msg_set_bits(m, 0, 18, 1, d);
}
static inline bool msg_is_rcast(struct tipc_msg *m)
{
return msg_bits(m, 0, 18, 0x1);
}
static inline void msg_set_is_rcast(struct tipc_msg *m, bool d)
{
msg_set_bits(m, 0, 18, 0x1, d);
}
static inline void msg_set_size(struct tipc_msg *m, u32 sz)
{
m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz);
}
static inline unchar *msg_data(struct tipc_msg *m)
{
return ((unchar *)m) + msg_hdr_sz(m);
}
static inline struct tipc_msg *msg_inner_hdr(struct tipc_msg *m)
{
return (struct tipc_msg *)msg_data(m);
}
/*
* Word 1
*/
static inline u32 msg_type(struct tipc_msg *m)
{
return msg_bits(m, 1, 29, 0x7);
}
static inline void msg_set_type(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 1, 29, 0x7, n);
}
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
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;
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
}
static inline u32 msg_named(struct tipc_msg *m)
{
return msg_type(m) == TIPC_NAMED_MSG;
}
static inline u32 msg_mcast(struct tipc_msg *m)
{
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
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)
{
return msg_type(m) == TIPC_CONN_MSG;
}
static inline u32 msg_errcode(struct tipc_msg *m)
{
return msg_bits(m, 1, 25, 0xf);
}
static inline void msg_set_errcode(struct tipc_msg *m, u32 err)
{
msg_set_bits(m, 1, 25, 0xf, err);
}
static inline u32 msg_reroute_cnt(struct tipc_msg *m)
{
return msg_bits(m, 1, 21, 0xf);
}
static inline void msg_incr_reroute_cnt(struct tipc_msg *m)
{
msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1);
}
static inline void msg_reset_reroute_cnt(struct tipc_msg *m)
{
msg_set_bits(m, 1, 21, 0xf, 0);
}
static inline u32 msg_lookup_scope(struct tipc_msg *m)
{
return msg_bits(m, 1, 19, 0x3);
}
static inline void msg_set_lookup_scope(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 1, 19, 0x3, n);
}
static inline u16 msg_bcast_ack(struct tipc_msg *m)
{
return msg_bits(m, 1, 0, 0xffff);
}
static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 1, 0, 0xffff, n);
}
tipc: fix link session and re-establish issues When a link endpoint is re-created (e.g. after a node reboot or interface reset), the link session number is varied by random, the peer endpoint will be synced with this new session number before the link is re-established. However, there is a shortcoming in this mechanism that can lead to the link never re-established or faced with a failure then. It happens when the peer endpoint is ready in ESTABLISHING state, the 'peer_session' as well as the 'in_session' flag have been set, but suddenly this link endpoint leaves. When it comes back with a random session number, there are two situations possible: 1/ If the random session number is larger than (or equal to) the previous one, the peer endpoint will be updated with this new session upon receipt of a RESET_MSG from this endpoint, and the link can be re- established as normal. Otherwise, all the RESET_MSGs from this endpoint will be rejected by the peer. In turn, when this link endpoint receives one ACTIVATE_MSG from the peer, it will move to ESTABLISHED and start to send STATE_MSGs, but again these messages will be dropped by the peer due to wrong session. The peer link endpoint can still become ESTABLISHED after receiving a traffic message from this endpoint (e.g. a BCAST_PROTOCOL or NAME_DISTRIBUTOR), but since all the STATE_MSGs are invalid, the link will be forced down sooner or later! Even in case the random session number is larger than the previous one, it can be that the ACTIVATE_MSG from the peer arrives first, and this link endpoint moves quickly to ESTABLISHED without sending out any RESET_MSG yet. Consequently, the peer link will not be updated with the new session number, and the same link failure scenario as above will happen. 2/ Another situation can be that, the peer link endpoint was reset due to any reasons in the meantime, its link state was set to RESET from ESTABLISHING but still in session, i.e. the 'in_session' flag is not reset... Now, if the random session number from this endpoint is less than the previous one, all the RESET_MSGs from this endpoint will be rejected by the peer. In the other direction, when this link endpoint receives a RESET_MSG from the peer, it moves to ESTABLISHING and starts to send ACTIVATE_MSGs, but all these messages will be rejected by the peer too. As a result, the link cannot be re-established but gets stuck with this link endpoint in state ESTABLISHING and the peer in RESET! Solution: =========== This link endpoint should not go directly to ESTABLISHED when getting ACTIVATE_MSG from the peer which may belong to the old session if the link was re-created. To ensure the session to be correct before the link is re-established, the peer endpoint in ESTABLISHING state will send back the last session number in ACTIVATE_MSG for a verification at this endpoint. Then, if needed, a new and more appropriate session number will be regenerated to force a re-synch first. In addition, when a link in ESTABLISHING state is reset, its state will move to RESET according to the link FSM, along with resetting the 'in_session' flag (and the other data) as a normal link reset, it will also be deleted if requested. The solution is backward compatible. Acked-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-11 14:29:43 +08:00
/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch
* link peer session number
*/
static inline bool msg_dest_session_valid(struct tipc_msg *m)
{
return msg_bits(m, 1, 16, 0x1);
}
static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid)
{
msg_set_bits(m, 1, 16, 0x1, valid);
}
static inline u16 msg_dest_session(struct tipc_msg *m)
{
return msg_bits(m, 1, 0, 0xffff);
}
static inline void msg_set_dest_session(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 1, 0, 0xffff, n);
}
/*
* Word 2
*/
static inline u16 msg_ack(struct tipc_msg *m)
{
return msg_bits(m, 2, 16, 0xffff);
}
static inline void msg_set_ack(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 2, 16, 0xffff, n);
}
static inline u16 msg_seqno(struct tipc_msg *m)
{
return msg_bits(m, 2, 0, 0xffff);
}
static inline void msg_set_seqno(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 2, 0, 0xffff, n);
}
/*
* Words 3-10
*/
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
static inline u32 msg_importance(struct tipc_msg *m)
{
tipc: improve link congestion algorithm The link congestion algorithm used until now implies two problems. - It is too generous towards lower-level messages in situations of high load by giving "absolute" bandwidth guarantees to the different priority levels. LOW traffic is guaranteed 10%, MEDIUM is guaranted 20%, HIGH is guaranteed 30%, and CRITICAL is guaranteed 40% of the available bandwidth. But, in the absence of higher level traffic, the ratio between two distinct levels becomes unreasonable. E.g. if there is only LOW and MEDIUM traffic on a system, the former is guaranteed 1/3 of the bandwidth, and the latter 2/3. This again means that if there is e.g. one LOW user and 10 MEDIUM users, the former will have 33.3% of the bandwidth, and the others will have to compete for the remainder, i.e. each will end up with 6.7% of the capacity. - Packets of type MSG_BUNDLER are created at SYSTEM importance level, but only after the packets bundled into it have passed the congestion test for their own respective levels. Since bundled packets don't result in incrementing the level counter for their own importance, only occasionally for the SYSTEM level counter, they do in practice obtain SYSTEM level importance. Hence, the current implementation provides a gap in the congestion algorithm that in the worst case may lead to a link reset. We now refine the congestion algorithm as follows: - A message is accepted to the link backlog only if its own level counter, and all superior level counters, permit it. - The importance of a created bundle packet is set according to its contents. A bundle packet created from messges at levels LOW to CRITICAL is given importance level CRITICAL, while a bundle created from a SYSTEM level message is given importance SYSTEM. In the latter case only subsequent SYSTEM level messages are allowed to be bundled into it. This solves the first problem described above, by making the bandwidth guarantee relative to the total number of users at all levels; only the upper limit for each level remains absolute. In the example described above, the single LOW user would use 1/11th of the bandwidth, the same as each of the ten MEDIUM users, but he still has the same guarantee against starvation as the latter ones. The fix also solves the second problem. If the CRITICAL level is filled up by bundle packets of that level, no lower level packets will be accepted any more. Suggested-by: Gergely Kiss <gergely.kiss@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-14 22:46:17 +08:00
int usr = msg_user(m);
if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m)))
return usr;
if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))
return msg_bits(m, 9, 0, 0x7);
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
return TIPC_SYSTEM_IMPORTANCE;
}
static inline void msg_set_importance(struct tipc_msg *m, u32 i)
{
tipc: improve link congestion algorithm The link congestion algorithm used until now implies two problems. - It is too generous towards lower-level messages in situations of high load by giving "absolute" bandwidth guarantees to the different priority levels. LOW traffic is guaranteed 10%, MEDIUM is guaranted 20%, HIGH is guaranteed 30%, and CRITICAL is guaranteed 40% of the available bandwidth. But, in the absence of higher level traffic, the ratio between two distinct levels becomes unreasonable. E.g. if there is only LOW and MEDIUM traffic on a system, the former is guaranteed 1/3 of the bandwidth, and the latter 2/3. This again means that if there is e.g. one LOW user and 10 MEDIUM users, the former will have 33.3% of the bandwidth, and the others will have to compete for the remainder, i.e. each will end up with 6.7% of the capacity. - Packets of type MSG_BUNDLER are created at SYSTEM importance level, but only after the packets bundled into it have passed the congestion test for their own respective levels. Since bundled packets don't result in incrementing the level counter for their own importance, only occasionally for the SYSTEM level counter, they do in practice obtain SYSTEM level importance. Hence, the current implementation provides a gap in the congestion algorithm that in the worst case may lead to a link reset. We now refine the congestion algorithm as follows: - A message is accepted to the link backlog only if its own level counter, and all superior level counters, permit it. - The importance of a created bundle packet is set according to its contents. A bundle packet created from messges at levels LOW to CRITICAL is given importance level CRITICAL, while a bundle created from a SYSTEM level message is given importance SYSTEM. In the latter case only subsequent SYSTEM level messages are allowed to be bundled into it. This solves the first problem described above, by making the bandwidth guarantee relative to the total number of users at all levels; only the upper limit for each level remains absolute. In the example described above, the single LOW user would use 1/11th of the bandwidth, the same as each of the ten MEDIUM users, but he still has the same guarantee against starvation as the latter ones. The fix also solves the second problem. If the CRITICAL level is filled up by bundle packets of that level, no lower level packets will be accepted any more. Suggested-by: Gergely Kiss <gergely.kiss@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-14 22:46:17 +08:00
int usr = msg_user(m);
if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)))
msg_set_bits(m, 9, 0, 0x7, i);
tipc: improve link congestion algorithm The link congestion algorithm used until now implies two problems. - It is too generous towards lower-level messages in situations of high load by giving "absolute" bandwidth guarantees to the different priority levels. LOW traffic is guaranteed 10%, MEDIUM is guaranted 20%, HIGH is guaranteed 30%, and CRITICAL is guaranteed 40% of the available bandwidth. But, in the absence of higher level traffic, the ratio between two distinct levels becomes unreasonable. E.g. if there is only LOW and MEDIUM traffic on a system, the former is guaranteed 1/3 of the bandwidth, and the latter 2/3. This again means that if there is e.g. one LOW user and 10 MEDIUM users, the former will have 33.3% of the bandwidth, and the others will have to compete for the remainder, i.e. each will end up with 6.7% of the capacity. - Packets of type MSG_BUNDLER are created at SYSTEM importance level, but only after the packets bundled into it have passed the congestion test for their own respective levels. Since bundled packets don't result in incrementing the level counter for their own importance, only occasionally for the SYSTEM level counter, they do in practice obtain SYSTEM level importance. Hence, the current implementation provides a gap in the congestion algorithm that in the worst case may lead to a link reset. We now refine the congestion algorithm as follows: - A message is accepted to the link backlog only if its own level counter, and all superior level counters, permit it. - The importance of a created bundle packet is set according to its contents. A bundle packet created from messges at levels LOW to CRITICAL is given importance level CRITICAL, while a bundle created from a SYSTEM level message is given importance SYSTEM. In the latter case only subsequent SYSTEM level messages are allowed to be bundled into it. This solves the first problem described above, by making the bandwidth guarantee relative to the total number of users at all levels; only the upper limit for each level remains absolute. In the example described above, the single LOW user would use 1/11th of the bandwidth, the same as each of the ten MEDIUM users, but he still has the same guarantee against starvation as the latter ones. The fix also solves the second problem. If the CRITICAL level is filled up by bundle packets of that level, no lower level packets will be accepted any more. Suggested-by: Gergely Kiss <gergely.kiss@ericsson.com> Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-14 22:46:17 +08:00
else if (i < TIPC_SYSTEM_IMPORTANCE)
tipc: clean up handling of message priorities Messages transferred by TIPC are assigned an "importance priority", -an integer value indicating how to treat the message when there is link or destination socket congestion. There is no separate header field for this value. Instead, the message user values have been chosen in ascending order according to perceived importance, so that the message user field can be used for this. This is not a good solution. First, we have many more users than the needed priority levels, so we end up with treating more priority levels than necessary. Second, the user field cannot always accurately reflect the priority of the message. E.g., a message fragment packet should really have the priority of the enveloped user data message, and not the priority of the MSG_FRAGMENTER user. Until now, we have been working around this problem in different ways, but it is now time to implement a consistent way of handling such priorities, although still within the constraint that we cannot allocate any more bits in the regular data message header for this. In this commit, we define a new priority level, TIPC_SYSTEM_IMPORTANCE, that will be the only one used apart from the four (lower) user data levels. All non-data messages map down to this priority. Furthermore, we take some free bits from the MSG_FRAGMENTER header and allocate them to store the priority of the enveloped message. We then adjust the functions msg_importance()/msg_set_importance() so that they read/set the correct header fields depending on user type. This small protocol change is fully compatible, because the code at the receiving end of a link currently reads the importance level only from user data messages, where there is no change. Reviewed-by: Erik Hugne <erik.hugne@ericsson.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-14 04:08:11 +08:00
msg_set_user(m, i);
else
pr_warn("Trying to set illegal importance in message\n");
}
static inline u32 msg_prevnode(struct tipc_msg *m)
{
return msg_word(m, 3);
}
static inline void msg_set_prevnode(struct tipc_msg *m, u32 a)
{
msg_set_word(m, 3, a);
}
static inline u32 msg_origport(struct tipc_msg *m)
{
if (msg_user(m) == MSG_FRAGMENTER)
m = msg_inner_hdr(m);
return msg_word(m, 4);
}
static inline void msg_set_origport(struct tipc_msg *m, u32 p)
{
msg_set_word(m, 4, p);
}
static inline u32 msg_destport(struct tipc_msg *m)
{
return msg_word(m, 5);
}
static inline void msg_set_destport(struct tipc_msg *m, u32 p)
{
msg_set_word(m, 5, p);
}
static inline u32 msg_mc_netid(struct tipc_msg *m)
{
return msg_word(m, 5);
}
static inline void msg_set_mc_netid(struct tipc_msg *m, u32 p)
{
msg_set_word(m, 5, p);
}
static inline int msg_short(struct tipc_msg *m)
{
return msg_hdr_sz(m) == SHORT_H_SIZE;
}
static inline u32 msg_orignode(struct tipc_msg *m)
{
if (likely(msg_short(m)))
return msg_prevnode(m);
return msg_word(m, 6);
}
static inline void msg_set_orignode(struct tipc_msg *m, u32 a)
{
msg_set_word(m, 6, a);
}
static inline u32 msg_destnode(struct tipc_msg *m)
{
return msg_word(m, 7);
}
static inline void msg_set_destnode(struct tipc_msg *m, u32 a)
{
msg_set_word(m, 7, a);
}
static inline u32 msg_nametype(struct tipc_msg *m)
{
return msg_word(m, 8);
}
static inline void msg_set_nametype(struct tipc_msg *m, u32 n)
{
msg_set_word(m, 8, n);
}
static inline u32 msg_nameinst(struct tipc_msg *m)
{
return msg_word(m, 9);
}
static inline u32 msg_namelower(struct tipc_msg *m)
{
return msg_nameinst(m);
}
static inline void msg_set_namelower(struct tipc_msg *m, u32 n)
{
msg_set_word(m, 9, n);
}
static inline void msg_set_nameinst(struct tipc_msg *m, u32 n)
{
msg_set_namelower(m, n);
}
static inline u32 msg_nameupper(struct tipc_msg *m)
{
return msg_word(m, 10);
}
static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
{
msg_set_word(m, 10, n);
}
/*
* Constants and routines used to read and write TIPC internal message headers
*/
/*
* Connection management protocol message types
*/
#define CONN_PROBE 0
#define CONN_PROBE_REPLY 1
#define CONN_ACK 2
/*
* Name distributor message types
*/
#define PUBLICATION 0
#define WITHDRAWAL 1
/*
* Segmentation message types
*/
#define FIRST_FRAGMENT 0
#define FRAGMENT 1
#define LAST_FRAGMENT 2
/*
* Link management protocol message types
*/
#define STATE_MSG 0
#define RESET_MSG 1
#define ACTIVATE_MSG 2
/*
* Changeover tunnel message types
*/
#define SYNCH_MSG 0
#define FAILOVER_MSG 1
/*
* Config protocol message types
*/
#define DSC_REQ_MSG 0
#define DSC_RESP_MSG 1
tipc: handle collisions of 32-bit node address hash values When a 32-bit node address is generated from a 128-bit identifier, there is a risk of collisions which must be discovered and handled. We do this as follows: - We don't apply the generated address immediately to the node, but do instead initiate a 1 sec trial period to allow other cluster members to discover and handle such collisions. - During the trial period the node periodically sends out a new type of message, DSC_TRIAL_MSG, using broadcast or emulated broadcast, to all the other nodes in the cluster. - When a node is receiving such a message, it must check that the presented 32-bit identifier either is unused, or was used by the very same peer in a previous session. In both cases it accepts the request by not responding to it. - If it finds that the same node has been up before using a different address, it responds with a DSC_TRIAL_FAIL_MSG containing that address. - If it finds that the address has already been taken by some other node, it generates a new, unused address and returns it to the requester. - During the trial period the requesting node must always be prepared to accept a failure message, i.e., a message where a peer suggests a different (or equal) address to the one tried. In those cases it must apply the suggested value as trial address and restart the trial period. This algorithm ensures that in the vast majority of cases a node will have the same address before and after a reboot. If a legacy user configures the address explicitly, there will be no trial period and messages, so this protocol addition is completely backwards compatible. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-23 03:42:51 +08:00
#define DSC_TRIAL_MSG 2
#define DSC_TRIAL_FAIL_MSG 3
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
/*
* Group protocol message types
*/
#define GRP_JOIN_MSG 0
#define GRP_LEAVE_MSG 1
#define GRP_ADV_MSG 2
tipc: guarantee that group broadcast doesn't bypass group unicast We need a mechanism guaranteeing that group unicasts sent out from a socket are not bypassed by later sent broadcasts from the same socket. We do this as follows: - Each time a unicast is sent, we set a the broadcast method for the socket to "replicast" and "mandatory". This forces the first subsequent broadcast message to follow the same network and data path as the preceding unicast to a destination, hence preventing it from overtaking the latter. - In order to make the 'same data path' statement above true, we let group unicasts pass through the multicast link input queue, instead of as previously through the unicast link input queue. - In the first broadcast following a unicast, we set a new header flag, requiring all recipients to immediately acknowledge its reception. - During the period before all the expected acknowledges are received, the socket refuses to accept any more broadcast attempts, i.e., by blocking or returning EAGAIN. This period should typically not be longer than a few microseconds. - When all acknowledges have been received, the sending socket will open up for subsequent broadcasts, this time giving the link layer freedom to itself select the best transmission method. - The forced and/or abrupt transmission method changes described above may lead to broadcasts arriving out of order to the recipients. We remedy this by introducing code that checks and if necessary re-orders such messages at the receiving end. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:31 +08:00
#define GRP_ACK_MSG 3
tipc: add multipoint-to-point flow control We already have point-to-multipoint flow control within a group. But we even need the opposite; -a scheme which can handle that potentially hundreds of sources may try to send messages to the same destination simultaneously without causing buffer overflow at the recipient. This commit adds such a mechanism. The algorithm works as follows: - When a member detects a new, joining member, it initially set its state to JOINED and advertises a minimum window to the new member. This window is chosen so that the new member can send exactly one maximum sized message, or several smaller ones, to the recipient before it must stop and wait for an additional advertisement. This minimum window ADV_IDLE is set to 65 1kB blocks. - When a member receives the first data message from a JOINED member, it changes the state of the latter to ACTIVE, and advertises a larger window ADV_ACTIVE = 12 x ADV_IDLE blocks to the sender, so it can continue sending with minimal disturbances to the data flow. - The active members are kept in a dedicated linked list. Each time a message is received from an active member, it will be moved to the tail of that list. This way, we keep a record of which members have been most (tail) and least (head) recently active. - There is a maximum number (16) of permitted simultaneous active senders per receiver. When this limit is reached, the receiver will not advertise anything immediately to a new sender, but instead put it in a PENDING state, and add it to a corresponding queue. At the same time, it will pick the least recently active member, send it an advertisement RECLAIM message, and set this member to state RECLAIMING. - The reclaimee member has to respond with a REMIT message, meaning that it goes back to a send window of ADV_IDLE, and returns its unused advertised blocks beyond that value to the reclaiming member. - When the reclaiming member receives the REMIT message, it unlinks the reclaimee from its active list, resets its state to JOINED, and notes that it is now back at ADV_IDLE advertised blocks to that member. If there are still unread data messages sent out by reclaimee before the REMIT, the member goes into an intermediate state REMITTED, where it stays until the said messages have been consumed. - The returned advertised blocks can now be re-advertised to the pending member, which is now set to state ACTIVE and added to the active member list. - To be proactive, i.e., to minimize the risk that any member will end up in the pending queue, we start reclaiming resources already when the number of active members exceeds 3/4 of the permitted maximum. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:34 +08:00
#define GRP_RECLAIM_MSG 4
#define GRP_REMIT_MSG 5
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
/*
* Word 1
*/
static inline u32 msg_seq_gap(struct tipc_msg *m)
{
return msg_bits(m, 1, 16, 0x1fff);
}
static inline void msg_set_seq_gap(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 1, 16, 0x1fff, n);
}
static inline u32 msg_node_sig(struct tipc_msg *m)
{
return msg_bits(m, 1, 0, 0xffff);
}
static inline void msg_set_node_sig(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 1, 0, 0xffff, n);
}
static inline u32 msg_node_capabilities(struct tipc_msg *m)
{
return msg_bits(m, 1, 15, 0x1fff);
}
static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 1, 15, 0x1fff, n);
}
/*
* Word 2
*/
static inline u32 msg_dest_domain(struct tipc_msg *m)
{
return msg_word(m, 2);
}
static inline void msg_set_dest_domain(struct tipc_msg *m, u32 n)
{
msg_set_word(m, 2, n);
}
static inline u32 msg_bcgap_after(struct tipc_msg *m)
{
return msg_bits(m, 2, 16, 0xffff);
}
static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 2, 16, 0xffff, n);
}
static inline u32 msg_bcgap_to(struct tipc_msg *m)
{
return msg_bits(m, 2, 0, 0xffff);
}
static inline void msg_set_bcgap_to(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 2, 0, 0xffff, n);
}
/*
* Word 4
*/
static inline u32 msg_last_bcast(struct tipc_msg *m)
{
return msg_bits(m, 4, 16, 0xffff);
}
static inline u32 msg_bc_snd_nxt(struct tipc_msg *m)
{
return msg_last_bcast(m) + 1;
}
static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 4, 16, 0xffff, n);
}
tipc: fix changeover issues due to large packet In conjunction with changing the interfaces' MTU (e.g. especially in the case of a bonding) where the TIPC links are brought up and down in a short time, a couple of issues were detected with the current link changeover mechanism: 1) When one link is up but immediately forced down again, the failover procedure will be carried out in order to failover all the messages in the link's transmq queue onto the other working link. The link and node state is also set to FAILINGOVER as part of the process. The message will be transmited in form of a FAILOVER_MSG, so its size is plus of 40 bytes (= the message header size). There is no problem if the original message size is not larger than the link's MTU - 40, and indeed this is the max size of a normal payload messages. However, in the situation above, because the link has just been up, the messages in the link's transmq are almost SYNCH_MSGs which had been generated by the link synching procedure, then their size might reach the max value already! When the FAILOVER_MSG is built on the top of such a SYNCH_MSG, its size will exceed the link's MTU. As a result, the messages are dropped silently and the failover procedure will never end up, the link will not be able to exit the FAILINGOVER state, so cannot be re-established. 2) The same scenario above can happen more easily in case the MTU of the links is set differently or when changing. In that case, as long as a large message in the failure link's transmq queue was built and fragmented with its link's MTU > the other link's one, the issue will happen (there is no need of a link synching in advance). 3) The link synching procedure also faces with the same issue but since the link synching is only started upon receipt of a SYNCH_MSG, dropping the message will not result in a state deadlock, but it is not expected as design. The 1) & 3) issues are resolved by the last commit that only a dummy SYNCH_MSG (i.e. without data) is generated at the link synching, so the size of a FAILOVER_MSG if any then will never exceed the link's MTU. For the 2) issue, the only solution is trying to fragment the messages in the failure link's transmq queue according to the working link's MTU so they can be failovered then. A new function is made to accomplish this, it will still be a TUNNEL PROTOCOL/FAILOVER MSG but if the original message size is too large, it will be fragmented & reassembled at the receiving side. Acked-by: Ying Xue <ying.xue@windriver.com> Acked-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-24 09:56:12 +08:00
static inline u32 msg_nof_fragms(struct tipc_msg *m)
{
return msg_bits(m, 4, 0, 0xffff);
}
static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 4, 0, 0xffff, n);
}
static inline u32 msg_fragm_no(struct tipc_msg *m)
{
return msg_bits(m, 4, 16, 0xffff);
}
static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 4, 16, 0xffff, n);
}
static inline u16 msg_next_sent(struct tipc_msg *m)
{
return msg_bits(m, 4, 0, 0xffff);
}
static inline void msg_set_next_sent(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 4, 0, 0xffff, n);
}
static inline void msg_set_long_msgno(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 4, 0, 0xffff, n);
}
static inline u32 msg_bc_netid(struct tipc_msg *m)
{
return msg_word(m, 4);
}
static inline void msg_set_bc_netid(struct tipc_msg *m, u32 id)
{
msg_set_word(m, 4, id);
}
static inline u32 msg_link_selector(struct tipc_msg *m)
{
if (msg_user(m) == MSG_FRAGMENTER)
m = (void *)msg_data(m);
return msg_bits(m, 4, 0, 1);
}
/*
* Word 5
*/
static inline u16 msg_session(struct tipc_msg *m)
{
return msg_bits(m, 5, 16, 0xffff);
}
static inline void msg_set_session(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 5, 16, 0xffff, n);
}
static inline u32 msg_probe(struct tipc_msg *m)
{
return msg_bits(m, 5, 0, 1);
}
static inline void msg_set_probe(struct tipc_msg *m, u32 val)
{
msg_set_bits(m, 5, 0, 1, val);
}
static inline char msg_net_plane(struct tipc_msg *m)
{
return msg_bits(m, 5, 1, 7) + 'A';
}
static inline void msg_set_net_plane(struct tipc_msg *m, char n)
{
msg_set_bits(m, 5, 1, 7, (n - 'A'));
}
static inline u32 msg_linkprio(struct tipc_msg *m)
{
return msg_bits(m, 5, 4, 0x1f);
}
static inline void msg_set_linkprio(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 5, 4, 0x1f, n);
}
static inline u32 msg_bearer_id(struct tipc_msg *m)
{
return msg_bits(m, 5, 9, 0x7);
}
static inline void msg_set_bearer_id(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 5, 9, 0x7, n);
}
static inline u32 msg_redundant_link(struct tipc_msg *m)
{
return msg_bits(m, 5, 12, 0x1);
}
static inline void msg_set_redundant_link(struct tipc_msg *m, u32 r)
{
msg_set_bits(m, 5, 12, 0x1, r);
}
tipc: guarantee peer bearer id exchange after reboot When a link endpoint is going down locally, e.g., because its interface is being stopped, it will spontaneously send out a RESET message to its peer, informing it about this fact. This saves the peer from detecting the failure via probing, and hence gives both speedier and less resource consuming failure detection on the peer side. According to the link FSM, a receiver of a RESET message, ignoring the reason for it, must now consider the sender ready to come back up, and starts periodically sending out ACTIVATE messages to the peer in order to re-establish the link. Also, according to the FSM, the receiver of an ACTIVATE message can now go directly to state ESTABLISHED and start sending regular traffic packets. This is a well-proven and robust FSM. However, in the case of a reboot, there is a small possibilty that link endpoint on the rebooted node may have been re-created with a new bearer identity between the moment it sent its (pre-boot) RESET and the moment it receives the ACTIVATE from the peer. The new bearer identity cannot be known by the peer according to this scenario, since traffic headers don't convey such information. This is a problem, because both endpoints need to know the correct value of the peer's bearer id at any moment in time in order to be able to produce correct link events for their users. The only way to guarantee this is to enforce a full setup message exchange (RESET + ACTIVATE) even after the reboot, since those messages carry the bearer idientity in their header. In this commit we do this by introducing and setting a "stopping" bit in the header of the spontaneously generated RESET messages, informing the peer that the sender will not be immediately ready to re-establish the link. A receiver seeing this bit must act as if this were a locally detected connectivity failure, and hence has to go through a full two- way setup message exchange before any link can be re-established. Although never reported, this problem seems to have always been around. This protocol addition is fully backwards compatible. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-16 01:33:03 +08:00
static inline u32 msg_peer_stopping(struct tipc_msg *m)
{
return msg_bits(m, 5, 13, 0x1);
}
static inline void msg_set_peer_stopping(struct tipc_msg *m, u32 s)
{
msg_set_bits(m, 5, 13, 0x1, s);
}
tipc: fix broadcast link synchronization problem In commit 2d18ac4ba745 ("tipc: extend broadcast link initialization criteria") we tried to fix a problem with the initial synchronization of broadcast link acknowledge values. Unfortunately that solution is not sufficient to solve the issue. We have seen it happen that LINK_PROTOCOL/STATE packets with a valid non-zero unicast acknowledge number may bypass BCAST_PROTOCOL initialization, NAME_DISTRIBUTOR and other STATE packets with invalid broadcast acknowledge numbers, leading to premature opening of the broadcast link. When the bypassed packets finally arrive, they are inadvertently accepted, and the already correctly initialized acknowledge number in the broadcast receive link is overwritten by the invalid (zero) value of the said packets. After this the broadcast link goes stale. We now fix this by marking the packets where we know the acknowledge value is or may be invalid, and then ignoring the acks from those. To this purpose, we claim an unused bit in the header to indicate that the value is invalid. We set the bit to 1 in the initial BCAST_PROTOCOL synchronization packet and all initial ("bulk") NAME_DISTRIBUTOR packets, plus those LINK_PROTOCOL packets sent out before the broadcast links are fully synchronized. This minor protocol update is fully backwards compatible. Reported-by: John Thompson <thompa.atl@gmail.com> Tested-by: John Thompson <thompa.atl@gmail.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-28 06:51:55 +08:00
static inline bool msg_bc_ack_invalid(struct tipc_msg *m)
{
switch (msg_user(m)) {
case BCAST_PROTOCOL:
case NAME_DISTRIBUTOR:
case LINK_PROTOCOL:
return msg_bits(m, 5, 14, 0x1);
default:
return false;
}
}
static inline void msg_set_bc_ack_invalid(struct tipc_msg *m, bool invalid)
{
msg_set_bits(m, 5, 14, 0x1, invalid);
}
static inline char *msg_media_addr(struct tipc_msg *m)
{
return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET];
}
static inline u32 msg_bc_gap(struct tipc_msg *m)
{
return msg_bits(m, 8, 0, 0x3ff);
}
static inline void msg_set_bc_gap(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 8, 0, 0x3ff, n);
}
/*
* Word 9
*/
static inline u16 msg_msgcnt(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff);
}
static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 9, 16, 0xffff, n);
}
static inline u16 msg_syncpt(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff);
}
static inline void msg_set_syncpt(struct tipc_msg *m, u16 n)
{
msg_set_bits(m, 9, 16, 0xffff, n);
}
tipc: redesign connection-level flow control There are two flow control mechanisms in TIPC; one at link level that handles network congestion, burst control, and retransmission, and one at connection level which' only remaining task is to prevent overflow in the receiving socket buffer. In TIPC, the latter task has to be solved end-to-end because messages can not be thrown away once they have been accepted and delivered upwards from the link layer, i.e, we can never permit the receive buffer to overflow. Currently, this algorithm is message based. A counter in the receiving socket keeps track of number of consumed messages, and sends a dedicated acknowledge message back to the sender for each 256 consumed message. A counter at the sending end keeps track of the sent, not yet acknowledged messages, and blocks the sender if this number ever reaches 512 unacknowledged messages. When the missing acknowledge arrives, the socket is then woken up for renewed transmission. This works well for keeping the message flow running, as it almost never happens that a sender socket is blocked this way. A problem with the current mechanism is that it potentially is very memory consuming. Since we don't distinguish between small and large messages, we have to dimension the socket receive buffer according to a worst-case of both. I.e., the window size must be chosen large enough to sustain a reasonable throughput even for the smallest messages, while we must still consider a scenario where all messages are of maximum size. Hence, the current fix window size of 512 messages and a maximum message size of 66k results in a receive buffer of 66 MB when truesize(66k) = 131k is taken into account. It is possible to do much better. This commit introduces an algorithm where we instead use 1024-byte blocks as base unit. This unit, always rounded upwards from the actual message size, is used when we advertise windows as well as when we count and acknowledge transmitted data. The advertised window is based on the configured receive buffer size in such a way that even the worst-case truesize/msgsize ratio always is covered. Since the smallest possible message size (from a flow control viewpoint) now is 1024 bytes, we can safely assume this ratio to be less than four, which is the value we are now using. This way, we have been able to reduce the default receive buffer size from 66 MB to 2 MB with maintained performance. In order to keep this solution backwards compatible, we introduce a new capability bit in the discovery protocol, and use this throughout the message sending/reception path to always select the right unit. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-02 23:58:47 +08:00
static inline u32 msg_conn_ack(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff);
}
tipc: redesign connection-level flow control There are two flow control mechanisms in TIPC; one at link level that handles network congestion, burst control, and retransmission, and one at connection level which' only remaining task is to prevent overflow in the receiving socket buffer. In TIPC, the latter task has to be solved end-to-end because messages can not be thrown away once they have been accepted and delivered upwards from the link layer, i.e, we can never permit the receive buffer to overflow. Currently, this algorithm is message based. A counter in the receiving socket keeps track of number of consumed messages, and sends a dedicated acknowledge message back to the sender for each 256 consumed message. A counter at the sending end keeps track of the sent, not yet acknowledged messages, and blocks the sender if this number ever reaches 512 unacknowledged messages. When the missing acknowledge arrives, the socket is then woken up for renewed transmission. This works well for keeping the message flow running, as it almost never happens that a sender socket is blocked this way. A problem with the current mechanism is that it potentially is very memory consuming. Since we don't distinguish between small and large messages, we have to dimension the socket receive buffer according to a worst-case of both. I.e., the window size must be chosen large enough to sustain a reasonable throughput even for the smallest messages, while we must still consider a scenario where all messages are of maximum size. Hence, the current fix window size of 512 messages and a maximum message size of 66k results in a receive buffer of 66 MB when truesize(66k) = 131k is taken into account. It is possible to do much better. This commit introduces an algorithm where we instead use 1024-byte blocks as base unit. This unit, always rounded upwards from the actual message size, is used when we advertise windows as well as when we count and acknowledge transmitted data. The advertised window is based on the configured receive buffer size in such a way that even the worst-case truesize/msgsize ratio always is covered. Since the smallest possible message size (from a flow control viewpoint) now is 1024 bytes, we can safely assume this ratio to be less than four, which is the value we are now using. This way, we have been able to reduce the default receive buffer size from 66 MB to 2 MB with maintained performance. In order to keep this solution backwards compatible, we introduce a new capability bit in the discovery protocol, and use this throughout the message sending/reception path to always select the right unit. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-02 23:58:47 +08:00
static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 9, 16, 0xffff, n);
}
static inline u16 msg_adv_win(struct tipc_msg *m)
tipc: redesign connection-level flow control There are two flow control mechanisms in TIPC; one at link level that handles network congestion, burst control, and retransmission, and one at connection level which' only remaining task is to prevent overflow in the receiving socket buffer. In TIPC, the latter task has to be solved end-to-end because messages can not be thrown away once they have been accepted and delivered upwards from the link layer, i.e, we can never permit the receive buffer to overflow. Currently, this algorithm is message based. A counter in the receiving socket keeps track of number of consumed messages, and sends a dedicated acknowledge message back to the sender for each 256 consumed message. A counter at the sending end keeps track of the sent, not yet acknowledged messages, and blocks the sender if this number ever reaches 512 unacknowledged messages. When the missing acknowledge arrives, the socket is then woken up for renewed transmission. This works well for keeping the message flow running, as it almost never happens that a sender socket is blocked this way. A problem with the current mechanism is that it potentially is very memory consuming. Since we don't distinguish between small and large messages, we have to dimension the socket receive buffer according to a worst-case of both. I.e., the window size must be chosen large enough to sustain a reasonable throughput even for the smallest messages, while we must still consider a scenario where all messages are of maximum size. Hence, the current fix window size of 512 messages and a maximum message size of 66k results in a receive buffer of 66 MB when truesize(66k) = 131k is taken into account. It is possible to do much better. This commit introduces an algorithm where we instead use 1024-byte blocks as base unit. This unit, always rounded upwards from the actual message size, is used when we advertise windows as well as when we count and acknowledge transmitted data. The advertised window is based on the configured receive buffer size in such a way that even the worst-case truesize/msgsize ratio always is covered. Since the smallest possible message size (from a flow control viewpoint) now is 1024 bytes, we can safely assume this ratio to be less than four, which is the value we are now using. This way, we have been able to reduce the default receive buffer size from 66 MB to 2 MB with maintained performance. In order to keep this solution backwards compatible, we introduce a new capability bit in the discovery protocol, and use this throughout the message sending/reception path to always select the right unit. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-02 23:58:47 +08:00
{
return msg_bits(m, 9, 0, 0xffff);
}
static inline void msg_set_adv_win(struct tipc_msg *m, u16 n)
tipc: redesign connection-level flow control There are two flow control mechanisms in TIPC; one at link level that handles network congestion, burst control, and retransmission, and one at connection level which' only remaining task is to prevent overflow in the receiving socket buffer. In TIPC, the latter task has to be solved end-to-end because messages can not be thrown away once they have been accepted and delivered upwards from the link layer, i.e, we can never permit the receive buffer to overflow. Currently, this algorithm is message based. A counter in the receiving socket keeps track of number of consumed messages, and sends a dedicated acknowledge message back to the sender for each 256 consumed message. A counter at the sending end keeps track of the sent, not yet acknowledged messages, and blocks the sender if this number ever reaches 512 unacknowledged messages. When the missing acknowledge arrives, the socket is then woken up for renewed transmission. This works well for keeping the message flow running, as it almost never happens that a sender socket is blocked this way. A problem with the current mechanism is that it potentially is very memory consuming. Since we don't distinguish between small and large messages, we have to dimension the socket receive buffer according to a worst-case of both. I.e., the window size must be chosen large enough to sustain a reasonable throughput even for the smallest messages, while we must still consider a scenario where all messages are of maximum size. Hence, the current fix window size of 512 messages and a maximum message size of 66k results in a receive buffer of 66 MB when truesize(66k) = 131k is taken into account. It is possible to do much better. This commit introduces an algorithm where we instead use 1024-byte blocks as base unit. This unit, always rounded upwards from the actual message size, is used when we advertise windows as well as when we count and acknowledge transmitted data. The advertised window is based on the configured receive buffer size in such a way that even the worst-case truesize/msgsize ratio always is covered. Since the smallest possible message size (from a flow control viewpoint) now is 1024 bytes, we can safely assume this ratio to be less than four, which is the value we are now using. This way, we have been able to reduce the default receive buffer size from 66 MB to 2 MB with maintained performance. In order to keep this solution backwards compatible, we introduce a new capability bit in the discovery protocol, and use this throughout the message sending/reception path to always select the right unit. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-02 23:58:47 +08:00
{
msg_set_bits(m, 9, 0, 0xffff, n);
}
static inline u32 msg_max_pkt(struct tipc_msg *m)
{
return msg_bits(m, 9, 16, 0xffff) * 4;
}
static inline void msg_set_max_pkt(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 9, 16, 0xffff, (n / 4));
}
static inline u32 msg_link_tolerance(struct tipc_msg *m)
{
return msg_bits(m, 9, 0, 0xffff);
}
static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 9, 0, 0xffff, n);
}
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
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);
}
tipc: guarantee that group broadcast doesn't bypass group unicast We need a mechanism guaranteeing that group unicasts sent out from a socket are not bypassed by later sent broadcasts from the same socket. We do this as follows: - Each time a unicast is sent, we set a the broadcast method for the socket to "replicast" and "mandatory". This forces the first subsequent broadcast message to follow the same network and data path as the preceding unicast to a destination, hence preventing it from overtaking the latter. - In order to make the 'same data path' statement above true, we let group unicasts pass through the multicast link input queue, instead of as previously through the unicast link input queue. - In the first broadcast following a unicast, we set a new header flag, requiring all recipients to immediately acknowledge its reception. - During the period before all the expected acknowledges are received, the socket refuses to accept any more broadcast attempts, i.e., by blocking or returning EAGAIN. This period should typically not be longer than a few microseconds. - When all acknowledges have been received, the sending socket will open up for subsequent broadcasts, this time giving the link layer freedom to itself select the best transmission method. - The forced and/or abrupt transmission method changes described above may lead to broadcasts arriving out of order to the recipients. We remedy this by introducing code that checks and if necessary re-orders such messages at the receiving end. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:31 +08:00
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);
}
tipc: add multipoint-to-point flow control We already have point-to-multipoint flow control within a group. But we even need the opposite; -a scheme which can handle that potentially hundreds of sources may try to send messages to the same destination simultaneously without causing buffer overflow at the recipient. This commit adds such a mechanism. The algorithm works as follows: - When a member detects a new, joining member, it initially set its state to JOINED and advertises a minimum window to the new member. This window is chosen so that the new member can send exactly one maximum sized message, or several smaller ones, to the recipient before it must stop and wait for an additional advertisement. This minimum window ADV_IDLE is set to 65 1kB blocks. - When a member receives the first data message from a JOINED member, it changes the state of the latter to ACTIVE, and advertises a larger window ADV_ACTIVE = 12 x ADV_IDLE blocks to the sender, so it can continue sending with minimal disturbances to the data flow. - The active members are kept in a dedicated linked list. Each time a message is received from an active member, it will be moved to the tail of that list. This way, we keep a record of which members have been most (tail) and least (head) recently active. - There is a maximum number (16) of permitted simultaneous active senders per receiver. When this limit is reached, the receiver will not advertise anything immediately to a new sender, but instead put it in a PENDING state, and add it to a corresponding queue. At the same time, it will pick the least recently active member, send it an advertisement RECLAIM message, and set this member to state RECLAIMING. - The reclaimee member has to respond with a REMIT message, meaning that it goes back to a send window of ADV_IDLE, and returns its unused advertised blocks beyond that value to the reclaiming member. - When the reclaiming member receives the REMIT message, it unlinks the reclaimee from its active list, resets its state to JOINED, and notes that it is now back at ADV_IDLE advertised blocks to that member. If there are still unread data messages sent out by reclaimee before the REMIT, the member goes into an intermediate state REMITTED, where it stays until the said messages have been consumed. - The returned advertised blocks can now be re-advertised to the pending member, which is now set to state ACTIVE and added to the active member list. - To be proactive, i.e., to minimize the risk that any member will end up in the pending queue, we start reclaiming resources already when the number of active members exceeds 3/4 of the permitted maximum. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:34 +08:00
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);
}
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
/* 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);
}
tipc: guarantee that group broadcast doesn't bypass group unicast We need a mechanism guaranteeing that group unicasts sent out from a socket are not bypassed by later sent broadcasts from the same socket. We do this as follows: - Each time a unicast is sent, we set a the broadcast method for the socket to "replicast" and "mandatory". This forces the first subsequent broadcast message to follow the same network and data path as the preceding unicast to a destination, hence preventing it from overtaking the latter. - In order to make the 'same data path' statement above true, we let group unicasts pass through the multicast link input queue, instead of as previously through the unicast link input queue. - In the first broadcast following a unicast, we set a new header flag, requiring all recipients to immediately acknowledge its reception. - During the period before all the expected acknowledges are received, the socket refuses to accept any more broadcast attempts, i.e., by blocking or returning EAGAIN. This period should typically not be longer than a few microseconds. - When all acknowledges have been received, the sending socket will open up for subsequent broadcasts, this time giving the link layer freedom to itself select the best transmission method. - The forced and/or abrupt transmission method changes described above may lead to broadcasts arriving out of order to the recipients. We remedy this by introducing code that checks and if necessary re-orders such messages at the receiving end. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:31 +08:00
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);
}
tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is 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. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-13 17:04:23 +08:00
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)
tipc: introduce node contact FSM The logics for determining when a node is permitted to establish and maintain contact with its peer node becomes non-trivial in the presence of multiple parallel links that may come and go independently. A known failure scenario is that one endpoint registers both its links to the peer lost, cleans up it binding table, and prepares for a table update once contact is re-establihed, while the other endpoint may see its links reset and re-established one by one, hence seeing no need to re-synchronize the binding table. To avoid this, a node must not allow re-establishing contact until it has confirmation that even the peer has lost both links. Currently, the mechanism for handling this consists of setting and resetting two state flags from different locations in the code. This solution is hard to understand and maintain. A closer analysis even reveals that it is not completely safe. In this commit we do instead introduce an FSM that keeps track of the conditions for when the node can establish and maintain links. It has six states and four events, and is strictly based on explicit knowledge about the own node's and the peer node's contact states. Only events leading to state change are shown as edges in the figure below. +--------------+ | SELF_UP/ | +---------------->| PEER_COMING |-----------------+ SELF_ | +--------------+ |PEER_ ESTBL_ | | |ESTBL_ CONTACT| SELF_LOST_CONTACT | |CONTACT | v | | +--------------+ | | PEER_ | SELF_DOWN/ | SELF_ | | LOST_ +--| PEER_LEAVING |<--+ LOST_ v +-------------+ CONTACT | +--------------+ | CONTACT +-----------+ | SELF_DOWN/ |<----------+ +----------| SELF_UP/ | | PEER_DOWN |<----------+ +----------| PEER_UP | +-------------+ SELF_ | +--------------+ | PEER_ +-----------+ | LOST_ +--| SELF_LEAVING/|<--+ LOST_ A | CONTACT | PEER_DOWN | CONTACT | | +--------------+ | | A | PEER_ | PEER_LOST_CONTACT | |SELF_ ESTBL_ | | |ESTBL_ CONTACT| +--------------+ |CONTACT +---------------->| PEER_UP/ |-----------------+ | SELF_COMING | +--------------+ Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-17 04:54:30 +08:00
{
if (likely(msg_user(m) != LINK_PROTOCOL))
tipc: introduce node contact FSM The logics for determining when a node is permitted to establish and maintain contact with its peer node becomes non-trivial in the presence of multiple parallel links that may come and go independently. A known failure scenario is that one endpoint registers both its links to the peer lost, cleans up it binding table, and prepares for a table update once contact is re-establihed, while the other endpoint may see its links reset and re-established one by one, hence seeing no need to re-synchronize the binding table. To avoid this, a node must not allow re-establishing contact until it has confirmation that even the peer has lost both links. Currently, the mechanism for handling this consists of setting and resetting two state flags from different locations in the code. This solution is hard to understand and maintain. A closer analysis even reveals that it is not completely safe. In this commit we do instead introduce an FSM that keeps track of the conditions for when the node can establish and maintain links. It has six states and four events, and is strictly based on explicit knowledge about the own node's and the peer node's contact states. Only events leading to state change are shown as edges in the figure below. +--------------+ | SELF_UP/ | +---------------->| PEER_COMING |-----------------+ SELF_ | +--------------+ |PEER_ ESTBL_ | | |ESTBL_ CONTACT| SELF_LOST_CONTACT | |CONTACT | v | | +--------------+ | | PEER_ | SELF_DOWN/ | SELF_ | | LOST_ +--| PEER_LEAVING |<--+ LOST_ v +-------------+ CONTACT | +--------------+ | CONTACT +-----------+ | SELF_DOWN/ |<----------+ +----------| SELF_UP/ | | PEER_DOWN |<----------+ +----------| PEER_UP | +-------------+ SELF_ | +--------------+ | PEER_ +-----------+ | LOST_ +--| SELF_LEAVING/|<--+ LOST_ A | CONTACT | PEER_DOWN | CONTACT | | +--------------+ | | A | PEER_ | PEER_LOST_CONTACT | |SELF_ ESTBL_ | | |ESTBL_ CONTACT| +--------------+ |CONTACT +---------------->| PEER_UP/ |-----------------+ | SELF_COMING | +--------------+ Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-17 04:54:30 +08:00
return true;
if (msg_type(m) == STATE_MSG)
return true;
return false;
}
static inline bool msg_peer_node_is_up(struct tipc_msg *m)
{
if (msg_peer_link_is_up(m))
return true;
tipc: introduce node contact FSM The logics for determining when a node is permitted to establish and maintain contact with its peer node becomes non-trivial in the presence of multiple parallel links that may come and go independently. A known failure scenario is that one endpoint registers both its links to the peer lost, cleans up it binding table, and prepares for a table update once contact is re-establihed, while the other endpoint may see its links reset and re-established one by one, hence seeing no need to re-synchronize the binding table. To avoid this, a node must not allow re-establishing contact until it has confirmation that even the peer has lost both links. Currently, the mechanism for handling this consists of setting and resetting two state flags from different locations in the code. This solution is hard to understand and maintain. A closer analysis even reveals that it is not completely safe. In this commit we do instead introduce an FSM that keeps track of the conditions for when the node can establish and maintain links. It has six states and four events, and is strictly based on explicit knowledge about the own node's and the peer node's contact states. Only events leading to state change are shown as edges in the figure below. +--------------+ | SELF_UP/ | +---------------->| PEER_COMING |-----------------+ SELF_ | +--------------+ |PEER_ ESTBL_ | | |ESTBL_ CONTACT| SELF_LOST_CONTACT | |CONTACT | v | | +--------------+ | | PEER_ | SELF_DOWN/ | SELF_ | | LOST_ +--| PEER_LEAVING |<--+ LOST_ v +-------------+ CONTACT | +--------------+ | CONTACT +-----------+ | SELF_DOWN/ |<----------+ +----------| SELF_UP/ | | PEER_DOWN |<----------+ +----------| PEER_UP | +-------------+ SELF_ | +--------------+ | PEER_ +-----------+ | LOST_ +--| SELF_LEAVING/|<--+ LOST_ A | CONTACT | PEER_DOWN | CONTACT | | +--------------+ | | A | PEER_ | PEER_LOST_CONTACT | |SELF_ ESTBL_ | | |ESTBL_ CONTACT| +--------------+ |CONTACT +---------------->| PEER_UP/ |-----------------+ | SELF_COMING | +--------------+ Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-17 04:54:30 +08:00
return msg_redundant_link(m);
}
static inline bool msg_is_reset(struct tipc_msg *hdr)
{
return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG);
}
tipc: handle collisions of 32-bit node address hash values When a 32-bit node address is generated from a 128-bit identifier, there is a risk of collisions which must be discovered and handled. We do this as follows: - We don't apply the generated address immediately to the node, but do instead initiate a 1 sec trial period to allow other cluster members to discover and handle such collisions. - During the trial period the node periodically sends out a new type of message, DSC_TRIAL_MSG, using broadcast or emulated broadcast, to all the other nodes in the cluster. - When a node is receiving such a message, it must check that the presented 32-bit identifier either is unused, or was used by the very same peer in a previous session. In both cases it accepts the request by not responding to it. - If it finds that the same node has been up before using a different address, it responds with a DSC_TRIAL_FAIL_MSG containing that address. - If it finds that the address has already been taken by some other node, it generates a new, unused address and returns it to the requester. - During the trial period the requesting node must always be prepared to accept a failure message, i.e., a message where a peer suggests a different (or equal) address to the one tried. In those cases it must apply the suggested value as trial address and restart the trial period. This algorithm ensures that in the vast majority of cases a node will have the same address before and after a reboot. If a legacy user configures the address explicitly, there will be no trial period and messages, so this protocol addition is completely backwards compatible. Acked-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-23 03:42:51 +08:00
static inline u32 msg_sugg_node_addr(struct tipc_msg *m)
{
return msg_word(m, 14);
}
static inline void msg_set_sugg_node_addr(struct tipc_msg *m, u32 n)
{
msg_set_word(m, 14, n);
}
static inline void msg_set_node_id(struct tipc_msg *hdr, u8 *id)
{
memcpy(msg_data(hdr), id, 16);
}
static inline u8 *msg_node_id(struct tipc_msg *hdr)
{
return (u8 *)msg_data(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);
2015-02-05 21:36:36 +08:00
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,
uint data_sz, u32 dnode, u32 onode,
u32 dport, u32 oport, int errcode);
int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf);
bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu);
bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg,
u32 mtu, u32 dnode);
tipc: resolve race problem at unicast message reception TIPC handles message cardinality and sequencing at the link layer, before passing messages upwards to the destination sockets. During the upcall from link to socket no locks are held. It is therefore possible, and we see it happen occasionally, that messages arriving in different threads and delivered in sequence still bypass each other before they reach the destination socket. This must not happen, since it violates the sequentiality guarantee. We solve this by adding a new input buffer queue to the link structure. Arriving messages are added safely to the tail of that queue by the link, while the head of the queue is consumed, also safely, by the receiving socket. Sequentiality is secured per socket by only allowing buffers to be dequeued inside the socket lock. Since there may be multiple simultaneous readers of the queue, we use a 'filter' parameter to reduce the risk that they peek the same buffer from the queue, hence also reducing the risk of contention on the receiving socket locks. This solves the sequentiality problem, and seems to cause no measurable performance degradation. A nice side effect of this change is that lock handling in the functions tipc_rcv() and tipc_bcast_rcv() now becomes uniform, something that will enable future simplifications of those functions. Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-05 21:36:41 +08:00
bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos);
tipc: fix changeover issues due to large packet In conjunction with changing the interfaces' MTU (e.g. especially in the case of a bonding) where the TIPC links are brought up and down in a short time, a couple of issues were detected with the current link changeover mechanism: 1) When one link is up but immediately forced down again, the failover procedure will be carried out in order to failover all the messages in the link's transmq queue onto the other working link. The link and node state is also set to FAILINGOVER as part of the process. The message will be transmited in form of a FAILOVER_MSG, so its size is plus of 40 bytes (= the message header size). There is no problem if the original message size is not larger than the link's MTU - 40, and indeed this is the max size of a normal payload messages. However, in the situation above, because the link has just been up, the messages in the link's transmq are almost SYNCH_MSGs which had been generated by the link synching procedure, then their size might reach the max value already! When the FAILOVER_MSG is built on the top of such a SYNCH_MSG, its size will exceed the link's MTU. As a result, the messages are dropped silently and the failover procedure will never end up, the link will not be able to exit the FAILINGOVER state, so cannot be re-established. 2) The same scenario above can happen more easily in case the MTU of the links is set differently or when changing. In that case, as long as a large message in the failure link's transmq queue was built and fragmented with its link's MTU > the other link's one, the issue will happen (there is no need of a link synching in advance). 3) The link synching procedure also faces with the same issue but since the link synching is only started upon receipt of a SYNCH_MSG, dropping the message will not result in a state deadlock, but it is not expected as design. The 1) & 3) issues are resolved by the last commit that only a dummy SYNCH_MSG (i.e. without data) is generated at the link synching, so the size of a FAILOVER_MSG if any then will never exceed the link's MTU. For the 2) issue, the only solution is trying to fragment the messages in the failure link's transmq queue according to the working link's MTU so they can be failovered then. A new function is made to accomplish this, it will still be a TUNNEL PROTOCOL/FAILOVER MSG but if the original message size is too large, it will be fragmented & reassembled at the receiving side. Acked-by: Ying Xue <ying.xue@windriver.com> Acked-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-24 09:56:12 +08:00
int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
int pktmax, struct sk_buff_head *frags);
2015-02-05 21:36:36 +08:00
int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
int offset, int dsz, int mtu, struct sk_buff_head *list);
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err);
bool tipc_msg_assemble(struct sk_buff_head *list);
bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq);
bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg,
struct sk_buff_head *cpy);
void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
struct sk_buff *skb);
bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy);
static inline u16 buf_seqno(struct sk_buff *skb)
{
return msg_seqno(buf_msg(skb));
}
static inline int buf_roundup_len(struct sk_buff *skb)
{
return (skb->len / 1024 + 1) * 1024;
}
/* tipc_skb_peek(): peek and reserve first buffer in list
* @list: list to be peeked in
* Returns pointer to first buffer in list, if any
*/
static inline struct sk_buff *tipc_skb_peek(struct sk_buff_head *list,
spinlock_t *lock)
{
struct sk_buff *skb;
spin_lock_bh(lock);
skb = skb_peek(list);
if (skb)
skb_get(skb);
spin_unlock_bh(lock);
return skb;
}
tipc: resolve race problem at unicast message reception TIPC handles message cardinality and sequencing at the link layer, before passing messages upwards to the destination sockets. During the upcall from link to socket no locks are held. It is therefore possible, and we see it happen occasionally, that messages arriving in different threads and delivered in sequence still bypass each other before they reach the destination socket. This must not happen, since it violates the sequentiality guarantee. We solve this by adding a new input buffer queue to the link structure. Arriving messages are added safely to the tail of that queue by the link, while the head of the queue is consumed, also safely, by the receiving socket. Sequentiality is secured per socket by only allowing buffers to be dequeued inside the socket lock. Since there may be multiple simultaneous readers of the queue, we use a 'filter' parameter to reduce the risk that they peek the same buffer from the queue, hence also reducing the risk of contention on the receiving socket locks. This solves the sequentiality problem, and seems to cause no measurable performance degradation. A nice side effect of this change is that lock handling in the functions tipc_rcv() and tipc_bcast_rcv() now becomes uniform, something that will enable future simplifications of those functions. Reviewed-by: Ying Xue <ying.xue@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-05 21:36:41 +08:00
/* tipc_skb_peek_port(): find a destination port, ignoring all destinations
* up to and including 'filter'.
* Note: ignoring previously tried destinations minimizes the risk of
* contention on the socket lock
* @list: list to be peeked in
* @filter: last destination to be ignored from search
* Returns a destination port number, of applicable.
*/
static inline u32 tipc_skb_peek_port(struct sk_buff_head *list, u32 filter)
{
struct sk_buff *skb;
u32 dport = 0;
bool ignore = true;
spin_lock_bh(&list->lock);
skb_queue_walk(list, skb) {
dport = msg_destport(buf_msg(skb));
if (!filter || skb_queue_is_last(list, skb))
break;
if (dport == filter)
ignore = false;
else if (!ignore)
break;
}
spin_unlock_bh(&list->lock);
return dport;
}
/* tipc_skb_dequeue(): unlink first buffer with dest 'dport' from list
* @list: list to be unlinked from
* @dport: selection criteria for buffer to unlink
*/
static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list,
u32 dport)
{
struct sk_buff *_skb, *tmp, *skb = NULL;
spin_lock_bh(&list->lock);
skb_queue_walk_safe(list, _skb, tmp) {
if (msg_destport(buf_msg(_skb)) == dport) {
__skb_unlink(_skb, list);
skb = _skb;
break;
}
}
spin_unlock_bh(&list->lock);
return skb;
}
/* tipc_skb_queue_splice_tail - append an skb list to lock protected list
* @list: the new list to append. Not lock protected
* @head: target list. Lock protected.
*/
static inline void tipc_skb_queue_splice_tail(struct sk_buff_head *list,
struct sk_buff_head *head)
{
spin_lock_bh(&head->lock);
skb_queue_splice_tail(list, head);
spin_unlock_bh(&head->lock);
}
/* tipc_skb_queue_splice_tail_init - merge two lock protected skb lists
* @list: the new list to add. Lock protected. Will be reinitialized
* @head: target list. Lock protected.
*/
static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list,
struct sk_buff_head *head)
{
struct sk_buff_head tmp;
__skb_queue_head_init(&tmp);
spin_lock_bh(&list->lock);
skb_queue_splice_tail_init(list, &tmp);
spin_unlock_bh(&list->lock);
tipc_skb_queue_splice_tail(&tmp, head);
}
tipc: reduce duplicate packets for unicast traffic For unicast transmission, the current NACK sending althorithm is over- active that forces the sending side to retransmit a packet that is not really lost but just arrived at the receiving side with some delay, or even retransmit same packets that have already been retransmitted before. As a result, many duplicates are observed also under normal condition, ie. without packet loss. One example case is: node1 transmits 1 2 3 4 10 5 6 7 8 9, when node2 receives packet #10, it puts into the deferdq. When the packet #5 comes it sends NACK with gap [6 - 9]. However, shortly after that, when packet #6 arrives, it pulls out packet #10 from the deferfq, but it is still out of order, so it makes another NACK with gap [7 - 9] and so on ... Finally, node1 has to retransmit the packets 5 6 7 8 9 a number of times, but in fact all the packets are not lost at all, so duplicates! This commit reduces duplicates by changing the condition to send NACK, also restricting the retransmissions on individual packets via a timer of about 1ms. However, it also needs to say that too tricky condition for NACKs or too long timeout value for retransmissions will result in performance reducing! The criterias in this commit are found to be effective for both the requirements to reduce duplicates but not affect performance. The tipc_link_rcv() is also improved to only dequeue skb from the link deferdq if it is expected (ie. its seqno <= rcv_nxt). Acked-by: Ying Xue <ying.xue@windriver.com> Acked-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-04 12:09:52 +08:00
/* __tipc_skb_dequeue() - dequeue the head skb according to expected seqno
* @list: list to be dequeued from
* @seqno: seqno of the expected msg
*
* returns skb dequeued from the list if its seqno is less than or equal to
* the expected one, otherwise the skb is still hold
*
* Note: must be used with appropriate locks held only
*/
static inline struct sk_buff *__tipc_skb_dequeue(struct sk_buff_head *list,
u16 seqno)
{
struct sk_buff *skb = skb_peek(list);
if (skb && less_eq(buf_seqno(skb), seqno)) {
__skb_unlink(skb, list);
return skb;
}
return NULL;
}
#endif