linux/net/tipc/link.h

312 lines
10 KiB
C
Raw Normal View History

/*
* net/tipc/link.h: Include file for TIPC link code
*
* Copyright (c) 1995-2006, 2013-2014, Ericsson AB
* Copyright (c) 2004-2005, 2010-2011, Wind River Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the names of the copyright holders nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* Alternatively, this software may be distributed under the terms of the
* GNU General Public License ("GPL") version 2 as published by the Free
* Software Foundation.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef _TIPC_LINK_H
#define _TIPC_LINK_H
#include <net/genetlink.h>
#include "msg.h"
#include "node.h"
/* TIPC-specific error codes
*/
#define ELINKCONG EAGAIN /* link congestion <=> resource unavailable */
/* Out-of-range value for link sequence numbers
*/
#define INVALID_LINK_SEQ 0x10000
/* Link working states
*/
#define WORKING_WORKING 560810u
#define WORKING_UNKNOWN 560811u
#define RESET_UNKNOWN 560812u
#define RESET_RESET 560813u
/* Link endpoint execution states
*/
#define LINK_STARTED 0x0001
#define LINK_STOPPED 0x0002
#define LINK_SYNCHING 0x0004
#define LINK_FAILINGOVER 0x0008
/* Starting value for maximum packet size negotiation on unicast links
* (unless bearer MTU is less)
*/
#define MAX_PKT_DEFAULT 1500
struct tipc_stats {
u32 sent_info; /* used in counting # sent packets */
u32 recv_info; /* used in counting # recv'd packets */
u32 sent_states;
u32 recv_states;
u32 sent_probes;
u32 recv_probes;
u32 sent_nacks;
u32 recv_nacks;
u32 sent_acks;
u32 sent_bundled;
u32 sent_bundles;
u32 recv_bundled;
u32 recv_bundles;
u32 retransmitted;
u32 sent_fragmented;
u32 sent_fragments;
u32 recv_fragmented;
u32 recv_fragments;
u32 link_congs; /* # port sends blocked by congestion */
u32 deferred_recv;
u32 duplicates;
u32 max_queue_sz; /* send queue size high water mark */
u32 accu_queue_sz; /* used for send queue size profiling */
u32 queue_sz_counts; /* used for send queue size profiling */
u32 msg_length_counts; /* used for message length profiling */
u32 msg_lengths_total; /* used for message length profiling */
u32 msg_length_profile[7]; /* used for msg. length profiling */
};
/**
* struct tipc_link - TIPC link data structure
* @addr: network address of link's peer node
* @name: link name character string
* @media_addr: media address to use when sending messages over link
* @timer: link timer
* @owner: pointer to peer node
* @refcnt: reference counter for permanent references (owner node & timer)
* @flags: execution state flags for link endpoint instance
* @checkpoint: reference point for triggering link continuity checking
* @peer_session: link session # being used by peer end of link
* @peer_bearer_id: bearer id used by link's peer endpoint
* @bearer_id: local bearer id used by link
* @tolerance: minimum link continuity loss needed to reset link [in ms]
* @cont_intv: link continuity testing interval
* @abort_limit: # of unacknowledged continuity probes needed to reset link
* @state: current state of link FSM
* @fsm_msg_cnt: # of protocol messages link FSM has sent in current state
* @proto_msg: template for control messages generated by link
* @pmsg: convenience pointer to "proto_msg" field
* @priority: current link priority
* @net_plane: current link network plane ('A' through 'H')
* @backlog_limit: backlog queue congestion thresholds (indexed by importance)
* @exp_msg_count: # of tunnelled messages expected during link changeover
* @reset_checkpoint: seq # of last acknowledged message at time of link reset
* @mtu: current maximum packet size for this link
* @advertised_mtu: advertised own mtu when link is being established
* @transmitq: queue for sent, non-acked messages
* @backlogq: queue for messages waiting to be sent
* @next_out_no: next sequence number to use for outbound messages
* @last_retransmitted: sequence number of most recently retransmitted message
* @stale_count: # of identical retransmit requests made by peer
* @next_in_no: next sequence number to expect for inbound messages
* @deferred_queue: deferred queue saved OOS b'cast message received from node
* @unacked_window: # of inbound messages rx'd without ack'ing back to peer
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 14:36:41 +01:00
* @inputq: buffer queue for messages to be delivered upwards
* @namedq: buffer queue for name table messages to be delivered upwards
* @next_out: ptr to first unsent outbound message in queue
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 14:36:41 +01:00
* @wakeupq: linked list of wakeup msgs waiting for link congestion to abate
* @long_msg_seq_no: next identifier to use for outbound fragmented messages
* @reasm_buf: head of partially reassembled inbound message fragments
* @stats: collects statistics regarding link activity
*/
struct tipc_link {
u32 addr;
char name[TIPC_MAX_LINK_NAME];
struct tipc_media_addr media_addr;
struct timer_list timer;
struct tipc_node *owner;
struct kref ref;
/* Management and link supervision data */
unsigned int flags;
u32 checkpoint;
u32 peer_session;
u32 peer_bearer_id;
u32 bearer_id;
u32 tolerance;
unsigned long cont_intv;
u32 abort_limit;
int state;
u32 fsm_msg_cnt;
struct {
unchar hdr[INT_H_SIZE];
unchar body[TIPC_MAX_IF_NAME];
} proto_msg;
struct tipc_msg *pmsg;
u32 priority;
char net_plane;
u16 synch_point;
/* Failover */
u16 failover_pkts;
u16 failover_checkpt;
struct sk_buff *failover_skb;
/* Max packet negotiation */
u16 mtu;
u16 advertised_mtu;
/* Sending */
struct sk_buff_head transmq;
struct sk_buff_head backlogq;
struct {
u16 len;
u16 limit;
} backlog[5];
u32 next_out_no;
u32 window;
u32 last_retransmitted;
u32 stale_count;
/* Reception */
u32 next_in_no;
u32 rcv_unacked;
struct sk_buff_head deferdq;
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 14:36:41 +01:00
struct sk_buff_head inputq;
struct sk_buff_head namedq;
/* Congestion handling */
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 14:36:41 +01:00
struct sk_buff_head wakeupq;
tipc: message reassembly using fragment chain When the first fragment of a long data data message is received on a link, a reassembly buffer large enough to hold the data from this and all subsequent fragments of the message is allocated. The payload of each new fragment is copied into this buffer upon arrival. When the last fragment is received, the reassembled message is delivered upwards to the port/socket layer. Not only is this an inefficient approach, but it may also cause bursts of reassembly failures in low memory situations. since we may fail to allocate the necessary large buffer in the first place. Furthermore, after 100 subsequent such failures the link will be reset, something that in reality aggravates the situation. To remedy this problem, this patch introduces a different approach. Instead of allocating a big reassembly buffer, we now append the arriving fragments to a reassembly chain on the link, and deliver the whole chain up to the socket layer once the last fragment has been received. This is safe because the retransmission layer of a TIPC link always delivers packets in strict uninterrupted order, to the reassembly layer as to all other upper layers. Hence there can never be more than one fragment chain pending reassembly at any given time in a link, and we can trust (but still verify) that the fragments will be chained up in the correct order. Signed-off-by: Erik Hugne <erik.hugne@ericsson.com> Reviewed-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-06 09:28:06 +01:00
/* Fragmentation/reassembly */
struct sk_buff *reasm_buf;
/* Statistics */
struct tipc_stats stats;
};
struct tipc_port;
struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
struct tipc_bearer *b_ptr,
const struct tipc_media_addr *media_addr);
void tipc_link_delete(struct tipc_link *link);
void tipc_link_delete_list(struct net *net, unsigned int bearer_id,
bool shutting_down);
void tipc_link_failover_send_queue(struct tipc_link *l_ptr);
tipc: align tipc function names with common naming practice in the network Rename the following functions, which are shorter and more in line with common naming practice in the network subsystem. tipc_bclink_send_msg->tipc_bclink_xmit tipc_bclink_recv_pkt->tipc_bclink_rcv tipc_disc_recv_msg->tipc_disc_rcv tipc_link_send_proto_msg->tipc_link_proto_xmit link_recv_proto_msg->tipc_link_proto_rcv link_send_sections_long->tipc_link_iovec_long_xmit tipc_link_send_sections_fast->tipc_link_iovec_xmit_fast tipc_link_send_sync->tipc_link_sync_xmit tipc_link_recv_sync->tipc_link_sync_rcv tipc_link_send_buf->__tipc_link_xmit tipc_link_send->tipc_link_xmit tipc_link_send_names->tipc_link_names_xmit tipc_named_recv->tipc_named_rcv tipc_link_recv_bundle->tipc_link_bundle_rcv tipc_link_dup_send_queue->tipc_link_dup_queue_xmit link_send_long_buf->tipc_link_frag_xmit tipc_multicast->tipc_port_mcast_xmit tipc_port_recv_mcast->tipc_port_mcast_rcv tipc_port_reject_sections->tipc_port_iovec_reject tipc_port_recv_proto_msg->tipc_port_proto_rcv tipc_connect->tipc_port_connect __tipc_connect->__tipc_port_connect __tipc_disconnect->__tipc_port_disconnect tipc_disconnect->tipc_port_disconnect tipc_shutdown->tipc_port_shutdown tipc_port_recv_msg->tipc_port_rcv tipc_port_recv_sections->tipc_port_iovec_rcv release->tipc_release accept->tipc_accept bind->tipc_bind get_name->tipc_getname poll->tipc_poll send_msg->tipc_sendmsg send_packet->tipc_send_packet send_stream->tipc_send_stream recv_msg->tipc_recvmsg recv_stream->tipc_recv_stream connect->tipc_connect listen->tipc_listen shutdown->tipc_shutdown setsockopt->tipc_setsockopt getsockopt->tipc_getsockopt Above changes have no impact on current users of the functions. Signed-off-by: Ying Xue <ying.xue@windriver.com> Reviewed-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-18 09:06:46 +01:00
void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest);
void tipc_link_reset_fragments(struct tipc_link *l_ptr);
int tipc_link_is_up(struct tipc_link *l_ptr);
int tipc_link_is_active(struct tipc_link *l_ptr);
void tipc_link_purge_queues(struct tipc_link *l_ptr);
void tipc_link_reset_all(struct tipc_node *node);
void tipc_link_reset(struct tipc_link *l_ptr);
void tipc_link_reset_list(struct net *net, unsigned int bearer_id);
int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest,
u32 selector);
int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest,
u32 selector);
int __tipc_link_xmit(struct net *net, struct tipc_link *link,
struct sk_buff_head *list);
tipc: align tipc function names with common naming practice in the network Rename the following functions, which are shorter and more in line with common naming practice in the network subsystem. tipc_bclink_send_msg->tipc_bclink_xmit tipc_bclink_recv_pkt->tipc_bclink_rcv tipc_disc_recv_msg->tipc_disc_rcv tipc_link_send_proto_msg->tipc_link_proto_xmit link_recv_proto_msg->tipc_link_proto_rcv link_send_sections_long->tipc_link_iovec_long_xmit tipc_link_send_sections_fast->tipc_link_iovec_xmit_fast tipc_link_send_sync->tipc_link_sync_xmit tipc_link_recv_sync->tipc_link_sync_rcv tipc_link_send_buf->__tipc_link_xmit tipc_link_send->tipc_link_xmit tipc_link_send_names->tipc_link_names_xmit tipc_named_recv->tipc_named_rcv tipc_link_recv_bundle->tipc_link_bundle_rcv tipc_link_dup_send_queue->tipc_link_dup_queue_xmit link_send_long_buf->tipc_link_frag_xmit tipc_multicast->tipc_port_mcast_xmit tipc_port_recv_mcast->tipc_port_mcast_rcv tipc_port_reject_sections->tipc_port_iovec_reject tipc_port_recv_proto_msg->tipc_port_proto_rcv tipc_connect->tipc_port_connect __tipc_connect->__tipc_port_connect __tipc_disconnect->__tipc_port_disconnect tipc_disconnect->tipc_port_disconnect tipc_shutdown->tipc_port_shutdown tipc_port_recv_msg->tipc_port_rcv tipc_port_recv_sections->tipc_port_iovec_rcv release->tipc_release accept->tipc_accept bind->tipc_bind get_name->tipc_getname poll->tipc_poll send_msg->tipc_sendmsg send_packet->tipc_send_packet send_stream->tipc_send_stream recv_msg->tipc_recvmsg recv_stream->tipc_recv_stream connect->tipc_connect listen->tipc_listen shutdown->tipc_shutdown setsockopt->tipc_setsockopt getsockopt->tipc_getsockopt Above changes have no impact on current users of the functions. Signed-off-by: Ying Xue <ying.xue@windriver.com> Reviewed-by: Jon Maloy <jon.maloy@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-18 09:06:46 +01:00
void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob,
u32 gap, u32 tolerance, u32 priority);
void tipc_link_push_packets(struct tipc_link *l_ptr);
u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *buf);
void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
void tipc_link_retransmit(struct tipc_link *l_ptr,
struct sk_buff *start, u32 retransmits);
struct sk_buff *tipc_skb_queue_next(const struct sk_buff_head *list,
const struct sk_buff *skb);
int tipc_nl_link_dump(struct sk_buff *skb, struct netlink_callback *cb);
int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info);
int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info);
int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info);
int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]);
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 14:36:41 +01:00
void link_prepare_wakeup(struct tipc_link *l);
/*
* Link sequence number manipulation routines (uses modulo 2**16 arithmetic)
*/
static inline u32 buf_seqno(struct sk_buff *buf)
{
return msg_seqno(buf_msg(buf));
}
static inline u32 mod(u32 x)
{
return x & 0xffffu;
}
static inline int less_eq(u32 left, u32 right)
{
return mod(right - left) < 32768u;
}
static inline int more(u32 left, u32 right)
{
return !less_eq(left, right);
}
static inline int less(u32 left, u32 right)
{
return less_eq(left, right) && (mod(right) != mod(left));
}
static inline u32 lesser(u32 left, u32 right)
{
return less_eq(left, right) ? left : right;
}
2015-02-05 14:36:36 +01:00
static inline u32 link_own_addr(struct tipc_link *l)
{
return msg_prevnode(l->pmsg);
}
/*
* Link status checking routines
*/
static inline int link_working_working(struct tipc_link *l_ptr)
{
return l_ptr->state == WORKING_WORKING;
}
static inline int link_working_unknown(struct tipc_link *l_ptr)
{
return l_ptr->state == WORKING_UNKNOWN;
}
static inline int link_reset_unknown(struct tipc_link *l_ptr)
{
return l_ptr->state == RESET_UNKNOWN;
}
static inline int link_reset_reset(struct tipc_link *l_ptr)
{
return l_ptr->state == RESET_RESET;
}
#endif