2014-03-12 19:31:09 +04:00
|
|
|
/* net/tipc/socket.h: Include file for TIPC socket code
|
|
|
|
|
*
|
|
|
|
|
* Copyright (c) 2014, Ericsson AB
|
|
|
|
|
* All rights reserved.
|
|
|
|
|
*
|
|
|
|
|
* Redistribution and use in source and binary forms, with or without
|
|
|
|
|
* modification, are permitted provided that the following conditions are met:
|
|
|
|
|
*
|
|
|
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
|
|
|
* notice, this list of conditions and the following disclaimer.
|
|
|
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
|
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
|
|
|
* documentation and/or other materials provided with the distribution.
|
|
|
|
|
* 3. Neither the names of the copyright holders nor the names of its
|
|
|
|
|
* contributors may be used to endorse or promote products derived from
|
|
|
|
|
* this software without specific prior written permission.
|
|
|
|
|
*
|
|
|
|
|
* Alternatively, this software may be distributed under the terms of the
|
|
|
|
|
* GNU General Public License ("GPL") version 2 as published by the Free
|
|
|
|
|
* Software Foundation.
|
|
|
|
|
*
|
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
|
|
|
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
|
|
|
|
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
|
|
|
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
|
|
|
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
|
|
|
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
|
|
|
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
|
|
|
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
|
|
|
* POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef _TIPC_SOCK_H
|
|
|
|
|
#define _TIPC_SOCK_H
|
|
|
|
|
|
|
|
|
|
#include "port.h"
|
|
|
|
|
#include <net/sock.h>
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* struct tipc_sock - TIPC socket structure
|
|
|
|
|
* @sk: socket - interacts with 'port' and with user via the socket API
|
|
|
|
|
* @port: port - interacts with 'sk' and with the rest of the TIPC stack
|
|
|
|
|
* @peer_name: the peer of the connection, if any
|
|
|
|
|
* @conn_timeout: the time we can wait for an unresponded setup request
|
tipc: compensate for double accounting in socket rcv buffer
The function net/core/sock.c::__release_sock() runs a tight loop
to move buffers from the socket backlog queue to the receive queue.
As a security measure, sk_backlog.len of the receiving socket
is not set to zero until after the loop is finished, i.e., until
the whole backlog queue has been transferred to the receive queue.
During this transfer, the data that has already been moved is counted
both in the backlog queue and the receive queue, hence giving an
incorrect picture of the available queue space for new arriving buffers.
This leads to unnecessary rejection of buffers by sk_add_backlog(),
which in TIPC leads to unnecessarily broken connections.
In this commit, we compensate for this double accounting by adding
a counter that keeps track of it. The function socket.c::backlog_rcv()
receives buffers one by one from __release_sock(), and adds them to the
socket receive queue. If the transfer is successful, it increases a new
atomic counter 'tipc_sock::dupl_rcvcnt' with 'truesize' of the
transferred buffer. If a new buffer arrives during this transfer and
finds the socket busy (owned), we attempt to add it to the backlog.
However, when sk_add_backlog() is called, we adjust the 'limit'
parameter with the value of the new counter, so that the risk of
inadvertent rejection is eliminated.
It should be noted that this change does not invalidate the original
purpose of zeroing 'sk_backlog.len' after the full transfer. We set an
upper limit for dupl_rcvcnt, so that if a 'wild' sender (i.e., one that
doesn't respect the send window) keeps pumping in buffers to
sk_add_backlog(), he will eventually reach an upper limit,
(2 x TIPC_CONN_OVERLOAD_LIMIT). After that, no messages can be added
to the backlog, and the connection will be broken. Ordinary, well-
behaved senders will never reach this buffer limit at all.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 13:39:09 +04:00
|
|
|
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
|
2014-03-12 19:31:09 +04:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
struct tipc_sock {
|
|
|
|
|
struct sock sk;
|
|
|
|
|
struct tipc_port port;
|
|
|
|
|
unsigned int conn_timeout;
|
tipc: compensate for double accounting in socket rcv buffer
The function net/core/sock.c::__release_sock() runs a tight loop
to move buffers from the socket backlog queue to the receive queue.
As a security measure, sk_backlog.len of the receiving socket
is not set to zero until after the loop is finished, i.e., until
the whole backlog queue has been transferred to the receive queue.
During this transfer, the data that has already been moved is counted
both in the backlog queue and the receive queue, hence giving an
incorrect picture of the available queue space for new arriving buffers.
This leads to unnecessary rejection of buffers by sk_add_backlog(),
which in TIPC leads to unnecessarily broken connections.
In this commit, we compensate for this double accounting by adding
a counter that keeps track of it. The function socket.c::backlog_rcv()
receives buffers one by one from __release_sock(), and adds them to the
socket receive queue. If the transfer is successful, it increases a new
atomic counter 'tipc_sock::dupl_rcvcnt' with 'truesize' of the
transferred buffer. If a new buffer arrives during this transfer and
finds the socket busy (owned), we attempt to add it to the backlog.
However, when sk_add_backlog() is called, we adjust the 'limit'
parameter with the value of the new counter, so that the risk of
inadvertent rejection is eliminated.
It should be noted that this change does not invalidate the original
purpose of zeroing 'sk_backlog.len' after the full transfer. We set an
upper limit for dupl_rcvcnt, so that if a 'wild' sender (i.e., one that
doesn't respect the send window) keeps pumping in buffers to
sk_add_backlog(), he will eventually reach an upper limit,
(2 x TIPC_CONN_OVERLOAD_LIMIT). After that, no messages can be added
to the backlog, and the connection will be broken. Ordinary, well-
behaved senders will never reach this buffer limit at all.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-14 13:39:09 +04:00
|
|
|
atomic_t dupl_rcvcnt;
|
2014-03-12 19:31:09 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static inline struct tipc_sock *tipc_sk(const struct sock *sk)
|
|
|
|
|
{
|
|
|
|
|
return container_of(sk, struct tipc_sock, sk);
|
|
|
|
|
}
|
|
|
|
|
|
2014-03-12 19:31:12 +04:00
|
|
|
static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port)
|
2014-03-12 19:31:09 +04:00
|
|
|
{
|
2014-03-12 19:31:12 +04:00
|
|
|
return container_of(port, struct tipc_sock, port);
|
2014-03-12 19:31:09 +04:00
|
|
|
}
|
|
|
|
|
|
2014-03-12 19:31:12 +04:00
|
|
|
static inline void tipc_sock_wakeup(struct tipc_sock *tsk)
|
2014-03-12 19:31:09 +04:00
|
|
|
{
|
2014-03-12 19:31:12 +04:00
|
|
|
tsk->sk.sk_write_space(&tsk->sk);
|
2014-03-12 19:31:10 +04:00
|
|
|
}
|
|
|
|
|
|
2014-05-14 13:39:15 +04:00
|
|
|
int tipc_sk_rcv(struct sk_buff *buf);
|
2014-03-12 19:31:10 +04:00
|
|
|
|
2014-03-12 19:31:09 +04:00
|
|
|
#endif
|