2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-26 06:04:14 +08:00
linux-next/net/rxrpc/sysctl.c

164 lines
4.1 KiB
C
Raw Normal View History

/* sysctls for configuring RxRPC operating parameters
*
* Copyright (C) 2014 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#include <linux/sysctl.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
static struct ctl_table_header *rxrpc_sysctl_reg_table;
static const unsigned int zero = 0;
static const unsigned int one = 1;
static const unsigned int four = 4;
rxrpc: Limit the listening backlog Limit the socket incoming call backlog queue size so that a remote client can't pump in sufficient new calls that the server runs out of memory. Note that this is partially theoretical at the moment since whilst the number of calls is limited, the number of packets trying to set up new calls is not. This will be addressed in a later patch. If the caller of listen() specifies a backlog INT_MAX, then they get the current maximum; anything else greater than max_backlog or anything negative incurs EINVAL. The limit on the maximum queue size can be set by: echo N >/proc/sys/net/rxrpc/max_backlog where 4<=N<=32. Further, set the default backlog to 0, requiring listen() to be called before we start actually queueing new calls. Whilst this kind of is a change in the UAPI, the caller can't actually *accept* new calls anyway unless they've first called listen() to put the socket into the LISTENING state - thus the aforementioned new calls would otherwise just sit there, eating up kernel memory. (Note that sockets that don't have a non-zero service ID bound don't get incoming calls anyway.) Given that the default backlog is now 0, make the AFS filesystem call kernel_listen() to set the maximum backlog for itself. Possible improvements include: (1) Trimming a too-large backlog to max_backlog when listen is called. (2) Trimming the backlog value whenever the value is used so that changes to max_backlog are applied to an open socket automatically. Note that the AFS filesystem opens one socket and keeps it open for extended periods, so would miss out on changes to max_backlog. (3) Having a separate setting for the AFS filesystem. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-11 05:30:37 +08:00
static const unsigned int thirtytwo = 32;
static const unsigned int n_65535 = 65535;
static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1;
/*
* RxRPC operating parameters.
*
* See Documentation/networking/rxrpc.txt and the variable definitions for more
* information on the individual parameters.
*/
static struct ctl_table rxrpc_sysctl_table[] = {
/* Values measured in milliseconds */
{
.procname = "req_ack_delay",
.data = &rxrpc_requested_ack_delay,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = (void *)&zero,
},
{
.procname = "soft_ack_delay",
.data = &rxrpc_soft_ack_delay,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = (void *)&one,
},
{
.procname = "idle_ack_delay",
.data = &rxrpc_idle_ack_delay,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = (void *)&one,
},
{
.procname = "resend_timeout",
.data = &rxrpc_resend_timeout,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = (void *)&one,
},
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 14:30:52 +08:00
{
.procname = "idle_conn_expiry",
.data = &rxrpc_conn_idle_client_expiry,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
.extra1 = (void *)&one,
},
{
.procname = "idle_conn_fast_expiry",
.data = &rxrpc_conn_idle_client_fast_expiry,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
.extra1 = (void *)&one,
},
/* Values measured in seconds but used in jiffies */
{
.procname = "max_call_lifetime",
.data = &rxrpc_max_call_lifetime,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
.extra1 = (void *)&one,
},
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 14:30:52 +08:00
/* Non-time values */
{
.procname = "max_client_conns",
.data = &rxrpc_max_client_connections,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&rxrpc_reap_client_connections,
},
{
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 14:30:52 +08:00
.procname = "reap_client_conns",
.data = &rxrpc_reap_client_connections,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
rxrpc: Improve management and caching of client connection objects Improve the management and caching of client rxrpc connection objects. From this point, client connections will be managed separately from service connections because AF_RXRPC controls the creation and re-use of client connections but doesn't have that luxury with service connections. Further, there will be limits on the numbers of client connections that may be live on a machine. No direct restriction will be placed on the number of client calls, excepting that each client connection can support a maximum of four concurrent calls. Note that, for a number of reasons, we don't want to simply discard a client connection as soon as the last call is apparently finished: (1) Security is negotiated per-connection and the context is then shared between all calls on that connection. The context can be negotiated again if the connection lapses, but that involves holding up calls whilst at least two packets are exchanged and various crypto bits are performed - so we'd ideally like to cache it for a little while at least. (2) If a packet goes astray, we will need to retransmit a final ACK or ABORT packet. To make this work, we need to keep around the connection details for a little while. (3) The locally held structures represent some amount of setup time, to be weighed against their occupation of memory when idle. To this end, the client connection cache is managed by a state machine on each connection. There are five states: (1) INACTIVE - The connection is not held in any list and may not have been exposed to the world. If it has been previously exposed, it was discarded from the idle list after expiring. (2) WAITING - The connection is waiting for the number of client conns to drop below the maximum capacity. Calls may be in progress upon it from when it was active and got culled. The connection is on the rxrpc_waiting_client_conns list which is kept in to-be-granted order. Culled conns with waiters go to the back of the queue just like new conns. (3) ACTIVE - The connection has at least one call in progress upon it, it may freely grant available channels to new calls and calls may be waiting on it for channels to become available. The connection is on the rxrpc_active_client_conns list which is kept in activation order for culling purposes. (4) CULLED - The connection got summarily culled to try and free up capacity. Calls currently in progress on the connection are allowed to continue, but new calls will have to wait. There can be no waiters in this state - the conn would have to go to the WAITING state instead. (5) IDLE - The connection has no calls in progress upon it and must have been exposed to the world (ie. the EXPOSED flag must be set). When it expires, the EXPOSED flag is cleared and the connection transitions to the INACTIVE state. The connection is on the rxrpc_idle_client_conns list which is kept in order of how soon they'll expire. A connection in the ACTIVE or CULLED state must have at least one active call upon it; if in the WAITING state it may have active calls upon it; other states may not have active calls. As long as a connection remains active and doesn't get culled, it may continue to process calls - even if there are connections on the wait queue. This simplifies things a bit and reduces the amount of checking we need do. There are a couple flags of relevance to the cache: (1) EXPOSED - The connection ID got exposed to the world. If this flag is set, an extra ref is added to the connection preventing it from being reaped when it has no calls outstanding. This flag is cleared and the ref dropped when a conn is discarded from the idle list. (2) DONT_REUSE - The connection should be discarded as soon as possible and should not be reused. This commit also provides a number of new settings: (*) /proc/net/rxrpc/max_client_conns The maximum number of live client connections. Above this number, new connections get added to the wait list and must wait for an active conn to be culled. Culled connections can be reused, but they will go to the back of the wait list and have to wait. (*) /proc/net/rxrpc/reap_client_conns If the number of desired connections exceeds the maximum above, the active connection list will be culled until there are only this many left in it. (*) /proc/net/rxrpc/idle_conn_expiry The normal expiry time for a client connection, provided there are fewer than reap_client_conns of them around. (*) /proc/net/rxrpc/idle_conn_fast_expiry The expedited expiry time, used when there are more than reap_client_conns of them around. Note that I combined the Tx wait queue with the channel grant wait queue to save space as only one of these should be in use at once. Note also that, for the moment, the service connection cache still uses the old connection management code. Signed-off-by: David Howells <dhowells@redhat.com>
2016-08-24 14:30:52 +08:00
.extra2 = (void *)&rxrpc_max_client_connections,
},
rxrpc: Limit the listening backlog Limit the socket incoming call backlog queue size so that a remote client can't pump in sufficient new calls that the server runs out of memory. Note that this is partially theoretical at the moment since whilst the number of calls is limited, the number of packets trying to set up new calls is not. This will be addressed in a later patch. If the caller of listen() specifies a backlog INT_MAX, then they get the current maximum; anything else greater than max_backlog or anything negative incurs EINVAL. The limit on the maximum queue size can be set by: echo N >/proc/sys/net/rxrpc/max_backlog where 4<=N<=32. Further, set the default backlog to 0, requiring listen() to be called before we start actually queueing new calls. Whilst this kind of is a change in the UAPI, the caller can't actually *accept* new calls anyway unless they've first called listen() to put the socket into the LISTENING state - thus the aforementioned new calls would otherwise just sit there, eating up kernel memory. (Note that sockets that don't have a non-zero service ID bound don't get incoming calls anyway.) Given that the default backlog is now 0, make the AFS filesystem call kernel_listen() to set the maximum backlog for itself. Possible improvements include: (1) Trimming a too-large backlog to max_backlog when listen is called. (2) Trimming the backlog value whenever the value is used so that changes to max_backlog are applied to an open socket automatically. Note that the AFS filesystem opens one socket and keeps it open for extended periods, so would miss out on changes to max_backlog. (3) Having a separate setting for the AFS filesystem. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-11 05:30:37 +08:00
{
.procname = "max_backlog",
.data = &rxrpc_max_backlog,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&four,
.extra2 = (void *)&thirtytwo,
},
{
.procname = "rx_window_size",
.data = &rxrpc_rx_window_size,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&n_max_acks,
},
{
.procname = "rx_mtu",
.data = &rxrpc_rx_mtu,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&n_65535,
},
{
.procname = "rx_jumbo_max",
.data = &rxrpc_rx_jumbo_max,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&four,
},
{ }
};
int __init rxrpc_sysctl_init(void)
{
rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc",
rxrpc_sysctl_table);
if (!rxrpc_sysctl_reg_table)
return -ENOMEM;
return 0;
}
void rxrpc_sysctl_exit(void)
{
if (rxrpc_sysctl_reg_table)
unregister_net_sysctl_table(rxrpc_sysctl_reg_table);
}