/*

 * sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem.

 *

 * Begun April 1, 1996, Mike Shaver.

 * Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS]

 */

#include <linux/mm.h>

#include <linux/module.h>

#include <linux/sysctl.h>

#include <linux/igmp.h>

#include <linux/inetdevice.h>

#include <linux/seqlock.h>

#include <linux/init.h>

#include <net/snmp.h>

#include <net/icmp.h>

#include <net/ip.h>

#include <net/route.h>

#include <net/tcp.h>

#include <net/udp.h>

#include <net/cipso_ipv4.h>

#include <net/inet_frag.h>

static int zero;

static int tcp_retr1_max = 255;

static int ip_local_port_range_min[] = { 1, 1 };

static int ip_local_port_range_max[] = { 65535, 65535 };

/* Update system visible IP port range */

static void set_local_port_range(int range[2])

{

	write_seqlock(&sysctl_local_ports.lock);

	sysctl_local_ports.range[0] = range[0];

	sysctl_local_ports.range[1] = range[1];

	write_sequnlock(&sysctl_local_ports.lock);

}

/* Validate changes from /proc interface. */

static int ipv4_local_port_range(ctl_table *table, int write, struct file *filp,

				 void __user *buffer,

				 size_t *lenp, loff_t *ppos)

{

	int ret;

	int range[2];

	ctl_table tmp = {

		.data = &range,

		.maxlen = sizeof(range),

		.mode = table->mode,

		.extra1 = &ip_local_port_range_min,

		.extra2 = &ip_local_port_range_max,

	};

	inet_get_local_port_range(range, range + 1);

	ret = proc_dointvec_minmax(&tmp, write, filp, buffer, lenp, ppos);

	if (write && ret == 0) {

		if (range[1] < range[0])

			ret = -EINVAL;

		else

			set_local_port_range(range);

	}

	return ret;

}

/* Validate changes from sysctl interface. */

static int ipv4_sysctl_local_port_range(ctl_table *table,

					 void __user *oldval,

					 size_t __user *oldlenp,

					void __user *newval, size_t newlen)

{

	int ret;

	int range[2];

	ctl_table tmp = {

		.data = &range,

		.maxlen = sizeof(range),

		.mode = table->mode,

		.extra1 = &ip_local_port_range_min,

		.extra2 = &ip_local_port_range_max,

	};

	inet_get_local_port_range(range, range + 1);

	ret = sysctl_intvec(&tmp, oldval, oldlenp, newval, newlen);

	if (ret == 0 && newval && newlen) {

		if (range[1] < range[0])

			ret = -EINVAL;

		else

			set_local_port_range(range);

	}

	return ret;

}

static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp,

				       void __user *buffer, size_t *lenp, loff_t *ppos)

{

	char val[TCP_CA_NAME_MAX];

	ctl_table tbl = {

		.data = val,

		.maxlen = TCP_CA_NAME_MAX,

	};

	int ret;

	tcp_get_default_congestion_control(val);

	ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos);

	if (write && ret == 0)

		ret = tcp_set_default_congestion_control(val);

	return ret;

}

static int sysctl_tcp_congestion_control(ctl_table *table,

					 void __user *oldval,

					 size_t __user *oldlenp,

					 void __user *newval, size_t newlen)

{

	char val[TCP_CA_NAME_MAX];

	ctl_table tbl = {

		.data = val,

		.maxlen = TCP_CA_NAME_MAX,

	};

	int ret;

	tcp_get_default_congestion_control(val);

	ret = sysctl_string(&tbl, oldval, oldlenp, newval, newlen);

	if (ret == 1 && newval && newlen)

		ret = tcp_set_default_congestion_control(val);

	return ret;

}

static int proc_tcp_available_congestion_control(ctl_table *ctl,

						 int write, struct file * filp,

						 void __user *buffer, size_t *lenp,

						 loff_t *ppos)

{

	ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, };

	int ret;

	tbl.data = kmalloc(tbl.maxlen, GFP_USER);

	if (!tbl.data)

		return -ENOMEM;

	tcp_get_available_congestion_control(tbl.data, TCP_CA_BUF_MAX);

	ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos);

	kfree(tbl.data);

	return ret;

}

static int proc_allowed_congestion_control(ctl_table *ctl,

					   int write, struct file * filp,

					   void __user *buffer, size_t *lenp,

					   loff_t *ppos)

{

	ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };

	int ret;

	tbl.data = kmalloc(tbl.maxlen, GFP_USER);

	if (!tbl.data)

		return -ENOMEM;

	tcp_get_allowed_congestion_control(tbl.data, tbl.maxlen);

	ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos);

	if (write && ret == 0)

		ret = tcp_set_allowed_congestion_control(tbl.data);

	kfree(tbl.data);

	return ret;

}

static int strategy_allowed_congestion_control(ctl_table *table,

					       void __user *oldval,

					       size_t __user *oldlenp,

					       void __user *newval,

					       size_t newlen)

{

	ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };

	int ret;

	tbl.data = kmalloc(tbl.maxlen, GFP_USER);

	if (!tbl.data)

		return -ENOMEM;

	tcp_get_available_congestion_control(tbl.data, tbl.maxlen);

	ret = sysctl_string(&tbl, oldval, oldlenp, newval, newlen);

	if (ret == 1 && newval && newlen)

		ret = tcp_set_allowed_congestion_control(tbl.data);

	kfree(tbl.data);

	return ret;

}

static struct ctl_table ipv4_table[] = {

	{

		.ctl_name	= NET_IPV4_TCP_TIMESTAMPS,

		.procname	= "tcp_timestamps",

		.data		= &sysctl_tcp_timestamps,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_WINDOW_SCALING,

		.procname	= "tcp_window_scaling",

		.data		= &sysctl_tcp_window_scaling,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_SACK,

		.procname	= "tcp_sack",

		.data		= &sysctl_tcp_sack,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_RETRANS_COLLAPSE,

		.procname	= "tcp_retrans_collapse",

		.data		= &sysctl_tcp_retrans_collapse,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_DEFAULT_TTL,

		.procname	= "ip_default_ttl",

		.data		= &sysctl_ip_default_ttl,

		.maxlen		= sizeof(int),

		.mode		= 0644,

		.extra2		= &init_net,

	},

	{

		.ctl_name	= NET_IPV4_NO_PMTU_DISC,

		.procname	= "ip_no_pmtu_disc",

		.data		= &ipv4_config.no_pmtu_disc,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_NONLOCAL_BIND,

		.procname	= "ip_nonlocal_bind",

		.data		= &sysctl_ip_nonlocal_bind,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_SYN_RETRIES,

		.procname	= "tcp_syn_retries",

		.data		= &sysctl_tcp_syn_retries,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_SYNACK_RETRIES,

		.procname	= "tcp_synack_retries",

		.data		= &sysctl_tcp_synack_retries,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_MAX_ORPHANS,

		.procname	= "tcp_max_orphans",

		.data		= &sysctl_tcp_max_orphans,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_MAX_TW_BUCKETS,

		.procname	= "tcp_max_tw_buckets",

		.data		= &tcp_death_row.sysctl_max_tw_buckets,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_DYNADDR,

		.procname	= "ip_dynaddr",

		.data		= &sysctl_ip_dynaddr,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_KEEPALIVE_TIME,

		.procname	= "tcp_keepalive_time",

		.data		= &sysctl_tcp_keepalive_time,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_KEEPALIVE_PROBES,

		.procname	= "tcp_keepalive_probes",

		.data		= &sysctl_tcp_keepalive_probes,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_KEEPALIVE_INTVL,

		.procname	= "tcp_keepalive_intvl",

		.data		= &sysctl_tcp_keepalive_intvl,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_RETRIES1,

		.procname	= "tcp_retries1",

		.data		= &sysctl_tcp_retries1,

		.maxlen		= sizeof(int),

		.mode		= 0644,

		.extra2		= &tcp_retr1_max

	},

	{

		.ctl_name	= NET_IPV4_TCP_RETRIES2,

		.procname	= "tcp_retries2",

		.data		= &sysctl_tcp_retries2,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_TCP_FIN_TIMEOUT,

		.procname	= "tcp_fin_timeout",

		.data		= &sysctl_tcp_fin_timeout,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

#ifdef CONFIG_SYN_COOKIES

	{

		.ctl_name	= NET_TCP_SYNCOOKIES,

		.procname	= "tcp_syncookies",

		.data		= &sysctl_tcp_syncookies,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

#endif

	{

		.ctl_name	= NET_TCP_TW_RECYCLE,

		.procname	= "tcp_tw_recycle",

		.data		= &tcp_death_row.sysctl_tw_recycle,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_ABORT_ON_OVERFLOW,

		.procname	= "tcp_abort_on_overflow",

		.data		= &sysctl_tcp_abort_on_overflow,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_STDURG,

		.procname	= "tcp_stdurg",

		.data		= &sysctl_tcp_stdurg,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_RFC1337,

		.procname	= "tcp_rfc1337",

		.data		= &sysctl_tcp_rfc1337,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_MAX_SYN_BACKLOG,

		.procname	= "tcp_max_syn_backlog",

		.data		= &sysctl_max_syn_backlog,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_LOCAL_PORT_RANGE,

		.procname	= "ip_local_port_range",

		.data		= &sysctl_local_ports.range,

		.maxlen		= sizeof(sysctl_local_ports.range),

		.mode		= 0644,

	},

#ifdef CONFIG_IP_MULTICAST

	{

		.ctl_name	= NET_IPV4_IGMP_MAX_MEMBERSHIPS,

		.procname	= "igmp_max_memberships",

		.data		= &sysctl_igmp_max_memberships,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

#endif

	{

		.ctl_name	= NET_IPV4_IGMP_MAX_MSF,

		.procname	= "igmp_max_msf",

		.data		= &sysctl_igmp_max_msf,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_INET_PEER_THRESHOLD,

		.procname	= "inet_peer_threshold",

		.data		= &inet_peer_threshold,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_INET_PEER_MINTTL,

		.procname	= "inet_peer_minttl",

		.data		= &inet_peer_minttl,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_INET_PEER_MAXTTL,

		.procname	= "inet_peer_maxttl",

		.data		= &inet_peer_maxttl,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_INET_PEER_GC_MINTIME,

		.procname	= "inet_peer_gc_mintime",

		.data		= &inet_peer_gc_mintime,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_IPV4_INET_PEER_GC_MAXTIME,

		.procname	= "inet_peer_gc_maxtime",

		.data		= &inet_peer_gc_maxtime,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_ORPHAN_RETRIES,

		.procname	= "tcp_orphan_retries",

		.data		= &sysctl_tcp_orphan_retries,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_FACK,

		.procname	= "tcp_fack",

		.data		= &sysctl_tcp_fack,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_REORDERING,

		.procname	= "tcp_reordering",

		.data		= &sysctl_tcp_reordering,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_ECN,

		.procname	= "tcp_ecn",

		.data		= &sysctl_tcp_ecn,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_DSACK,

		.procname	= "tcp_dsack",

		.data		= &sysctl_tcp_dsack,

		.maxlen		= sizeof(int),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_MEM,

		.procname	= "tcp_mem",

		.data		= &sysctl_tcp_mem,

		.maxlen		= sizeof(sysctl_tcp_mem),

		.mode		= 0644,

	},

	{

		.ctl_name	= NET_TCP_WMEM,

		.procname	= "tcp_wmem",

		.data		= &sysctl_tcp_wmem,

		.maxlen		= sizeof(sysctl_tcp_wmem),

		.mode		= 0644,

	},