davidlt/kernel-ark
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
b7de529c79
kernel-ark/net/ipv4/sysctl_net_ipv4.c
David Ahern a6db4494d2 net: ipv4: Consider failed nexthops in multipath routes 
Multipath route lookups should consider knowledge about next hops and not
select a hop that is known to be failed.

Example:

                     [h2]                   [h3]   15.0.0.5
                      |                      |
                     3|                     3|
                    [SP1]                  [SP2]--+
                     1  2                   1     2
                     |  |     /-------------+     |
                     |   \   /                    |
                     |     X                      |
                     |    / \                     |
                     |   /   \---------------\    |
                     1  2                     1   2
         12.0.0.2  [TOR1] 3-----------------3 [TOR2] 12.0.0.3
                     4                         4
                      \                       /
                        \                    /
                         \                  /
                          -------|   |-----/
                                 1   2
                                [TOR3]
                                  3|
                                   |
                                  [h1]  12.0.0.1

host h1 with IP 12.0.0.1 has 2 paths to host h3 at 15.0.0.5:

    root@h1:~# ip ro ls
    ...
    12.0.0.0/24 dev swp1  proto kernel  scope link  src 12.0.0.1
    15.0.0.0/16
            nexthop via 12.0.0.2  dev swp1 weight 1
            nexthop via 12.0.0.3  dev swp1 weight 1
    ...

If the link between tor3 and tor1 is down and the link between tor1
and tor2 then tor1 is effectively cut-off from h1. Yet the route lookups
in h1 are alternating between the 2 routes: ping 15.0.0.5 gets one and
ssh 15.0.0.5 gets the other. Connections that attempt to use the
12.0.0.2 nexthop fail since that neighbor is not reachable:

    root@h1:~# ip neigh show
    ...
    12.0.0.3 dev swp1 lladdr 00:02:00:00:00:1b REACHABLE
    12.0.0.2 dev swp1  FAILED
    ...

The failed path can be avoided by considering known neighbor information
when selecting next hops. If the neighbor lookup fails we have no
knowledge about the nexthop, so give it a shot. If there is an entry
then only select the nexthop if the state is sane. This is similar to
what fib_detect_death does.

To maintain backward compatibility use of the neighbor information is
based on a new sysctl, fib_multipath_use_neigh.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-11 15:16:13 -04:00

1049 lines
25 KiB
C
Raw Blame History

/*
* 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 <linux/slab.h>
#include <linux/nsproxy.h>
#include <linux/swap.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>
#include <net/ping.h>
static int zero;
static int one = 1;
static int four = 4;
static int thousand = 1000;
static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
static int tcp_adv_win_scale_min = -31;
static int tcp_adv_win_scale_max = 31;
static int ip_ttl_min = 1;
static int ip_ttl_max = 255;
static int tcp_syn_retries_min = 1;
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
/* Update system visible IP port range */
static void set_local_port_range(struct net *net, int range[2])
{
bool same_parity = !((range[0] ^ range[1]) & 1);
write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
if (same_parity && !net->ipv4.ip_local_ports.warned) {
net->ipv4.ip_local_ports.warned = true;
pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
}
net->ipv4.ip_local_ports.range[0] = range[0];
net->ipv4.ip_local_ports.range[1] = range[1];
write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
static int ipv4_local_port_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
struct net *net =
container_of(table->data, struct net, ipv4.ip_local_ports.range);
int ret;
int range[2];
struct 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(net, &range[0], &range[1]);
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (range[1] < range[0])
ret = -EINVAL;
else
set_local_port_range(net, range);
}
return ret;
}
static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
{
kgid_t *data = table->data;
struct net *net =
container_of(table->data, struct net, ipv4.ping_group_range.range);
unsigned int seq;
do {
seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
*low = data[0];
*high = data[1];
} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
}
/* Update system visible IP port range */
static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
{
kgid_t *data = table->data;
struct net *net =
container_of(table->data, struct net, ipv4.ping_group_range.range);
write_seqlock(&net->ipv4.ip_local_ports.lock);
data[0] = low;
data[1] = high;
write_sequnlock(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
static int ipv4_ping_group_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
struct user_namespace *user_ns = current_user_ns();
int ret;
gid_t urange[2];
kgid_t low, high;
struct ctl_table tmp = {
.data = &urange,
.maxlen = sizeof(urange),
.mode = table->mode,
.extra1 = &ip_ping_group_range_min,
.extra2 = &ip_ping_group_range_max,
};
inet_get_ping_group_range_table(table, &low, &high);
urange[0] = from_kgid_munged(user_ns, low);
urange[1] = from_kgid_munged(user_ns, high);
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
low = make_kgid(user_ns, urange[0]);
high = make_kgid(user_ns, urange[1]);
if (!gid_valid(low) || !gid_valid(high) ||
(urange[1] < urange[0]) || gid_lt(high, low)) {
low = make_kgid(&init_user_ns, 1);
high = make_kgid(&init_user_ns, 0);
}
set_ping_group_range(table, low, high);
}
return ret;
}
static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
char val[TCP_CA_NAME_MAX];
struct ctl_table tbl = {
.data = val,
.maxlen = TCP_CA_NAME_MAX,
};
int ret;
tcp_get_default_congestion_control(val);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0)
ret = tcp_set_default_congestion_control(val);
return ret;
}
static int proc_tcp_available_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct 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, buffer, lenp, ppos);
kfree(tbl.data);
return ret;
}
static int proc_allowed_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct 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, buffer, lenp, ppos);
if (write && ret == 0)
ret = tcp_set_allowed_congestion_control(tbl.data);
kfree(tbl.data);
return ret;
}
static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
int ret;
u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
if (!tbl.data)
return -ENOMEM;
rcu_read_lock();
ctxt = rcu_dereference(tcp_fastopen_ctx);
if (ctxt)
memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
memset(user_key, 0, sizeof(user_key));
rcu_read_unlock();
snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
user_key[0], user_key[1], user_key[2], user_key[3]);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (sscanf(tbl.data, "%x-%x-%x-%x", user_key, user_key + 1,
user_key + 2, user_key + 3) != 4) {
ret = -EINVAL;
goto bad_key;
}
/* Generate a dummy secret but don't publish it. This
* is needed so we don't regenerate a new key on the
* first invocation of tcp_fastopen_cookie_gen
*/
tcp_fastopen_init_key_once(false);
tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
user_key[0], user_key[1], user_key[2], user_key[3],
(char *)tbl.data, ret);
kfree(tbl.data);
return ret;
}
static struct ctl_table ipv4_table[] = {
{
.procname = "tcp_timestamps",
.data = &sysctl_tcp_timestamps,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_window_scaling",
.data = &sysctl_tcp_window_scaling,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_sack",
.data = &sysctl_tcp_sack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_retrans_collapse",
.data = &sysctl_tcp_retrans_collapse,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_max_orphans",
.data = &sysctl_tcp_max_orphans,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_max_tw_buckets",
.data = &tcp_death_row.sysctl_max_tw_buckets,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_fastopen",
.data = &sysctl_tcp_fastopen,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_fastopen_key",
.mode = 0600,
.maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
.proc_handler = proc_tcp_fastopen_key,
},
{
.procname = "tcp_tw_recycle",
.data = &tcp_death_row.sysctl_tw_recycle,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_abort_on_overflow",
.data = &sysctl_tcp_abort_on_overflow,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_stdurg",
.data = &sysctl_tcp_stdurg,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_rfc1337",
.data = &sysctl_tcp_rfc1337,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_max_syn_backlog",
.data = &sysctl_max_syn_backlog,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "inet_peer_threshold",
.data = &inet_peer_threshold,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "inet_peer_minttl",
.data = &inet_peer_minttl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "inet_peer_maxttl",
.data = &inet_peer_maxttl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_fack",
.data = &sysctl_tcp_fack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_recovery",
.data = &sysctl_tcp_recovery,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_max_reordering",
.data = &sysctl_tcp_max_reordering,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_dsack",
.data = &sysctl_tcp_dsack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_mem",
.maxlen = sizeof(sysctl_tcp_mem),
.data = &sysctl_tcp_mem,
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "tcp_wmem",
.data = &sysctl_tcp_wmem,
.maxlen = sizeof(sysctl_tcp_wmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
},
{
.procname = "tcp_rmem",
.data = &sysctl_tcp_rmem,
.maxlen = sizeof(sysctl_tcp_rmem),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
},
{
.procname = "tcp_app_win",
.data = &sysctl_tcp_app_win,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_adv_win_scale",
.data = &sysctl_tcp_adv_win_scale,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &tcp_adv_win_scale_min,
.extra2 = &tcp_adv_win_scale_max,
},
{
.procname = "tcp_tw_reuse",
.data = &sysctl_tcp_tw_reuse,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_frto",
.data = &sysctl_tcp_frto,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_min_rtt_wlen",
.data = &sysctl_tcp_min_rtt_wlen,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_low_latency",
.data = &sysctl_tcp_low_latency,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_no_metrics_save",
.data = &sysctl_tcp_nometrics_save,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_moderate_rcvbuf",
.data = &sysctl_tcp_moderate_rcvbuf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_tso_win_divisor",
.data = &sysctl_tcp_tso_win_divisor,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_congestion_control",
.mode = 0644,
.maxlen = TCP_CA_NAME_MAX,
.proc_handler = proc_tcp_congestion_control,
},
{
.procname = "tcp_workaround_signed_windows",
.data = &sysctl_tcp_workaround_signed_windows,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_limit_output_bytes",
.data = &sysctl_tcp_limit_output_bytes,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_challenge_ack_limit",
.data = &sysctl_tcp_challenge_ack_limit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_slow_start_after_idle",
.data = &sysctl_tcp_slow_start_after_idle,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#ifdef CONFIG_NETLABEL
{
.procname = "cipso_cache_enable",
.data = &cipso_v4_cache_enabled,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cipso_cache_bucket_size",
.data = &cipso_v4_cache_bucketsize,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cipso_rbm_optfmt",
.data = &cipso_v4_rbm_optfmt,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "cipso_rbm_strictvalid",
.data = &cipso_v4_rbm_strictvalid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#endif /* CONFIG_NETLABEL */
{
.procname = "tcp_available_congestion_control",
.maxlen = TCP_CA_BUF_MAX,
.mode = 0444,
.proc_handler = proc_tcp_available_congestion_control,
},
{
.procname = "tcp_allowed_congestion_control",
.maxlen = TCP_CA_BUF_MAX,
.mode = 0644,
.proc_handler = proc_allowed_congestion_control,
},
{
.procname = "tcp_thin_linear_timeouts",
.data = &sysctl_tcp_thin_linear_timeouts,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_thin_dupack",
.data = &sysctl_tcp_thin_dupack,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_early_retrans",
.data = &sysctl_tcp_early_retrans,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &four,
},
{
.procname = "tcp_min_tso_segs",
.data = &sysctl_tcp_min_tso_segs,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
.extra2 = &gso_max_segs,
},
{
.procname = "tcp_pacing_ss_ratio",
.data = &sysctl_tcp_pacing_ss_ratio,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &thousand,
},
{
.procname = "tcp_pacing_ca_ratio",
.data = &sysctl_tcp_pacing_ca_ratio,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &thousand,
},
{
.procname = "tcp_autocorking",
.data = &sysctl_tcp_autocorking,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "tcp_invalid_ratelimit",
.data = &sysctl_tcp_invalid_ratelimit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "icmp_msgs_per_sec",
.data = &sysctl_icmp_msgs_per_sec,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
{
.procname = "icmp_msgs_burst",
.data = &sysctl_icmp_msgs_burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
{
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
{
.procname = "udp_rmem_min",
.data = &sysctl_udp_rmem_min,
.maxlen = sizeof(sysctl_udp_rmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one
},
{
.procname = "udp_wmem_min",
.data = &sysctl_udp_wmem_min,
.maxlen = sizeof(sysctl_udp_wmem_min),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one
},
{ }
};
static struct ctl_table ipv4_net_table[] = {
{
.procname = "icmp_echo_ignore_all",
.data = &init_net.ipv4.sysctl_icmp_echo_ignore_all,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_echo_ignore_broadcasts",
.data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_ignore_bogus_error_responses",
.data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_errors_use_inbound_ifaddr",
.data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "icmp_ratelimit",
.data = &init_net.ipv4.sysctl_icmp_ratelimit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "icmp_ratemask",
.data = &init_net.ipv4.sysctl_icmp_ratemask,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ping_group_range",
.data = &init_net.ipv4.ping_group_range.range,
.maxlen = sizeof(gid_t)*2,
.mode = 0644,
.proc_handler = ipv4_ping_group_range,
},
{
.procname = "tcp_ecn",
.data = &init_net.ipv4.sysctl_tcp_ecn,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_ecn_fallback",
.data = &init_net.ipv4.sysctl_tcp_ecn_fallback,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_dynaddr",
.data = &init_net.ipv4.sysctl_ip_dynaddr,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_early_demux",
.data = &init_net.ipv4.sysctl_ip_early_demux,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_default_ttl",
.data = &init_net.ipv4.sysctl_ip_default_ttl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &ip_ttl_min,
.extra2 = &ip_ttl_max,
},
{
.procname = "ip_local_port_range",
.maxlen = sizeof(init_net.ipv4.ip_local_ports.range),
.data = &init_net.ipv4.ip_local_ports.range,
.mode = 0644,
.proc_handler = ipv4_local_port_range,
},
{
.procname = "ip_local_reserved_ports",
.data = &init_net.ipv4.sysctl_local_reserved_ports,
.maxlen = 65536,
.mode = 0644,
.proc_handler = proc_do_large_bitmap,
},
{
.procname = "ip_no_pmtu_disc",
.data = &init_net.ipv4.sysctl_ip_no_pmtu_disc,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "ip_forward_use_pmtu",
.data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "ip_nonlocal_bind",
.data = &init_net.ipv4.sysctl_ip_nonlocal_bind,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "fwmark_reflect",
.data = &init_net.ipv4.sysctl_fwmark_reflect,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_fwmark_accept",
.data = &init_net.ipv4.sysctl_tcp_fwmark_accept,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_NET_L3_MASTER_DEV
{
.procname = "tcp_l3mdev_accept",
.data = &init_net.ipv4.sysctl_tcp_l3mdev_accept,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{
.procname = "tcp_mtu_probing",
.data = &init_net.ipv4.sysctl_tcp_mtu_probing,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_base_mss",
.data = &init_net.ipv4.sysctl_tcp_base_mss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_probe_threshold",
.data = &init_net.ipv4.sysctl_tcp_probe_threshold,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "tcp_probe_interval",
.data = &init_net.ipv4.sysctl_tcp_probe_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "igmp_link_local_mcast_reports",
.data = &init_net.ipv4.sysctl_igmp_llm_reports,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "igmp_max_memberships",
.data = &init_net.ipv4.sysctl_igmp_max_memberships,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "igmp_max_msf",
.data = &init_net.ipv4.sysctl_igmp_max_msf,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#ifdef CONFIG_IP_MULTICAST
{
.procname = "igmp_qrv",
.data = &init_net.ipv4.sysctl_igmp_qrv,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one
},
#endif
{
.procname = "tcp_keepalive_time",
.data = &init_net.ipv4.sysctl_tcp_keepalive_time,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_keepalive_probes",
.data = &init_net.ipv4.sysctl_tcp_keepalive_probes,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_keepalive_intvl",
.data = &init_net.ipv4.sysctl_tcp_keepalive_intvl,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_syn_retries",
.data = &init_net.ipv4.sysctl_tcp_syn_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &tcp_syn_retries_min,
.extra2 = &tcp_syn_retries_max
},
{
.procname = "tcp_synack_retries",
.data = &init_net.ipv4.sysctl_tcp_synack_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#ifdef CONFIG_SYN_COOKIES
{
.procname = "tcp_syncookies",
.data = &init_net.ipv4.sysctl_tcp_syncookies,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
#endif
{
.procname = "tcp_reordering",
.data = &init_net.ipv4.sysctl_tcp_reordering,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_retries1",
.data = &init_net.ipv4.sysctl_tcp_retries1,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra2 = &tcp_retr1_max
},
{
.procname = "tcp_retries2",
.data = &init_net.ipv4.sysctl_tcp_retries2,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_orphan_retries",
.data = &init_net.ipv4.sysctl_tcp_orphan_retries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "tcp_fin_timeout",
.data = &init_net.ipv4.sysctl_tcp_fin_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "tcp_notsent_lowat",
.data = &init_net.ipv4.sysctl_tcp_notsent_lowat,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_IP_ROUTE_MULTIPATH
{
.procname = "fib_multipath_use_neigh",
.data = &init_net.ipv4.sysctl_fib_multipath_use_neigh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &one,
},
#endif
{ }
};
static __net_init int ipv4_sysctl_init_net(struct net *net)
{
struct ctl_table *table;
table = ipv4_net_table;
if (!net_eq(net, &init_net)) {
int i;
table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL);
if (!table)
goto err_alloc;
/* Update the variables to point into the current struct net */
for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++)
table[i].data += (void *)net - (void *)&init_net;
}
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
if (!net->ipv4.ipv4_hdr)
goto err_reg;
net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
if (!net->ipv4.sysctl_local_reserved_ports)
goto err_ports;
net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
net->ipv4.sysctl_ip_dynaddr = 0;
net->ipv4.sysctl_ip_early_demux = 1;
return 0;
err_ports:
unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static __net_exit void ipv4_sysctl_exit_net(struct net *net)
{
struct ctl_table *table;
kfree(net->ipv4.sysctl_local_reserved_ports);
table = net->ipv4.ipv4_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
kfree(table);
}
static __net_initdata struct pernet_operations ipv4_sysctl_ops = {
.init = ipv4_sysctl_init_net,
.exit = ipv4_sysctl_exit_net,
};
static __init int sysctl_ipv4_init(void)
{
struct ctl_table_header *hdr;
hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table);
if (!hdr)
return -ENOMEM;
if (register_pernet_subsys(&ipv4_sysctl_ops)) {
unregister_net_sysctl_table(hdr);
return -ENOMEM;
}
return 0;
}
__initcall(sysctl_ipv4_init);
Reference in New Issue View Git Blame Copy Permalink