aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/sysctl_net_ipv4.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/sysctl_net_ipv4.c')
-rw-r--r--net/ipv4/sysctl_net_ipv4.c268
1 files changed, 128 insertions, 140 deletions
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index fa2f63fc453..79a007c5255 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,7 @@
static int zero;
static int one = 1;
static int four = 4;
+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 };
@@ -36,26 +37,30 @@ 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(int range[2])
+static void set_local_port_range(struct net *net, 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);
+ write_seqlock(&net->ipv4.ip_local_ports.lock);
+ net->ipv4.ip_local_ports.range[0] = range[0];
+ net->ipv4.ip_local_ports.range[1] = range[1];
+ write_sequnlock(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
-static int ipv4_local_port_range(ctl_table *table, int write,
+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];
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &range,
.maxlen = sizeof(range),
.mode = table->mode,
@@ -63,14 +68,15 @@ static int ipv4_local_port_range(ctl_table *table, int write,
.extra2 = &ip_local_port_range_max,
};
- inet_get_local_port_range(range, range + 1);
+ 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(range);
+ set_local_port_range(net, range);
}
return ret;
@@ -80,27 +86,31 @@ static int ipv4_local_port_range(ctl_table *table, int write,
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(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ } 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;
- write_seqlock(&sysctl_local_ports.lock);
+ 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(&sysctl_local_ports.lock);
+ write_sequnlock(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
-static int ipv4_ping_group_range(ctl_table *table, int write,
+static int ipv4_ping_group_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
@@ -108,7 +118,7 @@ static int ipv4_ping_group_range(ctl_table *table, int write,
int ret;
gid_t urange[2];
kgid_t low, high;
- ctl_table tmp = {
+ struct ctl_table tmp = {
.data = &urange,
.maxlen = sizeof(urange),
.mode = table->mode,
@@ -135,11 +145,11 @@ static int ipv4_ping_group_range(ctl_table *table, int write,
return ret;
}
-static int proc_tcp_congestion_control(ctl_table *ctl, int write,
+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];
- ctl_table tbl = {
+ struct ctl_table tbl = {
.data = val,
.maxlen = TCP_CA_NAME_MAX,
};
@@ -153,12 +163,12 @@ static int proc_tcp_congestion_control(ctl_table *ctl, int write,
return ret;
}
-static int proc_tcp_available_congestion_control(ctl_table *ctl,
+static int proc_tcp_available_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, };
+ struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX, };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
@@ -170,12 +180,12 @@ static int proc_tcp_available_congestion_control(ctl_table *ctl,
return ret;
}
-static int proc_allowed_congestion_control(ctl_table *ctl,
+static int proc_allowed_congestion_control(struct ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };
+ struct ctl_table tbl = { .maxlen = TCP_CA_BUF_MAX };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
@@ -190,53 +200,11 @@ static int proc_allowed_congestion_control(ctl_table *ctl,
return ret;
}
-static int ipv4_tcp_mem(ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int ret;
- unsigned long vec[3];
- struct net *net = current->nsproxy->net_ns;
-#ifdef CONFIG_MEMCG_KMEM
- struct mem_cgroup *memcg;
-#endif
-
- ctl_table tmp = {
- .data = &vec,
- .maxlen = sizeof(vec),
- .mode = ctl->mode,
- };
-
- if (!write) {
- ctl->data = &net->ipv4.sysctl_tcp_mem;
- return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
- }
-
- ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
- if (ret)
- return ret;
-
-#ifdef CONFIG_MEMCG_KMEM
- rcu_read_lock();
- memcg = mem_cgroup_from_task(current);
-
- tcp_prot_mem(memcg, vec[0], 0);
- tcp_prot_mem(memcg, vec[1], 1);
- tcp_prot_mem(memcg, vec[2], 2);
- rcu_read_unlock();
-#endif
-
- net->ipv4.sysctl_tcp_mem[0] = vec[0];
- net->ipv4.sysctl_tcp_mem[1] = vec[1];
- net->ipv4.sysctl_tcp_mem[2] = vec[2];
-
- return 0;
-}
-
-static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
- size_t *lenp, loff_t *ppos)
+static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
{
- ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
+ 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 */
@@ -263,6 +231,11 @@ static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
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);
}
@@ -313,13 +286,6 @@ static struct ctl_table ipv4_table[] = {
.extra2 = &ip_ttl_max,
},
{
- .procname = "ip_no_pmtu_disc",
- .data = &ipv4_config.no_pmtu_disc,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "ip_nonlocal_bind",
.data = &sysctl_ip_nonlocal_bind,
.maxlen = sizeof(int),
@@ -331,7 +297,9 @@ static struct ctl_table ipv4_table[] = {
.data = &sysctl_tcp_syn_retries,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &tcp_syn_retries_min,
+ .extra2 = &tcp_syn_retries_max
},
{
.procname = "tcp_synack_retries",
@@ -469,20 +437,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "ip_local_port_range",
- .data = &sysctl_local_ports.range,
- .maxlen = sizeof(sysctl_local_ports.range),
- .mode = 0644,
- .proc_handler = ipv4_local_port_range,
- },
- {
- .procname = "ip_local_reserved_ports",
- .data = NULL, /* initialized in sysctl_ipv4_init */
- .maxlen = 65536,
- .mode = 0644,
- .proc_handler = proc_do_large_bitmap,
- },
- {
.procname = "igmp_max_memberships",
.data = &sysctl_igmp_max_memberships,
.maxlen = sizeof(int),
@@ -546,6 +500,13 @@ static struct ctl_table ipv4_table[] = {
.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),
@@ -554,6 +515,13 @@ static struct ctl_table ipv4_table[] = {
.extra1 = &one,
},
{
+ .procname = "tcp_notsent_lowat",
+ .data = &sysctl_tcp_notsent_lowat,
+ .maxlen = sizeof(sysctl_tcp_notsent_lowat),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "tcp_rmem",
.data = &sysctl_tcp_rmem,
.maxlen = sizeof(sysctl_tcp_rmem),
@@ -719,20 +687,13 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_allowed_congestion_control,
},
{
- .procname = "tcp_max_ssthresh",
- .data = &sysctl_tcp_max_ssthresh,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.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),
@@ -749,6 +710,24 @@ static struct ctl_table ipv4_table[] = {
.extra2 = &four,
},
{
+ .procname = "tcp_min_tso_segs",
+ .data = &sysctl_tcp_min_tso_segs,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &gso_max_segs,
+ },
+ {
+ .procname = "tcp_autocorking",
+ .data = &sysctl_tcp_autocorking,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
@@ -819,7 +798,7 @@ static struct ctl_table ipv4_net_table[] = {
},
{
.procname = "ping_group_range",
- .data = &init_net.ipv4.sysctl_ping_group_range,
+ .data = &init_net.ipv4.ping_group_range.range,
.maxlen = sizeof(gid_t)*2,
.mode = 0644,
.proc_handler = ipv4_ping_group_range,
@@ -832,10 +811,46 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_mem",
- .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem),
+ .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 = "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 = ipv4_tcp_mem,
+ .proc_handler = proc_dointvec,
},
{ }
};
@@ -846,47 +861,29 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
table = ipv4_net_table;
if (!net_eq(net, &init_net)) {
+ int i;
+
table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL);
if (table == NULL)
goto err_alloc;
- table[0].data =
- &net->ipv4.sysctl_icmp_echo_ignore_all;
- table[1].data =
- &net->ipv4.sysctl_icmp_echo_ignore_broadcasts;
- table[2].data =
- &net->ipv4.sysctl_icmp_ignore_bogus_error_responses;
- table[3].data =
- &net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr;
- table[4].data =
- &net->ipv4.sysctl_icmp_ratelimit;
- table[5].data =
- &net->ipv4.sysctl_icmp_ratemask;
- table[6].data =
- &net->ipv4.sysctl_ping_group_range;
- table[7].data =
- &net->ipv4.sysctl_tcp_ecn;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[0].procname = NULL;
+ /* 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;
}
- /*
- * Sane defaults - nobody may create ping sockets.
- * Boot scripts should set this to distro-specific group.
- */
- net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
- net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
-
- tcp_init_mem(net);
-
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
if (net->ipv4.ipv4_hdr == NULL)
goto err_reg;
+ net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+ if (!net->ipv4.sysctl_local_reserved_ports)
+ goto err_ports;
+
return 0;
+err_ports:
+ unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
@@ -898,6 +895,7 @@ 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);
@@ -911,16 +909,6 @@ static __net_initdata struct pernet_operations ipv4_sysctl_ops = {
static __init int sysctl_ipv4_init(void)
{
struct ctl_table_header *hdr;
- struct ctl_table *i;
-
- for (i = ipv4_table; i->procname; i++) {
- if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
- i->data = sysctl_local_reserved_ports;
- break;
- }
- }
- if (!i->procname)
- return -EINVAL;
hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table);
if (hdr == NULL)
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 13:20:48 +0000