#include <linux/filter.h>
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/netdevice.h>
#include <linux/ratelimit.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/sched/isolation.h>
#include <linux/hex.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/net_ratelimit.h>
#include <net/busy_poll.h>
#include <net/pkt_sched.h>
#include <net/hotdata.h>
#include <net/proto_memory.h>
#include <net/rps.h>
#include "dev.h"
#include "net-sysfs.h"
static int int_3600 = 3600;
static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ;
static int net_msg_warn;
int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0;
EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net);
int sysctl_devconf_inherit_init_net __read_mostly;
EXPORT_SYMBOL(sysctl_devconf_inherit_init_net);
#if IS_ENABLED(CONFIG_NET_FLOW_LIMIT) || IS_ENABLED(CONFIG_RPS)
static int dump_cpumask(void *buffer, size_t *lenp, loff_t *ppos,
struct cpumask *mask)
{
char *kbuf;
int len;
if (*ppos || !*lenp) {
*lenp = 0;
return 0;
}
len = min(DIV_ROUND_UP(nr_cpumask_bits, 32) * (8 + 1), *lenp);
kbuf = kmalloc(len, GFP_KERNEL);
if (!kbuf) {
*lenp = 0;
return -ENOMEM;
}
len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask));
if (!len) {
*lenp = 0;
goto free_buf;
}
kbuf[len++] = '\n';
memcpy(buffer, kbuf, len);
*lenp = len;
*ppos += len;
free_buf:
kfree(kbuf);
return 0;
}
#endif
#ifdef CONFIG_RPS
DEFINE_MUTEX(rps_default_mask_mutex);
static int rps_default_mask_sysctl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net = (struct net *)table->data;
struct cpumask *mask;
int err = 0;
mutex_lock(&rps_default_mask_mutex);
mask = net->core.rps_default_mask;
if (write) {
if (!mask) {
mask = kzalloc(cpumask_size(), GFP_KERNEL);
net->core.rps_default_mask = mask;
}
err = -ENOMEM;
if (!mask)
goto done;
err = cpumask_parse(buffer, mask);
if (err)
goto done;
err = rps_cpumask_housekeeping(mask);
if (err)
goto done;
} else {
err = dump_cpumask(buffer, lenp, ppos,
mask ?: cpu_none_mask);
}
done:
mutex_unlock(&rps_default_mask_mutex);
return err;
}
static int rps_sock_flow_sysctl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int orig_size, size;
int ret, i;
struct ctl_table tmp = {
.data = &size,
.maxlen = sizeof(size),
.mode = table->mode
};
struct rps_sock_flow_table *orig_sock_table, *sock_table;
static DEFINE_MUTEX(sock_flow_mutex);
mutex_lock(&sock_flow_mutex);
orig_sock_table = rcu_dereference_protected(
net_hotdata.rps_sock_flow_table,
lockdep_is_held(&sock_flow_mutex));
size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0;
ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
if (write) {
if (size) {
if (size > 1<<29) {
mutex_unlock(&sock_flow_mutex);
return -EINVAL;
}
size = roundup_pow_of_two(size);
if (size != orig_size) {
sock_table =
vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size));
if (!sock_table) {
mutex_unlock(&sock_flow_mutex);
return -ENOMEM;
}
net_hotdata.rps_cpu_mask =
roundup_pow_of_two(nr_cpu_ids) - 1;
sock_table->mask = size - 1;
} else
sock_table = orig_sock_table;
for (i = 0; i < size; i++)
sock_table->ents[i] = RPS_NO_CPU;
} else
sock_table = NULL;
if (sock_table != orig_sock_table) {
rcu_assign_pointer(net_hotdata.rps_sock_flow_table,
sock_table);
if (sock_table) {
static_branch_inc(&rps_needed);
static_branch_inc(&rfs_needed);
}
if (orig_sock_table) {
static_branch_dec(&rps_needed);
static_branch_dec(&rfs_needed);
kvfree_rcu(orig_sock_table, rcu);
}
}
}
mutex_unlock(&sock_flow_mutex);
return ret;
}
#endif
#ifdef CONFIG_NET_FLOW_LIMIT
static DEFINE_MUTEX(flow_limit_update_mutex);
static int flow_limit_cpu_sysctl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct sd_flow_limit *cur;
struct softnet_data *sd;
cpumask_var_t mask;
int i, len, ret = 0;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
if (write) {
ret = cpumask_parse(buffer, mask);
if (ret)
goto done;
mutex_lock(&flow_limit_update_mutex);
len = sizeof(*cur) + netdev_flow_limit_table_len;
for_each_possible_cpu(i) {
sd = &per_cpu(softnet_data, i);
cur = rcu_dereference_protected(sd->flow_limit,
lockdep_is_held(&flow_limit_update_mutex));
if (cur && !cpumask_test_cpu(i, mask)) {
RCU_INIT_POINTER(sd->flow_limit, NULL);
kfree_rcu(cur, rcu);
} else if (!cur && cpumask_test_cpu(i, mask)) {
cur = kzalloc_node(len, GFP_KERNEL,
cpu_to_node(i));
if (!cur) {
ret = -ENOMEM;
goto write_unlock;
}
cur->log_buckets = ilog2(netdev_flow_limit_table_len);
rcu_assign_pointer(sd->flow_limit, cur);
}
}
write_unlock:
mutex_unlock(&flow_limit_update_mutex);
} else {
cpumask_clear(mask);
rcu_read_lock();
for_each_possible_cpu(i) {
sd = &per_cpu(softnet_data, i);
if (rcu_dereference(sd->flow_limit))
cpumask_set_cpu(i, mask);
}
rcu_read_unlock();
ret = dump_cpumask(buffer, lenp, ppos, mask);
}
done:
free_cpumask_var(mask);
return ret;
}
static int flow_limit_table_len_sysctl(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
unsigned int old, *ptr;
int ret;
mutex_lock(&flow_limit_update_mutex);
ptr = table->data;
old = *ptr;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write && !is_power_of_2(*ptr)) {
*ptr = old;
ret = -EINVAL;
}
mutex_unlock(&flow_limit_update_mutex);
return ret;
}
#endif
#ifdef CONFIG_NET_SCHED
static int set_default_qdisc(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
char id[IFNAMSIZ];
struct ctl_table tbl = {
.data = id,
.maxlen = IFNAMSIZ,
};
int ret;
qdisc_get_default(id, IFNAMSIZ);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
if (write && ret == 0)
ret = qdisc_set_default(id);
return ret;
}
#endif
static int proc_do_dev_weight(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
static DEFINE_MUTEX(dev_weight_mutex);
int ret, weight;
mutex_lock(&dev_weight_mutex);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write) {
weight = READ_ONCE(weight_p);
WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias);
WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias);
}
mutex_unlock(&dev_weight_mutex);
return ret;
}
static int proc_do_rss_key(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
char buf[NETDEV_RSS_KEY_LEN * 3];
struct ctl_table fake_table;
char *pos = buf;
for (int i = 0; i < NETDEV_RSS_KEY_LEN; i++) {
pos = hex_byte_pack(pos, netdev_rss_key[i]);
*pos++ = ':';
}
*(--pos) = 0;
fake_table.data = buf;
fake_table.maxlen = sizeof(buf);
return proc_dostring(&fake_table, write, buffer, lenp, ppos);
}
#ifdef CONFIG_BPF_JIT
static int proc_dointvec_minmax_bpf_enable(const struct ctl_table *table, int write,
void *buffer, size_t *lenp,
loff_t *ppos)
{
int ret, jit_enable = *(int *)table->data;
int min = *(int *)table->extra1;
int max = *(int *)table->extra2;
struct ctl_table tmp = *table;
if (write && !capable(CAP_SYS_ADMIN))
return -EPERM;
tmp.data = &jit_enable;
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && !ret) {
if (jit_enable < 2 ||
(jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) {
*(int *)table->data = jit_enable;
if (jit_enable == 2)
pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
} else {
ret = -EPERM;
}
}
if (write && ret && min == max)
pr_info_once("CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1.\n");
return ret;
}
# ifdef CONFIG_HAVE_EBPF_JIT
static int
proc_dointvec_minmax_bpf_restricted(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
# endif
static int
proc_dolongvec_minmax_bpf_restricted(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
static struct ctl_table net_core_table[] = {
{
.procname = "mem_pcpu_rsv",
.data = &net_hotdata.sysctl_mem_pcpu_rsv,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_mem_pcpu_rsv,
},
{
.procname = "dev_weight",
.data = &weight_p,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_do_dev_weight,
.extra1 = SYSCTL_ONE,
},
{
.procname = "dev_weight_rx_bias",
.data = &dev_weight_rx_bias,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_do_dev_weight,
.extra1 = SYSCTL_ONE,
},
{
.procname = "dev_weight_tx_bias",
.data = &dev_weight_tx_bias,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_do_dev_weight,
.extra1 = SYSCTL_ONE,
},
{
.procname = "netdev_max_backlog",
.data = &net_hotdata.max_backlog,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "qdisc_max_burst",
.data = &net_hotdata.qdisc_max_burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "netdev_rss_key",
.data = &netdev_rss_key,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_do_rss_key,
},
#ifdef CONFIG_BPF_JIT
{
.procname = "bpf_jit_enable",
.data = &bpf_jit_enable,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax_bpf_enable,
# ifdef CONFIG_BPF_JIT_ALWAYS_ON
.extra1 = SYSCTL_ONE,
.extra2 = SYSCTL_ONE,
# else
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
# endif
},
# ifdef CONFIG_HAVE_EBPF_JIT
{
.procname = "bpf_jit_harden",
.data = &bpf_jit_harden,
.maxlen = sizeof(int),
.mode = 0600,
.proc_handler = proc_dointvec_minmax_bpf_restricted,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{
.procname = "bpf_jit_kallsyms",
.data = &bpf_jit_kallsyms,
.maxlen = sizeof(int),
.mode = 0600,
.proc_handler = proc_dointvec_minmax_bpf_restricted,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
# endif
{
.procname = "bpf_jit_limit",
.data = &bpf_jit_limit,
.maxlen = sizeof(long),
.mode = 0600,
.proc_handler = proc_dolongvec_minmax_bpf_restricted,
.extra1 = SYSCTL_LONG_ONE,
.extra2 = &bpf_jit_limit_max,
},
#endif
{
.procname = "netdev_tstamp_prequeue",
.data = &net_hotdata.tstamp_prequeue,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "message_cost",
.data = &net_ratelimit_state.interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "message_burst",
.data = &net_ratelimit_state.burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
#ifdef CONFIG_RPS
{
.procname = "rps_sock_flow_entries",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = rps_sock_flow_sysctl
},
#endif
#ifdef CONFIG_NET_FLOW_LIMIT
{
.procname = "flow_limit_cpu_bitmap",
.mode = 0644,
.proc_handler = flow_limit_cpu_sysctl
},
{
.procname = "flow_limit_table_len",
.data = &netdev_flow_limit_table_len,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = flow_limit_table_len_sysctl
},
#endif
#ifdef CONFIG_NET_RX_BUSY_POLL
{
.procname = "busy_poll",
.data = &sysctl_net_busy_poll,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
{
.procname = "busy_read",
.data = &sysctl_net_busy_read,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
#endif
#ifdef CONFIG_NET_SCHED
{
.procname = "default_qdisc",
.mode = 0644,
.maxlen = IFNAMSIZ,
.proc_handler = set_default_qdisc
},
#endif
{
.procname = "netdev_budget",
.data = &net_hotdata.netdev_budget,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "warnings",
.data = &net_msg_warn,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
{
.procname = "max_skb_frags",
.data = &net_hotdata.sysctl_max_skb_frags,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = &max_skb_frags,
},
{
.procname = "netdev_budget_usecs",
.data = &net_hotdata.netdev_budget_usecs,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &netdev_budget_usecs_min,
},
{
.procname = "fb_tunnels_only_for_init_net",
.data = &sysctl_fb_tunnels_only_for_init_net,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{
.procname = "devconf_inherit_init_net",
.data = &sysctl_devconf_inherit_init_net,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_THREE,
},
{
.procname = "high_order_alloc_disable",
.data = &net_high_order_alloc_disable_key.key,
.maxlen = sizeof(net_high_order_alloc_disable_key),
.mode = 0644,
.proc_handler = proc_do_static_key,
},
{
.procname = "gro_normal_batch",
.data = &net_hotdata.gro_normal_batch,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
},
{
.procname = "netdev_unregister_timeout_secs",
.data = &netdev_unregister_timeout_secs,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ONE,
.extra2 = &int_3600,
},
{
.procname = "skb_defer_max",
.data = &net_hotdata.sysctl_skb_defer_max,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
};
static struct ctl_table netns_core_table[] = {
#if IS_ENABLED(CONFIG_RPS)
{
.procname = "rps_default_mask",
.data = &init_net,
.mode = 0644,
.proc_handler = rps_default_mask_sysctl
},
#endif
{
.procname = "somaxconn",
.data = &init_net.core.sysctl_somaxconn,
.maxlen = sizeof(int),
.mode = 0644,
.extra1 = SYSCTL_ZERO,
.proc_handler = proc_dointvec_minmax
},
{
.procname = "optmem_max",
.data = &init_net.core.sysctl_optmem_max,
.maxlen = sizeof(int),
.mode = 0644,
.extra1 = SYSCTL_ZERO,
.proc_handler = proc_dointvec_minmax
},
{
.procname = "txrehash",
.data = &init_net.core.sysctl_txrehash,
.maxlen = sizeof(u8),
.mode = 0644,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
.proc_handler = proc_dou8vec_minmax,
},
{
.procname = "txq_reselection_ms",
.data = &init_net.core.sysctl_txq_reselection,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "tstamp_allow_data",
.data = &init_net.core.sysctl_tstamp_allow_data,
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE
},
{
.procname = "bypass_prot_mem",
.data = &init_net.core.sysctl_bypass_prot_mem,
.maxlen = sizeof(u8),
.mode = 0644,
.proc_handler = proc_dou8vec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE
},
{
.procname = "wmem_max",
.data = &sysctl_wmem_max,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_sndbuf,
},
{
.procname = "rmem_max",
.data = &sysctl_rmem_max,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_rcvbuf,
},
{
.procname = "wmem_default",
.data = &sysctl_wmem_default,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_sndbuf,
},
{
.procname = "rmem_default",
.data = &sysctl_rmem_default,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_rcvbuf,
},
};
static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str)
{
if (!strncmp(str, "initns", 6))
sysctl_fb_tunnels_only_for_init_net = 1;
else if (!strncmp(str, "none", 4))
sysctl_fb_tunnels_only_for_init_net = 2;
return 1;
}
__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup);
static __net_init int sysctl_core_net_init(struct net *net)
{
size_t table_size = ARRAY_SIZE(netns_core_table);
struct ctl_table *tbl;
tbl = netns_core_table;
if (!net_eq(net, &init_net)) {
int i;
tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL);
if (tbl == NULL)
goto err_dup;
for (i = 0; i < table_size; ++i) {
if (tbl[i].data == &sysctl_wmem_max)
break;
tbl[i].data += (char *)net - (char *)&init_net;
}
for (; i < table_size; ++i)
tbl[i].mode &= ~0222;
}
net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, table_size);
if (net->core.sysctl_hdr == NULL)
goto err_reg;
return 0;
err_reg:
if (tbl != netns_core_table)
kfree(tbl);
err_dup:
return -ENOMEM;
}
static __net_exit void sysctl_core_net_exit(struct net *net)
{
const struct ctl_table *tbl;
tbl = net->core.sysctl_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->core.sysctl_hdr);
BUG_ON(tbl == netns_core_table);
#if IS_ENABLED(CONFIG_RPS)
kfree(net->core.rps_default_mask);
#endif
kfree(tbl);
}
static __net_initdata struct pernet_operations sysctl_core_ops = {
.init = sysctl_core_net_init,
.exit = sysctl_core_net_exit,
};
static __init int sysctl_core_init(void)
{
register_net_sysctl(&init_net, "net/core", net_core_table);
return register_pernet_subsys(&sysctl_core_ops);
}
fs_initcall(sysctl_core_init);
