UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/net/netlink/af_netlink.c

2955 lines
70 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* NETLINK Kernel-user communication protocol.
*
* Authors: Alan Cox <alan@lxorguk.ukuu.org.uk>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
* Patrick McHardy <kaber@trash.net>
*
* Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith
* added netlink_proto_exit
* Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br>
* use nlk_sk, as sk->protinfo is on a diet 8)
* Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org>
* - inc module use count of module that owns
* the kernel socket in case userspace opens
* socket of same protocol
* - remove all module support, since netlink is
* mandatory if CONFIG_NET=y these days
*/
#include <linux/module.h>
#include <linux/bpf.h>
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/filter.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/security.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/random.h>
#include <linux/bitops.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <linux/audit.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/if_arp.h>
#include <linux/rhashtable.h>
#include <asm/cacheflush.h>
#include <linux/hash.h>
#include <linux/genetlink.h>
#include <linux/net_namespace.h>
#include <linux/nospec.h>
#include <linux/btf_ids.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>
#include <net/scm.h>
#include <net/netlink.h>
#define CREATE_TRACE_POINTS
#include <trace/events/netlink.h>
#include "af_netlink.h"
struct listeners {
struct rcu_head rcu;
unsigned long masks[];
};
/* state bits */
#define NETLINK_S_CONGESTED 0x0
static inline int netlink_is_kernel(struct sock *sk)
{
return nlk_test_bit(KERNEL_SOCKET, sk);
}
struct netlink_table *nl_table __read_mostly;
EXPORT_SYMBOL_GPL(nl_table);
static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS];
static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = {
"nlk_cb_mutex-ROUTE",
"nlk_cb_mutex-1",
"nlk_cb_mutex-USERSOCK",
"nlk_cb_mutex-FIREWALL",
"nlk_cb_mutex-SOCK_DIAG",
"nlk_cb_mutex-NFLOG",
"nlk_cb_mutex-XFRM",
"nlk_cb_mutex-SELINUX",
"nlk_cb_mutex-ISCSI",
"nlk_cb_mutex-AUDIT",
"nlk_cb_mutex-FIB_LOOKUP",
"nlk_cb_mutex-CONNECTOR",
"nlk_cb_mutex-NETFILTER",
"nlk_cb_mutex-IP6_FW",
"nlk_cb_mutex-DNRTMSG",
"nlk_cb_mutex-KOBJECT_UEVENT",
"nlk_cb_mutex-GENERIC",
"nlk_cb_mutex-17",
"nlk_cb_mutex-SCSITRANSPORT",
"nlk_cb_mutex-ECRYPTFS",
"nlk_cb_mutex-RDMA",
"nlk_cb_mutex-CRYPTO",
"nlk_cb_mutex-SMC",
"nlk_cb_mutex-23",
"nlk_cb_mutex-24",
"nlk_cb_mutex-25",
"nlk_cb_mutex-26",
"nlk_cb_mutex-27",
"nlk_cb_mutex-28",
"nlk_cb_mutex-29",
"nlk_cb_mutex-30",
"nlk_cb_mutex-31",
"nlk_cb_mutex-MAX_LINKS"
};
static int netlink_dump(struct sock *sk);
/* nl_table locking explained:
* Lookup and traversal are protected with an RCU read-side lock. Insertion
* and removal are protected with per bucket lock while using RCU list
* modification primitives and may run in parallel to RCU protected lookups.
* Destruction of the Netlink socket may only occur *after* nl_table_lock has
* been acquired * either during or after the socket has been removed from
* the list and after an RCU grace period.
*/
DEFINE_RWLOCK(nl_table_lock);
EXPORT_SYMBOL_GPL(nl_table_lock);
static atomic_t nl_table_users = ATOMIC_INIT(0);
#define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock));
static BLOCKING_NOTIFIER_HEAD(netlink_chain);
static const struct rhashtable_params netlink_rhashtable_params;
void do_trace_netlink_extack(const char *msg)
{
trace_netlink_extack(msg);
}
EXPORT_SYMBOL(do_trace_netlink_extack);
static inline u32 netlink_group_mask(u32 group)
{
if (group > 32)
return 0;
return group ? 1 << (group - 1) : 0;
}
static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
gfp_t gfp_mask)
{
unsigned int len = skb->len;
struct sk_buff *new;
new = alloc_skb(len, gfp_mask);
if (new == NULL)
return NULL;
NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
skb_put_data(new, skb->data, len);
return new;
}
static unsigned int netlink_tap_net_id;
struct netlink_tap_net {
struct list_head netlink_tap_all;
struct mutex netlink_tap_lock;
};
int netlink_add_tap(struct netlink_tap *nt)
{
struct net *net = dev_net(nt->dev);
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
if (unlikely(nt->dev->type != ARPHRD_NETLINK))
return -EINVAL;
mutex_lock(&nn->netlink_tap_lock);
list_add_rcu(&nt->list, &nn->netlink_tap_all);
mutex_unlock(&nn->netlink_tap_lock);
__module_get(nt->module);
return 0;
}
EXPORT_SYMBOL_GPL(netlink_add_tap);
static int __netlink_remove_tap(struct netlink_tap *nt)
{
struct net *net = dev_net(nt->dev);
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
bool found = false;
struct netlink_tap *tmp;
mutex_lock(&nn->netlink_tap_lock);
list_for_each_entry(tmp, &nn->netlink_tap_all, list) {
if (nt == tmp) {
list_del_rcu(&nt->list);
found = true;
goto out;
}
}
pr_warn("__netlink_remove_tap: %p not found\n", nt);
out:
mutex_unlock(&nn->netlink_tap_lock);
if (found)
module_put(nt->module);
return found ? 0 : -ENODEV;
}
int netlink_remove_tap(struct netlink_tap *nt)
{
int ret;
ret = __netlink_remove_tap(nt);
synchronize_net();
return ret;
}
EXPORT_SYMBOL_GPL(netlink_remove_tap);
static __net_init int netlink_tap_init_net(struct net *net)
{
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
INIT_LIST_HEAD(&nn->netlink_tap_all);
mutex_init(&nn->netlink_tap_lock);
return 0;
}
static struct pernet_operations netlink_tap_net_ops = {
.init = netlink_tap_init_net,
.id = &netlink_tap_net_id,
.size = sizeof(struct netlink_tap_net),
};
static bool netlink_filter_tap(const struct sk_buff *skb)
{
struct sock *sk = skb->sk;
/* We take the more conservative approach and
* whitelist socket protocols that may pass.
*/
switch (sk->sk_protocol) {
case NETLINK_ROUTE:
case NETLINK_USERSOCK:
case NETLINK_SOCK_DIAG:
case NETLINK_NFLOG:
case NETLINK_XFRM:
case NETLINK_FIB_LOOKUP:
case NETLINK_NETFILTER:
case NETLINK_GENERIC:
return true;
}
return false;
}
static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct net_device *dev)
{
struct sk_buff *nskb;
struct sock *sk = skb->sk;
int ret = -ENOMEM;
if (!net_eq(dev_net(dev), sock_net(sk)))
return 0;
dev_hold(dev);
if (is_vmalloc_addr(skb->head))
nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
else
nskb = skb_clone(skb, GFP_ATOMIC);
if (nskb) {
nskb->dev = dev;
nskb->protocol = htons((u16) sk->sk_protocol);
nskb->pkt_type = netlink_is_kernel(sk) ?
PACKET_KERNEL : PACKET_USER;
skb_reset_network_header(nskb);
ret = dev_queue_xmit(nskb);
if (unlikely(ret > 0))
ret = net_xmit_errno(ret);
}
dev_put(dev);
return ret;
}
static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn)
{
int ret;
struct netlink_tap *tmp;
if (!netlink_filter_tap(skb))
return;
list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) {
ret = __netlink_deliver_tap_skb(skb, tmp->dev);
if (unlikely(ret))
break;
}
}
static void netlink_deliver_tap(struct net *net, struct sk_buff *skb)
{
struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
rcu_read_lock();
if (unlikely(!list_empty(&nn->netlink_tap_all)))
__netlink_deliver_tap(skb, nn);
rcu_read_unlock();
}
static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
struct sk_buff *skb)
{
if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
netlink_deliver_tap(sock_net(dst), skb);
}
static void netlink_overrun(struct sock *sk)
{
if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) {
if (!test_and_set_bit(NETLINK_S_CONGESTED,
&nlk_sk(sk)->state)) {
WRITE_ONCE(sk->sk_err, ENOBUFS);
sk_error_report(sk);
}
}
atomic_inc(&sk->sk_drops);
}
static void netlink_rcv_wake(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (skb_queue_empty_lockless(&sk->sk_receive_queue))
clear_bit(NETLINK_S_CONGESTED, &nlk->state);
if (!test_bit(NETLINK_S_CONGESTED, &nlk->state))
wake_up_interruptible(&nlk->wait);
}
static void netlink_skb_destructor(struct sk_buff *skb)
{
if (is_vmalloc_addr(skb->head)) {
if (!skb->cloned ||
!atomic_dec_return(&(skb_shinfo(skb)->dataref)))
vfree_atomic(skb->head);
skb->head = NULL;
}
if (skb->sk != NULL)
sock_rfree(skb);
}
static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
WARN_ON(skb->sk != NULL);
skb->sk = sk;
skb->destructor = netlink_skb_destructor;
atomic_add(skb->truesize, &sk->sk_rmem_alloc);
sk_mem_charge(sk, skb->truesize);
}
static void netlink_sock_destruct(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->cb_running) {
if (nlk->cb.done)
nlk->cb.done(&nlk->cb);
module_put(nlk->cb.module);
kfree_skb(nlk->cb.skb);
}
skb_queue_purge(&sk->sk_receive_queue);
if (!sock_flag(sk, SOCK_DEAD)) {
printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
return;
}
WARN_ON(atomic_read(&sk->sk_rmem_alloc));
WARN_ON(refcount_read(&sk->sk_wmem_alloc));
WARN_ON(nlk_sk(sk)->groups);
}
static void netlink_sock_destruct_work(struct work_struct *work)
{
struct netlink_sock *nlk = container_of(work, struct netlink_sock,
work);
sk_free(&nlk->sk);
}
/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
* SMP. Look, when several writers sleep and reader wakes them up, all but one
* immediately hit write lock and grab all the cpus. Exclusive sleep solves
* this, _but_ remember, it adds useless work on UP machines.
*/
void netlink_table_grab(void)
__acquires(nl_table_lock)
{
might_sleep();
write_lock_irq(&nl_table_lock);
if (atomic_read(&nl_table_users)) {
DECLARE_WAITQUEUE(wait, current);
add_wait_queue_exclusive(&nl_table_wait, &wait);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (atomic_read(&nl_table_users) == 0)
break;
write_unlock_irq(&nl_table_lock);
schedule();
write_lock_irq(&nl_table_lock);
}
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nl_table_wait, &wait);
}
}
void netlink_table_ungrab(void)
__releases(nl_table_lock)
{
write_unlock_irq(&nl_table_lock);
wake_up(&nl_table_wait);
}
static inline void
netlink_lock_table(void)
{
unsigned long flags;
/* read_lock() synchronizes us to netlink_table_grab */
read_lock_irqsave(&nl_table_lock, flags);
atomic_inc(&nl_table_users);
read_unlock_irqrestore(&nl_table_lock, flags);
}
static inline void
netlink_unlock_table(void)
{
if (atomic_dec_and_test(&nl_table_users))
wake_up(&nl_table_wait);
}
struct netlink_compare_arg
{
possible_net_t pnet;
u32 portid;
};
/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */
#define netlink_compare_arg_len \
(offsetof(struct netlink_compare_arg, portid) + sizeof(u32))
static inline int netlink_compare(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct netlink_compare_arg *x = arg->key;
const struct netlink_sock *nlk = ptr;
return nlk->portid != x->portid ||
!net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
}
static void netlink_compare_arg_init(struct netlink_compare_arg *arg,
struct net *net, u32 portid)
{
memset(arg, 0, sizeof(*arg));
write_pnet(&arg->pnet, net);
arg->portid = portid;
}
static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
struct net *net)
{
struct netlink_compare_arg arg;
netlink_compare_arg_init(&arg, net, portid);
return rhashtable_lookup_fast(&table->hash, &arg,
netlink_rhashtable_params);
}
static int __netlink_insert(struct netlink_table *table, struct sock *sk)
{
struct netlink_compare_arg arg;
netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
return rhashtable_lookup_insert_key(&table->hash, &arg,
&nlk_sk(sk)->node,
netlink_rhashtable_params);
}
static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
{
struct netlink_table *table = &nl_table[protocol];
struct sock *sk;
rcu_read_lock();
sk = __netlink_lookup(table, portid, net);
if (sk)
sock_hold(sk);
rcu_read_unlock();
return sk;
}
static const struct proto_ops netlink_ops;
static void
netlink_update_listeners(struct sock *sk)
{
struct netlink_table *tbl = &nl_table[sk->sk_protocol];
unsigned long mask;
unsigned int i;
struct listeners *listeners;
listeners = nl_deref_protected(tbl->listeners);
if (!listeners)
return;
for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
mask = 0;
sk_for_each_bound(sk, &tbl->mc_list) {
if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
mask |= nlk_sk(sk)->groups[i];
}
listeners->masks[i] = mask;
}
/* this function is only called with the netlink table "grabbed", which
* makes sure updates are visible before bind or setsockopt return. */
}
static int netlink_insert(struct sock *sk, u32 portid)
{
struct netlink_table *table = &nl_table[sk->sk_protocol];
int err;
lock_sock(sk);
err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
if (nlk_sk(sk)->bound)
goto err;
/* portid can be read locklessly from netlink_getname(). */
WRITE_ONCE(nlk_sk(sk)->portid, portid);
sock_hold(sk);
err = __netlink_insert(table, sk);
if (err) {
/* In case the hashtable backend returns with -EBUSY
* from here, it must not escape to the caller.
*/
if (unlikely(err == -EBUSY))
err = -EOVERFLOW;
if (err == -EEXIST)
err = -EADDRINUSE;
sock_put(sk);
goto err;
}
/* We need to ensure that the socket is hashed and visible. */
smp_wmb();
/* Paired with lockless reads from netlink_bind(),
* netlink_connect() and netlink_sendmsg().
*/
WRITE_ONCE(nlk_sk(sk)->bound, portid);
err:
release_sock(sk);
return err;
}
static void netlink_remove(struct sock *sk)
{
struct netlink_table *table;
table = &nl_table[sk->sk_protocol];
if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node,
netlink_rhashtable_params)) {
WARN_ON(refcount_read(&sk->sk_refcnt) == 1);
__sock_put(sk);
}
netlink_table_grab();
if (nlk_sk(sk)->subscriptions) {
__sk_del_bind_node(sk);
netlink_update_listeners(sk);
}
if (sk->sk_protocol == NETLINK_GENERIC)
atomic_inc(&genl_sk_destructing_cnt);
netlink_table_ungrab();
}
struct proto netlink_proto = {
.name = "NETLINK",
.owner = THIS_MODULE,
.obj_size = sizeof(struct netlink_sock),
};
EXPORT_SYMBOL(netlink_proto);
static int __netlink_create(struct net *net, struct socket *sock,
struct mutex *cb_mutex, int protocol,
int kern)
{
struct sock *sk;
struct netlink_sock *nlk;
sock->ops = &netlink_ops;
sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern);
if (!sk)
return -ENOMEM;
sock_init_data(sock, sk);
nlk = nlk_sk(sk);
if (cb_mutex) {
nlk->cb_mutex = cb_mutex;
} else {
nlk->cb_mutex = &nlk->cb_def_mutex;
mutex_init(nlk->cb_mutex);
lockdep_set_class_and_name(nlk->cb_mutex,
nlk_cb_mutex_keys + protocol,
nlk_cb_mutex_key_strings[protocol]);
}
init_waitqueue_head(&nlk->wait);
sk->sk_destruct = netlink_sock_destruct;
sk->sk_protocol = protocol;
return 0;
}
static int netlink_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct module *module = NULL;
struct mutex *cb_mutex;
struct netlink_sock *nlk;
int (*bind)(struct net *net, int group);
void (*unbind)(struct net *net, int group);
void (*release)(struct sock *sock, unsigned long *groups);
int err = 0;
sock->state = SS_UNCONNECTED;
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
return -ESOCKTNOSUPPORT;
if (protocol < 0 || protocol >= MAX_LINKS)
return -EPROTONOSUPPORT;
protocol = array_index_nospec(protocol, MAX_LINKS);
netlink_lock_table();
#ifdef CONFIG_MODULES
if (!nl_table[protocol].registered && protocol != NETLINK_AUDIT && protocol != NETLINK_SELINUX) {
netlink_unlock_table();
request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol);
netlink_lock_table();
}
#endif
if (nl_table[protocol].registered &&
try_module_get(nl_table[protocol].module))
module = nl_table[protocol].module;
else
err = -EPROTONOSUPPORT;
cb_mutex = nl_table[protocol].cb_mutex;
bind = nl_table[protocol].bind;
unbind = nl_table[protocol].unbind;
release = nl_table[protocol].release;
netlink_unlock_table();
if (err < 0)
goto out;
err = __netlink_create(net, sock, cb_mutex, protocol, kern);
if (err < 0)
goto out_module;
sock_prot_inuse_add(net, &netlink_proto, 1);
nlk = nlk_sk(sock->sk);
nlk->module = module;
nlk->netlink_bind = bind;
nlk->netlink_unbind = unbind;
nlk->netlink_release = release;
out:
return err;
out_module:
module_put(module);
goto out;
}
static void deferred_put_nlk_sk(struct rcu_head *head)
{
struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
struct sock *sk = &nlk->sk;
kfree(nlk->groups);
nlk->groups = NULL;
if (!refcount_dec_and_test(&sk->sk_refcnt))
return;
if (nlk->cb_running && nlk->cb.done) {
INIT_WORK(&nlk->work, netlink_sock_destruct_work);
schedule_work(&nlk->work);
return;
}
sk_free(sk);
}
static int netlink_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk;
if (!sk)
return 0;
netlink_remove(sk);
sock_orphan(sk);
nlk = nlk_sk(sk);
/*
* OK. Socket is unlinked, any packets that arrive now
* will be purged.
*/
if (nlk->netlink_release)
nlk->netlink_release(sk, nlk->groups);
/* must not acquire netlink_table_lock in any way again before unbind
* and notifying genetlink is done as otherwise it might deadlock
*/
if (nlk->netlink_unbind) {
int i;
for (i = 0; i < nlk->ngroups; i++)
if (test_bit(i, nlk->groups))
nlk->netlink_unbind(sock_net(sk), i + 1);
}
if (sk->sk_protocol == NETLINK_GENERIC &&
atomic_dec_return(&genl_sk_destructing_cnt) == 0)
wake_up(&genl_sk_destructing_waitq);
sock->sk = NULL;
wake_up_interruptible_all(&nlk->wait);
skb_queue_purge(&sk->sk_write_queue);
if (nlk->portid && nlk->bound) {
struct netlink_notify n = {
.net = sock_net(sk),
.protocol = sk->sk_protocol,
.portid = nlk->portid,
};
blocking_notifier_call_chain(&netlink_chain,
NETLINK_URELEASE, &n);
}
module_put(nlk->module);
if (netlink_is_kernel(sk)) {
netlink_table_grab();
BUG_ON(nl_table[sk->sk_protocol].registered == 0);
if (--nl_table[sk->sk_protocol].registered == 0) {
struct listeners *old;
old = nl_deref_protected(nl_table[sk->sk_protocol].listeners);
RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL);
kfree_rcu(old, rcu);
nl_table[sk->sk_protocol].module = NULL;
nl_table[sk->sk_protocol].bind = NULL;
nl_table[sk->sk_protocol].unbind = NULL;
nl_table[sk->sk_protocol].flags = 0;
nl_table[sk->sk_protocol].registered = 0;
}
netlink_table_ungrab();
}
sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
/* Because struct net might disappear soon, do not keep a pointer. */
if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) {
__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
/* Because of deferred_put_nlk_sk and use of work queue,
* it is possible netns will be freed before this socket.
*/
sock_net_set(sk, &init_net);
__netns_tracker_alloc(&init_net, &sk->ns_tracker,
false, GFP_KERNEL);
}
call_rcu(&nlk->rcu, deferred_put_nlk_sk);
return 0;
}
static int netlink_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct netlink_table *table = &nl_table[sk->sk_protocol];
s32 portid = task_tgid_vnr(current);
int err;
s32 rover = -4096;
bool ok;
retry:
cond_resched();
rcu_read_lock();
ok = !__netlink_lookup(table, portid, net);
rcu_read_unlock();
if (!ok) {
/* Bind collision, search negative portid values. */
if (rover == -4096)
/* rover will be in range [S32_MIN, -4097] */
rover = S32_MIN + get_random_u32_below(-4096 - S32_MIN);
else if (rover >= -4096)
rover = -4097;
portid = rover--;
goto retry;
}
err = netlink_insert(sk, portid);
if (err == -EADDRINUSE)
goto retry;
/* If 2 threads race to autobind, that is fine. */
if (err == -EBUSY)
err = 0;
return err;
}
/**
* __netlink_ns_capable - General netlink message capability test
* @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
* @user_ns: The user namespace of the capability to use
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has the capability @cap in the user namespace @user_ns.
*/
bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
struct user_namespace *user_ns, int cap)
{
return ((nsp->flags & NETLINK_SKB_DST) ||
file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
ns_capable(user_ns, cap);
}
EXPORT_SYMBOL(__netlink_ns_capable);
/**
* netlink_ns_capable - General netlink message capability test
* @skb: socket buffer holding a netlink command from userspace
* @user_ns: The user namespace of the capability to use
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has the capability @cap in the user namespace @user_ns.
*/
bool netlink_ns_capable(const struct sk_buff *skb,
struct user_namespace *user_ns, int cap)
{
return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
}
EXPORT_SYMBOL(netlink_ns_capable);
/**
* netlink_capable - Netlink global message capability test
* @skb: socket buffer holding a netlink command from userspace
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has the capability @cap in all user namespaces.
*/
bool netlink_capable(const struct sk_buff *skb, int cap)
{
return netlink_ns_capable(skb, &init_user_ns, cap);
}
EXPORT_SYMBOL(netlink_capable);
/**
* netlink_net_capable - Netlink network namespace message capability test
* @skb: socket buffer holding a netlink command from userspace
* @cap: The capability to use
*
* Test to see if the opener of the socket we received the message
* from had when the netlink socket was created and the sender of the
* message has the capability @cap over the network namespace of
* the socket we received the message from.
*/
bool netlink_net_capable(const struct sk_buff *skb, int cap)
{
return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
}
EXPORT_SYMBOL(netlink_net_capable);
static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].flags & flag) ||
ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
}
static void
netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->subscriptions && !subscriptions)
__sk_del_bind_node(sk);
else if (!nlk->subscriptions && subscriptions)
sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list);
nlk->subscriptions = subscriptions;
}
static int netlink_realloc_groups(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
unsigned int groups;
unsigned long *new_groups;
int err = 0;
netlink_table_grab();
groups = nl_table[sk->sk_protocol].groups;
if (!nl_table[sk->sk_protocol].registered) {
err = -ENOENT;
goto out_unlock;
}
if (nlk->ngroups >= groups)
goto out_unlock;
new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC);
if (new_groups == NULL) {
err = -ENOMEM;
goto out_unlock;
}
memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0,
NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
nlk->groups = new_groups;
nlk->ngroups = groups;
out_unlock:
netlink_table_ungrab();
return err;
}
static void netlink_undo_bind(int group, long unsigned int groups,
struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
int undo;
if (!nlk->netlink_unbind)
return;
for (undo = 0; undo < group; undo++)
if (test_bit(undo, &groups))
nlk->netlink_unbind(sock_net(sk), undo + 1);
}
static int netlink_bind(struct socket *sock, struct sockaddr *addr,
int addr_len)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err = 0;
unsigned long groups;
bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
return -EINVAL;
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
groups = nladdr->nl_groups;
/* Only superuser is allowed to listen multicasts */
if (groups) {
if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
return err;
}
if (nlk->ngroups < BITS_PER_LONG)
groups &= (1UL << nlk->ngroups) - 1;
/* Paired with WRITE_ONCE() in netlink_insert() */
bound = READ_ONCE(nlk->bound);
if (bound) {
/* Ensure nlk->portid is up-to-date. */
smp_rmb();
if (nladdr->nl_pid != nlk->portid)
return -EINVAL;
}
if (nlk->netlink_bind && groups) {
int group;
/* nl_groups is a u32, so cap the maximum groups we can bind */
for (group = 0; group < BITS_PER_TYPE(u32); group++) {
if (!test_bit(group, &groups))
continue;
err = nlk->netlink_bind(net, group + 1);
if (!err)
continue;
netlink_undo_bind(group, groups, sk);
return err;
}
}
/* No need for barriers here as we return to user-space without
* using any of the bound attributes.
*/
netlink_lock_table();
if (!bound) {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
netlink_autobind(sock);
if (err) {
netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk);
goto unlock;
}
}
if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
goto unlock;
netlink_unlock_table();
netlink_table_grab();
netlink_update_subscriptions(sk, nlk->subscriptions +
hweight32(groups) -
hweight32(nlk->groups[0]));
nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups;
netlink_update_listeners(sk);
netlink_table_ungrab();
return 0;
unlock:
netlink_unlock_table();
return err;
}
static int netlink_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
int err = 0;
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
if (alen < sizeof(addr->sa_family))
return -EINVAL;
if (addr->sa_family == AF_UNSPEC) {
/* paired with READ_ONCE() in netlink_getsockbyportid() */
WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED);
/* dst_portid and dst_group can be read locklessly */
WRITE_ONCE(nlk->dst_portid, 0);
WRITE_ONCE(nlk->dst_group, 0);
return 0;
}
if (addr->sa_family != AF_NETLINK)
return -EINVAL;
if (alen < sizeof(struct sockaddr_nl))
return -EINVAL;
if ((nladdr->nl_groups || nladdr->nl_pid) &&
!netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
/* No need for barriers here as we return to user-space without
* using any of the bound attributes.
* Paired with WRITE_ONCE() in netlink_insert().
*/
if (!READ_ONCE(nlk->bound))
err = netlink_autobind(sock);
if (err == 0) {
/* paired with READ_ONCE() in netlink_getsockbyportid() */
WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED);
/* dst_portid and dst_group can be read locklessly */
WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid);
WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups));
}
return err;
}
static int netlink_getname(struct socket *sock, struct sockaddr *addr,
int peer)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr);
nladdr->nl_family = AF_NETLINK;
nladdr->nl_pad = 0;
if (peer) {
/* Paired with WRITE_ONCE() in netlink_connect() */
nladdr->nl_pid = READ_ONCE(nlk->dst_portid);
nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group));
} else {
/* Paired with WRITE_ONCE() in netlink_insert() */
nladdr->nl_pid = READ_ONCE(nlk->portid);
netlink_lock_table();
nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
netlink_unlock_table();
}
return sizeof(*nladdr);
}
static int netlink_ioctl(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
/* try to hand this ioctl down to the NIC drivers.
*/
return -ENOIOCTLCMD;
}
static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)
{
struct sock *sock;
struct netlink_sock *nlk;
sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid);
if (!sock)
return ERR_PTR(-ECONNREFUSED);
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
/* dst_portid and sk_state can be changed in netlink_connect() */
if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED &&
READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
return sock;
}
struct sock *netlink_getsockbyfilp(struct file *filp)
{
struct inode *inode = file_inode(filp);
struct sock *sock;
if (!S_ISSOCK(inode->i_mode))
return ERR_PTR(-ENOTSOCK);
sock = SOCKET_I(inode)->sk;
if (sock->sk_family != AF_NETLINK)
return ERR_PTR(-EINVAL);
sock_hold(sock);
return sock;
}
static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
int broadcast)
{
struct sk_buff *skb;
void *data;
if (size <= NLMSG_GOODSIZE || broadcast)
return alloc_skb(size, GFP_KERNEL);
size = SKB_DATA_ALIGN(size) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
data = vmalloc(size);
if (data == NULL)
return NULL;
skb = __build_skb(data, size);
if (skb == NULL)
vfree(data);
else
skb->destructor = netlink_skb_destructor;
return skb;
}
/*
* Attach a skb to a netlink socket.
* The caller must hold a reference to the destination socket. On error, the
* reference is dropped. The skb is not send to the destination, just all
* all error checks are performed and memory in the queue is reserved.
* Return values:
* < 0: error. skb freed, reference to sock dropped.
* 0: continue
* 1: repeat lookup - reference dropped while waiting for socket memory.
*/
int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
long *timeo, struct sock *ssk)
{
struct netlink_sock *nlk;
nlk = nlk_sk(sk);
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(NETLINK_S_CONGESTED, &nlk->state))) {
DECLARE_WAITQUEUE(wait, current);
if (!*timeo) {
if (!ssk || netlink_is_kernel(ssk))
netlink_overrun(sk);
sock_put(sk);
kfree_skb(skb);
return -EAGAIN;
}
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&nlk->wait, &wait);
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
!sock_flag(sk, SOCK_DEAD))
*timeo = schedule_timeout(*timeo);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nlk->wait, &wait);
sock_put(sk);
if (signal_pending(current)) {
kfree_skb(skb);
return sock_intr_errno(*timeo);
}
return 1;
}
netlink_skb_set_owner_r(skb, sk);
return 0;
}
static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = skb->len;
netlink_deliver_tap(sock_net(sk), skb);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk);
return len;
}
int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = __netlink_sendskb(sk, skb);
sock_put(sk);
return len;
}
void netlink_detachskb(struct sock *sk, struct sk_buff *skb)
{
kfree_skb(skb);
sock_put(sk);
}
static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
{
int delta;
WARN_ON(skb->sk != NULL);
delta = skb->end - skb->tail;
if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize)
return skb;
if (skb_shared(skb)) {
struct sk_buff *nskb = skb_clone(skb, allocation);
if (!nskb)
return skb;
consume_skb(skb);
skb = nskb;
}
pskb_expand_head(skb, 0, -delta,
(allocation & ~__GFP_DIRECT_RECLAIM) |
__GFP_NOWARN | __GFP_NORETRY);
return skb;
}
static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
struct sock *ssk)
{
int ret;
struct netlink_sock *nlk = nlk_sk(sk);
ret = -ECONNREFUSED;
if (nlk->netlink_rcv != NULL) {
ret = skb->len;
netlink_skb_set_owner_r(skb, sk);
NETLINK_CB(skb).sk = ssk;
netlink_deliver_tap_kernel(sk, ssk, skb);
nlk->netlink_rcv(skb);
consume_skb(skb);
} else {
kfree_skb(skb);
}
sock_put(sk);
return ret;
}
int netlink_unicast(struct sock *ssk, struct sk_buff *skb,
u32 portid, int nonblock)
{
struct sock *sk;
int err;
long timeo;
skb = netlink_trim(skb, gfp_any());
timeo = sock_sndtimeo(ssk, nonblock);
retry:
sk = netlink_getsockbyportid(ssk, portid);
if (IS_ERR(sk)) {
kfree_skb(skb);
return PTR_ERR(sk);
}
if (netlink_is_kernel(sk))
return netlink_unicast_kernel(sk, skb, ssk);
if (sk_filter(sk, skb)) {
err = skb->len;
kfree_skb(skb);
sock_put(sk);
return err;
}
err = netlink_attachskb(sk, skb, &timeo, ssk);
if (err == 1)
goto retry;
if (err)
return err;
return netlink_sendskb(sk, skb);
}
EXPORT_SYMBOL(netlink_unicast);
int netlink_has_listeners(struct sock *sk, unsigned int group)
{
int res = 0;
struct listeners *listeners;
BUG_ON(!netlink_is_kernel(sk));
rcu_read_lock();
listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);
if (listeners && group - 1 < nl_table[sk->sk_protocol].groups)
res = test_bit(group - 1, listeners->masks);
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL_GPL(netlink_has_listeners);
bool netlink_strict_get_check(struct sk_buff *skb)
{
return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk);
}
EXPORT_SYMBOL_GPL(netlink_strict_get_check);
static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
!test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
netlink_skb_set_owner_r(skb, sk);
__netlink_sendskb(sk, skb);
return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
}
return -1;
}
struct netlink_broadcast_data {
struct sock *exclude_sk;
struct net *net;
u32 portid;
u32 group;
int failure;
int delivery_failure;
int congested;
int delivered;
gfp_t allocation;
struct sk_buff *skb, *skb2;
int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data);
void *tx_data;
};
static void do_one_broadcast(struct sock *sk,
struct netlink_broadcast_data *p)
{
struct netlink_sock *nlk = nlk_sk(sk);
int val;
if (p->exclude_sk == sk)
return;
if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups ||
!test_bit(p->group - 1, nlk->groups))
return;
if (!net_eq(sock_net(sk), p->net)) {
if (!nlk_test_bit(LISTEN_ALL_NSID, sk))
return;
if (!peernet_has_id(sock_net(sk), p->net))
return;
if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns,
CAP_NET_BROADCAST))
return;
}
if (p->failure) {
netlink_overrun(sk);
return;
}
sock_hold(sk);
if (p->skb2 == NULL) {
if (skb_shared(p->skb)) {
p->skb2 = skb_clone(p->skb, p->allocation);
} else {
p->skb2 = skb_get(p->skb);
/*
* skb ownership may have been set when
* delivered to a previous socket.
*/
skb_orphan(p->skb2);
}
}
if (p->skb2 == NULL) {
netlink_overrun(sk);
/* Clone failed. Notify ALL listeners. */
p->failure = 1;
if (nlk_test_bit(BROADCAST_SEND_ERROR, sk))
p->delivery_failure = 1;
goto out;
}
if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) {
kfree_skb(p->skb2);
p->skb2 = NULL;
goto out;
}
if (sk_filter(sk, p->skb2)) {
kfree_skb(p->skb2);
p->skb2 = NULL;
goto out;
}
NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net);
if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED)
NETLINK_CB(p->skb2).nsid_is_set = true;
val = netlink_broadcast_deliver(sk, p->skb2);
if (val < 0) {
netlink_overrun(sk);
if (nlk_test_bit(BROADCAST_SEND_ERROR, sk))
p->delivery_failure = 1;
} else {
p->congested |= val;
p->delivered = 1;
p->skb2 = NULL;
}
out:
sock_put(sk);
}
int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
u32 portid,
u32 group, gfp_t allocation,
int (*filter)(struct sock *dsk,
struct sk_buff *skb, void *data),
void *filter_data)
{
struct net *net = sock_net(ssk);
struct netlink_broadcast_data info;
struct sock *sk;
skb = netlink_trim(skb, allocation);
info.exclude_sk = ssk;
info.net = net;
info.portid = portid;
info.group = group;
info.failure = 0;
info.delivery_failure = 0;
info.congested = 0;
info.delivered = 0;
info.allocation = allocation;
info.skb = skb;
info.skb2 = NULL;
info.tx_filter = filter;
info.tx_data = filter_data;
/* While we sleep in clone, do not allow to change socket list */
netlink_lock_table();
sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list)
do_one_broadcast(sk, &info);
consume_skb(skb);
netlink_unlock_table();
if (info.delivery_failure) {
kfree_skb(info.skb2);
return -ENOBUFS;
}
consume_skb(info.skb2);
if (info.delivered) {
if (info.congested && gfpflags_allow_blocking(allocation))
yield();
return 0;
}
return -ESRCH;
}
EXPORT_SYMBOL(netlink_broadcast_filtered);
int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid,
u32 group, gfp_t allocation)
{
return netlink_broadcast_filtered(ssk, skb, portid, group, allocation,
NULL, NULL);
}
EXPORT_SYMBOL(netlink_broadcast);
struct netlink_set_err_data {
struct sock *exclude_sk;
u32 portid;
u32 group;
int code;
};
static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p)
{
struct netlink_sock *nlk = nlk_sk(sk);
int ret = 0;
if (sk == p->exclude_sk)
goto out;
if (!net_eq(sock_net(sk), sock_net(p->exclude_sk)))
goto out;
if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups ||
!test_bit(p->group - 1, nlk->groups))
goto out;
if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) {
ret = 1;
goto out;
}
WRITE_ONCE(sk->sk_err, p->code);
sk_error_report(sk);
out:
return ret;
}
/**
* netlink_set_err - report error to broadcast listeners
* @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
* @portid: the PORTID of a process that we want to skip (if any)
* @group: the broadcast group that will notice the error
* @code: error code, must be negative (as usual in kernelspace)
*
* This function returns the number of broadcast listeners that have set the
* NETLINK_NO_ENOBUFS socket option.
*/
int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
{
struct netlink_set_err_data info;
unsigned long flags;
struct sock *sk;
int ret = 0;
info.exclude_sk = ssk;
info.portid = portid;
info.group = group;
/* sk->sk_err wants a positive error value */
info.code = -code;
read_lock_irqsave(&nl_table_lock, flags);
sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list)
ret += do_one_set_err(sk, &info);
read_unlock_irqrestore(&nl_table_lock, flags);
return ret;
}
EXPORT_SYMBOL(netlink_set_err);
/* must be called with netlink table grabbed */
static void netlink_update_socket_mc(struct netlink_sock *nlk,
unsigned int group,
int is_new)
{
int old, new = !!is_new, subscriptions;
old = test_bit(group - 1, nlk->groups);
subscriptions = nlk->subscriptions - old + new;
__assign_bit(group - 1, nlk->groups, new);
netlink_update_subscriptions(&nlk->sk, subscriptions);
netlink_update_listeners(&nlk->sk);
}
static int netlink_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
unsigned int val = 0;
int nr = -1;
if (level != SOL_NETLINK)
return -ENOPROTOOPT;
if (optlen >= sizeof(int) &&
copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
switch (optname) {
case NETLINK_PKTINFO:
nr = NETLINK_F_RECV_PKTINFO;
break;
case NETLINK_ADD_MEMBERSHIP:
case NETLINK_DROP_MEMBERSHIP: {
int err;
if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
return err;
if (!val || val - 1 >= nlk->ngroups)
return -EINVAL;
if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
err = nlk->netlink_bind(sock_net(sk), val);
if (err)
return err;
}
netlink_table_grab();
netlink_update_socket_mc(nlk, val,
optname == NETLINK_ADD_MEMBERSHIP);
netlink_table_ungrab();
if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
nlk->netlink_unbind(sock_net(sk), val);
break;
}
case NETLINK_BROADCAST_ERROR:
nr = NETLINK_F_BROADCAST_SEND_ERROR;
break;
case NETLINK_NO_ENOBUFS:
assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val);
if (val) {
clear_bit(NETLINK_S_CONGESTED, &nlk->state);
wake_up_interruptible(&nlk->wait);
}
break;
case NETLINK_LISTEN_ALL_NSID:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST))
return -EPERM;
nr = NETLINK_F_LISTEN_ALL_NSID;
break;
case NETLINK_CAP_ACK:
nr = NETLINK_F_CAP_ACK;
break;
case NETLINK_EXT_ACK:
nr = NETLINK_F_EXT_ACK;
break;
case NETLINK_GET_STRICT_CHK:
nr = NETLINK_F_STRICT_CHK;
break;
default:
return -ENOPROTOOPT;
}
if (nr >= 0)
assign_bit(nr, &nlk->flags, val);
return 0;
}
static int netlink_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
unsigned int flag;
int len, val;
if (level != SOL_NETLINK)
return -ENOPROTOOPT;
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
switch (optname) {
case NETLINK_PKTINFO:
flag = NETLINK_F_RECV_PKTINFO;
break;
case NETLINK_BROADCAST_ERROR:
flag = NETLINK_F_BROADCAST_SEND_ERROR;
break;
case NETLINK_NO_ENOBUFS:
flag = NETLINK_F_RECV_NO_ENOBUFS;
break;
case NETLINK_LIST_MEMBERSHIPS: {
int pos, idx, shift, err = 0;
netlink_lock_table();
for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) {
if (len - pos < sizeof(u32))
break;
idx = pos / sizeof(unsigned long);
shift = (pos % sizeof(unsigned long)) * 8;
if (put_user((u32)(nlk->groups[idx] >> shift),
(u32 __user *)(optval + pos))) {
err = -EFAULT;
break;
}
}
if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen))
err = -EFAULT;
netlink_unlock_table();
return err;
}
case NETLINK_CAP_ACK:
flag = NETLINK_F_CAP_ACK;
break;
case NETLINK_EXT_ACK:
flag = NETLINK_F_EXT_ACK;
break;
case NETLINK_GET_STRICT_CHK:
flag = NETLINK_F_STRICT_CHK;
break;
default:
return -ENOPROTOOPT;
}
if (len < sizeof(int))
return -EINVAL;
len = sizeof(int);
val = test_bit(flag, &nlk->flags);
if (put_user(len, optlen) ||
copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
struct nl_pktinfo info;
info.group = NETLINK_CB(skb).dst_group;
put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
}
static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg,
struct sk_buff *skb)
{
if (!NETLINK_CB(skb).nsid_is_set)
return;
put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int),
&NETLINK_CB(skb).nsid);
}
static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
u32 dst_portid;
u32 dst_group;
struct sk_buff *skb;
int err;
struct scm_cookie scm;
u32 netlink_skb_flags = 0;
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
if (len == 0) {
pr_warn_once("Zero length message leads to an empty skb\n");
return -ENODATA;
}
err = scm_send(sock, msg, &scm, true);
if (err < 0)
return err;
if (msg->msg_namelen) {
err = -EINVAL;
if (msg->msg_namelen < sizeof(struct sockaddr_nl))
goto out;
if (addr->nl_family != AF_NETLINK)
goto out;
dst_portid = addr->nl_pid;
dst_group = ffs(addr->nl_groups);
err = -EPERM;
if ((dst_group || dst_portid) &&
!netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
goto out;
netlink_skb_flags |= NETLINK_SKB_DST;
} else {
/* Paired with WRITE_ONCE() in netlink_connect() */
dst_portid = READ_ONCE(nlk->dst_portid);
dst_group = READ_ONCE(nlk->dst_group);
}
/* Paired with WRITE_ONCE() in netlink_insert() */
if (!READ_ONCE(nlk->bound)) {
err = netlink_autobind(sock);
if (err)
goto out;
} else {
/* Ensure nlk is hashed and visible. */
smp_rmb();
}
err = -EMSGSIZE;
if (len > sk->sk_sndbuf - 32)
goto out;
err = -ENOBUFS;
skb = netlink_alloc_large_skb(len, dst_group);
if (skb == NULL)
goto out;
NETLINK_CB(skb).portid = nlk->portid;
NETLINK_CB(skb).dst_group = dst_group;
NETLINK_CB(skb).creds = scm.creds;
NETLINK_CB(skb).flags = netlink_skb_flags;
err = -EFAULT;
if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
kfree_skb(skb);
goto out;
}
err = security_netlink_send(sk, skb);
if (err) {
kfree_skb(skb);
goto out;
}
if (dst_group) {
refcount_inc(&skb->users);
netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL);
}
err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT);
out:
scm_destroy(&scm);
return err;
}
static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags)
{
struct scm_cookie scm;
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
size_t copied, max_recvmsg_len;
struct sk_buff *skb, *data_skb;
int err, ret;
if (flags & MSG_OOB)
return -EOPNOTSUPP;
copied = 0;
skb = skb_recv_datagram(sk, flags, &err);
if (skb == NULL)
goto out;
data_skb = skb;
#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
if (unlikely(skb_shinfo(skb)->frag_list)) {
/*
* If this skb has a frag_list, then here that means that we
* will have to use the frag_list skb's data for compat tasks
* and the regular skb's data for normal (non-compat) tasks.
*
* If we need to send the compat skb, assign it to the
* 'data_skb' variable so that it will be used below for data
* copying. We keep 'skb' for everything else, including
* freeing both later.
*/
if (flags & MSG_CMSG_COMPAT)
data_skb = skb_shinfo(skb)->frag_list;
}
#endif
/* Record the max length of recvmsg() calls for future allocations */
max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len);
max_recvmsg_len = min_t(size_t, max_recvmsg_len,
SKB_WITH_OVERHEAD(32768));
WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len);
copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(data_skb, 0, msg, copied);
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
addr->nl_family = AF_NETLINK;
addr->nl_pad = 0;
addr->nl_pid = NETLINK_CB(skb).portid;
addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group);
msg->msg_namelen = sizeof(*addr);
}
if (nlk_test_bit(RECV_PKTINFO, sk))
netlink_cmsg_recv_pktinfo(msg, skb);
if (nlk_test_bit(LISTEN_ALL_NSID, sk))
netlink_cmsg_listen_all_nsid(sk, msg, skb);
memset(&scm, 0, sizeof(scm));
scm.creds = *NETLINK_CREDS(skb);
if (flags & MSG_TRUNC)
copied = data_skb->len;
skb_free_datagram(sk, skb);
if (READ_ONCE(nlk->cb_running) &&
atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
ret = netlink_dump(sk);
if (ret) {
WRITE_ONCE(sk->sk_err, -ret);
sk_error_report(sk);
}
}
scm_recv(sock, msg, &scm, flags);
out:
netlink_rcv_wake(sk);
return err ? : copied;
}
static void netlink_data_ready(struct sock *sk)
{
BUG();
}
/*
* We export these functions to other modules. They provide a
* complete set of kernel non-blocking support for message
* queueing.
*/
struct sock *
__netlink_kernel_create(struct net *net, int unit, struct module *module,
struct netlink_kernel_cfg *cfg)
{
struct socket *sock;
struct sock *sk;
struct netlink_sock *nlk;
struct listeners *listeners = NULL;
struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL;
unsigned int groups;
BUG_ON(!nl_table);
if (unit < 0 || unit >= MAX_LINKS)
return NULL;
if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
return NULL;
if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0)
goto out_sock_release_nosk;
sk = sock->sk;
if (!cfg || cfg->groups < 32)
groups = 32;
else
groups = cfg->groups;
listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL);
if (!listeners)
goto out_sock_release;
sk->sk_data_ready = netlink_data_ready;
if (cfg && cfg->input)
nlk_sk(sk)->netlink_rcv = cfg->input;
if (netlink_insert(sk, 0))
goto out_sock_release;
nlk = nlk_sk(sk);
set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags);
netlink_table_grab();
if (!nl_table[unit].registered) {
nl_table[unit].groups = groups;
rcu_assign_pointer(nl_table[unit].listeners, listeners);
nl_table[unit].cb_mutex = cb_mutex;
nl_table[unit].module = module;
if (cfg) {
nl_table[unit].bind = cfg->bind;
nl_table[unit].unbind = cfg->unbind;
nl_table[unit].release = cfg->release;
nl_table[unit].flags = cfg->flags;
}
nl_table[unit].registered = 1;
} else {
kfree(listeners);
nl_table[unit].registered++;
}
netlink_table_ungrab();
return sk;
out_sock_release:
kfree(listeners);
netlink_kernel_release(sk);
return NULL;
out_sock_release_nosk:
sock_release(sock);
return NULL;
}
EXPORT_SYMBOL(__netlink_kernel_create);
void
netlink_kernel_release(struct sock *sk)
{
if (sk == NULL || sk->sk_socket == NULL)
return;
sock_release(sk->sk_socket);
}
EXPORT_SYMBOL(netlink_kernel_release);
int __netlink_change_ngroups(struct sock *sk, unsigned int groups)
{
struct listeners *new, *old;
struct netlink_table *tbl = &nl_table[sk->sk_protocol];
if (groups < 32)
groups = 32;
if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) {
new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC);
if (!new)
return -ENOMEM;
old = nl_deref_protected(tbl->listeners);
memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups));
rcu_assign_pointer(tbl->listeners, new);
kfree_rcu(old, rcu);
}
tbl->groups = groups;
return 0;
}
/**
* netlink_change_ngroups - change number of multicast groups
*
* This changes the number of multicast groups that are available
* on a certain netlink family. Note that it is not possible to
* change the number of groups to below 32. Also note that it does
* not implicitly call netlink_clear_multicast_users() when the
* number of groups is reduced.
*
* @sk: The kernel netlink socket, as returned by netlink_kernel_create().
* @groups: The new number of groups.
*/
int netlink_change_ngroups(struct sock *sk, unsigned int groups)
{
int err;
netlink_table_grab();
err = __netlink_change_ngroups(sk, groups);
netlink_table_ungrab();
return err;
}
void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
{
struct sock *sk;
struct netlink_table *tbl = &nl_table[ksk->sk_protocol];
sk_for_each_bound(sk, &tbl->mc_list)
netlink_update_socket_mc(nlk_sk(sk), group, 0);
}
struct nlmsghdr *
__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags)
{
struct nlmsghdr *nlh;
int size = nlmsg_msg_size(len);
nlh = skb_put(skb, NLMSG_ALIGN(size));
nlh->nlmsg_type = type;
nlh->nlmsg_len = size;
nlh->nlmsg_flags = flags;
nlh->nlmsg_pid = portid;
nlh->nlmsg_seq = seq;
if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0)
memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size);
return nlh;
}
EXPORT_SYMBOL(__nlmsg_put);
/*
* It looks a bit ugly.
* It would be better to create kernel thread.
*/
static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb,
struct netlink_callback *cb,
struct netlink_ext_ack *extack)
{
struct nlmsghdr *nlh;
nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno),
NLM_F_MULTI | cb->answer_flags);
if (WARN_ON(!nlh))
return -ENOBUFS;
nl_dump_check_consistent(cb, nlh);
memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno));
if (extack->_msg && test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) {
nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg))
nlmsg_end(skb, nlh);
}
return 0;
}
static int netlink_dump(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
struct netlink_ext_ack extack = {};
struct netlink_callback *cb;
struct sk_buff *skb = NULL;
size_t max_recvmsg_len;
struct module *module;
int err = -ENOBUFS;
int alloc_min_size;
int alloc_size;
mutex_lock(nlk->cb_mutex);
if (!nlk->cb_running) {
err = -EINVAL;
goto errout_skb;
}
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
goto errout_skb;
/* NLMSG_GOODSIZE is small to avoid high order allocations being
* required, but it makes sense to _attempt_ a 16K bytes allocation
* to reduce number of system calls on dump operations, if user
* ever provided a big enough buffer.
*/
cb = &nlk->cb;
alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len);
if (alloc_min_size < max_recvmsg_len) {
alloc_size = max_recvmsg_len;
skb = alloc_skb(alloc_size,
(GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) |
__GFP_NOWARN | __GFP_NORETRY);
}
if (!skb) {
alloc_size = alloc_min_size;
skb = alloc_skb(alloc_size, GFP_KERNEL);
}
if (!skb)
goto errout_skb;
/* Trim skb to allocated size. User is expected to provide buffer as
* large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at
* netlink_recvmsg())). dump will pack as many smaller messages as
* could fit within the allocated skb. skb is typically allocated
* with larger space than required (could be as much as near 2x the
* requested size with align to next power of 2 approach). Allowing
* dump to use the excess space makes it difficult for a user to have a
* reasonable static buffer based on the expected largest dump of a
* single netdev. The outcome is MSG_TRUNC error.
*/
skb_reserve(skb, skb_tailroom(skb) - alloc_size);
/* Make sure malicious BPF programs can not read unitialized memory
* from skb->head -> skb->data
*/
skb_reset_network_header(skb);
skb_reset_mac_header(skb);
netlink_skb_set_owner_r(skb, sk);
if (nlk->dump_done_errno > 0) {
cb->extack = &extack;
nlk->dump_done_errno = cb->dump(skb, cb);
cb->extack = NULL;
}
if (nlk->dump_done_errno > 0 ||
skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
mutex_unlock(nlk->cb_mutex);
if (sk_filter(sk, skb))
kfree_skb(skb);
else
__netlink_sendskb(sk, skb);
return 0;
}
if (netlink_dump_done(nlk, skb, cb, &extack))
goto errout_skb;
#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
/* frag_list skb's data is used for compat tasks
* and the regular skb's data for normal (non-compat) tasks.
* See netlink_recvmsg().
*/
if (unlikely(skb_shinfo(skb)->frag_list)) {
if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack))
goto errout_skb;
}
#endif
if (sk_filter(sk, skb))
kfree_skb(skb);
else
__netlink_sendskb(sk, skb);
if (cb->done)
cb->done(cb);
WRITE_ONCE(nlk->cb_running, false);
module = cb->module;
skb = cb->skb;
mutex_unlock(nlk->cb_mutex);
module_put(module);
consume_skb(skb);
return 0;
errout_skb:
mutex_unlock(nlk->cb_mutex);
kfree_skb(skb);
return err;
}
int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
const struct nlmsghdr *nlh,
struct netlink_dump_control *control)
{
struct netlink_callback *cb;
struct netlink_sock *nlk;
struct sock *sk;
int ret;
refcount_inc(&skb->users);
sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid);
if (sk == NULL) {
ret = -ECONNREFUSED;
goto error_free;
}
nlk = nlk_sk(sk);
mutex_lock(nlk->cb_mutex);
/* A dump is in progress... */
if (nlk->cb_running) {
ret = -EBUSY;
goto error_unlock;
}
/* add reference of module which cb->dump belongs to */
if (!try_module_get(control->module)) {
ret = -EPROTONOSUPPORT;
goto error_unlock;
}
cb = &nlk->cb;
memset(cb, 0, sizeof(*cb));
cb->dump = control->dump;
cb->done = control->done;
cb->nlh = nlh;
cb->data = control->data;
cb->module = control->module;
cb->min_dump_alloc = control->min_dump_alloc;
cb->skb = skb;
cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk);
if (control->start) {
cb->extack = control->extack;
ret = control->start(cb);
cb->extack = NULL;
if (ret)
goto error_put;
}
WRITE_ONCE(nlk->cb_running, true);
nlk->dump_done_errno = INT_MAX;
mutex_unlock(nlk->cb_mutex);
ret = netlink_dump(sk);
sock_put(sk);
if (ret)
return ret;
/* We successfully started a dump, by returning -EINTR we
* signal not to send ACK even if it was requested.
*/
return -EINTR;
error_put:
module_put(control->module);
error_unlock:
sock_put(sk);
mutex_unlock(nlk->cb_mutex);
error_free:
kfree_skb(skb);
return ret;
}
EXPORT_SYMBOL(__netlink_dump_start);
static size_t
netlink_ack_tlv_len(struct netlink_sock *nlk, int err,
const struct netlink_ext_ack *extack)
{
size_t tlvlen;
if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags))
return 0;
tlvlen = 0;
if (extack->_msg)
tlvlen += nla_total_size(strlen(extack->_msg) + 1);
if (extack->cookie_len)
tlvlen += nla_total_size(extack->cookie_len);
/* Following attributes are only reported as error (not warning) */
if (!err)
return tlvlen;
if (extack->bad_attr)
tlvlen += nla_total_size(sizeof(u32));
if (extack->policy)
tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy);
if (extack->miss_type)
tlvlen += nla_total_size(sizeof(u32));
if (extack->miss_nest)
tlvlen += nla_total_size(sizeof(u32));
return tlvlen;
}
static void
netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb,
struct nlmsghdr *nlh, int err,
const struct netlink_ext_ack *extack)
{
if (extack->_msg)
WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg));
if (extack->cookie_len)
WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
extack->cookie_len, extack->cookie));
if (!err)
return;
if (extack->bad_attr &&
!WARN_ON((u8 *)extack->bad_attr < in_skb->data ||
(u8 *)extack->bad_attr >= in_skb->data + in_skb->len))
WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS,
(u8 *)extack->bad_attr - (u8 *)nlh));
if (extack->policy)
netlink_policy_dump_write_attr(skb, extack->policy,
NLMSGERR_ATTR_POLICY);
if (extack->miss_type)
WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE,
extack->miss_type));
if (extack->miss_nest &&
!WARN_ON((u8 *)extack->miss_nest < in_skb->data ||
(u8 *)extack->miss_nest > in_skb->data + in_skb->len))
WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST,
(u8 *)extack->miss_nest - (u8 *)nlh));
}
void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
const struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
struct nlmsghdr *rep;
struct nlmsgerr *errmsg;
size_t payload = sizeof(*errmsg);
struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk);
unsigned int flags = 0;
size_t tlvlen;
/* Error messages get the original request appened, unless the user
* requests to cap the error message, and get extra error data if
* requested.
*/
if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags))
payload += nlmsg_len(nlh);
else
flags |= NLM_F_CAPPED;
tlvlen = netlink_ack_tlv_len(nlk, err, extack);
if (tlvlen)
flags |= NLM_F_ACK_TLVS;
skb = nlmsg_new(payload + tlvlen, GFP_KERNEL);
if (!skb)
goto err_skb;
rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
NLMSG_ERROR, sizeof(*errmsg), flags);
if (!rep)
goto err_bad_put;
errmsg = nlmsg_data(rep);
errmsg->error = err;
errmsg->msg = *nlh;
if (!(flags & NLM_F_CAPPED)) {
if (!nlmsg_append(skb, nlmsg_len(nlh)))
goto err_bad_put;
memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh),
nlmsg_len(nlh));
}
if (tlvlen)
netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack);
nlmsg_end(skb, rep);
nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid);
return;
err_bad_put:
nlmsg_free(skb);
err_skb:
WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS);
sk_error_report(NETLINK_CB(in_skb).sk);
}
EXPORT_SYMBOL(netlink_ack);
int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
struct nlmsghdr *,
struct netlink_ext_ack *))
{
struct netlink_ext_ack extack;
struct nlmsghdr *nlh;
int err;
while (skb->len >= nlmsg_total_size(0)) {
int msglen;
memset(&extack, 0, sizeof(extack));
nlh = nlmsg_hdr(skb);
err = 0;
if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
return 0;
/* Only requests are handled by the kernel */
if (!(nlh->nlmsg_flags & NLM_F_REQUEST))
goto ack;
/* Skip control messages */
if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
goto ack;
err = cb(skb, nlh, &extack);
if (err == -EINTR)
goto skip;
ack:
if (nlh->nlmsg_flags & NLM_F_ACK || err)
netlink_ack(skb, nlh, err, &extack);
skip:
msglen = NLMSG_ALIGN(nlh->nlmsg_len);
if (msglen > skb->len)
msglen = skb->len;
skb_pull(skb, msglen);
}
return 0;
}
EXPORT_SYMBOL(netlink_rcv_skb);
/**
* nlmsg_notify - send a notification netlink message
* @sk: netlink socket to use
* @skb: notification message
* @portid: destination netlink portid for reports or 0
* @group: destination multicast group or 0
* @report: 1 to report back, 0 to disable
* @flags: allocation flags
*/
int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
unsigned int group, int report, gfp_t flags)
{
int err = 0;
if (group) {
int exclude_portid = 0;
if (report) {
refcount_inc(&skb->users);
exclude_portid = portid;
}
/* errors reported via destination sk->sk_err, but propagate
* delivery errors if NETLINK_BROADCAST_ERROR flag is set */
err = nlmsg_multicast(sk, skb, exclude_portid, group, flags);
if (err == -ESRCH)
err = 0;
}
if (report) {
int err2;
err2 = nlmsg_unicast(sk, skb, portid);
if (!err)
err = err2;
}
return err;
}
EXPORT_SYMBOL(nlmsg_notify);
#ifdef CONFIG_PROC_FS
struct nl_seq_iter {
struct seq_net_private p;
struct rhashtable_iter hti;
int link;
};
static void netlink_walk_start(struct nl_seq_iter *iter)
{
rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti);
rhashtable_walk_start(&iter->hti);
}
static void netlink_walk_stop(struct nl_seq_iter *iter)
{
rhashtable_walk_stop(&iter->hti);
rhashtable_walk_exit(&iter->hti);
}
static void *__netlink_seq_next(struct seq_file *seq)
{
struct nl_seq_iter *iter = seq->private;
struct netlink_sock *nlk;
do {
for (;;) {
nlk = rhashtable_walk_next(&iter->hti);
if (IS_ERR(nlk)) {
if (PTR_ERR(nlk) == -EAGAIN)
continue;
return nlk;
}
if (nlk)
break;
netlink_walk_stop(iter);
if (++iter->link >= MAX_LINKS)
return NULL;
netlink_walk_start(iter);
}
} while (sock_net(&nlk->sk) != seq_file_net(seq));
return nlk;
}
static void *netlink_seq_start(struct seq_file *seq, loff_t *posp)
__acquires(RCU)
{
struct nl_seq_iter *iter = seq->private;
void *obj = SEQ_START_TOKEN;
loff_t pos;
iter->link = 0;
netlink_walk_start(iter);
for (pos = *posp; pos && obj && !IS_ERR(obj); pos--)
obj = __netlink_seq_next(seq);
return obj;
}
static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return __netlink_seq_next(seq);
}
static void netlink_native_seq_stop(struct seq_file *seq, void *v)
{
struct nl_seq_iter *iter = seq->private;
if (iter->link >= MAX_LINKS)
return;
netlink_walk_stop(iter);
}
static int netlink_native_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
"sk Eth Pid Groups "
"Rmem Wmem Dump Locks Drops Inode\n");
} else {
struct sock *s = v;
struct netlink_sock *nlk = nlk_sk(s);
seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8lu\n",
s,
s->sk_protocol,
nlk->portid,
nlk->groups ? (u32)nlk->groups[0] : 0,
sk_rmem_alloc_get(s),
sk_wmem_alloc_get(s),
READ_ONCE(nlk->cb_running),
refcount_read(&s->sk_refcnt),
atomic_read(&s->sk_drops),
sock_i_ino(s)
);
}
return 0;
}
#ifdef CONFIG_BPF_SYSCALL
struct bpf_iter__netlink {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct netlink_sock *, sk);
};
DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk)
static int netlink_prog_seq_show(struct bpf_prog *prog,
struct bpf_iter_meta *meta,
void *v)
{
struct bpf_iter__netlink ctx;
meta->seq_num--; /* skip SEQ_START_TOKEN */
ctx.meta = meta;
ctx.sk = nlk_sk((struct sock *)v);
return bpf_iter_run_prog(prog, &ctx);
}
static int netlink_seq_show(struct seq_file *seq, void *v)
{
struct bpf_iter_meta meta;
struct bpf_prog *prog;
meta.seq = seq;
prog = bpf_iter_get_info(&meta, false);
if (!prog)
return netlink_native_seq_show(seq, v);
if (v != SEQ_START_TOKEN)
return netlink_prog_seq_show(prog, &meta, v);
return 0;
}
static void netlink_seq_stop(struct seq_file *seq, void *v)
{
struct bpf_iter_meta meta;
struct bpf_prog *prog;
if (!v) {
meta.seq = seq;
prog = bpf_iter_get_info(&meta, true);
if (prog)
(void)netlink_prog_seq_show(prog, &meta, v);
}
netlink_native_seq_stop(seq, v);
}
#else
static int netlink_seq_show(struct seq_file *seq, void *v)
{
return netlink_native_seq_show(seq, v);
}
static void netlink_seq_stop(struct seq_file *seq, void *v)
{
netlink_native_seq_stop(seq, v);
}
#endif
static const struct seq_operations netlink_seq_ops = {
.start = netlink_seq_start,
.next = netlink_seq_next,
.stop = netlink_seq_stop,
.show = netlink_seq_show,
};
#endif
int netlink_register_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&netlink_chain, nb);
}
EXPORT_SYMBOL(netlink_register_notifier);
int netlink_unregister_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&netlink_chain, nb);
}
EXPORT_SYMBOL(netlink_unregister_notifier);
static const struct proto_ops netlink_ops = {
.family = PF_NETLINK,
.owner = THIS_MODULE,
.release = netlink_release,
.bind = netlink_bind,
.connect = netlink_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
.poll = datagram_poll,
.ioctl = netlink_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = netlink_setsockopt,
.getsockopt = netlink_getsockopt,
.sendmsg = netlink_sendmsg,
.recvmsg = netlink_recvmsg,
.mmap = sock_no_mmap,
};
static const struct net_proto_family netlink_family_ops = {
.family = PF_NETLINK,
.create = netlink_create,
.owner = THIS_MODULE, /* for consistency 8) */
};
static int __net_init netlink_net_init(struct net *net)
{
#ifdef CONFIG_PROC_FS
if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops,
sizeof(struct nl_seq_iter)))
return -ENOMEM;
#endif
return 0;
}
static void __net_exit netlink_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
remove_proc_entry("netlink", net->proc_net);
#endif
}
static void __init netlink_add_usersock_entry(void)
{
struct listeners *listeners;
int groups = 32;
listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL);
if (!listeners)
panic("netlink_add_usersock_entry: Cannot allocate listeners\n");
netlink_table_grab();
nl_table[NETLINK_USERSOCK].groups = groups;
rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners);
nl_table[NETLINK_USERSOCK].module = THIS_MODULE;
nl_table[NETLINK_USERSOCK].registered = 1;
nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND;
netlink_table_ungrab();
}
static struct pernet_operations __net_initdata netlink_net_ops = {
.init = netlink_net_init,
.exit = netlink_net_exit,
};
static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
{
const struct netlink_sock *nlk = data;
struct netlink_compare_arg arg;
netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
}
static const struct rhashtable_params netlink_rhashtable_params = {
.head_offset = offsetof(struct netlink_sock, node),
.key_len = netlink_compare_arg_len,
.obj_hashfn = netlink_hash,
.obj_cmpfn = netlink_compare,
.automatic_shrinking = true,
};
#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
BTF_ID_LIST(btf_netlink_sock_id)
BTF_ID(struct, netlink_sock)
static const struct bpf_iter_seq_info netlink_seq_info = {
.seq_ops = &netlink_seq_ops,
.init_seq_private = bpf_iter_init_seq_net,
.fini_seq_private = bpf_iter_fini_seq_net,
.seq_priv_size = sizeof(struct nl_seq_iter),
};
static struct bpf_iter_reg netlink_reg_info = {
.target = "netlink",
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__netlink, sk),
PTR_TO_BTF_ID_OR_NULL },
},
.seq_info = &netlink_seq_info,
};
static int __init bpf_iter_register(void)
{
netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id;
return bpf_iter_reg_target(&netlink_reg_info);
}
#endif
static int __init netlink_proto_init(void)
{
int i;
int err = proto_register(&netlink_proto, 0);
if (err != 0)
goto out;
#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
err = bpf_iter_register();
if (err)
goto out;
#endif
BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb));
nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL);
if (!nl_table)
goto panic;
for (i = 0; i < MAX_LINKS; i++) {
if (rhashtable_init(&nl_table[i].hash,
&netlink_rhashtable_params) < 0) {
while (--i > 0)
rhashtable_destroy(&nl_table[i].hash);
kfree(nl_table);
goto panic;
}
}
netlink_add_usersock_entry();
sock_register(&netlink_family_ops);
register_pernet_subsys(&netlink_net_ops);
register_pernet_subsys(&netlink_tap_net_ops);
/* The netlink device handler may be needed early. */
rtnetlink_init();
out:
return err;
panic:
panic("netlink_init: Cannot allocate nl_table\n");
}
core_initcall(netlink_proto_init);
Reference in New Issue View Git Blame Copy Permalink