openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity
linux/net/core/rtnetlink.c

4362 lines
105 KiB
C
Raw Blame History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Routing netlink socket interface: protocol independent part.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Fixes:
* Vitaly E. Lavrov RTA_OK arithmetics was wrong.
*/
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/if_addr.h>
#include <linux/if_bridge.h>
#include <linux/if_vlan.h>
#include <linux/pci.h>
#include <linux/etherdevice.h>
#include <linux/bpf.h>
#include <linux/uaccess.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <net/switchdev.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/fib_rules.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
struct rtnl_link {
rtnl_doit_func doit;
rtnl_dumpit_func dumpit;
unsigned int flags;
};
static DEFINE_MUTEX(rtnl_mutex);
void rtnl_lock(void)
{
mutex_lock(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_lock);
static struct sk_buff *defer_kfree_skb_list;
void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail)
{
if (head && tail) {
tail->next = defer_kfree_skb_list;
defer_kfree_skb_list = head;
}
}
EXPORT_SYMBOL(rtnl_kfree_skbs);
void __rtnl_unlock(void)
{
struct sk_buff *head = defer_kfree_skb_list;
defer_kfree_skb_list = NULL;
mutex_unlock(&rtnl_mutex);
while (head) {
struct sk_buff *next = head->next;
kfree_skb(head);
cond_resched();
head = next;
}
}
void rtnl_unlock(void)
{
/* This fellow will unlock it for us. */
netdev_run_todo();
}
EXPORT_SYMBOL(rtnl_unlock);
int rtnl_trylock(void)
{
return mutex_trylock(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_trylock);
int rtnl_is_locked(void)
{
return mutex_is_locked(&rtnl_mutex);
}
EXPORT_SYMBOL(rtnl_is_locked);
#ifdef CONFIG_PROVE_LOCKING
bool lockdep_rtnl_is_held(void)
{
return lockdep_is_held(&rtnl_mutex);
}
EXPORT_SYMBOL(lockdep_rtnl_is_held);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
static struct rtnl_link __rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
static refcount_t rtnl_msg_handlers_ref[RTNL_FAMILY_MAX + 1];
static inline int rtm_msgindex(int msgtype)
{
int msgindex = msgtype - RTM_BASE;
/*
* msgindex < 0 implies someone tried to register a netlink
* control code. msgindex >= RTM_NR_MSGTYPES may indicate that
* the message type has not been added to linux/rtnetlink.h
*/
BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES);
return msgindex;
}
/**
* __rtnl_register - Register a rtnetlink message type
* @protocol: Protocol family or PF_UNSPEC
* @msgtype: rtnetlink message type
* @doit: Function pointer called for each request message
* @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
* @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
*
* Registers the specified function pointers (at least one of them has
* to be non-NULL) to be called whenever a request message for the
* specified protocol family and message type is received.
*
* The special protocol family PF_UNSPEC may be used to define fallback
* function pointers for the case when no entry for the specific protocol
* family exists.
*
* Returns 0 on success or a negative error code.
*/
int __rtnl_register(int protocol, int msgtype,
rtnl_doit_func doit, rtnl_dumpit_func dumpit,
unsigned int flags)
{
struct rtnl_link *tab;
int msgindex;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
msgindex = rtm_msgindex(msgtype);
tab = rcu_dereference_raw(rtnl_msg_handlers[protocol]);
if (tab == NULL) {
tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL);
if (tab == NULL)
return -ENOBUFS;
rcu_assign_pointer(rtnl_msg_handlers[protocol], tab);
}
if (doit)
tab[msgindex].doit = doit;
if (dumpit)
tab[msgindex].dumpit = dumpit;
tab[msgindex].flags |= flags;
return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_register);
/**
* rtnl_register - Register a rtnetlink message type
*
* Identical to __rtnl_register() but panics on failure. This is useful
* as failure of this function is very unlikely, it can only happen due
* to lack of memory when allocating the chain to store all message
* handlers for a protocol. Meant for use in init functions where lack
* of memory implies no sense in continuing.
*/
void rtnl_register(int protocol, int msgtype,
rtnl_doit_func doit, rtnl_dumpit_func dumpit,
unsigned int flags)
{
if (__rtnl_register(protocol, msgtype, doit, dumpit, flags) < 0)
panic("Unable to register rtnetlink message handler, "
"protocol = %d, message type = %d\n",
protocol, msgtype);
}
EXPORT_SYMBOL_GPL(rtnl_register);
/**
* rtnl_unregister - Unregister a rtnetlink message type
* @protocol: Protocol family or PF_UNSPEC
* @msgtype: rtnetlink message type
*
* Returns 0 on success or a negative error code.
*/
int rtnl_unregister(int protocol, int msgtype)
{
struct rtnl_link *handlers;
int msgindex;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
msgindex = rtm_msgindex(msgtype);
rtnl_lock();
handlers = rtnl_dereference(rtnl_msg_handlers[protocol]);
if (!handlers) {
rtnl_unlock();
return -ENOENT;
}
handlers[msgindex].doit = NULL;
handlers[msgindex].dumpit = NULL;
handlers[msgindex].flags = 0;
rtnl_unlock();
return 0;
}
EXPORT_SYMBOL_GPL(rtnl_unregister);
/**
* rtnl_unregister_all - Unregister all rtnetlink message type of a protocol
* @protocol : Protocol family or PF_UNSPEC
*
* Identical to calling rtnl_unregster() for all registered message types
* of a certain protocol family.
*/
void rtnl_unregister_all(int protocol)
{
struct rtnl_link *handlers;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
rtnl_lock();
handlers = rtnl_dereference(rtnl_msg_handlers[protocol]);
RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
rtnl_unlock();
synchronize_net();
while (refcount_read(&rtnl_msg_handlers_ref[protocol]) > 1)
schedule();
kfree(handlers);
}
EXPORT_SYMBOL_GPL(rtnl_unregister_all);
static LIST_HEAD(link_ops);
static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
{
const struct rtnl_link_ops *ops;
list_for_each_entry(ops, &link_ops, list) {
if (!strcmp(ops->kind, kind))
return ops;
}
return NULL;
}
/**
* __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
* @ops: struct rtnl_link_ops * to register
*
* The caller must hold the rtnl_mutex. This function should be used
* by drivers that create devices during module initialization. It
* must be called before registering the devices.
*
* Returns 0 on success or a negative error code.
*/
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
if (rtnl_link_ops_get(ops->kind))
return -EEXIST;
/* The check for setup is here because if ops
* does not have that filled up, it is not possible
* to use the ops for creating device. So do not
* fill up dellink as well. That disables rtnl_dellink.
*/
if (ops->setup && !ops->dellink)
ops->dellink = unregister_netdevice_queue;
list_add_tail(&ops->list, &link_ops);
return 0;
}
EXPORT_SYMBOL_GPL(__rtnl_link_register);
/**
* rtnl_link_register - Register rtnl_link_ops with rtnetlink.
* @ops: struct rtnl_link_ops * to register
*
* Returns 0 on success or a negative error code.
*/
int rtnl_link_register(struct rtnl_link_ops *ops)
{
int err;
rtnl_lock();
err = __rtnl_link_register(ops);
rtnl_unlock();
return err;
}
EXPORT_SYMBOL_GPL(rtnl_link_register);
static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
{
struct net_device *dev;
LIST_HEAD(list_kill);
for_each_netdev(net, dev) {
if (dev->rtnl_link_ops == ops)
ops->dellink(dev, &list_kill);
}
unregister_netdevice_many(&list_kill);
}
/**
* __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
* @ops: struct rtnl_link_ops * to unregister
*
* The caller must hold the rtnl_mutex.
*/
void __rtnl_link_unregister(struct rtnl_link_ops *ops)
{
struct net *net;
for_each_net(net) {
__rtnl_kill_links(net, ops);
}
list_del(&ops->list);
}
EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
/* Return with the rtnl_lock held when there are no network
* devices unregistering in any network namespace.
*/
static void rtnl_lock_unregistering_all(void)
{
struct net *net;
bool unregistering;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(&netdev_unregistering_wq, &wait);
for (;;) {
unregistering = false;
rtnl_lock();
for_each_net(net) {
if (net->dev_unreg_count > 0) {
unregistering = true;
break;
}
}
if (!unregistering)
break;
__rtnl_unlock();
wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
remove_wait_queue(&netdev_unregistering_wq, &wait);
}
/**
* rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
* @ops: struct rtnl_link_ops * to unregister
*/
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
/* Close the race with cleanup_net() */
mutex_lock(&net_mutex);
rtnl_lock_unregistering_all();
__rtnl_link_unregister(ops);
rtnl_unlock();
mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(rtnl_link_unregister);
static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev)
{
struct net_device *master_dev;
const struct rtnl_link_ops *ops;
size_t size = 0;
rcu_read_lock();
master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
if (!master_dev)
goto out;
ops = master_dev->rtnl_link_ops;
if (!ops || !ops->get_slave_size)
goto out;
/* IFLA_INFO_SLAVE_DATA + nested data */
size = nla_total_size(sizeof(struct nlattr)) +
ops->get_slave_size(master_dev, dev);
out:
rcu_read_unlock();
return size;
}
static size_t rtnl_link_get_size(const struct net_device *dev)
{
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
size_t size;
if (!ops)
return 0;
size = nla_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */
nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */
if (ops->get_size)
/* IFLA_INFO_DATA + nested data */
size += nla_total_size(sizeof(struct nlattr)) +
ops->get_size(dev);
if (ops->get_xstats_size)
/* IFLA_INFO_XSTATS */
size += nla_total_size(ops->get_xstats_size(dev));
size += rtnl_link_get_slave_info_data_size(dev);
return size;
}
static LIST_HEAD(rtnl_af_ops);
static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
{
const struct rtnl_af_ops *ops;
list_for_each_entry(ops, &rtnl_af_ops, list) {
if (ops->family == family)
return ops;
}
return NULL;
}
/**
* rtnl_af_register - Register rtnl_af_ops with rtnetlink.
* @ops: struct rtnl_af_ops * to register
*
* Returns 0 on success or a negative error code.
*/
void rtnl_af_register(struct rtnl_af_ops *ops)
{
rtnl_lock();
list_add_tail(&ops->list, &rtnl_af_ops);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_af_register);
/**
* __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
* @ops: struct rtnl_af_ops * to unregister
*
* The caller must hold the rtnl_mutex.
*/
void __rtnl_af_unregister(struct rtnl_af_ops *ops)
{
list_del(&ops->list);
}
EXPORT_SYMBOL_GPL(__rtnl_af_unregister);
/**
* rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink.
* @ops: struct rtnl_af_ops * to unregister
*/
void rtnl_af_unregister(struct rtnl_af_ops *ops)
{
rtnl_lock();
__rtnl_af_unregister(ops);
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(rtnl_af_unregister);
static size_t rtnl_link_get_af_size(const struct net_device *dev,
u32 ext_filter_mask)
{
struct rtnl_af_ops *af_ops;
size_t size;
/* IFLA_AF_SPEC */
size = nla_total_size(sizeof(struct nlattr));
list_for_each_entry(af_ops, &rtnl_af_ops, list) {
if (af_ops->get_link_af_size) {
/* AF_* + nested data */
size += nla_total_size(sizeof(struct nlattr)) +
af_ops->get_link_af_size(dev, ext_filter_mask);
}
}
return size;
}
static bool rtnl_have_link_slave_info(const struct net_device *dev)
{
struct net_device *master_dev;
master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
if (master_dev && master_dev->rtnl_link_ops)
return true;
return false;
}
static int rtnl_link_slave_info_fill(struct sk_buff *skb,
const struct net_device *dev)
{
struct net_device *master_dev;
const struct rtnl_link_ops *ops;
struct nlattr *slave_data;
int err;
master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
if (!master_dev)
return 0;
ops = master_dev->rtnl_link_ops;
if (!ops)
return 0;
if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0)
return -EMSGSIZE;
if (ops->fill_slave_info) {
slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA);
if (!slave_data)
return -EMSGSIZE;
err = ops->fill_slave_info(skb, master_dev, dev);
if (err < 0)
goto err_cancel_slave_data;
nla_nest_end(skb, slave_data);
}
return 0;
err_cancel_slave_data:
nla_nest_cancel(skb, slave_data);
return err;
}
static int rtnl_link_info_fill(struct sk_buff *skb,
const struct net_device *dev)
{
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
struct nlattr *data;
int err;
if (!ops)
return 0;
if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
return -EMSGSIZE;
if (ops->fill_xstats) {
err = ops->fill_xstats(skb, dev);
if (err < 0)
return err;
}
if (ops->fill_info) {
data = nla_nest_start(skb, IFLA_INFO_DATA);
if (data == NULL)
return -EMSGSIZE;
err = ops->fill_info(skb, dev);
if (err < 0)
goto err_cancel_data;
nla_nest_end(skb, data);
}
return 0;
err_cancel_data:
nla_nest_cancel(skb, data);
return err;
}
static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
{
struct nlattr *linkinfo;
int err = -EMSGSIZE;
linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
if (linkinfo == NULL)
goto out;
err = rtnl_link_info_fill(skb, dev);
if (err < 0)
goto err_cancel_link;
err = rtnl_link_slave_info_fill(skb, dev);
if (err < 0)
goto err_cancel_link;
nla_nest_end(skb, linkinfo);
return 0;
err_cancel_link:
nla_nest_cancel(skb, linkinfo);
out:
return err;
}
int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
{
struct sock *rtnl = net->rtnl;
int err = 0;
NETLINK_CB(skb).dst_group = group;
if (echo)
refcount_inc(&skb->users);
netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL);
if (echo)
err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
return err;
}
int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid)
{
struct sock *rtnl = net->rtnl;
return nlmsg_unicast(rtnl, skb, pid);
}
EXPORT_SYMBOL(rtnl_unicast);
void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
struct nlmsghdr *nlh, gfp_t flags)
{
struct sock *rtnl = net->rtnl;
int report = 0;
if (nlh)
report = nlmsg_report(nlh);
nlmsg_notify(rtnl, skb, pid, group, report, flags);
}
EXPORT_SYMBOL(rtnl_notify);
void rtnl_set_sk_err(struct net *net, u32 group, int error)
{
struct sock *rtnl = net->rtnl;
netlink_set_err(rtnl, 0, group, error);
}
EXPORT_SYMBOL(rtnl_set_sk_err);
int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
{
struct nlattr *mx;
int i, valid = 0;
mx = nla_nest_start(skb, RTA_METRICS);
if (mx == NULL)
return -ENOBUFS;
for (i = 0; i < RTAX_MAX; i++) {
if (metrics[i]) {
if (i == RTAX_CC_ALGO - 1) {
char tmp[TCP_CA_NAME_MAX], *name;
name = tcp_ca_get_name_by_key(metrics[i], tmp);
if (!name)
continue;
if (nla_put_string(skb, i + 1, name))
goto nla_put_failure;
} else if (i == RTAX_FEATURES - 1) {
u32 user_features = metrics[i] & RTAX_FEATURE_MASK;
if (!user_features)
continue;
BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK);
if (nla_put_u32(skb, i + 1, user_features))
goto nla_put_failure;
} else {
if (nla_put_u32(skb, i + 1, metrics[i]))
goto nla_put_failure;
}
valid++;
}
}
if (!valid) {
nla_nest_cancel(skb, mx);
return 0;
}
return nla_nest_end(skb, mx);
nla_put_failure:
nla_nest_cancel(skb, mx);
return -EMSGSIZE;
}
EXPORT_SYMBOL(rtnetlink_put_metrics);
int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
long expires, u32 error)
{
struct rta_cacheinfo ci = {
.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse),
.rta_used = dst->__use,
.rta_clntref = atomic_read(&(dst->__refcnt)),
.rta_error = error,
.rta_id = id,
};
if (expires) {
unsigned long clock;
clock = jiffies_to_clock_t(abs(expires));
clock = min_t(unsigned long, clock, INT_MAX);
ci.rta_expires = (expires > 0) ? clock : -clock;
}
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
static void set_operstate(struct net_device *dev, unsigned char transition)
{
unsigned char operstate = dev->operstate;
switch (transition) {
case IF_OPER_UP:
if ((operstate == IF_OPER_DORMANT ||
operstate == IF_OPER_UNKNOWN) &&
!netif_dormant(dev))
operstate = IF_OPER_UP;
break;
case IF_OPER_DORMANT:
if (operstate == IF_OPER_UP ||
operstate == IF_OPER_UNKNOWN)
operstate = IF_OPER_DORMANT;
break;
}
if (dev->operstate != operstate) {
write_lock_bh(&dev_base_lock);
dev->operstate = operstate;
write_unlock_bh(&dev_base_lock);
netdev_state_change(dev);
}
}
static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
{
return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) |
(dev->gflags & (IFF_PROMISC | IFF_ALLMULTI));
}
static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
const struct ifinfomsg *ifm)
{
unsigned int flags = ifm->ifi_flags;
/* bugwards compatibility: ifi_change == 0 is treated as ~0 */
if (ifm->ifi_change)
flags = (flags & ifm->ifi_change) |
(rtnl_dev_get_flags(dev) & ~ifm->ifi_change);
return flags;
}
static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
const struct rtnl_link_stats64 *b)
{
a->rx_packets = b->rx_packets;
a->tx_packets = b->tx_packets;
a->rx_bytes = b->rx_bytes;
a->tx_bytes = b->tx_bytes;
a->rx_errors = b->rx_errors;
a->tx_errors = b->tx_errors;
a->rx_dropped = b->rx_dropped;
a->tx_dropped = b->tx_dropped;
a->multicast = b->multicast;
a->collisions = b->collisions;
a->rx_length_errors = b->rx_length_errors;
a->rx_over_errors = b->rx_over_errors;
a->rx_crc_errors = b->rx_crc_errors;
a->rx_frame_errors = b->rx_frame_errors;
a->rx_fifo_errors = b->rx_fifo_errors;
a->rx_missed_errors = b->rx_missed_errors;
a->tx_aborted_errors = b->tx_aborted_errors;
a->tx_carrier_errors = b->tx_carrier_errors;
a->tx_fifo_errors = b->tx_fifo_errors;
a->tx_heartbeat_errors = b->tx_heartbeat_errors;
a->tx_window_errors = b->tx_window_errors;
a->rx_compressed = b->rx_compressed;
a->tx_compressed = b->tx_compressed;
a->rx_nohandler = b->rx_nohandler;
}
/* All VF info */
static inline int rtnl_vfinfo_size(const struct net_device *dev,
u32 ext_filter_mask)
{
if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) {
int num_vfs = dev_num_vf(dev->dev.parent);
size_t size = nla_total_size(0);
size += num_vfs *
(nla_total_size(0) +
nla_total_size(sizeof(struct ifla_vf_mac)) +
nla_total_size(sizeof(struct ifla_vf_vlan)) +
nla_total_size(0) + /* nest IFLA_VF_VLAN_LIST */
nla_total_size(MAX_VLAN_LIST_LEN *
sizeof(struct ifla_vf_vlan_info)) +
nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
nla_total_size(sizeof(struct ifla_vf_rate)) +
nla_total_size(sizeof(struct ifla_vf_link_state)) +
nla_total_size(sizeof(struct ifla_vf_rss_query_en)) +
nla_total_size(0) + /* nest IFLA_VF_STATS */
/* IFLA_VF_STATS_RX_PACKETS */
nla_total_size_64bit(sizeof(__u64)) +
/* IFLA_VF_STATS_TX_PACKETS */
nla_total_size_64bit(sizeof(__u64)) +
/* IFLA_VF_STATS_RX_BYTES */
nla_total_size_64bit(sizeof(__u64)) +
/* IFLA_VF_STATS_TX_BYTES */
nla_total_size_64bit(sizeof(__u64)) +
/* IFLA_VF_STATS_BROADCAST */
nla_total_size_64bit(sizeof(__u64)) +
/* IFLA_VF_STATS_MULTICAST */
nla_total_size_64bit(sizeof(__u64)) +
nla_total_size(sizeof(struct ifla_vf_trust)));
return size;
} else
return 0;
}
static size_t rtnl_port_size(const struct net_device *dev,
u32 ext_filter_mask)
{
size_t port_size = nla_total_size(4) /* PORT_VF */
+ nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */
+ nla_total_size(PORT_UUID_MAX) /* PORT_INSTANCE_UUID */
+ nla_total_size(PORT_UUID_MAX) /* PORT_HOST_UUID */
+ nla_total_size(1) /* PROT_VDP_REQUEST */
+ nla_total_size(2); /* PORT_VDP_RESPONSE */
size_t vf_ports_size = nla_total_size(sizeof(struct nlattr));
size_t vf_port_size = nla_total_size(sizeof(struct nlattr))
+ port_size;
size_t port_self_size = nla_total_size(sizeof(struct nlattr))
+ port_size;
if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
!(ext_filter_mask & RTEXT_FILTER_VF))
return 0;
if (dev_num_vf(dev->dev.parent))
return port_self_size + vf_ports_size +
vf_port_size * dev_num_vf(dev->dev.parent);
else
return port_self_size;
}
static size_t rtnl_xdp_size(void)
{
size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */
nla_total_size(1) + /* XDP_ATTACHED */
nla_total_size(4); /* XDP_PROG_ID */
return xdp_size;
}
static noinline size_t if_nlmsg_size(const struct net_device *dev,
u32 ext_filter_mask)
{
return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+ nla_total_size(IFALIASZ) /* IFLA_IFALIAS */
+ nla_total_size(IFNAMSIZ) /* IFLA_QDISC */
+ nla_total_size_64bit(sizeof(struct rtnl_link_ifmap))
+ nla_total_size(sizeof(struct rtnl_link_stats))
+ nla_total_size_64bit(sizeof(struct rtnl_link_stats64))
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */
+ nla_total_size(4) /* IFLA_TXQLEN */
+ nla_total_size(4) /* IFLA_WEIGHT */
+ nla_total_size(4) /* IFLA_MTU */
+ nla_total_size(4) /* IFLA_LINK */
+ nla_total_size(4) /* IFLA_MASTER */
+ nla_total_size(1) /* IFLA_CARRIER */
+ nla_total_size(4) /* IFLA_PROMISCUITY */
+ nla_total_size(4) /* IFLA_NUM_TX_QUEUES */
+ nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
+ nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
+ nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+ nla_total_size(4) /* IFLA_LINK_NETNSID */
+ nla_total_size(4) /* IFLA_GROUP */
+ nla_total_size(ext_filter_mask
& RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
+ rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
+ rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
+ rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */
+ nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
+ nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+ nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
+ rtnl_xdp_size() /* IFLA_XDP */
+ nla_total_size(4) /* IFLA_EVENT */
+ nla_total_size(1); /* IFLA_PROTO_DOWN */
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *vf_ports;
struct nlattr *vf_port;
int vf;
int err;
vf_ports = nla_nest_start(skb, IFLA_VF_PORTS);
if (!vf_ports)
return -EMSGSIZE;
for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) {
vf_port = nla_nest_start(skb, IFLA_VF_PORT);
if (!vf_port)
goto nla_put_failure;
if (nla_put_u32(skb, IFLA_PORT_VF, vf))
goto nla_put_failure;
err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb);
if (err == -EMSGSIZE)
goto nla_put_failure;
if (err) {
nla_nest_cancel(skb, vf_port);
continue;
}
nla_nest_end(skb, vf_port);
}
nla_nest_end(skb, vf_ports);
return 0;
nla_put_failure:
nla_nest_cancel(skb, vf_ports);
return -EMSGSIZE;
}
static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *port_self;
int err;
port_self = nla_nest_start(skb, IFLA_PORT_SELF);
if (!port_self)
return -EMSGSIZE;
err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb);
if (err) {
nla_nest_cancel(skb, port_self);
return (err == -EMSGSIZE) ? err : 0;
}
nla_nest_end(skb, port_self);
return 0;
}
static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
u32 ext_filter_mask)
{
int err;
if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
!(ext_filter_mask & RTEXT_FILTER_VF))
return 0;
err = rtnl_port_self_fill(skb, dev);
if (err)
return err;
if (dev_num_vf(dev->dev.parent)) {
err = rtnl_vf_ports_fill(skb, dev);
if (err)
return err;
}
return 0;
}
static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
struct netdev_phys_item_id ppid;
err = dev_get_phys_port_id(dev, &ppid);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id))
return -EMSGSIZE;
return 0;
}
static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
{
char name[IFNAMSIZ];
int err;
err = dev_get_phys_port_name(dev, name, sizeof(name));
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name))
return -EMSGSIZE;
return 0;
}
static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
struct switchdev_attr attr = {
.orig_dev = dev,
.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
err = switchdev_port_attr_get(dev, &attr);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len,
attr.u.ppid.id))
return -EMSGSIZE;
return 0;
}
static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb,
struct net_device *dev)
{
struct rtnl_link_stats64 *sp;
struct nlattr *attr;
attr = nla_reserve_64bit(skb, IFLA_STATS64,
sizeof(struct rtnl_link_stats64), IFLA_PAD);
if (!attr)
return -EMSGSIZE;
sp = nla_data(attr);
dev_get_stats(dev, sp);
attr = nla_reserve(skb, IFLA_STATS,
sizeof(struct rtnl_link_stats));
if (!attr)
return -EMSGSIZE;
copy_rtnl_link_stats(nla_data(attr), sp);
return 0;
}
static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
struct net_device *dev,
int vfs_num,
struct nlattr *vfinfo)
{
struct ifla_vf_rss_query_en vf_rss_query_en;
struct nlattr *vf, *vfstats, *vfvlanlist;
struct ifla_vf_link_state vf_linkstate;
struct ifla_vf_vlan_info vf_vlan_info;
struct ifla_vf_spoofchk vf_spoofchk;
struct ifla_vf_tx_rate vf_tx_rate;
struct ifla_vf_stats vf_stats;
struct ifla_vf_trust vf_trust;
struct ifla_vf_vlan vf_vlan;
struct ifla_vf_rate vf_rate;
struct ifla_vf_mac vf_mac;
struct ifla_vf_info ivi;
memset(&ivi, 0, sizeof(ivi));
/* Not all SR-IOV capable drivers support the
* spoofcheck and "RSS query enable" query. Preset to
* -1 so the user space tool can detect that the driver
* didn't report anything.
*/
ivi.spoofchk = -1;
ivi.rss_query_en = -1;
ivi.trusted = -1;
/* The default value for VF link state is "auto"
* IFLA_VF_LINK_STATE_AUTO which equals zero
*/
ivi.linkstate = 0;
/* VLAN Protocol by default is 802.1Q */
ivi.vlan_proto = htons(ETH_P_8021Q);
if (dev->netdev_ops->ndo_get_vf_config(dev, vfs_num, &ivi))
return 0;
memset(&vf_vlan_info, 0, sizeof(vf_vlan_info));
vf_mac.vf =
vf_vlan.vf =
vf_vlan_info.vf =
vf_rate.vf =
vf_tx_rate.vf =
vf_spoofchk.vf =
vf_linkstate.vf =
vf_rss_query_en.vf =
vf_trust.vf = ivi.vf;
memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
vf_vlan.vlan = ivi.vlan;
vf_vlan.qos = ivi.qos;
vf_vlan_info.vlan = ivi.vlan;
vf_vlan_info.qos = ivi.qos;
vf_vlan_info.vlan_proto = ivi.vlan_proto;
vf_tx_rate.rate = ivi.max_tx_rate;
vf_rate.min_tx_rate = ivi.min_tx_rate;
vf_rate.max_tx_rate = ivi.max_tx_rate;
vf_spoofchk.setting = ivi.spoofchk;
vf_linkstate.link_state = ivi.linkstate;
vf_rss_query_en.setting = ivi.rss_query_en;
vf_trust.setting = ivi.trusted;
vf = nla_nest_start(skb, IFLA_VF_INFO);
if (!vf)
goto nla_put_vfinfo_failure;
if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
&vf_rate) ||
nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
&vf_tx_rate) ||
nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
&vf_spoofchk) ||
nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate),
&vf_linkstate) ||
nla_put(skb, IFLA_VF_RSS_QUERY_EN,
sizeof(vf_rss_query_en),
&vf_rss_query_en) ||
nla_put(skb, IFLA_VF_TRUST,
sizeof(vf_trust), &vf_trust))
goto nla_put_vf_failure;
vfvlanlist = nla_nest_start(skb, IFLA_VF_VLAN_LIST);
if (!vfvlanlist)
goto nla_put_vf_failure;
if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info),
&vf_vlan_info)) {
nla_nest_cancel(skb, vfvlanlist);
goto nla_put_vf_failure;
}
nla_nest_end(skb, vfvlanlist);
memset(&vf_stats, 0, sizeof(vf_stats));
if (dev->netdev_ops->ndo_get_vf_stats)
dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
&vf_stats);
vfstats = nla_nest_start(skb, IFLA_VF_STATS);
if (!vfstats)
goto nla_put_vf_failure;
if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
vf_stats.rx_packets, IFLA_VF_STATS_PAD) ||
nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS,
vf_stats.tx_packets, IFLA_VF_STATS_PAD) ||
nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES,
vf_stats.rx_bytes, IFLA_VF_STATS_PAD) ||
nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES,
vf_stats.tx_bytes, IFLA_VF_STATS_PAD) ||
nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
vf_stats.multicast, IFLA_VF_STATS_PAD)) {
nla_nest_cancel(skb, vfstats);
goto nla_put_vf_failure;
}
nla_nest_end(skb, vfstats);
nla_nest_end(skb, vf);
return 0;
nla_put_vf_failure:
nla_nest_cancel(skb, vf);
nla_put_vfinfo_failure:
nla_nest_cancel(skb, vfinfo);
return -EMSGSIZE;
}
static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
{
struct rtnl_link_ifmap map;
memset(&map, 0, sizeof(map));
map.mem_start = dev->mem_start;
map.mem_end = dev->mem_end;
map.base_addr = dev->base_addr;
map.irq = dev->irq;
map.dma = dev->dma;
map.port = dev->if_port;
if (nla_put_64bit(skb, IFLA_MAP, sizeof(map), &map, IFLA_PAD))
return -EMSGSIZE;
return 0;
}
static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
{
const struct net_device_ops *ops = dev->netdev_ops;
const struct bpf_prog *generic_xdp_prog;
ASSERT_RTNL();
*prog_id = 0;
generic_xdp_prog = rtnl_dereference(dev->xdp_prog);
if (generic_xdp_prog) {
*prog_id = generic_xdp_prog->aux->id;
return XDP_ATTACHED_SKB;
}
if (!ops->ndo_xdp)
return XDP_ATTACHED_NONE;
return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id);
}
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *xdp;
u32 prog_id;
int err;
xdp = nla_nest_start(skb, IFLA_XDP);
if (!xdp)
return -EMSGSIZE;
err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
rtnl_xdp_attached_mode(dev, &prog_id));
if (err)
goto err_cancel;
if (prog_id) {
err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
if (err)
goto err_cancel;
}
nla_nest_end(skb, xdp);
return 0;
err_cancel:
nla_nest_cancel(skb, xdp);
return err;
}
static u32 rtnl_get_event(unsigned long event)
{
u32 rtnl_event_type = IFLA_EVENT_NONE;
switch (event) {
case NETDEV_REBOOT:
rtnl_event_type = IFLA_EVENT_REBOOT;
break;
case NETDEV_FEAT_CHANGE:
rtnl_event_type = IFLA_EVENT_FEATURES;
break;
case NETDEV_BONDING_FAILOVER:
rtnl_event_type = IFLA_EVENT_BONDING_FAILOVER;
break;
case NETDEV_NOTIFY_PEERS:
rtnl_event_type = IFLA_EVENT_NOTIFY_PEERS;
break;
case NETDEV_RESEND_IGMP:
rtnl_event_type = IFLA_EVENT_IGMP_RESEND;
break;
case NETDEV_CHANGEINFODATA:
rtnl_event_type = IFLA_EVENT_BONDING_OPTIONS;
break;
default:
break;
}
return rtnl_event_type;
}
static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask,
u32 event)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
struct nlattr *af_spec;
struct rtnl_af_ops *af_ops;
struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
ASSERT_RTNL();
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
if (nlh == NULL)
return -EMSGSIZE;
ifm = nlmsg_data(nlh);
ifm->ifi_family = AF_UNSPEC;
ifm->__ifi_pad = 0;
ifm->ifi_type = dev->type;
ifm->ifi_index = dev->ifindex;
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = change;
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) ||
nla_put_u8(skb, IFLA_OPERSTATE,
netif_running(dev) ? dev->operstate : IF_OPER_DOWN) ||
nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) ||
nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
nla_put_u32(skb, IFLA_GROUP, dev->group) ||
nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) ||
nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) ||
nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
(dev->ifindex != dev_get_iflink(dev) &&
nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) ||
(upper_dev &&
nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) ||
nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
(dev->qdisc &&
nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
(dev->ifalias &&
nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
nla_put_u32(skb, IFLA_CARRIER_CHANGES,
atomic_read(&dev->carrier_changes)) ||
nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
goto nla_put_failure;
if (event != IFLA_EVENT_NONE) {
if (nla_put_u32(skb, IFLA_EVENT, event))
goto nla_put_failure;
}
if (rtnl_fill_link_ifmap(skb, dev))
goto nla_put_failure;
if (dev->addr_len) {
if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) ||
nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast))
goto nla_put_failure;
}
if (rtnl_phys_port_id_fill(skb, dev))
goto nla_put_failure;
if (rtnl_phys_port_name_fill(skb, dev))
goto nla_put_failure;
if (rtnl_phys_switch_id_fill(skb, dev))
goto nla_put_failure;
if (rtnl_fill_stats(skb, dev))
goto nla_put_failure;
if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) &&
nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)))
goto nla_put_failure;
if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent &&
ext_filter_mask & RTEXT_FILTER_VF) {
int i;
struct nlattr *vfinfo;
int num_vfs = dev_num_vf(dev->dev.parent);
vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
if (!vfinfo)
goto nla_put_failure;
for (i = 0; i < num_vfs; i++) {
if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
goto nla_put_failure;
}
nla_nest_end(skb, vfinfo);
}
if (rtnl_port_fill(skb, dev, ext_filter_mask))
goto nla_put_failure;
if (rtnl_xdp_fill(skb, dev))
goto nla_put_failure;
if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
if (rtnl_link_fill(skb, dev) < 0)
goto nla_put_failure;
}
if (dev->rtnl_link_ops &&
dev->rtnl_link_ops->get_link_net) {
struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
if (!net_eq(dev_net(dev), link_net)) {
int id = peernet2id_alloc(dev_net(dev), link_net);
if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
goto nla_put_failure;
}
}
if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
goto nla_put_failure;
list_for_each_entry(af_ops, &rtnl_af_ops, list) {
if (af_ops->fill_link_af) {
struct nlattr *af;
int err;
if (!(af = nla_nest_start(skb, af_ops->family)))
goto nla_put_failure;
err = af_ops->fill_link_af(skb, dev, ext_filter_mask);
/*
* Caller may return ENODATA to indicate that there
* was no data to be dumped. This is not an error, it
* means we should trim the attribute header and
* continue.
*/
if (err == -ENODATA)
nla_nest_cancel(skb, af);
else if (err < 0)
goto nla_put_failure;
nla_nest_end(skb, af);
}
}
nla_nest_end(skb, af_spec);
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
[IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) },
[IFLA_MTU] = { .type = NLA_U32 },
[IFLA_LINK] = { .type = NLA_U32 },
[IFLA_MASTER] = { .type = NLA_U32 },
[IFLA_CARRIER] = { .type = NLA_U8 },
[IFLA_TXQLEN] = { .type = NLA_U32 },
[IFLA_WEIGHT] = { .type = NLA_U32 },
[IFLA_OPERSTATE] = { .type = NLA_U8 },
[IFLA_LINKMODE] = { .type = NLA_U8 },
[IFLA_LINKINFO] = { .type = NLA_NESTED },
[IFLA_NET_NS_PID] = { .type = NLA_U32 },
[IFLA_NET_NS_FD] = { .type = NLA_U32 },
[IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
[IFLA_VFINFO_LIST] = {. type = NLA_NESTED },
[IFLA_VF_PORTS] = { .type = NLA_NESTED },
[IFLA_PORT_SELF] = { .type = NLA_NESTED },
[IFLA_AF_SPEC] = { .type = NLA_NESTED },
[IFLA_EXT_MASK] = { .type = NLA_U32 },
[IFLA_PROMISCUITY] = { .type = NLA_U32 },
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
[IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
[IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_LINK_NETNSID] = { .type = NLA_S32 },
[IFLA_PROTO_DOWN] = { .type = NLA_U8 },
[IFLA_XDP] = { .type = NLA_NESTED },
[IFLA_EVENT] = { .type = NLA_U32 },
[IFLA_GROUP] = { .type = NLA_U32 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
[IFLA_INFO_KIND] = { .type = NLA_STRING },
[IFLA_INFO_DATA] = { .type = NLA_NESTED },
[IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING },
[IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED },
};
static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
[IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) },
[IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) },
[IFLA_VF_VLAN_LIST] = { .type = NLA_NESTED },
[IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) },
[IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) },
[IFLA_VF_RATE] = { .len = sizeof(struct ifla_vf_rate) },
[IFLA_VF_LINK_STATE] = { .len = sizeof(struct ifla_vf_link_state) },
[IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) },
[IFLA_VF_STATS] = { .type = NLA_NESTED },
[IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) },
[IFLA_VF_IB_NODE_GUID] = { .len = sizeof(struct ifla_vf_guid) },
[IFLA_VF_IB_PORT_GUID] = { .len = sizeof(struct ifla_vf_guid) },
};
static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
[IFLA_PORT_VF] = { .type = NLA_U32 },
[IFLA_PORT_PROFILE] = { .type = NLA_STRING,
.len = PORT_PROFILE_MAX },
[IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY,
.len = PORT_UUID_MAX },
[IFLA_PORT_HOST_UUID] = { .type = NLA_STRING,
.len = PORT_UUID_MAX },
[IFLA_PORT_REQUEST] = { .type = NLA_U8, },
[IFLA_PORT_RESPONSE] = { .type = NLA_U16, },
/* Unused, but we need to keep it here since user space could
* fill it. It's also broken with regard to NLA_BINARY use in
* combination with structs.
*/
[IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY,
.len = sizeof(struct ifla_port_vsi) },
};
static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = {
[IFLA_XDP_FD] = { .type = NLA_S32 },
[IFLA_XDP_ATTACHED] = { .type = NLA_U8 },
[IFLA_XDP_FLAGS] = { .type = NLA_U32 },
[IFLA_XDP_PROG_ID] = { .type = NLA_U32 },
};
static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla)
{
const struct rtnl_link_ops *ops = NULL;
struct nlattr *linfo[IFLA_INFO_MAX + 1];
if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla,
ifla_info_policy, NULL) < 0)
return NULL;
if (linfo[IFLA_INFO_KIND]) {
char kind[MODULE_NAME_LEN];
nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
}
return ops;
}
static bool link_master_filtered(struct net_device *dev, int master_idx)
{
struct net_device *master;
if (!master_idx)
return false;
master = netdev_master_upper_dev_get(dev);
if (!master || master->ifindex != master_idx)
return true;
return false;
}
static bool link_kind_filtered(const struct net_device *dev,
const struct rtnl_link_ops *kind_ops)
{
if (kind_ops && dev->rtnl_link_ops != kind_ops)
return true;
return false;
}
static bool link_dump_filtered(struct net_device *dev,
int master_idx,
const struct rtnl_link_ops *kind_ops)
{
if (link_master_filtered(dev, master_idx) ||
link_kind_filtered(dev, kind_ops))
return true;
return false;
}
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
int h, s_h;
int idx = 0, s_idx;
struct net_device *dev;
struct hlist_head *head;
struct nlattr *tb[IFLA_MAX+1];
u32 ext_filter_mask = 0;
const struct rtnl_link_ops *kind_ops = NULL;
unsigned int flags = NLM_F_MULTI;
int master_idx = 0;
int err;
int hdrlen;
s_h = cb->args[0];
s_idx = cb->args[1];
/* A hack to preserve kernel<->userspace interface.
* The correct header is ifinfomsg. It is consistent with rtnl_getlink.
* However, before Linux v3.9 the code here assumed rtgenmsg and that's
* what iproute2 < v3.9.0 used.
* We can detect the old iproute2. Even including the IFLA_EXT_MASK
* attribute, its netlink message is shorter than struct ifinfomsg.
*/
hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
ifla_policy, NULL) >= 0) {
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
if (tb[IFLA_MASTER])
master_idx = nla_get_u32(tb[IFLA_MASTER]);
if (tb[IFLA_LINKINFO])
kind_ops = linkinfo_to_kind_ops(tb[IFLA_LINKINFO]);
if (master_idx || kind_ops)
flags |= NLM_F_DUMP_FILTERED;
}
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
hlist_for_each_entry(dev, head, index_hlist) {
if (link_dump_filtered(dev, master_idx, kind_ops))
goto cont;
if (idx < s_idx)
goto cont;
err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0,
flags,
ext_filter_mask, 0);
if (err < 0) {
if (likely(skb->len))
goto out;
goto out_err;
}
cont:
idx++;
}
}
out:
err = skb->len;
out_err:
cb->args[1] = idx;
cb->args[0] = h;
cb->seq = net->dev_base_seq;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
return err;
}
int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
struct netlink_ext_ack *exterr)
{
return nla_parse(tb, IFLA_MAX, head, len, ifla_policy, exterr);
}
EXPORT_SYMBOL(rtnl_nla_parse_ifla);
struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
{
struct net *net;
/* Examine the link attributes and figure out which
* network namespace we are talking about.
*/
if (tb[IFLA_NET_NS_PID])
net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID]));
else if (tb[IFLA_NET_NS_FD])
net = get_net_ns_by_fd(nla_get_u32(tb[IFLA_NET_NS_FD]));
else
net = get_net(src_net);
return net;
}
EXPORT_SYMBOL(rtnl_link_get_net);
static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
{
if (dev) {
if (tb[IFLA_ADDRESS] &&
nla_len(tb[IFLA_ADDRESS]) < dev->addr_len)
return -EINVAL;
if (tb[IFLA_BROADCAST] &&
nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
return -EINVAL;
}
if (tb[IFLA_AF_SPEC]) {
struct nlattr *af;
int rem, err;
nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
const struct rtnl_af_ops *af_ops;
if (!(af_ops = rtnl_af_lookup(nla_type(af))))
return -EAFNOSUPPORT;
if (!af_ops->set_link_af)
return -EOPNOTSUPP;
if (af_ops->validate_link_af) {
err = af_ops->validate_link_af(dev, af);
if (err < 0)
return err;
}
}
}
return 0;
}
static int handle_infiniband_guid(struct net_device *dev, struct ifla_vf_guid *ivt,
int guid_type)
{
const struct net_device_ops *ops = dev->netdev_ops;
return ops->ndo_set_vf_guid(dev, ivt->vf, ivt->guid, guid_type);
}
static int handle_vf_guid(struct net_device *dev, struct ifla_vf_guid *ivt, int guid_type)
{
if (dev->type != ARPHRD_INFINIBAND)
return -EOPNOTSUPP;
return handle_infiniband_guid(dev, ivt, guid_type);
}
static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
{
const struct net_device_ops *ops = dev->netdev_ops;
int err = -EINVAL;
if (tb[IFLA_VF_MAC]) {
struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_mac)
err = ops->ndo_set_vf_mac(dev, ivm->vf,
ivm->mac);
if (err < 0)
return err;
}
if (tb[IFLA_VF_VLAN]) {
struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_vlan)
err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
ivv->qos,
htons(ETH_P_8021Q));
if (err < 0)
return err;
}
if (tb[IFLA_VF_VLAN_LIST]) {
struct ifla_vf_vlan_info *ivvl[MAX_VLAN_LIST_LEN];
struct nlattr *attr;
int rem, len = 0;
err = -EOPNOTSUPP;
if (!ops->ndo_set_vf_vlan)
return err;
nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) {
if (nla_type(attr) != IFLA_VF_VLAN_INFO ||
nla_len(attr) < NLA_HDRLEN) {
return -EINVAL;
}
if (len >= MAX_VLAN_LIST_LEN)
return -EOPNOTSUPP;
ivvl[len] = nla_data(attr);
len++;
}
if (len == 0)
return -EINVAL;
err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan,
ivvl[0]->qos, ivvl[0]->vlan_proto);
if (err < 0)
return err;
}
if (tb[IFLA_VF_TX_RATE]) {
struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
struct ifla_vf_info ivf;
err = -EOPNOTSUPP;
if (ops->ndo_get_vf_config)
err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
if (err < 0)
return err;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_rate)
err = ops->ndo_set_vf_rate(dev, ivt->vf,
ivf.min_tx_rate,
ivt->rate);
if (err < 0)
return err;
}
if (tb[IFLA_VF_RATE]) {
struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_rate)
err = ops->ndo_set_vf_rate(dev, ivt->vf,
ivt->min_tx_rate,
ivt->max_tx_rate);
if (err < 0)
return err;
}
if (tb[IFLA_VF_SPOOFCHK]) {
struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_spoofchk)
err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
ivs->setting);
if (err < 0)
return err;
}
if (tb[IFLA_VF_LINK_STATE]) {
struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_link_state)
err = ops->ndo_set_vf_link_state(dev, ivl->vf,
ivl->link_state);
if (err < 0)
return err;
}
if (tb[IFLA_VF_RSS_QUERY_EN]) {
struct ifla_vf_rss_query_en *ivrssq_en;
err = -EOPNOTSUPP;
ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
if (ops->ndo_set_vf_rss_query_en)
err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
ivrssq_en->setting);
if (err < 0)
return err;
}
if (tb[IFLA_VF_TRUST]) {
struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_trust)
err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
if (err < 0)
return err;
}
if (tb[IFLA_VF_IB_NODE_GUID]) {
struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]);
if (!ops->ndo_set_vf_guid)
return -EOPNOTSUPP;
return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID);
}
if (tb[IFLA_VF_IB_PORT_GUID]) {
struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]);
if (!ops->ndo_set_vf_guid)
return -EOPNOTSUPP;
return handle_vf_guid(dev, ivt, IFLA_VF_IB_PORT_GUID);
}
return err;
}
static int do_set_master(struct net_device *dev, int ifindex)
{
struct net_device *upper_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops;
int err;
if (upper_dev) {
if (upper_dev->ifindex == ifindex)
return 0;
ops = upper_dev->netdev_ops;
if (ops->ndo_del_slave) {
err = ops->ndo_del_slave(upper_dev, dev);
if (err)
return err;
} else {
return -EOPNOTSUPP;
}
}
if (ifindex) {
upper_dev = __dev_get_by_index(dev_net(dev), ifindex);
if (!upper_dev)
return -EINVAL;
ops = upper_dev->netdev_ops;
if (ops->ndo_add_slave) {
err = ops->ndo_add_slave(upper_dev, dev);
if (err)
return err;
} else {
return -EOPNOTSUPP;
}
}
return 0;
}
#define DO_SETLINK_MODIFIED 0x01
/* notify flag means notify + modified. */
#define DO_SETLINK_NOTIFY 0x03
static int do_setlink(const struct sk_buff *skb,
struct net_device *dev, struct ifinfomsg *ifm,
struct netlink_ext_ack *extack,
struct nlattr **tb, char *ifname, int status)
{
const struct net_device_ops *ops = dev->netdev_ops;
int err;
if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) {
struct net *net = rtnl_link_get_net(dev_net(dev), tb);
if (IS_ERR(net)) {
err = PTR_ERR(net);
goto errout;
}
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
put_net(net);
err = -EPERM;
goto errout;
}
err = dev_change_net_namespace(dev, net, ifname);
put_net(net);
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_MAP]) {
struct rtnl_link_ifmap *u_map;
struct ifmap k_map;
if (!ops->ndo_set_config) {
err = -EOPNOTSUPP;
goto errout;
}
if (!netif_device_present(dev)) {
err = -ENODEV;
goto errout;
}
u_map = nla_data(tb[IFLA_MAP]);
k_map.mem_start = (unsigned long) u_map->mem_start;
k_map.mem_end = (unsigned long) u_map->mem_end;
k_map.base_addr = (unsigned short) u_map->base_addr;
k_map.irq = (unsigned char) u_map->irq;
k_map.dma = (unsigned char) u_map->dma;
k_map.port = (unsigned char) u_map->port;
err = ops->ndo_set_config(dev, &k_map);
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_ADDRESS]) {
struct sockaddr *sa;
int len;
len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
sizeof(*sa));
sa = kmalloc(len, GFP_KERNEL);
if (!sa) {
err = -ENOMEM;
goto errout;
}
sa->sa_family = dev->type;
memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
dev->addr_len);
err = dev_set_mac_address(dev, sa);
kfree(sa);
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_MTU]) {
err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
if (err < 0)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_GROUP]) {
dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
status |= DO_SETLINK_NOTIFY;
}
/*
* Interface selected by interface index but interface
* name provided implies that a name change has been
* requested.
*/
if (ifm->ifi_index > 0 && ifname[0]) {
err = dev_change_name(dev, ifname);
if (err < 0)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_IFALIAS]) {
err = dev_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
nla_len(tb[IFLA_IFALIAS]));
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_BROADCAST]) {
nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len);
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
}
if (ifm->ifi_flags || ifm->ifi_change) {
err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm));
if (err < 0)
goto errout;
}
if (tb[IFLA_MASTER]) {
err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_CARRIER]) {
err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_TXQLEN]) {
unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
unsigned int orig_len = dev->tx_queue_len;
if (dev->tx_queue_len ^ value) {
dev->tx_queue_len = value;
err = call_netdevice_notifiers(
NETDEV_CHANGE_TX_QUEUE_LEN, dev);
err = notifier_to_errno(err);
if (err) {
dev->tx_queue_len = orig_len;
goto errout;
}
status |= DO_SETLINK_NOTIFY;
}
}
if (tb[IFLA_OPERSTATE])
set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
if (tb[IFLA_LINKMODE]) {
unsigned char value = nla_get_u8(tb[IFLA_LINKMODE]);
write_lock_bh(&dev_base_lock);
if (dev->link_mode ^ value)
status |= DO_SETLINK_NOTIFY;
dev->link_mode = value;
write_unlock_bh(&dev_base_lock);
}
if (tb[IFLA_VFINFO_LIST]) {
struct nlattr *vfinfo[IFLA_VF_MAX + 1];
struct nlattr *attr;
int rem;
nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
if (nla_type(attr) != IFLA_VF_INFO ||
nla_len(attr) < NLA_HDRLEN) {
err = -EINVAL;
goto errout;
}
err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
ifla_vf_policy, NULL);
if (err < 0)
goto errout;
err = do_setvfinfo(dev, vfinfo);
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
}
err = 0;
if (tb[IFLA_VF_PORTS]) {
struct nlattr *port[IFLA_PORT_MAX+1];
struct nlattr *attr;
int vf;
int rem;
err = -EOPNOTSUPP;
if (!ops->ndo_set_vf_port)
goto errout;
nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) {
if (nla_type(attr) != IFLA_VF_PORT ||
nla_len(attr) < NLA_HDRLEN) {
err = -EINVAL;
goto errout;
}
err = nla_parse_nested(port, IFLA_PORT_MAX, attr,
ifla_port_policy, NULL);
if (err < 0)
goto errout;
if (!port[IFLA_PORT_VF]) {
err = -EOPNOTSUPP;
goto errout;
}
vf = nla_get_u32(port[IFLA_PORT_VF]);
err = ops->ndo_set_vf_port(dev, vf, port);
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
}
err = 0;
if (tb[IFLA_PORT_SELF]) {
struct nlattr *port[IFLA_PORT_MAX+1];
err = nla_parse_nested(port, IFLA_PORT_MAX,
tb[IFLA_PORT_SELF], ifla_port_policy,
NULL);
if (err < 0)
goto errout;
err = -EOPNOTSUPP;
if (ops->ndo_set_vf_port)
err = ops->ndo_set_vf_port(dev, PORT_SELF_VF, port);
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_AF_SPEC]) {
struct nlattr *af;
int rem;
nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) {
const struct rtnl_af_ops *af_ops;
if (!(af_ops = rtnl_af_lookup(nla_type(af))))
BUG();
err = af_ops->set_link_af(dev, af);
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
}
err = 0;
if (tb[IFLA_PROTO_DOWN]) {
err = dev_change_proto_down(dev,
nla_get_u8(tb[IFLA_PROTO_DOWN]));
if (err)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_XDP]) {
struct nlattr *xdp[IFLA_XDP_MAX + 1];
u32 xdp_flags = 0;
err = nla_parse_nested(xdp, IFLA_XDP_MAX, tb[IFLA_XDP],
ifla_xdp_policy, NULL);
if (err < 0)
goto errout;
if (xdp[IFLA_XDP_ATTACHED] || xdp[IFLA_XDP_PROG_ID]) {
err = -EINVAL;
goto errout;
}
if (xdp[IFLA_XDP_FLAGS]) {
xdp_flags = nla_get_u32(xdp[IFLA_XDP_FLAGS]);
if (xdp_flags & ~XDP_FLAGS_MASK) {
err = -EINVAL;
goto errout;
}
if (hweight32(xdp_flags & XDP_FLAGS_MODES) > 1) {
err = -EINVAL;
goto errout;
}
}
if (xdp[IFLA_XDP_FD]) {
err = dev_change_xdp_fd(dev, extack,
nla_get_s32(xdp[IFLA_XDP_FD]),
xdp_flags);
if (err)
goto errout;
status |= DO_SETLINK_NOTIFY;
}
}
errout:
if (status & DO_SETLINK_MODIFIED) {
if (status & DO_SETLINK_NOTIFY)
netdev_state_change(dev);
if (err < 0)
net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
dev->name);
}
return err;
}
static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
struct net_device *dev;
int err;
struct nlattr *tb[IFLA_MAX+1];
char ifname[IFNAMSIZ];
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
extack);
if (err < 0)
goto errout;
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
err = -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
dev = __dev_get_by_name(net, ifname);
else
goto errout;
if (dev == NULL) {
err = -ENODEV;
goto errout;
}
err = validate_linkmsg(dev, tb);
if (err < 0)
goto errout;
err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
errout:
return err;
}
static int rtnl_group_dellink(const struct net *net, int group)
{
struct net_device *dev, *aux;
LIST_HEAD(list_kill);
bool found = false;
if (!group)
return -EPERM;
for_each_netdev(net, dev) {
if (dev->group == group) {
const struct rtnl_link_ops *ops;
found = true;
ops = dev->rtnl_link_ops;
if (!ops || !ops->dellink)
return -EOPNOTSUPP;
}
}
if (!found)
return -ENODEV;
for_each_netdev_safe(net, dev, aux) {
if (dev->group == group) {
const struct rtnl_link_ops *ops;
ops = dev->rtnl_link_ops;
ops->dellink(dev, &list_kill);
}
}
unregister_netdevice_many(&list_kill);
return 0;
}
int rtnl_delete_link(struct net_device *dev)
{
const struct rtnl_link_ops *ops;
LIST_HEAD(list_kill);
ops = dev->rtnl_link_ops;
if (!ops || !ops->dellink)
return -EOPNOTSUPP;
ops->dellink(dev, &list_kill);
unregister_netdevice_many(&list_kill);
return 0;
}
EXPORT_SYMBOL_GPL(rtnl_delete_link);
static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct net_device *dev;
struct ifinfomsg *ifm;
char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
int err;
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
if (err < 0)
return err;
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
dev = __dev_get_by_name(net, ifname);
else if (tb[IFLA_GROUP])
return rtnl_group_dellink(net, nla_get_u32(tb[IFLA_GROUP]));
else
return -EINVAL;
if (!dev)
return -ENODEV;
return rtnl_delete_link(dev);
}
int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
{
unsigned int old_flags;
int err;
old_flags = dev->flags;
if (ifm && (ifm->ifi_flags || ifm->ifi_change)) {
err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm));
if (err < 0)
return err;
}
dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
__dev_notify_flags(dev, old_flags, ~0U);
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
struct net_device *rtnl_create_link(struct net *net,
const char *ifname, unsigned char name_assign_type,
const struct rtnl_link_ops *ops, struct nlattr *tb[])
{
struct net_device *dev;
unsigned int num_tx_queues = 1;
unsigned int num_rx_queues = 1;
if (tb[IFLA_NUM_TX_QUEUES])
num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]);
else if (ops->get_num_tx_queues)
num_tx_queues = ops->get_num_tx_queues();
if (tb[IFLA_NUM_RX_QUEUES])
num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]);
else if (ops->get_num_rx_queues)
num_rx_queues = ops->get_num_rx_queues();
dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
ops->setup, num_tx_queues, num_rx_queues);
if (!dev)
return ERR_PTR(-ENOMEM);
dev_net_set(dev, net);
dev->rtnl_link_ops = ops;
dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
if (tb[IFLA_MTU])
dev->mtu = nla_get_u32(tb[IFLA_MTU]);
if (tb[IFLA_ADDRESS]) {
memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
nla_len(tb[IFLA_ADDRESS]));
dev->addr_assign_type = NET_ADDR_SET;
}
if (tb[IFLA_BROADCAST])
memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]),
nla_len(tb[IFLA_BROADCAST]));
if (tb[IFLA_TXQLEN])
dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
if (tb[IFLA_OPERSTATE])
set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
if (tb[IFLA_LINKMODE])
dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
if (tb[IFLA_GROUP])
dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
return dev;
}
EXPORT_SYMBOL(rtnl_create_link);
static int rtnl_group_changelink(const struct sk_buff *skb,
struct net *net, int group,
struct ifinfomsg *ifm,
struct netlink_ext_ack *extack,
struct nlattr **tb)
{
struct net_device *dev, *aux;
int err;
for_each_netdev_safe(net, dev, aux) {
if (dev->group == group) {
err = do_setlink(skb, dev, ifm, extack, tb, NULL, 0);
if (err < 0)
return err;
}
}
return 0;
}
static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
const struct rtnl_link_ops *m_ops = NULL;
struct net_device *dev;
struct net_device *master_dev = NULL;
struct ifinfomsg *ifm;
char kind[MODULE_NAME_LEN];
char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
struct nlattr *linkinfo[IFLA_INFO_MAX+1];
unsigned char name_assign_type = NET_NAME_USER;
int err;
#ifdef CONFIG_MODULES
replay:
#endif
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
if (err < 0)
return err;
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
else {
if (ifname[0])
dev = __dev_get_by_name(net, ifname);
else
dev = NULL;
}
if (dev) {
master_dev = netdev_master_upper_dev_get(dev);
if (master_dev)
m_ops = master_dev->rtnl_link_ops;
}
err = validate_linkmsg(dev, tb);
if (err < 0)
return err;
if (tb[IFLA_LINKINFO]) {
err = nla_parse_nested(linkinfo, IFLA_INFO_MAX,
tb[IFLA_LINKINFO], ifla_info_policy,
NULL);
if (err < 0)
return err;
} else
memset(linkinfo, 0, sizeof(linkinfo));
if (linkinfo[IFLA_INFO_KIND]) {
nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
} else {
kind[0] = '\0';
ops = NULL;
}
if (1) {
struct nlattr *attr[ops ? ops->maxtype + 1 : 1];
struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 1];
struct nlattr **data = NULL;
struct nlattr **slave_data = NULL;
struct net *dest_net, *link_net = NULL;
if (ops) {
if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
err = nla_parse_nested(attr, ops->maxtype,
linkinfo[IFLA_INFO_DATA],
ops->policy, NULL);
if (err < 0)
return err;
data = attr;
}
if (ops->validate) {
err = ops->validate(tb, data, extack);
if (err < 0)
return err;
}
}
if (m_ops) {
if (m_ops->slave_maxtype &&
linkinfo[IFLA_INFO_SLAVE_DATA]) {
err = nla_parse_nested(slave_attr,
m_ops->slave_maxtype,
linkinfo[IFLA_INFO_SLAVE_DATA],
m_ops->slave_policy,
NULL);
if (err < 0)
return err;
slave_data = slave_attr;
}
if (m_ops->slave_validate) {
err = m_ops->slave_validate(tb, slave_data,
extack);
if (err < 0)
return err;
}
}
if (dev) {
int status = 0;
if (nlh->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
if (linkinfo[IFLA_INFO_DATA]) {
if (!ops || ops != dev->rtnl_link_ops ||
!ops->changelink)
return -EOPNOTSUPP;
err = ops->changelink(dev, tb, data, extack);
if (err < 0)
return err;
status |= DO_SETLINK_NOTIFY;
}
if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
if (!m_ops || !m_ops->slave_changelink)
return -EOPNOTSUPP;
err = m_ops->slave_changelink(master_dev, dev,
tb, slave_data,
extack);
if (err < 0)
return err;
status |= DO_SETLINK_NOTIFY;
}
return do_setlink(skb, dev, ifm, extack, tb, ifname,
status);
}
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
return rtnl_group_changelink(skb, net,
nla_get_u32(tb[IFLA_GROUP]),
ifm, extack, tb);
return -ENODEV;
}
if (tb[IFLA_MAP] || tb[IFLA_PROTINFO])
return -EOPNOTSUPP;
if (!ops) {
#ifdef CONFIG_MODULES
if (kind[0]) {
__rtnl_unlock();
request_module("rtnl-link-%s", kind);
rtnl_lock();
ops = rtnl_link_ops_get(kind);
if (ops)
goto replay;
}
#endif
return -EOPNOTSUPP;
}
if (!ops->setup)
return -EOPNOTSUPP;
if (!ifname[0]) {
snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
name_assign_type = NET_NAME_ENUM;
}
dest_net = rtnl_link_get_net(net, tb);
if (IS_ERR(dest_net))
return PTR_ERR(dest_net);
err = -EPERM;
if (!netlink_ns_capable(skb, dest_net->user_ns, CAP_NET_ADMIN))
goto out;
if (tb[IFLA_LINK_NETNSID]) {
int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
link_net = get_net_ns_by_id(dest_net, id);
if (!link_net) {
err = -EINVAL;
goto out;
}
err = -EPERM;
if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
goto out;
}
dev = rtnl_create_link(link_net ? : dest_net, ifname,
name_assign_type, ops, tb);
if (IS_ERR(dev)) {
err = PTR_ERR(dev);
goto out;
}
dev->ifindex = ifm->ifi_index;
if (ops->newlink) {
err = ops->newlink(link_net ? : net, dev, tb, data,
extack);
/* Drivers should call free_netdev() in ->destructor
* and unregister it on failure after registration
* so that device could be finally freed in rtnl_unlock.
*/
if (err < 0) {
/* If device is not registered at all, free it now */
if (dev->reg_state == NETREG_UNINITIALIZED)
free_netdev(dev);
goto out;
}
} else {
err = register_netdevice(dev);
if (err < 0) {
free_netdev(dev);
goto out;
}
}
err = rtnl_configure_link(dev, ifm);
if (err < 0)
goto out_unregister;
if (link_net) {
err = dev_change_net_namespace(dev, dest_net, ifname);
if (err < 0)
goto out_unregister;
}
if (tb[IFLA_MASTER]) {
err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
if (err)
goto out_unregister;
}
out:
if (link_net)
put_net(link_net);
put_net(dest_net);
return err;
out_unregister:
if (ops->newlink) {
LIST_HEAD(list_kill);
ops->dellink(dev, &list_kill);
unregister_netdevice_many(&list_kill);
} else {
unregister_netdevice(dev);
}
goto out;
}
}
static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
struct net_device *dev = NULL;
struct sk_buff *nskb;
int err;
u32 ext_filter_mask = 0;
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
if (err < 0)
return err;
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
dev = __dev_get_by_name(net, ifname);
else
return -EINVAL;
if (dev == NULL)
return -ENODEV;
nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
if (nskb == NULL)
return -ENOBUFS;
err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
kfree_skb(nskb);
} else
err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
return err;
}
static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct net_device *dev;
struct nlattr *tb[IFLA_MAX+1];
u32 ext_filter_mask = 0;
u16 min_ifinfo_dump_size = 0;
int hdrlen;
/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) {
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
}
if (!ext_filter_mask)
return NLMSG_GOODSIZE;
/*
* traverse the list of net devices and compute the minimum
* buffer size based upon the filter mask.
*/
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
if_nlmsg_size(dev,
ext_filter_mask));
}
rcu_read_unlock();
return nlmsg_total_size(min_ifinfo_dump_size);
}
static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
{
int idx;
int s_idx = cb->family;
if (s_idx == 0)
s_idx = 1;
for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
int type = cb->nlh->nlmsg_type-RTM_BASE;
struct rtnl_link *handlers;
rtnl_dumpit_func dumpit;
if (idx < s_idx || idx == PF_PACKET)
continue;
handlers = rtnl_dereference(rtnl_msg_handlers[idx]);
if (!handlers)
continue;
dumpit = READ_ONCE(handlers[type].dumpit);
if (!dumpit)
continue;
if (idx > s_idx) {
memset(&cb->args[0], 0, sizeof(cb->args));
cb->prev_seq = 0;
cb->seq = 0;
}
if (dumpit(skb, cb))
break;
}
cb->family = idx;
return skb->len;
}
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
unsigned int change,
u32 event, gfp_t flags)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -ENOBUFS;
size_t if_info_size;
skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags);
if (skb == NULL)
goto errout;
err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
return skb;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
return NULL;
}
void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
{
struct net *net = dev_net(dev);
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
}
static void rtmsg_ifinfo_event(int type, struct net_device *dev,
unsigned int change, u32 event,
gfp_t flags)
{
struct sk_buff *skb;
if (dev->reg_state != NETREG_REGISTERED)
return;
skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
if (skb)
rtmsg_ifinfo_send(skb, dev, flags);
}
void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
gfp_t flags)
{
rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags);
}
EXPORT_SYMBOL(rtmsg_ifinfo);
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
u8 *addr, u16 vid, u32 pid, u32 seq,
int type, unsigned int flags,
int nlflags, u16 ndm_state)
{
struct nlmsghdr *nlh;
struct ndmsg *ndm;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags);
if (!nlh)
return -EMSGSIZE;
ndm = nlmsg_data(nlh);
ndm->ndm_family = AF_BRIDGE;
ndm->ndm_pad1 = 0;
ndm->ndm_pad2 = 0;
ndm->ndm_flags = flags;
ndm->ndm_type = 0;
ndm->ndm_ifindex = dev->ifindex;
ndm->ndm_state = ndm_state;
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
goto nla_put_failure;
if (vid)
if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid))
goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static inline size_t rtnl_fdb_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ndmsg)) +
nla_total_size(ETH_ALEN) + /* NDA_LLADDR */
nla_total_size(sizeof(u16)) + /* NDA_VLAN */
0;
}
static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
u16 ndm_state)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -ENOBUFS;
skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC);
if (!skb)
goto errout;
err = nlmsg_populate_fdb_fill(skb, dev, addr, vid,
0, 0, type, NTF_SELF, 0, ndm_state);
if (err < 0) {
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
/**
* ndo_dflt_fdb_add - default netdevice operation to add an FDB entry
*/
int ndo_dflt_fdb_add(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
u16 flags)
{
int err = -EINVAL;
/* If aging addresses are supported device will need to
* implement its own handler for this.
*/
if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
pr_info("%s: FDB only supports static addresses\n", dev->name);
return err;
}
if (vid) {
pr_info("%s: vlans aren't supported yet for dev_uc|mc_add()\n", dev->name);
return err;
}
if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
err = dev_uc_add_excl(dev, addr);
else if (is_multicast_ether_addr(addr))
err = dev_mc_add_excl(dev, addr);
/* Only return duplicate errors if NLM_F_EXCL is set */
if (err == -EEXIST && !(flags & NLM_F_EXCL))
err = 0;
return err;
}
EXPORT_SYMBOL(ndo_dflt_fdb_add);
static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
{
u16 vid = 0;
if (vlan_attr) {
if (nla_len(vlan_attr) != sizeof(u16)) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
return -EINVAL;
}
vid = nla_get_u16(vlan_attr);
if (!vid || vid >= VLAN_VID_MASK) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
vid);
return -EINVAL;
}
}
*p_vid = vid;
return 0;
}
static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
struct nlattr *tb[NDA_MAX+1];
struct net_device *dev;
u8 *addr;
u16 vid;
int err;
err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
if (err < 0)
return err;
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n");
return -EINVAL;
}
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n");
return -ENODEV;
}
if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n");
return -EINVAL;
}
addr = nla_data(tb[NDA_LLADDR]);
err = fdb_vid_parse(tb[NDA_VLAN], &vid);
if (err)
return err;
err = -EOPNOTSUPP;
/* Support fdb on master device the net/bridge default case */
if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
(dev->priv_flags & IFF_BRIDGE_PORT)) {
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops = br_dev->netdev_ops;
err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid,
nlh->nlmsg_flags);
if (err)
goto out;
else
ndm->ndm_flags &= ~NTF_MASTER;
}
/* Embedded bridge, macvlan, and any other device support */
if ((ndm->ndm_flags & NTF_SELF)) {
if (dev->netdev_ops->ndo_fdb_add)
err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
vid,
nlh->nlmsg_flags);
else
err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid,
nlh->nlmsg_flags);
if (!err) {
rtnl_fdb_notify(dev, addr, vid, RTM_NEWNEIGH,
ndm->ndm_state);
ndm->ndm_flags &= ~NTF_SELF;
}
}
out:
return err;
}
/**
* ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry
*/
int ndo_dflt_fdb_del(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid)
{
int err = -EINVAL;
/* If aging addresses are supported device will need to
* implement its own handler for this.
*/
if (!(ndm->ndm_state & NUD_PERMANENT)) {
pr_info("%s: FDB only supports static addresses\n", dev->name);
return err;
}
if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
err = dev_uc_del(dev, addr);
else if (is_multicast_ether_addr(addr))
err = dev_mc_del(dev, addr);
return err;
}
EXPORT_SYMBOL(ndo_dflt_fdb_del);
static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
struct nlattr *tb[NDA_MAX+1];
struct net_device *dev;
int err = -EINVAL;
__u8 *addr;
u16 vid;
if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
if (err < 0)
return err;
ndm = nlmsg_data(nlh);
if (ndm->ndm_ifindex == 0) {
pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n");
return -EINVAL;
}
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n");
return -ENODEV;
}
if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n");
return -EINVAL;
}
addr = nla_data(tb[NDA_LLADDR]);
err = fdb_vid_parse(tb[NDA_VLAN], &vid);
if (err)
return err;
err = -EOPNOTSUPP;
/* Support fdb on master device the net/bridge default case */
if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
(dev->priv_flags & IFF_BRIDGE_PORT)) {
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops = br_dev->netdev_ops;
if (ops->ndo_fdb_del)
err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
if (err)
goto out;
else
ndm->ndm_flags &= ~NTF_MASTER;
}
/* Embedded bridge, macvlan, and any other device support */
if (ndm->ndm_flags & NTF_SELF) {
if (dev->netdev_ops->ndo_fdb_del)
err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
vid);
else
err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
if (!err) {
rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH,
ndm->ndm_state);
ndm->ndm_flags &= ~NTF_SELF;
}
}
out:
return err;
}
static int nlmsg_populate_fdb(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
int *idx,
struct netdev_hw_addr_list *list)
{
struct netdev_hw_addr *ha;
int err;
u32 portid, seq;
portid = NETLINK_CB(cb->skb).portid;
seq = cb->nlh->nlmsg_seq;
list_for_each_entry(ha, &list->list, list) {
if (*idx < cb->args[2])
goto skip;
err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0,
portid, seq,
RTM_NEWNEIGH, NTF_SELF,
NLM_F_MULTI, NUD_PERMANENT);
if (err < 0)
return err;
skip:
*idx += 1;
}
return 0;
}
/**
* ndo_dflt_fdb_dump - default netdevice operation to dump an FDB table.
* @nlh: netlink message header
* @dev: netdevice
*
* Default netdevice operation to dump the existing unicast address list.
* Returns number of addresses from list put in skb.
*/
int ndo_dflt_fdb_dump(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
int *idx)
{
int err;
netif_addr_lock_bh(dev);
err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->uc);
if (err)
goto out;
err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->mc);
out:
netif_addr_unlock_bh(dev);
return err;
}
EXPORT_SYMBOL(ndo_dflt_fdb_dump);
static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net_device *dev;
struct nlattr *tb[IFLA_MAX+1];
struct net_device *br_dev = NULL;
const struct net_device_ops *ops = NULL;
const struct net_device_ops *cops = NULL;
struct ifinfomsg *ifm = nlmsg_data(cb->nlh);
struct net *net = sock_net(skb->sk);
struct hlist_head *head;
int brport_idx = 0;
int br_idx = 0;
int h, s_h;
int idx = 0, s_idx;
int err = 0;
int fidx = 0;
err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
IFLA_MAX, ifla_policy, NULL);
if (err < 0) {
return -EINVAL;
} else if (err == 0) {
if (tb[IFLA_MASTER])
br_idx = nla_get_u32(tb[IFLA_MASTER]);
}
brport_idx = ifm->ifi_index;
if (br_idx) {
br_dev = __dev_get_by_index(net, br_idx);
if (!br_dev)
return -ENODEV;
ops = br_dev->netdev_ops;
}
s_h = cb->args[0];
s_idx = cb->args[1];
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
hlist_for_each_entry(dev, head, index_hlist) {
if (brport_idx && (dev->ifindex != brport_idx))
continue;
if (!br_idx) { /* user did not specify a specific bridge */
if (dev->priv_flags & IFF_BRIDGE_PORT) {
br_dev = netdev_master_upper_dev_get(dev);
cops = br_dev->netdev_ops;
}
} else {
if (dev != br_dev &&
!(dev->priv_flags & IFF_BRIDGE_PORT))
continue;
if (br_dev != netdev_master_upper_dev_get(dev) &&
!(dev->priv_flags & IFF_EBRIDGE))
continue;
cops = ops;
}
if (idx < s_idx)
goto cont;
if (dev->priv_flags & IFF_BRIDGE_PORT) {
if (cops && cops->ndo_fdb_dump) {
err = cops->ndo_fdb_dump(skb, cb,
br_dev, dev,
&fidx);
if (err == -EMSGSIZE)
goto out;
}
}
if (dev->netdev_ops->ndo_fdb_dump)
err = dev->netdev_ops->ndo_fdb_dump(skb, cb,
dev, NULL,
&fidx);
else
err = ndo_dflt_fdb_dump(skb, cb, dev, NULL,
&fidx);
if (err == -EMSGSIZE)
goto out;
cops = NULL;
/* reset fdb offset to 0 for rest of the interfaces */
cb->args[2] = 0;
fidx = 0;
cont:
idx++;
}
}
out:
cb->args[0] = h;
cb->args[1] = idx;
cb->args[2] = fidx;
return skb->len;
}
static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
unsigned int attrnum, unsigned int flag)
{
if (mask & flag)
return nla_put_u8(skb, attrnum, !!(flags & flag));
return 0;
}
int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
struct net_device *dev, u16 mode,
u32 flags, u32 mask, int nlflags,
u32 filter_mask,
int (*vlan_fill)(struct sk_buff *skb,
struct net_device *dev,
u32 filter_mask))
{
struct nlmsghdr *nlh;
struct ifinfomsg *ifm;
struct nlattr *br_afspec;
struct nlattr *protinfo;
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
int err = 0;
nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), nlflags);
if (nlh == NULL)
return -EMSGSIZE;
ifm = nlmsg_data(nlh);
ifm->ifi_family = AF_BRIDGE;
ifm->__ifi_pad = 0;
ifm->ifi_type = dev->type;
ifm->ifi_index = dev->ifindex;
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = 0;
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
(br_dev &&
nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) ||
(dev->addr_len &&
nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
(dev->ifindex != dev_get_iflink(dev) &&
nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
goto nla_put_failure;
br_afspec = nla_nest_start(skb, IFLA_AF_SPEC);
if (!br_afspec)
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF)) {
nla_nest_cancel(skb, br_afspec);
goto nla_put_failure;
}
if (mode != BRIDGE_MODE_UNDEF) {
if (nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
nla_nest_cancel(skb, br_afspec);
goto nla_put_failure;
}
}
if (vlan_fill) {
err = vlan_fill(skb, dev, filter_mask);
if (err) {
nla_nest_cancel(skb, br_afspec);
goto nla_put_failure;
}
}
nla_nest_end(skb, br_afspec);
protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
if (!protinfo)
goto nla_put_failure;
if (brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_MODE, BR_HAIRPIN_MODE) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_GUARD, BR_BPDU_GUARD) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_FAST_LEAVE,
BR_MULTICAST_FAST_LEAVE) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_LEARNING, BR_LEARNING) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_LEARNING_SYNC, BR_LEARNING_SYNC) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) ||
brport_nla_put_flag(skb, flags, mask,
IFLA_BRPORT_PROXYARP, BR_PROXYARP)) {
nla_nest_cancel(skb, protinfo);
goto nla_put_failure;
}
nla_nest_end(skb, protinfo);
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return err ? err : -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(ndo_dflt_bridge_getlink);
static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct net_device *dev;
int idx = 0;
u32 portid = NETLINK_CB(cb->skb).portid;
u32 seq = cb->nlh->nlmsg_seq;
u32 filter_mask = 0;
int err;
if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
struct nlattr *extfilt;
extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg),
IFLA_EXT_MASK);
if (extfilt) {
if (nla_len(extfilt) < sizeof(filter_mask))
return -EINVAL;
filter_mask = nla_get_u32(extfilt);
}
}
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
const struct net_device_ops *ops = dev->netdev_ops;
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
if (idx >= cb->args[0]) {
err = br_dev->netdev_ops->ndo_bridge_getlink(
skb, portid, seq, dev,
filter_mask, NLM_F_MULTI);
if (err < 0 && err != -EOPNOTSUPP) {
if (likely(skb->len))
break;
goto out_err;
}
}
idx++;
}
if (ops->ndo_bridge_getlink) {
if (idx >= cb->args[0]) {
err = ops->ndo_bridge_getlink(skb, portid,
seq, dev,
filter_mask,
NLM_F_MULTI);
if (err < 0 && err != -EOPNOTSUPP) {
if (likely(skb->len))
break;
goto out_err;
}
}
idx++;
}
}
err = skb->len;
out_err:
rcu_read_unlock();
cb->args[0] = idx;
return err;
}
static inline size_t bridge_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+ nla_total_size(sizeof(u32)) /* IFLA_MASTER */
+ nla_total_size(sizeof(u32)) /* IFLA_MTU */
+ nla_total_size(sizeof(u32)) /* IFLA_LINK */
+ nla_total_size(sizeof(u32)) /* IFLA_OPERSTATE */
+ nla_total_size(sizeof(u8)) /* IFLA_PROTINFO */
+ nla_total_size(sizeof(struct nlattr)) /* IFLA_AF_SPEC */
+ nla_total_size(sizeof(u16)) /* IFLA_BRIDGE_FLAGS */
+ nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_MODE */
}
static int rtnl_bridge_notify(struct net_device *dev)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
int err = -EOPNOTSUPP;
if (!dev->netdev_ops->ndo_bridge_getlink)
return 0;
skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC);
if (!skb) {
err = -ENOMEM;
goto errout;
}
err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0, 0);
if (err < 0)
goto errout;
if (!skb->len)
goto errout;
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
return 0;
errout:
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
if (err)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
return err;
}
static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
struct net_device *dev;
struct nlattr *br_spec, *attr = NULL;
int rem, err = -EOPNOTSUPP;
u16 flags = 0;
bool have_flags = false;
if (nlmsg_len(nlh) < sizeof(*ifm))
return -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_family != AF_BRIDGE)
return -EPFNOSUPPORT;
dev = __dev_get_by_index(net, ifm->ifi_index);
if (!dev) {
pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
return -ENODEV;
}
br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (br_spec) {
nla_for_each_nested(attr, br_spec, rem) {
if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
if (nla_len(attr) < sizeof(flags))
return -EINVAL;
have_flags = true;
flags = nla_get_u16(attr);
break;
}
}
}
if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) {
err = -EOPNOTSUPP;
goto out;
}
err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags);
if (err)
goto out;
flags &= ~BRIDGE_FLAGS_MASTER;
}
if ((flags & BRIDGE_FLAGS_SELF)) {
if (!dev->netdev_ops->ndo_bridge_setlink)
err = -EOPNOTSUPP;
else
err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh,
flags);
if (!err) {
flags &= ~BRIDGE_FLAGS_SELF;
/* Generate event to notify upper layer of bridge
* change
*/
err = rtnl_bridge_notify(dev);
}
}
if (have_flags)
memcpy(nla_data(attr), &flags, sizeof(flags));
out:
return err;
}
static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
struct net_device *dev;
struct nlattr *br_spec, *attr = NULL;
int rem, err = -EOPNOTSUPP;
u16 flags = 0;
bool have_flags = false;
if (nlmsg_len(nlh) < sizeof(*ifm))
return -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_family != AF_BRIDGE)
return -EPFNOSUPPORT;
dev = __dev_get_by_index(net, ifm->ifi_index);
if (!dev) {
pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n");
return -ENODEV;
}
br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (br_spec) {
nla_for_each_nested(attr, br_spec, rem) {
if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
if (nla_len(attr) < sizeof(flags))
return -EINVAL;
have_flags = true;
flags = nla_get_u16(attr);
break;
}
}
}
if (!flags || (flags & BRIDGE_FLAGS_MASTER)) {
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
if (!br_dev || !br_dev->netdev_ops->ndo_bridge_dellink) {
err = -EOPNOTSUPP;
goto out;
}
err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh, flags);
if (err)
goto out;
flags &= ~BRIDGE_FLAGS_MASTER;
}
if ((flags & BRIDGE_FLAGS_SELF)) {
if (!dev->netdev_ops->ndo_bridge_dellink)
err = -EOPNOTSUPP;
else
err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh,
flags);
if (!err) {
flags &= ~BRIDGE_FLAGS_SELF;
/* Generate event to notify upper layer of bridge
* change
*/
err = rtnl_bridge_notify(dev);
}
}
if (have_flags)
memcpy(nla_data(attr), &flags, sizeof(flags));
out:
return err;
}
static bool stats_attr_valid(unsigned int mask, int attrid, int idxattr)
{
return (mask & IFLA_STATS_FILTER_BIT(attrid)) &&
(!idxattr || idxattr == attrid);
}
#define IFLA_OFFLOAD_XSTATS_FIRST (IFLA_OFFLOAD_XSTATS_UNSPEC + 1)
static int rtnl_get_offload_stats_attr_size(int attr_id)
{
switch (attr_id) {
case IFLA_OFFLOAD_XSTATS_CPU_HIT:
return sizeof(struct rtnl_link_stats64);
}
return 0;
}
static int rtnl_get_offload_stats(struct sk_buff *skb, struct net_device *dev,
int *prividx)
{
struct nlattr *attr = NULL;
int attr_id, size;
void *attr_data;
int err;
if (!(dev->netdev_ops && dev->netdev_ops->ndo_has_offload_stats &&
dev->netdev_ops->ndo_get_offload_stats))
return -ENODATA;
for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST;
attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) {
if (attr_id < *prividx)
continue;
size = rtnl_get_offload_stats_attr_size(attr_id);
if (!size)
continue;
if (!dev->netdev_ops->ndo_has_offload_stats(dev, attr_id))
continue;
attr = nla_reserve_64bit(skb, attr_id, size,
IFLA_OFFLOAD_XSTATS_UNSPEC);
if (!attr)
goto nla_put_failure;
attr_data = nla_data(attr);
memset(attr_data, 0, size);
err = dev->netdev_ops->ndo_get_offload_stats(attr_id, dev,
attr_data);
if (err)
goto get_offload_stats_failure;
}
if (!attr)
return -ENODATA;
*prividx = 0;
return 0;
nla_put_failure:
err = -EMSGSIZE;
get_offload_stats_failure:
*prividx = attr_id;
return err;
}
static int rtnl_get_offload_stats_size(const struct net_device *dev)
{
int nla_size = 0;
int attr_id;
int size;
if (!(dev->netdev_ops && dev->netdev_ops->ndo_has_offload_stats &&
dev->netdev_ops->ndo_get_offload_stats))
return 0;
for (attr_id = IFLA_OFFLOAD_XSTATS_FIRST;
attr_id <= IFLA_OFFLOAD_XSTATS_MAX; attr_id++) {
if (!dev->netdev_ops->ndo_has_offload_stats(dev, attr_id))
continue;
size = rtnl_get_offload_stats_attr_size(attr_id);
nla_size += nla_total_size_64bit(size);
}
if (nla_size != 0)
nla_size += nla_total_size(0);
return nla_size;
}
static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, unsigned int filter_mask,
int *idxattr, int *prividx)
{
struct if_stats_msg *ifsm;
struct nlmsghdr *nlh;
struct nlattr *attr;
int s_prividx = *prividx;
int err;
ASSERT_RTNL();
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifsm), flags);
if (!nlh)
return -EMSGSIZE;
ifsm = nlmsg_data(nlh);
ifsm->ifindex = dev->ifindex;
ifsm->filter_mask = filter_mask;
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_64, *idxattr)) {
struct rtnl_link_stats64 *sp;
attr = nla_reserve_64bit(skb, IFLA_STATS_LINK_64,
sizeof(struct rtnl_link_stats64),
IFLA_STATS_UNSPEC);
if (!attr)
goto nla_put_failure;
sp = nla_data(attr);
dev_get_stats(dev, sp);
}
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS, *idxattr)) {
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
if (ops && ops->fill_linkxstats) {
*idxattr = IFLA_STATS_LINK_XSTATS;
attr = nla_nest_start(skb,
IFLA_STATS_LINK_XSTATS);
if (!attr)
goto nla_put_failure;
err = ops->fill_linkxstats(skb, dev, prividx, *idxattr);
nla_nest_end(skb, attr);
if (err)
goto nla_put_failure;
*idxattr = 0;
}
}
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS_SLAVE,
*idxattr)) {
const struct rtnl_link_ops *ops = NULL;
const struct net_device *master;
master = netdev_master_upper_dev_get(dev);
if (master)
ops = master->rtnl_link_ops;
if (ops && ops->fill_linkxstats) {
*idxattr = IFLA_STATS_LINK_XSTATS_SLAVE;
attr = nla_nest_start(skb,
IFLA_STATS_LINK_XSTATS_SLAVE);
if (!attr)
goto nla_put_failure;
err = ops->fill_linkxstats(skb, dev, prividx, *idxattr);
nla_nest_end(skb, attr);
if (err)
goto nla_put_failure;
*idxattr = 0;
}
}
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS,
*idxattr)) {
*idxattr = IFLA_STATS_LINK_OFFLOAD_XSTATS;
attr = nla_nest_start(skb, IFLA_STATS_LINK_OFFLOAD_XSTATS);
if (!attr)
goto nla_put_failure;
err = rtnl_get_offload_stats(skb, dev, prividx);
if (err == -ENODATA)
nla_nest_cancel(skb, attr);
else
nla_nest_end(skb, attr);
if (err && err != -ENODATA)
goto nla_put_failure;
*idxattr = 0;
}
if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, *idxattr)) {
struct rtnl_af_ops *af_ops;
*idxattr = IFLA_STATS_AF_SPEC;
attr = nla_nest_start(skb, IFLA_STATS_AF_SPEC);
if (!attr)
goto nla_put_failure;
list_for_each_entry(af_ops, &rtnl_af_ops, list) {
if (af_ops->fill_stats_af) {
struct nlattr *af;
int err;
af = nla_nest_start(skb, af_ops->family);
if (!af)
goto nla_put_failure;
err = af_ops->fill_stats_af(skb, dev);
if (err == -ENODATA)
nla_nest_cancel(skb, af);
else if (err < 0)
goto nla_put_failure;
nla_nest_end(skb, af);
}
}
nla_nest_end(skb, attr);
*idxattr = 0;
}
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
/* not a multi message or no progress mean a real error */
if (!(flags & NLM_F_MULTI) || s_prividx == *prividx)
nlmsg_cancel(skb, nlh);
else
nlmsg_end(skb, nlh);
return -EMSGSIZE;
}
static size_t if_nlmsg_stats_size(const struct net_device *dev,
u32 filter_mask)
{
size_t size = 0;
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_64, 0))
size += nla_total_size_64bit(sizeof(struct rtnl_link_stats64));
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS, 0)) {
const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
int attr = IFLA_STATS_LINK_XSTATS;
if (ops && ops->get_linkxstats_size) {
size += nla_total_size(ops->get_linkxstats_size(dev,
attr));
/* for IFLA_STATS_LINK_XSTATS */
size += nla_total_size(0);
}
}
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_XSTATS_SLAVE, 0)) {
struct net_device *_dev = (struct net_device *)dev;
const struct rtnl_link_ops *ops = NULL;
const struct net_device *master;
/* netdev_master_upper_dev_get can't take const */
master = netdev_master_upper_dev_get(_dev);
if (master)
ops = master->rtnl_link_ops;
if (ops && ops->get_linkxstats_size) {
int attr = IFLA_STATS_LINK_XSTATS_SLAVE;
size += nla_total_size(ops->get_linkxstats_size(dev,
attr));
/* for IFLA_STATS_LINK_XSTATS_SLAVE */
size += nla_total_size(0);
}
}
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0))
size += rtnl_get_offload_stats_size(dev);
if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, 0)) {
struct rtnl_af_ops *af_ops;
/* for IFLA_STATS_AF_SPEC */
size += nla_total_size(0);
list_for_each_entry(af_ops, &rtnl_af_ops, list) {
if (af_ops->get_stats_af_size) {
size += nla_total_size(
af_ops->get_stats_af_size(dev));
/* for AF_* */
size += nla_total_size(0);
}
}
}
return size;
}
static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct net_device *dev = NULL;
int idxattr = 0, prividx = 0;
struct if_stats_msg *ifsm;
struct sk_buff *nskb;
u32 filter_mask;
int err;
if (nlmsg_len(nlh) < sizeof(*ifsm))
return -EINVAL;
ifsm = nlmsg_data(nlh);
if (ifsm->ifindex > 0)
dev = __dev_get_by_index(net, ifsm->ifindex);
else
return -EINVAL;
if (!dev)
return -ENODEV;
filter_mask = ifsm->filter_mask;
if (!filter_mask)
return -EINVAL;
nskb = nlmsg_new(if_nlmsg_stats_size(dev, filter_mask), GFP_KERNEL);
if (!nskb)
return -ENOBUFS;
err = rtnl_fill_statsinfo(nskb, dev, RTM_NEWSTATS,
NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
0, filter_mask, &idxattr, &prividx);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_stats_size */
WARN_ON(err == -EMSGSIZE);
kfree_skb(nskb);
} else {
err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
}
return err;
}
static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
int h, s_h, err, s_idx, s_idxattr, s_prividx;
struct net *net = sock_net(skb->sk);
unsigned int flags = NLM_F_MULTI;
struct if_stats_msg *ifsm;
struct hlist_head *head;
struct net_device *dev;
u32 filter_mask = 0;
int idx = 0;
s_h = cb->args[0];
s_idx = cb->args[1];
s_idxattr = cb->args[2];
s_prividx = cb->args[3];
cb->seq = net->dev_base_seq;
if (nlmsg_len(cb->nlh) < sizeof(*ifsm))
return -EINVAL;
ifsm = nlmsg_data(cb->nlh);
filter_mask = ifsm->filter_mask;
if (!filter_mask)
return -EINVAL;
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
hlist_for_each_entry(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
err = rtnl_fill_statsinfo(skb, dev, RTM_NEWSTATS,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0,
flags, filter_mask,
&s_idxattr, &s_prividx);
/* If we ran out of room on the first message,
* we're in trouble
*/
WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
if (err < 0)
goto out;
s_prividx = 0;
s_idxattr = 0;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
}
out:
cb->args[3] = s_prividx;
cb->args[2] = s_idxattr;
cb->args[1] = idx;
cb->args[0] = h;
return skb->len;
}
/* Process one rtnetlink message. */
static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct rtnl_link *handlers;
int err = -EOPNOTSUPP;
rtnl_doit_func doit;
unsigned int flags;
int kind;
int family;
int type;
type = nlh->nlmsg_type;
if (type > RTM_MAX)
return -EOPNOTSUPP;
type -= RTM_BASE;
/* All the messages must have at least 1 byte length */
if (nlmsg_len(nlh) < sizeof(struct rtgenmsg))
return 0;
family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
kind = type&3;
if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (family >= ARRAY_SIZE(rtnl_msg_handlers))
family = PF_UNSPEC;
rcu_read_lock();
handlers = rcu_dereference(rtnl_msg_handlers[family]);
if (!handlers) {
family = PF_UNSPEC;
handlers = rcu_dereference(rtnl_msg_handlers[family]);
}
if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
struct sock *rtnl;
rtnl_dumpit_func dumpit;
u16 min_dump_alloc = 0;
dumpit = READ_ONCE(handlers[type].dumpit);
if (!dumpit) {
family = PF_UNSPEC;
handlers = rcu_dereference(rtnl_msg_handlers[PF_UNSPEC]);
if (!handlers)
goto err_unlock;
dumpit = READ_ONCE(handlers[type].dumpit);
if (!dumpit)
goto err_unlock;
}
refcount_inc(&rtnl_msg_handlers_ref[family]);
if (type == RTM_GETLINK - RTM_BASE)
min_dump_alloc = rtnl_calcit(skb, nlh);
rcu_read_unlock();
rtnl = net->rtnl;
{
struct netlink_dump_control c = {
.dump = dumpit,
.min_dump_alloc = min_dump_alloc,
};
err = netlink_dump_start(rtnl, skb, nlh, &c);
}
refcount_dec(&rtnl_msg_handlers_ref[family]);
return err;
}
doit = READ_ONCE(handlers[type].doit);
if (!doit) {
family = PF_UNSPEC;
handlers = rcu_dereference(rtnl_msg_handlers[family]);
}
flags = READ_ONCE(handlers[type].flags);
if (flags & RTNL_FLAG_DOIT_UNLOCKED) {
refcount_inc(&rtnl_msg_handlers_ref[family]);
doit = READ_ONCE(handlers[type].doit);
rcu_read_unlock();
if (doit)
err = doit(skb, nlh, extack);
refcount_dec(&rtnl_msg_handlers_ref[family]);
return err;
}
rcu_read_unlock();
rtnl_lock();
handlers = rtnl_dereference(rtnl_msg_handlers[family]);
if (handlers) {
doit = READ_ONCE(handlers[type].doit);
if (doit)
err = doit(skb, nlh, extack);
}
rtnl_unlock();
return err;
err_unlock:
rcu_read_unlock();
return -EOPNOTSUPP;
}
static void rtnetlink_rcv(struct sk_buff *skb)
{
netlink_rcv_skb(skb, &rtnetlink_rcv_msg);
}
static int rtnetlink_bind(struct net *net, int group)
{
switch (group) {
case RTNLGRP_IPV4_MROUTE_R:
case RTNLGRP_IPV6_MROUTE_R:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
break;
}
return 0;
}
static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
switch (event) {
case NETDEV_REBOOT:
case NETDEV_CHANGEADDR:
case NETDEV_CHANGENAME:
case NETDEV_FEAT_CHANGE:
case NETDEV_BONDING_FAILOVER:
case NETDEV_NOTIFY_PEERS:
case NETDEV_RESEND_IGMP:
case NETDEV_CHANGEINFODATA:
rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
GFP_KERNEL);
break;
default:
break;
}
return NOTIFY_DONE;
}
static struct notifier_block rtnetlink_dev_notifier = {
.notifier_call = rtnetlink_event,
};
static int __net_init rtnetlink_net_init(struct net *net)
{
struct sock *sk;
struct netlink_kernel_cfg cfg = {
.groups = RTNLGRP_MAX,
.input = rtnetlink_rcv,
.cb_mutex = &rtnl_mutex,
.flags = NL_CFG_F_NONROOT_RECV,
.bind = rtnetlink_bind,
};
sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg);
if (!sk)
return -ENOMEM;
net->rtnl = sk;
return 0;
}
static void __net_exit rtnetlink_net_exit(struct net *net)
{
netlink_kernel_release(net->rtnl);
net->rtnl = NULL;
}
static struct pernet_operations rtnetlink_net_ops = {
.init = rtnetlink_net_init,
.exit = rtnetlink_net_exit,
};
void __init rtnetlink_init(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(rtnl_msg_handlers_ref); i++)
refcount_set(&rtnl_msg_handlers_ref[i], 1);
if (register_pernet_subsys(&rtnetlink_net_ops))
panic("rtnetlink_init: cannot initialize rtnetlink\n");
register_netdevice_notifier(&rtnetlink_dev_notifier);
rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
rtnl_dump_ifinfo, 0);
rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, 0);
rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0);
rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0);
rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, 0);
rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0);
rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_GETSTATS, rtnl_stats_get, rtnl_stats_dump,
0);
}
Reference in New Issue View Git Blame Copy Permalink