summaryrefslogtreecommitdiff
path: root/net/core/rtnetlink.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/rtnetlink.c')
-rw-r--r--net/core/rtnetlink.c199
1 files changed, 141 insertions, 58 deletions
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index df042da422ef..12aa3aa1688b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -63,7 +63,7 @@
#include "dev.h"
#define RTNL_MAX_TYPE 50
-#define RTNL_SLAVE_MAX_TYPE 44
+#define RTNL_SLAVE_MAX_TYPE 45
struct rtnl_link {
rtnl_doit_func doit;
@@ -750,13 +750,12 @@ static size_t rtnl_link_get_size(const struct net_device *dev)
}
static LIST_HEAD(rtnl_af_ops);
+static DEFINE_SPINLOCK(rtnl_af_ops_lock);
static struct rtnl_af_ops *rtnl_af_lookup(const int family, int *srcu_index)
{
struct rtnl_af_ops *ops;
- ASSERT_RTNL();
-
rcu_read_lock();
list_for_each_entry_rcu(ops, &rtnl_af_ops, list) {
@@ -791,9 +790,9 @@ int rtnl_af_register(struct rtnl_af_ops *ops)
if (err)
return err;
- rtnl_lock();
+ spin_lock(&rtnl_af_ops_lock);
list_add_tail_rcu(&ops->list, &rtnl_af_ops);
- rtnl_unlock();
+ spin_unlock(&rtnl_af_ops_lock);
return 0;
}
@@ -805,9 +804,9 @@ EXPORT_SYMBOL_GPL(rtnl_af_register);
*/
void rtnl_af_unregister(struct rtnl_af_ops *ops)
{
- rtnl_lock();
+ spin_lock(&rtnl_af_ops_lock);
list_del_rcu(&ops->list);
- rtnl_unlock();
+ spin_unlock(&rtnl_af_ops_lock);
synchronize_rcu();
synchronize_srcu(&ops->srcu);
@@ -1264,11 +1263,11 @@ static size_t rtnl_devlink_port_size(const struct net_device *dev)
return size;
}
-static size_t rtnl_dpll_pin_size(const struct net_device *dev)
+static size_t rtnl_dpll_pin_size(void)
{
size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */
- size += dpll_netdev_pin_handle_size(dev);
+ size += dpll_netdev_pin_handle_size();
return size;
}
@@ -1295,7 +1294,12 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
size = NLMSG_ALIGN(sizeof(struct ifinfomsg))
+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
- + nla_total_size(IFALIASZ) /* IFLA_IFALIAS */
+ + rtnl_prop_list_size(dev);
+
+ if (ext_filter_mask & RTEXT_FILTER_NAME_ONLY)
+ return size;
+
+ size += nla_total_size(IFALIASZ) /* IFLA_IFALIAS */
+ nla_total_size(IFNAMSIZ) /* IFLA_QDISC */
+ nla_total_size_64bit(sizeof(struct rtnl_link_ifmap))
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
@@ -1342,10 +1346,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */
+ nla_total_size(4) /* IFLA_MIN_MTU */
+ nla_total_size(4) /* IFLA_MAX_MTU */
- + rtnl_prop_list_size(dev)
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */
+ rtnl_devlink_port_size(dev)
- + rtnl_dpll_pin_size(dev)
+ + rtnl_dpll_pin_size()
+ nla_total_size(8) /* IFLA_MAX_PACING_OFFLOAD_HORIZON */
+ nla_total_size(2) /* IFLA_HEADROOM */
+ nla_total_size(2) /* IFLA_TAILROOM */
@@ -1941,15 +1944,18 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb,
struct netdev_name_node *name_node;
int count = 0;
+ rcu_read_lock();
list_for_each_entry_rcu(name_node, &dev->name_node->list, list) {
- if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name))
+ if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name)) {
+ rcu_read_unlock();
return -EMSGSIZE;
+ }
count++;
}
+ rcu_read_unlock();
return count;
}
-/* RCU protected. */
static int rtnl_fill_prop_list(struct sk_buff *skb,
const struct net_device *dev)
{
@@ -1964,7 +1970,10 @@ static int rtnl_fill_prop_list(struct sk_buff *skb,
if (ret <= 0)
goto nest_cancel;
- nla_nest_end(skb, prop_list);
+ ret = -EMSGSIZE;
+ if (nla_nest_end_safe(skb, prop_list) < 0)
+ goto nest_cancel;
+
return 0;
nest_cancel:
@@ -2059,7 +2068,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
struct nlmsghdr *nlh;
struct Qdisc *qdisc;
- ASSERT_RTNL();
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2072,13 +2080,21 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
ifm->ifi_flags = netif_get_flags(dev);
ifm->ifi_change = change;
- if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
- goto nla_put_failure;
-
netdev_copy_name(dev, devname);
if (nla_put_string(skb, IFLA_IFNAME, devname))
goto nla_put_failure;
+ if (rtnl_fill_prop_list(skb, dev))
+ goto nla_put_failure;
+
+ if (ext_filter_mask & RTEXT_FILTER_NAME_ONLY)
+ goto end;
+
+ ASSERT_RTNL();
+ if (tgt_netnsid >= 0 &&
+ nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
+ goto nla_put_failure;
+
if (nla_put_u32(skb, IFLA_TXQLEN, READ_ONCE(dev->tx_queue_len)) ||
nla_put_u8(skb, IFLA_OPERSTATE,
netif_running(dev) ? READ_ONCE(dev->operstate) :
@@ -2191,8 +2207,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure_rcu;
if (rtnl_fill_link_ifmap(skb, dev))
goto nla_put_failure_rcu;
- if (rtnl_fill_prop_list(skb, dev))
- goto nla_put_failure_rcu;
rcu_read_unlock();
if (dev->dev.parent &&
@@ -2211,6 +2225,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
if (rtnl_fill_dpll_pin(skb, dev))
goto nla_put_failure;
+end:
nlmsg_end(skb, nlh);
return 0;
@@ -2356,22 +2371,24 @@ static struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla,
static bool link_master_filtered(struct net_device *dev, int master_idx)
{
struct net_device *master;
+ bool res = false;
if (!master_idx)
return false;
- master = netdev_master_upper_dev_get(dev);
+ rcu_read_lock();
+ master = netdev_master_upper_dev_get_rcu(dev);
/* 0 is already used to denote IFLA_MASTER wasn't passed, therefore need
* another invalid value for ifindex to denote "no master".
*/
if (master_idx == -1)
- return !!master;
-
- if (!master || master->ifindex != master_idx)
- return true;
+ res = !!master;
+ else if (!master || master->ifindex != master_idx)
+ res = true;
+ rcu_read_unlock();
- return false;
+ return res;
}
static bool link_kind_filtered(const struct net_device *dev,
@@ -2421,6 +2438,14 @@ struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid)
}
EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable);
+bool rtnl_dev_link_net_capable(const struct net_device *dev,
+ const struct net *link_net)
+{
+ return net_eq(link_net, dev_net(dev)) ||
+ ns_capable(link_net->user_ns, CAP_NET_ADMIN);
+}
+EXPORT_SYMBOL_GPL(rtnl_dev_link_net_capable);
+
static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
bool strict_check, struct nlattr **tb,
struct netlink_ext_ack *extack)
@@ -2482,6 +2507,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
int ops_srcu_index;
int master_idx = 0;
int netnsid = -1;
+ bool need_rtnl;
int err, i;
err = rtnl_valid_dump_ifinfo_req(nlh, cb->strict_check, tb, extack);
@@ -2531,6 +2557,12 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
walk_entries:
err = 0;
+ need_rtnl = !(ext_filter_mask & RTEXT_FILTER_NAME_ONLY);
+ if (need_rtnl)
+ rtnl_lock();
+ else
+ rcu_read_lock();
+
for_each_netdev_dump(tgt_net, dev, ctx->ifindex) {
if (link_dump_filtered(dev, master_idx, kind_ops))
continue;
@@ -2542,11 +2574,13 @@ walk_entries:
if (err < 0)
break;
}
-
-
- cb->seq = tgt_net->dev_base_seq;
+ cb->seq = READ_ONCE(tgt_net->dev_base_seq);
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ if (need_rtnl)
+ rtnl_unlock();
+ else
+ rcu_read_unlock();
out:
if (kind_ops)
@@ -3453,6 +3487,21 @@ static struct net_device *rtnl_dev_get(struct net *net,
return __dev_get_by_name(net, ifname);
}
+static struct net_device *rtnl_dev_get_rcu(struct net *net,
+ struct nlattr *tb[])
+{
+ char ifname[ALTIFNAMSIZ];
+
+ if (tb[IFLA_IFNAME])
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ else if (tb[IFLA_ALT_IFNAME])
+ nla_strscpy(ifname, tb[IFLA_ALT_IFNAME], ALTIFNAMSIZ);
+ else
+ return NULL;
+
+ return dev_get_by_name_rcu(net, ifname);
+}
+
static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -4172,14 +4221,16 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
+ struct nlattr *tb[IFLA_MAX + 1];
+ netdevice_tracker dev_tracker;
+ struct net_device *dev = NULL;
struct net *tgt_net = net;
+ u32 ext_filter_mask = 0;
struct ifinfomsg *ifm;
- struct nlattr *tb[IFLA_MAX+1];
- struct net_device *dev = NULL;
struct sk_buff *nskb;
int netnsid = -1;
+ bool need_rtnl;
int err;
- u32 ext_filter_mask = 0;
err = rtnl_valid_getlink_req(skb, nlh, tb, extack);
if (err < 0)
@@ -4199,43 +4250,71 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
- err = -EINVAL;
ifm = nlmsg_data(nlh);
- if (ifm->ifi_index > 0)
- dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(tgt_net, tb);
- else
+ rcu_read_lock();
+ if (ifm->ifi_index > 0) {
+ dev = dev_get_by_index_rcu(tgt_net, ifm->ifi_index);
+ } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
+ dev = rtnl_dev_get_rcu(tgt_net, tb);
+ } else {
+ rcu_read_unlock();
+ err = -EINVAL;
goto out;
+ }
+ netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
+ rcu_read_unlock();
err = -ENODEV;
if (dev == NULL)
goto out;
+ need_rtnl = !(ext_filter_mask & RTEXT_FILTER_NAME_ONLY);
+
+retry:
+ if (need_rtnl) {
+ rtnl_lock();
+ if (!dev_isalive(dev)) {
+ err = -ENODEV;
+ nskb = NULL;
+ goto unlock;
+ }
+ /* Synchronize the carrier state so we don't report a state
+ * that we're not actually going to honour immediately; if
+ * the driver just did a carrier off->on transition, we can
+ * only TX if link watch work has run, but without this we'd
+ * already report carrier on, even if it doesn't work yet.
+ */
+ linkwatch_sync_dev(dev);
+ }
+
err = -ENOBUFS;
nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask));
- if (nskb == NULL)
- goto out;
+ if (nskb)
+ err = rtnl_fill_ifinfo(nskb, dev, net,
+ RTM_NEWLINK, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq, 0, 0, ext_filter_mask,
+ 0, NULL, 0, netnsid, GFP_KERNEL);
- /* Synchronize the carrier state so we don't report a state
- * that we're not actually going to honour immediately; if
- * the driver just did a carrier off->on transition, we can
- * only TX if link watch work has run, but without this we'd
- * already report carrier on, even if it doesn't work yet.
- */
- linkwatch_sync_dev(dev);
+unlock:
+ if (need_rtnl)
+ rtnl_unlock();
- err = rtnl_fill_ifinfo(nskb, dev, net,
- RTM_NEWLINK, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq, 0, 0, ext_filter_mask,
- 0, NULL, 0, netnsid, GFP_KERNEL);
if (err < 0) {
- /* -EMSGSIZE implies BUG in if_nlmsg_size */
- WARN_ON(err == -EMSGSIZE);
kfree_skb(nskb);
- } else
+ if (err == -EMSGSIZE) {
+ if (!need_rtnl) {
+ /* Some altnames were added, retry with RTNL. */
+ need_rtnl = true;
+ goto retry;
+ }
+ /* -EMSGSIZE implies BUG in if_nlmsg_size */
+ WARN_ON_ONCE(1);
+ }
+ } else {
err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
+ }
out:
+ netdev_put(dev, &dev_tracker);
if (netnsid >= 0)
put_net(tgt_net);
@@ -6328,8 +6407,9 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
0, &filters, &idxattr, &prividx, extack);
if (err < 0) {
- /* -EMSGSIZE implies BUG in if_nlmsg_stats_size */
- WARN_ON(err == -EMSGSIZE);
+ /* -EMSGSIZE implies BUG in if_nlmsg_stats_size
+ * or a too big nested attribute.
+ */
kfree_skb(nskb);
} else {
err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
@@ -7101,7 +7181,10 @@ static const struct rtnl_msg_handler rtnetlink_rtnl_msg_handlers[] __initconst =
{.msgtype = RTM_DELLINK, .doit = rtnl_dellink,
.flags = RTNL_FLAG_DOIT_PERNET_WIP},
{.msgtype = RTM_GETLINK, .doit = rtnl_getlink,
- .dumpit = rtnl_dump_ifinfo, .flags = RTNL_FLAG_DUMP_SPLIT_NLM_DONE},
+ .dumpit = rtnl_dump_ifinfo,
+ .flags = RTNL_FLAG_DUMP_SPLIT_NLM_DONE |
+ RTNL_FLAG_DOIT_UNLOCKED |
+ RTNL_FLAG_DUMP_UNLOCKED},
{.msgtype = RTM_SETLINK, .doit = rtnl_setlink,
.flags = RTNL_FLAG_DOIT_PERNET_WIP},
{.msgtype = RTM_GETADDR, .dumpit = rtnl_dump_all},
generated by cgit v1.2.3 (git 2.0.4) at 2026-08-14 20:17:39 +0000