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.c222
1 files changed, 126 insertions, 96 deletions
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d9f959c619d9..5a24a30dfc2d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -53,6 +53,7 @@
#include <net/fib_rules.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
+#include <net/netdev_lock.h>
#include <net/devlink.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/addrconf.h>
@@ -80,11 +81,15 @@ void rtnl_lock(void)
}
EXPORT_SYMBOL(rtnl_lock);
+int rtnl_lock_interruptible(void)
+{
+ return mutex_lock_interruptible(&rtnl_mutex);
+}
+
int rtnl_lock_killable(void)
{
return mutex_lock_killable(&rtnl_mutex);
}
-EXPORT_SYMBOL(rtnl_lock_killable);
static struct sk_buff *defer_kfree_skb_list;
void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail)
@@ -221,6 +226,16 @@ int rtnl_net_trylock(struct net *net)
}
EXPORT_SYMBOL(rtnl_net_trylock);
+int rtnl_net_lock_killable(struct net *net)
+{
+ int ret = rtnl_lock_killable();
+
+ if (!ret)
+ __rtnl_net_lock(net);
+
+ return ret;
+}
+
static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b)
{
if (net_eq(net_a, net_b))
@@ -1278,6 +1293,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ + nla_total_size(1) /* IFLA_NETNS_IMMUTABLE */
+ nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+ nla_total_size(4) /* IFLA_LINK_NETNSID */
+ nla_total_size(4) /* IFLA_GROUP */
@@ -2032,6 +2048,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
netif_running(dev) ? READ_ONCE(dev->operstate) :
IF_OPER_DOWN) ||
nla_put_u8(skb, IFLA_LINKMODE, READ_ONCE(dev->link_mode)) ||
+ nla_put_u8(skb, IFLA_NETNS_IMMUTABLE, dev->netns_immutable) ||
nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) ||
nla_put_u32(skb, IFLA_MIN_MTU, READ_ONCE(dev->min_mtu)) ||
nla_put_u32(skb, IFLA_MAX_MTU, READ_ONCE(dev->max_mtu)) ||
@@ -2220,6 +2237,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_ALLMULTI] = { .type = NLA_REJECT },
[IFLA_GSO_IPV4_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
[IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 },
+ [IFLA_NETNS_IMMUTABLE] = { .type = NLA_REJECT },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2895,12 +2913,19 @@ static int do_set_master(struct net_device *dev, int ifindex,
const struct net_device_ops *ops;
int err;
+ /* Release the lower lock, the upper is responsible for locking
+ * the lower if needed. None of the existing upper devices
+ * use netdev instance lock, so don't grab it.
+ */
+
if (upper_dev) {
if (upper_dev->ifindex == ifindex)
return 0;
ops = upper_dev->netdev_ops;
if (ops->ndo_del_slave) {
+ netdev_unlock_ops(dev);
err = ops->ndo_del_slave(upper_dev, dev);
+ netdev_lock_ops(dev);
if (err)
return err;
} else {
@@ -2914,7 +2939,9 @@ static int do_set_master(struct net_device *dev, int ifindex,
return -EINVAL;
ops = upper_dev->netdev_ops;
if (ops->ndo_add_slave) {
+ netdev_unlock_ops(dev);
err = ops->ndo_add_slave(upper_dev, dev, extack);
+ netdev_lock_ops(dev);
if (err)
return err;
} else {
@@ -2964,7 +2991,7 @@ static int do_set_proto_down(struct net_device *dev,
if (pdreason[IFLA_PROTO_DOWN_REASON_MASK])
mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]);
- dev_change_proto_down_reason(dev, mask, value);
+ netdev_change_proto_down_reason_locked(dev, mask, value);
}
if (nl_proto_down) {
@@ -2975,8 +3002,7 @@ static int do_set_proto_down(struct net_device *dev,
NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
return -EBUSY;
}
- err = dev_change_proto_down(dev,
- proto_down);
+ err = netif_change_proto_down(dev, proto_down);
if (err)
return err;
}
@@ -2996,6 +3022,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
char ifname[IFNAMSIZ];
int err;
+ netdev_lock_ops(dev);
+
err = validate_linkmsg(dev, tb, extack);
if (err < 0)
goto errout;
@@ -3011,7 +3039,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0);
- err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex);
+ err = netif_change_net_namespace(dev, tgt_net, pat,
+ new_ifindex, extack);
if (err)
goto errout;
@@ -3059,24 +3088,35 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
goto errout;
}
sa->sa_family = dev->type;
+
+ netdev_unlock_ops(dev);
+
+ /* dev_addr_sem is an outer lock, enforce proper ordering */
+ down_write(&dev_addr_sem);
+ netdev_lock_ops(dev);
+
memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
dev->addr_len);
- err = dev_set_mac_address_user(dev, sa, extack);
+ err = netif_set_mac_address(dev, sa, extack);
kfree(sa);
- if (err)
+ if (err) {
+ up_write(&dev_addr_sem);
goto errout;
+ }
status |= DO_SETLINK_MODIFIED;
+
+ up_write(&dev_addr_sem);
}
if (tb[IFLA_MTU]) {
- err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
+ err = netif_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
if (err < 0)
goto errout;
status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_GROUP]) {
- dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
+ netif_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
status |= DO_SETLINK_NOTIFY;
}
@@ -3086,15 +3126,15 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
* requested.
*/
if (ifm->ifi_index > 0 && ifname[0]) {
- err = dev_change_name(dev, ifname);
+ err = netif_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]));
+ err = netif_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
+ nla_len(tb[IFLA_IFALIAS]));
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
@@ -3106,8 +3146,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
}
if (ifm->ifi_flags || ifm->ifi_change) {
- err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
- extack);
+ err = netif_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+ extack);
if (err < 0)
goto errout;
}
@@ -3120,7 +3160,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
}
if (tb[IFLA_CARRIER]) {
- err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
+ err = netif_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
@@ -3129,7 +3169,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
if (tb[IFLA_TXQLEN]) {
unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
- err = dev_change_tx_queue_len(dev, value);
+ err = netif_change_tx_queue_len(dev, value);
if (err)
goto errout;
status |= DO_SETLINK_MODIFIED;
@@ -3360,6 +3400,8 @@ errout:
dev->name);
}
+ netdev_unlock_ops(dev);
+
return err;
}
@@ -3423,6 +3465,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
err = -ENODEV;
rtnl_nets_unlock(&rtnl_nets);
+ rtnl_nets_destroy(&rtnl_nets);
errout:
return err;
}
@@ -3752,7 +3795,13 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
struct netlink_ext_ack *extack)
{
unsigned char name_assign_type = NET_NAME_USER;
- struct net *net = sock_net(skb->sk);
+ struct rtnl_newlink_params params = {
+ .src_net = sock_net(skb->sk),
+ .link_net = link_net,
+ .peer_net = peer_net,
+ .tb = tb,
+ .data = data,
+ };
u32 portid = NETLINK_CB(skb).portid;
struct net_device *dev;
char ifname[IFNAMSIZ];
@@ -3768,8 +3817,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
name_assign_type = NET_NAME_ENUM;
}
- dev = rtnl_create_link(link_net ? : tgt_net, ifname,
- name_assign_type, ops, tb, extack);
+ dev = rtnl_create_link(tgt_net, ifname, name_assign_type, ops, tb,
+ extack);
if (IS_ERR(dev)) {
err = PTR_ERR(dev);
goto out;
@@ -3777,13 +3826,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
dev->ifindex = ifm->ifi_index;
- if (link_net)
- net = link_net;
- if (peer_net)
- net = peer_net;
-
if (ops->newlink)
- err = ops->newlink(net, dev, tb, data, extack);
+ err = ops->newlink(dev, &params, extack);
else
err = register_netdevice(dev);
if (err < 0) {
@@ -3791,22 +3835,22 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
goto out;
}
+ netdev_lock_ops(dev);
+
err = rtnl_configure_link(dev, ifm, portid, nlh);
if (err < 0)
goto out_unregister;
- if (link_net) {
- err = dev_change_net_namespace(dev, tgt_net, ifname);
- if (err < 0)
- goto out_unregister;
- }
if (tb[IFLA_MASTER]) {
err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
if (err)
goto out_unregister;
}
+
+ netdev_unlock_ops(dev);
out:
return err;
out_unregister:
+ netdev_unlock_ops(dev);
if (ops->newlink) {
LIST_HEAD(list_kill);
@@ -3852,20 +3896,26 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
{
struct nlattr ** const tb = tbs->tb;
struct net *net = sock_net(skb->sk);
+ struct net *device_net;
struct net_device *dev;
struct ifinfomsg *ifm;
bool link_specified;
+ /* When creating, lookup for existing device in target net namespace */
+ device_net = (nlh->nlmsg_flags & NLM_F_CREATE) &&
+ (nlh->nlmsg_flags & NLM_F_EXCL) ?
+ tgt_net : net;
+
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0) {
link_specified = true;
- dev = __dev_get_by_index(net, ifm->ifi_index);
+ dev = __dev_get_by_index(device_net, ifm->ifi_index);
} else if (ifm->ifi_index < 0) {
NL_SET_ERR_MSG(extack, "ifindex can't be negative");
return -EINVAL;
} else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
link_specified = true;
- dev = rtnl_dev_get(net, tb);
+ dev = rtnl_dev_get(device_net, tb);
} else {
link_specified = false;
dev = NULL;
@@ -4765,15 +4815,16 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
int *idx,
struct netdev_hw_addr_list *list)
{
+ struct ndo_fdb_dump_context *ctx = (void *)cb->ctx;
struct netdev_hw_addr *ha;
- int err;
u32 portid, seq;
+ int err;
portid = NETLINK_CB(cb->skb).portid;
seq = cb->nlh->nlmsg_seq;
list_for_each_entry(ha, &list->list, list) {
- if (*idx < cb->args[2])
+ if (*idx < ctx->fdb_idx)
goto skip;
err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0,
@@ -4912,18 +4963,16 @@ static int valid_fdb_dump_legacy(const struct nlmsghdr *nlh,
static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct net_device *dev;
- struct net_device *br_dev = NULL;
- const struct net_device_ops *ops = NULL;
- const struct net_device_ops *cops = NULL;
+ const struct net_device_ops *ops = NULL, *cops = NULL;
+ struct ndo_fdb_dump_context *ctx = (void *)cb->ctx;
+ struct net_device *dev, *br_dev = NULL;
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;
+ int err;
+
+ NL_ASSERT_CTX_FITS(struct ndo_fdb_dump_context);
if (cb->strict_check)
err = valid_fdb_dump_strict(cb->nlh, &br_idx, &brport_idx,
@@ -4942,70 +4991,51 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
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 (netif_is_bridge_port(dev)) {
- br_dev = netdev_master_upper_dev_get(dev);
- cops = br_dev->netdev_ops;
- }
- } else {
- if (dev != br_dev &&
- !netif_is_bridge_port(dev))
- continue;
+ for_each_netdev_dump(net, dev, ctx->ifindex) {
+ if (brport_idx && (dev->ifindex != brport_idx))
+ continue;
- if (br_dev != netdev_master_upper_dev_get(dev) &&
- !netif_is_bridge_master(dev))
- continue;
- cops = ops;
+ if (!br_idx) { /* user did not specify a specific bridge */
+ if (netif_is_bridge_port(dev)) {
+ br_dev = netdev_master_upper_dev_get(dev);
+ cops = br_dev->netdev_ops;
}
+ } else {
+ if (dev != br_dev &&
+ !netif_is_bridge_port(dev))
+ continue;
- if (idx < s_idx)
- goto cont;
+ if (br_dev != netdev_master_upper_dev_get(dev) &&
+ !netif_is_bridge_master(dev))
+ continue;
+ cops = ops;
+ }
- if (netif_is_bridge_port(dev)) {
- if (cops && cops->ndo_fdb_dump) {
- err = cops->ndo_fdb_dump(skb, cb,
- br_dev, dev,
- &fidx);
- if (err == -EMSGSIZE)
- goto out;
- }
+ if (netif_is_bridge_port(dev)) {
+ if (cops && cops->ndo_fdb_dump) {
+ err = cops->ndo_fdb_dump(skb, cb, br_dev, dev,
+ &fidx);
+ if (err == -EMSGSIZE)
+ break;
}
+ }
- 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;
+ 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)
+ break;
- cops = NULL;
+ cops = NULL;
- /* reset fdb offset to 0 for rest of the interfaces */
- cb->args[2] = 0;
- fidx = 0;
-cont:
- idx++;
- }
+ /* reset fdb offset to 0 for rest of the interfaces */
+ ctx->fdb_idx = 0;
+ fidx = 0;
}
-out:
- cb->args[0] = h;
- cb->args[1] = idx;
- cb->args[2] = fidx;
+ ctx->fdb_idx = fidx;
return skb->len;
}