aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c406
-rw-r--r--net/core/devlink.c264
-rw-r--r--net/core/fib_notifier.c95
-rw-r--r--net/core/fib_rules.c23
-rw-r--r--net/core/filter.c4
-rw-r--r--net/core/flow_dissector.c46
-rw-r--r--net/core/net-procfs.c4
-rw-r--r--net/core/pktgen.c1
-rw-r--r--net/core/rtnetlink.c206
-rw-r--r--net/core/sock.c14
-rw-r--r--net/core/xdp.c2
11 files changed, 821 insertions, 244 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index bf3ed413abaf..74f593986524 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -228,6 +228,122 @@ static inline void rps_unlock(struct softnet_data *sd)
#endif
}
+static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev,
+ const char *name)
+{
+ struct netdev_name_node *name_node;
+
+ name_node = kmalloc(sizeof(*name_node), GFP_KERNEL);
+ if (!name_node)
+ return NULL;
+ INIT_HLIST_NODE(&name_node->hlist);
+ name_node->dev = dev;
+ name_node->name = name;
+ return name_node;
+}
+
+static struct netdev_name_node *
+netdev_name_node_head_alloc(struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+
+ name_node = netdev_name_node_alloc(dev, dev->name);
+ if (!name_node)
+ return NULL;
+ INIT_LIST_HEAD(&name_node->list);
+ return name_node;
+}
+
+static void netdev_name_node_free(struct netdev_name_node *name_node)
+{
+ kfree(name_node);
+}
+
+static void netdev_name_node_add(struct net *net,
+ struct netdev_name_node *name_node)
+{
+ hlist_add_head_rcu(&name_node->hlist,
+ dev_name_hash(net, name_node->name));
+}
+
+static void netdev_name_node_del(struct netdev_name_node *name_node)
+{
+ hlist_del_rcu(&name_node->hlist);
+}
+
+static struct netdev_name_node *netdev_name_node_lookup(struct net *net,
+ const char *name)
+{
+ struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *name_node;
+
+ hlist_for_each_entry(name_node, head, hlist)
+ if (!strcmp(name_node->name, name))
+ return name_node;
+ return NULL;
+}
+
+static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net,
+ const char *name)
+{
+ struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *name_node;
+
+ hlist_for_each_entry_rcu(name_node, head, hlist)
+ if (!strcmp(name_node->name, name))
+ return name_node;
+ return NULL;
+}
+
+int netdev_name_node_alt_create(struct net_device *dev, const char *name)
+{
+ struct netdev_name_node *name_node;
+ struct net *net = dev_net(dev);
+
+ name_node = netdev_name_node_lookup(net, name);
+ if (name_node)
+ return -EEXIST;
+ name_node = netdev_name_node_alloc(dev, name);
+ if (!name_node)
+ return -ENOMEM;
+ netdev_name_node_add(net, name_node);
+ /* The node that holds dev->name acts as a head of per-device list. */
+ list_add_tail(&name_node->list, &dev->name_node->list);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_name_node_alt_create);
+
+static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
+{
+ list_del(&name_node->list);
+ netdev_name_node_del(name_node);
+ kfree(name_node->name);
+ netdev_name_node_free(name_node);
+}
+
+int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
+{
+ struct netdev_name_node *name_node;
+ struct net *net = dev_net(dev);
+
+ name_node = netdev_name_node_lookup(net, name);
+ if (!name_node)
+ return -ENOENT;
+ __netdev_name_node_alt_destroy(name_node);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_name_node_alt_destroy);
+
+static void netdev_name_node_alt_flush(struct net_device *dev)
+{
+ struct netdev_name_node *name_node, *tmp;
+
+ list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list)
+ __netdev_name_node_alt_destroy(name_node);
+}
+
/* Device list insertion */
static void list_netdevice(struct net_device *dev)
{
@@ -237,7 +353,7 @@ static void list_netdevice(struct net_device *dev)
write_lock_bh(&dev_base_lock);
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
- hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ netdev_name_node_add(net, dev->name_node);
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
@@ -255,7 +371,7 @@ static void unlist_netdevice(struct net_device *dev)
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
- hlist_del_rcu(&dev->name_hlist);
+ netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
@@ -733,14 +849,10 @@ EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
- struct net_device *dev;
- struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *node_name;
- hlist_for_each_entry(dev, head, name_hlist)
- if (!strncmp(dev->name, name, IFNAMSIZ))
- return dev;
-
- return NULL;
+ node_name = netdev_name_node_lookup(net, name);
+ return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);
@@ -758,14 +870,10 @@ EXPORT_SYMBOL(__dev_get_by_name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
- struct net_device *dev;
- struct hlist_head *head = dev_name_hash(net, name);
-
- hlist_for_each_entry_rcu(dev, head, name_hlist)
- if (!strncmp(dev->name, name, IFNAMSIZ))
- return dev;
+ struct netdev_name_node *node_name;
- return NULL;
+ node_name = netdev_name_node_lookup_rcu(net, name);
+ return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);
@@ -1141,8 +1249,8 @@ int dev_alloc_name(struct net_device *dev, const char *name)
}
EXPORT_SYMBOL(dev_alloc_name);
-int dev_get_valid_name(struct net *net, struct net_device *dev,
- const char *name)
+static int dev_get_valid_name(struct net *net, struct net_device *dev,
+ const char *name)
{
BUG_ON(!net);
@@ -1158,7 +1266,6 @@ int dev_get_valid_name(struct net *net, struct net_device *dev,
return 0;
}
-EXPORT_SYMBOL(dev_get_valid_name);
/**
* dev_change_name - change name of a device
@@ -1232,13 +1339,13 @@ rollback:
netdev_adjacent_rename_links(dev, oldname);
write_lock_bh(&dev_base_lock);
- hlist_del_rcu(&dev->name_hlist);
+ netdev_name_node_del(dev->name_node);
write_unlock_bh(&dev_base_lock);
synchronize_rcu();
write_lock_bh(&dev_base_lock);
- hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ netdev_name_node_add(net, dev->name_node);
write_unlock_bh(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
@@ -1617,6 +1724,62 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
return nb->notifier_call(nb, val, &info);
}
+static int call_netdevice_register_notifiers(struct notifier_block *nb,
+ struct net_device *dev)
+{
+ int err;
+
+ err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ return err;
+
+ if (!(dev->flags & IFF_UP))
+ return 0;
+
+ call_netdevice_notifier(nb, NETDEV_UP, dev);
+ return 0;
+}
+
+static void call_netdevice_unregister_notifiers(struct notifier_block *nb,
+ struct net_device *dev)
+{
+ if (dev->flags & IFF_UP) {
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
+ }
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
+}
+
+static int call_netdevice_register_net_notifiers(struct notifier_block *nb,
+ struct net *net)
+{
+ struct net_device *dev;
+ int err;
+
+ for_each_netdev(net, dev) {
+ err = call_netdevice_register_notifiers(nb, dev);
+ if (err)
+ goto rollback;
+ }
+ return 0;
+
+rollback:
+ for_each_netdev_continue_reverse(net, dev)
+ call_netdevice_unregister_notifiers(nb, dev);
+ return err;
+}
+
+static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb,
+ struct net *net)
+{
+ struct net_device *dev;
+
+ for_each_netdev(net, dev)
+ call_netdevice_unregister_notifiers(nb, dev);
+}
+
static int dev_boot_phase = 1;
/**
@@ -1635,8 +1798,6 @@ static int dev_boot_phase = 1;
int register_netdevice_notifier(struct notifier_block *nb)
{
- struct net_device *dev;
- struct net_device *last;
struct net *net;
int err;
@@ -1649,17 +1810,9 @@ int register_netdevice_notifier(struct notifier_block *nb)
if (dev_boot_phase)
goto unlock;
for_each_net(net) {
- for_each_netdev(net, dev) {
- err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
- err = notifier_to_errno(err);
- if (err)
- goto rollback;
-
- if (!(dev->flags & IFF_UP))
- continue;
-
- call_netdevice_notifier(nb, NETDEV_UP, dev);
- }
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err)
+ goto rollback;
}
unlock:
@@ -1668,22 +1821,9 @@ unlock:
return err;
rollback:
- last = dev;
- for_each_net(net) {
- for_each_netdev(net, dev) {
- if (dev == last)
- goto outroll;
+ for_each_net_continue_reverse(net)
+ call_netdevice_unregister_net_notifiers(nb, net);
- if (dev->flags & IFF_UP) {
- call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
- dev);
- call_netdevice_notifier(nb, NETDEV_DOWN, dev);
- }
- call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
- }
- }
-
-outroll:
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
@@ -1734,6 +1874,80 @@ unlock:
EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
+ * register_netdevice_notifier_net - register a per-netns network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
+ *
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
+ */
+
+int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb)
+{
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_register(&net->netdev_chain, nb);
+ if (err)
+ goto unlock;
+ if (dev_boot_phase)
+ goto unlock;
+
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err)
+ goto chain_unregister;
+
+unlock:
+ rtnl_unlock();
+ return err;
+
+chain_unregister:
+ raw_notifier_chain_unregister(&netdev_chain, nb);
+ goto unlock;
+}
+EXPORT_SYMBOL(register_netdevice_notifier_net);
+
+/**
+ * unregister_netdevice_notifier_net - unregister a per-netns
+ * network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
+ *
+ * After unregistering unregister and down device events are synthesized
+ * for all devices on the device list to the removed notifier to remove
+ * the need for special case cleanup code.
+ */
+
+int unregister_netdevice_notifier_net(struct net *net,
+ struct notifier_block *nb)
+{
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
+ if (err)
+ goto unlock;
+
+ call_netdevice_unregister_net_notifiers(nb, net);
+
+unlock:
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(unregister_netdevice_notifier_net);
+
+/**
* call_netdevice_notifiers_info - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @info: notifier information data
@@ -1745,7 +1959,18 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
static int call_netdevice_notifiers_info(unsigned long val,
struct netdev_notifier_info *info)
{
+ struct net *net = dev_net(info->dev);
+ int ret;
+
ASSERT_RTNL();
+
+ /* Run per-netns notifier block chain first, then run the global one.
+ * Hopefully, one day, the global one is going to be removed after
+ * all notifier block registrators get converted to be per-netns.
+ */
+ ret = raw_notifier_call_chain(&net->netdev_chain, val, info);
+ if (ret & NOTIFY_STOP_MASK)
+ return ret;
return raw_notifier_call_chain(&netdev_chain, val, info);
}
@@ -2771,7 +2996,7 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
void netif_schedule_queue(struct netdev_queue *txq)
{
rcu_read_lock();
- if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
+ if (!netif_xmit_stopped(txq)) {
struct Qdisc *q = rcu_dereference(txq->qdisc);
__netif_schedule(q);
@@ -2939,12 +3164,9 @@ int skb_checksum_help(struct sk_buff *skb)
offset += skb->csum_offset;
BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(__sum16))) {
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (ret)
- goto out;
- }
+ ret = skb_ensure_writable(skb, offset + sizeof(__sum16));
+ if (ret)
+ goto out;
*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
@@ -2979,12 +3201,11 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
ret = -EINVAL;
goto out;
}
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(__le32))) {
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (ret)
- goto out;
- }
+
+ ret = skb_ensure_writable(skb, offset + sizeof(__le32));
+ if (ret)
+ goto out;
+
crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
skb->len - start, ~(__u32)0,
crc32c_csum_stub));
@@ -5663,6 +5884,26 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
}
EXPORT_SYMBOL(gro_find_complete_by_type);
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static void gro_normal_list(struct napi_struct *napi)
+{
+ if (!napi->rx_count)
+ return;
+ netif_receive_skb_list_internal(&napi->rx_list);
+ INIT_LIST_HEAD(&napi->rx_list);
+ napi->rx_count = 0;
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+{
+ list_add_tail(&skb->list, &napi->rx_list);
+ if (++napi->rx_count >= gro_normal_batch)
+ gro_normal_list(napi);
+}
+
static void napi_skb_free_stolen_head(struct sk_buff *skb)
{
skb_dst_drop(skb);
@@ -5670,12 +5911,13 @@ static void napi_skb_free_stolen_head(struct sk_buff *skb)
kmem_cache_free(skbuff_head_cache, skb);
}
-static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
+static gro_result_t napi_skb_finish(struct napi_struct *napi,
+ struct sk_buff *skb,
+ gro_result_t ret)
{
switch (ret) {
case GRO_NORMAL:
- if (netif_receive_skb_internal(skb))
- ret = GRO_DROP;
+ gro_normal_one(napi, skb);
break;
case GRO_DROP:
@@ -5707,7 +5949,7 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
skb_gro_reset_offset(skb);
- ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+ ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
trace_napi_gro_receive_exit(ret);
return ret;
@@ -5753,26 +5995,6 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_get_frags);
-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static void gro_normal_list(struct napi_struct *napi)
-{
- if (!napi->rx_count)
- return;
- netif_receive_skb_list_internal(&napi->rx_list);
- INIT_LIST_HEAD(&napi->rx_list);
- napi->rx_count = 0;
-}
-
-/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
- * pass the whole batch up to the stack.
- */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
-{
- list_add_tail(&skb->list, &napi->rx_list);
- if (++napi->rx_count >= gro_normal_batch)
- gro_normal_list(napi);
-}
-
static gro_result_t napi_frags_finish(struct napi_struct *napi,
struct sk_buff *skb,
gro_result_t ret)
@@ -8264,6 +8486,9 @@ static void rollback_registered_many(struct list_head *head)
dev_uc_flush(dev);
dev_mc_flush(dev);
+ netdev_name_node_alt_flush(dev);
+ netdev_name_node_free(dev->name_node);
+
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
@@ -8706,6 +8931,11 @@ int register_netdevice(struct net_device *dev)
if (ret < 0)
goto out;
+ ret = -ENOMEM;
+ dev->name_node = netdev_name_node_head_alloc(dev);
+ if (!dev->name_node)
+ goto out;
+
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
@@ -8827,6 +9057,8 @@ out:
return ret;
err_uninit:
+ if (dev->name_node)
+ netdev_name_node_free(dev->name_node);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
if (dev->priv_destructor)
@@ -9635,6 +9867,8 @@ static int __net_init netdev_init(struct net *net)
if (net->dev_index_head == NULL)
goto err_idx;
+ RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
+
return 0;
err_idx:
diff --git a/net/core/devlink.c b/net/core/devlink.c
index f80151eeaf51..97e9a2246929 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -95,16 +95,25 @@ static LIST_HEAD(devlink_list);
*/
static DEFINE_MUTEX(devlink_mutex);
-static struct net *devlink_net(const struct devlink *devlink)
+struct net *devlink_net(const struct devlink *devlink)
{
return read_pnet(&devlink->_net);
}
+EXPORT_SYMBOL_GPL(devlink_net);
-static void devlink_net_set(struct devlink *devlink, struct net *net)
+static void __devlink_net_set(struct devlink *devlink, struct net *net)
{
write_pnet(&devlink->_net, net);
}
+void devlink_net_set(struct devlink *devlink, struct net *net)
+{
+ if (WARN_ON(devlink->registered))
+ return;
+ __devlink_net_set(devlink, net);
+}
+EXPORT_SYMBOL_GPL(devlink_net_set);
+
static struct devlink *devlink_get_from_attrs(struct net *net,
struct nlattr **attrs)
{
@@ -434,8 +443,16 @@ static void devlink_nl_post_doit(const struct genl_ops *ops,
{
struct devlink *devlink;
- devlink = devlink_get_from_info(info);
- if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
+ /* When devlink changes netns, it would not be found
+ * by devlink_get_from_info(). So try if it is stored first.
+ */
+ if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) {
+ devlink = info->user_ptr[0];
+ } else {
+ devlink = devlink_get_from_info(info);
+ WARN_ON(IS_ERR(devlink));
+ }
+ if (!IS_ERR(devlink) && ~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
mutex_unlock(&devlink->lock);
mutex_unlock(&devlink_mutex);
}
@@ -1035,7 +1052,7 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg,
struct devlink_sb *devlink_sb;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -1058,6 +1075,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -1233,7 +1253,7 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg,
struct devlink_sb *devlink_sb;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -1256,6 +1276,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -1460,7 +1483,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
struct devlink_sb *devlink_sb;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -1485,6 +1508,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -2674,6 +2700,72 @@ devlink_resources_validate(struct devlink *devlink,
return err;
}
+static struct net *devlink_netns_get(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID];
+ struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD];
+ struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID];
+ struct net *net;
+
+ if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) {
+ NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (netns_pid_attr) {
+ net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr));
+ } else if (netns_fd_attr) {
+ net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr));
+ } else if (netns_id_attr) {
+ net = get_net_ns_by_id(sock_net(skb->sk),
+ nla_get_u32(netns_id_attr));
+ if (!net)
+ net = ERR_PTR(-EINVAL);
+ } else {
+ WARN_ON(1);
+ net = ERR_PTR(-EINVAL);
+ }
+ if (IS_ERR(net)) {
+ NL_SET_ERR_MSG(info->extack, "Unknown network namespace");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ put_net(net);
+ return ERR_PTR(-EPERM);
+ }
+ return net;
+}
+
+static void devlink_param_notify(struct devlink *devlink,
+ unsigned int port_index,
+ struct devlink_param_item *param_item,
+ enum devlink_command cmd);
+
+static void devlink_reload_netns_change(struct devlink *devlink,
+ struct net *dest_net)
+{
+ struct devlink_param_item *param_item;
+
+ /* Userspace needs to be notified about devlink objects
+ * removed from original and entering new network namespace.
+ * The rest of the devlink objects are re-created during
+ * reload process so the notifications are generated separatelly.
+ */
+
+ list_for_each_entry(param_item, &devlink->param_list, list)
+ devlink_param_notify(devlink, 0, param_item,
+ DEVLINK_CMD_PARAM_DEL);
+ devlink_notify(devlink, DEVLINK_CMD_DEL);
+
+ __devlink_net_set(devlink, dest_net);
+
+ devlink_notify(devlink, DEVLINK_CMD_NEW);
+ list_for_each_entry(param_item, &devlink->param_list, list)
+ devlink_param_notify(devlink, 0, param_item,
+ DEVLINK_CMD_PARAM_NEW);
+}
+
static bool devlink_reload_supported(struct devlink *devlink)
{
return devlink->ops->reload_down && devlink->ops->reload_up;
@@ -2694,9 +2786,27 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
}
EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
+static int devlink_reload(struct devlink *devlink, struct net *dest_net,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = devlink->ops->reload_down(devlink, !!dest_net, extack);
+ if (err)
+ return err;
+
+ if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
+ devlink_reload_netns_change(devlink, dest_net);
+
+ err = devlink->ops->reload_up(devlink, extack);
+ devlink_reload_failed_set(devlink, !!err);
+ return err;
+}
+
static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
{
struct devlink *devlink = info->user_ptr[0];
+ struct net *dest_net = NULL;
int err;
if (!devlink_reload_supported(devlink))
@@ -2707,11 +2817,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed");
return err;
}
- err = devlink->ops->reload_down(devlink, info->extack);
- if (err)
- return err;
- err = devlink->ops->reload_up(devlink, info->extack);
- devlink_reload_failed_set(devlink, !!err);
+
+ if (info->attrs[DEVLINK_ATTR_NETNS_PID] ||
+ info->attrs[DEVLINK_ATTR_NETNS_FD] ||
+ info->attrs[DEVLINK_ATTR_NETNS_ID]) {
+ dest_net = devlink_netns_get(skb, info);
+ if (IS_ERR(dest_net))
+ return PTR_ERR(dest_net);
+ }
+
+ err = devlink_reload(devlink, dest_net, info->extack);
+
+ if (dest_net)
+ put_net(dest_net);
+
return err;
}
@@ -3155,7 +3274,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -3183,6 +3302,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -3411,7 +3533,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -3444,6 +3566,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
out:
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -3818,29 +3943,19 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
struct netlink_callback *cb)
{
+ const struct genl_dumpit_info *info = genl_dumpit_info(cb);
u64 ret_offset, start_offset, end_offset = 0;
+ struct nlattr **attrs = info->attrs;
struct devlink_region *region;
struct nlattr *chunks_attr;
const char *region_name;
struct devlink *devlink;
- struct nlattr **attrs;
bool dump = true;
void *hdr;
int err;
start_offset = *((u64 *)&cb->args[0]);
- attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL);
- if (!attrs)
- return -ENOMEM;
-
- err = nlmsg_parse_deprecated(cb->nlh,
- GENL_HDRLEN + devlink_nl_family.hdrsize,
- attrs, DEVLINK_ATTR_MAX,
- devlink_nl_family.policy, cb->extack);
- if (err)
- goto out_free;
-
mutex_lock(&devlink_mutex);
devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
if (IS_ERR(devlink)) {
@@ -3917,7 +4032,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
genlmsg_end(skb, hdr);
mutex_unlock(&devlink->lock);
mutex_unlock(&devlink_mutex);
- kfree(attrs);
return skb->len;
@@ -3927,8 +4041,6 @@ out_unlock:
mutex_unlock(&devlink->lock);
out_dev:
mutex_unlock(&devlink_mutex);
-out_free:
- kfree(attrs);
return err;
}
@@ -4066,7 +4178,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
struct devlink *devlink;
int start = cb->args[0];
int idx = 0;
- int err;
+ int err = 0;
mutex_lock(&devlink_mutex);
list_for_each_entry(devlink, &devlink_list, list) {
@@ -4094,6 +4206,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
}
mutex_unlock(&devlink_mutex);
+ if (err != -EMSGSIZE)
+ return err;
+
cb->args[0] = idx;
return msg->len;
}
@@ -4732,14 +4847,17 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update);
static int
devlink_health_reporter_recover(struct devlink_health_reporter *reporter,
- void *priv_ctx)
+ void *priv_ctx, struct netlink_ext_ack *extack)
{
int err;
+ if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY)
+ return 0;
+
if (!reporter->ops->recover)
return -EOPNOTSUPP;
- err = reporter->ops->recover(reporter, priv_ctx);
+ err = reporter->ops->recover(reporter, priv_ctx, extack);
if (err)
return err;
@@ -4760,7 +4878,8 @@ devlink_health_dump_clear(struct devlink_health_reporter *reporter)
}
static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
- void *priv_ctx)
+ void *priv_ctx,
+ struct netlink_ext_ack *extack)
{
int err;
@@ -4781,7 +4900,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
goto dump_err;
err = reporter->ops->dump(reporter, reporter->dump_fmsg,
- priv_ctx);
+ priv_ctx, extack);
if (err)
goto dump_err;
@@ -4828,11 +4947,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
mutex_lock(&reporter->dump_lock);
/* store current dump of current error, for later analysis */
- devlink_health_do_dump(reporter, priv_ctx);
+ devlink_health_do_dump(reporter, priv_ctx, NULL);
mutex_unlock(&reporter->dump_lock);
if (reporter->auto_recover)
- return devlink_health_reporter_recover(reporter, priv_ctx);
+ return devlink_health_reporter_recover(reporter,
+ priv_ctx, NULL);
return 0;
}
@@ -4867,21 +4987,10 @@ devlink_health_reporter_get_from_info(struct devlink *devlink,
static struct devlink_health_reporter *
devlink_health_reporter_get_from_cb(struct netlink_callback *cb)
{
+ const struct genl_dumpit_info *info = genl_dumpit_info(cb);
struct devlink_health_reporter *reporter;
+ struct nlattr **attrs = info->attrs;
struct devlink *devlink;
- struct nlattr **attrs;
- int err;
-
- attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL);
- if (!attrs)
- return NULL;
-
- err = nlmsg_parse_deprecated(cb->nlh,
- GENL_HDRLEN + devlink_nl_family.hdrsize,
- attrs, DEVLINK_ATTR_MAX,
- devlink_nl_family.policy, cb->extack);
- if (err)
- goto free;
mutex_lock(&devlink_mutex);
devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
@@ -4890,12 +4999,9 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb)
reporter = devlink_health_reporter_get_from_attrs(devlink, attrs);
mutex_unlock(&devlink_mutex);
- kfree(attrs);
return reporter;
unlock:
mutex_unlock(&devlink_mutex);
-free:
- kfree(attrs);
return NULL;
}
@@ -5084,7 +5190,7 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
if (!reporter)
return -EINVAL;
- err = devlink_health_reporter_recover(reporter, NULL);
+ err = devlink_health_reporter_recover(reporter, NULL, info->extack);
devlink_health_reporter_put(reporter);
return err;
@@ -5117,7 +5223,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb,
if (err)
goto out;
- err = reporter->ops->diagnose(reporter, fmsg);
+ err = reporter->ops->diagnose(reporter, fmsg, info->extack);
if (err)
goto out;
@@ -5152,7 +5258,7 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb,
}
mutex_lock(&reporter->dump_lock);
if (!start) {
- err = devlink_health_do_dump(reporter, NULL);
+ err = devlink_health_do_dump(reporter, NULL, cb->extack);
if (err)
goto unlock;
cb->args[1] = reporter->dump_ts;
@@ -5793,6 +5899,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 },
};
static const struct genl_ops devlink_nl_ops[] = {
@@ -6023,7 +6132,8 @@ static const struct genl_ops devlink_nl_ops[] = {
},
{
.cmd = DEVLINK_CMD_REGION_READ,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = devlink_nl_cmd_region_read_dumpit,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
@@ -6071,7 +6181,8 @@ static const struct genl_ops devlink_nl_ops[] = {
},
{
.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+ .validate = GENL_DONT_VALIDATE_STRICT |
+ GENL_DONT_VALIDATE_DUMP_STRICT,
.dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit,
.flags = GENL_ADMIN_PERM,
.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -6155,7 +6266,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
if (!devlink)
return NULL;
devlink->ops = ops;
- devlink_net_set(devlink, &init_net);
+ __devlink_net_set(devlink, &init_net);
INIT_LIST_HEAD(&devlink->port_list);
INIT_LIST_HEAD(&devlink->sb_list);
INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
@@ -6181,6 +6292,7 @@ int devlink_register(struct devlink *devlink, struct device *dev)
{
mutex_lock(&devlink_mutex);
devlink->dev = dev;
+ devlink->registered = true;
list_add_tail(&devlink->list, &devlink_list);
devlink_notify(devlink, DEVLINK_CMD_NEW);
mutex_unlock(&devlink_mutex);
@@ -8060,9 +8172,43 @@ int devlink_compat_switch_id_get(struct net_device *dev,
return 0;
}
+static void __net_exit devlink_pernet_pre_exit(struct net *net)
+{
+ struct devlink *devlink;
+ int err;
+
+ /* In case network namespace is getting destroyed, reload
+ * all devlink instances from this namespace into init_net.
+ */
+ mutex_lock(&devlink_mutex);
+ list_for_each_entry(devlink, &devlink_list, list) {
+ if (net_eq(devlink_net(devlink), net)) {
+ if (WARN_ON(!devlink_reload_supported(devlink)))
+ continue;
+ err = devlink_reload(devlink, &init_net, NULL);
+ if (err)
+ pr_warn("Failed to reload devlink instance into init_net\n");
+ }
+ }
+ mutex_unlock(&devlink_mutex);
+}
+
+static struct pernet_operations devlink_pernet_ops __net_initdata = {
+ .pre_exit = devlink_pernet_pre_exit,
+};
+
static int __init devlink_init(void)
{
- return genl_register_family(&devlink_nl_family);
+ int err;
+
+ err = genl_register_family(&devlink_nl_family);
+ if (err)
+ goto out;
+ err = register_pernet_subsys(&devlink_pernet_ops);
+
+out:
+ WARN_ON(err);
+ return err;
}
subsys_initcall(devlink_init);
diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c
index 470a606d5e8d..fc96259807b6 100644
--- a/net/core/fib_notifier.c
+++ b/net/core/fib_notifier.c
@@ -12,17 +12,15 @@ static unsigned int fib_notifier_net_id;
struct fib_notifier_net {
struct list_head fib_notifier_ops;
+ struct atomic_notifier_head fib_chain;
};
-static ATOMIC_NOTIFIER_HEAD(fib_chain);
-
-int call_fib_notifier(struct notifier_block *nb, struct net *net,
+int call_fib_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
struct fib_notifier_info *info)
{
int err;
- info->net = net;
err = nb->notifier_call(nb, event_type, info);
return notifier_to_errno(err);
}
@@ -31,106 +29,100 @@ EXPORT_SYMBOL(call_fib_notifier);
int call_fib_notifiers(struct net *net, enum fib_event_type event_type,
struct fib_notifier_info *info)
{
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
int err;
- info->net = net;
- err = atomic_notifier_call_chain(&fib_chain, event_type, info);
+ err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info);
return notifier_to_errno(err);
}
EXPORT_SYMBOL(call_fib_notifiers);
-static unsigned int fib_seq_sum(void)
+static unsigned int fib_seq_sum(struct net *net)
{
- struct fib_notifier_net *fn_net;
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
struct fib_notifier_ops *ops;
unsigned int fib_seq = 0;
- struct net *net;
rtnl_lock();
- down_read(&net_rwsem);
- for_each_net(net) {
- fn_net = net_generic(net, fib_notifier_net_id);
- rcu_read_lock();
- list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) {
- if (!try_module_get(ops->owner))
- continue;
- fib_seq += ops->fib_seq_read(net);
- module_put(ops->owner);
- }
- rcu_read_unlock();
+ rcu_read_lock();
+ list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) {
+ if (!try_module_get(ops->owner))
+ continue;
+ fib_seq += ops->fib_seq_read(net);
+ module_put(ops->owner);
}
- up_read(&net_rwsem);
+ rcu_read_unlock();
rtnl_unlock();
return fib_seq;
}
-static int fib_net_dump(struct net *net, struct notifier_block *nb)
+static int fib_net_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
struct fib_notifier_ops *ops;
+ int err = 0;
+ rcu_read_lock();
list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) {
- int err;
-
if (!try_module_get(ops->owner))
continue;
- err = ops->fib_dump(net, nb);
+ err = ops->fib_dump(net, nb, extack);
module_put(ops->owner);
if (err)
- return err;
+ goto unlock;
}
- return 0;
+unlock:
+ rcu_read_unlock();
+
+ return err;
}
-static bool fib_dump_is_consistent(struct notifier_block *nb,
+static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb,
void (*cb)(struct notifier_block *nb),
unsigned int fib_seq)
{
- atomic_notifier_chain_register(&fib_chain, nb);
- if (fib_seq == fib_seq_sum())
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
+
+ atomic_notifier_chain_register(&fn_net->fib_chain, nb);
+ if (fib_seq == fib_seq_sum(net))
return true;
- atomic_notifier_chain_unregister(&fib_chain, nb);
+ atomic_notifier_chain_unregister(&fn_net->fib_chain, nb);
if (cb)
cb(nb);
return false;
}
#define FIB_DUMP_MAX_RETRIES 5
-int register_fib_notifier(struct notifier_block *nb,
- void (*cb)(struct notifier_block *nb))
+int register_fib_notifier(struct net *net, struct notifier_block *nb,
+ void (*cb)(struct notifier_block *nb),
+ struct netlink_ext_ack *extack)
{
int retries = 0;
int err;
do {
- unsigned int fib_seq = fib_seq_sum();
- struct net *net;
-
- rcu_read_lock();
- for_each_net_rcu(net) {
- err = fib_net_dump(net, nb);
- if (err)
- goto err_fib_net_dump;
- }
- rcu_read_unlock();
-
- if (fib_dump_is_consistent(nb, cb, fib_seq))
+ unsigned int fib_seq = fib_seq_sum(net);
+
+ err = fib_net_dump(net, nb, extack);
+ if (err)
+ return err;
+
+ if (fib_dump_is_consistent(net, nb, cb, fib_seq))
return 0;
} while (++retries < FIB_DUMP_MAX_RETRIES);
return -EBUSY;
-
-err_fib_net_dump:
- rcu_read_unlock();
- return err;
}
EXPORT_SYMBOL(register_fib_notifier);
-int unregister_fib_notifier(struct notifier_block *nb)
+int unregister_fib_notifier(struct net *net, struct notifier_block *nb)
{
- return atomic_notifier_chain_unregister(&fib_chain, nb);
+ struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
+
+ return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb);
}
EXPORT_SYMBOL(unregister_fib_notifier);
@@ -181,6 +173,7 @@ static int __net_init fib_notifier_net_init(struct net *net)
struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id);
INIT_LIST_HEAD(&fn_net->fib_notifier_ops);
+ ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain);
return 0;
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index dd220ce7ca7a..3e7e15278c46 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -321,16 +321,18 @@ out:
}
EXPORT_SYMBOL_GPL(fib_rules_lookup);
-static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net,
+static int call_fib_rule_notifier(struct notifier_block *nb,
enum fib_event_type event_type,
- struct fib_rule *rule, int family)
+ struct fib_rule *rule, int family,
+ struct netlink_ext_ack *extack)
{
struct fib_rule_notifier_info info = {
.info.family = family,
+ .info.extack = extack,
.rule = rule,
};
- return call_fib_notifier(nb, net, event_type, &info.info);
+ return call_fib_notifier(nb, event_type, &info.info);
}
static int call_fib_rule_notifiers(struct net *net,
@@ -350,20 +352,25 @@ static int call_fib_rule_notifiers(struct net *net,
}
/* Called with rcu_read_lock() */
-int fib_rules_dump(struct net *net, struct notifier_block *nb, int family)
+int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
+ struct netlink_ext_ack *extack)
{
struct fib_rules_ops *ops;
struct fib_rule *rule;
+ int err = 0;
ops = lookup_rules_ops(net, family);
if (!ops)
return -EAFNOSUPPORT;
- list_for_each_entry_rcu(rule, &ops->rules_list, list)
- call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule,
- family);
+ list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+ err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD,
+ rule, family, extack);
+ if (err)
+ break;
+ }
rules_ops_put(ops);
- return 0;
+ return err;
}
EXPORT_SYMBOL_GPL(fib_rules_dump);
diff --git a/net/core/filter.c b/net/core/filter.c
index 3fed5755494b..72b6af6b089e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2245,7 +2245,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
* account for the headroom.
*/
bytes_sg_total = start - offset + bytes;
- if (!msg->sg.copy[i] && bytes_sg_total <= len)
+ if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len)
goto out;
/* At this point we need to linearize multiple scatterlist
@@ -2450,7 +2450,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
/* Place newly allocated data buffer */
sk_mem_charge(msg->sk, len);
msg->sg.size += len;
- msg->sg.copy[new] = false;
+ __clear_bit(new, &msg->sg.copy);
sg_set_page(&msg->sg.data[new], page, len + copy, 0);
if (rsge.length) {
get_page(sg_page(&rsge));
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 7c09d87d3269..dbf502c18656 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -114,19 +114,50 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
{
struct bpf_prog *attached;
struct net *net;
+ int ret = 0;
net = current->nsproxy->net_ns;
mutex_lock(&flow_dissector_mutex);
+
+ if (net == &init_net) {
+ /* BPF flow dissector in the root namespace overrides
+ * any per-net-namespace one. When attaching to root,
+ * make sure we don't have any BPF program attached
+ * to the non-root namespaces.
+ */
+ struct net *ns;
+
+ for_each_net(ns) {
+ if (ns == &init_net)
+ continue;
+ if (rcu_access_pointer(ns->flow_dissector_prog)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+ } else {
+ /* Make sure root flow dissector is not attached
+ * when attaching to the non-root namespace.
+ */
+ if (rcu_access_pointer(init_net.flow_dissector_prog)) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
+
attached = rcu_dereference_protected(net->flow_dissector_prog,
lockdep_is_held(&flow_dissector_mutex));
- if (attached) {
- /* Only one BPF program can be attached at a time */
- mutex_unlock(&flow_dissector_mutex);
- return -EEXIST;
+ if (attached == prog) {
+ /* The same program cannot be attached twice */
+ ret = -EINVAL;
+ goto out;
}
rcu_assign_pointer(net->flow_dissector_prog, prog);
+ if (attached)
+ bpf_prog_put(attached);
+out:
mutex_unlock(&flow_dissector_mutex);
- return 0;
+ return ret;
}
int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
@@ -910,7 +941,10 @@ bool __skb_flow_dissect(const struct net *net,
WARN_ON_ONCE(!net);
if (net) {
rcu_read_lock();
- attached = rcu_dereference(net->flow_dissector_prog);
+ attached = rcu_dereference(init_net.flow_dissector_prog);
+
+ if (!attached)
+ attached = rcu_dereference(net->flow_dissector_prog);
if (attached) {
struct bpf_flow_keys flow_keys;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 36347933ec3a..6bbd06f7dc7d 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -20,8 +20,8 @@ static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff
struct hlist_head *h;
unsigned int count = 0, offset = get_offset(*pos);
- h = &net->dev_name_head[get_bucket(*pos)];
- hlist_for_each_entry_rcu(dev, h, name_hlist) {
+ h = &net->dev_index_head[get_bucket(*pos)];
+ hlist_for_each_entry_rcu(dev, h, index_hlist) {
if (++count == offset)
return dev;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 48b1e429857c..294bfcf0ce0e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3404,7 +3404,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
HARD_TX_LOCK(odev, txq, smp_processor_id());
if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) {
- ret = NETDEV_TX_BUSY;
pkt_dev->last_ok = 0;
goto unlock;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1ee6460f8275..49fa910b58af 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -980,6 +980,19 @@ static size_t rtnl_xdp_size(void)
return xdp_size;
}
+static size_t rtnl_prop_list_size(const struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+ size_t size;
+
+ if (list_empty(&dev->name_node->list))
+ return 0;
+ size = nla_total_size(0);
+ list_for_each_entry(name_node, &dev->name_node->list, list)
+ size += nla_total_size(ALTIFNAMSIZ);
+ return size;
+}
+
static noinline size_t if_nlmsg_size(const struct net_device *dev,
u32 ext_filter_mask)
{
@@ -1027,6 +1040,7 @@ 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)
+ 0;
}
@@ -1584,6 +1598,42 @@ static int rtnl_fill_link_af(struct sk_buff *skb,
return 0;
}
+static int rtnl_fill_alt_ifnames(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+ int count = 0;
+
+ list_for_each_entry(name_node, &dev->name_node->list, list) {
+ if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name))
+ return -EMSGSIZE;
+ count++;
+ }
+ return count;
+}
+
+static int rtnl_fill_prop_list(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct nlattr *prop_list;
+ int ret;
+
+ prop_list = nla_nest_start(skb, IFLA_PROP_LIST);
+ if (!prop_list)
+ return -EMSGSIZE;
+
+ ret = rtnl_fill_alt_ifnames(skb, dev);
+ if (ret <= 0)
+ goto nest_cancel;
+
+ nla_nest_end(skb, prop_list);
+ return 0;
+
+nest_cancel:
+ nla_nest_cancel(skb, prop_list);
+ return ret;
+}
+
static int rtnl_fill_ifinfo(struct sk_buff *skb,
struct net_device *dev, struct net *src_net,
int type, u32 pid, u32 seq, u32 change,
@@ -1697,6 +1747,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure_rcu;
rcu_read_unlock();
+ if (rtnl_fill_prop_list(skb, dev))
+ goto nla_put_failure;
+
nlmsg_end(skb, nlh);
return 0;
@@ -1750,6 +1803,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 },
[IFLA_MIN_MTU] = { .type = NLA_U32 },
[IFLA_MAX_MTU] = { .type = NLA_U32 },
+ [IFLA_PROP_LIST] = { .type = NLA_NESTED },
+ [IFLA_ALT_IFNAME] = { .type = NLA_STRING,
+ .len = ALTIFNAMSIZ - 1 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2722,6 +2778,26 @@ errout:
return err;
}
+static struct net_device *rtnl_dev_get(struct net *net,
+ struct nlattr *ifname_attr,
+ struct nlattr *altifname_attr,
+ char *ifname)
+{
+ char buffer[ALTIFNAMSIZ];
+
+ if (!ifname) {
+ ifname = buffer;
+ if (ifname_attr)
+ nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+ else if (altifname_attr)
+ nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+ else
+ return NULL;
+ }
+
+ return __dev_get_by_name(net, ifname);
+}
+
static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -2750,8 +2826,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
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_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname);
else
goto errout;
@@ -2824,7 +2900,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *tgt_net = net;
struct net_device *dev = NULL;
struct ifinfomsg *ifm;
- char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
int err;
int netnsid = -1;
@@ -2838,9 +2913,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
- if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
-
if (tb[IFLA_TARGET_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid);
@@ -2852,8 +2924,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(tgt_net, ifname);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, tb[IFLA_IFNAME],
+ tb[IFLA_ALT_IFNAME], NULL);
else if (tb[IFLA_GROUP])
err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
else
@@ -3024,12 +3097,10 @@ replay:
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;
- }
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname);
+ else
+ dev = NULL;
if (dev) {
master_dev = netdev_master_upper_dev_get(dev);
@@ -3291,6 +3362,7 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
switch (i) {
case IFLA_IFNAME:
+ case IFLA_ALT_IFNAME:
case IFLA_EXT_MASK:
case IFLA_TARGET_NETNSID:
break;
@@ -3309,7 +3381,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct net *tgt_net = net;
struct ifinfomsg *ifm;
- char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
struct net_device *dev = NULL;
struct sk_buff *nskb;
@@ -3332,9 +3403,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
return PTR_ERR(tgt_net);
}
- 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]);
@@ -3342,8 +3410,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(tgt_net, ifname);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(tgt_net, tb[IFLA_IFNAME],
+ tb[IFLA_ALT_IFNAME], NULL);
else
goto out;
@@ -3373,6 +3442,100 @@ out:
return err;
}
+static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr,
+ bool *changed, struct netlink_ext_ack *extack)
+{
+ char *alt_ifname;
+ int err;
+
+ err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack);
+ if (err)
+ return err;
+
+ alt_ifname = nla_data(attr);
+ if (cmd == RTM_NEWLINKPROP) {
+ alt_ifname = kstrdup(alt_ifname, GFP_KERNEL);
+ if (!alt_ifname)
+ return -ENOMEM;
+ err = netdev_name_node_alt_create(dev, alt_ifname);
+ if (err) {
+ kfree(alt_ifname);
+ return err;
+ }
+ } else if (cmd == RTM_DELLINKPROP) {
+ err = netdev_name_node_alt_destroy(dev, alt_ifname);
+ if (err)
+ return err;
+ } else {
+ WARN_ON(1);
+ return 0;
+ }
+
+ *changed = true;
+ return 0;
+}
+
+static int rtnl_linkprop(int cmd, 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];
+ struct net_device *dev;
+ struct ifinfomsg *ifm;
+ bool changed = false;
+ struct nlattr *attr;
+ int err, rem;
+
+ err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
+ if (err)
+ return err;
+
+ err = rtnl_ensure_unique_netns(tb, extack, true);
+ if (err)
+ return err;
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->ifi_index > 0)
+ dev = __dev_get_by_index(net, ifm->ifi_index);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+ dev = rtnl_dev_get(net, tb[IFLA_IFNAME],
+ tb[IFLA_ALT_IFNAME], NULL);
+ else
+ return -EINVAL;
+
+ if (!dev)
+ return -ENODEV;
+
+ if (!tb[IFLA_PROP_LIST])
+ return 0;
+
+ nla_for_each_nested(attr, tb[IFLA_PROP_LIST], rem) {
+ switch (nla_type(attr)) {
+ case IFLA_ALT_IFNAME:
+ err = rtnl_alt_ifname(cmd, dev, attr, &changed, extack);
+ if (err)
+ return err;
+ break;
+ }
+ }
+
+ if (changed)
+ netdev_state_change(dev);
+ return 0;
+}
+
+static int rtnl_newlinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ return rtnl_linkprop(RTM_NEWLINKPROP, skb, nlh, extack);
+}
+
+static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack);
+}
+
static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
@@ -5331,6 +5494,9 @@ void __init rtnetlink_init(void)
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_UNSPEC, RTM_NEWLINKPROP, rtnl_newlinkprop, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_DELLINKPROP, rtnl_dellinkprop, NULL, 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, rtnl_fdb_get, rtnl_fdb_dump, 0);
diff --git a/net/core/sock.c b/net/core/sock.c
index a515392ba84b..5cb567e36f5e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -333,7 +333,6 @@ EXPORT_SYMBOL(__sk_backlog_rcv);
static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
{
struct __kernel_sock_timeval tv;
- int size;
if (timeo == MAX_SCHEDULE_TIMEOUT) {
tv.tv_sec = 0;
@@ -354,13 +353,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
old_tv.tv_sec = tv.tv_sec;
old_tv.tv_usec = tv.tv_usec;
*(struct __kernel_old_timeval *)optval = old_tv;
- size = sizeof(old_tv);
- } else {
- *(struct __kernel_sock_timeval *)optval = tv;
- size = sizeof(tv);
+ return sizeof(old_tv);
}
- return size;
+ *(struct __kernel_sock_timeval *)optval = tv;
+ return sizeof(tv);
}
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval)
@@ -687,7 +684,8 @@ out:
return ret;
}
-static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
+static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit,
+ int valbool)
{
if (valbool)
sock_set_flag(sk, bit);
@@ -3042,7 +3040,7 @@ int sock_gettstamp(struct socket *sock, void __user *userstamp,
}
EXPORT_SYMBOL(sock_gettstamp);
-void sock_enable_timestamp(struct sock *sk, int flag)
+void sock_enable_timestamp(struct sock *sk, enum sock_flags flag)
{
if (!sock_flag(sk, flag)) {
unsigned long previous_flags = sk->sk_flags;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index d7bf62ffbb5e..20781ad5f9c3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -386,7 +386,7 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
/* XDP RX runs under NAPI protection, and in different delivery error
* scenarios (e.g. queue full), it is possible to return the xdp_frame
- * while still leveraging this protection. The @napi_direct boolian
+ * while still leveraging this protection. The @napi_direct boolean
* is used for those calls sites. Thus, allowing for faster recycling
* of xdp_frames/pages in those cases.
*/
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.