summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c622
-rw-r--r--net/core/dev_addr_lists.c4
-rw-r--r--net/core/drop_monitor.c15
-rw-r--r--net/core/ethtool.c3
-rw-r--r--net/core/fib_rules.c3
-rw-r--r--net/core/filter.c8
-rw-r--r--net/core/flow_dissector.c81
-rw-r--r--net/core/iovec.c5
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/net-sysfs.c16
-rw-r--r--net/core/netpoll.c31
-rw-r--r--net/core/netprio_cgroup.c3
-rw-r--r--net/core/rtnetlink.c12
-rw-r--r--net/core/secure_seq.c19
-rw-r--r--net/core/skbuff.c219
-rw-r--r--net/core/sock.c46
-rw-r--r--net/core/utils.c49
18 files changed, 796 insertions, 344 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index af814e764206..a16ed7bbe376 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -577,7 +577,7 @@ EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
/**
* zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
* @skb: buffer to copy
- * @from: io vector to copy to
+ * @from: io vector to copy from
* @offset: offset in the io vector to start copying from
* @count: amount of vectors to copy to buffer from
*
diff --git a/net/core/dev.c b/net/core/dev.c
index 5c713f2239cc..ba3b7ea5ebb3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -131,6 +131,7 @@
#include <linux/static_key.h>
#include <linux/hashtable.h>
#include <linux/vmalloc.h>
+#include <linux/if_macvlan.h>
#include "net-sysfs.h"
@@ -1203,7 +1204,7 @@ void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
call_netdevice_notifiers(NETDEV_CHANGE, dev);
- rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
}
}
EXPORT_SYMBOL(netdev_state_change);
@@ -1293,7 +1294,7 @@ int dev_open(struct net_device *dev)
if (ret < 0)
return ret;
- rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
call_netdevice_notifiers(NETDEV_UP, dev);
return ret;
@@ -1307,7 +1308,7 @@ static int __dev_close_many(struct list_head *head)
ASSERT_RTNL();
might_sleep();
- list_for_each_entry(dev, head, unreg_list) {
+ list_for_each_entry(dev, head, close_list) {
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1323,7 +1324,7 @@ static int __dev_close_many(struct list_head *head)
dev_deactivate_many(head);
- list_for_each_entry(dev, head, unreg_list) {
+ list_for_each_entry(dev, head, close_list) {
const struct net_device_ops *ops = dev->netdev_ops;
/*
@@ -1351,7 +1352,7 @@ static int __dev_close(struct net_device *dev)
/* Temporarily disable netpoll until the interface is down */
netpoll_rx_disable(dev);
- list_add(&dev->unreg_list, &single);
+ list_add(&dev->close_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
@@ -1362,21 +1363,20 @@ static int __dev_close(struct net_device *dev)
static int dev_close_many(struct list_head *head)
{
struct net_device *dev, *tmp;
- LIST_HEAD(tmp_list);
- list_for_each_entry_safe(dev, tmp, head, unreg_list)
+ /* Remove the devices that don't need to be closed */
+ list_for_each_entry_safe(dev, tmp, head, close_list)
if (!(dev->flags & IFF_UP))
- list_move(&dev->unreg_list, &tmp_list);
+ list_del_init(&dev->close_list);
__dev_close_many(head);
- list_for_each_entry(dev, head, unreg_list) {
- rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
+ list_for_each_entry_safe(dev, tmp, head, close_list) {
+ rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
call_netdevice_notifiers(NETDEV_DOWN, dev);
+ list_del_init(&dev->close_list);
}
- /* rollback_registered_many needs the complete original list */
- list_splice(&tmp_list, head);
return 0;
}
@@ -1397,7 +1397,7 @@ int dev_close(struct net_device *dev)
/* Block netpoll rx while the interface is going down */
netpoll_rx_disable(dev);
- list_add(&dev->unreg_list, &single);
+ list_add(&dev->close_list, &single);
dev_close_many(&single);
list_del(&single);
@@ -1425,6 +1425,10 @@ void dev_disable_lro(struct net_device *dev)
if (is_vlan_dev(dev))
dev = vlan_dev_real_dev(dev);
+ /* the same for macvlan devices */
+ if (netif_is_macvlan(dev))
+ dev = macvlan_dev_real_dev(dev);
+
dev->wanted_features &= ~NETIF_F_LRO;
netdev_update_features(dev);
@@ -1691,13 +1695,9 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
kfree_skb(skb);
return NET_RX_DROP;
}
- skb->protocol = eth_type_trans(skb, dev);
- /* eth_type_trans() can set pkt_type.
- * call skb_scrub_packet() after it to clear pkt_type _after_ calling
- * eth_type_trans().
- */
skb_scrub_packet(skb, true);
+ skb->protocol = eth_type_trans(skb, dev);
return netif_rx(skb);
}
@@ -1917,7 +1917,8 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
return new_map;
}
-int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index)
+int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
+ u16 index)
{
struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
struct xps_map *map, *new_map;
@@ -2377,6 +2378,8 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
}
SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
+ SKB_GSO_CB(skb)->encap_level = 0;
+
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
@@ -2536,7 +2539,7 @@ static inline int skb_needs_linearize(struct sk_buff *skb,
}
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq)
+ struct netdev_queue *txq, void *accel_priv)
{
const struct net_device_ops *ops = dev->netdev_ops;
int rc = NETDEV_TX_OK;
@@ -2602,9 +2605,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
- rc = ops->ndo_start_xmit(skb, dev);
+ if (accel_priv)
+ rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
+ else
+ rc = ops->ndo_start_xmit(skb, dev);
+
trace_net_dev_xmit(skb, rc, dev, skb_len);
- if (rc == NETDEV_TX_OK)
+ if (rc == NETDEV_TX_OK && txq)
txq_trans_update(txq);
return rc;
}
@@ -2620,7 +2627,10 @@ gso:
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
- rc = ops->ndo_start_xmit(nskb, dev);
+ if (accel_priv)
+ rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
+ else
+ rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
@@ -2645,6 +2655,7 @@ out_kfree_skb:
out:
return rc;
}
+EXPORT_SYMBOL_GPL(dev_hard_start_xmit);
static void qdisc_pkt_len_init(struct sk_buff *skb)
{
@@ -2852,7 +2863,7 @@ int dev_queue_xmit(struct sk_buff *skb)
if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
- rc = dev_hard_start_xmit(skb, dev, txq);
+ rc = dev_hard_start_xmit(skb, dev, txq, NULL);
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
@@ -4373,42 +4384,40 @@ struct netdev_adjacent {
/* upper master flag, there can only be one master device per list */
bool master;
- /* indicates that this dev is our first-level lower/upper device */
- bool neighbour;
-
/* counter for the number of times this device was added to us */
u16 ref_nr;
+ /* private field for the users */
+ void *private;
+
struct list_head list;
struct rcu_head rcu;
};
-static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
- struct net_device *adj_dev,
- bool upper)
+static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *adj_list)
{
struct netdev_adjacent *adj;
- struct list_head *dev_list;
-
- dev_list = upper ? &dev->upper_dev_list : &dev->lower_dev_list;
- list_for_each_entry(adj, dev_list, list) {
+ list_for_each_entry_rcu(adj, adj_list, list) {
if (adj->dev == adj_dev)
return adj;
}
return NULL;
}
-static inline struct netdev_adjacent *__netdev_find_upper(struct net_device *dev,
- struct net_device *udev)
+static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *adj_list)
{
- return __netdev_find_adj(dev, udev, true);
-}
+ struct netdev_adjacent *adj;
-static inline struct netdev_adjacent *__netdev_find_lower(struct net_device *dev,
- struct net_device *ldev)
-{
- return __netdev_find_adj(dev, ldev, false);
+ list_for_each_entry(adj, adj_list, list) {
+ if (adj->dev == adj_dev)
+ return adj;
+ }
+ return NULL;
}
/**
@@ -4425,7 +4434,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return __netdev_find_upper(dev, upper_dev);
+ return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -4440,7 +4449,7 @@ bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
- return !list_empty(&dev->upper_dev_list);
+ return !list_empty(&dev->all_adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_any_upper_dev);
@@ -4457,10 +4466,10 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
ASSERT_RTNL();
- if (list_empty(&dev->upper_dev_list))
+ if (list_empty(&dev->adj_list.upper))
return NULL;
- upper = list_first_entry(&dev->upper_dev_list,
+ upper = list_first_entry(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (likely(upper->master))
return upper->dev;
@@ -4468,15 +4477,26 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
-/* netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+void *netdev_adjacent_get_private(struct list_head *adj_list)
+{
+ struct netdev_adjacent *adj;
+
+ adj = list_entry(adj_list, struct netdev_adjacent, list);
+
+ return adj->private;
+}
+EXPORT_SYMBOL(netdev_adjacent_get_private);
+
+/**
+ * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
* @dev: device
* @iter: list_head ** of the current position
*
* Gets the next device from the dev's upper list, starting from iter
* position. The caller must hold RCU read lock.
*/
-struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
- struct list_head **iter)
+struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
{
struct netdev_adjacent *upper;
@@ -4484,14 +4504,71 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
- if (&upper->list == &dev->upper_dev_list)
+ if (&upper->list == &dev->all_adj_list.upper)
return NULL;
*iter = &upper->list;
return upper->dev;
}
-EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
+
+/**
+ * netdev_lower_get_next_private - Get the next ->private from the
+ * lower neighbour list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent->private from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold either hold the
+ * RTNL lock or its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next_private(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry(*iter, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ if (iter)
+ *iter = lower->list.next;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_get_next_private);
+
+/**
+ * netdev_lower_get_next_private_rcu - Get the next ->private from the
+ * lower neighbour list, RCU
+ * variant
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent->private from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RCU read lock.
+ */
+void *netdev_lower_get_next_private_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ if (iter)
+ *iter = &lower->list;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
* netdev_master_upper_dev_get_rcu - Get master upper device
@@ -4504,7 +4581,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
{
struct netdev_adjacent *upper;
- upper = list_first_or_null_rcu(&dev->upper_dev_list,
+ upper = list_first_or_null_rcu(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (upper && likely(upper->master))
return upper->dev;
@@ -4514,15 +4591,16 @@ EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
- bool neighbour, bool master,
- bool upper)
+ struct list_head *dev_list,
+ void *private, bool master)
{
struct netdev_adjacent *adj;
+ char linkname[IFNAMSIZ+7];
+ int ret;
- adj = __netdev_find_adj(dev, adj_dev, upper);
+ adj = __netdev_find_adj(dev, adj_dev, dev_list);
if (adj) {
- BUG_ON(neighbour);
adj->ref_nr++;
return 0;
}
@@ -4533,124 +4611,179 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->dev = adj_dev;
adj->master = master;
- adj->neighbour = neighbour;
adj->ref_nr = 1;
-
+ adj->private = private;
dev_hold(adj_dev);
- pr_debug("dev_hold for %s, because of %s link added from %s to %s\n",
- adj_dev->name, upper ? "upper" : "lower", dev->name,
- adj_dev->name);
- if (!upper) {
- list_add_tail_rcu(&adj->list, &dev->lower_dev_list);
- return 0;
+ pr_debug("dev_hold for %s, because of link added from %s to %s\n",
+ adj_dev->name, dev->name, adj_dev->name);
+
+ if (dev_list == &dev->adj_list.lower) {
+ sprintf(linkname, "lower_%s", adj_dev->name);
+ ret = sysfs_create_link(&(dev->dev.kobj),
+ &(adj_dev->dev.kobj), linkname);
+ if (ret)
+ goto free_adj;
+ } else if (dev_list == &dev->adj_list.upper) {
+ sprintf(linkname, "upper_%s", adj_dev->name);
+ ret = sysfs_create_link(&(dev->dev.kobj),
+ &(adj_dev->dev.kobj), linkname);
+ if (ret)
+ goto free_adj;
}
- /* Ensure that master upper link is always the first item in list. */
- if (master)
- list_add_rcu(&adj->list, &dev->upper_dev_list);
- else
- list_add_tail_rcu(&adj->list, &dev->upper_dev_list);
+ /* Ensure that master link is always the first item in list. */
+ if (master) {
+ ret = sysfs_create_link(&(dev->dev.kobj),
+ &(adj_dev->dev.kobj), "master");
+ if (ret)
+ goto remove_symlinks;
+
+ list_add_rcu(&adj->list, dev_list);
+ } else {
+ list_add_tail_rcu(&adj->list, dev_list);
+ }
return 0;
-}
-static inline int __netdev_upper_dev_insert(struct net_device *dev,
- struct net_device *udev,
- bool master, bool neighbour)
-{
- return __netdev_adjacent_dev_insert(dev, udev, neighbour, master,
- true);
-}
+remove_symlinks:
+ if (dev_list == &dev->adj_list.lower) {
+ sprintf(linkname, "lower_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ } else if (dev_list == &dev->adj_list.upper) {
+ sprintf(linkname, "upper_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ }
-static inline int __netdev_lower_dev_insert(struct net_device *dev,
- struct net_device *ldev,
- bool neighbour)
-{
- return __netdev_adjacent_dev_insert(dev, ldev, neighbour, false,
- false);
+free_adj:
+ kfree(adj);
+ dev_put(adj_dev);
+
+ return ret;
}
void __netdev_adjacent_dev_remove(struct net_device *dev,
- struct net_device *adj_dev, bool upper)
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
{
struct netdev_adjacent *adj;
+ char linkname[IFNAMSIZ+7];
- if (upper)
- adj = __netdev_find_upper(dev, adj_dev);
- else
- adj = __netdev_find_lower(dev, adj_dev);
+ adj = __netdev_find_adj(dev, adj_dev, dev_list);
- if (!adj)
+ if (!adj) {
+ pr_err("tried to remove device %s from %s\n",
+ dev->name, adj_dev->name);
BUG();
+ }
if (adj->ref_nr > 1) {
+ pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
+ adj->ref_nr-1);
adj->ref_nr--;
return;
}
+ if (adj->master)
+ sysfs_remove_link(&(dev->dev.kobj), "master");
+
+ if (dev_list == &dev->adj_list.lower) {
+ sprintf(linkname, "lower_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ } else if (dev_list == &dev->adj_list.upper) {
+ sprintf(linkname, "upper_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ }
+
list_del_rcu(&adj->list);
- pr_debug("dev_put for %s, because of %s link removed from %s to %s\n",
- adj_dev->name, upper ? "upper" : "lower", dev->name,
- adj_dev->name);
+ pr_debug("dev_put for %s, because link removed from %s to %s\n",
+ adj_dev->name, dev->name, adj_dev->name);
dev_put(adj_dev);
kfree_rcu(adj, rcu);
}
-static inline void __netdev_upper_dev_remove(struct net_device *dev,
- struct net_device *udev)
-{
- return __netdev_adjacent_dev_remove(dev, udev, true);
-}
-
-static inline void __netdev_lower_dev_remove(struct net_device *dev,
- struct net_device *ldev)
-{
- return __netdev_adjacent_dev_remove(dev, ldev, false);
-}
-
-int __netdev_adjacent_dev_insert_link(struct net_device *dev,
- struct net_device *upper_dev,
- bool master, bool neighbour)
+int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list,
+ void *private, bool master)
{
int ret;
- ret = __netdev_upper_dev_insert(dev, upper_dev, master, neighbour);
+ ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
+ master);
if (ret)
return ret;
- ret = __netdev_lower_dev_insert(upper_dev, dev, neighbour);
+ ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
+ false);
if (ret) {
- __netdev_upper_dev_remove(dev, upper_dev);
+ __netdev_adjacent_dev_remove(dev, upper_dev, up_list);
return ret;
}
return 0;
}
-static inline int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *udev)
+int __netdev_adjacent_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
- return __netdev_adjacent_dev_insert_link(dev, udev, false, false);
+ return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+ &dev->all_adj_list.upper,
+ &upper_dev->all_adj_list.lower,
+ NULL, false);
}
-static inline int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
- struct net_device *udev,
- bool master)
+void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list)
{
- return __netdev_adjacent_dev_insert_link(dev, udev, master, true);
+ __netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+ __netdev_adjacent_dev_remove(upper_dev, dev, down_list);
}
void __netdev_adjacent_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
- __netdev_upper_dev_remove(dev, upper_dev);
- __netdev_lower_dev_remove(upper_dev, dev);
+ __netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+ &dev->all_adj_list.upper,
+ &upper_dev->all_adj_list.lower);
}
+int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private, bool master)
+{
+ int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+
+ if (ret)
+ return ret;
+
+ ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+ &dev->adj_list.upper,
+ &upper_dev->adj_list.lower,
+ private, master);
+ if (ret) {
+ __netdev_adjacent_dev_unlink(dev, upper_dev);
+ return ret;
+ }
+
+ return 0;
+}
+
+void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+ &dev->adj_list.upper,
+ &upper_dev->adj_list.lower);
+}
static int __netdev_upper_dev_link(struct net_device *dev,
- struct net_device *upper_dev, bool master)
+ struct net_device *upper_dev, bool master,
+ void *private)
{
struct netdev_adjacent *i, *j, *to_i, *to_j;
int ret = 0;
@@ -4661,26 +4794,29 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (__netdev_find_upper(upper_dev, dev))
+ if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
return -EBUSY;
- if (__netdev_find_upper(dev, upper_dev))
+ if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
return -EBUSY;
- ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, master);
+ ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
+ master);
if (ret)
return ret;
/* Now that we linked these devs, make all the upper_dev's
- * upper_dev_list visible to every dev's lower_dev_list and vice
+ * all_adj_list.upper visible to every dev's all_adj_list.lower an
* versa, and don't forget the devices itself. All of these
* links are non-neighbours.
*/
- list_for_each_entry(i, &dev->lower_dev_list, list) {
- list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+ list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
+ pr_debug("Interlinking %s with %s, non-neighbour\n",
+ i->dev->name, j->dev->name);
ret = __netdev_adjacent_dev_link(i->dev, j->dev);
if (ret)
goto rollback_mesh;
@@ -4688,14 +4824,18 @@ static int __netdev_upper_dev_link(struct net_device *dev,
}
/* add dev to every upper_dev's upper device */
- list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
+ pr_debug("linking %s's upper device %s with %s\n",
+ upper_dev->name, i->dev->name, dev->name);
ret = __netdev_adjacent_dev_link(dev, i->dev);
if (ret)
goto rollback_upper_mesh;
}
/* add upper_dev to every dev's lower device */
- list_for_each_entry(i, &dev->lower_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+ pr_debug("linking %s's lower device %s with %s\n", dev->name,
+ i->dev->name, upper_dev->name);
ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
if (ret)
goto rollback_lower_mesh;
@@ -4706,7 +4846,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
rollback_lower_mesh:
to_i = i;
- list_for_each_entry(i, &dev->lower_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
if (i == to_i)
break;
__netdev_adjacent_dev_unlink(i->dev, upper_dev);
@@ -4716,7 +4856,7 @@ rollback_lower_mesh:
rollback_upper_mesh:
to_i = i;
- list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
if (i == to_i)
break;
__netdev_adjacent_dev_unlink(dev, i->dev);
@@ -4727,8 +4867,8 @@ rollback_upper_mesh:
rollback_mesh:
to_i = i;
to_j = j;
- list_for_each_entry(i, &dev->lower_dev_list, list) {
- list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+ list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
if (i == to_i && j == to_j)
break;
__netdev_adjacent_dev_unlink(i->dev, j->dev);
@@ -4737,7 +4877,7 @@ rollback_mesh:
break;
}
- __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
return ret;
}
@@ -4755,7 +4895,7 @@ rollback_mesh:
int netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev)
{
- return __netdev_upper_dev_link(dev, upper_dev, false);
+ return __netdev_upper_dev_link(dev, upper_dev, false, NULL);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
@@ -4773,10 +4913,18 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev)
{
- return __netdev_upper_dev_link(dev, upper_dev, true);
+ return __netdev_upper_dev_link(dev, upper_dev, true, NULL);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
+int netdev_master_upper_dev_link_private(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private)
+{
+ return __netdev_upper_dev_link(dev, upper_dev, true, private);
+}
+EXPORT_SYMBOL(netdev_master_upper_dev_link_private);
+
/**
* netdev_upper_dev_unlink - Removes a link to upper device
* @dev: device
@@ -4791,38 +4939,68 @@ void netdev_upper_dev_unlink(struct net_device *dev,
struct netdev_adjacent *i, *j;
ASSERT_RTNL();
- __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
/* Here is the tricky part. We must remove all dev's lower
* devices from all upper_dev's upper devices and vice
* versa, to maintain the graph relationship.
*/
- list_for_each_entry(i, &dev->lower_dev_list, list)
- list_for_each_entry(j, &upper_dev->upper_dev_list, list)
+ list_for_each_entry(i, &dev->all_adj_list.lower, list)
+ list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
__netdev_adjacent_dev_unlink(i->dev, j->dev);
/* remove also the devices itself from lower/upper device
* list
*/
- list_for_each_entry(i, &dev->lower_dev_list, list)
+ list_for_each_entry(i, &dev->all_adj_list.lower, list)
__netdev_adjacent_dev_unlink(i->dev, upper_dev);
- list_for_each_entry(i, &upper_dev->upper_dev_list, list)
+ list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
__netdev_adjacent_dev_unlink(dev, i->dev);
call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
+void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
+ struct net_device *lower_dev)
+{
+ struct netdev_adjacent *lower;
+
+ if (!lower_dev)
+ return NULL;
+ lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
+ if (!lower)
+ return NULL;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
+
+void *netdev_lower_dev_get_private(struct net_device *dev,
+ struct net_device *lower_dev)
+{
+ struct netdev_adjacent *lower;
+
+ if (!lower_dev)
+ return NULL;
+ lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower);
+ if (!lower)
+ return NULL;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_dev_get_private);
+
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
- if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ if (ops->ndo_change_rx_flags)
ops->ndo_change_rx_flags(dev, flags);
}
-static int __dev_set_promiscuity(struct net_device *dev, int inc)
+static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
{
unsigned int old_flags = dev->flags;
kuid_t uid;
@@ -4865,6 +5043,8 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc)
dev_change_rx_flags(dev, IFF_PROMISC);
}
+ if (notify)
+ __dev_notify_flags(dev, old_flags, IFF_PROMISC);
return 0;
}
@@ -4884,7 +5064,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
unsigned int old_flags = dev->flags;
int err;
- err = __dev_set_promiscuity(dev, inc);
+ err = __dev_set_promiscuity(dev, inc, true);
if (err < 0)
return err;
if (dev->flags != old_flags)
@@ -4893,22 +5073,9 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
}
EXPORT_SYMBOL(dev_set_promiscuity);
-/**
- * dev_set_allmulti - update allmulti count on a device
- * @dev: device
- * @inc: modifier
- *
- * Add or remove reception of all multicast frames to a device. While the
- * count in the device remains above zero the interface remains listening
- * to all interfaces. Once it hits zero the device reverts back to normal
- * filtering operation. A negative @inc value is used to drop the counter
- * when releasing a resource needing all multicasts.
- * Return 0 if successful or a negative errno code on error.
- */
-
-int dev_set_allmulti(struct net_device *dev, int inc)
+static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify)
{
- unsigned int old_flags = dev->flags;
+ unsigned int old_flags = dev->flags, old_gflags = dev->gflags;
ASSERT_RTNL();
@@ -4931,9 +5098,30 @@ int dev_set_allmulti(struct net_device *dev, int inc)
if (dev->flags ^ old_flags) {
dev_change_rx_flags(dev, IFF_ALLMULTI);
dev_set_rx_mode(dev);
+ if (notify)
+ __dev_notify_flags(dev, old_flags,
+ dev->gflags ^ old_gflags);
}
return 0;
}
+
+/**
+ * dev_set_allmulti - update allmulti count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove reception of all multicast frames to a device. While the
+ * count in the device remains above zero the interface remains listening
+ * to all interfaces. Once it hits zero the device reverts back to normal
+ * filtering operation. A negative @inc value is used to drop the counter
+ * when releasing a resource needing all multicasts.
+ * Return 0 if successful or a negative errno code on error.
+ */
+
+int dev_set_allmulti(struct net_device *dev, int inc)
+{
+ return __dev_set_allmulti(dev, inc, true);
+}
EXPORT_SYMBOL(dev_set_allmulti);
/*
@@ -4958,10 +5146,10 @@ void __dev_set_rx_mode(struct net_device *dev)
* therefore calling __dev_set_promiscuity here is safe.
*/
if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
- __dev_set_promiscuity(dev, 1);
+ __dev_set_promiscuity(dev, 1, false);
dev->uc_promisc = true;
} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
- __dev_set_promiscuity(dev, -1);
+ __dev_set_promiscuity(dev, -1, false);
dev->uc_promisc = false;
}
}
@@ -5050,9 +5238,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
if ((flags ^ dev->gflags) & IFF_PROMISC) {
int inc = (flags & IFF_PROMISC) ? 1 : -1;
+ unsigned int old_flags = dev->flags;
dev->gflags ^= IFF_PROMISC;
- dev_set_promiscuity(dev, inc);
+
+ if (__dev_set_promiscuity(dev, inc, false) >= 0)
+ if (dev->flags != old_flags)
+ dev_set_rx_mode(dev);
}
/* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
@@ -5063,16 +5255,20 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
dev->gflags ^= IFF_ALLMULTI;
- dev_set_allmulti(dev, inc);
+ __dev_set_allmulti(dev, inc, false);
}
return ret;
}
-void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
+void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
+ unsigned int gchanges)
{
unsigned int changes = dev->flags ^ old_flags;
+ if (gchanges)
+ rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC);
+
if (changes & IFF_UP) {
if (dev->flags & IFF_UP)
call_netdevice_notifiers(NETDEV_UP, dev);
@@ -5101,17 +5297,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
int dev_change_flags(struct net_device *dev, unsigned int flags)
{
int ret;
- unsigned int changes, old_flags = dev->flags;
+ unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
ret = __dev_change_flags(dev, flags);
if (ret < 0)
return ret;
- changes = old_flags ^ dev->flags;
- if (changes)
- rtmsg_ifinfo(RTM_NEWLINK, dev, changes);
-
- __dev_notify_flags(dev, old_flags);
+ changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags);
+ __dev_notify_flags(dev, old_flags, changes);
return ret;
}
EXPORT_SYMBOL(dev_change_flags);
@@ -5247,15 +5440,18 @@ static int dev_new_index(struct net *net)
/* Delayed registration/unregisteration */
static LIST_HEAD(net_todo_list);
+static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
static void net_set_todo(struct net_device *dev)
{
list_add_tail(&dev->todo_list, &net_todo_list);
+ dev_net(dev)->dev_unreg_count++;
}
static void rollback_registered_many(struct list_head *head)
{
struct net_device *dev, *tmp;
+ LIST_HEAD(close_head);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
@@ -5278,7 +5474,9 @@ static void rollback_registered_many(struct list_head *head)
}
/* If device is running, close it first. */
- dev_close_many(head);
+ list_for_each_entry(dev, head, unreg_list)
+ list_add_tail(&dev->close_list, &close_head);
+ dev_close_many(&close_head);
list_for_each_entry(dev, head, unreg_list) {
/* And unlink it from device chain. */
@@ -5301,7 +5499,7 @@ static void rollback_registered_many(struct list_head *head)
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
- rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
+ rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
/*
* Flush the unicast and multicast chains
@@ -5700,7 +5898,7 @@ int register_netdevice(struct net_device *dev)
*/
if (!dev->rtnl_link_ops ||
dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
- rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);
out:
return ret;
@@ -5918,6 +6116,12 @@ void netdev_run_todo(void)
if (dev->destructor)
dev->destructor(dev);
+ /* Report a network device has been unregistered */
+ rtnl_lock();
+ dev_net(dev)->dev_unreg_count--;
+ __rtnl_unlock();
+ wake_up(&netdev_unregistering_wq);
+
/* Free network device */
kobject_put(&dev->dev.kobj);
}
@@ -6001,6 +6205,16 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
}
EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops);
+void netdev_freemem(struct net_device *dev)
+{
+ char *addr = (char *)dev - dev->padded;
+
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+}
+
/**
* alloc_netdev_mqs - allocate network device
* @sizeof_priv: size of private data to allocate space for
@@ -6044,7 +6258,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
/* ensure 32-byte alignment of whole construct */
alloc_size += NETDEV_ALIGN - 1;
- p = kzalloc(alloc_size, GFP_KERNEL);
+ p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!p)
+ p = vzalloc(alloc_size);
if (!p)
return NULL;
@@ -6053,7 +6269,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev->pcpu_refcnt = alloc_percpu(int);
if (!dev->pcpu_refcnt)
- goto free_p;
+ goto free_dev;
if (dev_addr_init(dev))
goto free_pcpu;
@@ -6068,9 +6284,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
+ INIT_LIST_HEAD(&dev->close_list);
INIT_LIST_HEAD(&dev->link_watch_list);
- INIT_LIST_HEAD(&dev->upper_dev_list);
- INIT_LIST_HEAD(&dev->lower_dev_list);
+ INIT_LIST_HEAD(&dev->adj_list.upper);
+ INIT_LIST_HEAD(&dev->adj_list.lower);
+ INIT_LIST_HEAD(&dev->all_adj_list.upper);
+ INIT_LIST_HEAD(&dev->all_adj_list.lower);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
@@ -6103,8 +6322,8 @@ free_pcpu:
kfree(dev->_rx);
#endif
-free_p:
- kfree(p);
+free_dev:
+ netdev_freemem(dev);
return NULL;
}
EXPORT_SYMBOL(alloc_netdev_mqs);
@@ -6141,7 +6360,7 @@ void free_netdev(struct net_device *dev)
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
- kfree((char *)dev - dev->padded);
+ netdev_freemem(dev);
return;
}
@@ -6303,7 +6522,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
- rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
+ rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
/*
* Flush the unicast and multicast chains
@@ -6342,7 +6561,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
* Prevent userspace races by waiting until the network
* device is fully setup before sending notifications.
*/
- rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);
synchronize_net();
err = 0;
@@ -6603,6 +6822,34 @@ static void __net_exit default_device_exit(struct net *net)
rtnl_unlock();
}
+static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
+{
+ /* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace in net_list.
+ */
+ struct net *net;
+ bool unregistering;
+ DEFINE_WAIT(wait);
+
+ for (;;) {
+ prepare_to_wait(&netdev_unregistering_wq, &wait,
+ TASK_UNINTERRUPTIBLE);
+ unregistering = false;
+ rtnl_lock();
+ list_for_each_entry(net, net_list, exit_list) {
+ if (net->dev_unreg_count > 0) {
+ unregistering = true;
+ break;
+ }
+ }
+ if (!unregistering)
+ break;
+ __rtnl_unlock();
+ schedule();
+ }
+ finish_wait(&netdev_unregistering_wq, &wait);
+}
+
static void __net_exit default_device_exit_batch(struct list_head *net_list)
{
/* At exit all network devices most be removed from a network
@@ -6614,7 +6861,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
struct net *net;
LIST_HEAD(dev_kill_list);
- rtnl_lock();
+ /* To prevent network device cleanup code from dereferencing
+ * loopback devices or network devices that have been freed
+ * wait here for all pending unregistrations to complete,
+ * before unregistring the loopback device and allowing the
+ * network namespace be freed.
+ *
+ * The netdev todo list containing all network devices
+ * unregistrations that happen in default_device_exit_batch
+ * will run in the rtnl_unlock() at the end of
+ * default_device_exit_batch.
+ */
+ rtnl_lock_unregistering(net_list);
list_for_each_entry(net, net_list, exit_list) {
for_each_netdev_reverse(net, dev) {
if (dev->rtnl_link_ops)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 6cda4e2c2132..ec40a849fc42 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -752,7 +752,7 @@ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr)
EXPORT_SYMBOL(dev_mc_del_global);
/**
- * dev_mc_sync - Synchronize device's unicast list to another device
+ * dev_mc_sync - Synchronize device's multicast list to another device
* @to: destination device
* @from: source device
*
@@ -780,7 +780,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
EXPORT_SYMBOL(dev_mc_sync);
/**
- * dev_mc_sync_multiple - Synchronize device's unicast list to another
+ * dev_mc_sync_multiple - Synchronize device's multicast list to another
* device, but allow for multiple calls to sync to multiple devices.
* @to: destination device
* @from: source device
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 5e78d44333b9..95897183226e 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -106,6 +106,10 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
return skb;
}
+static struct genl_multicast_group dropmon_mcgrps[] = {
+ { .name = "events", },
+};
+
static void send_dm_alert(struct work_struct *work)
{
struct sk_buff *skb;
@@ -116,7 +120,8 @@ static void send_dm_alert(struct work_struct *work)
skb = reset_per_cpu_data(data);
if (skb)
- genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+ genlmsg_multicast(&net_drop_monitor_family, skb, 0,
+ 0, GFP_KERNEL);
}
/*
@@ -333,7 +338,7 @@ out:
return NOTIFY_DONE;
}
-static struct genl_ops dropmon_ops[] = {
+static const struct genl_ops dropmon_ops[] = {
{
.cmd = NET_DM_CMD_CONFIG,
.doit = net_dm_cmd_config,
@@ -364,13 +369,13 @@ static int __init init_net_drop_monitor(void)
return -ENOSPC;
}
- rc = genl_register_family_with_ops(&net_drop_monitor_family,
- dropmon_ops,
- ARRAY_SIZE(dropmon_ops));
+ rc = genl_register_family_with_ops_groups(&net_drop_monitor_family,
+ dropmon_ops, dropmon_mcgrps);
if (rc) {
pr_err("Could not create drop monitor netlink family\n");
return rc;
}
+ WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
rc = register_netdevice_notifier(&dropmon_net_notifier);
if (rc < 0) {
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 78e9d9223e40..30071dec287a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -81,6 +81,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation",
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
[NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
+ [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation",
+ [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
[NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation",
@@ -94,6 +96,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_LOOPBACK_BIT] = "loopback",
[NETIF_F_RXFCS_BIT] = "rx-fcs",
[NETIF_F_RXALL_BIT] = "rx-all",
+ [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
};
static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 2e654138433c..f409e0bd35c0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -460,7 +460,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
if (frh->action && (frh->action != rule->action))
continue;
- if (frh->table && (frh_get_table(frh, tb) != rule->table))
+ if (frh_get_table(frh, tb) &&
+ (frh_get_table(frh, tb) != rule->table))
continue;
if (tb[FRA_PRIORITY] &&
diff --git a/net/core/filter.c b/net/core/filter.c
index 6438f29ff266..01b780856db2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -644,7 +644,6 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
bpf_jit_free(fp);
- kfree(fp);
}
EXPORT_SYMBOL(sk_filter_release_rcu);
@@ -683,7 +682,7 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
if (fprog->filter == NULL)
return -EINVAL;
- fp = kmalloc(fsize + sizeof(*fp), GFP_KERNEL);
+ fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
if (!fp)
return -ENOMEM;
memcpy(fp->insns, fprog->filter, fsize);
@@ -723,6 +722,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
struct sk_filter *fp, *old_fp;
unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+ unsigned int sk_fsize = sk_filter_size(fprog->len);
int err;
if (sock_flag(sk, SOCK_FILTER_LOCKED))
@@ -732,11 +732,11 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
if (fprog->filter == NULL)
return -EINVAL;
- fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL);
+ fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
if (!fp)
return -ENOMEM;
if (copy_from_user(fp->insns, fprog->filter, fsize)) {
- sock_kfree_s(sk, fp, fsize+sizeof(*fp));
+ sock_kfree_s(sk, fp, sk_fsize);
return -EFAULT;
}
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 1929af87b260..d6ef17322500 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -25,9 +25,35 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
}
+/**
+ * skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: buffer to extract the ports from
+ * @thoff: transport header offset
+ * @ip_proto: protocol for which to get port offset
+ *
+ * The function will try to retrieve the ports at offset thoff + poff where poff
+ * is the protocol port offset returned from proto_ports_offset
+ */
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+{
+ int poff = proto_ports_offset(ip_proto);
+
+ if (poff >= 0) {
+ __be32 *ports, _ports;
+
+ ports = skb_header_pointer(skb, thoff + poff,
+ sizeof(_ports), &_ports);
+ if (ports)
+ return *ports;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(skb_flow_get_ports);
+
bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
{
- int poff, nhoff = skb_network_offset(skb);
+ int nhoff = skb_network_offset(skb);
u8 ip_proto;
__be16 proto = skb->protocol;
@@ -40,15 +66,15 @@ again:
struct iphdr _iph;
ip:
iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
+ if (!iph || iph->ihl < 5)
return false;
+ nhoff += iph->ihl * 4;
+ ip_proto = iph->protocol;
if (ip_is_fragment(iph))
ip_proto = 0;
- else
- ip_proto = iph->protocol;
+
iph_to_flow_copy_addrs(flow, iph);
- nhoff += iph->ihl * 4;
break;
}
case __constant_htons(ETH_P_IPV6): {
@@ -150,16 +176,7 @@ ipv6:
}
flow->ip_proto = ip_proto;
- poff = proto_ports_offset(ip_proto);
- if (poff >= 0) {
- __be32 *ports, _ports;
-
- nhoff += poff;
- ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
- if (ports)
- flow->ports = *ports;
- }
-
+ flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
flow->thoff = (u16) nhoff;
return true;
@@ -167,6 +184,22 @@ ipv6:
EXPORT_SYMBOL(skb_flow_dissect);
static u32 hashrnd __read_mostly;
+static __always_inline void __flow_hash_secret_init(void)
+{
+ net_get_random_once(&hashrnd, sizeof(hashrnd));
+}
+
+static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c)
+{
+ __flow_hash_secret_init();
+ return jhash_3words(a, b, c, hashrnd);
+}
+
+static __always_inline u32 __flow_hash_1word(u32 a)
+{
+ __flow_hash_secret_init();
+ return jhash_1word(a, hashrnd);
+}
/*
* __skb_get_rxhash: calculate a flow hash based on src/dst addresses
@@ -193,9 +226,9 @@ void __skb_get_rxhash(struct sk_buff *skb)
swap(keys.port16[0], keys.port16[1]);
}
- hash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src,
- (__force u32)keys.ports, hashrnd);
+ hash = __flow_hash_3words((__force u32)keys.dst,
+ (__force u32)keys.src,
+ (__force u32)keys.ports);
if (!hash)
hash = 1;
@@ -231,7 +264,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol;
- hash = jhash_1word(hash, hashrnd);
+ hash = __flow_hash_1word(hash);
return (u16) (((u64) hash * qcount) >> 32) + qoffset;
}
@@ -323,7 +356,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
else
hash = (__force u16) skb->protocol ^
skb->rxhash;
- hash = jhash_1word(hash, hashrnd);
+ hash = __flow_hash_1word(hash);
queue_index = map->queues[
((u64)hash * map->len) >> 32];
}
@@ -378,11 +411,3 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
}
-
-static int __init initialize_hashrnd(void)
-{
- get_random_bytes(&hashrnd, sizeof(hashrnd));
- return 0;
-}
-
-late_initcall_sync(initialize_hashrnd);
diff --git a/net/core/iovec.c b/net/core/iovec.c
index b77eeecc0011..b61869429f4c 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
if (err < 0)
return err;
}
- m->msg_name = address;
+ if (m->msg_name)
+ m->msg_name = address;
} else {
m->msg_name = NULL;
}
@@ -100,7 +101,7 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
EXPORT_SYMBOL(memcpy_toiovecend);
/*
- * Copy iovec from kernel. Returns -EFAULT on error.
+ * Copy iovec to kernel. Returns -EFAULT on error.
*/
int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6072610a8672..ca15f32821fb 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -867,7 +867,7 @@ static void neigh_invalidate(struct neighbour *neigh)
static void neigh_probe(struct neighbour *neigh)
__releases(neigh->lock)
{
- struct sk_buff *skb = skb_peek(&neigh->arp_queue);
+ struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue);
/* keep skb alive even if arp_queue overflows */
if (skb)
skb = skb_copy(skb, GFP_ATOMIC);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index d954b56b4e47..f3edf9635e02 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1263,7 +1263,7 @@ static void netdev_release(struct device *d)
BUG_ON(dev->reg_state != NETREG_RELEASED);
kfree(dev->ifalias);
- kfree((char *)dev - dev->padded);
+ netdev_freemem(dev);
}
static const void *net_namespace(struct device *d)
@@ -1344,17 +1344,19 @@ int netdev_register_kobject(struct net_device *net)
return error;
}
-int netdev_class_create_file(struct class_attribute *class_attr)
+int netdev_class_create_file_ns(struct class_attribute *class_attr,
+ const void *ns)
{
- return class_create_file(&net_class, class_attr);
+ return class_create_file_ns(&net_class, class_attr, ns);
}
-EXPORT_SYMBOL(netdev_class_create_file);
+EXPORT_SYMBOL(netdev_class_create_file_ns);
-void netdev_class_remove_file(struct class_attribute *class_attr)
+void netdev_class_remove_file_ns(struct class_attribute *class_attr,
+ const void *ns)
{
- class_remove_file(&net_class, class_attr);
+ class_remove_file_ns(&net_class, class_attr, ns);
}
-EXPORT_SYMBOL(netdev_class_remove_file);
+EXPORT_SYMBOL(netdev_class_remove_file_ns);
int netdev_kobject_init(void)
{
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index fc75c9e461b8..8f971990677c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -636,8 +636,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
netpoll_send_skb(np, send_skb);
- /* If there are several rx_hooks for the same address,
- we're fine by sending a single reply */
+ /* If there are several rx_skb_hooks for the same
+ * address we're fine by sending a single reply
+ */
break;
}
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
@@ -719,8 +720,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
netpoll_send_skb(np, send_skb);
- /* If there are several rx_hooks for the same address,
- we're fine by sending a single reply */
+ /* If there are several rx_skb_hooks for the same
+ * address, we're fine by sending a single reply
+ */
break;
}
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
@@ -756,11 +758,12 @@ static bool pkt_is_ns(struct sk_buff *skb)
int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
{
- int proto, len, ulen;
- int hits = 0;
+ int proto, len, ulen, data_len;
+ int hits = 0, offset;
const struct iphdr *iph;
struct udphdr *uh;
struct netpoll *np, *tmp;
+ uint16_t source;
if (list_empty(&npinfo->rx_np))
goto out;
@@ -820,7 +823,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
len -= iph->ihl*4;
uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
+ offset = (unsigned char *)(uh + 1) - skb->data;
ulen = ntohs(uh->len);
+ data_len = skb->len - offset;
+ source = ntohs(uh->source);
if (ulen != len)
goto out;
@@ -834,9 +840,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
if (np->local_port && np->local_port != ntohs(uh->dest))
continue;
- np->rx_hook(np, ntohs(uh->source),
- (char *)(uh+1),
- ulen - sizeof(struct udphdr));
+ np->rx_skb_hook(np, source, skb, offset, data_len);
hits++;
}
} else {
@@ -859,7 +863,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
uh = udp_hdr(skb);
+ offset = (unsigned char *)(uh + 1) - skb->data;
ulen = ntohs(uh->len);
+ data_len = skb->len - offset;
+ source = ntohs(uh->source);
if (ulen != skb->len)
goto out;
if (udp6_csum_init(skb, uh, IPPROTO_UDP))
@@ -872,9 +879,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
if (np->local_port && np->local_port != ntohs(uh->dest))
continue;
- np->rx_hook(np, ntohs(uh->source),
- (char *)(uh+1),
- ulen - sizeof(struct udphdr));
+ np->rx_skb_hook(np, source, skb, offset, data_len);
hits++;
}
#endif
@@ -1062,7 +1067,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
npinfo->netpoll = np;
- if (np->rx_hook) {
+ if (np->rx_skb_hook) {
spin_lock_irqsave(&npinfo->rx_lock, flags);
npinfo->rx_flags |= NETPOLL_RX_ENABLED;
list_add_tail(&np->rx, &npinfo->rx_np);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index d9cd627e6a16..9b7cf6c85f82 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -222,11 +222,10 @@ static void net_prio_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p;
- void *v;
+ void *v = (void *)(unsigned long)css->cgroup->id;
cgroup_taskset_for_each(p, css, tset) {
task_lock(p);
- v = (void *)(unsigned long)task_netprioidx(p);
iterate_fd(p->files, 0, update_netprio, v);
task_unlock(p);
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2a0e21de3060..cf67144d3e3c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1647,9 +1647,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
}
dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
- rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
- __dev_notify_flags(dev, old_flags);
+ __dev_notify_flags(dev, old_flags, ~0U);
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
@@ -1985,14 +1984,15 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+ 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)), GFP_KERNEL);
+ skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags);
if (skb == NULL)
goto errout;
@@ -2003,7 +2003,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
+ rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
return;
errout:
if (err < 0)
@@ -2717,7 +2717,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
case NETDEV_JOIN:
break;
default:
- rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+ rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
break;
}
return NOTIFY_DONE;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 6a2f13cee86a..897da56f3aff 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -7,15 +7,20 @@
#include <linux/hrtimer.h>
#include <linux/ktime.h>
#include <linux/string.h>
+#include <linux/net.h>
#include <net/secure_seq.h>
-static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
-void net_secret_init(void)
+static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+
+static __always_inline void net_secret_init(void)
{
- get_random_bytes(net_secret, sizeof(net_secret));
+ net_get_random_once(net_secret, sizeof(net_secret));
}
+#endif
#ifdef CONFIG_INET
static u32 seq_scale(u32 seq)
@@ -42,6 +47,7 @@ __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
u32 hash[MD5_DIGEST_WORDS];
u32 i;
+ net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
secret[i] = net_secret[i] + (__force u32)daddr[i];
@@ -63,6 +69,7 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
u32 hash[MD5_DIGEST_WORDS];
u32 i;
+ net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
secret[i] = net_secret[i] + (__force u32) daddr[i];
@@ -82,6 +89,7 @@ __u32 secure_ip_id(__be32 daddr)
{
u32 hash[MD5_DIGEST_WORDS];
+ net_secret_init();
hash[0] = (__force __u32) daddr;
hash[1] = net_secret[13];
hash[2] = net_secret[14];
@@ -96,6 +104,7 @@ __u32 secure_ipv6_id(const __be32 daddr[4])
{
__u32 hash[4];
+ net_secret_init();
memcpy(hash, daddr, 16);
md5_transform(hash, net_secret);
@@ -107,6 +116,7 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
{
u32 hash[MD5_DIGEST_WORDS];
+ net_secret_init();
hash[0] = (__force u32)saddr;
hash[1] = (__force u32)daddr;
hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -121,6 +131,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
{
u32 hash[MD5_DIGEST_WORDS];
+ net_secret_init();
hash[0] = (__force u32)saddr;
hash[1] = (__force u32)daddr;
hash[2] = (__force u32)dport ^ net_secret[14];
@@ -140,6 +151,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
u32 hash[MD5_DIGEST_WORDS];
u64 seq;
+ net_secret_init();
hash[0] = (__force u32)saddr;
hash[1] = (__force u32)daddr;
hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -164,6 +176,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
u64 seq;
u32 i;
+ net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
secret[i] = net_secret[i] + daddr[i];
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d81cff119f73..2718fed53d8c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -476,6 +476,18 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
}
EXPORT_SYMBOL(skb_add_rx_frag);
+void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
+ unsigned int truesize)
+{
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ skb_frag_size_add(frag, size);
+ skb->len += size;
+ skb->data_len += size;
+ skb->truesize += truesize;
+}
+EXPORT_SYMBOL(skb_coalesce_rx_frag);
+
static void skb_drop_list(struct sk_buff **listp)
{
kfree_skb_list(*listp);
@@ -580,9 +592,6 @@ static void skb_release_head_state(struct sk_buff *skb)
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb->nfct);
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(skb->nf_bridge);
#endif
@@ -903,6 +912,9 @@ EXPORT_SYMBOL(skb_clone);
static void skb_headers_offset_update(struct sk_buff *skb, int off)
{
+ /* Only adjust this if it actually is csum_start rather than csum */
+ if (skb->ip_summed == CHECKSUM_PARTIAL)
+ skb->csum_start += off;
/* {transport,network,mac}_header and tail are relative to skb->head */
skb->transport_header += off;
skb->network_header += off;
@@ -1036,8 +1048,8 @@ EXPORT_SYMBOL(__pskb_copy);
* @ntail: room to add at tail
* @gfp_mask: allocation priority
*
- * Expands (or creates identical copy, if &nhead and &ntail are zero)
- * header of skb. &sk_buff itself is not changed. &sk_buff MUST have
+ * Expands (or creates identical copy, if @nhead and @ntail are zero)
+ * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have
* reference count of 1. Returns zero in the case of success or error,
* if expansion failed. In the last case, &sk_buff is not changed.
*
@@ -1109,9 +1121,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
#endif
skb->tail += off;
skb_headers_offset_update(skb, nhead);
- /* Only adjust this if it actually is csum_start rather than csum */
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- skb->csum_start += nhead;
skb->cloned = 0;
skb->hdr_len = 0;
skb->nohdr = 0;
@@ -1176,7 +1185,6 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
NUMA_NO_NODE);
int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
- int off;
if (!n)
return NULL;
@@ -1200,11 +1208,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
copy_skb_header(n, skb);
- off = newheadroom - oldheadroom;
- if (n->ip_summed == CHECKSUM_PARTIAL)
- n->csum_start += off;
-
- skb_headers_offset_update(n, off);
+ skb_headers_offset_update(n, newheadroom - oldheadroom);
return n;
}
@@ -1257,6 +1261,29 @@ free_skb:
EXPORT_SYMBOL(skb_pad);
/**
+ * pskb_put - add data to the tail of a potentially fragmented buffer
+ * @skb: start of the buffer to use
+ * @tail: tail fragment of the buffer to use
+ * @len: amount of data to add
+ *
+ * This function extends the used data area of the potentially
+ * fragmented buffer. @tail must be the last fragment of @skb -- or
+ * @skb itself. If this would exceed the total buffer size the kernel
+ * will panic. A pointer to the first byte of the extra data is
+ * returned.
+ */
+
+unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
+{
+ if (tail != skb) {
+ skb->data_len += len;
+ skb->len += len;
+ }
+ return skb_put(tail, len);
+}
+EXPORT_SYMBOL_GPL(pskb_put);
+
+/**
* skb_put - add data to a buffer
* @skb: buffer to use
* @len: amount of data to add
@@ -1933,9 +1960,8 @@ fault:
EXPORT_SYMBOL(skb_store_bits);
/* Checksum skb data. */
-
-__wsum skb_checksum(const struct sk_buff *skb, int offset,
- int len, __wsum csum)
+__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
+ __wsum csum, const struct skb_checksum_ops *ops)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
@@ -1946,7 +1972,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
if (copy > 0) {
if (copy > len)
copy = len;
- csum = csum_partial(skb->data + offset, copy, csum);
+ csum = ops->update(skb->data + offset, copy, csum);
if ((len -= copy) == 0)
return csum;
offset += copy;
@@ -1967,10 +1993,10 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
if (copy > len)
copy = len;
vaddr = kmap_atomic(skb_frag_page(frag));
- csum2 = csum_partial(vaddr + frag->page_offset +
- offset - start, copy, 0);
+ csum2 = ops->update(vaddr + frag->page_offset +
+ offset - start, copy, 0);
kunmap_atomic(vaddr);
- csum = csum_block_add(csum, csum2, pos);
+ csum = ops->combine(csum, csum2, pos, copy);
if (!(len -= copy))
return csum;
offset += copy;
@@ -1989,9 +2015,9 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
__wsum csum2;
if (copy > len)
copy = len;
- csum2 = skb_checksum(frag_iter, offset - start,
- copy, 0);
- csum = csum_block_add(csum, csum2, pos);
+ csum2 = __skb_checksum(frag_iter, offset - start,
+ copy, 0, ops);
+ csum = ops->combine(csum, csum2, pos, copy);
if ((len -= copy) == 0)
return csum;
offset += copy;
@@ -2003,6 +2029,18 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
return csum;
}
+EXPORT_SYMBOL(__skb_checksum);
+
+__wsum skb_checksum(const struct sk_buff *skb, int offset,
+ int len, __wsum csum)
+{
+ const struct skb_checksum_ops ops = {
+ .update = csum_partial_ext,
+ .combine = csum_block_add_ext,
+ };
+
+ return __skb_checksum(skb, offset, len, csum, &ops);
+}
EXPORT_SYMBOL(skb_checksum);
/* Both of above in one bottle. */
@@ -2522,14 +2560,14 @@ EXPORT_SYMBOL(skb_prepare_seq_read);
* @data: destination pointer for data to be returned
* @st: state variable
*
- * Reads a block of skb data at &consumed relative to the
+ * Reads a block of skb data at @consumed relative to the
* lower offset specified to skb_prepare_seq_read(). Assigns
- * the head of the data block to &data and returns the length
+ * the head of the data block to @data and returns the length
* of the block or 0 if the end of the skb data or the upper
* offset has been reached.
*
* The caller is not required to consume all of the data
- * returned, i.e. &consumed is typically set to the number
+ * returned, i.e. @consumed is typically set to the number
* of bytes already consumed and the next call to
* skb_seq_read() will return the remaining part of the block.
*
@@ -2758,6 +2796,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
+ skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
unsigned int mss = skb_shinfo(skb)->gso_size;
unsigned int doffset = skb->data - skb_mac_header(skb);
unsigned int offset = doffset;
@@ -2797,16 +2836,38 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
if (hsize > len || !sg)
hsize = len;
- if (!hsize && i >= nfrags) {
- BUG_ON(fskb->len != len);
+ if (!hsize && i >= nfrags && skb_headlen(fskb) &&
+ (skb_headlen(fskb) == len || sg)) {
+ BUG_ON(skb_headlen(fskb) > len);
+
+ i = 0;
+ nfrags = skb_shinfo(fskb)->nr_frags;
+ skb_frag = skb_shinfo(fskb)->frags;
+ pos += skb_headlen(fskb);
+
+ while (pos < offset + len) {
+ BUG_ON(i >= nfrags);
+
+ size = skb_frag_size(skb_frag);
+ if (pos + size > offset + len)
+ break;
+
+ i++;
+ pos += size;
+ skb_frag++;
+ }
- pos += len;
nskb = skb_clone(fskb, GFP_ATOMIC);
fskb = fskb->next;
if (unlikely(!nskb))
goto err;
+ if (unlikely(pskb_trim(nskb, len))) {
+ kfree_skb(nskb);
+ goto err;
+ }
+
hsize = skb_end_offset(nskb);
if (skb_cow_head(nskb, doffset + headroom)) {
kfree_skb(nskb);
@@ -2837,20 +2898,13 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
__copy_skb_header(nskb, skb);
nskb->mac_len = skb->mac_len;
- /* nskb and skb might have different headroom */
- if (nskb->ip_summed == CHECKSUM_PARTIAL)
- nskb->csum_start += skb_headroom(nskb) - headroom;
-
- skb_reset_mac_header(nskb);
- skb_set_network_header(nskb, skb->mac_len);
- nskb->transport_header = (nskb->network_header +
- skb_network_header_len(skb));
+ skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
skb_copy_from_linear_data_offset(skb, -tnl_hlen,
nskb->data - tnl_hlen,
doffset + tnl_hlen);
- if (fskb != skb_shinfo(skb)->frag_list)
+ if (nskb->len == len + doffset)
goto perform_csum_check;
if (!sg) {
@@ -2868,8 +2922,28 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
- while (pos < offset + len && i < nfrags) {
- *frag = skb_shinfo(skb)->frags[i];
+ while (pos < offset + len) {
+ if (i >= nfrags) {
+ BUG_ON(skb_headlen(fskb));
+
+ i = 0;
+ nfrags = skb_shinfo(fskb)->nr_frags;
+ skb_frag = skb_shinfo(fskb)->frags;
+
+ BUG_ON(!nfrags);
+
+ fskb = fskb->next;
+ }
+
+ if (unlikely(skb_shinfo(nskb)->nr_frags >=
+ MAX_SKB_FRAGS)) {
+ net_warn_ratelimited(
+ "skb_segment: too many frags: %u %u\n",
+ pos, mss);
+ goto err;
+ }
+
+ *frag = *skb_frag;
__skb_frag_ref(frag);
size = skb_frag_size(frag);
@@ -2882,6 +2956,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
if (pos + size <= offset + len) {
i++;
+ skb_frag++;
pos += size;
} else {
skb_frag_size_sub(frag, pos + size - (offset + len));
@@ -2891,25 +2966,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
frag++;
}
- if (pos < offset + len) {
- struct sk_buff *fskb2 = fskb;
-
- BUG_ON(pos + fskb->len != offset + len);
-
- pos += fskb->len;
- fskb = fskb->next;
-
- if (fskb2->next) {
- fskb2 = skb_clone(fskb2, GFP_ATOMIC);
- if (!fskb2)
- goto err;
- } else
- skb_get(fskb2);
-
- SKB_FRAG_ASSERT(nskb);
- skb_shinfo(nskb)->frag_list = fskb2;
- }
-
skip_fraglist:
nskb->data_len = len - hsize;
nskb->len += nskb->data_len;
@@ -2936,32 +2992,30 @@ EXPORT_SYMBOL_GPL(skb_segment);
int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
- struct sk_buff *p = *head;
- struct sk_buff *nskb;
- struct skb_shared_info *skbinfo = skb_shinfo(skb);
- struct skb_shared_info *pinfo = skb_shinfo(p);
- unsigned int headroom;
- unsigned int len = skb_gro_len(skb);
+ struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
unsigned int offset = skb_gro_offset(skb);
unsigned int headlen = skb_headlen(skb);
+ struct sk_buff *nskb, *lp, *p = *head;
+ unsigned int len = skb_gro_len(skb);
unsigned int delta_truesize;
+ unsigned int headroom;
- if (p->len + len >= 65536)
+ if (unlikely(p->len + len >= 65536))
return -E2BIG;
- if (pinfo->frag_list)
- goto merge;
- else if (headlen <= offset) {
+ lp = NAPI_GRO_CB(p)->last ?: p;
+ pinfo = skb_shinfo(lp);
+
+ if (headlen <= offset) {
skb_frag_t *frag;
skb_frag_t *frag2;
int i = skbinfo->nr_frags;
int nr_frags = pinfo->nr_frags + i;
- offset -= headlen;
-
if (nr_frags > MAX_SKB_FRAGS)
- return -E2BIG;
+ goto merge;
+ offset -= headlen;
pinfo->nr_frags = nr_frags;
skbinfo->nr_frags = 0;
@@ -2992,7 +3046,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
unsigned int first_offset;
if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS)
- return -E2BIG;
+ goto merge;
first_offset = skb->data -
(unsigned char *)page_address(page) +
@@ -3010,7 +3064,10 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
goto done;
- } else if (skb_gro_len(p) != pinfo->gso_size)
+ }
+ if (pinfo->frag_list)
+ goto merge;
+ if (skb_gro_len(p) != pinfo->gso_size)
return -E2BIG;
headroom = skb_headroom(p);
@@ -3062,16 +3119,24 @@ merge:
__skb_pull(skb, offset);
- NAPI_GRO_CB(p)->last->next = skb;
+ if (!NAPI_GRO_CB(p)->last)
+ skb_shinfo(p)->frag_list = skb;
+ else
+ NAPI_GRO_CB(p)->last->next = skb;
NAPI_GRO_CB(p)->last = skb;
skb_header_release(skb);
+ lp = p;
done:
NAPI_GRO_CB(p)->count++;
p->data_len += len;
p->truesize += delta_truesize;
p->len += len;
-
+ if (lp != p) {
+ lp->data_len += len;
+ lp->truesize += delta_truesize;
+ lp->len += len;
+ }
NAPI_GRO_CB(skb)->same_flow = 1;
return 0;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 5b6beba494a3..ab20ed9b0f31 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -475,12 +475,6 @@ discard_and_relse:
}
EXPORT_SYMBOL(sk_receive_skb);
-void sk_reset_txq(struct sock *sk)
-{
- sk_tx_queue_clear(sk);
-}
-EXPORT_SYMBOL(sk_reset_txq);
-
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = __sk_dst_get(sk);
@@ -914,6 +908,13 @@ set_rcvbuf:
}
break;
#endif
+
+ case SO_MAX_PACING_RATE:
+ sk->sk_max_pacing_rate = val;
+ sk->sk_pacing_rate = min(sk->sk_pacing_rate,
+ sk->sk_max_pacing_rate);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1177,6 +1178,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
#endif
+ case SO_MAX_PACING_RATE:
+ v.val = sk->sk_max_pacing_rate;
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -1836,7 +1841,17 @@ EXPORT_SYMBOL(sock_alloc_send_skb);
/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER get_order(32768)
-bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+/**
+ * skb_page_frag_refill - check that a page_frag contains enough room
+ * @sz: minimum size of the fragment we want to get
+ * @pfrag: pointer to page_frag
+ * @prio: priority for memory allocation
+ *
+ * Note: While this allocator tries to use high order pages, there is
+ * no guarantee that allocations succeed. Therefore, @sz MUST be
+ * less or equal than PAGE_SIZE.
+ */
+bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
{
int order;
@@ -1845,16 +1860,16 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
pfrag->offset = 0;
return true;
}
- if (pfrag->offset < pfrag->size)
+ if (pfrag->offset + sz <= pfrag->size)
return true;
put_page(pfrag->page);
}
/* We restrict high order allocations to users that can afford to wait */
- order = (sk->sk_allocation & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
+ order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
do {
- gfp_t gfp = sk->sk_allocation;
+ gfp_t gfp = prio;
if (order)
gfp |= __GFP_COMP | __GFP_NOWARN;
@@ -1866,6 +1881,15 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
}
} while (--order >= 0);
+ return false;
+}
+EXPORT_SYMBOL(skb_page_frag_refill);
+
+bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+{
+ if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
+ return true;
+
sk_enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
return false;
@@ -2319,6 +2343,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_ll_usec = sysctl_net_busy_read;
#endif
+ sk->sk_max_pacing_rate = ~0U;
+ sk->sk_pacing_rate = ~0U;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/utils.c b/net/core/utils.c
index aa88e23fc87a..2f737bf90b3f 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -338,3 +338,52 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
csum_unfold(*sum)));
}
EXPORT_SYMBOL(inet_proto_csum_replace16);
+
+struct __net_random_once_work {
+ struct work_struct work;
+ struct static_key *key;
+};
+
+static void __net_random_once_deferred(struct work_struct *w)
+{
+ struct __net_random_once_work *work =
+ container_of(w, struct __net_random_once_work, work);
+ if (!static_key_enabled(work->key))
+ static_key_slow_inc(work->key);
+ kfree(work);
+}
+
+static void __net_random_once_disable_jump(struct static_key *key)
+{
+ struct __net_random_once_work *w;
+
+ w = kmalloc(sizeof(*w), GFP_ATOMIC);
+ if (!w)
+ return;
+
+ INIT_WORK(&w->work, __net_random_once_deferred);
+ w->key = key;
+ schedule_work(&w->work);
+}
+
+bool __net_get_random_once(void *buf, int nbytes, bool *done,
+ struct static_key *done_key)
+{
+ static DEFINE_SPINLOCK(lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&lock, flags);
+ if (*done) {
+ spin_unlock_irqrestore(&lock, flags);
+ return false;
+ }
+
+ get_random_bytes(buf, nbytes);
+ *done = true;
+ spin_unlock_irqrestore(&lock, flags);
+
+ __net_random_once_disable_jump(done_key);
+
+ return true;
+}
+EXPORT_SYMBOL(__net_get_random_once);
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-05 00:47:25 +0000