summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c18
-rw-r--r--net/core/dev.c475
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/rtnetlink.c3
-rw-r--r--net/core/sock.c12
-rw-r--r--net/ethernet/eth.c30
-rw-r--r--net/ipv4/icmp.c5
-rw-r--r--net/ipv4/inet_connection_sock.c20
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_output.c13
-rw-r--r--net/ipv4/ip_sockglue.c20
-rw-r--r--net/ipv4/ip_vti.c67
-rw-r--r--net/ipv4/ping.c8
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/syncookies.c53
-rw-r--r--net/ipv4/sysctl_net_ipv4.c52
-rw-r--r--net/ipv4/tcp_input.c86
-rw-r--r--net/ipv4/udp.c6
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c16
-rw-r--r--net/ipv6/af_inet6.c48
-rw-r--r--net/ipv6/ip6_fib.c205
-rw-r--r--net/ipv6/route.c49
-rw-r--r--net/ipv6/syncookies.c39
-rw-r--r--net/openvswitch/vport-vxlan.c2
-rw-r--r--net/sched/act_police.c4
-rw-r--r--net/sched/cls_basic.c2
-rw-r--r--net/sched/em_meta.c4
-rw-r--r--net/sched/sch_generic.c5
-rw-r--r--net/sched/sch_htb.c17
-rw-r--r--net/sched/sch_tbf.c4
-rw-r--r--net/sctp/socket.c2
-rw-r--r--net/xfrm/xfrm_state.c2
32 files changed, 765 insertions, 510 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 61fc573..b3d17d1 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -98,14 +98,14 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
vlan_gvrp_request_leave(dev);
vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL);
+
+ netdev_upper_dev_unlink(real_dev, dev);
/* Because unregister_netdevice_queue() makes sure at least one rcu
* grace period is respected before device freeing,
* we dont need to call synchronize_net() here.
*/
unregister_netdevice_queue(dev, head);
- netdev_upper_dev_unlink(real_dev, dev);
-
if (grp->nr_vlan_devs == 0) {
vlan_mvrp_uninit_applicant(real_dev);
vlan_gvrp_uninit_applicant(real_dev);
@@ -169,13 +169,13 @@ int register_vlan_dev(struct net_device *dev)
if (err < 0)
goto out_uninit_mvrp;
- err = netdev_upper_dev_link(real_dev, dev);
- if (err)
- goto out_uninit_mvrp;
-
err = register_netdevice(dev);
if (err < 0)
- goto out_upper_dev_unlink;
+ goto out_uninit_mvrp;
+
+ err = netdev_upper_dev_link(real_dev, dev);
+ if (err)
+ goto out_unregister_netdev;
/* Account for reference in struct vlan_dev_priv */
dev_hold(real_dev);
@@ -191,8 +191,8 @@ int register_vlan_dev(struct net_device *dev)
return 0;
-out_upper_dev_unlink:
- netdev_upper_dev_unlink(real_dev, dev);
+out_unregister_netdev:
+ unregister_netdevice(dev);
out_uninit_mvrp:
if (grp->nr_vlan_devs == 0)
vlan_mvrp_uninit_applicant(real_dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 65f829c..c25db20 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4373,42 +4373,40 @@ 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 +4423,7 @@ 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 +4438,7 @@ 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 +4455,10 @@ 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 +4466,26 @@ 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 +4493,71 @@ 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 +4570,7 @@ 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 +4580,16 @@ 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 +4600,178 @@ 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);
+
+ 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 +4782,29 @@ 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 +4812,18 @@ 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 +4834,7 @@ 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 +4844,7 @@ 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 +4855,8 @@ 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 +4865,7 @@ rollback_mesh:
break;
}
- __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
return ret;
}
@@ -4755,7 +4883,7 @@ 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 +4901,18 @@ 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
@@ -4791,29 +4927,59 @@ 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;
@@ -4822,7 +4988,7 @@ static void dev_change_rx_flags(struct net_device *dev, int 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 +5031,8 @@ 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 +5052,7 @@ 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 +5061,9 @@ 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 +5086,30 @@ 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 +5134,10 @@ 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 +5226,13 @@ 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 +5243,20 @@ 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);
+
if (changes & IFF_UP) {
if (dev->flags & IFF_UP)
call_netdevice_notifiers(NETDEV_UP, dev);
@@ -5101,17 +5285,14 @@ 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);
@@ -6077,8 +6258,10 @@ 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->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);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6072610..ca15f32 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/rtnetlink.c b/net/core/rtnetlink.c
index 2a0e21d..4aedf03 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);
diff --git a/net/core/sock.c b/net/core/sock.c
index 5b6beba..2bd9b3f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -914,6 +914,13 @@ 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 +1184,10 @@ 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;
}
@@ -2319,6 +2330,7 @@ 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;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index be1f64d..8f032ba 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -58,7 +58,7 @@
#include <net/ipv6.h>
#include <net/ip.h>
#include <net/dsa.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
__setup("ether=", netdev_boot_setup);
@@ -133,7 +133,7 @@ int eth_rebuild_header(struct sk_buff *skb)
return arp_find(eth->h_dest, skb);
#endif
default:
- printk(KERN_DEBUG
+ netdev_dbg(dev,
"%s: unable to resolve type %X addresses.\n",
dev->name, ntohs(eth->h_proto));
@@ -169,20 +169,9 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
else
skb->pkt_type = PACKET_MULTICAST;
}
-
- /*
- * This ALLMULTI check should be redundant by 1.4
- * so don't forget to remove it.
- *
- * Seems, you forgot to remove it. All silly devices
- * seems to set IFF_PROMISC.
- */
-
- else if (1 /*dev->flags&IFF_PROMISC */ ) {
- if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
- dev->dev_addr)))
- skb->pkt_type = PACKET_OTHERHOST;
- }
+ else if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
+ dev->dev_addr)))
+ skb->pkt_type = PACKET_OTHERHOST;
/*
* Some variants of DSA tagging don't have an ethertype field
@@ -190,12 +179,13 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
* variants has been configured on the receiving interface,
* and if so, set skb->protocol without looking at the packet.
*/
- if (netdev_uses_dsa_tags(dev))
+ if (unlikely(netdev_uses_dsa_tags(dev)))
return htons(ETH_P_DSA);
- if (netdev_uses_trailer_tags(dev))
+
+ if (unlikely(netdev_uses_trailer_tags(dev)))
return htons(ETH_P_TRAILER);
- if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN)
+ if (likely(ntohs(eth->h_proto) >= ETH_P_802_3_MIN))
return eth->h_proto;
/*
@@ -204,7 +194,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
* layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
* won't work for fault tolerant netware but does for the rest.
*/
- if (skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF)
+ if (unlikely(skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF))
return htons(ETH_P_802_3);
/*
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5f7d11a..5c0e8bc 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,6 +353,9 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
saddr = fib_compute_spec_dst(skb);
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
+
if (icmp_param->replyopts.opt.opt.optlen) {
ipc.opt = &icmp_param->replyopts.opt;
if (ipc.opt->opt.srr)
@@ -608,6 +611,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
ipc.addr = iph->saddr;
ipc.opt = &icmp_param->replyopts.opt;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
type, code, icmp_param);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6acb541..7ac7aa1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,27 +29,19 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
EXPORT_SYMBOL(inet_csk_timer_bug_msg);
#endif
-/*
- * This struct holds the first and last local port number.
- */
-struct local_ports sysctl_local_ports __read_mostly = {
- .lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock),
- .range = { 32768, 61000 },
-};
-
unsigned long *sysctl_local_reserved_ports;
EXPORT_SYMBOL(sysctl_local_reserved_ports);
-void inet_get_local_port_range(int *low, int *high)
+void inet_get_local_port_range(struct net *net, int *low, int *high)
{
unsigned int seq;
do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
- *low = sysctl_local_ports.range[0];
- *high = sysctl_local_ports.range[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ *low = net->ipv4.sysctl_local_ports.range[0];
+ *high = net->ipv4.sysctl_local_ports.range[1];
+ } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
}
EXPORT_SYMBOL(inet_get_local_port_range);
@@ -116,7 +108,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
int remaining, rover, low, high;
again:
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
smallest_rover = rover = net_random() % remaining + low;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7bd8983..2779037 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -494,7 +494,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
u32 offset = hint + port_offset;
struct inet_timewait_sock *tw = NULL;
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
local_bh_disable();
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a04d872..7d8357b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1060,6 +1060,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
rt->dst.dev->mtu : dst_mtu(&rt->dst);
cork->dst = &rt->dst;
cork->length = 0;
+ cork->ttl = ipc->ttl;
+ cork->tos = ipc->tos;
+ cork->priority = ipc->priority;
cork->tx_flags = ipc->tx_flags;
return 0;
@@ -1311,7 +1314,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
if (cork->flags & IPCORK_OPT)
opt = cork->opt;
- if (rt->rt_type == RTN_MULTICAST)
+ if (cork->ttl != 0)
+ ttl = cork->ttl;
+ else if (rt->rt_type == RTN_MULTICAST)
ttl = inet->mc_ttl;
else
ttl = ip_select_ttl(inet, &rt->dst);
@@ -1319,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
- iph->tos = inet->tos;
+ iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
iph->frag_off = df;
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
@@ -1331,7 +1336,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
ip_options_build(skb, opt, cork->addr, rt, 0);
}
- skb->priority = sk->sk_priority;
+ skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
skb->mark = sk->sk_mark;
/*
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1481,6 +1486,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
ipc.addr = daddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
if (replyopts.opt.opt.optlen) {
ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f11..56e3445 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(ip_cmsg_recv);
int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
{
- int err;
+ int err, val;
struct cmsghdr *cmsg;
for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
@@ -215,6 +215,24 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
ipc->addr = info->ipi_spec_dst.s_addr;
break;
}
+ case IP_TTL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->ttl = val;
+ break;
+ case IP_TOS:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 0 || val > 255)
+ return -EINVAL;
+ ipc->tos = val;
+ ipc->priority = rt_tos2priority(ipc->tos);
+ break;
+
default:
return -EINVAL;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e805e7b..91f69bc 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -49,70 +49,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly;
static int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
-static int vti_err(struct sk_buff *skb, u32 info)
-{
-
- /* All the routers (except for Linux) return only
- * 8 bytes of packet payload. It means, that precise relaying of
- * ICMP in the real Internet is absolutely infeasible.
- */
- struct net *net = dev_net(skb->dev);
- struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- struct iphdr *iph = (struct iphdr *)skb->data;
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
- struct ip_tunnel *t;
- int err;
-
- switch (type) {
- default:
- case ICMP_PARAMETERPROB:
- return 0;
-
- case ICMP_DEST_UNREACH:
- switch (code) {
- case ICMP_SR_FAILED:
- case ICMP_PORT_UNREACH:
- /* Impossible event. */
- return 0;
- default:
- /* All others are translated to HOST_UNREACH. */
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return 0;
- break;
- }
-
- err = -ENOENT;
-
- t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
- iph->daddr, iph->saddr, 0);
- if (t == NULL)
- goto out;
-
- if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, IPPROTO_IPIP, 0);
- err = 0;
- goto out;
- }
-
- err = 0;
- if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
- goto out;
-
- if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
- t->err_count++;
- else
- t->err_count = 1;
- t->err_time = jiffies;
-out:
- return err;
-}
-
/* We dont digest the packet therefore let the packet pass */
static int vti_rcv(struct sk_buff *skb)
{
@@ -296,9 +232,8 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev)
iph->ihl = 5;
}
-static struct xfrm_tunnel vti_handler __read_mostly = {
+static struct xfrm_tunnel_notifier vti_handler __read_mostly = {
.handler = vti_rcv,
- .err_handler = vti_err,
.priority = 1,
};
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index d7d9882..a626104 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -237,11 +237,11 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
unsigned int seq;
do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
}
@@ -713,6 +713,8 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.opt = NULL;
ipc.oif = sk->sk_bound_dev_if;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
sock_tx_timestamp(sk, &ipc.tx_flags);
@@ -744,7 +746,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
return -EINVAL;
faddr = ipc.opt->opt.faddr;
}
- tos = RT_TOS(inet->tos);
+ tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 193db03..b2fa14c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -519,6 +519,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
@@ -558,7 +560,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
daddr = ipc.opt->opt.faddr;
}
}
- tos = RT_CONN_FLAGS(sk);
+ tos = get_rtconn_flags(&ipc, sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 14a15c4..15e0241 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -89,8 +89,7 @@ __u32 cookie_init_timestamp(struct request_sock *req)
static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
- __be16 dport, __u32 sseq, __u32 count,
- __u32 data)
+ __be16 dport, __u32 sseq, __u32 data)
{
/*
* Compute the secure sequence number.
@@ -102,7 +101,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
* As an extra hack, we add a small "data" value that encodes the
* MSS into the second hash value.
*/
-
+ u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -114,22 +113,21 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
* If the syncookie is bad, the data returned will be out of
* range. This must be checked by the caller.
*
- * The count value used to generate the cookie must be within
- * "maxdiff" if the current (passed-in) "count". The return value
- * is (__u32)-1 if this test fails.
+ * The count value used to generate the cookie must be less than
+ * MAX_SYNCOOKIE_AGE minutes in the past.
+ * The return value (__u32)-1 if this test fails.
*/
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
- __be16 sport, __be16 dport, __u32 sseq,
- __u32 count, __u32 maxdiff)
+ __be16 sport, __be16 dport, __u32 sseq)
{
- __u32 diff;
+ u32 diff, count = tcp_cookie_time();
/* Strip away the layers from the cookie */
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
- if (diff >= maxdiff)
+ if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
@@ -138,22 +136,22 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
}
/*
- * MSS Values are taken from the 2009 paper
- * 'Measuring TCP Maximum Segment Size' by S. Alcock and R. Nelson:
- * - values 1440 to 1460 accounted for 80% of observed mss values
- * - values outside the 536-1460 range are rare (<0.2%).
+ * MSS Values are chosen based on the 2011 paper
+ * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
+ * Values ..
+ * .. lower than 536 are rare (< 0.2%)
+ * .. between 537 and 1299 account for less than < 1.5% of observed values
+ * .. in the 1300-1349 range account for about 15 to 20% of observed mss values
+ * .. exceeding 1460 are very rare (< 0.04%)
*
- * Table must be sorted.
+ * 1460 is the single most frequently announced mss value (30 to 46% depending
+ * on monitor location). Table must be sorted.
*/
static __u16 const msstab[] = {
- 64,
- 512,
536,
- 1024,
- 1440,
+ 1300,
+ 1440, /* 1440, 1452: PPPoE */
1460,
- 4312,
- 8960,
};
/*
@@ -173,7 +171,7 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
th->source, th->dest, ntohl(th->seq),
- jiffies / (HZ * 60), mssind);
+ mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
@@ -189,13 +187,6 @@ __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
}
/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-/*
* Check if a ack sequence number is a valid syncookie.
* Return the decoded mss if it is, or 0 if not.
*/
@@ -204,9 +195,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
- th->source, th->dest, seq,
- jiffies / (HZ * 60),
- COUNTER_TRIES);
+ th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 540279f..c08f096 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -43,12 +43,12 @@ static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
/* Update system visible IP port range */
-static void set_local_port_range(int range[2])
+static void set_local_port_range(struct net *net, int range[2])
{
- write_seqlock(&sysctl_local_ports.lock);
- sysctl_local_ports.range[0] = range[0];
- sysctl_local_ports.range[1] = range[1];
- write_sequnlock(&sysctl_local_ports.lock);
+ write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+ net->ipv4.sysctl_local_ports.range[0] = range[0];
+ net->ipv4.sysctl_local_ports.range[1] = range[1];
+ write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
}
/* Validate changes from /proc interface. */
@@ -56,6 +56,8 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ struct net *net =
+ container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
int ret;
int range[2];
struct ctl_table tmp = {
@@ -66,14 +68,15 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
.extra2 = &ip_local_port_range_max,
};
- inet_get_local_port_range(range, range + 1);
+ inet_get_local_port_range(net, &range[0], &range[1]);
+
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (range[1] < range[0])
ret = -EINVAL;
else
- set_local_port_range(range);
+ set_local_port_range(net, range);
}
return ret;
@@ -83,23 +86,27 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
{
kgid_t *data = table->data;
+ struct net *net =
+ container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
unsigned int seq;
do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
}
/* Update system visible IP port range */
static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
{
kgid_t *data = table->data;
- write_seqlock(&sysctl_local_ports.lock);
+ struct net *net =
+ container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+ write_seqlock(&net->ipv4.sysctl_local_ports.lock);
data[0] = low;
data[1] = high;
- write_sequnlock(&sysctl_local_ports.lock);
+ write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
}
/* Validate changes from /proc interface. */
@@ -475,13 +482,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "ip_local_port_range",
- .data = &sysctl_local_ports.range,
- .maxlen = sizeof(sysctl_local_ports.range),
- .mode = 0644,
- .proc_handler = ipv4_local_port_range,
- },
- {
.procname = "ip_local_reserved_ports",
.data = NULL, /* initialized in sysctl_ipv4_init */
.maxlen = 65536,
@@ -854,6 +854,13 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "ip_local_port_range",
+ .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range),
+ .data = &init_net.ipv4.sysctl_local_ports.range,
+ .mode = 0644,
+ .proc_handler = ipv4_local_port_range,
+ },
+ {
.procname = "tcp_mem",
.maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem),
.mode = 0644,
@@ -888,6 +895,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
&net->ipv4.sysctl_ping_group_range;
table[7].data =
&net->ipv4.sysctl_tcp_ecn;
+ table[8].data =
+ &net->ipv4.sysctl_local_ports.range;
/* Don't export sysctls to unprivileged users */
if (net->user_ns != &init_user_ns)
@@ -901,6 +910,13 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
+ /*
+ * Set defaults for local port range
+ */
+ seqlock_init(&net->ipv4.sysctl_local_ports.lock);
+ net->ipv4.sysctl_local_ports.range[0] = 32768;
+ net->ipv4.sysctl_local_ports.range[1] = 61000;
+
tcp_init_mem(net);
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 25a89ea..66aa816 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -355,6 +355,12 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
tcp_default_init_rwnd(mss);
+ /* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
+ * Allow enough cushion so that sender is not limited by our window
+ */
+ if (sysctl_tcp_moderate_rcvbuf)
+ rcvmem <<= 2;
+
if (sk->sk_rcvbuf < rcvmem)
sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
}
@@ -373,6 +379,8 @@ void tcp_init_buffer_space(struct sock *sk)
tcp_fixup_sndbuf(sk);
tp->rcvq_space.space = tp->rcv_wnd;
+ tp->rcvq_space.time = tcp_time_stamp;
+ tp->rcvq_space.seq = tp->copied_seq;
maxwin = tcp_full_space(sk);
@@ -512,48 +520,62 @@ void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int time;
- int space;
-
- if (tp->rcvq_space.time == 0)
- goto new_measure;
+ int copied;
time = tcp_time_stamp - tp->rcvq_space.time;
if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0)
return;
- space = 2 * (tp->copied_seq - tp->rcvq_space.seq);
+ /* Number of bytes copied to user in last RTT */
+ copied = tp->copied_seq - tp->rcvq_space.seq;
+ if (copied <= tp->rcvq_space.space)
+ goto new_measure;
+
+ /* A bit of theory :
+ * copied = bytes received in previous RTT, our base window
+ * To cope with packet losses, we need a 2x factor
+ * To cope with slow start, and sender growing its cwin by 100 %
+ * every RTT, we need a 4x factor, because the ACK we are sending
+ * now is for the next RTT, not the current one :
+ * <prev RTT . ><current RTT .. ><next RTT .... >
+ */
+
+ if (sysctl_tcp_moderate_rcvbuf &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int rcvwin, rcvmem, rcvbuf;
- space = max(tp->rcvq_space.space, space);
+ /* minimal window to cope with packet losses, assuming
+ * steady state. Add some cushion because of small variations.
+ */
+ rcvwin = (copied << 1) + 16 * tp->advmss;
- if (tp->rcvq_space.space != space) {
- int rcvmem;
+ /* If rate increased by 25%,
+ * assume slow start, rcvwin = 3 * copied
+ * If rate increased by 50%,
+ * assume sender can use 2x growth, rcvwin = 4 * copied
+ */
+ if (copied >=
+ tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) {
+ if (copied >=
+ tp->rcvq_space.space + (tp->rcvq_space.space >> 1))
+ rcvwin <<= 1;
+ else
+ rcvwin += (rcvwin >> 1);
+ }
- tp->rcvq_space.space = space;
+ rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
+ while (tcp_win_from_space(rcvmem) < tp->advmss)
+ rcvmem += 128;
- if (sysctl_tcp_moderate_rcvbuf &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- int new_clamp = space;
+ rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]);
+ if (rcvbuf > sk->sk_rcvbuf) {
+ sk->sk_rcvbuf = rcvbuf;
- /* Receive space grows, normalize in order to
- * take into account packet headers and sk_buff
- * structure overhead.
- */
- space /= tp->advmss;
- if (!space)
- space = 1;
- rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
- while (tcp_win_from_space(rcvmem) < tp->advmss)
- rcvmem += 128;
- space *= rcvmem;
- space = min(space, sysctl_tcp_rmem[2]);
- if (space > sk->sk_rcvbuf) {
- sk->sk_rcvbuf = space;
-
- /* Make the window clamp follow along. */
- tp->window_clamp = new_clamp;
- }
+ /* Make the window clamp follow along. */
+ tp->window_clamp = rcvwin;
}
}
+ tp->rcvq_space.space = copied;
new_measure:
tp->rcvq_space.seq = tp->copied_seq;
@@ -713,7 +735,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
if (tp->srtt > 8 + 2)
do_div(rate, tp->srtt);
- sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+ sk->sk_pacing_rate = min_t(u64, rate, sk->sk_max_pacing_rate);
}
/* Calculate rto without backoff. This is the second half of Van Jacobson's
@@ -5674,8 +5696,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
tcp_init_congestion_control(sk);
tcp_mtup_init(sk);
- tcp_init_buffer_space(sk);
tp->copied_seq = tp->rcv_nxt;
+ tcp_init_buffer_space(sk);
}
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0ca44df..c41833e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -219,7 +219,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
unsigned short first, last;
DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
rand = net_random();
@@ -855,6 +855,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
@@ -938,7 +940,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
faddr = ipc.opt->opt.faddr;
connected = 0;
}
- tos = RT_TOS(inet->tos);
+ tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index b5663c3..31b1815 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -16,13 +16,13 @@
#include <net/xfrm.h>
/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel __rcu *rcv_notify_handlers __read_mostly;
+static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex);
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
{
- struct xfrm_tunnel __rcu **pprev;
- struct xfrm_tunnel *t;
+ struct xfrm_tunnel_notifier __rcu **pprev;
+ struct xfrm_tunnel_notifier *t;
int ret = -EEXIST;
int priority = handler->priority;
@@ -50,10 +50,10 @@ err:
}
EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register);
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
{
- struct xfrm_tunnel __rcu **pprev;
- struct xfrm_tunnel *t;
+ struct xfrm_tunnel_notifier __rcu **pprev;
+ struct xfrm_tunnel_notifier *t;
int ret = -ENOENT;
mutex_lock(&xfrm4_mode_tunnel_input_mutex);
@@ -134,7 +134,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- struct xfrm_tunnel *handler;
+ struct xfrm_tunnel_notifier *handler;
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7c96100..4966b12 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1028,52 +1028,4 @@ out_unregister_tcp_proto:
}
module_init(inet6_init);
-static void __exit inet6_exit(void)
-{
- if (disable_ipv6_mod)
- return;
-
- /* First of all disallow new sockets creation. */
- sock_unregister(PF_INET6);
- /* Disallow any further netlink messages */
- rtnl_unregister_all(PF_INET6);
-
- udpv6_exit();
- udplitev6_exit();
- tcpv6_exit();
-
- /* Cleanup code parts. */
- ipv6_packet_cleanup();
- ipv6_frag_exit();
- ipv6_exthdrs_exit();
- addrconf_cleanup();
- ip6_flowlabel_cleanup();
- ndisc_late_cleanup();
- ip6_route_cleanup();
-#ifdef CONFIG_PROC_FS
-
- /* Cleanup code parts. */
- if6_proc_exit();
- ipv6_misc_proc_exit();
- udplite6_proc_exit();
- raw6_proc_exit();
-#endif
- ipv6_netfilter_fini();
- ipv6_stub = NULL;
- igmp6_cleanup();
- ndisc_cleanup();
- ip6_mr_cleanup();
- icmpv6_cleanup();
- rawv6_exit();
-
- unregister_pernet_subsys(&inet6_net_ops);
- proto_unregister(&rawv6_prot);
- proto_unregister(&udplitev6_prot);
- proto_unregister(&udpv6_prot);
- proto_unregister(&tcpv6_prot);
-
- rcu_barrier(); /* Wait for completion of call_rcu()'s */
-}
-module_exit(inet6_exit);
-
MODULE_ALIAS_NETPROTO(PF_INET6);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5bec666..5550a81 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1529,25 +1529,6 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
fib6_walk(&c.w);
}
-void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg),
- int prune, void *arg)
-{
- struct fib6_table *table;
- struct hlist_head *head;
- unsigned int h;
-
- rcu_read_lock();
- for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
- head = &net->ipv6.fib_table_hash[h];
- hlist_for_each_entry_rcu(table, head, tb6_hlist) {
- read_lock_bh(&table->tb6_lock);
- fib6_clean_tree(net, &table->tb6_root,
- func, prune, arg);
- read_unlock_bh(&table->tb6_lock);
- }
- }
- rcu_read_unlock();
-}
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
@@ -1782,3 +1763,189 @@ void fib6_gc_cleanup(void)
unregister_pernet_subsys(&fib6_net_ops);
kmem_cache_destroy(fib6_node_kmem);
}
+
+#ifdef CONFIG_PROC_FS
+
+struct ipv6_route_iter {
+ struct seq_net_private p;
+ struct fib6_walker_t w;
+ loff_t skip;
+ struct fib6_table *tbl;
+ __u32 sernum;
+};
+
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+ struct rt6_info *rt = v;
+ struct ipv6_route_iter *iter = seq->private;
+
+ seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
+#else
+ seq_puts(seq, "00000000000000000000000000000000 00 ");
+#endif
+ if (rt->rt6i_flags & RTF_GATEWAY)
+ seq_printf(seq, "%pi6", &rt->rt6i_gateway);
+ else
+ seq_puts(seq, "00000000000000000000000000000000");
+
+ seq_printf(seq, " %08x %08x %08x %08x %8s\n",
+ rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
+ rt->dst.__use, rt->rt6i_flags,
+ rt->dst.dev ? rt->dst.dev->name : "");
+ iter->w.leaf = NULL;
+ return 0;
+}
+
+static int ipv6_route_yield(struct fib6_walker_t *w)
+{
+ struct ipv6_route_iter *iter = w->args;
+
+ if (!iter->skip)
+ return 1;
+
+ do {
+ iter->w.leaf = iter->w.leaf->dst.rt6_next;
+ iter->skip--;
+ if (!iter->skip && iter->w.leaf)
+ return 1;
+ } while (iter->w.leaf);
+
+ return 0;
+}
+
+static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter)
+{
+ memset(&iter->w, 0, sizeof(iter->w));
+ iter->w.func = ipv6_route_yield;
+ iter->w.root = &iter->tbl->tb6_root;
+ iter->w.state = FWS_INIT;
+ iter->w.node = iter->w.root;
+ iter->w.args = iter;
+ iter->sernum = iter->w.root->fn_sernum;
+ INIT_LIST_HEAD(&iter->w.lh);
+ fib6_walker_link(&iter->w);
+}
+
+static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl,
+ struct net *net)
+{
+ unsigned int h;
+ struct hlist_node *node;
+
+ if (tbl) {
+ h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1;
+ node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist));
+ } else {
+ h = 0;
+ node = NULL;
+ }
+
+ while (!node && h < FIB6_TABLE_HASHSZ) {
+ node = rcu_dereference_bh(
+ hlist_first_rcu(&net->ipv6.fib_table_hash[h++]));
+ }
+ return hlist_entry_safe(node, struct fib6_table, tb6_hlist);
+}
+
+static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
+{
+ if (iter->sernum != iter->w.root->fn_sernum) {
+ iter->sernum = iter->w.root->fn_sernum;
+ iter->w.state = FWS_INIT;
+ iter->w.node = iter->w.root;
+ WARN_ON(iter->w.skip);
+ iter->w.skip = iter->w.count;
+ }
+}
+
+static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ int r;
+ struct rt6_info *n;
+ struct net *net = seq_file_net(seq);
+ struct ipv6_route_iter *iter = seq->private;
+
+ if (!v)
+ goto iter_table;
+
+ n = ((struct rt6_info *)v)->dst.rt6_next;
+ if (n) {
+ ++*pos;
+ return n;
+ }
+
+iter_table:
+ ipv6_route_check_sernum(iter);
+ read_lock(&iter->tbl->tb6_lock);
+ r = fib6_walk_continue(&iter->w);
+ read_unlock(&iter->tbl->tb6_lock);
+ if (r > 0) {
+ if (v)
+ ++*pos;
+ return iter->w.leaf;
+ } else if (r < 0) {
+ fib6_walker_unlink(&iter->w);
+ return NULL;
+ }
+ fib6_walker_unlink(&iter->w);
+
+ iter->tbl = ipv6_route_seq_next_table(iter->tbl, net);
+ if (!iter->tbl)
+ return NULL;
+
+ ipv6_route_seq_setup_walk(iter);
+ goto iter_table;
+}
+
+static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU_BH)
+{
+ struct net *net = seq_file_net(seq);
+ struct ipv6_route_iter *iter = seq->private;
+
+ rcu_read_lock_bh();
+ iter->tbl = ipv6_route_seq_next_table(NULL, net);
+ iter->skip = *pos;
+
+ if (iter->tbl) {
+ ipv6_route_seq_setup_walk(iter);
+ return ipv6_route_seq_next(seq, NULL, pos);
+ } else {
+ return NULL;
+ }
+}
+
+static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
+{
+ struct fib6_walker_t *w = &iter->w;
+ return w->node && !(w->state == FWS_U && w->node == w->root);
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU_BH)
+{
+ struct ipv6_route_iter *iter = seq->private;
+
+ if (ipv6_route_iter_active(iter))
+ fib6_walker_unlink(&iter->w);
+
+ rcu_read_unlock_bh();
+}
+
+static const struct seq_operations ipv6_route_seq_ops = {
+ .start = ipv6_route_seq_start,
+ .next = ipv6_route_seq_next,
+ .stop = ipv6_route_seq_stop,
+ .show = ipv6_route_seq_show
+};
+
+int ipv6_route_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &ipv6_route_seq_ops,
+ sizeof(struct ipv6_route_iter));
+}
+
+#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c979dd9..c3130ff 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1137,7 +1137,6 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
- fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
@@ -1236,7 +1235,6 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
- fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
@@ -1258,7 +1256,6 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
- fl6.flowi6_flags = 0;
fl6.daddr = msg->dest;
fl6.saddr = iph->daddr;
@@ -2800,56 +2797,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
#ifdef CONFIG_PROC_FS
-struct rt6_proc_arg
-{
- char *buffer;
- int offset;
- int length;
- int skip;
- int len;
-};
-
-static int rt6_info_route(struct rt6_info *rt, void *p_arg)
-{
- struct seq_file *m = p_arg;
-
- seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
-
-#ifdef CONFIG_IPV6_SUBTREES
- seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
-#else
- seq_puts(m, "00000000000000000000000000000000 00 ");
-#endif
- if (rt->rt6i_flags & RTF_GATEWAY) {
- seq_printf(m, "%pi6", &rt->rt6i_gateway);
- } else {
- seq_puts(m, "00000000000000000000000000000000");
- }
- seq_printf(m, " %08x %08x %08x %08x %8s\n",
- rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
- rt->dst.__use, rt->rt6i_flags,
- rt->dst.dev ? rt->dst.dev->name : "");
- return 0;
-}
-
-static int ipv6_route_show(struct seq_file *m, void *v)
-{
- struct net *net = (struct net *)m->private;
- fib6_clean_all_ro(net, rt6_info_route, 0, m);
- return 0;
-}
-
-static int ipv6_route_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, ipv6_route_show);
-}
-
static const struct file_operations ipv6_route_proc_fops = {
.owner = THIS_MODULE,
.open = ipv6_route_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release_net,
+ .release = seq_release_net,
};
static int rt6_stats_seq_show(struct seq_file *seq, void *v)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bf63ac8..d703218 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,26 +24,21 @@
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
-/* Table must be sorted. */
+/* RFC 2460, Section 8.3:
+ * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
+ *
+ * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows
+ * using higher values than ipv4 tcp syncookies.
+ * The other values are chosen based on ethernet (1500 and 9k MTU), plus
+ * one that accounts for common encap (PPPoe) overhead. Table must be sorted.
+ */
static __u16 const msstab[] = {
- 64,
- 512,
- 536,
- 1280 - 60,
+ 1280 - 60, /* IPV6_MIN_MTU - 60 */
1480 - 60,
1500 - 60,
- 4460 - 60,
9000 - 60,
};
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-
static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
@@ -86,8 +81,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__be16 sport, __be16 dport, __u32 sseq,
- __u32 count, __u32 data)
+ __u32 data)
{
+ u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -96,15 +92,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
const struct in6_addr *daddr, __be16 sport,
- __be16 dport, __u32 sseq, __u32 count,
- __u32 maxdiff)
+ __be16 dport, __u32 sseq)
{
- __u32 diff;
+ __u32 diff, count = tcp_cookie_time();
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
- if (diff >= maxdiff)
+ if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
@@ -125,8 +120,7 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
*mssp = msstab[mssind];
return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
- th->dest, ntohl(th->seq),
- jiffies / (HZ * 60), mssind);
+ th->dest, ntohl(th->seq), mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
@@ -146,8 +140,7 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
- th->source, th->dest, seq,
- jiffies / (HZ * 60), COUNTER_TRIES);
+ th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index a481c03..56e22b7 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -173,7 +173,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
skb->local_df = 1;
- inet_get_local_port_range(&port_min, &port_max);
+ inet_get_local_port_range(net, &port_min, &port_max);
src_port = vxlan_src_port(port_min, port_max, skb);
err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 189e3c5..272d8e9 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -231,14 +231,14 @@ override:
}
if (R_tab) {
police->rate_present = true;
- psched_ratecfg_precompute(&police->rate, &R_tab->rate);
+ psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0);
qdisc_put_rtab(R_tab);
} else {
police->rate_present = false;
}
if (P_tab) {
police->peak_present = true;
- psched_ratecfg_precompute(&police->peak, &P_tab->rate);
+ psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0);
qdisc_put_rtab(P_tab);
} else {
police->peak_present = false;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index d76a35d..636d913 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -137,7 +137,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
struct nlattr **tb,
struct nlattr *est)
{
- int err = -EINVAL;
+ int err;
struct tcf_exts e;
struct tcf_ematch_tree t;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 7c3de6f..e5cef956 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -793,8 +793,10 @@ static int em_meta_change(struct tcf_proto *tp, void *data, int len,
goto errout;
meta = kzalloc(sizeof(*meta), GFP_KERNEL);
- if (meta == NULL)
+ if (meta == NULL) {
+ err = -ENOMEM;
goto errout;
+ }
memcpy(&meta->lvalue.hdr, &hdr->left, sizeof(hdr->left));
memcpy(&meta->rvalue.hdr, &hdr->right, sizeof(hdr->right));
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a74e278..e7121d2 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -910,11 +910,12 @@ void dev_shutdown(struct net_device *dev)
}
void psched_ratecfg_precompute(struct psched_ratecfg *r,
- const struct tc_ratespec *conf)
+ const struct tc_ratespec *conf,
+ u64 rate64)
{
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
- r->rate_bytes_ps = conf->rate;
+ r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
r->mult = 1;
/*
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 863846c..0e1e38b 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -997,6 +997,8 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
[TCA_HTB_CTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
[TCA_HTB_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
[TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 },
+ [TCA_HTB_RATE64] = { .type = NLA_U64 },
+ [TCA_HTB_CEIL64] = { .type = NLA_U64 },
};
static void htb_work_func(struct work_struct *work)
@@ -1114,6 +1116,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
opt.level = cl->level;
if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
+ if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) &&
+ nla_put_u64(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps))
+ goto nla_put_failure;
+ if ((cl->ceil.rate_bytes_ps >= (1ULL << 32)) &&
+ nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps))
+ goto nla_put_failure;
nla_nest_end(skb, nest);
spin_unlock_bh(root_lock);
@@ -1332,6 +1340,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_opt *hopt;
+ u64 rate64, ceil64;
/* extract all subattrs from opt attr */
if (!opt)
@@ -1491,8 +1500,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
cl->prio = TC_HTB_NUMPRIO - 1;
}
- psched_ratecfg_precompute(&cl->rate, &hopt->rate);
- psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
+ rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
+
+ ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;
+
+ psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
+ psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);
cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1aaf1b6..b057122 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -341,9 +341,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
q->tokens = q->buffer;
q->ptokens = q->mtu;
- psched_ratecfg_precompute(&q->rate, &rtab->rate);
+ psched_ratecfg_precompute(&q->rate, &rtab->rate, 0);
if (ptab) {
- psched_ratecfg_precompute(&q->peak, &ptab->rate);
+ psched_ratecfg_precompute(&q->peak, &ptab->rate, 0);
q->peak_present = true;
} else {
q->peak_present = false;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 911b71b..72046b9 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5890,7 +5890,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
int low, high, remaining, index;
unsigned int rover;
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(sock_net(sk), &low, &high);
remaining = (high - low) + 1;
rover = net_random() % remaining + low;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b9c3f9e..d6e7f98 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -468,7 +468,7 @@ expired:
}
err = __xfrm_state_delete(x);
- if (!err && x->id.spi)
+ if (!err)
km_state_expired(x, 1, 0);
xfrm_audit_state_delete(x, err ? 0 : 1,
generated by cgit v0.10.2 at 2024-09-22 09:03:19 (GMT)