summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c55
-rw-r--r--net/8021q/vlan.h4
-rw-r--r--net/8021q/vlan_dev.c15
-rw-r--r--net/bluetooth/hci_sysfs.c4
-rw-r--r--net/bluetooth/l2cap.c9
-rw-r--r--net/bridge/br_if.c19
-rw-r--r--net/can/raw.c2
-rw-r--r--net/compat.c3
-rw-r--r--net/core/dev.c177
-rw-r--r--net/core/net-sysfs.c8
-rw-r--r--net/core/pktgen.c15
-rw-r--r--net/core/rtnetlink.c51
-rw-r--r--net/ipv4/inet_connection_sock.c34
-rw-r--r--net/ipv4/ip_gre.c55
-rw-r--r--net/ipv4/ip_sockglue.c9
-rw-r--r--net/ipv4/ipip.c66
-rw-r--r--net/ipv4/ipmr.c15
-rw-r--r--net/ipv4/syncookies.c27
-rw-r--r--net/ipv4/tcp.c59
-rw-r--r--net/ipv4/tcp_input.c30
-rw-r--r--net/ipv4/tcp_ipv4.c21
-rw-r--r--net/ipv4/tcp_minisocks.c14
-rw-r--r--net/ipv4/tcp_output.c18
-rw-r--r--net/ipv6/ip6_tunnel.c55
-rw-r--r--net/ipv6/ip6mr.c15
-rw-r--r--net/ipv6/ipv6_sockglue.c6
-rw-r--r--net/ipv6/sit.c135
-rw-r--r--net/ipv6/syncookies.c28
-rw-r--r--net/ipv6/tcp_ipv6.c3
-rw-r--r--net/ipv6/xfrm6_tunnel.c47
-rw-r--r--net/packet/af_packet.c5
-rw-r--r--net/unix/af_unix.c2
-rw-r--r--net/x25/x25_in.c2
-rw-r--r--net/x25/x25_route.c2
34 files changed, 655 insertions, 355 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 8836575f9d7..511afe72af3 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -140,7 +140,7 @@ static void vlan_rcu_free(struct rcu_head *rcu)
vlan_group_free(container_of(rcu, struct vlan_group, rcu));
}
-void unregister_vlan_dev(struct net_device *dev)
+void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
{
struct vlan_dev_info *vlan = vlan_dev_info(dev);
struct net_device *real_dev = vlan->real_dev;
@@ -159,12 +159,13 @@ void unregister_vlan_dev(struct net_device *dev)
if (real_dev->features & NETIF_F_HW_VLAN_FILTER)
ops->ndo_vlan_rx_kill_vid(real_dev, vlan_id);
- vlan_group_set_device(grp, vlan_id, NULL);
grp->nr_vlans--;
- synchronize_net();
-
- unregister_netdevice(dev);
+ if (!grp->killall) {
+ vlan_group_set_device(grp, vlan_id, NULL);
+ synchronize_net();
+ }
+ unregister_netdevice_queue(dev, head);
/* If the group is now empty, kill off the group. */
if (grp->nr_vlans == 0) {
@@ -183,6 +184,34 @@ void unregister_vlan_dev(struct net_device *dev)
dev_put(real_dev);
}
+void unregister_vlan_dev_alls(struct vlan_group *grp)
+{
+ LIST_HEAD(list);
+ int i;
+ struct net_device *vlandev;
+ struct vlan_group save;
+
+ memcpy(&save, grp, sizeof(save));
+ memset(&grp->vlan_devices_arrays, 0, sizeof(grp->vlan_devices_arrays));
+ grp->killall = 1;
+
+ synchronize_net();
+
+ /* Delete all VLANs for this dev. */
+ for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) {
+ vlandev = vlan_group_get_device(&save, i);
+ if (!vlandev)
+ continue;
+
+ unregister_vlan_dev(vlandev, &list);
+ if (grp->nr_vlans == 0)
+ break;
+ }
+ unregister_netdevice_many(&list);
+ for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
+ kfree(save.vlan_devices_arrays[i]);
+}
+
static void vlan_transfer_operstate(const struct net_device *dev,
struct net_device *vlandev)
{
@@ -524,19 +553,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
break;
case NETDEV_UNREGISTER:
- /* Delete all VLANs for this dev. */
- for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
- /* unregistration of last vlan destroys group, abort
- * afterwards */
- if (grp->nr_vlans == 1)
- i = VLAN_GROUP_ARRAY_LEN;
-
- unregister_vlan_dev(vlandev);
- }
+ unregister_vlan_dev_alls(grp);
break;
}
@@ -642,7 +659,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg)
err = -EPERM;
if (!capable(CAP_NET_ADMIN))
break;
- unregister_vlan_dev(dev);
+ unregister_vlan_dev(dev, NULL);
err = 0;
break;
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 82570bc2a18..68f9290e683 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -82,14 +82,14 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id);
void vlan_setup(struct net_device *dev);
int register_vlan_dev(struct net_device *dev);
-void unregister_vlan_dev(struct net_device *dev);
+void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
static inline u32 vlan_get_ingress_priority(struct net_device *dev,
u16 vlan_tci)
{
struct vlan_dev_info *vip = vlan_dev_info(dev);
- return vip->ingress_priority_map[(vlan_tci >> 13) & 0x7];
+ return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7];
}
#ifdef CONFIG_VLAN_8021Q_GVRP
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 4198ec5c8ab..790fd55ec31 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -393,7 +393,7 @@ int vlan_dev_set_egress_priority(const struct net_device *dev,
struct vlan_dev_info *vlan = vlan_dev_info(dev);
struct vlan_priority_tci_mapping *mp = NULL;
struct vlan_priority_tci_mapping *np;
- u32 vlan_qos = (vlan_prio << 13) & 0xE000;
+ u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;
/* See if a priority mapping exists.. */
mp = vlan->egress_priority_map[skb_prio & 0xF];
@@ -626,6 +626,17 @@ static int vlan_dev_fcoe_disable(struct net_device *dev)
rc = ops->ndo_fcoe_disable(real_dev);
return rc;
}
+
+static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
+{
+ struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ const struct net_device_ops *ops = real_dev->netdev_ops;
+ int rc = -EINVAL;
+
+ if (ops->ndo_fcoe_get_wwn)
+ rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
+ return rc;
+}
#endif
static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
@@ -791,6 +802,7 @@ static const struct net_device_ops vlan_netdev_ops = {
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
.ndo_fcoe_enable = vlan_dev_fcoe_enable,
.ndo_fcoe_disable = vlan_dev_fcoe_disable,
+ .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn,
#endif
};
@@ -813,6 +825,7 @@ static const struct net_device_ops vlan_netdev_accel_ops = {
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
.ndo_fcoe_enable = vlan_dev_fcoe_enable,
.ndo_fcoe_disable = vlan_dev_fcoe_disable,
+ .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn,
#endif
};
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 7f939ce2980..2bc6f6a8de6 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -92,6 +92,8 @@ static void add_conn(struct work_struct *work)
dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
+ dev_set_drvdata(&conn->dev, conn);
+
if (device_add(&conn->dev) < 0) {
BT_ERR("Failed to register connection device");
return;
@@ -144,8 +146,6 @@ void hci_conn_init_sysfs(struct hci_conn *conn)
conn->dev.class = bt_class;
conn->dev.parent = &hdev->dev;
- dev_set_drvdata(&conn->dev, conn);
-
device_initialize(&conn->dev);
INIT_WORK(&conn->work_add, add_conn);
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 4b66bd579f4..d65101d92ee 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -555,12 +555,12 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status)
conn->feat_mask = 0;
- setup_timer(&conn->info_timer, l2cap_info_timeout,
- (unsigned long) conn);
-
spin_lock_init(&conn->lock);
rwlock_init(&conn->chan_list.lock);
+ setup_timer(&conn->info_timer, l2cap_info_timeout,
+ (unsigned long) conn);
+
conn->disc_reason = 0x13;
return conn;
@@ -783,6 +783,9 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
/* Default config options */
pi->conf_len = 0;
pi->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+ skb_queue_head_init(TX_QUEUE(sk));
+ skb_queue_head_init(SREJ_QUEUE(sk));
+ INIT_LIST_HEAD(SREJ_LIST(sk));
}
static struct proto l2cap_proto = {
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index b1b3b0fbf41..2117e5ba24c 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -154,7 +154,7 @@ static void del_nbp(struct net_bridge_port *p)
}
/* called with RTNL */
-static void del_br(struct net_bridge *br)
+static void del_br(struct net_bridge *br, struct list_head *head)
{
struct net_bridge_port *p, *n;
@@ -165,7 +165,7 @@ static void del_br(struct net_bridge *br)
del_timer_sync(&br->gc_timer);
br_sysfs_delbr(br->dev);
- unregister_netdevice(br->dev);
+ unregister_netdevice_queue(br->dev, head);
}
static struct net_device *new_bridge_dev(struct net *net, const char *name)
@@ -323,7 +323,7 @@ int br_del_bridge(struct net *net, const char *name)
}
else
- del_br(netdev_priv(dev));
+ del_br(netdev_priv(dev), NULL);
rtnl_unlock();
return ret;
@@ -462,15 +462,14 @@ int br_del_if(struct net_bridge *br, struct net_device *dev)
void br_net_exit(struct net *net)
{
struct net_device *dev;
+ LIST_HEAD(list);
rtnl_lock();
-restart:
- for_each_netdev(net, dev) {
- if (dev->priv_flags & IFF_EBRIDGE) {
- del_br(netdev_priv(dev));
- goto restart;
- }
- }
+ for_each_netdev(net, dev)
+ if (dev->priv_flags & IFF_EBRIDGE)
+ del_br(netdev_priv(dev), &list);
+
+ unregister_netdevice_many(&list);
rtnl_unlock();
}
diff --git a/net/can/raw.c b/net/can/raw.c
index 962fc9f1d0c..6e77db58b9e 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -424,8 +424,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
if (level != SOL_CAN_RAW)
return -EINVAL;
- if (optlen < 0)
- return -EINVAL;
switch (optname) {
diff --git a/net/compat.c b/net/compat.c
index e13f5256fd2..6a2f75fb3f4 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -390,9 +390,6 @@ asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
int err;
struct socket *sock;
- if (optlen < 0)
- return -EINVAL;
-
if ((sock = sockfd_lookup(fd, &err))!=NULL)
{
err = security_socket_setsockopt(sock,level,optname);
diff --git a/net/core/dev.c b/net/core/dev.c
index fa88dcd476d..68a1bb68b5a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -193,18 +193,15 @@ static struct list_head ptype_all __read_mostly; /* Taps */
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
-#define NETDEV_HASHBITS 8
-#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
-
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
- return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)];
+ return &net->dev_name_head[hash & (NETDEV_HASHENTRIES - 1)];
}
static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
{
- return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
+ return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
}
/* Device list insertion */
@@ -217,12 +214,15 @@ static int list_netdevice(struct net_device *dev)
write_lock_bh(&dev_base_lock);
list_add_tail(&dev->dev_list, &net->dev_base_head);
hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
- hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex));
+ hlist_add_head_rcu(&dev->index_hlist,
+ dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
return 0;
}
-/* Device list removal */
+/* Device list removal
+ * caller must respect a RCU grace period before freeing/reusing dev
+ */
static void unlist_netdevice(struct net_device *dev)
{
ASSERT_RTNL();
@@ -231,7 +231,7 @@ static void unlist_netdevice(struct net_device *dev)
write_lock_bh(&dev_base_lock);
list_del(&dev->dev_list);
hlist_del(&dev->name_hlist);
- hlist_del(&dev->index_hlist);
+ hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
}
@@ -649,6 +649,31 @@ struct net_device *__dev_get_by_index(struct net *net, int ifindex)
}
EXPORT_SYMBOL(__dev_get_by_index);
+/**
+ * dev_get_by_index_rcu - find a device by its ifindex
+ * @net: the applicable net namespace
+ * @ifindex: index of device
+ *
+ * Search for an interface by index. Returns %NULL if the device
+ * is not found or a pointer to the device. The device has not
+ * had its reference counter increased so the caller must be careful
+ * about locking. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
+{
+ struct hlist_node *p;
+ struct net_device *dev;
+ struct hlist_head *head = dev_index_hash(net, ifindex);
+
+ hlist_for_each_entry_rcu(dev, p, head, index_hlist)
+ if (dev->ifindex == ifindex)
+ return dev;
+
+ return NULL;
+}
+EXPORT_SYMBOL(dev_get_by_index_rcu);
+
/**
* dev_get_by_index - find a device by its ifindex
@@ -665,11 +690,11 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_index(net, ifindex);
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
dev_hold(dev);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return dev;
}
EXPORT_SYMBOL(dev_get_by_index);
@@ -2303,7 +2328,7 @@ int netif_receive_skb(struct sk_buff *skb)
if (!skb->tstamp.tv64)
net_timestamp(skb);
- if (skb->vlan_tci && vlan_hwaccel_do_receive(skb))
+ if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
return NET_RX_SUCCESS;
/* if we've gotten here through NAPI, check netpoll */
@@ -2942,15 +2967,15 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
return -EFAULT;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_index(net, ifr.ifr_ifindex);
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
if (!dev) {
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return -ENODEV;
}
strcpy(ifr.ifr_name, dev->name);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
return -EFAULT;
@@ -4640,59 +4665,76 @@ static void net_set_todo(struct net_device *dev)
list_add_tail(&dev->todo_list, &net_todo_list);
}
-static void rollback_registered(struct net_device *dev)
+static void rollback_registered_many(struct list_head *head)
{
+ struct net_device *dev;
+
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
- /* Some devices call without registering for initialization unwind. */
- if (dev->reg_state == NETREG_UNINITIALIZED) {
- printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
- "was registered\n", dev->name, dev);
+ list_for_each_entry(dev, head, unreg_list) {
+ /* Some devices call without registering
+ * for initialization unwind.
+ */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ pr_debug("unregister_netdevice: device %s/%p never "
+ "was registered\n", dev->name, dev);
- WARN_ON(1);
- return;
- }
+ WARN_ON(1);
+ return;
+ }
- BUG_ON(dev->reg_state != NETREG_REGISTERED);
+ BUG_ON(dev->reg_state != NETREG_REGISTERED);
- /* If device is running, close it first. */
- dev_close(dev);
+ /* If device is running, close it first. */
+ dev_close(dev);
- /* And unlink it from device chain. */
- unlist_netdevice(dev);
+ /* And unlink it from device chain. */
+ unlist_netdevice(dev);
- dev->reg_state = NETREG_UNREGISTERING;
+ dev->reg_state = NETREG_UNREGISTERING;
+ }
synchronize_net();
- /* Shutdown queueing discipline. */
- dev_shutdown(dev);
+ list_for_each_entry(dev, head, unreg_list) {
+ /* Shutdown queueing discipline. */
+ dev_shutdown(dev);
- /* Notify protocols, that we are about to destroy
- this device. They should clean all the things.
- */
- call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ /* Notify protocols, that we are about to destroy
+ this device. They should clean all the things.
+ */
+ call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
- /*
- * Flush the unicast and multicast chains
- */
- dev_unicast_flush(dev);
- dev_addr_discard(dev);
+ /*
+ * Flush the unicast and multicast chains
+ */
+ dev_unicast_flush(dev);
+ dev_addr_discard(dev);
- if (dev->netdev_ops->ndo_uninit)
- dev->netdev_ops->ndo_uninit(dev);
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
- /* Notifier chain MUST detach us from master device. */
- WARN_ON(dev->master);
+ /* Notifier chain MUST detach us from master device. */
+ WARN_ON(dev->master);
- /* Remove entries from kobject tree */
- netdev_unregister_kobject(dev);
+ /* Remove entries from kobject tree */
+ netdev_unregister_kobject(dev);
+ }
synchronize_net();
- dev_put(dev);
+ list_for_each_entry(dev, head, unreg_list)
+ dev_put(dev);
+}
+
+static void rollback_registered(struct net_device *dev)
+{
+ LIST_HEAD(single);
+
+ list_add(&dev->unreg_list, &single);
+ rollback_registered_many(&single);
}
static void __netdev_init_queue_locks_one(struct net_device *dev,
@@ -5248,25 +5290,48 @@ void synchronize_net(void)
EXPORT_SYMBOL(synchronize_net);
/**
- * unregister_netdevice - remove device from the kernel
+ * unregister_netdevice_queue - remove device from the kernel
* @dev: device
- *
+ * @head: list
+
* This function shuts down a device interface and removes it
* from the kernel tables.
+ * If head not NULL, device is queued to be unregistered later.
*
* Callers must hold the rtnl semaphore. You may want
* unregister_netdev() instead of this.
*/
-void unregister_netdevice(struct net_device *dev)
+void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
{
ASSERT_RTNL();
- rollback_registered(dev);
- /* Finish processing unregister after unlock */
- net_set_todo(dev);
+ if (head) {
+ list_add_tail(&dev->unreg_list, head);
+ } else {
+ rollback_registered(dev);
+ /* Finish processing unregister after unlock */
+ net_set_todo(dev);
+ }
+}
+EXPORT_SYMBOL(unregister_netdevice_queue);
+
+/**
+ * unregister_netdevice_many - unregister many devices
+ * @head: list of devices
+ *
+ */
+void unregister_netdevice_many(struct list_head *head)
+{
+ struct net_device *dev;
+
+ if (!list_empty(head)) {
+ rollback_registered_many(head);
+ list_for_each_entry(dev, head, unreg_list)
+ net_set_todo(dev);
+ }
}
-EXPORT_SYMBOL(unregister_netdevice);
+EXPORT_SYMBOL(unregister_netdevice_many);
/**
* unregister_netdev - remove device from the kernel
@@ -5593,7 +5658,7 @@ restart:
/* Delete virtual devices */
if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
- dev->rtnl_link_ops->dellink(dev);
+ dev->rtnl_link_ops->dellink(dev, NULL);
goto restart;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 753c420060d..89de182353b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -139,7 +139,9 @@ static ssize_t show_speed(struct device *dev,
if (!rtnl_trylock())
return restart_syscall();
- if (netif_running(netdev) && netdev->ethtool_ops->get_settings) {
+ if (netif_running(netdev) &&
+ netdev->ethtool_ops &&
+ netdev->ethtool_ops->get_settings) {
struct ethtool_cmd cmd = { ETHTOOL_GSET };
if (!netdev->ethtool_ops->get_settings(netdev, &cmd))
@@ -158,7 +160,9 @@ static ssize_t show_duplex(struct device *dev,
if (!rtnl_trylock())
return restart_syscall();
- if (netif_running(netdev) && netdev->ethtool_ops->get_settings) {
+ if (netif_running(netdev) &&
+ netdev->ethtool_ops &&
+ netdev->ethtool_ops->get_settings) {
struct ethtool_cmd cmd = { ETHTOOL_GSET };
if (!netdev->ethtool_ops->get_settings(netdev, &cmd))
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 1da0e038df7..5ce017bf4af 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -335,6 +335,7 @@ struct pktgen_dev {
__u32 cur_src_mac_offset;
__be32 cur_saddr;
__be32 cur_daddr;
+ __u16 ip_id;
__u16 cur_udp_dst;
__u16 cur_udp_src;
__u16 cur_queue_map;
@@ -2630,6 +2631,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
iph->protocol = IPPROTO_UDP; /* UDP */
iph->saddr = pkt_dev->cur_saddr;
iph->daddr = pkt_dev->cur_daddr;
+ iph->id = htons(pkt_dev->ip_id);
+ pkt_dev->ip_id++;
iph->frag_off = 0;
iplen = 20 + 8 + datalen;
iph->tot_len = htons(iplen);
@@ -2641,24 +2644,26 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
- if (pkt_dev->nfrags <= 0)
+ if (pkt_dev->nfrags <= 0) {
pgh = (struct pktgen_hdr *)skb_put(skb, datalen);
- else {
+ memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr));
+ } else {
int frags = pkt_dev->nfrags;
- int i;
+ int i, len;
pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8);
if (frags > MAX_SKB_FRAGS)
frags = MAX_SKB_FRAGS;
if (datalen > frags * PAGE_SIZE) {
- skb_put(skb, datalen - frags * PAGE_SIZE);
+ len = datalen - frags * PAGE_SIZE;
+ memset(skb_put(skb, len), 0, len);
datalen = frags * PAGE_SIZE;
}
i = 0;
while (datalen > 0) {
- struct page *page = alloc_pages(GFP_KERNEL, 0);
+ struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
skb_shinfo(skb)->frags[i].page = page;
skb_shinfo(skb)->frags[i].page_offset = 0;
skb_shinfo(skb)->frags[i].size =
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ba13b0974a7..391a62cd9df 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -248,7 +248,7 @@ static LIST_HEAD(link_ops);
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
if (!ops->dellink)
- ops->dellink = unregister_netdevice;
+ ops->dellink = unregister_netdevice_queue;
list_add_tail(&ops->list, &link_ops);
return 0;
@@ -277,13 +277,13 @@ EXPORT_SYMBOL_GPL(rtnl_link_register);
static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
{
struct net_device *dev;
-restart:
+ LIST_HEAD(list_kill);
+
for_each_netdev(net, dev) {
- if (dev->rtnl_link_ops == ops) {
- ops->dellink(dev);
- goto restart;
- }
+ if (dev->rtnl_link_ops == ops)
+ ops->dellink(dev, &list_kill);
}
+ unregister_netdevice_many(&list_kill);
}
void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
@@ -682,22 +682,33 @@ nla_put_failure:
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
- int idx;
- int s_idx = cb->args[0];
+ int h, s_h;
+ int idx = 0, s_idx;
struct net_device *dev;
-
- idx = 0;
- for_each_netdev(net, dev) {
- if (idx < s_idx)
- goto cont;
- if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
- NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0)
- break;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ s_h = cb->args[0];
+ s_idx = cb->args[1];
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ hlist_for_each_entry(dev, node, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, 0,
+ NLM_F_MULTI) <= 0)
+ goto out;
cont:
- idx++;
+ idx++;
+ }
}
- cb->args[0] = idx;
+out:
+ cb->args[1] = idx;
+ cb->args[0] = h;
return skb->len;
}
@@ -961,7 +972,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
if (!ops)
return -EOPNOTSUPP;
- ops->dellink(dev);
+ ops->dellink(dev, NULL);
return 0;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f6a0af75993..26fb50e9131 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -447,6 +447,28 @@ extern int sysctl_tcp_synack_retries;
EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
+/* Decide when to expire the request and when to resend SYN-ACK */
+static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
+ const int max_retries,
+ const u8 rskq_defer_accept,
+ int *expire, int *resend)
+{
+ if (!rskq_defer_accept) {
+ *expire = req->retrans >= thresh;
+ *resend = 1;
+ return;
+ }
+ *expire = req->retrans >= thresh &&
+ (!inet_rsk(req)->acked || req->retrans >= max_retries);
+ /*
+ * Do not resend while waiting for data after ACK,
+ * start to resend on end of deferring period to give
+ * last chance for data or ACK to create established socket.
+ */
+ *resend = !inet_rsk(req)->acked ||
+ req->retrans >= rskq_defer_accept - 1;
+}
+
void inet_csk_reqsk_queue_prune(struct sock *parent,
const unsigned long interval,
const unsigned long timeout,
@@ -502,9 +524,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
reqp=&lopt->syn_table[i];
while ((req = *reqp) != NULL) {
if (time_after_eq(now, req->expires)) {
- if ((req->retrans < thresh ||
- (inet_rsk(req)->acked && req->retrans < max_retries))
- && !req->rsk_ops->rtx_syn_ack(parent, req)) {
+ int expire = 0, resend = 0;
+
+ syn_ack_recalc(req, thresh, max_retries,
+ queue->rskq_defer_accept,
+ &expire, &resend);
+ if (!expire &&
+ (!resend ||
+ !req->rsk_ops->rtx_syn_ack(parent, req) ||
+ inet_rsk(req)->acked)) {
unsigned long timeo;
if (req->retrans++ == 0)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 89ff9d5b150..a77807d449e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -156,8 +156,13 @@ struct ipgre_net {
#define tunnels_r tunnels[2]
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipgre_lock);
-static DEFINE_RWLOCK(ipgre_lock);
+#define for_each_ip_tunnel_rcu(start) \
+ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
/* Given src, dst and key, find appropriate for input tunnel. */
@@ -175,7 +180,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
ARPHRD_ETHER : ARPHRD_IPGRE;
int score, cand_score = 4;
- for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
if (local != t->parms.iph.saddr ||
remote != t->parms.iph.daddr ||
key != t->parms.i_key ||
@@ -200,7 +205,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
}
}
- for (t = ign->tunnels_r[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
if (remote != t->parms.iph.daddr ||
key != t->parms.i_key ||
!(t->dev->flags & IFF_UP))
@@ -224,7 +229,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
}
}
- for (t = ign->tunnels_l[h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
if ((local != t->parms.iph.saddr &&
(local != t->parms.iph.daddr ||
!ipv4_is_multicast(local))) ||
@@ -250,7 +255,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
}
}
- for (t = ign->tunnels_wc[h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
if (t->parms.i_key != key ||
!(t->dev->flags & IFF_UP))
continue;
@@ -276,8 +281,9 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
if (cand != NULL)
return cand;
- if (ign->fb_tunnel_dev->flags & IFF_UP)
- return netdev_priv(ign->fb_tunnel_dev);
+ dev = ign->fb_tunnel_dev;
+ if (dev->flags & IFF_UP)
+ return netdev_priv(dev);
return NULL;
}
@@ -311,10 +317,10 @@ static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
{
struct ip_tunnel **tp = ipgre_bucket(ign, t);
+ spin_lock_bh(&ipgre_lock);
t->next = *tp;
- write_lock_bh(&ipgre_lock);
- *tp = t;
- write_unlock_bh(&ipgre_lock);
+ rcu_assign_pointer(*tp, t);
+ spin_unlock_bh(&ipgre_lock);
}
static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
@@ -323,9 +329,9 @@ static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
- write_lock_bh(&ipgre_lock);
+ spin_lock_bh(&ipgre_lock);
*tp = t->next;
- write_unlock_bh(&ipgre_lock);
+ spin_unlock_bh(&ipgre_lock);
break;
}
}
@@ -476,7 +482,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
break;
}
- read_lock(&ipgre_lock);
+ rcu_read_lock();
t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
flags & GRE_KEY ?
*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
@@ -494,7 +500,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
t->err_count = 1;
t->err_time = jiffies;
out:
- read_unlock(&ipgre_lock);
+ rcu_read_unlock();
return;
}
@@ -573,7 +579,7 @@ static int ipgre_rcv(struct sk_buff *skb)
gre_proto = *(__be16 *)(h + 2);
- read_lock(&ipgre_lock);
+ rcu_read_lock();
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
@@ -647,13 +653,13 @@ static int ipgre_rcv(struct sk_buff *skb)
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
- read_unlock(&ipgre_lock);
+ rcu_read_unlock();
return(0);
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
- read_unlock(&ipgre_lock);
+ rcu_read_unlock();
drop_nolock:
kfree_skb(skb);
return(0);
@@ -1284,16 +1290,19 @@ static const struct net_protocol ipgre_protocol = {
.netns_ok = 1,
};
-static void ipgre_destroy_tunnels(struct ipgre_net *ign)
+static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
{
int prio;
for (prio = 0; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
- while ((t = ign->tunnels[prio][h]) != NULL)
- unregister_netdevice(t->dev);
+ struct ip_tunnel *t = ign->tunnels[prio][h];
+
+ while (t != NULL) {
+ unregister_netdevice_queue(t->dev, head);
+ t = t->next;
+ }
}
}
}
@@ -1341,10 +1350,12 @@ err_alloc:
static void ipgre_exit_net(struct net *net)
{
struct ipgre_net *ign;
+ LIST_HEAD(list);
ign = net_generic(net, ipgre_net_id);
rtnl_lock();
- ipgre_destroy_tunnels(ign);
+ ipgre_destroy_tunnels(ign, &list);
+ unregister_netdevice_many(&list);
rtnl_unlock();
kfree(ign);
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 2445fedec0b..cafad9baff0 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -480,7 +480,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
case IP_OPTIONS:
{
struct ip_options *opt = NULL;
- if (optlen > 40 || optlen < 0)
+ if (optlen > 40)
goto e_inval;
err = ip_options_get_from_user(sock_net(sk), &opt,
optval, optlen);
@@ -634,17 +634,16 @@ static int do_ip_setsockopt(struct sock *sk, int level,
break;
}
dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
- if (dev) {
+ if (dev)
mreq.imr_ifindex = dev->ifindex;
- dev_put(dev);
- }
} else
- dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
+ dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
+ dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 6a5539236ab..a2ca53da437 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -134,7 +134,13 @@ static void ipip_fb_tunnel_init(struct net_device *dev);
static void ipip_tunnel_init(struct net_device *dev);
static void ipip_tunnel_setup(struct net_device *dev);
-static DEFINE_RWLOCK(ipip_lock);
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipip_lock);
+
+#define for_each_ip_tunnel_rcu(start) \
+ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
static struct ip_tunnel * ipip_tunnel_lookup(struct net *net,
__be32 remote, __be32 local)
@@ -144,20 +150,21 @@ static struct ip_tunnel * ipip_tunnel_lookup(struct net *net,
struct ip_tunnel *t;
struct ipip_net *ipn = net_generic(net, ipip_net_id);
- for (t = ipn->tunnels_r_l[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
- }
- for (t = ipn->tunnels_r[h0]; t; t = t->next) {
+
+ for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
- }
- for (t = ipn->tunnels_l[h1]; t; t = t->next) {
+
+ for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
return t;
- }
- if ((t = ipn->tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
+
+ t = rcu_dereference(ipn->tunnels_wc[0]);
+ if (t && (t->dev->flags&IFF_UP))
return t;
return NULL;
}
@@ -193,9 +200,9 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
for (tp = ipip_bucket(ipn, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
- write_lock_bh(&ipip_lock);
+ spin_lock_bh(&ipip_lock);
*tp = t->next;
- write_unlock_bh(&ipip_lock);
+ spin_unlock_bh(&ipip_lock);
break;
}
}
@@ -205,10 +212,10 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
{
struct ip_tunnel **tp = ipip_bucket(ipn, t);
+ spin_lock_bh(&ipip_lock);
t->next = *tp;
- write_lock_bh(&ipip_lock);
- *tp = t;
- write_unlock_bh(&ipip_lock);
+ rcu_assign_pointer(*tp, t);
+ spin_unlock_bh(&ipip_lock);
}
static struct ip_tunnel * ipip_tunnel_locate(struct net *net,
@@ -267,9 +274,9 @@ static void ipip_tunnel_uninit(struct net_device *dev)
struct ipip_net *ipn = net_generic(net, ipip_net_id);
if (dev == ipn->fb_tunnel_dev) {
- write_lock_bh(&ipip_lock);
+ spin_lock_bh(&ipip_lock);
ipn->tunnels_wc[0] = NULL;
- write_unlock_bh(&ipip_lock);
+ spin_unlock_bh(&ipip_lock);
} else
ipip_tunnel_unlink(ipn, netdev_priv(dev));
dev_put(dev);
@@ -318,7 +325,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
err = -ENOENT;
- read_lock(&ipip_lock);
+ rcu_read_lock();
t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
if (t == NULL || t->parms.iph.daddr == 0)
goto out;
@@ -333,7 +340,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
t->err_count = 1;
t->err_time = jiffies;
out:
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
return err;
}
@@ -351,11 +358,11 @@ static int ipip_rcv(struct sk_buff *skb)
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
- read_lock(&ipip_lock);
+ rcu_read_lock();
if ((tunnel = ipip_tunnel_lookup(dev_net(skb->dev),
iph->saddr, iph->daddr)) != NULL) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
kfree_skb(skb);
return 0;
}
@@ -374,10 +381,10 @@ static int ipip_rcv(struct sk_buff *skb)
nf_reset(skb);
ipip_ecn_decapsulate(iph, skb);
netif_rx(skb);
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
return 0;
}
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
return -1;
}
@@ -747,16 +754,19 @@ static struct xfrm_tunnel ipip_handler = {
static const char banner[] __initconst =
KERN_INFO "IPv4 over IPv4 tunneling driver\n";
-static void ipip_destroy_tunnels(struct ipip_net *ipn)
+static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
{
int prio;
for (prio = 1; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
- while ((t = ipn->tunnels[prio][h]) != NULL)
- unregister_netdevice(t->dev);
+ struct ip_tunnel *t = ipn->tunnels[prio][h];
+
+ while (t != NULL) {
+ unregister_netdevice_queue(t->dev, head);
+ t = t->next;
+ }
}
}
}
@@ -809,11 +819,13 @@ err_alloc:
static void ipip_exit_net(struct net *net)
{
struct ipip_net *ipn;
+ LIST_HEAD(list);
ipn = net_generic(net, ipip_net_id);
rtnl_lock();
- ipip_destroy_tunnels(ipn);
- unregister_netdevice(ipn->fb_tunnel_dev);
+ ipip_destroy_tunnels(ipn, &list);
+ unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
+ unregister_netdevice_many(&list);
rtnl_unlock();
kfree(ipn);
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 694974502ea..ef4ee45b928 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -275,7 +275,8 @@ failure:
* @notify: Set to 1, if the caller is a notifier_call
*/
-static int vif_delete(struct net *net, int vifi, int notify)
+static int vif_delete(struct net *net, int vifi, int notify,
+ struct list_head *head)
{
struct vif_device *v;
struct net_device *dev;
@@ -319,7 +320,7 @@ static int vif_delete(struct net *net, int vifi, int notify)
}
if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER) && !notify)
- unregister_netdevice(dev);
+ unregister_netdevice_queue(dev, head);
dev_put(dev);
return 0;
@@ -870,14 +871,16 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock)
static void mroute_clean_tables(struct net *net)
{
int i;
+ LIST_HEAD(list);
/*
* Shut down all active vif entries
*/
for (i = 0; i < net->ipv4.maxvif; i++) {
if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC))
- vif_delete(net, i, 0);
+ vif_delete(net, i, 0, &list);
}
+ unregister_netdevice_many(&list);
/*
* Wipe the cache
@@ -993,7 +996,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
if (optname == MRT_ADD_VIF) {
ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk);
} else {
- ret = vif_delete(net, vif.vifc_vifi, 0);
+ ret = vif_delete(net, vif.vifc_vifi, 0, NULL);
}
rtnl_unlock();
return ret;
@@ -1156,6 +1159,7 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
struct net *net = dev_net(dev);
struct vif_device *v;
int ct;
+ LIST_HEAD(list);
if (!net_eq(dev_net(dev), net))
return NOTIFY_DONE;
@@ -1165,8 +1169,9 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
v = &net->ipv4.vif_table[0];
for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) {
if (v->dev == dev)
- vif_delete(net, ct, 1);
+ vif_delete(net, ct, 1, &list);
}
+ unregister_netdevice_many(&list);
return NOTIFY_DONE;
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 5ec678ad70e..3146cc40174 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -276,13 +276,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, 0);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
ret = NULL;
req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
if (!req)
@@ -298,12 +291,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
ireq->loc_addr = ip_hdr(skb)->daddr;
ireq->rmt_addr = ip_hdr(skb)->saddr;
ireq->ecn_ok = 0;
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -352,6 +339,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
}
}
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, 0, &rt->u.dst);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
+
/* Try to redo what tcp_v4_send_synack did. */
req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 206a291dff0..e0cfa633680 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,6 +326,43 @@ void tcp_enter_memory_pressure(struct sock *sk)
EXPORT_SYMBOL(tcp_enter_memory_pressure);
+/* Convert seconds to retransmits based on initial and max timeout */
+static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
+{
+ u8 res = 0;
+
+ if (seconds > 0) {
+ int period = timeout;
+
+ res = 1;
+ while (seconds > period && res < 255) {
+ res++;
+ timeout <<= 1;
+ if (timeout > rto_max)
+ timeout = rto_max;
+ period += timeout;
+ }
+ }
+ return res;
+}
+
+/* Convert retransmits to seconds based on initial and max timeout */
+static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
+{
+ int period = 0;
+
+ if (retrans > 0) {
+ period = timeout;
+ while (--retrans) {
+ timeout <<= 1;
+ if (timeout > rto_max)
+ timeout = rto_max;
+ period += timeout;
+ }
+ }
+ return period;
+}
+
/*
* Wait for a TCP event.
*
@@ -1405,7 +1442,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
goto found_ok_skb;
if (tcp_hdr(skb)->fin)
goto found_fin_ok;
- WARN_ON(!(flags & MSG_PEEK));
+ WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: "
+ "copied %X seq %X\n", *seq,
+ TCP_SKB_CB(skb)->seq);
}
/* Well, if we have backlog, try to process it now yet. */
@@ -2163,16 +2202,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
break;
case TCP_DEFER_ACCEPT:
- icsk->icsk_accept_queue.rskq_defer_accept = 0;
- if (val > 0) {
- /* Translate value in seconds to number of
- * retransmits */
- while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
- val > ((TCP_TIMEOUT_INIT / HZ) <<
- icsk->icsk_accept_queue.rskq_defer_accept))
- icsk->icsk_accept_queue.rskq_defer_accept++;
- icsk->icsk_accept_queue.rskq_defer_accept++;
- }
+ /* Translate value in seconds to number of retransmits */
+ icsk->icsk_accept_queue.rskq_defer_accept =
+ secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+ TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
@@ -2353,8 +2386,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = (val ? : sysctl_tcp_fin_timeout) / HZ;
break;
case TCP_DEFER_ACCEPT:
- val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
- ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
+ val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
+ TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
val = tp->window_clamp;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d86784be7ab..ba0eab65fe8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2300,7 +2300,7 @@ static inline int tcp_fackets_out(struct tcp_sock *tp)
* they differ. Since neither occurs due to loss, TCP should really
* ignore them.
*/
-static inline int tcp_dupack_heurestics(struct tcp_sock *tp)
+static inline int tcp_dupack_heuristics(struct tcp_sock *tp)
{
return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
}
@@ -2425,7 +2425,7 @@ static int tcp_time_to_recover(struct sock *sk)
return 1;
/* Not-A-Trick#2 : Classic rule... */
- if (tcp_dupack_heurestics(tp) > tp->reordering)
+ if (tcp_dupack_heuristics(tp) > tp->reordering)
return 1;
/* Trick#3 : when we use RFC2988 timer restart, fast
@@ -3698,12 +3698,14 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- int estab)
+ int estab, struct dst_entry *dst)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
int length = (th->doff * 4) - sizeof(struct tcphdr);
+ BUG_ON(!estab && !dst);
+
ptr = (unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
@@ -3737,7 +3739,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && sysctl_tcp_window_scaling) {
+ !estab && sysctl_tcp_window_scaling &&
+ !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > 14) {
@@ -3753,7 +3756,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
case TCPOPT_TIMESTAMP:
if ((opsize == TCPOLEN_TIMESTAMP) &&
((estab && opt_rx->tstamp_ok) ||
- (!estab && sysctl_tcp_timestamps))) {
+ (!estab && sysctl_tcp_timestamps &&
+ !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) {
opt_rx->saw_tstamp = 1;
opt_rx->rcv_tsval = get_unaligned_be32(ptr);
opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -3761,7 +3765,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && sysctl_tcp_sack) {
+ !estab && sysctl_tcp_sack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_SACK)) {
opt_rx->sack_ok = 1;
tcp_sack_reset(opt_rx);
}
@@ -3820,7 +3825,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, 1);
+ tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
return 1;
}
@@ -4075,8 +4080,10 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct dst_entry *dst = __sk_dst_get(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4105,13 +4112,15 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct dst_entry *dst = __sk_dst_get(sk);
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -5364,8 +5373,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int saved_clamp = tp->rx_opt.mss_clamp;
+ struct dst_entry *dst = __sk_dst_get(sk);
- tcp_parse_options(skb, &tp->rx_opt, 0);
+ tcp_parse_options(skb, &tp->rx_opt, 0, dst);
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a4a3390a528..657ae334f12 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1257,11 +1257,21 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
#endif
+ ireq = inet_rsk(req);
+ ireq->loc_addr = daddr;
+ ireq->rmt_addr = saddr;
+ ireq->no_srccheck = inet_sk(sk)->transparent;
+ ireq->opt = tcp_v4_save_options(sk, skb);
+
+ dst = inet_csk_route_req(sk, req);
+ if(!dst)
+ goto drop_and_free;
+
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = 536;
tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 0, dst);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1270,14 +1280,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_openreq_init(req, &tmp_opt, skb);
- ireq = inet_rsk(req);
- ireq->loc_addr = daddr;
- ireq->rmt_addr = saddr;
- ireq->no_srccheck = inet_sk(sk)->transparent;
- ireq->opt = tcp_v4_save_options(sk, skb);
-
if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
+ goto drop_and_release;
if (!want_cookie)
TCP_ECN_create_request(req, tcp_hdr(skb));
@@ -1302,7 +1306,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
*/
if (tmp_opt.saw_tstamp &&
tcp_death_row.sysctl_tw_recycle &&
- (dst = inet_csk_route_req(sk, req)) != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e320afea07f..463d51b53d3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -100,9 +100,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
struct tcp_options_received tmp_opt;
int paws_reject = 0;
- tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, 0);
+ tmp_opt.tstamp_ok = 1;
+ tcp_parse_options(skb, &tmp_opt, 1, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -500,10 +500,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
int paws_reject = 0;
struct tcp_options_received tmp_opt;
struct sock *child;
+ struct dst_entry *dst = inet_csk_route_req(sk, req);
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 0, dst);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
@@ -516,6 +517,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
}
}
+ dst_release(dst);
+
/* Check for pure retransmitted SYN. */
if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn &&
flg == TCP_FLAG_SYN &&
@@ -641,10 +644,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!(flg & TCP_FLAG_ACK))
return NULL;
- /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
- if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+ /* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
+ if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
- inet_csk(sk)->icsk_accept_queue.rskq_defer_accept--;
inet_rsk(req)->acked = 1;
return NULL;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2e2eb74ac4c..616c686ca25 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -464,6 +464,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
unsigned size = 0;
+ struct dst_entry *dst = __sk_dst_get(sk);
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -487,18 +488,22 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->mss = tcp_advertise_mss(sk);
size += TCPOLEN_MSS_ALIGNED;
- if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
+ if (likely(sysctl_tcp_timestamps &&
+ !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&
+ *md5 == NULL)) {
opts->options |= OPTION_TS;
opts->tsval = TCP_SKB_CB(skb)->when;
opts->tsecr = tp->rx_opt.ts_recent;
size += TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sysctl_tcp_window_scaling)) {
+ if (likely(sysctl_tcp_window_scaling &&
+ !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
size += TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sysctl_tcp_sack)) {
+ if (likely(sysctl_tcp_sack &&
+ !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
size += TCPOLEN_SACKPERM_ALIGNED;
@@ -2315,7 +2320,9 @@ static void tcp_connect_init(struct sock *sk)
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr) +
- (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
+ (sysctl_tcp_timestamps &&
+ (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ?
+ TCPOLEN_TSTAMP_ALIGNED : 0));
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk) != NULL)
@@ -2341,7 +2348,8 @@ static void tcp_connect_init(struct sock *sk)
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- sysctl_tcp_window_scaling,
+ (sysctl_tcp_window_scaling &&
+ !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)),
&rcv_wscale);
tp->rx_opt.rcv_wscale = rcv_wscale;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index c595bbe1ed9..6c1b5c98e81 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -88,8 +88,10 @@ struct ip6_tnl_net {
struct ip6_tnl **tnls[2];
};
-/* lock for the tunnel lists */
-static DEFINE_RWLOCK(ip6_tnl_lock);
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ip6_tnl_lock);
static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
{
@@ -130,6 +132,9 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
* else %NULL
**/
+#define for_each_ip6_tunnel_rcu(start) \
+ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
+
static struct ip6_tnl *
ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
{
@@ -138,13 +143,14 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- for (t = ip6n->tnls_r_l[h0 ^ h1]; t; t = t->next) {
+ for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
- if ((t = ip6n->tnls_wc[0]) != NULL && (t->dev->flags & IFF_UP))
+ t = rcu_dereference(ip6n->tnls_wc[0]);
+ if (t && (t->dev->flags & IFF_UP))
return t;
return NULL;
@@ -186,10 +192,10 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms);
+ spin_lock_bh(&ip6_tnl_lock);
t->next = *tp;
- write_lock_bh(&ip6_tnl_lock);
- *tp = t;
- write_unlock_bh(&ip6_tnl_lock);
+ rcu_assign_pointer(*tp, t);
+ spin_unlock_bh(&ip6_tnl_lock);
}
/**
@@ -204,9 +210,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) {
if (t == *tp) {
- write_lock_bh(&ip6_tnl_lock);
+ spin_lock_bh(&ip6_tnl_lock);
*tp = t->next;
- write_unlock_bh(&ip6_tnl_lock);
+ spin_unlock_bh(&ip6_tnl_lock);
break;
}
}
@@ -313,9 +319,9 @@ ip6_tnl_dev_uninit(struct net_device *dev)
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev) {
- write_lock_bh(&ip6_tnl_lock);
+ spin_lock_bh(&ip6_tnl_lock);
ip6n->tnls_wc[0] = NULL;
- write_unlock_bh(&ip6_tnl_lock);
+ spin_unlock_bh(&ip6_tnl_lock);
} else {
ip6_tnl_unlink(ip6n, t);
}
@@ -409,7 +415,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
in trouble since we might need the source address for further
processing of the error. */
- read_lock(&ip6_tnl_lock);
+ rcu_read_lock();
if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr,
&ipv6h->saddr)) == NULL)
goto out;
@@ -482,7 +488,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
*msg = rel_msg;
out:
- read_unlock(&ip6_tnl_lock);
+ rcu_read_unlock();
return err;
}
@@ -693,23 +699,23 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
struct ip6_tnl *t;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
- read_lock(&ip6_tnl_lock);
+ rcu_read_lock();
if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
&ipv6h->daddr)) != NULL) {
if (t->parms.proto != ipproto && t->parms.proto != 0) {
- read_unlock(&ip6_tnl_lock);
+ rcu_read_unlock();
goto discard;
}
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- read_unlock(&ip6_tnl_lock);
+ rcu_read_unlock();
goto discard;
}
if (!ip6_tnl_rcv_ctl(t)) {
t->dev->stats.rx_dropped++;
- read_unlock(&ip6_tnl_lock);
+ rcu_read_unlock();
goto discard;
}
secpath_reset(skb);
@@ -727,10 +733,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
t->dev->stats.rx_packets++;
t->dev->stats.rx_bytes += skb->len;
netif_rx(skb);
- read_unlock(&ip6_tnl_lock);
+ rcu_read_unlock();
return 0;
}
- read_unlock(&ip6_tnl_lock);
+ rcu_read_unlock();
return 1;
discard:
@@ -1387,14 +1393,19 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
{
int h;
struct ip6_tnl *t;
+ LIST_HEAD(list);
for (h = 0; h < HASH_SIZE; h++) {
- while ((t = ip6n->tnls_r_l[h]) != NULL)
- unregister_netdevice(t->dev);
+ t = ip6n->tnls_r_l[h];
+ while (t != NULL) {
+ unregister_netdevice_queue(t->dev, &list);
+ t = t->next;
+ }
}
t = ip6n->tnls_wc[0];
- unregister_netdevice(t->dev);
+ unregister_netdevice_queue(t->dev, &list);
+ unregister_netdevice_many(&list);
}
static int ip6_tnl_init_net(struct net *net)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 85849b4f5a3..52e0f74fdfe 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -477,7 +477,7 @@ failure:
* Delete a VIF entry
*/
-static int mif6_delete(struct net *net, int vifi)
+static int mif6_delete(struct net *net, int vifi, struct list_head *head)
{
struct mif_device *v;
struct net_device *dev;
@@ -519,7 +519,7 @@ static int mif6_delete(struct net *net, int vifi)
in6_dev->cnf.mc_forwarding--;
if (v->flags & MIFF_REGISTER)
- unregister_netdevice(dev);
+ unregister_netdevice_queue(dev, head);
dev_put(dev);
return 0;
@@ -976,6 +976,7 @@ static int ip6mr_device_event(struct notifier_block *this,
struct net *net = dev_net(dev);
struct mif_device *v;
int ct;
+ LIST_HEAD(list);
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
@@ -983,8 +984,10 @@ static int ip6mr_device_event(struct notifier_block *this,
v = &net->ipv6.vif6_table[0];
for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) {
if (v->dev == dev)
- mif6_delete(net, ct);
+ mif6_delete(net, ct, &list);
}
+ unregister_netdevice_many(&list);
+
return NOTIFY_DONE;
}
@@ -1188,14 +1191,16 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock)
static void mroute_clean_tables(struct net *net)
{
int i;
+ LIST_HEAD(list);
/*
* Shut down all active vif entries
*/
for (i = 0; i < net->ipv6.maxvif; i++) {
if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC))
- mif6_delete(net, i);
+ mif6_delete(net, i, &list);
}
+ unregister_netdevice_many(&list);
/*
* Wipe the cache
@@ -1325,7 +1330,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
return -EFAULT;
rtnl_lock();
- ret = mif6_delete(net, mifi);
+ ret = mif6_delete(net, mifi, NULL);
rtnl_unlock();
return ret;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 68566de4bcc..430454ee5ea 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -497,13 +497,17 @@ done:
goto e_inval;
if (val) {
+ struct net_device *dev;
+
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
goto e_inval;
- if (__dev_get_by_index(net, val) == NULL) {
+ dev = dev_get_by_index(net, val);
+ if (!dev) {
retv = -ENODEV;
break;
}
+ dev_put(dev);
}
np->mcast_oif = val;
retv = 0;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 510d31f3cb9..2362a3397e9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -77,8 +77,17 @@ struct sit_net {
struct net_device *fb_tunnel_dev;
};
-static DEFINE_RWLOCK(ipip6_lock);
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipip6_lock);
+
+#define for_each_ip_tunnel_rcu(start) \
+ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
+/*
+ * Must be invoked with rcu_read_lock
+ */
static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
struct net_device *dev, __be32 remote, __be32 local)
{
@@ -87,26 +96,26 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
struct ip_tunnel *t;
struct sit_net *sitn = net_generic(net, sit_net_id);
- for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
(!dev || !t->parms.link || dev->iflink == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
- for (t = sitn->tunnels_r[h0]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) {
if (remote == t->parms.iph.daddr &&
(!dev || !t->parms.link || dev->iflink == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
- for (t = sitn->tunnels_l[h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) {
if (local == t->parms.iph.saddr &&
(!dev || !t->parms.link || dev->iflink == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
- t = sitn->tunnels_wc[0];
+ t = rcu_dereference(sitn->tunnels_wc[0]);
if ((t != NULL) && (t->dev->flags & IFF_UP))
return t;
return NULL;
@@ -143,9 +152,9 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
- write_lock_bh(&ipip6_lock);
+ spin_lock_bh(&ipip6_lock);
*tp = t->next;
- write_unlock_bh(&ipip6_lock);
+ spin_unlock_bh(&ipip6_lock);
break;
}
}
@@ -155,10 +164,10 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
{
struct ip_tunnel **tp = ipip6_bucket(sitn, t);
+ spin_lock_bh(&ipip6_lock);
t->next = *tp;
- write_lock_bh(&ipip6_lock);
- *tp = t;
- write_unlock_bh(&ipip6_lock);
+ rcu_assign_pointer(*tp, t);
+ spin_unlock_bh(&ipip6_lock);
}
static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
@@ -240,15 +249,22 @@ failed:
return NULL;
}
+static DEFINE_SPINLOCK(ipip6_prl_lock);
+
+#define for_each_prl_rcu(start) \
+ for (prl = rcu_dereference(start); \
+ prl; \
+ prl = rcu_dereference(prl->next))
+
static struct ip_tunnel_prl_entry *
__ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr)
{
- struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *)NULL;
+ struct ip_tunnel_prl_entry *prl;
- for (p = t->prl; p; p = p->next)
- if (p->addr == addr)
+ for_each_prl_rcu(t->prl)
+ if (prl->addr == addr)
break;
- return p;
+ return prl;
}
@@ -273,7 +289,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
kcalloc(cmax, sizeof(*kp), GFP_KERNEL) :
NULL;
- read_lock(&ipip6_lock);
+ rcu_read_lock();
ca = t->prl_count < cmax ? t->prl_count : cmax;
@@ -291,7 +307,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
}
c = 0;
- for (prl = t->prl; prl; prl = prl->next) {
+ for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr)
@@ -303,7 +319,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
break;
}
out:
- read_unlock(&ipip6_lock);
+ rcu_read_unlock();
len = sizeof(*kp) * c;
ret = 0;
@@ -324,12 +340,14 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
if (a->addr == htonl(INADDR_ANY))
return -EINVAL;
- write_lock(&ipip6_lock);
+ spin_lock(&ipip6_prl_lock);
for (p = t->prl; p; p = p->next) {
if (p->addr == a->addr) {
- if (chg)
- goto update;
+ if (chg) {
+ p->flags = a->flags;
+ goto out;
+ }
err = -EEXIST;
goto out;
}
@@ -346,46 +364,63 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
goto out;
}
+ INIT_RCU_HEAD(&p->rcu_head);
p->next = t->prl;
- t->prl = p;
- t->prl_count++;
-update:
p->addr = a->addr;
p->flags = a->flags;
+ t->prl_count++;
+ rcu_assign_pointer(t->prl, p);
out:
- write_unlock(&ipip6_lock);
+ spin_unlock(&ipip6_prl_lock);
return err;
}
+static void prl_entry_destroy_rcu(struct rcu_head *head)
+{
+ kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head));
+}
+
+static void prl_list_destroy_rcu(struct rcu_head *head)
+{
+ struct ip_tunnel_prl_entry *p, *n;
+
+ p = container_of(head, struct ip_tunnel_prl_entry, rcu_head);
+ do {
+ n = p->next;
+ kfree(p);
+ p = n;
+ } while (p);
+}
+
static int
ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a)
{
struct ip_tunnel_prl_entry *x, **p;
int err = 0;
- write_lock(&ipip6_lock);
+ spin_lock(&ipip6_prl_lock);
if (a && a->addr != htonl(INADDR_ANY)) {
for (p = &t->prl; *p; p = &(*p)->next) {
if ((*p)->addr == a->addr) {
x = *p;
*p = x->next;
- kfree(x);
+ call_rcu(&x->rcu_head, prl_entry_destroy_rcu);
t->prl_count--;
goto out;
}
}
err = -ENXIO;
} else {
- while (t->prl) {
+ if (t->prl) {
+ t->prl_count = 0;
x = t->prl;
- t->prl = t->prl->next;
- kfree(x);
- t->prl_count--;
+ call_rcu(&x->rcu_head, prl_list_destroy_rcu);
+ t->prl = NULL;
}
}
out:
- write_unlock(&ipip6_lock);
+ spin_unlock(&ipip6_prl_lock);
return err;
}
@@ -395,7 +430,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
struct ip_tunnel_prl_entry *p;
int ok = 1;
- read_lock(&ipip6_lock);
+ rcu_read_lock();
p = __ipip6_tunnel_locate_prl(t, iph->saddr);
if (p) {
if (p->flags & PRL_DEFAULT)
@@ -411,7 +446,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
else
ok = 0;
}
- read_unlock(&ipip6_lock);
+ rcu_read_unlock();
return ok;
}
@@ -421,9 +456,9 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
struct sit_net *sitn = net_generic(net, sit_net_id);
if (dev == sitn->fb_tunnel_dev) {
- write_lock_bh(&ipip6_lock);
+ spin_lock_bh(&ipip6_lock);
sitn->tunnels_wc[0] = NULL;
- write_unlock_bh(&ipip6_lock);
+ spin_unlock_bh(&ipip6_lock);
dev_put(dev);
} else {
ipip6_tunnel_unlink(sitn, netdev_priv(dev));
@@ -476,7 +511,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
err = -ENOENT;
- read_lock(&ipip6_lock);
+ rcu_read_lock();
t = ipip6_tunnel_lookup(dev_net(skb->dev),
skb->dev,
iph->daddr,
@@ -494,7 +529,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
t->err_count = 1;
t->err_time = jiffies;
out:
- read_unlock(&ipip6_lock);
+ rcu_read_unlock();
return err;
}
@@ -514,7 +549,7 @@ static int ipip6_rcv(struct sk_buff *skb)
iph = ip_hdr(skb);
- read_lock(&ipip6_lock);
+ rcu_read_lock();
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel != NULL) {
@@ -528,7 +563,7 @@ static int ipip6_rcv(struct sk_buff *skb)
if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
!isatap_chksrc(skb, iph, tunnel)) {
tunnel->dev->stats.rx_errors++;
- read_unlock(&ipip6_lock);
+ rcu_read_unlock();
kfree_skb(skb);
return 0;
}
@@ -539,12 +574,12 @@ static int ipip6_rcv(struct sk_buff *skb)
nf_reset(skb);
ipip6_ecn_decapsulate(iph, skb);
netif_rx(skb);
- read_unlock(&ipip6_lock);
+ rcu_read_unlock();
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
- read_unlock(&ipip6_lock);
+ rcu_read_unlock();
out:
kfree_skb(skb);
return 0;
@@ -1110,16 +1145,19 @@ static struct xfrm_tunnel sit_handler = {
.priority = 1,
};
-static void sit_destroy_tunnels(struct sit_net *sitn)
+static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
{
int prio;
for (prio = 1; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
- while ((t = sitn->tunnels[prio][h]) != NULL)
- unregister_netdevice(t->dev);
+ struct ip_tunnel *t = sitn->tunnels[prio][h];
+
+ while (t != NULL) {
+ unregister_netdevice_queue(t->dev, head);
+ t = t->next;
+ }
}
}
}
@@ -1173,11 +1211,13 @@ err_alloc:
static void sit_exit_net(struct net *net)
{
struct sit_net *sitn;
+ LIST_HEAD(list);
sitn = net_generic(net, sit_net_id);
rtnl_lock();
- sit_destroy_tunnels(sitn);
- unregister_netdevice(sitn->fb_tunnel_dev);
+ sit_destroy_tunnels(sitn, &list);
+ unregister_netdevice_queue(sitn->fb_tunnel_dev, &list);
+ unregister_netdevice_many(&list);
rtnl_unlock();
kfree(sitn);
}
@@ -1192,6 +1232,7 @@ static void __exit sit_cleanup(void)
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
unregister_pernet_gen_device(sit_net_id, &sit_net_ops);
+ rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
static int __init sit_init(void)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index c46da533888..612fc53e0bb 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -184,13 +184,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, 0);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
ret = NULL;
req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
if (!req)
@@ -224,12 +217,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
req->expires = 0UL;
req->retrans = 0;
ireq->ecn_ok = 0;
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
@@ -265,6 +252,21 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
goto out_free;
}
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, 0, dst);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
+
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+
req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
&req->rcv_wnd, &req->window_clamp,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c54ec3615de..34925f089e0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1167,6 +1167,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock *req = NULL;
__u32 isn = TCP_SKB_CB(skb)->when;
+ struct dst_entry *dst = __sk_dst_get(sk);
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
#else
@@ -1205,7 +1206,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, 0);
+ tcp_parse_options(skb, &tmp_opt, 0, dst);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 81a95c00e50..438831d3359 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -23,7 +23,7 @@
*/
#include <linux/module.h>
#include <linux/xfrm.h>
-#include <linux/list.h>
+#include <linux/rculist.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/ipv6.h>
@@ -36,14 +36,15 @@
* per xfrm_address_t.
*/
struct xfrm6_tunnel_spi {
- struct hlist_node list_byaddr;
- struct hlist_node list_byspi;
- xfrm_address_t addr;
- u32 spi;
- atomic_t refcnt;
+ struct hlist_node list_byaddr;
+ struct hlist_node list_byspi;
+ xfrm_address_t addr;
+ u32 spi;
+ atomic_t refcnt;
+ struct rcu_head rcu_head;
};
-static DEFINE_RWLOCK(xfrm6_tunnel_spi_lock);
+static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock);
static u32 xfrm6_tunnel_spi;
@@ -107,6 +108,7 @@ static void xfrm6_tunnel_spi_fini(void)
if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i]))
return;
}
+ rcu_barrier();
kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
xfrm6_tunnel_spi_kmem = NULL;
}
@@ -116,7 +118,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
struct xfrm6_tunnel_spi *x6spi;
struct hlist_node *pos;
- hlist_for_each_entry(x6spi, pos,
+ hlist_for_each_entry_rcu(x6spi, pos,
&xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
list_byaddr) {
if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0)
@@ -131,10 +133,10 @@ __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr)
struct xfrm6_tunnel_spi *x6spi;
u32 spi;
- read_lock_bh(&xfrm6_tunnel_spi_lock);
+ rcu_read_lock_bh();
x6spi = __xfrm6_tunnel_spi_lookup(saddr);
spi = x6spi ? x6spi->spi : 0;
- read_unlock_bh(&xfrm6_tunnel_spi_lock);
+ rcu_read_unlock_bh();
return htonl(spi);
}
@@ -185,14 +187,15 @@ alloc_spi:
if (!x6spi)
goto out;
+ INIT_RCU_HEAD(&x6spi->rcu_head);
memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr));
x6spi->spi = spi;
atomic_set(&x6spi->refcnt, 1);
- hlist_add_head(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]);
+ hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]);
index = xfrm6_tunnel_spi_hash_byaddr(saddr);
- hlist_add_head(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]);
+ hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]);
out:
return spi;
}
@@ -202,26 +205,32 @@ __be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr)
struct xfrm6_tunnel_spi *x6spi;
u32 spi;
- write_lock_bh(&xfrm6_tunnel_spi_lock);
+ spin_lock_bh(&xfrm6_tunnel_spi_lock);
x6spi = __xfrm6_tunnel_spi_lookup(saddr);
if (x6spi) {
atomic_inc(&x6spi->refcnt);
spi = x6spi->spi;
} else
spi = __xfrm6_tunnel_alloc_spi(saddr);
- write_unlock_bh(&xfrm6_tunnel_spi_lock);
+ spin_unlock_bh(&xfrm6_tunnel_spi_lock);
return htonl(spi);
}
EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi);
+static void x6spi_destroy_rcu(struct rcu_head *head)
+{
+ kmem_cache_free(xfrm6_tunnel_spi_kmem,
+ container_of(head, struct xfrm6_tunnel_spi, rcu_head));
+}
+
void xfrm6_tunnel_free_spi(xfrm_address_t *saddr)
{
struct xfrm6_tunnel_spi *x6spi;
struct hlist_node *pos, *n;
- write_lock_bh(&xfrm6_tunnel_spi_lock);
+ spin_lock_bh(&xfrm6_tunnel_spi_lock);
hlist_for_each_entry_safe(x6spi, pos, n,
&xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)],
@@ -229,14 +238,14 @@ void xfrm6_tunnel_free_spi(xfrm_address_t *saddr)
{
if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) {
if (atomic_dec_and_test(&x6spi->refcnt)) {
- hlist_del(&x6spi->list_byaddr);
- hlist_del(&x6spi->list_byspi);
- kmem_cache_free(xfrm6_tunnel_spi_kmem, x6spi);
+ hlist_del_rcu(&x6spi->list_byaddr);
+ hlist_del_rcu(&x6spi->list_byspi);
+ call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu);
break;
}
}
}
- write_unlock_bh(&xfrm6_tunnel_spi_lock);
+ spin_unlock_bh(&xfrm6_tunnel_spi_lock);
}
EXPORT_SYMBOL(xfrm6_tunnel_free_spi);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ff752c60641..33e68f20ec6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -79,6 +79,7 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/mutex.h>
+#include <linux/if_vlan.h>
#ifdef CONFIG_INET
#include <net/inet_common.h>
@@ -766,7 +767,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
getnstimeofday(&ts);
h.h2->tp_sec = ts.tv_sec;
h.h2->tp_nsec = ts.tv_nsec;
- h.h2->tp_vlan_tci = skb->vlan_tci;
+ h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
hdrlen = sizeof(*h.h2);
break;
default:
@@ -1493,7 +1494,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
aux.tp_snaplen = skb->len;
aux.tp_mac = 0;
aux.tp_net = skb_network_offset(skb);
- aux.tp_vlan_tci = skb->vlan_tci;
+ aux.tp_vlan_tci = vlan_tx_tag_get(skb);
put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0f133c5a8d3..3291902f0b8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1074,6 +1074,8 @@ restart:
err = -ECONNREFUSED;
if (other->sk_state != TCP_LISTEN)
goto out_unlock;
+ if (other->sk_shutdown & RCV_SHUTDOWN)
+ goto out_unlock;
if (unix_recvq_full(other)) {
err = -EAGAIN;
diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index 7d7c3abf38b..96d92278354 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -114,7 +114,7 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp
/*
* Copy any Call User Data.
*/
- if (skb->len >= 0) {
+ if (skb->len > 0) {
skb_copy_from_linear_data(skb,
x25->calluserdata.cuddata,
skb->len);
diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c
index 2c999ccf504..66961ea28c9 100644
--- a/net/x25/x25_route.c
+++ b/net/x25/x25_route.c
@@ -190,7 +190,7 @@ int x25_route_ioctl(unsigned int cmd, void __user *arg)
goto out;
rc = -EINVAL;
- if (rt.sigdigits < 0 || rt.sigdigits > 15)
+ if (rt.sigdigits > 15)
goto out;
dev = x25_dev_get(rt.device);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-08 21:25:06 +0000