summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan_dev.c52
-rw-r--r--net/atm/common.c1
-rw-r--r--net/atm/pvc.c1
-rw-r--r--net/batman-adv/gateway_client.c6
-rw-r--r--net/batman-adv/translation-table.c1
-rw-r--r--net/bluetooth/hci_sock.c2
-rw-r--r--net/bluetooth/l2cap_sock.c1
-rw-r--r--net/bluetooth/rfcomm/sock.c2
-rw-r--r--net/bluetooth/rfcomm/tty.c2
-rw-r--r--net/bridge/br_device.c30
-rw-r--r--net/bridge/br_forward.c2
-rw-r--r--net/bridge/br_if.c6
-rw-r--r--net/bridge/br_private.h4
-rw-r--r--net/caif/chnl_net.c4
-rw-r--r--net/ceph/ceph_common.c1
-rw-r--r--net/ceph/crypto.c1
-rw-r--r--net/ceph/crypto.h3
-rw-r--r--net/ceph/debugfs.c4
-rw-r--r--net/ceph/messenger.c11
-rw-r--r--net/ceph/mon_client.c51
-rw-r--r--net/core/dev.c24
-rw-r--r--net/core/dst.c10
-rw-r--r--net/core/netpoll.c99
-rw-r--r--net/core/netprio_cgroup.c30
-rw-r--r--net/core/scm.c4
-rw-r--r--net/core/sock.c7
-rw-r--r--net/dccp/ccid.h4
-rw-r--r--net/dccp/ccids/ccid3.c1
-rw-r--r--net/ipv4/fib_trie.c2
-rw-r--r--net/ipv4/inet_connection_sock.c7
-rw-r--r--net/ipv4/ip_output.c10
-rw-r--r--net/ipv4/ipmr.c14
-rw-r--r--net/ipv4/netfilter/nf_nat_sip.c14
-rw-r--r--net/ipv4/route.c7
-rw-r--r--net/ipv4/tcp_input.c19
-rw-r--r--net/ipv4/tcp_ipv4.c23
-rw-r--r--net/ipv4/tcp_metrics.c12
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_output.c16
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv4/udp.c7
-rw-r--r--net/ipv6/addrconf.c4
-rw-r--r--net/ipv6/esp6.c6
-rw-r--r--net/ipv6/proc.c4
-rw-r--r--net/ipv6/tcp_ipv6.c34
-rw-r--r--net/ipv6/udp.c11
-rw-r--r--net/ipv6/xfrm6_policy.c8
-rw-r--r--net/l2tp/l2tp_core.c7
-rw-r--r--net/l2tp/l2tp_core.h1
-rw-r--r--net/l2tp/l2tp_eth.c2
-rw-r--r--net/l2tp/l2tp_ip6.c1
-rw-r--r--net/llc/af_llc.c8
-rw-r--r--net/llc/llc_input.c21
-rw-r--r--net/llc/llc_station.c29
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c5
-rw-r--r--net/netfilter/nf_conntrack_core.c16
-rw-r--r--net/netfilter/nf_conntrack_expect.c29
-rw-r--r--net/netfilter/nf_conntrack_netlink.c10
-rw-r--r--net/netfilter/nf_conntrack_sip.c92
-rw-r--r--net/netfilter/nfnetlink_log.c6
-rw-r--r--net/netlink/af_netlink.c6
-rw-r--r--net/netrom/af_netrom.c7
-rw-r--r--net/openvswitch/actions.c2
-rw-r--r--net/openvswitch/datapath.c6
-rw-r--r--net/openvswitch/flow.h8
-rw-r--r--net/packet/af_packet.c12
-rw-r--r--net/sched/act_gact.c14
-rw-r--r--net/sched/act_ipt.c7
-rw-r--r--net/sched/act_mirred.c11
-rw-r--r--net/sched/act_pedit.c5
-rw-r--r--net/sched/act_simple.c5
-rw-r--r--net/sched/sch_fq_codel.c2
-rw-r--r--net/sched/sch_qfq.c95
-rw-r--r--net/sctp/output.c21
-rw-r--r--net/socket.c1
-rw-r--r--net/sunrpc/svc_xprt.c10
-rw-r--r--net/sunrpc/svcsock.c2
-rw-r--r--net/unix/af_unix.c4
-rw-r--r--net/xfrm/xfrm_input.c2
-rw-r--r--net/xfrm/xfrm_policy.c2
-rw-r--r--net/xfrm/xfrm_replay.c15
-rw-r--r--net/xfrm/xfrm_state.c4
82 files changed, 718 insertions, 320 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 73a2a83ee2da..402442402af7 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -137,9 +137,21 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
return rc;
}
+static inline netdev_tx_t vlan_netpoll_send_skb(struct vlan_dev_priv *vlan, struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ if (vlan->netpoll)
+ netpoll_send_skb(vlan->netpoll, skb);
+#else
+ BUG();
+#endif
+ return NETDEV_TX_OK;
+}
+
static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
unsigned int len;
int ret;
@@ -150,29 +162,30 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
* OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
*/
if (veth->h_vlan_proto != htons(ETH_P_8021Q) ||
- vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR) {
+ vlan->flags & VLAN_FLAG_REORDER_HDR) {
u16 vlan_tci;
- vlan_tci = vlan_dev_priv(dev)->vlan_id;
+ vlan_tci = vlan->vlan_id;
vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
}
- skb->dev = vlan_dev_priv(dev)->real_dev;
+ skb->dev = vlan->real_dev;
len = skb->len;
- if (netpoll_tx_running(dev))
- return skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev);
+ if (unlikely(netpoll_tx_running(dev)))
+ return vlan_netpoll_send_skb(vlan, skb);
+
ret = dev_queue_xmit(skb);
if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
struct vlan_pcpu_stats *stats;
- stats = this_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats);
+ stats = this_cpu_ptr(vlan->vlan_pcpu_stats);
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
stats->tx_bytes += len;
u64_stats_update_end(&stats->syncp);
} else {
- this_cpu_inc(vlan_dev_priv(dev)->vlan_pcpu_stats->tx_dropped);
+ this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped);
}
return ret;
@@ -669,25 +682,26 @@ static void vlan_dev_poll_controller(struct net_device *dev)
return;
}
-static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo,
+ gfp_t gfp)
{
- struct vlan_dev_priv *info = vlan_dev_priv(dev);
- struct net_device *real_dev = info->real_dev;
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+ struct net_device *real_dev = vlan->real_dev;
struct netpoll *netpoll;
int err = 0;
- netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+ netpoll = kzalloc(sizeof(*netpoll), gfp);
err = -ENOMEM;
if (!netpoll)
goto out;
- err = __netpoll_setup(netpoll, real_dev);
+ err = __netpoll_setup(netpoll, real_dev, gfp);
if (err) {
kfree(netpoll);
goto out;
}
- info->netpoll = netpoll;
+ vlan->netpoll = netpoll;
out:
return err;
@@ -695,19 +709,15 @@ out:
static void vlan_dev_netpoll_cleanup(struct net_device *dev)
{
- struct vlan_dev_priv *info = vlan_dev_priv(dev);
- struct netpoll *netpoll = info->netpoll;
+ struct vlan_dev_priv *vlan= vlan_dev_priv(dev);
+ struct netpoll *netpoll = vlan->netpoll;
if (!netpoll)
return;
- info->netpoll = NULL;
-
- /* Wait for transmitting packets to finish before freeing. */
- synchronize_rcu_bh();
+ vlan->netpoll = NULL;
- __netpoll_cleanup(netpoll);
- kfree(netpoll);
+ __netpoll_free_rcu(netpoll);
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
diff --git a/net/atm/common.c b/net/atm/common.c
index b4b44dbed645..0c0ad930a632 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -812,6 +812,7 @@ int vcc_getsockopt(struct socket *sock, int level, int optname,
if (!vcc->dev || !test_bit(ATM_VF_ADDR, &vcc->flags))
return -ENOTCONN;
+ memset(&pvc, 0, sizeof(pvc));
pvc.sap_family = AF_ATMPVC;
pvc.sap_addr.itf = vcc->dev->number;
pvc.sap_addr.vpi = vcc->vpi;
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 3a734919c36c..ae0324021407 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -95,6 +95,7 @@ static int pvc_getname(struct socket *sock, struct sockaddr *sockaddr,
return -ENOTCONN;
*sockaddr_len = sizeof(struct sockaddr_atmpvc);
addr = (struct sockaddr_atmpvc *)sockaddr;
+ memset(addr, 0, sizeof(*addr));
addr->sap_family = AF_ATMPVC;
addr->sap_addr.itf = vcc->dev->number;
addr->sap_addr.vpi = vcc->vpi;
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index b421cc49d2cd..fc866f2e4528 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -200,11 +200,11 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT)
goto out;
- if (!batadv_atomic_dec_not_zero(&bat_priv->gw_reselect))
- goto out;
-
curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
+ if (!batadv_atomic_dec_not_zero(&bat_priv->gw_reselect) && curr_gw)
+ goto out;
+
next_gw = batadv_gw_get_best_gw_node(bat_priv);
if (curr_gw == next_gw)
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index a438f4b582fc..99dd8f75b3ff 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -197,6 +197,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
del:
list_del(&entry->list);
kfree(entry);
+ kfree(tt_change_node);
event_removed = true;
goto unlock;
}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index a7f04de03d79..19fdac78e555 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -694,6 +694,7 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr,
*addr_len = sizeof(*haddr);
haddr->hci_family = AF_BLUETOOTH;
haddr->hci_dev = hdev->id;
+ haddr->hci_channel= 0;
release_sock(sk);
return 0;
@@ -1009,6 +1010,7 @@ static int hci_sock_getsockopt(struct socket *sock, int level, int optname,
{
struct hci_filter *f = &hci_pi(sk)->filter;
+ memset(&uf, 0, sizeof(uf));
uf.type_mask = f->type_mask;
uf.opcode = f->opcode;
uf.event_mask[0] = *((u32 *) f->event_mask + 0);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 45cb0b0dd2c7..34bbe1c5e389 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -245,6 +245,7 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, int *l
BT_DBG("sock %p, sk %p", sock, sk);
+ memset(la, 0, sizeof(struct sockaddr_l2));
addr->sa_family = AF_BLUETOOTH;
*len = sizeof(struct sockaddr_l2);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 7e1e59645c05..1a17850d093c 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -528,6 +528,7 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *
BT_DBG("sock %p, sk %p", sock, sk);
+ memset(sa, 0, sizeof(*sa));
sa->rc_family = AF_BLUETOOTH;
sa->rc_channel = rfcomm_pi(sk)->channel;
if (peer)
@@ -822,6 +823,7 @@ static int rfcomm_sock_getsockopt(struct socket *sock, int level, int optname, c
}
sec.level = rfcomm_pi(sk)->sec_level;
+ sec.key_size = 0;
len = min_t(unsigned int, len, sizeof(sec));
if (copy_to_user(optval, (char *) &sec, len))
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index cb960773c002..56f182393c4c 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -456,7 +456,7 @@ static int rfcomm_get_dev_list(void __user *arg)
size = sizeof(*dl) + dev_num * sizeof(*di);
- dl = kmalloc(size, GFP_KERNEL);
+ dl = kzalloc(size, GFP_KERNEL);
if (!dl)
return -ENOMEM;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 333484537600..070e8a68cfc6 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -31,9 +31,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
struct net_bridge_mdb_entry *mdst;
struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+ rcu_read_lock();
#ifdef CONFIG_BRIDGE_NETFILTER
if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) {
br_nf_pre_routing_finish_bridge_slow(skb);
+ rcu_read_unlock();
return NETDEV_TX_OK;
}
#endif
@@ -48,7 +50,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
- rcu_read_lock();
if (is_broadcast_ether_addr(dest))
br_flood_deliver(br, skb);
else if (is_multicast_ether_addr(dest)) {
@@ -206,24 +207,23 @@ static void br_poll_controller(struct net_device *br_dev)
static void br_netpoll_cleanup(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
- struct net_bridge_port *p, *n;
+ struct net_bridge_port *p;
- list_for_each_entry_safe(p, n, &br->port_list, list) {
+ list_for_each_entry(p, &br->port_list, list)
br_netpoll_disable(p);
- }
}
-static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
+ gfp_t gfp)
{
struct net_bridge *br = netdev_priv(dev);
- struct net_bridge_port *p, *n;
+ struct net_bridge_port *p;
int err = 0;
- list_for_each_entry_safe(p, n, &br->port_list, list) {
+ list_for_each_entry(p, &br->port_list, list) {
if (!p->dev)
continue;
-
- err = br_netpoll_enable(p);
+ err = br_netpoll_enable(p, gfp);
if (err)
goto fail;
}
@@ -236,17 +236,17 @@ fail:
goto out;
}
-int br_netpoll_enable(struct net_bridge_port *p)
+int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
struct netpoll *np;
int err = 0;
- np = kzalloc(sizeof(*p->np), GFP_KERNEL);
+ np = kzalloc(sizeof(*p->np), gfp);
err = -ENOMEM;
if (!np)
goto out;
- err = __netpoll_setup(np, p->dev);
+ err = __netpoll_setup(np, p->dev, gfp);
if (err) {
kfree(np);
goto out;
@@ -267,11 +267,7 @@ void br_netpoll_disable(struct net_bridge_port *p)
p->np = NULL;
- /* Wait for transmitting packets to finish before freeing. */
- synchronize_rcu_bh();
-
- __netpoll_cleanup(np);
- kfree(np);
+ __netpoll_free_rcu(np);
}
#endif
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index e9466d412707..02015a505d2a 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -65,7 +65,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
{
skb->dev = to->dev;
- if (unlikely(netpoll_tx_running(to->dev))) {
+ if (unlikely(netpoll_tx_running(to->br->dev))) {
if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))
kfree_skb(skb);
else {
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index e1144e1617be..1c8fdc3558cd 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -361,7 +361,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
if (err)
goto err2;
- if (br_netpoll_info(br) && ((err = br_netpoll_enable(p))))
+ if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL))))
goto err3;
err = netdev_set_master(dev, br->dev);
@@ -427,6 +427,10 @@ int br_del_if(struct net_bridge *br, struct net_device *dev)
if (!p || p->br != br)
return -EINVAL;
+ /* Since more than one interface can be attached to a bridge,
+ * there still maybe an alternate path for netconsole to use;
+ * therefore there is no reason for a NETDEV_RELEASE event.
+ */
del_nbp(p);
spin_lock_bh(&br->lock);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a768b2408edf..f507d2af9646 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -316,7 +316,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
netpoll_send_skb(np, skb);
}
-extern int br_netpoll_enable(struct net_bridge_port *p);
+extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
extern void br_netpoll_disable(struct net_bridge_port *p);
#else
static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br)
@@ -329,7 +329,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
{
}
-static inline int br_netpoll_enable(struct net_bridge_port *p)
+static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
return 0;
}
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 69771c04ba8f..e597733affb8 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -94,6 +94,10 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt)
/* check the version of IP */
ip_version = skb_header_pointer(skb, 0, 1, &buf);
+ if (!ip_version) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
switch (*ip_version >> 4) {
case 4:
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 69e38db28e5f..a8020293f342 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -84,7 +84,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
return -1;
}
} else {
- pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid);
memcpy(&client->fsid, fsid, sizeof(*fsid));
}
return 0;
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index b780cb7947dd..9da7fdd3cd8a 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -466,6 +466,7 @@ void ceph_key_destroy(struct key *key) {
struct ceph_crypto_key *ckey = key->payload.data;
ceph_crypto_key_destroy(ckey);
+ kfree(ckey);
}
struct key_type key_type_ceph = {
diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
index 1919d1550d75..3572dc518bc9 100644
--- a/net/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -16,7 +16,8 @@ struct ceph_crypto_key {
static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
{
- kfree(key->key);
+ if (key)
+ kfree(key->key);
}
extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst,
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 54b531a01121..38b5dc1823d4 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -189,6 +189,9 @@ int ceph_debugfs_client_init(struct ceph_client *client)
snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
client->monc.auth->global_id);
+ dout("ceph_debugfs_client_init %p %s\n", client, name);
+
+ BUG_ON(client->debugfs_dir);
client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
if (!client->debugfs_dir)
goto out;
@@ -234,6 +237,7 @@ out:
void ceph_debugfs_client_cleanup(struct ceph_client *client)
{
+ dout("ceph_debugfs_client_cleanup %p\n", client);
debugfs_remove(client->debugfs_osdmap);
debugfs_remove(client->debugfs_monmap);
debugfs_remove(client->osdc.debugfs_file);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index b9796750034a..24c5eea8c45b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -915,7 +915,6 @@ static int prepare_write_connect(struct ceph_connection *con)
con->out_connect.authorizer_len = auth ?
cpu_to_le32(auth->authorizer_buf_len) : 0;
- con_out_kvec_reset(con);
con_out_kvec_add(con, sizeof (con->out_connect),
&con->out_connect);
if (auth && auth->authorizer_buf_len)
@@ -1557,6 +1556,7 @@ static int process_connect(struct ceph_connection *con)
return -1;
}
con->auth_retry = 1;
+ con_out_kvec_reset(con);
ret = prepare_write_connect(con);
if (ret < 0)
return ret;
@@ -1577,6 +1577,7 @@ static int process_connect(struct ceph_connection *con)
ENTITY_NAME(con->peer_name),
ceph_pr_addr(&con->peer_addr.in_addr));
reset_connection(con);
+ con_out_kvec_reset(con);
ret = prepare_write_connect(con);
if (ret < 0)
return ret;
@@ -1601,6 +1602,7 @@ static int process_connect(struct ceph_connection *con)
le32_to_cpu(con->out_connect.connect_seq),
le32_to_cpu(con->in_reply.connect_seq));
con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
+ con_out_kvec_reset(con);
ret = prepare_write_connect(con);
if (ret < 0)
return ret;
@@ -1617,6 +1619,7 @@ static int process_connect(struct ceph_connection *con)
le32_to_cpu(con->in_reply.global_seq));
get_global_seq(con->msgr,
le32_to_cpu(con->in_reply.global_seq));
+ con_out_kvec_reset(con);
ret = prepare_write_connect(con);
if (ret < 0)
return ret;
@@ -2135,7 +2138,11 @@ more:
BUG_ON(con->state != CON_STATE_CONNECTING);
con->state = CON_STATE_NEGOTIATING;
- /* Banner is good, exchange connection info */
+ /*
+ * Received banner is good, exchange connection info.
+ * Do not reset out_kvec, as sending our banner raced
+ * with receiving peer banner after connect completed.
+ */
ret = prepare_write_connect(con);
if (ret < 0)
goto out;
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 105d533b55f3..900ea0f043fc 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -311,6 +311,17 @@ int ceph_monc_open_session(struct ceph_mon_client *monc)
EXPORT_SYMBOL(ceph_monc_open_session);
/*
+ * We require the fsid and global_id in order to initialize our
+ * debugfs dir.
+ */
+static bool have_debugfs_info(struct ceph_mon_client *monc)
+{
+ dout("have_debugfs_info fsid %d globalid %lld\n",
+ (int)monc->client->have_fsid, monc->auth->global_id);
+ return monc->client->have_fsid && monc->auth->global_id > 0;
+}
+
+/*
* The monitor responds with mount ack indicate mount success. The
* included client ticket allows the client to talk to MDSs and OSDs.
*/
@@ -320,9 +331,12 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
struct ceph_client *client = monc->client;
struct ceph_monmap *monmap = NULL, *old = monc->monmap;
void *p, *end;
+ int had_debugfs_info, init_debugfs = 0;
mutex_lock(&monc->mutex);
+ had_debugfs_info = have_debugfs_info(monc);
+
dout("handle_monmap\n");
p = msg->front.iov_base;
end = p + msg->front.iov_len;
@@ -344,12 +358,22 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
if (!client->have_fsid) {
client->have_fsid = true;
+ if (!had_debugfs_info && have_debugfs_info(monc)) {
+ pr_info("client%lld fsid %pU\n",
+ ceph_client_id(monc->client),
+ &monc->client->fsid);
+ init_debugfs = 1;
+ }
mutex_unlock(&monc->mutex);
- /*
- * do debugfs initialization without mutex to avoid
- * creating a locking dependency
- */
- ceph_debugfs_client_init(client);
+
+ if (init_debugfs) {
+ /*
+ * do debugfs initialization without mutex to avoid
+ * creating a locking dependency
+ */
+ ceph_debugfs_client_init(monc->client);
+ }
+
goto out_unlocked;
}
out:
@@ -865,8 +889,10 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
{
int ret;
int was_auth = 0;
+ int had_debugfs_info, init_debugfs = 0;
mutex_lock(&monc->mutex);
+ had_debugfs_info = have_debugfs_info(monc);
if (monc->auth->ops)
was_auth = monc->auth->ops->is_authenticated(monc->auth);
monc->pending_auth = 0;
@@ -889,7 +915,22 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
__send_subscribe(monc);
__resend_generic_request(monc);
}
+
+ if (!had_debugfs_info && have_debugfs_info(monc)) {
+ pr_info("client%lld fsid %pU\n",
+ ceph_client_id(monc->client),
+ &monc->client->fsid);
+ init_debugfs = 1;
+ }
mutex_unlock(&monc->mutex);
+
+ if (init_debugfs) {
+ /*
+ * do debugfs initialization without mutex to avoid
+ * creating a locking dependency
+ */
+ ceph_debugfs_client_init(monc->client);
+ }
}
static int __validate_auth(struct ceph_mon_client *monc)
diff --git a/net/core/dev.c b/net/core/dev.c
index f91abf800161..83988362805e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1055,6 +1055,8 @@ rollback:
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
+ char *new_ifalias;
+
ASSERT_RTNL();
if (len >= IFALIASZ)
@@ -1068,9 +1070,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
return 0;
}
- dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
- if (!dev->ifalias)
+ new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+ if (!new_ifalias)
return -ENOMEM;
+ dev->ifalias = new_ifalias;
strlcpy(dev->ifalias, alias, len+1);
return len;
@@ -1639,6 +1642,19 @@ static inline int deliver_skb(struct sk_buff *skb,
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
+static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
+{
+ if (ptype->af_packet_priv == NULL)
+ return false;
+
+ if (ptype->id_match)
+ return ptype->id_match(ptype, skb->sk);
+ else if ((struct sock *)ptype->af_packet_priv == skb->sk)
+ return true;
+
+ return false;
+}
+
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
@@ -1656,8 +1672,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
* they originated from - MvS (miquels@drinkel.ow.org)
*/
if ((ptype->dev == dev || !ptype->dev) &&
- (ptype->af_packet_priv == NULL ||
- (struct sock *)ptype->af_packet_priv != skb->sk)) {
+ (!skb_loop_sk(ptype, skb))) {
if (pt_prev) {
deliver_skb(skb2, pt_prev, skb->dev);
pt_prev = ptype;
@@ -5729,6 +5744,7 @@ EXPORT_SYMBOL(netdev_refcnt_read);
/**
* netdev_wait_allrefs - wait until all references are gone.
+ * @dev: target net_device
*
* This is called when unregistering network devices.
*
diff --git a/net/core/dst.c b/net/core/dst.c
index 069d51d29414..56d63612e1e4 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -149,7 +149,15 @@ int dst_discard(struct sk_buff *skb)
}
EXPORT_SYMBOL(dst_discard);
-const u32 dst_default_metrics[RTAX_MAX];
+const u32 dst_default_metrics[RTAX_MAX + 1] = {
+ /* This initializer is needed to force linker to place this variable
+ * into const section. Otherwise it might end into bss section.
+ * We really want to avoid false sharing on this variable, and catch
+ * any writes on it.
+ */
+ [RTAX_MAX] = 0xdeadbeef,
+};
+
void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
int initial_ref, int initial_obsolete, unsigned short flags)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index b4c90e42b443..e4ba3e70c174 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -26,6 +26,7 @@
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/if_vlan.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <asm/unaligned.h>
@@ -54,7 +55,7 @@ static atomic_t trapped;
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void arp_reply(struct sk_buff *skb);
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
static unsigned int carrier_timeout = 4;
module_param(carrier_timeout, uint, 0644);
@@ -170,7 +171,8 @@ static void poll_napi(struct net_device *dev)
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(dev->npinfo, napi, budget);
+ budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
+ napi, budget);
spin_unlock(&napi->poll_lock);
if (!budget)
@@ -185,13 +187,14 @@ static void service_arp_queue(struct netpoll_info *npi)
struct sk_buff *skb;
while ((skb = skb_dequeue(&npi->arp_tx)))
- arp_reply(skb);
+ netpoll_arp_reply(skb, npi);
}
}
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
+ struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
if (!dev || !netif_running(dev))
return;
@@ -206,17 +209,18 @@ static void netpoll_poll_dev(struct net_device *dev)
poll_napi(dev);
if (dev->flags & IFF_SLAVE) {
- if (dev->npinfo) {
+ if (ni) {
struct net_device *bond_dev = dev->master;
struct sk_buff *skb;
- while ((skb = skb_dequeue(&dev->npinfo->arp_tx))) {
+ struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo);
+ while ((skb = skb_dequeue(&ni->arp_tx))) {
skb->dev = bond_dev;
- skb_queue_tail(&bond_dev->npinfo->arp_tx, skb);
+ skb_queue_tail(&bond_ni->arp_tx, skb);
}
}
}
- service_arp_queue(dev->npinfo);
+ service_arp_queue(ni);
zap_completion_queue();
}
@@ -302,6 +306,7 @@ static int netpoll_owner_active(struct net_device *dev)
return 0;
}
+/* call with IRQ disabled */
void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
struct net_device *dev)
{
@@ -309,8 +314,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
unsigned long tries;
const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
- struct netpoll_info *npinfo = np->dev->npinfo;
+ struct netpoll_info *npinfo;
+
+ WARN_ON_ONCE(!irqs_disabled());
+ npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
__kfree_skb(skb);
return;
@@ -319,16 +327,22 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
/* don't get messages out of order, and no recursion */
if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
struct netdev_queue *txq;
- unsigned long flags;
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
- local_irq_save(flags);
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
if (__netif_tx_trylock(txq)) {
if (!netif_xmit_stopped(txq)) {
+ if (vlan_tx_tag_present(skb) &&
+ !(netif_skb_features(skb) & NETIF_F_HW_VLAN_TX)) {
+ skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
+ if (unlikely(!skb))
+ break;
+ skb->vlan_tci = 0;
+ }
+
status = ops->ndo_start_xmit(skb, dev);
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
@@ -347,10 +361,9 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
}
WARN_ONCE(!irqs_disabled(),
- "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n",
+ "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
dev->name, ops->ndo_start_xmit);
- local_irq_restore(flags);
}
if (status != NETDEV_TX_OK) {
@@ -423,9 +436,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void arp_reply(struct sk_buff *skb)
+static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
{
- struct netpoll_info *npinfo = skb->dev->npinfo;
struct arphdr *arp;
unsigned char *arp_ptr;
int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
@@ -543,13 +555,12 @@ static void arp_reply(struct sk_buff *skb)
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
-int __netpoll_rx(struct sk_buff *skb)
+int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
{
int proto, len, ulen;
int hits = 0;
const struct iphdr *iph;
struct udphdr *uh;
- struct netpoll_info *npinfo = skb->dev->npinfo;
struct netpoll *np, *tmp;
if (list_empty(&npinfo->rx_np))
@@ -565,6 +576,12 @@ int __netpoll_rx(struct sk_buff *skb)
return 1;
}
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ skb = vlan_untag(skb);
+ if (unlikely(!skb))
+ goto out;
+ }
+
proto = ntohs(eth_hdr(skb)->h_proto);
if (proto != ETH_P_IP)
goto out;
@@ -715,7 +732,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
}
EXPORT_SYMBOL(netpoll_parse_options);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
{
struct netpoll_info *npinfo;
const struct net_device_ops *ops;
@@ -734,7 +751,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
}
if (!ndev->npinfo) {
- npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
+ npinfo = kmalloc(sizeof(*npinfo), gfp);
if (!npinfo) {
err = -ENOMEM;
goto out;
@@ -752,7 +769,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
ops = np->dev->netdev_ops;
if (ops->ndo_netpoll_setup) {
- err = ops->ndo_netpoll_setup(ndev, npinfo);
+ err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
if (err)
goto free_npinfo;
}
@@ -857,7 +874,7 @@ int netpoll_setup(struct netpoll *np)
refill_skbs();
rtnl_lock();
- err = __netpoll_setup(np, ndev);
+ err = __netpoll_setup(np, ndev, GFP_KERNEL);
rtnl_unlock();
if (err)
@@ -878,6 +895,24 @@ static int __init netpoll_init(void)
}
core_initcall(netpoll_init);
+static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
+{
+ struct netpoll_info *npinfo =
+ container_of(rcu_head, struct netpoll_info, rcu);
+
+ skb_queue_purge(&npinfo->arp_tx);
+ skb_queue_purge(&npinfo->txq);
+
+ /* we can't call cancel_delayed_work_sync here, as we are in softirq */
+ cancel_delayed_work(&npinfo->tx_work);
+
+ /* clean after last, unfinished work */
+ __skb_queue_purge(&npinfo->txq);
+ /* now cancel it again */
+ cancel_delayed_work(&npinfo->tx_work);
+ kfree(npinfo);
+}
+
void __netpoll_cleanup(struct netpoll *np)
{
struct netpoll_info *npinfo;
@@ -903,20 +938,24 @@ void __netpoll_cleanup(struct netpoll *np)
ops->ndo_netpoll_cleanup(np->dev);
RCU_INIT_POINTER(np->dev->npinfo, NULL);
+ call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
+ }
+}
+EXPORT_SYMBOL_GPL(__netpoll_cleanup);
- /* avoid racing with NAPI reading npinfo */
- synchronize_rcu_bh();
+static void rcu_cleanup_netpoll(struct rcu_head *rcu_head)
+{
+ struct netpoll *np = container_of(rcu_head, struct netpoll, rcu);
- skb_queue_purge(&npinfo->arp_tx);
- skb_queue_purge(&npinfo->txq);
- cancel_delayed_work_sync(&npinfo->tx_work);
+ __netpoll_cleanup(np);
+ kfree(np);
+}
- /* clean after last, unfinished work */
- __skb_queue_purge(&npinfo->txq);
- kfree(npinfo);
- }
+void __netpoll_free_rcu(struct netpoll *np)
+{
+ call_rcu_bh(&np->rcu, rcu_cleanup_netpoll);
}
-EXPORT_SYMBOL_GPL(__netpoll_cleanup);
+EXPORT_SYMBOL_GPL(__netpoll_free_rcu);
void netpoll_cleanup(struct netpoll *np)
{
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index ed0c0431fcd8..c75e3f9d060f 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -101,12 +101,10 @@ static int write_update_netdev_table(struct net_device *dev)
u32 max_len;
struct netprio_map *map;
- rtnl_lock();
max_len = atomic_read(&max_prioidx) + 1;
map = rtnl_dereference(dev->priomap);
if (!map || map->priomap_len < max_len)
ret = extend_netdev_table(dev, max_len);
- rtnl_unlock();
return ret;
}
@@ -256,17 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
if (!dev)
goto out_free_devname;
+ rtnl_lock();
ret = write_update_netdev_table(dev);
if (ret < 0)
goto out_put_dev;
- rcu_read_lock();
- map = rcu_dereference(dev->priomap);
+ map = rtnl_dereference(dev->priomap);
if (map)
map->priomap[prioidx] = priority;
- rcu_read_unlock();
out_put_dev:
+ rtnl_unlock();
dev_put(dev);
out_free_devname:
@@ -277,12 +275,6 @@ out_free_devname:
void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
{
struct task_struct *p;
- char *tmp = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
-
- if (!tmp) {
- pr_warn("Unable to attach cgrp due to alloc failure!\n");
- return;
- }
cgroup_taskset_for_each(p, cgrp, tset) {
unsigned int fd;
@@ -296,32 +288,24 @@ void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
continue;
}
- rcu_read_lock();
+ spin_lock(&files->file_lock);
fdt = files_fdtable(files);
for (fd = 0; fd < fdt->max_fds; fd++) {
- char *path;
struct file *file;
struct socket *sock;
- unsigned long s;
- int rv, err = 0;
+ int err;
file = fcheck_files(files, fd);
if (!file)
continue;
- path = d_path(&file->f_path, tmp, PAGE_SIZE);
- rv = sscanf(path, "socket:[%lu]", &s);
- if (rv <= 0)
- continue;
-
sock = sock_from_file(file, &err);
- if (!err)
+ if (sock)
sock_update_netprioidx(sock->sk, p);
}
- rcu_read_unlock();
+ spin_unlock(&files->file_lock);
task_unlock(p);
}
- kfree(tmp);
}
static struct cftype ss_files[] = {
diff --git a/net/core/scm.c b/net/core/scm.c
index 8f6ccfd68ef4..040cebeed45b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -265,6 +265,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax;
i++, cmfptr++)
{
+ struct socket *sock;
int new_fd;
err = security_file_receive(fp[i]);
if (err)
@@ -281,6 +282,9 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
}
/* Bump the usage count and install the file. */
get_file(fp[i]);
+ sock = sock_from_file(fp[i], &err);
+ if (sock)
+ sock_update_netprioidx(sock->sk, current);
fd_install(new_fd, fp[i]);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 8f67ced8d6a8..7f64467535d1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1523,7 +1523,12 @@ EXPORT_SYMBOL(sock_rfree);
void sock_edemux(struct sk_buff *skb)
{
- sock_put(skb->sk);
+ struct sock *sk = skb->sk;
+
+ if (sk->sk_state == TCP_TIME_WAIT)
+ inet_twsk_put(inet_twsk(sk));
+ else
+ sock_put(sk);
}
EXPORT_SYMBOL(sock_edemux);
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 75c3582a7678..fb85d371a8de 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -246,7 +246,7 @@ static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk,
u32 __user *optval, int __user *optlen)
{
int rc = -ENOPROTOOPT;
- if (ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL)
+ if (ccid != NULL && ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL)
rc = ccid->ccid_ops->ccid_hc_rx_getsockopt(sk, optname, len,
optval, optlen);
return rc;
@@ -257,7 +257,7 @@ static inline int ccid_hc_tx_getsockopt(struct ccid *ccid, struct sock *sk,
u32 __user *optval, int __user *optlen)
{
int rc = -ENOPROTOOPT;
- if (ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL)
+ if (ccid != NULL && ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL)
rc = ccid->ccid_ops->ccid_hc_tx_getsockopt(sk, optname, len,
optval, optlen);
return rc;
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index d65e98798eca..119c04317d48 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -535,6 +535,7 @@ static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len,
case DCCP_SOCKOPT_CCID_TX_INFO:
if (len < sizeof(tfrc))
return -EINVAL;
+ memset(&tfrc, 0, sizeof(tfrc));
tfrc.tfrctx_x = hc->tx_x;
tfrc.tfrctx_x_recv = hc->tx_x_recv;
tfrc.tfrctx_x_calc = hc->tx_x_calc;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index f0cdb30921c0..57bd978483e1 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -367,7 +367,7 @@ static void __leaf_free_rcu(struct rcu_head *head)
static inline void free_leaf(struct leaf *l)
{
- call_rcu_bh(&l->rcu, __leaf_free_rcu);
+ call_rcu(&l->rcu, __leaf_free_rcu);
}
static inline void free_leaf_info(struct leaf_info *leaf)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index db0cf17c00f7..7f75f21d7b83 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -404,12 +404,15 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct inet_sock *newinet = inet_sk(newsk);
- struct ip_options_rcu *opt = ireq->opt;
+ struct ip_options_rcu *opt;
struct net *net = sock_net(sk);
struct flowi4 *fl4;
struct rtable *rt;
fl4 = &newinet->cork.fl.u.ip4;
+
+ rcu_read_lock();
+ opt = rcu_dereference(newinet->inet_opt);
flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -421,11 +424,13 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_gateway)
goto route_err;
+ rcu_read_unlock();
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
+ rcu_read_unlock();
IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ba39a52d18c1..c196d749daf2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -197,7 +197,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
- if (neigh) {
+ if (!IS_ERR(neigh)) {
int res = dst_neigh_output(dst, neigh, skb);
rcu_read_unlock_bh();
@@ -1338,10 +1338,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
iph->ihl = 5;
iph->tos = inet->tos;
iph->frag_off = df;
- ip_select_ident(iph, &rt->dst, sk);
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);
+ ip_select_ident(iph, &rt->dst, sk);
if (opt) {
iph->ihl += opt->optlen>>2;
@@ -1366,9 +1366,8 @@ out:
return skb;
}
-int ip_send_skb(struct sk_buff *skb)
+int ip_send_skb(struct net *net, struct sk_buff *skb)
{
- struct net *net = sock_net(skb->sk);
int err;
err = ip_local_out(skb);
@@ -1391,7 +1390,7 @@ int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)
return 0;
/* Netfilter gets whole the not fragmented skb. */
- return ip_send_skb(skb);
+ return ip_send_skb(sock_net(sk), skb);
}
/*
@@ -1536,6 +1535,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
arg->csumoffset) = csum_fold(csum_add(nskb->csum,
arg->csum));
nskb->ip_summed = CHECKSUM_NONE;
+ skb_orphan(nskb);
skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
ip_push_pending_frames(sk, &fl4);
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8eec8f4a0536..ebdf06f938bf 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -124,6 +124,8 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
static struct kmem_cache *mrt_cachep __read_mostly;
static struct mr_table *ipmr_new_table(struct net *net, u32 id);
+static void ipmr_free_table(struct mr_table *mrt);
+
static int ip_mr_forward(struct net *net, struct mr_table *mrt,
struct sk_buff *skb, struct mfc_cache *cache,
int local);
@@ -131,6 +133,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert);
static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
+static void mroute_clean_tables(struct mr_table *mrt);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -271,7 +274,7 @@ static void __net_exit ipmr_rules_exit(struct net *net)
list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
list_del(&mrt->list);
- kfree(mrt);
+ ipmr_free_table(mrt);
}
fib_rules_unregister(net->ipv4.mr_rules_ops);
}
@@ -299,7 +302,7 @@ static int __net_init ipmr_rules_init(struct net *net)
static void __net_exit ipmr_rules_exit(struct net *net)
{
- kfree(net->ipv4.mrt);
+ ipmr_free_table(net->ipv4.mrt);
}
#endif
@@ -336,6 +339,13 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
return mrt;
}
+static void ipmr_free_table(struct mr_table *mrt)
+{
+ del_timer_sync(&mrt->ipmr_expire_timer);
+ mroute_clean_tables(mrt);
+ kfree(mrt);
+}
+
/* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v)
diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c
index ea4a23813d26..9c87cde28ff8 100644
--- a/net/ipv4/netfilter/nf_nat_sip.c
+++ b/net/ipv4/netfilter/nf_nat_sip.c
@@ -148,7 +148,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff,
if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen,
hdr, NULL, &matchoff, &matchlen,
&addr, &port) > 0) {
- unsigned int matchend, poff, plen, buflen, n;
+ unsigned int olen, matchend, poff, plen, buflen, n;
char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")];
/* We're only interested in headers related to this
@@ -163,17 +163,18 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff,
goto next;
}
+ olen = *datalen;
if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen,
&addr, port))
return NF_DROP;
- matchend = matchoff + matchlen;
+ matchend = matchoff + matchlen + *datalen - olen;
/* The maddr= parameter (RFC 2361) specifies where to send
* the reply. */
if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen,
"maddr=", &poff, &plen,
- &addr) > 0 &&
+ &addr, true) > 0 &&
addr.ip == ct->tuplehash[dir].tuple.src.u3.ip &&
addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) {
buflen = sprintf(buffer, "%pI4",
@@ -187,7 +188,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff,
* from which the server received the request. */
if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen,
"received=", &poff, &plen,
- &addr) > 0 &&
+ &addr, false) > 0 &&
addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip &&
addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) {
buflen = sprintf(buffer, "%pI4",
@@ -501,7 +502,10 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff,
ret = nf_ct_expect_related(rtcp_exp);
if (ret == 0)
break;
- else if (ret != -EBUSY) {
+ else if (ret == -EBUSY) {
+ nf_ct_unexpect_related(rtp_exp);
+ continue;
+ } else if (ret < 0) {
nf_ct_unexpect_related(rtp_exp);
port = 0;
break;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e4ba974f143c..82cf2a722b23 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -934,12 +934,14 @@ static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
+ rcu_read_lock();
if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
struct fib_nh *nh = &FIB_RES_NH(res);
update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
jiffies + ip_rt_mtu_expires);
}
+ rcu_read_unlock();
return mtu;
}
@@ -956,7 +958,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
dst->obsolete = DST_OBSOLETE_KILL;
} else {
rt->rt_pmtu = mtu;
- dst_set_expires(&rt->dst, ip_rt_mtu_expires);
+ rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
}
}
@@ -1263,7 +1265,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *) dst;
- if (dst->flags & DST_NOCACHE) {
+ if (!list_empty(&rt->rt_uncached)) {
spin_lock_bh(&rt_uncached_lock);
list_del(&rt->rt_uncached);
spin_unlock_bh(&rt_uncached_lock);
@@ -2028,7 +2030,6 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
}
dev_out = net->loopback_dev;
fl4->flowi4_oif = dev_out->ifindex;
- res.fi = NULL;
flags |= RTCF_LOCAL;
goto make_route;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2fd2bc9e3c64..6e38c6c23caa 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2926,13 +2926,14 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
* tcp_xmit_retransmit_queue().
*/
static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
- int newly_acked_sacked, bool is_dupack,
+ int prior_sacked, bool is_dupack,
int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
+ int newly_acked_sacked = 0;
int fast_rexmit = 0;
if (WARN_ON(!tp->packets_out && tp->sacked_out))
@@ -2992,6 +2993,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
tcp_add_reno_sack(sk);
} else
do_lost = tcp_try_undo_partial(sk, pkts_acked);
+ newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
break;
case TCP_CA_Loss:
if (flag & FLAG_DATA_ACKED)
@@ -3013,6 +3015,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (is_dupack)
tcp_add_reno_sack(sk);
}
+ newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
@@ -3590,7 +3593,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
int prior_packets;
int prior_sacked = tp->sacked_out;
int pkts_acked = 0;
- int newly_acked_sacked = 0;
bool frto_cwnd = false;
/* If the ack is older than previous acks
@@ -3666,8 +3668,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
pkts_acked = prior_packets - tp->packets_out;
- newly_acked_sacked = (prior_packets - prior_sacked) -
- (tp->packets_out - tp->sacked_out);
if (tp->frto_counter)
frto_cwnd = tcp_process_frto(sk, flag);
@@ -3681,7 +3681,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
is_dupack, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
@@ -3698,7 +3698,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK)
- tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
is_dupack, flag);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
@@ -3718,8 +3718,7 @@ old_ack:
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- newly_acked_sacked = tp->sacked_out - prior_sacked;
- tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+ tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
is_dupack, flag);
}
@@ -5392,6 +5391,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
{
struct tcp_sock *tp = tcp_sk(sk);
+ if (unlikely(sk->sk_rx_dst == NULL))
+ inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
/*
* Header prediction.
* The code loosely follows the one in the famous
@@ -5605,7 +5606,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
tcp_set_state(sk, TCP_ESTABLISHED);
if (skb != NULL) {
- inet_sk_rx_dst_set(sk, skb);
+ icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
security_inet_conn_established(sk, skb);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 42b2a6a73092..00a748d14062 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -417,10 +417,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
tp->mtu_info = info;
- if (!sock_owned_by_user(sk))
+ if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
- else
- set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags);
+ } else {
+ if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags))
+ sock_hold(sk);
+ }
goto out;
}
@@ -1462,6 +1464,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
goto exit_nonewsk;
newsk->sk_gso_type = SKB_GSO_TCPV4;
+ inet_sk_rx_dst_set(newsk, skb);
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
@@ -1627,9 +1630,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
sk->sk_rx_dst = NULL;
}
}
- if (unlikely(sk->sk_rx_dst == NULL))
- inet_sk_rx_dst_set(sk, skb);
-
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
rsk = sk;
goto reset;
@@ -1872,10 +1872,21 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
.twsk_destructor= tcp_twsk_destructor,
};
+void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+}
+EXPORT_SYMBOL(inet_sk_rx_dst_set);
+
const struct inet_connection_sock_af_ops ipv4_specific = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
+ .sk_rx_dst_set = inet_sk_rx_dst_set,
.conn_request = tcp_v4_conn_request,
.syn_recv_sock = tcp_v4_syn_recv_sock,
.net_header_len = sizeof(struct iphdr),
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 2288a6399e1e..0abe67bb4d3a 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -731,6 +731,18 @@ static int __net_init tcp_net_metrics_init(struct net *net)
static void __net_exit tcp_net_metrics_exit(struct net *net)
{
+ unsigned int i;
+
+ for (i = 0; i < (1U << net->ipv4.tcp_metrics_hash_log) ; i++) {
+ struct tcp_metrics_block *tm, *next;
+
+ tm = rcu_dereference_protected(net->ipv4.tcp_metrics_hash[i].chain, 1);
+ while (tm) {
+ next = rcu_dereference_protected(tm->tcpm_next, 1);
+ kfree(tm);
+ tm = next;
+ }
+ }
kfree(net->ipv4.tcp_metrics_hash);
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 232a90c3ec86..6ff7f10dce9d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -387,8 +387,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
- inet_sk_rx_dst_set(newsk, skb);
-
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
* copy any s_data_payload stored at the original socket.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a7b3ec9b6c3e..d04632673a9e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -910,14 +910,18 @@ void tcp_release_cb(struct sock *sk)
if (flags & (1UL << TCP_TSQ_DEFERRED))
tcp_tsq_handler(sk);
- if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED))
+ if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
tcp_write_timer_handler(sk);
-
- if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED))
+ __sock_put(sk);
+ }
+ if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) {
tcp_delack_timer_handler(sk);
-
- if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED))
+ __sock_put(sk);
+ }
+ if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
sk->sk_prot->mtu_reduced(sk);
+ __sock_put(sk);
+ }
}
EXPORT_SYMBOL(tcp_release_cb);
@@ -940,7 +944,7 @@ void __init tcp_tasklet_init(void)
* We cant xmit new skbs from this context, as we might already
* hold qdisc lock.
*/
-void tcp_wfree(struct sk_buff *skb)
+static void tcp_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6df36ad55a38..b774a03bd1dc 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -252,7 +252,8 @@ static void tcp_delack_timer(unsigned long data)
inet_csk(sk)->icsk_ack.blocked = 1;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
/* deleguate our work to tcp_release_cb() */
- set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags);
+ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
+ sock_hold(sk);
}
bh_unlock_sock(sk);
sock_put(sk);
@@ -481,7 +482,8 @@ static void tcp_write_timer(unsigned long data)
tcp_write_timer_handler(sk);
} else {
/* deleguate our work to tcp_release_cb() */
- set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags);
+ if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
+ sock_hold(sk);
}
bh_unlock_sock(sk);
sock_put(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b4c3582a991f..2814f66dac64 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -758,7 +758,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
uh->check = CSUM_MANGLED_0;
send:
- err = ip_send_skb(skb);
+ err = ip_send_skb(sock_net(sk), skb);
if (err) {
if (err == -ENOBUFS && !inet->recverr) {
UDP_INC_STATS_USER(sock_net(sk),
@@ -1226,6 +1226,11 @@ try_again:
if (unlikely(err)) {
trace_kfree_skb(skb, udp_recvmsg);
+ if (!peeked) {
+ atomic_inc(&sk->sk_drops);
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INERRORS, is_udplite);
+ }
goto out_free;
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 79181819a24f..6bc85f7c31e3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -494,8 +494,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf)
struct net_device *dev;
struct inet6_dev *idev;
- rcu_read_lock();
- for_each_netdev_rcu(net, dev) {
+ for_each_netdev(net, dev) {
idev = __in6_dev_get(dev);
if (idev) {
int changed = (!idev->cnf.forwarding) ^ (!newf);
@@ -504,7 +503,6 @@ static void addrconf_forward_change(struct net *net, __s32 newf)
dev_forward_change(idev);
}
}
- rcu_read_unlock();
}
static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 6dc7fd353ef5..282f3723ee19 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -167,8 +167,6 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
struct esp_data *esp = x->data;
/* skb is pure payload to encrypt */
- err = -ENOMEM;
-
aead = esp->aead;
alen = crypto_aead_authsize(aead);
@@ -203,8 +201,10 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
}
tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
- if (!tmp)
+ if (!tmp) {
+ err = -ENOMEM;
goto error;
+ }
seqhi = esp_tmp_seqhi(tmp);
iv = esp_tmp_iv(aead, tmp, seqhilen);
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index da2e92d05c15..745a32042950 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -307,10 +307,10 @@ static int __net_init ipv6_proc_init_net(struct net *net)
goto proc_dev_snmp6_fail;
return 0;
+proc_dev_snmp6_fail:
+ proc_net_remove(net, "snmp6");
proc_snmp6_fail:
proc_net_remove(net, "sockstat6");
-proc_dev_snmp6_fail:
- proc_net_remove(net, "dev_snmp6");
return -ENOMEM;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c66b90f71c9b..acd32e3f1b68 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -94,6 +94,18 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
}
#endif
+static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+ inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+ if (rt->rt6i_node)
+ inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+}
+
static void tcp_v6_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
@@ -391,8 +403,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
tp->mtu_info = ntohl(info);
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
- else
- set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags);
+ else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
+ &tp->tsq_flags))
+ sock_hold(sk);
goto out;
}
@@ -1270,6 +1283,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
newsk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(newsk, dst, NULL, NULL);
+ inet6_sk_rx_dst_set(newsk, skb);
newtcp6sk = (struct tcp6_sock *)newsk;
inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;
@@ -1447,7 +1461,17 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+ struct dst_entry *dst = sk->sk_rx_dst;
+
sock_rps_save_rxhash(sk, skb);
+ if (dst) {
+ if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
+ dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
+ dst_release(dst);
+ sk->sk_rx_dst = NULL;
+ }
+ }
+
if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
goto reset;
if (opt_skb)
@@ -1705,9 +1729,9 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
struct dst_entry *dst = sk->sk_rx_dst;
struct inet_sock *icsk = inet_sk(sk);
if (dst)
- dst = dst_check(dst, 0);
+ dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
if (dst &&
- icsk->rx_dst_ifindex == inet6_iif(skb))
+ icsk->rx_dst_ifindex == skb->skb_iif)
skb_dst_set_noref(skb, dst);
}
}
@@ -1723,6 +1747,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
.queue_xmit = inet6_csk_xmit,
.send_check = tcp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
+ .sk_rx_dst_set = inet6_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct ipv6hdr),
@@ -1754,6 +1779,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
.queue_xmit = ip_queue_xmit,
.send_check = tcp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
+ .sk_rx_dst_set = inet_sk_rx_dst_set,
.conn_request = tcp_v6_conn_request,
.syn_recv_sock = tcp_v6_syn_recv_sock,
.net_header_len = sizeof(struct iphdr),
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 99d0077b56b8..07e2bfef6845 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -394,6 +394,17 @@ try_again:
}
if (unlikely(err)) {
trace_kfree_skb(skb, udpv6_recvmsg);
+ if (!peeked) {
+ atomic_inc(&sk->sk_drops);
+ if (is_udp4)
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INERRORS,
+ is_udplite);
+ else
+ UDP6_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INERRORS,
+ is_udplite);
+ }
goto out_free;
}
if (!peeked) {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index ef39812107b1..f8c4c08ffb60 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -73,6 +73,13 @@ static int xfrm6_get_tos(const struct flowi *fl)
return 0;
}
+static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst)
+{
+ struct rt6_info *rt = (struct rt6_info *)xdst;
+
+ rt6_init_peer(rt, net->ipv6.peers);
+}
+
static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
@@ -286,6 +293,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
+ .init_dst = xfrm6_init_dst,
.init_path = xfrm6_init_path,
.fill_dst = xfrm6_fill_dst,
.blackhole_route = ip6_blackhole_route,
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 393355d37b47..1a9f3723c13c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1347,11 +1347,10 @@ static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
/* Remove from tunnel list */
spin_lock_bh(&pn->l2tp_tunnel_list_lock);
list_del_rcu(&tunnel->list);
+ kfree_rcu(tunnel, rcu);
spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
- synchronize_rcu();
atomic_dec(&l2tp_tunnel_count);
- kfree(tunnel);
}
/* Create a socket for the tunnel, if one isn't set up by
@@ -1502,6 +1501,8 @@ out:
return err;
}
+static struct lock_class_key l2tp_socket_class;
+
int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
{
struct l2tp_tunnel *tunnel = NULL;
@@ -1606,6 +1607,8 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
tunnel->old_sk_destruct = sk->sk_destruct;
sk->sk_destruct = &l2tp_tunnel_destruct;
tunnel->sock = sk;
+ lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
+
sk->sk_allocation = GFP_ATOMIC;
/* Add tunnel to our list */
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a38ec6cdeee1..56d583e083a7 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -163,6 +163,7 @@ struct l2tp_tunnel_cfg {
struct l2tp_tunnel {
int magic; /* Should be L2TP_TUNNEL_MAGIC */
+ struct rcu_head rcu;
rwlock_t hlist_lock; /* protect session_hlist */
struct hlist_head session_hlist[L2TP_HASH_SIZE];
/* hashed list of sessions,
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index f9ee74deeac2..3bfb34aaee29 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -153,7 +153,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length);
}
- if (!pskb_may_pull(skb, sizeof(ETH_HLEN)))
+ if (!pskb_may_pull(skb, ETH_HLEN))
goto error;
secpath_reset(skb);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 35e1e4bde587..927547171bc7 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -410,6 +410,7 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
lsa->l2tp_family = AF_INET6;
lsa->l2tp_flowinfo = 0;
lsa->l2tp_scope_id = 0;
+ lsa->l2tp_unused = 0;
if (peer) {
if (!lsk->peer_conn_id)
return -ENOTCONN;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index f6fe4d400502..c2190005a114 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -969,14 +969,13 @@ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr,
struct sockaddr_llc sllc;
struct sock *sk = sock->sk;
struct llc_sock *llc = llc_sk(sk);
- int rc = 0;
+ int rc = -EBADF;
memset(&sllc, 0, sizeof(sllc));
lock_sock(sk);
if (sock_flag(sk, SOCK_ZAPPED))
goto out;
*uaddrlen = sizeof(sllc);
- memset(uaddr, 0, *uaddrlen);
if (peer) {
rc = -ENOTCONN;
if (sk->sk_state != TCP_ESTABLISHED)
@@ -1206,7 +1205,7 @@ static int __init llc2_init(void)
rc = llc_proc_init();
if (rc != 0) {
printk(llc_proc_err_msg);
- goto out_unregister_llc_proto;
+ goto out_station;
}
rc = llc_sysctl_init();
if (rc) {
@@ -1226,7 +1225,8 @@ out_sysctl:
llc_sysctl_exit();
out_proc:
llc_proc_exit();
-out_unregister_llc_proto:
+out_station:
+ llc_station_exit();
proto_unregister(&llc_proto);
goto out;
}
diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c
index e32cab44ea95..dd3e83328ad5 100644
--- a/net/llc/llc_input.c
+++ b/net/llc/llc_input.c
@@ -42,6 +42,7 @@ static void (*llc_type_handlers[2])(struct llc_sap *sap,
void llc_add_pack(int type, void (*handler)(struct llc_sap *sap,
struct sk_buff *skb))
{
+ smp_wmb(); /* ensure initialisation is complete before it's called */
if (type == LLC_DEST_SAP || type == LLC_DEST_CONN)
llc_type_handlers[type - 1] = handler;
}
@@ -50,11 +51,19 @@ void llc_remove_pack(int type)
{
if (type == LLC_DEST_SAP || type == LLC_DEST_CONN)
llc_type_handlers[type - 1] = NULL;
+ synchronize_net();
}
void llc_set_station_handler(void (*handler)(struct sk_buff *skb))
{
+ /* Ensure initialisation is complete before it's called */
+ if (handler)
+ smp_wmb();
+
llc_station_handler = handler;
+
+ if (!handler)
+ synchronize_net();
}
/**
@@ -150,6 +159,8 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev,
int dest;
int (*rcv)(struct sk_buff *, struct net_device *,
struct packet_type *, struct net_device *);
+ void (*sta_handler)(struct sk_buff *skb);
+ void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb);
if (!net_eq(dev_net(dev), &init_net))
goto drop;
@@ -182,7 +193,8 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev,
*/
rcv = rcu_dereference(sap->rcv_func);
dest = llc_pdu_type(skb);
- if (unlikely(!dest || !llc_type_handlers[dest - 1])) {
+ sap_handler = dest ? ACCESS_ONCE(llc_type_handlers[dest - 1]) : NULL;
+ if (unlikely(!sap_handler)) {
if (rcv)
rcv(skb, dev, pt, orig_dev);
else
@@ -193,7 +205,7 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev,
if (cskb)
rcv(cskb, dev, pt, orig_dev);
}
- llc_type_handlers[dest - 1](sap, skb);
+ sap_handler(sap, skb);
}
llc_sap_put(sap);
out:
@@ -202,9 +214,10 @@ drop:
kfree_skb(skb);
goto out;
handle_station:
- if (!llc_station_handler)
+ sta_handler = ACCESS_ONCE(llc_station_handler);
+ if (!sta_handler)
goto drop;
- llc_station_handler(skb);
+ sta_handler(skb);
goto out;
}
diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c
index 39a8d8924b9c..b2f2bac2c2a2 100644
--- a/net/llc/llc_station.c
+++ b/net/llc/llc_station.c
@@ -268,7 +268,7 @@ static int llc_station_ac_send_null_dsap_xid_c(struct sk_buff *skb)
out:
return rc;
free:
- kfree_skb(skb);
+ kfree_skb(nskb);
goto out;
}
@@ -293,7 +293,7 @@ static int llc_station_ac_send_xid_r(struct sk_buff *skb)
out:
return rc;
free:
- kfree_skb(skb);
+ kfree_skb(nskb);
goto out;
}
@@ -322,7 +322,7 @@ static int llc_station_ac_send_test_r(struct sk_buff *skb)
out:
return rc;
free:
- kfree_skb(skb);
+ kfree_skb(nskb);
goto out;
}
@@ -687,12 +687,8 @@ static void llc_station_rcv(struct sk_buff *skb)
llc_station_state_process(skb);
}
-int __init llc_station_init(void)
+void __init llc_station_init(void)
{
- int rc = -ENOBUFS;
- struct sk_buff *skb;
- struct llc_station_state_ev *ev;
-
skb_queue_head_init(&llc_main_station.mac_pdu_q);
skb_queue_head_init(&llc_main_station.ev_q.list);
spin_lock_init(&llc_main_station.ev_q.lock);
@@ -700,23 +696,12 @@ int __init llc_station_init(void)
(unsigned long)&llc_main_station);
llc_main_station.ack_timer.expires = jiffies +
sysctl_llc_station_ack_timeout;
- skb = alloc_skb(0, GFP_ATOMIC);
- if (!skb)
- goto out;
- rc = 0;
- llc_set_station_handler(llc_station_rcv);
- ev = llc_station_ev(skb);
- memset(ev, 0, sizeof(*ev));
llc_main_station.maximum_retry = 1;
- llc_main_station.state = LLC_STATION_STATE_DOWN;
- ev->type = LLC_STATION_EV_TYPE_SIMPLE;
- ev->prim_type = LLC_STATION_EV_ENABLE_WITHOUT_DUP_ADDR_CHECK;
- rc = llc_station_next_state(skb);
-out:
- return rc;
+ llc_main_station.state = LLC_STATION_STATE_UP;
+ llc_set_station_handler(llc_station_rcv);
}
-void __exit llc_station_exit(void)
+void llc_station_exit(void)
{
llc_set_station_handler(NULL);
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 84444dda194b..f51013c07b9f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1171,8 +1171,10 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
goto out_err;
}
svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!svc->stats.cpustats)
+ if (!svc->stats.cpustats) {
+ ret = -ENOMEM;
goto out_err;
+ }
/* I'm the first user of the service */
atomic_set(&svc->usecnt, 0);
@@ -2759,6 +2761,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
struct ip_vs_timeout_user t;
+ memset(&t, 0, sizeof(t));
__ip_vs_get_timeouts(net, &t);
if (copy_to_user(user, &t, sizeof(t)) != 0)
ret = -EFAULT;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index cf4875565d67..2ceec64b19f9 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -249,12 +249,15 @@ static void death_by_event(unsigned long ul_conntrack)
{
struct nf_conn *ct = (void *)ul_conntrack;
struct net *net = nf_ct_net(ct);
+ struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
+
+ BUG_ON(ecache == NULL);
if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) {
/* bad luck, let's retry again */
- ct->timeout.expires = jiffies +
+ ecache->timeout.expires = jiffies +
(random32() % net->ct.sysctl_events_retry_timeout);
- add_timer(&ct->timeout);
+ add_timer(&ecache->timeout);
return;
}
/* we've got the event delivered, now it's dying */
@@ -268,6 +271,9 @@ static void death_by_event(unsigned long ul_conntrack)
void nf_ct_insert_dying_list(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
+ struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
+
+ BUG_ON(ecache == NULL);
/* add this conntrack to the dying list */
spin_lock_bh(&nf_conntrack_lock);
@@ -275,10 +281,10 @@ void nf_ct_insert_dying_list(struct nf_conn *ct)
&net->ct.dying);
spin_unlock_bh(&nf_conntrack_lock);
/* set a new timer to retry event delivery */
- setup_timer(&ct->timeout, death_by_event, (unsigned long)ct);
- ct->timeout.expires = jiffies +
+ setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct);
+ ecache->timeout.expires = jiffies +
(random32() % net->ct.sysctl_events_retry_timeout);
- add_timer(&ct->timeout);
+ add_timer(&ecache->timeout);
}
EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 45cf602a76bc..527651a53a45 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -361,23 +361,6 @@ static void evict_oldest_expect(struct nf_conn *master,
}
}
-static inline int refresh_timer(struct nf_conntrack_expect *i)
-{
- struct nf_conn_help *master_help = nfct_help(i->master);
- const struct nf_conntrack_expect_policy *p;
-
- if (!del_timer(&i->timeout))
- return 0;
-
- p = &rcu_dereference_protected(
- master_help->helper,
- lockdep_is_held(&nf_conntrack_lock)
- )->expect_policy[i->class];
- i->timeout.expires = jiffies + p->timeout * HZ;
- add_timer(&i->timeout);
- return 1;
-}
-
static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
{
const struct nf_conntrack_expect_policy *p;
@@ -386,7 +369,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
struct nf_conn_help *master_help = nfct_help(master);
struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(expect);
- struct hlist_node *n;
+ struct hlist_node *n, *next;
unsigned int h;
int ret = 1;
@@ -395,12 +378,12 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
goto out;
}
h = nf_ct_expect_dst_hash(&expect->tuple);
- hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry_safe(i, n, next, &net->ct.expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
- /* Refresh timer: if it's dying, ignore.. */
- if (refresh_timer(i)) {
- ret = 0;
- goto out;
+ if (del_timer(&i->timeout)) {
+ nf_ct_unlink_expect(i);
+ nf_ct_expect_put(i);
+ break;
}
} else if (expect_clash(i, expect)) {
ret = -EBUSY;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 14f67a2cbcb5..9807f3278fcb 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1896,10 +1896,15 @@ static int
ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct)
{
struct nlattr *cda[CTA_MAX+1];
+ int ret;
nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy);
- return ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct);
+ spin_lock_bh(&nf_conntrack_lock);
+ ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct);
+ spin_unlock_bh(&nf_conntrack_lock);
+
+ return ret;
}
static struct nfq_ct_hook ctnetlink_nfqueue_hook = {
@@ -2785,7 +2790,8 @@ static int __init ctnetlink_init(void)
goto err_unreg_subsys;
}
- if (register_pernet_subsys(&ctnetlink_net_ops)) {
+ ret = register_pernet_subsys(&ctnetlink_net_ops);
+ if (ret < 0) {
pr_err("ctnetlink_init: cannot register pernet operations\n");
goto err_unreg_exp_subsys;
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 758a1bacc126..5c0a112aeee6 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -183,12 +183,12 @@ static int media_len(const struct nf_conn *ct, const char *dptr,
return len + digits_len(ct, dptr, limit, shift);
}
-static int parse_addr(const struct nf_conn *ct, const char *cp,
- const char **endp, union nf_inet_addr *addr,
- const char *limit)
+static int sip_parse_addr(const struct nf_conn *ct, const char *cp,
+ const char **endp, union nf_inet_addr *addr,
+ const char *limit, bool delim)
{
const char *end;
- int ret = 0;
+ int ret;
if (!ct)
return 0;
@@ -197,16 +197,28 @@ static int parse_addr(const struct nf_conn *ct, const char *cp,
switch (nf_ct_l3num(ct)) {
case AF_INET:
ret = in4_pton(cp, limit - cp, (u8 *)&addr->ip, -1, &end);
+ if (ret == 0)
+ return 0;
break;
case AF_INET6:
+ if (cp < limit && *cp == '[')
+ cp++;
+ else if (delim)
+ return 0;
+
ret = in6_pton(cp, limit - cp, (u8 *)&addr->ip6, -1, &end);
+ if (ret == 0)
+ return 0;
+
+ if (end < limit && *end == ']')
+ end++;
+ else if (delim)
+ return 0;
break;
default:
BUG();
}
- if (ret == 0 || end == cp)
- return 0;
if (endp)
*endp = end;
return 1;
@@ -219,7 +231,7 @@ static int epaddr_len(const struct nf_conn *ct, const char *dptr,
union nf_inet_addr addr;
const char *aux = dptr;
- if (!parse_addr(ct, dptr, &dptr, &addr, limit)) {
+ if (!sip_parse_addr(ct, dptr, &dptr, &addr, limit, true)) {
pr_debug("ip: %s parse failed.!\n", dptr);
return 0;
}
@@ -296,7 +308,7 @@ int ct_sip_parse_request(const struct nf_conn *ct,
return 0;
dptr += shift;
- if (!parse_addr(ct, dptr, &end, addr, limit))
+ if (!sip_parse_addr(ct, dptr, &end, addr, limit, true))
return -1;
if (end < limit && *end == ':') {
end++;
@@ -550,7 +562,7 @@ int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr,
if (ret == 0)
return ret;
- if (!parse_addr(ct, dptr + *matchoff, &c, addr, limit))
+ if (!sip_parse_addr(ct, dptr + *matchoff, &c, addr, limit, true))
return -1;
if (*c == ':') {
c++;
@@ -599,7 +611,7 @@ int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr,
unsigned int dataoff, unsigned int datalen,
const char *name,
unsigned int *matchoff, unsigned int *matchlen,
- union nf_inet_addr *addr)
+ union nf_inet_addr *addr, bool delim)
{
const char *limit = dptr + datalen;
const char *start, *end;
@@ -613,7 +625,7 @@ int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr,
return 0;
start += strlen(name);
- if (!parse_addr(ct, start, &end, addr, limit))
+ if (!sip_parse_addr(ct, start, &end, addr, limit, delim))
return 0;
*matchoff = start - dptr;
*matchlen = end - start;
@@ -675,6 +687,47 @@ static int ct_sip_parse_transport(struct nf_conn *ct, const char *dptr,
return 1;
}
+static int sdp_parse_addr(const struct nf_conn *ct, const char *cp,
+ const char **endp, union nf_inet_addr *addr,
+ const char *limit)
+{
+ const char *end;
+ int ret;
+
+ memset(addr, 0, sizeof(*addr));
+ switch (nf_ct_l3num(ct)) {
+ case AF_INET:
+ ret = in4_pton(cp, limit - cp, (u8 *)&addr->ip, -1, &end);
+ break;
+ case AF_INET6:
+ ret = in6_pton(cp, limit - cp, (u8 *)&addr->ip6, -1, &end);
+ break;
+ default:
+ BUG();
+ }
+
+ if (ret == 0)
+ return 0;
+ if (endp)
+ *endp = end;
+ return 1;
+}
+
+/* skip ip address. returns its length. */
+static int sdp_addr_len(const struct nf_conn *ct, const char *dptr,
+ const char *limit, int *shift)
+{
+ union nf_inet_addr addr;
+ const char *aux = dptr;
+
+ if (!sdp_parse_addr(ct, dptr, &dptr, &addr, limit)) {
+ pr_debug("ip: %s parse failed.!\n", dptr);
+ return 0;
+ }
+
+ return dptr - aux;
+}
+
/* SDP header parsing: a SDP session description contains an ordered set of
* headers, starting with a section containing general session parameters,
* optionally followed by multiple media descriptions.
@@ -686,10 +739,10 @@ static int ct_sip_parse_transport(struct nf_conn *ct, const char *dptr,
*/
static const struct sip_header ct_sdp_hdrs[] = {
[SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len),
- [SDP_HDR_OWNER_IP4] = SDP_HDR("o=", "IN IP4 ", epaddr_len),
- [SDP_HDR_CONNECTION_IP4] = SDP_HDR("c=", "IN IP4 ", epaddr_len),
- [SDP_HDR_OWNER_IP6] = SDP_HDR("o=", "IN IP6 ", epaddr_len),
- [SDP_HDR_CONNECTION_IP6] = SDP_HDR("c=", "IN IP6 ", epaddr_len),
+ [SDP_HDR_OWNER_IP4] = SDP_HDR("o=", "IN IP4 ", sdp_addr_len),
+ [SDP_HDR_CONNECTION_IP4] = SDP_HDR("c=", "IN IP4 ", sdp_addr_len),
+ [SDP_HDR_OWNER_IP6] = SDP_HDR("o=", "IN IP6 ", sdp_addr_len),
+ [SDP_HDR_CONNECTION_IP6] = SDP_HDR("c=", "IN IP6 ", sdp_addr_len),
[SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len),
};
@@ -775,8 +828,8 @@ static int ct_sip_parse_sdp_addr(const struct nf_conn *ct, const char *dptr,
if (ret <= 0)
return ret;
- if (!parse_addr(ct, dptr + *matchoff, NULL, addr,
- dptr + *matchoff + *matchlen))
+ if (!sdp_parse_addr(ct, dptr + *matchoff, NULL, addr,
+ dptr + *matchoff + *matchlen))
return -1;
return 1;
}
@@ -1515,7 +1568,6 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff,
}
static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly;
-static char sip_names[MAX_PORTS][4][sizeof("sip-65535")] __read_mostly;
static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1] = {
[SIP_EXPECT_SIGNALLING] = {
@@ -1585,9 +1637,9 @@ static int __init nf_conntrack_sip_init(void)
sip[i][j].me = THIS_MODULE;
if (ports[i] == SIP_PORT)
- sprintf(sip_names[i][j], "sip");
+ sprintf(sip[i][j].name, "sip");
else
- sprintf(sip_names[i][j], "sip-%u", i);
+ sprintf(sip[i][j].name, "sip-%u", i);
pr_debug("port #%u: %u\n", i, ports[i]);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 169ab59ed9d4..14e2f3903142 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -480,7 +480,7 @@ __build_packet_message(struct nfulnl_instance *inst,
}
if (indev && skb_mac_header_was_set(skb)) {
- if (nla_put_be32(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) ||
+ if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) ||
nla_put_be16(inst->skb, NFULA_HWLEN,
htons(skb->dev->hard_header_len)) ||
nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len,
@@ -996,8 +996,10 @@ static int __init nfnetlink_log_init(void)
#ifdef CONFIG_PROC_FS
if (!proc_create("nfnetlink_log", 0440,
- proc_net_netfilter, &nful_file_ops))
+ proc_net_netfilter, &nful_file_ops)) {
+ status = -ENOMEM;
goto cleanup_logger;
+ }
#endif
return status;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5463969da45b..527023823b5c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1362,7 +1362,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
if (NULL == siocb->scm)
siocb->scm = &scm;
- err = scm_send(sock, msg, siocb->scm);
+ err = scm_send(sock, msg, siocb->scm, true);
if (err < 0)
return err;
@@ -1373,7 +1373,8 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
dst_pid = addr->nl_pid;
dst_group = ffs(addr->nl_groups);
err = -EPERM;
- if (dst_group && !netlink_capable(sock, NL_NONROOT_SEND))
+ if ((dst_group || dst_pid) &&
+ !netlink_capable(sock, NL_NONROOT_SEND))
goto out;
} else {
dst_pid = nlk->dst_pid;
@@ -2147,6 +2148,7 @@ static void __init netlink_add_usersock_entry(void)
rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners);
nl_table[NETLINK_USERSOCK].module = THIS_MODULE;
nl_table[NETLINK_USERSOCK].registered = 1;
+ nl_table[NETLINK_USERSOCK].nl_nonroot = NL_NONROOT_SEND;
netlink_table_ungrab();
}
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 06592d8b4a2b..1b9024ee963c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1169,7 +1169,12 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
msg->msg_flags |= MSG_TRUNC;
}
- skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ er = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (er < 0) {
+ skb_free_datagram(sk, skb);
+ release_sock(sk);
+ return er;
+ }
if (sax != NULL) {
sax->sax25_family = AF_NETROM;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index f3f96badf5aa..954405ceae9e 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -45,7 +45,7 @@ static int make_writable(struct sk_buff *skb, int write_len)
return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
}
-/* remove VLAN header from packet and update csum accrodingly. */
+/* remove VLAN header from packet and update csum accordingly. */
static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
{
struct vlan_hdr *vhdr;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d8277d29e710..cf58cedad083 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -425,10 +425,10 @@ static int validate_sample(const struct nlattr *attr,
static int validate_tp_port(const struct sw_flow_key *flow_key)
{
if (flow_key->eth.type == htons(ETH_P_IP)) {
- if (flow_key->ipv4.tp.src && flow_key->ipv4.tp.dst)
+ if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
return 0;
} else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
- if (flow_key->ipv6.tp.src && flow_key->ipv6.tp.dst)
+ if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
return 0;
}
@@ -460,7 +460,7 @@ static int validate_set(const struct nlattr *a,
if (flow_key->eth.type != htons(ETH_P_IP))
return -EINVAL;
- if (!flow_key->ipv4.addr.src || !flow_key->ipv4.addr.dst)
+ if (!flow_key->ip.proto)
return -EINVAL;
ipv4_key = nla_data(ovs_key);
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 9b75617ca4e0..c30df1a10c67 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -145,15 +145,17 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies);
* OVS_KEY_ATTR_PRIORITY 4 -- 4 8
* OVS_KEY_ATTR_IN_PORT 4 -- 4 8
* OVS_KEY_ATTR_ETHERNET 12 -- 4 16
+ * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8 (outer VLAN ethertype)
* OVS_KEY_ATTR_8021Q 4 -- 4 8
- * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8
+ * OVS_KEY_ATTR_ENCAP 0 -- 4 4 (VLAN encapsulation)
+ * OVS_KEY_ATTR_ETHERTYPE 2 2 4 8 (inner VLAN ethertype)
* OVS_KEY_ATTR_IPV6 40 -- 4 44
* OVS_KEY_ATTR_ICMPV6 2 2 4 8
* OVS_KEY_ATTR_ND 28 -- 4 32
* -------------------------------------------------
- * total 132
+ * total 144
*/
-#define FLOW_BUFSIZE 132
+#define FLOW_BUFSIZE 144
int ovs_flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *);
int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ceaca7c134a0..c5c9e2a54218 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1079,7 +1079,7 @@ static void *packet_current_rx_frame(struct packet_sock *po,
default:
WARN(1, "TPACKET version not supported\n");
BUG();
- return 0;
+ return NULL;
}
}
@@ -1273,6 +1273,14 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
spin_unlock(&f->lock);
}
+static bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
+{
+ if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout)
+ return true;
+
+ return false;
+}
+
static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
{
struct packet_sock *po = pkt_sk(sk);
@@ -1325,6 +1333,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
match->prot_hook.dev = po->prot_hook.dev;
match->prot_hook.func = packet_rcv_fanout;
match->prot_hook.af_packet_priv = match;
+ match->prot_hook.id_match = match_fanout_group;
dev_add_pack(&match->prot_hook);
list_add(&match->list, &fanout_list);
}
@@ -1936,7 +1945,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
if (likely(po->tx_ring.pg_vec)) {
ph = skb_shinfo(skb)->destructor_arg;
- BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING);
BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
atomic_dec(&po->tx_ring.pending);
__packet_set_status(po, ph, TP_STATUS_AVAILABLE);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index f10fb8256442..05d60859d8e3 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -67,6 +67,9 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est,
struct tcf_common *pc;
int ret = 0;
int err;
+#ifdef CONFIG_GACT_PROB
+ struct tc_gact_p *p_parm = NULL;
+#endif
if (nla == NULL)
return -EINVAL;
@@ -82,6 +85,12 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est,
#ifndef CONFIG_GACT_PROB
if (tb[TCA_GACT_PROB] != NULL)
return -EOPNOTSUPP;
+#else
+ if (tb[TCA_GACT_PROB]) {
+ p_parm = nla_data(tb[TCA_GACT_PROB]);
+ if (p_parm->ptype >= MAX_RAND)
+ return -EINVAL;
+ }
#endif
pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info);
@@ -103,8 +112,7 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est,
spin_lock_bh(&gact->tcf_lock);
gact->tcf_action = parm->action;
#ifdef CONFIG_GACT_PROB
- if (tb[TCA_GACT_PROB] != NULL) {
- struct tc_gact_p *p_parm = nla_data(tb[TCA_GACT_PROB]);
+ if (p_parm) {
gact->tcfg_paction = p_parm->paction;
gact->tcfg_pval = p_parm->pval;
gact->tcfg_ptype = p_parm->ptype;
@@ -133,7 +141,7 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a,
spin_lock(&gact->tcf_lock);
#ifdef CONFIG_GACT_PROB
- if (gact->tcfg_ptype && gact_rand[gact->tcfg_ptype] != NULL)
+ if (gact->tcfg_ptype)
action = gact_rand[gact->tcfg_ptype](gact);
else
action = gact->tcf_action;
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 60e281ad0f07..58fb3c7aab9e 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -185,7 +185,12 @@ err3:
err2:
kfree(tname);
err1:
- kfree(pc);
+ if (ret == ACT_P_CREATED) {
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
+ }
return err;
}
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index fe81cc18e9e0..9c0fd0c78814 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -200,13 +200,12 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
out:
if (err) {
m->tcf_qstats.overlimits++;
- /* should we be asking for packet to be dropped?
- * may make sense for redirect case only
- */
- retval = TC_ACT_SHOT;
- } else {
+ if (m->tcfm_eaction != TCA_EGRESS_MIRROR)
+ retval = TC_ACT_SHOT;
+ else
+ retval = m->tcf_action;
+ } else
retval = m->tcf_action;
- }
spin_unlock(&m->tcf_lock);
return retval;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 26aa2f6ce257..45c53ab067a6 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -74,7 +74,10 @@ static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est,
p = to_pedit(pc);
keys = kmalloc(ksize, GFP_KERNEL);
if (keys == NULL) {
- kfree(pc);
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
return -ENOMEM;
}
ret = ACT_P_CREATED;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 3922f2a2821b..3714f60f0b3c 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -131,7 +131,10 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est,
d = to_defact(pc);
ret = alloc_defdata(d, defdata);
if (ret < 0) {
- kfree(pc);
+ if (est)
+ gen_kill_estimator(&pc->tcfc_bstats,
+ &pc->tcfc_rate_est);
+ kfree_rcu(pc, tcfc_rcu);
return ret;
}
d->tcf_action = parm->action;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9fc1c62ec80e..4e606fcb2534 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -191,7 +191,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (list_empty(&flow->flowchain)) {
list_add_tail(&flow->flowchain, &q->new_flows);
- codel_vars_init(&flow->cvars);
q->new_flow_count++;
flow->deficit = q->quantum;
flow->dropped = 0;
@@ -418,6 +417,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
struct fq_codel_flow *flow = q->flows + i;
INIT_LIST_HEAD(&flow->flowchain);
+ codel_vars_init(&flow->cvars);
}
}
if (sch->limit >= 1)
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 9af01f3df18c..e4723d31fdd5 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -203,6 +203,34 @@ out:
return index;
}
+/* Length of the next packet (0 if the queue is empty). */
+static unsigned int qdisc_peek_len(struct Qdisc *sch)
+{
+ struct sk_buff *skb;
+
+ skb = sch->ops->peek(sch);
+ return skb ? qdisc_pkt_len(skb) : 0;
+}
+
+static void qfq_deactivate_class(struct qfq_sched *, struct qfq_class *);
+static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl,
+ unsigned int len);
+
+static void qfq_update_class_params(struct qfq_sched *q, struct qfq_class *cl,
+ u32 lmax, u32 inv_w, int delta_w)
+{
+ int i;
+
+ /* update qfq-specific data */
+ cl->lmax = lmax;
+ cl->inv_w = inv_w;
+ i = qfq_calc_index(cl->inv_w, cl->lmax);
+
+ cl->grp = &q->groups[i];
+
+ q->wsum += delta_w;
+}
+
static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
struct nlattr **tca, unsigned long *arg)
{
@@ -250,6 +278,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
lmax = 1UL << QFQ_MTU_SHIFT;
if (cl != NULL) {
+ bool need_reactivation = false;
+
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
@@ -258,12 +288,29 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
return err;
}
- if (inv_w != cl->inv_w) {
- sch_tree_lock(sch);
- q->wsum += delta_w;
- cl->inv_w = inv_w;
- sch_tree_unlock(sch);
+ if (lmax == cl->lmax && inv_w == cl->inv_w)
+ return 0; /* nothing to update */
+
+ i = qfq_calc_index(inv_w, lmax);
+ sch_tree_lock(sch);
+ if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) {
+ /*
+ * shift cl->F back, to not charge the
+ * class for the not-yet-served head
+ * packet
+ */
+ cl->F = cl->S;
+ /* remove class from its slot in the old group */
+ qfq_deactivate_class(q, cl);
+ need_reactivation = true;
}
+
+ qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
+
+ if (need_reactivation) /* activate in new group */
+ qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc));
+ sch_tree_unlock(sch);
+
return 0;
}
@@ -273,11 +320,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->refcnt = 1;
cl->common.classid = classid;
- cl->lmax = lmax;
- cl->inv_w = inv_w;
- i = qfq_calc_index(cl->inv_w, cl->lmax);
- cl->grp = &q->groups[i];
+ qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
cl->qdisc = qdisc_create_dflt(sch->dev_queue,
&pfifo_qdisc_ops, classid);
@@ -294,7 +338,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
return err;
}
}
- q->wsum += weight;
sch_tree_lock(sch);
qdisc_class_hash_insert(&q->clhash, &cl->common);
@@ -711,15 +754,6 @@ static void qfq_update_eligible(struct qfq_sched *q, u64 old_V)
}
}
-/* What is length of next packet in queue (0 if queue is empty) */
-static unsigned int qdisc_peek_len(struct Qdisc *sch)
-{
- struct sk_buff *skb;
-
- skb = sch->ops->peek(sch);
- return skb ? qdisc_pkt_len(skb) : 0;
-}
-
/*
* Updates the class, returns true if also the group needs to be updated.
*/
@@ -843,11 +877,8 @@ static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl)
static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
{
struct qfq_sched *q = qdisc_priv(sch);
- struct qfq_group *grp;
struct qfq_class *cl;
int err;
- u64 roundedS;
- int s;
cl = qfq_classify(skb, sch, &err);
if (cl == NULL) {
@@ -876,11 +907,25 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return err;
/* If reach this point, queue q was idle */
- grp = cl->grp;
+ qfq_activate_class(q, cl, qdisc_pkt_len(skb));
+
+ return err;
+}
+
+/*
+ * Handle class switch from idle to backlogged.
+ */
+static void qfq_activate_class(struct qfq_sched *q, struct qfq_class *cl,
+ unsigned int pkt_len)
+{
+ struct qfq_group *grp = cl->grp;
+ u64 roundedS;
+ int s;
+
qfq_update_start(q, cl);
/* compute new finish time and rounded start. */
- cl->F = cl->S + (u64)qdisc_pkt_len(skb) * cl->inv_w;
+ cl->F = cl->S + (u64)pkt_len * cl->inv_w;
roundedS = qfq_round_down(cl->S, grp->slot_shift);
/*
@@ -917,8 +962,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
skip_update:
qfq_slot_insert(grp, cl, roundedS);
-
- return err;
}
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 838e18b4d7ea..be50aa234dcd 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -364,6 +364,25 @@ finish:
return retval;
}
+static void sctp_packet_release_owner(struct sk_buff *skb)
+{
+ sk_free(skb->sk);
+}
+
+static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk)
+{
+ skb_orphan(skb);
+ skb->sk = sk;
+ skb->destructor = sctp_packet_release_owner;
+
+ /*
+ * The data chunks have already been accounted for in sctp_sendmsg(),
+ * therefore only reserve a single byte to keep socket around until
+ * the packet has been transmitted.
+ */
+ atomic_inc(&sk->sk_wmem_alloc);
+}
+
/* All packets are sent to the network through this function from
* sctp_outq_tail().
*
@@ -405,7 +424,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
/* Set the owning socket so that we know where to get the
* destination IP address.
*/
- skb_set_owner_w(nskb, sk);
+ sctp_packet_set_owner_w(nskb, sk);
if (!sctp_transport_dst_check(tp)) {
sctp_transport_route(tp, NULL, sctp_sk(sk));
diff --git a/net/socket.c b/net/socket.c
index dfe5b66c97e0..a5471f804d99 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2657,6 +2657,7 @@ static int dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32)
if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf)))
return -EFAULT;
+ memset(&ifc, 0, sizeof(ifc));
if (ifc32.ifcbuf == 0) {
ifc32.ifc_len = 0;
ifc.ifc_len = 0;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 88f2bf671960..bac973a31367 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -316,7 +316,6 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
*/
void svc_xprt_enqueue(struct svc_xprt *xprt)
{
- struct svc_serv *serv = xprt->xpt_server;
struct svc_pool *pool;
struct svc_rqst *rqstp;
int cpu;
@@ -362,8 +361,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
rqstp, rqstp->rq_xprt);
rqstp->rq_xprt = xprt;
svc_xprt_get(xprt);
- rqstp->rq_reserved = serv->sv_max_mesg;
- atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
pool->sp_stats.threads_woken++;
wake_up(&rqstp->rq_wait);
} else {
@@ -640,8 +637,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
if (xprt) {
rqstp->rq_xprt = xprt;
svc_xprt_get(xprt);
- rqstp->rq_reserved = serv->sv_max_mesg;
- atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
/* As there is a shortage of threads and this request
* had to be queued, don't allow the thread to wait so
@@ -738,6 +733,8 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
else
len = xprt->xpt_ops->xpo_recvfrom(rqstp);
dprintk("svc: got len=%d\n", len);
+ rqstp->rq_reserved = serv->sv_max_mesg;
+ atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
}
svc_xprt_received(xprt);
@@ -794,7 +791,8 @@ int svc_send(struct svc_rqst *rqstp)
/* Grab mutex to serialize outgoing data. */
mutex_lock(&xprt->xpt_mutex);
- if (test_bit(XPT_DEAD, &xprt->xpt_flags))
+ if (test_bit(XPT_DEAD, &xprt->xpt_flags)
+ || test_bit(XPT_CLOSE, &xprt->xpt_flags))
len = -ENOTCONN;
else
len = xprt->xpt_ops->xpo_sendto(rqstp);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 18bc130255a7..998aa8c1807c 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1129,9 +1129,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
if (len >= 0)
svsk->sk_tcplen += len;
if (len != want) {
+ svc_tcp_save_pages(svsk, rqstp);
if (len < 0 && len != -EAGAIN)
goto err_other;
- svc_tcp_save_pages(svsk, rqstp);
dprintk("svc: incomplete TCP record (%d of %d)\n",
svsk->sk_tcplen, svsk->sk_reclen);
goto err_noclose;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e4768c180da2..c5ee4ff61364 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1450,7 +1450,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
if (NULL == siocb->scm)
siocb->scm = &tmp_scm;
wait_for_unix_gc();
- err = scm_send(sock, msg, siocb->scm);
+ err = scm_send(sock, msg, siocb->scm, false);
if (err < 0)
return err;
@@ -1619,7 +1619,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
if (NULL == siocb->scm)
siocb->scm = &tmp_scm;
wait_for_unix_gc();
- err = scm_send(sock, msg, siocb->scm);
+ err = scm_send(sock, msg, siocb->scm, false);
if (err < 0)
return err;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 54a0dc2e2f8d..ab2bb42fe094 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -212,7 +212,7 @@ resume:
/* only the first xfrm gets the encap type */
encap_type = 0;
- if (async && x->repl->check(x, skb, seq)) {
+ if (async && x->repl->recheck(x, skb, seq)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
goto drop_unlock;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c5a5165a5927..5a2aa17e4d3c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1357,6 +1357,8 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst));
xdst->flo.ops = &xfrm_bundle_fc_ops;
+ if (afinfo->init_dst)
+ afinfo->init_dst(net, xdst);
} else
xdst = ERR_PTR(-ENOBUFS);
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 2f6d11d04a2b..3efb07d3eb27 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -420,6 +420,18 @@ err:
return -EINVAL;
}
+static int xfrm_replay_recheck_esn(struct xfrm_state *x,
+ struct sk_buff *skb, __be32 net_seq)
+{
+ if (unlikely(XFRM_SKB_CB(skb)->seq.input.hi !=
+ htonl(xfrm_replay_seqhi(x, net_seq)))) {
+ x->stats.replay_window++;
+ return -EINVAL;
+ }
+
+ return xfrm_replay_check_esn(x, skb, net_seq);
+}
+
static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
{
unsigned int bitnr, nr, i;
@@ -479,6 +491,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
static struct xfrm_replay xfrm_replay_legacy = {
.advance = xfrm_replay_advance,
.check = xfrm_replay_check,
+ .recheck = xfrm_replay_check,
.notify = xfrm_replay_notify,
.overflow = xfrm_replay_overflow,
};
@@ -486,6 +499,7 @@ static struct xfrm_replay xfrm_replay_legacy = {
static struct xfrm_replay xfrm_replay_bmp = {
.advance = xfrm_replay_advance_bmp,
.check = xfrm_replay_check_bmp,
+ .recheck = xfrm_replay_check_bmp,
.notify = xfrm_replay_notify_bmp,
.overflow = xfrm_replay_overflow_bmp,
};
@@ -493,6 +507,7 @@ static struct xfrm_replay xfrm_replay_bmp = {
static struct xfrm_replay xfrm_replay_esn = {
.advance = xfrm_replay_advance_esn,
.check = xfrm_replay_check_esn,
+ .recheck = xfrm_replay_recheck_esn,
.notify = xfrm_replay_notify_bmp,
.overflow = xfrm_replay_overflow_esn,
};
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 87cd0e4d4282..210be48d8ae3 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1994,8 +1994,10 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
goto error;
x->outer_mode = xfrm_get_mode(x->props.mode, family);
- if (x->outer_mode == NULL)
+ if (x->outer_mode == NULL) {
+ err = -EPROTONOSUPPORT;
goto error;
+ }
if (init_replay) {
err = xfrm_init_replay(x);