summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorBharat Nihalani <bnihalani@nvidia.com>2013-12-19 23:29:52 -0800
committerGerrit Code Review <gerrit2@nvidia.com>2013-12-19 23:29:52 -0800
commit2b2f508eeb26fd48e6c56b8bd59aa7ad1abf5fd3 (patch)
tree07326c802b07a0477a0d48a1be6d0dfc34507a54 /net
parent3321cd648c8ac7af09d52e200ab7816024cfc06d (diff)
parent4186e42658f8f3e95fa4f87f917872e8a3431057 (diff)
Merge "Merge tag 'v3.10.24' into HEAD" into dev-kernel-3.10
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan_netlink.c2
-rw-r--r--net/9p/trans_virtio.c5
-rw-r--r--net/appletalk/ddp.c16
-rw-r--r--net/atm/common.c2
-rw-r--r--net/ax25/af_ax25.c4
-rw-r--r--net/batman-adv/main.c5
-rw-r--r--net/batman-adv/network-coding.c28
-rw-r--r--net/batman-adv/network-coding.h14
-rw-r--r--net/bluetooth/af_bluetooth.c4
-rw-r--r--net/bluetooth/hci_sock.c2
-rw-r--r--net/bluetooth/rfcomm/sock.c1
-rw-r--r--net/bluetooth/sco.c1
-rw-r--r--net/bridge/br_if.c2
-rw-r--r--net/bridge/br_stp_if.c2
-rw-r--r--net/caif/caif_socket.c4
-rw-r--r--net/compat.c5
-rw-r--r--net/core/dev.c2
-rw-r--r--net/core/fib_rules.c3
-rw-r--r--net/core/flow_dissector.c2
-rw-r--r--net/core/iovec.c3
-rw-r--r--net/core/pktgen.c7
-rw-r--r--net/core/secure_seq.c2
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/core/sock.c1
-rw-r--r--net/ieee802154/6lowpan.c4
-rw-r--r--net/ieee802154/dgram.c3
-rw-r--r--net/ipv4/datagram.c2
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_gre.c2
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c3
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ip_vti.c15
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/ping.c19
-rw-r--r--net/ipv4/raw.c6
-rw-r--r--net/ipv4/route.c10
-rw-r--r--net/ipv4/sysctl_net_ipv4.c10
-rw-r--r--net/ipv4/tcp.c39
-rw-r--r--net/ipv4/tcp_input.c41
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_metrics.c5
-rw-r--r--net/ipv4/tcp_output.c33
-rw-r--r--net/ipv4/udp.c17
-rw-r--r--net/ipv6/datagram.c8
-rw-r--r--net/ipv6/inet6_hashtables.c2
-rw-r--r--net/ipv6/ip6_flowlabel.c2
-rw-r--r--net/ipv6/ip6_output.c13
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c54
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c19
-rw-r--r--net/ipv6/netfilter/nf_defrag_ipv6_hooks.c7
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/route.c62
-rw-r--r--net/ipv6/udp.c9
-rw-r--r--net/ipv6/udp_offload.c2
-rw-r--r--net/ipx/af_ipx.c3
-rw-r--r--net/irda/af_irda.c4
-rw-r--r--net/iucv/af_iucv.c2
-rw-r--r--net/key/af_key.c1
-rw-r--r--net/l2tp/l2tp_core.c36
-rw-r--r--net/l2tp/l2tp_core.h3
-rw-r--r--net/l2tp/l2tp_ip.c4
-rw-r--r--net/l2tp/l2tp_ip6.c2
-rw-r--r--net/l2tp/l2tp_ppp.c6
-rw-r--r--net/llc/af_llc.c2
-rw-r--r--net/mac80211/cfg.c2
-rw-r--r--net/mac80211/ieee80211_i.h3
-rw-r--r--net/mac80211/rx.c3
-rw-r--r--net/mac80211/scan.c19
-rw-r--r--net/mac80211/status.c3
-rw-r--r--net/mac80211/tx.c3
-rw-r--r--net/mac80211/util.c4
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c55
-rw-r--r--net/netfilter/ipvs/ip_vs_pe_sip.c8
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c4
-rw-r--r--net/netlink/af_netlink.c2
-rw-r--r--net/netrom/af_netrom.c3
-rw-r--r--net/nfc/llcp_sock.c2
-rw-r--r--net/nfc/rawsock.c2
-rw-r--r--net/packet/af_packet.c95
-rw-r--r--net/packet/internal.h1
-rw-r--r--net/phonet/datagram.c9
-rw-r--r--net/rds/recv.c2
-rw-r--r--net/rose/af_rose.c8
-rw-r--r--net/rxrpc/ar-recvmsg.c9
-rw-r--r--net/sctp/output.c3
-rw-r--r--net/socket.c46
-rw-r--r--net/sunrpc/clnt.c2
-rw-r--r--net/sunrpc/xprtsock.c28
-rw-r--r--net/tipc/socket.c6
-rw-r--r--net/unix/af_unix.c15
-rw-r--r--net/unix/diag.c1
-rw-r--r--net/vmw_vsock/af_vsock.c2
-rw-r--r--net/vmw_vsock/vmci_transport.c2
-rw-r--r--net/wireless/ibss.c3
-rw-r--r--net/wireless/radiotap.c7
-rw-r--r--net/wireless/scan.c4
-rw-r--r--net/x25/af_x25.c3
98 files changed, 531 insertions, 418 deletions
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 309129732285..c7e634af8516 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev)
return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */
nla_total_size(2) + /* IFLA_VLAN_ID */
- sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
+ nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */
vlan_qos_map_size(vlan->nr_ingress_mappings) +
vlan_qos_map_size(vlan->nr_egress_mappings);
}
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index e1c26b101830..990afab2be1b 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -577,6 +577,10 @@ static int p9_virtio_probe(struct virtio_device *vdev)
mutex_lock(&virtio_9p_lock);
list_add_tail(&chan->chan_list, &virtio_chan_list);
mutex_unlock(&virtio_9p_lock);
+
+ /* Let udev rules use the new mount_tag attribute. */
+ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
return 0;
out_free_tag:
@@ -654,6 +658,7 @@ static void p9_virtio_remove(struct virtio_device *vdev)
list_del(&chan->chan_list);
mutex_unlock(&virtio_9p_lock);
sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
kfree(chan->tag);
kfree(chan->vc_wq);
kfree(chan);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index ef12839a7cfe..0018daccdea9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1735,7 +1735,6 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
size_t size, int flags)
{
struct sock *sk = sock->sk;
- struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
struct ddpehdr *ddp;
int copied = 0;
int offset = 0;
@@ -1764,14 +1763,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
}
err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
- if (!err) {
- if (sat) {
- sat->sat_family = AF_APPLETALK;
- sat->sat_port = ddp->deh_sport;
- sat->sat_addr.s_node = ddp->deh_snode;
- sat->sat_addr.s_net = ddp->deh_snet;
- }
- msg->msg_namelen = sizeof(*sat);
+ if (!err && msg->msg_name) {
+ struct sockaddr_at *sat = msg->msg_name;
+ sat->sat_family = AF_APPLETALK;
+ sat->sat_port = ddp->deh_sport;
+ sat->sat_addr.s_node = ddp->deh_snode;
+ sat->sat_addr.s_net = ddp->deh_snet;
+ msg->msg_namelen = sizeof(*sat);
}
skb_free_datagram(sk, skb); /* Free the datagram. */
diff --git a/net/atm/common.c b/net/atm/common.c
index 737bef59ce89..7b491006eaf4 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -531,8 +531,6 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
struct sk_buff *skb;
int copied, error = -EINVAL;
- msg->msg_namelen = 0;
-
if (sock->state != SS_CONNECTED)
return -ENOTCONN;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index e277e38f736b..ba6db78a02b1 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (msg->msg_namelen != 0) {
- struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+ if (msg->msg_name) {
ax25_digi digi;
ax25_address src;
const unsigned char *mac = skb_mac_header(skb);
+ struct sockaddr_ax25 *sax = msg->msg_name;
memset(sax, 0, sizeof(struct full_sockaddr_ax25));
ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 51aafd669cbb..f1cb1f56cda9 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -61,6 +61,7 @@ static int __init batadv_init(void)
batadv_recv_handler_init();
batadv_iv_init();
+ batadv_nc_init();
batadv_event_workqueue = create_singlethread_workqueue("bat_events");
@@ -138,7 +139,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
if (ret < 0)
goto err;
- ret = batadv_nc_init(bat_priv);
+ ret = batadv_nc_mesh_init(bat_priv);
if (ret < 0)
goto err;
@@ -163,7 +164,7 @@ void batadv_mesh_free(struct net_device *soft_iface)
batadv_vis_quit(bat_priv);
batadv_gw_node_purge(bat_priv);
- batadv_nc_free(bat_priv);
+ batadv_nc_mesh_free(bat_priv);
batadv_dat_free(bat_priv);
batadv_bla_free(bat_priv);
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index e84629ece9b7..f97aeee2201c 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -35,6 +35,20 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
/**
+ * batadv_nc_init - one-time initialization for network coding
+ */
+int __init batadv_nc_init(void)
+{
+ int ret;
+
+ /* Register our packet type */
+ ret = batadv_recv_handler_register(BATADV_CODED,
+ batadv_nc_recv_coded_packet);
+
+ return ret;
+}
+
+/**
* batadv_nc_start_timer - initialise the nc periodic worker
* @bat_priv: the bat priv with all the soft interface information
*/
@@ -45,10 +59,10 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv)
}
/**
- * batadv_nc_init - initialise coding hash table and start house keeping
+ * batadv_nc_mesh_init - initialise coding hash table and start house keeping
* @bat_priv: the bat priv with all the soft interface information
*/
-int batadv_nc_init(struct batadv_priv *bat_priv)
+int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
{
bat_priv->nc.timestamp_fwd_flush = jiffies;
bat_priv->nc.timestamp_sniffed_purge = jiffies;
@@ -70,11 +84,6 @@ int batadv_nc_init(struct batadv_priv *bat_priv)
batadv_hash_set_lock_class(bat_priv->nc.coding_hash,
&batadv_nc_decoding_hash_lock_class_key);
- /* Register our packet type */
- if (batadv_recv_handler_register(BATADV_CODED,
- batadv_nc_recv_coded_packet) < 0)
- goto err;
-
INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker);
batadv_nc_start_timer(bat_priv);
@@ -1722,12 +1731,11 @@ free_nc_packet:
}
/**
- * batadv_nc_free - clean up network coding memory
+ * batadv_nc_mesh_free - clean up network coding memory
* @bat_priv: the bat priv with all the soft interface information
*/
-void batadv_nc_free(struct batadv_priv *bat_priv)
+void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
{
- batadv_recv_handler_unregister(BATADV_CODED);
cancel_delayed_work_sync(&bat_priv->nc.work);
batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL);
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 4fa6d0caddbd..bd4295fb960f 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -22,8 +22,9 @@
#ifdef CONFIG_BATMAN_ADV_NC
-int batadv_nc_init(struct batadv_priv *bat_priv);
-void batadv_nc_free(struct batadv_priv *bat_priv);
+int batadv_nc_init(void);
+int batadv_nc_mesh_init(struct batadv_priv *bat_priv);
+void batadv_nc_mesh_free(struct batadv_priv *bat_priv);
void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
struct batadv_orig_node *orig_neigh_node,
@@ -47,12 +48,17 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv);
#else /* ifdef CONFIG_BATMAN_ADV_NC */
-static inline int batadv_nc_init(struct batadv_priv *bat_priv)
+static inline int batadv_nc_init(void)
{
return 0;
}
-static inline void batadv_nc_free(struct batadv_priv *bat_priv)
+static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
+{
+ return 0;
+}
+
+static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
{
return;
}
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index a44c12c2de4a..f7c36826f3f4 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -255,8 +255,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
if (flags & (MSG_OOB))
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb) {
if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -321,8 +319,6 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
BT_DBG("sk %p size %zu", sk, size);
lock_sock(sk);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 9bd7d959e384..fa4bf6631425 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -752,8 +752,6 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
if (!skb)
return err;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 30b3721dc6d7..c1c6028e389a 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -608,7 +608,6 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
rfcomm_dlc_accept(d);
- msg->msg_namelen = 0;
return 0;
}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 91c184f9528e..3178c7b4a171 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -717,7 +717,6 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
sco_conn_defer_accept(pi->conn->hcon, 0);
sk->sk_state = BT_CONFIG;
- msg->msg_namelen = 0;
release_sock(sk);
return 0;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 4cdba60926ff..32bd1e87f149 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -172,6 +172,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head)
del_nbp(p);
}
+ br_fdb_delete_by_port(br, NULL, 1);
+
del_timer_sync(&br->gc_timer);
br_sysfs_delbr(br->dev);
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 108084a04671..656a6f3e40de 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -134,7 +134,7 @@ static void br_stp_start(struct net_bridge *br)
if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY)
__br_set_forward_delay(br, BR_MIN_FORWARD_DELAY);
- else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY)
+ else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
__br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
if (r == 0) {
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 05a41c7ec304..d6be3edb7a43 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -286,8 +286,6 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
if (m->msg_flags&MSG_OOB)
goto read_error;
- m->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags, 0 , &ret);
if (!skb)
goto read_error;
@@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
/*
* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
diff --git a/net/compat.c b/net/compat.c
index f0a1ba6c8086..dd32e34c1e2c 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -71,6 +71,8 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
__get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
__get_user(kmsg->msg_flags, &umsg->msg_flags))
return -EFAULT;
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ kmsg->msg_namelen = sizeof(struct sockaddr_storage);
kmsg->msg_name = compat_ptr(tmp1);
kmsg->msg_iov = compat_ptr(tmp2);
kmsg->msg_control = compat_ptr(tmp3);
@@ -91,7 +93,8 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
if (err < 0)
return err;
}
- kern_msg->msg_name = kern_address;
+ if (kern_msg->msg_name)
+ kern_msg->msg_name = kern_address;
} else
kern_msg->msg_name = NULL;
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ddbb31b10d3..1283c8442e99 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4478,7 +4478,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
- if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ if (ops->ndo_change_rx_flags)
ops->ndo_change_rx_flags(dev, flags);
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d5a9f8ead0d8..0e9131195eb0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -445,7 +445,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
if (frh->action && (frh->action != rule->action))
continue;
- if (frh->table && (frh_get_table(frh, tb) != rule->table))
+ if (frh_get_table(frh, tb) &&
+ (frh_get_table(frh, tb) != rule->table))
continue;
if (tb[FRA_PRIORITY] &&
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 44db78ae6a65..f97101b4d373 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -40,7 +40,7 @@ again:
struct iphdr _iph;
ip:
iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
+ if (!iph || iph->ihl < 5)
return false;
if (ip_is_fragment(iph))
diff --git a/net/core/iovec.c b/net/core/iovec.c
index de178e462682..9a31515fb8e3 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
if (err < 0)
return err;
}
- m->msg_name = address;
+ if (m->msg_name)
+ m->msg_name = address;
} else {
m->msg_name = NULL;
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 11f2704c3810..ebbea5371967 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2515,6 +2515,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
if (x) {
int ret;
__u8 *eth;
+ struct iphdr *iph;
+
nhead = x->props.header_len - skb_headroom(skb);
if (nhead > 0) {
ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);
@@ -2536,6 +2538,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev,
eth = (__u8 *) skb_push(skb, ETH_HLEN);
memcpy(eth, pkt_dev->hh, 12);
*(u16 *) &eth[12] = protocol;
+
+ /* Update IPv4 header len as well as checksum value */
+ iph = ip_hdr(skb);
+ iph->tot_len = htons(skb->len - ETH_HLEN);
+ ip_send_check(iph);
}
}
return 1;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 3f1ec1586ae1..8d9d05edd2eb 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -10,6 +10,7 @@
#include <net/secure_seq.h>
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
@@ -29,6 +30,7 @@ static void net_secret_init(void)
cmpxchg(&net_secret[--i], 0, tmp);
}
}
+#endif
#ifdef CONFIG_INET
static u32 seq_scale(u32 seq)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1c1738cc4538..d9e8736bcdc1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -585,9 +585,6 @@ static void skb_release_head_state(struct sk_buff *skb)
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb->nfct);
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(skb->nf_bridge);
#endif
diff --git a/net/core/sock.c b/net/core/sock.c
index 4ff2028245f2..818fca56b1b0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2275,6 +2275,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_stamp = ktime_set(-1L, 0);
+ sk->sk_pacing_rate = ~0U;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 55e1fd5b3e56..31b127e8086b 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -862,7 +862,7 @@ lowpan_process_data(struct sk_buff *skb)
* Traffic class carried in-line
* ECN + DSCP (1 byte), Flow Label is elided
*/
- case 1: /* 10b */
+ case 2: /* 10b */
if (lowpan_fetch_skb_u8(skb, &tmp))
goto drop;
@@ -875,7 +875,7 @@ lowpan_process_data(struct sk_buff *skb)
* Flow Label carried in-line
* ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided
*/
- case 2: /* 01b */
+ case 1: /* 01b */
if (lowpan_fetch_skb_u8(skb, &tmp))
goto drop;
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 581a59504bd5..1865fdf5a5a5 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -315,9 +315,8 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
if (saddr) {
saddr->family = AF_IEEE802154;
saddr->addr = mac_cb(skb)->sa;
- }
- if (addr_len)
*addr_len = sizeof(*saddr);
+ }
if (flags & MSG_TRUNC)
copied = skb->len;
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index b28e863fe0a7..19e36376d2a0 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
goto out;
}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 6af375afeeef..c95848d00039 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -287,7 +287,7 @@ begintw:
if (unlikely(!INET_TW_MATCH(sk, net, acookie,
saddr, daddr, ports,
dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c52fee0976da..64e4e98c8786 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -335,7 +335,7 @@ static int ipgre_rcv(struct sk_buff *skb)
iph->saddr, iph->daddr, tpi.key);
if (tunnel) {
- ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+ ip_tunnel_rcv(tunnel, skb, &tpi, hdr_len, log_ecn_error);
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ec2d430a6a55..6ca5873d6175 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -844,7 +844,7 @@ static int __ip_append_data(struct sock *sk,
csummode = CHECKSUM_PARTIAL;
cork->length += length;
- if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+ if (((length > mtu) || (skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f113d709..23e6ab0a2dc0 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -368,7 +368,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
/*
* Handle MSG_ERRQUEUE
*/
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb, *skb2;
@@ -405,6 +405,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 92d2f0f5d7bf..46dcf32c012e 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -402,7 +402,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
}
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
- const struct tnl_ptk_info *tpi, bool log_ecn_error)
+ const struct tnl_ptk_info *tpi, int hdr_len, bool log_ecn_error)
{
struct pcpu_tstats *tstats;
const struct iphdr *iph = ip_hdr(skb);
@@ -413,7 +413,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
skb->protocol = tpi->proto;
skb->mac_header = skb->network_header;
- __pskb_pull(skb, tunnel->hlen);
+ __pskb_pull(skb, hdr_len);
skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 17cc0ffa8c0d..feb19db62359 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -285,8 +285,17 @@ static int vti_rcv(struct sk_buff *skb)
tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ u32 oldmark = skb->mark;
+ int ret;
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+
+ /* temporarily mark the skb with the tunnel o_key, to
+ * only match policies with this mark.
+ */
+ skb->mark = be32_to_cpu(tunnel->parms.o_key);
+ ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
+ skb->mark = oldmark;
+ if (!ret)
return -1;
tstats = this_cpu_ptr(tunnel->dev->tstats);
@@ -295,7 +304,6 @@ static int vti_rcv(struct sk_buff *skb)
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- skb->mark = 0;
secpath_reset(skb);
skb->dev = tunnel->dev;
return 1;
@@ -327,7 +335,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
+ be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
dst, tiph->saddr, 0, 0);
@@ -342,6 +350,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (!rt->dst.xfrm ||
rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
dev->stats.tx_carrier_errors++;
+ ip_rt_put(rt);
goto tx_error_icmp;
}
tdev = rt->dst.dev;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 7cfc45624b6d..f5cc7b331511 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -195,7 +195,7 @@ static int ipip_rcv(struct sk_buff *skb)
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
- return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+ return ip_tunnel_rcv(tunnel, skb, &tpi, 0, log_ecn_error);
}
return -1;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 3d6cf7f5d54d..0b26c09e5af7 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -775,7 +775,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -853,7 +853,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_ERRQUEUE) {
if (family == AF_INET) {
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
#if IS_ENABLED(CONFIG_IPV6)
} else if (family == AF_INET6) {
return pingv6_ops.ipv6_recv_error(sk, msg, len);
@@ -881,10 +881,17 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
/* Copy the address and add cmsg data. */
if (family == AF_INET) {
sin = (struct sockaddr_in *) msg->msg_name;
- sin->sin_family = AF_INET;
- sin->sin_port = 0 /* skb->h.uh->source */;
- sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
- memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+
+ /* Copy the address. */
+ if (msg->msg_name) {
+ struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+
+ sin->sin_family = AF_INET;
+ sin->sin_port = 0 /* skb->h.uh->source */;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
+ memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
+ }
if (isk->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6fb233772f79..402870fdfa0e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -692,11 +692,8 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE) {
- err = ip_recv_error(sk, msg, len);
+ err = ip_recv_error(sk, msg, len, addr_len);
goto out;
}
@@ -722,6 +719,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d35bbf0cf404..f6c6ab14da41 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1720,8 +1720,12 @@ local_input:
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- if (do_cache)
- rt_cache_route(&FIB_RES_NH(res), rth);
+ if (do_cache) {
+ if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+ rth->dst.flags |= DST_NOCACHE;
+ rt_add_uncached_list(rth);
+ }
+ }
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
@@ -2020,7 +2024,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
RT_SCOPE_LINK);
goto make_route;
}
- if (fl4->saddr) {
+ if (!fl4->saddr) {
if (ipv4_is_multicast(fl4->daddr))
fl4->saddr = inet_select_addr(dev_out, 0,
fl4->flowi4_scope);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3f25e75ae692..90b26beb84d4 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,7 @@
static int zero;
static int one = 1;
static int four = 4;
+static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -753,6 +754,15 @@ static struct ctl_table ipv4_table[] = {
.extra2 = &four,
},
{
+ .procname = "tcp_min_tso_segs",
+ .data = &sysctl_tcp_min_tso_segs,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &gso_max_segs,
+ },
+ {
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a5b4f535a519..78411dad59ef 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -286,6 +286,8 @@
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -790,14 +792,24 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
xmit_size_goal = mss_now;
if (large_allowed && sk_can_gso(sk)) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
+ u32 gso_size, hlen;
+
+ /* Maybe we should/could use sk->sk_prot->max_header here ? */
+ hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+ inet_csk(sk)->icsk_ext_hdr_len +
+ tp->tcp_header_len;
- /* TSQ : try to have two TSO segments in flight */
- xmit_size_goal = min_t(u32, xmit_size_goal,
- sysctl_tcp_limit_output_bytes >> 1);
+ /* Goal is to send at least one packet per ms,
+ * not one big TSO packet every 100 ms.
+ * This preserves ACK clocking and is consistent
+ * with tcp_tso_should_defer() heuristic.
+ */
+ gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+ gso_size = max_t(u32, gso_size,
+ sysctl_tcp_min_tso_segs * mss_now);
+
+ xmit_size_goal = min_t(u32, gso_size,
+ sk->sk_gso_max_size - 1 - hlen);
xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
@@ -2900,6 +2912,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int sum_truesize = 0;
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
@@ -2983,13 +2996,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
- /* {tcp|sock}_wfree() use exact truesize accounting :
- * sum(skb->truesize) MUST be exactly be gso_skb->truesize
- * So we account mss bytes of 'true size' for each segment.
- * The last segment will contain the remaining.
- */
- skb->truesize = mss;
- gso_skb->truesize -= mss;
+ sum_truesize += skb->truesize;
}
skb = skb->next;
th = tcp_hdr(skb);
@@ -3006,7 +3013,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
- swap(gso_skb->truesize, skb->truesize);
+ sum_truesize += skb->truesize;
+ atomic_add(sum_truesize - gso_skb->truesize,
+ &skb->sk->sk_wmem_alloc);
}
delta = htonl(oldlen + (skb->tail - skb->transport_header) +
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4b75aad14b04..e15d330919af 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -699,6 +699,34 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
}
}
+/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
+ * Note: TCP stack does not yet implement pacing.
+ * FQ packet scheduler can be used to implement cheap but effective
+ * TCP pacing, to smooth the burst on large writes when packets
+ * in flight is significantly lower than cwnd (or rwin)
+ */
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u64 rate;
+
+ /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+ rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+
+ rate *= max(tp->snd_cwnd, tp->packets_out);
+
+ /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
+ * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+ * We probably need usec resolution in the future.
+ * Note: This also takes care of possible srtt=0 case,
+ * when tcp_rtt_estimator() was not yet called.
+ */
+ if (tp->srtt > 8 + 2)
+ do_div(rate, tp->srtt);
+
+ sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+}
+
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
@@ -1264,7 +1292,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
}
- TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
+ TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ TCP_SKB_CB(prev)->end_seq++;
+
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
@@ -3314,7 +3345,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
tcp_init_cwnd_reduction(sk, true);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
- tcp_set_ca_state(sk, TCP_CA_Open);
+ tcp_try_keep_open(sk);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
}
@@ -3330,7 +3361,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_in_flight;
+ u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
u32 prior_fackets;
int prior_packets = tp->packets_out;
int prior_sacked = tp->sacked_out;
@@ -3438,6 +3469,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
+ if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
+ tcp_update_pacing_rate(sk);
return 1;
no_queue:
@@ -5736,6 +5769,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on
* first data packet.
*/
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1fb157f0957d..bc172b836ed6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -178,7 +178,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return err;
}
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index f6a005c485a9..306dbd9a9441 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -665,10 +665,13 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
struct tcp_fastopen_cookie *cookie, bool syn_lost)
{
+ struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_metrics_block *tm;
+ if (!dst)
+ return;
rcu_read_lock();
- tm = tcp_get_metrics(sk, __sk_dst_get(sk), true);
+ tm = tcp_get_metrics(sk, dst, true);
if (tm) {
struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0145ce7e6098..5560abfe6d30 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -887,8 +887,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb_orphan(skb);
skb->sk = sk;
- skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
- tcp_wfree : sock_wfree;
+ skb->destructor = tcp_wfree;
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
/* Build TCP header and checksum it. */
@@ -977,6 +976,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
+ /* Make sure we own this skb before messing gso_size/gso_segs */
+ WARN_ON_ONCE(skb_cloned(skb));
+
if (skb->len <= mss_now || !sk_can_gso(sk) ||
skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
@@ -1058,9 +1060,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
if (nsize < 0)
nsize = 0;
- if (skb_cloned(skb) &&
- skb_is_nonlinear(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
@@ -1623,7 +1623,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
- sk->sk_gso_max_segs * tp->mss_cache))
+ tp->xmit_size_goal_segs * tp->mss_cache))
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
@@ -1832,7 +1832,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
-
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
@@ -1861,13 +1860,24 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
break;
}
- /* TSQ : sk_wmem_alloc accounts skb truesize,
- * including skb overhead. But thats OK.
+ /* TCP Small Queues :
+ * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+ * This allows for :
+ * - better RTT estimation and ACK scheduling
+ * - faster recovery
+ * - high rates
+ * Alas, some drivers / subsystems require a fair amount
+ * of queued bytes to ensure line rate.
+ * One example is wifi aggregation (802.11 AMPDU)
*/
- if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+ limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+ sk->sk_pacing_rate >> 10);
+
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
break;
}
+
limit = mss_now;
if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2329,6 +2339,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ return -ENOMEM;
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
@@ -3090,7 +3102,6 @@ void tcp_send_window_probe(struct sock *sk)
{
if (sk->sk_state == TCP_ESTABLISHED) {
tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
- tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
tcp_xmit_probe_skb(sk, 0);
}
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6c9ab80efb52..5ed9a7a09f04 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -973,7 +973,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -1072,6 +1072,12 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
struct udp_sock *up = udp_sk(sk);
int ret;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
if (!up->pending) {
struct msghdr msg = { .msg_flags = flags|MSG_MORE };
@@ -1209,14 +1215,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
int is_udplite = IS_UDPLITE(sk);
bool slow;
- /*
- * Check any passed addresses
- */
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1276,6 +1276,7 @@ try_again:
sin->sin_port = udp_hdr(skb)->source;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4b56cbbc7890..8997340e3742 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
/*
* Handle MSG_ERRQUEUE
*/
-int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sock_exterr_skb *serr;
@@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
&sin->sin6_addr);
sin->sin6_scope_id = 0;
}
+ *addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
@@ -377,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
+ sin->sin6_port = 0;
if (skb->protocol == htons(ETH_P_IPV6)) {
sin->sin6_addr = ipv6_hdr(skb)->saddr;
if (np->rxopt.all)
@@ -423,7 +425,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error);
/*
* Handle IPV6_RECVPATHMTU
*/
-int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+ int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
@@ -457,6 +460,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
sin->sin6_port = 0;
sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
+ *addr_len = sizeof(*sin);
}
put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 32b4a1675d82..066640e0ba8e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -116,7 +116,7 @@ begintw:
}
if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
ports, dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 46e88433ec7d..f0ccdb787100 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -453,8 +453,10 @@ static int mem_check(struct sock *sk)
if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
return 0;
+ rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl)
count++;
+ rcu_read_unlock_bh();
if (room <= 0 ||
((count >= FL_MAX_PER_SOCK ||
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 44ffdb99a62e..b98b8e06739e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -130,7 +130,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+ nexthop = rt6_nexthop((struct rt6_info *)dst);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
@@ -141,8 +141,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
}
rcu_read_unlock_bh();
- IP6_INC_STATS_BH(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ IP6_INC_STATS(dev_net(dst->dev),
+ ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
@@ -150,7 +150,8 @@ static int ip6_finish_output2(struct sk_buff *skb)
static int ip6_finish_output(struct sk_buff *skb)
{
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
- dst_allfrag(skb_dst(skb)))
+ dst_allfrag(skb_dst(skb)) ||
+ (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
return ip6_fragment(skb, ip6_finish_output2);
else
return ip6_finish_output2(skb);
@@ -898,7 +899,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
- n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
@@ -1250,7 +1251,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
skb = skb_peek_tail(&sk->sk_write_queue);
cork->length += length;
if (((length > mtu) ||
- (skb && skb_is_gso(skb))) &&
+ (skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index c9b6a6e6a1e8..97cd7507c1a4 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -172,63 +172,13 @@ out:
return nf_conntrack_confirm(skb);
}
-static unsigned int __ipv6_conntrack_in(struct net *net,
- unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- struct sk_buff *reasm = skb->nfct_reasm;
- const struct nf_conn_help *help;
- struct nf_conn *ct;
- enum ip_conntrack_info ctinfo;
-
- /* This packet is fragmented and has reassembled packet. */
- if (reasm) {
- /* Reassembled packet isn't parsed yet ? */
- if (!reasm->nfct) {
- unsigned int ret;
-
- ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm);
- if (ret != NF_ACCEPT)
- return ret;
- }
-
- /* Conntrack helpers need the entire reassembled packet in the
- * POST_ROUTING hook. In case of unconfirmed connections NAT
- * might reassign a helper, so the entire packet is also
- * required.
- */
- ct = nf_ct_get(reasm, &ctinfo);
- if (ct != NULL && !nf_ct_is_untracked(ct)) {
- help = nfct_help(ct);
- if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
- nf_conntrack_get_reasm(reasm);
- NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
- (struct net_device *)in,
- (struct net_device *)out,
- okfn, NF_IP6_PRI_CONNTRACK + 1);
- return NF_DROP_ERR(-ECANCELED);
- }
- }
-
- nf_conntrack_get(reasm->nfct);
- skb->nfct = reasm->nfct;
- skb->nfctinfo = reasm->nfctinfo;
- return NF_ACCEPT;
- }
-
- return nf_conntrack_in(net, PF_INET6, hooknum, skb);
-}
-
static unsigned int ipv6_conntrack_in(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
+ return nf_conntrack_in(dev_net(in), PF_INET6, hooknum, skb);
}
static unsigned int ipv6_conntrack_local(unsigned int hooknum,
@@ -242,7 +192,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
return NF_ACCEPT;
}
- return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
+ return nf_conntrack_in(dev_net(out), PF_INET6, hooknum, skb);
}
static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index dffdc1a389c5..253566a8d55b 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -621,31 +621,16 @@ ret_orig:
return skb;
}
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
- struct net_device *in, struct net_device *out,
- int (*okfn)(struct sk_buff *))
+void nf_ct_frag6_consume_orig(struct sk_buff *skb)
{
struct sk_buff *s, *s2;
- unsigned int ret = 0;
for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
- nf_conntrack_put_reasm(s->nfct_reasm);
- nf_conntrack_get_reasm(skb);
- s->nfct_reasm = skb;
-
s2 = s->next;
s->next = NULL;
-
- if (ret != -ECANCELED)
- ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
- in, out, okfn,
- NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
- else
- kfree_skb(s);
-
+ consume_skb(s);
s = s2;
}
- nf_conntrack_put_reasm(skb);
}
static int nf_ct_net_init(struct net *net)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index aacd121fe8c5..581dd9ede0de 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
if (reasm == skb)
return NF_ACCEPT;
- nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
- (struct net_device *)out, okfn);
+ nf_ct_frag6_consume_orig(reasm);
+
+ NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
+ (struct net_device *) in, (struct net_device *) out,
+ okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
return NF_STOLEN;
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index eedff8ccded5..464b1c9c08e4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -459,14 +459,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- if (addr_len)
- *addr_len=sizeof(*sin6);
-
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
- return ipv6_recv_rxpmtu(sk, msg, len);
+ return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -500,6 +497,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
IP6CB(skb)->iif);
+ *addr_len = sizeof(*sin6);
}
sock_recv_ts_and_drops(msg, sk, skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bacce6c08644..5a8bf536026c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -473,6 +473,24 @@ out:
}
#ifdef CONFIG_IPV6_ROUTER_PREF
+struct __rt6_probe_work {
+ struct work_struct work;
+ struct in6_addr target;
+ struct net_device *dev;
+};
+
+static void rt6_probe_deferred(struct work_struct *w)
+{
+ struct in6_addr mcaddr;
+ struct __rt6_probe_work *work =
+ container_of(w, struct __rt6_probe_work, work);
+
+ addrconf_addr_solict_mult(&work->target, &mcaddr);
+ ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
+ dev_put(work->dev);
+ kfree(w);
+}
+
static void rt6_probe(struct rt6_info *rt)
{
struct neighbour *neigh;
@@ -496,17 +514,23 @@ static void rt6_probe(struct rt6_info *rt)
if (!neigh ||
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
- struct in6_addr mcaddr;
- struct in6_addr *target;
+ struct __rt6_probe_work *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
- if (neigh) {
+ if (neigh && work)
neigh->updated = jiffies;
+
+ if (neigh)
write_unlock(&neigh->lock);
- }
- target = (struct in6_addr *)&rt->rt6i_gateway;
- addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
+ if (work) {
+ INIT_WORK(&work->work, rt6_probe_deferred);
+ work->target = rt->rt6i_gateway;
+ dev_hold(rt->dst.dev);
+ work->dev = rt->dst.dev;
+ schedule_work(&work->work);
+ }
} else {
out:
write_unlock(&neigh->lock);
@@ -704,8 +728,11 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
prefix = &prefix_buf;
}
- rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
- dev->ifindex);
+ if (rinfo->prefix_len == 0)
+ rt = rt6_get_dflt_router(gwaddr, dev);
+ else
+ rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
+ gwaddr, dev->ifindex);
if (rt && !lifetime) {
ip6_del_rt(rt);
@@ -848,7 +875,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
- rt->rt6i_gateway = *daddr;
}
rt->rt6i_flags |= RTF_CACHE;
@@ -1061,10 +1087,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
return NULL;
- if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
- return dst;
+ if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+ return NULL;
- return NULL;
+ if (rt6_check_expired(rt))
+ return NULL;
+
+ return dst;
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -1245,6 +1274,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
atomic_set(&rt->dst.__refcnt, 1);
+ rt->rt6i_gateway = fl6->daddr;
rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
rt->rt6i_idev = idev;
@@ -1801,7 +1831,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
- rt->rt6i_gateway = ort->rt6i_gateway;
+ if (ort->rt6i_flags & RTF_GATEWAY)
+ rt->rt6i_gateway = ort->rt6i_gateway;
+ else
+ rt->rt6i_gateway = *dest;
rt->rt6i_flags = ort->rt6i_flags;
if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
(RTF_DEFAULT | RTF_ADDRCONF))
@@ -2088,6 +2121,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
else
rt->rt6i_flags |= RTF_LOCAL;
+ rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 51330d91c825..99636a77cdfc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -375,14 +375,11 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
int is_udp4;
bool slow;
- if (addr_len)
- *addr_len = sizeof(struct sockaddr_in6);
-
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
- return ipv6_recv_rxpmtu(sk, msg, len);
+ return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -463,7 +460,7 @@ try_again:
ipv6_iface_scope_id(&sin6->sin6_addr,
IP6CB(skb)->iif);
}
-
+ *addr_len = sizeof(*sin6);
}
if (is_udp4) {
if (inet->cmsg_flags)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index d3cfaf9c7a08..76f165ef8d49 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -85,7 +85,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
/* Check if there is enough headroom to insert fragment header. */
tnl_hlen = skb_tnl_header_len(skb);
- if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) {
+ if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) {
if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
goto out;
}
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index f547a47d381c..e0897377b3b4 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1823,8 +1823,6 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
if (skb->tstamp.tv64)
sk->sk_stamp = skb->tstamp;
- msg->msg_namelen = sizeof(*sipx);
-
if (sipx) {
sipx->sipx_family = AF_IPX;
sipx->sipx_port = ipx->ipx_source.sock;
@@ -1832,6 +1830,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net;
sipx->sipx_type = ipx->ipx_type;
sipx->sipx_zero = 0;
+ msg->msg_namelen = sizeof(*sipx);
}
rc = copied;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 0578d4fa00a9..a5e62ef57155 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1385,8 +1385,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
IRDA_DEBUG(4, "%s()\n", __func__);
- msg->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
if (!skb)
@@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, noblock);
- msg->msg_namelen = 0;
-
do {
int chunk;
struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index ae691651b721..276aa86f366b 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
int err = 0;
u32 offset;
- msg->msg_namelen = 0;
-
if ((sk->sk_state == IUCV_DISCONN) &&
skb_queue_empty(&iucv->backlog_skb_q) &&
skb_queue_empty(&sk->sk_receive_queue) &&
diff --git a/net/key/af_key.c b/net/key/af_key.c
index ab8bd2cabfa0..66f51c5a8a3a 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3623,7 +3623,6 @@ static int pfkey_recvmsg(struct kiocb *kiocb,
if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
goto out;
- msg->msg_namelen = 0;
skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6984c3a353cd..8c27de2b4d5a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -115,6 +115,11 @@ struct l2tp_net {
static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
+static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
+{
+ return sk->sk_user_data;
+}
+
static inline struct l2tp_net *l2tp_pernet(struct net *net)
{
BUG_ON(!net);
@@ -507,7 +512,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk,
return 0;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6) {
+ if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) {
if (!uh->check) {
LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n");
return 1;
@@ -1071,7 +1076,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
/* Queue the packet to IP for output */
skb->local_df = 1;
#if IS_ENABLED(CONFIG_IPV6)
- if (skb->sk->sk_family == PF_INET6)
+ if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped)
error = inet6_csk_xmit(skb, NULL);
else
#endif
@@ -1198,7 +1203,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
/* Calculate UDP checksum if configured to do so */
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6)
+ if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
l2tp_xmit_ipv6_csum(sk, skb, udp_len);
else
#endif
@@ -1247,10 +1252,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
*/
static void l2tp_tunnel_destruct(struct sock *sk)
{
- struct l2tp_tunnel *tunnel;
+ struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
struct l2tp_net *pn;
- tunnel = sk->sk_user_data;
if (tunnel == NULL)
goto end;
@@ -1618,7 +1622,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
}
/* Check if this socket has already been prepped */
- tunnel = (struct l2tp_tunnel *)sk->sk_user_data;
+ tunnel = l2tp_tunnel(sk);
if (tunnel != NULL) {
/* This socket has already been prepped */
err = -EBUSY;
@@ -1647,6 +1651,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
if (cfg != NULL)
tunnel->debug = cfg->debug;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == PF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (ipv6_addr_v4mapped(&np->saddr) &&
+ ipv6_addr_v4mapped(&np->daddr)) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ tunnel->v4mapped = true;
+ inet->inet_saddr = np->saddr.s6_addr32[3];
+ inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3];
+ inet->inet_daddr = np->daddr.s6_addr32[3];
+ } else {
+ tunnel->v4mapped = false;
+ }
+ }
+#endif
+
/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
tunnel->encap = encap;
if (encap == L2TP_ENCAPTYPE_UDP) {
@@ -1655,7 +1677,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6)
+ if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
udpv6_encap_enable();
else
#endif
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 485a490fd990..2f89d43877d7 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -189,6 +189,9 @@ struct l2tp_tunnel {
struct sock *sock; /* Parent socket */
int fd; /* Parent fd, if tunnel socket
* was created by userspace */
+#if IS_ENABLED(CONFIG_IPV6)
+ bool v4mapped;
+#endif
struct work_struct del_work;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 571db8dd2292..da1a1cee1a08 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -518,9 +518,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
@@ -543,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b8a6039314e8..e6e8408c9e36 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
*addr_len = sizeof(*lsa);
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 5ebee2ded9e9..44441c0c5037 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
if (sk->sk_state & PPPOX_BOUND)
goto end;
- msg->msg_namelen = 0;
-
err = 0;
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
@@ -353,7 +351,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
goto error_put_sess_tun;
}
+ local_bh_disable();
l2tp_xmit_skb(session, skb, session->hdr_len);
+ local_bh_enable();
sock_put(ps->tunnel_sock);
sock_put(sk);
@@ -422,7 +422,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
skb->data[0] = ppph[0];
skb->data[1] = ppph[1];
+ local_bh_disable();
l2tp_xmit_skb(session, skb, session->hdr_len);
+ local_bh_enable();
sock_put(sk_tun);
sock_put(sk);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 48aaa89253e0..88709882c464 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -720,8 +720,6 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
int target; /* Read at least this many bytes */
long timeo;
- msg->msg_namelen = 0;
-
lock_sock(sk);
copied = -ENOTCONN;
if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ae36f8e11ae4..5ab17b82605d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3315,7 +3315,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
return -EINVAL;
}
band = chanctx_conf->def.chan->band;
- sta = sta_info_get(sdata, peer);
+ sta = sta_info_get_bss(sdata, peer);
if (sta) {
qos = test_sta_flag(sta, WLAN_STA_WME);
} else {
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9f48d84ae633..8b7a15383108 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -842,6 +842,8 @@ struct tpt_led_trigger {
* that the scan completed.
* @SCAN_ABORTED: Set for our scan work function when the driver reported
* a scan complete for an aborted scan.
+ * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being
+ * cancelled.
*/
enum {
SCAN_SW_SCANNING,
@@ -849,6 +851,7 @@ enum {
SCAN_ONCHANNEL_SCANNING,
SCAN_COMPLETED,
SCAN_ABORTED,
+ SCAN_HW_CANCELLED,
};
/**
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 83f6d29202aa..ec09bcba9bae 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3002,6 +3002,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
case NL80211_IFTYPE_ADHOC:
if (!bssid)
return 0;
+ if (ether_addr_equal(sdata->vif.addr, hdr->addr2) ||
+ ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2))
+ return 0;
if (ieee80211_is_beacon(hdr->frame_control)) {
return 1;
} else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) {
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 5d8b2e7b8f9f..e1ae2388e2b4 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -202,6 +202,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
enum ieee80211_band band;
int i, ielen, n_chans;
+ if (test_bit(SCAN_HW_CANCELLED, &local->scanning))
+ return false;
+
do {
if (local->hw_scan_band == IEEE80211_NUM_BANDS)
return false;
@@ -892,7 +895,23 @@ void ieee80211_scan_cancel(struct ieee80211_local *local)
if (!local->scan_req)
goto out;
+ /*
+ * We have a scan running and the driver already reported completion,
+ * but the worker hasn't run yet or is stuck on the mutex - mark it as
+ * cancelled.
+ */
+ if (test_bit(SCAN_HW_SCANNING, &local->scanning) &&
+ test_bit(SCAN_COMPLETED, &local->scanning)) {
+ set_bit(SCAN_HW_CANCELLED, &local->scanning);
+ goto out;
+ }
+
if (test_bit(SCAN_HW_SCANNING, &local->scanning)) {
+ /*
+ * Make sure that __ieee80211_scan_completed doesn't trigger a
+ * scan on another band.
+ */
+ set_bit(SCAN_HW_CANCELLED, &local->scanning);
if (local->ops->cancel_hw_scan)
drv_cancel_hw_scan(local,
rcu_dereference_protected(local->scan_sdata,
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 43439203f4e4..9e78206bd9bb 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -180,6 +180,9 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb)
struct ieee80211_local *local = sta->local;
struct ieee80211_sub_if_data *sdata = sta->sdata;
+ if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+ sta->last_rx = jiffies;
+
if (ieee80211_is_data_qos(mgmt->frame_control)) {
struct ieee80211_hdr *hdr = (void *) skb->data;
u8 *qc = ieee80211_get_qos_ctl(hdr);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 9972e07a2f96..e9d18c30071f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1100,7 +1100,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
tx->sta = rcu_dereference(sdata->u.vlan.sta);
if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr)
return TX_DROP;
- } else if (info->flags & IEEE80211_TX_CTL_INJECTED ||
+ } else if (info->flags & (IEEE80211_TX_CTL_INJECTED |
+ IEEE80211_TX_INTFL_NL80211_FRAME_TX) ||
tx->sdata->control_port_protocol == tx->skb->protocol) {
tx->sta = sta_info_get_bss(sdata, hdr->addr1);
}
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 72e6292955bb..5db8eb5d56cf 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2174,6 +2174,10 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
}
rate = cfg80211_calculate_bitrate(&ri);
+ if (WARN_ONCE(!rate,
+ "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n",
+ status->flag, status->rate_idx, status->vht_nss))
+ return 0;
/* rewind from end of MPDU */
if (status->flag & RX_FLAG_MACTIME_END)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 23b8eb53a569..21a3a475d7cd 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1131,12 +1131,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
ip_vs_fill_iph_skb(af, skb, &iph);
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (!iph.fragoffs && skb_nfct_reasm(skb)) {
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- /* Save fw mark for coming frags */
- reasm->ipvs_property = 1;
- reasm->mark = skb->mark;
- }
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_out_icmp_v6(skb, &related,
@@ -1606,12 +1600,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (!iph.fragoffs && skb_nfct_reasm(skb)) {
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- /* Save fw mark for coming frags. */
- reasm->ipvs_property = 1;
- reasm->mark = skb->mark;
- }
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
@@ -1663,9 +1651,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG_PKT(12, af, pp, skb, 0,
"ip_vs_in: packet continues traversal as normal");
- if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+ if (iph.fragoffs) {
/* Fragment that couldn't be mapped to a conn entry
- * and don't have any pointer to a reasm skb
* is missing module nf_defrag_ipv6
*/
IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
@@ -1748,38 +1735,6 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
#ifdef CONFIG_IP_VS_IPV6
/*
- * AF_INET6 fragment handling
- * Copy info from first fragment, to the rest of them.
- */
-static unsigned int
-ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- struct net *net;
-
- /* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
- * ipvs_property is set when checking first fragment
- * in ip_vs_in() and ip_vs_out().
- */
- if (reasm)
- IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
- if (!reasm || !reasm->ipvs_property)
- return NF_ACCEPT;
-
- net = skb_net(skb);
- if (!net_ipvs(net)->enable)
- return NF_ACCEPT;
-
- /* Copy stored fw mark, saved in ip_vs_{in,out} */
- skb->mark = reasm->mark;
-
- return NF_ACCEPT;
-}
-
-/*
* AF_INET6 handler in NF_INET_LOCAL_IN chain
* Schedule and forward packets from remote clients
*/
@@ -1916,14 +1871,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
.priority = 100,
},
#ifdef CONFIG_IP_VS_IPV6
- /* After mangle & nat fetch 2:nd fragment and following */
- {
- .hook = ip_vs_preroute_frag6,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_PRE_ROUTING,
- .priority = NF_IP6_PRI_NAT_DST + 1,
- },
/* After packet filtering, change source only for VS/NAT */
{
.hook = ip_vs_reply6,
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 9ef22bdce9f1..bed5f7042529 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -65,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff,
static int
ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
{
- struct sk_buff *reasm = skb_nfct_reasm(skb);
struct ip_vs_iphdr iph;
unsigned int dataoff, datalen, matchoff, matchlen;
const char *dptr;
@@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
/* todo: IPv6 fragments:
* I think this only should be done for the first fragment. /HS
*/
- if (reasm) {
- skb = reasm;
- dataoff = iph.thoff_reasm + sizeof(struct udphdr);
- } else
- dataoff = iph.len + sizeof(struct udphdr);
+ dataoff = iph.len + sizeof(struct udphdr);
if (dataoff >= skb->len)
return -EINVAL;
- /* todo: Check if this will mess-up the reasm skb !!! /HS */
retc = skb_linearize(skb);
if (retc < 0)
return retc;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index bdebd03bc8cd..70866d192efc 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src,
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
flowi6_to_flowi(&fl2), false)) {
- if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
- sizeof(rt1->rt6i_gateway)) &&
+ if (ipv6_addr_equal(rt6_nexthop(rt1),
+ rt6_nexthop(rt2)) &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index daf7c576b24b..b55ab2d9a94b 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2168,8 +2168,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
}
#endif
- msg->msg_namelen = 0;
-
copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index ec0c80fde69f..13b92982a506 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
sax->sax25_family = AF_NETROM;
skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
AX25_ADDR_LEN);
+ msg->msg_namelen = sizeof(*sax);
}
- msg->msg_namelen = sizeof(*sax);
-
skb_free_datagram(sk, skb);
release_sock(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 7522c3708723..86470cf54cee 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -800,8 +800,6 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
pr_debug("%p %zu\n", sk, len);
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state == LLCP_CLOSED &&
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 313bf1bc848a..5d11f4ac3ecb 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -241,8 +241,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock,
if (!skb)
return rc;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a6895ab597c2..c503ad6f610f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -244,11 +244,15 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
static void register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
+
if (!po->running) {
- if (po->fanout)
+ if (po->fanout) {
__fanout_link(sk, po);
- else
+ } else {
dev_add_pack(&po->prot_hook);
+ rcu_assign_pointer(po->cached_dev, po->prot_hook.dev);
+ }
+
sock_hold(sk);
po->running = 1;
}
@@ -266,10 +270,13 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
struct packet_sock *po = pkt_sk(sk);
po->running = 0;
- if (po->fanout)
+ if (po->fanout) {
__fanout_unlink(sk, po);
- else
+ } else {
__dev_remove_pack(&po->prot_hook);
+ RCU_INIT_POINTER(po->cached_dev, NULL);
+ }
+
__sock_put(sk);
if (sync) {
@@ -432,9 +439,9 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
- spin_lock(&rb_queue->lock);
+ spin_lock_bh(&rb_queue->lock);
pkc->delete_blk_timer = 1;
- spin_unlock(&rb_queue->lock);
+ spin_unlock_bh(&rb_queue->lock);
prb_del_retire_blk_timer(pkc);
}
@@ -2041,12 +2048,24 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
return tp_len;
}
+static struct net_device *packet_cached_dev_get(struct packet_sock *po)
+{
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = rcu_dereference(po->cached_dev);
+ if (dev)
+ dev_hold(dev);
+ rcu_read_unlock();
+
+ return dev;
+}
+
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
{
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
int err, reserve = 0;
void *ph;
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
@@ -2059,7 +2078,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
mutex_lock(&po->pg_vec_lock);
if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
@@ -2073,19 +2092,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
if (unlikely(dev == NULL))
goto out;
-
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ reserve = dev->hard_header_len;
+
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
@@ -2162,8 +2179,7 @@ out_status:
__packet_set_status(po, ph, status);
kfree_skb(skb);
out_put:
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
out:
mutex_unlock(&po->pg_vec_lock);
return err;
@@ -2201,7 +2217,6 @@ static int packet_snd(struct socket *sock,
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
unsigned char *addr;
int err, reserve = 0;
struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2217,7 +2232,7 @@ static int packet_snd(struct socket *sock,
*/
if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
@@ -2229,19 +2244,17 @@ static int packet_snd(struct socket *sock,
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
- if (dev == NULL)
+ if (unlikely(dev == NULL))
goto out_unlock;
- if (sock->type == SOCK_RAW)
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
- if (!(dev->flags & IFF_UP))
+ if (unlikely(!(dev->flags & IFF_UP)))
goto out_unlock;
+ if (sock->type == SOCK_RAW)
+ reserve = dev->hard_header_len;
if (po->has_vnet_hdr) {
vnet_hdr_len = sizeof(vnet_hdr);
@@ -2375,15 +2388,14 @@ static int packet_snd(struct socket *sock,
if (err > 0 && (err = net_xmit_errno(err)) != 0)
goto out_unlock;
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
return len;
out_free:
kfree_skb(skb);
out_unlock:
- if (dev && need_rls_dev)
+ if (dev)
dev_put(dev);
out:
return err;
@@ -2603,6 +2615,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
po = pkt_sk(sk);
sk->sk_family = PF_PACKET;
po->num = proto;
+ RCU_INIT_POINTER(po->cached_dev, NULL);
sk->sk_destruct = packet_sock_destruct;
sk_refcnt_debug_inc(sk);
@@ -2694,7 +2707,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
- struct sockaddr_ll *sll;
int vnet_hdr_len = 0;
err = -EINVAL;
@@ -2777,22 +2789,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
goto out_free;
}
- /*
- * If the address length field is there to be filled in, we fill
- * it in now.
+ /* You lose any data beyond the buffer you gave. If it worries
+ * a user program they can ask the device for its MTU
+ * anyway.
*/
-
- sll = &PACKET_SKB_CB(skb)->sa.ll;
- if (sock->type == SOCK_PACKET)
- msg->msg_namelen = sizeof(struct sockaddr_pkt);
- else
- msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
- /*
- * You lose any data beyond the buffer you gave. If it worries a
- * user program they can ask the device for its MTU anyway.
- */
-
copied = skb->len;
if (copied > len) {
copied = len;
@@ -2805,9 +2805,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
sock_recv_ts_and_drops(msg, sk, skb);
- if (msg->msg_name)
+ if (msg->msg_name) {
+ /* If the address length field is there to be filled
+ * in, we fill it in now.
+ */
+ if (sock->type == SOCK_PACKET) {
+ msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ } else {
+ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+ msg->msg_namelen = sll->sll_halen +
+ offsetof(struct sockaddr_ll, sll_addr);
+ }
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
msg->msg_namelen);
+ }
if (pkt_sk(sk)->auxdata) {
struct tpacket_auxdata aux;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index c4e4b4561207..1035fa2d909c 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -113,6 +113,7 @@ struct packet_sock {
unsigned int tp_loss:1;
unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
+ struct net_device __rcu *cached_dev;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 12c30f3e643e..38946b26e471 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -139,9 +139,6 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
MSG_CMSG_COMPAT))
goto out_nofree;
- if (addr_len)
- *addr_len = sizeof(sa);
-
skb = skb_recv_datagram(sk, flags, noblock, &rval);
if (skb == NULL)
goto out_nofree;
@@ -162,8 +159,10 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
rval = (flags & MSG_TRUNC) ? skb->len : copylen;
- if (msg->msg_name != NULL)
- memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn));
+ if (msg->msg_name != NULL) {
+ memcpy(msg->msg_name, &sa, sizeof(sa));
+ *addr_len = sizeof(sa);
+ }
out:
skb_free_datagram(sk, skb);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 9f0f17cf6bf9..de339b24ca14 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
- msg->msg_namelen = 0;
-
if (msg_flags & MSG_OOB)
goto out;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9c8347451597..abf0ad6311d0 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
{
struct sock *sk = sock->sk;
struct rose_sock *rose = rose_sk(sk);
- struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
size_t copied;
unsigned char *asmptr;
struct sk_buff *skb;
@@ -1252,8 +1251,11 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (srose != NULL) {
- memset(srose, 0, msg->msg_namelen);
+ if (msg->msg_name) {
+ struct sockaddr_rose *srose;
+
+ memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+ srose = msg->msg_name;
srose->srose_family = AF_ROSE;
srose->srose_addr = rose->dest_addr;
srose->srose_call = rose->dest_call;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4b48687c3890..898492a8d61b 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
/* copy the peer address and timestamp */
if (!continue_call) {
- if (msg->msg_name && msg->msg_namelen > 0)
+ if (msg->msg_name) {
+ size_t len =
+ sizeof(call->conn->trans->peer->srx);
memcpy(msg->msg_name,
- &call->conn->trans->peer->srx,
- sizeof(call->conn->trans->peer->srx));
+ &call->conn->trans->peer->srx, len);
+ msg->msg_namelen = len;
+ }
sock_recv_ts_and_drops(msg, &rx->sk, skb);
}
diff --git a/net/sctp/output.c b/net/sctp/output.c
index bbef4a7a9b56..0beb2f9c8a7c 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -547,7 +547,8 @@ int sctp_packet_transmit(struct sctp_packet *packet)
* by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
*/
if (!sctp_checksum_disable) {
- if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) {
+ if (!(dst->dev->features & NETIF_F_SCTP_CSUM) ||
+ (dst_xfrm(dst) != NULL) || packet->ipfragok) {
__u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len);
/* 3) Put the resultant value into the checksum field in the
diff --git a/net/socket.c b/net/socket.c
index 30d6ec51b620..6b315a8cd0c9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -217,12 +217,13 @@ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen,
int err;
int len;
+ BUG_ON(klen > sizeof(struct sockaddr_storage));
err = get_user(len, ulen);
if (err)
return err;
if (len > klen)
len = klen;
- if (len < 0 || len > sizeof(struct sockaddr_storage))
+ if (len < 0)
return -EINVAL;
if (len) {
if (audit_sockaddr(klen, kaddr))
@@ -1837,8 +1838,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
msg.msg_iov = &iov;
iov.iov_len = size;
iov.iov_base = ubuf;
- msg.msg_name = (struct sockaddr *)&address;
- msg.msg_namelen = sizeof(address);
+ /* Save some cycles and don't copy the address if not needed */
+ msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg.msg_namelen = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, size, flags);
@@ -1961,6 +1964,16 @@ struct used_address {
unsigned int name_len;
};
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+ struct msghdr __user *umsg)
+{
+ if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+ return -EFAULT;
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ kmsg->msg_namelen = sizeof(struct sockaddr_storage);
+ return 0;
+}
+
static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags,
struct used_address *used_address)
@@ -1979,8 +1992,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2188,8 +2204,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2202,16 +2221,14 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
goto out;
}
- /*
- * Save the user-mode address (verify_iovec will change the
- * kernel msghdr to use the kernel address space)
+ /* Save the user-mode address (verify_iovec will change the
+ * kernel msghdr to use the kernel address space)
*/
-
uaddr = (__force void __user *)msg_sys->msg_name;
uaddr_len = COMPAT_NAMELEN(msg);
- if (MSG_CMSG_COMPAT & flags) {
+ if (MSG_CMSG_COMPAT & flags)
err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
- } else
+ else
err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
if (err < 0)
goto out_freeiov;
@@ -2220,6 +2237,9 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
cmsg_ptr = (unsigned long)msg_sys->msg_control;
msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg_sys->msg_namelen = 0;
+
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 426f8fcc4c6c..5b1bf7b530f1 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1407,9 +1407,9 @@ call_refreshresult(struct rpc_task *task)
return;
case -ETIMEDOUT:
rpc_delay(task, 3*HZ);
- case -EKEYEXPIRED:
case -EAGAIN:
status = -EACCES;
+ case -EKEYEXPIRED:
if (!task->tk_cred_retry)
break;
task->tk_cred_retry--;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index ffd50348a509..8a0e04d0928a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -391,8 +391,10 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen,
return kernel_sendmsg(sock, &msg, NULL, 0, 0);
}
-static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy)
{
+ ssize_t (*do_sendpage)(struct socket *sock, struct page *page,
+ int offset, size_t size, int flags);
struct page **ppage;
unsigned int remainder;
int err, sent = 0;
@@ -401,6 +403,9 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
base += xdr->page_base;
ppage = xdr->pages + (base >> PAGE_SHIFT);
base &= ~PAGE_MASK;
+ do_sendpage = sock->ops->sendpage;
+ if (!zerocopy)
+ do_sendpage = sock_no_sendpage;
for(;;) {
unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
int flags = XS_SENDMSG_FLAGS;
@@ -408,7 +413,7 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
remainder -= len;
if (remainder != 0 || more)
flags |= MSG_MORE;
- err = sock->ops->sendpage(sock, *ppage, base, len, flags);
+ err = do_sendpage(sock, *ppage, base, len, flags);
if (remainder == 0 || err != len)
break;
sent += err;
@@ -429,9 +434,10 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
* @addrlen: UDP only -- length of destination address
* @xdr: buffer containing this request
* @base: starting position in the buffer
+ * @zerocopy: true if it is safe to use sendpage()
*
*/
-static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy)
{
unsigned int remainder = xdr->len - base;
int err, sent = 0;
@@ -459,7 +465,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
if (base < xdr->page_len) {
unsigned int len = xdr->page_len - base;
remainder -= len;
- err = xs_send_pagedata(sock, xdr, base, remainder != 0);
+ err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy);
if (remainder == 0 || err != len)
goto out;
sent += err;
@@ -562,7 +568,7 @@ static int xs_local_send_request(struct rpc_task *task)
req->rq_svec->iov_base, req->rq_svec->iov_len);
status = xs_sendpages(transport->sock, NULL, 0,
- xdr, req->rq_bytes_sent);
+ xdr, req->rq_bytes_sent, true);
dprintk("RPC: %s(%u) = %d\n",
__func__, xdr->len - req->rq_bytes_sent, status);
if (likely(status >= 0)) {
@@ -618,7 +624,7 @@ static int xs_udp_send_request(struct rpc_task *task)
status = xs_sendpages(transport->sock,
xs_addr(xprt),
xprt->addrlen, xdr,
- req->rq_bytes_sent);
+ req->rq_bytes_sent, true);
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
@@ -689,6 +695,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
+ bool zerocopy = true;
int status;
xs_encode_stream_record_marker(&req->rq_snd_buf);
@@ -696,13 +703,20 @@ static int xs_tcp_send_request(struct rpc_task *task)
xs_pktdump("packet data:",
req->rq_svec->iov_base,
req->rq_svec->iov_len);
+ /* Don't use zero copy if this is a resend. If the RPC call
+ * completes while the socket holds a reference to the pages,
+ * then we may end up resending corrupted data.
+ */
+ if (task->tk_flags & RPC_TASK_SENT)
+ zerocopy = false;
/* Continue transmitting the packet/record. We must be careful
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
while (1) {
status = xs_sendpages(transport->sock,
- NULL, 0, xdr, req->rq_bytes_sent);
+ NULL, 0, xdr, req->rq_bytes_sent,
+ zerocopy);
dprintk("RPC: xs_tcp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7e26ad416af1..2b1d7c2d677d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -905,9 +905,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock,
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
restart:
@@ -1017,9 +1014,6 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock,
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c4ce243824bb..6c66e8d4c715 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1246,6 +1246,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
return 0;
}
+static void unix_sock_inherit_flags(const struct socket *old,
+ struct socket *new)
+{
+ if (test_bit(SOCK_PASSCRED, &old->flags))
+ set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSSEC, &old->flags))
+ set_bit(SOCK_PASSSEC, &new->flags);
+}
+
static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
{
struct sock *sk = sock->sk;
@@ -1280,6 +1289,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
/* attach accepted sock to socket */
unix_state_lock(tsk);
newsock->state = SS_CONNECTED;
+ unix_sock_inherit_flags(sock, newsock);
sock_graft(tsk, newsock);
unix_state_unlock(tsk);
return 0;
@@ -1752,7 +1762,6 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
{
struct unix_sock *u = unix_sk(sk);
- msg->msg_namelen = 0;
if (u->addr) {
msg->msg_namelen = u->addr->len;
memcpy(msg->msg_name, u->addr->name, u->addr->len);
@@ -1776,8 +1785,6 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
err = mutex_lock_interruptible(&u->readlock);
if (err) {
err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
@@ -1917,8 +1924,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
- msg->msg_namelen = 0;
-
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
diff --git a/net/unix/diag.c b/net/unix/diag.c
index d591091603bf..86fa0f3b2caf 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
rep->udiag_family = AF_UNIX;
rep->udiag_type = sk->sk_type;
rep->udiag_state = sk->sk_state;
+ rep->pad = 0;
rep->udiag_ino = sk_ino;
sock_diag_save_cookie(sk, rep->udiag_cookie);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 3f77f42a3b58..9b88693bcc99 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1670,8 +1670,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb,
vsk = vsock_sk(sk);
err = 0;
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state != SS_CONNECTED) {
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index daff75200e25..62bbf7d73980 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
/* Retrieve the head sk_buff from the socket's receive queue. */
err = 0;
skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index d80e47194d49..e62c1ad4e4c9 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -269,6 +269,8 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
if (chan->flags & IEEE80211_CHAN_DISABLED)
continue;
wdev->wext.ibss.chandef.chan = chan;
+ wdev->wext.ibss.chandef.center_freq1 =
+ chan->center_freq;
break;
}
@@ -353,6 +355,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
if (chan) {
wdev->wext.ibss.chandef.chan = chan;
wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
+ wdev->wext.ibss.chandef.center_freq1 = freq;
wdev->wext.ibss.channel_fixed = true;
} else {
/* cfg80211_ibss_wext_join will pick one if needed */
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index 7d604c06c3dc..a271c27fac77 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init(
struct ieee80211_radiotap_header *radiotap_header,
int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns)
{
+ /* check the radiotap header can actually be present */
+ if (max_length < sizeof(struct ieee80211_radiotap_header))
+ return -EINVAL;
+
/* Linux only supports version 0 radiotap format */
if (radiotap_header->it_version)
return -EINVAL;
@@ -131,7 +135,8 @@ int ieee80211_radiotap_iterator_init(
*/
if ((unsigned long)iterator->_arg -
- (unsigned long)iterator->_rtheader >
+ (unsigned long)iterator->_rtheader +
+ sizeof(uint32_t) >
(unsigned long)iterator->_max_length)
return -EINVAL;
}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 41b0f96a933f..4db2177a69ea 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -253,10 +253,10 @@ void __cfg80211_sched_scan_results(struct work_struct *wk)
rdev = container_of(wk, struct cfg80211_registered_device,
sched_scan_results_wk);
- request = rdev->sched_scan_req;
-
mutex_lock(&rdev->sched_scan_mtx);
+ request = rdev->sched_scan_req;
+
/* we don't have sched_scan_req anymore if the scan is stopping */
if (request) {
if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 22c88d2e6846..f96af3b96322 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
if (sx25) {
sx25->sx25_family = AF_X25;
sx25->sx25_addr = x25->dest_addr;
+ msg->msg_namelen = sizeof(*sx25);
}
- msg->msg_namelen = sizeof(struct sockaddr_x25);
-
x25_check_rbuf(sk);
rc = copied;
out_free_dgram: