aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/Kconfig1
-rw-r--r--net/atm/lec.h2
-rw-r--r--net/batman-adv/Kconfig14
-rw-r--r--net/batman-adv/Makefile3
-rw-r--r--net/batman-adv/bat_iv_ogm.c5
-rw-r--r--net/batman-adv/debugfs.c18
-rw-r--r--net/batman-adv/distributed-arp-table.c22
-rw-r--r--net/batman-adv/gateway_client.c2
-rw-r--r--net/batman-adv/hard-interface.c66
-rw-r--r--net/batman-adv/hard-interface.h13
-rw-r--r--net/batman-adv/main.c10
-rw-r--r--net/batman-adv/main.h15
-rw-r--r--net/batman-adv/network-coding.c1821
-rw-r--r--net/batman-adv/network-coding.h123
-rw-r--r--net/batman-adv/originator.c10
-rw-r--r--net/batman-adv/packet.h33
-rw-r--r--net/batman-adv/routing.c49
-rw-r--r--net/batman-adv/send.c5
-rw-r--r--net/batman-adv/soft-interface.c281
-rw-r--r--net/batman-adv/soft-interface.h3
-rw-r--r--net/batman-adv/sysfs.c22
-rw-r--r--net/batman-adv/translation-table.c29
-rw-r--r--net/batman-adv/types.h136
-rw-r--r--net/batman-adv/unicast.c6
-rw-r--r--net/batman-adv/vis.c4
-rw-r--r--net/bluetooth/af_bluetooth.c3
-rw-r--r--net/bluetooth/bnep/netdev.c2
-rw-r--r--net/bridge/br_fdb.c14
-rw-r--r--net/bridge/br_if.c1
-rw-r--r--net/bridge/br_mdb.c4
-rw-r--r--net/bridge/br_multicast.c2
-rw-r--r--net/bridge/br_netlink.c21
-rw-r--r--net/bridge/netfilter/ebt_ulog.c7
-rw-r--r--net/bridge/netfilter/ebtable_broute.c4
-rw-r--r--net/bridge/netfilter/ebtables.c2
-rw-r--r--net/caif/caif_dev.c9
-rw-r--r--net/caif/caif_socket.c22
-rw-r--r--net/caif/caif_usb.c4
-rw-r--r--net/caif/cfcnfg.c19
-rw-r--r--net/caif/cfctrl.c14
-rw-r--r--net/caif/cffrml.c4
-rw-r--r--net/caif/cfmuxl.c4
-rw-r--r--net/caif/cfpkt_skbuff.c8
-rw-r--r--net/caif/cfrfml.c4
-rw-r--r--net/caif/cfserl.c4
-rw-r--r--net/caif/cfsrvl.c13
-rw-r--r--net/caif/chnl_net.c6
-rw-r--r--net/can/af_can.c30
-rw-r--r--net/can/gw.c5
-rw-r--r--net/core/datagram.c4
-rw-r--r--net/core/dev.c80
-rw-r--r--net/core/ethtool.c1
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/filter.c5
-rw-r--r--net/core/flow.c42
-rw-r--r--net/core/flow_dissector.c68
-rw-r--r--net/core/neighbour.c6
-rw-r--r--net/core/net-procfs.c2
-rw-r--r--net/core/netpoll.c3
-rw-r--r--net/core/rtnetlink.c176
-rw-r--r--net/core/skbuff.c50
-rw-r--r--net/core/sock.c10
-rw-r--r--net/core/utils.c5
-rw-r--r--net/dcb/dcbevent.c1
-rw-r--r--net/dcb/dcbnl.c2
-rw-r--r--net/dccp/ipv4.c5
-rw-r--r--net/dccp/ipv6.c5
-rw-r--r--net/decnet/dn_dev.c4
-rw-r--r--net/decnet/dn_fib.c203
-rw-r--r--net/decnet/dn_route.c43
-rw-r--r--net/decnet/dn_table.c46
-rw-r--r--net/decnet/netfilter/dn_rtmsg.c12
-rw-r--r--net/dsa/dsa.c233
-rw-r--r--net/ethernet/eth.c2
-rw-r--r--net/ieee802154/6lowpan.c138
-rw-r--r--net/ieee802154/6lowpan.h7
-rw-r--r--net/ieee802154/dgram.c10
-rw-r--r--net/ieee802154/netlink.c8
-rw-r--r--net/ipv4/Kconfig7
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/af_inet.c10
-rw-r--r--net/ipv4/arp.c27
-rw-r--r--net/ipv4/devinet.c83
-rw-r--r--net/ipv4/fib_frontend.c10
-rw-r--r--net/ipv4/gre.c5
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_diag.c4
-rw-r--r--net/ipv4/inet_fragment.c27
-rw-r--r--net/ipv4/inet_lro.c5
-rw-r--r--net/ipv4/ip_fragment.c31
-rw-r--r--net/ipv4/ip_gre.c1517
-rw-r--r--net/ipv4/ip_tunnel.c1035
-rw-r--r--net/ipv4/ip_vti.c42
-rw-r--r--net/ipv4/ipconfig.c13
-rw-r--r--net/ipv4/ipip.c748
-rw-r--r--net/ipv4/ipmr.c12
-rw-r--r--net/ipv4/netfilter/arptable_filter.c4
-rw-r--r--net/ipv4/netfilter/ipt_ULOG.c4
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/syncookies.c3
-rw-r--r--net/ipv4/sysctl_net_ipv4.c18
-rw-r--r--net/ipv4/tcp.c268
-rw-r--r--net/ipv4/tcp_input.c606
-rw-r--r--net/ipv4/tcp_ipv4.c108
-rw-r--r--net/ipv4/tcp_minisocks.c44
-rw-r--r--net/ipv4/tcp_output.c367
-rw-r--r--net/ipv4/tcp_timer.c21
-rw-r--r--net/ipv4/tcp_westwood.c2
-rw-r--r--net/ipv4/udp.c115
-rw-r--r--net/ipv4/udp_diag.c6
-rw-r--r--net/ipv6/Kconfig2
-rw-r--r--net/ipv6/addrconf.c108
-rw-r--r--net/ipv6/addrlabel.c12
-rw-r--r--net/ipv6/af_inet6.c7
-rw-r--r--net/ipv6/datagram.c20
-rw-r--r--net/ipv6/icmp.c2
-rw-r--r--net/ipv6/inet6_connection_sock.c10
-rw-r--r--net/ipv6/ip6_flowlabel.c11
-rw-r--r--net/ipv6/ip6_gre.c62
-rw-r--r--net/ipv6/ip6_offload.c4
-rw-r--r--net/ipv6/ip6_tunnel.c16
-rw-r--r--net/ipv6/ip6mr.c10
-rw-r--r--net/ipv6/ndisc.c2
-rw-r--r--net/ipv6/netfilter/ip6t_NPT.c11
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c8
-rw-r--r--net/ipv6/raw.c9
-rw-r--r--net/ipv6/reassembly.c23
-rw-r--r--net/ipv6/route.c6
-rw-r--r--net/ipv6/sit.c41
-rw-r--r--net/ipv6/syncookies.c3
-rw-r--r--net/ipv6/tcp_ipv6.c56
-rw-r--r--net/ipv6/udp.c13
-rw-r--r--net/ipv6/udp_offload.c8
-rw-r--r--net/iucv/af_iucv.c3
-rw-r--r--net/l2tp/l2tp_core.c2
-rw-r--r--net/mac80211/cfg.c151
-rw-r--r--net/mac80211/debugfs_sta.c31
-rw-r--r--net/mac80211/driver-ops.h7
-rw-r--r--net/mac80211/ht.c52
-rw-r--r--net/mac80211/ibss.c29
-rw-r--r--net/mac80211/ieee80211_i.h26
-rw-r--r--net/mac80211/iface.c14
-rw-r--r--net/mac80211/key.c103
-rw-r--r--net/mac80211/key.h5
-rw-r--r--net/mac80211/main.c55
-rw-r--r--net/mac80211/mesh.c59
-rw-r--r--net/mac80211/mesh.h12
-rw-r--r--net/mac80211/mesh_plink.c37
-rw-r--r--net/mac80211/mlme.c100
-rw-r--r--net/mac80211/offchannel.c2
-rw-r--r--net/mac80211/pm.c117
-rw-r--r--net/mac80211/rc80211_minstrel.c204
-rw-r--r--net/mac80211/rc80211_minstrel.h31
-rw-r--r--net/mac80211/rc80211_minstrel_debugfs.c12
-rw-r--r--net/mac80211/rc80211_minstrel_ht.c79
-rw-r--r--net/mac80211/rc80211_minstrel_ht.h6
-rw-r--r--net/mac80211/rx.c61
-rw-r--r--net/mac80211/sta_info.c12
-rw-r--r--net/mac80211/sta_info.h2
-rw-r--r--net/mac80211/trace.h11
-rw-r--r--net/mac80211/tx.c2
-rw-r--r--net/mac80211/util.c73
-rw-r--r--net/mac80211/vht.c212
-rw-r--r--net/mac802154/mac802154.h1
-rw-r--r--net/mac802154/mac_cmd.c1
-rw-r--r--net/mac802154/mib.c9
-rw-r--r--net/mac802154/wpan.c2
-rw-r--r--net/netfilter/ipset/ip_set_core.c5
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c8
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c8
-rw-r--r--net/netfilter/ipvs/ip_vs_est.c2
-rw-r--r--net/netfilter/nf_conntrack_core.c47
-rw-r--r--net/netfilter/nf_conntrack_netlink.c100
-rw-r--r--net/netfilter/nf_conntrack_standalone.c16
-rw-r--r--net/netfilter/nfnetlink.c7
-rw-r--r--net/netfilter/nfnetlink_log.c4
-rw-r--r--net/netfilter/nfnetlink_queue_core.c98
-rw-r--r--net/netlink/Kconfig10
-rw-r--r--net/netlink/Makefile3
-rw-r--r--net/netlink/af_netlink.c63
-rw-r--r--net/netlink/af_netlink.h62
-rw-r--r--net/netlink/diag.c188
-rw-r--r--net/nfc/llcp/commands.c205
-rw-r--r--net/nfc/llcp/llcp.c112
-rw-r--r--net/nfc/llcp/llcp.h36
-rw-r--r--net/nfc/llcp/sock.c133
-rw-r--r--net/nfc/netlink.c172
-rw-r--r--net/nfc/nfc.h14
-rw-r--r--net/openvswitch/datapath.c15
-rw-r--r--net/openvswitch/datapath.h2
-rw-r--r--net/openvswitch/flow.c6
-rw-r--r--net/openvswitch/vport-internal_dev.c13
-rw-r--r--net/openvswitch/vport.h4
-rw-r--r--net/packet/af_packet.c114
-rw-r--r--net/packet/internal.h3
-rw-r--r--net/phonet/pn_netlink.c4
-rw-r--r--net/rfkill/rfkill-regulator.c2
-rw-r--r--net/sched/act_api.c2
-rw-r--r--net/sched/cls_api.c15
-rw-r--r--net/sched/sch_api.c44
-rw-r--r--net/sched/sch_htb.c31
-rw-r--r--net/sctp/socket.c3
-rw-r--r--net/tipc/netlink.c6
-rw-r--r--net/unix/af_unix.c4
-rw-r--r--net/vmw_vsock/vmci_transport.c16
-rw-r--r--net/vmw_vsock/vmci_transport.h3
-rw-r--r--net/wireless/ap.c62
-rw-r--r--net/wireless/core.c73
-rw-r--r--net/wireless/core.h24
-rw-r--r--net/wireless/mesh.c15
-rw-r--r--net/wireless/mlme.c230
-rw-r--r--net/wireless/nl80211.c1857
-rw-r--r--net/wireless/nl80211.h68
-rw-r--r--net/wireless/rdev-ops.h20
-rw-r--r--net/wireless/reg.c6
-rw-r--r--net/wireless/sme.c26
-rw-r--r--net/wireless/sysfs.c25
-rw-r--r--net/wireless/trace.h46
-rw-r--r--net/wireless/util.c2
-rw-r--r--net/xfrm/xfrm_policy.c23
221 files changed, 9200 insertions, 6047 deletions
diff --git a/net/Kconfig b/net/Kconfig
index 6f676ab885be..2ddc9046868e 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -217,6 +217,7 @@ source "net/dns_resolver/Kconfig"
source "net/batman-adv/Kconfig"
source "net/openvswitch/Kconfig"
source "net/vmw_vsock/Kconfig"
+source "net/netlink/Kconfig"
config RPS
boolean
diff --git a/net/atm/lec.h b/net/atm/lec.h
index a86aff9a3c04..4149db1b7885 100644
--- a/net/atm/lec.h
+++ b/net/atm/lec.h
@@ -58,7 +58,7 @@ struct lane2_ops {
* field in h_type field. Data follows immediately after header.
* 2. LLC Data frames whose total length, including LLC field and data,
* but not padding required to meet the minimum data frame length,
- * is less than 1536(0x0600) MUST be encoded by placing that length
+ * is less than ETH_P_802_3_MIN MUST be encoded by placing that length
* in the h_type field. The LLC field follows header immediately.
* 3. LLC data frames longer than this maximum MUST be encoded by placing
* the value 0 in the h_type field.
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index 8d8afb134b3a..fa780b76630e 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -36,6 +36,20 @@ config BATMAN_ADV_DAT
mesh networks. If you think that your network does not need
this option you can safely remove it and save some space.
+config BATMAN_ADV_NC
+ bool "Network Coding"
+ depends on BATMAN_ADV
+ default n
+ help
+ This option enables network coding, a mechanism that aims to
+ increase the overall network throughput by fusing multiple
+ packets in one transmission.
+ Note that interfaces controlled by batman-adv must be manually
+ configured to have promiscuous mode enabled in order to make
+ network coding work.
+ If you think that your network does not need this feature you
+ can safely disable it and save some space.
+
config BATMAN_ADV_DEBUG
bool "B.A.T.M.A.N. debugging"
depends on BATMAN_ADV
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index e45e3b4e32e3..acbac2a9c62f 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -1,5 +1,5 @@
#
-# Copyright (C) 2007-2012 B.A.T.M.A.N. contributors:
+# Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
#
# Marek Lindner, Simon Wunderlich
#
@@ -30,6 +30,7 @@ batman-adv-y += hard-interface.o
batman-adv-y += hash.o
batman-adv-y += icmp_socket.o
batman-adv-y += main.o
+batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
batman-adv-y += originator.o
batman-adv-y += ring_buffer.o
batman-adv-y += routing.o
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index a5bb0a769eb9..071f288b77a8 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -27,6 +27,7 @@
#include "hard-interface.h"
#include "send.h"
#include "bat_algo.h"
+#include "network-coding.h"
static struct batadv_neigh_node *
batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
@@ -1185,6 +1186,10 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
if (!orig_neigh_node)
goto out;
+ /* Update nc_nodes of the originator */
+ batadv_nc_update_nc_node(bat_priv, orig_node, orig_neigh_node,
+ batadv_ogm_packet, is_single_hop_neigh);
+
orig_neigh_router = batadv_orig_node_get_router(orig_neigh_node);
/* drop packet if sender is not a direct neighbor and if we
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 6ae86516db4d..f186a55b23c3 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -32,6 +32,7 @@
#include "icmp_socket.h"
#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
+#include "network-coding.h"
static struct dentry *batadv_debugfs;
@@ -310,6 +311,14 @@ struct batadv_debuginfo {
const struct file_operations fops;
};
+#ifdef CONFIG_BATMAN_ADV_NC
+static int batadv_nc_nodes_open(struct inode *inode, struct file *file)
+{
+ struct net_device *net_dev = (struct net_device *)inode->i_private;
+ return single_open(file, batadv_nc_nodes_seq_print_text, net_dev);
+}
+#endif
+
#define BATADV_DEBUGINFO(_name, _mode, _open) \
struct batadv_debuginfo batadv_debuginfo_##_name = { \
.attr = { .name = __stringify(_name), \
@@ -348,6 +357,9 @@ static BATADV_DEBUGINFO(dat_cache, S_IRUGO, batadv_dat_cache_open);
static BATADV_DEBUGINFO(transtable_local, S_IRUGO,
batadv_transtable_local_open);
static BATADV_DEBUGINFO(vis_data, S_IRUGO, batadv_vis_data_open);
+#ifdef CONFIG_BATMAN_ADV_NC
+static BATADV_DEBUGINFO(nc_nodes, S_IRUGO, batadv_nc_nodes_open);
+#endif
static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
&batadv_debuginfo_originators,
@@ -362,6 +374,9 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
#endif
&batadv_debuginfo_transtable_local,
&batadv_debuginfo_vis_data,
+#ifdef CONFIG_BATMAN_ADV_NC
+ &batadv_debuginfo_nc_nodes,
+#endif
NULL,
};
@@ -431,6 +446,9 @@ int batadv_debugfs_add_meshif(struct net_device *dev)
}
}
+ if (batadv_nc_init_debugfs(bat_priv) < 0)
+ goto rem_attr;
+
return 0;
rem_attr:
debugfs_remove_recursive(bat_priv->debug_dir);
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index d54188a112ea..8e15d966d9b0 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -816,7 +816,6 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
bool ret = false;
struct batadv_dat_entry *dat_entry = NULL;
struct sk_buff *skb_new;
- struct batadv_hard_iface *primary_if = NULL;
if (!atomic_read(&bat_priv->distributed_arp_table))
goto out;
@@ -838,22 +837,18 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst);
if (dat_entry) {
- primary_if = batadv_primary_if_get_selected(bat_priv);
- if (!primary_if)
- goto out;
-
skb_new = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_src,
- primary_if->soft_iface, ip_dst, hw_src,
+ bat_priv->soft_iface, ip_dst, hw_src,
dat_entry->mac_addr, hw_src);
if (!skb_new)
goto out;
skb_reset_mac_header(skb_new);
skb_new->protocol = eth_type_trans(skb_new,
- primary_if->soft_iface);
+ bat_priv->soft_iface);
bat_priv->stats.rx_packets++;
bat_priv->stats.rx_bytes += skb->len + ETH_HLEN;
- primary_if->soft_iface->last_rx = jiffies;
+ bat_priv->soft_iface->last_rx = jiffies;
netif_rx(skb_new);
batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n");
@@ -866,8 +861,6 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
out:
if (dat_entry)
batadv_dat_entry_free_ref(dat_entry);
- if (primary_if)
- batadv_hardif_free_ref(primary_if);
return ret;
}
@@ -887,7 +880,6 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
__be32 ip_src, ip_dst;
uint8_t *hw_src;
struct sk_buff *skb_new;
- struct batadv_hard_iface *primary_if = NULL;
struct batadv_dat_entry *dat_entry = NULL;
bool ret = false;
int err;
@@ -912,12 +904,8 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
if (!dat_entry)
goto out;
- primary_if = batadv_primary_if_get_selected(bat_priv);
- if (!primary_if)
- goto out;
-
skb_new = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_src,
- primary_if->soft_iface, ip_dst, hw_src,
+ bat_priv->soft_iface, ip_dst, hw_src,
dat_entry->mac_addr, hw_src);
if (!skb_new)
@@ -941,8 +929,6 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
out:
if (dat_entry)
batadv_dat_entry_free_ref(dat_entry);
- if (primary_if)
- batadv_hardif_free_ref(primary_if);
if (ret)
kfree_skb(skb);
return ret;
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 34f99a46ec1d..f105219f4a4b 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -500,7 +500,7 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset)
rcu_read_unlock();
if (gw_count == 0)
- seq_printf(seq, "No gateways in range ...\n");
+ seq_puts(seq, "No gateways in range ...\n");
out:
if (primary_if)
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 368219e026a9..522243aff2f3 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -307,11 +307,35 @@ batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface)
batadv_update_min_mtu(hard_iface->soft_iface);
}
+/**
+ * batadv_master_del_slave - remove hard_iface from the current master interface
+ * @slave: the interface enslaved in another master
+ * @master: the master from which slave has to be removed
+ *
+ * Invoke ndo_del_slave on master passing slave as argument. In this way slave
+ * is free'd and master can correctly change its internal state.
+ * Return 0 on success, a negative value representing the error otherwise
+ */
+static int batadv_master_del_slave(struct batadv_hard_iface *slave,
+ struct net_device *master)
+{
+ int ret;
+
+ if (!master)
+ return 0;
+
+ ret = -EBUSY;
+ if (master->netdev_ops->ndo_del_slave)
+ ret = master->netdev_ops->ndo_del_slave(master, slave->net_dev);
+
+ return ret;
+}
+
int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
const char *iface_name)
{
struct batadv_priv *bat_priv;
- struct net_device *soft_iface;
+ struct net_device *soft_iface, *master;
__be16 ethertype = __constant_htons(ETH_P_BATMAN);
int ret;
@@ -321,11 +345,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
if (!atomic_inc_not_zero(&hard_iface->refcount))
goto out;
- /* hard-interface is part of a bridge */
- if (hard_iface->net_dev->priv_flags & IFF_BRIDGE_PORT)
- pr_err("You are about to enable batman-adv on '%s' which already is part of a bridge. Unless you know exactly what you are doing this is probably wrong and won't work the way you think it would.\n",
- hard_iface->net_dev->name);
-
soft_iface = dev_get_by_name(&init_net, iface_name);
if (!soft_iface) {
@@ -347,12 +366,24 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
goto err_dev;
}
+ /* check if the interface is enslaved in another virtual one and
+ * in that case unlink it first
+ */
+ master = netdev_master_upper_dev_get(hard_iface->net_dev);
+ ret = batadv_master_del_slave(hard_iface, master);
+ if (ret)
+ goto err_dev;
+
hard_iface->soft_iface = soft_iface;
bat_priv = netdev_priv(hard_iface->soft_iface);
+ ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface);
+ if (ret)
+ goto err_dev;
+
ret = bat_priv->bat_algo_ops->bat_iface_enable(hard_iface);
if (ret < 0)
- goto err_dev;
+ goto err_upper;
hard_iface->if_num = bat_priv->num_ifaces;
bat_priv->num_ifaces++;
@@ -362,7 +393,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
bat_priv->bat_algo_ops->bat_iface_disable(hard_iface);
bat_priv->num_ifaces--;
hard_iface->if_status = BATADV_IF_NOT_IN_USE;
- goto err_dev;
+ goto err_upper;
}
hard_iface->batman_adv_ptype.type = ethertype;
@@ -401,14 +432,18 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
out:
return 0;
+err_upper:
+ netdev_upper_dev_unlink(hard_iface->net_dev, soft_iface);
err_dev:
+ hard_iface->soft_iface = NULL;
dev_put(soft_iface);
err:
batadv_hardif_free_ref(hard_iface);
return ret;
}
-void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
+void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
+ enum batadv_hard_if_cleanup autodel)
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
struct batadv_hard_iface *primary_if = NULL;
@@ -446,9 +481,10 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
dev_put(hard_iface->soft_iface);
/* nobody uses this interface anymore */
- if (!bat_priv->num_ifaces)
- batadv_softif_destroy(hard_iface->soft_iface);
+ if (!bat_priv->num_ifaces && autodel == BATADV_IF_CLEANUP_AUTO)
+ batadv_softif_destroy_sysfs(hard_iface->soft_iface);
+ netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface);
hard_iface->soft_iface = NULL;
batadv_hardif_free_ref(hard_iface);
@@ -533,7 +569,8 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface)
/* first deactivate interface */
if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
- batadv_hardif_disable_interface(hard_iface);
+ batadv_hardif_disable_interface(hard_iface,
+ BATADV_IF_CLEANUP_AUTO);
if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
return;
@@ -563,6 +600,11 @@ static int batadv_hard_if_event(struct notifier_block *this,
struct batadv_hard_iface *primary_if = NULL;
struct batadv_priv *bat_priv;
+ if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) {
+ batadv_sysfs_add_meshif(net_dev);
+ return NOTIFY_DONE;
+ }
+
hard_iface = batadv_hardif_get_by_netdev(net_dev);
if (!hard_iface && event == NETDEV_REGISTER)
hard_iface = batadv_hardif_add_interface(net_dev);
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 308437d52e22..49892881a7c5 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -29,13 +29,24 @@ enum batadv_hard_if_state {
BATADV_IF_I_WANT_YOU,
};
+/**
+ * enum batadv_hard_if_cleanup - Cleanup modi for soft_iface after slave removal
+ * @BATADV_IF_CLEANUP_KEEP: Don't automatically delete soft-interface
+ * @BATADV_IF_CLEANUP_AUTO: Delete soft-interface after last slave was removed
+ */
+enum batadv_hard_if_cleanup {
+ BATADV_IF_CLEANUP_KEEP,
+ BATADV_IF_CLEANUP_AUTO,
+};
+
extern struct notifier_block batadv_hard_if_notifier;
struct batadv_hard_iface*
batadv_hardif_get_by_netdev(const struct net_device *net_dev);
int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
const char *iface_name);
-void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface);
+void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
+ enum batadv_hard_if_cleanup autodel);
void batadv_hardif_remove_interfaces(void);
int batadv_hardif_min_mtu(struct net_device *soft_iface);
void batadv_update_min_mtu(struct net_device *soft_iface);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 0488d70c8c35..6277735cd89e 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -35,6 +35,7 @@
#include "vis.h"
#include "hash.h"
#include "bat_algo.h"
+#include "network-coding.h"
/* List manipulations on hardif_list have to be rtnl_lock()'ed,
@@ -70,6 +71,7 @@ static int __init batadv_init(void)
batadv_debugfs_init();
register_netdevice_notifier(&batadv_hard_if_notifier);
+ rtnl_link_register(&batadv_link_ops);
pr_info("B.A.T.M.A.N. advanced %s (compatibility version %i) loaded\n",
BATADV_SOURCE_VERSION, BATADV_COMPAT_VERSION);
@@ -80,6 +82,7 @@ static int __init batadv_init(void)
static void __exit batadv_exit(void)
{
batadv_debugfs_destroy();
+ rtnl_link_unregister(&batadv_link_ops);
unregister_netdevice_notifier(&batadv_hard_if_notifier);
batadv_hardif_remove_interfaces();
@@ -135,6 +138,10 @@ int batadv_mesh_init(struct net_device *soft_iface)
if (ret < 0)
goto err;
+ ret = batadv_nc_init(bat_priv);
+ if (ret < 0)
+ goto err;
+
atomic_set(&bat_priv->gw.reselect, 0);
atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE);
@@ -157,6 +164,7 @@ void batadv_mesh_free(struct net_device *soft_iface)
batadv_gw_node_purge(bat_priv);
batadv_originator_free(bat_priv);
+ batadv_nc_free(bat_priv);
batadv_tt_free(bat_priv);
@@ -411,7 +419,7 @@ int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
{
struct batadv_algo_ops *bat_algo_ops;
- seq_printf(seq, "Available routing algorithms:\n");
+ seq_puts(seq, "Available routing algorithms:\n");
hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) {
seq_printf(seq, "%s\n", bat_algo_ops->name);
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index ced08b936a96..f90f5bc8e426 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -26,7 +26,7 @@
#define BATADV_DRIVER_DEVICE "batman-adv"
#ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2013.1.0"
+#define BATADV_SOURCE_VERSION "2013.2.0"
#endif
/* B.A.T.M.A.N. parameters */
@@ -105,6 +105,8 @@
#define BATADV_RESET_PROTECTION_MS 30000
#define BATADV_EXPECTED_SEQNO_RANGE 65536
+#define BATADV_NC_NODE_TIMEOUT 10000 /* Milliseconds */
+
enum batadv_mesh_state {
BATADV_MESH_INACTIVE,
BATADV_MESH_ACTIVE,
@@ -150,6 +152,7 @@ enum batadv_uev_type {
#include <linux/percpu.h>
#include <linux/slab.h>
#include <net/sock.h> /* struct sock */
+#include <net/rtnetlink.h>
#include <linux/jiffies.h>
#include <linux/seq_file.h>
#include "types.h"
@@ -185,6 +188,7 @@ __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr);
* @BATADV_DBG_TT: translation table messages
* @BATADV_DBG_BLA: bridge loop avoidance messages
* @BATADV_DBG_DAT: ARP snooping and DAT related messages
+ * @BATADV_DBG_NC: network coding related messages
* @BATADV_DBG_ALL: the union of all the above log levels
*/
enum batadv_dbg_level {
@@ -193,7 +197,8 @@ enum batadv_dbg_level {
BATADV_DBG_TT = BIT(2),
BATADV_DBG_BLA = BIT(3),
BATADV_DBG_DAT = BIT(4),
- BATADV_DBG_ALL = 31,
+ BATADV_DBG_NC = BIT(5),
+ BATADV_DBG_ALL = 63,
};
#ifdef CONFIG_BATMAN_ADV_DEBUG
@@ -298,4 +303,10 @@ static inline uint64_t batadv_sum_counter(struct batadv_priv *bat_priv,
return sum;
}
+/* Define a macro to reach the control buffer of the skb. The members of the
+ * control buffer are defined in struct batadv_skb_cb in types.h.
+ * The macro is inspired by the similar macro TCP_SKB_CB() in tcp.h.
+ */
+#define BATADV_SKB_CB(__skb) ((struct batadv_skb_cb *)&((__skb)->cb[0]))
+
#endif /* _NET_BATMAN_ADV_MAIN_H_ */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
new file mode 100644
index 000000000000..6b9a54485314
--- /dev/null
+++ b/net/batman-adv/network-coding.c
@@ -0,0 +1,1821 @@
+/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors:
+ *
+ * Martin Hundebøll, Jeppe Ledet-Pedersen
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/debugfs.h>
+
+#include "main.h"
+#include "hash.h"
+#include "network-coding.h"
+#include "send.h"
+#include "originator.h"
+#include "hard-interface.h"
+#include "routing.h"
+
+static struct lock_class_key batadv_nc_coding_hash_lock_class_key;
+static struct lock_class_key batadv_nc_decoding_hash_lock_class_key;
+
+static void batadv_nc_worker(struct work_struct *work);
+static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
+ struct batadv_hard_iface *recv_if);
+
+/**
+ * batadv_nc_start_timer - initialise the nc periodic worker
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+static void batadv_nc_start_timer(struct batadv_priv *bat_priv)
+{
+ queue_delayed_work(batadv_event_workqueue, &bat_priv->nc.work,
+ msecs_to_jiffies(10));
+}
+
+/**
+ * batadv_nc_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)
+{
+ bat_priv->nc.timestamp_fwd_flush = jiffies;
+ bat_priv->nc.timestamp_sniffed_purge = jiffies;
+
+ if (bat_priv->nc.coding_hash || bat_priv->nc.decoding_hash)
+ return 0;
+
+ bat_priv->nc.coding_hash = batadv_hash_new(128);
+ if (!bat_priv->nc.coding_hash)
+ goto err;
+
+ batadv_hash_set_lock_class(bat_priv->nc.coding_hash,
+ &batadv_nc_coding_hash_lock_class_key);
+
+ bat_priv->nc.decoding_hash = batadv_hash_new(128);
+ if (!bat_priv->nc.decoding_hash)
+ goto err;
+
+ 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);
+
+ return 0;
+
+err:
+ return -ENOMEM;
+}
+
+/**
+ * batadv_nc_init_bat_priv - initialise the nc specific bat_priv variables
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv)
+{
+ atomic_set(&bat_priv->network_coding, 1);
+ bat_priv->nc.min_tq = 200;
+ bat_priv->nc.max_fwd_delay = 10;
+ bat_priv->nc.max_buffer_time = 200;
+}
+
+/**
+ * batadv_nc_init_orig - initialise the nc fields of an orig_node
+ * @orig_node: the orig_node which is going to be initialised
+ */
+void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
+{
+ INIT_LIST_HEAD(&orig_node->in_coding_list);
+ INIT_LIST_HEAD(&orig_node->out_coding_list);
+ spin_lock_init(&orig_node->in_coding_list_lock);
+ spin_lock_init(&orig_node->out_coding_list_lock);
+}
+
+/**
+ * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove
+ * its refcount on the orig_node
+ * @rcu: rcu pointer of the nc node
+ */
+static void batadv_nc_node_free_rcu(struct rcu_head *rcu)
+{
+ struct batadv_nc_node *nc_node;
+
+ nc_node = container_of(rcu, struct batadv_nc_node, rcu);
+ batadv_orig_node_free_ref(nc_node->orig_node);
+ kfree(nc_node);
+}
+
+/**
+ * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly
+ * frees it
+ * @nc_node: the nc node to free
+ */
+static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node)
+{
+ if (atomic_dec_and_test(&nc_node->refcount))
+ call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu);
+}
+
+/**
+ * batadv_nc_path_free_ref - decrements the nc path refcounter and possibly
+ * frees it
+ * @nc_path: the nc node to free
+ */
+static void batadv_nc_path_free_ref(struct batadv_nc_path *nc_path)
+{
+ if (atomic_dec_and_test(&nc_path->refcount))
+ kfree_rcu(nc_path, rcu);
+}
+
+/**
+ * batadv_nc_packet_free - frees nc packet
+ * @nc_packet: the nc packet to free
+ */
+static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet)
+{
+ if (nc_packet->skb)
+ kfree_skb(nc_packet->skb);
+
+ batadv_nc_path_free_ref(nc_packet->nc_path);
+ kfree(nc_packet);
+}
+
+/**
+ * batadv_nc_to_purge_nc_node - checks whether an nc node has to be purged
+ * @bat_priv: the bat priv with all the soft interface information
+ * @nc_node: the nc node to check
+ *
+ * Returns true if the entry has to be purged now, false otherwise
+ */
+static bool batadv_nc_to_purge_nc_node(struct batadv_priv *bat_priv,
+ struct batadv_nc_node *nc_node)
+{
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
+ return true;
+
+ return batadv_has_timed_out(nc_node->last_seen, BATADV_NC_NODE_TIMEOUT);
+}
+
+/**
+ * batadv_nc_to_purge_nc_path_coding - checks whether an nc path has timed out
+ * @bat_priv: the bat priv with all the soft interface information
+ * @nc_path: the nc path to check
+ *
+ * Returns true if the entry has to be purged now, false otherwise
+ */
+static bool batadv_nc_to_purge_nc_path_coding(struct batadv_priv *bat_priv,
+ struct batadv_nc_path *nc_path)
+{
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
+ return true;
+
+ /* purge the path when no packets has been added for 10 times the
+ * max_fwd_delay time
+ */
+ return batadv_has_timed_out(nc_path->last_valid,
+ bat_priv->nc.max_fwd_delay * 10);
+}
+
+/**
+ * batadv_nc_to_purge_nc_path_decoding - checks whether an nc path has timed out
+ * @bat_priv: the bat priv with all the soft interface information
+ * @nc_path: the nc path to check
+ *
+ * Returns true if the entry has to be purged now, false otherwise
+ */
+static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv,
+ struct batadv_nc_path *nc_path)
+{
+ if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
+ return true;
+
+ /* purge the path when no packets has been added for 10 times the
+ * max_buffer time
+ */
+ return batadv_has_timed_out(nc_path->last_valid,
+ bat_priv->nc.max_buffer_time*10);
+}
+
+/**
+ * batadv_nc_purge_orig_nc_nodes - go through list of nc nodes and purge stale
+ * entries
+ * @bat_priv: the bat priv with all the soft interface information
+ * @list: list of nc nodes
+ * @lock: nc node list lock
+ * @to_purge: function in charge to decide whether an entry has to be purged or
+ * not. This function takes the nc node as argument and has to return
+ * a boolean value: true if the entry has to be deleted, false
+ * otherwise
+ */
+static void
+batadv_nc_purge_orig_nc_nodes(struct batadv_priv *bat_priv,
+ struct list_head *list,
+ spinlock_t *lock,
+ bool (*to_purge)(struct batadv_priv *,
+ struct batadv_nc_node *))
+{
+ struct batadv_nc_node *nc_node, *nc_node_tmp;
+
+ /* For each nc_node in list */
+ spin_lock_bh(lock);
+ list_for_each_entry_safe(nc_node, nc_node_tmp, list, list) {
+ /* if an helper function has been passed as parameter,
+ * ask it if the entry has to be purged or not
+ */
+ if (to_purge && !to_purge(bat_priv, nc_node))
+ continue;
+
+ batadv_dbg(BATADV_DBG_NC, bat_priv,
+ "Removing nc_node %pM -> %pM\n",
+ nc_node->addr, nc_node->orig_node->orig);
+ list_del_rcu(&nc_node->list);
+ batadv_nc_node_free_ref(nc_node);
+ }
+ spin_unlock_bh(lock);
+}
+
+/**
+ * batadv_nc_purge_orig - purges all nc node data attached of the given
+ * originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig_node with the nc node entries to be purged
+ * @to_purge: function in charge to decide whether an entry has to be purged or
+ * not. This function takes the nc node as argument and has to return
+ * a boolean value: true is the entry has to be deleted, false
+ * otherwise
+ */
+void batadv_nc_purge_orig(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ bool (*to_purge)(struct batadv_priv *,
+ struct batadv_nc_node *))
+{
+ /* Check ingoing nc_node's of this orig_node */
+ batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->in_coding_list,
+ &orig_node->in_coding_list_lock,
+ to_purge);
+
+ /* Check outgoing nc_node's of this orig_node */
+ batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->out_coding_list,
+ &orig_node->out_coding_list_lock,
+ to_purge);
+}
+
+/**
+ * batadv_nc_purge_orig_hash - traverse entire originator hash to check if they
+ * have timed out nc nodes
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv)
+{
+ struct batadv_hashtable *hash = bat_priv->orig_hash;
+ struct hlist_head *head;
+ struct batadv_orig_node *orig_node;
+ uint32_t i;
+
+ if (!hash)
+ return;
+
+ /* For each orig_node */
+ for (i = 0; i < hash->size; i++) {
+ head = &hash->table[i];
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(orig_node, head, hash_entry)
+ batadv_nc_purge_orig(bat_priv, orig_node,
+ batadv_nc_to_purge_nc_node);
+ rcu_read_unlock();
+ }
+}
+
+/**
+ * batadv_nc_purge_paths - traverse all nc paths part of the hash and remove
+ * unused ones
+ * @bat_priv: the bat priv with all the soft interface information
+ * @hash: hash table containing the nc paths to check
+ * @to_purge: function in charge to decide whether an entry has to be purged or
+ * not. This function takes the nc node as argument and has to return
+ * a boolean value: true is the entry has to be deleted, false
+ * otherwise
+ */
+static void batadv_nc_purge_paths(struct batadv_priv *bat_priv,
+ struct batadv_hashtable *hash,
+ bool (*to_purge)(struct batadv_priv *,
+ struct batadv_nc_path *))
+{
+ struct hlist_head *head;
+ struct hlist_node *node_tmp;
+ struct batadv_nc_path *nc_path;
+ spinlock_t *lock; /* Protects lists in hash */
+ uint32_t i;
+
+ for (i = 0; i < hash->size; i++) {
+ head = &hash->table[i];
+ lock = &hash->list_locks[i];
+
+ /* For each nc_path in this bin */
+ spin_lock_bh(lock);
+ hlist_for_each_entry_safe(nc_path, node_tmp, head, hash_entry) {
+ /* if an helper function has been passed as parameter,
+ * ask it if the entry has to be purged or not
+ */
+ if (to_purge && !to_purge(bat_priv, nc_path))
+ continue;
+
+ /* purging an non-empty nc_path should never happen, but
+ * is observed under high CPU load. Delay the purging
+ * until next iteration to allow the packet_list to be
+ * emptied first.
+ */
+ if (!unlikely(list_empty(&nc_path->packet_list))) {
+ net_ratelimited_function(printk,
+ KERN_WARNING
+ "Skipping free of non-empty nc_path (%pM -> %pM)!\n",
+ nc_path->prev_hop,
+ nc_path->next_hop);
+ continue;
+ }
+
+ /* nc_path is unused, so remove it */
+ batadv_dbg(BATADV_DBG_NC, bat_priv,
+ "Remove nc_path %pM -> %pM\n",
+ nc_path->prev_hop, nc_path->next_hop);
+ hlist_del_rcu(&nc_path->hash_entry);
+ batadv_nc_path_free_ref(nc_path);
+ }
+ spin_unlock_bh(lock);
+ }
+}
+
+/**
+ * batadv_nc_hash_key_gen - computes the nc_path hash key
+ * @key: buffer to hold the final hash key
+ * @src: source ethernet mac address going into the hash key
+ * @dst: destination ethernet mac address going into the hash key
+ */
+static void batadv_nc_hash_key_gen(struct batadv_nc_path *key, const char *src,
+ const char *dst)
+{
+ memcpy(key->prev_hop, src, sizeof(key->prev_hop));
+ memcpy(key->next_hop, dst, sizeof(key->next_hop));
+}
+
+/**
+ * batadv_nc_hash_choose - compute the hash value for an nc path
+ * @data: data to hash
+ * @size: size of the hash table
+ *
+ * Returns the selected index in the hash table for the given data.
+ */
+static uint32_t batadv_nc_hash_choose(const void *data, uint32_t size)
+{
+ const struct batadv_nc_path *nc_path = data;
+ uint32_t hash = 0;
+
+ hash = batadv_hash_bytes(hash, &nc_path->prev_hop,
+ sizeof(nc_path->prev_hop));
+ hash = batadv_hash_bytes(hash, &nc_path->next_hop,
+ sizeof(nc_path->next_hop));
+
+ hash += (hash << 3);
+ hash ^= (hash >> 11);
+ hash += (hash << 15);
+
+ return hash % size;
+}
+
+/**
+ * batadv_nc_hash_compare - comparing function used in the network coding hash
+ * tables
+ * @node: node in the local table
+ * @data2: second object to compare the node to
+ *
+ * Returns 1 if the two entry are the same, 0 otherwise
+ */
+static int batadv_nc_hash_compare(const struct hlist_node *node,
+ const void *data2)
+{
+ const struct batadv_nc_path *nc_path1, *nc_path2;
+
+ nc_path1 = container_of(node, struct batadv_nc_path, hash_entry);
+ nc_path2 = data2;
+
+ /* Return 1 if the two keys are identical */
+ if (memcmp(nc_path1->prev_hop, nc_path2->prev_hop,
+ sizeof(nc_path1->prev_hop)) != 0)
+ return 0;
+
+ if (memcmp(nc_path1->next_hop, nc_path2->next_hop,
+ sizeof(nc_path1->next_hop)) != 0)
+ return 0;
+
+ return 1;
+}
+
+/**
+ * batadv_nc_hash_find - search for an existing nc path and return it
+ * @hash: hash table containing the nc path
+ * @data: search key
+ *
+ * Returns the nc_path if found, NULL otherwise.
+ */
+static struct batadv_nc_path *
+batadv_nc_hash_find(struct batadv_hashtable *hash,
+ void *data)
+{
+ struct hlist_head *head;
+ struct batadv_nc_path *nc_path, *nc_path_tmp = NULL;
+ int index;
+
+ if (!hash)
+ return NULL;
+
+ index = batadv_nc_hash_choose(data, hash->size);
+ head = &hash->table[index];
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(nc_path, head, hash_entry) {
+ if (!batadv_nc_hash_compare(&nc_path->hash_entry, data))
+ continue;
+
+ if (!atomic_inc_not_zero(&nc_path->refcount))
+ continue;
+
+ nc_path_tmp = nc_path;
+ break;
+ }
+ rcu_read_unlock();
+
+ return nc_path_tmp;
+}
+
+/**
+ * batadv_nc_send_packet - send non-coded packet and free nc_packet struct
+ * @nc_packet: the nc packet to send
+ */
+static void batadv_nc_send_packet(struct batadv_nc_packet *nc_packet)
+{
+ batadv_send_skb_packet(nc_packet->skb,
+ nc_packet->neigh_node->if_incoming,
+ nc_packet->nc_path->next_hop);
+ nc_packet->skb = NULL;
+ batadv_nc_packet_free(nc_packet);
+}
+
+/**
+ * batadv_nc_sniffed_purge - Checks timestamp of given sniffed nc_packet.
+ * @bat_priv: the bat priv with all the soft interface information
+ * @nc_path: the nc path the packet belongs to
+ * @nc_packet: the nc packet to be checked
+ *
+ * Checks whether the given sniffed (overheard) nc_packet has hit its buffering
+ * timeout. If so, the packet is no longer kept and the entry deleted from the
+ * queue. Has to be called with the appropriate locks.
+ *
+ * Returns false as soon as the entry in the fifo queue has not been timed out
+ * yet and true otherwise.
+ */
+static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv,
+ struct batadv_nc_path *nc_path,
+ struct batadv_nc_packet *nc_packet)
+{
+ unsigned long timeout = bat_priv->nc.max_buffer_time;
+ bool res = false;
+
+ /* Packets are added to tail, so the remaining packets did not time
+ * out and we can stop processing the current queue
+ */
+ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE &&
+ !batadv_has_timed_out(nc_packet->timestamp, timeout))
+ goto out;
+
+ /* purge nc packet */
+ list_del(&nc_packet->list);
+ batadv_nc_packet_free(nc_packet);
+
+ res = true;
+
+out:
+ return res;
+}
+
+/**
+ * batadv_nc_fwd_flush - Checks the timestamp of the given nc packet.
+ * @bat_priv: the bat priv with all the soft interface information
+ * @nc_path: the nc path the packet belongs to
+ * @nc_packet: the nc packet to be checked
+ *
+ * Checks whether the given nc packet has hit its forward timeout. If so, the
+ * packet is no longer delayed, immediately sent and the entry deleted from the
+ * queue. Has to be called with the appropriate locks.
+ *
+ * Returns false as soon as the entry in the fifo queue has not been timed out
+ * yet and true otherwise.
+ */
+static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv,
+ struct batadv_nc_path *nc_path,
+ struct batadv_nc_packet *nc_packet)
+{
+ unsigned long timeout = bat_priv->nc.max_fwd_delay;
+
+ /* Packets are added to tail, so the remaining packets did not time
+ * out and we can stop processing the current queue
+ */
+ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE &&
+ !batadv_has_timed_out(nc_packet->timestamp, timeout))
+ return false;
+
+ /* Send packet */
+ batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD);
+ batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES,
+ nc_packet->skb->len + ETH_HLEN);
+ list_del(&nc_packet->list);
+ batadv_nc_send_packet(nc_packet);
+
+ return true;
+}
+
+/**
+ * batadv_nc_process_nc_paths - traverse given nc packet pool and free timed out
+ * nc packets
+ * @bat_priv: the bat priv with all the soft interface information
+ * @hash: to be processed hash table
+ * @process_fn: Function called to process given nc packet. Should return true
+ * to encourage this function to proceed with the next packet.
+ * Otherwise the rest of the current queue is skipped.
+ */
+static void
+batadv_nc_process_nc_paths(struct batadv_priv *bat_priv,
+ struct batadv_hashtable *hash,
+ bool (*process_fn)(struct batadv_priv *,
+ struct batadv_nc_path *,
+ struct batadv_nc_packet *))
+{
+ struct hlist_head *head;
+ struct batadv_nc_packet *nc_packet, *nc_packet_tmp;
+ struct batadv_nc_path *nc_path;
+ bool ret;
+ int i;
+
+ if (!hash)
+ return;
+
+ /* Loop hash table bins */
+ for (i = 0; i < hash->size; i++) {
+ head = &hash->table[i];
+
+ /* Loop coding paths */
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(nc_path, head, hash_entry) {
+ /* Loop packets */
+ spin_lock_bh(&nc_path->packet_list_lock);
+ list_for_each_entry_safe(nc_packet, nc_packet_tmp,
+ &nc_path->packet_list, list) {
+ ret = process_fn(bat_priv, nc_path, nc_packet);
+ if (!ret)
+ break;
+ }
+ spin_unlock_bh(&nc_path->packet_list_lock);
+ }
+ rcu_read_unlock();
+ }
+}
+
+/**
+ * batadv_nc_worker - periodic task for house keeping related to network coding
+ * @work: kernel work struct
+ */
+static void batadv_nc_worker(struct work_struct *work)
+{
+ struct delayed_work *delayed_work;
+ struct batadv_priv_nc *priv_nc;
+ struct batadv_priv *bat_priv;
+ unsigned long timeout;
+
+ delayed_work = container_of(work, struct delayed_work, work);
+ priv_nc = container_of(delayed_work, struct batadv_priv_nc, work);
+ bat_priv = container_of(priv_nc, struct batadv_priv, nc);
+
+ batadv_nc_purge_orig_hash(bat_priv);
+ batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash,
+ batadv_nc_to_purge_nc_path_coding);
+ batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash,
+ batadv_nc_to_purge_nc_path_decoding);
+
+ timeout = bat_priv->nc.max_fwd_delay;
+
+ if (batadv_has_timed_out(bat_priv->nc.timestamp_fwd_flush, timeout)) {
+ batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.coding_hash,
+ batadv_nc_fwd_flush);
+ bat_priv->nc.timestamp_fwd_flush = jiffies;
+ }
+
+ if (batadv_has_timed_out(bat_priv->nc.timestamp_sniffed_purge,
+ bat_priv->nc.max_buffer_time)) {
+ batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.decoding_hash,
+ batadv_nc_sniffed_purge);
+ bat_priv->nc.timestamp_sniffed_purge = jiffies;
+ }
+
+ /* Schedule a new check */
+ batadv_nc_start_timer(bat_priv);
+}
+
+/**
+ * batadv_can_nc_with_orig - checks whether the given orig node is suitable for
+ * coding or not
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: neighboring orig node which may be used as nc candidate
+ * @ogm_packet: incoming ogm packet also used for the checks
+ *
+ * Returns true if:
+ * 1) The OGM must have the most recent sequence number.
+ * 2) The TTL must be decremented by one and only one.
+ * 3) The OGM must be received from the first hop from orig_node.
+ * 4) The TQ value of the OGM must be above bat_priv->nc.min_tq.
+ */
+static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ struct batadv_ogm_packet *ogm_packet)
+{
+ if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno))
+ return false;
+ if (orig_node->last_ttl != ogm_packet->header.ttl + 1)
+ return false;
+ if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender))
+ return false;
+ if (ogm_packet->tq < bat_priv->nc.min_tq)
+ return false;
+
+ return true;
+}
+
+/**
+ * batadv_nc_find_nc_node - search for an existing nc node and return it
+ * @orig_node: orig node originating the ogm packet
+ * @orig_neigh_node: neighboring orig node from which we received the ogm packet
+ * (can be equal to orig_node)
+ * @in_coding: traverse incoming or outgoing network coding list
+ *
+ * Returns the nc_node if found, NULL otherwise.
+ */
+static struct batadv_nc_node
+*batadv_nc_find_nc_node(struct batadv_orig_node *orig_node,
+ struct batadv_orig_node *orig_neigh_node,
+ bool in_coding)
+{
+ struct batadv_nc_node *nc_node, *nc_node_out = NULL;
+ struct list_head *list;
+
+ if (in_coding)
+ list = &orig_neigh_node->in_coding_list;
+ else
+ list = &orig_neigh_node->out_coding_list;
+
+ /* Traverse list of nc_nodes to orig_node */
+ rcu_read_lock();
+ list_for_each_entry_rcu(nc_node, list, list) {
+ if (!batadv_compare_eth(nc_node->addr, orig_node->orig))
+ continue;
+
+ if (!atomic_inc_not_zero(&nc_node->refcount))
+ continue;
+
+ /* Found a match */
+ nc_node_out = nc_node;
+ break;
+ }
+ rcu_read_unlock();
+
+ return nc_node_out;
+}
+
+/**
+ * batadv_nc_get_nc_node - retrieves an nc node or creates the entry if it was
+ * not found
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node originating the ogm packet
+ * @orig_neigh_node: neighboring orig node from which we received the ogm packet
+ * (can be equal to orig_node)
+ * @in_coding: traverse incoming or outgoing network coding list
+ *
+ * Returns the nc_node if found or created, NULL in case of an error.
+ */
+static struct batadv_nc_node
+*batadv_nc_get_nc_node(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ struct batadv_orig_node *orig_neigh_node,
+ bool in_coding)
+{
+ struct batadv_nc_node *nc_node;
+ spinlock_t *lock; /* Used to lock list selected by "int in_coding" */
+ struct list_head *list;
+
+ /* Check if nc_node is already added */
+ nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding);
+
+ /* Node found */
+ if (nc_node)
+ return nc_node;
+
+ nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC);
+ if (!nc_node)
+ return NULL;
+
+ if (!atomic_inc_not_zero(&orig_neigh_node->refcount))
+ goto free;
+
+ /* Initialize nc_node */
+ INIT_LIST_HEAD(&nc_node->list);
+ memcpy(nc_node->addr, orig_node->orig, ETH_ALEN);
+ nc_node->orig_node = orig_neigh_node;
+ atomic_set(&nc_node->refcount, 2);
+
+ /* Select ingoing or outgoing coding node */
+ if (in_coding) {
+ lock = &orig_neigh_node->in_coding_list_lock;
+ list = &orig_neigh_node->in_coding_list;
+ } else {
+ lock = &orig_neigh_node->out_coding_list_lock;
+ list = &orig_neigh_node->out_coding_list;
+ }
+
+ batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n",
+ nc_node->addr, nc_node->orig_node->orig);
+
+ /* Add nc_node to orig_node */
+ spin_lock_bh(lock);
+ list_add_tail_rcu(&nc_node->list, list);
+ spin_unlock_bh(lock);
+
+ return nc_node;
+
+free:
+ kfree(nc_node);
+ return NULL;
+}
+
+/**
+ * batadv_nc_update_nc_node - updates stored incoming and outgoing nc node structs
+ * (best called on incoming OGMs)
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node originating the ogm packet
+ * @orig_neigh_node: neighboring orig node from which we received the ogm packet
+ * (can be equal to orig_node)
+ * @ogm_packet: incoming ogm packet
+ * @is_single_hop_neigh: orig_node is a single hop neighbor
+ */
+void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ struct batadv_orig_node *orig_neigh_node,
+ struct batadv_ogm_packet *ogm_packet,
+ int is_single_hop_neigh)
+{
+ struct batadv_nc_node *in_nc_node = NULL, *out_nc_node = NULL;
+
+ /* Check if network coding is enabled */
+ if (!atomic_read(&bat_priv->network_coding))
+ goto out;
+
+ /* accept ogms from 'good' neighbors and single hop neighbors */
+ if (!batadv_can_nc_with_orig(bat_priv, orig_node, ogm_packet) &&
+ !is_single_hop_neigh)
+ goto out;
+
+ /* Add orig_node as in_nc_node on hop */
+ in_nc_node = batadv_nc_get_nc_node(bat_priv, orig_node,
+ orig_neigh_node, true);
+ if (!in_nc_node)
+ goto out;
+
+ in_nc_node->last_seen = jiffies;
+
+ /* Add hop as out_nc_node on orig_node */
+ out_nc_node = batadv_nc_get_nc_node(bat_priv, orig_neigh_node,
+ orig_node, false);
+ if (!out_nc_node)
+ goto out;
+
+ out_nc_node->last_seen = jiffies;
+
+out:
+ if (in_nc_node)
+ batadv_nc_node_free_ref(in_nc_node);
+ if (out_nc_node)
+ batadv_nc_node_free_ref(out_nc_node);
+}
+
+/**
+ * batadv_nc_get_path - get existing nc_path or allocate a new one
+ * @bat_priv: the bat priv with all the soft interface information
+ * @hash: hash table containing the nc path
+ * @src: ethernet source address - first half of the nc path search key
+ * @dst: ethernet destination address - second half of the nc path search key
+ *
+ * Returns pointer to nc_path if the path was found or created, returns NULL
+ * on error.
+ */
+static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv,
+ struct batadv_hashtable *hash,
+ uint8_t *src,
+ uint8_t *dst)
+{
+ int hash_added;
+ struct batadv_nc_path *nc_path, nc_path_key;
+
+ batadv_nc_hash_key_gen(&nc_path_key, src, dst);
+
+ /* Search for existing nc_path */
+ nc_path = batadv_nc_hash_find(hash, (void *)&nc_path_key);
+
+ if (nc_path) {
+ /* Set timestamp to delay removal of nc_path */
+ nc_path->last_valid = jiffies;
+ return nc_path;
+ }
+
+ /* No existing nc_path was found; create a new */
+ nc_path = kzalloc(sizeof(*nc_path), GFP_ATOMIC);
+
+ if (!nc_path)
+ return NULL;
+
+ /* Initialize nc_path */
+ INIT_LIST_HEAD(&nc_path->packet_list);
+ spin_lock_init(&nc_path->packet_list_lock);
+ atomic_set(&nc_path->refcount, 2);
+ nc_path->last_valid = jiffies;
+ memcpy(nc_path->next_hop, dst, ETH_ALEN);
+ memcpy(nc_path->prev_hop, src, ETH_ALEN);
+
+ batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n",
+ nc_path->prev_hop,
+ nc_path->next_hop);
+
+ /* Add nc_path to hash table */
+ hash_added = batadv_hash_add(hash, batadv_nc_hash_compare,
+ batadv_nc_hash_choose, &nc_path_key,
+ &nc_path->hash_entry);
+
+ if (hash_added < 0) {
+ kfree(nc_path);
+ return NULL;
+ }
+
+ return nc_path;
+}
+
+/**
+ * batadv_nc_random_weight_tq - scale the receivers TQ-value to avoid unfair
+ * selection of a receiver with slightly lower TQ than the other
+ * @tq: to be weighted tq value
+ */
+static uint8_t batadv_nc_random_weight_tq(uint8_t tq)
+{
+ uint8_t rand_val, rand_tq;
+
+ get_random_bytes(&rand_val, sizeof(rand_val));
+
+ /* randomize the estimated packet loss (max TQ - estimated TQ) */
+ rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq);
+
+ /* normalize the randomized packet loss */
+ rand_tq /= BATADV_TQ_MAX_VALUE;
+
+ /* convert to (randomized) estimated tq again */
+ return BATADV_TQ_MAX_VALUE - rand_tq;
+}
+
+/**
+ * batadv_nc_memxor - XOR destination with source
+ * @dst: byte array to XOR into
+ * @src: byte array to XOR from
+ * @len: length of destination array
+ */
+static void batadv_nc_memxor(char *dst, const char *src, unsigned int len)
+{
+ unsigned int i;
+
+ for (i = 0; i < len; ++i)
+ dst[i] ^= src[i];
+}
+
+/**
+ * batadv_nc_code_packets - code a received unicast_packet with an nc packet
+ * into a coded_packet and send it
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: data skb to forward
+ * @ethhdr: pointer to the ethernet header inside the skb
+ * @nc_packet: structure containing the packet to the skb can be coded with
+ * @neigh_node: next hop to forward packet to
+ *
+ * Returns true if both packets are consumed, false otherwise.
+ */
+static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
+ struct sk_buff *skb,
+ struct ethhdr *ethhdr,
+ struct batadv_nc_packet *nc_packet,
+ struct batadv_neigh_node *neigh_node)
+{
+ uint8_t tq_weighted_neigh, tq_weighted_coding;
+ struct sk_buff *skb_dest, *skb_src;
+ struct batadv_unicast_packet *packet1;
+ struct batadv_unicast_packet *packet2;
+ struct batadv_coded_packet *coded_packet;
+ struct batadv_neigh_node *neigh_tmp, *router_neigh;
+ struct batadv_neigh_node *router_coding = NULL;
+ uint8_t *first_source, *first_dest, *second_source, *second_dest;
+ __be32 packet_id1, packet_id2;
+ size_t count;
+ bool res = false;
+ int coding_len;
+ int unicast_size = sizeof(*packet1);
+ int coded_size = sizeof(*coded_packet);
+ int header_add = coded_size - unicast_size;
+
+ router_neigh = batadv_orig_node_get_router(neigh_node->orig_node);
+ if (!router_neigh)
+ goto out;
+
+ neigh_tmp = nc_packet->neigh_node;
+ router_coding = batadv_orig_node_get_router(neigh_tmp->orig_node);
+ if (!router_coding)
+ goto out;
+
+ tq_weighted_neigh = batadv_nc_random_weight_tq(router_neigh->tq_avg);
+ tq_weighted_coding = batadv_nc_random_weight_tq(router_coding->tq_avg);
+
+ /* Select one destination for the MAC-header dst-field based on
+ * weighted TQ-values.
+ */
+ if (tq_weighted_neigh >= tq_weighted_coding) {
+ /* Destination from nc_packet is selected for MAC-header */
+ first_dest = nc_packet->nc_path->next_hop;
+ first_source = nc_packet->nc_path->prev_hop;
+ second_dest = neigh_node->addr;
+ second_source = ethhdr->h_source;
+ packet1 = (struct batadv_unicast_packet *)nc_packet->skb->data;
+ packet2 = (struct batadv_unicast_packet *)skb->data;
+ packet_id1 = nc_packet->packet_id;
+ packet_id2 = batadv_skb_crc32(skb,
+ skb->data + sizeof(*packet2));
+ } else {
+ /* Destination for skb is selected for MAC-header */
+ first_dest = neigh_node->addr;
+ first_source = ethhdr->h_source;
+ second_dest = nc_packet->nc_path->next_hop;
+ second_source = nc_packet->nc_path->prev_hop;
+ packet1 = (struct batadv_unicast_packet *)skb->data;
+ packet2 = (struct batadv_unicast_packet *)nc_packet->skb->data;
+ packet_id1 = batadv_skb_crc32(skb,
+ skb->data + sizeof(*packet1));
+ packet_id2 = nc_packet->packet_id;
+ }
+
+ /* Instead of zero padding the smallest data buffer, we
+ * code into the largest.
+ */
+ if (skb->len <= nc_packet->skb->len) {
+ skb_dest = nc_packet->skb;
+ skb_src = skb;
+ } else {
+ skb_dest = skb;
+ skb_src = nc_packet->skb;
+ }
+
+ /* coding_len is used when decoding the packet shorter packet */
+ coding_len = skb_src->len - unicast_size;
+
+ if (skb_linearize(skb_dest) < 0 || skb_linearize(skb_src) < 0)
+ goto out;
+
+ skb_push(skb_dest, header_add);
+
+ coded_packet = (struct batadv_coded_packet *)skb_dest->data;
+ skb_reset_mac_header(skb_dest);
+
+ coded_packet->header.packet_type = BATADV_CODED;
+ coded_packet->header.version = BATADV_COMPAT_VERSION;
+ coded_packet->header.ttl = packet1->header.ttl;
+
+ /* Info about first unicast packet */
+ memcpy(coded_packet->first_source, first_source, ETH_ALEN);
+ memcpy(coded_packet->first_orig_dest, packet1->dest, ETH_ALEN);
+ coded_packet->first_crc = packet_id1;
+ coded_packet->first_ttvn = packet1->ttvn;
+
+ /* Info about second unicast packet */
+ memcpy(coded_packet->second_dest, second_dest, ETH_ALEN);
+ memcpy(coded_packet->second_source, second_source, ETH_ALEN);
+ memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN);
+ coded_packet->second_crc = packet_id2;
+ coded_packet->second_ttl = packet2->header.ttl;
+ coded_packet->second_ttvn = packet2->ttvn;
+ coded_packet->coded_len = htons(coding_len);
+
+ /* This is where the magic happens: Code skb_src into skb_dest */
+ batadv_nc_memxor(skb_dest->data + coded_size,
+ skb_src->data + unicast_size, coding_len);
+
+ /* Update counters accordingly */
+ if (BATADV_SKB_CB(skb_src)->decoded &&
+ BATADV_SKB_CB(skb_dest)->decoded) {
+ /* Both packets are recoded */
+ count = skb_src->len + ETH_HLEN;
+ count += skb_dest->len + ETH_HLEN;
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE, 2);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, count);
+ } else if (!BATADV_SKB_CB(skb_src)->decoded &&
+ !BATADV_SKB_CB(skb_dest)->decoded) {
+ /* Both packets are newly coded */
+ count = skb_src->len + ETH_HLEN;
+ count += skb_dest->len + ETH_HLEN;
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE, 2);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, count);
+ } else if (BATADV_SKB_CB(skb_src)->decoded &&
+ !BATADV_SKB_CB(skb_dest)->decoded) {
+ /* skb_src recoded and skb_dest is newly coded */
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES,
+ skb_src->len + ETH_HLEN);
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES,
+ skb_dest->len + ETH_HLEN);
+ } else if (!BATADV_SKB_CB(skb_src)->decoded &&
+ BATADV_SKB_CB(skb_dest)->decoded) {
+ /* skb_src is newly coded and skb_dest is recoded */
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES,
+ skb_src->len + ETH_HLEN);
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES,
+ skb_dest->len + ETH_HLEN);
+ }
+
+ /* skb_src is now coded into skb_dest, so free it */
+ kfree_skb(skb_src);
+
+ /* avoid duplicate free of skb from nc_packet */
+ nc_packet->skb = NULL;
+ batadv_nc_packet_free(nc_packet);
+
+ /* Send the coded packet and return true */
+ batadv_send_skb_packet(skb_dest, neigh_node->if_incoming, first_dest);
+ res = true;
+out:
+ if (router_neigh)
+ batadv_neigh_node_free_ref(router_neigh);
+ if (router_coding)
+ batadv_neigh_node_free_ref(router_coding);
+ return res;
+}
+
+/**
+ * batadv_nc_skb_coding_possible - true if a decoded skb is available at dst.
+ * @skb: data skb to forward
+ * @dst: destination mac address of the other skb to code with
+ * @src: source mac address of skb
+ *
+ * Whenever we network code a packet we have to check whether we received it in
+ * a network coded form. If so, we may not be able to use it for coding because
+ * some neighbors may also have received (overheard) the packet in the network
+ * coded form without being able to decode it. It is hard to know which of the
+ * neighboring nodes was able to decode the packet, therefore we can only
+ * re-code the packet if the source of the previous encoded packet is involved.
+ * Since the source encoded the packet we can be certain it has all necessary
+ * decode information.
+ *
+ * Returns true if coding of a decoded packet is allowed.
+ */
+static bool batadv_nc_skb_coding_possible(struct sk_buff *skb,
+ uint8_t *dst, uint8_t *src)
+{
+ if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src))
+ return false;
+ else
+ return true;
+}
+
+/**
+ * batadv_nc_path_search - Find the coding path matching in_nc_node and
+ * out_nc_node to retrieve a buffered packet that can be used for coding.
+ * @bat_priv: the bat priv with all the soft interface information
+ * @in_nc_node: pointer to skb next hop's neighbor nc node
+ * @out_nc_node: pointer to skb source's neighbor nc node
+ * @skb: data skb to forward
+ * @eth_dst: next hop mac address of skb
+ *
+ * Returns true if coding of a decoded skb is allowed.
+ */
+static struct batadv_nc_packet *
+batadv_nc_path_search(struct batadv_priv *bat_priv,
+ struct batadv_nc_node *in_nc_node,
+ struct batadv_nc_node *out_nc_node,
+ struct sk_buff *skb,
+ uint8_t *eth_dst)
+{
+ struct batadv_nc_path *nc_path, nc_path_key;
+ struct batadv_nc_packet *nc_packet_out = NULL;
+ struct batadv_nc_packet *nc_packet, *nc_packet_tmp;
+ struct batadv_hashtable *hash = bat_priv->nc.coding_hash;
+ int idx;
+
+ if (!hash)
+ return NULL;
+
+ /* Create almost path key */
+ batadv_nc_hash_key_gen(&nc_path_key, in_nc_node->addr,
+ out_nc_node->addr);
+ idx = batadv_nc_hash_choose(&nc_path_key, hash->size);
+
+ /* Check for coding opportunities in this nc_path */
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(nc_path, &hash->table[idx], hash_entry) {
+ if (!batadv_compare_eth(nc_path->prev_hop, in_nc_node->addr))
+ continue;
+
+ if (!batadv_compare_eth(nc_path->next_hop, out_nc_node->addr))
+ continue;
+
+ spin_lock_bh(&nc_path->packet_list_lock);
+ if (list_empty(&nc_path->packet_list)) {
+ spin_unlock_bh(&nc_path->packet_list_lock);
+ continue;
+ }
+
+ list_for_each_entry_safe(nc_packet, nc_packet_tmp,
+ &nc_path->packet_list, list) {
+ if (!batadv_nc_skb_coding_possible(nc_packet->skb,
+ eth_dst,
+ in_nc_node->addr))
+ continue;
+
+ /* Coding opportunity is found! */
+ list_del(&nc_packet->list);
+ nc_packet_out = nc_packet;
+ break;
+ }
+
+ spin_unlock_bh(&nc_path->packet_list_lock);
+ break;
+ }
+ rcu_read_unlock();
+
+ return nc_packet_out;
+}
+
+/**
+ * batadv_nc_skb_src_search - Loops through the list of neighoring nodes of the
+ * skb's sender (may be equal to the originator).
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: data skb to forward
+ * @eth_dst: next hop mac address of skb
+ * @eth_src: source mac address of skb
+ * @in_nc_node: pointer to skb next hop's neighbor nc node
+ *
+ * Returns an nc packet if a suitable coding packet was found, NULL otherwise.
+ */
+static struct batadv_nc_packet *
+batadv_nc_skb_src_search(struct batadv_priv *bat_priv,
+ struct sk_buff *skb,
+ uint8_t *eth_dst,
+ uint8_t *eth_src,
+ struct batadv_nc_node *in_nc_node)
+{
+ struct batadv_orig_node *orig_node;
+ struct batadv_nc_node *out_nc_node;
+ struct batadv_nc_packet *nc_packet = NULL;
+
+ orig_node = batadv_orig_hash_find(bat_priv, eth_src);
+ if (!orig_node)
+ return NULL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(out_nc_node,
+ &orig_node->out_coding_list, list) {
+ /* Check if the skb is decoded and if recoding is possible */
+ if (!batadv_nc_skb_coding_possible(skb,
+ out_nc_node->addr, eth_src))
+ continue;
+
+ /* Search for an opportunity in this nc_path */
+ nc_packet = batadv_nc_path_search(bat_priv, in_nc_node,
+ out_nc_node, skb, eth_dst);
+ if (nc_packet)
+ break;
+ }
+ rcu_read_unlock();
+
+ batadv_orig_node_free_ref(orig_node);
+ return nc_packet;
+}
+
+/**
+ * batadv_nc_skb_store_before_coding - set the ethernet src and dst of the
+ * unicast skb before it is stored for use in later decoding
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: data skb to store
+ * @eth_dst_new: new destination mac address of skb
+ */
+static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv,
+ struct sk_buff *skb,
+ uint8_t *eth_dst_new)
+{
+ struct ethhdr *ethhdr;
+
+ /* Copy skb header to change the mac header */
+ skb = pskb_copy(skb, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ /* Set the mac header as if we actually sent the packet uncoded */
+ ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN);
+ memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN);
+
+ /* Set data pointer to MAC header to mimic packets from our tx path */
+ skb_push(skb, ETH_HLEN);
+
+ /* Add the packet to the decoding packet pool */
+ batadv_nc_skb_store_for_decoding(bat_priv, skb);
+
+ /* batadv_nc_skb_store_for_decoding() clones the skb, so we must free
+ * our ref
+ */
+ kfree_skb(skb);
+}
+
+/**
+ * batadv_nc_skb_dst_search - Loops through list of neighboring nodes to dst.
+ * @skb: data skb to forward
+ * @neigh_node: next hop to forward packet to
+ * @ethhdr: pointer to the ethernet header inside the skb
+ *
+ * Loops through list of neighboring nodes the next hop has a good connection to
+ * (receives OGMs with a sufficient quality). We need to find a neighbor of our
+ * next hop that potentially sent a packet which our next hop also received
+ * (overheard) and has stored for later decoding.
+ *
+ * Returns true if the skb was consumed (encoded packet sent) or false otherwise
+ */
+static bool batadv_nc_skb_dst_search(struct sk_buff *skb,
+ struct batadv_neigh_node *neigh_node,
+ struct ethhdr *ethhdr)
+{
+ struct net_device *netdev = neigh_node->if_incoming->soft_iface;
+ struct batadv_priv *bat_priv = netdev_priv(netdev);
+ struct batadv_orig_node *orig_node = neigh_node->orig_node;
+ struct batadv_nc_node *nc_node;
+ struct batadv_nc_packet *nc_packet = NULL;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(nc_node, &orig_node->in_coding_list, list) {
+ /* Search for coding opportunity with this in_nc_node */
+ nc_packet = batadv_nc_skb_src_search(bat_priv, skb,
+ neigh_node->addr,
+ ethhdr->h_source, nc_node);
+
+ /* Opportunity was found, so stop searching */
+ if (nc_packet)
+ break;
+ }
+ rcu_read_unlock();
+
+ if (!nc_packet)
+ return false;
+
+ /* Save packets for later decoding */
+ batadv_nc_skb_store_before_coding(bat_priv, skb,
+ neigh_node->addr);
+ batadv_nc_skb_store_before_coding(bat_priv, nc_packet->skb,
+ nc_packet->neigh_node->addr);
+
+ /* Code and send packets */
+ if (batadv_nc_code_packets(bat_priv, skb, ethhdr, nc_packet,
+ neigh_node))
+ return true;
+
+ /* out of mem ? Coding failed - we have to free the buffered packet
+ * to avoid memleaks. The skb passed as argument will be dealt with
+ * by the calling function.
+ */
+ batadv_nc_send_packet(nc_packet);
+ return false;
+}
+
+/**
+ * batadv_nc_skb_add_to_path - buffer skb for later encoding / decoding
+ * @skb: skb to add to path
+ * @nc_path: path to add skb to
+ * @neigh_node: next hop to forward packet to
+ * @packet_id: checksum to identify packet
+ *
+ * Returns true if the packet was buffered or false in case of an error.
+ */
+static bool batadv_nc_skb_add_to_path(struct sk_buff *skb,
+ struct batadv_nc_path *nc_path,
+ struct batadv_neigh_node *neigh_node,
+ __be32 packet_id)
+{
+ struct batadv_nc_packet *nc_packet;
+
+ nc_packet = kzalloc(sizeof(*nc_packet), GFP_ATOMIC);
+ if (!nc_packet)
+ return false;
+
+ /* Initialize nc_packet */
+ nc_packet->timestamp = jiffies;
+ nc_packet->packet_id = packet_id;
+ nc_packet->skb = skb;
+ nc_packet->neigh_node = neigh_node;
+ nc_packet->nc_path = nc_path;
+
+ /* Add coding packet to list */
+ spin_lock_bh(&nc_path->packet_list_lock);
+ list_add_tail(&nc_packet->list, &nc_path->packet_list);
+ spin_unlock_bh(&nc_path->packet_list_lock);
+
+ return true;
+}
+
+/**
+ * batadv_nc_skb_forward - try to code a packet or add it to the coding packet
+ * buffer
+ * @skb: data skb to forward
+ * @neigh_node: next hop to forward packet to
+ * @ethhdr: pointer to the ethernet header inside the skb
+ *
+ * Returns true if the skb was consumed (encoded packet sent) or false otherwise
+ */
+bool batadv_nc_skb_forward(struct sk_buff *skb,
+ struct batadv_neigh_node *neigh_node,
+ struct ethhdr *ethhdr)
+{
+ const struct net_device *netdev = neigh_node->if_incoming->soft_iface;
+ struct batadv_priv *bat_priv = netdev_priv(netdev);
+ struct batadv_unicast_packet *packet;
+ struct batadv_nc_path *nc_path;
+ __be32 packet_id;
+ u8 *payload;
+
+ /* Check if network coding is enabled */
+ if (!atomic_read(&bat_priv->network_coding))
+ goto out;
+
+ /* We only handle unicast packets */
+ payload = skb_network_header(skb);
+ packet = (struct batadv_unicast_packet *)payload;
+ if (packet->header.packet_type != BATADV_UNICAST)
+ goto out;
+
+ /* Try to find a coding opportunity and send the skb if one is found */
+ if (batadv_nc_skb_dst_search(skb, neigh_node, ethhdr))
+ return true;
+
+ /* Find or create a nc_path for this src-dst pair */
+ nc_path = batadv_nc_get_path(bat_priv,
+ bat_priv->nc.coding_hash,
+ ethhdr->h_source,
+ neigh_node->addr);
+
+ if (!nc_path)
+ goto out;
+
+ /* Add skb to nc_path */
+ packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet));
+ if (!batadv_nc_skb_add_to_path(skb, nc_path, neigh_node, packet_id))
+ goto free_nc_path;
+
+ /* Packet is consumed */
+ return true;
+
+free_nc_path:
+ batadv_nc_path_free_ref(nc_path);
+out:
+ /* Packet is not consumed */
+ return false;
+}
+
+/**
+ * batadv_nc_skb_store_for_decoding - save a clone of the skb which can be used
+ * when decoding coded packets
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: data skb to store
+ */
+void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
+ struct sk_buff *skb)
+{
+ struct batadv_unicast_packet *packet;
+ struct batadv_nc_path *nc_path;
+ struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ __be32 packet_id;
+ u8 *payload;
+
+ /* Check if network coding is enabled */
+ if (!atomic_read(&bat_priv->network_coding))
+ goto out;
+
+ /* Check for supported packet type */
+ payload = skb_network_header(skb);
+ packet = (struct batadv_unicast_packet *)payload;
+ if (packet->header.packet_type != BATADV_UNICAST)
+ goto out;
+
+ /* Find existing nc_path or create a new */
+ nc_path = batadv_nc_get_path(bat_priv,
+ bat_priv->nc.decoding_hash,
+ ethhdr->h_source,
+ ethhdr->h_dest);
+
+ if (!nc_path)
+ goto out;
+
+ /* Clone skb and adjust skb->data to point at batman header */
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
+ goto free_nc_path;
+
+ if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
+ goto free_skb;
+
+ if (unlikely(!skb_pull_rcsum(skb, ETH_HLEN)))
+ goto free_skb;
+
+ /* Add skb to nc_path */
+ packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet));
+ if (!batadv_nc_skb_add_to_path(skb, nc_path, NULL, packet_id))
+ goto free_skb;
+
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_BUFFER);
+ return;
+
+free_skb:
+ kfree_skb(skb);
+free_nc_path:
+ batadv_nc_path_free_ref(nc_path);
+out:
+ return;
+}
+
+/**
+ * batadv_nc_skb_store_sniffed_unicast - check if a received unicast packet
+ * should be saved in the decoding buffer and, if so, store it there
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: unicast skb to store
+ */
+void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
+ struct sk_buff *skb)
+{
+ struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
+
+ if (batadv_is_my_mac(ethhdr->h_dest))
+ return;
+
+ /* Set data pointer to MAC header to mimic packets from our tx path */
+ skb_push(skb, ETH_HLEN);
+
+ batadv_nc_skb_store_for_decoding(bat_priv, skb);
+}
+
+/**
+ * batadv_nc_skb_decode_packet - decode given skb using the decode data stored
+ * in nc_packet
+ * @skb: unicast skb to decode
+ * @nc_packet: decode data needed to decode the skb
+ *
+ * Returns pointer to decoded unicast packet if the packet was decoded or NULL
+ * in case of an error.
+ */
+static struct batadv_unicast_packet *
+batadv_nc_skb_decode_packet(struct sk_buff *skb,
+ struct batadv_nc_packet *nc_packet)
+{
+ const int h_size = sizeof(struct batadv_unicast_packet);
+ const int h_diff = sizeof(struct batadv_coded_packet) - h_size;
+ struct batadv_unicast_packet *unicast_packet;
+ struct batadv_coded_packet coded_packet_tmp;
+ struct ethhdr *ethhdr, ethhdr_tmp;
+ uint8_t *orig_dest, ttl, ttvn;
+ unsigned int coding_len;
+
+ /* Save headers temporarily */
+ memcpy(&coded_packet_tmp, skb->data, sizeof(coded_packet_tmp));
+ memcpy(&ethhdr_tmp, skb_mac_header(skb), sizeof(ethhdr_tmp));
+
+ if (skb_cow(skb, 0) < 0)
+ return NULL;
+
+ if (unlikely(!skb_pull_rcsum(skb, h_diff)))
+ return NULL;
+
+ /* Data points to batman header, so set mac header 14 bytes before
+ * and network to data
+ */
+ skb_set_mac_header(skb, -ETH_HLEN);
+ skb_reset_network_header(skb);
+
+ /* Reconstruct original mac header */
+ ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ memcpy(ethhdr, &ethhdr_tmp, sizeof(*ethhdr));
+
+ /* Select the correct unicast header information based on the location
+ * of our mac address in the coded_packet header
+ */
+ if (batadv_is_my_mac(coded_packet_tmp.second_dest)) {
+ /* If we are the second destination the packet was overheard,
+ * so the Ethernet address must be copied to h_dest and
+ * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST
+ */
+ memcpy(ethhdr->h_dest, coded_packet_tmp.second_dest, ETH_ALEN);
+ skb->pkt_type = PACKET_HOST;
+
+ orig_dest = coded_packet_tmp.second_orig_dest;
+ ttl = coded_packet_tmp.second_ttl;
+ ttvn = coded_packet_tmp.second_ttvn;
+ } else {
+ orig_dest = coded_packet_tmp.first_orig_dest;
+ ttl = coded_packet_tmp.header.ttl;
+ ttvn = coded_packet_tmp.first_ttvn;
+ }
+
+ coding_len = ntohs(coded_packet_tmp.coded_len);
+
+ if (coding_len > skb->len)
+ return NULL;
+
+ /* Here the magic is reversed:
+ * extract the missing packet from the received coded packet
+ */
+ batadv_nc_memxor(skb->data + h_size,
+ nc_packet->skb->data + h_size,
+ coding_len);
+
+ /* Resize decoded skb if decoded with larger packet */
+ if (nc_packet->skb->len > coding_len + h_size)
+ pskb_trim_rcsum(skb, coding_len + h_size);
+
+ /* Create decoded unicast packet */
+ unicast_packet = (struct batadv_unicast_packet *)skb->data;
+ unicast_packet->header.packet_type = BATADV_UNICAST;
+ unicast_packet->header.version = BATADV_COMPAT_VERSION;
+ unicast_packet->header.ttl = ttl;
+ memcpy(unicast_packet->dest, orig_dest, ETH_ALEN);
+ unicast_packet->ttvn = ttvn;
+
+ batadv_nc_packet_free(nc_packet);
+ return unicast_packet;
+}
+
+/**
+ * batadv_nc_find_decoding_packet - search through buffered decoding data to
+ * find the data needed to decode the coded packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: pointer to the ethernet header inside the coded packet
+ * @coded: coded packet we try to find decode data for
+ *
+ * Returns pointer to nc packet if the needed data was found or NULL otherwise.
+ */
+static struct batadv_nc_packet *
+batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv,
+ struct ethhdr *ethhdr,
+ struct batadv_coded_packet *coded)
+{
+ struct batadv_hashtable *hash = bat_priv->nc.decoding_hash;
+ struct batadv_nc_packet *tmp_nc_packet, *nc_packet = NULL;
+ struct batadv_nc_path *nc_path, nc_path_key;
+ uint8_t *dest, *source;
+ __be32 packet_id;
+ int index;
+
+ if (!hash)
+ return NULL;
+
+ /* Select the correct packet id based on the location of our mac-addr */
+ dest = ethhdr->h_source;
+ if (!batadv_is_my_mac(coded->second_dest)) {
+ source = coded->second_source;
+ packet_id = coded->second_crc;
+ } else {
+ source = coded->first_source;
+ packet_id = coded->first_crc;
+ }
+
+ batadv_nc_hash_key_gen(&nc_path_key, source, dest);
+ index = batadv_nc_hash_choose(&nc_path_key, hash->size);
+
+ /* Search for matching coding path */
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(nc_path, &hash->table[index], hash_entry) {
+ /* Find matching nc_packet */
+ spin_lock_bh(&nc_path->packet_list_lock);
+ list_for_each_entry(tmp_nc_packet,
+ &nc_path->packet_list, list) {
+ if (packet_id == tmp_nc_packet->packet_id) {
+ list_del(&tmp_nc_packet->list);
+
+ nc_packet = tmp_nc_packet;
+ break;
+ }
+ }
+ spin_unlock_bh(&nc_path->packet_list_lock);
+
+ if (nc_packet)
+ break;
+ }
+ rcu_read_unlock();
+
+ if (!nc_packet)
+ batadv_dbg(BATADV_DBG_NC, bat_priv,
+ "No decoding packet found for %u\n", packet_id);
+
+ return nc_packet;
+}
+
+/**
+ * batadv_nc_recv_coded_packet - try to decode coded packet and enqueue the
+ * resulting unicast packet
+ * @skb: incoming coded packet
+ * @recv_if: pointer to interface this packet was received on
+ */
+static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
+ struct batadv_hard_iface *recv_if)
+{
+ struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+ struct batadv_unicast_packet *unicast_packet;
+ struct batadv_coded_packet *coded_packet;
+ struct batadv_nc_packet *nc_packet;
+ struct ethhdr *ethhdr;
+ int hdr_size = sizeof(*coded_packet);
+
+ /* Check if network coding is enabled */
+ if (!atomic_read(&bat_priv->network_coding))
+ return NET_RX_DROP;
+
+ /* Make sure we can access (and remove) header */
+ if (unlikely(!pskb_may_pull(skb, hdr_size)))
+ return NET_RX_DROP;
+
+ coded_packet = (struct batadv_coded_packet *)skb->data;
+ ethhdr = (struct ethhdr *)skb_mac_header(skb);
+
+ /* Verify frame is destined for us */
+ if (!batadv_is_my_mac(ethhdr->h_dest) &&
+ !batadv_is_my_mac(coded_packet->second_dest))
+ return NET_RX_DROP;
+
+ /* Update stat counter */
+ if (batadv_is_my_mac(coded_packet->second_dest))
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_SNIFFED);
+
+ nc_packet = batadv_nc_find_decoding_packet(bat_priv, ethhdr,
+ coded_packet);
+ if (!nc_packet) {
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED);
+ return NET_RX_DROP;
+ }
+
+ /* Make skb's linear, because decoding accesses the entire buffer */
+ if (skb_linearize(skb) < 0)
+ goto free_nc_packet;
+
+ if (skb_linearize(nc_packet->skb) < 0)
+ goto free_nc_packet;
+
+ /* Decode the packet */
+ unicast_packet = batadv_nc_skb_decode_packet(skb, nc_packet);
+ if (!unicast_packet) {
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED);
+ goto free_nc_packet;
+ }
+
+ /* Mark packet as decoded to do correct recoding when forwarding */
+ BATADV_SKB_CB(skb)->decoded = true;
+ batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE);
+ batadv_add_counter(bat_priv, BATADV_CNT_NC_DECODE_BYTES,
+ skb->len + ETH_HLEN);
+ return batadv_recv_unicast_packet(skb, recv_if);
+
+free_nc_packet:
+ batadv_nc_packet_free(nc_packet);
+ return NET_RX_DROP;
+}
+
+/**
+ * batadv_nc_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)
+{
+ 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);
+ batadv_hash_destroy(bat_priv->nc.coding_hash);
+ batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, NULL);
+ batadv_hash_destroy(bat_priv->nc.decoding_hash);
+}
+
+/**
+ * batadv_nc_nodes_seq_print_text - print the nc node information
+ * @seq: seq file to print on
+ * @offset: not used
+ */
+int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset)
+{
+ struct net_device *net_dev = (struct net_device *)seq->private;
+ struct batadv_priv *bat_priv = netdev_priv(net_dev);
+ struct batadv_hashtable *hash = bat_priv->orig_hash;
+ struct batadv_hard_iface *primary_if;
+ struct hlist_head *head;
+ struct batadv_orig_node *orig_node;
+ struct batadv_nc_node *nc_node;
+ int i;
+
+ primary_if = batadv_seq_print_text_primary_if_get(seq);
+ if (!primary_if)
+ goto out;
+
+ /* Traverse list of originators */
+ for (i = 0; i < hash->size; i++) {
+ head = &hash->table[i];
+
+ /* For each orig_node in this bin */
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
+ seq_printf(seq, "Node: %pM\n", orig_node->orig);
+
+ seq_puts(seq, " Ingoing: ");
+ /* For each in_nc_node to this orig_node */
+ list_for_each_entry_rcu(nc_node,
+ &orig_node->in_coding_list,
+ list)
+ seq_printf(seq, "%pM ",
+ nc_node->addr);
+ seq_puts(seq, "\n");
+
+ seq_puts(seq, " Outgoing: ");
+ /* For out_nc_node to this orig_node */
+ list_for_each_entry_rcu(nc_node,
+ &orig_node->out_coding_list,
+ list)
+ seq_printf(seq, "%pM ",
+ nc_node->addr);
+ seq_puts(seq, "\n\n");
+ }
+ rcu_read_unlock();
+ }
+
+out:
+ if (primary_if)
+ batadv_hardif_free_ref(primary_if);
+ return 0;
+}
+
+/**
+ * batadv_nc_init_debugfs - create nc folder and related files in debugfs
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+int batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
+{
+ struct dentry *nc_dir, *file;
+
+ nc_dir = debugfs_create_dir("nc", bat_priv->debug_dir);
+ if (!nc_dir)
+ goto out;
+
+ file = debugfs_create_u8("min_tq", S_IRUGO | S_IWUSR, nc_dir,
+ &bat_priv->nc.min_tq);
+ if (!file)
+ goto out;
+
+ file = debugfs_create_u32("max_fwd_delay", S_IRUGO | S_IWUSR, nc_dir,
+ &bat_priv->nc.max_fwd_delay);
+ if (!file)
+ goto out;
+
+ file = debugfs_create_u32("max_buffer_time", S_IRUGO | S_IWUSR, nc_dir,
+ &bat_priv->nc.max_buffer_time);
+ if (!file)
+ goto out;
+
+ return 0;
+
+out:
+ return -ENOMEM;
+}
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
new file mode 100644
index 000000000000..4fa6d0caddbd
--- /dev/null
+++ b/net/batman-adv/network-coding.h
@@ -0,0 +1,123 @@
+/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors:
+ *
+ * Martin Hundebøll, Jeppe Ledet-Pedersen
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef _NET_BATMAN_ADV_NETWORK_CODING_H_
+#define _NET_BATMAN_ADV_NETWORK_CODING_H_
+
+#ifdef CONFIG_BATMAN_ADV_NC
+
+int batadv_nc_init(struct batadv_priv *bat_priv);
+void batadv_nc_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,
+ struct batadv_ogm_packet *ogm_packet,
+ int is_single_hop_neigh);
+void batadv_nc_purge_orig(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ bool (*to_purge)(struct batadv_priv *,
+ struct batadv_nc_node *));
+void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv);
+void batadv_nc_init_orig(struct batadv_orig_node *orig_node);
+bool batadv_nc_skb_forward(struct sk_buff *skb,
+ struct batadv_neigh_node *neigh_node,
+ struct ethhdr *ethhdr);
+void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
+ struct sk_buff *skb);
+void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
+ struct sk_buff *skb);
+int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset);
+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)
+{
+ return 0;
+}
+
+static inline void batadv_nc_free(struct batadv_priv *bat_priv)
+{
+ return;
+}
+
+static inline void
+batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ struct batadv_orig_node *orig_neigh_node,
+ struct batadv_ogm_packet *ogm_packet,
+ int is_single_hop_neigh)
+{
+ return;
+}
+
+static inline void
+batadv_nc_purge_orig(struct batadv_priv *bat_priv,
+ struct batadv_orig_node *orig_node,
+ bool (*to_purge)(struct batadv_priv *,
+ struct batadv_nc_node *))
+{
+ return;
+}
+
+static inline void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv)
+{
+ return;
+}
+
+static inline void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
+{
+ return;
+}
+
+static inline bool batadv_nc_skb_forward(struct sk_buff *skb,
+ struct batadv_neigh_node *neigh_node,
+ struct ethhdr *ethhdr)
+{
+ return false;
+}
+
+static inline void
+batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
+ struct sk_buff *skb)
+{
+ return;
+}
+
+static inline void
+batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
+ struct sk_buff *skb)
+{
+ return;
+}
+
+static inline int batadv_nc_nodes_seq_print_text(struct seq_file *seq,
+ void *offset)
+{
+ return 0;
+}
+
+static inline int batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
+{
+ return 0;
+}
+
+#endif /* ifdef CONFIG_BATMAN_ADV_NC */
+
+#endif /* _NET_BATMAN_ADV_NETWORK_CODING_H_ */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 96fb80b724dc..2f3452546636 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -28,6 +28,7 @@
#include "unicast.h"
#include "soft-interface.h"
#include "bridge_loop_avoidance.h"
+#include "network-coding.h"
/* hash class keys */
static struct lock_class_key batadv_orig_hash_lock_class_key;
@@ -142,6 +143,9 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
spin_unlock_bh(&orig_node->neigh_list_lock);
+ /* Free nc_nodes */
+ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL);
+
batadv_frag_list_free(&orig_node->frag_list);
batadv_tt_global_del_orig(orig_node->bat_priv, orig_node,
"originator timed out");
@@ -219,6 +223,8 @@ struct batadv_orig_node *batadv_get_orig_node(struct batadv_priv *bat_priv,
spin_lock_init(&orig_node->neigh_list_lock);
spin_lock_init(&orig_node->tt_buff_lock);
+ batadv_nc_init_orig(orig_node);
+
/* extra reference for return */
atomic_set(&orig_node->refcount, 2);
@@ -459,7 +465,7 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset)
neigh_node_tmp->tq_avg);
}
- seq_printf(seq, "\n");
+ seq_puts(seq, "\n");
batman_count++;
next:
@@ -469,7 +475,7 @@ next:
}
if (batman_count == 0)
- seq_printf(seq, "No batman nodes in range ...\n");
+ seq_puts(seq, "No batman nodes in range ...\n");
out:
if (primary_if)
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index ed0aa89bbf8b..a51ccfc39da4 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -30,6 +30,7 @@ enum batadv_packettype {
BATADV_TT_QUERY = 0x07,
BATADV_ROAM_ADV = 0x08,
BATADV_UNICAST_4ADDR = 0x09,
+ BATADV_CODED = 0x0a,
};
/**
@@ -278,4 +279,36 @@ struct batadv_tt_change {
uint8_t addr[ETH_ALEN];
} __packed;
+/**
+ * struct batadv_coded_packet - network coded packet
+ * @header: common batman packet header and ttl of first included packet
+ * @reserved: Align following fields to 2-byte boundaries
+ * @first_source: original source of first included packet
+ * @first_orig_dest: original destinal of first included packet
+ * @first_crc: checksum of first included packet
+ * @first_ttvn: tt-version number of first included packet
+ * @second_ttl: ttl of second packet
+ * @second_dest: second receiver of this coded packet
+ * @second_source: original source of second included packet
+ * @second_orig_dest: original destination of second included packet
+ * @second_crc: checksum of second included packet
+ * @second_ttvn: tt version number of second included packet
+ * @coded_len: length of network coded part of the payload
+ */
+struct batadv_coded_packet {
+ struct batadv_header header;
+ uint8_t first_ttvn;
+ /* uint8_t first_dest[ETH_ALEN]; - saved in mac header destination */
+ uint8_t first_source[ETH_ALEN];
+ uint8_t first_orig_dest[ETH_ALEN];
+ __be32 first_crc;
+ uint8_t second_ttl;
+ uint8_t second_ttvn;
+ uint8_t second_dest[ETH_ALEN];
+ uint8_t second_source[ETH_ALEN];
+ uint8_t second_orig_dest[ETH_ALEN];
+ __be32 second_crc;
+ __be16 coded_len;
+};
+
#endif /* _NET_BATMAN_ADV_PACKET_H_ */
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 5ee21cebbbb0..8f88967ff14b 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -29,6 +29,7 @@
#include "unicast.h"
#include "bridge_loop_avoidance.h"
#include "distributed-arp-table.h"
+#include "network-coding.h"
static int batadv_route_unicast_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if);
@@ -548,27 +549,37 @@ batadv_find_ifalter_router(struct batadv_orig_node *primary_orig,
return router;
}
+/**
+ * batadv_check_unicast_packet - Check for malformed unicast packets
+ * @skb: packet to check
+ * @hdr_size: size of header to pull
+ *
+ * Check for short header and bad addresses in given packet. Returns negative
+ * value when check fails and 0 otherwise. The negative value depends on the
+ * reason: -ENODATA for bad header, -EBADR for broadcast destination or source,
+ * and -EREMOTE for non-local (other host) destination.
+ */
static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size)
{
struct ethhdr *ethhdr;
/* drop packet if it has not necessary minimum size */
if (unlikely(!pskb_may_pull(skb, hdr_size)))
- return -1;
+ return -ENODATA;
ethhdr = (struct ethhdr *)skb_mac_header(skb);
/* packet with unicast indication but broadcast recipient */
if (is_broadcast_ether_addr(ethhdr->h_dest))
- return -1;
+ return -EBADR;
/* packet with broadcast sender address */
if (is_broadcast_ether_addr(ethhdr->h_source))
- return -1;
+ return -EBADR;
/* not for me */
if (!batadv_is_my_mac(ethhdr->h_dest))
- return -1;
+ return -EREMOTE;
return 0;
}
@@ -850,15 +861,18 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
/* decrement ttl */
unicast_packet->header.ttl--;
- /* Update stats counter */
- batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD);
- batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES,
- skb->len + ETH_HLEN);
-
- /* route it */
- if (batadv_send_skb_to_orig(skb, orig_node, recv_if))
+ /* network code packet if possible */
+ if (batadv_nc_skb_forward(skb, neigh_node, ethhdr)) {
+ ret = NET_RX_SUCCESS;
+ } else if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) {
ret = NET_RX_SUCCESS;
+ /* Update stats counter */
+ batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD);
+ batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES,
+ skb->len + ETH_HLEN);
+ }
+
out:
if (neigh_node)
batadv_neigh_node_free_ref(neigh_node);
@@ -1033,7 +1047,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
struct batadv_unicast_4addr_packet *unicast_4addr_packet;
uint8_t *orig_addr;
struct batadv_orig_node *orig_node = NULL;
- int hdr_size = sizeof(*unicast_packet);
+ int check, hdr_size = sizeof(*unicast_packet);
bool is4addr;
unicast_packet = (struct batadv_unicast_packet *)skb->data;
@@ -1044,7 +1058,16 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
if (is4addr)
hdr_size = sizeof(*unicast_4addr_packet);
- if (batadv_check_unicast_packet(skb, hdr_size) < 0)
+ /* function returns -EREMOTE for promiscuous packets */
+ check = batadv_check_unicast_packet(skb, hdr_size);
+
+ /* Even though the packet is not for us, we might save it to use for
+ * decoding a later received coded packet
+ */
+ if (check == -EREMOTE)
+ batadv_nc_skb_store_sniffed_unicast(bat_priv, skb);
+
+ if (check < 0)
return NET_RX_DROP;
if (!batadv_check_unicast_ttvn(bat_priv, skb))
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index a67cffde37ae..263cfd1ccee7 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -27,6 +27,7 @@
#include "vis.h"
#include "gateway_common.h"
#include "originator.h"
+#include "network-coding.h"
#include <linux/if_ether.h>
@@ -39,6 +40,7 @@ int batadv_send_skb_packet(struct sk_buff *skb,
struct batadv_hard_iface *hard_iface,
const uint8_t *dst_addr)
{
+ struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
struct ethhdr *ethhdr;
if (hard_iface->if_status != BATADV_IF_ACTIVE)
@@ -70,6 +72,9 @@ int batadv_send_skb_packet(struct sk_buff *skb,
skb->dev = hard_iface->net_dev;
+ /* Save a clone of the skb to use when decoding coded packets */
+ batadv_nc_skb_store_for_decoding(bat_priv, skb);
+
/* dev_queue_xmit() returns a negative result on error. However on
* congestion and traffic shaping, it drops and returns NET_XMIT_DROP
* (which is > 0). This will not be treated as an error.
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 2711e870f557..403b8c46085e 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -37,6 +37,7 @@
#include <linux/if_ether.h>
#include "unicast.h"
#include "bridge_loop_avoidance.h"
+#include "network-coding.h"
static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd);
@@ -401,55 +402,6 @@ static void batadv_set_lockdep_class(struct net_device *dev)
}
/**
- * batadv_softif_init - Late stage initialization of soft interface
- * @dev: registered network device to modify
- *
- * Returns error code on failures
- */
-static int batadv_softif_init(struct net_device *dev)
-{
- batadv_set_lockdep_class(dev);
-
- return 0;
-}
-
-static const struct net_device_ops batadv_netdev_ops = {
- .ndo_init = batadv_softif_init,
- .ndo_open = batadv_interface_open,
- .ndo_stop = batadv_interface_release,
- .ndo_get_stats = batadv_interface_stats,
- .ndo_set_mac_address = batadv_interface_set_mac_addr,
- .ndo_change_mtu = batadv_interface_change_mtu,
- .ndo_start_xmit = batadv_interface_tx,
- .ndo_validate_addr = eth_validate_addr
-};
-
-static void batadv_interface_setup(struct net_device *dev)
-{
- struct batadv_priv *priv = netdev_priv(dev);
-
- ether_setup(dev);
-
- dev->netdev_ops = &batadv_netdev_ops;
- dev->destructor = free_netdev;
- dev->tx_queue_len = 0;
-
- /* can't call min_mtu, because the needed variables
- * have not been initialized yet
- */
- dev->mtu = ETH_DATA_LEN;
- /* reserve more space in the skbuff for our header */
- dev->hard_header_len = BATADV_HEADER_LEN;
-
- /* generate random address */
- eth_hw_addr_random(dev);
-
- SET_ETHTOOL_OPS(dev, &batadv_ethtool_ops);
-
- memset(priv, 0, sizeof(*priv));
-}
-
-/**
* batadv_softif_destroy_finish - cleans up the remains of a softif
* @work: work queue item
*
@@ -465,7 +417,6 @@ static void batadv_softif_destroy_finish(struct work_struct *work)
cleanup_work);
soft_iface = bat_priv->soft_iface;
- batadv_debugfs_del_meshif(soft_iface);
batadv_sysfs_del_meshif(soft_iface);
rtnl_lock();
@@ -473,21 +424,22 @@ static void batadv_softif_destroy_finish(struct work_struct *work)
rtnl_unlock();
}
-struct net_device *batadv_softif_create(const char *name)
+/**
+ * batadv_softif_init_late - late stage initialization of soft interface
+ * @dev: registered network device to modify
+ *
+ * Returns error code on failures
+ */
+static int batadv_softif_init_late(struct net_device *dev)
{
- struct net_device *soft_iface;
struct batadv_priv *bat_priv;
int ret;
size_t cnt_len = sizeof(uint64_t) * BATADV_CNT_NUM;
- soft_iface = alloc_netdev(sizeof(*bat_priv), name,
- batadv_interface_setup);
-
- if (!soft_iface)
- goto out;
+ batadv_set_lockdep_class(dev);
- bat_priv = netdev_priv(soft_iface);
- bat_priv->soft_iface = soft_iface;
+ bat_priv = netdev_priv(dev);
+ bat_priv->soft_iface = dev;
INIT_WORK(&bat_priv->cleanup_work, batadv_softif_destroy_finish);
/* batadv_interface_stats() needs to be available as soon as
@@ -495,14 +447,7 @@ struct net_device *batadv_softif_create(const char *name)
*/
bat_priv->bat_counters = __alloc_percpu(cnt_len, __alignof__(uint64_t));
if (!bat_priv->bat_counters)
- goto free_soft_iface;
-
- ret = register_netdevice(soft_iface);
- if (ret < 0) {
- pr_err("Unable to register the batman interface '%s': %i\n",
- name, ret);
- goto free_bat_counters;
- }
+ return -ENOMEM;
atomic_set(&bat_priv->aggregated_ogms, 1);
atomic_set(&bat_priv->bonding, 0);
@@ -540,49 +485,189 @@ struct net_device *batadv_softif_create(const char *name)
bat_priv->primary_if = NULL;
bat_priv->num_ifaces = 0;
- ret = batadv_algo_select(bat_priv, batadv_routing_algo);
- if (ret < 0)
- goto unreg_soft_iface;
+ batadv_nc_init_bat_priv(bat_priv);
- ret = batadv_sysfs_add_meshif(soft_iface);
+ ret = batadv_algo_select(bat_priv, batadv_routing_algo);
if (ret < 0)
- goto unreg_soft_iface;
+ goto free_bat_counters;
- ret = batadv_debugfs_add_meshif(soft_iface);
+ ret = batadv_debugfs_add_meshif(dev);
if (ret < 0)
- goto unreg_sysfs;
+ goto free_bat_counters;
- ret = batadv_mesh_init(soft_iface);
+ ret = batadv_mesh_init(dev);
if (ret < 0)
goto unreg_debugfs;
- return soft_iface;
+ return 0;
unreg_debugfs:
- batadv_debugfs_del_meshif(soft_iface);
-unreg_sysfs:
- batadv_sysfs_del_meshif(soft_iface);
-unreg_soft_iface:
- free_percpu(bat_priv->bat_counters);
- unregister_netdevice(soft_iface);
- return NULL;
-
+ batadv_debugfs_del_meshif(dev);
free_bat_counters:
free_percpu(bat_priv->bat_counters);
-free_soft_iface:
- free_netdev(soft_iface);
+
+ return ret;
+}
+
+/**
+ * batadv_softif_slave_add - Add a slave interface to a batadv_soft_interface
+ * @dev: batadv_soft_interface used as master interface
+ * @slave_dev: net_device which should become the slave interface
+ *
+ * Return 0 if successful or error otherwise.
+ */
+static int batadv_softif_slave_add(struct net_device *dev,
+ struct net_device *slave_dev)
+{
+ struct batadv_hard_iface *hard_iface;
+ int ret = -EINVAL;
+
+ hard_iface = batadv_hardif_get_by_netdev(slave_dev);
+ if (!hard_iface || hard_iface->soft_iface != NULL)
+ goto out;
+
+ ret = batadv_hardif_enable_interface(hard_iface, dev->name);
+
out:
- return NULL;
+ if (hard_iface)
+ batadv_hardif_free_ref(hard_iface);
+ return ret;
}
-void batadv_softif_destroy(struct net_device *soft_iface)
+/**
+ * batadv_softif_slave_del - Delete a slave iface from a batadv_soft_interface
+ * @dev: batadv_soft_interface used as master interface
+ * @slave_dev: net_device which should be removed from the master interface
+ *
+ * Return 0 if successful or error otherwise.
+ */
+static int batadv_softif_slave_del(struct net_device *dev,
+ struct net_device *slave_dev)
+{
+ struct batadv_hard_iface *hard_iface;
+ int ret = -EINVAL;
+
+ hard_iface = batadv_hardif_get_by_netdev(slave_dev);
+
+ if (!hard_iface || hard_iface->soft_iface != dev)
+ goto out;
+
+ batadv_hardif_disable_interface(hard_iface, BATADV_IF_CLEANUP_KEEP);
+ ret = 0;
+
+out:
+ if (hard_iface)
+ batadv_hardif_free_ref(hard_iface);
+ return ret;
+}
+
+static const struct net_device_ops batadv_netdev_ops = {
+ .ndo_init = batadv_softif_init_late,
+ .ndo_open = batadv_interface_open,
+ .ndo_stop = batadv_interface_release,
+ .ndo_get_stats = batadv_interface_stats,
+ .ndo_set_mac_address = batadv_interface_set_mac_addr,
+ .ndo_change_mtu = batadv_interface_change_mtu,
+ .ndo_start_xmit = batadv_interface_tx,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_add_slave = batadv_softif_slave_add,
+ .ndo_del_slave = batadv_softif_slave_del,
+};
+
+/**
+ * batadv_softif_free - Deconstructor of batadv_soft_interface
+ * @dev: Device to cleanup and remove
+ */
+static void batadv_softif_free(struct net_device *dev)
+{
+ batadv_debugfs_del_meshif(dev);
+ batadv_mesh_free(dev);
+ free_netdev(dev);
+}
+
+/**
+ * batadv_softif_init_early - early stage initialization of soft interface
+ * @dev: registered network device to modify
+ */
+static void batadv_softif_init_early(struct net_device *dev)
+{
+ struct batadv_priv *priv = netdev_priv(dev);
+
+ ether_setup(dev);
+
+ dev->netdev_ops = &batadv_netdev_ops;
+ dev->destructor = batadv_softif_free;
+ dev->tx_queue_len = 0;
+
+ /* can't call min_mtu, because the needed variables
+ * have not been initialized yet
+ */
+ dev->mtu = ETH_DATA_LEN;
+ /* reserve more space in the skbuff for our header */
+ dev->hard_header_len = BATADV_HEADER_LEN;
+
+ /* generate random address */
+ eth_hw_addr_random(dev);
+
+ SET_ETHTOOL_OPS(dev, &batadv_ethtool_ops);
+
+ memset(priv, 0, sizeof(*priv));
+}
+
+struct net_device *batadv_softif_create(const char *name)
+{
+ struct net_device *soft_iface;
+ int ret;
+
+ soft_iface = alloc_netdev(sizeof(struct batadv_priv), name,
+ batadv_softif_init_early);
+ if (!soft_iface)
+ return NULL;
+
+ soft_iface->rtnl_link_ops = &batadv_link_ops;
+
+ ret = register_netdevice(soft_iface);
+ if (ret < 0) {
+ pr_err("Unable to register the batman interface '%s': %i\n",
+ name, ret);
+ free_netdev(soft_iface);
+ return NULL;
+ }
+
+ return soft_iface;
+}
+
+/**
+ * batadv_softif_destroy_sysfs - deletion of batadv_soft_interface via sysfs
+ * @soft_iface: the to-be-removed batman-adv interface
+ */
+void batadv_softif_destroy_sysfs(struct net_device *soft_iface)
{
struct batadv_priv *bat_priv = netdev_priv(soft_iface);
- batadv_mesh_free(soft_iface);
queue_work(batadv_event_workqueue, &bat_priv->cleanup_work);
}
+/**
+ * batadv_softif_destroy_netlink - deletion of batadv_soft_interface via netlink
+ * @soft_iface: the to-be-removed batman-adv interface
+ * @head: list pointer
+ */
+static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
+ struct list_head *head)
+{
+ struct batadv_hard_iface *hard_iface;
+
+ list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
+ if (hard_iface->soft_iface == soft_iface)
+ batadv_hardif_disable_interface(hard_iface,
+ BATADV_IF_CLEANUP_KEEP);
+ }
+
+ batadv_sysfs_del_meshif(soft_iface);
+ unregister_netdevice_queue(soft_iface, head);
+}
+
int batadv_softif_is_valid(const struct net_device *net_dev)
{
if (net_dev->netdev_ops->ndo_start_xmit == batadv_interface_tx)
@@ -591,6 +676,13 @@ int batadv_softif_is_valid(const struct net_device *net_dev)
return 0;
}
+struct rtnl_link_ops batadv_link_ops __read_mostly = {
+ .kind = "batadv",
+ .priv_size = sizeof(struct batadv_priv),
+ .setup = batadv_softif_init_early,
+ .dellink = batadv_softif_destroy_netlink,
+};
+
/* ethtool */
static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
@@ -662,6 +754,17 @@ static const struct {
{ "dat_put_rx" },
{ "dat_cached_reply_tx" },
#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+ { "nc_code" },
+ { "nc_code_bytes" },
+ { "nc_recode" },
+ { "nc_recode_bytes" },
+ { "nc_buffer" },
+ { "nc_decode" },
+ { "nc_decode_bytes" },
+ { "nc_decode_failed" },
+ { "nc_sniffed" },
+#endif
};
static void batadv_get_strings(struct net_device *dev, uint32_t stringset,
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index 43182e5e603a..2f2472c2ea0d 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -25,7 +25,8 @@ void batadv_interface_rx(struct net_device *soft_iface,
struct sk_buff *skb, struct batadv_hard_iface *recv_if,
int hdr_size, struct batadv_orig_node *orig_node);
struct net_device *batadv_softif_create(const char *name);
-void batadv_softif_destroy(struct net_device *soft_iface);
+void batadv_softif_destroy_sysfs(struct net_device *soft_iface);
int batadv_softif_is_valid(const struct net_device *net_dev);
+extern struct rtnl_link_ops batadv_link_ops;
#endif /* _NET_BATMAN_ADV_SOFT_INTERFACE_H_ */
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index afbba319d73a..15a22efa9a67 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -442,6 +442,9 @@ static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth,
#ifdef CONFIG_BATMAN_ADV_DEBUG
BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL);
#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+BATADV_ATTR_SIF_BOOL(network_coding, S_IRUGO | S_IWUSR, NULL);
+#endif
static struct batadv_attribute *batadv_mesh_attrs[] = {
&batadv_attr_aggregated_ogms,
@@ -464,6 +467,9 @@ static struct batadv_attribute *batadv_mesh_attrs[] = {
#ifdef CONFIG_BATMAN_ADV_DEBUG
&batadv_attr_log_level,
#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+ &batadv_attr_network_coding,
+#endif
NULL,
};
@@ -582,13 +588,15 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj,
}
if (status_tmp == BATADV_IF_NOT_IN_USE) {
- batadv_hardif_disable_interface(hard_iface);
+ batadv_hardif_disable_interface(hard_iface,
+ BATADV_IF_CLEANUP_AUTO);
goto unlock;
}
/* if the interface already is in use */
if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
- batadv_hardif_disable_interface(hard_iface);
+ batadv_hardif_disable_interface(hard_iface,
+ BATADV_IF_CLEANUP_AUTO);
ret = batadv_hardif_enable_interface(hard_iface, buff);
@@ -688,15 +696,10 @@ int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type,
enum batadv_uev_action action, const char *data)
{
int ret = -ENOMEM;
- struct batadv_hard_iface *primary_if;
struct kobject *bat_kobj;
char *uevent_env[4] = { NULL, NULL, NULL, NULL };
- primary_if = batadv_primary_if_get_selected(bat_priv);
- if (!primary_if)
- goto out;
-
- bat_kobj = &primary_if->soft_iface->dev.kobj;
+ bat_kobj = &bat_priv->soft_iface->dev.kobj;
uevent_env[0] = kmalloc(strlen(BATADV_UEV_TYPE_VAR) +
strlen(batadv_uev_type_str[type]) + 1,
@@ -732,9 +735,6 @@ out:
kfree(uevent_env[1]);
kfree(uevent_env[2]);
- if (primary_if)
- batadv_hardif_free_ref(primary_if);
-
if (ret)
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Impossible to send uevent for (%s,%s,%s) event (err: %d)\n",
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 98a66a021a60..932232087449 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -385,25 +385,19 @@ static void batadv_tt_prepare_packet_buff(struct batadv_priv *bat_priv,
int *packet_buff_len,
int min_packet_len)
{
- struct batadv_hard_iface *primary_if;
int req_len;
- primary_if = batadv_primary_if_get_selected(bat_priv);
-
req_len = min_packet_len;
req_len += batadv_tt_len(atomic_read(&bat_priv->tt.local_changes));
/* if we have too many changes for one packet don't send any
* and wait for the tt table request which will be fragmented
*/
- if ((!primary_if) || (req_len > primary_if->soft_iface->mtu))
+ if (req_len > bat_priv->soft_iface->mtu)
req_len = min_packet_len;
batadv_tt_realloc_packet_buff(packet_buff, packet_buff_len,
min_packet_len, req_len);
-
- if (primary_if)
- batadv_hardif_free_ref(primary_if);
}
static int batadv_tt_changes_fill_buff(struct batadv_priv *bat_priv,
@@ -908,7 +902,7 @@ out_remove:
/* remove address from local hash if present */
local_flags = batadv_tt_local_remove(bat_priv, tt_addr,
"global tt received",
- !!(flags & BATADV_TT_CLIENT_ROAM));
+ flags & BATADV_TT_CLIENT_ROAM);
tt_global_entry->common.flags |= local_flags & BATADV_TT_CLIENT_WIFI;
if (!(flags & BATADV_TT_CLIENT_ROAM))
@@ -1580,7 +1574,7 @@ static int batadv_tt_global_valid(const void *entry_ptr,
static struct sk_buff *
batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
struct batadv_hashtable *hash,
- struct batadv_hard_iface *primary_if,
+ struct batadv_priv *bat_priv,
int (*valid_cb)(const void *, const void *),
void *cb_data)
{
@@ -1594,8 +1588,8 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
uint32_t i;
size_t len;
- if (tt_query_size + tt_len > primary_if->soft_iface->mtu) {
- tt_len = primary_if->soft_iface->mtu - tt_query_size;
+ if (tt_query_size + tt_len > bat_priv->soft_iface->mtu) {
+ tt_len = bat_priv->soft_iface->mtu - tt_query_size;
tt_len -= tt_len % sizeof(struct batadv_tt_change);
}
tt_tot = tt_len / sizeof(struct batadv_tt_change);
@@ -1715,7 +1709,6 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv,
{
struct batadv_orig_node *req_dst_orig_node;
struct batadv_orig_node *res_dst_orig_node = NULL;
- struct batadv_hard_iface *primary_if = NULL;
uint8_t orig_ttvn, req_ttvn, ttvn;
int ret = false;
unsigned char *tt_buff;
@@ -1740,10 +1733,6 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv,
if (!res_dst_orig_node)
goto out;
- primary_if = batadv_primary_if_get_selected(bat_priv);
- if (!primary_if)
- goto out;
-
orig_ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn);
req_ttvn = tt_request->ttvn;
@@ -1791,7 +1780,7 @@ batadv_send_other_tt_response(struct batadv_priv *bat_priv,
skb = batadv_tt_response_fill_table(tt_len, ttvn,
bat_priv->tt.global_hash,
- primary_if,
+ bat_priv,
batadv_tt_global_valid,
req_dst_orig_node);
if (!skb)
@@ -1828,8 +1817,6 @@ out:
batadv_orig_node_free_ref(res_dst_orig_node);
if (req_dst_orig_node)
batadv_orig_node_free_ref(req_dst_orig_node);
- if (primary_if)
- batadv_hardif_free_ref(primary_if);
if (!ret)
kfree_skb(skb);
return ret;
@@ -1907,7 +1894,7 @@ batadv_send_my_tt_response(struct batadv_priv *bat_priv,
skb = batadv_tt_response_fill_table(tt_len, ttvn,
bat_priv->tt.local_hash,
- primary_if,
+ bat_priv,
batadv_tt_local_valid_entry,
NULL);
if (!skb)
@@ -2528,7 +2515,7 @@ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv,
if (!tt_global_entry)
goto out;
- ret = !!(tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM);
+ ret = tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM;
batadv_tt_global_entry_free_ref(tt_global_entry);
out:
return ret;
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 4cd87a0b5b80..aba8364c3689 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -128,6 +128,10 @@ struct batadv_hard_iface {
* @bond_list: list of bonding candidates
* @refcount: number of contexts the object is used
* @rcu: struct used for freeing in an RCU-safe manner
+ * @in_coding_list: list of nodes this orig can hear
+ * @out_coding_list: list of nodes that can hear this orig
+ * @in_coding_list_lock: protects in_coding_list
+ * @out_coding_list_lock: protects out_coding_list
*/
struct batadv_orig_node {
uint8_t orig[ETH_ALEN];
@@ -171,6 +175,12 @@ struct batadv_orig_node {
struct list_head bond_list;
atomic_t refcount;
struct rcu_head rcu;
+#ifdef CONFIG_BATMAN_ADV_NC
+ struct list_head in_coding_list;
+ struct list_head out_coding_list;
+ spinlock_t in_coding_list_lock; /* Protects in_coding_list */
+ spinlock_t out_coding_list_lock; /* Protects out_coding_list */
+#endif
};
/**
@@ -265,6 +275,17 @@ struct batadv_bcast_duplist_entry {
* @BATADV_CNT_DAT_PUT_RX: received dht PUT traffic packet counter
* @BATADV_CNT_DAT_CACHED_REPLY_TX: transmitted dat cache reply traffic packet
* counter
+ * @BATADV_CNT_NC_CODE: transmitted nc-combined traffic packet counter
+ * @BATADV_CNT_NC_CODE_BYTES: transmitted nc-combined traffic bytes counter
+ * @BATADV_CNT_NC_RECODE: transmitted nc-recombined traffic packet counter
+ * @BATADV_CNT_NC_RECODE_BYTES: transmitted nc-recombined traffic bytes counter
+ * @BATADV_CNT_NC_BUFFER: counter for packets buffered for later nc decoding
+ * @BATADV_CNT_NC_DECODE: received and nc-decoded traffic packet counter
+ * @BATADV_CNT_NC_DECODE_BYTES: received and nc-decoded traffic bytes counter
+ * @BATADV_CNT_NC_DECODE_FAILED: received and decode-failed traffic packet
+ * counter
+ * @BATADV_CNT_NC_SNIFFED: counter for nc-decoded packets received in promisc
+ * mode.
* @BATADV_CNT_NUM: number of traffic counters
*/
enum batadv_counters {
@@ -292,6 +313,17 @@ enum batadv_counters {
BATADV_CNT_DAT_PUT_RX,
BATADV_CNT_DAT_CACHED_REPLY_TX,
#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+ BATADV_CNT_NC_CODE,
+ BATADV_CNT_NC_CODE_BYTES,
+ BATADV_CNT_NC_RECODE,
+ BATADV_CNT_NC_RECODE_BYTES,
+ BATADV_CNT_NC_BUFFER,
+ BATADV_CNT_NC_DECODE,
+ BATADV_CNT_NC_DECODE_BYTES,
+ BATADV_CNT_NC_DECODE_FAILED,
+ BATADV_CNT_NC_SNIFFED,
+#endif
BATADV_CNT_NUM,
};
@@ -428,6 +460,35 @@ struct batadv_priv_dat {
#endif
/**
+ * struct batadv_priv_nc - per mesh interface network coding private data
+ * @work: work queue callback item for cleanup
+ * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs
+ * @min_tq: only consider neighbors for encoding if neigh_tq > min_tq
+ * @max_fwd_delay: maximum packet forward delay to allow coding of packets
+ * @max_buffer_time: buffer time for sniffed packets used to decoding
+ * @timestamp_fwd_flush: timestamp of last forward packet queue flush
+ * @timestamp_sniffed_purge: timestamp of last sniffed packet queue purge
+ * @coding_hash: Hash table used to buffer skbs while waiting for another
+ * incoming skb to code it with. Skbs are added to the buffer just before being
+ * forwarded in routing.c
+ * @decoding_hash: Hash table used to buffer skbs that might be needed to decode
+ * a received coded skb. The buffer is used for 1) skbs arriving on the
+ * soft-interface; 2) skbs overheard on the hard-interface; and 3) skbs
+ * forwarded by batman-adv.
+ */
+struct batadv_priv_nc {
+ struct delayed_work work;
+ struct dentry *debug_dir;
+ u8 min_tq;
+ u32 max_fwd_delay;
+ u32 max_buffer_time;
+ unsigned long timestamp_fwd_flush;
+ unsigned long timestamp_sniffed_purge;
+ struct batadv_hashtable *coding_hash;
+ struct batadv_hashtable *decoding_hash;
+};
+
+/**
* struct batadv_priv - per mesh interface data
* @mesh_state: current status of the mesh (inactive/active/deactivating)
* @soft_iface: net device which holds this struct as private data
@@ -470,6 +531,8 @@ struct batadv_priv_dat {
* @tt: translation table data
* @vis: vis data
* @dat: distributed arp table data
+ * @network_coding: bool indicating whether network coding is enabled
+ * @batadv_priv_nc: network coding data
*/
struct batadv_priv {
atomic_t mesh_state;
@@ -522,6 +585,10 @@ struct batadv_priv {
#ifdef CONFIG_BATMAN_ADV_DAT
struct batadv_priv_dat dat;
#endif
+#ifdef CONFIG_BATMAN_ADV_NC
+ atomic_t network_coding;
+ struct batadv_priv_nc nc;
+#endif /* CONFIG_BATMAN_ADV_NC */
};
/**
@@ -702,6 +769,75 @@ struct batadv_tt_roam_node {
};
/**
+ * struct batadv_nc_node - network coding node
+ * @list: next and prev pointer for the list handling
+ * @addr: the node's mac address
+ * @refcount: number of contexts the object is used by
+ * @rcu: struct used for freeing in an RCU-safe manner
+ * @orig_node: pointer to corresponding orig node struct
+ * @last_seen: timestamp of last ogm received from this node
+ */
+struct batadv_nc_node {
+ struct list_head list;
+ uint8_t addr[ETH_ALEN];
+ atomic_t refcount;
+ struct rcu_head rcu;
+ struct batadv_orig_node *orig_node;
+ unsigned long last_seen;
+};
+
+/**
+ * struct batadv_nc_path - network coding path
+ * @hash_entry: next and prev pointer for the list handling
+ * @rcu: struct used for freeing in an RCU-safe manner
+ * @refcount: number of contexts the object is used by
+ * @packet_list: list of buffered packets for this path
+ * @packet_list_lock: access lock for packet list
+ * @next_hop: next hop (destination) of path
+ * @prev_hop: previous hop (source) of path
+ * @last_valid: timestamp for last validation of path
+ */
+struct batadv_nc_path {
+ struct hlist_node hash_entry;
+ struct rcu_head rcu;
+ atomic_t refcount;
+ struct list_head packet_list;
+ spinlock_t packet_list_lock; /* Protects packet_list */
+ uint8_t next_hop[ETH_ALEN];
+ uint8_t prev_hop[ETH_ALEN];
+ unsigned long last_valid;
+};
+
+/**
+ * struct batadv_nc_packet - network coding packet used when coding and
+ * decoding packets
+ * @list: next and prev pointer for the list handling
+ * @packet_id: crc32 checksum of skb data
+ * @timestamp: field containing the info when the packet was added to path
+ * @neigh_node: pointer to original next hop neighbor of skb
+ * @skb: skb which can be encoded or used for decoding
+ * @nc_path: pointer to path this nc packet is attached to
+ */
+struct batadv_nc_packet {
+ struct list_head list;
+ __be32 packet_id;
+ unsigned long timestamp;
+ struct batadv_neigh_node *neigh_node;
+ struct sk_buff *skb;
+ struct batadv_nc_path *nc_path;
+};
+
+/**
+ * batadv_skb_cb - control buffer structure used to store private data relevant
+ * to batman-adv in the skb->cb buffer in skbs.
+ * @decoded: Marks a skb as decoded, which is checked when searching for coding
+ * opportunities in network-coding.c
+ */
+struct batadv_skb_cb {
+ bool decoded;
+};
+
+/**
* struct batadv_forw_packet - structure for bcast packets to be sent/forwarded
* @list: list node for batadv_socket_client::queue_list
* @send_time: execution time for delayed_work (packet sending)
diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c
index 50e079f00be6..0bb3b5982f94 100644
--- a/net/batman-adv/unicast.c
+++ b/net/batman-adv/unicast.c
@@ -122,7 +122,7 @@ batadv_frag_search_packet(struct list_head *head,
{
struct batadv_frag_packet_list_entry *tfp;
struct batadv_unicast_frag_packet *tmp_up = NULL;
- int is_head_tmp, is_head;
+ bool is_head_tmp, is_head;
uint16_t search_seqno;
if (up->flags & BATADV_UNI_FRAG_HEAD)
@@ -130,7 +130,7 @@ batadv_frag_search_packet(struct list_head *head,
else
search_seqno = ntohs(up->seqno)-1;
- is_head = !!(up->flags & BATADV_UNI_FRAG_HEAD);
+ is_head = up->flags & BATADV_UNI_FRAG_HEAD;
list_for_each_entry(tfp, head, list) {
if (!tfp->skb)
@@ -142,7 +142,7 @@ batadv_frag_search_packet(struct list_head *head,
tmp_up = (struct batadv_unicast_frag_packet *)tfp->skb->data;
if (tfp->seqno == search_seqno) {
- is_head_tmp = !!(tmp_up->flags & BATADV_UNI_FRAG_HEAD);
+ is_head_tmp = tmp_up->flags & BATADV_UNI_FRAG_HEAD;
if (is_head_tmp != is_head)
return tfp;
else
diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c
index c053244b97bd..962ccf3b8382 100644
--- a/net/batman-adv/vis.c
+++ b/net/batman-adv/vis.c
@@ -149,7 +149,7 @@ static void batadv_vis_data_read_prim_sec(struct seq_file *seq,
hlist_for_each_entry(entry, if_list, list) {
if (entry->primary)
- seq_printf(seq, "PRIMARY, ");
+ seq_puts(seq, "PRIMARY, ");
else
seq_printf(seq, "SEC %pM, ", entry->addr);
}
@@ -207,7 +207,7 @@ static void batadv_vis_data_read_entries(struct seq_file *seq,
if (batadv_compare_eth(entry->addr, packet->vis_orig))
batadv_vis_data_read_prim_sec(seq, list);
- seq_printf(seq, "\n");
+ seq_puts(seq, "\n");
}
}
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index d3ee69b35a78..fea778e1dc27 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -422,7 +422,8 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,
return bt_accept_poll(sk);
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR;
+ mask |= POLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP | POLLIN | POLLRDNORM;
diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c
index e58c8b32589c..4b488ec26105 100644
--- a/net/bluetooth/bnep/netdev.c
+++ b/net/bluetooth/bnep/netdev.c
@@ -136,7 +136,7 @@ static u16 bnep_net_eth_proto(struct sk_buff *skb)
struct ethhdr *eh = (void *) skb->data;
u16 proto = ntohs(eh->h_proto);
- if (proto >= 1536)
+ if (proto >= ETH_P_802_3_MIN)
return proto;
if (get_unaligned((__be16 *) skb->data) == htons(0xFFFF))
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index bab338e6270d..c581f1200ef7 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -161,9 +161,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
if (!pv)
return;
- for (vid = find_next_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN, vid);
- vid < BR_VLAN_BITMAP_LEN;
- vid = find_next_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN, vid+1)) {
+ for_each_set_bit_from(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
f = __br_fdb_get(br, br->dev->dev_addr, vid);
if (f && f->is_local && !f->dst)
fdb_delete(br, f);
@@ -724,13 +722,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
* specify a VLAN. To be nice, add/update entry for every
* vlan on this port.
*/
- vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN);
- while (vid < BR_VLAN_BITMAP_LEN) {
+ for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
if (err)
goto out;
- vid = find_next_bit(pv->vlan_bitmap,
- BR_VLAN_BITMAP_LEN, vid+1);
}
}
@@ -815,11 +810,8 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
* vlan on this port.
*/
err = -ENOENT;
- vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN);
- while (vid < BR_VLAN_BITMAP_LEN) {
+ for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
err &= __br_fdb_delete(p, addr, vid);
- vid = find_next_bit(pv->vlan_bitmap,
- BR_VLAN_BITMAP_LEN, vid+1);
}
}
out:
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index ef1b91431c6b..f17fcb3097c2 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -148,7 +148,6 @@ static void del_nbp(struct net_bridge_port *p)
dev->priv_flags &= ~IFF_BRIDGE_PORT;
netdev_rx_handler_unregister(dev);
- synchronize_net();
netdev_upper_dev_unlink(dev, br->dev);
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index ee79f3f20383..19942e38fd2d 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -382,7 +382,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
return ret;
}
-static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct br_mdb_entry *entry;
@@ -458,7 +458,7 @@ unlock:
return err;
}
-static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net_device *dev;
struct br_mdb_entry *entry;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 923fbeaf7afd..81f2389f78eb 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1369,7 +1369,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
return -EINVAL;
if (iph->protocol != IPPROTO_IGMP) {
- if ((iph->daddr & IGMP_LOCAL_GROUP_MASK) != IGMP_LOCAL_GROUP)
+ if (!ipv4_is_local_multicast(iph->daddr))
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
return 0;
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 299fc5f40a26..8e3abf564798 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -136,10 +136,7 @@ static int br_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure;
pvid = br_get_pvid(pv);
- for (vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN);
- vid < BR_VLAN_BITMAP_LEN;
- vid = find_next_bit(pv->vlan_bitmap,
- BR_VLAN_BITMAP_LEN, vid+1)) {
+ for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
vinfo.vid = vid;
vinfo.flags = 0;
if (vid == pvid)
@@ -355,17 +352,14 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
/* Change state and parameters on port. */
int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
{
- struct ifinfomsg *ifm;
struct nlattr *protinfo;
struct nlattr *afspec;
struct net_bridge_port *p;
struct nlattr *tb[IFLA_BRPORT_MAX + 1];
- int err;
-
- ifm = nlmsg_data(nlh);
+ int err = 0;
- protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO);
- afspec = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_AF_SPEC);
+ protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
+ afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (!protinfo && !afspec)
return 0;
@@ -373,7 +367,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
/* We want to accept dev as bridge itself if the AF_SPEC
* is set to see if someone is setting vlan info on the brigde
*/
- if (!p && ((dev->priv_flags & IFF_EBRIDGE) && !afspec))
+ if (!p && !afspec)
return -EINVAL;
if (p && protinfo) {
@@ -414,14 +408,11 @@ out:
/* Delete port information */
int br_dellink(struct net_device *dev, struct nlmsghdr *nlh)
{
- struct ifinfomsg *ifm;
struct nlattr *afspec;
struct net_bridge_port *p;
int err;
- ifm = nlmsg_data(nlh);
-
- afspec = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_AF_SPEC);
+ afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (!afspec)
return 0;
diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c
index 3bf43f7bb9d4..961d870ab283 100644
--- a/net/bridge/netfilter/ebt_ulog.c
+++ b/net/bridge/netfilter/ebt_ulog.c
@@ -35,7 +35,7 @@
#include <linux/skbuff.h>
#include <linux/kernel.h>
#include <linux/timer.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
#include <linux/netdevice.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_bridge/ebtables.h>
@@ -134,7 +134,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb,
else
copy_len = uloginfo->cprange;
- size = NLMSG_SPACE(sizeof(*pm) + copy_len);
+ size = nlmsg_total_size(sizeof(*pm) + copy_len);
if (size > nlbufsiz) {
pr_debug("Size %Zd needed, but nlbufsiz=%d\n", size, nlbufsiz);
return;
@@ -319,12 +319,11 @@ static void __exit ebt_ulog_fini(void)
for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) {
ub = &ulog_buffers[i];
del_timer(&ub->timer);
- spin_lock_bh(&ub->lock);
+
if (ub->skb) {
kfree_skb(ub->skb);
ub->skb = NULL;
}
- spin_unlock_bh(&ub->lock);
}
netlink_kernel_release(ebtulognl);
}
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 40d8258bf74f..70f656ce0f4a 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -64,9 +64,7 @@ static int ebt_broute(struct sk_buff *skb)
static int __net_init broute_net_init(struct net *net)
{
net->xt.broute_table = ebt_register_table(net, &broute_table);
- if (IS_ERR(net->xt.broute_table))
- return PTR_ERR(net->xt.broute_table);
- return 0;
+ return PTR_RET(net->xt.broute_table);
}
static void __net_exit broute_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 8d493c91a562..3d110c4fc787 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -138,7 +138,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
ethproto = h->h_proto;
if (e->bitmask & EBT_802_3) {
- if (FWINV2(ntohs(ethproto) >= 1536, EBT_IPROTO))
+ if (FWINV2(ntohs(ethproto) >= ETH_P_802_3_MIN, EBT_IPROTO))
return 1;
} else if (!(e->bitmask & EBT_NOPROTO) &&
FWINV2(e->ethproto != ethproto, EBT_IPROTO))
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 21760f008974..df6d56d8689a 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -301,10 +301,11 @@ static void dev_flowctrl(struct net_device *dev, int on)
}
void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
- struct cflayer *link_support, int head_room,
- struct cflayer **layer, int (**rcv_func)(
- struct sk_buff *, struct net_device *,
- struct packet_type *, struct net_device *))
+ struct cflayer *link_support, int head_room,
+ struct cflayer **layer,
+ int (**rcv_func)(struct sk_buff *, struct net_device *,
+ struct packet_type *,
+ struct net_device *))
{
struct caif_device_entry *caifd;
enum cfcnfg_phy_preference pref;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 095259f83902..1d337e02bc63 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -197,8 +197,8 @@ static void cfsk_put(struct cflayer *layr)
/* Packet Control Callback function called from CAIF */
static void caif_ctrl_cb(struct cflayer *layr,
- enum caif_ctrlcmd flow,
- int phyid)
+ enum caif_ctrlcmd flow,
+ int phyid)
{
struct caifsock *cf_sk = container_of(layr, struct caifsock, layer);
switch (flow) {
@@ -274,7 +274,7 @@ static void caif_check_flow_release(struct sock *sk)
* changed locking, address handling and added MSG_TRUNC.
*/
static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *m, size_t len, int flags)
+ struct msghdr *m, size_t len, int flags)
{
struct sock *sk = sock->sk;
@@ -346,8 +346,8 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
* changed locking calls, changed address handling.
*/
static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *msg, size_t size,
- int flags)
+ struct msghdr *msg, size_t size,
+ int flags)
{
struct sock *sk = sock->sk;
int copied = 0;
@@ -462,7 +462,7 @@ out:
* CAIF flow-on and sock_writable.
*/
static long caif_wait_for_flow_on(struct caifsock *cf_sk,
- int wait_writeable, long timeo, int *err)
+ int wait_writeable, long timeo, int *err)
{
struct sock *sk = &cf_sk->sk;
DEFINE_WAIT(wait);
@@ -516,7 +516,7 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk,
/* Copied from af_unix:unix_dgram_sendmsg, and adapted to CAIF */
static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
- struct msghdr *msg, size_t len)
+ struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -591,7 +591,7 @@ err:
* and other minor adaptations.
*/
static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
- struct msghdr *msg, size_t len)
+ struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -670,7 +670,7 @@ out_err:
}
static int setsockopt(struct socket *sock,
- int lvl, int opt, char __user *ov, unsigned int ol)
+ int lvl, int opt, char __user *ov, unsigned int ol)
{
struct sock *sk = sock->sk;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -932,7 +932,7 @@ static int caif_release(struct socket *sock)
/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
static unsigned int caif_poll(struct file *file,
- struct socket *sock, poll_table *wait)
+ struct socket *sock, poll_table *wait)
{
struct sock *sk = sock->sk;
unsigned int mask;
@@ -1022,7 +1022,7 @@ static void caif_sock_destructor(struct sock *sk)
}
static int caif_create(struct net *net, struct socket *sock, int protocol,
- int kern)
+ int kern)
{
struct sock *sk = NULL;
struct caifsock *cf_sk = NULL;
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index ef8ebaa993cf..d76278d644b8 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -75,7 +75,7 @@ static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt)
}
static void cfusbl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid)
+ int phyid)
{
if (layr->up && layr->up->ctrlcmd)
layr->up->ctrlcmd(layr->up, ctrl, layr->id);
@@ -121,7 +121,7 @@ static struct packet_type caif_usb_type __read_mostly = {
};
static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
- void *arg)
+ void *arg)
{
struct net_device *dev = arg;
struct caif_dev_common common;
diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c
index f1dbddb95a6c..246ac3aa8de5 100644
--- a/net/caif/cfcnfg.c
+++ b/net/caif/cfcnfg.c
@@ -61,11 +61,11 @@ struct cfcnfg {
};
static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id,
- enum cfctrl_srv serv, u8 phyid,
- struct cflayer *adapt_layer);
+ enum cfctrl_srv serv, u8 phyid,
+ struct cflayer *adapt_layer);
static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id);
static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id,
- struct cflayer *adapt_layer);
+ struct cflayer *adapt_layer);
static void cfctrl_resp_func(void);
static void cfctrl_enum_resp(void);
@@ -131,7 +131,7 @@ static void cfctrl_resp_func(void)
}
static struct cfcnfg_phyinfo *cfcnfg_get_phyinfo_rcu(struct cfcnfg *cnfg,
- u8 phyid)
+ u8 phyid)
{
struct cfcnfg_phyinfo *phy;
@@ -216,8 +216,8 @@ static const int protohead[CFCTRL_SRV_MASK] = {
static int caif_connect_req_to_link_param(struct cfcnfg *cnfg,
- struct caif_connect_request *s,
- struct cfctrl_link_param *l)
+ struct caif_connect_request *s,
+ struct cfctrl_link_param *l)
{
struct dev_info *dev_info;
enum cfcnfg_phy_preference pref;
@@ -301,8 +301,7 @@ static int caif_connect_req_to_link_param(struct cfcnfg *cnfg,
int caif_connect_client(struct net *net, struct caif_connect_request *conn_req,
struct cflayer *adap_layer, int *ifindex,
- int *proto_head,
- int *proto_tail)
+ int *proto_head, int *proto_tail)
{
struct cflayer *frml;
struct cfcnfg_phyinfo *phy;
@@ -364,7 +363,7 @@ unlock:
EXPORT_SYMBOL(caif_connect_client);
static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id,
- struct cflayer *adapt_layer)
+ struct cflayer *adapt_layer)
{
if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL)
adapt_layer->ctrlcmd(adapt_layer,
@@ -526,7 +525,7 @@ out_err:
EXPORT_SYMBOL(cfcnfg_add_phy_layer);
int cfcnfg_set_phy_state(struct cfcnfg *cnfg, struct cflayer *phy_layer,
- bool up)
+ bool up)
{
struct cfcnfg_phyinfo *phyinfo;
diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c
index a376ec1ac0a7..9cd057c59c59 100644
--- a/net/caif/cfctrl.c
+++ b/net/caif/cfctrl.c
@@ -20,12 +20,12 @@
#ifdef CAIF_NO_LOOP
static int handle_loop(struct cfctrl *ctrl,
- int cmd, struct cfpkt *pkt){
+ int cmd, struct cfpkt *pkt){
return -1;
}
#else
static int handle_loop(struct cfctrl *ctrl,
- int cmd, struct cfpkt *pkt);
+ int cmd, struct cfpkt *pkt);
#endif
static int cfctrl_recv(struct cflayer *layr, struct cfpkt *pkt);
static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
@@ -72,7 +72,7 @@ void cfctrl_remove(struct cflayer *layer)
}
static bool param_eq(const struct cfctrl_link_param *p1,
- const struct cfctrl_link_param *p2)
+ const struct cfctrl_link_param *p2)
{
bool eq =
p1->linktype == p2->linktype &&
@@ -197,8 +197,8 @@ void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid)
}
int cfctrl_linkup_request(struct cflayer *layer,
- struct cfctrl_link_param *param,
- struct cflayer *user_layer)
+ struct cfctrl_link_param *param,
+ struct cflayer *user_layer)
{
struct cfctrl *cfctrl = container_obj(layer);
u32 tmp32;
@@ -301,7 +301,7 @@ int cfctrl_linkup_request(struct cflayer *layer,
}
int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid,
- struct cflayer *client)
+ struct cflayer *client)
{
int ret;
struct cfpkt *pkt;
@@ -555,7 +555,7 @@ error:
}
static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid)
+ int phyid)
{
struct cfctrl *this = container_obj(layr);
switch (ctrl) {
diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c
index 0a7df7ef062d..204c5e226a61 100644
--- a/net/caif/cffrml.c
+++ b/net/caif/cffrml.c
@@ -28,7 +28,7 @@ struct cffrml {
static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt);
static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt);
static void cffrml_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid);
+ int phyid);
static u32 cffrml_rcv_error;
static u32 cffrml_rcv_checsum_error;
@@ -167,7 +167,7 @@ static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt)
}
static void cffrml_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid)
+ int phyid)
{
if (layr->up && layr->up->ctrlcmd)
layr->up->ctrlcmd(layr->up, ctrl, layr->id);
diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c
index 94b08612a4d8..154d9f8f964c 100644
--- a/net/caif/cfmuxl.c
+++ b/net/caif/cfmuxl.c
@@ -42,7 +42,7 @@ struct cfmuxl {
static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt);
static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt);
static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid);
+ int phyid);
static struct cflayer *get_up(struct cfmuxl *muxl, u16 id);
struct cflayer *cfmuxl_create(void)
@@ -244,7 +244,7 @@ static int cfmuxl_transmit(struct cflayer *layr, struct cfpkt *pkt)
}
static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid)
+ int phyid)
{
struct cfmuxl *muxl = container_obj(layr);
struct cflayer *layer;
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 863dedd91bb6..e8f9c149504d 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -266,8 +266,8 @@ inline u16 cfpkt_getlen(struct cfpkt *pkt)
}
inline u16 cfpkt_iterate(struct cfpkt *pkt,
- u16 (*iter_func)(u16, void *, u16),
- u16 data)
+ u16 (*iter_func)(u16, void *, u16),
+ u16 data)
{
/*
* Don't care about the performance hit of linearizing,
@@ -307,8 +307,8 @@ int cfpkt_setlen(struct cfpkt *pkt, u16 len)
}
struct cfpkt *cfpkt_append(struct cfpkt *dstpkt,
- struct cfpkt *addpkt,
- u16 expectlen)
+ struct cfpkt *addpkt,
+ u16 expectlen)
{
struct sk_buff *dst = pkt_to_skb(dstpkt);
struct sk_buff *add = pkt_to_skb(addpkt);
diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c
index 2b563ad04597..db51830c8587 100644
--- a/net/caif/cfrfml.c
+++ b/net/caif/cfrfml.c
@@ -43,7 +43,7 @@ static void cfrfml_release(struct cflayer *layer)
}
struct cflayer *cfrfml_create(u8 channel_id, struct dev_info *dev_info,
- int mtu_size)
+ int mtu_size)
{
int tmp;
struct cfrfml *this = kzalloc(sizeof(struct cfrfml), GFP_ATOMIC);
@@ -69,7 +69,7 @@ struct cflayer *cfrfml_create(u8 channel_id, struct dev_info *dev_info,
}
static struct cfpkt *rfm_append(struct cfrfml *rfml, char *seghead,
- struct cfpkt *pkt, int *err)
+ struct cfpkt *pkt, int *err)
{
struct cfpkt *tmppkt;
*err = -EPROTO;
diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c
index 8e68b97f13ee..147c232b1285 100644
--- a/net/caif/cfserl.c
+++ b/net/caif/cfserl.c
@@ -29,7 +29,7 @@ struct cfserl {
static int cfserl_receive(struct cflayer *layr, struct cfpkt *pkt);
static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt);
static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid);
+ int phyid);
struct cflayer *cfserl_create(int instance, bool use_stx)
{
@@ -182,7 +182,7 @@ static int cfserl_transmit(struct cflayer *layer, struct cfpkt *newpkt)
}
static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid)
+ int phyid)
{
layr->up->ctrlcmd(layr->up, ctrl, phyid);
}
diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c
index ba217e90765e..95f7f5ea30ef 100644
--- a/net/caif/cfsrvl.c
+++ b/net/caif/cfsrvl.c
@@ -25,7 +25,7 @@
#define container_obj(layr) container_of(layr, struct cfsrvl, layer)
static void cfservl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
- int phyid)
+ int phyid)
{
struct cfsrvl *service = container_obj(layr);
@@ -158,10 +158,9 @@ static void cfsrvl_release(struct cflayer *layer)
}
void cfsrvl_init(struct cfsrvl *service,
- u8 channel_id,
- struct dev_info *dev_info,
- bool supports_flowctrl
- )
+ u8 channel_id,
+ struct dev_info *dev_info,
+ bool supports_flowctrl)
{
caif_assert(offsetof(struct cfsrvl, layer) == 0);
service->open = false;
@@ -207,8 +206,8 @@ void caif_free_client(struct cflayer *adap_layer)
EXPORT_SYMBOL(caif_free_client);
void caif_client_register_refcnt(struct cflayer *adapt_layer,
- void (*hold)(struct cflayer *lyr),
- void (*put)(struct cflayer *lyr))
+ void (*hold)(struct cflayer *lyr),
+ void (*put)(struct cflayer *lyr))
{
struct cfsrvl *service;
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index e597733affb8..26a4e4e3a767 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -167,7 +167,7 @@ static void chnl_put(struct cflayer *lyr)
}
static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow,
- int phyid)
+ int phyid)
{
struct chnl_net *priv = container_of(layr, struct chnl_net, chnl);
pr_debug("NET flowctrl func called flow: %s\n",
@@ -443,7 +443,7 @@ nla_put_failure:
}
static void caif_netlink_parms(struct nlattr *data[],
- struct caif_connect_request *conn_req)
+ struct caif_connect_request *conn_req)
{
if (!data) {
pr_warn("no params data found\n");
@@ -488,7 +488,7 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev,
}
static int ipcaif_changelink(struct net_device *dev, struct nlattr *tb[],
- struct nlattr *data[])
+ struct nlattr *data[])
{
struct chnl_net *caifdev;
ASSERT_RTNL();
diff --git a/net/can/af_can.c b/net/can/af_can.c
index c48e5220bbac..c4e50852c9f4 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -525,7 +525,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
d = find_dev_rcv_lists(dev);
if (!d) {
- printk(KERN_ERR "BUG: receive list not found for "
+ pr_err("BUG: receive list not found for "
"dev %s, id %03X, mask %03X\n",
DNAME(dev), can_id, mask);
goto out;
@@ -546,16 +546,13 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
}
/*
- * Check for bugs in CAN protocol implementations:
- * If no matching list item was found, the list cursor variable next
- * will be NULL, while r will point to the last item of the list.
+ * Check for bugs in CAN protocol implementations using af_can.c:
+ * 'r' will be NULL if no matching list item was found for removal.
*/
if (!r) {
- printk(KERN_ERR "BUG: receive list entry not found for "
- "dev %s, id %03X, mask %03X\n",
- DNAME(dev), can_id, mask);
- r = NULL;
+ WARN(1, "BUG: receive list entry not found for dev %s, "
+ "id %03X, mask %03X\n", DNAME(dev), can_id, mask);
goto out;
}
@@ -749,8 +746,7 @@ int can_proto_register(const struct can_proto *cp)
int err = 0;
if (proto < 0 || proto >= CAN_NPROTO) {
- printk(KERN_ERR "can: protocol number %d out of range\n",
- proto);
+ pr_err("can: protocol number %d out of range\n", proto);
return -EINVAL;
}
@@ -761,8 +757,7 @@ int can_proto_register(const struct can_proto *cp)
mutex_lock(&proto_tab_lock);
if (proto_tab[proto]) {
- printk(KERN_ERR "can: protocol %d already registered\n",
- proto);
+ pr_err("can: protocol %d already registered\n", proto);
err = -EBUSY;
} else
RCU_INIT_POINTER(proto_tab[proto], cp);
@@ -816,11 +811,8 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
/* create new dev_rcv_lists for this device */
d = kzalloc(sizeof(*d), GFP_KERNEL);
- if (!d) {
- printk(KERN_ERR
- "can: allocation of receive list failed\n");
+ if (!d)
return NOTIFY_DONE;
- }
BUG_ON(dev->ml_priv);
dev->ml_priv = d;
@@ -838,8 +830,8 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg,
dev->ml_priv = NULL;
}
} else
- printk(KERN_ERR "can: notifier: receive list not "
- "found for dev %s\n", dev->name);
+ pr_err("can: notifier: receive list not found for dev "
+ "%s\n", dev->name);
spin_unlock(&can_rcvlists_lock);
@@ -927,7 +919,7 @@ static __exit void can_exit(void)
/* remove created dev_rcv_lists from still registered CAN devices */
rcu_read_lock();
for_each_netdev_rcu(&init_net, dev) {
- if (dev->type == ARPHRD_CAN && dev->ml_priv){
+ if (dev->type == ARPHRD_CAN && dev->ml_priv) {
struct dev_rcv_lists *d = dev->ml_priv;
diff --git a/net/can/gw.c b/net/can/gw.c
index 2d117dc5ebea..2dc619db805a 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -778,8 +778,7 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
return 0;
}
-static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
- void *arg)
+static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct rtcanmsg *r;
struct cgw_job *gwj;
@@ -868,7 +867,7 @@ static void cgw_remove_all_jobs(void)
}
}
-static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct cgw_job *gwj = NULL;
struct hlist_node *nx;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 368f9c3f9dc6..ebba65d7e0da 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -749,7 +749,9 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR;
+ mask |= POLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
diff --git a/net/core/dev.c b/net/core/dev.c
index 13e6447f0398..63e25332924d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2206,16 +2206,8 @@ out:
}
EXPORT_SYMBOL(skb_checksum_help);
-/**
- * skb_mac_gso_segment - mac layer segmentation handler.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- */
-struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
+__be16 skb_network_protocol(struct sk_buff *skb)
{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
@@ -2223,13 +2215,31 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
struct vlan_hdr *vh;
if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
- return ERR_PTR(-EINVAL);
+ return 0;
vh = (struct vlan_hdr *)(skb->data + vlan_depth);
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
}
+ return type;
+}
+
+/**
+ * skb_mac_gso_segment - mac layer segmentation handler.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ */
+struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+ struct packet_offload *ptype;
+ __be16 type = skb_network_protocol(skb);
+
+ if (unlikely(!type))
+ return ERR_PTR(-EINVAL);
+
__skb_pull(skb, skb->mac_len);
rcu_read_lock();
@@ -2396,24 +2406,12 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
return 0;
}
-static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
-{
- return ((features & NETIF_F_GEN_CSUM) ||
- ((features & NETIF_F_V4_CSUM) &&
- protocol == htons(ETH_P_IP)) ||
- ((features & NETIF_F_V6_CSUM) &&
- protocol == htons(ETH_P_IPV6)) ||
- ((features & NETIF_F_FCOE_CRC) &&
- protocol == htons(ETH_P_FCOE)));
-}
-
static netdev_features_t harmonize_features(struct sk_buff *skb,
__be16 protocol, netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, protocol)) {
features &= ~NETIF_F_ALL_CSUM;
- features &= ~NETIF_F_SG;
} else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
}
@@ -2588,6 +2586,7 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
*/
if (shinfo->gso_size) {
unsigned int hdr_len;
+ u16 gso_segs = shinfo->gso_segs;
/* mac layer + network layer */
hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
@@ -2597,7 +2596,12 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
hdr_len += tcp_hdrlen(skb);
else
hdr_len += sizeof(struct udphdr);
- qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len;
+
+ if (shinfo->gso_type & SKB_GSO_DODGY)
+ gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
+ shinfo->gso_size);
+
+ qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len;
}
}
@@ -3325,7 +3329,7 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
* netdev_rx_handler_unregister - unregister receive handler
* @dev: device to unregister a handler from
*
- * Unregister a receive hander from a device.
+ * Unregister a receive handler from a device.
*
* The caller must hold the rtnl_mutex.
*/
@@ -4062,6 +4066,9 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
napi->gro_list = NULL;
napi->skb = NULL;
napi->poll = poll;
+ if (weight > NAPI_POLL_WEIGHT)
+ pr_err_once("netif_napi_add() called with weight %d on device %s\n",
+ weight, dev->name);
napi->weight = weight;
list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
@@ -4923,20 +4930,25 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
- /* Fix illegal SG+CSUM combinations. */
- if ((features & NETIF_F_SG) &&
- !(features & NETIF_F_ALL_CSUM)) {
- netdev_dbg(dev,
- "Dropping NETIF_F_SG since no checksum feature.\n");
- features &= ~NETIF_F_SG;
- }
-
/* TSO requires that SG is present as well. */
if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) {
netdev_dbg(dev, "Dropping TSO features since no SG feature.\n");
features &= ~NETIF_F_ALL_TSO;
}
+ if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) &&
+ !(features & NETIF_F_IP_CSUM)) {
+ netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n");
+ features &= ~NETIF_F_TSO;
+ features &= ~NETIF_F_TSO_ECN;
+ }
+
+ if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) &&
+ !(features & NETIF_F_IPV6_CSUM)) {
+ netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n");
+ features &= ~NETIF_F_TSO6;
+ }
+
/* TSO ECN requires that TSO is present as well. */
if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN)
features &= ~NETIF_F_TSO_ECN;
@@ -5204,6 +5216,10 @@ int register_netdevice(struct net_device *dev)
*/
dev->vlan_features |= NETIF_F_HIGHDMA;
+ /* Make NETIF_F_SG inheritable to tunnel devices.
+ */
+ dev->hw_enc_features |= NETIF_F_SG;
+
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 3e9b2c3e30f0..adc1351e6873 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -78,6 +78,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation",
[NETIF_F_FSO_BIT] = "tx-fcoe-segmentation",
[NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation",
+ [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 58a4ba27dfe3..d5a9f8ead0d8 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -266,7 +266,7 @@ errout:
return err;
}
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -415,7 +415,7 @@ errout:
return err;
}
-static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_rule_hdr *frh = nlmsg_data(nlh);
diff --git a/net/core/filter.c b/net/core/filter.c
index 2e20b55a7830..dad2a178f9f8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -348,6 +348,9 @@ load_b:
case BPF_S_ANC_VLAN_TAG_PRESENT:
A = !!vlan_tx_tag_present(skb);
continue;
+ case BPF_S_ANC_PAY_OFFSET:
+ A = __skb_get_poff(skb);
+ continue;
case BPF_S_ANC_NLATTR: {
struct nlattr *nla;
@@ -612,6 +615,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
ANCILLARY(ALU_XOR_X);
ANCILLARY(VLAN_TAG);
ANCILLARY(VLAN_TAG_PRESENT);
+ ANCILLARY(PAY_OFFSET);
}
/* ancillary operation unknown or unsupported */
@@ -814,6 +818,7 @@ static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
[BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
[BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS,
[BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS,
[BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN,
[BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND,
[BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND,
diff --git a/net/core/flow.c b/net/core/flow.c
index 2bfd081c59f7..7102f166482d 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -323,6 +323,24 @@ static void flow_cache_flush_tasklet(unsigned long data)
complete(&info->completion);
}
+/*
+ * Return whether a cpu needs flushing. Conservatively, we assume
+ * the presence of any entries means the core may require flushing,
+ * since the flow_cache_ops.check() function may assume it's running
+ * on the same core as the per-cpu cache component.
+ */
+static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
+{
+ struct flow_cache_percpu *fcp;
+ int i;
+
+ fcp = per_cpu_ptr(fc->percpu, cpu);
+ for (i = 0; i < flow_cache_hash_size(fc); i++)
+ if (!hlist_empty(&fcp->hash_table[i]))
+ return 0;
+ return 1;
+}
+
static void flow_cache_flush_per_cpu(void *data)
{
struct flow_flush_info *info = data;
@@ -337,22 +355,40 @@ void flow_cache_flush(void)
{
struct flow_flush_info info;
static DEFINE_MUTEX(flow_flush_sem);
+ cpumask_var_t mask;
+ int i, self;
+
+ /* Track which cpus need flushing to avoid disturbing all cores. */
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return;
+ cpumask_clear(mask);
/* Don't want cpus going down or up during this. */
get_online_cpus();
mutex_lock(&flow_flush_sem);
info.cache = &flow_cache_global;
- atomic_set(&info.cpuleft, num_online_cpus());
+ for_each_online_cpu(i)
+ if (!flow_cache_percpu_empty(info.cache, i))
+ cpumask_set_cpu(i, mask);
+ atomic_set(&info.cpuleft, cpumask_weight(mask));
+ if (atomic_read(&info.cpuleft) == 0)
+ goto done;
+
init_completion(&info.completion);
local_bh_disable();
- smp_call_function(flow_cache_flush_per_cpu, &info, 0);
- flow_cache_flush_tasklet((unsigned long)&info);
+ self = cpumask_test_and_clear_cpu(smp_processor_id(), mask);
+ on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0);
+ if (self)
+ flow_cache_flush_tasklet((unsigned long)&info);
local_bh_enable();
wait_for_completion(&info.completion);
+
+done:
mutex_unlock(&flow_flush_sem);
put_online_cpus();
+ free_cpumask_var(mask);
}
static void flow_cache_flush_task(struct work_struct *work)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e187bf06d673..00ee068efc1c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,10 @@
#include <linux/if_vlan.h>
#include <net/ip.h>
#include <net/ipv6.h>
+#include <linux/igmp.h>
+#include <linux/icmp.h>
+#include <linux/sctp.h>
+#include <linux/dccp.h>
#include <linux/if_tunnel.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
@@ -119,6 +123,17 @@ ipv6:
nhoff += 4;
if (hdr->flags & GRE_SEQ)
nhoff += 4;
+ if (proto == htons(ETH_P_TEB)) {
+ const struct ethhdr *eth;
+ struct ethhdr _eth;
+
+ eth = skb_header_pointer(skb, nhoff,
+ sizeof(_eth), &_eth);
+ if (!eth)
+ return false;
+ proto = eth->h_proto;
+ nhoff += sizeof(*eth);
+ }
goto again;
}
break;
@@ -217,6 +232,59 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
}
EXPORT_SYMBOL(__skb_tx_hash);
+/* __skb_get_poff() returns the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
+ * truncate packets without needing to push actual payload to the user
+ * space and can analyze headers only, instead.
+ */
+u32 __skb_get_poff(const struct sk_buff *skb)
+{
+ struct flow_keys keys;
+ u32 poff = 0;
+
+ if (!skb_flow_dissect(skb, &keys))
+ return 0;
+
+ poff += keys.thoff;
+ switch (keys.ip_proto) {
+ case IPPROTO_TCP: {
+ const struct tcphdr *tcph;
+ struct tcphdr _tcph;
+
+ tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
+ if (!tcph)
+ return poff;
+
+ poff += max_t(u32, sizeof(struct tcphdr), tcph->doff * 4);
+ break;
+ }
+ case IPPROTO_UDP:
+ case IPPROTO_UDPLITE:
+ poff += sizeof(struct udphdr);
+ break;
+ /* For the rest, we do not really care about header
+ * extensions at this point for now.
+ */
+ case IPPROTO_ICMP:
+ poff += sizeof(struct icmphdr);
+ break;
+ case IPPROTO_ICMPV6:
+ poff += sizeof(struct icmp6hdr);
+ break;
+ case IPPROTO_IGMP:
+ poff += sizeof(struct igmphdr);
+ break;
+ case IPPROTO_DCCP:
+ poff += sizeof(struct dccp_hdr);
+ break;
+ case IPPROTO_SCTP:
+ poff += sizeof(struct sctphdr);
+ break;
+ }
+
+ return poff;
+}
+
static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3863b8f639c5..c72a646d9f44 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1613,7 +1613,7 @@ int neigh_table_clear(struct neigh_table *tbl)
}
EXPORT_SYMBOL(neigh_table_clear);
-static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -1677,7 +1677,7 @@ out:
return err;
}
-static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -1955,7 +1955,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
[NDTPA_LOCKTIME] = { .type = NLA_U64 },
};
-static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct neigh_table *tbl;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 3174f1998ee6..569d355fec3e 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -271,7 +271,7 @@ static int ptype_seq_show(struct seq_file *seq, void *v)
else
seq_printf(seq, "%04x", ntohs(pt->type));
- seq_printf(seq, " %-8s %pF\n",
+ seq_printf(seq, " %-8s %pf\n",
pt->dev ? pt->dev->name : "", pt->func);
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index fa32899006a2..a3a17aed3639 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -47,7 +47,7 @@ static struct sk_buff_head skb_pool;
static atomic_t trapped;
-static struct srcu_struct netpoll_srcu;
+DEFINE_STATIC_SRCU(netpoll_srcu);
#define USEC_PER_POLL 50
#define NETPOLL_RX_ENABLED 1
@@ -1212,7 +1212,6 @@ EXPORT_SYMBOL(netpoll_setup);
static int __init netpoll_init(void)
{
skb_queue_head_init(&skb_pool);
- init_srcu_struct(&netpoll_srcu);
return 0;
}
core_initcall(netpoll_init);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b65441da74ab..589d0abb34a0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -517,32 +517,6 @@ out:
return err;
}
-static const int rtm_min[RTM_NR_FAMILIES] =
-{
- [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
- [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)),
- [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)),
- [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)),
- [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
- [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
- [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)),
- [RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)),
- [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
- [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
-};
-
-static const int rta_max[RTM_NR_FAMILIES] =
-{
- [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX,
- [RTM_FAM(RTM_NEWADDR)] = IFA_MAX,
- [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX,
- [RTM_FAM(RTM_NEWRULE)] = FRA_MAX,
- [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX,
- [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX,
- [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX,
- [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX,
-};
-
int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
{
struct sock *rtnl = net->rtnl;
@@ -1539,7 +1513,7 @@ errout:
return err;
}
-static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -1580,7 +1554,7 @@ errout:
return err;
}
-static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
@@ -1711,7 +1685,7 @@ static int rtnl_group_changelink(struct net *net, int group,
return 0;
}
-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
@@ -1866,7 +1840,7 @@ out:
}
}
-static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -1957,8 +1931,11 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
if (rtnl_msg_handlers[idx] == NULL ||
rtnl_msg_handlers[idx][type].dumpit == NULL)
continue;
- if (idx > s_idx)
+ if (idx > s_idx) {
memset(&cb->args[0], 0, sizeof(cb->args));
+ cb->prev_seq = 0;
+ cb->seq = 0;
+ }
if (rtnl_msg_handlers[idx][type].dumpit(skb, cb))
break;
}
@@ -2051,7 +2028,39 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
-static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+/**
+ * ndo_dflt_fdb_add - default netdevice operation to add an FDB entry
+ */
+int ndo_dflt_fdb_add(struct ndmsg *ndm,
+ struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr,
+ u16 flags)
+{
+ int err = -EINVAL;
+
+ /* If aging addresses are supported device will need to
+ * implement its own handler for this.
+ */
+ if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+ pr_info("%s: FDB only supports static addresses\n", dev->name);
+ return err;
+ }
+
+ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+ err = dev_uc_add_excl(dev, addr);
+ else if (is_multicast_ether_addr(addr))
+ err = dev_mc_add_excl(dev, addr);
+
+ /* Only return duplicate errors if NLM_F_EXCL is set */
+ if (err == -EEXIST && !(flags & NLM_F_EXCL))
+ err = 0;
+
+ return err;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_add);
+
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -2082,7 +2091,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
addr = nla_data(tb[NDA_LLADDR]);
- if (!is_valid_ether_addr(addr)) {
+ if (is_zero_ether_addr(addr)) {
pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
return -EINVAL;
}
@@ -2103,10 +2112,13 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
/* Embedded bridge, macvlan, and any other device support */
- if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) {
- err = dev->netdev_ops->ndo_fdb_add(ndm, tb,
- dev, addr,
- nlh->nlmsg_flags);
+ if ((ndm->ndm_flags & NTF_SELF)) {
+ if (dev->netdev_ops->ndo_fdb_add)
+ err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+ nlh->nlmsg_flags);
+ else
+ err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+ nlh->nlmsg_flags);
if (!err) {
rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH);
@@ -2117,7 +2129,36 @@ out:
return err;
}
-static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+/**
+ * ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry
+ */
+int ndo_dflt_fdb_del(struct ndmsg *ndm,
+ struct nlattr *tb[],
+ struct net_device *dev,
+ const unsigned char *addr)
+{
+ int err = -EOPNOTSUPP;
+
+ /* If aging addresses are supported device will need to
+ * implement its own handler for this.
+ */
+ if (ndm->ndm_state & NUD_PERMANENT) {
+ pr_info("%s: FDB only supports static addresses\n", dev->name);
+ return -EINVAL;
+ }
+
+ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+ err = dev_uc_del(dev, addr);
+ else if (is_multicast_ether_addr(addr))
+ err = dev_mc_del(dev, addr);
+ else
+ err = -EINVAL;
+
+ return err;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_del);
+
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
@@ -2174,8 +2215,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
}
/* Embedded bridge, macvlan, and any other device support */
- if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) {
- err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+ if (ndm->ndm_flags & NTF_SELF) {
+ if (dev->netdev_ops->ndo_fdb_del)
+ err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+ else
+ err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
if (!err) {
rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
@@ -2220,7 +2264,7 @@ skip:
* @dev: netdevice
*
* Default netdevice operation to dump the existing unicast address list.
- * Returns zero on success.
+ * Returns number of addresses from list put in skb.
*/
int ndo_dflt_fdb_dump(struct sk_buff *skb,
struct netlink_callback *cb,
@@ -2260,6 +2304,8 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (dev->netdev_ops->ndo_fdb_dump)
idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
+ else
+ idx = ndo_dflt_fdb_dump(skb, cb, dev, idx);
}
rcu_read_unlock();
@@ -2411,8 +2457,7 @@ errout:
return err;
}
-static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
- void *arg)
+static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -2482,8 +2527,7 @@ out:
return err;
}
-static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
- void *arg)
+static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
@@ -2553,10 +2597,6 @@ out:
return err;
}
-/* Protected by RTNL sempahore. */
-static struct rtattr **rta_buf;
-static int rtattr_max;
-
/* Process one rtnetlink message. */
static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -2564,7 +2604,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net *net = sock_net(skb->sk);
rtnl_doit_func doit;
int sz_idx, kind;
- int min_len;
int family;
int type;
int err;
@@ -2576,10 +2615,10 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
type -= RTM_BASE;
/* All the messages must have at least 1 byte length */
- if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg)))
+ if (nlmsg_len(nlh) < sizeof(struct rtgenmsg))
return 0;
- family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family;
+ family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
sz_idx = type>>2;
kind = type&3;
@@ -2612,32 +2651,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
}
- memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *)));
-
- min_len = rtm_min[sz_idx];
- if (nlh->nlmsg_len < min_len)
- return -EINVAL;
-
- if (nlh->nlmsg_len > min_len) {
- int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
- struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
-
- while (RTA_OK(attr, attrlen)) {
- unsigned int flavor = attr->rta_type & NLA_TYPE_MASK;
- if (flavor) {
- if (flavor > rta_max[sz_idx])
- return -EINVAL;
- rta_buf[flavor-1] = attr;
- }
- attr = RTA_NEXT(attr, attrlen);
- }
- }
-
doit = rtnl_get_doit(family, type);
if (doit == NULL)
return -EOPNOTSUPP;
- return doit(skb, nlh, (void *)&rta_buf[0]);
+ return doit(skb, nlh);
}
static void rtnetlink_rcv(struct sk_buff *skb)
@@ -2707,16 +2725,6 @@ static struct pernet_operations rtnetlink_net_ops = {
void __init rtnetlink_init(void)
{
- int i;
-
- rtattr_max = 0;
- for (i = 0; i < ARRAY_SIZE(rta_max); i++)
- if (rta_max[i] > rtattr_max)
- rtattr_max = rta_max[i];
- rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL);
- if (!rta_buf)
- panic("rtnetlink_init: cannot allocate rta_buf\n");
-
if (register_pernet_subsys(&rtnetlink_net_ops))
panic("rtnetlink_init: cannot initialize rtnetlink\n");
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 33245ef54c3b..ba646145cd5c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -673,6 +673,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->mac_header = old->mac_header;
new->inner_transport_header = old->inner_transport_header;
new->inner_network_header = old->inner_network_header;
+ new->inner_mac_header = old->inner_mac_header;
skb_dst_copy(new, old);
new->rxhash = old->rxhash;
new->ooo_okay = old->ooo_okay;
@@ -867,6 +868,18 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
}
EXPORT_SYMBOL(skb_clone);
+static void skb_headers_offset_update(struct sk_buff *skb, int off)
+{
+ /* {transport,network,mac}_header and tail are relative to skb->head */
+ skb->transport_header += off;
+ skb->network_header += off;
+ if (skb_mac_header_was_set(skb))
+ skb->mac_header += off;
+ skb->inner_transport_header += off;
+ skb->inner_network_header += off;
+ skb->inner_mac_header += off;
+}
+
static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
{
#ifndef NET_SKBUFF_DATA_USES_OFFSET
@@ -879,13 +892,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
__copy_skb_header(new, old);
#ifndef NET_SKBUFF_DATA_USES_OFFSET
- /* {transport,network,mac}_header are relative to skb->head */
- new->transport_header += offset;
- new->network_header += offset;
- if (skb_mac_header_was_set(new))
- new->mac_header += offset;
- new->inner_transport_header += offset;
- new->inner_network_header += offset;
+ skb_headers_offset_update(new, offset);
#endif
skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
@@ -1077,14 +1084,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
#else
skb->end = skb->head + size;
#endif
- /* {transport,network,mac}_header and tail are relative to skb->head */
skb->tail += off;
- skb->transport_header += off;
- skb->network_header += off;
- if (skb_mac_header_was_set(skb))
- skb->mac_header += off;
- skb->inner_transport_header += off;
- skb->inner_network_header += off;
+ skb_headers_offset_update(skb, off);
/* Only adjust this if it actually is csum_start rather than csum */
if (skb->ip_summed == CHECKSUM_PARTIAL)
skb->csum_start += nhead;
@@ -1180,12 +1181,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
if (n->ip_summed == CHECKSUM_PARTIAL)
n->csum_start += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- n->transport_header += off;
- n->network_header += off;
- if (skb_mac_header_was_set(skb))
- n->mac_header += off;
- n->inner_transport_header += off;
- n->inner_network_header += off;
+ skb_headers_offset_update(n, off);
#endif
return n;
@@ -2741,12 +2737,19 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
unsigned int tnl_hlen = skb_tnl_header_len(skb);
unsigned int headroom;
unsigned int len;
+ __be16 proto;
+ bool csum;
int sg = !!(features & NETIF_F_SG);
int nfrags = skb_shinfo(skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
int pos;
+ proto = skb_network_protocol(skb);
+ if (unlikely(!proto))
+ return ERR_PTR(-EINVAL);
+
+ csum = !!can_checksum_protocol(features, proto);
__skb_push(skb, doffset);
headroom = skb_headroom(skb);
pos = skb_headlen(skb);
@@ -2884,6 +2887,12 @@ skip_fraglist:
nskb->data_len = len - hsize;
nskb->len += nskb->data_len;
nskb->truesize += nskb->data_len;
+
+ if (!csum) {
+ nskb->csum = skb_checksum(nskb, doffset,
+ nskb->len - doffset, 0);
+ nskb->ip_summed = CHECKSUM_NONE;
+ }
} while ((offset += len) < skb->len);
return segs;
@@ -3361,6 +3370,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_headroom(skb) + start;
skb->csum_offset = off;
+ skb_set_transport_header(skb, start);
return true;
}
EXPORT_SYMBOL_GPL(skb_partial_csum_set);
diff --git a/net/core/sock.c b/net/core/sock.c
index b261a7977746..2ff5f3619a8d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -907,6 +907,10 @@ set_rcvbuf:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
break;
+ case SO_SELECT_ERR_QUEUE:
+ sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1160,6 +1164,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
break;
+ case SO_SELECT_ERR_QUEUE:
+ v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -1298,7 +1306,6 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
module_put(owner);
}
-#ifdef CONFIG_CGROUPS
#if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
void sock_update_classid(struct sock *sk, struct task_struct *task)
{
@@ -1321,7 +1328,6 @@ void sock_update_netprioidx(struct sock *sk, struct task_struct *task)
}
EXPORT_SYMBOL_GPL(sock_update_netprioidx);
#endif
-#endif
/**
* sk_alloc - All socket objects are allocated here
diff --git a/net/core/utils.c b/net/core/utils.c
index e3487e461939..3c7f5b51b979 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -17,6 +17,7 @@
#include <linux/module.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
+#include <linux/ctype.h>
#include <linux/inet.h>
#include <linux/mm.h>
#include <linux/net.h>
@@ -348,9 +349,7 @@ int mac_pton(const char *s, u8 *mac)
/* Don't dirty result unless string is valid MAC. */
for (i = 0; i < ETH_ALEN; i++) {
- if (!strchr("0123456789abcdefABCDEF", s[i * 3]))
- return 0;
- if (!strchr("0123456789abcdefABCDEF", s[i * 3 + 1]))
+ if (!isxdigit(s[i * 3]) || !isxdigit(s[i * 3 + 1]))
return 0;
if (i != ETH_ALEN - 1 && s[i * 3 + 2] != ':')
return 0;
diff --git a/net/dcb/dcbevent.c b/net/dcb/dcbevent.c
index 1d9eb7c60a68..4f72fc40bf02 100644
--- a/net/dcb/dcbevent.c
+++ b/net/dcb/dcbevent.c
@@ -20,6 +20,7 @@
#include <linux/rtnetlink.h>
#include <linux/notifier.h>
#include <linux/export.h>
+#include <net/dcbevent.h>
static ATOMIC_NOTIFIER_HEAD(dcbevent_notif_chain);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 21291f1abcd6..40d5829ed36a 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1658,7 +1658,7 @@ static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = {
[DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get },
};
-static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 4f9f5eb478f1..ebc54fef85a5 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -500,8 +500,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
return &rt->dst;
}
-static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
- struct request_values *rv_unused)
+static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
{
int err = -1;
struct sk_buff *skb;
@@ -658,7 +657,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
- if (dccp_v4_send_response(sk, req, NULL))
+ if (dccp_v4_send_response(sk, req))
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6e05981f271e..9c61f9c02fdb 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -213,8 +213,7 @@ out:
}
-static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
- struct request_values *rv_unused)
+static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -428,7 +427,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
- if (dccp_v6_send_response(sk, req, NULL))
+ if (dccp_v6_send_response(sk, req))
goto drop_and_free;
inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index c8da116d84a4..7d9197063ebb 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -563,7 +563,7 @@ static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = {
.len = IFNAMSIZ - 1 },
};
-static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
@@ -607,7 +607,7 @@ errout:
return err;
}
-static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index e36614eccc04..57dc159245ec 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -145,22 +145,10 @@ static inline struct dn_fib_info *dn_fib_find_info(const struct dn_fib_info *nfi
return NULL;
}
-__le16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type)
+static int dn_fib_count_nhs(const struct nlattr *attr)
{
- while(RTA_OK(attr,attrlen)) {
- if (attr->rta_type == type)
- return *(__le16*)RTA_DATA(attr);
- attr = RTA_NEXT(attr, attrlen);
- }
-
- return 0;
-}
-
-static int dn_fib_count_nhs(struct rtattr *rta)
-{
- int nhs = 0;
- struct rtnexthop *nhp = RTA_DATA(rta);
- int nhlen = RTA_PAYLOAD(rta);
+ struct rtnexthop *nhp = nla_data(attr);
+ int nhs = 0, nhlen = nla_len(attr);
while(nhlen >= (int)sizeof(struct rtnexthop)) {
if ((nhlen -= nhp->rtnh_len) < 0)
@@ -172,10 +160,11 @@ static int dn_fib_count_nhs(struct rtattr *rta)
return nhs;
}
-static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct rtattr *rta, const struct rtmsg *r)
+static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr,
+ const struct rtmsg *r)
{
- struct rtnexthop *nhp = RTA_DATA(rta);
- int nhlen = RTA_PAYLOAD(rta);
+ struct rtnexthop *nhp = nla_data(attr);
+ int nhlen = nla_len(attr);
change_nexthops(fi) {
int attrlen = nhlen - sizeof(struct rtnexthop);
@@ -187,7 +176,10 @@ static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct rtattr *rta, cons
nh->nh_weight = nhp->rtnh_hops + 1;
if (attrlen) {
- nh->nh_gw = dn_fib_get_attr16(RTNH_DATA(nhp), attrlen, RTA_GATEWAY);
+ struct nlattr *gw_attr;
+
+ gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY);
+ nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0;
}
nhp = RTNH_NEXT(nhp);
} endfor_nexthops(fi);
@@ -268,7 +260,8 @@ out:
}
-struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct dn_kern_rta *rta, const struct nlmsghdr *nlh, int *errp)
+struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *attrs[],
+ const struct nlmsghdr *nlh, int *errp)
{
int err;
struct dn_fib_info *fi = NULL;
@@ -281,11 +274,9 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct dn_kern_rta
if (dn_fib_props[r->rtm_type].scope > r->rtm_scope)
goto err_inval;
- if (rta->rta_mp) {
- nhs = dn_fib_count_nhs(rta->rta_mp);
- if (nhs == 0)
- goto err_inval;
- }
+ if (attrs[RTA_MULTIPATH] &&
+ (nhs = dn_fib_count_nhs(attrs[RTA_MULTIPATH])) == 0)
+ goto err_inval;
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct dn_fib_nh), GFP_KERNEL);
err = -ENOBUFS;
@@ -295,53 +286,65 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct dn_kern_rta
fi->fib_protocol = r->rtm_protocol;
fi->fib_nhs = nhs;
fi->fib_flags = r->rtm_flags;
- if (rta->rta_priority)
- fi->fib_priority = *rta->rta_priority;
- if (rta->rta_mx) {
- int attrlen = RTA_PAYLOAD(rta->rta_mx);
- struct rtattr *attr = RTA_DATA(rta->rta_mx);
- while(RTA_OK(attr, attrlen)) {
- unsigned int flavour = attr->rta_type;
+ if (attrs[RTA_PRIORITY])
+ fi->fib_priority = nla_get_u32(attrs[RTA_PRIORITY]);
+
+ if (attrs[RTA_METRICS]) {
+ struct nlattr *attr;
+ int rem;
- if (flavour) {
- if (flavour > RTAX_MAX)
+ nla_for_each_nested(attr, attrs[RTA_METRICS], rem) {
+ int type = nla_type(attr);
+
+ if (type) {
+ if (type > RTAX_MAX || nla_len(attr) < 4)
goto err_inval;
- fi->fib_metrics[flavour-1] = *(unsigned int *)RTA_DATA(attr);
+
+ fi->fib_metrics[type-1] = nla_get_u32(attr);
}
- attr = RTA_NEXT(attr, attrlen);
}
}
- if (rta->rta_prefsrc)
- memcpy(&fi->fib_prefsrc, rta->rta_prefsrc, 2);
- if (rta->rta_mp) {
- if ((err = dn_fib_get_nhs(fi, rta->rta_mp, r)) != 0)
+ if (attrs[RTA_PREFSRC])
+ fi->fib_prefsrc = nla_get_le16(attrs[RTA_PREFSRC]);
+
+ if (attrs[RTA_MULTIPATH]) {
+ if ((err = dn_fib_get_nhs(fi, attrs[RTA_MULTIPATH], r)) != 0)
goto failure;
- if (rta->rta_oif && fi->fib_nh->nh_oif != *rta->rta_oif)
+
+ if (attrs[RTA_OIF] &&
+ fi->fib_nh->nh_oif != nla_get_u32(attrs[RTA_OIF]))
goto err_inval;
- if (rta->rta_gw && memcmp(&fi->fib_nh->nh_gw, rta->rta_gw, 2))
+
+ if (attrs[RTA_GATEWAY] &&
+ fi->fib_nh->nh_gw != nla_get_le16(attrs[RTA_GATEWAY]))
goto err_inval;
} else {
struct dn_fib_nh *nh = fi->fib_nh;
- if (rta->rta_oif)
- nh->nh_oif = *rta->rta_oif;
- if (rta->rta_gw)
- memcpy(&nh->nh_gw, rta->rta_gw, 2);
+
+ if (attrs[RTA_OIF])
+ nh->nh_oif = nla_get_u32(attrs[RTA_OIF]);
+
+ if (attrs[RTA_GATEWAY])
+ nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]);
+
nh->nh_flags = r->rtm_flags;
nh->nh_weight = 1;
}
if (r->rtm_type == RTN_NAT) {
- if (rta->rta_gw == NULL || nhs != 1 || rta->rta_oif)
+ if (!attrs[RTA_GATEWAY] || nhs != 1 || attrs[RTA_OIF])
goto err_inval;
- memcpy(&fi->fib_nh->nh_gw, rta->rta_gw, 2);
+
+ fi->fib_nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]);
goto link_it;
}
if (dn_fib_props[r->rtm_type].error) {
- if (rta->rta_gw || rta->rta_oif || rta->rta_mp)
+ if (attrs[RTA_GATEWAY] || attrs[RTA_OIF] || attrs[RTA_MULTIPATH])
goto err_inval;
+
goto link_it;
}
@@ -367,8 +370,8 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct dn_kern_rta
}
if (fi->fib_prefsrc) {
- if (r->rtm_type != RTN_LOCAL || rta->rta_dst == NULL ||
- memcmp(&fi->fib_prefsrc, rta->rta_dst, 2))
+ if (r->rtm_type != RTN_LOCAL || !attrs[RTA_DST] ||
+ fi->fib_prefsrc != nla_get_le16(attrs[RTA_DST]))
if (dnet_addr_type(fi->fib_prefsrc) != RTN_LOCAL)
goto err_inval;
}
@@ -486,39 +489,21 @@ void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res)
spin_unlock_bh(&dn_fib_multipath_lock);
}
-
-static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta)
-{
- int i;
-
- for(i = 1; i <= RTA_MAX; i++) {
- struct rtattr *attr = rta[i-1];
- if (attr) {
- if (RTA_PAYLOAD(attr) < 4 && RTA_PAYLOAD(attr) != 2)
- return -EINVAL;
- if (i != RTA_MULTIPATH && i != RTA_METRICS &&
- i != RTA_TABLE)
- rta[i-1] = (struct rtattr *)RTA_DATA(attr);
- }
- }
-
- return 0;
-}
-
-static inline u32 rtm_get_table(struct rtattr **rta, u8 table)
+static inline u32 rtm_get_table(struct nlattr *attrs[], u8 table)
{
- if (rta[RTA_TABLE - 1])
- table = nla_get_u32((struct nlattr *) rta[RTA_TABLE - 1]);
+ if (attrs[RTA_TABLE])
+ table = nla_get_u32(attrs[RTA_TABLE]);
return table;
}
-static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct dn_fib_table *tb;
- struct rtattr **rta = arg;
- struct rtmsg *r = NLMSG_DATA(nlh);
+ struct rtmsg *r = nlmsg_data(nlh);
+ struct nlattr *attrs[RTA_MAX+1];
+ int err;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -526,22 +511,24 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *
if (!net_eq(net, &init_net))
return -EINVAL;
- if (dn_fib_check_attr(r, rta))
- return -EINVAL;
+ err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy);
+ if (err < 0)
+ return err;
- tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 0);
- if (tb)
- return tb->delete(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb));
+ tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 0);
+ if (!tb)
+ return -ESRCH;
- return -ESRCH;
+ return tb->delete(tb, r, attrs, nlh, &NETLINK_CB(skb));
}
-static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct dn_fib_table *tb;
- struct rtattr **rta = arg;
- struct rtmsg *r = NLMSG_DATA(nlh);
+ struct rtmsg *r = nlmsg_data(nlh);
+ struct nlattr *attrs[RTA_MAX+1];
+ int err;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -549,14 +536,15 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *
if (!net_eq(net, &init_net))
return -EINVAL;
- if (dn_fib_check_attr(r, rta))
- return -EINVAL;
+ err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy);
+ if (err < 0)
+ return err;
- tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 1);
- if (tb)
- return tb->insert(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb));
+ tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 1);
+ if (!tb)
+ return -ENOBUFS;
- return -ENOBUFS;
+ return tb->insert(tb, r, attrs, nlh, &NETLINK_CB(skb));
}
static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifaddr *ifa)
@@ -566,10 +554,31 @@ static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifad
struct nlmsghdr nlh;
struct rtmsg rtm;
} req;
- struct dn_kern_rta rta;
+ struct {
+ struct nlattr hdr;
+ __le16 dst;
+ } dst_attr = {
+ .dst = dst,
+ };
+ struct {
+ struct nlattr hdr;
+ __le16 prefsrc;
+ } prefsrc_attr = {
+ .prefsrc = ifa->ifa_local,
+ };
+ struct {
+ struct nlattr hdr;
+ u32 oif;
+ } oif_attr = {
+ .oif = ifa->ifa_dev->dev->ifindex,
+ };
+ struct nlattr *attrs[RTA_MAX+1] = {
+ [RTA_DST] = (struct nlattr *) &dst_attr,
+ [RTA_PREFSRC] = (struct nlattr * ) &prefsrc_attr,
+ [RTA_OIF] = (struct nlattr *) &oif_attr,
+ };
memset(&req.rtm, 0, sizeof(req.rtm));
- memset(&rta, 0, sizeof(rta));
if (type == RTN_UNICAST)
tb = dn_fib_get_table(RT_MIN_TABLE, 1);
@@ -591,14 +600,10 @@ static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifad
req.rtm.rtm_scope = (type != RTN_LOCAL ? RT_SCOPE_LINK : RT_SCOPE_HOST);
req.rtm.rtm_type = type;
- rta.rta_dst = &dst;
- rta.rta_prefsrc = &ifa->ifa_local;
- rta.rta_oif = &ifa->ifa_dev->dev->ifindex;
-
if (cmd == RTM_NEWROUTE)
- tb->insert(tb, &req.rtm, &rta, &req.nlh, NULL);
+ tb->insert(tb, &req.rtm, attrs, &req.nlh, NULL);
else
- tb->delete(tb, &req.rtm, &rta, &req.nlh, NULL);
+ tb->delete(tb, &req.rtm, attrs, &req.nlh, NULL);
}
static void dn_fib_add_ifaddr(struct dn_ifaddr *ifa)
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 5ac0e153ef83..fe32388ea24f 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1613,23 +1613,41 @@ errout:
return -EMSGSIZE;
}
+const struct nla_policy rtm_dn_policy[RTA_MAX + 1] = {
+ [RTA_DST] = { .type = NLA_U16 },
+ [RTA_SRC] = { .type = NLA_U16 },
+ [RTA_IIF] = { .type = NLA_U32 },
+ [RTA_OIF] = { .type = NLA_U32 },
+ [RTA_GATEWAY] = { .type = NLA_U16 },
+ [RTA_PRIORITY] = { .type = NLA_U32 },
+ [RTA_PREFSRC] = { .type = NLA_U16 },
+ [RTA_METRICS] = { .type = NLA_NESTED },
+ [RTA_MULTIPATH] = { .type = NLA_NESTED },
+ [RTA_TABLE] = { .type = NLA_U32 },
+ [RTA_MARK] = { .type = NLA_U32 },
+};
+
/*
* This is called by both endnodes and routers now.
*/
-static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg)
+static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
- struct rtattr **rta = arg;
struct rtmsg *rtm = nlmsg_data(nlh);
struct dn_route *rt = NULL;
struct dn_skb_cb *cb;
int err;
struct sk_buff *skb;
struct flowidn fld;
+ struct nlattr *tb[RTA_MAX+1];
if (!net_eq(net, &init_net))
return -EINVAL;
+ err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_dn_policy);
+ if (err < 0)
+ return err;
+
memset(&fld, 0, sizeof(fld));
fld.flowidn_proto = DNPROTO_NSP;
@@ -1639,12 +1657,14 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
skb_reset_mac_header(skb);
cb = DN_SKB_CB(skb);
- if (rta[RTA_SRC-1])
- memcpy(&fld.saddr, RTA_DATA(rta[RTA_SRC-1]), 2);
- if (rta[RTA_DST-1])
- memcpy(&fld.daddr, RTA_DATA(rta[RTA_DST-1]), 2);
- if (rta[RTA_IIF-1])
- memcpy(&fld.flowidn_iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));
+ if (tb[RTA_SRC])
+ fld.saddr = nla_get_le16(tb[RTA_SRC]);
+
+ if (tb[RTA_DST])
+ fld.daddr = nla_get_le16(tb[RTA_DST]);
+
+ if (tb[RTA_IIF])
+ fld.flowidn_iif = nla_get_u32(tb[RTA_IIF]);
if (fld.flowidn_iif) {
struct net_device *dev;
@@ -1669,10 +1689,9 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (!err && -rt->dst.error)
err = rt->dst.error;
} else {
- int oif = 0;
- if (rta[RTA_OIF - 1])
- memcpy(&oif, RTA_DATA(rta[RTA_OIF - 1]), sizeof(int));
- fld.flowidn_oif = oif;
+ if (tb[RTA_OIF])
+ fld.flowidn_oif = nla_get_u32(tb[RTA_OIF]);
+
err = dn_route_output_key((struct dst_entry **)&rt, &fld, 0);
}
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 6c2445bcaba1..b15c1d1720fb 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -19,7 +19,7 @@
#include <linux/sockios.h>
#include <linux/init.h>
#include <linux/skbuff.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/netdevice.h>
@@ -224,26 +224,27 @@ static struct dn_zone *dn_new_zone(struct dn_hash *table, int z)
}
-static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern_rta *rta, struct dn_fib_info *fi)
+static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct nlattr *attrs[], struct dn_fib_info *fi)
{
struct rtnexthop *nhp;
int nhlen;
- if (rta->rta_priority && *rta->rta_priority != fi->fib_priority)
+ if (attrs[RTA_PRIORITY] &&
+ nla_get_u32(attrs[RTA_PRIORITY]) != fi->fib_priority)
return 1;
- if (rta->rta_oif || rta->rta_gw) {
- if ((!rta->rta_oif || *rta->rta_oif == fi->fib_nh->nh_oif) &&
- (!rta->rta_gw || memcmp(rta->rta_gw, &fi->fib_nh->nh_gw, 2) == 0))
+ if (attrs[RTA_OIF] || attrs[RTA_GATEWAY]) {
+ if ((!attrs[RTA_OIF] || nla_get_u32(attrs[RTA_OIF]) == fi->fib_nh->nh_oif) &&
+ (!attrs[RTA_GATEWAY] || nla_get_le16(attrs[RTA_GATEWAY]) != fi->fib_nh->nh_gw))
return 0;
return 1;
}
- if (rta->rta_mp == NULL)
+ if (!attrs[RTA_MULTIPATH])
return 0;
- nhp = RTA_DATA(rta->rta_mp);
- nhlen = RTA_PAYLOAD(rta->rta_mp);
+ nhp = nla_data(attrs[RTA_MULTIPATH]);
+ nhlen = nla_len(attrs[RTA_MULTIPATH]);
for_nexthops(fi) {
int attrlen = nhlen - sizeof(struct rtnexthop);
@@ -254,7 +255,10 @@ static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern
if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif)
return 1;
if (attrlen) {
- gw = dn_fib_get_attr16(RTNH_DATA(nhp), attrlen, RTA_GATEWAY);
+ struct nlattr *gw_attr;
+
+ gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY);
+ gw = gw_attr ? nla_get_le16(gw_attr) : 0;
if (gw && gw != nh->nh_gw)
return 1;
@@ -488,7 +492,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (!net_eq(net, &init_net))
return 0;
- if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) &&
+ if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
((struct rtmsg *)nlmsg_data(cb->nlh))->rtm_flags&RTM_F_CLONED)
return dn_cache_dump(skb, cb);
@@ -517,7 +521,8 @@ out:
return skb->len;
}
-static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct dn_kern_rta *rta, struct nlmsghdr *n, struct netlink_skb_parms *req)
+static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct nlattr *attrs[],
+ struct nlmsghdr *n, struct netlink_skb_parms *req)
{
struct dn_hash *table = (struct dn_hash *)tb->data;
struct dn_fib_node *new_f, *f, **fp, **del_fp;
@@ -536,15 +541,14 @@ static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct
return -ENOBUFS;
dz_key_0(key);
- if (rta->rta_dst) {
- __le16 dst;
- memcpy(&dst, rta->rta_dst, 2);
+ if (attrs[RTA_DST]) {
+ __le16 dst = nla_get_le16(attrs[RTA_DST]);
if (dst & ~DZ_MASK(dz))
return -EINVAL;
key = dz_key(dst, dz);
}
- if ((fi = dn_fib_create_info(r, rta, n, &err)) == NULL)
+ if ((fi = dn_fib_create_info(r, attrs, n, &err)) == NULL)
return err;
if (dz->dz_nent > (dz->dz_divisor << 2) &&
@@ -654,7 +658,8 @@ out:
}
-static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct dn_kern_rta *rta, struct nlmsghdr *n, struct netlink_skb_parms *req)
+static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct nlattr *attrs[],
+ struct nlmsghdr *n, struct netlink_skb_parms *req)
{
struct dn_hash *table = (struct dn_hash*)tb->data;
struct dn_fib_node **fp, **del_fp, *f;
@@ -671,9 +676,8 @@ static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct
return -ESRCH;
dz_key_0(key);
- if (rta->rta_dst) {
- __le16 dst;
- memcpy(&dst, rta->rta_dst, 2);
+ if (attrs[RTA_DST]) {
+ __le16 dst = nla_get_le16(attrs[RTA_DST]);
if (dst & ~DZ_MASK(dz))
return -EINVAL;
key = dz_key(dst, dz);
@@ -703,7 +707,7 @@ static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct
(r->rtm_scope == RT_SCOPE_NOWHERE || f->fn_scope == r->rtm_scope) &&
(!r->rtm_protocol ||
fi->fib_protocol == r->rtm_protocol) &&
- dn_fib_nh_match(r, n, rta, fi) == 0)
+ dn_fib_nh_match(r, n, attrs, fi) == 0)
del_fp = fp;
}
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index dfe42012a044..2a7efe388344 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -19,7 +19,7 @@
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/spinlock.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
#include <linux/netfilter_decnet.h>
#include <net/sock.h>
@@ -39,21 +39,21 @@ static struct sk_buff *dnrmg_build_message(struct sk_buff *rt_skb, int *errp)
unsigned char *ptr;
struct nf_dn_rtmsg *rtm;
- size = NLMSG_SPACE(rt_skb->len);
- size += NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg));
- skb = alloc_skb(size, GFP_ATOMIC);
+ size = NLMSG_ALIGN(rt_skb->len) +
+ NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg));
+ skb = nlmsg_new(size, GFP_ATOMIC);
if (!skb) {
*errp = -ENOMEM;
return NULL;
}
old_tail = skb->tail;
- nlh = nlmsg_put(skb, 0, 0, 0, size - sizeof(*nlh), 0);
+ nlh = nlmsg_put(skb, 0, 0, 0, size, 0);
if (!nlh) {
kfree_skb(skb);
*errp = -ENOMEM;
return NULL;
}
- rtm = (struct nf_dn_rtmsg *)NLMSG_DATA(nlh);
+ rtm = (struct nf_dn_rtmsg *)nlmsg_data(nlh);
rtm->nfdn_ifindex = rt_skb->dev->ifindex;
ptr = NFDN_RTMSG(rtm);
skb_copy_from_linear_data(rt_skb, ptr, rt_skb->len);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 2bc62ea857c8..0eb5d5e76dfb 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -1,6 +1,7 @@
/*
* net/dsa/dsa.c - Hardware switch handling
* Copyright (c) 2008-2009 Marvell Semiconductor
+ * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -14,6 +15,9 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <net/dsa.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_platform.h>
#include "dsa_priv.h"
char dsa_driver_version[] = "0.1";
@@ -287,34 +291,239 @@ static struct net_device *dev_to_net_device(struct device *dev)
return NULL;
}
+#ifdef CONFIG_OF
+static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
+ struct dsa_chip_data *cd,
+ int chip_index,
+ struct device_node *link)
+{
+ int ret;
+ const __be32 *reg;
+ int link_port_addr;
+ int link_sw_addr;
+ struct device_node *parent_sw;
+ int len;
+
+ parent_sw = of_get_parent(link);
+ if (!parent_sw)
+ return -EINVAL;
+
+ reg = of_get_property(parent_sw, "reg", &len);
+ if (!reg || (len != sizeof(*reg) * 2))
+ return -EINVAL;
+
+ link_sw_addr = be32_to_cpup(reg + 1);
+
+ if (link_sw_addr >= pd->nr_chips)
+ return -EINVAL;
+
+ /* First time routing table allocation */
+ if (!cd->rtable) {
+ cd->rtable = kmalloc(pd->nr_chips * sizeof(s8), GFP_KERNEL);
+ if (!cd->rtable)
+ return -ENOMEM;
+
+ /* default to no valid uplink/downlink */
+ memset(cd->rtable, -1, pd->nr_chips * sizeof(s8));
+ }
+
+ reg = of_get_property(link, "reg", NULL);
+ if (!reg) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ link_port_addr = be32_to_cpup(reg);
+
+ cd->rtable[link_sw_addr] = link_port_addr;
+
+ return 0;
+out:
+ kfree(cd->rtable);
+ return ret;
+}
+
+static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
+{
+ int i;
+ int port_index;
+
+ for (i = 0; i < pd->nr_chips; i++) {
+ port_index = 0;
+ while (port_index < DSA_MAX_PORTS) {
+ if (pd->chip[i].port_names[port_index])
+ kfree(pd->chip[i].port_names[port_index]);
+ port_index++;
+ }
+ kfree(pd->chip[i].rtable);
+ }
+ kfree(pd->chip);
+}
+
+static int dsa_of_probe(struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ struct device_node *child, *mdio, *ethernet, *port, *link;
+ struct mii_bus *mdio_bus;
+ struct platform_device *ethernet_dev;
+ struct dsa_platform_data *pd;
+ struct dsa_chip_data *cd;
+ const char *port_name;
+ int chip_index, port_index;
+ const unsigned int *sw_addr, *port_reg;
+ int ret;
+
+ mdio = of_parse_phandle(np, "dsa,mii-bus", 0);
+ if (!mdio)
+ return -EINVAL;
+
+ mdio_bus = of_mdio_find_bus(mdio);
+ if (!mdio_bus)
+ return -EINVAL;
+
+ ethernet = of_parse_phandle(np, "dsa,ethernet", 0);
+ if (!ethernet)
+ return -EINVAL;
+
+ ethernet_dev = of_find_device_by_node(ethernet);
+ if (!ethernet_dev)
+ return -ENODEV;
+
+ pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+ if (!pd)
+ return -ENOMEM;
+
+ pdev->dev.platform_data = pd;
+ pd->netdev = &ethernet_dev->dev;
+ pd->nr_chips = of_get_child_count(np);
+ if (pd->nr_chips > DSA_MAX_SWITCHES)
+ pd->nr_chips = DSA_MAX_SWITCHES;
+
+ pd->chip = kzalloc(pd->nr_chips * sizeof(struct dsa_chip_data),
+ GFP_KERNEL);
+ if (!pd->chip) {
+ ret = -ENOMEM;
+ goto out_free;
+ }
+
+ chip_index = 0;
+ for_each_available_child_of_node(np, child) {
+ cd = &pd->chip[chip_index];
+
+ cd->mii_bus = &mdio_bus->dev;
+
+ sw_addr = of_get_property(child, "reg", NULL);
+ if (!sw_addr)
+ continue;
+
+ cd->sw_addr = be32_to_cpup(sw_addr);
+ if (cd->sw_addr > PHY_MAX_ADDR)
+ continue;
+
+ for_each_available_child_of_node(child, port) {
+ port_reg = of_get_property(port, "reg", NULL);
+ if (!port_reg)
+ continue;
+
+ port_index = be32_to_cpup(port_reg);
+
+ port_name = of_get_property(port, "label", NULL);
+ if (!port_name)
+ continue;
+
+ cd->port_names[port_index] = kstrdup(port_name,
+ GFP_KERNEL);
+ if (!cd->port_names[port_index]) {
+ ret = -ENOMEM;
+ goto out_free_chip;
+ }
+
+ link = of_parse_phandle(port, "link", 0);
+
+ if (!strcmp(port_name, "dsa") && link &&
+ pd->nr_chips > 1) {
+ ret = dsa_of_setup_routing_table(pd, cd,
+ chip_index, link);
+ if (ret)
+ goto out_free_chip;
+ }
+
+ if (port_index == DSA_MAX_PORTS)
+ break;
+ }
+ }
+
+ return 0;
+
+out_free_chip:
+ dsa_of_free_platform_data(pd);
+out_free:
+ kfree(pd);
+ pdev->dev.platform_data = NULL;
+ return ret;
+}
+
+static void dsa_of_remove(struct platform_device *pdev)
+{
+ struct dsa_platform_data *pd = pdev->dev.platform_data;
+
+ if (!pdev->dev.of_node)
+ return;
+
+ dsa_of_free_platform_data(pd);
+ kfree(pd);
+}
+#else
+static inline int dsa_of_probe(struct platform_device *pdev)
+{
+ return 0;
+}
+
+static inline void dsa_of_remove(struct platform_device *pdev)
+{
+}
+#endif
+
static int dsa_probe(struct platform_device *pdev)
{
static int dsa_version_printed;
struct dsa_platform_data *pd = pdev->dev.platform_data;
struct net_device *dev;
struct dsa_switch_tree *dst;
- int i;
+ int i, ret;
if (!dsa_version_printed++)
printk(KERN_NOTICE "Distributed Switch Architecture "
"driver version %s\n", dsa_driver_version);
+ if (pdev->dev.of_node) {
+ ret = dsa_of_probe(pdev);
+ if (ret)
+ return ret;
+
+ pd = pdev->dev.platform_data;
+ }
+
if (pd == NULL || pd->netdev == NULL)
return -EINVAL;
dev = dev_to_net_device(pd->netdev);
- if (dev == NULL)
- return -EINVAL;
+ if (dev == NULL) {
+ ret = -EINVAL;
+ goto out;
+ }
if (dev->dsa_ptr != NULL) {
dev_put(dev);
- return -EEXIST;
+ ret = -EEXIST;
+ goto out;
}
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
if (dst == NULL) {
dev_put(dev);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
platform_set_drvdata(pdev, dst);
@@ -366,6 +575,11 @@ static int dsa_probe(struct platform_device *pdev)
}
return 0;
+
+out:
+ dsa_of_remove(pdev);
+
+ return ret;
}
static int dsa_remove(struct platform_device *pdev)
@@ -385,6 +599,8 @@ static int dsa_remove(struct platform_device *pdev)
dsa_switch_destroy(ds);
}
+ dsa_of_remove(pdev);
+
return 0;
}
@@ -392,6 +608,12 @@ static void dsa_shutdown(struct platform_device *pdev)
{
}
+static const struct of_device_id dsa_of_match_table[] = {
+ { .compatible = "marvell,dsa", },
+ {}
+};
+MODULE_DEVICE_TABLE(of, dsa_of_match_table);
+
static struct platform_driver dsa_driver = {
.probe = dsa_probe,
.remove = dsa_remove,
@@ -399,6 +621,7 @@ static struct platform_driver dsa_driver = {
.driver = {
.name = "dsa",
.owner = THIS_MODULE,
+ .of_match_table = dsa_of_match_table,
},
};
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index a36c85eab5b4..5359560926bc 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -195,7 +195,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
if (netdev_uses_trailer_tags(dev))
return htons(ETH_P_TRAILER);
- if (ntohs(eth->h_proto) >= 1536)
+ if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN)
return eth->h_proto;
/*
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 43b95ca61114..e1b4580f78dd 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -104,6 +104,7 @@ static const u8 lowpan_llprefix[] = {0xfe, 0x80};
struct lowpan_dev_info {
struct net_device *real_dev; /* real WPAN device ptr */
struct mutex dev_list_mtx; /* mutex for list ops */
+ unsigned short fragment_tag;
};
struct lowpan_dev_record {
@@ -120,7 +121,6 @@ struct lowpan_fragment {
struct list_head list; /* fragments list */
};
-static unsigned short fragment_tag;
static LIST_HEAD(lowpan_fragments);
static DEFINE_SPINLOCK(flist_lock);
@@ -284,6 +284,9 @@ lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb)
/* checksum is always inline */
memcpy(*hc06_ptr, &uh->check, 2);
*hc06_ptr += 2;
+
+ /* skip the UDP header */
+ skb_pull(skb, sizeof(struct udphdr));
}
static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val)
@@ -309,9 +312,8 @@ static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val)
}
static int
-lowpan_uncompress_udp_header(struct sk_buff *skb)
+lowpan_uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh)
{
- struct udphdr *uh = udp_hdr(skb);
u8 tmp;
if (!uh)
@@ -358,6 +360,14 @@ lowpan_uncompress_udp_header(struct sk_buff *skb)
/* copy checksum */
memcpy(&uh->check, &skb->data[0], 2);
skb_pull(skb, 2);
+
+ /*
+ * UDP lenght needs to be infered from the lower layers
+ * here, we obtain the hint from the remaining size of the
+ * frame
+ */
+ uh->len = htons(skb->len + sizeof(struct udphdr));
+ pr_debug("uncompressed UDP length: src = %d", uh->len);
} else {
pr_debug("ERROR: unsupported NH format\n");
goto err;
@@ -572,17 +582,31 @@ static int lowpan_header_create(struct sk_buff *skb,
* this isn't implemented in mainline yet, so currently we assign 0xff
*/
{
+ mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
+ mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
+
/* prepare wpan address data */
sa.addr_type = IEEE802154_ADDR_LONG;
- sa.pan_id = 0xff;
-
- da.addr_type = IEEE802154_ADDR_LONG;
- da.pan_id = 0xff;
+ sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
- memcpy(&(da.hwaddr), daddr, 8);
memcpy(&(sa.hwaddr), saddr, 8);
+ /* intra-PAN communications */
+ da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
- mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
+ /*
+ * if the destination address is the broadcast address, use the
+ * corresponding short address
+ */
+ if (lowpan_is_addr_broadcast(daddr)) {
+ da.addr_type = IEEE802154_ADDR_SHORT;
+ da.short_addr = IEEE802154_ADDR_BROADCAST;
+ } else {
+ da.addr_type = IEEE802154_ADDR_LONG;
+ memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN);
+
+ /* request acknowledgment */
+ mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
+ }
return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
type, (void *)&da, (void *)&sa, skb->len);
@@ -650,7 +674,7 @@ static void lowpan_fragment_timer_expired(unsigned long entry_addr)
}
static struct lowpan_fragment *
-lowpan_alloc_new_frame(struct sk_buff *skb, u8 len, u16 tag)
+lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag)
{
struct lowpan_fragment *frame;
@@ -720,7 +744,7 @@ lowpan_process_data(struct sk_buff *skb)
{
struct lowpan_fragment *frame;
/* slen stores the rightmost 8 bits of the 11 bits length */
- u8 slen, offset;
+ u8 slen, offset = 0;
u16 len, tag;
bool found = false;
@@ -731,6 +755,18 @@ lowpan_process_data(struct sk_buff *skb)
/* adds the 3 MSB to the 8 LSB to retrieve the 11 bits length */
len = ((iphc0 & 7) << 8) | slen;
+ if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) {
+ pr_debug("%s received a FRAG1 packet (tag: %d, "
+ "size of the entire IP packet: %d)",
+ __func__, tag, len);
+ } else { /* FRAGN */
+ if (lowpan_fetch_skb_u8(skb, &offset))
+ goto unlock_and_drop;
+ pr_debug("%s received a FRAGN packet (tag: %d, "
+ "size of the entire IP packet: %d, "
+ "offset: %d)", __func__, tag, len, offset * 8);
+ }
+
/*
* check if frame assembling with the same tag is
* already in progress
@@ -745,17 +781,13 @@ lowpan_process_data(struct sk_buff *skb)
/* alloc new frame structure */
if (!found) {
+ pr_debug("%s first fragment received for tag %d, "
+ "begin packet reassembly", __func__, tag);
frame = lowpan_alloc_new_frame(skb, len, tag);
if (!frame)
goto unlock_and_drop;
}
- if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1)
- goto unlock_and_drop;
-
- if (lowpan_fetch_skb_u8(skb, &offset)) /* fetch offset */
- goto unlock_and_drop;
-
/* if payload fits buffer, copy it */
if (likely((offset * 8 + skb->len) <= frame->length))
skb_copy_to_linear_data_offset(frame->skb, offset * 8,
@@ -773,6 +805,9 @@ lowpan_process_data(struct sk_buff *skb)
list_del(&frame->list);
spin_unlock_bh(&flist_lock);
+ pr_debug("%s successfully reassembled fragment "
+ "(tag %d)", __func__, tag);
+
dev_kfree_skb(skb);
skb = frame->skb;
kfree(frame);
@@ -918,10 +953,35 @@ lowpan_process_data(struct sk_buff *skb)
}
/* UDP data uncompression */
- if (iphc0 & LOWPAN_IPHC_NH_C)
- if (lowpan_uncompress_udp_header(skb))
+ if (iphc0 & LOWPAN_IPHC_NH_C) {
+ struct udphdr uh;
+ struct sk_buff *new;
+ if (lowpan_uncompress_udp_header(skb, &uh))
goto drop;
+ /*
+ * replace the compressed UDP head by the uncompressed UDP
+ * header
+ */
+ new = skb_copy_expand(skb, sizeof(struct udphdr),
+ skb_tailroom(skb), GFP_ATOMIC);
+ kfree_skb(skb);
+
+ if (!new)
+ return -ENOMEM;
+
+ skb = new;
+
+ skb_push(skb, sizeof(struct udphdr));
+ skb_reset_transport_header(skb);
+ skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr));
+
+ lowpan_raw_dump_table(__func__, "raw UDP header dump",
+ (u8 *)&uh, sizeof(uh));
+
+ hdr.nexthdr = UIP_PROTO_UDP;
+ }
+
/* Not fragmented package */
hdr.payload_len = htons(skb->len);
@@ -969,13 +1029,13 @@ static int lowpan_get_mac_header_length(struct sk_buff *skb)
static int
lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
- int mlen, int plen, int offset)
+ int mlen, int plen, int offset, int type)
{
struct sk_buff *frag;
int hlen, ret;
- /* if payload length is zero, therefore it's a first fragment */
- hlen = (plen == 0 ? LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE);
+ hlen = (type == LOWPAN_DISPATCH_FRAG1) ?
+ LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE;
lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen);
@@ -1003,14 +1063,14 @@ lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
}
static int
-lowpan_skb_fragmentation(struct sk_buff *skb)
+lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev)
{
int err, header_length, payload_length, tag, offset = 0;
u8 head[5];
header_length = lowpan_get_mac_header_length(skb);
payload_length = skb->len - header_length;
- tag = fragment_tag++;
+ tag = lowpan_dev_info(dev)->fragment_tag++;
/* first fragment header */
head[0] = LOWPAN_DISPATCH_FRAG1 | ((payload_length >> 8) & 0x7);
@@ -1018,7 +1078,16 @@ lowpan_skb_fragmentation(struct sk_buff *skb)
head[2] = tag >> 8;
head[3] = tag & 0xff;
- err = lowpan_fragment_xmit(skb, head, header_length, 0, 0);
+ err = lowpan_fragment_xmit(skb, head, header_length, LOWPAN_FRAG_SIZE,
+ 0, LOWPAN_DISPATCH_FRAG1);
+
+ if (err) {
+ pr_debug("%s unable to send FRAG1 packet (tag: %d)",
+ __func__, tag);
+ goto exit;
+ }
+
+ offset = LOWPAN_FRAG_SIZE;
/* next fragment header */
head[0] &= ~LOWPAN_DISPATCH_FRAG1;
@@ -1033,10 +1102,17 @@ lowpan_skb_fragmentation(struct sk_buff *skb)
len = payload_length - offset;
err = lowpan_fragment_xmit(skb, head, header_length,
- len, offset);
+ len, offset, LOWPAN_DISPATCH_FRAGN);
+ if (err) {
+ pr_debug("%s unable to send a subsequent FRAGN packet "
+ "(tag: %d, offset: %d", __func__, tag, offset);
+ goto exit;
+ }
+
offset += len;
}
+exit:
return err;
}
@@ -1059,7 +1135,7 @@ static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
}
pr_debug("frame is too big, fragmentation is needed\n");
- err = lowpan_skb_fragmentation(skb);
+ err = lowpan_skb_fragmentation(skb, dev);
error:
dev_kfree_skb(skb);
out:
@@ -1087,6 +1163,12 @@ static u16 lowpan_get_short_addr(const struct net_device *dev)
return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev);
}
+static u8 lowpan_get_dsn(const struct net_device *dev)
+{
+ struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
+ return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev);
+}
+
static struct header_ops lowpan_header_ops = {
.create = lowpan_header_create,
};
@@ -1100,6 +1182,7 @@ static struct ieee802154_mlme_ops lowpan_mlme = {
.get_pan_id = lowpan_get_pan_id,
.get_phy = lowpan_get_phy,
.get_short_addr = lowpan_get_short_addr,
+ .get_dsn = lowpan_get_dsn,
};
static void lowpan_setup(struct net_device *dev)
@@ -1203,6 +1286,7 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev,
return -ENODEV;
lowpan_dev_info(dev)->real_dev = real_dev;
+ lowpan_dev_info(dev)->fragment_tag = 0;
mutex_init(&lowpan_dev_info(dev)->dev_list_mtx);
entry = kzalloc(sizeof(struct lowpan_dev_record), GFP_KERNEL);
diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h
index bba5f8336317..4b8f917658b5 100644
--- a/net/ieee802154/6lowpan.h
+++ b/net/ieee802154/6lowpan.h
@@ -92,9 +92,10 @@
*/
#define lowpan_is_iid_16_bit_compressable(a) \
((((a)->s6_addr16[4]) == 0) && \
- (((a)->s6_addr16[5]) == 0) && \
- (((a)->s6_addr16[6]) == 0) && \
- ((((a)->s6_addr[14]) & 0x80) == 0))
+ (((a)->s6_addr[10]) == 0) && \
+ (((a)->s6_addr[11]) == 0xff) && \
+ (((a)->s6_addr[12]) == 0xfe) && \
+ (((a)->s6_addr[13]) == 0))
/* multicast address */
#define is_addr_mcast(a) (((a)->s6_addr[0]) == 0xFF)
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index e0da175f8e5b..581a59504bd5 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -291,6 +291,9 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
size_t copied = 0;
int err = -EOPNOTSUPP;
struct sk_buff *skb;
+ struct sockaddr_ieee802154 *saddr;
+
+ saddr = (struct sockaddr_ieee802154 *)msg->msg_name;
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -309,6 +312,13 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
sock_recv_ts_and_drops(msg, sk, skb);
+ 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;
done:
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 97351e1d07a4..7e49bbcc6967 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -64,8 +64,8 @@ struct sk_buff *ieee802154_nl_create(int flags, u8 req)
int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group)
{
- /* XXX: nlh is right at the start of msg */
- void *hdr = genlmsg_data(NLMSG_DATA(msg->data));
+ struct nlmsghdr *nlh = nlmsg_hdr(msg);
+ void *hdr = genlmsg_data(nlmsg_data(nlh));
if (genlmsg_end(msg, hdr) < 0)
goto out;
@@ -97,8 +97,8 @@ struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info,
int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
{
- /* XXX: nlh is right at the start of msg */
- void *hdr = genlmsg_data(NLMSG_DATA(msg->data));
+ struct nlmsghdr *nlh = nlmsg_hdr(msg);
+ void *hdr = genlmsg_data(nlmsg_data(nlh));
if (genlmsg_end(msg, hdr) < 0)
goto out;
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 7944df768454..8603ca827104 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -166,6 +166,7 @@ config IP_PNP_RARP
config NET_IPIP
tristate "IP: tunneling"
select INET_TUNNEL
+ select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
@@ -186,9 +187,14 @@ config NET_IPGRE_DEMUX
This is helper module to demultiplex GRE packets on GRE version field criteria.
Required by ip_gre and pptp modules.
+config NET_IP_TUNNEL
+ tristate
+ default n
+
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
+ select NET_IP_TUNNEL
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
@@ -313,6 +319,7 @@ config SYN_COOKIES
config NET_IPVTI
tristate "Virtual (secure) IP: tunneling"
select INET_TUNNEL
+ select NET_IP_TUNNEL
depends on INET_XFRM_MODE_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 15ca63ec604e..089cb9f36387 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -13,6 +13,7 @@ obj-y := route.o inetpeer.o protocol.o \
fib_frontend.o fib_semantics.o fib_trie.o \
inet_fragment.o ping.o
+obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c929d9c1c4b6..93824c57b108 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -111,7 +111,6 @@
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
-#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
@@ -1283,9 +1282,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
int ihl;
int id;
unsigned int offset = 0;
-
- if (!(features & NETIF_F_V4_CSUM))
- features &= ~NETIF_F_SG;
+ bool tunnel;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
@@ -1293,6 +1290,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
+ SKB_GSO_UDP_TUNNEL |
0)))
goto out;
@@ -1307,6 +1305,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, ihl)))
goto out;
+ tunnel = !!skb->encapsulation;
+
__skb_pull(skb, ihl);
skb_reset_transport_header(skb);
iph = ip_hdr(skb);
@@ -1326,7 +1326,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
skb = segs;
do {
iph = ip_hdr(skb);
- if (proto == IPPROTO_UDP) {
+ if (!tunnel && proto == IPPROTO_UDP) {
iph->id = htons(id);
iph->frag_off = htons(offset >> 3);
if (skb->next != NULL)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index fea4929f6200..247ec1951c35 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -654,11 +654,19 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
arp_ptr += dev->addr_len;
memcpy(arp_ptr, &src_ip, 4);
arp_ptr += 4;
- if (target_hw != NULL)
- memcpy(arp_ptr, target_hw, dev->addr_len);
- else
- memset(arp_ptr, 0, dev->addr_len);
- arp_ptr += dev->addr_len;
+
+ switch (dev->type) {
+#if IS_ENABLED(CONFIG_FIREWIRE_NET)
+ case ARPHRD_IEEE1394:
+ break;
+#endif
+ default:
+ if (target_hw != NULL)
+ memcpy(arp_ptr, target_hw, dev->addr_len);
+ else
+ memset(arp_ptr, 0, dev->addr_len);
+ arp_ptr += dev->addr_len;
+ }
memcpy(arp_ptr, &dest_ip, 4);
return skb;
@@ -781,7 +789,14 @@ static int arp_process(struct sk_buff *skb)
arp_ptr += dev->addr_len;
memcpy(&sip, arp_ptr, 4);
arp_ptr += 4;
- arp_ptr += dev->addr_len;
+ switch (dev_type) {
+#if IS_ENABLED(CONFIG_FIREWIRE_NET)
+ case ARPHRD_IEEE1394:
+ break;
+#endif
+ default:
+ arp_ptr += dev->addr_len;
+ }
memcpy(&tip, arp_ptr, 4);
/*
* Check for bad requests for 127.x.x.x and requests for multicast
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f678507bc829..5d985e367535 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -536,7 +536,7 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
return NULL;
}
-static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
@@ -775,7 +775,7 @@ static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
return NULL;
}
-static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct in_ifaddr *ifa;
@@ -1499,6 +1499,8 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
idx = 0;
head = &net->dev_index_head[h];
rcu_read_lock();
+ cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
+ net->dev_base_seq;
hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
@@ -1519,6 +1521,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_unlock();
goto done;
}
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
}
cont:
idx++;
@@ -1730,8 +1733,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
};
static int inet_netconf_get_devconf(struct sk_buff *in_skb,
- struct nlmsghdr *nlh,
- void *arg)
+ struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[NETCONFA_MAX+1];
@@ -1791,6 +1793,77 @@ errout:
return err;
}
+static int inet_netconf_dump_devconf(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ int h, s_h;
+ int idx, s_idx;
+ struct net_device *dev;
+ struct in_device *in_dev;
+ struct hlist_head *head;
+
+ s_h = cb->args[0];
+ s_idx = idx = cb->args[1];
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ rcu_read_lock();
+ cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
+ net->dev_base_seq;
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ in_dev = __in_dev_get_rcu(dev);
+ if (!in_dev)
+ goto cont;
+
+ if (inet_netconf_fill_devconf(skb, dev->ifindex,
+ &in_dev->cnf,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF,
+ NLM_F_MULTI,
+ -1) <= 0) {
+ rcu_read_unlock();
+ goto done;
+ }
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+ idx++;
+ }
+ rcu_read_unlock();
+ }
+ if (h == NETDEV_HASHENTRIES) {
+ if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL,
+ net->ipv4.devconf_all,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF, NLM_F_MULTI,
+ -1) <= 0)
+ goto done;
+ else
+ h++;
+ }
+ if (h == NETDEV_HASHENTRIES + 1) {
+ if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT,
+ net->ipv4.devconf_dflt,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF, NLM_F_MULTI,
+ -1) <= 0)
+ goto done;
+ else
+ h++;
+ }
+done:
+ cb->args[0] = h;
+ cb->args[1] = idx;
+
+ return skb->len;
+}
+
#ifdef CONFIG_SYSCTL
static void devinet_copy_dflt_conf(struct net *net, int i)
@@ -2195,6 +2268,6 @@ void __init devinet_init(void)
rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL);
rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL);
rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf,
- NULL, NULL);
+ inet_netconf_dump_devconf, NULL);
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eb4bb12b3eb4..c7629a209f9d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -604,7 +604,7 @@ errout:
return err;
}
-static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
@@ -626,7 +626,7 @@ errout:
return err;
}
-static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
@@ -957,8 +957,8 @@ static void nl_fib_input(struct sk_buff *skb)
net = sock_net(skb->sk);
nlh = nlmsg_hdr(skb);
- if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len ||
- nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn)))
+ if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+ nlmsg_len(nlh) < sizeof(*frn))
return;
skb = skb_clone(skb, GFP_KERNEL);
@@ -966,7 +966,7 @@ static void nl_fib_input(struct sk_buff *skb)
return;
nlh = nlmsg_hdr(skb);
- frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
+ frn = (struct fib_result_nl *) nlmsg_data(nlh);
tb = fib_get_table(net, frn->tb_id_in);
nl_fib_lookup(frn, tb);
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
index 7a4c710c4cdd..d2d5a99fba09 100644
--- a/net/ipv4/gre.c
+++ b/net/ipv4/gre.c
@@ -27,11 +27,6 @@
static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
static DEFINE_SPINLOCK(gre_proto_lock);
-struct gre_base_hdr {
- __be16 flags;
- __be16 protocol;
-};
-#define GRE_HEADER_SECTION 4
int gre_add_protocol(const struct gre_protocol *proto, u8 version)
{
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 786d97aee751..6acb541c9091 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -559,7 +559,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
{
- int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL);
+ int err = req->rsk_ops->rtx_syn_ack(parent, req);
if (!err)
req->num_retrans++;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7afa2c3c788f..8620408af574 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -158,7 +158,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
#define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
- if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+ if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index f4fd23de9b13..1206ca64b0ea 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -23,6 +23,28 @@
#include <net/sock.h>
#include <net/inet_frag.h>
+#include <net/inet_ecn.h>
+
+/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
+ * Value : 0xff if frame should be dropped.
+ * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
+ */
+const u8 ip_frag_ecn_table[16] = {
+ /* at least one fragment had CE, and others ECT_0 or ECT_1 */
+ [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE,
+ [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
+ [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
+
+ /* invalid combinations : drop frame */
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
+ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
+};
+EXPORT_SYMBOL(ip_frag_ecn_table);
static void inet_frag_secret_rebuild(unsigned long dummy)
{
@@ -102,7 +124,6 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
{
write_lock(&f->lock);
hlist_del(&fq->list);
- fq->net->nqueues--;
write_unlock(&f->lock);
inet_frag_lru_del(fq);
}
@@ -182,6 +203,9 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
q = list_first_entry(&nf->lru_list,
struct inet_frag_queue, lru_list);
atomic_inc(&q->refcnt);
+ /* Remove q from list to avoid several CPUs grabbing it */
+ list_del_init(&q->lru_list);
+
spin_unlock(&nf->lru_lock);
spin_lock(&q->lock);
@@ -235,7 +259,6 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
atomic_inc(&qp->refcnt);
hlist_add_head(&qp->list, &f->hash[hash]);
- nf->nqueues++;
write_unlock(&f->lock);
inet_frag_lru_add(nf, qp);
return qp;
diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c
index cc280a3f4f96..1975f52933c5 100644
--- a/net/ipv4/inet_lro.c
+++ b/net/ipv4/inet_lro.c
@@ -29,6 +29,7 @@
#include <linux/module.h>
#include <linux/if_vlan.h>
#include <linux/inet_lro.h>
+#include <net/checksum.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jan-Bernd Themann <themann@de.ibm.com>");
@@ -114,11 +115,9 @@ static void lro_update_tcp_ip_header(struct net_lro_desc *lro_desc)
*(p+2) = lro_desc->tcp_rcv_tsecr;
}
+ csum_replace2(&iph->check, iph->tot_len, htons(lro_desc->ip_tot_len));
iph->tot_len = htons(lro_desc->ip_tot_len);
- iph->check = 0;
- iph->check = ip_fast_csum((u8 *)lro_desc->iph, iph->ihl);
-
tcph->check = 0;
tcp_hdr_csum = csum_partial(tcph, TCP_HDR_LEN(tcph), 0);
lro_desc->data_csum = csum_add(lro_desc->data_csum, tcp_hdr_csum);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a6445b843ef4..938520668b2f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -79,40 +79,11 @@ struct ipq {
struct inet_peer *peer;
};
-/* RFC 3168 support :
- * We want to check ECN values of all fragments, do detect invalid combinations.
- * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
- */
-#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */
-#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */
-#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */
-#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */
-
static inline u8 ip4_frag_ecn(u8 tos)
{
return 1 << (tos & INET_ECN_MASK);
}
-/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
- * Value : 0xff if frame should be dropped.
- * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
- */
-static const u8 ip4_frag_ecn_table[16] = {
- /* at least one fragment had CE, and others ECT_0 or ECT_1 */
- [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE,
- [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
- [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE,
-
- /* invalid combinations : drop frame */
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff,
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff,
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff,
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff,
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff,
- [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff,
-};
-
static struct inet_frags ip4_frags;
int ip_frag_nqueues(struct net *net)
@@ -551,7 +522,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
ipq_kill(qp);
- ecn = ip4_frag_ecn_table[qp->ecn];
+ ecn = ip_frag_ecn_table[qp->ecn];
if (unlikely(ecn == 0xff)) {
err = -EINVAL;
goto out_fail;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 91d66dbde9c0..e5dfd2843f28 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -37,7 +37,7 @@
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
@@ -108,15 +108,6 @@
fatal route to network, even if it were you who configured
fatal static route: you are innocent. :-)
-
-
- 3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
- practically identical code. It would be good to glue them
- together, but it is not very evident, how to make them modular.
- sit is integral part of IPv6, ipip and gre are naturally modular.
- We could extract common parts (hash table, ioctl etc)
- to a separate module (ip_tunnel.c).
-
Alexey Kuznetsov.
*/
@@ -126,400 +117,135 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
-static void ipgre_tunnel_setup(struct net_device *dev);
-static int ipgre_tunnel_bind_dev(struct net_device *dev);
-
-/* Fallback tunnel: no source, no destination, no key, no options */
-
-#define HASH_SIZE 16
static int ipgre_net_id __read_mostly;
-struct ipgre_net {
- struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];
-
- struct net_device *fb_tunnel_dev;
-};
-
-/* Tunnel hash table */
-
-/*
- 4 hash tables:
-
- 3: (remote,local)
- 2: (remote,*)
- 1: (*,local)
- 0: (*,*)
+static int gre_tap_net_id __read_mostly;
- We require exact key match i.e. if a key is present in packet
- it will match only tunnel with the same key; if it is not present,
- it will match only keyless tunnel.
-
- All keysless packets, if not matched configured keyless tunnels
- will match fallback tunnel.
- */
+static __sum16 check_checksum(struct sk_buff *skb)
+{
+ __sum16 csum = 0;
-#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
+ switch (skb->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ csum = csum_fold(skb->csum);
-#define tunnels_r_l tunnels[3]
-#define tunnels_r tunnels[2]
-#define tunnels_l tunnels[1]
-#define tunnels_wc tunnels[0]
+ if (!csum)
+ break;
+ /* Fall through. */
-static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
+ case CHECKSUM_NONE:
+ skb->csum = 0;
+ csum = __skb_checksum_complete(skb);
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ break;
}
- tot->multicast = dev->stats.multicast;
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
+ return csum;
}
-/* Does key in tunnel parameters match packet */
-static bool ipgre_key_match(const struct ip_tunnel_parm *p,
- __be16 flags, __be32 key)
+static int ip_gre_calc_hlen(__be16 o_flags)
{
- if (p->i_flags & GRE_KEY) {
- if (flags & GRE_KEY)
- return key == p->i_key;
- else
- return false; /* key expected, none present */
- } else
- return !(flags & GRE_KEY);
-}
+ int addend = 4;
-/* Given src, dst and key, find appropriate for input tunnel. */
+ if (o_flags&TUNNEL_CSUM)
+ addend += 4;
+ if (o_flags&TUNNEL_KEY)
+ addend += 4;
+ if (o_flags&TUNNEL_SEQ)
+ addend += 4;
+ return addend;
+}
-static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
- __be32 remote, __be32 local,
- __be16 flags, __be32 key,
- __be16 gre_proto)
+static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+ bool *csum_err, int *hdr_len)
{
- struct net *net = dev_net(dev);
- int link = dev->ifindex;
- unsigned int h0 = HASH(remote);
- unsigned int h1 = HASH(key);
- struct ip_tunnel *t, *cand = NULL;
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
- ARPHRD_ETHER : ARPHRD_IPGRE;
- int score, cand_score = 4;
-
- for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
- if (local != t->parms.iph.saddr ||
- remote != t->parms.iph.daddr ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (!ipgre_key_match(&t->parms, flags, key))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
-
- for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) {
- if (remote != t->parms.iph.daddr ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (!ipgre_key_match(&t->parms, flags, key))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
+ struct iphdr *iph = ip_hdr(skb);
+ struct gre_base_hdr *greh;
+ __be32 *options;
- for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) {
- if ((local != t->parms.iph.saddr &&
- (local != t->parms.iph.daddr ||
- !ipv4_is_multicast(local))) ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (!ipgre_key_match(&t->parms, flags, key))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
+ return -EINVAL;
- for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) {
- if (t->parms.i_key != key ||
- !(t->dev->flags & IFF_UP))
- continue;
-
- if (t->dev->type != ARPHRD_IPGRE &&
- t->dev->type != dev_type)
- continue;
-
- score = 0;
- if (t->parms.link != link)
- score |= 1;
- if (t->dev->type != dev_type)
- score |= 2;
- if (score == 0)
- return t;
-
- if (score < cand_score) {
- cand = t;
- cand_score = score;
- }
- }
+ greh = (struct gre_base_hdr *)((u8 *)iph + (iph->ihl << 2));
+ if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
+ return -EINVAL;
- if (cand != NULL)
- return cand;
+ tpi->flags = gre_flags_to_tnl_flags(greh->flags);
+ *hdr_len = ip_gre_calc_hlen(tpi->flags);
- dev = ign->fb_tunnel_dev;
- if (dev->flags & IFF_UP)
- return netdev_priv(dev);
+ if (!pskb_may_pull(skb, *hdr_len))
+ return -EINVAL;
- return NULL;
-}
+ tpi->proto = greh->protocol;
-static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
- struct ip_tunnel_parm *parms)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- __be32 key = parms->i_key;
- unsigned int h = HASH(key);
- int prio = 0;
-
- if (local)
- prio |= 1;
- if (remote && !ipv4_is_multicast(remote)) {
- prio |= 2;
- h ^= HASH(remote);
+ options = (__be32 *)(greh + 1);
+ if (greh->flags & GRE_CSUM) {
+ if (check_checksum(skb)) {
+ *csum_err = true;
+ return -EINVAL;
+ }
+ options++;
}
- return &ign->tunnels[prio][h];
-}
-
-static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
- struct ip_tunnel *t)
-{
- return __ipgre_bucket(ign, &t->parms);
-}
-
-static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);
+ if (greh->flags & GRE_KEY) {
+ tpi->key = *options;
+ options++;
+ } else
+ tpi->key = 0;
- rcu_assign_pointer(t->next, rtnl_dereference(*tp));
- rcu_assign_pointer(*tp, t);
-}
+ if (unlikely(greh->flags & GRE_SEQ)) {
+ tpi->seq = *options;
+ options++;
+ } else
+ tpi->seq = 0;
-static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp;
- struct ip_tunnel *iter;
-
- for (tp = ipgre_bucket(ign, t);
- (iter = rtnl_dereference(*tp)) != NULL;
- tp = &iter->next) {
- if (t == iter) {
- rcu_assign_pointer(*tp, t->next);
- break;
+ /* WCCP version 1 and 2 protocol decoding.
+ * - Change protocol to IP
+ * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
+ */
+ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+ tpi->proto = htons(ETH_P_IP);
+ if ((*(u8 *)options & 0xF0) != 0x40) {
+ *hdr_len += 4;
+ if (!pskb_may_pull(skb, *hdr_len))
+ return -EINVAL;
}
}
-}
-
-static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
- struct ip_tunnel_parm *parms,
- int type)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- __be32 key = parms->i_key;
- int link = parms->link;
- struct ip_tunnel *t;
- struct ip_tunnel __rcu **tp;
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- for (tp = __ipgre_bucket(ign, parms);
- (t = rtnl_dereference(*tp)) != NULL;
- tp = &t->next)
- if (local == t->parms.iph.saddr &&
- remote == t->parms.iph.daddr &&
- key == t->parms.i_key &&
- link == t->parms.link &&
- type == t->dev->type)
- break;
-
- return t;
-}
-
-static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
- struct ip_tunnel_parm *parms, int create)
-{
- struct ip_tunnel *t, *nt;
- struct net_device *dev;
- char name[IFNAMSIZ];
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
- if (t || !create)
- return t;
-
- if (parms->name[0])
- strlcpy(name, parms->name, IFNAMSIZ);
- else
- strcpy(name, "gre%d");
-
- dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
- if (!dev)
- return NULL;
-
- dev_net_set(dev, net);
-
- nt = netdev_priv(dev);
- nt->parms = *parms;
- dev->rtnl_link_ops = &ipgre_link_ops;
- dev->mtu = ipgre_tunnel_bind_dev(dev);
-
- if (register_netdevice(dev) < 0)
- goto failed_free;
-
- /* Can use a lockless transmit, unless we generate output sequences */
- if (!(nt->parms.o_flags & GRE_SEQ))
- dev->features |= NETIF_F_LLTX;
-
- dev_hold(dev);
- ipgre_tunnel_link(ign, nt);
- return nt;
-
-failed_free:
- free_netdev(dev);
- return NULL;
-}
-
-static void ipgre_tunnel_uninit(struct net_device *dev)
-{
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- ipgre_tunnel_unlink(ign, netdev_priv(dev));
- dev_put(dev);
+ return 0;
}
-
static void ipgre_err(struct sk_buff *skb, u32 info)
{
-/* All the routers (except for Linux) return only
- 8 bytes of packet payload. It means, that precise relaying of
- ICMP in the real Internet is absolutely infeasible.
+ /* All the routers (except for Linux) return only
+ 8 bytes of packet payload. It means, that precise relaying of
+ ICMP in the real Internet is absolutely infeasible.
- Moreover, Cisco "wise men" put GRE key to the third word
- in GRE header. It makes impossible maintaining even soft state for keyed
- GRE tunnels with enabled checksum. Tell them "thank you".
-
- Well, I wonder, rfc1812 was written by Cisco employee,
- what the hell these idiots break standards established
- by themselves???
- */
+ Moreover, Cisco "wise men" put GRE key to the third word
+ in GRE header. It makes impossible maintaining even soft
+ state for keyed GRE tunnels with enabled checksum. Tell
+ them "thank you".
+ Well, I wonder, rfc1812 was written by Cisco employee,
+ what the hell these idiots break standards established
+ by themselves???
+ */
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn;
const struct iphdr *iph = (const struct iphdr *)skb->data;
- __be16 *p = (__be16 *)(skb->data+(iph->ihl<<2));
- int grehlen = (iph->ihl<<2) + 4;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
- __be16 flags;
- __be32 key = 0;
+ struct tnl_ptk_info tpi;
+ int hdr_len;
+ bool csum_err = false;
- flags = p[0];
- if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
- if (flags&(GRE_VERSION|GRE_ROUTING))
+ if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len)) {
+ if (!csum_err) /* ignore csum errors. */
return;
- if (flags&GRE_KEY) {
- grehlen += 4;
- if (flags&GRE_CSUM)
- grehlen += 4;
- }
}
- /* If only 8 bytes returned, keyed message will be dropped here */
- if (skb_headlen(skb) < grehlen)
- return;
-
- if (flags & GRE_KEY)
- key = *(((__be32 *)p) + (grehlen / 4) - 1);
-
switch (type) {
default:
case ICMP_PARAMETERPROB:
@@ -548,8 +274,13 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
break;
}
- t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
- flags, key, p[1]);
+ if (tpi.proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
+
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
+ iph->daddr, iph->saddr, tpi.key);
if (t == NULL)
return;
@@ -578,158 +309,33 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
t->err_time = jiffies;
}
-static inline u8
-ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
-{
- u8 inner = 0;
- if (skb->protocol == htons(ETH_P_IP))
- inner = old_iph->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
- inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
- return INET_ECN_encapsulate(tos, inner);
-}
-
static int ipgre_rcv(struct sk_buff *skb)
{
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn;
const struct iphdr *iph;
- u8 *h;
- __be16 flags;
- __sum16 csum = 0;
- __be32 key = 0;
- u32 seqno = 0;
struct ip_tunnel *tunnel;
- int offset = 4;
- __be16 gre_proto;
- int err;
+ struct tnl_ptk_info tpi;
+ int hdr_len;
+ bool csum_err = false;
- if (!pskb_may_pull(skb, 16))
+ if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len) < 0)
goto drop;
- iph = ip_hdr(skb);
- h = skb->data;
- flags = *(__be16 *)h;
-
- if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
- /* - Version must be 0.
- - We do not support routing headers.
- */
- if (flags&(GRE_VERSION|GRE_ROUTING))
- goto drop;
-
- if (flags&GRE_CSUM) {
- switch (skb->ip_summed) {
- case CHECKSUM_COMPLETE:
- csum = csum_fold(skb->csum);
- if (!csum)
- break;
- /* fall through */
- case CHECKSUM_NONE:
- skb->csum = 0;
- csum = __skb_checksum_complete(skb);
- skb->ip_summed = CHECKSUM_COMPLETE;
- }
- offset += 4;
- }
- if (flags&GRE_KEY) {
- key = *(__be32 *)(h + offset);
- offset += 4;
- }
- if (flags&GRE_SEQ) {
- seqno = ntohl(*(__be32 *)(h + offset));
- offset += 4;
- }
- }
+ if (tpi.proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
- gre_proto = *(__be16 *)(h + 2);
+ iph = ip_hdr(skb);
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
+ iph->saddr, iph->daddr, tpi.key);
- tunnel = ipgre_tunnel_lookup(skb->dev,
- iph->saddr, iph->daddr, flags, key,
- gre_proto);
if (tunnel) {
- struct pcpu_tstats *tstats;
-
- secpath_reset(skb);
-
- skb->protocol = gre_proto;
- /* WCCP version 1 and 2 protocol decoding.
- * - Change protocol to IP
- * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
- */
- if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
- skb->protocol = htons(ETH_P_IP);
- if ((*(h + offset) & 0xF0) != 0x40)
- offset += 4;
- }
-
- skb->mac_header = skb->network_header;
- __pskb_pull(skb, offset);
- skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
- skb->pkt_type = PACKET_HOST;
-#ifdef CONFIG_NET_IPGRE_BROADCAST
- if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (rt_is_output_route(skb_rtable(skb)))
- goto drop;
- tunnel->dev->stats.multicast++;
- skb->pkt_type = PACKET_BROADCAST;
- }
-#endif
-
- if (((flags&GRE_CSUM) && csum) ||
- (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
- tunnel->dev->stats.rx_crc_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
- if (tunnel->parms.i_flags&GRE_SEQ) {
- if (!(flags&GRE_SEQ) ||
- (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
- tunnel->dev->stats.rx_fifo_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
- tunnel->i_seqno = seqno + 1;
- }
-
- /* Warning: All skb pointers will be invalidated! */
- if (tunnel->dev->type == ARPHRD_ETHER) {
- if (!pskb_may_pull(skb, ETH_HLEN)) {
- tunnel->dev->stats.rx_length_errors++;
- tunnel->dev->stats.rx_errors++;
- goto drop;
- }
-
- iph = ip_hdr(skb);
- skb->protocol = eth_type_trans(skb, tunnel->dev);
- skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
- }
-
- __skb_tunnel_rx(skb, tunnel->dev);
-
- skb_reset_network_header(skb);
- err = IP_ECN_decapsulate(iph, skb);
- if (unlikely(err)) {
- if (log_ecn_error)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &iph->saddr, iph->tos);
- if (err > 1) {
- ++tunnel->dev->stats.rx_frame_errors;
- ++tunnel->dev->stats.rx_errors;
- goto drop;
- }
- }
-
- tstats = this_cpu_ptr(tunnel->dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
-
- gro_cells_receive(&tunnel->gro_cells, skb);
+ ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-
drop:
kfree_skb(skb);
return 0;
@@ -746,7 +352,7 @@ static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff
skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
return skb;
} else if (skb->ip_summed == CHECKSUM_PARTIAL &&
- tunnel->parms.o_flags&GRE_CSUM) {
+ tunnel->parms.o_flags&TUNNEL_CSUM) {
err = skb_checksum_help(skb);
if (unlikely(err))
goto error;
@@ -760,494 +366,157 @@ error:
return ERR_PTR(err);
}
-static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *gre_build_header(struct sk_buff *skb,
+ const struct tnl_ptk_info *tpi,
+ int hdr_len)
{
- struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
- struct ip_tunnel *tunnel = netdev_priv(dev);
- const struct iphdr *old_iph;
- const struct iphdr *tiph;
- struct flowi4 fl4;
- u8 tos;
- __be16 df;
- struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
- struct iphdr *iph; /* Our new IP header */
- unsigned int max_headroom; /* The extra header space needed */
- int gre_hlen;
- __be32 dst;
- int mtu;
- u8 ttl;
- int err;
- int pkt_len;
-
- skb = handle_offloads(tunnel, skb);
- if (IS_ERR(skb)) {
- dev->stats.tx_dropped++;
- return NETDEV_TX_OK;
- }
+ struct gre_base_hdr *greh;
- if (!skb->encapsulation) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
+ skb_push(skb, hdr_len);
- old_iph = ip_hdr(skb);
+ greh = (struct gre_base_hdr *)skb->data;
+ greh->flags = tnl_flags_to_gre_flags(tpi->flags);
+ greh->protocol = tpi->proto;
- if (dev->type == ARPHRD_ETHER)
- IPCB(skb)->flags = 0;
+ if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) {
+ __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
- if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
- gre_hlen = 0;
- tiph = (const struct iphdr *)skb->data;
- } else {
- gre_hlen = tunnel->hlen;
- tiph = &tunnel->parms.iph;
- }
-
- if ((dst = tiph->daddr) == 0) {
- /* NBMA tunnel */
-
- if (skb_dst(skb) == NULL) {
- dev->stats.tx_fifo_errors++;
- goto tx_error;
+ if (tpi->flags&TUNNEL_SEQ) {
+ *ptr = tpi->seq;
+ ptr--;
}
-
- if (skb->protocol == htons(ETH_P_IP)) {
- rt = skb_rtable(skb);
- dst = rt_nexthop(rt, old_iph->daddr);
+ if (tpi->flags&TUNNEL_KEY) {
+ *ptr = tpi->key;
+ ptr--;
}
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- const struct in6_addr *addr6;
- struct neighbour *neigh;
- bool do_tx_error_icmp;
- int addr_type;
-
- neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr);
- if (neigh == NULL)
- goto tx_error;
-
- addr6 = (const struct in6_addr *)&neigh->primary_key;
- addr_type = ipv6_addr_type(addr6);
-
- if (addr_type == IPV6_ADDR_ANY) {
- addr6 = &ipv6_hdr(skb)->daddr;
- addr_type = ipv6_addr_type(addr6);
- }
-
- if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
- do_tx_error_icmp = true;
- else {
- do_tx_error_icmp = false;
- dst = addr6->s6_addr32[3];
- }
- neigh_release(neigh);
- if (do_tx_error_icmp)
- goto tx_error_icmp;
+ if (tpi->flags&TUNNEL_CSUM &&
+ !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
+ *(__sum16 *)ptr = 0;
+ *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
+ skb->len, 0));
}
-#endif
- else
- goto tx_error;
}
- ttl = tiph->ttl;
- tos = tiph->tos;
- if (tos & 0x1) {
- tos &= ~0x1;
- if (skb->protocol == htons(ETH_P_IP))
- tos = old_iph->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
- tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
- }
+ return skb;
+}
- rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr,
- tunnel->parms.o_key, RT_TOS(tos),
- tunnel->parms.link);
- if (IS_ERR(rt)) {
- dev->stats.tx_carrier_errors++;
- goto tx_error;
- }
- tdev = rt->dst.dev;
+static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params,
+ __be16 proto)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct tnl_ptk_info tpi;
- if (tdev == dev) {
- ip_rt_put(rt);
- dev->stats.collisions++;
- goto tx_error;
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
}
- df = tiph->frag_off;
- if (df)
- mtu = dst_mtu(&rt->dst) - dev->hard_header_len - tunnel->hlen;
- else
- mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
-
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
- if (skb->protocol == htons(ETH_P_IP)) {
- df |= (old_iph->frag_off&htons(IP_DF));
+ tpi.flags = tunnel->parms.o_flags;
+ tpi.proto = proto;
+ tpi.key = tunnel->parms.o_key;
+ if (tunnel->parms.o_flags & TUNNEL_SEQ)
+ tunnel->o_seqno++;
+ tpi.seq = htonl(tunnel->o_seqno);
- if (!skb_is_gso(skb) &&
- (old_iph->frag_off&htons(IP_DF)) &&
- mtu < ntohs(old_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
+ /* Push GRE header. */
+ skb = gre_build_header(skb, &tpi, tunnel->hlen);
+ if (unlikely(!skb)) {
+ dev->stats.tx_dropped++;
+ return;
}
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
-
- if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) {
- if ((tunnel->parms.iph.daddr &&
- !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
- rt6->rt6i_dst.plen == 128) {
- rt6->rt6i_flags |= RTF_MODIFIED;
- dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
- }
- }
- if (!skb_is_gso(skb) &&
- mtu >= IPV6_MIN_MTU &&
- mtu < skb->len - tunnel->hlen + gre_hlen) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-#endif
+ ip_tunnel_xmit(skb, dev, tnl_params);
+}
- if (tunnel->err_count > 0) {
- if (time_before(jiffies,
- tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
- tunnel->err_count--;
+static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *tnl_params;
- dst_link_failure(skb);
- } else
- tunnel->err_count = 0;
- }
+ skb = handle_offloads(tunnel, skb);
+ if (IS_ERR(skb))
+ goto out;
- max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len;
-
- if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
- (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
- struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
- if (max_headroom > dev->needed_headroom)
- dev->needed_headroom = max_headroom;
- if (!new_skb) {
- ip_rt_put(rt);
- dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
- }
- if (skb->sk)
- skb_set_owner_w(new_skb, skb->sk);
- dev_kfree_skb(skb);
- skb = new_skb;
- old_iph = ip_hdr(skb);
- /* Warning : tiph value might point to freed memory */
- }
+ if (dev->header_ops) {
+ /* Need space for new headers */
+ if (skb_cow_head(skb, dev->needed_headroom -
+ (tunnel->hlen + sizeof(struct iphdr))));
+ goto free_skb;
- skb_push(skb, gre_hlen);
- skb_reset_network_header(skb);
- skb_set_transport_header(skb, sizeof(*iph));
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
- IPSKB_REROUTED);
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
- /*
- * Push down and install the IPIP header.
- */
+ tnl_params = (const struct iphdr *)skb->data;
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr) >> 2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_GRE;
- iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb);
- iph->daddr = fl4.daddr;
- iph->saddr = fl4.saddr;
- iph->ttl = ttl;
-
- tunnel_ip_select_ident(skb, old_iph, &rt->dst);
-
- if (ttl == 0) {
- if (skb->protocol == htons(ETH_P_IP))
- iph->ttl = old_iph->ttl;
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6))
- iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
-#endif
- else
- iph->ttl = ip4_dst_hoplimit(&rt->dst);
- }
-
- ((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
- ((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
- htons(ETH_P_TEB) : skb->protocol;
-
- if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
- __be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4);
+ /* Pull skb since ip_tunnel_xmit() needs skb->data pointing
+ * to gre header.
+ */
+ skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+ } else {
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto free_skb;
- if (tunnel->parms.o_flags&GRE_SEQ) {
- ++tunnel->o_seqno;
- *ptr = htonl(tunnel->o_seqno);
- ptr--;
- }
- if (tunnel->parms.o_flags&GRE_KEY) {
- *ptr = tunnel->parms.o_key;
- ptr--;
- }
- /* Skip GRE checksum if skb is getting offloaded. */
- if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) &&
- (tunnel->parms.o_flags&GRE_CSUM)) {
- int offset = skb_transport_offset(skb);
-
- if (skb_has_shared_frag(skb)) {
- err = __skb_linearize(skb);
- if (err)
- goto tx_error;
- }
-
- *ptr = 0;
- *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset,
- skb->len - offset,
- 0));
- }
+ tnl_params = &tunnel->parms.iph;
}
- nf_reset(skb);
+ __gre_xmit(skb, dev, tnl_params, skb->protocol);
- pkt_len = skb->len - skb_transport_offset(skb);
- err = ip_local_out(skb);
- if (likely(net_xmit_eval(err) == 0)) {
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += pkt_len;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
- } else {
- dev->stats.tx_errors++;
- dev->stats.tx_aborted_errors++;
- }
return NETDEV_TX_OK;
-#if IS_ENABLED(CONFIG_IPV6)
-tx_error_icmp:
- dst_link_failure(skb);
-#endif
-tx_error:
- dev->stats.tx_errors++;
+free_skb:
dev_kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
-static int ipgre_tunnel_bind_dev(struct net_device *dev)
+static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
+ struct net_device *dev)
{
- struct net_device *tdev = NULL;
- struct ip_tunnel *tunnel;
- const struct iphdr *iph;
- int hlen = LL_MAX_HEADER;
- int mtu = ETH_DATA_LEN;
- int addend = sizeof(struct iphdr) + 4;
-
- tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
-
- /* Guess output device to choose reasonable mtu and needed_headroom */
-
- if (iph->daddr) {
- struct flowi4 fl4;
- struct rtable *rt;
-
- rt = ip_route_output_gre(dev_net(dev), &fl4,
- iph->daddr, iph->saddr,
- tunnel->parms.o_key,
- RT_TOS(iph->tos),
- tunnel->parms.link);
- if (!IS_ERR(rt)) {
- tdev = rt->dst.dev;
- ip_rt_put(rt);
- }
-
- if (dev->type != ARPHRD_ETHER)
- dev->flags |= IFF_POINTOPOINT;
- }
+ struct ip_tunnel *tunnel = netdev_priv(dev);
- if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+ skb = handle_offloads(tunnel, skb);
+ if (IS_ERR(skb))
+ goto out;
- if (tdev) {
- hlen = tdev->hard_header_len + tdev->needed_headroom;
- mtu = tdev->mtu;
- }
- dev->iflink = tunnel->parms.link;
-
- /* Precalculate GRE options length */
- if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
- if (tunnel->parms.o_flags&GRE_CSUM)
- addend += 4;
- if (tunnel->parms.o_flags&GRE_KEY)
- addend += 4;
- if (tunnel->parms.o_flags&GRE_SEQ)
- addend += 4;
- }
- dev->needed_headroom = addend + hlen;
- mtu -= dev->hard_header_len + addend;
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto free_skb;
- if (mtu < 68)
- mtu = 68;
+ __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB));
- tunnel->hlen = addend;
- /* TCP offload with GRE SEQ is not supported. */
- if (!(tunnel->parms.o_flags & GRE_SEQ)) {
- dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_GSO_SOFTWARE;
- }
+ return NETDEV_TX_OK;
- return mtu;
+free_skb:
+ dev_kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
}
-static int
-ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+static int ipgre_tunnel_ioctl(struct net_device *dev,
+ struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
- struct ip_tunnel *t;
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
- switch (cmd) {
- case SIOCGETTUNNEL:
- t = NULL;
- if (dev == ign->fb_tunnel_dev) {
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
- err = -EFAULT;
- break;
- }
- t = ipgre_tunnel_locate(net, &p, 0);
- }
- if (t == NULL)
- t = netdev_priv(dev);
- memcpy(&p, &t->parms, sizeof(p));
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
- err = -EFAULT;
- break;
-
- case SIOCADDTUNNEL:
- case SIOCCHGTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
-
- err = -EINVAL;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
- ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
- goto done;
- if (p.iph.ttl)
- p.iph.frag_off |= htons(IP_DF);
-
- if (!(p.i_flags&GRE_KEY))
- p.i_key = 0;
- if (!(p.o_flags&GRE_KEY))
- p.o_key = 0;
-
- t = ipgre_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
-
- if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
- if (t != NULL) {
- if (t->dev != dev) {
- err = -EEXIST;
- break;
- }
- } else {
- unsigned int nflags = 0;
-
- t = netdev_priv(dev);
-
- if (ipv4_is_multicast(p.iph.daddr))
- nflags = IFF_BROADCAST;
- else if (p.iph.daddr)
- nflags = IFF_POINTOPOINT;
-
- if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
- err = -EINVAL;
- break;
- }
- ipgre_tunnel_unlink(ign, t);
- synchronize_net();
- t->parms.iph.saddr = p.iph.saddr;
- t->parms.iph.daddr = p.iph.daddr;
- t->parms.i_key = p.i_key;
- t->parms.o_key = p.o_key;
- memcpy(dev->dev_addr, &p.iph.saddr, 4);
- memcpy(dev->broadcast, &p.iph.daddr, 4);
- ipgre_tunnel_link(ign, t);
- netdev_state_change(dev);
- }
- }
-
- if (t) {
- err = 0;
- if (cmd == SIOCCHGTUNNEL) {
- t->parms.iph.ttl = p.iph.ttl;
- t->parms.iph.tos = p.iph.tos;
- t->parms.iph.frag_off = p.iph.frag_off;
- if (t->parms.link != p.link) {
- t->parms.link = p.link;
- dev->mtu = ipgre_tunnel_bind_dev(dev);
- netdev_state_change(dev);
- }
- }
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
- err = -EFAULT;
- } else
- err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
- break;
-
- case SIOCDELTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- if (dev == ign->fb_tunnel_dev) {
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
- err = -ENOENT;
- if ((t = ipgre_tunnel_locate(net, &p, 0)) == NULL)
- goto done;
- err = -EPERM;
- if (t == netdev_priv(ign->fb_tunnel_dev))
- goto done;
- dev = t->dev;
- }
- unregister_netdevice(dev);
- err = 0;
- break;
- default:
- err = -EINVAL;
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+ return -EFAULT;
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
+ ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) {
+ return -EINVAL;
}
+ p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
+ p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
-done:
- return err;
-}
+ err = ip_tunnel_ioctl(dev, &p, cmd);
+ if (err)
+ return err;
-static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- if (new_mtu < 68 ||
- new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen)
- return -EINVAL;
- dev->mtu = new_mtu;
+ p.i_flags = tnl_flags_to_gre_flags(p.i_flags);
+ p.o_flags = tnl_flags_to_gre_flags(p.o_flags);
+
+ if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+ return -EFAULT;
return 0;
}
@@ -1277,25 +546,23 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
...
ftp fec0:6666:6666::193.233.7.65
...
-
*/
-
static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
const void *daddr, const void *saddr, unsigned int len)
{
struct ip_tunnel *t = netdev_priv(dev);
- struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
- __be16 *p = (__be16 *)(iph+1);
+ struct iphdr *iph;
+ struct gre_base_hdr *greh;
- memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
- p[0] = t->parms.o_flags;
- p[1] = htons(type);
+ iph = (struct iphdr *)skb_push(skb, t->hlen + sizeof(*iph));
+ greh = (struct gre_base_hdr *)(iph+1);
+ greh->flags = tnl_flags_to_gre_flags(t->parms.o_flags);
+ greh->protocol = htons(type);
- /*
- * Set the source hardware address.
- */
+ memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
+ /* Set the source hardware address. */
if (saddr)
memcpy(&iph->saddr, saddr, 4);
if (daddr)
@@ -1303,7 +570,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
if (iph->daddr)
return t->hlen;
- return -t->hlen;
+ return -(t->hlen + sizeof(*iph));
}
static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
@@ -1357,31 +624,21 @@ static int ipgre_close(struct net_device *dev)
}
return 0;
}
-
#endif
static const struct net_device_ops ipgre_netdev_ops = {
.ndo_init = ipgre_tunnel_init,
- .ndo_uninit = ipgre_tunnel_uninit,
+ .ndo_uninit = ip_tunnel_uninit,
#ifdef CONFIG_NET_IPGRE_BROADCAST
.ndo_open = ipgre_open,
.ndo_stop = ipgre_close,
#endif
- .ndo_start_xmit = ipgre_tunnel_xmit,
+ .ndo_start_xmit = ipgre_xmit,
.ndo_do_ioctl = ipgre_tunnel_ioctl,
- .ndo_change_mtu = ipgre_tunnel_change_mtu,
- .ndo_get_stats64 = ipgre_get_stats64,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
-static void ipgre_dev_free(struct net_device *dev)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
-
- gro_cells_destroy(&tunnel->gro_cells);
- free_percpu(dev->tstats);
- free_netdev(dev);
-}
-
#define GRE_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
@@ -1390,35 +647,48 @@ static void ipgre_dev_free(struct net_device *dev)
static void ipgre_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipgre_netdev_ops;
- dev->destructor = ipgre_dev_free;
+ ip_tunnel_setup(dev, ipgre_net_id);
+}
- dev->type = ARPHRD_IPGRE;
- dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
+static void __gre_tunnel_init(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel;
+
+ tunnel = netdev_priv(dev);
+ tunnel->hlen = ip_gre_calc_hlen(tunnel->parms.o_flags);
+ tunnel->parms.iph.protocol = IPPROTO_GRE;
+
+ dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 4;
- dev->flags = IFF_NOARP;
- dev->iflink = 0;
- dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
- dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
- dev->features |= GRE_FEATURES;
+ dev->features |= NETIF_F_NETNS_LOCAL | GRE_FEATURES;
dev->hw_features |= GRE_FEATURES;
+
+ if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
+ /* TCP offload with GRE SEQ is not supported. */
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ /* Can use a lockless transmit, unless we generate
+ * output sequences
+ */
+ dev->features |= NETIF_F_LLTX;
+ }
}
static int ipgre_tunnel_init(struct net_device *dev)
{
- struct ip_tunnel *tunnel;
- struct iphdr *iph;
- int err;
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct iphdr *iph = &tunnel->parms.iph;
- tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
+ __gre_tunnel_init(dev);
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
+ memcpy(dev->dev_addr, &iph->saddr, 4);
+ memcpy(dev->broadcast, &iph->daddr, 4);
- memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
- memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
+ dev->type = ARPHRD_IPGRE;
+ dev->flags = IFF_NOARP;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ dev->addr_len = 4;
if (iph->daddr) {
#ifdef CONFIG_NET_IPGRE_BROADCAST
@@ -1432,106 +702,30 @@ static int ipgre_tunnel_init(struct net_device *dev)
} else
dev->header_ops = &ipgre_header_ops;
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- err = gro_cells_init(&tunnel->gro_cells, dev);
- if (err) {
- free_percpu(dev->tstats);
- return err;
- }
-
- return 0;
-}
-
-static void ipgre_fb_tunnel_init(struct net_device *dev)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- struct iphdr *iph = &tunnel->parms.iph;
-
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
- iph->version = 4;
- iph->protocol = IPPROTO_GRE;
- iph->ihl = 5;
- tunnel->hlen = sizeof(struct iphdr) + 4;
-
- dev_hold(dev);
+ return ip_tunnel_init(dev);
}
-
static const struct gre_protocol ipgre_protocol = {
.handler = ipgre_rcv,
.err_handler = ipgre_err,
};
-static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
-{
- int prio;
-
- for (prio = 0; prio < 4; prio++) {
- int h;
- for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
-
- t = rtnl_dereference(ign->tunnels[prio][h]);
-
- while (t != NULL) {
- unregister_netdevice_queue(t->dev, head);
- t = rtnl_dereference(t->next);
- }
- }
- }
-}
-
static int __net_init ipgre_init_net(struct net *net)
{
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- int err;
-
- ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
- ipgre_tunnel_setup);
- if (!ign->fb_tunnel_dev) {
- err = -ENOMEM;
- goto err_alloc_dev;
- }
- dev_net_set(ign->fb_tunnel_dev, net);
-
- ipgre_fb_tunnel_init(ign->fb_tunnel_dev);
- ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops;
-
- if ((err = register_netdev(ign->fb_tunnel_dev)))
- goto err_reg_dev;
-
- rcu_assign_pointer(ign->tunnels_wc[0],
- netdev_priv(ign->fb_tunnel_dev));
- return 0;
-
-err_reg_dev:
- ipgre_dev_free(ign->fb_tunnel_dev);
-err_alloc_dev:
- return err;
+ return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
}
static void __net_exit ipgre_exit_net(struct net *net)
{
- struct ipgre_net *ign;
- LIST_HEAD(list);
-
- ign = net_generic(net, ipgre_net_id);
- rtnl_lock();
- ipgre_destroy_tunnels(ign, &list);
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
+ ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipgre_net_ops = {
.init = ipgre_init_net,
.exit = ipgre_exit_net,
.id = &ipgre_net_id,
- .size = sizeof(struct ipgre_net),
+ .size = sizeof(struct ip_tunnel_net),
};
static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1576,8 +770,8 @@ out:
return ipgre_tunnel_validate(tb, data);
}
-static void ipgre_netlink_parms(struct nlattr *data[],
- struct ip_tunnel_parm *parms)
+static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[],
+ struct ip_tunnel_parm *parms)
{
memset(parms, 0, sizeof(*parms));
@@ -1590,10 +784,10 @@ static void ipgre_netlink_parms(struct nlattr *data[],
parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
if (data[IFLA_GRE_IFLAGS])
- parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]);
+ parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS]));
if (data[IFLA_GRE_OFLAGS])
- parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]);
+ parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS]));
if (data[IFLA_GRE_IKEY])
parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]);
@@ -1617,148 +811,46 @@ static void ipgre_netlink_parms(struct nlattr *data[],
parms->iph.frag_off = htons(IP_DF);
}
-static int ipgre_tap_init(struct net_device *dev)
+static int gre_tap_init(struct net_device *dev)
{
- struct ip_tunnel *tunnel;
-
- tunnel = netdev_priv(dev);
-
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
+ __gre_tunnel_init(dev);
- ipgre_tunnel_bind_dev(dev);
-
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- return 0;
+ return ip_tunnel_init(dev);
}
-static const struct net_device_ops ipgre_tap_netdev_ops = {
- .ndo_init = ipgre_tap_init,
- .ndo_uninit = ipgre_tunnel_uninit,
- .ndo_start_xmit = ipgre_tunnel_xmit,
+static const struct net_device_ops gre_tap_netdev_ops = {
+ .ndo_init = gre_tap_init,
+ .ndo_uninit = ip_tunnel_uninit,
+ .ndo_start_xmit = gre_tap_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
- .ndo_change_mtu = ipgre_tunnel_change_mtu,
- .ndo_get_stats64 = ipgre_get_stats64,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipgre_tap_setup(struct net_device *dev)
{
-
ether_setup(dev);
-
- dev->netdev_ops = &ipgre_tap_netdev_ops;
- dev->destructor = ipgre_dev_free;
-
- dev->iflink = 0;
- dev->features |= NETIF_F_NETNS_LOCAL;
-
- dev->features |= GRE_FEATURES;
- dev->hw_features |= GRE_FEATURES;
+ dev->netdev_ops = &gre_tap_netdev_ops;
+ ip_tunnel_setup(dev, gre_tap_net_id);
}
-static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
- struct nlattr *data[])
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
{
- struct ip_tunnel *nt;
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- int mtu;
- int err;
-
- nt = netdev_priv(dev);
- ipgre_netlink_parms(data, &nt->parms);
-
- if (ipgre_tunnel_find(net, &nt->parms, dev->type))
- return -EEXIST;
-
- if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
- eth_hw_addr_random(dev);
-
- mtu = ipgre_tunnel_bind_dev(dev);
- if (!tb[IFLA_MTU])
- dev->mtu = mtu;
-
- /* Can use a lockless transmit, unless we generate output sequences */
- if (!(nt->parms.o_flags & GRE_SEQ))
- dev->features |= NETIF_F_LLTX;
-
- err = register_netdevice(dev);
- if (err)
- goto out;
-
- dev_hold(dev);
- ipgre_tunnel_link(ign, nt);
+ struct ip_tunnel_parm p;
-out:
- return err;
+ ipgre_netlink_parms(data, tb, &p);
+ return ip_tunnel_newlink(dev, tb, &p);
}
static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip_tunnel *t, *nt;
- struct net *net = dev_net(dev);
- struct ipgre_net *ign = net_generic(net, ipgre_net_id);
struct ip_tunnel_parm p;
- int mtu;
-
- if (dev == ign->fb_tunnel_dev)
- return -EINVAL;
-
- nt = netdev_priv(dev);
- ipgre_netlink_parms(data, &p);
-
- t = ipgre_tunnel_locate(net, &p, 0);
-
- if (t) {
- if (t->dev != dev)
- return -EEXIST;
- } else {
- t = nt;
-
- if (dev->type != ARPHRD_ETHER) {
- unsigned int nflags = 0;
-
- if (ipv4_is_multicast(p.iph.daddr))
- nflags = IFF_BROADCAST;
- else if (p.iph.daddr)
- nflags = IFF_POINTOPOINT;
-
- if ((dev->flags ^ nflags) &
- (IFF_POINTOPOINT | IFF_BROADCAST))
- return -EINVAL;
- }
- ipgre_tunnel_unlink(ign, t);
- t->parms.iph.saddr = p.iph.saddr;
- t->parms.iph.daddr = p.iph.daddr;
- t->parms.i_key = p.i_key;
- if (dev->type != ARPHRD_ETHER) {
- memcpy(dev->dev_addr, &p.iph.saddr, 4);
- memcpy(dev->broadcast, &p.iph.daddr, 4);
- }
- ipgre_tunnel_link(ign, t);
- netdev_state_change(dev);
- }
-
- t->parms.o_key = p.o_key;
- t->parms.iph.ttl = p.iph.ttl;
- t->parms.iph.tos = p.iph.tos;
- t->parms.iph.frag_off = p.iph.frag_off;
-
- if (t->parms.link != p.link) {
- t->parms.link = p.link;
- mtu = ipgre_tunnel_bind_dev(dev);
- if (!tb[IFLA_MTU])
- dev->mtu = mtu;
- netdev_state_change(dev);
- }
-
- return 0;
+ ipgre_netlink_parms(data, tb, &p);
+ return ip_tunnel_changelink(dev, tb, &p);
}
static size_t ipgre_get_size(const struct net_device *dev)
@@ -1793,8 +885,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
struct ip_tunnel_parm *p = &t->parms;
if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
- nla_put_be16(skb, IFLA_GRE_IFLAGS, p->i_flags) ||
- nla_put_be16(skb, IFLA_GRE_OFLAGS, p->o_flags) ||
+ nla_put_be16(skb, IFLA_GRE_IFLAGS, tnl_flags_to_gre_flags(p->i_flags)) ||
+ nla_put_be16(skb, IFLA_GRE_OFLAGS, tnl_flags_to_gre_flags(p->o_flags)) ||
nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
nla_put_be32(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
@@ -1832,6 +924,7 @@ static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
.validate = ipgre_tunnel_validate,
.newlink = ipgre_newlink,
.changelink = ipgre_changelink,
+ .dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
};
@@ -1845,13 +938,28 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
.validate = ipgre_tap_validate,
.newlink = ipgre_newlink,
.changelink = ipgre_changelink,
+ .dellink = ip_tunnel_dellink,
.get_size = ipgre_get_size,
.fill_info = ipgre_fill_info,
};
-/*
- * And now the modules code and kernel interface.
- */
+static int __net_init ipgre_tap_init_net(struct net *net)
+{
+ return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL);
+}
+
+static void __net_exit ipgre_tap_exit_net(struct net *net)
+{
+ struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
+ ip_tunnel_delete_net(itn);
+}
+
+static struct pernet_operations ipgre_tap_net_ops = {
+ .init = ipgre_tap_init_net,
+ .exit = ipgre_tap_exit_net,
+ .id = &gre_tap_net_id,
+ .size = sizeof(struct ip_tunnel_net),
+};
static int __init ipgre_init(void)
{
@@ -1863,6 +971,10 @@ static int __init ipgre_init(void)
if (err < 0)
return err;
+ err = register_pernet_device(&ipgre_tap_net_ops);
+ if (err < 0)
+ goto pnet_tap_faied;
+
err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
if (err < 0) {
pr_info("%s: can't add protocol\n", __func__);
@@ -1877,16 +989,17 @@ static int __init ipgre_init(void)
if (err < 0)
goto tap_ops_failed;
-out:
- return err;
+ return 0;
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
add_proto_failed:
+ unregister_pernet_device(&ipgre_tap_net_ops);
+pnet_tap_faied:
unregister_pernet_device(&ipgre_net_ops);
- goto out;
+ return err;
}
static void __exit ipgre_fini(void)
@@ -1895,6 +1008,7 @@ static void __exit ipgre_fini(void)
rtnl_link_unregister(&ipgre_link_ops);
if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
pr_info("%s: can't remove protocol\n", __func__);
+ unregister_pernet_device(&ipgre_tap_net_ops);
unregister_pernet_device(&ipgre_net_ops);
}
@@ -1904,3 +1018,4 @@ MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
MODULE_ALIAS_NETDEV("gre0");
+MODULE_ALIAS_NETDEV("gretap0");
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
new file mode 100644
index 000000000000..e4147ec1665a
--- /dev/null
+++ b/net/ipv4/ip_tunnel.c
@@ -0,0 +1,1035 @@
+/*
+ * Copyright (c) 2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/if_arp.h>
+#include <linux/mroute.h>
+#include <linux/init.h>
+#include <linux/in6.h>
+#include <linux/inetdevice.h>
+#include <linux/igmp.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/rculist.h>
+
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/protocol.h>
+#include <net/ip_tunnels.h>
+#include <net/arp.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+#include <net/inet_ecn.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/ipv6.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+#endif
+
+static unsigned int ip_tunnel_hash(struct ip_tunnel_net *itn,
+ __be32 key, __be32 remote)
+{
+ return hash_32((__force u32)key ^ (__force u32)remote,
+ IP_TNL_HASH_BITS);
+}
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *tot)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&tstats->syncp);
+ rx_packets = tstats->rx_packets;
+ tx_packets = tstats->tx_packets;
+ rx_bytes = tstats->rx_bytes;
+ tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+ tot->rx_packets += rx_packets;
+ tot->tx_packets += tx_packets;
+ tot->rx_bytes += rx_bytes;
+ tot->tx_bytes += tx_bytes;
+ }
+
+ tot->multicast = dev->stats.multicast;
+
+ tot->rx_crc_errors = dev->stats.rx_crc_errors;
+ tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+ tot->rx_length_errors = dev->stats.rx_length_errors;
+ tot->rx_frame_errors = dev->stats.rx_frame_errors;
+ tot->rx_errors = dev->stats.rx_errors;
+
+ tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+ tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+ tot->tx_dropped = dev->stats.tx_dropped;
+ tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+ tot->tx_errors = dev->stats.tx_errors;
+
+ tot->collisions = dev->stats.collisions;
+
+ return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
+
+static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
+ __be16 flags, __be32 key)
+{
+ if (p->i_flags & TUNNEL_KEY) {
+ if (flags & TUNNEL_KEY)
+ return key == p->i_key;
+ else
+ /* key expected, none present */
+ return false;
+ } else
+ return !(flags & TUNNEL_KEY);
+}
+
+/* Fallback tunnel: no source, no destination, no key, no options
+
+ Tunnel hash table:
+ We require exact key match i.e. if a key is present in packet
+ it will match only tunnel with the same key; if it is not present,
+ it will match only keyless tunnel.
+
+ All keysless packets, if not matched configured keyless tunnels
+ will match fallback tunnel.
+ Given src, dst and key, find appropriate for input tunnel.
+*/
+struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
+ int link, __be16 flags,
+ __be32 remote, __be32 local,
+ __be32 key)
+{
+ unsigned int hash;
+ struct ip_tunnel *t, *cand = NULL;
+ struct hlist_head *head;
+
+ hash = ip_tunnel_hash(itn, key, remote);
+ head = &itn->tunnels[hash];
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (local != t->parms.iph.saddr ||
+ remote != t->parms.iph.daddr ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (!ip_tunnel_key_match(&t->parms, flags, key))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else
+ cand = t;
+ }
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (remote != t->parms.iph.daddr ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (!ip_tunnel_key_match(&t->parms, flags, key))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else if (!cand)
+ cand = t;
+ }
+
+ hash = ip_tunnel_hash(itn, key, 0);
+ head = &itn->tunnels[hash];
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if ((local != t->parms.iph.saddr &&
+ (local != t->parms.iph.daddr ||
+ !ipv4_is_multicast(local))) ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (!ip_tunnel_key_match(&t->parms, flags, key))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else if (!cand)
+ cand = t;
+ }
+
+ if (flags & TUNNEL_NO_KEY)
+ goto skip_key_lookup;
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (t->parms.i_key != key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->parms.link == link)
+ return t;
+ else if (!cand)
+ cand = t;
+ }
+
+skip_key_lookup:
+ if (cand)
+ return cand;
+
+ if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
+ return netdev_priv(itn->fb_tunnel_dev);
+
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_lookup);
+
+static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn,
+ struct ip_tunnel_parm *parms)
+{
+ unsigned int h;
+ __be32 remote;
+
+ if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
+ remote = parms->iph.daddr;
+ else
+ remote = 0;
+
+ h = ip_tunnel_hash(itn, parms->i_key, remote);
+ return &itn->tunnels[h];
+}
+
+static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t)
+{
+ struct hlist_head *head = ip_bucket(itn, &t->parms);
+
+ hlist_add_head_rcu(&t->hash_node, head);
+}
+
+static void ip_tunnel_del(struct ip_tunnel *t)
+{
+ hlist_del_init_rcu(&t->hash_node);
+}
+
+static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
+ struct ip_tunnel_parm *parms,
+ int type)
+{
+ __be32 remote = parms->iph.daddr;
+ __be32 local = parms->iph.saddr;
+ __be32 key = parms->i_key;
+ int link = parms->link;
+ struct ip_tunnel *t = NULL;
+ struct hlist_head *head = ip_bucket(itn, parms);
+
+ hlist_for_each_entry_rcu(t, head, hash_node) {
+ if (local == t->parms.iph.saddr &&
+ remote == t->parms.iph.daddr &&
+ key == t->parms.i_key &&
+ link == t->parms.link &&
+ type == t->dev->type)
+ break;
+ }
+ return t;
+}
+
+static struct net_device *__ip_tunnel_create(struct net *net,
+ const struct rtnl_link_ops *ops,
+ struct ip_tunnel_parm *parms)
+{
+ int err;
+ struct ip_tunnel *tunnel;
+ struct net_device *dev;
+ char name[IFNAMSIZ];
+
+ if (parms->name[0])
+ strlcpy(name, parms->name, IFNAMSIZ);
+ else {
+ if (strlen(ops->kind) > (IFNAMSIZ - 3)) {
+ err = -E2BIG;
+ goto failed;
+ }
+ strlcpy(name, ops->kind, IFNAMSIZ);
+ strncat(name, "%d", 2);
+ }
+
+ ASSERT_RTNL();
+ dev = alloc_netdev(ops->priv_size, name, ops->setup);
+ if (!dev) {
+ err = -ENOMEM;
+ goto failed;
+ }
+ dev_net_set(dev, net);
+
+ dev->rtnl_link_ops = ops;
+
+ tunnel = netdev_priv(dev);
+ tunnel->parms = *parms;
+
+ err = register_netdevice(dev);
+ if (err)
+ goto failed_free;
+
+ return dev;
+
+failed_free:
+ free_netdev(dev);
+failed:
+ return ERR_PTR(err);
+}
+
+static inline struct rtable *ip_route_output_tunnel(struct net *net,
+ struct flowi4 *fl4,
+ int proto,
+ __be32 daddr, __be32 saddr,
+ __be32 key, __u8 tos, int oif)
+{
+ memset(fl4, 0, sizeof(*fl4));
+ fl4->flowi4_oif = oif;
+ fl4->daddr = daddr;
+ fl4->saddr = saddr;
+ fl4->flowi4_tos = tos;
+ fl4->flowi4_proto = proto;
+ fl4->fl4_gre_key = key;
+ return ip_route_output_key(net, fl4);
+}
+
+static int ip_tunnel_bind_dev(struct net_device *dev)
+{
+ struct net_device *tdev = NULL;
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *iph;
+ int hlen = LL_MAX_HEADER;
+ int mtu = ETH_DATA_LEN;
+ int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+ iph = &tunnel->parms.iph;
+
+ /* Guess output device to choose reasonable mtu and needed_headroom */
+ if (iph->daddr) {
+ struct flowi4 fl4;
+ struct rtable *rt;
+
+ rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+ tunnel->parms.iph.protocol,
+ iph->daddr, iph->saddr,
+ tunnel->parms.o_key,
+ RT_TOS(iph->tos),
+ tunnel->parms.link);
+ if (!IS_ERR(rt)) {
+ tdev = rt->dst.dev;
+ ip_rt_put(rt);
+ }
+ if (dev->type != ARPHRD_ETHER)
+ dev->flags |= IFF_POINTOPOINT;
+ }
+
+ if (!tdev && tunnel->parms.link)
+ tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+
+ if (tdev) {
+ hlen = tdev->hard_header_len + tdev->needed_headroom;
+ mtu = tdev->mtu;
+ }
+ dev->iflink = tunnel->parms.link;
+
+ dev->needed_headroom = t_hlen + hlen;
+ mtu -= (dev->hard_header_len + t_hlen);
+
+ if (mtu < 68)
+ mtu = 68;
+
+ return mtu;
+}
+
+static struct ip_tunnel *ip_tunnel_create(struct net *net,
+ struct ip_tunnel_net *itn,
+ struct ip_tunnel_parm *parms)
+{
+ struct ip_tunnel *nt, *fbt;
+ struct net_device *dev;
+
+ BUG_ON(!itn->fb_tunnel_dev);
+ fbt = netdev_priv(itn->fb_tunnel_dev);
+ dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
+ if (IS_ERR(dev))
+ return NULL;
+
+ dev->mtu = ip_tunnel_bind_dev(dev);
+
+ nt = netdev_priv(dev);
+ ip_tunnel_add(itn, nt);
+ return nt;
+}
+
+int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
+ const struct tnl_ptk_info *tpi, bool log_ecn_error)
+{
+ struct pcpu_tstats *tstats;
+ const struct iphdr *iph = ip_hdr(skb);
+ int err;
+
+ secpath_reset(skb);
+
+ skb->protocol = tpi->proto;
+
+ skb->mac_header = skb->network_header;
+ __pskb_pull(skb, tunnel->hlen);
+ skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ if (ipv4_is_multicast(iph->daddr)) {
+ /* Looped back packet, drop it! */
+ if (rt_is_output_route(skb_rtable(skb)))
+ goto drop;
+ tunnel->dev->stats.multicast++;
+ skb->pkt_type = PACKET_BROADCAST;
+ }
+#endif
+
+ if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) ||
+ ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) {
+ tunnel->dev->stats.rx_crc_errors++;
+ tunnel->dev->stats.rx_errors++;
+ goto drop;
+ }
+
+ if (tunnel->parms.i_flags&TUNNEL_SEQ) {
+ if (!(tpi->flags&TUNNEL_SEQ) ||
+ (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
+ tunnel->dev->stats.rx_fifo_errors++;
+ tunnel->dev->stats.rx_errors++;
+ goto drop;
+ }
+ tunnel->i_seqno = ntohl(tpi->seq) + 1;
+ }
+
+ /* Warning: All skb pointers will be invalidated! */
+ if (tunnel->dev->type == ARPHRD_ETHER) {
+ if (!pskb_may_pull(skb, ETH_HLEN)) {
+ tunnel->dev->stats.rx_length_errors++;
+ tunnel->dev->stats.rx_errors++;
+ goto drop;
+ }
+
+ iph = ip_hdr(skb);
+ skb->protocol = eth_type_trans(skb, tunnel->dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ }
+
+ skb->pkt_type = PACKET_HOST;
+ __skb_tunnel_rx(skb, tunnel->dev);
+
+ skb_reset_network_header(skb);
+ err = IP_ECN_decapsulate(iph, skb);
+ if (unlikely(err)) {
+ if (log_ecn_error)
+ net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+ &iph->saddr, iph->tos);
+ if (err > 1) {
+ ++tunnel->dev->stats.rx_frame_errors;
+ ++tunnel->dev->stats.rx_errors;
+ goto drop;
+ }
+ }
+
+ tstats = this_cpu_ptr(tunnel->dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
+
+ gro_cells_receive(&tunnel->gro_cells, skb);
+ return 0;
+
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
+
+void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *inner_iph;
+ struct iphdr *iph;
+ struct flowi4 fl4;
+ u8 tos, ttl;
+ __be16 df;
+ struct rtable *rt; /* Route to the other host */
+ struct net_device *tdev; /* Device to other host */
+ unsigned int max_headroom; /* The extra header space needed */
+ __be32 dst;
+ int mtu;
+
+ inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+
+ dst = tnl_params->daddr;
+ if (dst == 0) {
+ /* NBMA tunnel */
+
+ if (skb_dst(skb) == NULL) {
+ dev->stats.tx_fifo_errors++;
+ goto tx_error;
+ }
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ rt = skb_rtable(skb);
+ dst = rt_nexthop(rt, inner_iph->daddr);
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
+ const struct in6_addr *addr6;
+ struct neighbour *neigh;
+ bool do_tx_error_icmp;
+ int addr_type;
+
+ neigh = dst_neigh_lookup(skb_dst(skb),
+ &ipv6_hdr(skb)->daddr);
+ if (neigh == NULL)
+ goto tx_error;
+
+ addr6 = (const struct in6_addr *)&neigh->primary_key;
+ addr_type = ipv6_addr_type(addr6);
+
+ if (addr_type == IPV6_ADDR_ANY) {
+ addr6 = &ipv6_hdr(skb)->daddr;
+ addr_type = ipv6_addr_type(addr6);
+ }
+
+ if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
+ do_tx_error_icmp = true;
+ else {
+ do_tx_error_icmp = false;
+ dst = addr6->s6_addr32[3];
+ }
+ neigh_release(neigh);
+ if (do_tx_error_icmp)
+ goto tx_error_icmp;
+ }
+#endif
+ else
+ goto tx_error;
+ }
+
+ tos = tnl_params->tos;
+ if (tos & 0x1) {
+ tos &= ~0x1;
+ if (skb->protocol == htons(ETH_P_IP))
+ tos = inner_iph->tos;
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
+ }
+
+ rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+ tunnel->parms.iph.protocol,
+ dst, tnl_params->saddr,
+ tunnel->parms.o_key,
+ RT_TOS(tos),
+ tunnel->parms.link);
+ if (IS_ERR(rt)) {
+ dev->stats.tx_carrier_errors++;
+ goto tx_error;
+ }
+ tdev = rt->dst.dev;
+
+ if (tdev == dev) {
+ ip_rt_put(rt);
+ dev->stats.collisions++;
+ goto tx_error;
+ }
+
+ df = tnl_params->frag_off;
+
+ if (df)
+ mtu = dst_mtu(&rt->dst) - dev->hard_header_len
+ - sizeof(struct iphdr);
+ else
+ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+
+ if (skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ df |= (inner_iph->frag_off&htons(IP_DF));
+
+ if (!skb_is_gso(skb) &&
+ (inner_iph->frag_off&htons(IP_DF)) &&
+ mtu < ntohs(inner_iph->tot_len)) {
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+ ip_rt_put(rt);
+ goto tx_error;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
+
+ if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
+ mtu >= IPV6_MIN_MTU) {
+ if ((tunnel->parms.iph.daddr &&
+ !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
+ rt6->rt6i_dst.plen == 128) {
+ rt6->rt6i_flags |= RTF_MODIFIED;
+ dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
+ }
+ }
+
+ if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
+ mtu < skb->len) {
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ ip_rt_put(rt);
+ goto tx_error;
+ }
+ }
+#endif
+
+ if (tunnel->err_count > 0) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
+ tunnel->err_count--;
+
+ dst_link_failure(skb);
+ } else
+ tunnel->err_count = 0;
+ }
+
+ ttl = tnl_params->ttl;
+ if (ttl == 0) {
+ if (skb->protocol == htons(ETH_P_IP))
+ ttl = inner_iph->ttl;
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
+#endif
+ else
+ ttl = ip4_dst_hoplimit(&rt->dst);
+ }
+
+ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
+ + rt->dst.header_len;
+ if (max_headroom > dev->needed_headroom) {
+ dev->needed_headroom = max_headroom;
+ if (skb_cow_head(skb, dev->needed_headroom)) {
+ dev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return;
+ }
+ }
+
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->dst);
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+
+ /* Push down and install the IP header. */
+ skb_push(skb, sizeof(struct iphdr));
+ skb_reset_network_header(skb);
+
+ iph = ip_hdr(skb);
+ inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+
+ iph->version = 4;
+ iph->ihl = sizeof(struct iphdr) >> 2;
+ iph->frag_off = df;
+ iph->protocol = tnl_params->protocol;
+ iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
+ iph->daddr = fl4.daddr;
+ iph->saddr = fl4.saddr;
+ iph->ttl = ttl;
+ tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
+
+ iptunnel_xmit(skb, dev);
+ return;
+
+#if IS_ENABLED(CONFIG_IPV6)
+tx_error_icmp:
+ dst_link_failure(skb);
+#endif
+tx_error:
+ dev->stats.tx_errors++;
+ dev_kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_xmit);
+
+static void ip_tunnel_update(struct ip_tunnel_net *itn,
+ struct ip_tunnel *t,
+ struct net_device *dev,
+ struct ip_tunnel_parm *p,
+ bool set_mtu)
+{
+ ip_tunnel_del(t);
+ t->parms.iph.saddr = p->iph.saddr;
+ t->parms.iph.daddr = p->iph.daddr;
+ t->parms.i_key = p->i_key;
+ t->parms.o_key = p->o_key;
+ if (dev->type != ARPHRD_ETHER) {
+ memcpy(dev->dev_addr, &p->iph.saddr, 4);
+ memcpy(dev->broadcast, &p->iph.daddr, 4);
+ }
+ ip_tunnel_add(itn, t);
+
+ t->parms.iph.ttl = p->iph.ttl;
+ t->parms.iph.tos = p->iph.tos;
+ t->parms.iph.frag_off = p->iph.frag_off;
+
+ if (t->parms.link != p->link) {
+ int mtu;
+
+ t->parms.link = p->link;
+ mtu = ip_tunnel_bind_dev(dev);
+ if (set_mtu)
+ dev->mtu = mtu;
+ }
+ netdev_state_change(dev);
+}
+
+int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
+{
+ int err = 0;
+ struct ip_tunnel *t;
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+
+ BUG_ON(!itn->fb_tunnel_dev);
+ switch (cmd) {
+ case SIOCGETTUNNEL:
+ t = NULL;
+ if (dev == itn->fb_tunnel_dev)
+ t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+ if (t == NULL)
+ t = netdev_priv(dev);
+ memcpy(p, &t->parms, sizeof(*p));
+ break;
+
+ case SIOCADDTUNNEL:
+ case SIOCCHGTUNNEL:
+ err = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ goto done;
+ if (p->iph.ttl)
+ p->iph.frag_off |= htons(IP_DF);
+ if (!(p->i_flags&TUNNEL_KEY))
+ p->i_key = 0;
+ if (!(p->o_flags&TUNNEL_KEY))
+ p->o_key = 0;
+
+ t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+
+ if (!t && (cmd == SIOCADDTUNNEL))
+ t = ip_tunnel_create(net, itn, p);
+
+ if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
+ if (t != NULL) {
+ if (t->dev != dev) {
+ err = -EEXIST;
+ break;
+ }
+ } else {
+ unsigned int nflags = 0;
+
+ if (ipv4_is_multicast(p->iph.daddr))
+ nflags = IFF_BROADCAST;
+ else if (p->iph.daddr)
+ nflags = IFF_POINTOPOINT;
+
+ if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
+ err = -EINVAL;
+ break;
+ }
+
+ t = netdev_priv(dev);
+ }
+ }
+
+ if (t) {
+ err = 0;
+ ip_tunnel_update(itn, t, dev, p, true);
+ } else
+ err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+ break;
+
+ case SIOCDELTUNNEL:
+ err = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ goto done;
+
+ if (dev == itn->fb_tunnel_dev) {
+ err = -ENOENT;
+ t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+ if (t == NULL)
+ goto done;
+ err = -EPERM;
+ if (t == netdev_priv(itn->fb_tunnel_dev))
+ goto done;
+ dev = t->dev;
+ }
+ unregister_netdevice(dev);
+ err = 0;
+ break;
+
+ default:
+ err = -EINVAL;
+ }
+
+done:
+ return err;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+
+ if (new_mtu < 68 ||
+ new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+ return -EINVAL;
+ dev->mtu = new_mtu;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
+
+static void ip_tunnel_dev_free(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+
+ gro_cells_destroy(&tunnel->gro_cells);
+ free_percpu(dev->tstats);
+ free_netdev(dev);
+}
+
+void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn;
+
+ itn = net_generic(net, tunnel->ip_tnl_net_id);
+
+ if (itn->fb_tunnel_dev != dev) {
+ ip_tunnel_del(netdev_priv(dev));
+ unregister_netdevice_queue(dev, head);
+ }
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_dellink);
+
+int __net_init ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
+ struct rtnl_link_ops *ops, char *devname)
+{
+ struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);
+ struct ip_tunnel_parm parms;
+
+ itn->tunnels = kzalloc(IP_TNL_HASH_SIZE * sizeof(struct hlist_head), GFP_KERNEL);
+ if (!itn->tunnels)
+ return -ENOMEM;
+
+ if (!ops) {
+ itn->fb_tunnel_dev = NULL;
+ return 0;
+ }
+ memset(&parms, 0, sizeof(parms));
+ if (devname)
+ strlcpy(parms.name, devname, IFNAMSIZ);
+
+ rtnl_lock();
+ itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
+ rtnl_unlock();
+ if (IS_ERR(itn->fb_tunnel_dev)) {
+ kfree(itn->tunnels);
+ return PTR_ERR(itn->fb_tunnel_dev);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
+
+static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head)
+{
+ int h;
+
+ for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
+ struct ip_tunnel *t;
+ struct hlist_node *n;
+ struct hlist_head *thead = &itn->tunnels[h];
+
+ hlist_for_each_entry_safe(t, n, thead, hash_node)
+ unregister_netdevice_queue(t->dev, head);
+ }
+ if (itn->fb_tunnel_dev)
+ unregister_netdevice_queue(itn->fb_tunnel_dev, head);
+}
+
+void __net_exit ip_tunnel_delete_net(struct ip_tunnel_net *itn)
+{
+ LIST_HEAD(list);
+
+ rtnl_lock();
+ ip_tunnel_destroy(itn, &list);
+ unregister_netdevice_many(&list);
+ rtnl_unlock();
+ kfree(itn->tunnels);
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
+
+int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p)
+{
+ struct ip_tunnel *nt;
+ struct net *net = dev_net(dev);
+ struct ip_tunnel_net *itn;
+ int mtu;
+ int err;
+
+ nt = netdev_priv(dev);
+ itn = net_generic(net, nt->ip_tnl_net_id);
+
+ if (ip_tunnel_find(itn, p, dev->type))
+ return -EEXIST;
+
+ nt->parms = *p;
+ err = register_netdevice(dev);
+ if (err)
+ goto out;
+
+ if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
+ eth_hw_addr_random(dev);
+
+ mtu = ip_tunnel_bind_dev(dev);
+ if (!tb[IFLA_MTU])
+ dev->mtu = mtu;
+
+ ip_tunnel_add(itn, nt);
+
+out:
+ return err;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
+
+int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct ip_tunnel_parm *p)
+{
+ struct ip_tunnel *t, *nt;
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+
+ if (dev == itn->fb_tunnel_dev)
+ return -EINVAL;
+
+ nt = netdev_priv(dev);
+
+ t = ip_tunnel_find(itn, p, dev->type);
+
+ if (t) {
+ if (t->dev != dev)
+ return -EEXIST;
+ } else {
+ t = nt;
+
+ if (dev->type != ARPHRD_ETHER) {
+ unsigned int nflags = 0;
+
+ if (ipv4_is_multicast(p->iph.daddr))
+ nflags = IFF_BROADCAST;
+ else if (p->iph.daddr)
+ nflags = IFF_POINTOPOINT;
+
+ if ((dev->flags ^ nflags) &
+ (IFF_POINTOPOINT | IFF_BROADCAST))
+ return -EINVAL;
+ }
+ }
+
+ ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU]);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_changelink);
+
+int ip_tunnel_init(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct iphdr *iph = &tunnel->parms.iph;
+ int err;
+
+ dev->destructor = ip_tunnel_dev_free;
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ err = gro_cells_init(&tunnel->gro_cells, dev);
+ if (err) {
+ free_percpu(dev->tstats);
+ return err;
+ }
+
+ tunnel->dev = dev;
+ strcpy(tunnel->parms.name, dev->name);
+ iph->version = 4;
+ iph->ihl = 5;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_init);
+
+void ip_tunnel_uninit(struct net_device *dev)
+{
+ struct net *net = dev_net(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct ip_tunnel_net *itn;
+
+ itn = net_generic(net, tunnel->ip_tnl_net_id);
+ /* fb_tunnel_dev will be unregisted in net-exit call. */
+ if (itn->fb_tunnel_dev != dev)
+ ip_tunnel_del(netdev_priv(dev));
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
+
+/* Do least required initialization, rest of init is done in tunnel_init call */
+void ip_tunnel_setup(struct net_device *dev, int net_id)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ tunnel->ip_tnl_net_id = net_id;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_setup);
+
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c3a4233c0ac2..9d2bdb2c1d3f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -38,7 +38,7 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
@@ -82,44 +82,6 @@ static int vti_tunnel_bind_dev(struct net_device *dev);
} while (0)
-static struct rtnl_link_stats64 *vti_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_errors = dev->stats.rx_errors;
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
-}
-
static struct ip_tunnel *vti_tunnel_lookup(struct net *net,
__be32 remote, __be32 local)
{
@@ -597,7 +559,7 @@ static const struct net_device_ops vti_netdev_ops = {
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = vti_tunnel_ioctl,
.ndo_change_mtu = vti_tunnel_change_mtu,
- .ndo_get_stats64 = vti_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void vti_dev_free(struct net_device *dev)
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index bf6c5cf31aed..efa1138fa523 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -206,7 +206,7 @@ static int __init ic_open_devs(void)
struct ic_device *d, **last;
struct net_device *dev;
unsigned short oflags;
- unsigned long start;
+ unsigned long start, next_msg;
last = &ic_first_dev;
rtnl_lock();
@@ -263,12 +263,23 @@ static int __init ic_open_devs(void)
/* wait for a carrier on at least one device */
start = jiffies;
+ next_msg = start + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12);
while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) {
+ int wait, elapsed;
+
for_each_netdev(&init_net, dev)
if (ic_is_init_dev(dev) && netif_carrier_ok(dev))
goto have_carrier;
msleep(1);
+
+ if time_before(jiffies, next_msg)
+ continue;
+
+ elapsed = jiffies_to_msecs(jiffies - start);
+ wait = (CONF_CARRIER_TIMEOUT - elapsed + 500)/1000;
+ pr_info("Waiting up to %d more seconds for network.\n", wait);
+ next_msg = jiffies + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12);
}
have_carrier:
rtnl_unlock();
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 8f024d41eefa..77bfcce64fe5 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -111,227 +111,21 @@
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
-#define HASH_SIZE 16
-#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static int ipip_net_id __read_mostly;
-struct ipip_net {
- struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
- struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
- struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
- struct ip_tunnel __rcu *tunnels_wc[1];
- struct ip_tunnel __rcu **tunnels[4];
-
- struct net_device *fb_tunnel_dev;
-};
static int ipip_tunnel_init(struct net_device *dev);
-static void ipip_tunnel_setup(struct net_device *dev);
-static void ipip_dev_free(struct net_device *dev);
static struct rtnl_link_ops ipip_link_ops __read_mostly;
-static struct rtnl_link_stats64 *ipip_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
- tot->collisions = dev->stats.collisions;
-
- return tot;
-}
-
-static struct ip_tunnel *ipip_tunnel_lookup(struct net *net,
- __be32 remote, __be32 local)
-{
- unsigned int h0 = HASH(remote);
- unsigned int h1 = HASH(local);
- struct ip_tunnel *t;
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1])
- if (local == t->parms.iph.saddr &&
- remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
- return t;
-
- for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0])
- if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
- return t;
-
- for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1])
- if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
- return t;
-
- t = rcu_dereference(ipn->tunnels_wc[0]);
- if (t && (t->dev->flags&IFF_UP))
- return t;
- return NULL;
-}
-
-static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn,
- struct ip_tunnel_parm *parms)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- unsigned int h = 0;
- int prio = 0;
-
- if (remote) {
- prio |= 2;
- h ^= HASH(remote);
- }
- if (local) {
- prio |= 1;
- h ^= HASH(local);
- }
- return &ipn->tunnels[prio][h];
-}
-
-static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn,
- struct ip_tunnel *t)
-{
- return __ipip_bucket(ipn, &t->parms);
-}
-
-static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp;
- struct ip_tunnel *iter;
-
- for (tp = ipip_bucket(ipn, t);
- (iter = rtnl_dereference(*tp)) != NULL;
- tp = &iter->next) {
- if (t == iter) {
- rcu_assign_pointer(*tp, t->next);
- break;
- }
- }
-}
-
-static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t)
-{
- struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t);
-
- rcu_assign_pointer(t->next, rtnl_dereference(*tp));
- rcu_assign_pointer(*tp, t);
-}
-
-static int ipip_tunnel_create(struct net_device *dev)
-{
- struct ip_tunnel *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
- int err;
-
- err = ipip_tunnel_init(dev);
- if (err < 0)
- goto out;
-
- err = register_netdevice(dev);
- if (err < 0)
- goto out;
-
- strcpy(t->parms.name, dev->name);
- dev->rtnl_link_ops = &ipip_link_ops;
-
- dev_hold(dev);
- ipip_tunnel_link(ipn, t);
- return 0;
-
-out:
- return err;
-}
-
-static struct ip_tunnel *ipip_tunnel_locate(struct net *net,
- struct ip_tunnel_parm *parms, int create)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- struct ip_tunnel *t, *nt;
- struct ip_tunnel __rcu **tp;
- struct net_device *dev;
- char name[IFNAMSIZ];
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- for (tp = __ipip_bucket(ipn, parms);
- (t = rtnl_dereference(*tp)) != NULL;
- tp = &t->next) {
- if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
- return t;
- }
- if (!create)
- return NULL;
-
- if (parms->name[0])
- strlcpy(name, parms->name, IFNAMSIZ);
- else
- strcpy(name, "tunl%d");
-
- dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup);
- if (dev == NULL)
- return NULL;
-
- dev_net_set(dev, net);
-
- nt = netdev_priv(dev);
- nt->parms = *parms;
-
- if (ipip_tunnel_create(dev) < 0)
- goto failed_free;
-
- return nt;
-
-failed_free:
- ipip_dev_free(dev);
- return NULL;
-}
-
-/* called with RTNL */
-static void ipip_tunnel_uninit(struct net_device *dev)
-{
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- if (dev == ipn->fb_tunnel_dev)
- RCU_INIT_POINTER(ipn->tunnels_wc[0], NULL);
- else
- ipip_tunnel_unlink(ipn, netdev_priv(dev));
- dev_put(dev);
-}
-
static int ipip_err(struct sk_buff *skb, u32 info)
{
@@ -339,41 +133,17 @@ static int ipip_err(struct sk_buff *skb, u32 info)
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
const struct iphdr *iph = (const struct iphdr *)skb->data;
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
int err;
-
- switch (type) {
- default:
- case ICMP_PARAMETERPROB:
- return 0;
-
- case ICMP_DEST_UNREACH:
- switch (code) {
- case ICMP_SR_FAILED:
- case ICMP_PORT_UNREACH:
- /* Impossible event. */
- return 0;
- default:
- /* All others are translated to HOST_UNREACH.
- rfc2003 contains "deep thoughts" about NET_UNREACH,
- I believe they are just ether pollution. --ANK
- */
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return 0;
- break;
- case ICMP_REDIRECT:
- break;
- }
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
err = -ENOENT;
- t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->daddr, iph->saddr, 0);
if (t == NULL)
goto out;
@@ -403,53 +173,29 @@ static int ipip_err(struct sk_buff *skb, u32 info)
else
t->err_count = 1;
t->err_time = jiffies;
-out:
+out:
return err;
}
+static const struct tnl_ptk_info tpi = {
+ /* no tunnel info required for ipip. */
+ .proto = htons(ETH_P_IP),
+};
+
static int ipip_rcv(struct sk_buff *skb)
{
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
- int err;
-
- tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
- if (tunnel != NULL) {
- struct pcpu_tstats *tstats;
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
-
- secpath_reset(skb);
-
- skb->mac_header = skb->network_header;
- skb_reset_network_header(skb);
- skb->protocol = htons(ETH_P_IP);
- skb->pkt_type = PACKET_HOST;
-
- __skb_tunnel_rx(skb, tunnel->dev);
-
- err = IP_ECN_decapsulate(iph, skb);
- if (unlikely(err)) {
- if (log_ecn_error)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &iph->saddr, iph->tos);
- if (err > 1) {
- ++tunnel->dev->stats.rx_frame_errors;
- ++tunnel->dev->stats.rx_errors;
- goto drop;
- }
- }
-
- tstats = this_cpu_ptr(tunnel->dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
-
- netif_rx(skb);
- return 0;
+ return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
return -1;
@@ -463,329 +209,64 @@ drop:
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
-
static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *tiph = &tunnel->parms.iph;
- u8 tos = tunnel->parms.iph.tos;
- __be16 df = tiph->frag_off;
- struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
- const struct iphdr *old_iph;
- struct iphdr *iph; /* Our new IP header */
- unsigned int max_headroom; /* The extra header space needed */
- __be32 dst = tiph->daddr;
- struct flowi4 fl4;
- int mtu;
-
- if (skb->protocol != htons(ETH_P_IP))
- goto tx_error;
- if (skb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_help(skb))
+ if (unlikely(skb->protocol != htons(ETH_P_IP)))
goto tx_error;
- old_iph = ip_hdr(skb);
-
- if (tos & 1)
- tos = old_iph->tos;
-
- if (!dst) {
- /* NBMA tunnel */
- if ((rt = skb_rtable(skb)) == NULL) {
- dev->stats.tx_fifo_errors++;
- goto tx_error;
- }
- dst = rt_nexthop(rt, old_iph->daddr);
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
}
- rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
- dst, tiph->saddr,
- 0, 0,
- IPPROTO_IPIP, RT_TOS(tos),
- tunnel->parms.link);
- if (IS_ERR(rt)) {
- dev->stats.tx_carrier_errors++;
- goto tx_error_icmp;
- }
- tdev = rt->dst.dev;
-
- if (tdev == dev) {
- ip_rt_put(rt);
- dev->stats.collisions++;
- goto tx_error;
- }
-
- df |= old_iph->frag_off & htons(IP_DF);
-
- if (df) {
- mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
-
- if (mtu < 68) {
- dev->stats.collisions++;
- ip_rt_put(rt);
- goto tx_error;
- }
-
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
- if ((old_iph->frag_off & htons(IP_DF)) &&
- mtu < ntohs(old_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-
- if (tunnel->err_count > 0) {
- if (time_before(jiffies,
- tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
- tunnel->err_count--;
- dst_link_failure(skb);
- } else
- tunnel->err_count = 0;
- }
-
- /*
- * Okay, now see if we can stuff it in the buffer as-is.
- */
- max_headroom = (LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr));
-
- if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
- (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
- struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
- if (!new_skb) {
- ip_rt_put(rt);
- dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
- return NETDEV_TX_OK;
- }
- if (skb->sk)
- skb_set_owner_w(new_skb, skb->sk);
- dev_kfree_skb(skb);
- skb = new_skb;
- old_iph = ip_hdr(skb);
- }
-
- skb->transport_header = skb->network_header;
- skb_push(skb, sizeof(struct iphdr));
- skb_reset_network_header(skb);
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
- IPSKB_REROUTED);
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
- /*
- * Push down and install the IPIP header.
- */
-
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr)>>2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_IPIP;
- iph->tos = INET_ECN_encapsulate(tos, old_iph->tos);
- iph->daddr = fl4.daddr;
- iph->saddr = fl4.saddr;
-
- if ((iph->ttl = tiph->ttl) == 0)
- iph->ttl = old_iph->ttl;
-
- iptunnel_xmit(skb, dev);
+ ip_tunnel_xmit(skb, dev, tiph);
return NETDEV_TX_OK;
-tx_error_icmp:
- dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
-static void ipip_tunnel_bind_dev(struct net_device *dev)
-{
- struct net_device *tdev = NULL;
- struct ip_tunnel *tunnel;
- const struct iphdr *iph;
-
- tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
-
- if (iph->daddr) {
- struct rtable *rt;
- struct flowi4 fl4;
-
- rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
- iph->daddr, iph->saddr,
- 0, 0,
- IPPROTO_IPIP,
- RT_TOS(iph->tos),
- tunnel->parms.link);
- if (!IS_ERR(rt)) {
- tdev = rt->dst.dev;
- ip_rt_put(rt);
- }
- dev->flags |= IFF_POINTOPOINT;
- }
-
- if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
-
- if (tdev) {
- dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
- dev->mtu = tdev->mtu - sizeof(struct iphdr);
- }
- dev->iflink = tunnel->parms.link;
-}
-
-static void ipip_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
-{
- struct net *net = dev_net(t->dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- ipip_tunnel_unlink(ipn, t);
- synchronize_net();
- t->parms.iph.saddr = p->iph.saddr;
- t->parms.iph.daddr = p->iph.daddr;
- memcpy(t->dev->dev_addr, &p->iph.saddr, 4);
- memcpy(t->dev->broadcast, &p->iph.daddr, 4);
- ipip_tunnel_link(ipn, t);
- t->parms.iph.ttl = p->iph.ttl;
- t->parms.iph.tos = p->iph.tos;
- t->parms.iph.frag_off = p->iph.frag_off;
- if (t->parms.link != p->link) {
- t->parms.link = p->link;
- ipip_tunnel_bind_dev(t->dev);
- }
- netdev_state_change(t->dev);
-}
-
static int
-ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
- struct ip_tunnel *t;
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- switch (cmd) {
- case SIOCGETTUNNEL:
- t = NULL;
- if (dev == ipn->fb_tunnel_dev) {
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
- err = -EFAULT;
- break;
- }
- t = ipip_tunnel_locate(net, &p, 0);
- }
- if (t == NULL)
- t = netdev_priv(dev);
- memcpy(&p, &t->parms, sizeof(p));
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
- err = -EFAULT;
- break;
-
- case SIOCADDTUNNEL:
- case SIOCCHGTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
-
- err = -EINVAL;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
- goto done;
- if (p.iph.ttl)
- p.iph.frag_off |= htons(IP_DF);
-
- t = ipip_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
-
- if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
- if (t != NULL) {
- if (t->dev != dev) {
- err = -EEXIST;
- break;
- }
- } else {
- if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
- (!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
- err = -EINVAL;
- break;
- }
- t = netdev_priv(dev);
- }
-
- ipip_tunnel_update(t, &p);
- }
-
- if (t) {
- err = 0;
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
- err = -EFAULT;
- } else
- err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
- break;
-
- case SIOCDELTUNNEL:
- err = -EPERM;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
- goto done;
-
- if (dev == ipn->fb_tunnel_dev) {
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
- err = -ENOENT;
- if ((t = ipip_tunnel_locate(net, &p, 0)) == NULL)
- goto done;
- err = -EPERM;
- if (t->dev == ipn->fb_tunnel_dev)
- goto done;
- dev = t->dev;
- }
- unregister_netdevice(dev);
- err = 0;
- break;
- default:
- err = -EINVAL;
- }
-
-done:
- return err;
-}
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+ return -EFAULT;
-static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
-{
- if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
+ return -EINVAL;
+ if (p.i_key || p.o_key || p.i_flags || p.o_flags)
return -EINVAL;
- dev->mtu = new_mtu;
+ if (p.iph.ttl)
+ p.iph.frag_off |= htons(IP_DF);
+
+ err = ip_tunnel_ioctl(dev, &p, cmd);
+ if (err)
+ return err;
+
+ if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+ return -EFAULT;
+
return 0;
}
static const struct net_device_ops ipip_netdev_ops = {
- .ndo_uninit = ipip_tunnel_uninit,
+ .ndo_init = ipip_tunnel_init,
+ .ndo_uninit = ip_tunnel_uninit,
.ndo_start_xmit = ipip_tunnel_xmit,
.ndo_do_ioctl = ipip_tunnel_ioctl,
- .ndo_change_mtu = ipip_tunnel_change_mtu,
- .ndo_get_stats64 = ipip_get_stats64,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
-static void ipip_dev_free(struct net_device *dev)
-{
- free_percpu(dev->tstats);
- free_netdev(dev);
-}
-
#define IPIP_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
@@ -794,11 +275,8 @@ static void ipip_dev_free(struct net_device *dev)
static void ipip_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip_netdev_ops;
- dev->destructor = ipip_dev_free;
dev->type = ARPHRD_TUNNEL;
- dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
- dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr);
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
@@ -808,46 +286,19 @@ static void ipip_tunnel_setup(struct net_device *dev)
dev->features |= IPIP_FEATURES;
dev->hw_features |= IPIP_FEATURES;
+ ip_tunnel_setup(dev, ipip_net_id);
}
static int ipip_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- tunnel->dev = dev;
-
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
- ipip_tunnel_bind_dev(dev);
-
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- return 0;
-}
-
-static int __net_init ipip_fb_tunnel_init(struct net_device *dev)
-{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- struct iphdr *iph = &tunnel->parms.iph;
- struct ipip_net *ipn = net_generic(dev_net(dev), ipip_net_id);
-
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
- iph->version = 4;
- iph->protocol = IPPROTO_IPIP;
- iph->ihl = 5;
-
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
- dev_hold(dev);
- rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
- return 0;
+ tunnel->hlen = 0;
+ tunnel->parms.iph.protocol = IPPROTO_IPIP;
+ return ip_tunnel_init(dev);
}
static void ipip_netlink_parms(struct nlattr *data[],
@@ -887,28 +338,16 @@ static void ipip_netlink_parms(struct nlattr *data[],
static int ipip_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
- struct net *net = dev_net(dev);
- struct ip_tunnel *nt;
-
- nt = netdev_priv(dev);
- ipip_netlink_parms(data, &nt->parms);
-
- if (ipip_tunnel_locate(net, &nt->parms, 0))
- return -EEXIST;
+ struct ip_tunnel_parm p;
- return ipip_tunnel_create(dev);
+ ipip_netlink_parms(data, &p);
+ return ip_tunnel_newlink(dev, tb, &p);
}
static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip_tunnel *t;
struct ip_tunnel_parm p;
- struct net *net = dev_net(dev);
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
-
- if (dev == ipn->fb_tunnel_dev)
- return -EINVAL;
ipip_netlink_parms(data, &p);
@@ -916,16 +355,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],
(!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
return -EINVAL;
- t = ipip_tunnel_locate(net, &p, 0);
-
- if (t) {
- if (t->dev != dev)
- return -EEXIST;
- } else
- t = netdev_priv(dev);
-
- ipip_tunnel_update(t, &p);
- return 0;
+ return ip_tunnel_changelink(dev, tb, &p);
}
static size_t ipip_get_size(const struct net_device *dev)
@@ -982,6 +412,7 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly = {
.setup = ipip_tunnel_setup,
.newlink = ipip_newlink,
.changelink = ipip_changelink,
+ .dellink = ip_tunnel_dellink,
.get_size = ipip_get_size,
.fill_info = ipip_fill_info,
};
@@ -992,90 +423,29 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
.priority = 1,
};
-static const char banner[] __initconst =
- KERN_INFO "IPv4 over IPv4 tunneling driver\n";
-
-static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
-{
- int prio;
-
- for (prio = 1; prio < 4; prio++) {
- int h;
- for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
-
- t = rtnl_dereference(ipn->tunnels[prio][h]);
- while (t != NULL) {
- unregister_netdevice_queue(t->dev, head);
- t = rtnl_dereference(t->next);
- }
- }
- }
-}
-
static int __net_init ipip_init_net(struct net *net)
{
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
- struct ip_tunnel *t;
- int err;
-
- ipn->tunnels[0] = ipn->tunnels_wc;
- ipn->tunnels[1] = ipn->tunnels_l;
- ipn->tunnels[2] = ipn->tunnels_r;
- ipn->tunnels[3] = ipn->tunnels_r_l;
-
- ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel),
- "tunl0",
- ipip_tunnel_setup);
- if (!ipn->fb_tunnel_dev) {
- err = -ENOMEM;
- goto err_alloc_dev;
- }
- dev_net_set(ipn->fb_tunnel_dev, net);
-
- err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
- if (err)
- goto err_reg_dev;
-
- if ((err = register_netdev(ipn->fb_tunnel_dev)))
- goto err_reg_dev;
-
- t = netdev_priv(ipn->fb_tunnel_dev);
-
- strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
- return 0;
-
-err_reg_dev:
- ipip_dev_free(ipn->fb_tunnel_dev);
-err_alloc_dev:
- /* nothing */
- return err;
+ return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}
static void __net_exit ipip_exit_net(struct net *net)
{
- struct ipip_net *ipn = net_generic(net, ipip_net_id);
- LIST_HEAD(list);
-
- rtnl_lock();
- ipip_destroy_tunnels(ipn, &list);
- unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
- unregister_netdevice_many(&list);
- rtnl_unlock();
+ struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
+ ip_tunnel_delete_net(itn);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
.exit = ipip_exit_net,
.id = &ipip_net_id,
- .size = sizeof(struct ipip_net),
+ .size = sizeof(struct ip_tunnel_net),
};
static int __init ipip_init(void)
{
int err;
- printk(banner);
+ pr_info("ipip: IPv4 over IPv4 tunneling driver\n");
err = register_pernet_device(&ipip_net_ops);
if (err < 0)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5f95b3aa579e..9d9610ae7855 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -61,7 +61,7 @@
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
#include <linux/export.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/checksum.h>
#include <net/netlink.h>
#include <net/fib_rules.h>
@@ -626,9 +626,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
nlh->nlmsg_type = NLMSG_ERROR;
- nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+ nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
- e = NLMSG_DATA(nlh);
+ e = nlmsg_data(nlh);
e->error = -ETIMEDOUT;
memset(&e->msg, 0, sizeof(e->msg));
@@ -910,14 +910,14 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
- if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
+ if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) {
nlh->nlmsg_len = skb_tail_pointer(skb) -
(u8 *)nlh;
} else {
nlh->nlmsg_type = NLMSG_ERROR;
- nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+ nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
- e = NLMSG_DATA(nlh);
+ e = nlmsg_data(nlh);
e->error = -EMSGSIZE;
memset(&e->msg, 0, sizeof(e->msg));
}
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index 79ca5e70d497..eadab1ed6500 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -48,9 +48,7 @@ static int __net_init arptable_filter_net_init(struct net *net)
net->ipv4.arptable_filter =
arpt_register_table(net, &packet_filter, repl);
kfree(repl);
- if (IS_ERR(net->ipv4.arptable_filter))
- return PTR_ERR(net->ipv4.arptable_filter);
- return 0;
+ return PTR_RET(net->ipv4.arptable_filter);
}
static void __net_exit arptable_filter_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 7d168dcbd135..e7f8cad11393 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -37,7 +37,7 @@
#include <linux/skbuff.h>
#include <linux/kernel.h>
#include <linux/timer.h>
-#include <linux/netlink.h>
+#include <net/netlink.h>
#include <linux/netdevice.h>
#include <linux/mm.h>
#include <linux/moduleparam.h>
@@ -172,7 +172,7 @@ static void ipt_ulog_packet(unsigned int hooknum,
else
copy_len = loginfo->copy_range;
- size = NLMSG_SPACE(sizeof(*pm) + copy_len);
+ size = nlmsg_total_size(sizeof(*pm) + copy_len);
ub = &ulog_buffers[groupnum];
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 32030a24e776..b6f2ea174898 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -224,6 +224,8 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPForwardRetrans", LINUX_MIB_TCPFORWARDRETRANS),
SNMP_MIB_ITEM("TCPSlowStartRetrans", LINUX_MIB_TCPSLOWSTARTRETRANS),
SNMP_MIB_ITEM("TCPTimeouts", LINUX_MIB_TCPTIMEOUTS),
+ SNMP_MIB_ITEM("TCPLossProbes", LINUX_MIB_TCPLOSSPROBES),
+ SNMP_MIB_ITEM("TCPLossProbeRecovery", LINUX_MIB_TCPLOSSPROBERECOVERY),
SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL),
SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL),
SNMP_MIB_ITEM("TCPSchedulerFailed", LINUX_MIB_TCPSCHEDULERFAILED),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6e2851464f8f..550781a17b34 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2311,7 +2311,7 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg)
+static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct rtmsg *rtm;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index ef54377fb11c..7f4a5cb8f8d0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -267,7 +267,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt)
{
struct tcp_options_received tcp_opt;
- const u8 *hash_location;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
@@ -294,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tcp_opt, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
goto out;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 960fd29d9b8e..fa2f63fc453b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -28,7 +28,7 @@
static int zero;
static int one = 1;
-static int two = 2;
+static int four = 4;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -592,13 +592,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_frto_response",
- .data = &sysctl_tcp_frto_response,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_low_latency",
.data = &sysctl_tcp_low_latency,
.maxlen = sizeof(int),
@@ -733,13 +726,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "tcp_cookie_size",
- .data = &sysctl_tcp_cookie_size,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_thin_linear_timeouts",
.data = &sysctl_tcp_thin_linear_timeouts,
.maxlen = sizeof(int),
@@ -760,7 +746,7 @@ static struct ctl_table ipv4_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
- .extra2 = &two,
+ .extra2 = &four,
},
{
.procname = "udp_mem",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e22020790709..a96f7b586277 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -409,15 +409,6 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- /* TCP Cookie Transactions */
- if (sysctl_tcp_cookie_size > 0) {
- /* Default, cookies without s_data_payload. */
- tp->cookie_values =
- kzalloc(sizeof(*tp->cookie_values),
- sk->sk_allocation);
- if (tp->cookie_values != NULL)
- kref_init(&tp->cookie_values->kref);
- }
/* Presumed zeroed, in order of appearance:
* cookie_in_always, cookie_out_never,
* s_data_constant, s_data_in, s_data_out
@@ -2397,92 +2388,6 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
release_sock(sk);
return err;
}
- case TCP_COOKIE_TRANSACTIONS: {
- struct tcp_cookie_transactions ctd;
- struct tcp_cookie_values *cvp = NULL;
-
- if (sizeof(ctd) > optlen)
- return -EINVAL;
- if (copy_from_user(&ctd, optval, sizeof(ctd)))
- return -EFAULT;
-
- if (ctd.tcpct_used > sizeof(ctd.tcpct_value) ||
- ctd.tcpct_s_data_desired > TCP_MSS_DESIRED)
- return -EINVAL;
-
- if (ctd.tcpct_cookie_desired == 0) {
- /* default to global value */
- } else if ((0x1 & ctd.tcpct_cookie_desired) ||
- ctd.tcpct_cookie_desired > TCP_COOKIE_MAX ||
- ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) {
- return -EINVAL;
- }
-
- if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) {
- /* Supercedes all other values */
- lock_sock(sk);
- if (tp->cookie_values != NULL) {
- kref_put(&tp->cookie_values->kref,
- tcp_cookie_values_release);
- tp->cookie_values = NULL;
- }
- tp->rx_opt.cookie_in_always = 0; /* false */
- tp->rx_opt.cookie_out_never = 1; /* true */
- release_sock(sk);
- return err;
- }
-
- /* Allocate ancillary memory before locking.
- */
- if (ctd.tcpct_used > 0 ||
- (tp->cookie_values == NULL &&
- (sysctl_tcp_cookie_size > 0 ||
- ctd.tcpct_cookie_desired > 0 ||
- ctd.tcpct_s_data_desired > 0))) {
- cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used,
- GFP_KERNEL);
- if (cvp == NULL)
- return -ENOMEM;
-
- kref_init(&cvp->kref);
- }
- lock_sock(sk);
- tp->rx_opt.cookie_in_always =
- (TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags);
- tp->rx_opt.cookie_out_never = 0; /* false */
-
- if (tp->cookie_values != NULL) {
- if (cvp != NULL) {
- /* Changed values are recorded by a changed
- * pointer, ensuring the cookie will differ,
- * without separately hashing each value later.
- */
- kref_put(&tp->cookie_values->kref,
- tcp_cookie_values_release);
- } else {
- cvp = tp->cookie_values;
- }
- }
-
- if (cvp != NULL) {
- cvp->cookie_desired = ctd.tcpct_cookie_desired;
-
- if (ctd.tcpct_used > 0) {
- memcpy(cvp->s_data_payload, ctd.tcpct_value,
- ctd.tcpct_used);
- cvp->s_data_desired = ctd.tcpct_used;
- cvp->s_data_constant = 1; /* true */
- } else {
- /* No constant payload data. */
- cvp->s_data_desired = ctd.tcpct_s_data_desired;
- cvp->s_data_constant = 0; /* false */
- }
-
- tp->cookie_values = cvp;
- }
- release_sock(sk);
- return err;
- }
default:
/* fallthru */
break;
@@ -2902,41 +2807,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
- case TCP_COOKIE_TRANSACTIONS: {
- struct tcp_cookie_transactions ctd;
- struct tcp_cookie_values *cvp = tp->cookie_values;
-
- if (get_user(len, optlen))
- return -EFAULT;
- if (len < sizeof(ctd))
- return -EINVAL;
-
- memset(&ctd, 0, sizeof(ctd));
- ctd.tcpct_flags = (tp->rx_opt.cookie_in_always ?
- TCP_COOKIE_IN_ALWAYS : 0)
- | (tp->rx_opt.cookie_out_never ?
- TCP_COOKIE_OUT_NEVER : 0);
-
- if (cvp != NULL) {
- ctd.tcpct_flags |= (cvp->s_data_in ?
- TCP_S_DATA_IN : 0)
- | (cvp->s_data_out ?
- TCP_S_DATA_OUT : 0);
-
- ctd.tcpct_cookie_desired = cvp->cookie_desired;
- ctd.tcpct_s_data_desired = cvp->s_data_desired;
-
- memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0],
- cvp->cookie_pair_size);
- ctd.tcpct_used = cvp->cookie_pair_size;
- }
-
- if (put_user(sizeof(ctd), optlen))
- return -EFAULT;
- if (copy_to_user(optval, &ctd, sizeof(ctd)))
- return -EFAULT;
- return 0;
- }
case TCP_THIN_LINEAR_TIMEOUTS:
val = tp->thin_lto;
break;
@@ -3044,6 +2914,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
SKB_GSO_GRE |
+ SKB_GSO_UDP_TUNNEL |
0) ||
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
goto out;
@@ -3408,134 +3279,6 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
#endif
-/* Each Responder maintains up to two secret values concurrently for
- * efficient secret rollover. Each secret value has 4 states:
- *
- * Generating. (tcp_secret_generating != tcp_secret_primary)
- * Generates new Responder-Cookies, but not yet used for primary
- * verification. This is a short-term state, typically lasting only
- * one round trip time (RTT).
- *
- * Primary. (tcp_secret_generating == tcp_secret_primary)
- * Used both for generation and primary verification.
- *
- * Retiring. (tcp_secret_retiring != tcp_secret_secondary)
- * Used for verification, until the first failure that can be
- * verified by the newer Generating secret. At that time, this
- * cookie's state is changed to Secondary, and the Generating
- * cookie's state is changed to Primary. This is a short-term state,
- * typically lasting only one round trip time (RTT).
- *
- * Secondary. (tcp_secret_retiring == tcp_secret_secondary)
- * Used for secondary verification, after primary verification
- * failures. This state lasts no more than twice the Maximum Segment
- * Lifetime (2MSL). Then, the secret is discarded.
- */
-struct tcp_cookie_secret {
- /* The secret is divided into two parts. The digest part is the
- * equivalent of previously hashing a secret and saving the state,
- * and serves as an initialization vector (IV). The message part
- * serves as the trailing secret.
- */
- u32 secrets[COOKIE_WORKSPACE_WORDS];
- unsigned long expires;
-};
-
-#define TCP_SECRET_1MSL (HZ * TCP_PAWS_MSL)
-#define TCP_SECRET_2MSL (HZ * TCP_PAWS_MSL * 2)
-#define TCP_SECRET_LIFE (HZ * 600)
-
-static struct tcp_cookie_secret tcp_secret_one;
-static struct tcp_cookie_secret tcp_secret_two;
-
-/* Essentially a circular list, without dynamic allocation. */
-static struct tcp_cookie_secret *tcp_secret_generating;
-static struct tcp_cookie_secret *tcp_secret_primary;
-static struct tcp_cookie_secret *tcp_secret_retiring;
-static struct tcp_cookie_secret *tcp_secret_secondary;
-
-static DEFINE_SPINLOCK(tcp_secret_locker);
-
-/* Select a pseudo-random word in the cookie workspace.
- */
-static inline u32 tcp_cookie_work(const u32 *ws, const int n)
-{
- return ws[COOKIE_DIGEST_WORDS + ((COOKIE_MESSAGE_WORDS-1) & ws[n])];
-}
-
-/* Fill bakery[COOKIE_WORKSPACE_WORDS] with generator, updating as needed.
- * Called in softirq context.
- * Returns: 0 for success.
- */
-int tcp_cookie_generator(u32 *bakery)
-{
- unsigned long jiffy = jiffies;
-
- if (unlikely(time_after_eq(jiffy, tcp_secret_generating->expires))) {
- spin_lock_bh(&tcp_secret_locker);
- if (!time_after_eq(jiffy, tcp_secret_generating->expires)) {
- /* refreshed by another */
- memcpy(bakery,
- &tcp_secret_generating->secrets[0],
- COOKIE_WORKSPACE_WORDS);
- } else {
- /* still needs refreshing */
- get_random_bytes(bakery, COOKIE_WORKSPACE_WORDS);
-
- /* The first time, paranoia assumes that the
- * randomization function isn't as strong. But,
- * this secret initialization is delayed until
- * the last possible moment (packet arrival).
- * Although that time is observable, it is
- * unpredictably variable. Mash in the most
- * volatile clock bits available, and expire the
- * secret extra quickly.
- */
- if (unlikely(tcp_secret_primary->expires ==
- tcp_secret_secondary->expires)) {
- struct timespec tv;
-
- getnstimeofday(&tv);
- bakery[COOKIE_DIGEST_WORDS+0] ^=
- (u32)tv.tv_nsec;
-
- tcp_secret_secondary->expires = jiffy
- + TCP_SECRET_1MSL
- + (0x0f & tcp_cookie_work(bakery, 0));
- } else {
- tcp_secret_secondary->expires = jiffy
- + TCP_SECRET_LIFE
- + (0xff & tcp_cookie_work(bakery, 1));
- tcp_secret_primary->expires = jiffy
- + TCP_SECRET_2MSL
- + (0x1f & tcp_cookie_work(bakery, 2));
- }
- memcpy(&tcp_secret_secondary->secrets[0],
- bakery, COOKIE_WORKSPACE_WORDS);
-
- rcu_assign_pointer(tcp_secret_generating,
- tcp_secret_secondary);
- rcu_assign_pointer(tcp_secret_retiring,
- tcp_secret_primary);
- /*
- * Neither call_rcu() nor synchronize_rcu() needed.
- * Retiring data is not freed. It is replaced after
- * further (locked) pointer updates, and a quiet time
- * (minimum 1MSL, maximum LIFE - 2MSL).
- */
- }
- spin_unlock_bh(&tcp_secret_locker);
- } else {
- rcu_read_lock_bh();
- memcpy(bakery,
- &rcu_dereference(tcp_secret_generating)->secrets[0],
- COOKIE_WORKSPACE_WORDS);
- rcu_read_unlock_bh();
- }
- return 0;
-}
-EXPORT_SYMBOL(tcp_cookie_generator);
-
void tcp_done(struct sock *sk)
{
struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
@@ -3590,7 +3333,6 @@ void __init tcp_init(void)
unsigned long limit;
int max_rshare, max_wshare, cnt;
unsigned int i;
- unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3666,13 +3408,5 @@ void __init tcp_init(void)
tcp_register_congestion_control(&tcp_reno);
- memset(&tcp_secret_one.secrets[0], 0, sizeof(tcp_secret_one.secrets));
- memset(&tcp_secret_two.secrets[0], 0, sizeof(tcp_secret_two.secrets));
- tcp_secret_one.expires = jiffy; /* past due */
- tcp_secret_two.expires = jiffy; /* past due */
- tcp_secret_generating = &tcp_secret_one;
- tcp_secret_primary = &tcp_secret_one;
- tcp_secret_retiring = &tcp_secret_two;
- tcp_secret_secondary = &tcp_secret_two;
tcp_tasklet_init();
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3bd55bad230a..6d9ca35f0c35 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -93,12 +93,11 @@ int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
int sysctl_tcp_frto __read_mostly = 2;
-int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_thin_dupack __read_mostly;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_early_retrans __read_mostly = 2;
+int sysctl_tcp_early_retrans __read_mostly = 3;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
@@ -108,17 +107,15 @@ int sysctl_tcp_early_retrans __read_mostly = 2;
#define FLAG_DATA_SACKED 0x20 /* New SACK. */
#define FLAG_ECE 0x40 /* ECE in this ACK */
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
-#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
+#define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */
#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */
-#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE)
#define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED)
-#define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))
@@ -1159,10 +1156,8 @@ static u8 tcp_sacktag_one(struct sock *sk,
tcp_highest_sack_seq(tp)))
state->reord = min(fack_count,
state->reord);
-
- /* SACK enhanced F-RTO (RFC4138; Appendix B) */
- if (!after(end_seq, tp->frto_highmark))
- state->flag |= FLAG_ONLY_ORIG_SACKED;
+ if (!after(end_seq, tp->high_seq))
+ state->flag |= FLAG_ORIG_SACK_ACKED;
}
if (sacked & TCPCB_LOST) {
@@ -1555,7 +1550,6 @@ static int
tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
u32 prior_snd_una)
{
- const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
const unsigned char *ptr = (skb_transport_header(ack_skb) +
TCP_SKB_CB(ack_skb)->sacked);
@@ -1728,12 +1722,6 @@ walk:
start_seq, end_seq, dup_sack);
advance_sp:
- /* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct
- * due to in-order walk
- */
- if (after(end_seq, tp->frto_highmark))
- state.flag &= ~FLAG_ONLY_ORIG_SACKED;
-
i++;
}
@@ -1750,8 +1738,7 @@ advance_sp:
tcp_verify_left_out(tp);
if ((state.reord < tp->fackets_out) &&
- ((icsk->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker) &&
- (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark)))
+ ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);
out:
@@ -1825,197 +1812,6 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
tp->sacked_out = 0;
}
-static int tcp_is_sackfrto(const struct tcp_sock *tp)
-{
- return (sysctl_tcp_frto == 0x2) && !tcp_is_reno(tp);
-}
-
-/* F-RTO can only be used if TCP has never retransmitted anything other than
- * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
- */
-bool tcp_use_frto(struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- const struct inet_connection_sock *icsk = inet_csk(sk);
- struct sk_buff *skb;
-
- if (!sysctl_tcp_frto)
- return false;
-
- /* MTU probe and F-RTO won't really play nicely along currently */
- if (icsk->icsk_mtup.probe_size)
- return false;
-
- if (tcp_is_sackfrto(tp))
- return true;
-
- /* Avoid expensive walking of rexmit queue if possible */
- if (tp->retrans_out > 1)
- return false;
-
- skb = tcp_write_queue_head(sk);
- if (tcp_skb_is_last(sk, skb))
- return true;
- skb = tcp_write_queue_next(sk, skb); /* Skips head */
- tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
- return false;
- /* Short-circuit when first non-SACKed skb has been checked */
- if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
- break;
- }
- return true;
-}
-
-/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO
- * recovery a bit and use heuristics in tcp_process_frto() to detect if
- * the RTO was spurious. Only clear SACKED_RETRANS of the head here to
- * keep retrans_out counting accurate (with SACK F-RTO, other than head
- * may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS
- * bits are handled if the Loss state is really to be entered (in
- * tcp_enter_frto_loss).
- *
- * Do like tcp_enter_loss() would; when RTO expires the second time it
- * does:
- * "Reduce ssthresh if it has not yet been made inside this window."
- */
-void tcp_enter_frto(struct sock *sk)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
-
- if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) ||
- tp->snd_una == tp->high_seq ||
- ((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) &&
- !icsk->icsk_retransmits)) {
- tp->prior_ssthresh = tcp_current_ssthresh(sk);
- /* Our state is too optimistic in ssthresh() call because cwnd
- * is not reduced until tcp_enter_frto_loss() when previous F-RTO
- * recovery has not yet completed. Pattern would be this: RTO,
- * Cumulative ACK, RTO (2xRTO for the same segment does not end
- * up here twice).
- * RFC4138 should be more specific on what to do, even though
- * RTO is quite unlikely to occur after the first Cumulative ACK
- * due to back-off and complexity of triggering events ...
- */
- if (tp->frto_counter) {
- u32 stored_cwnd;
- stored_cwnd = tp->snd_cwnd;
- tp->snd_cwnd = 2;
- tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
- tp->snd_cwnd = stored_cwnd;
- } else {
- tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
- }
- /* ... in theory, cong.control module could do "any tricks" in
- * ssthresh(), which means that ca_state, lost bits and lost_out
- * counter would have to be faked before the call occurs. We
- * consider that too expensive, unlikely and hacky, so modules
- * using these in ssthresh() must deal these incompatibility
- * issues if they receives CA_EVENT_FRTO and frto_counter != 0
- */
- tcp_ca_event(sk, CA_EVENT_FRTO);
- }
-
- tp->undo_marker = tp->snd_una;
- tp->undo_retrans = 0;
-
- skb = tcp_write_queue_head(sk);
- if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
- tp->undo_marker = 0;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
- tp->retrans_out -= tcp_skb_pcount(skb);
- }
- tcp_verify_left_out(tp);
-
- /* Too bad if TCP was application limited */
- tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1);
-
- /* Earlier loss recovery underway (see RFC4138; Appendix B).
- * The last condition is necessary at least in tp->frto_counter case.
- */
- if (tcp_is_sackfrto(tp) && (tp->frto_counter ||
- ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
- after(tp->high_seq, tp->snd_una)) {
- tp->frto_highmark = tp->high_seq;
- } else {
- tp->frto_highmark = tp->snd_nxt;
- }
- tcp_set_ca_state(sk, TCP_CA_Disorder);
- tp->high_seq = tp->snd_nxt;
- tp->frto_counter = 1;
-}
-
-/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO,
- * which indicates that we should follow the traditional RTO recovery,
- * i.e. mark everything lost and do go-back-N retransmission.
- */
-static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
-
- tp->lost_out = 0;
- tp->retrans_out = 0;
- if (tcp_is_reno(tp))
- tcp_reset_reno_sack(tp);
-
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
-
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
- /*
- * Count the retransmission made on RTO correctly (only when
- * waiting for the first ACK and did not get it)...
- */
- if ((tp->frto_counter == 1) && !(flag & FLAG_DATA_ACKED)) {
- /* For some reason this R-bit might get cleared? */
- if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
- tp->retrans_out += tcp_skb_pcount(skb);
- /* ...enter this if branch just for the first segment */
- flag |= FLAG_DATA_ACKED;
- } else {
- if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
- tp->undo_marker = 0;
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
- }
-
- /* Marking forward transmissions that were made after RTO lost
- * can cause unnecessary retransmissions in some scenarios,
- * SACK blocks will mitigate that in some but not in all cases.
- * We used to not mark them but it was causing break-ups with
- * receivers that do only in-order receival.
- *
- * TODO: we could detect presence of such receiver and select
- * different behavior per flow.
- */
- if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- tp->retransmit_high = TCP_SKB_CB(skb)->end_seq;
- }
- }
- tcp_verify_left_out(tp);
-
- tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments;
- tp->snd_cwnd_cnt = 0;
- tp->snd_cwnd_stamp = tcp_time_stamp;
- tp->frto_counter = 0;
-
- tp->reordering = min_t(unsigned int, tp->reordering,
- sysctl_tcp_reordering);
- tcp_set_ca_state(sk, TCP_CA_Loss);
- tp->high_seq = tp->snd_nxt;
- TCP_ECN_queue_cwr(tp);
-
- tcp_clear_all_retrans_hints(tp);
-}
-
static void tcp_clear_retrans_partial(struct tcp_sock *tp)
{
tp->retrans_out = 0;
@@ -2042,10 +1838,13 @@ void tcp_enter_loss(struct sock *sk, int how)
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
+ bool new_recovery = false;
/* Reduce ssthresh if it has not yet been made inside this window. */
- if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq ||
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
+ !after(tp->high_seq, tp->snd_una) ||
(icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
+ new_recovery = true;
tp->prior_ssthresh = tcp_current_ssthresh(sk);
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tcp_ca_event(sk, CA_EVENT_LOSS);
@@ -2087,8 +1886,14 @@ void tcp_enter_loss(struct sock *sk, int how)
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
- /* Abort F-RTO algorithm if one is in progress */
- tp->frto_counter = 0;
+
+ /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+ * loss recovery is underway except recurring timeout(s) on
+ * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
+ */
+ tp->frto = sysctl_tcp_frto &&
+ (new_recovery || icsk->icsk_retransmits) &&
+ !inet_csk(sk)->icsk_mtup.probe_size;
}
/* If ACK arrived pointing to a remembered SACK, it means that our
@@ -2147,15 +1952,16 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
* max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples
* available, or RTO is scheduled to fire first.
*/
- if (sysctl_tcp_early_retrans < 2 || (flag & FLAG_ECE) || !tp->srtt)
+ if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 ||
+ (flag & FLAG_ECE) || !tp->srtt)
return false;
delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2));
if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay)))
return false;
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX);
- tp->early_retrans_delayed = 1;
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_EARLY_RETRANS, delay,
+ TCP_RTO_MAX);
return true;
}
@@ -2271,10 +2077,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
- /* Do not perform any recovery during F-RTO algorithm */
- if (tp->frto_counter)
- return false;
-
/* Trick#1: The loss is proven. */
if (tp->lost_out)
return true;
@@ -2318,7 +2120,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
* interval if appropriate.
*/
if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out &&
- (tp->packets_out == (tp->sacked_out + 1) && tp->packets_out < 4) &&
+ (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) &&
!tcp_may_send_now(sk))
return !tcp_pause_early_retransmit(sk, flag);
@@ -2635,12 +2437,12 @@ static int tcp_try_undo_partial(struct sock *sk, int acked)
return failed;
}
-/* Undo during loss recovery after partial ACK. */
-static bool tcp_try_undo_loss(struct sock *sk)
+/* Undo during loss recovery after partial ACK or using F-RTO. */
+static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_may_undo(tp)) {
+ if (frto_undo || tcp_may_undo(tp)) {
struct sk_buff *skb;
tcp_for_write_queue(skb, sk) {
if (skb == tcp_send_head(sk))
@@ -2654,9 +2456,12 @@ static bool tcp_try_undo_loss(struct sock *sk)
tp->lost_out = 0;
tcp_undo_cwr(sk, true);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
+ if (frto_undo)
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
tp->undo_marker = 0;
- if (tcp_is_sack(tp))
+ if (frto_undo || tcp_is_sack(tp))
tcp_set_ca_state(sk, TCP_CA_Open);
return true;
}
@@ -2678,6 +2483,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
struct tcp_sock *tp = tcp_sk(sk);
tp->high_seq = tp->snd_nxt;
+ tp->tlp_high_seq = 0;
tp->snd_cwnd_cnt = 0;
tp->prior_cwnd = tp->snd_cwnd;
tp->prr_delivered = 0;
@@ -2755,7 +2561,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked)
tcp_verify_left_out(tp);
- if (!tp->frto_counter && !tcp_any_retrans_done(sk))
+ if (!tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
if (flag & FLAG_ECE)
@@ -2872,6 +2678,58 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
tcp_set_ca_state(sk, TCP_CA_Recovery);
}
+/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
+ * recovered or spurious. Otherwise retransmits more on partial ACKs.
+ */
+static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ bool recovered = !before(tp->snd_una, tp->high_seq);
+
+ if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+ if (flag & FLAG_ORIG_SACK_ACKED) {
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ tcp_try_undo_loss(sk, true);
+ return;
+ }
+ if (after(tp->snd_nxt, tp->high_seq) &&
+ (flag & FLAG_DATA_SACKED || is_dupack)) {
+ tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
+ } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
+ tp->high_seq = tp->snd_nxt;
+ __tcp_push_pending_frames(sk, tcp_current_mss(sk),
+ TCP_NAGLE_OFF);
+ if (after(tp->snd_nxt, tp->high_seq))
+ return; /* Step 2.b */
+ tp->frto = 0;
+ }
+ }
+
+ if (recovered) {
+ /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
+ icsk->icsk_retransmits = 0;
+ tcp_try_undo_recovery(sk);
+ return;
+ }
+ if (flag & FLAG_DATA_ACKED)
+ icsk->icsk_retransmits = 0;
+ if (tcp_is_reno(tp)) {
+ /* A Reno DUPACK means new data in F-RTO step 2.b above are
+ * delivered. Lower inflight to clock out (re)tranmissions.
+ */
+ if (after(tp->snd_nxt, tp->high_seq) && is_dupack)
+ tcp_add_reno_sack(sk);
+ else if (flag & FLAG_SND_UNA_ADVANCED)
+ tcp_reset_reno_sack(tp);
+ }
+ if (tcp_try_undo_loss(sk, false))
+ return;
+ tcp_xmit_retransmit_queue(sk);
+}
+
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
@@ -2918,12 +2776,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
tp->retrans_stamp = 0;
} else if (!before(tp->snd_una, tp->high_seq)) {
switch (icsk->icsk_ca_state) {
- case TCP_CA_Loss:
- icsk->icsk_retransmits = 0;
- if (tcp_try_undo_recovery(sk))
- return;
- break;
-
case TCP_CA_CWR:
/* CWR is to be held something *above* high_seq
* is ACKed for CWR bit to reach receiver. */
@@ -2954,18 +2806,10 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
break;
case TCP_CA_Loss:
- if (flag & FLAG_DATA_ACKED)
- icsk->icsk_retransmits = 0;
- if (tcp_is_reno(tp) && flag & FLAG_SND_UNA_ADVANCED)
- tcp_reset_reno_sack(tp);
- if (!tcp_try_undo_loss(sk)) {
- tcp_moderate_cwnd(tp);
- tcp_xmit_retransmit_queue(sk);
- return;
- }
+ tcp_process_loss(sk, flag, is_dupack);
if (icsk->icsk_ca_state != TCP_CA_Open)
return;
- /* Loss is undone; fall through to processing in Open state. */
+ /* Fall through to processing in Open state. */
default:
if (tcp_is_reno(tp)) {
if (flag & FLAG_SND_UNA_ADVANCED)
@@ -3078,6 +2922,7 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
*/
void tcp_rearm_rto(struct sock *sk)
{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
/* If the retrans timer is currently being used by Fast Open
@@ -3091,12 +2936,13 @@ void tcp_rearm_rto(struct sock *sk)
} else {
u32 rto = inet_csk(sk)->icsk_rto;
/* Offset the time elapsed after installing regular RTO */
- if (tp->early_retrans_delayed) {
+ if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
struct sk_buff *skb = tcp_write_queue_head(sk);
const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
/* delta may not be positive if the socket is locked
- * when the delayed ER timer fires and is rescheduled.
+ * when the retrans timer fires and is rescheduled.
*/
if (delta > 0)
rto = delta;
@@ -3104,7 +2950,6 @@ void tcp_rearm_rto(struct sock *sk)
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
TCP_RTO_MAX);
}
- tp->early_retrans_delayed = 0;
}
/* This function is called when the delayed ER timer fires. TCP enters
@@ -3192,8 +3037,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
flag |= FLAG_RETRANS_DATA_ACKED;
ca_seq_rtt = -1;
seq_rtt = -1;
- if ((flag & FLAG_DATA_ACKED) || (acked_pcount > 1))
- flag |= FLAG_NONHEAD_RETRANS_ACKED;
} else {
ca_seq_rtt = now - scb->when;
last_ackt = skb->tstamp;
@@ -3202,6 +3045,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
}
if (!(sacked & TCPCB_SACKED_ACKED))
reord = min(pkts_acked, reord);
+ if (!after(scb->end_seq, tp->high_seq))
+ flag |= FLAG_ORIG_SACK_ACKED;
}
if (sacked & TCPCB_SACKED_ACKED)
@@ -3402,150 +3247,6 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
return flag;
}
-/* A very conservative spurious RTO response algorithm: reduce cwnd and
- * continue in congestion avoidance.
- */
-static void tcp_conservative_spur_to_response(struct tcp_sock *tp)
-{
- tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
- tp->snd_cwnd_cnt = 0;
- TCP_ECN_queue_cwr(tp);
- tcp_moderate_cwnd(tp);
-}
-
-/* A conservative spurious RTO response algorithm: reduce cwnd using
- * PRR and continue in congestion avoidance.
- */
-static void tcp_cwr_spur_to_response(struct sock *sk)
-{
- tcp_enter_cwr(sk, 0);
-}
-
-static void tcp_undo_spur_to_response(struct sock *sk, int flag)
-{
- if (flag & FLAG_ECE)
- tcp_cwr_spur_to_response(sk);
- else
- tcp_undo_cwr(sk, true);
-}
-
-/* F-RTO spurious RTO detection algorithm (RFC4138)
- *
- * F-RTO affects during two new ACKs following RTO (well, almost, see inline
- * comments). State (ACK number) is kept in frto_counter. When ACK advances
- * window (but not to or beyond highest sequence sent before RTO):
- * On First ACK, send two new segments out.
- * On Second ACK, RTO was likely spurious. Do spurious response (response
- * algorithm is not part of the F-RTO detection algorithm
- * given in RFC4138 but can be selected separately).
- * Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
- * and TCP falls back to conventional RTO recovery. F-RTO allows overriding
- * of Nagle, this is done using frto_counter states 2 and 3, when a new data
- * segment of any size sent during F-RTO, state 2 is upgraded to 3.
- *
- * Rationale: if the RTO was spurious, new ACKs should arrive from the
- * original window even after we transmit two new data segments.
- *
- * SACK version:
- * on first step, wait until first cumulative ACK arrives, then move to
- * the second step. In second step, the next ACK decides.
- *
- * F-RTO is implemented (mainly) in four functions:
- * - tcp_use_frto() is used to determine if TCP is can use F-RTO
- * - tcp_enter_frto() prepares TCP state on RTO if F-RTO is used, it is
- * called when tcp_use_frto() showed green light
- * - tcp_process_frto() handles incoming ACKs during F-RTO algorithm
- * - tcp_enter_frto_loss() is called if there is not enough evidence
- * to prove that the RTO is indeed spurious. It transfers the control
- * from F-RTO to the conventional RTO recovery
- */
-static bool tcp_process_frto(struct sock *sk, int flag)
-{
- struct tcp_sock *tp = tcp_sk(sk);
-
- tcp_verify_left_out(tp);
-
- /* Duplicate the behavior from Loss state (fastretrans_alert) */
- if (flag & FLAG_DATA_ACKED)
- inet_csk(sk)->icsk_retransmits = 0;
-
- if ((flag & FLAG_NONHEAD_RETRANS_ACKED) ||
- ((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED)))
- tp->undo_marker = 0;
-
- if (!before(tp->snd_una, tp->frto_highmark)) {
- tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
- return true;
- }
-
- if (!tcp_is_sackfrto(tp)) {
- /* RFC4138 shortcoming in step 2; should also have case c):
- * ACK isn't duplicate nor advances window, e.g., opposite dir
- * data, winupdate
- */
- if (!(flag & FLAG_ANY_PROGRESS) && (flag & FLAG_NOT_DUP))
- return true;
-
- if (!(flag & FLAG_DATA_ACKED)) {
- tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3),
- flag);
- return true;
- }
- } else {
- if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
- if (!tcp_packets_in_flight(tp)) {
- tcp_enter_frto_loss(sk, 2, flag);
- return true;
- }
-
- /* Prevent sending of new data. */
- tp->snd_cwnd = min(tp->snd_cwnd,
- tcp_packets_in_flight(tp));
- return true;
- }
-
- if ((tp->frto_counter >= 2) &&
- (!(flag & FLAG_FORWARD_PROGRESS) ||
- ((flag & FLAG_DATA_SACKED) &&
- !(flag & FLAG_ONLY_ORIG_SACKED)))) {
- /* RFC4138 shortcoming (see comment above) */
- if (!(flag & FLAG_FORWARD_PROGRESS) &&
- (flag & FLAG_NOT_DUP))
- return true;
-
- tcp_enter_frto_loss(sk, 3, flag);
- return true;
- }
- }
-
- if (tp->frto_counter == 1) {
- /* tcp_may_send_now needs to see updated state */
- tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
- tp->frto_counter = 2;
-
- if (!tcp_may_send_now(sk))
- tcp_enter_frto_loss(sk, 2, flag);
-
- return true;
- } else {
- switch (sysctl_tcp_frto_response) {
- case 2:
- tcp_undo_spur_to_response(sk, flag);
- break;
- case 1:
- tcp_conservative_spur_to_response(tp);
- break;
- default:
- tcp_cwr_spur_to_response(sk);
- break;
- }
- tp->frto_counter = 0;
- tp->undo_marker = 0;
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS);
- }
- return false;
-}
-
/* RFC 5961 7 [ACK Throttling] */
static void tcp_send_challenge_ack(struct sock *sk)
{
@@ -3564,6 +3265,38 @@ static void tcp_send_challenge_ack(struct sock *sk)
}
}
+/* This routine deals with acks during a TLP episode.
+ * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+ */
+static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ bool is_tlp_dupack = (ack == tp->tlp_high_seq) &&
+ !(flag & (FLAG_SND_UNA_ADVANCED |
+ FLAG_NOT_DUP | FLAG_DATA_SACKED));
+
+ /* Mark the end of TLP episode on receiving TLP dupack or when
+ * ack is after tlp_high_seq.
+ */
+ if (is_tlp_dupack) {
+ tp->tlp_high_seq = 0;
+ return;
+ }
+
+ if (after(ack, tp->tlp_high_seq)) {
+ tp->tlp_high_seq = 0;
+ /* Don't reduce cwnd if DSACK arrives for TLP retrans. */
+ if (!(flag & FLAG_DSACKING_ACK)) {
+ 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);
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPLOSSPROBERECOVERY);
+ }
+ }
+}
+
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
@@ -3578,7 +3311,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
int prior_packets;
int prior_sacked = tp->sacked_out;
int pkts_acked = 0;
- bool frto_cwnd = false;
/* If the ack is older than previous acks
* then we can probably ignore it.
@@ -3598,7 +3330,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (after(ack, tp->snd_nxt))
goto invalid_ack;
- if (tp->early_retrans_delayed)
+ if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
if (after(ack, prior_snd_una))
@@ -3651,30 +3384,29 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
pkts_acked = prior_packets - tp->packets_out;
- if (tp->frto_counter)
- frto_cwnd = tcp_process_frto(sk, flag);
- /* Guarantee sacktag reordering detection against wrap-arounds */
- if (before(tp->frto_highmark, tp->snd_una))
- tp->frto_highmark = 0;
-
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
- if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
- tcp_may_raise_cwnd(sk, flag))
+ if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
is_dupack, flag);
} else {
- if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
+ if (flag & FLAG_DATA_ACKED)
tcp_cong_avoid(sk, ack, prior_in_flight);
}
+ if (tp->tlp_high_seq)
+ tcp_process_tlp_ack(sk, ack, flag);
+
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
struct dst_entry *dst = __sk_dst_get(sk);
if (dst)
dst_confirm(dst);
}
+
+ if (icsk->icsk_pending == ICSK_TIME_RETRANS)
+ tcp_schedule_loss_probe(sk);
return 1;
no_queue:
@@ -3688,6 +3420,9 @@ no_queue:
*/
if (tcp_send_head(sk))
tcp_ack_probe(sk);
+
+ if (tp->tlp_high_seq)
+ tcp_process_tlp_ack(sk, ack, flag);
return 1;
invalid_ack:
@@ -3712,8 +3447,8 @@ old_ack:
* But, this can also be called on packets in the established flow when
* the fast version below fails.
*/
-void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx,
- const u8 **hvpp, int estab,
+void tcp_parse_options(const struct sk_buff *skb,
+ struct tcp_options_received *opt_rx, int estab,
struct tcp_fastopen_cookie *foc)
{
const unsigned char *ptr;
@@ -3797,31 +3532,6 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
*/
break;
#endif
- case TCPOPT_COOKIE:
- /* This option is variable length.
- */
- switch (opsize) {
- case TCPOLEN_COOKIE_BASE:
- /* not yet implemented */
- break;
- case TCPOLEN_COOKIE_PAIR:
- /* not yet implemented */
- break;
- case TCPOLEN_COOKIE_MIN+0:
- case TCPOLEN_COOKIE_MIN+2:
- case TCPOLEN_COOKIE_MIN+4:
- case TCPOLEN_COOKIE_MIN+6:
- case TCPOLEN_COOKIE_MAX:
- /* 16-bit multiple */
- opt_rx->cookie_plus = opsize;
- *hvpp = ptr;
- break;
- default:
- /* ignore option */
- break;
- }
- break;
-
case TCPOPT_EXP:
/* Fast Open option shares code 254 using a
* 16 bits magic number. It's valid only in
@@ -3867,8 +3577,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr
* If it is wrong it falls back on tcp_parse_options().
*/
static bool tcp_fast_parse_options(const struct sk_buff *skb,
- const struct tcphdr *th,
- struct tcp_sock *tp, const u8 **hvpp)
+ const struct tcphdr *th, struct tcp_sock *tp)
{
/* In the spirit of fast parsing, compare doff directly to constant
* values. Because equality is used, short doff can be ignored here.
@@ -3882,7 +3591,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
return true;
}
- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
if (tp->rx_opt.saw_tstamp)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
@@ -5263,12 +4972,10 @@ out:
static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, int syn_inerr)
{
- const u8 *hash_location;
struct tcp_sock *tp = tcp_sk(sk);
/* RFC1323: H1. Apply PAWS check first. */
- if (tcp_fast_parse_options(skb, th, tp, &hash_location) &&
- tp->rx_opt.saw_tstamp &&
+ if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
@@ -5622,12 +5329,11 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
if (mss == tp->rx_opt.user_mss) {
struct tcp_options_received opt;
- const u8 *hash_location;
/* Get original SYNACK MSS value if user MSS sets mss_clamp */
tcp_clear_options(&opt);
opt.user_mss = opt.mss_clamp = 0;
- tcp_parse_options(synack, &opt, &hash_location, 0, NULL);
+ tcp_parse_options(synack, &opt, 0, NULL);
mss = opt.mss_clamp;
}
@@ -5658,14 +5364,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, unsigned int len)
{
- const u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_cookie_values *cvp = tp->cookie_values;
struct tcp_fastopen_cookie foc = { .len = -1 };
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc);
+ tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
if (tp->rx_opt.saw_tstamp)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
@@ -5762,30 +5466,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
- if (cvp != NULL &&
- cvp->cookie_pair_size > 0 &&
- tp->rx_opt.cookie_plus > 0) {
- int cookie_size = tp->rx_opt.cookie_plus
- - TCPOLEN_COOKIE_BASE;
- int cookie_pair_size = cookie_size
- + cvp->cookie_desired;
-
- /* A cookie extension option was sent and returned.
- * Note that each incoming SYNACK replaces the
- * Responder cookie. The initial exchange is most
- * fragile, as protection against spoofing relies
- * entirely upon the sequence and timestamp (above).
- * This replacement strategy allows the correct pair to
- * pass through, while any others will be filtered via
- * Responder verification later.
- */
- if (sizeof(cvp->cookie_pair) >= cookie_pair_size) {
- memcpy(&cvp->cookie_pair[cvp->cookie_desired],
- hash_location, cookie_size);
- cvp->cookie_pair_size = cookie_pair_size;
- }
- }
-
smp_mb();
tcp_finish_connect(sk, skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d09203c63264..2278669b1d85 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -838,7 +838,6 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
*/
static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct request_values *rvp,
u16 queue_mapping,
bool nocache)
{
@@ -851,7 +850,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
return -1;
- skb = tcp_make_synack(sk, dst, req, rvp, NULL);
+ skb = tcp_make_synack(sk, dst, req, NULL);
if (skb) {
__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
@@ -868,10 +867,9 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
return err;
}
-static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
- struct request_values *rvp)
+static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
{
- int res = tcp_v4_send_synack(sk, NULL, req, rvp, 0, false);
+ int res = tcp_v4_send_synack(sk, NULL, req, 0, false);
if (!res)
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
@@ -1371,8 +1369,7 @@ static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
static int tcp_v4_conn_req_fastopen(struct sock *sk,
struct sk_buff *skb,
struct sk_buff *skb_synack,
- struct request_sock *req,
- struct request_values *rvp)
+ struct request_sock *req)
{
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
@@ -1467,9 +1464,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct request_sock *req;
struct inet_request_sock *ireq;
struct tcp_sock *tp = tcp_sk(sk);
@@ -1519,42 +1514,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0,
- want_cookie ? NULL : &foc);
-
- if (tmp_opt.cookie_plus > 0 &&
- tmp_opt.saw_tstamp &&
- !tp->rx_opt.cookie_out_never &&
- (sysctl_tcp_cookie_size > 0 ||
- (tp->cookie_values != NULL &&
- tp->cookie_values->cookie_desired > 0))) {
- u8 *c;
- u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
- int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
-
- if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
- goto drop_and_release;
-
- /* Secret recipe starts with IP addresses */
- *mess++ ^= (__force u32)daddr;
- *mess++ ^= (__force u32)saddr;
-
- /* plus variable length Initiator Cookie */
- c = (u8 *)mess;
- while (l-- > 0)
- *c++ ^= *hash_location++;
-
- want_cookie = false; /* not our kind of cookie */
- tmp_ext.cookie_out_never = 0; /* false */
- tmp_ext.cookie_plus = tmp_opt.cookie_plus;
- } else if (!tp->rx_opt.cookie_in_always) {
- /* redundant indications, but ensure initialization. */
- tmp_ext.cookie_out_never = 1; /* true */
- tmp_ext.cookie_plus = 0;
- } else {
- goto drop_and_release;
- }
- tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
+ tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1636,7 +1596,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
* of tcp_v4_send_synack()->tcp_select_initial_window().
*/
skb_synack = tcp_make_synack(sk, dst, req,
- (struct request_values *)&tmp_ext,
fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
if (skb_synack) {
@@ -1660,8 +1619,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (fastopen_cookie_present(&foc) && foc.len != 0)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
- } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req,
- (struct request_values *)&tmp_ext))
+ } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req))
goto drop_and_free;
return 0;
@@ -1950,6 +1908,50 @@ void tcp_v4_early_demux(struct sk_buff *skb)
}
}
+/* Packet is added to VJ-style prequeue for processing in process
+ * context, if a reader task is waiting. Apparently, this exciting
+ * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
+ * failed somewhere. Latency? Burstiness? Well, at least now we will
+ * see, why it failed. 8)8) --ANK
+ *
+ */
+bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (sysctl_tcp_low_latency || !tp->ucopy.task)
+ return false;
+
+ if (skb->len <= tcp_hdrlen(skb) &&
+ skb_queue_len(&tp->ucopy.prequeue) == 0)
+ return false;
+
+ __skb_queue_tail(&tp->ucopy.prequeue, skb);
+ tp->ucopy.memory += skb->truesize;
+ if (tp->ucopy.memory > sk->sk_rcvbuf) {
+ struct sk_buff *skb1;
+
+ BUG_ON(sock_owned_by_user(sk));
+
+ while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
+ sk_backlog_rcv(sk, skb1);
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPPREQUEUEDROPPED);
+ }
+
+ tp->ucopy.memory = 0;
+ } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
+ wake_up_interruptible_sync_poll(sk_sleep(sk),
+ POLLIN | POLLRDNORM | POLLRDBAND);
+ if (!inet_csk_ack_scheduled(sk))
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+ (3 * tcp_rto_min(sk)) / 4,
+ TCP_RTO_MAX);
+ }
+ return true;
+}
+EXPORT_SYMBOL(tcp_prequeue);
+
/*
* From tcp_input.c
*/
@@ -2197,12 +2199,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
if (inet_csk(sk)->icsk_bind_hash)
inet_put_port(sk);
- /* TCP Cookie Transactions */
- if (tp->cookie_values != NULL) {
- kref_put(&tp->cookie_values->kref,
- tcp_cookie_values_release);
- tp->cookie_values = NULL;
- }
BUG_ON(tp->fastopen_rsk != NULL);
/* If socket is aborted during connect operation */
@@ -2659,7 +2655,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
__u16 srcp = ntohs(inet->inet_sport);
int rx_queue;
- if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+ if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b83a49cc3816..05eaf8904613 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -93,13 +93,12 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
const struct tcphdr *th)
{
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
bool paws_reject = false;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
@@ -388,32 +387,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
struct tcp_sock *newtp = tcp_sk(newsk);
- struct tcp_sock *oldtp = tcp_sk(sk);
- struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
-
- /* TCP Cookie Transactions require space for the cookie pair,
- * as it differs for each connection. There is no need to
- * copy any s_data_payload stored at the original socket.
- * Failure will prevent resuming the connection.
- *
- * Presumed copied, in order of appearance:
- * cookie_in_always, cookie_out_never
- */
- if (oldcvp != NULL) {
- struct tcp_cookie_values *newcvp =
- kzalloc(sizeof(*newtp->cookie_values),
- GFP_ATOMIC);
-
- if (newcvp != NULL) {
- kref_init(&newcvp->kref);
- newcvp->cookie_desired =
- oldcvp->cookie_desired;
- newtp->cookie_values = newcvp;
- } else {
- /* Not Yet Implemented */
- newtp->cookie_values = NULL;
- }
- }
/* Now setup tcp_sock */
newtp->pred_flags = 0;
@@ -422,8 +395,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una =
- newtp->snd_nxt = newtp->snd_up =
- treq->snt_isn + 1 + tcp_s_data_size(oldtp);
+ newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
INIT_LIST_HEAD(&newtp->tsq_node);
@@ -440,6 +412,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->fackets_out = 0;
newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tcp_enable_early_retrans(newtp);
+ newtp->tlp_high_seq = 0;
/* So many TCP implementations out there (incorrectly) count the
* initial SYN frame in their delayed-ACK and congestion control
@@ -449,9 +422,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->snd_cwnd = TCP_INIT_CWND;
newtp->snd_cwnd_cnt = 0;
- newtp->frto_counter = 0;
- newtp->frto_highmark = 0;
-
if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
!try_module_get(newicsk->icsk_ca_ops->owner))
newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
@@ -459,8 +429,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
- newtp->write_seq = newtp->pushed_seq =
- treq->snt_isn + 1 + tcp_s_data_size(oldtp);
+ newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
newtp->rx_opt.saw_tstamp = 0;
@@ -537,7 +506,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
bool fastopen)
{
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct sock *child;
const struct tcphdr *th = tcp_hdr(skb);
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
@@ -547,7 +515,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
@@ -647,7 +615,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
*/
if ((flg & TCP_FLAG_ACK) && !fastopen &&
(TCP_SKB_CB(skb)->ack_seq !=
- tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk))))
+ tcp_rsk(req)->snt_isn + 1))
return sk;
/* Also, it would be not so bad idea to check rcv_tsecr, which
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5d0b4387cba6..af354c98fdb5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -65,27 +65,22 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
-int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
-EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size);
-
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
/* Account for new data that has been sent to the network. */
static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned int prior_packets = tp->packets_out;
tcp_advance_send_head(sk, skb);
tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
- /* Don't override Nagle indefinitely with F-RTO */
- if (tp->frto_counter == 2)
- tp->frto_counter = 3;
-
tp->packets_out += tcp_skb_pcount(skb);
- if (!prior_packets || tp->early_retrans_delayed)
+ if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+ icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
tcp_rearm_rto(sk);
}
@@ -384,7 +379,6 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_TS (1 << 1)
#define OPTION_MD5 (1 << 2)
#define OPTION_WSCALE (1 << 3)
-#define OPTION_COOKIE_EXTENSION (1 << 4)
#define OPTION_FAST_OPEN_COOKIE (1 << 8)
struct tcp_out_options {
@@ -398,36 +392,6 @@ struct tcp_out_options {
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
};
-/* The sysctl int routines are generic, so check consistency here.
- */
-static u8 tcp_cookie_size_check(u8 desired)
-{
- int cookie_size;
-
- if (desired > 0)
- /* previously specified */
- return desired;
-
- cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size);
- if (cookie_size <= 0)
- /* no default specified */
- return 0;
-
- if (cookie_size <= TCP_COOKIE_MIN)
- /* value too small, specify minimum */
- return TCP_COOKIE_MIN;
-
- if (cookie_size >= TCP_COOKIE_MAX)
- /* value too large, specify maximum */
- return TCP_COOKIE_MAX;
-
- if (cookie_size & 1)
- /* 8-bit multiple, illegal, fix it */
- cookie_size++;
-
- return (u8)cookie_size;
-}
-
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -446,27 +410,9 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
{
u16 options = opts->options; /* mungable copy */
- /* Having both authentication and cookies for security is redundant,
- * and there's certainly not enough room. Instead, the cookie-less
- * extension variant is proposed.
- *
- * Consider the pessimal case with authentication. The options
- * could look like:
- * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40
- */
if (unlikely(OPTION_MD5 & options)) {
- if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
- *ptr++ = htonl((TCPOPT_COOKIE << 24) |
- (TCPOLEN_COOKIE_BASE << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- } else {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- }
- options &= ~OPTION_COOKIE_EXTENSION;
+ *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
+ (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
/* overload cookie hash location */
opts->hash_location = (__u8 *)ptr;
ptr += 4;
@@ -495,44 +441,6 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
*ptr++ = htonl(opts->tsecr);
}
- /* Specification requires after timestamp, so do it now.
- *
- * Consider the pessimal case without authentication. The options
- * could look like:
- * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40
- */
- if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
- __u8 *cookie_copy = opts->hash_location;
- u8 cookie_size = opts->hash_size;
-
- /* 8-bit multiple handled in tcp_cookie_size_check() above,
- * and elsewhere.
- */
- if (0x2 & cookie_size) {
- __u8 *p = (__u8 *)ptr;
-
- /* 16-bit multiple */
- *p++ = TCPOPT_COOKIE;
- *p++ = TCPOLEN_COOKIE_BASE + cookie_size;
- *p++ = *cookie_copy++;
- *p++ = *cookie_copy++;
- ptr++;
- cookie_size -= 2;
- } else {
- /* 32-bit multiple */
- *ptr++ = htonl(((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_COOKIE << 8) |
- TCPOLEN_COOKIE_BASE) +
- cookie_size);
- }
-
- if (cookie_size > 0) {
- memcpy(ptr, cookie_copy, cookie_size);
- ptr += (cookie_size / 4);
- }
- }
-
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
@@ -591,11 +499,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_md5sig_key **md5)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_cookie_values *cvp = tp->cookie_values;
unsigned int remaining = MAX_TCP_OPTION_SPACE;
- u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
- tcp_cookie_size_check(cvp->cookie_desired) :
- 0;
struct tcp_fastopen_request *fastopen = tp->fastopen_req;
#ifdef CONFIG_TCP_MD5SIG
@@ -647,52 +551,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
tp->syn_fastopen = 1;
}
}
- /* Note that timestamps are required by the specification.
- *
- * Odd numbers of bytes are prohibited by the specification, ensuring
- * that the cookie is 16-bit aligned, and the resulting cookie pair is
- * 32-bit aligned.
- */
- if (*md5 == NULL &&
- (OPTION_TS & opts->options) &&
- cookie_size > 0) {
- int need = TCPOLEN_COOKIE_BASE + cookie_size;
-
- if (0x2 & need) {
- /* 32-bit multiple */
- need += 2; /* NOPs */
-
- if (need > remaining) {
- /* try shrinking cookie to fit */
- cookie_size -= 2;
- need -= 4;
- }
- }
- while (need > remaining && TCP_COOKIE_MIN <= cookie_size) {
- cookie_size -= 4;
- need -= 4;
- }
- if (TCP_COOKIE_MIN <= cookie_size) {
- opts->options |= OPTION_COOKIE_EXTENSION;
- opts->hash_location = (__u8 *)&cvp->cookie_pair[0];
- opts->hash_size = cookie_size;
-
- /* Remember for future incarnations. */
- cvp->cookie_desired = cookie_size;
-
- if (cvp->cookie_desired != cvp->cookie_pair_size) {
- /* Currently use random bytes as a nonce,
- * assuming these are completely unpredictable
- * by hostile users of the same system.
- */
- get_random_bytes(&cvp->cookie_pair[0],
- cookie_size);
- cvp->cookie_pair_size = cookie_size;
- }
- remaining -= need;
- }
- }
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -702,14 +561,10 @@ static unsigned int tcp_synack_options(struct sock *sk,
unsigned int mss, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5,
- struct tcp_extend_values *xvp,
struct tcp_fastopen_cookie *foc)
{
struct inet_request_sock *ireq = inet_rsk(req);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
- u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ?
- xvp->cookie_plus :
- 0;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
@@ -757,28 +612,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
remaining -= need;
}
}
- /* Similar rationale to tcp_syn_options() applies here, too.
- * If the <SYN> options fit, the same options should fit now!
- */
- if (*md5 == NULL &&
- ireq->tstamp_ok &&
- cookie_plus > TCPOLEN_COOKIE_BASE) {
- int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */
-
- if (0x2 & need) {
- /* 32-bit multiple */
- need += 2; /* NOPs */
- }
- if (need <= remaining) {
- opts->options |= OPTION_COOKIE_EXTENSION;
- opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE;
- remaining -= need;
- } else {
- /* There's no error return, so flag it. */
- xvp->cookie_out_never = 1; /* true */
- opts->hash_size = 0;
- }
- }
+
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -1632,11 +1466,8 @@ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buf
if (nonagle & TCP_NAGLE_PUSH)
return true;
- /* Don't use the nagle rule for urgent data (or for the final FIN).
- * Nagle can be ignored during F-RTO too (see RFC4138).
- */
- if (tcp_urg_mode(tp) || (tp->frto_counter == 2) ||
- (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
+ /* Don't use the nagle rule for urgent data (or for the final FIN). */
+ if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
return true;
if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
@@ -1961,6 +1792,9 @@ static int tcp_mtu_probe(struct sock *sk)
* snd_up-64k-mss .. snd_up cannot be large. However, taking into
* account rare use of URG, this is not a big flaw.
*
+ * Send at most one packet when push_one > 0. Temporarily ignore
+ * cwnd limit to force at most one packet out when push_one == 2.
+
* Returns true, if no segments are in flight and we have queued segments,
* but cannot send anything now because of SWS or another problem.
*/
@@ -1996,8 +1830,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
goto repair; /* Skip network transmission */
cwnd_quota = tcp_cwnd_test(tp, skb);
- if (!cwnd_quota)
- break;
+ if (!cwnd_quota) {
+ if (push_one == 2)
+ /* Force out a loss probe pkt. */
+ cwnd_quota = 1;
+ else
+ break;
+ }
if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
break;
@@ -2051,10 +1890,129 @@ repair:
if (likely(sent_pkts)) {
if (tcp_in_cwnd_reduction(sk))
tp->prr_out += sent_pkts;
+
+ /* Send one loss probe per tail loss episode. */
+ if (push_one != 2)
+ tcp_schedule_loss_probe(sk);
tcp_cwnd_validate(sk);
return false;
}
- return !tp->packets_out && tcp_send_head(sk);
+ return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
+}
+
+bool tcp_schedule_loss_probe(struct sock *sk)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 timeout, tlp_time_stamp, rto_time_stamp;
+ u32 rtt = tp->srtt >> 3;
+
+ if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
+ return false;
+ /* No consecutive loss probes. */
+ if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
+ tcp_rearm_rto(sk);
+ return false;
+ }
+ /* Don't do any loss probe on a Fast Open connection before 3WHS
+ * finishes.
+ */
+ if (sk->sk_state == TCP_SYN_RECV)
+ return false;
+
+ /* TLP is only scheduled when next timer event is RTO. */
+ if (icsk->icsk_pending != ICSK_TIME_RETRANS)
+ return false;
+
+ /* Schedule a loss probe in 2*RTT for SACK capable connections
+ * in Open state, that are either limited by cwnd or application.
+ */
+ if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
+ !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+ return false;
+
+ if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
+ tcp_send_head(sk))
+ return false;
+
+ /* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
+ * for delayed ack when there's one outstanding packet.
+ */
+ timeout = rtt << 1;
+ if (tp->packets_out == 1)
+ timeout = max_t(u32, timeout,
+ (rtt + (rtt >> 1) + TCP_DELACK_MAX));
+ timeout = max_t(u32, timeout, msecs_to_jiffies(10));
+
+ /* If RTO is shorter, just schedule TLP in its place. */
+ tlp_time_stamp = tcp_time_stamp + timeout;
+ rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout;
+ if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) {
+ s32 delta = rto_time_stamp - tcp_time_stamp;
+ if (delta > 0)
+ timeout = delta;
+ }
+
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
+ TCP_RTO_MAX);
+ return true;
+}
+
+/* When probe timeout (PTO) fires, send a new segment if one exists, else
+ * retransmit the last segment.
+ */
+void tcp_send_loss_probe(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+ int pcount;
+ int mss = tcp_current_mss(sk);
+ int err = -1;
+
+ if (tcp_send_head(sk) != NULL) {
+ err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+ goto rearm_timer;
+ }
+
+ /* At most one outstanding TLP retransmission. */
+ if (tp->tlp_high_seq)
+ goto rearm_timer;
+
+ /* Retransmit last segment. */
+ skb = tcp_write_queue_tail(sk);
+ if (WARN_ON(!skb))
+ goto rearm_timer;
+
+ pcount = tcp_skb_pcount(skb);
+ if (WARN_ON(!pcount))
+ goto rearm_timer;
+
+ if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
+ if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss)))
+ goto rearm_timer;
+ skb = tcp_write_queue_tail(sk);
+ }
+
+ if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
+ goto rearm_timer;
+
+ /* Probe with zero data doesn't trigger fast recovery. */
+ if (skb->len > 0)
+ err = __tcp_retransmit_skb(sk, skb);
+
+ /* Record snd_nxt for loss detection. */
+ if (likely(!err))
+ tp->tlp_high_seq = tp->snd_nxt;
+
+rearm_timer:
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto,
+ TCP_RTO_MAX);
+
+ if (likely(!err))
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPLOSSPROBES);
+ return;
}
/* Push out any pending frames which were held back due to
@@ -2675,32 +2633,24 @@ int tcp_send_synack(struct sock *sk)
* sk: listener socket
* dst: dst entry attached to the SYNACK
* req: request_sock pointer
- * rvp: request_values pointer
*
* Allocate one skb and build a SYNACK packet.
* @dst is consumed : Caller should not use it again.
*/
struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct request_values *rvp,
struct tcp_fastopen_cookie *foc)
{
struct tcp_out_options opts;
- struct tcp_extend_values *xvp = tcp_xv(rvp);
struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
- const struct tcp_cookie_values *cvp = tp->cookie_values;
struct tcphdr *th;
struct sk_buff *skb;
struct tcp_md5sig_key *md5;
int tcp_header_size;
int mss;
- int s_data_desired = 0;
- if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
- s_data_desired = cvp->s_data_desired;
- skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired,
- sk_gfp_atomic(sk, GFP_ATOMIC));
+ skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC));
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
@@ -2742,9 +2692,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
else
#endif
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_header_size = tcp_synack_options(sk, req, mss,
- skb, &opts, &md5, xvp, foc)
- + sizeof(*th);
+ tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
+ foc) + sizeof(*th);
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
@@ -2762,40 +2711,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
TCPHDR_SYN | TCPHDR_ACK);
- if (OPTION_COOKIE_EXTENSION & opts.options) {
- if (s_data_desired) {
- u8 *buf = skb_put(skb, s_data_desired);
-
- /* copy data directly from the listening socket. */
- memcpy(buf, cvp->s_data_payload, s_data_desired);
- TCP_SKB_CB(skb)->end_seq += s_data_desired;
- }
-
- if (opts.hash_size > 0) {
- __u32 workspace[SHA_WORKSPACE_WORDS];
- u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS];
- u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1];
-
- /* Secret recipe depends on the Timestamp, (future)
- * Sequence and Acknowledgment Numbers, Initiator
- * Cookie, and others handled by IP variant caller.
- */
- *tail-- ^= opts.tsval;
- *tail-- ^= tcp_rsk(req)->rcv_isn + 1;
- *tail-- ^= TCP_SKB_CB(skb)->seq + 1;
-
- /* recommended */
- *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source);
- *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
-
- sha_transform((__u32 *)&xvp->cookie_bakery[0],
- (char *)mess,
- &workspace[0]);
- opts.hash_location =
- (__u8 *)&xvp->cookie_bakery[0];
- }
- }
-
th->seq = htonl(TCP_SKB_CB(skb)->seq);
/* XXX data is queued and acked as is. No buffer/window check */
th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b78aac30c498..4b85e6f636c9 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -342,10 +342,6 @@ void tcp_retransmit_timer(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
- if (tp->early_retrans_delayed) {
- tcp_resume_early_retransmit(sk);
- return;
- }
if (tp->fastopen_rsk) {
WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
sk->sk_state != TCP_FIN_WAIT1);
@@ -360,6 +356,8 @@ void tcp_retransmit_timer(struct sock *sk)
WARN_ON(tcp_write_queue_empty(sk));
+ tp->tlp_high_seq = 0;
+
if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
!((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
/* Receiver dastardly shrinks window. Our retransmits
@@ -418,11 +416,7 @@ void tcp_retransmit_timer(struct sock *sk)
NET_INC_STATS_BH(sock_net(sk), mib_idx);
}
- if (tcp_use_frto(sk)) {
- tcp_enter_frto(sk);
- } else {
- tcp_enter_loss(sk, 0);
- }
+ tcp_enter_loss(sk, 0);
if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk)) > 0) {
/* Retransmission failed because of local congestion,
@@ -495,13 +489,20 @@ void tcp_write_timer_handler(struct sock *sk)
}
event = icsk->icsk_pending;
- icsk->icsk_pending = 0;
switch (event) {
+ case ICSK_TIME_EARLY_RETRANS:
+ tcp_resume_early_retransmit(sk);
+ break;
+ case ICSK_TIME_LOSS_PROBE:
+ tcp_send_loss_probe(sk);
+ break;
case ICSK_TIME_RETRANS:
+ icsk->icsk_pending = 0;
tcp_retransmit_timer(sk);
break;
case ICSK_TIME_PROBE0:
+ icsk->icsk_pending = 0;
tcp_probe_timer(sk);
break;
}
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index 1b91bf48e277..76a1e23259e1 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -236,7 +236,7 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
tp->snd_cwnd = tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
break;
- case CA_EVENT_FRTO:
+ case CA_EVENT_LOSS:
tp->snd_ssthresh = tcp_westwood_bw_rttmin(sk);
/* Update RTT_min when next ack arrives */
w->reset_rtt_min = 1;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0a073a263720..7117d1467b02 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2279,31 +2279,88 @@ void __init udp_init(void)
int udp4_ufo_send_check(struct sk_buff *skb)
{
- const struct iphdr *iph;
- struct udphdr *uh;
-
- if (!pskb_may_pull(skb, sizeof(*uh)))
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
return -EINVAL;
- iph = ip_hdr(skb);
- uh = udp_hdr(skb);
+ if (likely(!skb->encapsulation)) {
+ const struct iphdr *iph;
+ struct udphdr *uh;
- uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
- IPPROTO_UDP, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- skb->ip_summed = CHECKSUM_PARTIAL;
+ iph = ip_hdr(skb);
+ uh = udp_hdr(skb);
+
+ uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ IPPROTO_UDP, 0);
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ }
return 0;
}
+static struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ int mac_len = skb->mac_len;
+ int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+ int outer_hlen;
+ netdev_features_t enc_features;
+
+ if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
+ goto out;
+
+ skb->encapsulation = 0;
+ __skb_pull(skb, tnl_hlen);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, skb_inner_network_offset(skb));
+ skb->mac_len = skb_inner_network_offset(skb);
+
+ /* segment inner packet. */
+ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+ segs = skb_mac_gso_segment(skb, enc_features);
+ if (!segs || IS_ERR(segs))
+ goto out;
+
+ outer_hlen = skb_tnl_header_len(skb);
+ skb = segs;
+ do {
+ struct udphdr *uh;
+ int udp_offset = outer_hlen - tnl_hlen;
+
+ skb->mac_len = mac_len;
+
+ skb_push(skb, outer_hlen);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, mac_len);
+ skb_set_transport_header(skb, udp_offset);
+ uh = udp_hdr(skb);
+ uh->len = htons(skb->len - udp_offset);
+
+ /* csum segment if tunnel sets skb with csum. */
+ if (unlikely(uh->check)) {
+ struct iphdr *iph = ip_hdr(skb);
+
+ uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+ skb->len - udp_offset,
+ IPPROTO_UDP, 0);
+ uh->check = csum_fold(skb_checksum(skb, udp_offset,
+ skb->len - udp_offset, 0));
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+
+ }
+ skb->ip_summed = CHECKSUM_NONE;
+ } while ((skb = skb->next));
+out:
+ return segs;
+}
+
struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
- int offset;
- __wsum csum;
-
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
goto out;
@@ -2313,6 +2370,7 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
int type = skb_shinfo(skb)->gso_type;
if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
+ SKB_GSO_UDP_TUNNEL |
SKB_GSO_GRE) ||
!(type & (SKB_GSO_UDP))))
goto out;
@@ -2323,20 +2381,27 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
goto out;
}
- /* Do software UFO. Complete and fill in the UDP checksum as HW cannot
- * do checksum of UDP packets sent as multiple IP fragments.
- */
- offset = skb_checksum_start_offset(skb);
- csum = skb_checksum(skb, offset, skb->len - offset, 0);
- offset += skb->csum_offset;
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
- skb->ip_summed = CHECKSUM_NONE;
-
/* Fragment the skb. IP headers of the fragments are updated in
* inet_gso_segment()
*/
- segs = skb_segment(skb, features);
+ if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
+ segs = skb_udp_tunnel_segment(skb, features);
+ else {
+ int offset;
+ __wsum csum;
+
+ /* Do software UFO. Complete and fill in the UDP checksum as
+ * HW cannot do checksum of UDP packets sent as multiple
+ * IP fragments.
+ */
+ offset = skb_checksum_start_offset(skb);
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ offset += skb->csum_offset;
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+
+ segs = skb_segment(skb, features);
+ }
out:
return segs;
}
-
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 505b30ad9182..369a781851ad 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -64,9 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
goto out;
err = -ENOMEM;
- rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
- sizeof(struct inet_diag_meminfo) +
- 64)), GFP_KERNEL);
+ rep = nlmsg_new(sizeof(struct inet_diag_msg) +
+ sizeof(struct inet_diag_meminfo) + 64,
+ GFP_KERNEL);
if (!rep)
goto out;
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ed0b9e2e797a..11b13ea69db4 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -156,6 +156,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION
config IPV6_SIT
tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)"
select INET_TUNNEL
+ select NET_IP_TUNNEL
select IPV6_NDISC_NODETYPE
default y
---help---
@@ -201,6 +202,7 @@ config IPV6_TUNNEL
config IPV6_GRE
tristate "IPv6: GRE tunnel"
select IPV6_TUNNEL
+ select NET_IP_TUNNEL
---help---
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a459c4f5b769..a33b157d9ccf 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -70,6 +70,7 @@
#include <net/snmp.h>
#include <net/af_ieee802154.h>
+#include <net/firewire.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/ndisc.h>
@@ -544,8 +545,7 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
};
static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
- struct nlmsghdr *nlh,
- void *arg)
+ struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[NETCONFA_MAX+1];
@@ -605,6 +605,77 @@ errout:
return err;
}
+static int inet6_netconf_dump_devconf(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ int h, s_h;
+ int idx, s_idx;
+ struct net_device *dev;
+ struct inet6_dev *idev;
+ struct hlist_head *head;
+
+ s_h = cb->args[0];
+ s_idx = idx = cb->args[1];
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ rcu_read_lock();
+ cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^
+ net->dev_base_seq;
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ idev = __in6_dev_get(dev);
+ if (!idev)
+ goto cont;
+
+ if (inet6_netconf_fill_devconf(skb, dev->ifindex,
+ &idev->cnf,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF,
+ NLM_F_MULTI,
+ -1) <= 0) {
+ rcu_read_unlock();
+ goto done;
+ }
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+ idx++;
+ }
+ rcu_read_unlock();
+ }
+ if (h == NETDEV_HASHENTRIES) {
+ if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF, NLM_F_MULTI,
+ -1) <= 0)
+ goto done;
+ else
+ h++;
+ }
+ if (h == NETDEV_HASHENTRIES + 1) {
+ if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT,
+ net->ipv6.devconf_dflt,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ RTM_NEWNETCONF, NLM_F_MULTI,
+ -1) <= 0)
+ goto done;
+ else
+ h++;
+ }
+done:
+ cb->args[0] = h;
+ cb->args[1] = idx;
+
+ return skb->len;
+}
+
#ifdef CONFIG_SYSCTL
static void dev_forward_change(struct inet6_dev *idev)
{
@@ -1668,6 +1739,20 @@ static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev)
return 0;
}
+static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev)
+{
+ union fwnet_hwaddr *ha;
+
+ if (dev->addr_len != FWNET_ALEN)
+ return -1;
+
+ ha = (union fwnet_hwaddr *)dev->dev_addr;
+
+ memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id));
+ eui[0] ^= 2;
+ return 0;
+}
+
static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev)
{
/* XXX: inherit EUI-64 from other interface -- yoshfuji */
@@ -1732,6 +1817,8 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev)
return addrconf_ifid_gre(eui, dev);
case ARPHRD_IEEE802154:
return addrconf_ifid_eui64(eui, dev);
+ case ARPHRD_IEEE1394:
+ return addrconf_ifid_ieee1394(eui, dev);
}
return -1;
}
@@ -2600,7 +2687,8 @@ static void addrconf_dev_config(struct net_device *dev)
(dev->type != ARPHRD_FDDI) &&
(dev->type != ARPHRD_ARCNET) &&
(dev->type != ARPHRD_INFINIBAND) &&
- (dev->type != ARPHRD_IEEE802154)) {
+ (dev->type != ARPHRD_IEEE802154) &&
+ (dev->type != ARPHRD_IEEE1394)) {
/* Alas, we support only Ethernet autoconfiguration. */
return;
}
@@ -3537,7 +3625,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = {
};
static int
-inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifaddrmsg *ifm;
@@ -3603,7 +3691,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags,
}
static int
-inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifaddrmsg *ifm;
@@ -3834,6 +3922,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
NLM_F_MULTI);
if (err <= 0)
break;
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
}
break;
}
@@ -3891,6 +3980,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
s_ip_idx = ip_idx = cb->args[2];
rcu_read_lock();
+ cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq;
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
@@ -3942,8 +4032,7 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb)
return inet6_dump_addr(skb, cb, type);
}
-static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
- void *arg)
+static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct ifaddrmsg *ifm;
@@ -4368,6 +4457,8 @@ errout:
static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
{
+ struct net *net = dev_net(ifp->idev->dev);
+
inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
switch (event) {
@@ -4393,6 +4484,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
dst_free(&ifp->rt->dst);
break;
}
+ atomic_inc(&net->ipv6.dev_addr_genid);
}
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
@@ -4961,7 +5053,7 @@ int __init addrconf_init(void)
__rtnl_register(PF_INET6, RTM_GETANYCAST, NULL,
inet6_dump_ifacaddr, NULL);
__rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf,
- NULL, NULL);
+ inet6_netconf_dump_devconf, NULL);
ipv6_addr_label_rtnl_register();
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index aad64352cb60..f083a583a05c 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -414,8 +414,7 @@ static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
[IFAL_LABEL] = { .len = sizeof(u32), },
};
-static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
- void *arg)
+static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ifaddrlblmsg *ifal;
@@ -436,10 +435,7 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!tb[IFAL_ADDRESS])
return -EINVAL;
-
pfx = nla_data(tb[IFAL_ADDRESS]);
- if (!pfx)
- return -EINVAL;
if (!tb[IFAL_LABEL])
return -EINVAL;
@@ -533,8 +529,7 @@ static inline int ip6addrlbl_msgsize(void)
+ nla_total_size(4); /* IFAL_LABEL */
}
-static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh,
- void *arg)
+static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(in_skb->sk);
struct ifaddrlblmsg *ifal;
@@ -561,10 +556,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh,
if (!tb[IFAL_ADDRESS])
return -EINVAL;
-
addr = nla_data(tb[IFAL_ADDRESS]);
- if (!addr)
- return -EINVAL;
rcu_read_lock();
p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 6b793bfc0e10..ab5c7ad482cd 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -49,7 +49,6 @@
#include <net/udp.h>
#include <net/udplite.h>
#include <net/tcp.h>
-#include <net/ipip.h>
#include <net/protocol.h>
#include <net/inet_common.h>
#include <net/route.h>
@@ -323,7 +322,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
struct net_device *dev = NULL;
rcu_read_lock();
- if (addr_type & IPV6_ADDR_LINKLOCAL) {
+ if (__ipv6_addr_needs_scope_id(addr_type)) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
addr->sin6_scope_id) {
/* Override any existing binding, if another one
@@ -471,8 +470,8 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
sin->sin6_port = inet->inet_sport;
}
- if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin->sin6_scope_id = sk->sk_bound_dev_if;
+ sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr,
+ sk->sk_bound_dev_if);
*uaddr_len = sizeof(*sin);
return 0;
}
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index f5a54782a340..4b56cbbc7890 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -124,7 +124,7 @@ ipv4_connected:
goto out;
}
- if (addr_type&IPV6_ADDR_LINKLOCAL) {
+ if (__ipv6_addr_needs_scope_id(addr_type)) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
if (sk->sk_bound_dev_if &&
@@ -355,18 +355,19 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
sin->sin6_port = serr->port;
- sin->sin6_scope_id = 0;
if (skb->protocol == htons(ETH_P_IPV6)) {
const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset),
struct ipv6hdr, daddr);
sin->sin6_addr = ip6h->daddr;
if (np->sndflow)
sin->sin6_flowinfo = ip6_flowinfo(ip6h);
- if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin->sin6_scope_id = IP6CB(skb)->iif;
+ sin->sin6_scope_id =
+ ipv6_iface_scope_id(&sin->sin6_addr,
+ IP6CB(skb)->iif);
} else {
ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset),
&sin->sin6_addr);
+ sin->sin6_scope_id = 0;
}
}
@@ -376,18 +377,19 @@ 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_scope_id = 0;
if (skb->protocol == htons(ETH_P_IPV6)) {
sin->sin6_addr = ipv6_hdr(skb)->saddr;
if (np->rxopt.all)
ip6_datagram_recv_ctl(sk, msg, skb);
- if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin->sin6_scope_id = IP6CB(skb)->iif;
+ sin->sin6_scope_id =
+ ipv6_iface_scope_id(&sin->sin6_addr,
+ IP6CB(skb)->iif);
} else {
struct inet_sock *inet = inet_sk(sk);
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin->sin6_addr);
+ sin->sin6_scope_id = 0;
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
}
@@ -592,7 +594,9 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
sin6.sin6_addr = ipv6_hdr(skb)->daddr;
sin6.sin6_port = ports[1];
sin6.sin6_flowinfo = 0;
- sin6.sin6_scope_id = 0;
+ sin6.sin6_scope_id =
+ ipv6_iface_scope_id(&ipv6_hdr(skb)->daddr,
+ opt->iif);
put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6);
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index fff5bdd8b680..71b900c3f4ff 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -434,7 +434,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
* Source addr check
*/
- if (addr_type & IPV6_ADDR_LINKLOCAL)
+ if (__ipv6_addr_needs_scope_id(addr_type))
iif = skb->dev->ifindex;
/*
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 9bfab19ff3c0..e4311cbc8b4e 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -54,6 +54,10 @@ int inet6_csk_bind_conflict(const struct sock *sk,
if (ipv6_rcv_saddr_equal(sk, sk2))
break;
}
+ if (!relax && reuse && sk2->sk_reuse &&
+ sk2->sk_state != TCP_LISTEN &&
+ ipv6_rcv_saddr_equal(sk, sk2))
+ break;
}
}
@@ -169,10 +173,8 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
sin6->sin6_port = inet_sk(sk)->inet_dport;
/* We do not store received flowlabel for TCP */
sin6->sin6_flowinfo = 0;
- sin6->sin6_scope_id = 0;
- if (sk->sk_bound_dev_if &&
- ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin6->sin6_scope_id = sk->sk_bound_dev_if;
+ sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
+ sk->sk_bound_dev_if);
}
EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index b973ed3d06cf..46e88433ec7d 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -144,7 +144,9 @@ static void ip6_fl_gc(unsigned long dummy)
spin_lock(&ip6_fl_lock);
for (i=0; i<=FL_HASH_MASK; i++) {
- struct ip6_flowlabel *fl, **flp;
+ struct ip6_flowlabel *fl;
+ struct ip6_flowlabel __rcu **flp;
+
flp = &fl_ht[i];
while ((fl = rcu_dereference_protected(*flp,
lockdep_is_held(&ip6_fl_lock))) != NULL) {
@@ -179,7 +181,9 @@ static void __net_exit ip6_fl_purge(struct net *net)
spin_lock(&ip6_fl_lock);
for (i = 0; i <= FL_HASH_MASK; i++) {
- struct ip6_flowlabel *fl, **flp;
+ struct ip6_flowlabel *fl;
+ struct ip6_flowlabel __rcu **flp;
+
flp = &fl_ht[i];
while ((fl = rcu_dereference_protected(*flp,
lockdep_is_held(&ip6_fl_lock))) != NULL) {
@@ -506,7 +510,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
struct ipv6_fl_socklist *sfl1=NULL;
- struct ipv6_fl_socklist *sfl, **sflp;
+ struct ipv6_fl_socklist *sfl;
+ struct ipv6_fl_socklist __rcu **sflp;
struct ip6_flowlabel *fl, *fl1 = NULL;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e4efffe2522e..d3ddd8400354 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -38,6 +38,7 @@
#include <net/sock.h>
#include <net/ip.h>
+#include <net/ip_tunnels.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/addrconf.h>
@@ -110,46 +111,6 @@ static u32 HASH_ADDR(const struct in6_addr *addr)
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
-static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->multicast = dev->stats.multicast;
- tot->rx_crc_errors = dev->stats.rx_crc_errors;
- tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
- tot->rx_length_errors = dev->stats.rx_length_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->rx_errors = dev->stats.rx_errors;
-
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
-}
-
/* Given src, dst and key, find appropriate for input tunnel. */
static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
@@ -667,7 +628,6 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
struct net_device_stats *stats = &tunnel->dev->stats;
int err = -1;
u8 proto;
- int pkt_len;
struct sk_buff *new_skb;
if (dev->type == ARPHRD_ETHER)
@@ -801,23 +761,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
}
}
- nf_reset(skb);
- pkt_len = skb->len;
- err = ip6_local_out(skb);
-
- if (net_xmit_eval(err) == 0) {
- struct pcpu_tstats *tstats = this_cpu_ptr(tunnel->dev->tstats);
-
- tstats->tx_bytes += pkt_len;
- tstats->tx_packets++;
- } else {
- stats->tx_errors++;
- stats->tx_aborted_errors++;
- }
-
+ ip6tunnel_xmit(skb, dev);
if (ndst)
ip6_tnl_dst_store(tunnel, ndst);
-
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
@@ -1271,7 +1217,7 @@ static const struct net_device_ops ip6gre_netdev_ops = {
.ndo_start_xmit = ip6gre_tunnel_xmit,
.ndo_do_ioctl = ip6gre_tunnel_ioctl,
.ndo_change_mtu = ip6gre_tunnel_change_mtu,
- .ndo_get_stats64 = ip6gre_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ip6gre_dev_free(struct net_device *dev)
@@ -1520,7 +1466,7 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip6gre_tunnel_change_mtu,
- .ndo_get_stats64 = ip6gre_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ip6gre_tap_setup(struct net_device *dev)
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 8234c1dcdf72..71b766ee821d 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -92,14 +92,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
u8 *prevhdr;
int offset = 0;
- if (!(features & NETIF_F_V6_CSUM))
- features &= ~NETIF_F_SG;
-
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
+ SKB_GSO_UDP_TUNNEL |
SKB_GSO_TCPV6 |
0)))
goto out;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index fff83cbc197f..1e55866cead7 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -47,6 +47,7 @@
#include <net/icmp.h>
#include <net/ip.h>
+#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
@@ -955,7 +956,6 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
unsigned int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err = -1;
- int pkt_len;
if (!fl6->flowi6_mark)
dst = ip6_tnl_dst_check(t);
@@ -1035,19 +1035,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
ipv6h->nexthdr = proto;
ipv6h->saddr = fl6->saddr;
ipv6h->daddr = fl6->daddr;
- nf_reset(skb);
- pkt_len = skb->len;
- err = ip6_local_out(skb);
-
- if (net_xmit_eval(err) == 0) {
- struct pcpu_tstats *tstats = this_cpu_ptr(t->dev->tstats);
-
- tstats->tx_bytes += pkt_len;
- tstats->tx_packets++;
- } else {
- stats->tx_errors++;
- stats->tx_aborted_errors++;
- }
+ ip6tunnel_xmit(skb, dev);
if (ndst)
ip6_tnl_dst_store(t, ndst);
return 0;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 96bfb4e4b820..241fb8ad9fcf 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -842,9 +842,9 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
nlh->nlmsg_type = NLMSG_ERROR;
- nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+ nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
- ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT;
+ ((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT;
rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
} else
kfree_skb(skb);
@@ -1100,13 +1100,13 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
- if (__ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
+ if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) {
nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh;
} else {
nlh->nlmsg_type = NLMSG_ERROR;
- nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
+ nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
- ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE;
+ ((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE;
}
rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
} else
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 76ef4353d518..2712ab22a174 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -610,8 +610,6 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
}
}
#endif
- if (!dev->addr_len)
- send_sllao = 0;
if (send_sllao)
optlen += ndisc_opt_addr_space(dev);
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 33608c610276..938e0b7ea1bd 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -18,9 +18,8 @@
static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
{
struct ip6t_npt_tginfo *npt = par->targinfo;
- __wsum src_sum = 0, dst_sum = 0;
struct in6_addr pfx;
- unsigned int i;
+ __wsum src_sum, dst_sum;
if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
return -EINVAL;
@@ -33,12 +32,8 @@ static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6))
return -EINVAL;
- for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) {
- src_sum = csum_add(src_sum,
- (__force __wsum)npt->src_pfx.in6.s6_addr16[i]);
- dst_sum = csum_add(dst_sum,
- (__force __wsum)npt->dst_pfx.in6.s6_addr16[i]);
- }
+ src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0);
+ dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0);
npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum));
return 0;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 2b6c226f5198..97bcf2bae857 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -330,12 +330,8 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
sizeof(sin6.sin6_addr));
nf_ct_put(ct);
-
- if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin6.sin6_scope_id = sk->sk_bound_dev_if;
- else
- sin6.sin6_scope_id = 0;
-
+ sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr,
+ sk->sk_bound_dev_if);
return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 330b5e7b7df6..eedff8ccded5 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -263,7 +263,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (addr_type != IPV6_ADDR_ANY) {
struct net_device *dev = NULL;
- if (addr_type & IPV6_ADDR_LINKLOCAL) {
+ if (__ipv6_addr_needs_scope_id(addr_type)) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
addr->sin6_scope_id) {
/* Override any existing binding, if another
@@ -498,9 +498,8 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
sin6->sin6_port = 0;
sin6->sin6_addr = ipv6_hdr(skb)->saddr;
sin6->sin6_flowinfo = 0;
- sin6->sin6_scope_id = 0;
- if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin6->sin6_scope_id = IP6CB(skb)->iif;
+ sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
}
sock_recv_ts_and_drops(msg, sk, skb);
@@ -802,7 +801,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (addr_len >= sizeof(struct sockaddr_in6) &&
sin6->sin6_scope_id &&
- ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
+ __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
fl6.flowi6_oif = sin6->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 196ab9347ad1..e6e44cef8db2 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -58,6 +58,7 @@
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/inet_frag.h>
+#include <net/inet_ecn.h>
struct ip6frag_skb_cb
{
@@ -67,6 +68,10 @@ struct ip6frag_skb_cb
#define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb))
+static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
+{
+ return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
+}
static struct inet_frags ip6_frags;
@@ -119,6 +124,7 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a)
fq->user = arg->user;
fq->saddr = *arg->src;
fq->daddr = *arg->dst;
+ fq->ecn = arg->ecn;
}
EXPORT_SYMBOL(ip6_frag_init);
@@ -173,7 +179,8 @@ static void ip6_frag_expire(unsigned long data)
}
static __inline__ struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6_addr *dst)
+fq_find(struct net *net, __be32 id, const struct in6_addr *src,
+ const struct in6_addr *dst, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -183,6 +190,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6
arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
+ arg.ecn = ecn;
read_lock(&ip6_frags.lock);
hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
@@ -202,6 +210,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct net_device *dev;
int offset, end;
struct net *net = dev_net(skb_dst(skb)->dev);
+ u8 ecn;
if (fq->q.last_in & INET_FRAG_COMPLETE)
goto err;
@@ -219,6 +228,8 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
return -1;
}
+ ecn = ip6_frag_ecn(ipv6_hdr(skb));
+
if (skb->ip_summed == CHECKSUM_COMPLETE) {
const unsigned char *nh = skb_network_header(skb);
skb->csum = csum_sub(skb->csum,
@@ -319,6 +330,7 @@ found:
}
fq->q.stamp = skb->tstamp;
fq->q.meat += skb->len;
+ fq->ecn |= ecn;
add_frag_mem_limit(&fq->q, skb->truesize);
/* The first fragment.
@@ -362,9 +374,14 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
int payload_len;
unsigned int nhoff;
int sum_truesize;
+ u8 ecn;
inet_frag_kill(&fq->q, &ip6_frags);
+ ecn = ip_frag_ecn_table[fq->ecn];
+ if (unlikely(ecn == 0xff))
+ goto out_fail;
+
/* Make the one we just received the head. */
if (prev) {
head = prev->next;
@@ -463,6 +480,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
head->dev = dev;
head->tstamp = fq->q.stamp;
ipv6_hdr(head)->payload_len = htons(payload_len);
+ ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
IP6CB(head)->nhoff = nhoff;
/* Yes, and fold redundant checksum back. 8) */
@@ -526,7 +544,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS, evicted);
- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr);
+ fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
+ ip6_frag_ecn(hdr));
if (fq != NULL) {
int ret;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e5fe0041adfa..ad0aa6b0b86a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2355,7 +2355,7 @@ beginning:
return last_err;
}
-static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct fib6_config cfg;
int err;
@@ -2370,7 +2370,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a
return ip6_route_del(&cfg);
}
-static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh)
{
struct fib6_config cfg;
int err;
@@ -2562,7 +2562,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
prefix, 0, NLM_F_MULTI);
}
-static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
+static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
{
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[RTA_MAX+1];
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 02f96dcbcf02..335363478bbf 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -49,7 +49,7 @@
#include <net/ip.h>
#include <net/udp.h>
#include <net/icmp.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
@@ -87,41 +87,6 @@ struct sit_net {
struct net_device *fb_tunnel_dev;
};
-static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
- unsigned int start;
-
- do {
- start = u64_stats_fetch_begin_bh(&tstats->syncp);
- rx_packets = tstats->rx_packets;
- tx_packets = tstats->tx_packets;
- rx_bytes = tstats->rx_bytes;
- tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
- tot->rx_packets += rx_packets;
- tot->tx_packets += tx_packets;
- tot->rx_bytes += rx_bytes;
- tot->tx_bytes += tx_bytes;
- }
-
- tot->rx_errors = dev->stats.rx_errors;
- tot->rx_frame_errors = dev->stats.rx_frame_errors;
- tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
- tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
- tot->tx_dropped = dev->stats.tx_dropped;
- tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
- tot->tx_errors = dev->stats.tx_errors;
-
- return tot;
-}
-
/*
* Must be invoked with rcu_read_lock
*/
@@ -899,6 +864,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
+ skb->ip_summed = CHECKSUM_NONE;
+ ip_select_ident(iph, skb_dst(skb), NULL);
iptunnel_xmit(skb, dev);
return NETDEV_TX_OK;
@@ -1200,7 +1167,7 @@ static const struct net_device_ops ipip6_netdev_ops = {
.ndo_start_xmit = ipip6_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
.ndo_change_mtu = ipip6_tunnel_change_mtu,
- .ndo_get_stats64= ipip6_get_stats64,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
static void ipip6_dev_free(struct net_device *dev)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 8a0848b60b35..d5dda20bd717 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -149,7 +149,6 @@ static inline int cookie_check(const struct sk_buff *skb, __u32 cookie)
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
struct tcp_options_received tcp_opt;
- const u8 *hash_location;
struct inet_request_sock *ireq;
struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
@@ -177,7 +176,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tcp_opt, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
goto out;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f6d629fd6aee..1033d2b1d81e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -461,7 +461,6 @@ out:
static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
struct flowi6 *fl6,
struct request_sock *req,
- struct request_values *rvp,
u16 queue_mapping)
{
struct inet6_request_sock *treq = inet6_rsk(req);
@@ -473,7 +472,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
goto done;
- skb = tcp_make_synack(sk, dst, req, rvp, NULL);
+ skb = tcp_make_synack(sk, dst, req, NULL);
if (skb) {
__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
@@ -488,13 +487,12 @@ done:
return err;
}
-static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
- struct request_values *rvp)
+static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
{
struct flowi6 fl6;
int res;
- res = tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0);
+ res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0);
if (!res)
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
return res;
@@ -947,9 +945,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
*/
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct request_sock *req;
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -987,50 +983,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
-
- if (tmp_opt.cookie_plus > 0 &&
- tmp_opt.saw_tstamp &&
- !tp->rx_opt.cookie_out_never &&
- (sysctl_tcp_cookie_size > 0 ||
- (tp->cookie_values != NULL &&
- tp->cookie_values->cookie_desired > 0))) {
- u8 *c;
- u32 *d;
- u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
- int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
-
- if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
- goto drop_and_free;
-
- /* Secret recipe starts with IP addresses */
- d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0];
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0];
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
-
- /* plus variable length Initiator Cookie */
- c = (u8 *)mess;
- while (l-- > 0)
- *c++ ^= *hash_location++;
-
- want_cookie = false; /* not our kind of cookie */
- tmp_ext.cookie_out_never = 0; /* false */
- tmp_ext.cookie_plus = tmp_opt.cookie_plus;
- } else if (!tp->rx_opt.cookie_in_always) {
- /* redundant indications, but ensure initialization. */
- tmp_ext.cookie_out_never = 1; /* true */
- tmp_ext.cookie_plus = 0;
- } else {
- goto drop_and_free;
- }
- tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1108,7 +1061,6 @@ have_isn:
goto drop_and_release;
if (tcp_v6_send_synack(sk, dst, &fl6, req,
- (struct request_values *)&tmp_ext,
skb_get_queue_mapping(skb)) ||
want_cookie)
goto drop_and_free;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d8e5e852fc7a..da6019b63730 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -450,15 +450,16 @@ try_again:
sin6->sin6_family = AF_INET6;
sin6->sin6_port = udp_hdr(skb)->source;
sin6->sin6_flowinfo = 0;
- sin6->sin6_scope_id = 0;
- if (is_udp4)
+ if (is_udp4) {
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin6->sin6_addr);
- else {
+ sin6->sin6_scope_id = 0;
+ } else {
sin6->sin6_addr = ipv6_hdr(skb)->saddr;
- if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin6->sin6_scope_id = IP6CB(skb)->iif;
+ sin6->sin6_scope_id =
+ ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
}
}
@@ -1118,7 +1119,7 @@ do_udp_sendmsg:
if (addr_len >= sizeof(struct sockaddr_in6) &&
sin6->sin6_scope_id &&
- ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
+ __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
fl6.flowi6_oif = sin6->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index cf05cf073c51..3bb3a891a424 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -21,6 +21,10 @@ static int udp6_ufo_send_check(struct sk_buff *skb)
const struct ipv6hdr *ipv6h;
struct udphdr *uh;
+ /* UDP Tunnel offload on ipv6 is not yet supported. */
+ if (skb->encapsulation)
+ return -EINVAL;
+
if (!pskb_may_pull(skb, sizeof(*uh)))
return -EINVAL;
@@ -56,7 +60,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
/* Packet is from an untrusted source, reset gso_segs. */
int type = skb_shinfo(skb)->gso_type;
- if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
+ if (unlikely(type & ~(SKB_GSO_UDP |
+ SKB_GSO_DODGY |
+ SKB_GSO_UDP_TUNNEL |
SKB_GSO_GRE) ||
!(type & (SKB_GSO_UDP))))
goto out;
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a7d11ffe4284..7dfb9ed93698 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1461,7 +1461,8 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
return iucv_accept_poll(sk);
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR;
+ mask |= POLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 8aecf5df6656..6984c3a353cd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1777,7 +1777,7 @@ int l2tp_session_delete(struct l2tp_session *session)
if (session->session_close != NULL)
(*session->session_close)(session);
if (session->deref)
- (*session->ref)(session);
+ (*session->deref)(session);
l2tp_session_dec_refcount(session);
return 0;
}
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fb306814576a..1d1ddabd89ca 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -254,7 +254,7 @@ static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev,
goto out_unlock;
}
- __ieee80211_key_free(key);
+ __ieee80211_key_free(key, true);
ret = 0;
out_unlock:
@@ -1035,9 +1035,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
sta_info_flush_defer(vlan);
sta_info_flush_defer(sdata);
rcu_barrier();
- list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) {
sta_info_flush_cleanup(vlan);
+ ieee80211_free_keys(vlan);
+ }
sta_info_flush_cleanup(sdata);
+ ieee80211_free_keys(sdata);
sdata->vif.bss_conf.enable_beacon = false;
clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state);
@@ -1177,6 +1180,18 @@ static int sta_apply_parameters(struct ieee80211_local *local,
mask |= BIT(NL80211_STA_FLAG_ASSOCIATED);
if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED))
set |= BIT(NL80211_STA_FLAG_ASSOCIATED);
+ } else if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
+ /*
+ * TDLS -- everything follows authorized, but
+ * only becoming authorized is possible, not
+ * going back
+ */
+ if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) {
+ set |= BIT(NL80211_STA_FLAG_AUTHENTICATED) |
+ BIT(NL80211_STA_FLAG_ASSOCIATED);
+ mask |= BIT(NL80211_STA_FLAG_AUTHENTICATED) |
+ BIT(NL80211_STA_FLAG_ASSOCIATED);
+ }
}
ret = sta_apply_auth_flags(local, sta, mask, set);
@@ -1261,7 +1276,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
if (ieee80211_vif_is_mesh(&sdata->vif)) {
#ifdef CONFIG_MAC80211_MESH
u32 changed = 0;
- if (sdata->u.mesh.security & IEEE80211_MESH_SEC_SECURED) {
+
+ if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) {
switch (params->plink_state) {
case NL80211_PLINK_ESTAB:
if (sta->plink_state != NL80211_PLINK_ESTAB)
@@ -1292,15 +1308,18 @@ static int sta_apply_parameters(struct ieee80211_local *local,
/* nothing */
break;
}
- } else {
- switch (params->plink_action) {
- case PLINK_ACTION_OPEN:
- changed |= mesh_plink_open(sta);
- break;
- case PLINK_ACTION_BLOCK:
- changed |= mesh_plink_block(sta);
- break;
- }
+ }
+
+ switch (params->plink_action) {
+ case NL80211_PLINK_ACTION_NO_ACTION:
+ /* nothing */
+ break;
+ case NL80211_PLINK_ACTION_OPEN:
+ changed |= mesh_plink_open(sta);
+ break;
+ case NL80211_PLINK_ACTION_BLOCK:
+ changed |= mesh_plink_block(sta);
+ break;
}
if (params->local_pm)
@@ -1346,8 +1365,10 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
* defaults -- if userspace wants something else we'll
* change it accordingly in sta_apply_parameters()
*/
- sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
- sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
+ if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) {
+ sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
+ sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
+ }
err = sta_apply_parameters(local, sta, params);
if (err) {
@@ -1356,8 +1377,8 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
}
/*
- * for TDLS, rate control should be initialized only when supported
- * rates are known.
+ * for TDLS, rate control should be initialized only when
+ * rates are known and station is marked authorized
*/
if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER))
rate_control_rate_init(sta);
@@ -1394,50 +1415,67 @@ static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
}
static int ieee80211_change_station(struct wiphy *wiphy,
- struct net_device *dev,
- u8 *mac,
+ struct net_device *dev, u8 *mac,
struct station_parameters *params)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = wiphy_priv(wiphy);
struct sta_info *sta;
struct ieee80211_sub_if_data *vlansdata;
+ enum cfg80211_station_type statype;
int err;
mutex_lock(&local->sta_mtx);
sta = sta_info_get_bss(sdata, mac);
if (!sta) {
- mutex_unlock(&local->sta_mtx);
- return -ENOENT;
+ err = -ENOENT;
+ goto out_err;
}
- /* in station mode, some updates are only valid with TDLS */
- if (sdata->vif.type == NL80211_IFTYPE_STATION &&
- (params->supported_rates || params->ht_capa || params->vht_capa ||
- params->sta_modify_mask ||
- (params->sta_flags_mask & BIT(NL80211_STA_FLAG_WME))) &&
- !test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
- mutex_unlock(&local->sta_mtx);
- return -EINVAL;
+ switch (sdata->vif.type) {
+ case NL80211_IFTYPE_MESH_POINT:
+ if (sdata->u.mesh.user_mpm)
+ statype = CFG80211_STA_MESH_PEER_USER;
+ else
+ statype = CFG80211_STA_MESH_PEER_KERNEL;
+ break;
+ case NL80211_IFTYPE_ADHOC:
+ statype = CFG80211_STA_IBSS;
+ break;
+ case NL80211_IFTYPE_STATION:
+ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
+ statype = CFG80211_STA_AP_STA;
+ break;
+ }
+ if (test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+ statype = CFG80211_STA_TDLS_PEER_ACTIVE;
+ else
+ statype = CFG80211_STA_TDLS_PEER_SETUP;
+ break;
+ case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_AP_VLAN:
+ statype = CFG80211_STA_AP_CLIENT;
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ goto out_err;
}
+ err = cfg80211_check_station_change(wiphy, params, statype);
+ if (err)
+ goto out_err;
+
if (params->vlan && params->vlan != sta->sdata->dev) {
bool prev_4addr = false;
bool new_4addr = false;
vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan);
- if (vlansdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
- vlansdata->vif.type != NL80211_IFTYPE_AP) {
- mutex_unlock(&local->sta_mtx);
- return -EINVAL;
- }
-
if (params->vlan->ieee80211_ptr->use_4addr) {
if (vlansdata->u.vlan.sta) {
- mutex_unlock(&local->sta_mtx);
- return -EBUSY;
+ err = -EBUSY;
+ goto out_err;
}
rcu_assign_pointer(vlansdata->u.vlan.sta, sta);
@@ -1464,12 +1502,12 @@ static int ieee80211_change_station(struct wiphy *wiphy,
}
err = sta_apply_parameters(local, sta, params);
- if (err) {
- mutex_unlock(&local->sta_mtx);
- return err;
- }
+ if (err)
+ goto out_err;
- if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && params->supported_rates)
+ /* When peer becomes authorized, init rate control as well */
+ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
+ test_sta_flag(sta, WLAN_STA_AUTHORIZED))
rate_control_rate_init(sta);
mutex_unlock(&local->sta_mtx);
@@ -1479,7 +1517,11 @@ static int ieee80211_change_station(struct wiphy *wiphy,
ieee80211_recalc_ps(local, -1);
ieee80211_recalc_ps_vif(sdata);
}
+
return 0;
+out_err:
+ mutex_unlock(&local->sta_mtx);
+ return err;
}
#ifdef CONFIG_MAC80211_MESH
@@ -1687,6 +1729,7 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh,
ifmsh->mesh_sp_id = setup->sync_method;
ifmsh->mesh_pp_id = setup->path_sel_proto;
ifmsh->mesh_pm_id = setup->path_metric;
+ ifmsh->user_mpm = setup->user_mpm;
ifmsh->security = IEEE80211_MESH_SEC_NONE;
if (setup->is_authenticated)
ifmsh->security |= IEEE80211_MESH_SEC_AUTHED;
@@ -1730,8 +1773,11 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy,
conf->dot11MeshTTL = nconf->dot11MeshTTL;
if (_chg_mesh_attr(NL80211_MESHCONF_ELEMENT_TTL, mask))
conf->element_ttl = nconf->element_ttl;
- if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask))
+ if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) {
+ if (ifmsh->user_mpm)
+ return -EBUSY;
conf->auto_open_plinks = nconf->auto_open_plinks;
+ }
if (_chg_mesh_attr(NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, mask))
conf->dot11MeshNbrOffsetMaxNeighbor =
nconf->dot11MeshNbrOffsetMaxNeighbor;
@@ -2371,7 +2417,8 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
struct ieee80211_channel *channel,
unsigned int duration, u64 *cookie,
- struct sk_buff *txskb)
+ struct sk_buff *txskb,
+ enum ieee80211_roc_type type)
{
struct ieee80211_roc_work *roc, *tmp;
bool queued = false;
@@ -2390,6 +2437,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
roc->duration = duration;
roc->req_duration = duration;
roc->frame = txskb;
+ roc->type = type;
roc->mgmt_tx_cookie = (unsigned long)txskb;
roc->sdata = sdata;
INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work);
@@ -2420,7 +2468,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
if (!duration)
duration = 10;
- ret = drv_remain_on_channel(local, sdata, channel, duration);
+ ret = drv_remain_on_channel(local, sdata, channel, duration, type);
if (ret) {
kfree(roc);
return ret;
@@ -2439,10 +2487,13 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
*
* If it hasn't started yet, just increase the duration
* and add the new one to the list of dependents.
+ * If the type of the new ROC has higher priority, modify the
+ * type of the previous one to match that of the new one.
*/
if (!tmp->started) {
list_add_tail(&roc->list, &tmp->dependents);
tmp->duration = max(tmp->duration, roc->duration);
+ tmp->type = max(tmp->type, roc->type);
queued = true;
break;
}
@@ -2454,16 +2505,18 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
/*
* In the offloaded ROC case, if it hasn't begun, add
* this new one to the dependent list to be handled
- * when the the master one begins. If it has begun,
+ * when the master one begins. If it has begun,
* check that there's still a minimum time left and
* if so, start this one, transmitting the frame, but
- * add it to the list directly after this one with a
+ * add it to the list directly after this one with
* a reduced time so we'll ask the driver to execute
* it right after finishing the previous one, in the
* hope that it'll also be executed right afterwards,
* effectively extending the old one.
* If there's no minimum time left, just add it to the
* normal list.
+ * TODO: the ROC type is ignored here, assuming that it
+ * is better to immediately use the current ROC.
*/
if (!tmp->hw_begun) {
list_add_tail(&roc->list, &tmp->dependents);
@@ -2557,7 +2610,8 @@ static int ieee80211_remain_on_channel(struct wiphy *wiphy,
mutex_lock(&local->mtx);
ret = ieee80211_start_roc_work(local, sdata, chan,
- duration, cookie, NULL);
+ duration, cookie, NULL,
+ IEEE80211_ROC_TYPE_NORMAL);
mutex_unlock(&local->mtx);
return ret;
@@ -2790,7 +2844,8 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
/* This will handle all kinds of coalescing and immediate TX */
ret = ieee80211_start_roc_work(local, sdata, chan,
- wait, cookie, skb);
+ wait, cookie, skb,
+ IEEE80211_ROC_TYPE_MGMT_TX);
if (ret)
kfree_skb(skb);
out_unlock:
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index c7591f73dbc3..4f841fe559df 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -325,6 +325,36 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf,
}
STA_OPS(ht_capa);
+static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ char buf[128], *p = buf;
+ struct sta_info *sta = file->private_data;
+ struct ieee80211_sta_vht_cap *vhtc = &sta->sta.vht_cap;
+
+ p += scnprintf(p, sizeof(buf) + buf - p, "VHT %ssupported\n",
+ vhtc->vht_supported ? "" : "not ");
+ if (vhtc->vht_supported) {
+ p += scnprintf(p, sizeof(buf)+buf-p, "cap: %#.8x\n", vhtc->cap);
+
+ p += scnprintf(p, sizeof(buf)+buf-p, "RX MCS: %.4x\n",
+ le16_to_cpu(vhtc->vht_mcs.rx_mcs_map));
+ if (vhtc->vht_mcs.rx_highest)
+ p += scnprintf(p, sizeof(buf)+buf-p,
+ "MCS RX highest: %d Mbps\n",
+ le16_to_cpu(vhtc->vht_mcs.rx_highest));
+ p += scnprintf(p, sizeof(buf)+buf-p, "TX MCS: %.4x\n",
+ le16_to_cpu(vhtc->vht_mcs.tx_mcs_map));
+ if (vhtc->vht_mcs.tx_highest)
+ p += scnprintf(p, sizeof(buf)+buf-p,
+ "MCS TX highest: %d Mbps\n",
+ le16_to_cpu(vhtc->vht_mcs.tx_highest));
+ }
+
+ return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
+}
+STA_OPS(vht_capa);
+
static ssize_t sta_current_tx_rate_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
{
@@ -405,6 +435,7 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta)
DEBUGFS_ADD(dev);
DEBUGFS_ADD(last_signal);
DEBUGFS_ADD(ht_capa);
+ DEBUGFS_ADD(vht_capa);
DEBUGFS_ADD(last_ack_signal);
DEBUGFS_ADD(current_tx_rate);
DEBUGFS_ADD(last_rx_rate);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index ee56d0779d8b..832acea4a5cb 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -787,15 +787,16 @@ static inline int drv_get_antenna(struct ieee80211_local *local,
static inline int drv_remain_on_channel(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
struct ieee80211_channel *chan,
- unsigned int duration)
+ unsigned int duration,
+ enum ieee80211_roc_type type)
{
int ret;
might_sleep();
- trace_drv_remain_on_channel(local, sdata, chan, duration);
+ trace_drv_remain_on_channel(local, sdata, chan, duration, type);
ret = local->ops->remain_on_channel(&local->hw, &sdata->vif,
- chan, duration);
+ chan, duration, type);
trace_drv_return_int(local, ret);
return ret;
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 0db25d4bb223..af8cee06e4f3 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -40,13 +40,6 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
if (!ht_cap->ht_supported)
return;
- if (sdata->vif.type != NL80211_IFTYPE_STATION) {
- /* AP interfaces call this code when adding new stations,
- * so just silently ignore non station interfaces.
- */
- return;
- }
-
/* NOTE: If you add more over-rides here, update register_hw
* ht_capa_mod_msk logic in main.c as well.
* And, if this method can ever change ht_cap.ht_supported, fix
@@ -97,7 +90,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
const struct ieee80211_ht_cap *ht_cap_ie,
struct sta_info *sta)
{
- struct ieee80211_sta_ht_cap ht_cap;
+ struct ieee80211_sta_ht_cap ht_cap, own_cap;
u8 ampdu_info, tx_mcs_set_cap;
int i, max_tx_streams;
bool changed;
@@ -111,6 +104,18 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
ht_cap.ht_supported = true;
+ own_cap = sband->ht_cap;
+
+ /*
+ * If user has specified capability over-rides, take care
+ * of that if the station we're setting up is the AP that
+ * we advertised a restricted capability set to. Override
+ * our own capabilities and then use those below.
+ */
+ if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+ !test_sta_flag(sta, WLAN_STA_TDLS_PEER))
+ ieee80211_apply_htcap_overrides(sdata, &own_cap);
+
/*
* The bits listed in this expression should be
* the same for the peer and us, if the station
@@ -118,21 +123,20 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
* we mask them out.
*/
ht_cap.cap = le16_to_cpu(ht_cap_ie->cap_info) &
- (sband->ht_cap.cap |
- ~(IEEE80211_HT_CAP_LDPC_CODING |
- IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
- IEEE80211_HT_CAP_GRN_FLD |
- IEEE80211_HT_CAP_SGI_20 |
- IEEE80211_HT_CAP_SGI_40 |
- IEEE80211_HT_CAP_DSSSCCK40));
+ (own_cap.cap | ~(IEEE80211_HT_CAP_LDPC_CODING |
+ IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+ IEEE80211_HT_CAP_GRN_FLD |
+ IEEE80211_HT_CAP_SGI_20 |
+ IEEE80211_HT_CAP_SGI_40 |
+ IEEE80211_HT_CAP_DSSSCCK40));
/*
* The STBC bits are asymmetric -- if we don't have
* TX then mask out the peer's RX and vice versa.
*/
- if (!(sband->ht_cap.cap & IEEE80211_HT_CAP_TX_STBC))
+ if (!(own_cap.cap & IEEE80211_HT_CAP_TX_STBC))
ht_cap.cap &= ~IEEE80211_HT_CAP_RX_STBC;
- if (!(sband->ht_cap.cap & IEEE80211_HT_CAP_RX_STBC))
+ if (!(own_cap.cap & IEEE80211_HT_CAP_RX_STBC))
ht_cap.cap &= ~IEEE80211_HT_CAP_TX_STBC;
ampdu_info = ht_cap_ie->ampdu_params_info;
@@ -142,7 +146,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
(ampdu_info & IEEE80211_HT_AMPDU_PARM_DENSITY) >> 2;
/* own MCS TX capabilities */
- tx_mcs_set_cap = sband->ht_cap.mcs.tx_params;
+ tx_mcs_set_cap = own_cap.mcs.tx_params;
/* Copy peer MCS TX capabilities, the driver might need them. */
ht_cap.mcs.tx_params = ht_cap_ie->mcs.tx_params;
@@ -168,26 +172,20 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata,
*/
for (i = 0; i < max_tx_streams; i++)
ht_cap.mcs.rx_mask[i] =
- sband->ht_cap.mcs.rx_mask[i] & ht_cap_ie->mcs.rx_mask[i];
+ own_cap.mcs.rx_mask[i] & ht_cap_ie->mcs.rx_mask[i];
if (tx_mcs_set_cap & IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION)
for (i = IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE;
i < IEEE80211_HT_MCS_MASK_LEN; i++)
ht_cap.mcs.rx_mask[i] =
- sband->ht_cap.mcs.rx_mask[i] &
+ own_cap.mcs.rx_mask[i] &
ht_cap_ie->mcs.rx_mask[i];
/* handle MCS rate 32 too */
- if (sband->ht_cap.mcs.rx_mask[32/8] & ht_cap_ie->mcs.rx_mask[32/8] & 1)
+ if (own_cap.mcs.rx_mask[32/8] & ht_cap_ie->mcs.rx_mask[32/8] & 1)
ht_cap.mcs.rx_mask[32/8] |= 1;
apply:
- /*
- * If user has specified capability over-rides, take care
- * of that here.
- */
- ieee80211_apply_htcap_overrides(sdata, &ht_cap);
-
changed = memcmp(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap));
memcpy(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap));
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 40b71dfcc79d..539d4a11b47b 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -985,36 +985,9 @@ static void ieee80211_ibss_timer(unsigned long data)
{
struct ieee80211_sub_if_data *sdata =
(struct ieee80211_sub_if_data *) data;
- struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
- struct ieee80211_local *local = sdata->local;
-
- if (local->quiescing) {
- ifibss->timer_running = true;
- return;
- }
-
- ieee80211_queue_work(&local->hw, &sdata->work);
-}
-
-#ifdef CONFIG_PM
-void ieee80211_ibss_quiesce(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
- if (del_timer_sync(&ifibss->timer))
- ifibss->timer_running = true;
-}
-
-void ieee80211_ibss_restart(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
-
- if (ifibss->timer_running) {
- add_timer(&ifibss->timer);
- ifibss->timer_running = false;
- }
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
}
-#endif
void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata)
{
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 388580a1bada..f4433f081e77 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -315,6 +315,7 @@ struct ieee80211_roc_work {
u32 duration, req_duration;
struct sk_buff *frame;
u64 cookie, mgmt_tx_cookie;
+ enum ieee80211_roc_type type;
};
/* flags used in struct ieee80211_if_managed.flags */
@@ -400,7 +401,6 @@ struct ieee80211_if_managed {
u16 aid;
- unsigned long timers_running; /* used for quiesce/restart */
bool powersave; /* powersave requested for this iface */
bool broken_ap; /* AP is broken -- turn off powersave */
u8 dtim_period;
@@ -479,6 +479,8 @@ struct ieee80211_if_managed {
struct ieee80211_ht_cap ht_capa; /* configured ht-cap over-rides */
struct ieee80211_ht_cap ht_capa_mask; /* Valid parts of ht_capa */
+ struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */
+ struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */
};
struct ieee80211_if_ibss {
@@ -490,8 +492,6 @@ struct ieee80211_if_ibss {
u32 basic_rates;
- bool timer_running;
-
bool fixed_bssid;
bool fixed_channel;
bool privacy;
@@ -543,8 +543,6 @@ struct ieee80211_if_mesh {
struct timer_list mesh_path_timer;
struct timer_list mesh_path_root_timer;
- unsigned long timers_running;
-
unsigned long wrkq_flags;
u8 mesh_id[IEEE80211_MAX_MESH_ID_LEN];
@@ -590,6 +588,7 @@ struct ieee80211_if_mesh {
IEEE80211_MESH_SEC_AUTHED = 0x1,
IEEE80211_MESH_SEC_SECURED = 0x2,
} security;
+ bool user_mpm;
/* Extensible Synchronization Framework */
const struct ieee80211_mesh_sync_ops *sync_ops;
s64 sync_offset_clockdrift_max;
@@ -682,6 +681,8 @@ struct ieee80211_sub_if_data {
/* count for keys needing tailroom space allocation */
int crypto_tx_tailroom_needed_cnt;
+ int crypto_tx_tailroom_pending_dec;
+ struct delayed_work dec_tailroom_needed_wk;
struct net_device *dev;
struct ieee80211_local *local;
@@ -765,10 +766,6 @@ struct ieee80211_sub_if_data {
} debugfs;
#endif
-#ifdef CONFIG_PM
- struct ieee80211_bss_conf suspend_bss_conf;
-#endif
-
/* must be last, dynamically sized area in this! */
struct ieee80211_vif vif;
};
@@ -1136,11 +1133,6 @@ struct ieee80211_local {
struct ieee80211_sub_if_data __rcu *p2p_sdata;
- /* dummy netdev for use w/ NAPI */
- struct net_device napi_dev;
-
- struct napi_struct napi;
-
/* virtual monitor interface */
struct ieee80211_sub_if_data __rcu *monitor_sdata;
struct cfg80211_chan_def monitor_chandef;
@@ -1283,8 +1275,6 @@ void
ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
const struct ieee80211_channel_sw_ie *sw_elem,
struct ieee80211_bss *bss, u64 timestamp);
-void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata);
-void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata);
void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
@@ -1302,8 +1292,6 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata,
int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
struct cfg80211_ibss_params *params);
int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata);
-void ieee80211_ibss_quiesce(struct ieee80211_sub_if_data *sdata);
-void ieee80211_ibss_restart(struct ieee80211_sub_if_data *sdata);
void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata);
void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
@@ -1441,6 +1429,8 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta);
void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, u8 opmode,
enum ieee80211_band band, bool nss_only);
+void ieee80211_apply_vhtcap_overrides(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_sta_vht_cap *vht_cap);
/* Spectrum management */
void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 3bfe2612c8c2..7530c60fe502 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -488,8 +488,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
res = drv_start(local);
if (res)
goto err_del_bss;
- if (local->ops->napi_poll)
- napi_enable(&local->napi);
/* we're brought up, everything changes */
hw_reconf_flags = ~0;
ieee80211_led_radio(local, true);
@@ -841,14 +839,16 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
rcu_barrier();
sta_info_flush_cleanup(sdata);
- skb_queue_purge(&sdata->skb_queue);
-
/*
* Free all remaining keys, there shouldn't be any,
- * except maybe group keys in AP more or WDS?
+ * except maybe in WDS mode?
*/
ieee80211_free_keys(sdata);
+ /* fall through */
+ case NL80211_IFTYPE_AP:
+ skb_queue_purge(&sdata->skb_queue);
+
drv_remove_interface_debugfs(local, sdata);
if (going_down)
@@ -860,8 +860,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
ieee80211_recalc_ps(local, -1);
if (local->open_count == 0) {
- if (local->ops->napi_poll)
- napi_disable(&local->napi);
ieee80211_clear_tx_pending(local);
ieee80211_stop_device(local);
@@ -1550,6 +1548,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
INIT_WORK(&sdata->cleanup_stations_wk, ieee80211_cleanup_sdata_stas_wk);
INIT_DELAYED_WORK(&sdata->dfs_cac_timer_work,
ieee80211_dfs_cac_timer_work);
+ INIT_DELAYED_WORK(&sdata->dec_tailroom_needed_wk,
+ ieee80211_delayed_tailroom_dec);
for (i = 0; i < IEEE80211_NUM_BANDS; i++) {
struct ieee80211_supported_band *sband;
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index ef252eb58c36..99e9f6ae6a54 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -397,7 +397,8 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
return key;
}
-static void __ieee80211_key_destroy(struct ieee80211_key *key)
+static void __ieee80211_key_destroy(struct ieee80211_key *key,
+ bool delay_tailroom)
{
if (!key)
return;
@@ -416,8 +417,18 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key)
if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC)
ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm);
if (key->local) {
+ struct ieee80211_sub_if_data *sdata = key->sdata;
+
ieee80211_debugfs_key_remove(key);
- key->sdata->crypto_tx_tailroom_needed_cnt--;
+
+ if (delay_tailroom) {
+ /* see ieee80211_delayed_tailroom_dec */
+ sdata->crypto_tx_tailroom_pending_dec++;
+ schedule_delayed_work(&sdata->dec_tailroom_needed_wk,
+ HZ/2);
+ } else {
+ sdata->crypto_tx_tailroom_needed_cnt--;
+ }
}
kfree(key);
@@ -440,32 +451,6 @@ int ieee80211_key_link(struct ieee80211_key *key,
key->sdata = sdata;
key->sta = sta;
- if (sta) {
- /*
- * some hardware cannot handle TKIP with QoS, so
- * we indicate whether QoS could be in use.
- */
- if (test_sta_flag(sta, WLAN_STA_WME))
- key->conf.flags |= IEEE80211_KEY_FLAG_WMM_STA;
- } else {
- if (sdata->vif.type == NL80211_IFTYPE_STATION) {
- struct sta_info *ap;
-
- /*
- * We're getting a sta pointer in, so must be under
- * appropriate locking for sta_info_get().
- */
-
- /* same here, the AP could be using QoS */
- ap = sta_info_get(key->sdata, key->sdata->u.mgd.bssid);
- if (ap) {
- if (test_sta_flag(ap, WLAN_STA_WME))
- key->conf.flags |=
- IEEE80211_KEY_FLAG_WMM_STA;
- }
- }
- }
-
mutex_lock(&sdata->local->key_mtx);
if (sta && pairwise)
@@ -478,7 +463,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
increment_tailroom_need_count(sdata);
__ieee80211_key_replace(sdata, sta, pairwise, old_key, key);
- __ieee80211_key_destroy(old_key);
+ __ieee80211_key_destroy(old_key, true);
ieee80211_debugfs_key_add(key);
@@ -489,7 +474,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
return ret;
}
-void __ieee80211_key_free(struct ieee80211_key *key)
+void __ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom)
{
if (!key)
return;
@@ -501,14 +486,14 @@ void __ieee80211_key_free(struct ieee80211_key *key)
__ieee80211_key_replace(key->sdata, key->sta,
key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE,
key, NULL);
- __ieee80211_key_destroy(key);
+ __ieee80211_key_destroy(key, delay_tailroom);
}
void ieee80211_key_free(struct ieee80211_local *local,
struct ieee80211_key *key)
{
mutex_lock(&local->key_mtx);
- __ieee80211_key_free(key);
+ __ieee80211_key_free(key, true);
mutex_unlock(&local->key_mtx);
}
@@ -566,36 +551,60 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw,
}
EXPORT_SYMBOL(ieee80211_iter_keys);
-void ieee80211_disable_keys(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_key *key;
-
- ASSERT_RTNL();
-
- mutex_lock(&sdata->local->key_mtx);
-
- list_for_each_entry(key, &sdata->key_list, list)
- ieee80211_key_disable_hw_accel(key);
-
- mutex_unlock(&sdata->local->key_mtx);
-}
-
void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_key *key, *tmp;
+ cancel_delayed_work_sync(&sdata->dec_tailroom_needed_wk);
+
mutex_lock(&sdata->local->key_mtx);
+ sdata->crypto_tx_tailroom_needed_cnt -=
+ sdata->crypto_tx_tailroom_pending_dec;
+ sdata->crypto_tx_tailroom_pending_dec = 0;
+
ieee80211_debugfs_key_remove_mgmt_default(sdata);
list_for_each_entry_safe(key, tmp, &sdata->key_list, list)
- __ieee80211_key_free(key);
+ __ieee80211_key_free(key, false);
ieee80211_debugfs_key_update_default(sdata);
+ WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
+ sdata->crypto_tx_tailroom_pending_dec);
+
mutex_unlock(&sdata->local->key_mtx);
}
+void ieee80211_delayed_tailroom_dec(struct work_struct *wk)
+{
+ struct ieee80211_sub_if_data *sdata;
+
+ sdata = container_of(wk, struct ieee80211_sub_if_data,
+ dec_tailroom_needed_wk.work);
+
+ /*
+ * The reason for the delayed tailroom needed decrementing is to
+ * make roaming faster: during roaming, all keys are first deleted
+ * and then new keys are installed. The first new key causes the
+ * crypto_tx_tailroom_needed_cnt to go from 0 to 1, which invokes
+ * the cost of synchronize_net() (which can be slow). Avoid this
+ * by deferring the crypto_tx_tailroom_needed_cnt decrementing on
+ * key removal for a while, so if we roam the value is larger than
+ * zero and no 0->1 transition happens.
+ *
+ * The cost is that if the AP switching was from an AP with keys
+ * to one without, we still allocate tailroom while it would no
+ * longer be needed. However, in the typical (fast) roaming case
+ * within an ESS this usually won't happen.
+ */
+
+ mutex_lock(&sdata->local->key_mtx);
+ sdata->crypto_tx_tailroom_needed_cnt -=
+ sdata->crypto_tx_tailroom_pending_dec;
+ sdata->crypto_tx_tailroom_pending_dec = 0;
+ mutex_unlock(&sdata->local->key_mtx);
+}
void ieee80211_gtk_rekey_notify(struct ieee80211_vif *vif, const u8 *bssid,
const u8 *replay_ctr, gfp_t gfp)
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 382dc44ed330..2a682d81cee9 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -134,7 +134,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
int __must_check ieee80211_key_link(struct ieee80211_key *key,
struct ieee80211_sub_if_data *sdata,
struct sta_info *sta);
-void __ieee80211_key_free(struct ieee80211_key *key);
+void __ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom);
void ieee80211_key_free(struct ieee80211_local *local,
struct ieee80211_key *key);
void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx,
@@ -143,9 +143,10 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata,
int idx);
void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata);
void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata);
-void ieee80211_disable_keys(struct ieee80211_sub_if_data *sdata);
#define key_mtx_dereference(local, ref) \
rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx)))
+void ieee80211_delayed_tailroom_dec(struct work_struct *wk);
+
#endif /* IEEE80211_KEY_H */
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 1a8591b77a13..5a53aa5ede80 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -399,30 +399,6 @@ static int ieee80211_ifa6_changed(struct notifier_block *nb,
}
#endif
-static int ieee80211_napi_poll(struct napi_struct *napi, int budget)
-{
- struct ieee80211_local *local =
- container_of(napi, struct ieee80211_local, napi);
-
- return local->ops->napi_poll(&local->hw, budget);
-}
-
-void ieee80211_napi_schedule(struct ieee80211_hw *hw)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
- napi_schedule(&local->napi);
-}
-EXPORT_SYMBOL(ieee80211_napi_schedule);
-
-void ieee80211_napi_complete(struct ieee80211_hw *hw)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
- napi_complete(&local->napi);
-}
-EXPORT_SYMBOL(ieee80211_napi_complete);
-
/* There isn't a lot of sense in it, but you can transmit anything you like */
static const struct ieee80211_txrx_stypes
ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = {
@@ -501,6 +477,27 @@ static const struct ieee80211_ht_cap mac80211_ht_capa_mod_mask = {
},
};
+static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = {
+ .vht_cap_info =
+ cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC |
+ IEEE80211_VHT_CAP_SHORT_GI_80 |
+ IEEE80211_VHT_CAP_SHORT_GI_160 |
+ IEEE80211_VHT_CAP_RXSTBC_1 |
+ IEEE80211_VHT_CAP_RXSTBC_2 |
+ IEEE80211_VHT_CAP_RXSTBC_3 |
+ IEEE80211_VHT_CAP_RXSTBC_4 |
+ IEEE80211_VHT_CAP_TXSTBC |
+ IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE |
+ IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
+ IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN |
+ IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN |
+ IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK),
+ .supp_mcs = {
+ .rx_mcs_map = cpu_to_le16(~0),
+ .tx_mcs_map = cpu_to_le16(~0),
+ },
+};
+
static const u8 extended_capabilities[] = {
0, 0, 0, 0, 0, 0, 0,
WLAN_EXT_CAPA8_OPMODE_NOTIF,
@@ -572,7 +569,8 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
wiphy->features |= NL80211_FEATURE_SK_TX_STATUS |
NL80211_FEATURE_SAE |
NL80211_FEATURE_HT_IBSS |
- NL80211_FEATURE_VIF_TXPOWER;
+ NL80211_FEATURE_VIF_TXPOWER |
+ NL80211_FEATURE_USERSPACE_MPM;
if (!ops->hw_scan)
wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
@@ -609,6 +607,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH;
local->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
wiphy->ht_capa_mod_mask = &mac80211_ht_capa_mod_mask;
+ wiphy->vht_capa_mod_mask = &mac80211_vht_capa_mod_mask;
INIT_LIST_HEAD(&local->interfaces);
@@ -664,9 +663,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len,
skb_queue_head_init(&local->skb_queue);
skb_queue_head_init(&local->skb_queue_unreliable);
- /* init dummy netdev for use w/ NAPI */
- init_dummy_netdev(&local->napi_dev);
-
ieee80211_led_names(local);
ieee80211_roc_setup(local);
@@ -1021,9 +1017,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
goto fail_ifa6;
#endif
- netif_napi_add(&local->napi_dev, &local->napi, ieee80211_napi_poll,
- local->hw.napi_weight);
-
return 0;
#if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 4749b3858695..77b5710db241 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -13,10 +13,6 @@
#include "ieee80211_i.h"
#include "mesh.h"
-#define TMR_RUNNING_HK 0
-#define TMR_RUNNING_MP 1
-#define TMR_RUNNING_MPR 2
-
static int mesh_allocated;
static struct kmem_cache *rm_cache;
@@ -50,11 +46,6 @@ static void ieee80211_mesh_housekeeping_timer(unsigned long data)
set_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags);
- if (local->quiescing) {
- set_bit(TMR_RUNNING_HK, &ifmsh->timers_running);
- return;
- }
-
ieee80211_queue_work(&local->hw, &sdata->work);
}
@@ -165,7 +156,7 @@ void mesh_sta_cleanup(struct sta_info *sta)
* an update.
*/
changed = mesh_accept_plinks_update(sdata);
- if (sdata->u.mesh.security == IEEE80211_MESH_SEC_NONE) {
+ if (!sdata->u.mesh.user_mpm) {
changed |= mesh_plink_deactivate(sta);
del_timer_sync(&sta->plink_timer);
}
@@ -479,15 +470,8 @@ static void ieee80211_mesh_path_timer(unsigned long data)
{
struct ieee80211_sub_if_data *sdata =
(struct ieee80211_sub_if_data *) data;
- struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
- struct ieee80211_local *local = sdata->local;
-
- if (local->quiescing) {
- set_bit(TMR_RUNNING_MP, &ifmsh->timers_running);
- return;
- }
- ieee80211_queue_work(&local->hw, &sdata->work);
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
}
static void ieee80211_mesh_path_root_timer(unsigned long data)
@@ -495,16 +479,10 @@ static void ieee80211_mesh_path_root_timer(unsigned long data)
struct ieee80211_sub_if_data *sdata =
(struct ieee80211_sub_if_data *) data;
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
- struct ieee80211_local *local = sdata->local;
set_bit(MESH_WORK_ROOT, &ifmsh->wrkq_flags);
- if (local->quiescing) {
- set_bit(TMR_RUNNING_MPR, &ifmsh->timers_running);
- return;
- }
-
- ieee80211_queue_work(&local->hw, &sdata->work);
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
}
void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh)
@@ -622,35 +600,6 @@ static void ieee80211_mesh_rootpath(struct ieee80211_sub_if_data *sdata)
round_jiffies(TU_TO_EXP_TIME(interval)));
}
-#ifdef CONFIG_PM
-void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
-
- /* use atomic bitops in case all timers fire at the same time */
-
- if (del_timer_sync(&ifmsh->housekeeping_timer))
- set_bit(TMR_RUNNING_HK, &ifmsh->timers_running);
- if (del_timer_sync(&ifmsh->mesh_path_timer))
- set_bit(TMR_RUNNING_MP, &ifmsh->timers_running);
- if (del_timer_sync(&ifmsh->mesh_path_root_timer))
- set_bit(TMR_RUNNING_MPR, &ifmsh->timers_running);
-}
-
-void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
-
- if (test_and_clear_bit(TMR_RUNNING_HK, &ifmsh->timers_running))
- add_timer(&ifmsh->housekeeping_timer);
- if (test_and_clear_bit(TMR_RUNNING_MP, &ifmsh->timers_running))
- add_timer(&ifmsh->mesh_path_timer);
- if (test_and_clear_bit(TMR_RUNNING_MPR, &ifmsh->timers_running))
- add_timer(&ifmsh->mesh_path_root_timer);
- ieee80211_mesh_root_setup(ifmsh);
-}
-#endif
-
static int
ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
{
@@ -871,8 +820,6 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata)
local->fif_other_bss--;
atomic_dec(&local->iff_allmultis);
ieee80211_configure_filter(local);
-
- sdata->u.mesh.timers_running = 0;
}
static void
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 336c88a16687..6ffabbe99c46 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -313,8 +313,6 @@ void mesh_path_timer(unsigned long data);
void mesh_path_flush_by_nexthop(struct sta_info *sta);
void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
-void mesh_path_quiesce(struct ieee80211_sub_if_data *sdata);
-void mesh_path_restart(struct ieee80211_sub_if_data *sdata);
void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata);
bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt);
@@ -359,22 +357,12 @@ static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata)
void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local);
-void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata);
-void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata);
-void mesh_plink_quiesce(struct sta_info *sta);
-void mesh_plink_restart(struct sta_info *sta);
void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata);
void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata);
void ieee80211s_stop(void);
#else
static inline void
ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {}
-static inline void ieee80211_mesh_quiesce(struct ieee80211_sub_if_data *sdata)
-{}
-static inline void ieee80211_mesh_restart(struct ieee80211_sub_if_data *sdata)
-{}
-static inline void mesh_plink_quiesce(struct sta_info *sta) {}
-static inline void mesh_plink_restart(struct sta_info *sta) {}
static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata)
{ return false; }
static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 07d396d57079..937e06fe8f2a 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -420,7 +420,6 @@ __mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *hw_addr)
return NULL;
sta->plink_state = NL80211_PLINK_LISTEN;
- init_timer(&sta->plink_timer);
sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
@@ -437,8 +436,9 @@ mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *addr,
{
struct sta_info *sta = NULL;
- /* Userspace handles peer allocation when security is enabled */
- if (sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED)
+ /* Userspace handles station allocation */
+ if (sdata->u.mesh.user_mpm ||
+ sdata->u.mesh.security & IEEE80211_MESH_SEC_AUTHED)
cfg80211_notify_new_peer_candidate(sdata->dev, addr,
elems->ie_start,
elems->total_len,
@@ -534,10 +534,8 @@ static void mesh_plink_timer(unsigned long data)
*/
sta = (struct sta_info *) data;
- if (sta->sdata->local->quiescing) {
- sta->plink_timer_was_running = true;
+ if (sta->sdata->local->quiescing)
return;
- }
spin_lock_bh(&sta->lock);
if (sta->ignore_plink_timer) {
@@ -598,29 +596,6 @@ static void mesh_plink_timer(unsigned long data)
}
}
-#ifdef CONFIG_PM
-void mesh_plink_quiesce(struct sta_info *sta)
-{
- if (!ieee80211_vif_is_mesh(&sta->sdata->vif))
- return;
-
- /* no kernel mesh sta timers have been initialized */
- if (sta->sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE)
- return;
-
- if (del_timer_sync(&sta->plink_timer))
- sta->plink_timer_was_running = true;
-}
-
-void mesh_plink_restart(struct sta_info *sta)
-{
- if (sta->plink_timer_was_running) {
- add_timer(&sta->plink_timer);
- sta->plink_timer_was_running = false;
- }
-}
-#endif
-
static inline void mesh_plink_timer_set(struct sta_info *sta, int timeout)
{
sta->plink_timer.expires = jiffies + (HZ * timeout / 1000);
@@ -695,6 +670,10 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata,
if (len < IEEE80211_MIN_ACTION_SIZE + 3)
return;
+ if (sdata->u.mesh.user_mpm)
+ /* userspace must register for these */
+ return;
+
if (is_multicast_ether_addr(mgmt->da)) {
mpl_dbg(sdata,
"Mesh plink: ignore frame from multicast address\n");
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 82cc30318a86..167158646593 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -87,9 +87,6 @@ MODULE_PARM_DESC(probe_wait_ms,
*/
#define IEEE80211_SIGNAL_AVE_MIN_COUNT 4
-#define TMR_RUNNING_TIMER 0
-#define TMR_RUNNING_CHANSW 1
-
/*
* All cfg80211 functions have to be called outside a locked
* section so that they can acquire a lock themselves... This
@@ -609,6 +606,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
BUILD_BUG_ON(sizeof(vht_cap) != sizeof(sband->vht_cap));
memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap));
+ ieee80211_apply_vhtcap_overrides(sdata, &vht_cap);
/* determine capability flags */
cap = vht_cap.cap;
@@ -1038,14 +1036,8 @@ static void ieee80211_chswitch_timer(unsigned long data)
{
struct ieee80211_sub_if_data *sdata =
(struct ieee80211_sub_if_data *) data;
- struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- if (sdata->local->quiescing) {
- set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running);
- return;
- }
-
- ieee80211_queue_work(&sdata->local->hw, &ifmgd->chswitch_work);
+ ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.chswitch_work);
}
void
@@ -1802,9 +1794,11 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
sdata->vif.bss_conf.p2p_ctwindow = 0;
sdata->vif.bss_conf.p2p_oppps = false;
- /* on the next assoc, re-program HT parameters */
+ /* on the next assoc, re-program HT/VHT parameters */
memset(&ifmgd->ht_capa, 0, sizeof(ifmgd->ht_capa));
memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask));
+ memset(&ifmgd->vht_capa, 0, sizeof(ifmgd->vht_capa));
+ memset(&ifmgd->vht_capa_mask, 0, sizeof(ifmgd->vht_capa_mask));
sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL;
@@ -1830,8 +1824,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
del_timer_sync(&sdata->u.mgd.timer);
del_timer_sync(&sdata->u.mgd.chswitch_timer);
- sdata->u.mgd.timers_running = 0;
-
sdata->vif.bss_conf.dtim_period = 0;
ifmgd->flags = 0;
@@ -3140,15 +3132,8 @@ static void ieee80211_sta_timer(unsigned long data)
{
struct ieee80211_sub_if_data *sdata =
(struct ieee80211_sub_if_data *) data;
- struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- struct ieee80211_local *local = sdata->local;
-
- if (local->quiescing) {
- set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running);
- return;
- }
- ieee80211_queue_work(&local->hw, &sdata->work);
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
}
static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata,
@@ -3500,72 +3485,6 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata)
}
}
-#ifdef CONFIG_PM
-void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-
- /*
- * Stop timers before deleting work items, as timers
- * could race and re-add the work-items. They will be
- * re-established on connection.
- */
- del_timer_sync(&ifmgd->conn_mon_timer);
- del_timer_sync(&ifmgd->bcn_mon_timer);
-
- /*
- * we need to use atomic bitops for the running bits
- * only because both timers might fire at the same
- * time -- the code here is properly synchronised.
- */
-
- cancel_work_sync(&ifmgd->request_smps_work);
-
- cancel_work_sync(&ifmgd->monitor_work);
- cancel_work_sync(&ifmgd->beacon_connection_loss_work);
- cancel_work_sync(&ifmgd->csa_connection_drop_work);
- if (del_timer_sync(&ifmgd->timer))
- set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running);
-
- if (del_timer_sync(&ifmgd->chswitch_timer))
- set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running);
- cancel_work_sync(&ifmgd->chswitch_work);
-}
-
-void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
-{
- struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-
- mutex_lock(&ifmgd->mtx);
- if (!ifmgd->associated) {
- mutex_unlock(&ifmgd->mtx);
- return;
- }
-
- if (sdata->flags & IEEE80211_SDATA_DISCONNECT_RESUME) {
- sdata->flags &= ~IEEE80211_SDATA_DISCONNECT_RESUME;
- mlme_dbg(sdata, "driver requested disconnect after resume\n");
- ieee80211_sta_connection_lost(sdata,
- ifmgd->associated->bssid,
- WLAN_REASON_UNSPECIFIED,
- true);
- mutex_unlock(&ifmgd->mtx);
- return;
- }
- mutex_unlock(&ifmgd->mtx);
-
- if (test_and_clear_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running))
- add_timer(&ifmgd->timer);
- if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running))
- add_timer(&ifmgd->chswitch_timer);
- ieee80211_sta_reset_beacon_monitor(sdata);
-
- mutex_lock(&sdata->local->mtx);
- ieee80211_restart_sta_timer(sdata);
- mutex_unlock(&sdata->local->mtx);
-}
-#endif
-
/* interface setup */
void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
{
@@ -4073,6 +3992,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
}
+ if (req->flags & ASSOC_REQ_DISABLE_VHT)
+ ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
+
/* Also disable HT if we don't support it or the AP doesn't use WMM */
sband = local->hw.wiphy->bands[req->bss->channel->band];
if (!sband->ht_cap.ht_supported ||
@@ -4096,6 +4018,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
memcpy(&ifmgd->ht_capa_mask, &req->ht_capa_mask,
sizeof(ifmgd->ht_capa_mask));
+ memcpy(&ifmgd->vht_capa, &req->vht_capa, sizeof(ifmgd->vht_capa));
+ memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask,
+ sizeof(ifmgd->vht_capa_mask));
+
if (req->ie && req->ie_len) {
memcpy(assoc_data->ie, req->ie, req->ie_len);
assoc_data->ie_len = req->ie_len;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index cc79b4a2e821..db547fceaeb9 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -277,7 +277,7 @@ void ieee80211_start_next_roc(struct ieee80211_local *local)
duration = 10;
ret = drv_remain_on_channel(local, roc->sdata, roc->chan,
- duration);
+ duration, roc->type);
roc->started = true;
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index d0275f34bf70..b471a67f224d 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -6,32 +6,11 @@
#include "driver-ops.h"
#include "led.h"
-/* return value indicates whether the driver should be further notified */
-static void ieee80211_quiesce(struct ieee80211_sub_if_data *sdata)
-{
- switch (sdata->vif.type) {
- case NL80211_IFTYPE_STATION:
- ieee80211_sta_quiesce(sdata);
- break;
- case NL80211_IFTYPE_ADHOC:
- ieee80211_ibss_quiesce(sdata);
- break;
- case NL80211_IFTYPE_MESH_POINT:
- ieee80211_mesh_quiesce(sdata);
- break;
- default:
- break;
- }
-
- cancel_work_sync(&sdata->work);
-}
-
int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
{
struct ieee80211_local *local = hw_to_local(hw);
struct ieee80211_sub_if_data *sdata;
struct sta_info *sta;
- struct ieee80211_chanctx *ctx;
if (!local->open_count)
goto suspend;
@@ -93,19 +72,12 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
return err;
} else if (err > 0) {
WARN_ON(err != 1);
- local->wowlan = false;
+ return err;
} else {
- list_for_each_entry(sdata, &local->interfaces, list)
- if (ieee80211_sdata_running(sdata))
- ieee80211_quiesce(sdata);
goto suspend;
}
}
- /* disable keys */
- list_for_each_entry(sdata, &local->interfaces, list)
- ieee80211_disable_keys(sdata);
-
/* tear down aggregation sessions and remove STAs */
mutex_lock(&local->sta_mtx);
list_for_each_entry(sta, &local->sta_list, list) {
@@ -117,100 +89,25 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
WARN_ON(drv_sta_state(local, sta->sdata, sta,
state, state - 1));
}
-
- mesh_plink_quiesce(sta);
}
mutex_unlock(&local->sta_mtx);
/* remove all interfaces */
list_for_each_entry(sdata, &local->interfaces, list) {
- static u8 zero_addr[ETH_ALEN] = {};
- u32 changed = 0;
-
if (!ieee80211_sdata_running(sdata))
continue;
-
- switch (sdata->vif.type) {
- case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_MONITOR:
- /* skip these */
- continue;
- case NL80211_IFTYPE_STATION:
- if (sdata->vif.bss_conf.assoc)
- changed = BSS_CHANGED_ASSOC |
- BSS_CHANGED_BSSID |
- BSS_CHANGED_IDLE;
- break;
- case NL80211_IFTYPE_AP:
- case NL80211_IFTYPE_ADHOC:
- case NL80211_IFTYPE_MESH_POINT:
- if (sdata->vif.bss_conf.enable_beacon)
- changed = BSS_CHANGED_BEACON_ENABLED;
- break;
- default:
- break;
- }
-
- ieee80211_quiesce(sdata);
-
- sdata->suspend_bss_conf = sdata->vif.bss_conf;
- memset(&sdata->vif.bss_conf, 0, sizeof(sdata->vif.bss_conf));
- sdata->vif.bss_conf.idle = true;
- if (sdata->suspend_bss_conf.bssid)
- sdata->vif.bss_conf.bssid = zero_addr;
-
- /* disable beaconing or remove association */
- ieee80211_bss_info_change_notify(sdata, changed);
-
- if (sdata->vif.type == NL80211_IFTYPE_AP &&
- rcu_access_pointer(sdata->u.ap.beacon))
- drv_stop_ap(local, sdata);
-
- if (local->use_chanctx) {
- struct ieee80211_chanctx_conf *conf;
-
- mutex_lock(&local->chanctx_mtx);
- conf = rcu_dereference_protected(
- sdata->vif.chanctx_conf,
- lockdep_is_held(&local->chanctx_mtx));
- if (conf) {
- ctx = container_of(conf,
- struct ieee80211_chanctx,
- conf);
- drv_unassign_vif_chanctx(local, sdata, ctx);
- }
-
- mutex_unlock(&local->chanctx_mtx);
- }
drv_remove_interface(local, sdata);
}
sdata = rtnl_dereference(local->monitor_sdata);
- if (sdata) {
- if (local->use_chanctx) {
- struct ieee80211_chanctx_conf *conf;
-
- mutex_lock(&local->chanctx_mtx);
- conf = rcu_dereference_protected(
- sdata->vif.chanctx_conf,
- lockdep_is_held(&local->chanctx_mtx));
- if (conf) {
- ctx = container_of(conf,
- struct ieee80211_chanctx,
- conf);
- drv_unassign_vif_chanctx(local, sdata, ctx);
- }
-
- mutex_unlock(&local->chanctx_mtx);
- }
-
+ if (sdata)
drv_remove_interface(local, sdata);
- }
- mutex_lock(&local->chanctx_mtx);
- list_for_each_entry(ctx, &local->chanctx_list, list)
- drv_remove_chanctx(local, ctx);
- mutex_unlock(&local->chanctx_mtx);
+ /*
+ * We disconnected on all interfaces before suspend, all channel
+ * contexts should be released.
+ */
+ WARN_ON(!list_empty(&local->chanctx_list));
/* stop hardware - this must stop RX */
if (local->open_count)
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index eea45a2c7c35..1c36c9b4fa4a 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -55,7 +55,6 @@
#include "rate.h"
#include "rc80211_minstrel.h"
-#define SAMPLE_COLUMNS 10
#define SAMPLE_TBL(_mi, _idx, _col) \
_mi->sample_table[(_idx * SAMPLE_COLUMNS) + _col]
@@ -70,16 +69,31 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix)
return i;
}
+/* find & sort topmost throughput rates */
+static inline void
+minstrel_sort_best_tp_rates(struct minstrel_sta_info *mi, int i, u8 *tp_list)
+{
+ int j = MAX_THR_RATES;
+
+ while (j > 0 && mi->r[i].cur_tp > mi->r[tp_list[j - 1]].cur_tp)
+ j--;
+ if (j < MAX_THR_RATES - 1)
+ memmove(&tp_list[j + 1], &tp_list[j], MAX_THR_RATES - (j + 1));
+ if (j < MAX_THR_RATES)
+ tp_list[j] = i;
+}
+
static void
minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
{
- u32 max_tp = 0, index_max_tp = 0, index_max_tp2 = 0;
- u32 max_prob = 0, index_max_prob = 0;
+ u8 tmp_tp_rate[MAX_THR_RATES];
+ u8 tmp_prob_rate = 0;
u32 usecs;
- u32 p;
int i;
- mi->stats_update = jiffies;
+ for (i=0; i < MAX_THR_RATES; i++)
+ tmp_tp_rate[i] = 0;
+
for (i = 0; i < mi->n_rates; i++) {
struct minstrel_rate *mr = &mi->r[i];
@@ -87,27 +101,32 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
if (!usecs)
usecs = 1000000;
- /* To avoid rounding issues, probabilities scale from 0 (0%)
- * to 18000 (100%) */
- if (mr->attempts) {
- p = (mr->success * 18000) / mr->attempts;
+ if (unlikely(mr->attempts > 0)) {
+ mr->sample_skipped = 0;
+ mr->cur_prob = MINSTREL_FRAC(mr->success, mr->attempts);
mr->succ_hist += mr->success;
mr->att_hist += mr->attempts;
- mr->cur_prob = p;
- p = ((p * (100 - mp->ewma_level)) + (mr->probability *
- mp->ewma_level)) / 100;
- mr->probability = p;
- mr->cur_tp = p * (1000000 / usecs);
- }
+ mr->probability = minstrel_ewma(mr->probability,
+ mr->cur_prob,
+ EWMA_LEVEL);
+ } else
+ mr->sample_skipped++;
mr->last_success = mr->success;
mr->last_attempts = mr->attempts;
mr->success = 0;
mr->attempts = 0;
+ /* Update throughput per rate, reset thr. below 10% success */
+ if (mr->probability < MINSTREL_FRAC(10, 100))
+ mr->cur_tp = 0;
+ else
+ mr->cur_tp = mr->probability * (1000000 / usecs);
+
/* Sample less often below the 10% chance of success.
* Sample less often above the 95% chance of success. */
- if ((mr->probability > 17100) || (mr->probability < 1800)) {
+ if (mr->probability > MINSTREL_FRAC(95, 100) ||
+ mr->probability < MINSTREL_FRAC(10, 100)) {
mr->adjusted_retry_count = mr->retry_count >> 1;
if (mr->adjusted_retry_count > 2)
mr->adjusted_retry_count = 2;
@@ -118,35 +137,30 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
}
if (!mr->adjusted_retry_count)
mr->adjusted_retry_count = 2;
- }
- for (i = 0; i < mi->n_rates; i++) {
- struct minstrel_rate *mr = &mi->r[i];
- if (max_tp < mr->cur_tp) {
- index_max_tp = i;
- max_tp = mr->cur_tp;
- }
- if (max_prob < mr->probability) {
- index_max_prob = i;
- max_prob = mr->probability;
+ minstrel_sort_best_tp_rates(mi, i, tmp_tp_rate);
+
+ /* To determine the most robust rate (max_prob_rate) used at
+ * 3rd mmr stage we distinct between two cases:
+ * (1) if any success probabilitiy >= 95%, out of those rates
+ * choose the maximum throughput rate as max_prob_rate
+ * (2) if all success probabilities < 95%, the rate with
+ * highest success probability is choosen as max_prob_rate */
+ if (mr->probability >= MINSTREL_FRAC(95,100)) {
+ if (mr->cur_tp >= mi->r[tmp_prob_rate].cur_tp)
+ tmp_prob_rate = i;
+ } else {
+ if (mr->probability >= mi->r[tmp_prob_rate].probability)
+ tmp_prob_rate = i;
}
}
- max_tp = 0;
- for (i = 0; i < mi->n_rates; i++) {
- struct minstrel_rate *mr = &mi->r[i];
-
- if (i == index_max_tp)
- continue;
+ /* Assign the new rate set */
+ memcpy(mi->max_tp_rate, tmp_tp_rate, sizeof(mi->max_tp_rate));
+ mi->max_prob_rate = tmp_prob_rate;
- if (max_tp < mr->cur_tp) {
- index_max_tp2 = i;
- max_tp = mr->cur_tp;
- }
- }
- mi->max_tp_rate = index_max_tp;
- mi->max_tp_rate2 = index_max_tp2;
- mi->max_prob_rate = index_max_prob;
+ /* Reset update timer */
+ mi->stats_update = jiffies;
}
static void
@@ -207,10 +221,10 @@ static int
minstrel_get_next_sample(struct minstrel_sta_info *mi)
{
unsigned int sample_ndx;
- sample_ndx = SAMPLE_TBL(mi, mi->sample_idx, mi->sample_column);
- mi->sample_idx++;
- if ((int) mi->sample_idx > (mi->n_rates - 2)) {
- mi->sample_idx = 0;
+ sample_ndx = SAMPLE_TBL(mi, mi->sample_row, mi->sample_column);
+ mi->sample_row++;
+ if ((int) mi->sample_row >= mi->n_rates) {
+ mi->sample_row = 0;
mi->sample_column++;
if (mi->sample_column >= SAMPLE_COLUMNS)
mi->sample_column = 0;
@@ -228,31 +242,37 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
struct minstrel_priv *mp = priv;
struct ieee80211_tx_rate *ar = info->control.rates;
unsigned int ndx, sample_ndx = 0;
- bool mrr;
- bool sample_slower = false;
- bool sample = false;
+ bool mrr_capable;
+ bool indirect_rate_sampling = false;
+ bool rate_sampling = false;
int i, delta;
int mrr_ndx[3];
- int sample_rate;
+ int sampling_ratio;
+ /* management/no-ack frames do not use rate control */
if (rate_control_send_low(sta, priv_sta, txrc))
return;
- mrr = mp->has_mrr && !txrc->rts && !txrc->bss_conf->use_cts_prot;
-
- ndx = mi->max_tp_rate;
-
- if (mrr)
- sample_rate = mp->lookaround_rate_mrr;
+ /* check multi-rate-retry capabilities & adjust lookaround_rate */
+ mrr_capable = mp->has_mrr &&
+ !txrc->rts &&
+ !txrc->bss_conf->use_cts_prot;
+ if (mrr_capable)
+ sampling_ratio = mp->lookaround_rate_mrr;
else
- sample_rate = mp->lookaround_rate;
+ sampling_ratio = mp->lookaround_rate;
+
+ /* init rateindex [ndx] with max throughput rate */
+ ndx = mi->max_tp_rate[0];
+ /* increase sum packet counter */
mi->packet_count++;
- delta = (mi->packet_count * sample_rate / 100) -
+
+ delta = (mi->packet_count * sampling_ratio / 100) -
(mi->sample_count + mi->sample_deferred / 2);
/* delta > 0: sampling required */
- if ((delta > 0) && (mrr || !mi->prev_sample)) {
+ if ((delta > 0) && (mrr_capable || !mi->prev_sample)) {
struct minstrel_rate *msr;
if (mi->packet_count >= 10000) {
mi->sample_deferred = 0;
@@ -271,21 +291,28 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
mi->sample_count += (delta - mi->n_rates * 2);
}
+ /* get next random rate sample */
sample_ndx = minstrel_get_next_sample(mi);
msr = &mi->r[sample_ndx];
- sample = true;
- sample_slower = mrr && (msr->perfect_tx_time >
- mi->r[ndx].perfect_tx_time);
-
- if (!sample_slower) {
+ rate_sampling = true;
+
+ /* Decide if direct ( 1st mrr stage) or indirect (2nd mrr stage)
+ * rate sampling method should be used.
+ * Respect such rates that are not sampled for 20 interations.
+ */
+ if (mrr_capable &&
+ msr->perfect_tx_time > mi->r[ndx].perfect_tx_time &&
+ msr->sample_skipped < 20)
+ indirect_rate_sampling = true;
+
+ if (!indirect_rate_sampling) {
if (msr->sample_limit != 0) {
ndx = sample_ndx;
mi->sample_count++;
if (msr->sample_limit > 0)
msr->sample_limit--;
- } else {
- sample = false;
- }
+ } else
+ rate_sampling = false;
} else {
/* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark
* packets that have the sampling rate deferred to the
@@ -297,34 +324,39 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
mi->sample_deferred++;
}
}
- mi->prev_sample = sample;
+ mi->prev_sample = rate_sampling;
/* If we're not using MRR and the sampling rate already
* has a probability of >95%, we shouldn't be attempting
* to use it, as this only wastes precious airtime */
- if (!mrr && sample && (mi->r[ndx].probability > 17100))
- ndx = mi->max_tp_rate;
+ if (!mrr_capable && rate_sampling &&
+ (mi->r[ndx].probability > MINSTREL_FRAC(95, 100)))
+ ndx = mi->max_tp_rate[0];
+ /* mrr setup for 1st stage */
ar[0].idx = mi->r[ndx].rix;
ar[0].count = minstrel_get_retry_count(&mi->r[ndx], info);
- if (!mrr) {
- if (!sample)
+ /* non mrr setup for 2nd stage */
+ if (!mrr_capable) {
+ if (!rate_sampling)
ar[0].count = mp->max_retry;
ar[1].idx = mi->lowest_rix;
ar[1].count = mp->max_retry;
return;
}
- /* MRR setup */
- if (sample) {
- if (sample_slower)
+ /* mrr setup for 2nd stage */
+ if (rate_sampling) {
+ if (indirect_rate_sampling)
mrr_ndx[0] = sample_ndx;
else
- mrr_ndx[0] = mi->max_tp_rate;
+ mrr_ndx[0] = mi->max_tp_rate[0];
} else {
- mrr_ndx[0] = mi->max_tp_rate2;
+ mrr_ndx[0] = mi->max_tp_rate[1];
}
+
+ /* mrr setup for 3rd & 4th stage */
mrr_ndx[1] = mi->max_prob_rate;
mrr_ndx[2] = 0;
for (i = 1; i < 4; i++) {
@@ -351,26 +383,21 @@ static void
init_sample_table(struct minstrel_sta_info *mi)
{
unsigned int i, col, new_idx;
- unsigned int n_srates = mi->n_rates - 1;
u8 rnd[8];
mi->sample_column = 0;
- mi->sample_idx = 0;
- memset(mi->sample_table, 0, SAMPLE_COLUMNS * mi->n_rates);
+ mi->sample_row = 0;
+ memset(mi->sample_table, 0xff, SAMPLE_COLUMNS * mi->n_rates);
for (col = 0; col < SAMPLE_COLUMNS; col++) {
- for (i = 0; i < n_srates; i++) {
+ for (i = 0; i < mi->n_rates; i++) {
get_random_bytes(rnd, sizeof(rnd));
- new_idx = (i + rnd[i & 7]) % n_srates;
+ new_idx = (i + rnd[i & 7]) % mi->n_rates;
- while (SAMPLE_TBL(mi, new_idx, col) != 0)
- new_idx = (new_idx + 1) % n_srates;
+ while (SAMPLE_TBL(mi, new_idx, col) != 0xff)
+ new_idx = (new_idx + 1) % mi->n_rates;
- /* Don't sample the slowest rate (i.e. slowest base
- * rate). We must presume that the slowest rate works
- * fine, or else other management frames will also be
- * failing and the link will break */
- SAMPLE_TBL(mi, new_idx, col) = i + 1;
+ SAMPLE_TBL(mi, new_idx, col) = i;
}
}
}
@@ -542,9 +569,6 @@ minstrel_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir)
mp->lookaround_rate = 5;
mp->lookaround_rate_mrr = 10;
- /* moving average weight for EWMA */
- mp->ewma_level = 75;
-
/* maximum time that the hw is allowed to stay in one MRR segment */
mp->segment_size = 6000;
diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h
index 5ecf757817f2..85ebf42cb46d 100644
--- a/net/mac80211/rc80211_minstrel.h
+++ b/net/mac80211/rc80211_minstrel.h
@@ -9,6 +9,28 @@
#ifndef __RC_MINSTREL_H
#define __RC_MINSTREL_H
+#define EWMA_LEVEL 75 /* ewma weighting factor [%] */
+#define SAMPLE_COLUMNS 10 /* number of columns in sample table */
+
+
+/* scaled fraction values */
+#define MINSTREL_SCALE 16
+#define MINSTREL_FRAC(val, div) (((val) << MINSTREL_SCALE) / div)
+#define MINSTREL_TRUNC(val) ((val) >> MINSTREL_SCALE)
+
+/* number of highest throughput rates to consider*/
+#define MAX_THR_RATES 4
+
+/*
+ * Perform EWMA (Exponentially Weighted Moving Average) calculation
+ */
+static inline int
+minstrel_ewma(int old, int new, int weight)
+{
+ return (new * (100 - weight) + old * weight) / 100;
+}
+
+
struct minstrel_rate {
int bitrate;
int rix;
@@ -26,6 +48,7 @@ struct minstrel_rate {
u32 attempts;
u32 last_attempts;
u32 last_success;
+ u8 sample_skipped;
/* parts per thousand */
u32 cur_prob;
@@ -45,14 +68,13 @@ struct minstrel_sta_info {
unsigned int lowest_rix;
- unsigned int max_tp_rate;
- unsigned int max_tp_rate2;
- unsigned int max_prob_rate;
+ u8 max_tp_rate[MAX_THR_RATES];
+ u8 max_prob_rate;
unsigned int packet_count;
unsigned int sample_count;
int sample_deferred;
- unsigned int sample_idx;
+ unsigned int sample_row;
unsigned int sample_column;
int n_rates;
@@ -73,7 +95,6 @@ struct minstrel_priv {
unsigned int cw_min;
unsigned int cw_max;
unsigned int max_retry;
- unsigned int ewma_level;
unsigned int segment_size;
unsigned int update_interval;
unsigned int lookaround_rate;
diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c
index d5a56226e675..d1048348d399 100644
--- a/net/mac80211/rc80211_minstrel_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_debugfs.c
@@ -73,15 +73,17 @@ minstrel_stats_open(struct inode *inode, struct file *file)
for (i = 0; i < mi->n_rates; i++) {
struct minstrel_rate *mr = &mi->r[i];
- *(p++) = (i == mi->max_tp_rate) ? 'T' : ' ';
- *(p++) = (i == mi->max_tp_rate2) ? 't' : ' ';
+ *(p++) = (i == mi->max_tp_rate[0]) ? 'A' : ' ';
+ *(p++) = (i == mi->max_tp_rate[1]) ? 'B' : ' ';
+ *(p++) = (i == mi->max_tp_rate[2]) ? 'C' : ' ';
+ *(p++) = (i == mi->max_tp_rate[3]) ? 'D' : ' ';
*(p++) = (i == mi->max_prob_rate) ? 'P' : ' ';
p += sprintf(p, "%3u%s", mr->bitrate / 2,
(mr->bitrate & 1 ? ".5" : " "));
- tp = mr->cur_tp / ((18000 << 10) / 96);
- prob = mr->cur_prob / 18;
- eprob = mr->probability / 18;
+ tp = MINSTREL_TRUNC(mr->cur_tp / 10);
+ prob = MINSTREL_TRUNC(mr->cur_prob * 1000);
+ eprob = MINSTREL_TRUNC(mr->probability * 1000);
p += sprintf(p, " %6u.%1u %6u.%1u %6u.%1u "
"%3u(%3u) %8llu %8llu\n",
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 3af141c69712..749552bdcfe1 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -17,8 +17,6 @@
#include "rc80211_minstrel_ht.h"
#define AVG_PKT_SIZE 1200
-#define SAMPLE_COLUMNS 10
-#define EWMA_LEVEL 75
/* Number of bits for an average sized packet */
#define MCS_NBITS (AVG_PKT_SIZE << 3)
@@ -26,11 +24,11 @@
/* Number of symbols for a packet with (bps) bits per symbol */
#define MCS_NSYMS(bps) ((MCS_NBITS + (bps) - 1) / (bps))
-/* Transmission time for a packet containing (syms) symbols */
+/* Transmission time (nanoseconds) for a packet containing (syms) symbols */
#define MCS_SYMBOL_TIME(sgi, syms) \
(sgi ? \
- ((syms) * 18 + 4) / 5 : /* syms * 3.6 us */ \
- (syms) << 2 /* syms * 4 us */ \
+ ((syms) * 18000 + 4000) / 5 : /* syms * 3.6 us */ \
+ ((syms) * 1000) << 2 /* syms * 4 us */ \
)
/* Transmit duration for the raw data part of an average sized packet */
@@ -64,9 +62,9 @@
}
#define CCK_DURATION(_bitrate, _short, _len) \
- (10 /* SIFS */ + \
+ (1000 * (10 /* SIFS */ + \
(_short ? 72 + 24 : 144 + 48 ) + \
- (8 * (_len + 4) * 10) / (_bitrate))
+ (8 * (_len + 4) * 10) / (_bitrate)))
#define CCK_ACK_DURATION(_bitrate, _short) \
(CCK_DURATION((_bitrate > 10 ? 20 : 10), false, 60) + \
@@ -129,15 +127,6 @@ const struct mcs_group minstrel_mcs_groups[] = {
static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES];
/*
- * Perform EWMA (Exponentially Weighted Moving Average) calculation
- */
-static int
-minstrel_ewma(int old, int new, int weight)
-{
- return (new * (100 - weight) + old * weight) / 100;
-}
-
-/*
* Look up an MCS group index based on mac80211 rate information
*/
static int
@@ -211,7 +200,8 @@ static void
minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate)
{
struct minstrel_rate_stats *mr;
- unsigned int usecs = 0;
+ unsigned int nsecs = 0;
+ unsigned int tp;
mr = &mi->groups[group].rates[rate];
@@ -221,10 +211,12 @@ minstrel_ht_calc_tp(struct mi