summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c18
-rw-r--r--net/8021q/vlan_dev.c22
-rw-r--r--net/8021q/vlan_netlink.c3
-rw-r--r--net/appletalk/ddp.c7
-rw-r--r--net/atm/ioctl.c16
-rw-r--r--net/atm/lec.c6
-rw-r--r--net/atm/pvc.c1
-rw-r--r--net/atm/svc.c1
-rw-r--r--net/ax25/af_ax25.c13
-rw-r--r--net/bluetooth/af_bluetooth.c8
-rw-r--r--net/bluetooth/l2cap_sock.c1
-rw-r--r--net/bluetooth/rfcomm/sock.c1
-rw-r--r--net/bluetooth/sco.c5
-rw-r--r--net/bridge/br.c13
-rw-r--r--net/bridge/br_arp_nd_proxy.c18
-rw-r--r--net/bridge/br_input.c100
-rw-r--r--net/bridge/br_multicast.c4
-rw-r--r--net/bridge/br_netlink.c2
-rw-r--r--net/bridge/br_private.h29
-rw-r--r--net/bridge/br_vlan.c214
-rw-r--r--net/bridge/netfilter/ebtable_broute.c63
-rw-r--r--net/bridge/netfilter/ebtables.c7
-rw-r--r--net/can/af_can.c6
-rw-r--r--net/can/bcm.c1
-rw-r--r--net/can/raw.c1
-rw-r--r--net/compat.c57
-rw-r--r--net/core/dev.c16
-rw-r--r--net/core/failover.c6
-rw-r--r--net/core/filter.c58
-rw-r--r--net/core/neighbour.c5
-rw-r--r--net/core/net-sysfs.c14
-rw-r--r--net/core/ptp_classifier.c7
-rw-r--r--net/core/rtnetlink.c2
-rw-r--r--net/core/skbuff.c10
-rw-r--r--net/core/sock.c55
-rw-r--r--net/dccp/ipv4.c1
-rw-r--r--net/dccp/ipv6.c1
-rw-r--r--net/hsr/Makefile2
-rw-r--r--net/hsr/hsr_debugfs.c (renamed from net/hsr/hsr_prp_debugfs.c)43
-rw-r--r--net/hsr/hsr_device.c4
-rw-r--r--net/hsr/hsr_forward.c7
-rw-r--r--net/hsr/hsr_main.h9
-rw-r--r--net/ieee802154/socket.c6
-rw-r--r--net/ipv4/af_inet.c9
-rw-r--r--net/ipv4/fou.c4
-rw-r--r--net/ipv4/netfilter/Kconfig20
-rw-r--r--net/ipv4/netfilter/Makefile2
-rw-r--r--net/ipv4/netfilter/nft_chain_route_ipv4.c89
-rw-r--r--net/ipv4/route.c16
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_dctcp.c45
-rw-r--r--net/ipv4/tcp_input.c10
-rw-r--r--net/ipv6/addrconf_core.c29
-rw-r--r--net/ipv6/af_inet6.c19
-rw-r--r--net/ipv6/fib6_rules.c34
-rw-r--r--net/ipv6/icmp.c31
-rw-r--r--net/ipv6/ip6_fib.c7
-rw-r--r--net/ipv6/ndisc.c17
-rw-r--r--net/ipv6/netfilter/Kconfig19
-rw-r--r--net/ipv6/netfilter/Makefile2
-rw-r--r--net/ipv6/netfilter/ip6t_MASQUERADE.c81
-rw-r--r--net/ipv6/netfilter/nft_chain_route_ipv6.c91
-rw-r--r--net/ipv6/raw.c1
-rw-r--r--net/ipv6/route.c449
-rw-r--r--net/ipv6/udp.c2
-rw-r--r--net/l2tp/l2tp_ip.c1
-rw-r--r--net/l2tp/l2tp_ip6.c1
-rw-r--r--net/l2tp/l2tp_ppp.c3
-rw-r--r--net/llc/af_llc.c3
-rw-r--r--net/mac80211/driver-ops.h3
-rw-r--r--net/mac80211/key.c9
-rw-r--r--net/mac80211/mesh_pathtbl.c2
-rw-r--r--net/mac80211/rx.c10
-rw-r--r--net/mac80211/trace_msg.h7
-rw-r--r--net/mac80211/tx.c53
-rw-r--r--net/netfilter/Kconfig19
-rw-r--r--net/netfilter/Makefile4
-rw-r--r--net/netfilter/core.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c35
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c84
-rw-r--r--net/netfilter/nf_conntrack_expect.c2
-rw-r--r--net/netfilter/nf_conntrack_netlink.c16
-rw-r--r--net/netfilter/nf_conntrack_sip.c2
-rw-r--r--net/netfilter/nf_flow_table_ip.c10
-rw-r--r--net/netfilter/nf_internals.h3
-rw-r--r--net/netfilter/nf_nat_core.c16
-rw-r--r--net/netfilter/nf_nat_masquerade.c104
-rw-r--r--net/netfilter/nf_nat_proto.c59
-rw-r--r--net/netfilter/nf_queue.c1
-rw-r--r--net/netfilter/nf_tables_api.c16
-rw-r--r--net/netfilter/nfnetlink_osf.c14
-rw-r--r--net/netfilter/nft_chain_nat.c36
-rw-r--r--net/netfilter/nft_chain_route.c169
-rw-r--r--net/netfilter/nft_masq.c83
-rw-r--r--net/netfilter/nft_nat.c58
-rw-r--r--net/netfilter/nft_osf.c30
-rw-r--r--net/netfilter/nft_redir.c63
-rw-r--r--net/netfilter/x_tables.c3
-rw-r--r--net/netfilter/xt_MASQUERADE.c (renamed from net/ipv4/netfilter/ipt_MASQUERADE.c)84
-rw-r--r--net/netlink/af_netlink.c3
-rw-r--r--net/netrom/af_netrom.c90
-rw-r--r--net/netrom/nr_loopback.c2
-rw-r--r--net/netrom/nr_route.c2
-rw-r--r--net/netrom/sysctl_net_netrom.c5
-rw-r--r--net/openvswitch/conntrack.c18
-rw-r--r--net/packet/af_packet.c7
-rw-r--r--net/qrtr/qrtr.c4
-rw-r--r--net/rds/af_rds.c3
-rw-r--r--net/rds/bind.c2
-rw-r--r--net/rose/af_rose.c7
-rw-r--r--net/rxrpc/af_rxrpc.c17
-rw-r--r--net/rxrpc/ar-internal.h1
-rw-r--r--net/rxrpc/conn_event.c11
-rw-r--r--net/rxrpc/input.c18
-rw-r--r--net/rxrpc/peer_event.c5
-rw-r--r--net/rxrpc/sendmsg.c21
-rw-r--r--net/sched/sch_taprio.c17
-rw-r--r--net/sctp/ipv6.c1
-rw-r--r--net/sctp/protocol.c1
-rw-r--r--net/sctp/sm_statefuns.c6
-rw-r--r--net/sctp/socket.c13
-rw-r--r--net/sctp/ulpevent.c19
-rw-r--r--net/sctp/ulpqueue.c3
-rw-r--r--net/smc/af_smc.c58
-rw-r--r--net/smc/smc_close.c25
-rw-r--r--net/smc/smc_close.h1
-rw-r--r--net/smc/smc_ism.c5
-rw-r--r--net/smc/smc_pnet.c3
-rw-r--r--net/socket.c64
-rw-r--r--net/strparser/strparser.c12
-rw-r--r--net/sunrpc/clnt.c45
-rw-r--r--net/sunrpc/xprtrdma/verbs.c2
-rw-r--r--net/tipc/link.c2
-rw-r--r--net/tipc/name_table.c3
-rw-r--r--net/tipc/socket.c3
-rw-r--r--net/tipc/sysctl.c8
-rw-r--r--net/tls/tls_device.c12
-rw-r--r--net/tls/tls_main.c24
-rw-r--r--net/tls/tls_sw.c15
-rw-r--r--net/wireless/nl80211.c18
-rw-r--r--net/wireless/reg.c39
-rw-r--r--net/wireless/scan.c3
-rw-r--r--net/wireless/util.c6
-rw-r--r--net/x25/af_x25.c27
144 files changed, 2103 insertions, 1394 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index dc4411165e43..1f99678751df 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -75,6 +75,14 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg,
return 0;
}
+static void vlan_stacked_transfer_operstate(const struct net_device *rootdev,
+ struct net_device *dev,
+ struct vlan_dev_priv *vlan)
+{
+ if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING))
+ netif_stacked_transfer_operstate(rootdev, dev);
+}
+
void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
{
struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
@@ -180,7 +188,7 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
/* Account for reference in struct vlan_dev_priv */
dev_hold(real_dev);
- netif_stacked_transfer_operstate(real_dev, dev);
+ vlan_stacked_transfer_operstate(real_dev, dev, vlan);
linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */
/* So, got the sucker initialized, now lets place
@@ -399,7 +407,8 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
case NETDEV_CHANGE:
/* Propagate real device state to vlan devices */
vlan_group_for_each_dev(grp, i, vlandev)
- netif_stacked_transfer_operstate(dev, vlandev);
+ vlan_stacked_transfer_operstate(dev, vlandev,
+ vlan_dev_priv(vlandev));
break;
case NETDEV_CHANGEADDR:
@@ -446,7 +455,8 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
dev_close_many(&close_list, false);
list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) {
- netif_stacked_transfer_operstate(dev, vlandev);
+ vlan_stacked_transfer_operstate(dev, vlandev,
+ vlan_dev_priv(vlandev));
list_del_init(&vlandev->close_list);
}
list_del(&close_list);
@@ -463,7 +473,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
dev_change_flags(vlandev, flgs | IFF_UP,
extack);
- netif_stacked_transfer_operstate(dev, vlandev);
+ vlan_stacked_transfer_operstate(dev, vlandev, vlan);
}
break;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 8d77b6ee4477..f044ae56a313 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -223,7 +223,8 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
u32 old_flags = vlan->flags;
if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
- VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP))
+ VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP |
+ VLAN_FLAG_BRIDGE_BINDING))
return -EINVAL;
vlan->flags = (old_flags & ~mask) | (flags & mask);
@@ -296,7 +297,8 @@ static int vlan_dev_open(struct net_device *dev)
if (vlan->flags & VLAN_FLAG_MVRP)
vlan_mvrp_request_join(dev);
- if (netif_carrier_ok(real_dev))
+ if (netif_carrier_ok(real_dev) &&
+ !(vlan->flags & VLAN_FLAG_BRIDGE_BINDING))
netif_carrier_on(dev);
return 0;
@@ -326,7 +328,8 @@ static int vlan_dev_stop(struct net_device *dev)
if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
dev_uc_del(real_dev, dev->dev_addr);
- netif_carrier_off(dev);
+ if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING))
+ netif_carrier_off(dev);
return 0;
}
@@ -550,7 +553,8 @@ static const struct net_device_ops vlan_netdev_ops;
static int vlan_dev_init(struct net_device *dev)
{
- struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+ struct net_device *real_dev = vlan->real_dev;
netif_carrier_off(dev);
@@ -561,6 +565,9 @@ static int vlan_dev_init(struct net_device *dev)
(1<<__LINK_STATE_DORMANT))) |
(1<<__LINK_STATE_PRESENT);
+ if (vlan->flags & VLAN_FLAG_BRIDGE_BINDING)
+ dev->state |= (1 << __LINK_STATE_NOCARRIER);
+
dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG |
NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
NETIF_F_GSO_ENCAP_ALL |
@@ -591,8 +598,7 @@ static int vlan_dev_init(struct net_device *dev)
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (vlan_hw_offload_capable(real_dev->features,
- vlan_dev_priv(dev)->vlan_proto)) {
+ if (vlan_hw_offload_capable(real_dev->features, vlan->vlan_proto)) {
dev->header_ops = &vlan_passthru_header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
@@ -606,8 +612,8 @@ static int vlan_dev_init(struct net_device *dev)
vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
- vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
- if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
+ vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
+ if (!vlan->vlan_pcpu_stats)
return -ENOMEM;
return 0;
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 9b60c1e399e2..a624dccf68fd 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -84,7 +84,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[],
flags = nla_data(data[IFLA_VLAN_FLAGS]);
if ((flags->flags & flags->mask) &
~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
- VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) {
+ VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP |
+ VLAN_FLAG_BRIDGE_BINDING)) {
NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN flags");
return -EINVAL;
}
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 709d2542f729..e2511027d19b 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1806,12 +1806,6 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
rc = put_user(amount, (int __user *)argp);
break;
}
- case SIOCGSTAMP:
- rc = sock_get_timestamp(sk, argp);
- break;
- case SIOCGSTAMPNS:
- rc = sock_get_timestampns(sk, argp);
- break;
/* Routing */
case SIOCADDRT:
case SIOCDELRT:
@@ -1871,6 +1865,7 @@ static const struct proto_ops atalk_dgram_ops = {
.getname = atalk_getname,
.poll = datagram_poll,
.ioctl = atalk_ioctl,
+ .gettstamp = sock_gettstamp,
#ifdef CONFIG_COMPAT
.compat_ioctl = atalk_compat_ioctl,
#endif
diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c
index 2ff0e5e470e3..d955b683aa7c 100644
--- a/net/atm/ioctl.c
+++ b/net/atm/ioctl.c
@@ -81,22 +81,6 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd,
(int __user *)argp) ? -EFAULT : 0;
goto done;
}
- case SIOCGSTAMP: /* borrowed from IP */
-#ifdef CONFIG_COMPAT
- if (compat)
- error = compat_sock_get_timestamp(sk, argp);
- else
-#endif
- error = sock_get_timestamp(sk, argp);
- goto done;
- case SIOCGSTAMPNS: /* borrowed from IP */
-#ifdef CONFIG_COMPAT
- if (compat)
- error = compat_sock_get_timestampns(sk, argp);
- else
-#endif
- error = sock_get_timestampns(sk, argp);
- goto done;
case ATM_SETSC:
net_warn_ratelimited("ATM_SETSC is obsolete; used by %s:%d\n",
current->comm, task_pid_nr(current));
diff --git a/net/atm/lec.c b/net/atm/lec.c
index d7f5cf5b7594..ad4f829193f0 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
{
- if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg])
+ if (arg < 0 || arg >= MAX_LEC_ITF)
+ return -EINVAL;
+ arg = array_index_nospec(arg, MAX_LEC_ITF);
+ if (!dev_lec[arg])
return -EINVAL;
vcc->proto_data = dev_lec[arg];
return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc);
@@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
i = arg;
if (arg >= MAX_LEC_ITF)
return -EINVAL;
+ i = array_index_nospec(arg, MAX_LEC_ITF);
if (!dev_lec[i]) {
int size;
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 2cb10af16afc..02bd2a436bdf 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -118,6 +118,7 @@ static const struct proto_ops pvc_proto_ops = {
#ifdef CONFIG_COMPAT
.compat_ioctl = vcc_compat_ioctl,
#endif
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = pvc_shutdown,
.setsockopt = pvc_setsockopt,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 2f91b766ac42..908cbb8654f5 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -641,6 +641,7 @@ static const struct proto_ops svc_proto_ops = {
#ifdef CONFIG_COMPAT
.compat_ioctl = svc_compat_ioctl,
#endif
+ .gettstamp = sock_gettstamp,
.listen = svc_listen,
.shutdown = svc_shutdown,
.setsockopt = svc_setsockopt,
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 5d01edf8d819..012c0b6fc4f6 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1714,14 +1714,6 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
}
- case SIOCGSTAMP:
- res = sock_get_timestamp(sk, argp);
- break;
-
- case SIOCGSTAMPNS:
- res = sock_get_timestampns(sk, argp);
- break;
-
case SIOCAX25ADDUID: /* Add a uid to the uid/call map table */
case SIOCAX25DELUID: /* Delete a uid from the uid/call map table */
case SIOCAX25GETUID: {
@@ -1888,8 +1880,8 @@ static int ax25_info_show(struct seq_file *seq, void *v)
* magic dev src_addr dest_addr,digi1,digi2,.. st vs vr va t1 t1 t2 t2 t3 t3 idle idle n2 n2 rtt window paclen Snd-Q Rcv-Q inode
*/
- seq_printf(seq, "%8.8lx %s %s%s ",
- (long) ax25,
+ seq_printf(seq, "%p %s %s%s ",
+ ax25,
ax25->ax25_dev == NULL? "???" : ax25->ax25_dev->dev->name,
ax2asc(buf, &ax25->source_addr),
ax25->iamdigi? "*":"");
@@ -1950,6 +1942,7 @@ static const struct proto_ops ax25_proto_ops = {
.getname = ax25_getname,
.poll = datagram_poll,
.ioctl = ax25_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = ax25_listen,
.shutdown = ax25_shutdown,
.setsockopt = ax25_setsockopt,
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 8d12198eaa94..94ddf19998c7 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -521,14 +521,6 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
err = put_user(amount, (int __user *) arg);
break;
- case SIOCGSTAMP:
- err = sock_get_timestamp(sk, (struct timeval __user *) arg);
- break;
-
- case SIOCGSTAMPNS:
- err = sock_get_timestampns(sk, (struct timespec __user *) arg);
- break;
-
default:
err = -ENOIOCTLCMD;
break;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index a3a2cd55e23a..dcb14abebeba 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1655,6 +1655,7 @@ static const struct proto_ops l2cap_sock_ops = {
.recvmsg = l2cap_sock_recvmsg,
.poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
+ .gettstamp = sock_gettstamp,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
.shutdown = l2cap_sock_shutdown,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index b1f49fcc0478..90bb53aa4bee 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1039,6 +1039,7 @@ static const struct proto_ops rfcomm_sock_ops = {
.setsockopt = rfcomm_sock_setsockopt,
.getsockopt = rfcomm_sock_getsockopt,
.ioctl = rfcomm_sock_ioctl,
+ .gettstamp = sock_gettstamp,
.poll = bt_sock_poll,
.socketpair = sock_no_socketpair,
.mmap = sock_no_mmap
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 9a580999ca57..b91d6b440fdf 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -523,12 +523,12 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr,
struct sock *sk = sock->sk;
int err = 0;
- BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
-
if (!addr || addr_len < sizeof(struct sockaddr_sco) ||
addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
@@ -1190,6 +1190,7 @@ static const struct proto_ops sco_sock_ops = {
.recvmsg = sco_sock_recvmsg,
.poll = bt_sock_poll,
.ioctl = bt_sock_ioctl,
+ .gettstamp = sock_gettstamp,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
.shutdown = sco_sock_shutdown,
diff --git a/net/bridge/br.c b/net/bridge/br.c
index a5174e5001d8..e69fc87a13e0 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -40,10 +40,13 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
bool changed_addr;
int err;
- /* register of bridge completed, add sysfs entries */
- if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) {
- br_sysfs_addbr(dev);
- return NOTIFY_DONE;
+ if (dev->priv_flags & IFF_EBRIDGE) {
+ if (event == NETDEV_REGISTER) {
+ /* register of bridge completed, add sysfs entries */
+ br_sysfs_addbr(dev);
+ return NOTIFY_DONE;
+ }
+ br_vlan_bridge_event(dev, event, ptr);
}
/* not a port of a bridge */
@@ -126,6 +129,8 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
break;
}
+ br_vlan_port_event(p, event);
+
/* Events that may cause spanning tree to refresh */
if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
event == NETDEV_CHANGE || event == NETDEV_DOWN))
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 724b474ade54..15116752365a 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -131,7 +131,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
u8 *arpptr, *sha;
__be32 sip, tip;
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0;
if ((dev->flags & IFF_NOARP) ||
!pskb_may_pull(skb, arp_hdr_len(dev)))
@@ -161,7 +161,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
return;
if (ipv4_is_zeronet(sip) || sip == tip) {
/* prevent flooding to neigh suppress ports */
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
}
@@ -181,7 +181,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
/* its our local ip, so don't proxy reply
* and don't forward to neigh suppress ports
*/
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
@@ -217,7 +217,7 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br,
*/
if (replied ||
br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED))
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
}
neigh_release(n);
@@ -393,7 +393,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
struct ipv6hdr *iphdr;
struct neighbour *n;
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 0;
if (p && (p->flags & BR_NEIGH_SUPPRESS))
return;
@@ -401,7 +401,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT &&
!msg->icmph.icmp6_solicited) {
/* prevent flooding to neigh suppress ports */
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
@@ -414,7 +414,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) {
/* prevent flooding to neigh suppress ports */
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
@@ -432,7 +432,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
/* its our own ip, so don't proxy reply
* and don't forward to arp suppress ports
*/
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
return;
}
@@ -465,7 +465,7 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
*/
if (replied ||
br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED))
- BR_INPUT_SKB_CB(skb)->proxyarp_replied = true;
+ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1;
}
neigh_release(n);
}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 5ea7e56119c1..014af7efef25 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -16,6 +16,9 @@
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/netfilter_bridge.h>
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+#include <net/netfilter/nf_queue.h>
+#endif
#include <linux/neighbour.h>
#include <net/arp.h>
#include <linux/export.h>
@@ -23,10 +26,6 @@
#include "br_private.h"
#include "br_private_tunnel.h"
-/* Hook for brouter */
-br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
-EXPORT_SYMBOL(br_should_route_hook);
-
static int
br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
{
@@ -197,13 +196,63 @@ static void __br_handle_local_finish(struct sk_buff *skb)
/* note: already called with rcu_read_lock */
static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
__br_handle_local_finish(skb);
- BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
- br_pass_frame_up(skb);
- return 0;
+ /* return 1 to signal the okfn() was called so it's ok to use the skb */
+ return 1;
+}
+
+static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
+{
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ struct nf_hook_entries *e = NULL;
+ struct nf_hook_state state;
+ unsigned int verdict, i;
+ struct net *net;
+ int ret;
+
+ net = dev_net(skb->dev);
+#ifdef HAVE_JUMP_LABEL
+ if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING]))
+ goto frame_finish;
+#endif
+
+ e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]);
+ if (!e)
+ goto frame_finish;
+
+ nf_hook_state_init(&state, NF_BR_PRE_ROUTING,
+ NFPROTO_BRIDGE, skb->dev, NULL, NULL,
+ net, br_handle_frame_finish);
+
+ for (i = 0; i < e->num_hook_entries; i++) {
+ verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state);
+ switch (verdict & NF_VERDICT_MASK) {
+ case NF_ACCEPT:
+ if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) {
+ *pskb = skb;
+ return RX_HANDLER_PASS;
+ }
+ break;
+ case NF_DROP:
+ kfree_skb(skb);
+ return RX_HANDLER_CONSUMED;
+ case NF_QUEUE:
+ ret = nf_queue(skb, &state, e, i, verdict);
+ if (ret == 1)
+ continue;
+ return RX_HANDLER_CONSUMED;
+ default: /* STOLEN */
+ return RX_HANDLER_CONSUMED;
+ }
+ }
+frame_finish:
+ net = dev_net(skb->dev);
+ br_handle_frame_finish(net, NULL, skb);
+#else
+ br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
+#endif
+ return RX_HANDLER_CONSUMED;
}
/*
@@ -215,7 +264,6 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
struct net_bridge_port *p;
struct sk_buff *skb = *pskb;
const unsigned char *dest = eth_hdr(skb)->h_dest;
- br_should_route_hook_t *rhook;
if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
return RX_HANDLER_PASS;
@@ -227,6 +275,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
if (!skb)
return RX_HANDLER_CONSUMED;
+ memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
+
p = br_port_get_rcu(skb->dev);
if (p->flags & BR_VLAN_TUNNEL) {
if (br_handle_ingress_vlan_tunnel(skb, p,
@@ -280,32 +330,28 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
goto forward;
}
- /* Deliver packet to local host only */
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
- NULL, skb, skb->dev, NULL, br_handle_local_finish);
- return RX_HANDLER_CONSUMED;
+ /* The else clause should be hit when nf_hook():
+ * - returns < 0 (drop/error)
+ * - returns = 0 (stolen/nf_queue)
+ * Thus return 1 from the okfn() to signal the skb is ok to pass
+ */
+ if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+ dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+ br_handle_local_finish) == 1) {
+ return RX_HANDLER_PASS;
+ } else {
+ return RX_HANDLER_CONSUMED;
+ }
}
forward:
switch (p->state) {
case BR_STATE_FORWARDING:
- rhook = rcu_dereference(br_should_route_hook);
- if (rhook) {
- if ((*rhook)(skb)) {
- *pskb = skb;
- return RX_HANDLER_PASS;
- }
- dest = eth_hdr(skb)->h_dest;
- }
- /* fall through */
case BR_STATE_LEARNING:
if (ether_addr_equal(p->br->dev->dev_addr, dest))
skb->pkt_type = PACKET_HOST;
- NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
- dev_net(skb->dev), NULL, skb, skb->dev, NULL,
- br_handle_frame_finish);
- break;
+ return nf_hook_bridge_pre(skb, pskb);
default:
drop:
kfree_skb(skb);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 812560d7f7a2..c2a30f79a9d0 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2013,7 +2013,8 @@ static void br_multicast_start_querier(struct net_bridge *br,
__br_multicast_open(br, query);
- list_for_each_entry(port, &br->port_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(port, &br->port_list, list) {
if (port->state == BR_STATE_DISABLED ||
port->state == BR_STATE_BLOCKING)
continue;
@@ -2025,6 +2026,7 @@ static void br_multicast_start_querier(struct net_bridge *br,
br_multicast_enable(&port->ip6_own_query);
#endif
}
+ rcu_read_unlock();
}
int br_multicast_toggle(struct net_bridge *br, unsigned long val)
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 4f9f59eba8b4..8dfcc2d285d8 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1441,7 +1441,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED,
br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) ||
nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT,
- br_opt_get(br, IFLA_BR_VLAN_STATS_PER_PORT)))
+ br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)))
return -EMSGSIZE;
#endif
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 7946aa3b6e09..334a8c496b50 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -321,6 +321,7 @@ enum net_bridge_opts {
BROPT_MTU_SET_BY_USER,
BROPT_VLAN_STATS_PER_PORT,
BROPT_NO_LL_LEARN,
+ BROPT_VLAN_BRIDGE_BINDING,
};
struct net_bridge {
@@ -425,15 +426,16 @@ struct br_input_skb_cb {
struct net_device *brdev;
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
- int igmp;
- int mrouters_only;
+ u8 igmp;
+ u8 mrouters_only:1;
#endif
-
- bool proxyarp_replied;
- bool src_port_isolated;
-
+ u8 proxyarp_replied:1;
+ u8 src_port_isolated:1;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
- bool vlan_filtered;
+ u8 vlan_filtered:1;
+#endif
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+ u8 br_netfilter_broute:1;
#endif
#ifdef CONFIG_NET_SWITCHDEV
@@ -894,6 +896,9 @@ int nbp_vlan_init(struct net_bridge_port *port, struct netlink_ext_ack *extack);
int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
void br_vlan_get_stats(const struct net_bridge_vlan *v,
struct br_vlan_stats *stats);
+void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
+void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
+ void *ptr);
static inline struct net_bridge_vlan_group *br_vlan_group(
const struct net_bridge *br)
@@ -1077,6 +1082,16 @@ static inline void br_vlan_get_stats(const struct net_bridge_vlan *v,
struct br_vlan_stats *stats)
{
}
+
+static inline void br_vlan_port_event(struct net_bridge_port *p,
+ unsigned long event)
+{
+}
+
+static inline void br_vlan_bridge_event(struct net_device *dev,
+ unsigned long event, void *ptr)
+{
+}
#endif
struct nf_br_ops {
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 0a02822b5667..2db63997f313 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -7,6 +7,8 @@
#include "br_private.h"
#include "br_private_tunnel.h"
+static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid);
+
static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
@@ -293,6 +295,9 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
__vlan_add_list(v);
__vlan_add_flags(v, flags);
+
+ if (p)
+ nbp_vlan_set_vlan_dev_state(p, v->vid);
out:
return err;
@@ -357,6 +362,7 @@ static int __vlan_del(struct net_bridge_vlan *v)
rhashtable_remove_fast(&vg->vlan_hash, &v->vnode,
br_vlan_rht_params);
__vlan_del_list(v);
+ nbp_vlan_set_vlan_dev_state(p, v->vid);
call_rcu(&v->rcu, nbp_vlan_rcu_free);
}
@@ -1264,3 +1270,211 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid,
return 0;
}
EXPORT_SYMBOL_GPL(br_vlan_get_info);
+
+static int br_vlan_is_bind_vlan_dev(const struct net_device *dev)
+{
+ return is_vlan_dev(dev) &&
+ !!(vlan_dev_priv(dev)->flags & VLAN_FLAG_BRIDGE_BINDING);
+}
+
+static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev,
+ __always_unused void *data)
+{
+ return br_vlan_is_bind_vlan_dev(dev);
+}
+
+static bool br_vlan_has_upper_bind_vlan_dev(struct net_device *dev)
+{
+ int found;
+
+ rcu_read_lock();
+ found = netdev_walk_all_upper_dev_rcu(dev, br_vlan_is_bind_vlan_dev_fn,
+ NULL);
+ rcu_read_unlock();
+
+ return !!found;
+}
+
+struct br_vlan_bind_walk_data {
+ u16 vid;
+ struct net_device *result;
+};
+
+static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev,
+ void *data_in)
+{
+ struct br_vlan_bind_walk_data *data = data_in;
+ int found = 0;
+
+ if (br_vlan_is_bind_vlan_dev(dev) &&
+ vlan_dev_priv(dev)->vlan_id == data->vid) {
+ data->result = dev;
+ found = 1;
+ }
+
+ return found;
+}
+
+static struct net_device *
+br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid)
+{
+ struct br_vlan_bind_walk_data data = {
+ .vid = vid,
+ };
+
+ rcu_read_lock();
+ netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn,
+ &data);
+ rcu_read_unlock();
+
+ return data.result;
+}
+
+static bool br_vlan_is_dev_up(const struct net_device *dev)
+{
+ return !!(dev->flags & IFF_UP) && netif_oper_up(dev);
+}
+
+static void br_vlan_set_vlan_dev_state(const struct net_bridge *br,
+ struct net_device *vlan_dev)
+{
+ u16 vid = vlan_dev_priv(vlan_dev)->vlan_id;
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_port *p;
+ bool has_carrier = false;
+
+ if (!netif_carrier_ok(br->dev)) {
+ netif_carrier_off(vlan_dev);
+ return;
+ }
+
+ list_for_each_entry(p, &br->port_list, list) {
+ vg = nbp_vlan_group(p);
+ if (br_vlan_find(vg, vid) && br_vlan_is_dev_up(p->dev)) {
+ has_carrier = true;
+ break;
+ }
+ }
+
+ if (has_carrier)
+ netif_carrier_on(vlan_dev);
+ else
+ netif_carrier_off(vlan_dev);
+}
+
+static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p)
+{
+ struct net_bridge_vlan_group *vg = nbp_vlan_group(p);
+ struct net_bridge_vlan *vlan;
+ struct net_device *vlan_dev;
+
+ list_for_each_entry(vlan, &vg->vlan_list, vlist) {
+ vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev,
+ vlan->vid);
+ if (vlan_dev) {
+ if (br_vlan_is_dev_up(p->dev)) {
+ if (netif_carrier_ok(p->br->dev))
+ netif_carrier_on(vlan_dev);
+ } else {
+ br_vlan_set_vlan_dev_state(p->br, vlan_dev);
+ }
+ }
+ }
+}
+
+static void br_vlan_upper_change(struct net_device *dev,
+ struct net_device *upper_dev,
+ bool linking)
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ if (!br_vlan_is_bind_vlan_dev(upper_dev))
+ return;
+
+ if (linking) {
+ br_vlan_set_vlan_dev_state(br, upper_dev);
+ br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true);
+ } else {
+ br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING,
+ br_vlan_has_upper_bind_vlan_dev(dev));
+ }
+}
+
+struct br_vlan_link_state_walk_data {
+ struct net_bridge *br;
+};
+
+static int br_vlan_link_state_change_fn(struct net_device *vlan_dev,
+ void *data_in)
+{
+ struct br_vlan_link_state_walk_data *data = data_in;
+
+ if (br_vlan_is_bind_vlan_dev(vlan_dev))
+ br_vlan_set_vlan_dev_state(data->br, vlan_dev);
+
+ return 0;
+}
+
+static void br_vlan_link_state_change(struct net_device *dev,
+ struct net_bridge *br)
+{
+ struct br_vlan_link_state_walk_data data = {
+ .br = br
+ };
+
+ rcu_read_lock();
+ netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn,
+ &data);
+ rcu_read_unlock();
+}
+
+/* Must be protected by RTNL. */
+static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid)
+{
+ struct net_device *vlan_dev;
+
+ if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING))
+ return;
+
+ vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vid);
+ if (vlan_dev)
+ br_vlan_set_vlan_dev_state(p->br, vlan_dev);
+}
+
+/* Must be protected by RTNL. */
+void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
+ void *ptr)
+{
+ struct netdev_notifier_changeupper_info *info;
+ struct net_bridge *br;
+
+ switch (event) {
+ case NETDEV_CHANGEUPPER:
+ info = ptr;
+ br_vlan_upper_change(dev, info->upper_dev, info->linking);
+ break;
+
+ case NETDEV_CHANGE:
+ case NETDEV_UP:
+ br = netdev_priv(dev);
+ if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING))
+ return;
+ br_vlan_link_state_change(dev, br);
+ break;
+ }
+}
+
+/* Must be protected by RTNL. */
+void br_vlan_port_event(struct net_bridge_port *p, unsigned long event)
+{
+ if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING))
+ return;
+
+ switch (event) {
+ case NETDEV_CHANGE:
+ case NETDEV_DOWN:
+ case NETDEV_UP:
+ br_vlan_set_all_vlan_dev_state(p);
+ break;
+ }
+}
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 276b60262981..ec2652a459da 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -15,6 +15,8 @@
#include <linux/module.h>
#include <linux/if_bridge.h>
+#include "../br_private.h"
+
/* EBT_ACCEPT means the frame will be bridged
* EBT_DROP means the frame will be routed
*/
@@ -48,30 +50,63 @@ static const struct ebt_table broute_table = {
.me = THIS_MODULE,
};
-static int ebt_broute(struct sk_buff *skb)
+static unsigned int ebt_broute(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *s)
{
+ struct net_bridge_port *p = br_port_get_rcu(skb->dev);
struct nf_hook_state state;
+ unsigned char *dest;
int ret;
+ if (!p || p->state != BR_STATE_FORWARDING)
+ return NF_ACCEPT;
+
nf_hook_state_init(&state, NF_BR_BROUTING,
- NFPROTO_BRIDGE, skb->dev, NULL, NULL,
- dev_net(skb->dev), NULL);
+ NFPROTO_BRIDGE, s->in, NULL, NULL,
+ s->net, NULL);
ret = ebt_do_table(skb, &state, state.net->xt.broute_table);
- if (ret == NF_DROP)
- return 1; /* route it */
- return 0; /* bridge it */
+
+ if (ret != NF_DROP)
+ return ret;
+
+ /* DROP in ebtables -t broute means that the
+ * skb should be routed, not bridged.
+ * This is awkward, but can't be changed for compatibility
+ * reasons.
+ *
+ * We map DROP to ACCEPT and set the ->br_netfilter_broute flag.
+ */
+ BR_INPUT_SKB_CB(skb)->br_netfilter_broute = 1;
+
+ /* undo PACKET_HOST mangling done in br_input in case the dst
+ * address matches the logical bridge but not the port.
+ */
+ dest = eth_hdr(skb)->h_dest;
+ if (skb->pkt_type == PACKET_HOST &&
+ !ether_addr_equal(skb->dev->dev_addr, dest) &&
+ ether_addr_equal(p->br->dev->dev_addr, dest))
+ skb->pkt_type = PACKET_OTHERHOST;
+
+ return NF_ACCEPT;
}
+static const struct nf_hook_ops ebt_ops_broute = {
+ .hook = ebt_broute,
+ .pf = NFPROTO_BRIDGE,
+ .hooknum = NF_BR_PRE_ROUTING,
+ .priority = NF_BR_PRI_FIRST,
+};
+
static int __net_init broute_net_init(struct net *net)
{
- return ebt_register_table(net, &broute_table, NULL,
+ return ebt_register_table(net, &broute_table, &ebt_ops_broute,
&net->xt.broute_table);
}
static void __net_exit broute_net_exit(struct net *net)
{
- ebt_unregister_table(net, net->xt.broute_table, NULL);
+ ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute);
}
static struct pernet_operations broute_net_ops = {
@@ -81,21 +116,11 @@ static struct pernet_operations broute_net_ops = {
static int __init ebtable_broute_init(void)
{
- int ret;
-
- ret = register_pernet_subsys(&broute_net_ops);
- if (ret < 0)
- return ret;
- /* see br_input.c */
- RCU_INIT_POINTER(br_should_route_hook,
- (br_should_route_hook_t *)ebt_broute);
- return 0;
+ return register_pernet_subsys(&broute_net_ops);
}
static void __exit ebtable_broute_fini(void)
{
- RCU_INIT_POINTER(br_should_route_hook, NULL);
- synchronize_net();
unregister_pernet_subsys(&broute_net_ops);
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index eb15891f8b9f..383f0328ff68 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1221,10 +1221,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
mutex_unlock(&ebt_mutex);
WRITE_ONCE(*res, table);
-
- if (!ops)
- return 0;
-
ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
if (ret) {
__ebt_unregister_table(net, table);
@@ -1248,8 +1244,7 @@ out:
void ebt_unregister_table(struct net *net, struct ebt_table *table,
const struct nf_hook_ops *ops)
{
- if (ops)
- nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
__ebt_unregister_table(net, table);
}
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 1684ba5b51eb..e8fd5dc1780a 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -89,13 +89,7 @@ static atomic_t skbcounter = ATOMIC_INIT(0);
int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
- struct sock *sk = sock->sk;
-
switch (cmd) {
-
- case SIOCGSTAMP:
- return sock_get_timestamp(sk, (struct timeval __user *)arg);
-
default:
return -ENOIOCTLCMD;
}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 79bb8afa9c0c..a34ee52f19ea 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1689,6 +1689,7 @@ static const struct proto_ops bcm_ops = {
.getname = sock_no_getname,
.poll = datagram_poll,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/can/raw.c b/net/can/raw.c
index c70207537488..afcbff063a67 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -846,6 +846,7 @@ static const struct proto_ops raw_ops = {
.getname = raw_getname,
.poll = datagram_poll,
.ioctl = can_ioctl, /* use can_ioctl() from af_can.c */
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = raw_setsockopt,
diff --git a/net/compat.c b/net/compat.c
index eeea5eb71639..a031bd333092 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -395,63 +395,6 @@ COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
return __compat_sys_setsockopt(fd, level, optname, optval, optlen);
}
-int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
-{
- struct compat_timeval __user *ctv;
- int err;
- struct timeval tv;
-
- if (COMPAT_USE_64BIT_TIME)
- return sock_get_timestamp(sk, userstamp);
-
- ctv = (struct compat_timeval __user *) userstamp;
- err = -ENOENT;
- sock_enable_timestamp(sk, SOCK_TIMESTAMP);
- tv = ktime_to_timeval(sock_read_timestamp(sk));
-
- if (tv.tv_sec == -1)
- return err;
- if (tv.tv_sec == 0) {
- ktime_t kt = ktime_get_real();
- sock_write_timestamp(sk, kt);
- tv = ktime_to_timeval(kt);
- }
- err = 0;
- if (put_user(tv.tv_sec, &ctv->tv_sec) ||
- put_user(tv.tv_usec, &ctv->tv_usec))
- err = -EFAULT;
- return err;
-}
-EXPORT_SYMBOL(compat_sock_get_timestamp);
-
-int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
-{
- struct compat_timespec __user *ctv;
- int err;
- struct timespec ts;
-
- if (COMPAT_USE_64BIT_TIME)
- return sock_get_timestampns (sk, userstamp);
-
- ctv = (struct compat_timespec __user *) userstamp;
- err = -ENOENT;
- sock_enable_timestamp(sk, SOCK_TIMESTAMP);
- ts = ktime_to_timespec(sock_read_timestamp(sk));
- if (ts.tv_sec == -1)
- return err;
- if (ts.tv_sec == 0) {
- ktime_t kt = ktime_get_real();
- sock_write_timestamp(sk, kt);
- ts = ktime_to_timespec(kt);
- }
- err = 0;
- if (put_user(ts.tv_sec, &ctv->tv_sec) ||
- put_user(ts.tv_nsec, &ctv->tv_nsec))
- err = -EFAULT;
- return err;
-}
-EXPORT_SYMBOL(compat_sock_get_timestampns);
-
static int __compat_sys_getsockopt(int fd, int level, int optname,
char __user *optval,
int __user *optlen)
diff --git a/net/core/dev.c b/net/core/dev.c
index b430f851f377..22f2640f559a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1184,7 +1184,21 @@ int dev_change_name(struct net_device *dev, const char *newname)
BUG_ON(!dev_net(dev));
net = dev_net(dev);
- if (dev->flags & IFF_UP)
+
+ /* Some auto-enslaved devices e.g. failover slaves are
+ * special, as userspace might rename the device after
+ * the interface had been brought up and running since
+ * the point kernel initiated auto-enslavement. Allow
+ * live name change even when these slave devices are
+ * up and running.
+ *
+ * Typically, users of these auto-enslaving devices
+ * don't actually care about slave name change, as
+ * they are supposed to operate on master interface
+ * directly.
+ */
+ if (dev->flags & IFF_UP &&
+ likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
return -EBUSY;
write_seqcount_begin(&devnet_rename_seq);
diff --git a/net/core/failover.c b/net/core/failover.c
index 4a92a98ccce9..b5cd3c727285 100644
--- a/net/core/failover.c
+++ b/net/core/failover.c
@@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev)
goto err_upper_link;
}
- slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
if (fops && fops->slave_register &&
!fops->slave_register(slave_dev, failover_dev))
return NOTIFY_OK;
netdev_upper_dev_unlink(slave_dev, failover_dev);
- slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
err_upper_link:
netdev_rx_handler_unregister(slave_dev);
done:
@@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev)
netdev_rx_handler_unregister(slave_dev);
netdev_upper_dev_unlink(slave_dev, failover_dev);
- slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+ slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
if (fops && fops->slave_unregister &&
!fops->slave_unregister(slave_dev, failover_dev))
diff --git a/net/core/filter.c b/net/core/filter.c
index 1833926a63fc..fa8fb0548217 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4464,6 +4464,8 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr,
* Only binding to IP is supported.
*/
err = -EINVAL;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return err;
if (addr->sa_family == AF_INET) {
if (addr_len < sizeof(struct sockaddr_in))
return err;
@@ -4679,12 +4681,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
struct in6_addr *src = (struct in6_addr *) params->ipv6_src;
struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst;
struct neighbour *neigh;
+ struct fib6_result res;
struct net_device *dev;
struct inet6_dev *idev;
- struct fib6_info *f6i;
struct flowi6 fl6;
int strict = 0;
- int oif;
+ int oif, err;
u32 mtu;
/* link local addresses are never forwarded */
@@ -4726,54 +4728,52 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
if (unlikely(!tb))
return BPF_FIB_LKUP_RET_NOT_FWDED;
- f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+ err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res,
+ strict);
} else {
fl6.flowi6_mark = 0;
fl6.flowi6_secid = 0;
fl6.flowi6_tun_key.tun_id = 0;
fl6.flowi6_uid = sock_net_uid(net, NULL);
- f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+ err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict);
}
- if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+ if (unlikely(err || IS_ERR_OR_NULL(res.f6i) ||
+ res.f6i == net->ipv6.fib6_null_entry))
return BPF_FIB_LKUP_RET_NOT_FWDED;
- if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
- switch (f6i->fib6_type) {
- case RTN_BLACKHOLE:
- return BPF_FIB_LKUP_RET_BLACKHOLE;
- case RTN_UNREACHABLE:
- return BPF_FIB_LKUP_RET_UNREACHABLE;
- case RTN_PROHIBIT:
- return BPF_FIB_LKUP_RET_PROHIBIT;
- default:
- return BPF_FIB_LKUP_RET_NOT_FWDED;
- }
- }
-
- if (f6i->fib6_type != RTN_UNICAST)
+ switch (res.fib6_type) {
+ /* only unicast is forwarded */
+ case RTN_UNICAST:
+ break;
+ case RTN_BLACKHOLE:
+ return BPF_FIB_LKUP_RET_BLACKHOLE;
+ case RTN_UNREACHABLE:
+ return BPF_FIB_LKUP_RET_UNREACHABLE;
+ case RTN_PROHIBIT:
+ return BPF_FIB_LKUP_RET_PROHIBIT;
+ default:
return BPF_FIB_LKUP_RET_NOT_FWDED;
+ }
- if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
- f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
- fl6.flowi6_oif, NULL,
- strict);
+ ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif,
+ fl6.flowi6_oif != 0, NULL, strict);
if (check_mtu) {
- mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
+ mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
if (params->tot_len > mtu)
return BPF_FIB_LKUP_RET_FRAG_NEEDED;
}
- if (f6i->fib6_nh.fib_nh_lws)
+ if (res.nh->fib_nh_lws)
return BPF_FIB_LKUP_RET_UNSUPP_LWT;
- if (f6i->fib6_nh.fib_nh_gw_family)
- *dst = f6i->fib6_nh.fib_nh_gw6;
+ if (res.nh->fib_nh_gw_family)
+ *dst = res.nh->fib_nh_gw6;
- dev = f6i->fib6_nh.fib_nh_dev;
- params->rt_metric = f6i->fib6_metric;
+ dev = res.nh->fib_nh_dev;
+ params->rt_metric = res.f6i->fib6_metric;
/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
* not needed here.
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 30f6fd8f68e0..997cfa8f99ba 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1920,6 +1920,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
goto out;
}
+ if (tbl->allow_add && !tbl->allow_add(dev, extack)) {
+ err = -EINVAL;
+ goto out;
+ }
+
neigh = neigh_lookup(tbl, dst, dev);
if (neigh == NULL) {
bool exempt_from_gc;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index c14f0dc0157c..e4fd68389d6f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1747,20 +1747,16 @@ int netdev_register_kobject(struct net_device *ndev)
error = device_add(dev);
if (error)
- goto error_put_device;
+ return error;
error = register_queue_kobjects(ndev);
- if (error)
- goto error_device_del;
+ if (error) {
+ device_del(dev);
+ return error;
+ }
pm_runtime_set_memalloc_noio(dev, true);
- return 0;
-
-error_device_del:
- device_del(dev);
-error_put_device:
- put_device(dev);
return error;
}
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index 703cf76aa7c2..7109c168b5e0 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -185,9 +185,10 @@ void __init ptp_classifier_init(void)
{ 0x16, 0, 0, 0x00000000 },
{ 0x06, 0, 0, 0x00000000 },
};
- struct sock_fprog_kern ptp_prog = {
- .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
- };
+ struct sock_fprog_kern ptp_prog;
+
+ ptp_prog.len = ARRAY_SIZE(ptp_filter);
+ ptp_prog.filter = ptp_filter;
BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog));
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f9b964fd4e4d..5fa5bf3e9945 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4951,7 +4951,7 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
{
struct if_stats_msg *ifsm;
- if (nlh->nlmsg_len < sizeof(*ifsm)) {
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) {
NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
return -EINVAL;
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 087622298d77..e89be6282693 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5115,7 +5115,8 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
{
- int mac_len;
+ int mac_len, meta_len;
+ void *meta;
if (skb_cow(skb, skb_headroom(skb)) < 0) {
kfree_skb(skb);
@@ -5127,6 +5128,13 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
mac_len - VLAN_HLEN - ETH_TLEN);
}
+
+ meta_len = skb_metadata_len(skb);
+ if (meta_len) {
+ meta = skb_metadata_end(skb) - meta_len;
+ memmove(meta + VLAN_HLEN, meta, meta_len);
+ }
+
skb->mac_header += VLAN_HLEN;
return skb;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 782343bb925b..443b98d05f1e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -348,7 +348,7 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
}
- if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
*(struct old_timeval32 *)optval = tv32;
return sizeof(tv32);
@@ -372,7 +372,7 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool
{
struct __kernel_sock_timeval tv;
- if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+ if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32;
if (optlen < sizeof(tv32))
@@ -2977,39 +2977,44 @@ bool lock_sock_fast(struct sock *sk)
}
EXPORT_SYMBOL(lock_sock_fast);
-int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
+int sock_gettstamp(struct socket *sock, void __user *userstamp,
+ bool timeval, bool time32)
{
- struct timeval tv;
+ struct sock *sk = sock->sk;
+ struct timespec64 ts;
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
- tv = ktime_to_timeval(sock_read_timestamp(sk));
- if (tv.tv_sec == -1)
+ ts = ktime_to_timespec64(sock_read_timestamp(sk));
+ if (ts.tv_sec == -1)
return -ENOENT;
- if (tv.tv_sec == 0) {
+ if (ts.tv_sec == 0) {
ktime_t kt = ktime_get_real();
- sock_write_timestamp(sk, kt);
- tv = ktime_to_timeval(kt);
+ sock_write_timestamp(sk, kt);;
+ ts = ktime_to_timespec64(kt);
}
- return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
-}
-EXPORT_SYMBOL(sock_get_timestamp);
-int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
-{
- struct timespec ts;
+ if (timeval)
+ ts.tv_nsec /= 1000;
- sock_enable_timestamp(sk, SOCK_TIMESTAMP);
- ts = ktime_to_timespec(sock_read_timestamp(sk));
- if (ts.tv_sec == -1)
- return -ENOENT;
- if (ts.tv_sec == 0) {
- ktime_t kt = ktime_get_real();
- sock_write_timestamp(sk, kt);
- ts = ktime_to_timespec(sk->sk_stamp);
+#ifdef CONFIG_COMPAT_32BIT_TIME
+ if (time32)
+ return put_old_timespec32(&ts, userstamp);
+#endif
+#ifdef CONFIG_SPARC64
+ /* beware of padding in sparc64 timeval */
+ if (timeval && !in_compat_syscall()) {
+ struct __kernel_old_timeval __user tv = {
+ .tv_sec = ts.tv_sec;
+ .tv_usec = ts.tv_nsec;
+ };
+ if (copy_to_user(userstamp, &tv, sizeof(tv))
+ return -EFAULT;
+ return 0;
}
- return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
+#endif
+ return put_timespec64(&ts, userstamp);
}
-EXPORT_SYMBOL(sock_get_timestampns);
+EXPORT_SYMBOL(sock_gettstamp);
void sock_enable_timestamp(struct sock *sk, int flag)
{
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 26a21d97b6b0..004535e4c070 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -991,6 +991,7 @@ static const struct proto_ops inet_dccp_ops = {
/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
.poll = dccp_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 57d84e9b7b6f..c4e4d1301062 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1075,6 +1075,7 @@ static const struct proto_ops inet6_dccp_ops = {
.getname = inet6_getname,
.poll = dccp_poll,
.ioctl = inet6_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
diff --git a/net/hsr/Makefile b/net/hsr/Makefile
index d74d89d013b0..e45757fc477f 100644
--- a/net/hsr/Makefile
+++ b/net/hsr/Makefile
@@ -6,4 +6,4 @@ obj-$(CONFIG_HSR) += hsr.o
hsr-y := hsr_main.o hsr_framereg.o hsr_device.o \
hsr_netlink.o hsr_slave.o hsr_forward.o
-hsr-$(CONFIG_DEBUG_FS) += hsr_prp_debugfs.o
+hsr-$(CONFIG_DEBUG_FS) += hsr_debugfs.o
diff --git a/net/hsr/hsr_prp_debugfs.c b/net/hsr/hsr_debugfs.c
index b30e98734c61..94447974a3c0 100644
--- a/net/hsr/hsr_prp_debugfs.c
+++ b/net/hsr/hsr_debugfs.c
@@ -1,9 +1,9 @@
/*
- * hsr_prp_debugfs code
- * Copyright (C) 2017 Texas Instruments Incorporated
+ * hsr_debugfs code
+ * Copyright (C) 2019 Texas Instruments Incorporated
*
* Author(s):
- * Murali Karicheri <m-karicheri2@ti.com?
+ * Murali Karicheri <m-karicheri2@ti.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
@@ -26,9 +26,9 @@ static void print_mac_address(struct seq_file *sfp, unsigned char *mac)
mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
}
-/* hsr_prp_node_table_show - Formats and prints node_table entries */
+/* hsr_node_table_show - Formats and prints node_table entries */
static int
-hsr_prp_node_table_show(struct seq_file *sfp, void *data)
+hsr_node_table_show(struct seq_file *sfp, void *data)
{
struct hsr_priv *priv = (struct hsr_priv *)sfp->private;
struct hsr_node *node;
@@ -52,40 +52,40 @@ hsr_prp_node_table_show(struct seq_file *sfp, void *data)
return 0;
}
-/* hsr_prp_node_table_open - Open the node_table file
+/* hsr_node_table_open - Open the node_table file
*
* Description:
* This routine opens a debugfs file node_table of specific hsr device
*/
static int
-hsr_prp_node_table_open(struct inode *inode, struct file *filp)
+hsr_node_table_open(struct inode *inode, struct file *filp)
{
- return single_open(filp, hsr_prp_node_table_show, inode->i_private);
+ return single_open(filp, hsr_node_table_show, inode->i_private);
}
-static const struct file_operations hsr_prp_fops = {
+static const struct file_operations hsr_fops = {
.owner = THIS_MODULE,
- .open = hsr_prp_node_table_open,
+ .open = hsr_node_table_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
-/* hsr_prp_debugfs_init - create hsr-prp node_table file for dumping
+/* hsr_debugfs_init - create hsr node_table file for dumping
* the node table
*
* Description:
* When debugfs is configured this routine sets up the node_table file per
- * hsr/prp device for dumping the node_table entries
+ * hsr device for dumping the node_table entries
*/
-int hsr_prp_debugfs_init(struct hsr_priv *priv)
+int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev)
{
int rc = -1;
struct dentry *de = NULL;
- de = debugfs_create_dir("hsr", NULL);
+ de = debugfs_create_dir(hsr_dev->name, NULL);
if (!de) {
- pr_err("Cannot create hsr-prp debugfs root\n");
+ pr_err("Cannot create hsr debugfs root\n");
return rc;
}
@@ -93,25 +93,24 @@ int hsr_prp_debugfs_init(struct hsr_priv *priv)
de = debugfs_create_file("node_table", S_IFREG | 0444,
priv->node_tbl_root, priv,
- &hsr_prp_fops);
+ &hsr_fops);
if (!de) {
- pr_err("Cannot create hsr-prp node_table directory\n");
+ pr_err("Cannot create hsr node_table directory\n");
return rc;
}
priv->node_tbl_file = de;
- rc = 0;
- return rc;
+ return 0;
}
-/* hsr_prp_debugfs_term - Tear down debugfs intrastructure
+/* hsr_debugfs_term - Tear down debugfs intrastructure
*
* Description:
* When Debufs is configured this routine removes debugfs file system
- * elements that are specific to hsr-prp
+ * elements that are specific to hsr
*/
void
-hsr_prp_debugfs_term(struct hsr_priv *priv)
+hsr_debugfs_term(struct hsr_priv *priv)
{
debugfs_remove(priv->node_tbl_file);
priv->node_tbl_file = NULL;
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index b47a621e3f4e..15c72065df79 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -354,7 +354,7 @@ static void hsr_dev_destroy(struct net_device *hsr_dev)
hsr = netdev_priv(hsr_dev);
- hsr_prp_debugfs_term(hsr);
+ hsr_debugfs_term(hsr);
rtnl_lock();
hsr_for_each_port(hsr, port)
@@ -485,7 +485,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
goto fail;
mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD));
- res = hsr_prp_debugfs_init(hsr);
+ res = hsr_debugfs_init(hsr, hsr_dev);
if (res)
goto fail;
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 0cac992192d0..ddd9605bad04 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -359,6 +359,13 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
goto out_drop;
hsr_register_frame_in(frame.node_src, port, frame.sequence_nr);
hsr_forward_do(&frame);
+ /* Gets called for ingress frames as well as egress from master port.
+ * So check and increment stats for master port only here.
+ */
+ if (port->type == HSR_PT_MASTER) {
+ port->dev->stats.tx_packets++;
+ port->dev->stats.tx_bytes += skb->len;
+ }
if (frame.skb_hsr)
kfree_skb(frame.skb_hsr);
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 778213f07fe0..96fac696a1e1 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -184,15 +184,16 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb)
}
#if IS_ENABLED(CONFIG_DEBUG_FS)
-int hsr_prp_debugfs_init(struct hsr_priv *priv);
-void hsr_prp_debugfs_term(struct hsr_priv *priv);
+int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev);
+void hsr_debugfs_term(struct hsr_priv *priv);
#else
-static inline int hsr_prp_debugfs_init(struct hsr_priv *priv)
+static inline int hsr_debugfs_init(struct hsr_priv *priv,
+ struct net_device *hsr_dev)
{
return 0;
}
-static inline void hsr_prp_debugfs_term(struct hsr_priv *priv)
+static inline void hsr_debugfs_term(struct hsr_priv *priv)
{}
#endif
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index bc6b912603f1..ce2dfb997537 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -164,10 +164,6 @@ static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd,
struct sock *sk = sock->sk;
switch (cmd) {
- case SIOCGSTAMP:
- return sock_get_timestamp(sk, (struct timeval __user *)arg);
- case SIOCGSTAMPNS:
- return sock_get_timestampns(sk, (struct timespec __user *)arg);
case SIOCGIFADDR:
case SIOCSIFADDR:
return ieee802154_dev_ioctl(sk, (struct ifreq __user *)arg,
@@ -426,6 +422,7 @@ static const struct proto_ops ieee802154_raw_ops = {
.getname = sock_no_getname,
.poll = datagram_poll,
.ioctl = ieee802154_sock_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_common_setsockopt,
@@ -988,6 +985,7 @@ static const struct proto_ops ieee802154_dgram_ops = {
.getname = sock_no_getname,
.poll = datagram_poll,
.ioctl = ieee802154_sock_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_common_setsockopt,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 08a8430f5647..5183a2daba64 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -915,12 +915,6 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct rtentry rt;
switch (cmd) {
- case SIOCGSTAMP:
- err = sock_get_timestamp(sk, (struct timeval __user *)arg);
- break;
- case SIOCGSTAMPNS:
- err = sock_get_timestampns(sk, (struct timespec __user *)arg);
- break;
case SIOCADDRT:
case SIOCDELRT:
if (copy_from_user(&rt, p, sizeof(struct rtentry)))
@@ -992,6 +986,7 @@ const struct proto_ops inet_stream_ops = {
.getname = inet_getname,
.poll = tcp_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = inet_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
@@ -1027,6 +1022,7 @@ const struct proto_ops inet_dgram_ops = {
.getname = inet_getname,
.poll = udp_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
@@ -1059,6 +1055,7 @@ static const struct proto_ops inet_sockraw_ops = {
.getname = inet_getname,
.poll = datagram_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index b038f563baa4..1ca1586a7e46 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -121,6 +121,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
struct guehdr *guehdr;
void *data;
u16 doffset = 0;
+ u8 proto_ctype;
if (!fou)
return 1;
@@ -210,13 +211,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
if (unlikely(guehdr->control))
return gue_control_message(skb, guehdr);
+ proto_ctype = guehdr->proto_ctype;
__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
skb_reset_transport_header(skb);
if (iptunnel_pull_offloads(skb))
goto drop;
- return -guehdr->proto_ctype;
+ return -proto_ctype;
drop:
kfree_skb(skb);
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index c98391d49200..1412b029f37f 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -27,14 +27,6 @@ config NF_TABLES_IPV4
if NF_TABLES_IPV4
-config NFT_CHAIN_ROUTE_IPV4
- tristate "IPv4 nf_tables route chain support"
- help
- This option enables the "route" chain for IPv4 in nf_tables. This
- chain type is used to force packet re-routing after mangling header
- fields such as the source, destination, type of service and
- the packet mark.
-
config NFT_REJECT_IPV4
select NF_REJECT_IPV4
default NFT_REJECT
@@ -232,16 +224,10 @@ if IP_NF_NAT
config IP_NF_TARGET_MASQUERADE
tristate "MASQUERADE target support"
- select NF_NAT_MASQUERADE
- default m if NETFILTER_ADVANCED=n
+ select NETFILTER_XT_TARGET_MASQUERADE
help
- Masquerading is a special case of NAT: all outgoing connections are
- changed to seem to come from a particular interface's address, and
- if the interface goes down, those connections are lost. This is
- only useful for dialup accounts with dynamic IP address (ie. your IP
- address will be different on next dialup).
-
- To compile it as a module, choose M here. If unsure, say N.
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE.
config IP_NF_TARGET_NETMAP
tristate "NETMAP target support"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index e241f5188ebe..c50e0ec095d2 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -24,7 +24,6 @@ nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o
$(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
-obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
@@ -49,7 +48,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o
# targets
obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o
obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o
-obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o
obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o
obj-$(CONFIG_IP_NF_TARGET_SYNPROXY) += ipt_SYNPROXY.o
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
deleted file mode 100644
index 7d82934c46f4..000000000000
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/route.h>
-#include <net/ip.h>
-
-static unsigned int nf_route_table_hook(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- unsigned int ret;
- struct nft_pktinfo pkt;
- u32 mark;
- __be32 saddr, daddr;
- u_int8_t tos;
- const struct iphdr *iph;
- int err;
-
- nft_set_pktinfo(&pkt, skb, state);
- nft_set_pktinfo_ipv4(&pkt, skb);
-
- mark = skb->mark;
- iph = ip_hdr(skb);
- saddr = iph->saddr;
- daddr = iph->daddr;
- tos = iph->tos;
-
- ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_STOLEN) {
- iph = ip_hdr(skb);
-
- if (iph->saddr != saddr ||
- iph->daddr != daddr ||
- skb->mark != mark ||
- iph->tos != tos) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
- if (err < 0)
- ret = NF_DROP_ERR(err);
- }
- }
- return ret;
-}
-
-static const struct nft_chain_type nft_chain_route_ipv4 = {
- .name = "route",
- .type = NFT_CHAIN_T_ROUTE,
- .family = NFPROTO_IPV4,
- .owner = THIS_MODULE,
- .hook_mask = (1 << NF_INET_LOCAL_OUT),
- .hooks = {
- [NF_INET_LOCAL_OUT] = nf_route_table_hook,
- },
-};
-
-static int __init nft_chain_route_init(void)
-{
- nft_register_chain_type(&nft_chain_route_ipv4);
-
- return 0;
-}
-
-static void __exit nft_chain_route_exit(void)
-{
- nft_unregister_chain_type(&nft_chain_route_ipv4);
-}
-
-module_init(nft_chain_route_init);
-module_exit(nft_chain_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET, "route");
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index efa6a36cbfff..d9b5aa2290d6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1200,9 +1200,23 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
static void ipv4_link_failure(struct sk_buff *skb)
{
+ struct ip_options opt;
struct rtable *rt;
+ int res;
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ /* Recompile ip options since IPCB may not be valid anymore.
+ */
+ memset(&opt, 0, sizeof(opt));
+ opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+
+ rcu_read_lock();
+ res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ rcu_read_unlock();
+
+ if (res)
+ return;
+
+ __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
rt = skb_rtable(skb);
if (rt)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 603e770d59b3..f7567a3698eb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -868,7 +868,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
if (likely(!size)) {
skb = sk->sk_tx_skb_cache;
if (skb && !skb_cloned(skb)) {
- skb->truesize -= skb->data_len;
+ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
sk->sk_tx_skb_cache = NULL;
pskb_trim(skb, 0);
INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 359da68d7c06..477cb4aa456c 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -49,9 +49,8 @@
#define DCTCP_MAX_ALPHA 1024U
struct dctcp {
- u32 acked_bytes_ecn;
- u32 acked_bytes_total;
- u32 prior_snd_una;
+ u32 old_delivered;
+ u32 old_delivered_ce;
u32 prior_rcv_nxt;
u32 dctcp_alpha;
u32 next_seq;
@@ -73,8 +72,8 @@ static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
{
ca->next_seq = tp->snd_nxt;
- ca->acked_bytes_ecn = 0;
- ca->acked_bytes_total = 0;
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
}
static void dctcp_init(struct sock *sk)
@@ -86,7 +85,6 @@ static void dctcp_init(struct sock *sk)
sk->sk_state == TCP_CLOSE)) {
struct dctcp *ca = inet_csk_ca(sk);
- ca->prior_snd_una = tp->snd_una;
ca->prior_rcv_nxt = tp->rcv_nxt;
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
@@ -118,37 +116,25 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct dctcp *ca = inet_csk_ca(sk);
- u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
-
- /* If ack did not advance snd_una, count dupack as MSS size.
- * If ack did update window, do not count it at all.
- */
- if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
- acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
- if (acked_bytes) {
- ca->acked_bytes_total += acked_bytes;
- ca->prior_snd_una = tp->snd_una;
-
- if (flags & CA_ACK_ECE)
- ca->acked_bytes_ecn += acked_bytes;
- }
/* Expired RTT */
if (!before(tp->snd_una, ca->next_seq)) {
- u64 bytes_ecn = ca->acked_bytes_ecn;
+ u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
u32 alpha = ca->dctcp_alpha;
/* alpha = (1 - g) * alpha + g * F */
alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
- if (bytes_ecn) {
+ if (delivered_ce) {
+ u32 delivered = tp->delivered - ca->old_delivered;
+
/* If dctcp_shift_g == 1, a 32bit value would overflow
- * after 8 Mbytes.
+ * after 8 M packets.
*/
- bytes_ecn <<= (10 - dctcp_shift_g);
- do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
- alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
}
/* dctcp_alpha can be read from dctcp_get_info() without
* synchro, so we ask compiler to not use dctcp_alpha
@@ -200,6 +186,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info)
{
const struct dctcp *ca = inet_csk_ca(sk);
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Fill it also in case of VEGASINFO due to req struct limits.
* We can still correctly retrieve it later.
@@ -211,8 +198,10 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
info->dctcp.dctcp_enabled = 1;
info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
info->dctcp.dctcp_alpha = ca->dctcp_alpha;
- info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
- info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
+ info->dctcp.dctcp_ab_ecn = tp->mss_cache *
+ (tp->delivered_ce - ca->old_delivered_ce);
+ info->dctcp.dctcp_ab_tot = tp->mss_cache *
+ (tp->delivered - ca->old_delivered);
}
*attr = INET_DIAG_DCTCPINFO;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6660ce2a7333..97671bff597a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ int room;
+
+ room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
/* Check #1 */
- if (tp->rcv_ssthresh < tp->window_clamp &&
- (int)tp->rcv_ssthresh < tcp_space(sk) &&
- !tcp_under_memory_pressure(sk)) {
+ if (room > 0 && !tcp_under_memory_pressure(sk)) {
int incr;
/* Check #2. Increase window, if skb with such overhead
@@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
- tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
- tp->window_clamp);
+ tp->rcv_ssthresh += min(room, incr);
inet_csk(sk)->icsk_ack.quick |= 1;
}
}
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index e37e4c5871f7..763a947e0d14 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -144,31 +144,32 @@ static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
return NULL;
}
-static struct fib6_info *
+static int
eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6, int flags)
+ int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags)
{
- return NULL;
+ return -EAFNOSUPPORT;
}
-static struct fib6_info *
+static int
eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags)
+ struct fib6_result *res, int flags)
{
- return NULL;
+ return -EAFNOSUPPORT;
}
-static struct fib6_info *
-eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb, int strict)
+static void
+eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res,
+ struct flowi6 *fl6, int oif, bool have_oif_match,
+ const struct sk_buff *skb, int strict)
{
- return f6i;
}
static u32
-eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
- struct in6_addr *saddr)
+eafnosupport_ip6_mtu_from_fib6(const struct fib6_result *res,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
return 0;
}
@@ -187,7 +188,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.fib6_get_table = eafnosupport_fib6_get_table,
.fib6_table_lookup = eafnosupport_fib6_table_lookup,
.fib6_lookup = eafnosupport_fib6_lookup,
- .fib6_multipath_select = eafnosupport_fib6_multipath_select,
+ .fib6_select_path = eafnosupport_fib6_select_path,
.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
.fib6_nh_init = eafnosupport_fib6_nh_init,
};
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 1dac6ea6666a..c04ae282f4e4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -547,12 +547,6 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct net *net = sock_net(sk);
switch (cmd) {
- case SIOCGSTAMP:
- return sock_get_timestamp(sk, (struct timeval __user *)arg);
-
- case SIOCGSTAMPNS:
- return sock_get_timestampns(sk, (struct timespec __user *)arg);
-
case SIOCADDRT:
case SIOCDELRT:
@@ -585,6 +579,7 @@ const struct proto_ops inet6_stream_ops = {
.getname = inet6_getname,
.poll = tcp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
+ .gettstamp = sock_gettstamp,
.listen = inet_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
@@ -618,6 +613,7 @@ const struct proto_ops inet6_dgram_ops = {
.getname = inet6_getname,
.poll = udp_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
@@ -850,6 +846,15 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.icmpv6_echo_ignore_all = 0;
net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0;
net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0;
+
+ /* By default, rate limit error messages.
+ * Except for pmtu discovery, it would break it.
+ * proc_do_large_bitmap needs pointer to the bitmap.
+ */
+ bitmap_set(net->ipv6.sysctl.icmpv6_ratemask, 0, ICMPV6_ERRMSG_MAX + 1);
+ bitmap_clear(net->ipv6.sysctl.icmpv6_ratemask, ICMPV6_PKT_TOOBIG, 1);
+ net->ipv6.sysctl.icmpv6_ratemask_ptr = net->ipv6.sysctl.icmpv6_ratemask;
+
net->ipv6.sysctl.flowlabel_consistency = 1;
net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS;
net->ipv6.sysctl.idgen_retries = 3;
@@ -917,7 +922,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
.fib6_get_table = fib6_get_table,
.fib6_table_lookup = fib6_table_lookup,
.fib6_lookup = fib6_lookup,
- .fib6_multipath_select = fib6_multipath_select,
+ .fib6_select_path = fib6_select_path,
.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
.fib6_nh_init = fib6_nh_init,
.fib6_nh_release = fib6_nh_release,
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index f590446595d8..ab5ac643bae8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -61,16 +61,16 @@ unsigned int fib6_rules_seq_read(struct net *net)
}
/* called with rcu lock held; no reference taken on fib6_info */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags)
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags)
{
- struct fib6_info *f6i;
int err;
if (net->ipv6.fib6_has_custom_rules) {
struct fib_lookup_arg arg = {
.lookup_ptr = fib6_table_lookup,
.lookup_data = &oif,
+ .result = res,
.flags = FIB_LOOKUP_NOREF,
};
@@ -78,19 +78,15 @@ struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
flowi6_to_flowi(fl6), flags, &arg);
- if (err)
- return ERR_PTR(err);
-
- f6i = arg.result ? : net->ipv6.fib6_null_entry;
} else {
- f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl,
- oif, fl6, flags);
- if (!f6i || f6i == net->ipv6.fib6_null_entry)
- f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
- oif, fl6, flags);
+ err = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, oif,
+ fl6, res, flags);
+ if (err || res->f6i == net->ipv6.fib6_null_entry)
+ err = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
+ oif, fl6, res, flags);
}
- return f6i;
+ return err;
}
struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
@@ -157,10 +153,10 @@ static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
+ struct fib6_result *res = arg->result;
struct flowi6 *flp6 = &flp->u.ip6;
struct net *net = rule->fr_net;
struct fib6_table *table;
- struct fib6_info *f6i;
int err = -EAGAIN, *oif;
u32 tb_id;
@@ -182,14 +178,10 @@ static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
return -EAGAIN;
oif = (int *)arg->lookup_data;
- f6i = fib6_table_lookup(net, table, *oif, flp6, flags);
- if (f6i != net->ipv6.fib6_null_entry) {
+ err = fib6_table_lookup(net, table, *oif, flp6, res, flags);
+ if (!err && res->f6i != net->ipv6.fib6_null_entry)
err = fib6_rule_saddr(net, rule, flags, flp6,
- fib6_info_nh_dev(f6i));
-
- if (likely(!err))
- arg->result = f6i;
- }
+ res->nh->fib_nh_dev);
return err;
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index cc14b9998941..afb915807cd0 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -168,22 +168,21 @@ static bool is_ineligible(const struct sk_buff *skb)
return false;
}
-static bool icmpv6_mask_allow(int type)
+static bool icmpv6_mask_allow(struct net *net, int type)
{
- /* Informational messages are not limited. */
- if (type & ICMPV6_INFOMSG_MASK)
+ if (type > ICMPV6_MSG_MAX)
return true;
- /* Do not limit pmtu discovery, it would break it. */
- if (type == ICMPV6_PKT_TOOBIG)
+ /* Limit if icmp type is set in ratemask. */
+ if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask))
return true;
return false;
}
-static bool icmpv6_global_allow(int type)
+static bool icmpv6_global_allow(struct net *net, int type)
{
- if (icmpv6_mask_allow(type))
+ if (icmpv6_mask_allow(net, type))
return true;
if (icmp_global_allow())
@@ -202,7 +201,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
struct dst_entry *dst;
bool res = false;
- if (icmpv6_mask_allow(type))
+ if (icmpv6_mask_allow(net, type))
return true;
/*
@@ -511,7 +510,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
local_bh_disable();
/* Check global sysctl_icmp_msgs_per_sec ratelimit */
- if (!(skb->dev->flags&IFF_LOOPBACK) && !icmpv6_global_allow(type))
+ if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
goto out_bh_enable;
mip6_addr_swap(skb);
@@ -731,6 +730,11 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
if (IS_ERR(dst))
goto out;
+ /* Check the ratelimit */
+ if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) ||
+ !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6))
+ goto out_dst_release;
+
idev = __in6_dev_get(skb->dev);
msg.skb = skb;
@@ -751,6 +755,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
skb->len + sizeof(struct icmp6hdr));
}
+out_dst_release:
dst_release(dst);
out:
icmpv6_xmit_unlock(sk);
@@ -1137,6 +1142,13 @@ static struct ctl_table ipv6_icmp_table_template[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "ratemask",
+ .data = &init_net.ipv6.sysctl.icmpv6_ratemask_ptr,
+ .maxlen = ICMPV6_MSG_MAX + 1,
+ .mode = 0644,
+ .proc_handler = proc_do_large_bitmap,
+ },
{ },
};
@@ -1153,6 +1165,7 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast;
+ table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr;
}
return table;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 46f54a5bb1f0..b47e15df9769 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -354,10 +354,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
}
/* called with rcu lock held; no reference taken on fib6_info */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
- int flags)
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+ struct fib6_result *res, int flags)
{
- return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+ return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6,
+ res, flags);
}
static void __net_init fib6_tables_init(struct net *net)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 66c8b294e02b..4c8e2ea8bf19 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -77,6 +77,8 @@ static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
+static bool ndisc_allow_add(const struct net_device *dev,
+ struct netlink_ext_ack *extack);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -117,6 +119,7 @@ struct neigh_table nd_tbl = {
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
+ .allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
.tbl = &nd_tbl,
@@ -392,6 +395,20 @@ static void pndisc_destructor(struct pneigh_entry *n)
ipv6_dev_mc_dec(dev, &maddr);
}
+/* called with rtnl held */
+static bool ndisc_allow_add(const struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ struct inet6_dev *idev = __in6_dev_get(dev);
+
+ if (!idev || idev->cnf.disable_ipv6) {
+ NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device");
+ return false;
+ }
+
+ return true;
+}
+
static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
int len)
{
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ddc99a1653aa..086fc669279e 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -23,14 +23,6 @@ config NF_TABLES_IPV6
if NF_TABLES_IPV6
-config NFT_CHAIN_ROUTE_IPV6
- tristate "IPv6 nf_tables route chain support"
- help
- This option enables the "route" chain for IPv6 in nf_tables. This
- chain type is used to force packet re-routing after mangling header
- fields such as the source, destination, flowlabel, hop-limit and
- the packet mark.
-
config NFT_REJECT_IPV6
select NF_REJECT_IPV6
default NFT_REJECT
@@ -278,15 +270,10 @@ if IP6_NF_NAT
config IP6_NF_TARGET_MASQUERADE
tristate "MASQUERADE target support"
- select NF_NAT_MASQUERADE
+ select NETFILTER_XT_TARGET_MASQUERADE
help
- Masquerading is a special case of NAT: all outgoing connections are
- changed to seem to come from a particular interface's address, and
- if the interface goes down, those connections are lost. This is
- only useful for dialup accounts with dynamic IP address (ie. your IP
- address will be different on next dialup).
-
- To compile it as a module, choose M here. If unsure, say N.
+ This is a backwards-compat option for the user's convenience
+ (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE.
config IP6_NF_TARGET_NPT
tristate "NPT (Network Prefix translation) target support"
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 3853c648ebaa..731a74c60dca 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,7 +27,6 @@ obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
# nf_tables
-obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
@@ -47,7 +46,6 @@ obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
obj-$(CONFIG_IP6_NF_MATCH_SRH) += ip6t_srh.o
# targets
-obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o
obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o
obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o
obj-$(CONFIG_IP6_NF_TARGET_SYNPROXY) += ip6t_SYNPROXY.o
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
deleted file mode 100644
index 29c7f1915a96..000000000000
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
- * NAT funded by Astaro.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/ipv6.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/addrconf.h>
-#include <net/ipv6.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
-
-static unsigned int
-masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
-{
- return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par));
-}
-
-static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
-{
- const struct nf_nat_range2 *range = par->targinfo;
-
- if (range->flags & NF_NAT_RANGE_MAP_IPS)
- return -EINVAL;
- return nf_ct_netns_get(par->net, par->family);
-}
-
-static void masquerade_tg6_destroy(const struct xt_tgdtor_param *par)
-{
- nf_ct_netns_put(par->net, par->family);
-}
-
-static struct xt_target masquerade_tg6_reg __read_mostly = {
- .name = "MASQUERADE",
- .family = NFPROTO_IPV6,
- .checkentry = masquerade_tg6_checkentry,
- .destroy = masquerade_tg6_destroy,
- .target = masquerade_tg6,
- .targetsize = sizeof(struct nf_nat_range),
- .table = "nat",
- .hooks = 1 << NF_INET_POST_ROUTING,
- .me = THIS_MODULE,
-};
-
-static int __init masquerade_tg6_init(void)
-{
- int err;
-
- err = xt_register_target(&masquerade_tg6_reg);
- if (err)
- return err;
-
- err = nf_nat_masquerade_ipv6_register_notifier();
- if (err)
- xt_unregister_target(&masquerade_tg6_reg);
-
- return err;
-}
-static void __exit masquerade_tg6_exit(void)
-{
- nf_nat_masquerade_ipv6_unregister_notifier();
- xt_unregister_target(&masquerade_tg6_reg);
-}
-
-module_init(masquerade_tg6_init);
-module_exit(masquerade_tg6_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_DESCRIPTION("Xtables: automatic address SNAT");
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
deleted file mode 100644
index da3f1f8cb325..000000000000
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-#include <net/route.h>
-
-static unsigned int nf_route_table_hook(void *priv,
- struct sk_buff *skb,
- const struct nf_hook_state *state)
-{
- unsigned int ret;
- struct nft_pktinfo pkt;
- struct in6_addr saddr, daddr;
- u_int8_t hop_limit;
- u32 mark, flowlabel;
- int err;
-
- nft_set_pktinfo(&pkt, skb, state);
- nft_set_pktinfo_ipv6(&pkt, skb);
-
- /* save source/dest address, mark, hoplimit, flowlabel, priority */
- memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
- memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
- mark = skb->mark;
- hop_limit = ipv6_hdr(skb)->hop_limit;
-
- /* flowlabel and prio (includes version, which shouldn't change either */
- flowlabel = *((u32 *)ipv6_hdr(skb));
-
- ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_STOLEN &&
- (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
- memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
- skb->mark != mark ||
- ipv6_hdr(skb)->hop_limit != hop_limit ||
- flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
- err = ip6_route_me_harder(state->net, skb);
- if (err < 0)
- ret = NF_DROP_ERR(err);
- }
-
- return ret;
-}
-
-static const struct nft_chain_type nft_chain_route_ipv6 = {
- .name = "route",
- .type = NFT_CHAIN_T_ROUTE,
- .family = NFPROTO_IPV6,
- .owner = THIS_MODULE,
- .hook_mask = (1 << NF_INET_LOCAL_OUT),
- .hooks = {
- [NF_INET_LOCAL_OUT] = nf_route_table_hook,
- },
-};
-
-static int __init nft_chain_route_init(void)
-{
- nft_register_chain_type(&nft_chain_route_ipv6);
-
- return 0;
-}
-
-static void __exit nft_chain_route_exit(void)
-{
- nft_unregister_chain_type(&nft_chain_route_ipv6);
-}
-
-module_init(nft_chain_route_init);
-module_exit(nft_chain_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route");
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5a426226c762..84dbe21b71e5 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1356,6 +1356,7 @@ const struct proto_ops inet6_sockraw_ops = {
.getname = inet6_getname,
.poll = datagram_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d555edaaff13..e8c73b7782cd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -110,7 +110,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
-static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
struct in6_addr *daddr,
struct in6_addr *saddr);
@@ -428,13 +428,15 @@ static bool rt6_check_expired(const struct rt6_info *rt)
return false;
}
-struct fib6_info *fib6_multipath_select(const struct net *net,
- struct fib6_info *match,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb,
- int strict)
+void fib6_select_path(const struct net *net, struct fib6_result *res,
+ struct flowi6 *fl6, int oif, bool have_oif_match,
+ const struct sk_buff *skb, int strict)
{
struct fib6_info *sibling, *next_sibling;
+ struct fib6_info *match = res->f6i;
+
+ if (!match->fib6_nsiblings || have_oif_match)
+ goto out;
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
@@ -443,7 +445,7 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
- return match;
+ goto out;
list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
fib6_siblings) {
@@ -459,7 +461,9 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
break;
}
- return match;
+out:
+ res->f6i = match;
+ res->nh = &match->fib6_nh;
}
/*
@@ -487,29 +491,42 @@ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh,
return false;
}
-static inline struct fib6_info *rt6_device_match(struct net *net,
- struct fib6_info *rt,
- const struct in6_addr *saddr,
- int oif,
- int flags)
+static void rt6_device_match(struct net *net, struct fib6_result *res,
+ const struct in6_addr *saddr, int oif, int flags)
{
- const struct fib6_nh *nh;
- struct fib6_info *sprt;
+ struct fib6_info *f6i = res->f6i;
+ struct fib6_info *spf6i;
+ struct fib6_nh *nh;
- if (!oif && ipv6_addr_any(saddr) &&
- !(rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD))
- return rt;
+ if (!oif && ipv6_addr_any(saddr)) {
+ nh = &f6i->fib6_nh;
+ if (!(nh->fib_nh_flags & RTNH_F_DEAD))
+ goto out;
+ }
- for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) {
- nh = &sprt->fib6_nh;
- if (__rt6_device_match(net, nh, saddr, oif, flags))
- return sprt;
+ for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
+ nh = &spf6i->fib6_nh;
+ if (__rt6_device_match(net, nh, saddr, oif, flags)) {
+ res->f6i = spf6i;
+ goto out;
+ }
}
- if (oif && flags & RT6_LOOKUP_F_IFACE)
- return net->ipv6.fib6_null_entry;
+ if (oif && flags & RT6_LOOKUP_F_IFACE) {
+ res->f6i = net->ipv6.fib6_null_entry;
+ nh = &res->f6i->fib6_nh;
+ goto out;
+ }
- return rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
+ nh = &f6i->fib6_nh;
+ if (nh->fib_nh_flags & RTNH_F_DEAD) {
+ res->f6i = net->ipv6.fib6_null_entry;
+ nh = &res->f6i->fib6_nh;
+ }
+out:
+ res->nh = nh;
+ res->fib6_type = res->f6i->fib6_type;
+ res->fib6_flags = res->f6i->fib6_flags;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
@@ -680,66 +697,70 @@ out:
return rc;
}
-static void __find_rr_leaf(struct fib6_info *rt_start,
+static void __find_rr_leaf(struct fib6_info *f6i_start,
struct fib6_info *nomatch, u32 metric,
- struct fib6_info **match, struct fib6_info **cont,
+ struct fib6_result *res, struct fib6_info **cont,
int oif, int strict, bool *do_rr, int *mpri)
{
- struct fib6_info *rt;
+ struct fib6_info *f6i;
- for (rt = rt_start;
- rt && rt != nomatch;
- rt = rcu_dereference(rt->fib6_next)) {
+ for (f6i = f6i_start;
+ f6i && f6i != nomatch;
+ f6i = rcu_dereference(f6i->fib6_next)) {
struct fib6_nh *nh;
- if (cont && rt->fib6_metric != metric) {
- *cont = rt;
+ if (cont && f6i->fib6_metric != metric) {
+ *cont = f6i;
return;
}
- if (fib6_check_expired(rt))
+ if (fib6_check_expired(f6i))
continue;
- nh = &rt->fib6_nh;
- if (find_match(nh, rt->fib6_flags, oif, strict, mpri, do_rr))
- *match = rt;
+ nh = &f6i->fib6_nh;
+ if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) {
+ res->f6i = f6i;
+ res->nh = nh;
+ res->fib6_flags = f6i->fib6_flags;
+ res->fib6_type = f6i->fib6_type;
+ }
}
}
-static struct fib6_info *find_rr_leaf(struct fib6_node *fn,
- struct fib6_info *leaf,
- struct fib6_info *rr_head,
- u32 metric, int oif, int strict,
- bool *do_rr)
+static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf,
+ struct fib6_info *rr_head, int oif, int strict,
+ bool *do_rr, struct fib6_result *res)
{
- struct fib6_info *match = NULL, *cont = NULL;
+ u32 metric = rr_head->fib6_metric;
+ struct fib6_info *cont = NULL;
int mpri = -1;
- __find_rr_leaf(rr_head, NULL, metric, &match, &cont,
+ __find_rr_leaf(rr_head, NULL, metric, res, &cont,
oif, strict, do_rr, &mpri);
- __find_rr_leaf(leaf, rr_head, metric, &match, &cont,
+ __find_rr_leaf(leaf, rr_head, metric, res, &cont,
oif, strict, do_rr, &mpri);
- if (match || !cont)
- return match;
+ if (res->f6i || !cont)
+ return;
- __find_rr_leaf(cont, NULL, metric, &match, NULL,
+ __find_rr_leaf(cont, NULL, metric, res, NULL,
oif, strict, do_rr, &mpri);
-
- return match;
}
-static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
- int oif, int strict)
+static void rt6_select(struct net *net, struct fib6_node *fn, int oif,
+ struct fib6_result *res, int strict)
{
struct fib6_info *leaf = rcu_dereference(fn->leaf);
- struct fib6_info *match, *rt0;
+ struct fib6_info *rt0;
bool do_rr = false;
int key_plen;
+ /* make sure this function or its helpers sets f6i */
+ res->f6i = NULL;
+
if (!leaf || leaf == net->ipv6.fib6_null_entry)
- return net->ipv6.fib6_null_entry;
+ goto out;
rt0 = rcu_dereference(fn->rr_ptr);
if (!rt0)
@@ -756,11 +777,9 @@ static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
key_plen = rt0->fib6_src.plen;
#endif
if (fn->fn_bit != key_plen)
- return net->ipv6.fib6_null_entry;
-
- match = find_rr_leaf(fn, leaf, rt0, rt0->fib6_metric, oif, strict,
- &do_rr);
+ goto out;
+ find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res);
if (do_rr) {
struct fib6_info *next = rcu_dereference(rt0->fib6_next);
@@ -777,12 +796,19 @@ static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
}
}
- return match ? match : net->ipv6.fib6_null_entry;
+out:
+ if (!res->f6i) {
+ res->f6i = net->ipv6.fib6_null_entry;
+ res->nh = &res->f6i->fib6_nh;
+ res->fib6_flags = res->f6i->fib6_flags;
+ res->fib6_type = res->f6i->fib6_type;
+ }
}
-static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
+static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res)
{
- return (rt->fib6_flags & RTF_NONEXTHOP) || rt->fib6_nh.fib_nh_gw_family;
+ return (res->f6i->fib6_flags & RTF_NONEXTHOP) ||
+ res->nh->fib_nh_gw_family;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -866,17 +892,17 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
*/
/* called with rcu_lock held */
-static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt)
+static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)
{
- struct net_device *dev = rt->fib6_nh.fib_nh_dev;
+ struct net_device *dev = res->nh->fib_nh_dev;
- if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
+ if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
/* for copies of local routes, dst->dev needs to be the
* device if it is a master device, the master device if
* device is enslaved, and the loopback as the default
*/
if (netif_is_l3_slave(dev) &&
- !rt6_need_strict(&rt->fib6_dst.addr))
+ !rt6_need_strict(&res->f6i->fib6_dst.addr))
dev = l3mdev_master_dev_rcu(dev);
else if (!netif_is_l3_master(dev))
dev = dev_net(dev)->loopback_dev;
@@ -922,11 +948,11 @@ static unsigned short fib6_info_dst_flags(struct fib6_info *rt)
return flags;
}
-static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
+static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type)
{
- rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
+ rt->dst.error = ip6_rt_type_to_error(fib6_type);
- switch (ort->fib6_type) {
+ switch (fib6_type) {
case RTN_BLACKHOLE:
rt->dst.output = dst_discard_out;
rt->dst.input = dst_discard;
@@ -944,26 +970,28 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
}
}
-static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
+static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res)
{
- if (ort->fib6_flags & RTF_REJECT) {
- ip6_rt_init_dst_reject(rt, ort);
+ struct fib6_info *f6i = res->f6i;
+
+ if (res->fib6_flags & RTF_REJECT) {
+ ip6_rt_init_dst_reject(rt, res->fib6_type);
return;
}
rt->dst.error = 0;
rt->dst.output = ip6_output;
- if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) {
+ if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) {
rt->dst.input = ip6_input;
- } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
+ } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
rt->dst.input = ip6_mc_input;
} else {
rt->dst.input = ip6_forward;
}
- if (ort->fib6_nh.fib_nh_lws) {
- rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.fib_nh_lws);
+ if (res->nh->fib_nh_lws) {
+ rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws);
lwtunnel_set_redirect(&rt->dst);
}
@@ -978,23 +1006,25 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
ip_dst_init_metrics(&rt->dst, from->fib6_metrics);
}
-/* Caller must already hold reference to @ort */
-static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
+/* Caller must already hold reference to f6i in result */
+static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res)
{
- struct net_device *dev = fib6_info_nh_dev(ort);
+ const struct fib6_nh *nh = res->nh;
+ const struct net_device *dev = nh->fib_nh_dev;
+ struct fib6_info *f6i = res->f6i;
- ip6_rt_init_dst(rt, ort);
+ ip6_rt_init_dst(rt, res);
- rt->rt6i_dst = ort->fib6_dst;
+ rt->rt6i_dst = f6i->fib6_dst;
rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
- rt->rt6i_flags = ort->fib6_flags;
- if (ort->fib6_nh.fib_nh_gw_family) {
- rt->rt6i_gateway = ort->fib6_nh.fib_nh_gw6;
+ rt->rt6i_flags = res->fib6_flags;
+ if (nh->fib_nh_gw_family) {
+ rt->rt6i_gateway = nh->fib_nh_gw6;
rt->rt6i_flags |= RTF_GATEWAY;
}
- rt6_set_from(rt, ort);
+ rt6_set_from(rt, f6i);
#ifdef CONFIG_IPV6_SUBTREES
- rt->rt6i_src = ort->fib6_src;
+ rt->rt6i_src = f6i->fib6_src;
#endif
}
@@ -1033,22 +1063,24 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt)
}
/* called with rcu_lock held */
-static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
+static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res)
{
- unsigned short flags = fib6_info_dst_flags(rt);
- struct net_device *dev = rt->fib6_nh.fib_nh_dev;
+ struct net_device *dev = res->nh->fib_nh_dev;
+ struct fib6_info *f6i = res->f6i;
+ unsigned short flags;
struct rt6_info *nrt;
- if (!fib6_info_hold_safe(rt))
+ if (!fib6_info_hold_safe(f6i))
goto fallback;
+ flags = fib6_info_dst_flags(f6i);
nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
if (!nrt) {
- fib6_info_release(rt);
+ fib6_info_release(f6i);
goto fallback;
}
- ip6_rt_copy_init(nrt, rt);
+ ip6_rt_copy_init(nrt, res);
return nrt;
fallback:
@@ -1063,7 +1095,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
const struct sk_buff *skb,
int flags)
{
- struct fib6_info *f6i;
+ struct fib6_result res = {};
struct fib6_node *fn;
struct rt6_info *rt;
@@ -1073,14 +1105,14 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
rcu_read_lock();
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
- f6i = rcu_dereference(fn->leaf);
- if (!f6i)
- f6i = net->ipv6.fib6_null_entry;
+ res.f6i = rcu_dereference(fn->leaf);
+ if (!res.f6i)
+ res.f6i = net->ipv6.fib6_null_entry;
else
- f6i = rt6_device_match(net, f6i, &fl6->saddr,
- fl6->flowi6_oif, flags);
+ rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif,
+ flags);
- if (f6i == net->ipv6.fib6_null_entry) {
+ if (res.f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
@@ -1090,20 +1122,20 @@ restart:
goto out;
}
- if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
- f6i = fib6_multipath_select(net, f6i, fl6, fl6->flowi6_oif, skb,
- flags);
+ fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
+ fl6->flowi6_oif != 0, skb, flags);
+
/* Search through exception table */
- rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
if (rt) {
if (ip6_hold_safe(net, &rt))
dst_use_noref(&rt->dst, jiffies);
} else {
- rt = ip6_create_rt_rcu(f6i);
+ rt = ip6_create_rt_rcu(&res);
}
out:
- trace_fib6_table_lookup(net, f6i, table, fl6);
+ trace_fib6_table_lookup(net, &res, table, fl6);
rcu_read_unlock();
@@ -1170,10 +1202,11 @@ int ip6_ins_rt(struct net *net, struct fib6_info *rt)
return __ip6_ins_rt(rt, &info, NULL);
}
-static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
+static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
+ struct fib6_info *f6i = res->f6i;
struct net_device *dev;
struct rt6_info *rt;
@@ -1181,25 +1214,25 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
* Clone the route.
*/
- if (!fib6_info_hold_safe(ort))
+ if (!fib6_info_hold_safe(f6i))
return NULL;
- dev = ip6_rt_get_dev_rcu(ort);
+ dev = ip6_rt_get_dev_rcu(res);
rt = ip6_dst_alloc(dev_net(dev), dev, 0);
if (!rt) {
- fib6_info_release(ort);
+ fib6_info_release(f6i);
return NULL;
}
- ip6_rt_copy_init(rt, ort);
+ ip6_rt_copy_init(rt, res);
rt->rt6i_flags |= RTF_CACHE;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *daddr;
rt->rt6i_dst.plen = 128;
- if (!rt6_is_gw_or_nonexthop(ort)) {
- if (ort->fib6_dst.plen != 128 &&
- ipv6_addr_equal(&ort->fib6_dst.addr, daddr))
+ if (!rt6_is_gw_or_nonexthop(res)) {
+ if (f6i->fib6_dst.plen != 128 &&
+ ipv6_addr_equal(&f6i->fib6_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
@@ -1212,34 +1245,35 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
return rt;
}
-static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
+static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
{
- unsigned short flags = fib6_info_dst_flags(rt);
+ struct fib6_info *f6i = res->f6i;
+ unsigned short flags = fib6_info_dst_flags(f6i);
struct net_device *dev;
struct rt6_info *pcpu_rt;
- if (!fib6_info_hold_safe(rt))
+ if (!fib6_info_hold_safe(f6i))
return NULL;
rcu_read_lock();
- dev = ip6_rt_get_dev_rcu(rt);
+ dev = ip6_rt_get_dev_rcu(res);
pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
if (!pcpu_rt) {
- fib6_info_release(rt);
+ fib6_info_release(f6i);
return NULL;
}
- ip6_rt_copy_init(pcpu_rt, rt);
+ ip6_rt_copy_init(pcpu_rt, res);
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
}
/* It should be called with rcu_read_lock() acquired */
-static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt)
+static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
{
struct rt6_info *pcpu_rt, **p;
- p = this_cpu_ptr(rt->rt6i_pcpu);
+ p = this_cpu_ptr(res->f6i->rt6i_pcpu);
pcpu_rt = *p;
if (pcpu_rt)
@@ -1249,18 +1283,18 @@ static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt)
}
static struct rt6_info *rt6_make_pcpu_route(struct net *net,
- struct fib6_info *rt)
+ const struct fib6_result *res)
{
struct rt6_info *pcpu_rt, *prev, **p;
- pcpu_rt = ip6_rt_pcpu_alloc(rt);
+ pcpu_rt = ip6_rt_pcpu_alloc(res);
if (!pcpu_rt) {
dst_hold(&net->ipv6.ip6_null_entry->dst);
return net->ipv6.ip6_null_entry;
}
dst_hold(&pcpu_rt->dst);
- p = this_cpu_ptr(rt->rt6i_pcpu);
+ p = this_cpu_ptr(res->f6i->rt6i_pcpu);
prev = cmpxchg(p, NULL, pcpu_rt);
BUG_ON(prev);
@@ -1403,14 +1437,15 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
return NULL;
}
-static unsigned int fib6_mtu(const struct fib6_info *rt)
+static unsigned int fib6_mtu(const struct fib6_result *res)
{
+ const struct fib6_nh *nh = res->nh;
unsigned int mtu;
- if (rt->fib6_pmtu) {
- mtu = rt->fib6_pmtu;
+ if (res->f6i->fib6_pmtu) {
+ mtu = res->f6i->fib6_pmtu;
} else {
- struct net_device *dev = fib6_info_nh_dev(rt);
+ struct net_device *dev = nh->fib_nh_dev;
struct inet6_dev *idev;
rcu_read_lock();
@@ -1421,26 +1456,27 @@ static unsigned int fib6_mtu(const struct fib6_info *rt)
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
- return mtu - lwtunnel_headroom(rt->fib6_nh.fib_nh_lws, mtu);
+ return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
}
static int rt6_insert_exception(struct rt6_info *nrt,
- struct fib6_info *ort)
+ const struct fib6_result *res)
{
struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
+ struct fib6_info *f6i = res->f6i;
int err = 0;
spin_lock_bh(&rt6_exception_lock);
- if (ort->exception_bucket_flushed) {
+ if (f6i->exception_bucket_flushed) {
err = -EINVAL;
goto out;
}
- bucket = rcu_dereference_protected(ort->rt6i_exception_bucket,
+ bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket,
lockdep_is_held(&rt6_exception_lock));
if (!bucket) {
bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
@@ -1449,24 +1485,24 @@ static int rt6_insert_exception(struct rt6_info *nrt,
err = -ENOMEM;
goto out;
}
- rcu_assign_pointer(ort->rt6i_exception_bucket, bucket);
+ rcu_assign_pointer(f6i->rt6i_exception_bucket, bucket);
}
#ifdef CONFIG_IPV6_SUBTREES
- /* rt6i_src.plen != 0 indicates ort is in subtree
+ /* fib6_src.plen != 0 indicates f6i is in subtree
* and exception table is indexed by a hash of
- * both rt6i_dst and rt6i_src.
+ * both fib6_dst and fib6_src.
* Otherwise, the exception table is indexed by
- * a hash of only rt6i_dst.
+ * a hash of only fib6_dst.
*/
- if (ort->fib6_src.plen)
+ if (f6i->fib6_src.plen)
src_key = &nrt->rt6i_src.addr;
#endif
- /* rt6_mtu_change() might lower mtu on ort.
+ /* rt6_mtu_change() might lower mtu on f6i.
* Only insert this exception route if its mtu
- * is less than ort's mtu value.
+ * is less than f6i's mtu value.
*/
- if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(ort)) {
+ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) {
err = -EINVAL;
goto out;
}
@@ -1495,9 +1531,9 @@ out:
/* Update fn->fn_sernum to invalidate all cached dst */
if (!err) {
- spin_lock_bh(&ort->fib6_table->tb6_lock);
- fib6_update_sernum(net, ort);
- spin_unlock_bh(&ort->fib6_table->tb6_lock);
+ spin_lock_bh(&f6i->fib6_table->tb6_lock);
+ fib6_update_sernum(net, f6i);
+ spin_unlock_bh(&f6i->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
@@ -1534,33 +1570,33 @@ out:
/* Find cached rt in the hash table inside passed in rt
* Caller has to hold rcu_read_lock()
*/
-static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
struct in6_addr *daddr,
struct in6_addr *saddr)
{
struct rt6_exception_bucket *bucket;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
- struct rt6_info *res = NULL;
+ struct rt6_info *ret = NULL;
- bucket = rcu_dereference(rt->rt6i_exception_bucket);
+ bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
#ifdef CONFIG_IPV6_SUBTREES
- /* rt6i_src.plen != 0 indicates rt is in subtree
+ /* fib6i_src.plen != 0 indicates f6i is in subtree
* and exception table is indexed by a hash of
- * both rt6i_dst and rt6i_src.
+ * both fib6_dst and fib6_src.
* Otherwise, the exception table is indexed by
- * a hash of only rt6i_dst.
+ * a hash of only fib6_dst.
*/
- if (rt->fib6_src.plen)
+ if (res->f6i->fib6_src.plen)
src_key = saddr;
#endif
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
- res = rt6_ex->rt6i;
+ ret = rt6_ex->rt6i;
- return res;
+ return ret;
}
/* Remove the passed in cached rt from the hash table that contains it */
@@ -1808,11 +1844,10 @@ void rt6_age_exceptions(struct fib6_info *rt,
}
/* must be called with rcu lock held */
-struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6, int strict)
+int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
+ struct flowi6 *fl6, struct fib6_result *res, int strict)
{
struct fib6_node *fn, *saved_fn;
- struct fib6_info *f6i;
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
@@ -1821,8 +1856,8 @@ struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
oif = 0;
redo_rt6_select:
- f6i = rt6_select(net, fn, oif, strict);
- if (f6i == net->ipv6.fib6_null_entry) {
+ rt6_select(net, fn, oif, res, strict);
+ if (res->f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
@@ -1834,16 +1869,16 @@ redo_rt6_select:
}
}
- trace_fib6_table_lookup(net, f6i, table, fl6);
+ trace_fib6_table_lookup(net, res, table, fl6);
- return f6i;
+ return 0;
}
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int oif, struct flowi6 *fl6,
const struct sk_buff *skb, int flags)
{
- struct fib6_info *f6i;
+ struct fib6_result res = {};
struct rt6_info *rt;
int strict = 0;
@@ -1854,19 +1889,18 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
rcu_read_lock();
- f6i = fib6_table_lookup(net, table, oif, fl6, strict);
- if (f6i == net->ipv6.fib6_null_entry) {
+ fib6_table_lookup(net, table, oif, fl6, &res, strict);
+ if (res.f6i == net->ipv6.fib6_null_entry) {
rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
return rt;
}
- if (f6i->fib6_nsiblings)
- f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
+ fib6_select_path(net, &res, fl6, oif, false, skb, strict);
/*Search through exception table */
- rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
if (rt) {
if (ip6_hold_safe(net, &rt))
dst_use_noref(&rt->dst, jiffies);
@@ -1874,7 +1908,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
rcu_read_unlock();
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
- !f6i->fib6_nh.fib_nh_gw_family)) {
+ !res.nh->fib_nh_gw_family)) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
@@ -1882,7 +1916,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
*/
struct rt6_info *uncached_rt;
- uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
+ uncached_rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
rcu_read_unlock();
@@ -1904,10 +1938,10 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *pcpu_rt;
local_bh_disable();
- pcpu_rt = rt6_get_pcpu_route(f6i);
+ pcpu_rt = rt6_get_pcpu_route(&res);
if (!pcpu_rt)
- pcpu_rt = rt6_make_pcpu_route(net, f6i);
+ pcpu_rt = rt6_make_pcpu_route(net, &res);
local_bh_enable();
rcu_read_unlock();
@@ -2326,15 +2360,23 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (rt6->rt6i_flags & RTF_CACHE)
rt6_update_exception_stamp_rt(rt6);
} else if (daddr) {
- struct fib6_info *from;
+ struct fib6_result res = {};
struct rt6_info *nrt6;
rcu_read_lock();
- from = rcu_dereference(rt6->from);
- nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
+ res.f6i = rcu_dereference(rt6->from);
+ if (!res.f6i) {
+ rcu_read_unlock();
+ return;
+ }
+ res.nh = &res.f6i->fib6_nh;
+ res.fib6_flags = res.f6i->fib6_flags;
+ res.fib6_type = res.f6i->fib6_type;
+
+ nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
- if (rt6_insert_exception(nrt6, from))
+ if (rt6_insert_exception(nrt6, &res))
dst_release_immediate(&nrt6->dst);
}
rcu_read_unlock();
@@ -2407,12 +2449,13 @@ void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst,
NULL);
}
-static bool ip6_redirect_nh_match(struct fib6_info *f6i,
- struct fib6_nh *nh,
+static bool ip6_redirect_nh_match(const struct fib6_result *res,
struct flowi6 *fl6,
const struct in6_addr *gw,
struct rt6_info **ret)
{
+ const struct fib6_nh *nh = res->nh;
+
if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family ||
fl6->flowi6_oif != nh->fib_nh_dev->ifindex)
return false;
@@ -2425,7 +2468,7 @@ static bool ip6_redirect_nh_match(struct fib6_info *f6i,
if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) {
struct rt6_info *rt_cache;
- rt_cache = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr);
if (rt_cache &&
ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) {
*ret = rt_cache;
@@ -2450,6 +2493,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
{
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
struct rt6_info *ret = NULL;
+ struct fib6_result res = {};
struct fib6_info *rt;
struct fib6_node *fn;
@@ -2467,14 +2511,14 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
for_each_fib6_node_rt_rcu(fn) {
+ res.f6i = rt;
+ res.nh = &rt->fib6_nh;
+
if (fib6_check_expired(rt))
continue;
if (rt->fib6_flags & RTF_REJECT)
break;
- if (fl6->flowi6_oif != rt->fib6_nh.fib_nh_dev->ifindex)
- continue;
- if (ip6_redirect_nh_match(rt, &rt->fib6_nh, fl6,
- &rdfl->gateway, &ret))
+ if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret))
goto out;
}
@@ -2491,15 +2535,20 @@ restart:
goto restart;
}
+ res.f6i = rt;
+ res.nh = &rt->fib6_nh;
out:
- if (ret)
+ if (ret) {
ip6_hold_safe(net, &ret);
- else
- ret = ip6_create_rt_rcu(rt);
+ } else {
+ res.fib6_flags = res.f6i->fib6_flags;
+ res.fib6_type = res.f6i->fib6_type;
+ ret = ip6_create_rt_rcu(&res);
+ }
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
+ trace_fib6_table_lookup(net, &res, table, fl6);
return ret;
};
@@ -2617,12 +2666,15 @@ out:
* based on ip6_dst_mtu_forward and exception logic of
* rt6_find_cached_rt; called with rcu_read_lock
*/
-u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
- struct in6_addr *saddr)
+u32 ip6_mtu_from_fib6(const struct fib6_result *res,
+ const struct in6_addr *daddr,
+ const struct in6_addr *saddr)
{
struct rt6_exception_bucket *bucket;
+ const struct fib6_nh *nh = res->nh;
+ struct fib6_info *f6i = res->f6i;
+ const struct in6_addr *src_key;
struct rt6_exception *rt6_ex;
- struct in6_addr *src_key;
struct inet6_dev *idev;
u32 mtu = 0;
@@ -2644,7 +2696,7 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
if (likely(!mtu)) {
- struct net_device *dev = fib6_info_nh_dev(f6i);
+ struct net_device *dev = nh->fib_nh_dev;
mtu = IPV6_MIN_MTU;
idev = __in6_dev_get(dev);
@@ -2654,7 +2706,7 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
out:
- return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu);
+ return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
}
struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
@@ -3306,9 +3358,13 @@ static int ip6_route_del(struct fib6_config *cfg,
struct fib6_nh *nh;
if (cfg->fc_flags & RTF_CACHE) {
+ struct fib6_result res = {
+ .f6i = rt,
+ };
int rc;
- rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
+ rt_cache = rt6_find_cached_rt(&res,
+ &cfg->fc_dst,
&cfg->fc_src);
if (rt_cache) {
rc = ip6_del_cached_rt(rt_cache, cfg);
@@ -3352,10 +3408,10 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
{
struct netevent_redirect netevent;
struct rt6_info *rt, *nrt = NULL;
+ struct fib6_result res = {};
struct ndisc_options ndopts;
struct inet6_dev *in6_dev;
struct neighbour *neigh;
- struct fib6_info *from;
struct rd_msg *msg;
int optlen, on_link;
u8 *lladdr;
@@ -3438,14 +3494,17 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NDISC_REDIRECT, &ndopts);
rcu_read_lock();
- from = rcu_dereference(rt->from);
+ res.f6i = rcu_dereference(rt->from);
/* This fib6_info_hold() is safe here because we hold reference to rt
* and rt already holds reference to fib6_info.
*/
- fib6_info_hold(from);
+ fib6_info_hold(res.f6i);
rcu_read_unlock();
- nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
+ res.nh = &res.f6i->fib6_nh;
+ res.fib6_flags = res.f6i->fib6_flags;
+ res.fib6_type = res.f6i->fib6_type;
+ nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL);
if (!nrt)
goto out;
@@ -3459,7 +3518,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
* a cached route because rt6_insert_exception() will
* takes care of it
*/
- if (rt6_insert_exception(nrt, from)) {
+ if (rt6_insert_exception(nrt, &res)) {
dst_release_immediate(&nrt->dst);
goto out;
}
@@ -3471,7 +3530,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
out:
- fib6_info_release(from);
+ fib6_info_release(res.f6i);
neigh_release(neigh);
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d538fafaf4a9..2464fba569b4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1045,6 +1045,8 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
/* The following checks are replicated from __ip6_datagram_connect()
* and intended to prevent BPF program called below from accessing
* bytes that are out of the bound specified by user in addr_len.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index d4c60523c549..2cac910c1cd4 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -618,6 +618,7 @@ static const struct proto_ops l2tp_ip_ops = {
.getname = l2tp_ip_getname,
.poll = datagram_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 37a69df17cab..4ec546cc1dd6 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -752,6 +752,7 @@ static const struct proto_ops l2tp_ip6_ops = {
.getname = l2tp_ip6_getname,
.poll = datagram_poll,
.ioctl = inet6_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 04d9946dcdba..f36cae785e82 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1070,7 +1070,6 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
{
struct pppol2tp_ioc_stats stats;
struct l2tp_session *session;
- int val;
switch (cmd) {
case PPPIOCGMRU:
@@ -1097,7 +1096,7 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
if (!session->session_id && !session->peer_session_id)
return -ENOSYS;
- if (get_user(val, (int __user *)arg))
+ if (!access_ok((int __user *)arg, sizeof(int)))
return -EFAULT;
break;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index b99e73a7e7e0..2017b7d780f5 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -320,14 +320,13 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
struct llc_sap *sap;
int rc = -EINVAL;
- dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
-
lock_sock(sk);
if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
goto out;
rc = -EAFNOSUPPORT;
if (unlikely(addr->sllc_family != AF_LLC))
goto out;
+ dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
rc = -ENODEV;
rcu_read_lock();
if (sk->sk_bound_dev_if) {
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 28d022a3eee3..ae4f0be3b393 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1195,6 +1195,9 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local,
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
+ if (local->in_reconfig)
+ return;
+
if (!check_sdata_in_driver(sdata))
return;
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 4700718e010f..37e372896230 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -167,8 +167,10 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
* The driver doesn't know anything about VLAN interfaces.
* Hence, don't send GTKs for VLAN interfaces to the driver.
*/
- if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE))
+ if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
+ ret = 1;
goto out_unsupported;
+ }
}
ret = drv_set_key(key->local, SET_KEY, sdata,
@@ -213,11 +215,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
/* all of these we can do in software - if driver can */
if (ret == 1)
return 0;
- if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) {
- if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
- return 0;
+ if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL))
return -EINVAL;
- }
return 0;
default:
return -EINVAL;
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 95eb5064fa91..b76a2aefa9ec 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -23,7 +23,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath);
static u32 mesh_table_hash(const void *addr, u32 len, u32 seed)
{
/* Use last four bytes of hw addr as hash index */
- return jhash_1word(*(u32 *)(addr+2), seed);
+ return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed);
}
static const struct rhashtable_params mesh_rht_params = {
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 7f8d93401ce0..bf0b187f994e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1568,7 +1568,15 @@ static void sta_ps_start(struct sta_info *sta)
return;
for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) {
- if (txq_has_queue(sta->sta.txq[tid]))
+ struct ieee80211_txq *txq = sta->sta.txq[tid];
+ struct txq_info *txqi = to_txq_info(txq);
+
+ spin_lock(&local->active_txq_lock[txq->ac]);
+ if (!list_empty(&txqi->schedule_order))
+ list_del_init(&txqi->schedule_order);
+ spin_unlock(&local->active_txq_lock[txq->ac]);
+
+ if (txq_has_queue(txq))
set_bit(tid, &sta->txq_buffered_tids);
else
clear_bit(tid, &sta->txq_buffered_tids);
diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h
index 366b9e6f043e..40141df09f25 100644
--- a/net/mac80211/trace_msg.h
+++ b/net/mac80211/trace_msg.h
@@ -1,4 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Portions of this file
+ * Copyright (C) 2019 Intel Corporation
+ */
+
#ifdef CONFIG_MAC80211_MESSAGE_TRACING
#if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
@@ -11,7 +16,7 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM mac80211_msg
-#define MAX_MSG_LEN 100
+#define MAX_MSG_LEN 120
DECLARE_EVENT_CLASS(mac80211_msg_event,
TP_PROTO(struct va_format *vaf),
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8a49a74c0a37..2e816dd67be7 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3221,6 +3221,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
u8 max_subframes = sta->sta.max_amsdu_subframes;
int max_frags = local->hw.max_tx_fragments;
int max_amsdu_len = sta->sta.max_amsdu_len;
+ int orig_truesize;
__be16 len;
void *data;
bool ret = false;
@@ -3261,6 +3262,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
if (!head || skb_is_gso(head))
goto out;
+ orig_truesize = head->truesize;
orig_len = head->len;
if (skb->len + head->len > max_amsdu_len)
@@ -3318,6 +3320,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
*frag_tail = skb;
out_recalc:
+ fq->memory_usage += head->truesize - orig_truesize;
if (head->len != orig_len) {
flow->backlog += head->len - orig_len;
tin->backlog_bytes += head->len - orig_len;
@@ -3646,16 +3649,17 @@ EXPORT_SYMBOL(ieee80211_tx_dequeue);
struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
{
struct ieee80211_local *local = hw_to_local(hw);
+ struct ieee80211_txq *ret = NULL;
struct txq_info *txqi = NULL;
- lockdep_assert_held(&local->active_txq_lock[ac]);
+ spin_lock_bh(&local->active_txq_lock[ac]);
begin:
txqi = list_first_entry_or_null(&local->active_txqs[ac],
struct txq_info,
schedule_order);
if (!txqi)
- return NULL;
+ goto out;
if (txqi->txq.sta) {
struct sta_info *sta = container_of(txqi->txq.sta,
@@ -3672,24 +3676,30 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
if (txqi->schedule_round == local->schedule_round[ac])
- return NULL;
+ goto out;
list_del_init(&txqi->schedule_order);
txqi->schedule_round = local->schedule_round[ac];
- return &txqi->txq;
+ ret = &txqi->txq;
+
+out:
+ spin_unlock_bh(&local->active_txq_lock[ac]);
+ return ret;
}
EXPORT_SYMBOL(ieee80211_next_txq);
-void ieee80211_return_txq(struct ieee80211_hw *hw,
- struct ieee80211_txq *txq)
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+ struct ieee80211_txq *txq,
+ bool force)
{
struct ieee80211_local *local = hw_to_local(hw);
struct txq_info *txqi = to_txq_info(txq);
- lockdep_assert_held(&local->active_txq_lock[txq->ac]);
+ spin_lock_bh(&local->active_txq_lock[txq->ac]);
if (list_empty(&txqi->schedule_order) &&
- (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) {
+ (force || !skb_queue_empty(&txqi->frags) ||
+ txqi->tin.backlog_packets)) {
/* If airtime accounting is active, always enqueue STAs at the
* head of the list to ensure that they only get moved to the
* back by the airtime DRR scheduler once they have a negative
@@ -3706,20 +3716,10 @@ void ieee80211_return_txq(struct ieee80211_hw *hw,
list_add_tail(&txqi->schedule_order,
&local->active_txqs[txq->ac]);
}
-}
-EXPORT_SYMBOL(ieee80211_return_txq);
-void ieee80211_schedule_txq(struct ieee80211_hw *hw,
- struct ieee80211_txq *txq)
- __acquires(txq_lock) __releases(txq_lock)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
- spin_lock_bh(&local->active_txq_lock[txq->ac]);
- ieee80211_return_txq(hw, txq);
spin_unlock_bh(&local->active_txq_lock[txq->ac]);
}
-EXPORT_SYMBOL(ieee80211_schedule_txq);
+EXPORT_SYMBOL(__ieee80211_schedule_txq);
bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
struct ieee80211_txq *txq)
@@ -3729,7 +3729,7 @@ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
struct sta_info *sta;
u8 ac = txq->ac;
- lockdep_assert_held(&local->active_txq_lock[ac]);
+ spin_lock_bh(&local->active_txq_lock[ac]);
if (!txqi->txq.sta)
goto out;
@@ -3759,34 +3759,27 @@ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
sta->airtime[ac].deficit += sta->airtime_weight;
list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]);
+ spin_unlock_bh(&local->active_txq_lock[ac]);
return false;
out:
if (!list_empty(&txqi->schedule_order))
list_del_init(&txqi->schedule_order);
+ spin_unlock_bh(&local->active_txq_lock[ac]);
return true;
}
EXPORT_SYMBOL(ieee80211_txq_may_transmit);
void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
- __acquires(txq_lock)
{
struct ieee80211_local *local = hw_to_local(hw);
spin_lock_bh(&local->active_txq_lock[ac]);
local->schedule_round[ac]++;
-}
-EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
- __releases(txq_lock)
-{
- struct ieee80211_local *local = hw_to_local(hw);
-
spin_unlock_bh(&local->active_txq_lock[ac]);
}
-EXPORT_SYMBOL(ieee80211_txq_schedule_end);
+EXPORT_SYMBOL(ieee80211_txq_schedule_start);
void __ieee80211_subif_start_xmit(struct sk_buff *skb,
struct net_device *dev,
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6548271209a0..02b281d3c167 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -404,11 +404,6 @@ config NF_NAT
forms of full Network Address Port Translation. This can be
controlled by iptables, ip6tables or nft.
-config NF_NAT_NEEDED
- bool
- depends on NF_NAT
- default y
-
config NF_NAT_AMANDA
tristate
depends on NF_CONNTRACK && NF_NAT
@@ -1002,6 +997,20 @@ config NETFILTER_XT_TARGET_REDIRECT
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_TARGET_MASQUERADE
+ tristate "MASQUERADE target support"
+ depends on NF_NAT
+ default m if NETFILTER_ADVANCED=n
+ select NF_NAT_MASQUERADE
+ help
+ Masquerading is a special case of NAT: all outgoing connections are
+ changed to seem to come from a particular interface's address, and
+ if the interface goes down, those connections are lost. This is
+ only useful for dialup accounts with dynamic IP address (ie. your IP
+ address will be different on next dialup).
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_TARGET_TEE
tristate '"TEE" - packet cloning to alternate destination'
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4894a85cdd0b..72cca6b48960 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -77,7 +77,8 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o
nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
- nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
+ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \
+ nft_chain_route.o
nf_tables_set-objs := nf_tables_set_core.o \
nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
@@ -147,6 +148,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o
obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o
obj-$(CONFIG_NETFILTER_XT_TARGET_REDIRECT) += xt_REDIRECT.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_MASQUERADE) += xt_MASQUERADE.o
obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 93aaec3a54ec..71f06900473e 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -23,6 +23,7 @@
#include <linux/mm.h>
#include <linux/rcupdate.h>
#include <net/net_namespace.h>
+#include <net/netfilter/nf_queue.h>
#include <net/sock.h>
#include "nf_internals.h"
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 4b933669fd83..ab119a7540db 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -831,6 +831,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
conn_flags |= IP_VS_CONN_F_INACTIVE;
+ /* set the tunnel info */
+ dest->tun_type = udest->tun_type;
+ dest->tun_port = udest->tun_port;
+
/* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) {
conn_flags |= IP_VS_CONN_F_NOOUTPUT;
@@ -987,6 +991,13 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
return -ERANGE;
}
+ if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+ if (udest->tun_port == 0) {
+ pr_err("%s(): tunnel port is zero\n", __func__);
+ return -EINVAL;
+ }
+ }
+
ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
/* We use function that requires RCU lock */
@@ -1051,6 +1062,13 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
return -ERANGE;
}
+ if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+ if (udest->tun_port == 0) {
+ pr_err("%s(): tunnel port is zero\n", __func__);
+ return -EINVAL;
+ }
+ }
+
ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
/* We use function that requires RCU lock */
@@ -2333,6 +2351,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
udest->u_threshold = udest_compat->u_threshold;
udest->l_threshold = udest_compat->l_threshold;
udest->af = AF_INET;
+ udest->tun_type = IP_VS_CONN_F_TUNNEL_TYPE_IPIP;
}
static int
@@ -2890,6 +2909,8 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
[IPVS_DEST_ATTR_PERSIST_CONNS] = { .type = NLA_U32 },
[IPVS_DEST_ATTR_STATS] = { .type = NLA_NESTED },
[IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 },
+ [IPVS_DEST_ATTR_TUN_TYPE] = { .type = NLA_U8 },
+ [IPVS_DEST_ATTR_TUN_PORT] = { .type = NLA_U16 },
};
static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
@@ -3193,6 +3214,10 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
IP_VS_CONN_F_FWD_MASK)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_WEIGHT,
atomic_read(&dest->weight)) ||
+ nla_put_u8(skb, IPVS_DEST_ATTR_TUN_TYPE,
+ dest->tun_type) ||
+ nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT,
+ dest->tun_port) ||
nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) ||
nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) ||
nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS,
@@ -3315,12 +3340,14 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
/* If a full entry was requested, check for the additional fields */
if (full_entry) {
struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh,
- *nla_l_thresh;
+ *nla_l_thresh, *nla_tun_type, *nla_tun_port;
nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD];
nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT];
nla_u_thresh = attrs[IPVS_DEST_ATTR_U_THRESH];
nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH];
+ nla_tun_type = attrs[IPVS_DEST_ATTR_TUN_TYPE];
+ nla_tun_port = attrs[IPVS_DEST_ATTR_TUN_PORT];
if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh))
return -EINVAL;
@@ -3330,6 +3357,12 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
udest->weight = nla_get_u32(nla_weight);
udest->u_threshold = nla_get_u32(nla_u_thresh);
udest->l_threshold = nla_get_u32(nla_l_thresh);
+
+ if (nla_tun_type)
+ udest->tun_type = nla_get_u8(nla_tun_type);
+
+ if (nla_tun_port)
+ udest->tun_port = nla_get_be16(nla_tun_port);
}
return 0;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 175349fcf91f..8d6f94b67772 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -32,6 +32,7 @@
#include <linux/slab.h>
#include <linux/tcp.h> /* for tcphdr */
#include <net/ip.h>
+#include <net/gue.h>
#include <net/tcp.h> /* for csum_tcpudp_magic */
#include <net/udp.h>
#include <net/icmp.h> /* for icmp_send */
@@ -382,6 +383,10 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
mtu = dst_mtu(&rt->dst);
} else {
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
+ if (!dest)
+ goto err_put;
+ if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto err_put;
@@ -533,6 +538,10 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
mtu = dst_mtu(&rt->dst);
else {
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
+ if (!dest)
+ goto err_put;
+ if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
@@ -989,6 +998,41 @@ static inline int __tun_gso_type_mask(int encaps_af, int orig_af)
}
}
+static int
+ipvs_gue_encap(struct net *net, struct sk_buff *skb,
+ struct ip_vs_conn *cp, __u8 *next_protocol)
+{
+ __be16 dport;
+ __be16 sport = udp_flow_src_port(net, skb, 0, 0, false);
+ struct udphdr *udph; /* Our new UDP header */
+ struct guehdr *gueh; /* Our new GUE header */
+
+ skb_push(skb, sizeof(struct guehdr));
+
+ gueh = (struct guehdr *)skb->data;
+
+ gueh->control = 0;
+ gueh->version = 0;
+ gueh->hlen = 0;
+ gueh->flags = 0;
+ gueh->proto_ctype = *next_protocol;
+
+ skb_push(skb, sizeof(struct udphdr));
+ skb_reset_transport_header(skb);
+
+ udph = udp_hdr(skb);
+
+ dport = cp->dest->tun_port;
+ udph->dest = dport;
+ udph->source = sport;
+ udph->len = htons(skb->len);
+ udph->check = 0;
+
+ *next_protocol = IPPROTO_UDP;
+
+ return 0;
+}
+
/*
* IP Tunneling transmitter
*
@@ -1025,6 +1069,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
+ int tun_type, gso_type;
EnterFunction(10);
@@ -1046,6 +1091,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
+ tun_type = cp->dest->tun_type;
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+
/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
@@ -1054,11 +1104,20 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (IS_ERR(skb))
goto tx_error;
- if (iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET, cp->af)))
+ gso_type = __tun_gso_type_mask(AF_INET, cp->af);
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ gso_type |= SKB_GSO_UDP_TUNNEL;
+
+ if (iptunnel_handle_offloads(skb, gso_type))
goto tx_error;
skb->transport_header = skb->network_header;
+ skb_set_inner_ipproto(skb, next_protocol);
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ ipvs_gue_encap(net, skb, cp, &next_protocol);
+
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1102,6 +1161,8 @@ int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
+ struct netns_ipvs *ipvs = cp->ipvs;
+ struct net *net = ipvs->net;
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
@@ -1112,10 +1173,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ipv6hdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int ret, local;
+ int tun_type, gso_type;
EnterFunction(10);
- local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+ local = __ip_vs_get_out_rt_v6(ipvs, cp->af, skb, cp->dest,
&cp->daddr.in6,
&saddr, ipvsh, 1,
IP_VS_RT_MODE_LOCAL |
@@ -1134,17 +1196,31 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
+ tun_type = cp->dest->tun_type;
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+
skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
&next_protocol, &payload_len,
&dsfield, &ttl, NULL);
if (IS_ERR(skb))
goto tx_error;
- if (iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET6, cp->af)))
+ gso_type = __tun_gso_type_mask(AF_INET6, cp->af);
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ gso_type |= SKB_GSO_UDP_TUNNEL;
+
+ if (iptunnel_handle_offloads(skb, gso_type))
goto tx_error;
skb->transport_header = skb->network_header;
+ skb_set_inner_ipproto(skb, next_protocol);
+
+ if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+ ipvs_gue_encap(net, skb, cp, &next_protocol);
+
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1167,7 +1243,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
- ip6_local_out(cp->ipvs->net, skb->sk, skb);
+ ip6_local_out(net, skb->sk, skb);
else if (ret == NF_DROP)
kfree_skb(skb);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 334d6e5b7762..59c18804a10a 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -336,7 +336,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
exp->tuple.dst.u.all = *dst;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
#endif
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 66c596d287a5..32fe3060375a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -45,7 +45,7 @@
#include <net/netfilter/nf_conntrack_timestamp.h>
#include <net/netfilter/nf_conntrack_labels.h>
#include <net/netfilter/nf_conntrack_synproxy.h>
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_helper.h>
#endif
@@ -655,7 +655,7 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct)
+ nla_total_size(0) /* CTA_HELP */
+ nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
+ ctnetlink_secctx_size(ct)
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
+ 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
#endif
@@ -1494,7 +1494,7 @@ static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl,
return -EOPNOTSUPP;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
static int
ctnetlink_parse_nat_setup(struct nf_conn *ct,
enum nf_nat_manip_type manip,
@@ -1586,7 +1586,7 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
static int
ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
{
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
int ret;
if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
@@ -2369,7 +2369,7 @@ ctnetlink_glue_build_size(const struct nf_conn *ct)
+ nla_total_size(0) /* CTA_HELP */
+ nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
+ ctnetlink_secctx_size(ct)
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
+ 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
#endif
@@ -2699,7 +2699,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
struct nf_conn *master = exp->master;
long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
struct nf_conn_help *help;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nlattr *nest_parms;
struct nf_conntrack_tuple nat_tuple = {};
#endif
@@ -2717,7 +2717,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
CTA_EXPECT_MASTER) < 0)
goto nla_put_failure;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) ||
exp->saved_proto.all) {
nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED);
@@ -3180,7 +3180,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
struct nf_conntrack_expect *exp,
u_int8_t u3)
{
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nlattr *tb[CTA_EXPECT_NAT_MAX+1];
struct nf_conntrack_tuple nat_tuple = {};
int err;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 39fcc1ed18f3..d5454d1031a3 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -928,7 +928,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
nfct_help(exp->master)->helper != nfct_help(ct)->helper ||
exp->class != class)
break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
if (!direct_rtp &&
(!nf_inet_addr_cmp(&exp->saved_addr, &exp->tuple.dst.u3) ||
exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) &&
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 1d291a51cd45..6452550d187f 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -235,13 +235,10 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
if (tuplehash == NULL)
return NF_ACCEPT;
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+ outdev = rt->dst.dev;
if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
(ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
@@ -452,13 +449,10 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
if (tuplehash == NULL)
return NF_ACCEPT;
- outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
- if (!outdev)
- return NF_ACCEPT;
-
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
+ outdev = rt->dst.dev;
if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
return NF_ACCEPT;
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index e15779fd58e3..d6c43902ebd7 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -7,9 +7,6 @@
#include <linux/netdevice.h>
/* nf_queue.c */
-int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
- const struct nf_hook_entries *entries, unsigned int index,
- unsigned int verdict);
void nf_queue_nf_hook_drop(struct net *net);
/* nf_log.c */
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index af7dc6537758..a9ec49edd7f4 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1009,7 +1009,7 @@ static struct nf_ct_helper_expectfn follow_master_nat = {
.expectfn = nf_nat_follow_master,
};
-int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
+int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
const struct nf_hook_ops *orig_nat_ops, unsigned int ops_count)
{
struct nat_net *nat_net = net_generic(net, nat_net_id);
@@ -1019,14 +1019,12 @@ int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
struct nf_hook_ops *nat_ops;
int i, ret;
- if (WARN_ON_ONCE(ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
+ if (WARN_ON_ONCE(pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
return -EINVAL;
- nat_proto_net = &nat_net->nat_proto_net[ops->pf];
+ nat_proto_net = &nat_net->nat_proto_net[pf];
for (i = 0; i < ops_count; i++) {
- if (WARN_ON(orig_nat_ops[i].pf != ops->pf))
- return -EINVAL;
if (orig_nat_ops[i].hooknum == hooknum) {
hooknum = i;
break;
@@ -1086,8 +1084,8 @@ int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
return ret;
}
-void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
- unsigned int ops_count)
+void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
+ unsigned int ops_count)
{
struct nat_net *nat_net = net_generic(net, nat_net_id);
struct nf_nat_hooks_net *nat_proto_net;
@@ -1096,10 +1094,10 @@ void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
int hooknum = ops->hooknum;
int i;
- if (ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net))
+ if (pf >= ARRAY_SIZE(nat_net->nat_proto_net))
return;
- nat_proto_net = &nat_net->nat_proto_net[ops->pf];
+ nat_proto_net = &nat_net->nat_proto_net[pf];
mutex_lock(&nf_nat_proto_mutex);
if (WARN_ON(nat_proto_net->users == 0))
diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c
index d85c4d902e7b..8e8a65d46345 100644
--- a/net/netfilter/nf_nat_masquerade.c
+++ b/net/netfilter/nf_nat_masquerade.c
@@ -7,12 +7,10 @@
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
static DEFINE_MUTEX(masq_mutex);
-static unsigned int masq_refcnt4 __read_mostly;
-static unsigned int masq_refcnt6 __read_mostly;
+static unsigned int masq_refcnt __read_mostly;
unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
@@ -137,56 +135,6 @@ static struct notifier_block masq_inet_notifier = {
.notifier_call = masq_inet_event,
};
-int nf_nat_masquerade_ipv4_register_notifier(void)
-{
- int ret = 0;
-
- mutex_lock(&masq_mutex);
- if (WARN_ON_ONCE(masq_refcnt4 == UINT_MAX)) {
- ret = -EOVERFLOW;
- goto out_unlock;
- }
-
- /* check if the notifier was already set */
- if (++masq_refcnt4 > 1)
- goto out_unlock;
-
- /* Register for device down reports */
- ret = register_netdevice_notifier(&masq_dev_notifier);
- if (ret)
- goto err_dec;
- /* Register IP address change reports */
- ret = register_inetaddr_notifier(&masq_inet_notifier);
- if (ret)
- goto err_unregister;
-
- mutex_unlock(&masq_mutex);
- return ret;
-
-err_unregister:
- unregister_netdevice_notifier(&masq_dev_notifier);
-err_dec:
- masq_refcnt4--;
-out_unlock:
- mutex_unlock(&masq_mutex);
- return ret;
-}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
-
-void nf_nat_masquerade_ipv4_unregister_notifier(void)
-{
- mutex_lock(&masq_mutex);
- /* check if the notifier still has clients */
- if (--masq_refcnt4 > 0)
- goto out_unlock;
-
- unregister_netdevice_notifier(&masq_dev_notifier);
- unregister_inetaddr_notifier(&masq_inet_notifier);
-out_unlock:
- mutex_unlock(&masq_mutex);
-}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
-
#if IS_ENABLED(CONFIG_IPV6)
static atomic_t v6_worker_count __read_mostly;
@@ -322,44 +270,68 @@ static struct notifier_block masq_inet6_notifier = {
.notifier_call = masq_inet6_event,
};
-int nf_nat_masquerade_ipv6_register_notifier(void)
+static int nf_nat_masquerade_ipv6_register_notifier(void)
+{
+ return register_inet6addr_notifier(&masq_inet6_notifier);
+}
+#else
+static inline int nf_nat_masquerade_ipv6_register_notifier(void) { return 0; }
+#endif
+
+int nf_nat_masquerade_inet_register_notifiers(void)
{
int ret = 0;
mutex_lock(&masq_mutex);
- if (WARN_ON_ONCE(masq_refcnt6 == UINT_MAX)) {
+ if (WARN_ON_ONCE(masq_refcnt == UINT_MAX)) {
ret = -EOVERFLOW;
goto out_unlock;
}
- /* check if the notifier is already set */
- if (++masq_refcnt6 > 1)
+ /* check if the notifier was already set */
+ if (++masq_refcnt > 1)
goto out_unlock;
- ret = register_inet6addr_notifier(&masq_inet6_notifier);
+ /* Register for device down reports */
+ ret = register_netdevice_notifier(&masq_dev_notifier);
if (ret)
goto err_dec;
+ /* Register IP address change reports */
+ ret = register_inetaddr_notifier(&masq_inet_notifier);
+ if (ret)
+ goto err_unregister;
+
+ ret = nf_nat_masquerade_ipv6_register_notifier();
+ if (ret)
+ goto err_unreg_inet;
mutex_unlock(&masq_mutex);
return ret;
+err_unreg_inet:
+ unregister_inetaddr_notifier(&masq_inet_notifier);
+err_unregister:
+ unregister_netdevice_notifier(&masq_dev_notifier);
err_dec:
- masq_refcnt6--;
+ masq_refcnt--;
out_unlock:
mutex_unlock(&masq_mutex);
return ret;
}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_register_notifiers);
-void nf_nat_masquerade_ipv6_unregister_notifier(void)
+void nf_nat_masquerade_inet_unregister_notifiers(void)
{
mutex_lock(&masq_mutex);
- /* check if the notifier still has clients */
- if (--masq_refcnt6 > 0)
+ /* check if the notifiers still have clients */
+ if (--masq_refcnt > 0)
goto out_unlock;
+ unregister_netdevice_notifier(&masq_dev_notifier);
+ unregister_inetaddr_notifier(&masq_inet_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
unregister_inet6addr_notifier(&masq_inet6_notifier);
+#endif
out_unlock:
mutex_unlock(&masq_mutex);
}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
-#endif
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_unregister_notifiers);
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 62743da3004f..84f5c90a7f21 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -725,7 +725,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
return ret;
}
-static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
+const struct nf_hook_ops nf_nat_ipv4_ops[] = {
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv4_in,
@@ -758,13 +758,14 @@ static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
- return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+ return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops,
+ ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn);
void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
- nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+ nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn);
@@ -925,20 +926,6 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
return ret;
}
-static int nat_route_me_harder(struct net *net, struct sk_buff *skb)
-{
-#ifdef CONFIG_IPV6_MODULE
- const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
-
- if (!v6_ops)
- return -EHOSTUNREACH;
-
- return v6_ops->route_me_harder(net, skb);
-#else
- return ip6_route_me_harder(net, skb);
-#endif
-}
-
static unsigned int
nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
@@ -958,7 +945,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
- err = nat_route_me_harder(state->net, skb);
+ err = nf_ip6_route_me_harder(state->net, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
@@ -977,7 +964,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
return ret;
}
-static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
+const struct nf_hook_ops nf_nat_ipv6_ops[] = {
/* Before packet filtering, change destination */
{
.hook = nf_nat_ipv6_in,
@@ -1010,14 +997,44 @@ static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops)
{
- return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops,
+ return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops,
ARRAY_SIZE(nf_nat_ipv6_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn);
void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
{
- nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+ nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
}
EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn);
#endif /* CONFIG_IPV6 */
+
+#if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT)
+int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+ int ret;
+
+ if (WARN_ON_ONCE(ops->pf != NFPROTO_INET))
+ return -EINVAL;
+
+ ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops,
+ ARRAY_SIZE(nf_nat_ipv6_ops));
+ if (ret)
+ return ret;
+
+ ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops,
+ ARRAY_SIZE(nf_nat_ipv4_ops));
+ if (ret)
+ nf_nat_ipv6_unregister_fn(net, ops);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn);
+
+void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+ nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+ nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn);
+#endif /* NFT INET NAT */
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index a36a77bae1d6..9dc1d6e04946 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -240,6 +240,7 @@ int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
return 0;
}
+EXPORT_SYMBOL_GPL(nf_queue);
static unsigned int nf_iterate(struct sk_buff *skb,
struct nf_hook_state *state,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 90e6b09ef2af..e058273c5dde 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3193,9 +3193,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
static __be64 nf_jiffies64_to_msecs(u64 input)
{
- u64 ms = jiffies64_to_nsecs(input);
-
- return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC));
+ return cpu_to_be64(jiffies64_to_msecs(input));
}
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
@@ -3438,8 +3436,7 @@ err:
return err;
}
-static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
- struct nft_set_desc *desc,
+static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
const struct nlattr *nla)
{
struct nlattr *da[NFTA_SET_DESC_MAX + 1];
@@ -3565,7 +3562,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
if (nla[NFTA_SET_DESC] != NULL) {
- err = nf_tables_set_desc_parse(&ctx, &desc, nla[NFTA_SET_DESC]);
+ err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
if (err < 0)
return err;
}
@@ -3785,8 +3782,8 @@ bind:
}
EXPORT_SYMBOL_GPL(nf_tables_bind_set);
-void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding, bool event)
+static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
+ struct nft_set_binding *binding, bool event)
{
list_del_rcu(&binding->list);
@@ -3797,7 +3794,6 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
GFP_KERNEL);
}
}
-EXPORT_SYMBOL_GPL(nf_tables_unbind_set);
void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *binding,
@@ -7533,6 +7529,7 @@ static int __init nf_tables_module_init(void)
if (err < 0)
goto err5;
+ nft_chain_route_init();
return err;
err5:
rhltable_destroy(&nft_objname_ht);
@@ -7552,6 +7549,7 @@ static void __exit nf_tables_module_exit(void)
nfnetlink_subsys_unregister(&nf_tables_subsys);
unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
nft_chain_filter_fini();
+ nft_chain_route_fini();
unregister_pernet_subsys(&nf_tables_net_ops);
cancel_work_sync(&trans_destroy_work);
rcu_barrier();
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 1f1d90c1716b..7b827bcb412c 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -255,9 +255,9 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
}
EXPORT_SYMBOL_GPL(nf_osf_match);
-const char *nf_osf_find(const struct sk_buff *skb,
- const struct list_head *nf_osf_fingers,
- const int ttl_check)
+bool nf_osf_find(const struct sk_buff *skb,
+ const struct list_head *nf_osf_fingers,
+ const int ttl_check, struct nf_osf_data *data)
{
const struct iphdr *ip = ip_hdr(skb);
const struct nf_osf_user_finger *f;
@@ -265,24 +265,24 @@ const char *nf_osf_find(const struct sk_buff *skb,
const struct nf_osf_finger *kf;
struct nf_osf_hdr_ctx ctx;
const struct tcphdr *tcp;
- const char *genre = NULL;
memset(&ctx, 0, sizeof(ctx));
tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
if (!tcp)
- return NULL;
+ return false;
list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
f = &kf->finger;
if (!nf_osf_match_one(skb, f, ttl_check, &ctx))
continue;
- genre = f->genre;
+ data->genre = f->genre;
+ data->version = f->version;
break;
}
- return genre;
+ return true;
}
EXPORT_SYMBOL_GPL(nf_osf_find);
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index ee4852088d50..2f89bde3c61c 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -74,6 +74,36 @@ static const struct nft_chain_type nft_chain_nat_ipv6 = {
};
#endif
+#ifdef CONFIG_NF_TABLES_INET
+static int nft_nat_inet_reg(struct net *net, const struct nf_hook_ops *ops)
+{
+ return nf_nat_inet_register_fn(net, ops);
+}
+
+static void nft_nat_inet_unreg(struct net *net, const struct nf_hook_ops *ops)
+{
+ nf_nat_inet_unregister_fn(net, ops);
+}
+
+static const struct nft_chain_type nft_chain_nat_inet = {
+ .name = "nat",
+ .type = NFT_CHAIN_T_NAT,
+ .family = NFPROTO_INET,
+ .hook_mask = (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_POST_ROUTING),
+ .hooks = {
+ [NF_INET_PRE_ROUTING] = nft_nat_do_chain,
+ [NF_INET_LOCAL_IN] = nft_nat_do_chain,
+ [NF_INET_LOCAL_OUT] = nft_nat_do_chain,
+ [NF_INET_POST_ROUTING] = nft_nat_do_chain,
+ },
+ .ops_register = nft_nat_inet_reg,
+ .ops_unregister = nft_nat_inet_unreg,
+};
+#endif
+
static int __init nft_chain_nat_init(void)
{
#ifdef CONFIG_NF_TABLES_IPV6
@@ -82,6 +112,9 @@ static int __init nft_chain_nat_init(void)
#ifdef CONFIG_NF_TABLES_IPV4
nft_register_chain_type(&nft_chain_nat_ipv4);
#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_register_chain_type(&nft_chain_nat_inet);
+#endif
return 0;
}
@@ -94,6 +127,9 @@ static void __exit nft_chain_nat_exit(void)
#ifdef CONFIG_NF_TABLES_IPV6
nft_unregister_chain_type(&nft_chain_nat_ipv6);
#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_unregister_chain_type(&nft_chain_nat_inet);
+#endif
}
module_init(nft_chain_nat_init);
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
new file mode 100644
index 000000000000..8826bbe71136
--- /dev/null
+++ b/net/netfilter/nft_chain_route.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/skbuff.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+#ifdef CONFIG_NF_TABLES_IPV4
+static unsigned int nf_route_table_hook4(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ const struct iphdr *iph;
+ struct nft_pktinfo pkt;
+ __be32 saddr, daddr;
+ unsigned int ret;
+ u32 mark;
+ int err;
+ u8 tos;
+
+ nft_set_pktinfo(&pkt, skb, state);
+ nft_set_pktinfo_ipv4(&pkt, skb);
+
+ mark = skb->mark;
+ iph = ip_hdr(skb);
+ saddr = iph->saddr;
+ daddr = iph->daddr;
+ tos = iph->tos;
+
+ ret = nft_do_chain(&pkt, priv);
+ if (ret == NF_ACCEPT) {
+ iph = ip_hdr(skb);
+
+ if (iph->saddr != saddr ||
+ iph->daddr != daddr ||
+ skb->mark != mark ||
+ iph->tos != tos) {
+ err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+ }
+ return ret;
+}
+
+static const struct nft_chain_type nft_chain_route_ipv4 = {
+ .name = "route",
+ .type = NFT_CHAIN_T_ROUTE,
+ .family = NFPROTO_IPV4,
+ .hook_mask = (1 << NF_INET_LOCAL_OUT),
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nf_route_table_hook4,
+ },
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static unsigned int nf_route_table_hook6(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct in6_addr saddr, daddr;
+ struct nft_pktinfo pkt;
+ u32 mark, flowlabel;
+ unsigned int ret;
+ u8 hop_limit;
+ int err;
+
+ nft_set_pktinfo(&pkt, skb, state);
+ nft_set_pktinfo_ipv6(&pkt, skb);
+
+ /* save source/dest address, mark, hoplimit, flowlabel, priority */
+ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+ memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+ mark = skb->mark;
+ hop_limit = ipv6_hdr(skb)->hop_limit;
+
+ /* flowlabel and prio (includes version, which shouldn't change either)*/
+ flowlabel = *((u32 *)ipv6_hdr(skb));
+
+ ret = nft_do_chain(&pkt, priv);
+ if (ret == NF_ACCEPT &&
+ (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
+ memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
+ skb->mark != mark ||
+ ipv6_hdr(skb)->hop_limit != hop_limit ||
+ flowlabel != *((u32 *)ipv6_hdr(skb)))) {
+ err = nf_ip6_route_me_harder(state->net, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+
+ return ret;
+}
+
+static const struct nft_chain_type nft_chain_route_ipv6 = {
+ .name = "route",
+ .type = NFT_CHAIN_T_ROUTE,
+ .family = NFPROTO_IPV6,
+ .hook_mask = (1 << NF_INET_LOCAL_OUT),
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nf_route_table_hook6,
+ },
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_INET
+static unsigned int nf_route_table_inet(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct nft_pktinfo pkt;
+
+ switch (state->pf) {
+ case NFPROTO_IPV4:
+ return nf_route_table_hook4(priv, skb, state);
+ case NFPROTO_IPV6:
+ return nf_route_table_hook6(priv, skb, state);
+ default:
+ nft_set_pktinfo(&pkt, skb, state);
+ break;
+ }
+
+ return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_route_inet = {
+ .name = "route",
+ .type = NFT_CHAIN_T_ROUTE,
+ .family = NFPROTO_INET,
+ .hook_mask = (1 << NF_INET_LOCAL_OUT),
+ .hooks = {
+ [NF_INET_LOCAL_OUT] = nf_route_table_inet,
+ },
+};
+#endif
+
+void __init nft_chain_route_init(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+ nft_register_chain_type(&nft_chain_route_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+ nft_register_chain_type(&nft_chain_route_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_register_chain_type(&nft_chain_route_inet);
+#endif
+}
+
+void __exit nft_chain_route_fini(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+ nft_unregister_chain_type(&nft_chain_route_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+ nft_unregister_chain_type(&nft_chain_route_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_unregister_chain_type(&nft_chain_route_inet);
+#endif
+}
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index bee156eaa400..86fd90085eaf 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -14,8 +14,7 @@
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
struct nft_masq {
u32 flags;
@@ -196,28 +195,73 @@ static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
static int __init nft_masq_module_init_ipv6(void)
{
- int ret = nft_register_expr(&nft_masq_ipv6_type);
-
- if (ret)
- return ret;
-
- ret = nf_nat_masquerade_ipv6_register_notifier();
- if (ret < 0)
- nft_unregister_expr(&nft_masq_ipv6_type);
-
- return ret;
+ return nft_register_expr(&nft_masq_ipv6_type);
}
static void nft_masq_module_exit_ipv6(void)
{
nft_unregister_expr(&nft_masq_ipv6_type);
- nf_nat_masquerade_ipv6_unregister_notifier();
}
#else
static inline int nft_masq_module_init_ipv6(void) { return 0; }
static inline void nft_masq_module_exit_ipv6(void) {}
#endif
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_masq_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ switch (nft_pf(pkt)) {
+ case NFPROTO_IPV4:
+ return nft_masq_ipv4_eval(expr, regs, pkt);
+ case NFPROTO_IPV6:
+ return nft_masq_ipv6_eval(expr, regs, pkt);
+ }
+
+ WARN_ON_ONCE(1);
+}
+
+static void
+nft_masq_inet_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_INET);
+}
+
+static struct nft_expr_type nft_masq_inet_type;
+static const struct nft_expr_ops nft_masq_inet_ops = {
+ .type = &nft_masq_inet_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+ .eval = nft_masq_inet_eval,
+ .init = nft_masq_init,
+ .destroy = nft_masq_inet_destroy,
+ .dump = nft_masq_dump,
+ .validate = nft_masq_validate,
+};
+
+static struct nft_expr_type nft_masq_inet_type __read_mostly = {
+ .family = NFPROTO_INET,
+ .name = "masq",
+ .ops = &nft_masq_inet_ops,
+ .policy = nft_masq_policy,
+ .maxattr = NFTA_MASQ_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_masq_module_init_inet(void)
+{
+ return nft_register_expr(&nft_masq_inet_type);
+}
+
+static void nft_masq_module_exit_inet(void)
+{
+ nft_unregister_expr(&nft_masq_inet_type);
+}
+#else
+static inline int nft_masq_module_init_inet(void) { return 0; }
+static inline void nft_masq_module_exit_inet(void) {}
+#endif
+
static int __init nft_masq_module_init(void)
{
int ret;
@@ -226,15 +270,23 @@ static int __init nft_masq_module_init(void)
if (ret < 0)
return ret;
+ ret = nft_masq_module_init_inet();
+ if (ret < 0) {
+ nft_masq_module_exit_ipv6();
+ return ret;
+ }
+
ret = nft_register_expr(&nft_masq_ipv4_type);
if (ret < 0) {
+ nft_masq_module_exit_inet();
nft_masq_module_exit_ipv6();
return ret;
}
- ret = nf_nat_masquerade_ipv4_register_notifier();
+ ret = nf_nat_masquerade_inet_register_notifiers();
if (ret < 0) {
nft_masq_module_exit_ipv6();
+ nft_masq_module_exit_inet();
nft_unregister_expr(&nft_masq_ipv4_type);
return ret;
}
@@ -245,8 +297,9 @@ static int __init nft_masq_module_init(void)
static void __exit nft_masq_module_exit(void)
{
nft_masq_module_exit_ipv6();
+ nft_masq_module_exit_inet();
nft_unregister_expr(&nft_masq_ipv4_type);
- nf_nat_masquerade_ipv4_unregister_notifier();
+ nf_nat_masquerade_inet_unregister_notifiers();
}
module_init(nft_masq_module_init);
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index e93aed9bda88..d90d421826aa 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -140,7 +140,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;
family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
- if (family != ctx->family)
+ if (ctx->family != NFPROTO_INET && ctx->family != family)
return -EOPNOTSUPP;
switch (family) {
@@ -278,13 +278,67 @@ static struct nft_expr_type nft_nat_type __read_mostly = {
.owner = THIS_MODULE,
};
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_nat_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_nat *priv = nft_expr_priv(expr);
+
+ if (priv->family == nft_pf(pkt))
+ nft_nat_eval(expr, regs, pkt);
+}
+
+static const struct nft_expr_ops nft_nat_inet_ops = {
+ .type = &nft_nat_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+ .eval = nft_nat_inet_eval,
+ .init = nft_nat_init,
+ .destroy = nft_nat_destroy,
+ .dump = nft_nat_dump,
+ .validate = nft_nat_validate,
+};
+
+static struct nft_expr_type nft_inet_nat_type __read_mostly = {
+ .name = "nat",
+ .family = NFPROTO_INET,
+ .ops = &nft_nat_inet_ops,
+ .policy = nft_nat_policy,
+ .maxattr = NFTA_NAT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int nft_nat_inet_module_init(void)
+{
+ return nft_register_expr(&nft_inet_nat_type);
+}
+
+static void nft_nat_inet_module_exit(void)
+{
+ nft_unregister_expr(&nft_inet_nat_type);
+}
+#else
+static int nft_nat_inet_module_init(void) { return 0; }
+static void nft_nat_inet_module_exit(void) { }
+#endif
+
static int __init nft_nat_module_init(void)
{
- return nft_register_expr(&nft_nat_type);
+ int ret = nft_nat_inet_module_init();
+
+ if (ret)
+ return ret;
+
+ ret = nft_register_expr(&nft_nat_type);
+ if (ret)
+ nft_nat_inet_module_exit();
+
+ return ret;
}
static void __exit nft_nat_module_exit(void)
{
+ nft_nat_inet_module_exit();
nft_unregister_expr(&nft_nat_type);
}
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index b13618c764ec..87b60d6617ef 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -7,11 +7,13 @@
struct nft_osf {
enum nft_registers dreg:8;
u8 ttl;
+ u32 flags;
};
static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = {
[NFTA_OSF_DREG] = { .type = NLA_U32 },
[NFTA_OSF_TTL] = { .type = NLA_U8 },
+ [NFTA_OSF_FLAGS] = { .type = NLA_U32 },
};
static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
@@ -20,9 +22,10 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
struct nft_osf *priv = nft_expr_priv(expr);
u32 *dest = &regs->data[priv->dreg];
struct sk_buff *skb = pkt->skb;
+ char os_match[NFT_OSF_MAXGENRELEN + 1];
const struct tcphdr *tcp;
+ struct nf_osf_data data;
struct tcphdr _tcph;
- const char *os_name;
tcp = skb_header_pointer(skb, ip_hdrlen(skb),
sizeof(struct tcphdr), &_tcph);
@@ -35,11 +38,17 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
return;
}
- os_name = nf_osf_find(skb, nf_osf_fingers, priv->ttl);
- if (!os_name)
+ if (!nf_osf_find(skb, nf_osf_fingers, priv->ttl, &data)) {
strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN);
- else
- strncpy((char *)dest, os_name, NFT_OSF_MAXGENRELEN);
+ } else {
+ if (priv->flags & NFT_OSF_F_VERSION)
+ snprintf(os_match, NFT_OSF_MAXGENRELEN, "%s:%s",
+ data.genre, data.version);
+ else
+ strlcpy(os_match, data.genre, NFT_OSF_MAXGENRELEN);
+
+ strncpy((char *)dest, os_match, NFT_OSF_MAXGENRELEN);
+ }
}
static int nft_osf_init(const struct nft_ctx *ctx,
@@ -47,6 +56,7 @@ static int nft_osf_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_osf *priv = nft_expr_priv(expr);
+ u32 flags;
int err;
u8 ttl;
@@ -57,6 +67,13 @@ static int nft_osf_init(const struct nft_ctx *ctx,
priv->ttl = ttl;
}
+ if (tb[NFTA_OSF_FLAGS]) {
+ flags = ntohl(nla_get_be32(tb[NFTA_OSF_FLAGS]));
+ if (flags != NFT_OSF_F_VERSION)
+ return -EINVAL;
+ priv->flags = flags;
+ }
+
priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]);
err = nft_validate_register_store(ctx, priv->dreg, NULL,
NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN);
@@ -73,6 +90,9 @@ static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr)
if (nla_put_u8(skb, NFTA_OSF_TTL, priv->ttl))
goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_OSF_FLAGS, ntohl(priv->flags)))
+ goto nla_put_failure;
+
if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg))
goto nla_put_failure;
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index a340cd8a751b..da74fdc4a684 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -82,7 +82,7 @@ static int nft_redir_init(const struct nft_ctx *ctx,
return nf_ct_netns_get(ctx->net, ctx->family);
}
-int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
const struct nft_redir *priv = nft_expr_priv(expr);
@@ -202,6 +202,55 @@ static struct nft_expr_type nft_redir_ipv6_type __read_mostly = {
};
#endif
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_redir_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ switch (nft_pf(pkt)) {
+ case NFPROTO_IPV4:
+ return nft_redir_ipv4_eval(expr, regs, pkt);
+ case NFPROTO_IPV6:
+ return nft_redir_ipv6_eval(expr, regs, pkt);
+ }
+
+ WARN_ON_ONCE(1);
+}
+
+static void
+nft_redir_inet_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+ nf_ct_netns_put(ctx->net, NFPROTO_INET);
+}
+
+static struct nft_expr_type nft_redir_inet_type;
+static const struct nft_expr_ops nft_redir_inet_ops = {
+ .type = &nft_redir_inet_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+ .eval = nft_redir_inet_eval,
+ .init = nft_redir_init,
+ .destroy = nft_redir_inet_destroy,
+ .dump = nft_redir_dump,
+ .validate = nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_inet_type __read_mostly = {
+ .family = NFPROTO_INET,
+ .name = "redir",
+ .ops = &nft_redir_inet_ops,
+ .policy = nft_redir_policy,
+ .maxattr = NFTA_MASQ_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_redir_module_init_inet(void)
+{
+ return nft_register_expr(&nft_redir_inet_type);
+}
+#else
+static inline int nft_redir_module_init_inet(void) { return 0; }
+#endif
+
static int __init nft_redir_module_init(void)
{
int ret = nft_register_expr(&nft_redir_ipv4_type);
@@ -217,6 +266,15 @@ static int __init nft_redir_module_init(void)
}
#endif
+ ret = nft_redir_module_init_inet();
+ if (ret < 0) {
+ nft_unregister_expr(&nft_redir_ipv4_type);
+#ifdef CONFIG_NF_TABLES_IPV6
+ nft_unregister_expr(&nft_redir_ipv6_type);
+#endif
+ return ret;
+ }
+
return ret;
}
@@ -226,6 +284,9 @@ static void __exit nft_redir_module_exit(void)
#ifdef CONFIG_NF_TABLES_IPV6
nft_unregister_expr(&nft_redir_ipv6_type);
#endif
+#ifdef CONFIG_NF_TABLES_INET
+ nft_unregister_expr(&nft_redir_inet_type);
+#endif
}
module_init(nft_redir_module_init);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e5e5c64df8d1..0a6656ed1534 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -227,7 +227,7 @@ xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision)
EXPORT_SYMBOL_GPL(xt_request_find_match);
/* Find target, grabs ref. Returns ERR_PTR() on error. */
-struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
+static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
{
struct xt_target *t;
int err = -ENOENT;
@@ -255,7 +255,6 @@ struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
return ERR_PTR(err);
}
-EXPORT_SYMBOL(xt_find_target);
struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
{
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/netfilter/xt_MASQUERADE.c
index fd3f9e8a74da..ece20d832adc 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/netfilter/xt_MASQUERADE.c
@@ -9,20 +9,10 @@
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/types.h>
-#include <linux/inetdevice.h>
-#include <linux/ip.h>
-#include <linux/timer.h>
#include <linux/module.h>
-#include <linux/netfilter.h>
-#include <net/protocol.h>
-#include <net/ip.h>
-#include <net/checksum.h>
-#include <net/route.h>
-#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/x_tables.h>
#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -64,38 +54,78 @@ static void masquerade_tg_destroy(const struct xt_tgdtor_param *par)
nf_ct_netns_put(par->net, par->family);
}
-static struct xt_target masquerade_tg_reg __read_mostly = {
- .name = "MASQUERADE",
- .family = NFPROTO_IPV4,
- .target = masquerade_tg,
- .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
- .table = "nat",
- .hooks = 1 << NF_INET_POST_ROUTING,
- .checkentry = masquerade_tg_check,
- .destroy = masquerade_tg_destroy,
- .me = THIS_MODULE,
+#if IS_ENABLED(CONFIG_IPV6)
+static unsigned int
+masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par));
+}
+
+static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
+{
+ const struct nf_nat_range2 *range = par->targinfo;
+
+ if (range->flags & NF_NAT_RANGE_MAP_IPS)
+ return -EINVAL;
+
+ return nf_ct_netns_get(par->net, par->family);
+}
+#endif
+
+static struct xt_target masquerade_tg_reg[] __read_mostly = {
+ {
+#if IS_ENABLED(CONFIG_IPV6)
+ .name = "MASQUERADE",
+ .family = NFPROTO_IPV6,
+ .target = masquerade_tg6,
+ .targetsize = sizeof(struct nf_nat_range),
+ .table = "nat",
+ .hooks = 1 << NF_INET_POST_ROUTING,
+ .checkentry = masquerade_tg6_checkentry,
+ .destroy = masquerade_tg_destroy,
+ .me = THIS_MODULE,
+ }, {
+#endif
+ .name = "MASQUERADE",
+ .family = NFPROTO_IPV4,
+ .target = masquerade_tg,
+ .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat),
+ .table = "nat",
+ .hooks = 1 << NF_INET_POST_ROUTING,
+ .checkentry = masquerade_tg_check,
+ .destroy = masquerade_tg_destroy,
+ .me = THIS_MODULE,
+ }
};
static int __init masquerade_tg_init(void)
{
int ret;
- ret = xt_register_target(&masquerade_tg_reg);
+ ret = xt_register_targets(masquerade_tg_reg,
+ ARRAY_SIZE(masquerade_tg_reg));
if (ret)
return ret;
- ret = nf_nat_masquerade_ipv4_register_notifier();
- if (ret)
- xt_unregister_target(&masquerade_tg_reg);
+ ret = nf_nat_masquerade_inet_register_notifiers();
+ if (ret) {
+ xt_unregister_targets(masquerade_tg_reg,
+ ARRAY_SIZE(masquerade_tg_reg));
+ return ret;
+ }
return ret;
}
static void __exit masquerade_tg_exit(void)
{
- xt_unregister_target(&masquerade_tg_reg);
- nf_nat_masquerade_ipv4_unregister_notifier();
+ xt_unregister_targets(masquerade_tg_reg, ARRAY_SIZE(masquerade_tg_reg));
+ nf_nat_masquerade_inet_unregister_notifiers();
}
module_init(masquerade_tg_init);
module_exit(masquerade_tg_exit);
+#if IS_ENABLED(CONFIG_IPV6)
+MODULE_ALIAS("ip6t_MASQUERADE");
+#endif
+MODULE_ALIAS("ipt_MASQUERADE");
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f28e937320a3..216ab915dd54 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -988,7 +988,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err = 0;
- unsigned long groups = nladdr->nl_groups;
+ unsigned long groups;
bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
@@ -996,6 +996,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
+ groups = nladdr->nl_groups;
/* Only superuser is allowed to listen multicasts */
if (groups) {
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 1d3144d19903..167c09e1ea90 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1199,7 +1199,6 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
void __user *argp = (void __user *)arg;
- int ret;
switch (cmd) {
case TIOCOUTQ: {
@@ -1225,18 +1224,6 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return put_user(amount, (int __user *)argp);
}
- case SIOCGSTAMP:
- lock_sock(sk);
- ret = sock_get_timestamp(sk, argp);
- release_sock(sk);
- return ret;
-
- case SIOCGSTAMPNS:
- lock_sock(sk);
- ret = sock_get_timestampns(sk, argp);
- release_sock(sk);
- return ret;
-
case SIOCGIFADDR:
case SIOCSIFADDR:
case SIOCGIFDSTADDR:
@@ -1362,6 +1349,7 @@ static const struct proto_ops nr_proto_ops = {
.getname = nr_getname,
.poll = datagram_poll,
.ioctl = nr_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = nr_listen,
.shutdown = sock_no_shutdown,
.setsockopt = nr_setsockopt,
@@ -1392,18 +1380,22 @@ static int __init nr_proto_init(void)
int i;
int rc = proto_register(&nr_proto, 0);
- if (rc != 0)
- goto out;
+ if (rc)
+ return rc;
if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n");
- return -1;
+ pr_err("NET/ROM: %s - nr_ndevs parameter too large\n",
+ __func__);
+ rc = -EINVAL;
+ goto unregister_proto;
}
dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL);
- if (dev_nr == NULL) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n");
- return -1;
+ if (!dev_nr) {
+ pr_err("NET/ROM: %s - unable to allocate device array\n",
+ __func__);
+ rc = -ENOMEM;
+ goto unregister_proto;
}
for (i = 0; i < nr_ndevs; i++) {
@@ -1413,13 +1405,13 @@ static int __init nr_proto_init(void)
sprintf(name, "nr%d", i);
dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup);
if (!dev) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n");
+ rc = -ENOMEM;
goto fail;
}
dev->base_addr = i;
- if (register_netdev(dev)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n");
+ rc = register_netdev(dev);
+ if (rc) {
free_netdev(dev);
goto fail;
}
@@ -1427,36 +1419,64 @@ static int __init nr_proto_init(void)
dev_nr[i] = dev;
}
- if (sock_register(&nr_family_ops)) {
- printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n");
+ rc = sock_register(&nr_family_ops);
+ if (rc)
goto fail;
- }
- register_netdevice_notifier(&nr_dev_notifier);
+ rc = register_netdevice_notifier(&nr_dev_notifier);
+ if (rc)
+ goto out_sock;
ax25_register_pid(&nr_pid);
ax25_linkfail_register(&nr_linkfail_notifier);
#ifdef CONFIG_SYSCTL
- nr_register_sysctl();
+ rc = nr_register_sysctl();
+ if (rc)
+ goto out_sysctl;
#endif
nr_loopback_init();
- proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
- proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
- proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
-out:
- return rc;
+ rc = -ENOMEM;
+ if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops))
+ goto proc_remove1;
+ if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net,
+ &nr_neigh_seqops))
+ goto proc_remove2;
+ if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net,
+ &nr_node_seqops))
+ goto proc_remove3;
+
+ return 0;
+
+proc_remove3:
+ remove_proc_entry("nr_neigh", init_net.proc_net);
+proc_remove2:
+ remove_proc_entry("nr", init_net.proc_net);
+proc_remove1:
+
+ nr_loopback_clear();
+ nr_rt_free();
+
+#ifdef CONFIG_SYSCTL
+ nr_unregister_sysctl();
+out_sysctl:
+#endif
+ ax25_linkfail_release(&nr_linkfail_notifier);
+ ax25_protocol_release(AX25_P_NETROM);
+ unregister_netdevice_notifier(&nr_dev_notifier);
+out_sock:
+ sock_unregister(PF_NETROM);
fail:
while (--i >= 0) {
unregister_netdev(dev_nr[i]);
free_netdev(dev_nr[i]);
}
kfree(dev_nr);
+unregister_proto:
proto_unregister(&nr_proto);
- rc = -1;
- goto out;
+ return rc;
}
module_init(nr_proto_init);
diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c
index 215ad22a9647..93d13f019981 100644
--- a/net/netrom/nr_loopback.c
+++ b/net/netrom/nr_loopback.c
@@ -70,7 +70,7 @@ static void nr_loopback_timer(struct timer_list *unused)
}
}
-void __exit nr_loopback_clear(void)
+void nr_loopback_clear(void)
{
del_timer_sync(&loopback_timer);
skb_queue_purge(&loopback_queue);
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 6485f593e2f0..b76aa668a94b 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -953,7 +953,7 @@ const struct seq_operations nr_neigh_seqops = {
/*
* Free all memory associated with the nodes and routes lists.
*/
-void __exit nr_rt_free(void)
+void nr_rt_free(void)
{
struct nr_neigh *s = NULL;
struct nr_node *t = NULL;
diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c
index ba1c368b3f18..771011b84270 100644
--- a/net/netrom/sysctl_net_netrom.c
+++ b/net/netrom/sysctl_net_netrom.c
@@ -146,9 +146,12 @@ static struct ctl_table nr_table[] = {
{ }
};
-void __init nr_register_sysctl(void)
+int __init nr_register_sysctl(void)
{
nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table);
+ if (!nr_table_header)
+ return -ENOMEM;
+ return 0;
}
void nr_unregister_sysctl(void)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 0be3ab5bde26..626629944450 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -29,7 +29,7 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/ipv6_frag.h>
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
#include <net/netfilter/nf_nat.h>
#endif
@@ -75,7 +75,7 @@ struct ovs_conntrack_info {
struct md_mark mark;
struct md_labels labels;
char timeout[CTNL_TIMEOUT_NAME_MAX];
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */
#endif
};
@@ -721,7 +721,7 @@ static bool skb_nfct_cached(struct net *net,
return ct_executed;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
/* Modelled after nf_nat_ipv[46]_fn().
* range is only used for new, uninitialized NAT state.
* Returns either NF_ACCEPT or NF_DROP.
@@ -903,7 +903,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
return err;
}
-#else /* !CONFIG_NF_NAT_NEEDED */
+#else /* !CONFIG_NF_NAT */
static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb, struct nf_conn *ct,
@@ -1330,7 +1330,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
return 0;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
static int parse_nat(const struct nlattr *attr,
struct ovs_conntrack_info *info, bool log)
{
@@ -1467,7 +1467,7 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
.maxlen = sizeof(struct md_labels) },
[OVS_CT_ATTR_HELPER] = { .minlen = 1,
.maxlen = NF_CT_HELPER_NAME_LEN },
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
/* NAT length is checked when parsing the nested attributes. */
[OVS_CT_ATTR_NAT] = { .minlen = 0, .maxlen = INT_MAX },
#endif
@@ -1547,7 +1547,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
return -EINVAL;
}
break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
case OVS_CT_ATTR_NAT: {
int err = parse_nat(a, info, log);
@@ -1677,7 +1677,7 @@ err_free_ct:
return err;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
struct sk_buff *skb)
{
@@ -1783,7 +1783,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
return -EMSGSIZE;
}
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
return -EMSGSIZE;
#endif
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 08fe8b79c0bf..5c4a118d6f96 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4075,11 +4075,6 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
spin_unlock_bh(&sk->sk_receive_queue.lock);
return put_user(amount, (int __user *)arg);
}
- case SIOCGSTAMP:
- return sock_get_timestamp(sk, (struct timeval __user *)arg);
- case SIOCGSTAMPNS:
- return sock_get_timestampns(sk, (struct timespec __user *)arg);
-
#ifdef CONFIG_INET
case SIOCADDRT:
case SIOCDELRT:
@@ -4455,6 +4450,7 @@ static const struct proto_ops packet_ops_spkt = {
.getname = packet_getname_spkt,
.poll = datagram_poll,
.ioctl = packet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
@@ -4476,6 +4472,7 @@ static const struct proto_ops packet_ops = {
.getname = packet_getname,
.poll = packet_poll,
.ioctl = packet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = packet_setsockopt,
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b37e6e0a1026..7c5e8292cc0a 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -968,9 +968,6 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
}
break;
- case SIOCGSTAMP:
- rc = sock_get_timestamp(sk, argp);
- break;
case SIOCADDRT:
case SIOCDELRT:
case SIOCSIFADDR:
@@ -1033,6 +1030,7 @@ static const struct proto_ops qrtr_proto_ops = {
.recvmsg = qrtr_recvmsg,
.getname = qrtr_getname,
.ioctl = qrtr_ioctl,
+ .gettstamp = sock_gettstamp,
.poll = datagram_poll,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index d6cc97fbbbb0..2b969f99ef13 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -543,6 +543,9 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
struct rds_sock *rs = rds_sk_to_rs(sk);
int ret = 0;
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
+
lock_sock(sk);
switch (uaddr->sa_family) {
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 17c9d9f0c848..0f4398e7f2a7 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -173,6 +173,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
/* We allow an RDS socket to be bound to either IPv4 or IPv6
* address.
*/
+ if (addr_len < offsetofend(struct sockaddr, sa_family))
+ return -EINVAL;
if (uaddr->sa_family == AF_INET) {
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index c96f63ffe31e..e274bc6e1458 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1301,12 +1301,6 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return put_user(amount, (unsigned int __user *) argp);
}
- case SIOCGSTAMP:
- return sock_get_timestamp(sk, (struct timeval __user *) argp);
-
- case SIOCGSTAMPNS:
- return sock_get_timestampns(sk, (struct timespec __user *) argp);
-
case SIOCGIFADDR:
case SIOCSIFADDR:
case SIOCGIFDSTADDR:
@@ -1474,6 +1468,7 @@ static const struct proto_ops rose_proto_ops = {
.getname = rose_getname,
.poll = datagram_poll,
.ioctl = rose_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = rose_listen,
.shutdown = sock_no_shutdown,
.setsockopt = rose_setsockopt,
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 96f2952bbdfd..ae8c5d7f3bf1 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -135,7 +135,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr;
struct rxrpc_local *local;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
- u16 service_id = srx->srx_service;
+ u16 service_id;
int ret;
_enter("%p,%p,%d", rx, saddr, len);
@@ -143,6 +143,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
ret = rxrpc_validate_address(rx, srx, len);
if (ret < 0)
goto error;
+ service_id = srx->srx_service;
lock_sock(&rx->sk);
@@ -370,18 +371,22 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
* rxrpc_kernel_check_life - Check to see whether a call is still alive
* @sock: The socket the call is on
* @call: The call to check
+ * @_life: Where to store the life value
*
* Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server. Returns a number representing the life state
- * which can be compared to that returned by a previous call.
+ * getting ACKs from the server. Passes back in *_life a number representing
+ * the life state which can be compared to that returned by a previous call and
+ * return true if the call is still alive.
*
* If the life state stalls, rxrpc_kernel_probe_life() should be called and
* then 2RTT waited.
*/
-u32 rxrpc_kernel_check_life(const struct socket *sock,
- const struct rxrpc_call *call)
+bool rxrpc_kernel_check_life(const struct socket *sock,
+ const struct rxrpc_call *call,
+ u32 *_life)
{
- return call->acks_latest;
+ *_life = call->acks_latest;
+ return call->state != RXRPC_CALL_COMPLETE;
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 4b1a534d290a..062ca9dc29b8 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -654,6 +654,7 @@ struct rxrpc_call {
u8 ackr_reason; /* reason to ACK */
u16 ackr_skew; /* skew on packet being ACK'd */
rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */
+ rxrpc_serial_t ackr_first_seq; /* first sequence number received */
rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */
rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */
rxrpc_seq_t ackr_seen; /* Highest packet shown seen */
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index b6fca8ebb117..8d31fb4c51e1 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -153,7 +153,8 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
* pass a connection-level abort onto all calls on that connection
*/
static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl)
+ enum rxrpc_call_completion compl,
+ rxrpc_serial_t serial)
{
struct rxrpc_call *call;
int i;
@@ -173,6 +174,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
call->call_id, 0,
conn->abort_code,
conn->error);
+ else
+ trace_rxrpc_rx_abort(call, serial,
+ conn->abort_code);
if (rxrpc_set_call_completion(call, compl,
conn->abort_code,
conn->error))
@@ -213,8 +217,6 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
conn->state = RXRPC_CONN_LOCALLY_ABORTED;
spin_unlock_bh(&conn->state_lock);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
-
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
msg.msg_control = NULL;
@@ -242,6 +244,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
len = iov[0].iov_len + iov[1].iov_len;
serial = atomic_inc_return(&conn->serial);
+ rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
whdr.serial = htonl(serial);
_proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
@@ -321,7 +324,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
conn->error = -ECONNABORTED;
conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
+ rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9128aa0e40aa..4c6f9d0a00e7 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -837,7 +837,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
u8 acks[RXRPC_MAXACKS];
} buf;
rxrpc_serial_t acked_serial;
- rxrpc_seq_t first_soft_ack, hard_ack;
+ rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
int nr_acks, offset, ioffset;
_enter("");
@@ -851,13 +851,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
acked_serial = ntohl(buf.ack.serial);
first_soft_ack = ntohl(buf.ack.firstPacket);
+ prev_pkt = ntohl(buf.ack.previousPacket);
hard_ack = first_soft_ack - 1;
nr_acks = buf.ack.nAcks;
summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
buf.ack.reason : RXRPC_ACK__INVALID);
trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial,
- first_soft_ack, ntohl(buf.ack.previousPacket),
+ first_soft_ack, prev_pkt,
summary.ack_reason, nr_acks);
if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE)
@@ -878,8 +879,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
rxrpc_propose_ack_respond_to_ack);
}
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest))
+ /* Discard any out-of-order or duplicate ACKs (outside lock). */
+ if (before(first_soft_ack, call->ackr_first_seq) ||
+ before(prev_pkt, call->ackr_prev_seq))
return;
buf.info.rxMTU = 0;
@@ -890,12 +892,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
spin_lock(&call->input_lock);
- /* Discard any out-of-order or duplicate ACKs. */
- if (before_eq(sp->hdr.serial, call->acks_latest))
+ /* Discard any out-of-order or duplicate ACKs (inside lock). */
+ if (before(first_soft_ack, call->ackr_first_seq) ||
+ before(prev_pkt, call->ackr_prev_seq))
goto out;
call->acks_latest_ts = skb->tstamp;
call->acks_latest = sp->hdr.serial;
+ call->ackr_first_seq = first_soft_ack;
+ call->ackr_prev_seq = prev_pkt;
+
/* Parse rwind and mtu sizes if provided. */
if (buf.info.rxMTU)
rxrpc_input_ackinfo(call, skb, &buf.info);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index bc05af89fc38..6e84d878053c 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -157,6 +157,11 @@ void rxrpc_error_report(struct sock *sk)
_enter("%p{%d}", sk, local->debug_id);
+ /* Clear the outstanding error value on the socket so that it doesn't
+ * cause kernel_sendmsg() to return it later.
+ */
+ sock_error(sk);
+
skb = sock_dequeue_err_skb(sk);
if (!skb) {
_leave("UDP socket errqueue empty");
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 46c9312085b1..bec64deb7b0a 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -152,12 +152,13 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call,
}
/*
- * Queue a DATA packet for transmission, set the resend timeout and send the
- * packet immediately
+ * Queue a DATA packet for transmission, set the resend timeout and send
+ * the packet immediately. Returns the error from rxrpc_send_data_packet()
+ * in case the caller wants to do something with it.
*/
-static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
- struct sk_buff *skb, bool last,
- rxrpc_notify_end_tx_t notify_end_tx)
+static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
+ struct sk_buff *skb, bool last,
+ rxrpc_notify_end_tx_t notify_end_tx)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned long now;
@@ -250,7 +251,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
out:
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
- _leave("");
+ _leave(" = %d", ret);
+ return ret;
}
/*
@@ -423,9 +425,10 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
if (ret < 0)
goto out;
- rxrpc_queue_packet(rx, call, skb,
- !msg_data_left(msg) && !more,
- notify_end_tx);
+ ret = rxrpc_queue_packet(rx, call, skb,
+ !msg_data_left(msg) && !more,
+ notify_end_tx);
+ /* Should check for failure here */
skb = NULL;
}
} while (msg_data_left(msg) > 0);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 1b0fb80162e6..001182aa3959 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -13,6 +13,7 @@
#include <linux/list.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
+#include <linux/math64.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <net/netlink.h>
@@ -121,7 +122,14 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch)
static inline int length_to_duration(struct taprio_sched *q, int len)
{
- return (len * atomic64_read(&q->picos_per_byte)) / 1000;
+ return div_u64(len * atomic64_read(&q->picos_per_byte), 1000);
+}
+
+static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry)
+{
+ atomic_set(&entry->budget,
+ div64_u64((u64)entry->interval * 1000,
+ atomic64_read(&q->picos_per_byte)));
}
static struct sk_buff *taprio_dequeue(struct Qdisc *sch)
@@ -241,8 +249,7 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer)
close_time = ktime_add_ns(entry->close_time, next->interval);
next->close_time = close_time;
- atomic_set(&next->budget,
- (next->interval * 1000) / atomic64_read(&q->picos_per_byte));
+ taprio_set_budget(q, next);
first_run:
rcu_assign_pointer(q->current_entry, next);
@@ -575,9 +582,7 @@ static void taprio_start_sched(struct Qdisc *sch, ktime_t start)
list);
first->close_time = ktime_add_ns(start, first->interval);
- atomic_set(&first->budget,
- (first->interval * 1000) /
- atomic64_read(&q->picos_per_byte));
+ taprio_set_budget(q, first);
rcu_assign_pointer(q->current_entry, NULL);
spin_unlock_irqrestore(&q->current_entry_lock, flags);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 6200cd2b4b99..188c47eb206e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -1030,6 +1030,7 @@ static const struct proto_ops inet6_seqpacket_ops = {
.getname = sctp_getname,
.poll = sctp_poll,
.ioctl = inet6_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 951afdeea5e9..f0631bf486b6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1026,6 +1026,7 @@ static const struct proto_ops inet_seqpacket_ops = {
.getname = inet_getname, /* Semantics are different. */
.poll = sctp_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown, /* Looks harmless. */
.setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..7dfc34b28f4f 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6412,13 +6412,15 @@ static int sctp_eat_data(const struct sctp_association *asoc,
* in sctp_ulpevent_make_rcvmsg will drop the frame if we grow our
* memory usage too much
*/
- if (*sk->sk_prot_creator->memory_pressure) {
+ if (sk_under_memory_pressure(sk)) {
if (sctp_tsnmap_has_gap(map) &&
(sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
pr_debug("%s: under pressure, reneging for tsn:%u\n",
__func__, tsn);
deliver = SCTP_CMD_RENEGE;
- }
+ } else {
+ sk_mem_reclaim(sk);
+ }
}
/*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9874e60c9b0d..e4e892cc5644 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1913,7 +1913,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
if (sctp_wspace(asoc) < (int)msg_len)
sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
- if (sctp_wspace(asoc) <= 0) {
+ if (sk_under_memory_pressure(sk))
+ sk_mem_reclaim(sk);
+
+ if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) {
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
if (err)
@@ -4847,7 +4850,8 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr,
}
/* Validate addr_len before calling common connect/connectx routine. */
- af = sctp_get_af_specific(addr->sa_family);
+ af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL :
+ sctp_get_af_specific(addr->sa_family);
if (!af || addr_len < af->sockaddr_len) {
err = -EINVAL;
} else {
@@ -8930,7 +8934,10 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
goto do_error;
if (signal_pending(current))
goto do_interrupted;
- if ((int)msg_len <= sctp_wspace(asoc))
+ if (sk_under_memory_pressure(sk))
+ sk_mem_reclaim(sk);
+ if ((int)msg_len <= sctp_wspace(asoc) &&
+ sk_wmem_schedule(sk, msg_len))
break;
/* Let another process have a go. Since we are going
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 8cb7d9858270..c2a7478587ab 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -634,8 +634,9 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
gfp_t gfp)
{
struct sctp_ulpevent *event = NULL;
- struct sk_buff *skb;
- size_t padding, len;
+ struct sk_buff *skb = chunk->skb;
+ struct sock *sk = asoc->base.sk;
+ size_t padding, datalen;
int rx_count;
/*
@@ -646,15 +647,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
if (asoc->ep->rcvbuf_policy)
rx_count = atomic_read(&asoc->rmem_alloc);
else
- rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+ rx_count = atomic_read(&sk->sk_rmem_alloc);
- if (rx_count >= asoc->base.sk->sk_rcvbuf) {
+ datalen = ntohs(chunk->chunk_hdr->length);
- if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
- (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
- chunk->skb->truesize)))
- goto fail;
- }
+ if (rx_count >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, datalen))
+ goto fail;
/* Clone the original skb, sharing the data. */
skb = skb_clone(chunk->skb, gfp);
@@ -681,8 +679,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
* The sender should never pad with more than 3 bytes. The receiver
* MUST ignore the padding bytes.
*/
- len = ntohs(chunk->chunk_hdr->length);
- padding = SCTP_PAD4(len) - len;
+ padding = SCTP_PAD4(datalen) - datalen;
/* Fixup cloned skb with just this chunks data. */
skb_trim(skb, chunk->chunk_end - padding - skb->data);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 7cdc3623fa35..a212fe079c07 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -1104,7 +1104,8 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
freed += sctp_ulpq_renege_frags(ulpq, needed - freed);
}
/* If able to free enough room, accept this chunk. */
- if (freed >= needed) {
+ if (sk_rmem_schedule(asoc->base.sk, chunk->skb, needed) &&
+ freed >= needed) {
int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp);
/*
* Enter partial delivery if chunk has not been
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index e066899de72d..086d9913975d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -165,10 +165,9 @@ static int smc_release(struct socket *sock)
if (sk->sk_state == SMC_CLOSED) {
if (smc->clcsock) {
- mutex_lock(&smc->clcsock_release_lock);
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- mutex_unlock(&smc->clcsock_release_lock);
+ release_sock(sk);
+ smc_clcsock_release(smc);
+ lock_sock(sk);
}
if (!smc->use_fallback)
smc_conn_free(&smc->conn);
@@ -444,10 +443,19 @@ static void smc_link_save_peer_info(struct smc_link *link,
link->peer_mtu = clc->qp_mtu;
}
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+ smc->use_fallback = true;
+ if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+ smc->clcsock->file = smc->sk.sk_socket->file;
+ smc->clcsock->file->private_data = smc->clcsock;
+ }
+}
+
/* fall back during connect */
static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
{
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = reason_code;
smc_copy_sock_settings_to_clc(smc);
smc->connect_nonblock = 0;
@@ -780,10 +788,14 @@ static void smc_connect_work(struct work_struct *work)
smc->sk.sk_err = -rc;
out:
- if (smc->sk.sk_err)
- smc->sk.sk_state_change(&smc->sk);
- else
- smc->sk.sk_write_space(&smc->sk);
+ if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+ if (smc->sk.sk_err) {
+ smc->sk.sk_state_change(&smc->sk);
+ } else { /* allow polling before and after fallback decision */
+ smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+ smc->sk.sk_write_space(&smc->sk);
+ }
+ }
release_sock(&smc->sk);
}
@@ -867,11 +879,11 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
if (rc < 0)
lsk->sk_err = -rc;
if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
sock_set_flag(new_sk, SOCK_DEAD);
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
@@ -922,16 +934,21 @@ struct sock *smc_accept_dequeue(struct sock *parent,
smc_accept_unlink(new_sk);
if (new_sk->sk_state == SMC_CLOSED) {
+ new_sk->sk_prot->unhash(new_sk);
if (isk->clcsock) {
sock_release(isk->clcsock);
isk->clcsock = NULL;
}
- new_sk->sk_prot->unhash(new_sk);
sock_put(new_sk); /* final */
continue;
}
- if (new_sock)
+ if (new_sock) {
sock_graft(new_sk, new_sock);
+ if (isk->use_fallback) {
+ smc_sk(new_sk)->clcsock->file = new_sock->file;
+ isk->clcsock->file->private_data = isk->clcsock;
+ }
+ }
return new_sk;
}
return NULL;
@@ -951,6 +968,7 @@ void smc_close_non_accepted(struct sock *sk)
sock_set_flag(sk, SOCK_DEAD);
sk->sk_shutdown |= SHUTDOWN_MASK;
}
+ sk->sk_prot->unhash(sk);
if (smc->clcsock) {
struct socket *tcp;
@@ -966,7 +984,6 @@ void smc_close_non_accepted(struct sock *sk)
smc_conn_free(&smc->conn);
}
release_sock(sk);
- sk->sk_prot->unhash(sk);
sock_put(sk); /* final sock_put */
}
@@ -1032,13 +1049,13 @@ static void smc_listen_out(struct smc_sock *new_smc)
struct smc_sock *lsmc = new_smc->listen_smc;
struct sock *newsmcsk = &new_smc->sk;
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ release_sock(&lsmc->sk);
} else { /* no longer listening */
smc_close_non_accepted(newsmcsk);
}
- release_sock(&lsmc->sk);
/* Wake up accept */
lsmc->sk.sk_data_ready(&lsmc->sk);
@@ -1082,7 +1099,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
return;
}
smc_conn_free(&new_smc->conn);
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = reason_code;
if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
if (smc_clc_send_decline(new_smc, reason_code) < 0) {
@@ -1220,6 +1237,9 @@ static void smc_listen_work(struct work_struct *work)
u8 buf[SMC_CLC_MAX_LEN];
int rc = 0;
+ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+ return smc_listen_out_err(new_smc);
+
if (new_smc->use_fallback) {
smc_listen_out_connected(new_smc);
return;
@@ -1227,7 +1247,7 @@ static void smc_listen_work(struct work_struct *work)
/* check if peer is smc capable */
if (!tcp_sk(newclcsock->sk)->syn_smc) {
- new_smc->use_fallback = true;
+ smc_switch_to_fallback(new_smc);
new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
smc_listen_out_connected(new_smc);
return;
@@ -1507,7 +1527,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (msg->msg_flags & MSG_FASTOPEN) {
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
rc = -EINVAL;
@@ -1712,7 +1732,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
case TCP_FASTOPEN_NO_COOKIE:
/* option not supported by SMC */
if (sk->sk_state == SMC_INIT) {
- smc->use_fallback = true;
+ smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
if (!smc->use_fallback)
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 2ad37e998509..fc06720b53c1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -21,6 +21,22 @@
#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+ struct socket *tcp;
+
+ if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+ cancel_work_sync(&smc->smc_listen_work);
+ mutex_lock(&smc->clcsock_release_lock);
+ if (smc->clcsock) {
+ tcp = smc->clcsock;
+ smc->clcsock = NULL;
+ sock_release(tcp);
+ }
+ mutex_unlock(&smc->clcsock_release_lock);
+}
+
static void smc_close_cleanup_listen(struct sock *parent)
{
struct sock *sk;
@@ -321,6 +337,7 @@ static void smc_close_passive_work(struct work_struct *work)
close_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
struct smc_cdc_conn_state_flags *rxflags;
+ bool release_clcsock = false;
struct sock *sk = &smc->sk;
int old_state;
@@ -400,13 +417,13 @@ wakeup:
if ((sk->sk_state == SMC_CLOSED) &&
(sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
smc_conn_free(conn);
- if (smc->clcsock) {
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- }
+ if (smc->clcsock)
+ release_clcsock = true;
}
}
release_sock(sk);
+ if (release_clcsock)
+ smc_clcsock_release(smc);
sock_put(sk); /* sock_hold done by schedulers of close_work */
}
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 19eb6a211c23..e0e3b5df25d2 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc);
int smc_close_active(struct smc_sock *smc);
int smc_close_shutdown_write(struct smc_sock *smc);
void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
#endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 2fff79db1a59..e89e918b88e0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -289,6 +289,11 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
INIT_LIST_HEAD(&smcd->vlan);
smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
WQ_MEM_RECLAIM, name);
+ if (!smcd->event_wq) {
+ kfree(smcd->conn);
+ kfree(smcd);
+ return NULL;
+ }
return smcd;
}
EXPORT_SYMBOL_GPL(smcd_alloc_dev);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 2b246b94a3af..9f5d8f36f2d7 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -604,7 +604,8 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = genl_info_net(info);
- return smc_pnet_remove_by_pnetid(net, NULL);
+ smc_pnet_remove_by_pnetid(net, NULL);
+ return 0;
}
/* SMC_PNETID generic netlink operation definition */
diff --git a/net/socket.c b/net/socket.c
index 8255f5bda0aa..8d9d4fc7d962 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1164,6 +1164,25 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
err = open_related_ns(&net->ns, get_net_ns);
break;
+ case SIOCGSTAMP_OLD:
+ case SIOCGSTAMPNS_OLD:
+ if (!sock->ops->gettstamp) {
+ err = -ENOIOCTLCMD;
+ break;
+ }
+ err = sock->ops->gettstamp(sock, argp,
+ cmd == SIOCGSTAMP_OLD,
+ !IS_ENABLED(CONFIG_64BIT));
+ case SIOCGSTAMP_NEW:
+ case SIOCGSTAMPNS_NEW:
+ if (!sock->ops->gettstamp) {
+ err = -ENOIOCTLCMD;
+ break;
+ }
+ err = sock->ops->gettstamp(sock, argp,
+ cmd == SIOCGSTAMP_NEW,
+ false);
+ break;
default:
err = sock_do_ioctl(net, sock, cmd, arg);
break;
@@ -2916,38 +2935,6 @@ void socket_seq_show(struct seq_file *seq)
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_COMPAT
-static int do_siocgstamp(struct net *net, struct socket *sock,
- unsigned int cmd, void __user *up)
-{
- mm_segment_t old_fs = get_fs();
- struct timeval ktv;
- int err;
-
- set_fs(KERNEL_DS);
- err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
- set_fs(old_fs);
- if (!err)
- err = compat_put_timeval(&ktv, up);
-
- return err;
-}
-
-static int do_siocgstampns(struct net *net, struct socket *sock,
- unsigned int cmd, void __user *up)
-{
- mm_segment_t old_fs = get_fs();
- struct timespec kts;
- int err;
-
- set_fs(KERNEL_DS);
- err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
- set_fs(old_fs);
- if (!err)
- err = compat_put_timespec(&kts, up);
-
- return err;
-}
-
static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32)
{
struct compat_ifconf ifc32;
@@ -3347,10 +3334,13 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
case SIOCADDRT:
case SIOCDELRT:
return routing_ioctl(net, sock, cmd, argp);
- case SIOCGSTAMP:
- return do_siocgstamp(net, sock, cmd, argp);
- case SIOCGSTAMPNS:
- return do_siocgstampns(net, sock, cmd, argp);
+ case SIOCGSTAMP_OLD:
+ case SIOCGSTAMPNS_OLD:
+ if (!sock->ops->gettstamp)
+ return -ENOIOCTLCMD;
+ return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD,
+ !COMPAT_USE_64BIT_TIME);
+
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
case SIOCSHWTSTAMP:
@@ -3368,6 +3358,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
case SIOCADDDLCI:
case SIOCDELDLCI:
case SIOCGSKNS:
+ case SIOCGSTAMP_NEW:
+ case SIOCGSTAMPNS_NEW:
return sock_ioctl(file, cmd, arg);
case SIOCGIFFLAGS:
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 68a0885b9319..0ba363624339 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -140,13 +140,11 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
/* We are going to append to the frags_list of head.
* Need to unshare the frag_list.
*/
- if (skb_has_frag_list(head)) {
- err = skb_unclone(head, GFP_ATOMIC);
- if (err) {
- STRP_STATS_INCR(strp->stats.mem_fail);
- desc->error = err;
- return 0;
- }
+ err = skb_unclone(head, GFP_ATOMIC);
+ if (err) {
+ STRP_STATS_INCR(strp->stats.mem_fail);
+ desc->error = err;
+ return 0;
}
if (unlikely(skb_shinfo(head)->frag_list)) {
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 187d10443a15..1d0395ef62c9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1540,7 +1540,6 @@ call_start(struct rpc_task *task)
clnt->cl_stats->rpccnt++;
task->tk_action = call_reserve;
rpc_task_set_transport(task, clnt);
- call_reserve(task);
}
/*
@@ -1554,9 +1553,6 @@ call_reserve(struct rpc_task *task)
task->tk_status = 0;
task->tk_action = call_reserveresult;
xprt_reserve(task);
- if (rpc_task_need_resched(task))
- return;
- call_reserveresult(task);
}
static void call_retry_reserve(struct rpc_task *task);
@@ -1579,7 +1575,6 @@ call_reserveresult(struct rpc_task *task)
if (status >= 0) {
if (task->tk_rqstp) {
task->tk_action = call_refresh;
- call_refresh(task);
return;
}
@@ -1605,7 +1600,6 @@ call_reserveresult(struct rpc_task *task)
/* fall through */
case -EAGAIN: /* woken up; retry */
task->tk_action = call_retry_reserve;
- call_retry_reserve(task);
return;
case -EIO: /* probably a shutdown */
break;
@@ -1628,9 +1622,6 @@ call_retry_reserve(struct rpc_task *task)
task->tk_status = 0;
task->tk_action = call_reserveresult;
xprt_retry_reserve(task);
- if (rpc_task_need_resched(task))
- return;
- call_reserveresult(task);
}
/*
@@ -1645,9 +1636,6 @@ call_refresh(struct rpc_task *task)
task->tk_status = 0;
task->tk_client->cl_stats->rpcauthrefresh++;
rpcauth_refreshcred(task);
- if (rpc_task_need_resched(task))
- return;
- call_refreshresult(task);
}
/*
@@ -1666,7 +1654,6 @@ call_refreshresult(struct rpc_task *task)
case 0:
if (rpcauth_uptodatecred(task)) {
task->tk_action = call_allocate;
- call_allocate(task);
return;
}
/* Use rate-limiting and a max number of retries if refresh
@@ -1685,7 +1672,6 @@ call_refreshresult(struct rpc_task *task)
task->tk_cred_retry--;
dprintk("RPC: %5u %s: retry refresh creds\n",
task->tk_pid, __func__);
- call_refresh(task);
return;
}
dprintk("RPC: %5u %s: refresh creds failed with error %d\n",
@@ -1711,10 +1697,8 @@ call_allocate(struct rpc_task *task)
task->tk_status = 0;
task->tk_action = call_encode;
- if (req->rq_buffer) {
- call_encode(task);
+ if (req->rq_buffer)
return;
- }
if (proc->p_proc != 0) {
BUG_ON(proc->p_arglen == 0);
@@ -1740,12 +1724,8 @@ call_allocate(struct rpc_task *task)
status = xprt->ops->buf_alloc(task);
xprt_inject_disconnect(xprt);
- if (status == 0) {
- if (rpc_task_need_resched(task))
- return;
- call_encode(task);
+ if (status == 0)
return;
- }
if (status != -ENOMEM) {
rpc_exit(task, status);
return;
@@ -1828,8 +1808,12 @@ call_encode(struct rpc_task *task)
xprt_request_enqueue_receive(task);
xprt_request_enqueue_transmit(task);
out:
- task->tk_action = call_bind;
- call_bind(task);
+ task->tk_action = call_transmit;
+ /* Check that the connection is OK */
+ if (!xprt_bound(task->tk_xprt))
+ task->tk_action = call_bind;
+ else if (!xprt_connected(task->tk_xprt))
+ task->tk_action = call_connect;
}
/*
@@ -1847,7 +1831,6 @@ rpc_task_handle_transmitted(struct rpc_task *task)
{
xprt_end_transmit(task);
task->tk_action = call_transmit_status;
- call_transmit_status(task);
}
/*
@@ -1865,7 +1848,6 @@ call_bind(struct rpc_task *task)
if (xprt_bound(xprt)) {
task->tk_action = call_connect;
- call_connect(task);
return;
}
@@ -1896,7 +1878,6 @@ call_bind_status(struct rpc_task *task)
dprint_status(task);
task->tk_status = 0;
task->tk_action = call_connect;
- call_connect(task);
return;
}
@@ -1981,7 +1962,6 @@ call_connect(struct rpc_task *task)
if (xprt_connected(xprt)) {
task->tk_action = call_transmit;
- call_transmit(task);
return;
}
@@ -2051,7 +2031,6 @@ call_connect_status(struct rpc_task *task)
case 0:
clnt->cl_stats->netreconn++;
task->tk_action = call_transmit;
- call_transmit(task);
return;
}
rpc_exit(task, status);
@@ -2087,9 +2066,6 @@ call_transmit(struct rpc_task *task)
xprt_transmit(task);
}
xprt_end_transmit(task);
- if (rpc_task_need_resched(task))
- return;
- call_transmit_status(task);
}
/*
@@ -2107,9 +2083,6 @@ call_transmit_status(struct rpc_task *task)
if (rpc_task_transmitted(task)) {
if (task->tk_status == 0)
xprt_request_wait_receive(task);
- if (rpc_task_need_resched(task))
- return;
- call_status(task);
return;
}
@@ -2170,7 +2143,6 @@ call_bc_encode(struct rpc_task *task)
{
xprt_request_enqueue_transmit(task);
task->tk_action = call_bc_transmit;
- call_bc_transmit(task);
}
/*
@@ -2261,7 +2233,6 @@ call_status(struct rpc_task *task)
status = task->tk_status;
if (status >= 0) {
task->tk_action = call_decode;
- call_decode(task);
return;
}
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 89a63391d4d4..30cfc0efe699 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -90,7 +90,7 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
/* Flush Receives, then wait for deferred Reply work
* to complete.
*/
- ib_drain_qp(ia->ri_id->qp);
+ ib_drain_rq(ia->ri_id->qp);
drain_workqueue(buf->rb_completion_wq);
/* Deferred Reply processing might have scheduled
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 3cb9f326ee6f..6053489c8063 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -876,6 +876,8 @@ void tipc_link_reset(struct tipc_link *l)
__skb_queue_head_init(&list);
l->in_session = false;
+ /* Force re-synch of peer session number before establishing */
+ l->peer_session--;
l->session++;
l->mtu = l->advertised_mtu;
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bff241f03525..89993afe0fbd 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -909,7 +909,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg,
for (; i < TIPC_NAMETBL_SIZE; i++) {
head = &tn->nametbl->services[i];
- if (*last_type) {
+ if (*last_type ||
+ (!i && *last_key && (*last_lower == *last_key))) {
service = tipc_service_find(net, *last_type);
if (!service)
return -EPIPE;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 8ac8ddf1e324..1385207a301f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3070,6 +3070,9 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
case TIPC_SOCK_RECVQ_DEPTH:
value = skb_queue_len(&sk->sk_receive_queue);
break;
+ case TIPC_SOCK_RECVQ_USED:
+ value = sk_rmem_alloc_get(sk);
+ break;
case TIPC_GROUP_JOIN:
seq.type = 0;
if (tsk->group)
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 3481e4906bd6..9df82a573aa7 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -38,6 +38,8 @@
#include <linux/sysctl.h>
+static int zero;
+static int one = 1;
static struct ctl_table_header *tipc_ctl_hdr;
static struct ctl_table tipc_table[] = {
@@ -46,14 +48,16 @@ static struct ctl_table tipc_table[] = {
.data = &sysctl_tipc_rmem,
.maxlen = sizeof(sysctl_tipc_rmem),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "named_timeout",
.data = &sysctl_tipc_named_timeout,
.maxlen = sizeof(sysctl_tipc_named_timeout),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "sk_filter",
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 135a7ee9db03..9f3bdbc1e593 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,8 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock);
static void tls_device_free_ctx(struct tls_context *ctx)
{
- if (ctx->tx_conf == TLS_HW)
+ if (ctx->tx_conf == TLS_HW) {
kfree(tls_offload_ctx_tx(ctx));
+ kfree(ctx->tx.rec_seq);
+ kfree(ctx->tx.iv);
+ }
if (ctx->rx_conf == TLS_HW)
kfree(tls_offload_ctx_rx(ctx));
@@ -216,6 +219,13 @@ void tls_device_sk_destruct(struct sock *sk)
}
EXPORT_SYMBOL(tls_device_sk_destruct);
+void tls_device_free_resources_tx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+ tls_free_partial_record(sk, tls_ctx);
+}
+
static void tls_append_frag(struct tls_record_info *record,
struct page_frag *pfrag,
int size)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 0e24edab2535..7e546b8ec000 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -208,6 +208,26 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
return tls_push_sg(sk, ctx, sg, offset, flags);
}
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+{
+ struct scatterlist *sg;
+
+ sg = ctx->partially_sent_record;
+ if (!sg)
+ return false;
+
+ while (1) {
+ put_page(sg_page(sg));
+ sk_mem_uncharge(sk, sg->length);
+
+ if (sg_is_last(sg))
+ break;
+ sg++;
+ }
+ ctx->partially_sent_record = NULL;
+ return true;
+}
+
static void tls_write_space(struct sock *sk)
{
struct tls_context *ctx = tls_get_ctx(sk);
@@ -267,6 +287,10 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
kfree(ctx->tx.rec_seq);
kfree(ctx->tx.iv);
tls_sw_free_resources_tx(sk);
+#ifdef CONFIG_TLS_DEVICE
+ } else if (ctx->tx_conf == TLS_HW) {
+ tls_device_free_resources_tx(sk);
+#endif
}
if (ctx->rx_conf == TLS_SW) {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4741edf4bb1e..f780b473827b 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2065,20 +2065,7 @@ void tls_sw_free_resources_tx(struct sock *sk)
/* Free up un-sent records in tx_list. First, free
* the partially sent record if any at head of tx_list.
*/
- if (tls_ctx->partially_sent_record) {
- struct scatterlist *sg = tls_ctx->partially_sent_record;
-
- while (1) {
- put_page(sg_page(sg));
- sk_mem_uncharge(sk, sg->length);
-
- if (sg_is_last(sg))
- break;
- sg++;
- }
-
- tls_ctx->partially_sent_record = NULL;
-
+ if (tls_free_partial_record(sk, tls_ctx)) {
rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
list_del(&rec->list);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 33408ba1d7ee..e7ee18ab6cb7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13614,7 +13614,8 @@ static const struct genl_ops nl80211_ops[] = {
.doit = nl80211_associate,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEAUTHENTICATE,
@@ -13659,14 +13660,16 @@ static const struct genl_ops nl80211_ops[] = {
.doit = nl80211_connect,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
.doit = nl80211_update_connect_params,
.flags = GENL_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DISCONNECT,
@@ -13691,7 +13694,8 @@ static const struct genl_ops nl80211_ops[] = {
.doit = nl80211_setdel_pmksa,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMKSA,
@@ -13999,7 +14003,8 @@ static const struct genl_ops nl80211_ops[] = {
.dumpit = nl80211_vendor_cmd_dump,
.flags = GENL_UNS_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_WIPHY |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_SET_QOS_MAP,
@@ -14047,7 +14052,8 @@ static const struct genl_ops nl80211_ops[] = {
.cmd = NL80211_CMD_SET_PMK,
.doit = nl80211_set_pmk,
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
- NL80211_FLAG_NEED_RTNL,
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_CLEAR_SKB,
},
{
.cmd = NL80211_CMD_DEL_PMK,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2f1bf91eb226..0ba778f371cb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1309,6 +1309,16 @@ reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1,
return dfs_region1;
}
+static void reg_wmm_rules_intersect(const struct ieee80211_wmm_ac *wmm_ac1,
+ const struct ieee80211_wmm_ac *wmm_ac2,
+ struct ieee80211_wmm_ac *intersect)
+{
+ intersect->cw_min = max_t(u16, wmm_ac1->cw_min, wmm_ac2->cw_min);
+ intersect->cw_max = max_t(u16, wmm_ac1->cw_max, wmm_ac2->cw_max);
+ intersect->cot = min_t(u16, wmm_ac1->cot, wmm_ac2->cot);
+ intersect->aifsn = max_t(u8, wmm_ac1->aifsn, wmm_ac2->aifsn);
+}
+
/*
* Helper for regdom_intersect(), this does the real
* mathematical intersection fun
@@ -1323,6 +1333,8 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
struct ieee80211_freq_range *freq_range;
const struct ieee80211_power_rule *power_rule1, *power_rule2;
struct ieee80211_power_rule *power_rule;
+ const struct ieee80211_wmm_rule *wmm_rule1, *wmm_rule2;
+ struct ieee80211_wmm_rule *wmm_rule;
u32 freq_diff, max_bandwidth1, max_bandwidth2;
freq_range1 = &rule1->freq_range;
@@ -1333,6 +1345,10 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
power_rule2 = &rule2->power_rule;
power_rule = &intersected_rule->power_rule;
+ wmm_rule1 = &rule1->wmm_rule;
+ wmm_rule2 = &rule2->wmm_rule;
+ wmm_rule = &intersected_rule->wmm_rule;
+
freq_range->start_freq_khz = max(freq_range1->start_freq_khz,
freq_range2->start_freq_khz);
freq_range->end_freq_khz = min(freq_range1->end_freq_khz,
@@ -1376,6 +1392,29 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms,
rule2->dfs_cac_ms);
+ if (rule1->has_wmm && rule2->has_wmm) {
+ u8 ac;
+
+ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+ reg_wmm_rules_intersect(&wmm_rule1->client[ac],
+ &wmm_rule2->client[ac],
+ &wmm_rule->client[ac]);
+ reg_wmm_rules_intersect(&wmm_rule1->ap[ac],
+ &wmm_rule2->ap[ac],
+ &wmm_rule->ap[ac]);
+ }
+
+ intersected_rule->has_wmm = true;
+ } else if (rule1->has_wmm) {
+ *wmm_rule = *wmm_rule1;
+ intersected_rule->has_wmm = true;
+ } else if (rule2->has_wmm) {
+ *wmm_rule = *wmm_rule2;
+ intersected_rule->has_wmm = true;
+ } else {
+ intersected_rule->has_wmm = false;
+ }
+
if (!is_valid_reg_rule(intersected_rule))
return -EINVAL;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 287518c6caa4..04d888628f29 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -190,10 +190,9 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
/* copy subelement as we need to change its content to
* mark an ie after it is processed.
*/
- sub_copy = kmalloc(subie_len, gfp);
+ sub_copy = kmemdup(subelement, subie_len, gfp);
if (!sub_copy)
return 0;
- memcpy(sub_copy, subelement, subie_len);
pos = &new_ie[0];
diff --git a/net/wireless/util.c b/net/wireless/util.c
index e4b8db5e81ec..75899b62bdc9 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1220,9 +1220,11 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
else if (rate->bw == RATE_INFO_BW_HE_RU &&
rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26)
result = rates_26[rate->he_gi];
- else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
- rate->bw, rate->he_ru_alloc))
+ else {
+ WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
+ rate->bw, rate->he_ru_alloc);
return 0;
+ }
/* now scale to the appropriate MCS */
tmp = result;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 20a511398389..0ea48a52ce79 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1398,18 +1398,6 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
}
- case SIOCGSTAMP:
- rc = -EINVAL;
- if (sk)
- rc = sock_get_timestamp(sk,
- (struct timeval __user *)argp);
- break;
- case SIOCGSTAMPNS:
- rc = -EINVAL;
- if (sk)
- rc = sock_get_timestampns(sk,
- (struct timespec __user *)argp);
- break;
case SIOCGIFADDR:
case SIOCSIFADDR:
case SIOCGIFDSTADDR:
@@ -1681,8 +1669,6 @@ static int compat_x25_ioctl(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
void __user *argp = compat_ptr(arg);
- struct sock *sk = sock->sk;
-
int rc = -ENOIOCTLCMD;
switch(cmd) {
@@ -1690,18 +1676,6 @@ static int compat_x25_ioctl(struct socket *sock, unsigned int cmd,
case TIOCINQ:
rc = x25_ioctl(sock, cmd, (unsigned long)argp);
break;
- case SIOCGSTAMP:
- rc = -EINVAL;
- if (sk)
- rc = compat_sock_get_timestamp(sk,
- (struct timeval __user*)argp);
- break;
- case SIOCGSTAMPNS:
- rc = -EINVAL;
- if (sk)
- rc = compat_sock_get_timestampns(sk,
- (struct timespec __user*)argp);
- break;
case SIOCGIFADDR:
case SIOCSIFADDR:
case SIOCGIFDSTADDR:
@@ -1765,6 +1739,7 @@ static const struct proto_ops x25_proto_ops = {
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_x25_ioctl,
#endif
+ .gettstamp = sock_gettstamp,
.listen = x25_listen,
.shutdown = sock_no_shutdown,
.setsockopt = x25_setsockopt,