summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorPablo Neira Ayuso <pablo@netfilter.org>2015-10-17 14:11:08 +0200
committerPablo Neira Ayuso <pablo@netfilter.org>2015-10-17 14:28:03 +0200
commitf0a0a978b66fea782a52b0a7075b3fa9ab27ad0a (patch)
tree52ecc0eafbac697c6afaa542efe324984484120c /net
parentc8d71d08aa23679f56e7072358383442c6ede352 (diff)
parent4be3158abe1e02d24f82b34101e41d662fae2185 (diff)
downloadlinux-f0a0a978b66fea782a52b0a7075b3fa9ab27ad0a.tar.bz2
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
This merge resolves conflicts with 75aec9df3a78 ("bridge: Remove br_nf_push_frag_xmit_sk") as part of Eric Biederman's effort to improve netns support in the network stack that reached upstream via David's net-next tree. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: net/bridge/br_netfilter_hooks.c
Diffstat (limited to 'net')
-rw-r--r--net/6lowpan/core.c5
-rw-r--r--net/6lowpan/nhc.h2
-rw-r--r--net/bluetooth/6lowpan.c78
-rw-r--r--net/bluetooth/hci_core.c142
-rw-r--r--net/bluetooth/hci_sock.c70
-rw-r--r--net/bluetooth/lib.c16
-rw-r--r--net/bridge/br_device.c2
-rw-r--r--net/bridge/br_fdb.c129
-rw-r--r--net/bridge/br_forward.c6
-rw-r--r--net/bridge/br_if.c6
-rw-r--r--net/bridge/br_input.c4
-rw-r--r--net/bridge/br_ioctl.c3
-rw-r--r--net/bridge/br_netfilter_hooks.c13
-rw-r--r--net/bridge/br_netlink.c381
-rw-r--r--net/bridge/br_private.h37
-rw-r--r--net/bridge/br_stp.c26
-rw-r--r--net/bridge/br_sysfs_br.c11
-rw-r--r--net/bridge/br_vlan.c296
-rw-r--r--net/can/bcm.c15
-rw-r--r--net/core/dev.c10
-rw-r--r--net/core/dst.c14
-rw-r--r--net/core/filter.c41
-rw-r--r--net/core/lwtunnel.c4
-rw-r--r--net/core/neighbour.c17
-rw-r--r--net/core/request_sock.c1
-rw-r--r--net/core/rtnetlink.c2
-rw-r--r--net/core/sock.c31
-rw-r--r--net/core/sock_diag.c14
-rw-r--r--net/core/utils.c49
-rw-r--r--net/dcb/dcbnl.c30
-rw-r--r--net/dccp/dccp.h4
-rw-r--r--net/dccp/ipv4.c19
-rw-r--r--net/dccp/ipv6.c17
-rw-r--r--net/decnet/dn_nsp_out.c4
-rw-r--r--net/decnet/dn_route.c6
-rw-r--r--net/dsa/dsa.c4
-rw-r--r--net/dsa/slave.c41
-rw-r--r--net/ieee802154/6lowpan/core.c18
-rw-r--r--net/ieee802154/6lowpan/rx.c2
-rw-r--r--net/ieee802154/6lowpan/tx.c49
-rw-r--r--net/ieee802154/Kconfig5
-rw-r--r--net/ieee802154/core.c12
-rw-r--r--net/ieee802154/core.h1
-rw-r--r--net/ieee802154/header_ops.c20
-rw-r--r--net/ieee802154/nl802154.c1133
-rw-r--r--net/ieee802154/rdev-ops.h109
-rw-r--r--net/ieee802154/socket.c8
-rw-r--r--net/ipv4/fib_semantics.c161
-rw-r--r--net/ipv4/icmp.c19
-rw-r--r--net/ipv4/igmp.c4
-rw-r--r--net/ipv4/inet_connection_sock.c87
-rw-r--r--net/ipv4/inet_hashtables.c6
-rw-r--r--net/ipv4/ip_forward.c2
-rw-r--r--net/ipv4/ip_fragment.c7
-rw-r--r--net/ipv4/ip_input.c10
-rw-r--r--net/ipv4/ip_output.c86
-rw-r--r--net/ipv4/ip_tunnel_core.c6
-rw-r--r--net/ipv4/ip_vti.c2
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/netfilter/ipt_SYNPROXY.c2
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c7
-rw-r--r--net/ipv4/netfilter/nf_dup_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nf_reject_ipv4.c2
-rw-r--r--net/ipv4/raw.c10
-rw-r--r--net/ipv4/route.c81
-rw-r--r--net/ipv4/syncookies.c7
-rw-r--r--net/ipv4/tcp.c24
-rw-r--r--net/ipv4/tcp_fastopen.c26
-rw-r--r--net/ipv4/tcp_input.c16
-rw-r--r--net/ipv4/tcp_ipv4.c13
-rw-r--r--net/ipv4/tcp_minisocks.c19
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv4/udp.c28
-rw-r--r--net/ipv4/xfrm4_output.c6
-rw-r--r--net/ipv6/addrconf.c12
-rw-r--r--net/ipv6/icmp.c6
-rw-r--r--net/ipv6/ila.c4
-rw-r--r--net/ipv6/inet6_hashtables.c2
-rw-r--r--net/ipv6/ip6_fib.c1
-rw-r--r--net/ipv6/ip6_output.c31
-rw-r--r--net/ipv6/ip6_vti.c2
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/mcast.c4
-rw-r--r--net/ipv6/mip6.c16
-rw-r--r--net/ipv6/ndisc.c29
-rw-r--r--net/ipv6/netfilter/ip6t_SYNPROXY.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c4
-rw-r--r--net/ipv6/netfilter/nf_defrag_ipv6_hooks.c3
-rw-r--r--net/ipv6/netfilter/nf_dup_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c2
-rw-r--r--net/ipv6/output_core.c22
-rw-r--r--net/ipv6/raw.c2
-rw-r--r--net/ipv6/route.c73
-rw-r--r--net/ipv6/syncookies.c6
-rw-r--r--net/ipv6/tcp_ipv6.c9
-rw-r--r--net/ipv6/udp.c11
-rw-r--r--net/ipv6/xfrm6_output.c17
-rw-r--r--net/ipv6/xfrm6_policy.c1
-rw-r--r--net/l3mdev/l3mdev.c8
-rw-r--r--net/mac80211/agg-rx.c8
-rw-r--r--net/mac80211/agg-tx.c15
-rw-r--r--net/mac80211/cfg.c56
-rw-r--r--net/mac80211/debugfs.c2
-rw-r--r--net/mac80211/debugfs_key.c51
-rw-r--r--net/mac80211/debugfs_netdev.c41
-rw-r--r--net/mac80211/driver-ops.c222
-rw-r--r--net/mac80211/driver-ops.h259
-rw-r--r--net/mac80211/ieee80211_i.h19
-rw-r--r--net/mac80211/iface.c2
-rw-r--r--net/mac80211/main.c3
-rw-r--r--net/mac80211/mesh.c82
-rw-r--r--net/mac80211/mesh.h10
-rw-r--r--net/mac80211/mesh_plink.c9
-rw-r--r--net/mac80211/mlme.c155
-rw-r--r--net/mac80211/offchannel.c6
-rw-r--r--net/mac80211/pm.c3
-rw-r--r--net/mac80211/rate.c5
-rw-r--r--net/mac80211/rc80211_minstrel_debugfs.c12
-rw-r--r--net/mac80211/rc80211_minstrel_ht_debugfs.c12
-rw-r--r--net/mac80211/sta_info.c8
-rw-r--r--net/mac80211/sta_info.h2
-rw-r--r--net/mac80211/status.c108
-rw-r--r--net/mac80211/tdls.c8
-rw-r--r--net/mac80211/trace.h40
-rw-r--r--net/mac80211/tx.c22
-rw-r--r--net/mac80211/util.c11
-rw-r--r--net/mac802154/cfg.c205
-rw-r--r--net/mac802154/iface.c118
-rw-r--r--net/mac802154/llsec.c1
-rw-r--r--net/mac802154/rx.c4
-rw-r--r--net/mac802154/tx.c7
-rw-r--r--net/mpls/mpls_iptunnel.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c2
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c8
-rw-r--r--net/netfilter/nfnetlink.c2
-rw-r--r--net/netfilter/nfnetlink_log.c6
-rw-r--r--net/netlink/genetlink.c2
-rw-r--r--net/openvswitch/actions.c13
-rw-r--r--net/openvswitch/conntrack.c4
-rw-r--r--net/openvswitch/flow.c4
-rw-r--r--net/openvswitch/flow.h1
-rw-r--r--net/openvswitch/flow_netlink.c129
-rw-r--r--net/openvswitch/flow_table.c2
-rw-r--r--net/packet/af_packet.c34
-rw-r--r--net/rds/af_rds.c8
-rw-r--r--net/rds/bind.c85
-rw-r--r--net/rds/connection.c22
-rw-r--r--net/rds/ib.c47
-rw-r--r--net/rds/ib.h78
-rw-r--r--net/rds/ib_cm.c114
-rw-r--r--net/rds/ib_rdma.c116
-rw-r--r--net/rds/ib_recv.c136
-rw-r--r--net/rds/ib_send.c110
-rw-r--r--net/rds/ib_stats.c22
-rw-r--r--net/rds/rds.h5
-rw-r--r--net/rds/send.c20
-rw-r--r--net/rds/tcp.c16
-rw-r--r--net/rds/tcp_listen.c25
-rw-r--r--net/rds/tcp_send.c8
-rw-r--r--net/rds/threads.c2
-rw-r--r--net/sched/sch_blackhole.c15
-rw-r--r--net/sched/sch_fq.c3
-rw-r--r--net/sctp/sm_make_chunk.c2
-rw-r--r--net/sctp/sm_statefuns.c2
-rw-r--r--net/switchdev/switchdev.c327
-rw-r--r--net/tipc/bearer.c8
-rw-r--r--net/tipc/link.c170
-rw-r--r--net/tipc/link.h5
-rw-r--r--net/tipc/msg.c31
-rw-r--r--net/tipc/msg.h34
-rw-r--r--net/tipc/node.c43
-rw-r--r--net/tipc/udp_media.c1
-rw-r--r--net/wireless/core.c1
-rw-r--r--net/wireless/nl80211.c209
-rw-r--r--net/wireless/reg.c4
-rw-r--r--net/xfrm/xfrm_output.c4
-rw-r--r--net/xfrm/xfrm_policy.c11
178 files changed, 5237 insertions, 1983 deletions
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index ae1896fa45e2..83b19e072224 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -17,6 +17,11 @@
void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype)
{
+ dev->addr_len = EUI64_ADDR_LEN;
+ dev->type = ARPHRD_6LOWPAN;
+ dev->mtu = IPV6_MIN_MTU;
+ dev->priv_flags |= IFF_NO_QUEUE;
+
lowpan_priv(dev)->lltype = lltype;
}
EXPORT_SYMBOL(lowpan_netdev_setup);
diff --git a/net/6lowpan/nhc.h b/net/6lowpan/nhc.h
index ed44938eb5de..c249f17fa37b 100644
--- a/net/6lowpan/nhc.h
+++ b/net/6lowpan/nhc.h
@@ -8,8 +8,6 @@
#include <net/6lowpan.h>
#include <net/ipv6.h>
-#define LOWPAN_NHC_MAX_ID_LEN 1
-
/**
* LOWPAN_NHC - helper macro to generate nh id fields and lowpan_nhc struct
*
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 131e79cde350..db73b8a1433f 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -35,7 +35,6 @@ static struct dentry *lowpan_enable_debugfs;
static struct dentry *lowpan_control_debugfs;
#define IFACE_NAME_TEMPLATE "bt%d"
-#define EUI64_ADDR_LEN 8
struct skb_cb {
struct in6_addr addr;
@@ -674,13 +673,8 @@ static struct header_ops header_ops = {
static void netdev_setup(struct net_device *dev)
{
- dev->addr_len = EUI64_ADDR_LEN;
- dev->type = ARPHRD_6LOWPAN;
-
dev->hard_header_len = 0;
dev->needed_tailroom = 0;
- dev->mtu = IPV6_MIN_MTU;
- dev->tx_queue_len = 0;
dev->flags = IFF_RUNNING | IFF_POINTOPOINT |
IFF_MULTICAST;
dev->watchdog_timeo = 0;
@@ -775,24 +769,7 @@ static struct l2cap_chan *chan_create(void)
chan->chan_type = L2CAP_CHAN_CONN_ORIENTED;
chan->mode = L2CAP_MODE_LE_FLOWCTL;
- chan->omtu = 65535;
- chan->imtu = chan->omtu;
-
- return chan;
-}
-
-static struct l2cap_chan *chan_open(struct l2cap_chan *pchan)
-{
- struct l2cap_chan *chan;
-
- chan = chan_create();
- if (!chan)
- return NULL;
-
- chan->remote_mps = chan->omtu;
- chan->mps = chan->omtu;
-
- chan->state = BT_CONNECTED;
+ chan->imtu = 1280;
return chan;
}
@@ -919,7 +896,10 @@ static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *pchan)
{
struct l2cap_chan *chan;
- chan = chan_open(pchan);
+ chan = chan_create();
+ if (!chan)
+ return NULL;
+
chan->ops = pchan->ops;
BT_DBG("chan %p pchan %p", chan, pchan);
@@ -1065,34 +1045,23 @@ static inline __u8 bdaddr_type(__u8 type)
return BDADDR_LE_RANDOM;
}
-static struct l2cap_chan *chan_get(void)
-{
- struct l2cap_chan *pchan;
-
- pchan = chan_create();
- if (!pchan)
- return NULL;
-
- pchan->ops = &bt_6lowpan_chan_ops;
-
- return pchan;
-}
-
static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type)
{
- struct l2cap_chan *pchan;
+ struct l2cap_chan *chan;
int err;
- pchan = chan_get();
- if (!pchan)
+ chan = chan_create();
+ if (!chan)
return -EINVAL;
- err = l2cap_chan_connect(pchan, cpu_to_le16(L2CAP_PSM_IPSP), 0,
+ chan->ops = &bt_6lowpan_chan_ops;
+
+ err = l2cap_chan_connect(chan, cpu_to_le16(L2CAP_PSM_IPSP), 0,
addr, dst_type);
- BT_DBG("chan %p err %d", pchan, err);
+ BT_DBG("chan %p err %d", chan, err);
if (err < 0)
- l2cap_chan_put(pchan);
+ l2cap_chan_put(chan);
return err;
}
@@ -1117,31 +1086,32 @@ static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type)
static struct l2cap_chan *bt_6lowpan_listen(void)
{
bdaddr_t *addr = BDADDR_ANY;
- struct l2cap_chan *pchan;
+ struct l2cap_chan *chan;
int err;
if (!enable_6lowpan)
return NULL;
- pchan = chan_get();
- if (!pchan)
+ chan = chan_create();
+ if (!chan)
return NULL;
- pchan->state = BT_LISTEN;
- pchan->src_type = BDADDR_LE_PUBLIC;
+ chan->ops = &bt_6lowpan_chan_ops;
+ chan->state = BT_LISTEN;
+ chan->src_type = BDADDR_LE_PUBLIC;
- atomic_set(&pchan->nesting, L2CAP_NESTING_PARENT);
+ atomic_set(&chan->nesting, L2CAP_NESTING_PARENT);
- BT_DBG("chan %p src type %d", pchan, pchan->src_type);
+ BT_DBG("chan %p src type %d", chan, chan->src_type);
- err = l2cap_add_psm(pchan, addr, cpu_to_le16(L2CAP_PSM_IPSP));
+ err = l2cap_add_psm(chan, addr, cpu_to_le16(L2CAP_PSM_IPSP));
if (err) {
- l2cap_chan_put(pchan);
+ l2cap_chan_put(chan);
BT_ERR("psm cannot be added err %d", err);
return NULL;
}
- return pchan;
+ return chan;
}
static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type,
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index a7cdd99ec3f1..d2b3dd32d6cf 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -134,6 +134,66 @@ static const struct file_operations dut_mode_fops = {
.llseek = default_llseek,
};
+static ssize_t vendor_diag_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct hci_dev *hdev = file->private_data;
+ char buf[3];
+
+ buf[0] = hci_dev_test_flag(hdev, HCI_VENDOR_DIAG) ? 'Y': 'N';
+ buf[1] = '\n';
+ buf[2] = '\0';
+ return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t vendor_diag_write(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct hci_dev *hdev = file->private_data;
+ char buf[32];
+ size_t buf_size = min(count, (sizeof(buf)-1));
+ bool enable;
+ int err;
+
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+
+ buf[buf_size] = '\0';
+ if (strtobool(buf, &enable))
+ return -EINVAL;
+
+ hci_req_lock(hdev);
+ err = hdev->set_diag(hdev, enable);
+ hci_req_unlock(hdev);
+
+ if (err < 0)
+ return err;
+
+ if (enable)
+ hci_dev_set_flag(hdev, HCI_VENDOR_DIAG);
+ else
+ hci_dev_clear_flag(hdev, HCI_VENDOR_DIAG);
+
+ return count;
+}
+
+static const struct file_operations vendor_diag_fops = {
+ .open = simple_open,
+ .read = vendor_diag_read,
+ .write = vendor_diag_write,
+ .llseek = default_llseek,
+};
+
+static void hci_debugfs_create_basic(struct hci_dev *hdev)
+{
+ debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev,
+ &dut_mode_fops);
+
+ if (hdev->set_diag)
+ debugfs_create_file("vendor_diag", 0644, hdev->debugfs, hdev,
+ &vendor_diag_fops);
+}
+
/* ---- HCI requests ---- */
static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
@@ -850,13 +910,8 @@ static int __hci_init(struct hci_dev *hdev)
if (err < 0)
return err;
- /* The Device Under Test (DUT) mode is special and available for
- * all controller types. So just create it early on.
- */
- if (hci_dev_test_flag(hdev, HCI_SETUP)) {
- debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev,
- &dut_mode_fops);
- }
+ if (hci_dev_test_flag(hdev, HCI_SETUP))
+ hci_debugfs_create_basic(hdev);
err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT);
if (err < 0)
@@ -933,6 +988,9 @@ static int __hci_unconf_init(struct hci_dev *hdev)
if (err < 0)
return err;
+ if (hci_dev_test_flag(hdev, HCI_SETUP))
+ hci_debugfs_create_basic(hdev);
+
return 0;
}
@@ -1385,6 +1443,9 @@ static int hci_dev_do_open(struct hci_dev *hdev)
goto done;
}
+ set_bit(HCI_RUNNING, &hdev->flags);
+ hci_notify(hdev, HCI_DEV_OPEN);
+
atomic_set(&hdev->cmd_cnt, 1);
set_bit(HCI_INIT, &hdev->flags);
@@ -1466,6 +1527,9 @@ static int hci_dev_do_open(struct hci_dev *hdev)
hdev->sent_cmd = NULL;
}
+ clear_bit(HCI_RUNNING, &hdev->flags);
+ hci_notify(hdev, HCI_DEV_CLOSE);
+
hdev->close(hdev);
hdev->flags &= BIT(HCI_RAW);
}
@@ -1551,6 +1615,8 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev)
int hci_dev_do_close(struct hci_dev *hdev)
{
+ bool auto_off;
+
BT_DBG("%s %p", hdev->name, hdev);
if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) &&
@@ -1606,10 +1672,10 @@ int hci_dev_do_close(struct hci_dev *hdev)
hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
- if (!hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) {
- if (hdev->dev_type == HCI_BREDR)
- mgmt_powered(hdev, 0);
- }
+ auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF);
+
+ if (!auto_off && hdev->dev_type == HCI_BREDR)
+ mgmt_powered(hdev, 0);
hci_inquiry_cache_flush(hdev);
hci_pend_le_actions_clear(hdev);
@@ -1626,9 +1692,8 @@ int hci_dev_do_close(struct hci_dev *hdev)
/* Reset device */
skb_queue_purge(&hdev->cmd_q);
atomic_set(&hdev->cmd_cnt, 1);
- if (!hci_dev_test_flag(hdev, HCI_AUTO_OFF) &&
- !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
- test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) {
+ if (test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks) &&
+ !auto_off && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
set_bit(HCI_INIT, &hdev->flags);
__hci_req_sync(hdev, hci_reset_req, 0, HCI_CMD_TIMEOUT);
clear_bit(HCI_INIT, &hdev->flags);
@@ -1649,6 +1714,9 @@ int hci_dev_do_close(struct hci_dev *hdev)
hdev->sent_cmd = NULL;
}
+ clear_bit(HCI_RUNNING, &hdev->flags);
+ hci_notify(hdev, HCI_DEV_CLOSE);
+
/* After this point our queues are empty
* and no tasks are scheduled. */
hdev->close(hdev);
@@ -3471,6 +3539,13 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
return -ENXIO;
}
+ if (bt_cb(skb)->pkt_type != HCI_EVENT_PKT &&
+ bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+ bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
/* Incoming skb */
bt_cb(skb)->incoming = 1;
@@ -3484,6 +3559,21 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
}
EXPORT_SYMBOL(hci_recv_frame);
+/* Receive diagnostic message from HCI drivers */
+int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ /* Time stamp */
+ __net_timestamp(skb);
+
+ /* Mark as diagnostic packet and send to monitor */
+ bt_cb(skb)->pkt_type = HCI_DIAG_PKT;
+ hci_send_to_monitor(hdev, skb);
+
+ kfree_skb(skb);
+ return 0;
+}
+EXPORT_SYMBOL(hci_recv_diag);
+
/* ---- Interface to upper protocols ---- */
int hci_register_cb(struct hci_cb *cb)
@@ -3530,6 +3620,11 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
/* Get rid of skb owner, prior to sending to the driver. */
skb_orphan(skb);
+ if (!test_bit(HCI_RUNNING, &hdev->flags)) {
+ kfree_skb(skb);
+ return;
+ }
+
err = hdev->send(hdev, skb);
if (err < 0) {
BT_ERR("%s sending frame failed (%d)", hdev->name, err);
@@ -3580,6 +3675,25 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode)
return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE;
}
+/* Send HCI command and wait for command commplete event */
+struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
+ const void *param, u32 timeout)
+{
+ struct sk_buff *skb;
+
+ if (!test_bit(HCI_UP, &hdev->flags))
+ return ERR_PTR(-ENETDOWN);
+
+ bt_dev_dbg(hdev, "opcode 0x%4.4x plen %d", opcode, plen);
+
+ hci_req_lock(hdev);
+ skb = __hci_cmd_sync(hdev, opcode, plen, param, timeout);
+ hci_req_unlock(hdev);
+
+ return skb;
+}
+EXPORT_SYMBOL(hci_cmd_sync);
+
/* Send ACL data */
static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags)
{
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 150556345263..9a100c1fd7b5 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -279,6 +279,9 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
else
opcode = cpu_to_le16(HCI_MON_SCO_TX_PKT);
break;
+ case HCI_DIAG_PKT:
+ opcode = cpu_to_le16(HCI_MON_VENDOR_DIAG);
+ break;
default:
return;
}
@@ -303,6 +306,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
{
struct hci_mon_hdr *hdr;
struct hci_mon_new_index *ni;
+ struct hci_mon_index_info *ii;
struct sk_buff *skb;
__le16 opcode;
@@ -312,7 +316,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
if (!skb)
return NULL;
- ni = (void *) skb_put(skb, HCI_MON_NEW_INDEX_SIZE);
+ ni = (void *)skb_put(skb, HCI_MON_NEW_INDEX_SIZE);
ni->type = hdev->dev_type;
ni->bus = hdev->bus;
bacpy(&ni->bdaddr, &hdev->bdaddr);
@@ -329,6 +333,34 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
opcode = cpu_to_le16(HCI_MON_DEL_INDEX);
break;
+ case HCI_DEV_UP:
+ skb = bt_skb_alloc(HCI_MON_INDEX_INFO_SIZE, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ ii = (void *)skb_put(skb, HCI_MON_INDEX_INFO_SIZE);
+ bacpy(&ii->bdaddr, &hdev->bdaddr);
+ ii->manufacturer = cpu_to_le16(hdev->manufacturer);
+
+ opcode = cpu_to_le16(HCI_MON_INDEX_INFO);
+ break;
+
+ case HCI_DEV_OPEN:
+ skb = bt_skb_alloc(0, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ opcode = cpu_to_le16(HCI_MON_OPEN_INDEX);
+ break;
+
+ case HCI_DEV_CLOSE:
+ skb = bt_skb_alloc(0, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ opcode = cpu_to_le16(HCI_MON_CLOSE_INDEX);
+ break;
+
default:
return NULL;
}
@@ -358,6 +390,26 @@ static void send_monitor_replay(struct sock *sk)
if (sock_queue_rcv_skb(sk, skb))
kfree_skb(skb);
+
+ if (!test_bit(HCI_RUNNING, &hdev->flags))
+ continue;
+
+ skb = create_monitor_event(hdev, HCI_DEV_OPEN);
+ if (!skb)
+ continue;
+
+ if (sock_queue_rcv_skb(sk, skb))
+ kfree_skb(skb);
+
+ if (!test_bit(HCI_UP, &hdev->flags))
+ continue;
+
+ skb = create_monitor_event(hdev, HCI_DEV_UP);
+ if (!skb)
+ continue;
+
+ if (sock_queue_rcv_skb(sk, skb))
+ kfree_skb(skb);
}
read_unlock(&hci_dev_list_lock);
@@ -392,14 +444,12 @@ static void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data)
void hci_sock_dev_event(struct hci_dev *hdev, int event)
{
- struct hci_ev_si_device ev;
-
BT_DBG("hdev %s event %d", hdev->name, event);
- /* Send event to monitor */
if (atomic_read(&monitor_promisc)) {
struct sk_buff *skb;
+ /* Send event to monitor */
skb = create_monitor_event(hdev, event);
if (skb) {
hci_send_to_channel(HCI_CHANNEL_MONITOR, skb,
@@ -408,10 +458,14 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event)
}
}
- /* Send event to sockets */
- ev.event = event;
- ev.dev_id = hdev->id;
- hci_si_event(NULL, HCI_EV_SI_DEVICE, sizeof(ev), &ev);
+ if (event <= HCI_DEV_DOWN) {
+ struct hci_ev_si_device ev;
+
+ /* Send event to sockets */
+ ev.event = event;
+ ev.dev_id = hdev->id;
+ hci_si_event(NULL, HCI_EV_SI_DEVICE, sizeof(ev), &ev);
+ }
if (event == HCI_DEV_UNREG) {
struct sock *sk;
diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c
index 8b4cdce3f62e..aa4cf64e32a6 100644
--- a/net/bluetooth/lib.c
+++ b/net/bluetooth/lib.c
@@ -151,6 +151,22 @@ void bt_info(const char *format, ...)
}
EXPORT_SYMBOL(bt_info);
+void bt_warn(const char *format, ...)
+{
+ struct va_format vaf;
+ va_list args;
+
+ va_start(args, format);
+
+ vaf.fmt = format;
+ vaf.va = &args;
+
+ pr_warn("%pV", &vaf);
+
+ va_end(args);
+}
+EXPORT_SYMBOL(bt_warn);
+
void bt_err(const char *format, ...)
{
struct va_format vaf;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index bdfb9544ca03..5e88d3e17546 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -56,7 +56,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
- if (!br_allowed_ingress(br, br_vlan_group(br), skb, &vid))
+ if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid))
goto out;
if (is_broadcast_ether_addr(dest))
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 7f7d55132dd5..c88bd8e8937e 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -134,11 +134,14 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr)
static void fdb_del_external_learn(struct net_bridge_fdb_entry *f)
{
struct switchdev_obj_port_fdb fdb = {
- .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
- .addr = f->addr.addr,
+ .obj = {
+ .id = SWITCHDEV_OBJ_ID_PORT_FDB,
+ .flags = SWITCHDEV_F_DEFER,
+ },
.vid = f->vlan_id,
};
+ ether_addr_copy(fdb.addr, f->addr.addr);
switchdev_port_obj_del(f->dst->dev, &fdb.obj);
}
@@ -608,13 +611,14 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
}
}
-static int fdb_to_nud(const struct net_bridge_fdb_entry *fdb)
+static int fdb_to_nud(const struct net_bridge *br,
+ const struct net_bridge_fdb_entry *fdb)
{
if (fdb->is_local)
return NUD_PERMANENT;
else if (fdb->is_static)
return NUD_NOARP;
- else if (has_expired(fdb->dst->br, fdb))
+ else if (has_expired(br, fdb))
return NUD_STALE;
else
return NUD_REACHABLE;
@@ -640,7 +644,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
ndm->ndm_flags = fdb->added_by_external_learn ? NTF_EXT_LEARNED : 0;
ndm->ndm_type = 0;
ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
- ndm->ndm_state = fdb_to_nud(fdb);
+ ndm->ndm_state = fdb_to_nud(br, fdb);
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr))
goto nla_put_failure;
@@ -785,7 +789,7 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
}
}
- if (fdb_to_nud(fdb) != state) {
+ if (fdb_to_nud(br, fdb) != state) {
if (state & NUD_PERMANENT) {
fdb->is_local = 1;
if (!fdb->is_static) {
@@ -846,8 +850,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
const unsigned char *addr, u16 vid, u16 nlh_flags)
{
struct net_bridge_vlan_group *vg;
- struct net_bridge_port *p;
+ struct net_bridge_port *p = NULL;
struct net_bridge_vlan *v;
+ struct net_bridge *br = NULL;
int err = 0;
if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
@@ -860,26 +865,36 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
return -EINVAL;
}
- p = br_port_get_rtnl(dev);
- if (p == NULL) {
- pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
- dev->name);
- return -EINVAL;
+ if (dev->priv_flags & IFF_EBRIDGE) {
+ br = netdev_priv(dev);
+ vg = br_vlan_group(br);
+ } else {
+ p = br_port_get_rtnl(dev);
+ if (!p) {
+ pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
+ dev->name);
+ return -EINVAL;
+ }
+ vg = nbp_vlan_group(p);
}
- vg = nbp_vlan_group(p);
if (vid) {
v = br_vlan_find(vg, vid);
- if (!v) {
- pr_info("bridge: RTM_NEWNEIGH with unconfigured "
- "vlan %d on port %s\n", vid, dev->name);
+ if (!v || !br_vlan_should_use(v)) {
+ pr_info("bridge: RTM_NEWNEIGH with unconfigured vlan %d on %s\n", vid, dev->name);
return -EINVAL;
}
/* VID was specified, so use it. */
- err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
+ if (dev->priv_flags & IFF_EBRIDGE)
+ err = br_fdb_insert(br, NULL, addr, vid);
+ else
+ err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
} else {
- err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
+ if (dev->priv_flags & IFF_EBRIDGE)
+ err = br_fdb_insert(br, NULL, addr, 0);
+ else
+ err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
if (err || !vg || !vg->num_vlans)
goto out;
@@ -888,7 +903,13 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
* vlan on this port.
*/
list_for_each_entry(v, &vg->vlan_list, vlist) {
- err = __br_fdb_add(ndm, p, addr, nlh_flags, v->vid);
+ if (!br_vlan_should_use(v))
+ continue;
+ if (dev->priv_flags & IFF_EBRIDGE)
+ err = br_fdb_insert(br, NULL, addr, v->vid);
+ else
+ err = __br_fdb_add(ndm, p, addr, nlh_flags,
+ v->vid);
if (err)
goto out;
}
@@ -898,6 +919,32 @@ out:
return err;
}
+static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr,
+ u16 vid)
+{
+ struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+ struct net_bridge_fdb_entry *fdb;
+
+ fdb = fdb_find(head, addr, vid);
+ if (!fdb)
+ return -ENOENT;
+
+ fdb_delete(br, fdb);
+ return 0;
+}
+
+static int __br_fdb_delete_by_addr(struct net_bridge *br,
+ const unsigned char *addr, u16 vid)
+{
+ int err;
+
+ spin_lock_bh(&br->hash_lock);
+ err = fdb_delete_by_addr(br, addr, vid);
+ spin_unlock_bh(&br->hash_lock);
+
+ return err;
+}
+
static int fdb_delete_by_addr_and_port(struct net_bridge_port *p,
const u8 *addr, u16 vlan)
{
@@ -931,35 +978,53 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
const unsigned char *addr, u16 vid)
{
struct net_bridge_vlan_group *vg;
- struct net_bridge_port *p;
+ struct net_bridge_port *p = NULL;
struct net_bridge_vlan *v;
+ struct net_bridge *br = NULL;
int err;
- p = br_port_get_rtnl(dev);
- if (p == NULL) {
- pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
- dev->name);
- return -EINVAL;
+ if (dev->priv_flags & IFF_EBRIDGE) {
+ br = netdev_priv(dev);
+ vg = br_vlan_group(br);
+ } else {
+ p = br_port_get_rtnl(dev);
+ if (!p) {
+ pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
+ dev->name);
+ return -EINVAL;
+ }
+ vg = nbp_vlan_group(p);
}
- vg = nbp_vlan_group(p);
if (vid) {
v = br_vlan_find(vg, vid);
if (!v) {
- pr_info("bridge: RTM_DELNEIGH with unconfigured "
- "vlan %d on port %s\n", vid, dev->name);
+ pr_info("bridge: RTM_DELNEIGH with unconfigured vlan %d on %s\n", vid, dev->name);
return -EINVAL;
}
- err = __br_fdb_delete(p, addr, vid);
+ if (dev->priv_flags & IFF_EBRIDGE)
+ err = __br_fdb_delete_by_addr(br, addr, vid);
+ else
+ err = __br_fdb_delete(p, addr, vid);
} else {
err = -ENOENT;
- err &= __br_fdb_delete(p, addr, 0);
+ if (dev->priv_flags & IFF_EBRIDGE)
+ err = __br_fdb_delete_by_addr(br, addr, 0);
+ else
+ err &= __br_fdb_delete(p, addr, 0);
+
if (!vg || !vg->num_vlans)
goto out;
- list_for_each_entry(v, &vg->vlan_list, vlist)
- err &= __br_fdb_delete(p, addr, v->vid);
+ list_for_each_entry(v, &vg->vlan_list, vlist) {
+ if (!br_vlan_should_use(v))
+ continue;
+ if (dev->priv_flags & IFF_EBRIDGE)
+ err = __br_fdb_delete_by_addr(br, addr, v->vid);
+ else
+ err &= __br_fdb_delete(p, addr, v->vid);
+ }
}
out:
return err;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 6d5ed795c3e2..a9d424e20229 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -32,7 +32,7 @@ static inline int should_deliver(const struct net_bridge_port *p,
{
struct net_bridge_vlan_group *vg;
- vg = nbp_vlan_group(p);
+ vg = nbp_vlan_group_rcu(p);
return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING;
}
@@ -80,7 +80,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
{
struct net_bridge_vlan_group *vg;
- vg = nbp_vlan_group(to);
+ vg = nbp_vlan_group_rcu(to);
skb = br_handle_vlan(to->br, vg, skb);
if (!skb)
return;
@@ -112,7 +112,7 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
return;
}
- vg = nbp_vlan_group(to);
+ vg = nbp_vlan_group_rcu(to);
skb = br_handle_vlan(to->br, vg, skb);
if (!skb)
return;
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 934cae9fa317..ec02f5869a78 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <net/sock.h>
#include <linux/if_vlan.h>
+#include <net/switchdev.h>
#include "br_private.h"
@@ -248,7 +249,10 @@ static void del_nbp(struct net_bridge_port *p)
list_del_rcu(&p->list);
+ nbp_vlan_flush(p);
br_fdb_delete_by_port(br, p, 0, 1);
+ switchdev_deferred_process();
+
nbp_update_port_count(br);
netdev_upper_dev_unlink(dev, br->dev);
@@ -256,8 +260,6 @@ static void del_nbp(struct net_bridge_port *p)
dev->priv_flags &= ~IFF_BRIDGE_PORT;
netdev_rx_handler_unregister(dev);
- /* use the synchronize_rcu done by netdev_rx_handler_unregister */
- nbp_vlan_flush(p);
br_multicast_del_port(p);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index f5c5a4500e2f..f7fba74108a9 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -44,7 +44,7 @@ static int br_pass_frame_up(struct sk_buff *skb)
brstats->rx_bytes += skb->len;
u64_stats_update_end(&brstats->syncp);
- vg = br_vlan_group(br);
+ vg = br_vlan_group_rcu(br);
/* Bridge is just like any other port. Make sure the
* packet is allowed except in promisc modue when someone
* may be running packet capture.
@@ -140,7 +140,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
if (!p || p->state == BR_STATE_DISABLED)
goto drop;
- if (!br_allowed_ingress(p->br, nbp_vlan_group(p), skb, &vid))
+ if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid))
goto out;
/* insert into forwarding database after filtering to avoid spoofing */
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 8d423bc649b9..263b4de4de57 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -200,8 +200,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
- br->ageing_time = clock_t_to_jiffies(args[1]);
- return 0;
+ return br_set_ageing_time(br, args[1]);
case BRCTL_GET_PORT_INFO:
{
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 9d3051916a64..7ddbe7ec81d6 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -688,15 +688,10 @@ static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff
nf_bridge_info_free(skb);
return br_dev_queue_push_xmit(net, sk, skb);
}
-static int br_nf_push_frag_xmit_sk(struct sock *sk, struct sk_buff *skb)
-{
- struct net *net = dev_net(skb_dst(skb)->dev);
- return br_nf_push_frag_xmit(net, sk, skb);
-}
static int
br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *))
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
{
unsigned int mtu = ip_skb_dst_mtu(skb);
struct iphdr *iph = ip_hdr(skb);
@@ -709,7 +704,7 @@ br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
return -EMSGSIZE;
}
- return ip_do_fragment(sk, skb, output);
+ return ip_do_fragment(net, sk, skb, output);
}
static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
@@ -757,7 +752,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
data->size);
- return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit_sk);
+ return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit);
}
if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) &&
skb->protocol == htons(ETH_P_IPV6)) {
@@ -779,7 +774,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
data->size);
if (v6ops)
- return v6ops->fragment(sk, skb, br_nf_push_frag_xmit_sk);
+ return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit);
kfree_skb(skb);
return -EMSGSIZE;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index c64dcad11662..94b4de8c4646 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -34,7 +34,7 @@ static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg,
pvid = br_get_pvid(vg);
/* Count number of vlan infos */
- list_for_each_entry(v, &vg->vlan_list, vlist) {
+ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
flags = 0;
/* only a context, bridge vlan not activated */
if (!br_vlan_should_use(v))
@@ -76,13 +76,19 @@ initvars:
static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg,
u32 filter_mask)
{
+ int num_vlans;
+
if (!vg)
return 0;
if (filter_mask & RTEXT_FILTER_BRVLAN)
return vg->num_vlans;
- return __get_num_vlan_infos(vg, filter_mask);
+ rcu_read_lock();
+ num_vlans = __get_num_vlan_infos(vg, filter_mask);
+ rcu_read_unlock();
+
+ return num_vlans;
}
static size_t br_get_link_af_size_filtered(const struct net_device *dev,
@@ -96,10 +102,10 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
rcu_read_lock();
if (br_port_exists(dev)) {
p = br_port_get_rcu(dev);
- vg = nbp_vlan_group(p);
+ vg = nbp_vlan_group_rcu(p);
} else if (dev->priv_flags & IFF_EBRIDGE) {
br = netdev_priv(dev);
- vg = br_vlan_group(br);
+ vg = br_vlan_group_rcu(br);
}
num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask);
rcu_read_unlock();
@@ -121,6 +127,20 @@ static inline size_t br_port_info_size(void)
+ nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */
+ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */
+ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */
+ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */
+ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */
+ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */
+ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */
+ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */
+ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */
+ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */
+ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */
+ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */
+#endif
+ 0;
}
@@ -142,6 +162,7 @@ static int br_port_fill_attrs(struct sk_buff *skb,
const struct net_bridge_port *p)
{
u8 mode = !!(p->flags & BR_HAIRPIN_MODE);
+ u64 timerval;
if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
@@ -154,8 +175,35 @@ static int br_port_fill_attrs(struct sk_buff *skb,
nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) ||
nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) ||
nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI,
- !!(p->flags & BR_PROXYARP_WIFI)))
+ !!(p->flags & BR_PROXYARP_WIFI)) ||
+ nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id),
+ &p->designated_root) ||
+ nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id),
+ &p->designated_bridge) ||
+ nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) ||
+ nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) ||
+ nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) ||
+ nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) ||
+ nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK,
+ p->topology_change_ack) ||
+ nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending))
+ return -EMSGSIZE;
+
+ timerval = br_timer_value(&p->message_age_timer);
+ if (nla_put_u64(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval))
return -EMSGSIZE;
+ timerval = br_timer_value(&p->forward_delay_timer);
+ if (nla_put_u64(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval))
+ return -EMSGSIZE;
+ timerval = br_timer_value(&p->hold_timer);
+ if (nla_put_u64(skb, IFLA_BRPORT_HOLD_TIMER, timerval))
+ return -EMSGSIZE;
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER,
+ p->multicast_router))
+ return -EMSGSIZE;
+#endif
return 0;
}
@@ -205,7 +253,7 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb,
* if vlaninfo represents a range
*/
pvid = br_get_pvid(vg);
- list_for_each_entry(v, &vg->vlan_list, vlist) {
+ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
flags = 0;
if (!br_vlan_should_use(v))
continue;
@@ -255,7 +303,7 @@ static int br_fill_ifvlaninfo(struct sk_buff *skb,
u16 pvid;
pvid = br_get_pvid(vg);
- list_for_each_entry(v, &vg->vlan_list, vlist) {
+ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
if (!br_vlan_should_use(v))
continue;
@@ -338,22 +386,27 @@ static int br_fill_ifinfo(struct sk_buff *skb,
struct nlattr *af;
int err;
+ /* RCU needed because of the VLAN locking rules (rcu || rtnl) */
+ rcu_read_lock();
if (port)
- vg = nbp_vlan_group(port);
+ vg = nbp_vlan_group_rcu(port);
else
- vg = br_vlan_group(br);
+ vg = br_vlan_group_rcu(br);
- if (!vg || !vg->num_vlans)
+ if (!vg || !vg->num_vlans) {
+ rcu_read_unlock();
goto done;
-
+ }
af = nla_nest_start(skb, IFLA_AF_SPEC);
- if (!af)
+ if (!af) {
+ rcu_read_unlock();
goto nla_put_failure;
-
+ }
if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
err = br_fill_ifvlaninfo_compressed(skb, vg);
else
err = br_fill_ifvlaninfo(skb, vg);
+ rcu_read_unlock();
if (err)
goto nla_put_failure;
nla_nest_end(skb, af);
@@ -476,6 +529,9 @@ static int br_afspec(struct net_bridge *br,
if (vinfo_start)
return -EINVAL;
vinfo_start = vinfo;
+ /* don't allow range of pvids */
+ if (vinfo_start->flags & BRIDGE_VLAN_INFO_PVID)
+ return -EINVAL;
continue;
}
@@ -521,6 +577,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
[IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 },
[IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 },
+ [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 },
};
/* Change the state of the port and notify spanning tree */
@@ -592,6 +649,18 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
return err;
}
+ if (tb[IFLA_BRPORT_FLUSH])
+ br_fdb_delete_by_port(p->br, p, 0, 0);
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) {
+ u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]);
+
+ err = br_multicast_set_port_router(p, mcast_router);
+ if (err)
+ return err;
+ }
+#endif
br_port_flags_change(p, old_flags ^ p->flags);
return 0;
}
@@ -758,6 +827,27 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
[IFLA_BR_PRIORITY] = { .type = NLA_U16 },
[IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 },
[IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 },
+ [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 },
+ [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY,
+ .len = ETH_ALEN },
+ [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 },
+ [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 },
+ [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 },
+ [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 },
+ [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 },
+ [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 },
+ [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 },
+ [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 },
+ [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 },
+ [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 },
+ [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 },
+ [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 },
+ [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 },
+ [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 },
+ [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 },
+ [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 },
+ [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 },
+ [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 },
};
static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -788,9 +878,9 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
}
if (data[IFLA_BR_AGEING_TIME]) {
- u32 ageing_time = nla_get_u32(data[IFLA_BR_AGEING_TIME]);
-
- br->ageing_time = clock_t_to_jiffies(ageing_time);
+ err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME]));
+ if (err)
+ return err;
}
if (data[IFLA_BR_STP_STATE]) {
@@ -821,6 +911,158 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
if (err)
return err;
}
+
+ if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
+ __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
+
+ err = __br_vlan_set_default_pvid(br, defpvid);
+ if (err)
+ return err;
+ }
+#endif
+
+ if (data[IFLA_BR_GROUP_FWD_MASK]) {
+ u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]);
+
+ if (fwd_mask & BR_GROUPFWD_RESTRICTED)
+ return -EINVAL;
+ br->group_fwd_mask = fwd_mask;
+ }
+
+ if (data[IFLA_BR_GROUP_ADDR]) {
+ u8 new_addr[ETH_ALEN];
+
+ if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN)
+ return -EINVAL;
+ memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN);
+ if (!is_link_local_ether_addr(new_addr))
+ return -EINVAL;
+ if (new_addr[5] == 1 || /* 802.3x Pause address */
+ new_addr[5] == 2 || /* 802.3ad Slow protocols */
+ new_addr[5] == 3) /* 802.1X PAE address */
+ return -EINVAL;
+ spin_lock_bh(&br->lock);
+ memcpy(br->group_addr, new_addr, sizeof(br->group_addr));
+ spin_unlock_bh(&br->lock);
+ br->group_addr_set = true;
+ br_recalculate_fwd_mask(br);
+ }
+
+ if (data[IFLA_BR_FDB_FLUSH])
+ br_fdb_flush(br);
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ if (data[IFLA_BR_MCAST_ROUTER]) {
+ u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]);
+
+ err = br_multicast_set_router(br, multicast_router);
+ if (err)
+ return err;
+ }
+
+ if (data[IFLA_BR_MCAST_SNOOPING]) {
+ u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]);
+
+ err = br_multicast_toggle(br, mcast_snooping);
+ if (err)
+ return err;
+ }
+
+ if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) {
+ u8 val;
+
+ val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]);
+ br->multicast_query_use_ifaddr = !!val;
+ }
+
+ if (data[IFLA_BR_MCAST_QUERIER]) {
+ u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]);
+
+ err = br_multicast_set_querier(br, mcast_querier);
+ if (err)
+ return err;
+ }
+
+ if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) {
+ u32 val = nla_get_u32(data[IFLA_BR_MCAST_HASH_ELASTICITY]);
+
+ br->hash_elasticity = val;
+ }
+
+ if (data[IFLA_BR_MCAST_HASH_MAX]) {
+ u32 hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]);
+
+ err = br_multicast_set_hash_max(br, hash_max);
+ if (err)
+ return err;
+ }
+
+ if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) {
+ u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]);
+
+ br->multicast_last_member_count = val;
+ }
+
+ if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) {
+ u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]);
+
+ br->multicast_startup_query_count = val;
+ }
+
+ if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) {
+ u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]);
+
+ br->multicast_last_member_interval = clock_t_to_jiffies(val);
+ }
+
+ if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) {
+ u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]);
+
+ br->multicast_membership_interval = clock_t_to_jiffies(val);
+ }
+
+ if (data[IFLA_BR_MCAST_QUERIER_INTVL]) {
+ u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]);
+
+ br->multicast_querier_interval = clock_t_to_jiffies(val);
+ }
+
+ if (data[IFLA_BR_MCAST_QUERY_INTVL]) {
+ u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]);
+
+ br->multicast_query_interval = clock_t_to_jiffies(val);
+ }
+
+ if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) {
+ u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]);
+
+ br->multicast_query_response_interval = clock_t_to_jiffies(val);
+ }
+
+ if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) {
+ u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]);
+
+ br->multicast_startup_query_interval = clock_t_to_jiffies(val);
+ }
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ if (data[IFLA_BR_NF_CALL_IPTABLES]) {
+ u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]);
+
+ br->nf_call_iptables = val ? true : false;
+ }
+
+ if (data[IFLA_BR_NF_CALL_IP6TABLES]) {
+ u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]);
+
+ br->nf_call_ip6tables = val ? true : false;
+ }
+
+ if (data[IFLA_BR_NF_CALL_ARPTABLES]) {
+ u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]);
+
+ br->nf_call_arptables = val ? true : false;
+ }
#endif
return 0;
@@ -837,6 +1079,40 @@ static size_t br_get_size(const struct net_device *brdev)
nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */
+ nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */
+#endif
+ nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */
+ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */
+ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */
+ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */
+ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */
+ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */
+ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */
+ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */
#endif
0;
}
@@ -851,6 +1127,20 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
u32 stp_enabled = br->stp_enabled;
u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1];
u8 vlan_enabled = br_vlan_enabled(br);
+ u64 clockval;
+
+ clockval = br_timer_value(&br->hello_timer);
+ if (nla_put_u64(skb, IFLA_BR_HELLO_TIMER, clockval))
+ return -EMSGSIZE;
+ clockval = br_timer_value(&br->tcn_timer);
+ if (nla_put_u64(skb, IFLA_BR_TCN_TIMER, clockval))
+ return -EMSGSIZE;
+ clockval = br_timer_value(&br->topology_change_timer);
+ if (nla_put_u64(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval))
+ return -EMSGSIZE;
+ clockval = br_timer_value(&br->gc_timer);
+ if (nla_put_u64(skb, IFLA_BR_GC_TIMER, clockval))
+ return -EMSGSIZE;
if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) ||
nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) ||
@@ -858,11 +1148,66 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) ||
nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) ||
nla_put_u16(skb, IFLA_BR_PRIORITY, priority) ||
- nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled))
+ nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) ||
+ nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) ||
+ nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id),
+ &br->bridge_id) ||
+ nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id),
+ &br->designated_root) ||
+ nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) ||
+ nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) ||
+ nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) ||
+ nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
+ br->topology_change_detected) ||
+ nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr))
return -EMSGSIZE;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
- if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto))
+ if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) ||
+ nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid))
+ return -EMSGSIZE;
+#endif
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) ||
+ nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) ||
+ nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR,
+ br->multicast_query_use_ifaddr) ||
+ nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) ||
+ nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY,
+ br->hash_elasticity) ||
+ nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) ||
+ nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT,
+ br->multicast_last_member_count) ||
+ nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT,
+ br->multicast_startup_query_count))
+ return -EMSGSIZE;
+
+ clockval = jiffies_to_clock_t(br->multicast_last_member_interval);
+ if (nla_put_u64(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval))
+ return -EMSGSIZE;
+ clockval = jiffies_to_clock_t(br->multicast_membership_interval);
+ if (nla_put_u64(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval))
+ return -EMSGSIZE;
+ clockval = jiffies_to_clock_t(br->multicast_querier_interval);
+ if (nla_put_u64(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval))
+ return -EMSGSIZE;
+ clockval = jiffies_to_clock_t(br->multicast_query_interval);
+ if (nla_put_u64(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval))
+ return -EMSGSIZE;
+ clockval = jiffies_to_clock_t(br->multicast_query_response_interval);
+ if (nla_put_u64(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval))
+ return -EMSGSIZE;
+ clockval = jiffies_to_clock_t(br->multicast_startup_query_interval);
+ if (nla_put_u64(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval))
+ return -EMSGSIZE;
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES,
+ br->nf_call_iptables ? 1 : 0) ||
+ nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES,
+ br->nf_call_ip6tables ? 1 : 0) ||
+ nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES,
+ br->nf_call_arptables ? 1 : 0))
return -EMSGSIZE;
#endif
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 4ed8308db66e..216018c76018 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -229,7 +229,7 @@ struct net_bridge_port
struct netpoll *np;
#endif
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
- struct net_bridge_vlan_group *vlgrp;
+ struct net_bridge_vlan_group __rcu *vlgrp;
#endif
};
@@ -337,7 +337,7 @@ struct net_bridge
struct kobject *ifobj;
u32 auto_cnt;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
- struct net_bridge_vlan_group *vlgrp;
+ struct net_bridge_vlan_group __rcu *vlgrp;
u8 vlan_enabled;
__be16 vlan_proto;
u16 default_pvid;
@@ -400,7 +400,7 @@ static inline bool br_vlan_is_brentry(const struct net_bridge_vlan *v)
return v->flags & BRIDGE_VLAN_INFO_BRENTRY;
}
-/* check if we should use the vlan entry is usable */
+/* check if we should use the vlan entry, returns false if it's only context */
static inline bool br_vlan_should_use(const struct net_bridge_vlan *v)
{
if (br_vlan_is_master(v)) {
@@ -690,6 +690,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto);
int br_vlan_set_proto(struct net_bridge *br, unsigned long val);
int br_vlan_init(struct net_bridge *br);
int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val);
+int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid);
int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
void nbp_vlan_flush(struct net_bridge_port *port);
@@ -699,13 +700,25 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
static inline struct net_bridge_vlan_group *br_vlan_group(
const struct net_bridge *br)
{
- return br->vlgrp;
+ return rtnl_dereference(br->vlgrp);
}
static inline struct net_bridge_vlan_group *nbp_vlan_group(
const struct net_bridge_port *p)
{
- return p->vlgrp;
+ return rtnl_dereference(p->vlgrp);
+}
+
+static inline struct net_bridge_vlan_group *br_vlan_group_rcu(
+ const struct net_bridge *br)
+{
+ return rcu_dereference(br->vlgrp);
+}
+
+static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu(
+ const struct net_bridge_port *p)
+{
+ return rcu_dereference(p->vlgrp);
}
/* Since bridge now depends on 8021Q module, but the time bridge sees the
@@ -852,6 +865,19 @@ static inline struct net_bridge_vlan_group *nbp_vlan_group(
{
return NULL;
}
+
+static inline struct net_bridge_vlan_group *br_vlan_group_rcu(
+ const struct net_bridge *br)
+{
+ return NULL;
+}
+
+static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu(
+ const struct net_bridge_port *p)
+{
+ return NULL;
+}
+
#endif
struct nf_br_ops {
@@ -881,6 +907,7 @@ void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
int br_set_forward_delay(struct net_bridge *br, unsigned long x);
int br_set_hello_time(struct net_bridge *br, unsigned long x);
int br_set_max_age(struct net_bridge *br, unsigned long x);
+int br_set_ageing_time(struct net_bridge *br, u32 ageing_time);
/* br_stp_if.c */
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 3a982c02599a..80c34d70218c 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -41,13 +41,14 @@ void br_set_state(struct net_bridge_port *p, unsigned int state)
{
struct switchdev_attr attr = {
.id = SWITCHDEV_ATTR_ID_PORT_STP_STATE,
+ .flags = SWITCHDEV_F_DEFER,
.u.stp_state = state,
};
int err;
p->state = state;
err = switchdev_port_attr_set(p->dev, &attr);
- if (err && err != -EOPNOTSUPP)
+ if (err)
br_warn(p->br, "error setting offload STP state on port %u(%s)\n",
(unsigned int) p->port_no, p->dev->name);
}
@@ -566,6 +567,29 @@ int br_set_max_age(struct net_bridge *br, unsigned long val)
}
+int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
+{
+ struct switchdev_attr attr = {
+ .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
+ .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP,
+ .u.ageing_time = ageing_time,
+ };
+ unsigned long t = clock_t_to_jiffies(ageing_time);
+ int err;
+
+ if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME)
+ return -ERANGE;
+
+ err = switchdev_port_attr_set(br->dev, &attr);
+ if (err)
+ return err;
+
+ br->ageing_time = t;
+ mod_timer(&br->gc_timer, jiffies);
+
+ return 0;
+}
+
void __br_set_forward_delay(struct net_bridge *br, unsigned long t)
{
br->bridge_forward_delay = t;
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 4c97fc50fb70..8365bd53c421 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -102,8 +102,15 @@ static ssize_t ageing_time_show(struct device *d,
static int set_ageing_time(struct net_bridge *br, unsigned long val)
{
- br->ageing_time = clock_t_to_jiffies(val);
- return 0;
+ int ret;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ ret = br_set_ageing_time(br, val);
+ rtnl_unlock();
+
+ return ret;
}
static ssize_t ageing_time_store(struct device *d,
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 1a79e199ca3b..5f0d0cc4744f 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -54,9 +54,9 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
struct net_bridge_vlan_group *vg;
if (br_vlan_is_master(v))
- vg = v->br->vlgrp;
+ vg = br_vlan_group(v->br);
else
- vg = v->port->vlgrp;
+ vg = nbp_vlan_group(v->port);
if (flags & BRIDGE_VLAN_INFO_PVID)
__vlan_add_pvid(vg, v->vid);
@@ -72,38 +72,35 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags)
static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br,
u16 vid, u16 flags)
{
- const struct net_device_ops *ops = dev->netdev_ops;
+ struct switchdev_obj_port_vlan v = {
+ .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+ .flags = flags,
+ .vid_begin = vid,
+ .vid_end = vid,
+ };
int err;
- /* If driver uses VLAN ndo ops, use 8021q to install vid
- * on device, otherwise try switchdev ops to install vid.
+ /* Try switchdev op first. In case it is not supported, fallback to
+ * 8021q add.
*/
-
- if (ops->ndo_vlan_rx_add_vid) {
- err = vlan_vid_add(dev, br->vlan_proto, vid);
- } else {
- struct switchdev_obj_port_vlan v = {
- .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
- .flags = flags,
- .vid_begin = vid,
- .vid_end = vid,
- };
-
- err = switchdev_port_obj_add(dev, &v.obj);
- if (err == -EOPNOTSUPP)
- err = 0;
- }
-
+ err = switchdev_port_obj_add(dev, &v.obj);
+ if (err == -EOPNOTSUPP)
+ return vlan_vid_add(dev, br->vlan_proto, vid);
return err;
}
static void __vlan_add_list(struct net_bridge_vlan *v)
{
+ struct net_bridge_vlan_group *vg;
struct list_head *headp, *hpos;
struct net_bridge_vlan *vent;
- headp = br_vlan_is_master(v) ? &v->br->vlgrp->vlan_list :
- &v->port->vlgrp->vlan_list;
+ if (br_vlan_is_master(v))
+ vg = br_vlan_group(v->br);
+ else
+ vg = nbp_vlan_group(v->port);
+
+ headp = &vg->vlan_list;
list_for_each_prev(hpos, headp) {
vent = list_entry(hpos, struct net_bridge_vlan, vlist);
if (v->vid < vent->vid)
@@ -111,39 +108,72 @@ static void __vlan_add_list(struct net_bridge_vlan *v)
else
break;
}
- list_add(&v->vlist, hpos);
+ list_add_rcu(&v->vlist, hpos);
}
static void __vlan_del_list(struct net_bridge_vlan *v)
{
- list_del(&v->vlist);
+ list_del_rcu(&v->vlist);
}
static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br,
u16 vid)
{
- const struct net_device_ops *ops = dev->netdev_ops;
- int err = 0;
+ struct switchdev_obj_port_vlan v = {
+ .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+ .vid_begin = vid,
+ .vid_end = vid,
+ };
+ int err;
- /* If driver uses VLAN ndo ops, use 8021q to delete vid
- * on device, otherwise try switchdev ops to delete vid.
+ /* Try switchdev op first. In case it is not supported, fallback to
+ * 8021q del.
*/
-
- if (ops->ndo_vlan_rx_kill_vid) {
+ err = switchdev_port_obj_del(dev, &v.obj);
+ if (err == -EOPNOTSUPP) {
vlan_vid_del(dev, br->vlan_proto, vid);
- } else {
- struct switchdev_obj_port_vlan v = {
- .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
- .vid_begin = vid,
- .vid_end = vid,
- };
+ return 0;
+ }
+ return err;
+}
+
+/* Returns a master vlan, if it didn't exist it gets created. In all cases a
+ * a reference is taken to the master vlan before returning.
+ */
+static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid)
+{
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_vlan *masterv;
- err = switchdev_port_obj_del(dev, &v.obj);
- if (err == -EOPNOTSUPP)
- err = 0;
+ vg = br_vlan_group(br);
+ masterv = br_vlan_find(vg, vid);
+ if (!masterv) {
+ /* missing global ctx, create it now */
+ if (br_vlan_add(br, vid, 0))
+ return NULL;
+ masterv = br_vlan_find(vg, vid);
+ if (WARN_ON(!masterv))
+ return NULL;
}
+ atomic_inc(&masterv->refcnt);
- return err;
+ return masterv;
+}
+
+static void br_vlan_put_master(struct net_bridge_vlan *masterv)
+{
+ struct net_bridge_vlan_group *vg;
+
+ if (!br_vlan_is_master(masterv))
+ return;
+
+ vg = br_vlan_group(masterv->br);
+ if (atomic_dec_and_test(&masterv->refcnt)) {
+ rhashtable_remove_fast(&vg->vlan_hash,
+ &masterv->vnode, br_vlan_rht_params);
+ __vlan_del_list(masterv);
+ kfree_rcu(masterv, rcu);
+ }
}
/* This is the shared VLAN add function which works for both ports and bridge
@@ -161,7 +191,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
{
struct net_bridge_vlan *masterv = NULL;
struct net_bridge_port *p = NULL;
- struct rhashtable *tbl;
+ struct net_bridge_vlan_group *vg;
struct net_device *dev;
struct net_bridge *br;
int err;
@@ -169,17 +199,15 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
if (br_vlan_is_master(v)) {
br = v->br;
dev = br->dev;
- tbl = &br->vlgrp->vlan_hash;
+ vg = br_vlan_group(br);
} else {
p = v->port;
br = p->br;
dev = p->dev;
- tbl = &p->vlgrp->vlan_hash;
+ vg = nbp_vlan_group(p);
}
if (p) {
- u16 master_flags = flags;
-
/* Add VLAN to the device filter if it is supported.
* This ensures tagged traffic enters the bridge when
* promiscuous mode is disabled by br_manage_promisc().
@@ -190,57 +218,49 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
/* need to work on the master vlan too */
if (flags & BRIDGE_VLAN_INFO_MASTER) {
- master_flags |= BRIDGE_VLAN_INFO_BRENTRY;
- err = br_vlan_add(br, v->vid, master_flags);
+ err = br_vlan_add(br, v->vid, flags |
+ BRIDGE_VLAN_INFO_BRENTRY);
if (err)
goto out_filt;
}
- masterv = br_vlan_find(br->vlgrp, v->vid);
- if (!masterv) {
- /* missing global ctx, create it now */
- err = br_vlan_add(br, v->vid, 0);
- if (err)
- goto out_filt;
- masterv = br_vlan_find(br->vlgrp, v->vid);
- WARN_ON(!masterv);
- }
- atomic_inc(&masterv->refcnt);
+ masterv = br_vlan_get_master(br, v->vid);
+ if (!masterv)
+ goto out_filt;
v->brvlan = masterv;
}
- /* Add the dev mac only if it's a usable vlan */
+ /* Add the dev mac and count the vlan only if it's usable */
if (br_vlan_should_use(v)) {
err = br_fdb_insert(br, p, dev->dev_addr, v->vid);
if (err) {
br_err(br, "failed insert local address into bridge forwarding table\n");
goto out_filt;
}
+ vg->num_vlans++;
}
- err = rhashtable_lookup_insert_fast(tbl, &v->vnode, br_vlan_rht_params);
+ err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode,
+ br_vlan_rht_params);
if (err)
goto out_fdb_insert;
__vlan_add_list(v);
__vlan_add_flags(v, flags);
- if (br_vlan_is_master(v)) {
- if (br_vlan_is_brentry(v))
- br->vlgrp->num_vlans++;
- } else {
- p->vlgrp->num_vlans++;
- }
out:
return err;
out_fdb_insert:
- br_fdb_find_delete_local(br, p, br->dev->dev_addr, v->vid);
+ if (br_vlan_should_use(v)) {
+ br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid);
+ vg->num_vlans--;
+ }
out_filt:
if (p) {
__vlan_vid_del(dev, br, v->vid);
if (masterv) {
- atomic_dec(&masterv->refcnt);
+ br_vlan_put_master(masterv);
v->brvlan = NULL;
}
}
@@ -253,16 +273,13 @@ static int __vlan_del(struct net_bridge_vlan *v)
struct net_bridge_vlan *masterv = v;
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p = NULL;
- struct net_bridge *br;
int err = 0;
if (br_vlan_is_master(v)) {
- br = v->br;
- vg = v->br->vlgrp;
+ vg = br_vlan_group(v->br);
} else {
p = v->port;
- br = p->br;
- vg = v->port->vlgrp;
+ vg = nbp_vlan_group(v->port);
masterv = v->brvlan;
}
@@ -273,13 +290,9 @@ static int __vlan_del(struct net_bridge_vlan *v)
goto out;
}
- if (br_vlan_is_master(v)) {
- if (br_vlan_is_brentry(v)) {
- v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY;
- br->vlgrp->num_vlans--;
- }
- } else {
- p->vlgrp->num_vlans--;
+ if (br_vlan_should_use(v)) {
+ v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY;
+ vg->num_vlans--;
}
if (masterv != v) {
@@ -289,25 +302,25 @@ static int __vlan_del(struct net_bridge_vlan *v)
kfree_rcu(v, rcu);
}
- if (atomic_dec_and_test(&masterv->refcnt)) {
- rhashtable_remove_fast(&masterv->br->vlgrp->vlan_hash,
- &masterv->vnode, br_vlan_rht_params);
- __vlan_del_list(masterv);
- kfree_rcu(masterv, rcu);
- }
+ br_vlan_put_master(masterv);
out:
return err;
}
-static void __vlan_flush(struct net_bridge_vlan_group *vlgrp)
+static void __vlan_group_free(struct net_bridge_vlan_group *vg)
+{
+ WARN_ON(!list_empty(&vg->vlan_list));
+ rhashtable_destroy(&vg->vlan_hash);
+ kfree(vg);
+}
+
+static void __vlan_flush(struct net_bridge_vlan_group *vg)
{
struct net_bridge_vlan *vlan, *tmp;
- __vlan_delete_pvid(vlgrp, vlgrp->pvid);
- list_for_each_entry_safe(vlan, tmp, &vlgrp->vlan_list, vlist)
+ __vlan_delete_pvid(vg, vg->pvid);
+ list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
__vlan_del(vlan);
- rhashtable_destroy(&vlgrp->vlan_hash);
- kfree(vlgrp);
}
struct sk_buff *br_handle_vlan(struct net_bridge *br,
@@ -469,7 +482,7 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
if (!br->vlan_enabled)
return true;
- vg = p->vlgrp;
+ vg = nbp_vlan_group(p);
if (!vg || !vg->num_vlans)
return false;
@@ -495,12 +508,14 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
*/
int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
{
+ struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *vlan;
int ret;
ASSERT_RTNL();
- vlan = br_vlan_find(br->vlgrp, vid);
+ vg = br_vlan_group(br);
+ vlan = br_vlan_find(vg, vid);
if (vlan) {
if (!br_vlan_is_brentry(vlan)) {
/* Trying to change flags of non-existent bridge vlan */
@@ -515,7 +530,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
}
atomic_inc(&vlan->refcnt);
vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY;
- br->vlgrp->num_vlans++;
+ vg->num_vlans++;
}
__vlan_add_flags(vlan, flags);
return 0;
@@ -543,24 +558,33 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags)
*/
int br_vlan_delete(struct net_bridge *br, u16 vid)
{
+ struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
ASSERT_RTNL();
- v = br_vlan_find(br->vlgrp, vid);
+ vg = br_vlan_group(br);
+ v = br_vlan_find(vg, vid);
if (!v || !br_vlan_is_brentry(v))
return -ENOENT;
br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid);
+ br_fdb_delete_by_port(br, NULL, vid, 0);
return __vlan_del(v);
}
void br_vlan_flush(struct net_bridge *br)
{
+ struct net_bridge_vlan_group *vg;
+
ASSERT_RTNL();
- __vlan_flush(br_vlan_group(br));
+ vg = br_vlan_group(br);
+ __vlan_flush(vg);
+ RCU_INIT_POINTER(br->vlgrp, NULL);
+ synchronize_rcu();
+ __vlan_group_free(vg);
}
struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid)
@@ -627,6 +651,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
int err = 0;
struct net_bridge_port *p;
struct net_bridge_vlan *vlan;
+ struct net_bridge_vlan_group *vg;
__be16 oldproto;
if (br->vlan_proto == proto)
@@ -634,7 +659,8 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
/* Add VLANs for the new proto to the device filter. */
list_for_each_entry(p, &br->port_list, list) {
- list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) {
+ vg = nbp_vlan_group(p);
+ list_for_each_entry(vlan, &vg->vlan_list, vlist) {
err = vlan_vid_add(p->dev, proto, vlan->vid);
if (err)
goto err_filt;
@@ -648,19 +674,23 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
br_recalculate_fwd_mask(br);
/* Delete VLANs for the old proto from the device filter. */
- list_for_each_entry(p, &br->port_list, list)
- list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist)
+ list_for_each_entry(p, &br->port_list, list) {
+ vg = nbp_vlan_group(p);
+ list_for_each_entry(vlan, &vg->vlan_list, vlist)
vlan_vid_del(p->dev, oldproto, vlan->vid);
+ }
return 0;
err_filt:
- list_for_each_entry_continue_reverse(vlan, &p->vlgrp->vlan_list, vlist)
+ list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist)
vlan_vid_del(p->dev, proto, vlan->vid);
- list_for_each_entry_continue_reverse(p, &br->port_list, list)
- list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist)
+ list_for_each_entry_continue_reverse(p, &br->port_list, list) {
+ vg = nbp_vlan_group(p);
+ list_for_each_entry(vlan, &vg->vlan_list, vlist)
vlan_vid_del(p->dev, proto, vlan->vid);
+ }
return err;
}
@@ -704,25 +734,31 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br)
/* Disable default_pvid on all ports where it is still
* configured.
*/
- if (vlan_default_pvid(br->vlgrp, pvid))
+ if (vlan_default_pvid(br_vlan_group(br), pvid))
br_vlan_delete(br, pvid);
list_for_each_entry(p, &br->port_list, list) {
- if (vlan_default_pvid(p->vlgrp, pvid))
+ if (vlan_default_pvid(nbp_vlan_group(p), pvid))
nbp_vlan_delete(p, pvid);
}
br->default_pvid = 0;
}
-static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
+int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
{
const struct net_bridge_vlan *pvent;
+ struct net_bridge_vlan_group *vg;
struct net_bridge_port *p;
u16 old_pvid;
int err = 0;
unsigned long *changed;
+ if (!pvid) {
+ br_vlan_disable_default_pvid(br);
+ return 0;
+ }
+
changed = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long),
GFP_KERNEL);
if (!changed)
@@ -733,8 +769,9 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
/* Update default_pvid config only if we do not conflict with
* user configuration.
*/
- pvent = br_vlan_find(br->vlgrp, pvid);
- if ((!old_pvid || vlan_default_pvid(br->vlgrp, old_pvid)) &&
+ vg = br_vlan_group(br);
+ pvent = br_vlan_find(vg, pvid);
+ if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) &&
(!pvent || !br_vlan_should_use(pvent))) {
err = br_vlan_add(br, pvid,
BRIDGE_VLAN_INFO_PVID |
@@ -750,9 +787,10 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid)
/* Update default_pvid config only if we do not conflict with
* user configuration.
*/
+ vg = nbp_vlan_group(p);
if ((old_pvid &&
- !vlan_default_pvid(p->vlgrp, old_pvid)) ||
- br_vlan_find(p->vlgrp, pvid))
+ !vlan_default_pvid(vg, old_pvid)) ||
+ br_vlan_find(vg, pvid))
continue;
err = nbp_vlan_add(p, pvid,
@@ -813,12 +851,7 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val)
err = -EPERM;
goto unlock;
}
-
- if (!pvid)
- br_vlan_disable_default_pvid(br);
- else
- err = __br_vlan_set_default_pvid(br, pvid);
-
+ err = __br_vlan_set_default_pvid(br, pvid);
unlock:
rtnl_unlock();
return err;
@@ -826,17 +859,19 @@ unlock:
int br_vlan_init(struct net_bridge *br)
{
+ struct net_bridge_vlan_group *vg;
int ret = -ENOMEM;
- br->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL);
- if (!br->vlgrp)
+ vg = kzalloc(sizeof(*vg), GFP_KERNEL);
+ if (!vg)
goto out;
- ret = rhashtable_init(&br->vlgrp->vlan_hash, &br_vlan_rht_params);
+ ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params);
if (ret)
goto err_rhtbl;
- INIT_LIST_HEAD(&br->vlgrp->vlan_list);
+ INIT_LIST_HEAD(&vg->vlan_list);
br->vlan_proto = htons(ETH_P_8021Q);
br->default_pvid = 1;
+ rcu_assign_pointer(br->vlgrp, vg);
ret = br_vlan_add(br, 1,
BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
BRIDGE_VLAN_INFO_BRENTRY);
@@ -847,9 +882,9 @@ out:
return ret;
err_vlan_add:
- rhashtable_destroy(&br->vlgrp->vlan_hash);
+ rhashtable_destroy(&vg->vlan_hash);
err_rhtbl:
- kfree(br->vlgrp);
+ kfree(vg);
goto out;
}
@@ -867,9 +902,7 @@ int nbp_vlan_init(struct net_bridge_port *p)
if (ret)
goto err_rhtbl;
INIT_LIST_HEAD(&vg->vlan_list);
- /* Make sure everything's committed before publishing vg */
- smp_wmb();
- p->vlgrp = vg;
+ rcu_assign_pointer(p->vlgrp, vg);
if (p->br->default_pvid) {
ret = nbp_vlan_add(p, p->br->default_pvid,
BRIDGE_VLAN_INFO_PVID |
@@ -898,7 +931,7 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
ASSERT_RTNL();
- vlan = br_vlan_find(port->vlgrp, vid);
+ vlan = br_vlan_find(nbp_vlan_group(port), vid);
if (vlan) {
__vlan_add_flags(vlan, flags);
return 0;
@@ -926,7 +959,7 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid)
ASSERT_RTNL();
- v = br_vlan_find(port->vlgrp, vid);
+ v = br_vlan_find(nbp_vlan_group(port), vid);
if (!v)
return -ENOENT;
br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid);
@@ -937,12 +970,13 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid)
void nbp_vlan_flush(struct net_bridge_port *port)
{
- struct net_bridge_vlan *vlan;
+ struct net_bridge_vlan_group *vg;
ASSERT_RTNL();
- list_for_each_entry(vlan, &port->vlgrp->vlan_list, vlist)
- vlan_vid_del(port->dev, port->br->vlan_proto, vlan->vid);
-
- __vlan_flush(nbp_vlan_group(port));
+ vg = nbp_vlan_group(port);
+ __vlan_flush(vg);
+ RCU_INIT_POINTER(port->vlgrp, NULL);
+ synchronize_rcu();
+ __vlan_group_free(vg);
}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index a1ba6875c2a2..6863310d6973 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -96,7 +96,7 @@ struct bcm_op {
canid_t can_id;
u32 flags;
unsigned long frames_abs, frames_filtered;
- struct timeval ival1, ival2;
+ struct bcm_timeval ival1, ival2;
struct hrtimer timer, thrtimer;
struct tasklet_struct tsklet, thrtsklet;
ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
@@ -131,6 +131,11 @@ static inline struct bcm_sock *bcm_sk(const struct sock *sk)
return (struct bcm_sock *)sk;
}
+static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv)
+{
+ return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
+}
+
#define CFSIZ sizeof(struct can_frame)
#define OPSIZ sizeof(struct bcm_op)
#define MHSIZ sizeof(struct bcm_msg_head)
@@ -953,8 +958,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
op->count = msg_head->count;
op->ival1 = msg_head->ival1;
op->ival2 = msg_head->ival2;
- op->kt_ival1 = timeval_to_ktime(msg_head->ival1);
- op->kt_ival2 = timeval_to_ktime(msg_head->ival2);
+ op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
+ op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
/* disable an active timer due to zero values? */
if (!op->kt_ival1.tv64 && !op->kt_ival2.tv64)
@@ -1134,8 +1139,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
/* set timer value */
op->ival1 = msg_head->ival1;
op->ival2 = msg_head->ival2;
- op->kt_ival1 = timeval_to_ktime(msg_head->ival1);
- op->kt_ival2 = timeval_to_ktime(msg_head->ival2);
+ op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1);
+ op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2);
/* disable an active timer due to zero value? */
if (!op->kt_ival1.tv64)
diff --git a/net/core/dev.c b/net/core/dev.c
index 323c04edd779..1225b4be8ed6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2974,6 +2974,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
new_index = skb_tx_hash(dev, skb);
if (queue_index != new_index && sk &&
+ sk_fullsock(sk) &&
rcu_access_pointer(sk->sk_dst_cache))
sk_tx_queue_set(sk, new_index);
@@ -5345,6 +5346,12 @@ static int __netdev_upper_dev_link(struct net_device *dev,
changeupper_info.master = master;
changeupper_info.linking = true;
+ ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ &changeupper_info.info);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ return ret;
+
ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
master);
if (ret)
@@ -5487,6 +5494,9 @@ void netdev_upper_dev_unlink(struct net_device *dev,
changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev;
changeupper_info.linking = false;
+ call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
+ &changeupper_info.info);
+
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
/* Here is the tricky part. We must remove all dev's lower
diff --git a/net/core/dst.c b/net/core/dst.c
index 0771c8cb9307..2a1818065e12 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -144,12 +144,12 @@ loop:
mutex_unlock(&dst_gc_mutex);
}
-int dst_discard_sk(struct sock *sk, struct sk_buff *skb)
+int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
kfree_skb(skb);
return 0;
}
-EXPORT_SYMBOL(dst_discard_sk);
+EXPORT_SYMBOL(dst_discard_out);
const u32 dst_default_metrics[RTAX_MAX + 1] = {
/* This initializer is needed to force linker to place this variable
@@ -177,7 +177,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
dst->xfrm = NULL;
#endif
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
dst->error = 0;
dst->obsolete = initial_obsolete;
dst->header_len = 0;
@@ -224,7 +224,7 @@ static void ___dst_free(struct dst_entry *dst)
*/
if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) {
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
}
dst->obsolete = DST_OBSOLETE_DEAD;
}
@@ -352,7 +352,7 @@ static struct dst_ops md_dst_ops = {
.family = AF_UNSPEC,
};
-static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb)
+static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
WARN_ONCE(1, "Attempting to call output on metadata dst\n");
kfree_skb(skb);
@@ -375,7 +375,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
DST_METADATA | DST_NOCACHE | DST_NOCOUNT);
dst->input = dst_md_discard;
- dst->output = dst_md_discard_sk;
+ dst->output = dst_md_discard_out;
memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
}
@@ -430,7 +430,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
if (!unregister) {
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
} else {
dst->dev = dev_net(dst->dev)->loopback_dev;
dev_hold(dst->dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index 53a5036fb32d..0b00094932ab 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -56,10 +56,10 @@
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
*
- * Run the filter code and then cut skb->data to correct size returned by
- * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller
+ * Run the eBPF program and then cut skb->data to correct size returned by
+ * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
- * wrapper to SK_RUN_FILTER. It returns 0 if the packet should
+ * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
@@ -83,7 +83,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
- unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
+ unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
@@ -149,12 +149,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
return raw_smp_processor_id();
}
-/* note that this only generates 32-bit random numbers */
-static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
-{
- return prandom_u32();
-}
-
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
@@ -313,7 +307,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
- *insn = BPF_EMIT_CALL(__get_random_u32);
+ *insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
+ bpf_user_rnd_init_once();
break;
}
break;
@@ -1084,16 +1079,18 @@ EXPORT_SYMBOL_GPL(bpf_prog_create);
* @pfp: the unattached filter that is created
* @fprog: the filter program
* @trans: post-classic verifier transformation handler
+ * @save_orig: save classic BPF program
*
* This function effectively does the same as bpf_prog_create(), only
* that it builds up its insns buffer from user space provided buffer.
* It also allows for passing a bpf_aux_classic_check_t handler.
*/
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
- bpf_aux_classic_check_t trans)
+ bpf_aux_classic_check_t trans, bool save_orig)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
+ int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
@@ -1109,12 +1106,16 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
}
fp->len = fprog->len;
- /* Since unattached filters are not copied back to user
- * space through sk_get_filter(), we do not need to hold
- * a copy here, and can spare us the work.
- */
fp->orig_prog = NULL;
+ if (save_orig) {
+ err = bpf_prog_store_orig_filter(fp, fprog);
+ if (err) {
+ __bpf_prog_free(fp);
+ return -ENOMEM;
+ }
+ }
+
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
@@ -1456,6 +1457,7 @@ int skb_do_redirect(struct sk_buff *skb)
return dev_forward_skb(dev, skb);
skb->dev = dev;
+ skb_sender_cpu_clear(skb);
return dev_queue_xmit(skb);
}
@@ -1638,7 +1640,8 @@ sk_filter_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_trace_printk:
- return bpf_get_trace_printk_proto();
+ if (capable(CAP_SYS_ADMIN))
+ return bpf_get_trace_printk_proto();
default:
return NULL;
}
@@ -1734,7 +1737,8 @@ static bool tc_cls_act_is_valid_access(int off, int size,
static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
- struct bpf_insn *insn_buf)
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog)
{
struct bpf_insn *insn = insn_buf;
@@ -1825,6 +1829,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
offsetof(struct __sk_buff, cb[4]):
BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20);
+ prog->cb_access = 1;
ctx_off -= offsetof(struct __sk_buff, cb[0]);
ctx_off += offsetof(struct sk_buff, cb);
ctx_off += offsetof(struct qdisc_skb_cb, data);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index dfb1a9ca0835..299cfc24d888 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -180,7 +180,7 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
}
EXPORT_SYMBOL(lwtunnel_cmp_encap);
-int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
+int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
const struct lwtunnel_encap_ops *ops;
@@ -199,7 +199,7 @@ int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
if (likely(ops && ops->output))
- ret = ops->output(sk, skb);
+ ret = ops->output(net, sk, skb);
rcu_read_unlock();
if (ret == -EOPNOTSUPP)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8c57fdf4d68e..1aa8437ed6c4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2249,6 +2249,14 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx)
return false;
}
+static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx)
+{
+ if (filter_idx && dev->ifindex != filter_idx)
+ return true;
+
+ return false;
+}
+
static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
struct netlink_callback *cb)
{
@@ -2259,16 +2267,19 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
int rc, h, s_h = cb->args[1];
int idx, s_idx = idx = cb->args[2];
struct neigh_hash_table *nht;
- int filter_master_idx = 0;
+ int filter_master_idx = 0, filter_idx = 0;
unsigned int flags = NLM_F_MULTI;
int err;
err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL);
if (!err) {
+ if (tb[NDA_IFINDEX])
+ filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
+
if (tb[NDA_MASTER])
filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
- if (filter_master_idx)
+ if (filter_idx || filter_master_idx)
flags |= NLM_F_DUMP_FILTERED;
}
@@ -2283,6 +2294,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
n = rcu_dereference_bh(n->next)) {
if (!net_eq(dev_net(n->dev), net))
continue;
+ if (neigh_ifindex_filtered(n->dev, filter_idx))
+ continue;
if (neigh_master_filtered(n->dev, filter_master_idx))
continue;
if (idx < s_idx)
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 15c853806518..5d26056b6d8f 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -45,7 +45,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue)
queue->fastopenq.rskq_rst_head = NULL;
queue->fastopenq.rskq_rst_tail = NULL;
queue->fastopenq.qlen = 0;
- queue->fastopenq.max_qlen = 0;
queue->rskq_accept_head = NULL;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b2258a36d894..24775953fa68 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -96,7 +96,7 @@ int rtnl_is_locked(void)
EXPORT_SYMBOL(rtnl_is_locked);
#ifdef CONFIG_PROVE_LOCKING
-int lockdep_rtnl_is_held(void)
+bool lockdep_rtnl_is_held(void)
{
return lockdep_is_held(&rtnl_mutex);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 7dd1263e4c24..dcc7d62654d5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -988,6 +988,10 @@ set_rcvbuf:
sk->sk_max_pacing_rate);
break;
+ case SO_INCOMING_CPU:
+ sk->sk_incoming_cpu = val;
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1852,6 +1856,32 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
}
EXPORT_SYMBOL(sock_alloc_send_skb);
+int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
+ struct sockcm_cookie *sockc)
+{
+ struct cmsghdr *cmsg;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+ if (cmsg->cmsg_level != SOL_SOCKET)
+ continue;
+ switch (cmsg->cmsg_type) {
+ case SO_MARK:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ sockc->mark = *(u32 *)CMSG_DATA(cmsg);
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL(sock_cmsg_send);
+
/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER get_order(32768)
@@ -2353,6 +2383,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
+ sk->sk_incoming_cpu = -1;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 817622f3dbb7..0c1d58d43f67 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -1,3 +1,5 @@
+/* License: GPL */
+
#include <linux/mutex.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
@@ -323,14 +325,4 @@ static int __init sock_diag_init(void)
BUG_ON(!broadcast_wq);
return register_pernet_subsys(&diag_net_ops);
}
-
-static void __exit sock_diag_exit(void)
-{
- unregister_pernet_subsys(&diag_net_ops);
- destroy_workqueue(broadcast_wq);
-}
-
-module_init(sock_diag_init);
-module_exit(sock_diag_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG);
+device_initcall(sock_diag_init);
diff --git a/net/core/utils.c b/net/core/utils.c
index 3dffce953c39..3d17ca8b4744 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,52 +348,3 @@ void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
}
}
EXPORT_SYMBOL(inet_proto_csum_replace_by_diff);
-
-struct __net_random_once_work {
- struct work_struct work;
- struct static_key *key;
-};
-
-static void __net_random_once_deferred(struct work_struct *w)
-{
- struct __net_random_once_work *work =
- container_of(w, struct __net_random_once_work, work);
- BUG_ON(!static_key_enabled(work->key));
- static_key_slow_dec(work->key);
- kfree(work);
-}
-
-static void __net_random_once_disable_jump(struct static_key *key)
-{
- struct __net_random_once_work *w;
-
- w = kmalloc(sizeof(*w), GFP_ATOMIC);
- if (!w)
- return;
-
- INIT_WORK(&w->work, __net_random_once_deferred);
- w->key = key;
- schedule_work(&w->work);
-}
-
-bool __net_get_random_once(void *buf, int nbytes, bool *done,
- struct static_key *once_key)
-{
- static DEFINE_SPINLOCK(lock);
- unsigned long flags;
-
- spin_lock_irqsave(&lock, flags);
- if (*done) {
- spin_unlock_irqrestore(&lock, flags);
- return false;
- }
-
- get_random_bytes(buf, nbytes);
- *done = true;
- spin_unlock_irqrestore(&lock, flags);
-
- __net_random_once_disable_jump(once_key);
-
- return true;
-}
-EXPORT_SYMBOL(__net_get_random_once);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 5b21f6f88e97..4f6c1862dfd2 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -13,6 +13,7 @@
* You should have received a copy of the GNU General Public License along with
* this program; if not, see <http://www.gnu.org/licenses/>.
*
+ * Description: Data Center Bridging netlink interface
* Author: Lucy Liu <lucy.liu@intel.com>
*/
@@ -24,7 +25,7 @@
#include <linux/dcbnl.h>
#include <net/dcbevent.h>
#include <linux/rtnetlink.h>
-#include <linux/module.h>
+#include <linux/init.h>
#include <net/sock.h>
/* Data Center Bridging (DCB) is a collection of Ethernet enhancements
@@ -48,10 +49,6 @@
* features for capable devices.
*/
-MODULE_AUTHOR("Lucy Liu, <lucy.liu@intel.com>");
-MODULE_DESCRIPTION("Data Center Bridging netlink interface");
-MODULE_LICENSE("GPL");
-
/**************** DCB attribute policies *************************************/
/* DCB netlink attributes policy */
@@ -1935,19 +1932,6 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
}
EXPORT_SYMBOL(dcb_ieee_delapp);
-static void dcb_flushapp(void)
-{
- struct dcb_app_type *app;
- struct dcb_app_type *tmp;
-
- spin_lock_bh(&dcb_lock);
- list_for_each_entry_safe(app, tmp, &dcb_app_list, list) {
- list_del(&app->list);
- kfree(app);
- }
- spin_unlock_bh(&dcb_lock);
-}
-
static int __init dcbnl_init(void)
{
INIT_LIST_HEAD(&dcb_app_list);
@@ -1957,12 +1941,4 @@ static int __init dcbnl_init(void)
return 0;
}
-module_init(dcbnl_init);
-
-static void __exit dcbnl_exit(void)
-{
- rtnl_unregister(PF_UNSPEC, RTM_GETDCB);
- rtnl_unregister(PF_UNSPEC, RTM_SETDCB);
- dcb_flushapp();
-}
-module_exit(dcbnl_exit);
+device_initcall(dcbnl_init);
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index e1f823451565..923f5a180134 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -325,13 +325,13 @@ void dccp_send_close(struct sock *sk, const int active);
int dccp_invalid_packet(struct sk_buff *skb);
u32 dccp_sample_rtt(struct sock *sk, long delta);
-static inline int dccp_bad_service_code(const struct sock *sk,
+static inline bool dccp_bad_service_code(const struct sock *sk,
const __be32 service)
{
const struct dccp_sock *dp = dccp_sk(sk);
if (dp->dccps_service == service)
- return 0;
+ return false;
return !dccp_list_has_service(dp->dccps_service_list, service);
}
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8910c9567719..59bc180b02d8 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -208,7 +208,6 @@ void dccp_req_err(struct sock *sk, u64 seq)
if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
- reqsk_put(req);
} else {
/*
* Still in RESPOND, just remove it silently.
@@ -218,6 +217,7 @@ void dccp_req_err(struct sock *sk, u64 seq)
*/
inet_csk_reqsk_queue_drop(req->rsk_listener, req);
}
+ reqsk_put(req);
}
EXPORT_SYMBOL(dccp_req_err);
@@ -595,7 +595,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
goto drop;
- req = inet_reqsk_alloc(&dccp_request_sock_ops, sk);
+ req = inet_reqsk_alloc(&dccp_request_sock_ops, sk, true);
if (req == NULL)
goto drop;
@@ -799,15 +799,10 @@ static int dccp_v4_rcv(struct sk_buff *skb)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
}
- /* Step 2:
- * Look up flow ID in table and get corresponding socket */
+lookup:
sk = __inet_lookup_skb(&dccp_hashinfo, skb,
dh->dccph_sport, dh->dccph_dport);
- /*
- * Step 2:
- * If no socket ...
- */
- if (sk == NULL) {
+ if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
goto no_dccp_socket;
@@ -830,8 +825,12 @@ static int dccp_v4_rcv(struct sk_buff *skb)
struct sock *nsk = NULL;
sk = req->rsk_listener;
- if (sk->sk_state == DCCP_LISTEN)
+ if (likely(sk->sk_state == DCCP_LISTEN)) {
nsk = dccp_check_req(sk, skb, req);
+ } else {
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ goto lookup;
+ }
if (!nsk) {
reqsk_put(req);
goto discard_it;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 1361a3f45df7..d9cc731f2619 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -319,7 +319,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
goto drop;
- req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk);
+ req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk, true);
if (req == NULL)
goto drop;
@@ -656,16 +656,11 @@ static int dccp_v6_rcv(struct sk_buff *skb)
else
DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
- /* Step 2:
- * Look up flow ID in table and get corresponding socket */
+lookup:
sk = __inet6_lookup_skb(&dccp_hashinfo, skb,
dh->dccph_sport, dh->dccph_dport,
inet6_iif(skb));
- /*
- * Step 2:
- * If no socket ...
- */
- if (sk == NULL) {
+ if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
goto no_dccp_socket;
@@ -688,8 +683,12 @@ static int dccp_v6_rcv(struct sk_buff *skb)
struct sock *nsk = NULL;
sk = req->rsk_listener;
- if (sk->sk_state == DCCP_LISTEN)
+ if (likely(sk->sk_state == DCCP_LISTEN)) {
nsk = dccp_check_req(sk, skb, req);
+ } else {
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ goto lookup;
+ }
if (!nsk) {
reqsk_put(req);
goto discard_it;
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index 4b02dd300f50..849805e7af52 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -85,7 +85,7 @@ static void dn_nsp_send(struct sk_buff *skb)
if (dst) {
try_again:
skb_dst_set(skb, dst);
- dst_output(skb->sk, skb);
+ dst_output(&init_net, skb->sk, skb);
return;
}
@@ -582,7 +582,7 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg,
* associations.
*/
skb_dst_set(skb, dst_clone(dst));
- dst_output(skb->sk, skb);
+ dst_output(&init_net, skb->sk, skb);
}
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 0c491fc0e254..607a14f20d88 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -744,7 +744,7 @@ out:
return NET_RX_DROP;
}
-static int dn_output(struct sock *sk, struct sk_buff *skb)
+static int dn_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct dn_route *rt = (struct dn_route *)dst;
@@ -830,7 +830,7 @@ drop:
* Used to catch bugs. This should never normally get
* called.
*/
-static int dn_rt_bug_sk(struct sock *sk, struct sk_buff *skb)
+static int dn_rt_bug_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dn_skb_cb *cb = DN_SKB_CB(skb);
@@ -1467,7 +1467,7 @@ make_route:
rt->n = neigh;
rt->dst.lastuse = jiffies;
- rt->dst.output = dn_rt_bug_sk;
+ rt->dst.output = dn_rt_bug_out;
switch (res.type) {
case RTN_UNICAST:
rt->dst.input = dn_forward;
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index c59fa5d9c22c..aa398bcef9e3 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -326,8 +326,8 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
ret = dsa_slave_create(ds, parent, i, pd->port_names[i]);
if (ret < 0) {
- netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s)\n",
- index, i, pd->port_names[i]);
+ netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
+ index, i, pd->port_names[i], ret);
ret = 0;
}
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 5f65f929902e..b0b8da0f5af8 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -346,12 +346,15 @@ static int dsa_slave_port_fdb_add(struct net_device *dev,
{
struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_switch *ds = p->parent;
- int ret = -EOPNOTSUPP;
+ int ret;
+
+ if (!ds->drv->port_fdb_prepare || !ds->drv->port_fdb_add)
+ return -EOPNOTSUPP;
if (switchdev_trans_ph_prepare(trans))
- ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP;
+ ret = ds->drv->port_fdb_prepare(ds, p->port, fdb, trans);
else
- ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid);
+ ret = ds->drv->port_fdb_add(ds, p->port, fdb, trans);
return ret;
}
@@ -364,7 +367,7 @@ static int dsa_slave_port_fdb_del(struct net_device *dev,
int ret = -EOPNOTSUPP;
if (ds->drv->port_fdb_del)
- ret = ds->drv->port_fdb_del(ds, p->port, fdb->addr, fdb->vid);
+ ret = ds->drv->port_fdb_del(ds, p->port, fdb);
return ret;
}
@@ -390,7 +393,7 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev,
if (ret < 0)
break;
- fdb->addr = addr;
+ ether_addr_copy(fdb->addr, addr);
fdb->vid = vid;
fdb->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE;
@@ -450,7 +453,7 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state)
}
static int dsa_slave_port_attr_set(struct net_device *dev,
- struct switchdev_attr *attr,
+ const struct switchdev_attr *attr,
struct switchdev_trans *trans)
{
struct dsa_slave_priv *p = netdev_priv(dev);
@@ -1026,8 +1029,10 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
struct dsa_switch *ds = p->parent;
p->phy = ds->slave_mii_bus->phy_map[addr];
- if (!p->phy)
+ if (!p->phy) {
+ netdev_err(slave_dev, "no phy at %d\n", addr);
return -ENODEV;
+ }
/* Use already configured phy mode */
if (p->phy_interface == PHY_INTERFACE_MODE_NA)
@@ -1061,7 +1066,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
*/
ret = of_phy_register_fixed_link(port_dn);
if (ret) {
- netdev_err(slave_dev, "failed to register fixed PHY\n");
+ netdev_err(slave_dev, "failed to register fixed PHY: %d\n", ret);
return ret;
}
phy_is_fixed = true;
@@ -1072,17 +1077,20 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
phy_flags = ds->drv->get_phy_flags(ds, p->port);
if (phy_dn) {
- ret = of_mdio_parse_addr(&slave_dev->dev, phy_dn);
+ int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn);
+
/* If this PHY address is part of phys_mii_mask, which means
* that we need to divert reads and writes to/from it, then we
* want to bind this device using the slave MII bus created by
* DSA to make that happen.
*/
- if (!phy_is_fixed && ret >= 0 &&
- (ds->phys_mii_mask & (1 << ret))) {
- ret = dsa_slave_phy_connect(p, slave_dev, ret);
- if (ret)
+ if (!phy_is_fixed && phy_id >= 0 &&
+ (ds->phys_mii_mask & (1 << phy_id))) {
+ ret = dsa_slave_phy_connect(p, slave_dev, phy_id);
+ if (ret) {
+ netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret);
return ret;
+ }
} else {
p->phy = of_phy_connect(slave_dev, phy_dn,
dsa_slave_adjust_link,
@@ -1099,8 +1107,10 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
*/
if (!p->phy) {
ret = dsa_slave_phy_connect(p, slave_dev, p->port);
- if (ret)
+ if (ret) {
+ netdev_err(slave_dev, "failed to connect to port %d: %d\n", p->port, ret);
return ret;
+ }
} else {
netdev_info(slave_dev, "attached PHY at address %d [%s]\n",
p->phy->addr, p->phy->drv->name);
@@ -1212,6 +1222,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
ret = dsa_slave_phy_setup(p, slave_dev);
if (ret) {
+ netdev_err(master, "error %d setting up slave phy\n", ret);
free_netdev(slave_dev);
return ret;
}
@@ -1265,7 +1276,7 @@ int dsa_slave_netdevice_event(struct notifier_block *unused,
goto out;
err = dsa_slave_master_changed(dev);
- if (err)
+ if (err && err != -EOPNOTSUPP)
netdev_warn(dev, "failed to reflect master change\n");
break;
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 9f0cfa598e3a..20c49c724ba0 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -101,14 +101,9 @@ static const struct net_device_ops lowpan_netdev_ops = {
static void lowpan_setup(struct net_device *ldev)
{
- ldev->addr_len = IEEE802154_ADDR_LEN;
memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN);
- ldev->type = ARPHRD_6LOWPAN;
- /* Frame Control + Sequence Number + Address fields + Security Header */
- ldev->hard_header_len = 2 + 1 + 20 + 14;
- ldev->needed_tailroom = 2; /* FCS */
- ldev->mtu = IPV6_MIN_MTU;
- ldev->priv_flags |= IFF_NO_QUEUE;
+ /* We need an ipv6hdr as minimum len when calling xmit */
+ ldev->hard_header_len = sizeof(struct ipv6hdr);
ldev->flags = IFF_BROADCAST | IFF_MULTICAST;
ldev->netdev_ops = &lowpan_netdev_ops;
@@ -156,6 +151,15 @@ static int lowpan_newlink(struct net *src_net, struct net_device *ldev,
lowpan_dev_info(ldev)->wdev = wdev;
/* Set the lowpan hardware address to the wpan hardware address. */
memcpy(ldev->dev_addr, wdev->dev_addr, IEEE802154_ADDR_LEN);
+ /* We need headroom for possible wpan_dev_hard_header call and tailroom
+ * for encryption/fcs handling. The lowpan interface will replace
+ * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN
+ * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6
+ * header.
+ */
+ ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN +
+ wdev->needed_headroom;
+ ldev->needed_tailroom = wdev->needed_tailroom;
lowpan_netdev_setup(ldev, LOWPAN_LLTYPE_IEEE802154);
diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c
index b1fd47d2802b..65d55e05516c 100644
--- a/net/ieee802154/6lowpan/rx.c
+++ b/net/ieee802154/6lowpan/rx.c
@@ -29,6 +29,8 @@
static int lowpan_give_skb_to_device(struct sk_buff *skb)
{
skb->protocol = htons(ETH_P_IPV6);
+ skb->dev->stats.rx_packets++;
+ skb->dev->stats.rx_bytes += skb->len;
return netif_rx(skb);
}
diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index 54939d031ea5..62a21f6f021e 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -10,6 +10,7 @@
#include <net/6lowpan.h>
#include <net/ieee802154_netdev.h>
+#include <net/mac802154.h>
#include "6lowpan_i.h"
@@ -36,6 +37,13 @@ lowpan_addr_info *lowpan_skb_priv(const struct sk_buff *skb)
sizeof(struct lowpan_addr_info));
}
+/* This callback will be called from AF_PACKET and IPv6 stack, the AF_PACKET
+ * sockets gives an 8 byte array for addresses only!
+ *
+ * TODO I think AF_PACKET DGRAM (sending/receiving) RAW (sending) makes no
+ * sense here. We should disable it, the right use-case would be AF_INET6
+ * RAW/DGRAM sockets.
+ */
int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
unsigned short type, const void *_daddr,
const void *_saddr, unsigned int len)
@@ -71,27 +79,33 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
static struct sk_buff*
lowpan_alloc_frag(struct sk_buff *skb, int size,
- const struct ieee802154_hdr *master_hdr)
+ const struct ieee802154_hdr *master_hdr, bool frag1)
{
struct net_device *wdev = lowpan_dev_info(skb->dev)->wdev;
struct sk_buff *frag;
int rc;
- frag = alloc_skb(wdev->hard_header_len + wdev->needed_tailroom + size,
+ frag = alloc_skb(wdev->needed_headroom + wdev->needed_tailroom + size,
GFP_ATOMIC);
if (likely(frag)) {
frag->dev = wdev;
frag->priority = skb->priority;
- skb_reserve(frag, wdev->hard_header_len);
+ skb_reserve(frag, wdev->needed_headroom);
skb_reset_network_header(frag);
*mac_cb(frag) = *mac_cb(skb);
- rc = dev_hard_header(frag, wdev, 0, &master_hdr->dest,
- &master_hdr->source, size);
- if (rc < 0) {
- kfree_skb(frag);
- return ERR_PTR(rc);
+ if (frag1) {
+ memcpy(skb_put(frag, skb->mac_len),
+ skb_mac_header(skb), skb->mac_len);
+ } else {
+ rc = wpan_dev_hard_header(frag, wdev,
+ &master_hdr->dest,
+ &master_hdr->source, size);
+ if (rc < 0) {
+ kfree_skb(frag);
+ return ERR_PTR(rc);
+ }
}
} else {
frag = ERR_PTR(-ENOMEM);
@@ -103,13 +117,13 @@ lowpan_alloc_frag(struct sk_buff *skb, int size,
static int
lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr,
u8 *frag_hdr, int frag_hdrlen,
- int offset, int len)
+ int offset, int len, bool frag1)
{
struct sk_buff *frag;
raw_dump_inline(__func__, " fragment header", frag_hdr, frag_hdrlen);
- frag = lowpan_alloc_frag(skb, frag_hdrlen + len, wpan_hdr);
+ frag = lowpan_alloc_frag(skb, frag_hdrlen + len, wpan_hdr, frag1);
if (IS_ERR(frag))
return PTR_ERR(frag);
@@ -148,7 +162,8 @@ lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *ldev,
rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr,
LOWPAN_FRAG1_HEAD_SIZE, 0,
- frag_len + skb_network_header_len(skb));
+ frag_len + skb_network_header_len(skb),
+ true);
if (rc) {
pr_debug("%s unable to send FRAG1 packet (tag: %d)",
__func__, ntohs(frag_tag));
@@ -169,7 +184,7 @@ lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *ldev,
rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr,
LOWPAN_FRAGN_HEAD_SIZE, skb_offset,
- frag_len);
+ frag_len, false);
if (rc) {
pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n",
__func__, ntohs(frag_tag), skb_offset);
@@ -177,6 +192,8 @@ lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *ldev,
}
} while (skb_unprocessed > frag_cap);
+ ldev->stats.tx_packets++;
+ ldev->stats.tx_bytes += dgram_size;
consume_skb(skb);
return NET_XMIT_SUCCESS;
@@ -228,8 +245,8 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *ldev,
cb->ackreq = wpan_dev->ackreq;
}
- return dev_hard_header(skb, lowpan_dev_info(ldev)->wdev, ETH_P_IPV6,
- (void *)&da, (void *)&sa, 0);
+ return wpan_dev_hard_header(skb, lowpan_dev_info(ldev)->wdev, &da, &sa,
+ 0);
}
netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
@@ -240,6 +257,8 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
pr_debug("package xmit\n");
+ WARN_ON_ONCE(skb->len > IPV6_MIN_MTU);
+
/* We must take a copy of the skb before we modify/replace the ipv6
* header as the header could be used elsewhere
*/
@@ -262,6 +281,8 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
if (skb_tail_pointer(skb) - skb_network_header(skb) <= max_single) {
skb->dev = lowpan_dev_info(ldev)->wdev;
+ ldev->stats.tx_packets++;
+ ldev->stats.tx_bytes += dgram_size;
return dev_queue_xmit(skb);
} else {
netdev_tx_t rc;
diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig
index 1370d5b0041b..188135bcb803 100644
--- a/net/ieee802154/Kconfig
+++ b/net/ieee802154/Kconfig
@@ -12,6 +12,11 @@ menuconfig IEEE802154
if IEEE802154
+config IEEE802154_NL802154_EXPERIMENTAL
+ bool "IEEE 802.15.4 experimental netlink support"
+ ---help---
+ Adds experimental netlink support for nl802154.
+
config IEEE802154_SOCKET
tristate "IEEE 802.15.4 socket interface"
default y
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index b0248e934230..c35fdfa6d04e 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -95,6 +95,18 @@ cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx)
return result;
}
+struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx)
+{
+ struct cfg802154_registered_device *rdev;
+
+ ASSERT_RTNL();
+
+ rdev = cfg802154_rdev_by_wpan_phy_idx(wpan_phy_idx);
+ if (!rdev)
+ return NULL;
+ return &rdev->wpan_phy;
+}
+
struct wpan_phy *
wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size)
{
diff --git a/net/ieee802154/core.h b/net/ieee802154/core.h
index f3e95580caee..231fade959f3 100644
--- a/net/ieee802154/core.h
+++ b/net/ieee802154/core.h
@@ -42,5 +42,6 @@ extern int cfg802154_rdev_list_generation;
void cfg802154_dev_free(struct cfg802154_registered_device *rdev);
struct cfg802154_registered_device *
cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx);
+struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx);
#endif /* __IEEE802154_CORE_H */
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
index a051b6993177..c7439f0fbbdf 100644
--- a/net/ieee802154/header_ops.c
+++ b/net/ieee802154/header_ops.c
@@ -83,35 +83,35 @@ ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr)
}
int
-ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
+ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr)
{
- u8 buf[MAC802154_FRAME_HARD_HEADER_LEN];
+ u8 buf[IEEE802154_MAX_HEADER_LEN];
int pos = 2;
int rc;
- struct ieee802154_hdr_fc fc = hdr->fc;
+ struct ieee802154_hdr_fc *fc = &hdr->fc;
buf[pos++] = hdr->seq;
- fc.dest_addr_mode = hdr->dest.mode;
+ fc->dest_addr_mode = hdr->dest.mode;
rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false);
if (rc < 0)
return -EINVAL;
pos += rc;
- fc.source_addr_mode = hdr->source.mode;
+ fc->source_addr_mode = hdr->source.mode;
if (hdr->source.pan_id == hdr->dest.pan_id &&
hdr->dest.mode != IEEE802154_ADDR_NONE)
- fc.intra_pan = true;
+ fc->intra_pan = true;
- rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc.intra_pan);
+ rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc->intra_pan);
if (rc < 0)
return -EINVAL;
pos += rc;
- if (fc.security_enabled) {
- fc.version = 1;
+ if (fc->security_enabled) {
+ fc->version = 1;
rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec);
if (rc < 0)
@@ -120,7 +120,7 @@ ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
pos += rc;
}
- memcpy(buf, &fc, 2);
+ memcpy(buf, fc, 2);
memcpy(skb_push(skb, pos), buf, pos);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 3f89c0abdab1..16ef0d9f566e 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -232,8 +232,86 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
[NL802154_ATTR_SUPPORTED_COMMANDS] = { .type = NLA_NESTED },
[NL802154_ATTR_ACKREQ_DEFAULT] = { .type = NLA_U8 },
+
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+ [NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, },
+ [NL802154_ATTR_SEC_OUT_LEVEL] = { .type = NLA_U32, },
+ [NL802154_ATTR_SEC_OUT_KEY_ID] = { .type = NLA_NESTED, },
+ [NL802154_ATTR_SEC_FRAME_COUNTER] = { .type = NLA_U32 },
+
+ [NL802154_ATTR_SEC_LEVEL] = { .type = NLA_NESTED },
+ [NL802154_ATTR_SEC_DEVICE] = { .type = NLA_NESTED },
+ [NL802154_ATTR_SEC_DEVKEY] = { .type = NLA_NESTED },
+ [NL802154_ATTR_SEC_KEY] = { .type = NLA_NESTED },
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
};
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+static int
+nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct cfg802154_registered_device **rdev,
+ struct wpan_dev **wpan_dev)
+{
+ int err;
+
+ rtnl_lock();
+
+ if (!cb->args[0]) {
+ err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize,
+ nl802154_fam.attrbuf, nl802154_fam.maxattr,
+ nl802154_policy);
+ if (err)
+ goto out_unlock;
+
+ *wpan_dev = __cfg802154_wpan_dev_from_attrs(sock_net(skb->sk),
+ nl802154_fam.attrbuf);
+ if (IS_ERR(*wpan_dev)) {
+ err = PTR_ERR(*wpan_dev);
+ goto out_unlock;
+ }
+ *rdev = wpan_phy_to_rdev((*wpan_dev)->wpan_phy);
+ /* 0 is the first index - add 1 to parse only once */
+ cb->args[0] = (*rdev)->wpan_phy_idx + 1;
+ cb->args[1] = (*wpan_dev)->identifier;
+ } else {
+ /* subtract the 1 again here */
+ struct wpan_phy *wpan_phy = wpan_phy_idx_to_wpan_phy(cb->args[0] - 1);
+ struct wpan_dev *tmp;
+
+ if (!wpan_phy) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+ *rdev = wpan_phy_to_rdev(wpan_phy);
+ *wpan_dev = NULL;
+
+ list_for_each_entry(tmp, &(*rdev)->wpan_dev_list, list) {
+ if (tmp->identifier == cb->args[1]) {
+ *wpan_dev = tmp;
+ break;
+ }
+ }
+
+ if (!*wpan_dev) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+ }
+
+ return 0;
+ out_unlock:
+ rtnl_unlock();
+ return err;
+}
+
+static void
+nl802154_finish_wpan_dev_dump(struct cfg802154_registered_device *rdev)
+{
+ rtnl_unlock();
+}
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
+
/* message building helper */
static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
int flags, u8 cmd)
@@ -612,6 +690,107 @@ static inline u64 wpan_dev_id(struct wpan_dev *wpan_dev)
((u64)wpan_phy_to_rdev(wpan_dev->wpan_phy)->wpan_phy_idx << 32);
}
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+#include <net/ieee802154_netdev.h>
+
+static int
+ieee802154_llsec_send_key_id(struct sk_buff *msg,
+ const struct ieee802154_llsec_key_id *desc)
+{
+ struct nlattr *nl_dev_addr;
+
+ if (nla_put_u32(msg, NL802154_KEY_ID_ATTR_MODE, desc->mode))
+ return -ENOBUFS;
+
+ switch (desc->mode) {
+ case NL802154_KEY_ID_MODE_IMPLICIT:
+ nl_dev_addr = nla_nest_start(msg, NL802154_KEY_ID_ATTR_IMPLICIT);
+ if (!nl_dev_addr)
+ return -ENOBUFS;
+
+ if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_PAN_ID,
+ desc->device_addr.pan_id) ||
+ nla_put_u32(msg, NL802154_DEV_ADDR_ATTR_MODE,
+ desc->device_addr.mode))
+ return -ENOBUFS;
+
+ switch (desc->device_addr.mode) {
+ case NL802154_DEV_ADDR_SHORT:
+ if (nla_put_le16(msg, NL802154_DEV_ADDR_ATTR_SHORT,
+ desc->device_addr.short_addr))
+ return -ENOBUFS;
+ break;
+ case NL802154_DEV_ADDR_EXTENDED:
+ if (nla_put_le64(msg, NL802154_DEV_ADDR_ATTR_EXTENDED,
+ desc->device_addr.extended_addr))
+ return -ENOBUFS;
+ break;
+ default:
+ /* userspace should handle unknown */
+ break;
+ }
+
+ nla_nest_end(msg, nl_dev_addr);
+ break;
+ case NL802154_KEY_ID_MODE_INDEX:
+ break;
+ case NL802154_KEY_ID_MODE_INDEX_SHORT:
+ /* TODO renmae short_source? */
+ if (nla_put_le32(msg, NL802154_KEY_ID_ATTR_SOURCE_SHORT,
+ desc->short_source))
+ return -ENOBUFS;
+ break;
+ case NL802154_KEY_ID_MODE_INDEX_EXTENDED:
+ if (nla_put_le64(msg, NL802154_KEY_ID_ATTR_SOURCE_EXTENDED,
+ desc->extended_source))
+ return -ENOBUFS;
+ break;
+ default:
+ /* userspace should handle unknown */
+ break;
+ }
+
+ /* TODO key_id to key_idx ? Check naming */
+ if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) {
+ if (nla_put_u8(msg, NL802154_KEY_ID_ATTR_INDEX, desc->id))
+ return -ENOBUFS;
+ }
+
+ return 0;
+}
+
+static int nl802154_get_llsec_params(struct sk_buff *msg,
+ struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev)
+{
+ struct nlattr *nl_key_id;
+ struct ieee802154_llsec_params params;
+ int ret;
+
+ ret = rdev_get_llsec_params(rdev, wpan_dev, &params);
+ if (ret < 0)
+ return ret;
+
+ if (nla_put_u8(msg, NL802154_ATTR_SEC_ENABLED, params.enabled) ||
+ nla_put_u32(msg, NL802154_ATTR_SEC_OUT_LEVEL, params.out_level) ||
+ nla_put_be32(msg, NL802154_ATTR_SEC_FRAME_COUNTER,
+ params.frame_counter))
+ return -ENOBUFS;
+
+ nl_key_id = nla_nest_start(msg, NL802154_ATTR_SEC_OUT_KEY_ID);
+ if (!nl_key_id)
+ return -ENOBUFS;
+
+ ret = ieee802154_llsec_send_key_id(msg, &params.out_key);
+ if (ret < 0)
+ return ret;
+
+ nla_nest_end(msg, nl_key_id);
+
+ return 0;
+}
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
+
static int
nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
struct cfg802154_registered_device *rdev,
@@ -663,6 +842,11 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
if (nla_put_u8(msg, NL802154_ATTR_ACKREQ_DEFAULT, wpan_dev->ackreq))
goto nla_put_failure;
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+ if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0)
+ goto nla_put_failure;
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
+
genlmsg_end(msg, hdr);
return 0;
@@ -753,10 +937,8 @@ static int nl802154_new_interface(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
- /* TODO add nla_get_le64 to netlink */
if (info->attrs[NL802154_ATTR_EXTENDED_ADDR])
- extended_addr = (__force __le64)nla_get_u64(
- info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+ extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
if (!rdev->ops->add_virtual_intf)
return -EOPNOTSUPP;
@@ -1075,6 +1257,838 @@ nl802154_set_ackreq_default(struct sk_buff *skb, struct genl_info *info)
return rdev_set_ackreq_default(rdev, wpan_dev, ackreq);
}
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = {
+ [NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 },
+ [NL802154_DEV_ADDR_ATTR_MODE] = { .type = NLA_U32 },
+ [NL802154_DEV_ADDR_ATTR_SHORT] = { .type = NLA_U16 },
+ [NL802154_DEV_ADDR_ATTR_EXTENDED] = { .type = NLA_U64 },
+};
+
+static int
+ieee802154_llsec_parse_dev_addr(struct nlattr *nla,
+ struct ieee802154_addr *addr)
+{
+ struct nlattr *attrs[NL802154_DEV_ADDR_ATTR_MAX + 1];
+
+ if (!nla || nla_parse_nested(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla,
+ nl802154_dev_addr_policy))
+ return -EINVAL;
+
+ if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] &&
+ !attrs[NL802154_DEV_ADDR_ATTR_MODE] &&
+ !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] ||
+ attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]))
+ return -EINVAL;
+
+ addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]);
+ addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]);
+ switch (addr->mode) {
+ case NL802154_DEV_ADDR_SHORT:
+ addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]);
+ break;
+ case NL802154_DEV_ADDR_EXTENDED:
+ addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static const struct nla_policy nl802154_key_id_policy[NL802154_KEY_ID_ATTR_MAX + 1] = {
+ [NL802154_KEY_ID_ATTR_MODE] = { .type = NLA_U32 },
+ [NL802154_KEY_ID_ATTR_INDEX] = { .type = NLA_U8 },
+ [NL802154_KEY_ID_ATTR_IMPLICIT] = { .type = NLA_NESTED },
+ [NL802154_KEY_ID_ATTR_SOURCE_SHORT] = { .type = NLA_U32 },
+ [NL802154_KEY_ID_ATTR_SOURCE_EXTENDED] = { .type = NLA_U64 },
+};
+
+static int
+ieee802154_llsec_parse_key_id(struct nlattr *nla,
+ struct ieee802154_llsec_key_id *desc)
+{
+ struct nlattr *attrs[NL802154_KEY_ID_ATTR_MAX + 1];
+
+ if (!nla || nla_parse_nested(attrs, NL802154_KEY_ID_ATTR_MAX, nla,
+ nl802154_key_id_policy))
+ return -EINVAL;
+
+ if (!attrs[NL802154_KEY_ID_ATTR_MODE])
+ return -EINVAL;
+
+ desc->mode = nla_get_u32(attrs[NL802154_KEY_ID_ATTR_MODE]);
+ switch (desc->mode) {
+ case NL802154_KEY_ID_MODE_IMPLICIT:
+ if (!attrs[NL802154_KEY_ID_ATTR_IMPLICIT])
+ return -EINVAL;
+
+ if (ieee802154_llsec_parse_dev_addr(attrs[NL802154_KEY_ID_ATTR_IMPLICIT],
+ &desc->device_addr) < 0)
+ return -EINVAL;
+ break;
+ case NL802154_KEY_ID_MODE_INDEX:
+ break;
+ case NL802154_KEY_ID_MODE_INDEX_SHORT:
+ if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT])
+ return -EINVAL;
+
+ desc->short_source = nla_get_le32(attrs[NL802154_KEY_ID_ATTR_SOURCE_SHORT]);
+ break;
+ case NL802154_KEY_ID_MODE_INDEX_EXTENDED:
+ if (!attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED])
+ return -EINVAL;
+
+ desc->extended_source = nla_get_le64(attrs[NL802154_KEY_ID_ATTR_SOURCE_EXTENDED]);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (desc->mode != NL802154_KEY_ID_MODE_IMPLICIT) {
+ if (!attrs[NL802154_KEY_ID_ATTR_INDEX])
+ return -EINVAL;
+
+ /* TODO change id to idx */
+ desc->id = nla_get_u8(attrs[NL802154_KEY_ID_ATTR_INDEX]);
+ }
+
+ return 0;
+}
+
+static int nl802154_set_llsec_params(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct ieee802154_llsec_params params;
+ u32 changed = 0;
+ int ret;
+
+ if (info->attrs[NL802154_ATTR_SEC_ENABLED]) {
+ u8 enabled;
+
+ enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]);
+ if (enabled != 0 && enabled != 1)
+ return -EINVAL;
+
+ params.enabled = nla_get_u8(info->attrs[NL802154_ATTR_SEC_ENABLED]);
+ changed |= IEEE802154_LLSEC_PARAM_ENABLED;
+ }
+
+ if (info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID]) {
+ ret = ieee802154_llsec_parse_key_id(info->attrs[NL802154_ATTR_SEC_OUT_KEY_ID],
+ &params.out_key);
+ if (ret < 0)
+ return ret;
+
+ changed |= IEEE802154_LLSEC_PARAM_OUT_KEY;
+ }
+
+ if (info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]) {
+ params.out_level = nla_get_u32(info->attrs[NL802154_ATTR_SEC_OUT_LEVEL]);
+ if (params.out_level > NL802154_SECLEVEL_MAX)
+ return -EINVAL;
+
+ changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL;
+ }
+
+ if (info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]) {
+ params.frame_counter = nla_get_be32(info->attrs[NL802154_ATTR_SEC_FRAME_COUNTER]);
+ changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER;
+ }
+
+ return rdev_set_llsec_params(rdev, wpan_dev, &params, changed);
+}
+
+static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid,
+ u32 seq, int flags,
+ struct cfg802154_registered_device *rdev,
+ struct net_device *dev,
+ const struct ieee802154_llsec_key_entry *key)
+{
+ void *hdr;
+ u32 commands[NL802154_CMD_FRAME_NR_IDS / 32];
+ struct nlattr *nl_key, *nl_key_id;
+
+ hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
+ if (!hdr)
+ return -1;
+
+ if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
+ goto nla_put_failure;
+
+ nl_key = nla_nest_start(msg, NL802154_ATTR_SEC_KEY);
+ if (!nl_key)
+ goto nla_put_failure;
+
+ nl_key_id = nla_nest_start(msg, NL802154_KEY_ATTR_ID);
+ if (!nl_key_id)
+ goto nla_put_failure;
+
+ if (ieee802154_llsec_send_key_id(msg, &key->id) < 0)
+ goto nla_put_failure;
+
+ nla_nest_end(msg, nl_key_id);
+
+ if (nla_put_u8(msg, NL802154_KEY_ATTR_USAGE_FRAMES,
+ key->key->frame_types))
+ goto nla_put_failure;
+
+ if (key->key->frame_types & BIT(NL802154_FRAME_CMD)) {
+ /* TODO for each nested */
+ memset(commands, 0, sizeof(commands));
+ commands[7] = key->key->cmd_frame_ids;
+ if (nla_put(msg, NL802154_KEY_ATTR_USAGE_CMDS,
+ sizeof(commands), commands))
+ goto nla_put_failure;
+ }
+
+ if (nla_put(msg, NL802154_KEY_ATTR_BYTES, NL802154_KEY_SIZE,
+ key->key->key))
+ goto nla_put_failure;
+
+ nla_nest_end(msg, nl_key);
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int
+nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct cfg802154_registered_device *rdev = NULL;
+ struct ieee802154_llsec_key_entry *key;
+ struct ieee802154_llsec_table *table;
+ struct wpan_dev *wpan_dev;
+ int err;
+
+ err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev);
+ if (err)
+ return err;
+
+ if (!wpan_dev->netdev) {
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ rdev_lock_llsec_table(rdev, wpan_dev);
+ rdev_get_llsec_table(rdev, wpan_dev, &table);
+
+ /* TODO make it like station dump */
+ if (cb->args[2])
+ goto out;
+
+ list_for_each_entry(key, &table->keys, list) {
+ if (nl802154_send_key(skb, NL802154_CMD_NEW_SEC_KEY,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ rdev, wpan_dev->netdev, key) < 0) {
+ /* TODO */
+ err = -EIO;
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ goto out_err;
+ }
+ }
+
+ cb->args[2] = 1;
+
+out:
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ err = skb->len;
+out_err:
+ nl802154_finish_wpan_dev_dump(rdev);
+
+ return err;
+}
+
+static const struct nla_policy nl802154_key_policy[NL802154_KEY_ATTR_MAX + 1] = {
+ [NL802154_KEY_ATTR_ID] = { NLA_NESTED },
+ /* TODO handle it as for_each_nested and NLA_FLAG? */
+ [NL802154_KEY_ATTR_USAGE_FRAMES] = { NLA_U8 },
+ /* TODO handle it as for_each_nested, not static array? */
+ [NL802154_KEY_ATTR_USAGE_CMDS] = { .len = NL802154_CMD_FRAME_NR_IDS / 8 },
+ [NL802154_KEY_ATTR_BYTES] = { .len = NL802154_KEY_SIZE },
+};
+
+static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1];
+ struct ieee802154_llsec_key key = { };
+ struct ieee802154_llsec_key_id id = { };
+ u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { };
+
+ if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX,
+ info->attrs[NL802154_ATTR_SEC_KEY],
+ nl802154_key_policy))
+ return -EINVAL;
+
+ if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] ||
+ !attrs[NL802154_KEY_ATTR_BYTES])
+ return -EINVAL;
+
+ if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)
+ return -ENOBUFS;
+
+ key.frame_types = nla_get_u8(attrs[NL802154_KEY_ATTR_USAGE_FRAMES]);
+ if (key.frame_types > BIT(NL802154_FRAME_MAX) ||
+ ((key.frame_types & BIT(NL802154_FRAME_CMD)) &&
+ !attrs[NL802154_KEY_ATTR_USAGE_CMDS]))
+ return -EINVAL;
+
+ if (attrs[NL802154_KEY_ATTR_USAGE_CMDS]) {
+ /* TODO for each nested */
+ nla_memcpy(commands, attrs[NL802154_KEY_ATTR_USAGE_CMDS],
+ NL802154_CMD_FRAME_NR_IDS / 8);
+
+ /* TODO understand the -EINVAL logic here? last condition */
+ if (commands[0] || commands[1] || commands[2] || commands[3] ||
+ commands[4] || commands[5] || commands[6] ||
+ commands[7] > BIT(NL802154_CMD_FRAME_MAX))
+ return -EINVAL;
+
+ key.cmd_frame_ids = commands[7];
+ } else {
+ key.cmd_frame_ids = 0;
+ }
+
+ nla_memcpy(key.key, attrs[NL802154_KEY_ATTR_BYTES], NL802154_KEY_SIZE);
+
+ if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)
+ return -ENOBUFS;
+
+ return rdev_add_llsec_key(rdev, wpan_dev, &id, &key);
+}
+
+static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1];
+ struct ieee802154_llsec_key_id id;
+
+ if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX,
+ info->attrs[NL802154_ATTR_SEC_KEY],
+ nl802154_key_policy))
+ return -EINVAL;
+
+ if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)
+ return -ENOBUFS;
+
+ return rdev_del_llsec_key(rdev, wpan_dev, &id);
+}
+
+static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid,
+ u32 seq, int flags,
+ struct cfg802154_registered_device *rdev,
+ struct net_device *dev,
+ const struct ieee802154_llsec_device *dev_desc)
+{
+ void *hdr;
+ struct nlattr *nl_device;
+
+ hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
+ if (!hdr)
+ return -1;
+
+ if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
+ goto nla_put_failure;
+
+ nl_device = nla_nest_start(msg, NL802154_ATTR_SEC_DEVICE);
+ if (!nl_device)
+ goto nla_put_failure;
+
+ if (nla_put_u32(msg, NL802154_DEV_ATTR_FRAME_COUNTER,
+ dev_desc->frame_counter) ||
+ nla_put_le16(msg, NL802154_DEV_ATTR_PAN_ID, dev_desc->pan_id) ||
+ nla_put_le16(msg, NL802154_DEV_ATTR_SHORT_ADDR,
+ dev_desc->short_addr) ||
+ nla_put_le64(msg, NL802154_DEV_ATTR_EXTENDED_ADDR,
+ dev_desc->hwaddr) ||
+ nla_put_u8(msg, NL802154_DEV_ATTR_SECLEVEL_EXEMPT,
+ dev_desc->seclevel_exempt) ||
+ nla_put_u32(msg, NL802154_DEV_ATTR_KEY_MODE, dev_desc->key_mode))
+ goto nla_put_failure;
+
+ nla_nest_end(msg, nl_device);
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int
+nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct cfg802154_registered_device *rdev = NULL;
+ struct ieee802154_llsec_device *dev;
+ struct ieee802154_llsec_table *table;
+ struct wpan_dev *wpan_dev;
+ int err;
+
+ err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev);
+ if (err)
+ return err;
+
+ if (!wpan_dev->netdev) {
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ rdev_lock_llsec_table(rdev, wpan_dev);
+ rdev_get_llsec_table(rdev, wpan_dev, &table);
+
+ /* TODO make it like station dump */
+ if (cb->args[2])
+ goto out;
+
+ list_for_each_entry(dev, &table->devices, list) {
+ if (nl802154_send_device(skb, NL802154_CMD_NEW_SEC_LEVEL,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ rdev, wpan_dev->netdev, dev) < 0) {
+ /* TODO */
+ err = -EIO;
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ goto out_err;
+ }
+ }
+
+ cb->args[2] = 1;
+
+out:
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ err = skb->len;
+out_err:
+ nl802154_finish_wpan_dev_dump(rdev);
+
+ return err;
+}
+
+static const struct nla_policy nl802154_dev_policy[NL802154_DEV_ATTR_MAX + 1] = {
+ [NL802154_DEV_ATTR_FRAME_COUNTER] = { NLA_U32 },
+ [NL802154_DEV_ATTR_PAN_ID] = { .type = NLA_U16 },
+ [NL802154_DEV_ATTR_SHORT_ADDR] = { .type = NLA_U16 },
+ [NL802154_DEV_ATTR_EXTENDED_ADDR] = { .type = NLA_U64 },
+ [NL802154_DEV_ATTR_SECLEVEL_EXEMPT] = { NLA_U8 },
+ [NL802154_DEV_ATTR_KEY_MODE] = { NLA_U32 },
+};
+
+static int
+ieee802154_llsec_parse_device(struct nlattr *nla,
+ struct ieee802154_llsec_device *dev)
+{
+ struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
+
+ if (!nla || nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX, nla,
+ nl802154_dev_policy))
+ return -EINVAL;
+
+ memset(dev, 0, sizeof(*dev));
+
+ if (!attrs[NL802154_DEV_ATTR_FRAME_COUNTER] ||
+ !attrs[NL802154_DEV_ATTR_PAN_ID] ||
+ !attrs[NL802154_DEV_ATTR_SHORT_ADDR] ||
+ !attrs[NL802154_DEV_ATTR_EXTENDED_ADDR] ||
+ !attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT] ||
+ !attrs[NL802154_DEV_ATTR_KEY_MODE])
+ return -EINVAL;
+
+ /* TODO be32 */
+ dev->frame_counter = nla_get_u32(attrs[NL802154_DEV_ATTR_FRAME_COUNTER]);
+ dev->pan_id = nla_get_le16(attrs[NL802154_DEV_ATTR_PAN_ID]);
+ dev->short_addr = nla_get_le16(attrs[NL802154_DEV_ATTR_SHORT_ADDR]);
+ /* TODO rename hwaddr to extended_addr */
+ dev->hwaddr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]);
+ dev->seclevel_exempt = nla_get_u8(attrs[NL802154_DEV_ATTR_SECLEVEL_EXEMPT]);
+ dev->key_mode = nla_get_u32(attrs[NL802154_DEV_ATTR_KEY_MODE]);
+
+ if (dev->key_mode > NL802154_DEVKEY_MAX ||
+ (dev->seclevel_exempt != 0 && dev->seclevel_exempt != 1))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct ieee802154_llsec_device dev_desc;
+
+ if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE],
+ &dev_desc) < 0)
+ return -EINVAL;
+
+ return rdev_add_device(rdev, wpan_dev, &dev_desc);
+}
+
+static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
+ __le64 extended_addr;
+
+ if (nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX,
+ info->attrs[NL802154_ATTR_SEC_DEVICE],
+ nl802154_dev_policy))
+ return -EINVAL;
+
+ if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR])
+ return -EINVAL;
+
+ extended_addr = nla_get_le64(attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]);
+ return rdev_del_device(rdev, wpan_dev, extended_addr);
+}
+
+static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid,
+ u32 seq, int flags,
+ struct cfg802154_registered_device *rdev,
+ struct net_device *dev, __le64 extended_addr,
+ const struct ieee802154_llsec_device_key *devkey)
+{
+ void *hdr;
+ struct nlattr *nl_devkey, *nl_key_id;
+
+ hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
+ if (!hdr)
+ return -1;
+
+ if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
+ goto nla_put_failure;
+
+ nl_devkey = nla_nest_start(msg, NL802154_ATTR_SEC_DEVKEY);
+ if (!nl_devkey)
+ goto nla_put_failure;
+
+ if (nla_put_le64(msg, NL802154_DEVKEY_ATTR_EXTENDED_ADDR,
+ extended_addr) ||
+ nla_put_u32(msg, NL802154_DEVKEY_ATTR_FRAME_COUNTER,
+ devkey->frame_counter))
+ goto nla_put_failure;
+
+ nl_key_id = nla_nest_start(msg, NL802154_DEVKEY_ATTR_ID);
+ if (!nl_key_id)
+ goto nla_put_failure;
+
+ if (ieee802154_llsec_send_key_id(msg, &devkey->key_id) < 0)
+ goto nla_put_failure;
+
+ nla_nest_end(msg, nl_key_id);
+ nla_nest_end(msg, nl_devkey);
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int
+nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct cfg802154_registered_device *rdev = NULL;
+ struct ieee802154_llsec_device_key *kpos;
+ struct ieee802154_llsec_device *dpos;
+ struct ieee802154_llsec_table *table;
+ struct wpan_dev *wpan_dev;
+ int err;
+
+ err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev);
+ if (err)
+ return err;
+
+ if (!wpan_dev->netdev) {
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ rdev_lock_llsec_table(rdev, wpan_dev);
+ rdev_get_llsec_table(rdev, wpan_dev, &table);
+
+ /* TODO make it like station dump */
+ if (cb->args[2])
+ goto out;
+
+ /* TODO look if remove devkey and do some nested attribute */
+ list_for_each_entry(dpos, &table->devices, list) {
+ list_for_each_entry(kpos, &dpos->keys, list) {
+ if (nl802154_send_devkey(skb,
+ NL802154_CMD_NEW_SEC_LEVEL,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI, rdev,
+ wpan_dev->netdev,
+ dpos->hwaddr,
+ kpos) < 0) {
+ /* TODO */
+ err = -EIO;
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ goto out_err;
+ }
+ }
+ }
+
+ cb->args[2] = 1;
+
+out:
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ err = skb->len;
+out_err:
+ nl802154_finish_wpan_dev_dump(rdev);
+
+ return err;
+}
+
+static const struct nla_policy nl802154_devkey_policy[NL802154_DEVKEY_ATTR_MAX + 1] = {
+ [NL802154_DEVKEY_ATTR_FRAME_COUNTER] = { NLA_U32 },
+ [NL802154_DEVKEY_ATTR_EXTENDED_ADDR] = { NLA_U64 },
+ [NL802154_DEVKEY_ATTR_ID] = { NLA_NESTED },
+};
+
+static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1];
+ struct ieee802154_llsec_device_key key;
+ __le64 extended_addr;
+
+ if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
+ nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX,
+ info->attrs[NL802154_ATTR_SEC_DEVKEY],
+ nl802154_devkey_policy) < 0)
+ return -EINVAL;
+
+ if (!attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER] ||
+ !attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR])
+ return -EINVAL;
+
+ /* TODO change key.id ? */
+ if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID],
+ &key.key_id) < 0)
+ return -ENOBUFS;
+
+ /* TODO be32 */
+ key.frame_counter = nla_get_u32(attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER]);
+ /* TODO change naming hwaddr -> extended_addr
+ * check unique identifier short+pan OR extended_addr
+ */
+ extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]);
+ return rdev_add_devkey(rdev, wpan_dev, extended_addr, &key);
+}
+
+static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct nlattr *attrs[NL802154_DEVKEY_ATTR_MAX + 1];
+ struct ieee802154_llsec_device_key key;
+ __le64 extended_addr;
+
+ if (nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX,
+ info->attrs[NL802154_ATTR_SEC_DEVKEY],
+ nl802154_devkey_policy))
+ return -EINVAL;
+
+ if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR])
+ return -EINVAL;
+
+ /* TODO change key.id ? */
+ if (ieee802154_llsec_parse_key_id(attrs[NL802154_DEVKEY_ATTR_ID],
+ &key.key_id) < 0)
+ return -ENOBUFS;
+
+ /* TODO change naming hwaddr -> extended_addr
+ * check unique identifier short+pan OR extended_addr
+ */
+ extended_addr = nla_get_le64(attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]);
+ return rdev_del_devkey(rdev, wpan_dev, extended_addr, &key);
+}
+
+static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid,
+ u32 seq, int flags,
+ struct cfg802154_registered_device *rdev,
+ struct net_device *dev,
+ const struct ieee802154_llsec_seclevel *sl)
+{
+ void *hdr;
+ struct nlattr *nl_seclevel;
+
+ hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
+ if (!hdr)
+ return -1;
+
+ if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
+ goto nla_put_failure;
+
+ nl_seclevel = nla_nest_start(msg, NL802154_ATTR_SEC_LEVEL);
+ if (!nl_seclevel)
+ goto nla_put_failure;
+
+ if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_FRAME, sl->frame_type) ||
+ nla_put_u32(msg, NL802154_SECLEVEL_ATTR_LEVELS, sl->sec_levels) ||
+ nla_put_u8(msg, NL802154_SECLEVEL_ATTR_DEV_OVERRIDE,
+ sl->device_override))
+ goto nla_put_failure;
+
+ if (sl->frame_type == NL802154_FRAME_CMD) {
+ if (nla_put_u32(msg, NL802154_SECLEVEL_ATTR_CMD_FRAME,
+ sl->cmd_frame_id))
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(msg, nl_seclevel);
+ genlmsg_end(msg, hdr);
+
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static int
+nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct cfg802154_registered_device *rdev = NULL;
+ struct ieee802154_llsec_seclevel *sl;
+ struct ieee802154_llsec_table *table;
+ struct wpan_dev *wpan_dev;
+ int err;
+
+ err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev);
+ if (err)
+ return err;
+
+ if (!wpan_dev->netdev) {
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ rdev_lock_llsec_table(rdev, wpan_dev);
+ rdev_get_llsec_table(rdev, wpan_dev, &table);
+
+ /* TODO make it like station dump */
+ if (cb->args[2])
+ goto out;
+
+ list_for_each_entry(sl, &table->security_levels, list) {
+ if (nl802154_send_seclevel(skb, NL802154_CMD_NEW_SEC_LEVEL,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ rdev, wpan_dev->netdev, sl) < 0) {
+ /* TODO */
+ err = -EIO;
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ goto out_err;
+ }
+ }
+
+ cb->args[2] = 1;
+
+out:
+ rdev_unlock_llsec_table(rdev, wpan_dev);
+ err = skb->len;
+out_err:
+ nl802154_finish_wpan_dev_dump(rdev);
+
+ return err;
+}
+
+static const struct nla_policy nl802154_seclevel_policy[NL802154_SECLEVEL_ATTR_MAX + 1] = {
+ [NL802154_SECLEVEL_ATTR_LEVELS] = { .type = NLA_U8 },
+ [NL802154_SECLEVEL_ATTR_FRAME] = { .type = NLA_U32 },
+ [NL802154_SECLEVEL_ATTR_CMD_FRAME] = { .type = NLA_U32 },
+ [NL802154_SECLEVEL_ATTR_DEV_OVERRIDE] = { .type = NLA_U8 },
+};
+
+static int
+llsec_parse_seclevel(struct nlattr *nla, struct ieee802154_llsec_seclevel *sl)
+{
+ struct nlattr *attrs[NL802154_SECLEVEL_ATTR_MAX + 1];
+
+ if (!nla || nla_parse_nested(attrs, NL802154_SECLEVEL_ATTR_MAX, nla,
+ nl802154_seclevel_policy))
+ return -EINVAL;
+
+ memset(sl, 0, sizeof(*sl));
+
+ if (!attrs[NL802154_SECLEVEL_ATTR_LEVELS] ||
+ !attrs[NL802154_SECLEVEL_ATTR_FRAME] ||
+ !attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE])
+ return -EINVAL;
+
+ sl->sec_levels = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_LEVELS]);
+ sl->frame_type = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_FRAME]);
+ sl->device_override = nla_get_u8(attrs[NL802154_SECLEVEL_ATTR_DEV_OVERRIDE]);
+ if (sl->frame_type > NL802154_FRAME_MAX ||
+ (sl->device_override != 0 && sl->device_override != 1))
+ return -EINVAL;
+
+ if (sl->frame_type == NL802154_FRAME_CMD) {
+ if (!attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME])
+ return -EINVAL;
+
+ sl->cmd_frame_id = nla_get_u32(attrs[NL802154_SECLEVEL_ATTR_CMD_FRAME]);
+ if (sl->cmd_frame_id > NL802154_CMD_FRAME_MAX)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int nl802154_add_llsec_seclevel(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct ieee802154_llsec_seclevel sl;
+
+ if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL],
+ &sl) < 0)
+ return -EINVAL;
+
+ return rdev_add_seclevel(rdev, wpan_dev, &sl);
+}
+
+static int nl802154_del_llsec_seclevel(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct cfg802154_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+ struct ieee802154_llsec_seclevel sl;
+
+ if (!info->attrs[NL802154_ATTR_SEC_LEVEL] ||
+ llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL],
+ &sl) < 0)
+ return -EINVAL;
+
+ return rdev_del_seclevel(rdev, wpan_dev, &sl);
+}
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
+
#define NL802154_FLAG_NEED_WPAN_PHY 0x01
#define NL802154_FLAG_NEED_NETDEV 0x02
#define NL802154_FLAG_NEED_RTNL 0x04
@@ -1289,6 +2303,119 @@ static const struct genl_ops nl802154_ops[] = {
.internal_flags = NL802154_FLAG_NEED_NETDEV |
NL802154_FLAG_NEED_RTNL,
},
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+ {
+ .cmd = NL802154_CMD_SET_SEC_PARAMS,
+ .doit = nl802154_set_llsec_params,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_GET_SEC_KEY,
+ /* TODO .doit by matching key id? */
+ .dumpit = nl802154_dump_llsec_key,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_NEW_SEC_KEY,
+ .doit = nl802154_add_llsec_key,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_DEL_SEC_KEY,
+ .doit = nl802154_del_llsec_key,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ /* TODO unique identifier must short+pan OR extended_addr */
+ {
+ .cmd = NL802154_CMD_GET_SEC_DEV,
+ /* TODO .doit by matching extended_addr? */
+ .dumpit = nl802154_dump_llsec_dev,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_NEW_SEC_DEV,
+ .doit = nl802154_add_llsec_dev,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_DEL_SEC_DEV,
+ .doit = nl802154_del_llsec_dev,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ /* TODO remove complete devkey, put it as nested? */
+ {
+ .cmd = NL802154_CMD_GET_SEC_DEVKEY,
+ /* TODO doit by matching ??? */
+ .dumpit = nl802154_dump_llsec_devkey,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_NEW_SEC_DEVKEY,
+ .doit = nl802154_add_llsec_devkey,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_DEL_SEC_DEVKEY,
+ .doit = nl802154_del_llsec_devkey,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_GET_SEC_LEVEL,
+ /* TODO .doit by matching frame_type? */
+ .dumpit = nl802154_dump_llsec_seclevel,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_NEW_SEC_LEVEL,
+ .doit = nl802154_add_llsec_seclevel,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+ {
+ .cmd = NL802154_CMD_DEL_SEC_LEVEL,
+ /* TODO match frame_type only? */
+ .doit = nl802154_del_llsec_seclevel,
+ .policy = nl802154_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL802154_FLAG_NEED_NETDEV |
+ NL802154_FLAG_NEED_RTNL,
+ },
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
};
/* initialisation/exit functions */
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 03b357501cc5..4441c63b3ea6 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -208,4 +208,113 @@ rdev_set_ackreq_default(struct cfg802154_registered_device *rdev,
return ret;
}
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+/* TODO this is already a nl802154, so move into ieee802154 */
+static inline void
+rdev_get_llsec_table(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ struct ieee802154_llsec_table **table)
+{
+ rdev->ops->get_llsec_table(&rdev->wpan_phy, wpan_dev, table);
+}
+
+static inline void
+rdev_lock_llsec_table(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev)
+{
+ rdev->ops->lock_llsec_table(&rdev->wpan_phy, wpan_dev);
+}
+
+static inline void
+rdev_unlock_llsec_table(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev)
+{
+ rdev->ops->unlock_llsec_table(&rdev->wpan_phy, wpan_dev);
+}
+
+static inline int
+rdev_get_llsec_params(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ struct ieee802154_llsec_params *params)
+{
+ return rdev->ops->get_llsec_params(&rdev->wpan_phy, wpan_dev, params);
+}
+
+static inline int
+rdev_set_llsec_params(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_params *params,
+ u32 changed)
+{
+ return rdev->ops->set_llsec_params(&rdev->wpan_phy, wpan_dev, params,
+ changed);
+}
+
+static inline int
+rdev_add_llsec_key(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_key_id *id,
+ const struct ieee802154_llsec_key *key)
+{
+ return rdev->ops->add_llsec_key(&rdev->wpan_phy, wpan_dev, id, key);
+}
+
+static inline int
+rdev_del_llsec_key(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_key_id *id)
+{
+ return rdev->ops->del_llsec_key(&rdev->wpan_phy, wpan_dev, id);
+}
+
+static inline int
+rdev_add_seclevel(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_seclevel *sl)
+{
+ return rdev->ops->add_seclevel(&rdev->wpan_phy, wpan_dev, sl);
+}
+
+static inline int
+rdev_del_seclevel(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_seclevel *sl)
+{
+ return rdev->ops->del_seclevel(&rdev->wpan_phy, wpan_dev, sl);
+}
+
+static inline int
+rdev_add_device(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_device *dev_desc)
+{
+ return rdev->ops->add_device(&rdev->wpan_phy, wpan_dev, dev_desc);
+}
+
+static inline int
+rdev_del_device(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev, __le64 extended_addr)
+{
+ return rdev->ops->del_device(&rdev->wpan_phy, wpan_dev, extended_addr);
+}
+
+static inline int
+rdev_add_devkey(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev, __le64 extended_addr,
+ const struct ieee802154_llsec_device_key *devkey)
+{
+ return rdev->ops->add_devkey(&rdev->wpan_phy, wpan_dev, extended_addr,
+ devkey);
+}
+
+static inline int
+rdev_del_devkey(struct cfg802154_registered_device *rdev,
+ struct wpan_dev *wpan_dev, __le64 extended_addr,
+ const struct ieee802154_llsec_device_key *devkey)
+{
+ return rdev->ops->del_devkey(&rdev->wpan_phy, wpan_dev, extended_addr,
+ devkey);
+}
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
+
#endif /* __CFG802154_RDEV_OPS */
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index b6eacf30ee7a..a548be247e15 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -273,7 +273,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
goto out;
}
- mtu = dev->mtu;
+ mtu = IEEE802154_MTU;
pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
if (size > mtu) {
@@ -637,7 +637,7 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
err = -ENXIO;
goto out;
}
- mtu = dev->mtu;
+ mtu = IEEE802154_MTU;
pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
if (size > mtu) {
@@ -676,8 +676,8 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
cb->seclevel = ro->seclevel;
cb->seclevel_override = ro->seclevel_override;
- err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr,
- ro->bound ? &ro->src_addr : NULL, size);
+ err = wpan_dev_hard_header(skb, dev, &dst_addr,
+ ro->bound ? &ro->src_addr : NULL, size);
if (err < 0)
goto out_skb;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 064bd3caaa4f..42778d9d71e5 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -57,8 +57,7 @@ static unsigned int fib_info_cnt;
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];
#ifdef CONFIG_IP_ROUTE_MULTIPATH
-
-static DEFINE_SPINLOCK(fib_multipath_lock);
+u32 fib_multipath_secret __read_mostly;
#define for_nexthops(fi) { \
int nhsel; const struct fib_nh *nh; \
@@ -532,7 +531,67 @@ errout:
return ret;
}
-#endif
+static void fib_rebalance(struct fib_info *fi)
+{
+ int total;
+ int w;
+ struct in_device *in_dev;
+
+ if (fi->fib_nhs < 2)
+ return;
+
+ total = 0;
+ for_nexthops(fi) {
+ if (nh->nh_flags & RTNH_F_DEAD)
+ continue;
+
+ in_dev = __in_dev_get_rtnl(nh->nh_dev);
+
+ if (in_dev &&
+ IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+ nh->nh_flags & RTNH_F_LINKDOWN)
+ continue;
+
+ total += nh->nh_weight;
+ } endfor_nexthops(fi);
+
+ w = 0;
+ change_nexthops(fi) {
+ int upper_bound;
+
+ in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev);
+
+ if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
+ upper_bound = -1;
+ } else if (in_dev &&
+ IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+ nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
+ upper_bound = -1;
+ } else {
+ w += nexthop_nh->nh_weight;
+ upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
+ total) - 1;
+ }
+
+ atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
+ } endfor_nexthops(fi);
+
+ net_get_random_once(&fib_multipath_secret,
+ sizeof(fib_multipath_secret));
+}
+
+static inline void fib_add_weight(struct fib_info *fi,
+ const struct fib_nh *nh)
+{
+ fi->fib_weight += nh->nh_weight;
+}
+
+#else /* CONFIG_IP_ROUTE_MULTIPATH */
+
+#define fib_rebalance(fi) do { } while (0)
+#define fib_add_weight(fi, nh) do { } while (0)
+
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
static int fib_encap_match(struct net *net, u16 encap_type,
struct nlattr *encap,
@@ -1094,8 +1153,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
change_nexthops(fi) {
fib_info_update_nh_saddr(net, nexthop_nh);
+ fib_add_weight(fi, nexthop_nh);
} endfor_nexthops(fi)
+ fib_rebalance(fi);
+
link_it:
ofi = fib_find_info(fi);
if (ofi) {
@@ -1317,12 +1379,6 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
break;
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
- spin_lock_bh(&fib_multipath_lock);
- fi->fib_power -= nexthop_nh->nh_power;
- nexthop_nh->nh_power = 0;
- spin_unlock_bh(&fib_multipath_lock);
-#endif
dead++;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1345,6 +1401,8 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
}
ret++;
}
+
+ fib_rebalance(fi);
}
return ret;
@@ -1467,20 +1525,15 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
!__in_dev_get_rtnl(dev))
continue;
alive++;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
- spin_lock_bh(&fib_multipath_lock);
- nexthop_nh->nh_power = 0;
nexthop_nh->nh_flags &= ~nh_flags;
- spin_unlock_bh(&fib_multipath_lock);
-#else
- nexthop_nh->nh_flags &= ~nh_flags;
-#endif
} endfor_nexthops(fi)
if (alive > 0) {
fi->fib_flags &= ~nh_flags;
ret++;
}
+
+ fib_rebalance(fi);
}
return ret;
@@ -1488,62 +1541,40 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
#ifdef CONFIG_IP_ROUTE_MULTIPATH
-/*
- * The algorithm is suboptimal, but it provides really
- * fair weighted route distribution.
- */
-void fib_select_multipath(struct fib_result *res)
+void fib_select_multipath(struct fib_result *res, int hash)
{
struct fib_info *fi = res->fi;
- struct in_device *in_dev;
- int w;
-
- spin_lock_bh(&fib_multipath_lock);
- if (fi->fib_power <= 0) {
- int power = 0;
- change_nexthops(fi) {
- in_dev = __in_dev_get_rcu(nexthop_nh->nh_dev);
- if (nexthop_nh->nh_flags & RTNH_F_DEAD)
- continue;
- if (in_dev &&
- IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
- nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
- continue;
- power += nexthop_nh->nh_weight;
- nexthop_nh->nh_power = nexthop_nh->nh_weight;
- } endfor_nexthops(fi);
- fi->fib_power = power;
- if (power <= 0) {
- spin_unlock_bh(&fib_multipath_lock);
- /* Race condition: route has just become dead. */
- res->nh_sel = 0;
- return;
- }
- }
-
- /* w should be random number [0..fi->fib_power-1],
- * it is pretty bad approximation.
- */
-
- w = jiffies % fi->fib_power;
+ for_nexthops(fi) {
+ if (hash > atomic_read(&nh->nh_upper_bound))
+ continue;
- change_nexthops(fi) {
- if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) &&
- nexthop_nh->nh_power) {
- w -= nexthop_nh->nh_power;
- if (w <= 0) {
- nexthop_nh->nh_power--;
- fi->fib_power--;
- res->nh_sel = nhsel;
- spin_unlock_bh(&fib_multipath_lock);
- return;
- }
- }
+ res->nh_sel = nhsel;
+ return;
} endfor_nexthops(fi);
/* Race condition: route has just become dead. */
res->nh_sel = 0;
- spin_unlock_bh(&fib_multipath_lock);
}
#endif
+
+void fib_select_path(struct net *net, struct fib_result *res,
+ struct flowi4 *fl4, int mp_hash)
+{
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+ if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
+ if (mp_hash < 0)
+ mp_hash = fib_multipath_hash(fl4->saddr, fl4->daddr);
+ fib_select_multipath(res, mp_hash);
+ }
+ else
+#endif
+ if (!res->prefixlen &&
+ res->table->tb_num_default > 1 &&
+ res->type == RTN_UNICAST && !fl4->flowi4_oif)
+ fib_select_default(fl4, res);
+
+ if (!fl4->saddr)
+ fl4->saddr = FIB_RES_PREFSRC(net, *res);
+}
+EXPORT_SYMBOL_GPL(fib_select_path);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 6b96dee2800b..36e26977c908 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -440,6 +440,22 @@ out_unlock:
icmp_xmit_unlock(sk);
}
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+
+/* Source and destination is swapped. See ip_multipath_icmp_hash */
+static int icmp_multipath_hash_skb(const struct sk_buff *skb)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+
+ return fib_multipath_hash(iph->daddr, iph->saddr);
+}
+
+#else
+
+#define icmp_multipath_hash_skb(skb) (-1)
+
+#endif
+
static struct rtable *icmp_route_lookup(struct net *net,
struct flowi4 *fl4,
struct sk_buff *skb_in,
@@ -464,7 +480,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
- rt = __ip_route_output_key(net, fl4);
+ rt = __ip_route_output_key_hash(net, fl4,
+ icmp_multipath_hash_skb(skb_in));
if (IS_ERR(rt))
return rt;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index de6d4c8ba600..64aaf3522a59 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -397,7 +397,7 @@ static int igmpv3_sendpack(struct sk_buff *skb)
pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen);
- return ip_local_out(skb);
+ return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
}
static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
@@ -739,7 +739,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
ih->group = group;
ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr));
- return ip_local_out(skb);
+ return ip_local_out(net, skb->sk, skb);
}
static void igmp_gq_timer_expire(unsigned long data)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 89eedfbd4ad5..8430bc8ccd58 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -546,6 +546,13 @@ void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
+void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req)
+{
+ inet_csk_reqsk_queue_drop(sk, req);
+ reqsk_put(req);
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put);
+
static void reqsk_timer_handler(unsigned long data)
{
struct request_sock *req = (struct request_sock *)data;
@@ -579,7 +586,7 @@ static void reqsk_timer_handler(unsigned long data)
* ones are about to clog our table.
*/
qlen = reqsk_queue_len(queue);
- if ((qlen << 1) > sk_listener->sk_max_ack_backlog) {
+ if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) {
int young = reqsk_queue_len_young(queue) << 1;
while (thresh > 2) {
@@ -608,8 +615,7 @@ static void reqsk_timer_handler(unsigned long data)
return;
}
drop:
- inet_csk_reqsk_queue_drop(sk_listener, req);
- reqsk_put(req);
+ inet_csk_reqsk_queue_drop_and_put(sk_listener, req);
}
static void reqsk_queue_hash_req(struct request_sock *req,
@@ -727,14 +733,14 @@ void inet_csk_prepare_forced_close(struct sock *sk)
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
-int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
+int inet_csk_listen_start(struct sock *sk, int backlog)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
reqsk_queue_alloc(&icsk->icsk_accept_queue);
- sk->sk_max_ack_backlog = 0;
+ sk->sk_max_ack_backlog = backlog;
sk->sk_ack_backlog = 0;
inet_csk_delack_init(sk);
@@ -758,6 +764,53 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
}
EXPORT_SYMBOL_GPL(inet_csk_listen_start);
+static void inet_child_forget(struct sock *sk, struct request_sock *req,
+ struct sock *child)
+{
+ sk->sk_prot->disconnect(child, O_NONBLOCK);
+
+ sock_orphan(child);
+
+ percpu_counter_inc(sk->sk_prot->orphan_count);
+
+ if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
+ BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+ BUG_ON(sk != req->rsk_listener);
+
+ /* Paranoid, to prevent race condition if
+ * an inbound pkt destined for child is
+ * blocked by sock lock in tcp_v4_rcv().
+ * Also to satisfy an assertion in
+ * tcp_v4_destroy_sock().
+ */
+ tcp_sk(child)->fastopen_rsk = NULL;
+ }
+ inet_csk_destroy_sock(child);
+ reqsk_put(req);
+}
+
+void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
+ struct sock *child)
+{
+ struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+
+ spin_lock(&queue->rskq_lock);
+ if (unlikely(sk->sk_state != TCP_LISTEN)) {
+ inet_child_forget(sk, req, child);
+ } else {
+ req->sk = child;
+ req->dl_next = NULL;
+ if (queue->rskq_accept_head == NULL)
+ queue->rskq_accept_head = req;
+ else
+ queue->rskq_accept_tail->dl_next = req;
+ queue->rskq_accept_tail = req;
+ sk_acceptq_added(sk);
+ }
+ spin_unlock(&queue->rskq_lock);
+}
+EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
+
/*
* This routine closes sockets which have been at least partially
* opened, but not yet accepted.
@@ -784,31 +837,11 @@ void inet_csk_listen_stop(struct sock *sk)
WARN_ON(sock_owned_by_user(child));
sock_hold(child);
- sk->sk_prot->disconnect(child, O_NONBLOCK);
-
- sock_orphan(child);
-
- percpu_counter_inc(sk->sk_prot->orphan_count);
-
- if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
- BUG_ON(tcp_sk(child)->fastopen_rsk != req);
- BUG_ON(sk != req->rsk_listener);
-
- /* Paranoid, to prevent race condition if
- * an inbound pkt destined for child is
- * blocked by sock lock in tcp_v4_rcv().
- * Also to satisfy an assertion in
- * tcp_v4_destroy_sock().
- */
- tcp_sk(child)->fastopen_rsk = NULL;
- }
- inet_csk_destroy_sock(child);
-
+ inet_child_forget(sk, req, child);
bh_unlock_sock(child);
local_bh_enable();
sock_put(child);
- reqsk_put(req);
cond_resched();
}
if (queue->fastopenq.rskq_rst_head) {
@@ -823,7 +856,7 @@ void inet_csk_listen_stop(struct sock *sk)
req = next;
}
}
- WARN_ON(sk->sk_ack_backlog);
+ WARN_ON_ONCE(sk->sk_ack_backlog);
}
EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index bed8886a4b6c..958728a22001 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -137,6 +137,10 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
+ if (unlikely(!tb)) {
+ spin_unlock(&head->lock);
+ return -ENOENT;
+ }
if (tb->port != port) {
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
@@ -185,6 +189,8 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score += 4;
}
+ if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ score++;
}
return score;
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index d66cfb35ba74..da0d7ce85844 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -72,7 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s
ip_forward_options(skb);
skb_sender_cpu_clear(skb);
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
int ip_forward(struct sk_buff *skb)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9772b789adf3..5482745d5d68 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -654,11 +654,10 @@ out_fail:
}
/* Process an incoming IP datagram fragment. */
-int ip_defrag(struct sk_buff *skb, u32 user)
+int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
struct net_device *dev = skb->dev ? : skb_dst(skb)->dev;
int vif = l3mdev_master_ifindex_rcu(dev);
- struct net *net = dev_net(dev);
struct ipq *qp;
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
@@ -683,7 +682,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
}
EXPORT_SYMBOL(ip_defrag);
-struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
+struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
{
struct iphdr iph;
int netoff;
@@ -712,7 +711,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
if (pskb_trim_rcsum(skb, netoff + len))
return skb;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
- if (ip_defrag(skb, user))
+ if (ip_defrag(net, skb, user))
return NULL;
skb_clear_hash(skb);
}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 7cc9f7bb7fb7..b1209b63381f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -157,6 +157,7 @@ bool ip_call_ra_chain(struct sk_buff *skb)
u8 protocol = ip_hdr(skb)->protocol;
struct sock *last = NULL;
struct net_device *dev = skb->dev;
+ struct net *net = dev_net(dev);
for (ra = rcu_dereference(ip_ra_chain); ra; ra = rcu_dereference(ra->next)) {
struct sock *sk = ra->sk;
@@ -167,9 +168,9 @@ bool ip_call_ra_chain(struct sk_buff *skb)
if (sk && inet_sk(sk)->inet_num == protocol &&
(!sk->sk_bound_dev_if ||
sk->sk_bound_dev_if == dev->ifindex) &&
- net_eq(sock_net(sk), dev_net(dev))) {
+ net_eq(sock_net(sk), net)) {
if (ip_is_fragment(ip_hdr(skb))) {
- if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN))
+ if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN))
return true;
}
if (last) {
@@ -246,14 +247,15 @@ int ip_local_deliver(struct sk_buff *skb)
/*
* Reassemble IP fragments.
*/
+ struct net *net = dev_net(skb->dev);
if (ip_is_fragment(ip_hdr(skb))) {
- if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER))
+ if (ip_defrag(net, skb, IP_DEFRAG_LOCAL_DELIVER))
return 0;
}
return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN,
- dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+ net, NULL, skb, skb->dev, NULL,
ip_local_deliver_finish);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index aff6766922e8..67404e1fe7d4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -83,9 +83,10 @@
int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
EXPORT_SYMBOL(sysctl_ip_default_ttl);
-static int ip_fragment(struct sock *sk, struct sk_buff *skb,
- unsigned int mtu,
- int (*output)(struct sock *, struct sk_buff *));
+static int
+ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ unsigned int mtu,
+ int (*output)(struct net *, struct sock *, struct sk_buff *));
/* Generate a checksum for an outgoing IP datagram. */
void ip_send_check(struct iphdr *iph)
@@ -95,34 +96,28 @@ void ip_send_check(struct iphdr *iph)
}
EXPORT_SYMBOL(ip_send_check);
-static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
+int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
struct iphdr *iph = ip_hdr(skb);
iph->tot_len = htons(skb->len);
ip_send_check(iph);
return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, skb_dst(skb)->dev,
- dst_output_okfn);
-}
-
-int __ip_local_out(struct sk_buff *skb)
-{
- return __ip_local_out_sk(skb->sk, skb);
+ dst_output);
}
-int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
+int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
int err;
- err = __ip_local_out(skb);
+ err = __ip_local_out(net, sk, skb);
if (likely(err == 1))
- err = dst_output(sk, skb);
+ err = dst_output(net, sk, skb);
return err;
}
-EXPORT_SYMBOL_GPL(ip_local_out_sk);
+EXPORT_SYMBOL_GPL(ip_local_out);
static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
{
@@ -142,6 +137,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
{
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = skb_rtable(skb);
+ struct net *net = sock_net(sk);
struct iphdr *iph;
/* Build the IP header. */
@@ -160,7 +156,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
iph->id = 0;
} else {
iph->frag_off = 0;
- __ip_select_ident(sock_net(sk), iph, 1);
+ __ip_select_ident(net, iph, 1);
}
if (opt && opt->opt.optlen) {
@@ -172,16 +168,15 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
skb->mark = sk->sk_mark;
/* Send it out. */
- return ip_local_out(skb);
+ return ip_local_out(net, skb->sk, skb);
}
EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);
-static int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
- struct net *net = dev_net(dev);
unsigned int hh_len = LL_RESERVED_SPACE(dev);
struct neighbour *neigh;
u32 nexthop;
@@ -225,8 +220,8 @@ static int ip_finish_output2(struct sock *sk, struct sk_buff *skb)
return -EINVAL;
}
-static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
- unsigned int mtu)
+static int ip_finish_output_gso(struct net *net, struct sock *sk,
+ struct sk_buff *skb, unsigned int mtu)
{
netdev_features_t features;
struct sk_buff *segs;
@@ -235,7 +230,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
/* common case: locally created skb or seglen is <= mtu */
if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
skb_gso_network_seglen(skb) <= mtu)
- return ip_finish_output2(sk, skb);
+ return ip_finish_output2(net, sk, skb);
/* Slowpath - GSO segment length is exceeding the dst MTU.
*
@@ -258,7 +253,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
int err;
segs->next = NULL;
- err = ip_fragment(sk, segs, mtu, ip_finish_output2);
+ err = ip_fragment(net, sk, segs, mtu, ip_finish_output2);
if (err && ret == 0)
ret = err;
@@ -276,24 +271,23 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
IPCB(skb)->flags |= IPSKB_REROUTED;
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
#endif
mtu = ip_skb_dst_mtu(skb);
if (skb_is_gso(skb))
- return ip_finish_output_gso(sk, skb, mtu);
+ return ip_finish_output_gso(net, sk, skb, mtu);
if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
- return ip_fragment(sk, skb, mtu, ip_finish_output2);
+ return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
- return ip_finish_output2(sk, skb);
+ return ip_finish_output2(net, sk, skb);
}
-int ip_mc_output(struct sock *sk, struct sk_buff *skb)
+int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
- struct net *net = dev_net(dev);
/*
* If the indicated interface is up and running, send the packet.
@@ -352,10 +346,9 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb)
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
-int ip_output(struct sock *sk, struct sk_buff *skb)
+int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev;
- struct net *net = dev_net(dev);
IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);
@@ -386,6 +379,7 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
{
struct inet_sock *inet = inet_sk(sk);
+ struct net *net = sock_net(sk);
struct ip_options_rcu *inet_opt;
struct flowi4 *fl4;
struct rtable *rt;
@@ -416,7 +410,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
* keep trying until route appears or the connection times
* itself out.
*/
- rt = ip_route_output_ports(sock_net(sk), fl4, sk,
+ rt = ip_route_output_ports(net, fl4, sk,
daddr, inet->inet_saddr,
inet->inet_dport,
inet->inet_sport,
@@ -453,20 +447,20 @@ packet_routed:
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
}
- ip_select_ident_segs(sock_net(sk), skb, sk,
+ ip_select_ident_segs(net, skb, sk,
skb_shinfo(skb)->gso_segs ?: 1);
/* TODO : should we use skb->sk here instead of sk ? */
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
- res = ip_local_out(skb);
+ res = ip_local_out(net, sk, skb);
rcu_read_unlock();
return res;
no_route:
rcu_read_unlock();
- IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EHOSTUNREACH;
}
@@ -495,20 +489,18 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
skb_copy_secmark(to, from);
}
-static int ip_fragment(struct sock *sk, struct sk_buff *skb,
+static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
unsigned int mtu,
- int (*output)(struct sock *, struct sk_buff *))
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct iphdr *iph = ip_hdr(skb);
if ((iph->frag_off & htons(IP_DF)) == 0)
- return ip_do_fragment(sk, skb, output);
+ return ip_do_fragment(net, sk, skb, output);
if (unlikely(!skb->ignore_df ||
(IPCB(skb)->frag_max_size &&
IPCB(skb)->frag_max_size > mtu))) {
- struct net *net = dev_net(skb_rtable(skb)->dst.dev);
-
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
@@ -516,7 +508,7 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb,
return -EMSGSIZE;
}
- return ip_do_fragment(sk, skb, output);
+ return ip_do_fragment(net, sk, skb, output);
}
/*
@@ -526,8 +518,8 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb,
* single device frame, and queue such a frame for sending.
*/
-int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *))
+int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct iphdr *iph;
int ptr;
@@ -537,11 +529,9 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
int offset;
__be16 not_last_frag;
struct rtable *rt = skb_rtable(skb);
- struct net *net;
int err = 0;
dev = rt->dst.dev;
- net = dev_net(dev);
/*
* Point into the IP datagram header.
@@ -631,7 +621,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
ip_send_check(iph);
}
- err = output(sk, skb);
+ err = output(net, sk, skb);
if (!err)
IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
@@ -771,7 +761,7 @@ slow_path:
ip_send_check(iph);
- err = output(sk, skb2);
+ err = output(net, sk, skb2);
if (err)
goto fail;
@@ -1444,7 +1434,7 @@ int ip_send_skb(struct net *net, struct sk_buff *skb)
{
int err;
- err = ip_local_out(skb);
+ err = ip_local_out(net, skb->sk, skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 84dce6a92f93..6cb9009c3d96 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -53,6 +53,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
+ struct net *net = dev_net(rt->dst.dev);
struct iphdr *iph;
int err;
@@ -76,10 +77,9 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
- __ip_select_ident(dev_net(rt->dst.dev), iph,
- skb_shinfo(skb)->gso_segs ?: 1);
+ __ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
- err = ip_local_out_sk(sk, skb);
+ err = ip_local_out(net, sk, skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
return pkt_len;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 3b87ec5178f9..4d8f0b698777 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -197,7 +197,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
- err = dst_output(skb->sk, skb);
+ err = dst_output(tunnel->net, skb->sk, skb);
if (net_xmit_eval(err) == 0)
err = skb->len;
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index cfcb996ec51b..fc42525d8694 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1689,7 +1689,7 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
if (unlikely(opt->optlen))
ip_forward_options(skb);
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
/*
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index a1058363d2e9..5fdc556514ba 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -63,7 +63,7 @@ synproxy_send_tcp(const struct synproxy_net *snet,
nf_conntrack_get(nfct);
}
- ip_local_out(nskb);
+ ip_local_out(net, nskb->sk, nskb);
return;
free_nskb:
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 9df3f93269d3..0e5591c2ee9f 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,14 +22,15 @@
#endif
#include <net/netfilter/nf_conntrack_zones.h>
-static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
+static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
+ u_int32_t user)
{
int err;
skb_orphan(skb);
local_bh_disable();
- err = ip_defrag(skb, user);
+ err = ip_defrag(net, skb, user);
local_bh_enable();
if (!err) {
@@ -85,7 +86,7 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
enum ip_defrag_users user =
nf_ct_defrag_user(state->hook, skb);
- if (nf_ct_ipv4_gather_frags(skb, user))
+ if (nf_ct_ipv4_gather_frags(state->net, skb, user))
return NF_STOLEN;
}
return NF_ACCEPT;
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index ce2a59e5c665..ceb187308120 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -92,7 +92,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
if (nf_dup_ipv4_route(net, skb, gw, oif)) {
__this_cpu_write(nf_skb_duplicated, true);
- ip_local_out(skb);
+ ip_local_out(net, skb->sk, skb);
__this_cpu_write(nf_skb_duplicated, false);
} else {
kfree_skb(skb);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 2f5e925d3264..c747b2d9eb77 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -157,7 +157,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
dev_queue_xmit(nskb);
} else
#endif
- ip_local_out(nskb);
+ ip_local_out(net, nskb->sk, nskb);
return;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 28ef8a913130..8c0d0bdc2a7c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -413,7 +413,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, rt->dst.dev,
- dst_output_okfn);
+ dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
@@ -484,6 +484,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
+ struct net *net = sock_net(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
struct flowi4 fl4;
@@ -543,7 +544,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
- err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
+ err = ip_cmsg_send(net, msg, &ipc, false);
if (err)
goto out;
if (ipc.opt)
@@ -598,6 +599,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
+ if (!saddr && ipc.oif)
+ l3mdev_get_saddr(net, ipc.oif, &fl4);
+
if (!inet->hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
@@ -608,7 +612,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
- rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+ rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 76ca4e75f785..85f184e429c6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1152,7 +1152,7 @@ static void ipv4_link_failure(struct sk_buff *skb)
dst_set_expires(&rt->dst, 0);
}
-static int ip_rt_bug(struct sock *sk, struct sk_buff *skb)
+static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb)
{
pr_debug("%s: %pI4 -> %pI4, %s\n",
__func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
@@ -1651,6 +1651,48 @@ out:
return err;
}
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+
+/* To make ICMP packets follow the right flow, the multipath hash is
+ * calculated from the inner IP addresses in reverse order.
+ */
+static int ip_multipath_icmp_hash(struct sk_buff *skb)
+{
+ const struct iphdr *outer_iph = ip_hdr(skb);
+ struct icmphdr _icmph;
+ const struct icmphdr *icmph;
+ struct iphdr _inner_iph;
+ const struct iphdr *inner_iph;
+
+ if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
+ goto standard_hash;
+
+ icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
+ &_icmph);
+ if (!icmph)
+ goto standard_hash;
+
+ if (icmph->type != ICMP_DEST_UNREACH &&
+ icmph->type != ICMP_REDIRECT &&
+ icmph->type != ICMP_TIME_EXCEEDED &&
+ icmph->type != ICMP_PARAMETERPROB) {
+ goto standard_hash;
+ }
+
+ inner_iph = skb_header_pointer(skb,
+ outer_iph->ihl * 4 + sizeof(_icmph),
+ sizeof(_inner_iph), &_inner_iph);
+ if (!inner_iph)
+ goto standard_hash;
+
+ return fib_multipath_hash(inner_iph->daddr, inner_iph->saddr);
+
+standard_hash:
+ return fib_multipath_hash(outer_iph->saddr, outer_iph->daddr);
+}
+
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+
static int ip_mkroute_input(struct sk_buff *skb,
struct fib_result *res,
const struct flowi4 *fl4,
@@ -1658,8 +1700,15 @@ static int ip_mkroute_input(struct sk_buff *skb,
__be32 daddr, __be32 saddr, u32 tos)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (res->fi && res->fi->fib_nhs > 1)
- fib_select_multipath(res);
+ if (res->fi && res->fi->fib_nhs > 1) {
+ int h;
+
+ if (unlikely(ip_hdr(skb)->protocol == IPPROTO_ICMP))
+ h = ip_multipath_icmp_hash(skb);
+ else
+ h = fib_multipath_hash(saddr, daddr);
+ fib_select_multipath(res, h);
+ }
#endif
/* create a routing cache entry */
@@ -2026,7 +2075,8 @@ add:
* Major route resolver routine.
*/
-struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
+struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
+ int mp_hash)
{
struct net_device *dev_out = NULL;
__u8 tos = RT_FL_TOS(fl4);
@@ -2146,7 +2196,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
if (err) {
res.fi = NULL;
res.table = NULL;
- if (fl4->flowi4_oif) {
+ if (fl4->flowi4_oif &&
+ !netif_index_is_l3_master(net, fl4->flowi4_oif)) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
@@ -2188,18 +2239,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
goto make_route;
}
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0)
- fib_select_multipath(&res);
- else
-#endif
- if (!res.prefixlen &&
- res.table->tb_num_default > 1 &&
- res.type == RTN_UNICAST && !fl4->flowi4_oif)
- fib_select_default(fl4, &res);
-
- if (!fl4->saddr)
- fl4->saddr = FIB_RES_PREFSRC(net, res);
+ fib_select_path(net, &res, fl4, mp_hash);
dev_out = FIB_RES_DEV(res);
fl4->flowi4_oif = dev_out->ifindex;
@@ -2212,7 +2252,7 @@ out:
rcu_read_unlock();
return rth;
}
-EXPORT_SYMBOL_GPL(__ip_route_output_key);
+EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
{
@@ -2264,7 +2304,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
new->__use = 1;
new->input = dst_discard;
- new->output = dst_discard_sk;
+ new->output = dst_discard_out;
new->dev = ort->dst.dev;
if (new->dev)
@@ -2468,6 +2508,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ if (netif_index_is_l3_master(net, fl4.flowi4_oif))
+ fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF;
+
if (iif) {
struct net_device *dev;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 729ceb5f63c6..4c0892badb8b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -225,6 +225,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst);
if (child) {
atomic_set(&req->rsk_refcnt, 1);
+ sock_rps_save_rxhash(child, skb);
inet_csk_reqsk_queue_add(sk, req, child);
} else {
reqsk_free(req);
@@ -326,7 +327,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
goto out;
ret = NULL;
- req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */
+ req = inet_reqsk_alloc(&tcp_request_sock_ops, sk, false); /* for safety */
if (!req)
goto out;
@@ -381,10 +382,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
}
/* Try to redo what tcp_v4_send_synack did. */
- req->window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
- &req->rcv_wnd, &req->window_clamp,
+ &req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3c96fa87ff9e..ac1bdbb50352 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -900,7 +900,8 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
*/
if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
!tcp_passive_fastopen(sk)) {
- if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
+ err = sk_stream_wait_connect(sk, &timeo);
+ if (err != 0)
goto out_err;
}
@@ -967,7 +968,8 @@ new_segment:
copied += copy;
offset += copy;
- if (!(size -= copy)) {
+ size -= copy;
+ if (!size) {
tcp_tx_timestamp(sk, skb);
goto out;
}
@@ -988,7 +990,8 @@ wait_for_memory:
tcp_push(sk, flags & ~MSG_MORE, mss_now,
TCP_NAGLE_PUSH, size_goal);
- if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err != 0)
goto do_error;
mss_now = tcp_send_mss(sk, &size_goal, flags);
@@ -1111,7 +1114,8 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
*/
if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
!tcp_passive_fastopen(sk)) {
- if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
+ err = sk_stream_wait_connect(sk, &timeo);
+ if (err != 0)
goto do_error;
}
@@ -1267,7 +1271,8 @@ wait_for_memory:
tcp_push(sk, flags & ~MSG_MORE, mss_now,
TCP_NAGLE_PUSH, size_goal);
- if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err != 0)
goto do_error;
mss_now = tcp_send_mss(sk, &size_goal, flags);
@@ -1767,7 +1772,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
/* __ Restore normal policy in scheduler __ */
- if ((chunk = len - tp->ucopy.len) != 0) {
+ chunk = len - tp->ucopy.len;
+ if (chunk != 0) {
NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
len -= chunk;
copied += chunk;
@@ -1778,7 +1784,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
do_prequeue:
tcp_prequeue_process(sk);
- if ((chunk = len - tp->ucopy.len) != 0) {
+ chunk = len - tp->ucopy.len;
+ if (chunk != 0) {
NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
len -= chunk;
copied += chunk;
@@ -2230,7 +2237,8 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
tp->srtt_us = 0;
- if ((tp->write_seq += tp->max_window + 2) == 0)
+ tp->write_seq += tp->max_window + 2;
+ if (tp->write_seq == 0)
tp->write_seq = 1;
icsk->icsk_backoff = 0;
tp->snd_cwnd = 2;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 410ac481fda0..93396bf7b475 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -168,8 +168,6 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
atomic_set(&req->rsk_refcnt, 2);
- /* Add the child socket directly into the accept queue */
- inet_csk_reqsk_queue_add(sk, req, child);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
@@ -178,12 +176,10 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
tcp_init_metrics(child);
tcp_init_buffer_space(child);
- /* Queue the data carried in the SYN packet. We need to first
- * bump skb's refcnt because the caller will attempt to free it.
- * Note that IPv6 might also have used skb_get() trick
- * in tcp_v6_conn_request() to keep this SYN around (treq->pktopts)
- * So we need to eventually get a clone of the packet,
- * before inserting it in sk_receive_queue.
+ /* Queue the data carried in the SYN packet.
+ * We used to play tricky games with skb_get().
+ * With lockless listener, it is a dead end.
+ * Do not think about it.
*
* XXX (TFO) - we honor a zero-payload TFO request for now,
* (any reason not to?) but no need to queue the skb since
@@ -191,12 +187,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
*/
end_seq = TCP_SKB_CB(skb)->end_seq;
if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
- struct sk_buff *skb2;
-
- if (unlikely(skb_shared(skb)))
- skb2 = skb_clone(skb, GFP_ATOMIC);
- else
- skb2 = skb_get(skb);
+ struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (likely(skb2)) {
skb_dst_drop(skb2);
@@ -214,12 +205,9 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
}
}
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
- sk->sk_data_ready(sk);
- bh_unlock_sock(child);
- /* Note: sock_put(child) will be done by tcp_conn_request()
- * after SYNACK packet is sent.
+ /* tcp_conn_request() is sending the SYNACK,
+ * and queues the child into listener accept queue.
*/
- WARN_ON(!req->sk);
return child;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 27108757c310..3b35c3f4d268 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6022,7 +6022,7 @@ static void tcp_openreq_init(struct request_sock *req,
{
struct inet_request_sock *ireq = inet_rsk(req);
- req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */
+ req->rsk_rcv_wnd = 0; /* So that tcp_send_synack() knows! */
req->cookie_ts = 0;
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
@@ -6042,9 +6042,11 @@ static void tcp_openreq_init(struct request_sock *req,
}
struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
- struct sock *sk_listener)
+ struct sock *sk_listener,
+ bool attach_listener)
{
- struct request_sock *req = reqsk_alloc(ops, sk_listener);
+ struct request_sock *req = reqsk_alloc(ops, sk_listener,
+ attach_listener);
if (req) {
struct inet_request_sock *ireq = inet_rsk(req);
@@ -6143,7 +6145,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
goto drop;
}
- req = inet_reqsk_alloc(rsk_ops, sk);
+ req = inet_reqsk_alloc(rsk_ops, sk, !want_cookie);
if (!req)
goto drop;
@@ -6229,12 +6231,16 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->txhash = net_tx_rndhash();
tcp_openreq_init_rwin(req, sk, dst);
if (!want_cookie) {
- fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
tcp_reqsk_record_syn(sk, req, skb);
+ fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
}
if (fastopen_sk) {
af_ops->send_synack(fastopen_sk, dst, &fl, req,
skb_get_queue_mapping(skb), &foc, false);
+ /* Add the child socket directly into the accept queue */
+ inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
+ sk->sk_data_ready(sk);
+ bh_unlock_sock(fastopen_sk);
sock_put(fastopen_sk);
} else {
tcp_rsk(req)->tfo_listener = false;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 34310748a365..9c68cf3762c4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -324,7 +324,6 @@ void tcp_req_err(struct sock *sk, u32 seq)
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
- reqsk_put(req);
} else {
/*
* Still in SYN_RECV, just remove it silently.
@@ -332,9 +331,10 @@ void tcp_req_err(struct sock *sk, u32 seq)
* created socket, and POSIX does not want network
* errors returned from accept().
*/
- NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS);
inet_csk_reqsk_queue_drop(req->rsk_listener, req);
+ NET_INC_STATS_BH(net, LINUX_MIB_LISTENDROPS);
}
+ reqsk_put(req);
}
EXPORT_SYMBOL(tcp_req_err);
@@ -803,7 +803,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
*/
tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
- tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
+ tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
tcp_time_stamp,
req->ts_recent,
0,
@@ -1572,6 +1572,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
TCP_SKB_CB(skb)->sacked = 0;
+lookup:
sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
if (!sk)
goto no_tcp_socket;
@@ -1587,8 +1588,12 @@ process:
sk = req->rsk_listener;
if (tcp_v4_inbound_md5_hash(sk, skb))
goto discard_and_relse;
- if (sk->sk_state == TCP_LISTEN)
+ if (likely(sk->sk_state == TCP_LISTEN)) {
nsk = tcp_check_req(sk, skb, req, false);
+ } else {
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ goto lookup;
+ }
if (!nsk) {
reqsk_put(req);
goto discard_it;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 9adf1e2c3170..41828bdc5d32 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -381,18 +381,18 @@ void tcp_openreq_init_rwin(struct request_sock *req,
window_clamp = READ_ONCE(tp->window_clamp);
/* Set this up on the first call only */
- req->window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+ req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
/* limit the window selection if the user enforce a smaller rx buffer */
if (sk_listener->sk_userlocks & SOCK_RCVBUF_LOCK &&
- (req->window_clamp > full_space || req->window_clamp == 0))
- req->window_clamp = full_space;
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(full_space,
mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
- &req->rcv_wnd,
- &req->window_clamp,
+ &req->rsk_rcv_wnd,
+ &req->rsk_window_clamp,
ireq->wscale_ok,
&rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
@@ -512,9 +512,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
if (sysctl_tcp_fack)
tcp_enable_fack(newtp);
}
- newtp->window_clamp = req->window_clamp;
- newtp->rcv_ssthresh = req->rcv_wnd;
- newtp->rcv_wnd = req->rcv_wnd;
+ newtp->window_clamp = req->rsk_window_clamp;
+ newtp->rcv_ssthresh = req->rsk_rcv_wnd;
+ newtp->rcv_wnd = req->rsk_rcv_wnd;
newtp->rx_opt.wscale_ok = ireq->wscale_ok;
if (newtp->rx_opt.wscale_ok) {
newtp->rx_opt.snd_wscale = ireq->snd_wscale;
@@ -707,7 +707,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
/* RFC793: "first check sequence number". */
if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
- tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rcv_wnd)) {
+ tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) {
/* Out of window: send ACK and drop. */
if (!(flg & TCP_FLAG_RST))
req->rsk_ops->send_ack(sk, skb, req);
@@ -768,6 +768,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
if (!child)
goto listen_overflow;
+ sock_rps_save_rxhash(child, skb);
tcp_synack_rtt_meas(child, req);
inet_csk_reqsk_queue_drop(sk, req);
inet_csk_reqsk_queue_add(sk, req, child);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 55ed3266b05f..6e79fcb0addb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3023,7 +3023,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
- th->window = htons(min(req->rcv_wnd, 65535U));
+ th->window = htons(min(req->rsk_rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), NULL, &opts);
th->doff = (tcp_header_size >> 2);
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 7149ebc820c7..c9c716a483e4 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -83,7 +83,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
}
/* Calculate maximal number or retries on an orphaned socket. */
-static int tcp_orphan_retries(struct sock *sk, int alive)
+static int tcp_orphan_retries(struct sock *sk, bool alive)
{
int retries = sysctl_tcp_orphan_retries; /* May be zero. */
@@ -184,7 +184,7 @@ static int tcp_write_timeout(struct sock *sk)
retry_until = sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
- const int alive = icsk->icsk_rto < TCP_RTO_MAX;
+ const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
retry_until = tcp_orphan_retries(sk, alive);
do_reset = alive ||
@@ -298,7 +298,7 @@ static void tcp_probe_timer(struct sock *sk)
max_probes = sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
- const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
+ const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
max_probes = tcp_orphan_retries(sk, alive);
if (!alive && icsk->icsk_backoff >= max_probes)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 156ba75b6000..24ec14f9825c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -375,7 +375,8 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score += 4;
}
-
+ if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ score++;
return score;
}
@@ -419,6 +420,9 @@ static inline int compute_score2(struct sock *sk, struct net *net,
score += 4;
}
+ if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ score++;
+
return score;
}
@@ -1017,30 +1021,14 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl4 = &fl4_stack;
- /* unconnected socket. If output device is enslaved to a VRF
- * device lookup source address from VRF table. This mimics
- * behavior of ip_route_connect{_init}.
- */
- if (netif_index_is_l3_master(net, ipc.oif)) {
- flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
- RT_SCOPE_UNIVERSE, sk->sk_protocol,
- (flow_flags | FLOWI_FLAG_VRFSRC |
- FLOWI_FLAG_SKIP_NH_OIF),
- faddr, saddr, dport,
- inet->inet_sport);
-
- rt = ip_route_output_flow(net, fl4, sk);
- if (!IS_ERR(rt)) {
- saddr = fl4->saddr;
- ip_rt_put(rt);
- }
- }
-
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
faddr, saddr, dport, inet->inet_sport);
+ if (!saddr && ipc.oif)
+ l3mdev_get_saddr(net, ipc.oif, fl4);
+
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt)) {
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index cd6be736e19f..9f298d0dc9a1 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -87,17 +87,15 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
#ifdef CONFIG_NETFILTER
if (!x) {
IPCB(skb)->flags |= IPSKB_REROUTED;
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
#endif
return x->outer_mode->afinfo->output_finish(sk, skb);
}
-int xfrm4_output(struct sock *sk, struct sk_buff *skb)
+int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
-
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, skb, NULL, skb_dst(skb)->dev,
__xfrm4_output,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c8380f1876f1..f0326aae7a02 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -81,6 +81,7 @@
#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/l3mdev.h>
#include <linux/if_tunnel.h>
#include <linux/rtnetlink.h>
#include <linux/netconf.h>
@@ -2146,7 +2147,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_PREFIX,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
@@ -2179,8 +2180,9 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
+ u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX);
+ table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
return NULL;
@@ -2211,7 +2213,7 @@ out:
static void addrconf_add_mroute(struct net_device *dev)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_LOCAL,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_LOCAL,
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_dst_len = 8,
@@ -3029,6 +3031,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
{
struct in6_addr addr;
+ /* no link local addresses on L3 master devices */
+ if (netif_is_l3_master(idev->dev))
+ return;
+
ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 6c2b2132c8d3..efb1c00f2270 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -68,6 +68,7 @@
#include <net/xfrm.h>
#include <net/inet_common.h>
#include <net/dsfield.h>
+#include <net/l3mdev.h>
#include <asm/uaccess.h>
@@ -496,6 +497,9 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
+ if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = l3mdev_master_ifindex(skb->dev);
+
dst = icmpv6_route_lookup(net, skb, sk, &fl6);
if (IS_ERR(dst))
goto out;
@@ -575,7 +579,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.daddr = ipv6_hdr(skb)->saddr;
if (saddr)
fl6.saddr = *saddr;
- fl6.flowi6_oif = skb->dev->ifindex;
+ fl6.flowi6_oif = l3mdev_fib_oif(skb->dev);
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/ila.c b/net/ipv6/ila.c
index 678d2df4b8d9..1a6852e1ac69 100644
--- a/net/ipv6/ila.c
+++ b/net/ipv6/ila.c
@@ -91,7 +91,7 @@ static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
*(__be64 *)&ip6h->daddr = p->locator;
}
-static int ila_output(struct sock *sk, struct sk_buff *skb)
+static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -100,7 +100,7 @@ static int ila_output(struct sock *sk, struct sk_buff *skb)
update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
- return dst->lwtstate->orig_output(sk, skb);
+ return dst->lwtstate->orig_output(net, sk, skb);
drop:
kfree_skb(skb);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 6ac8dad0138a..21ace5a2bf7c 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -114,6 +114,8 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
+ if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ score++;
}
return score;
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7d2e0023c72d..09fddf70cca4 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -264,6 +264,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id)
return NULL;
}
+EXPORT_SYMBOL_GPL(fib6_get_table);
static void __net_init fib6_tables_init(struct net *net)
{
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a598fe2c0849..23f97c4783bb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -55,12 +55,12 @@
#include <net/xfrm.h>
#include <net/checksum.h>
#include <linux/mroute6.h>
+#include <net/l3mdev.h>
-static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
- struct net *net = dev_net(dev);
struct neighbour *neigh;
struct in6_addr *nexthop;
int ret;
@@ -126,16 +126,15 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
- return ip6_fragment(sk, skb, ip6_finish_output2);
+ return ip6_fragment(net, sk, skb, ip6_finish_output2);
else
- return ip6_finish_output2(sk, skb);
+ return ip6_finish_output2(net, sk, skb);
}
-int ip6_output(struct sock *sk, struct sk_buff *skb)
+int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
- struct net *net = dev_net(dev);
if (unlikely(idev->cnf.disable_ipv6)) {
IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
@@ -234,7 +233,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
*/
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, (struct sock *)sk, skb, NULL, dst->dev,
- dst_output_okfn);
+ dst_output);
}
skb->dev = dst->dev;
@@ -334,7 +333,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
skb_sender_cpu_clear(skb);
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
@@ -554,8 +553,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
skb_copy_secmark(to, from);
}
-int ip6_fragment(struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *))
+int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
@@ -568,7 +567,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
__be32 frag_id;
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
- struct net *net = dev_net(skb_dst(skb)->dev);
hlen = ip6_find_1stfragopt(skb, &prevhdr);
nexthdr = *prevhdr;
@@ -688,7 +686,7 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb,
ip6_copy_metadata(frag, skb);
}
- err = output(sk, skb);
+ err = output(net, sk, skb);
if (!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
@@ -816,7 +814,7 @@ slow_path:
/*
* Put this fragment into the sending queue.
*/
- err = output(sk, frag);
+ err = output(net, sk, frag);
if (err)
goto fail;
@@ -888,7 +886,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
#ifdef CONFIG_IPV6_SUBTREES
ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
#endif
- (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
+ (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) &&
+ (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) {
dst_release(dst);
dst = NULL;
}
@@ -1040,7 +1039,7 @@ struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
if (final_dst)
fl6->daddr = *final_dst;
if (!fl6->flowi6_oif)
- fl6->flowi6_oif = dst->dev->ifindex;
+ fl6->flowi6_oif = l3mdev_fib_oif(dst->dev);
return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
@@ -1694,7 +1693,7 @@ int ip6_send_skb(struct sk_buff *skb)
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
int err;
- err = ip6_local_out(skb);
+ err = ip6_local_out(net, skb->sk, skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index f96f1c19b4a8..0a8610b33d79 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -482,7 +482,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
return -EMSGSIZE;
}
- err = dst_output(skb->sk, skb);
+ err = dst_output(t->net, skb->sk, skb);
if (net_xmit_eval(err) == 0) {
struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 5e5d16e7ce85..ad19136086dd 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1991,7 +1991,7 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct
IPSTATS_MIB_OUTFORWDATAGRAMS);
IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUTOCTETS, skb->len);
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
/*
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index a8bf57ca74d3..124338a39e29 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1646,7 +1646,7 @@ static void mld_sendpack(struct sk_buff *skb)
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, net->ipv6.igmp_sk, skb, NULL, skb->dev,
- dst_output_okfn);
+ dst_output);
out:
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
@@ -2010,7 +2010,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
skb_dst_set(skb, dst);
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, skb->dev,
- dst_output_okfn);
+ dst_output);
out:
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index b9779d441b12..60c79a08e14a 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -118,7 +118,7 @@ static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb)
struct mip6_report_rate_limiter {
spinlock_t lock;
- struct timeval stamp;
+ ktime_t stamp;
int iif;
struct in6_addr src;
struct in6_addr dst;
@@ -184,20 +184,18 @@ static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb)
return 0;
}
-static inline int mip6_report_rl_allow(struct timeval *stamp,
+static inline int mip6_report_rl_allow(ktime_t stamp,
const struct in6_addr *dst,
const struct in6_addr *src, int iif)
{
int allow = 0;
spin_lock_bh(&mip6_report_rl.lock);
- if (mip6_report_rl.stamp.tv_sec != stamp->tv_sec ||
- mip6_report_rl.stamp.tv_usec != stamp->tv_usec ||
+ if (!ktime_equal(mip6_report_rl.stamp, stamp) ||
mip6_report_rl.iif != iif ||
!ipv6_addr_equal(&mip6_report_rl.src, src) ||
!ipv6_addr_equal(&mip6_report_rl.dst, dst)) {
- mip6_report_rl.stamp.tv_sec = stamp->tv_sec;
- mip6_report_rl.stamp.tv_usec = stamp->tv_usec;
+ mip6_report_rl.stamp = stamp;
mip6_report_rl.iif = iif;
mip6_report_rl.src = *src;
mip6_report_rl.dst = *dst;
@@ -216,7 +214,7 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
struct ipv6_destopt_hao *hao = NULL;
struct xfrm_selector sel;
int offset;
- struct timeval stamp;
+ ktime_t stamp;
int err = 0;
if (unlikely(fl6->flowi6_proto == IPPROTO_MH &&
@@ -230,9 +228,9 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
(skb_network_header(skb) + offset);
}
- skb_get_timestamp(skb, &stamp);
+ stamp = skb_get_ktime(skb);
- if (!mip6_report_rl_allow(&stamp, &ipv6_hdr(skb)->daddr,
+ if (!mip6_report_rl_allow(stamp, &ipv6_hdr(skb)->daddr,
hao ? &hao->addr : &ipv6_hdr(skb)->saddr,
opt->iif))
goto out;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 7089c305245c..3e0f855e1bea 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -67,6 +67,7 @@
#include <net/flow.h>
#include <net/ip6_checksum.h>
#include <net/inet_common.h>
+#include <net/l3mdev.h>
#include <linux/proc_fs.h>
#include <linux/netfilter.h>
@@ -147,6 +148,7 @@ struct neigh_table nd_tbl = {
.gc_thresh2 = 512,
.gc_thresh3 = 1024,
};
+EXPORT_SYMBOL_GPL(nd_tbl);
static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
{
@@ -441,8 +443,11 @@ static void ndisc_send_skb(struct sk_buff *skb,
if (!dst) {
struct flowi6 fl6;
+ int oif = l3mdev_fib_oif(skb->dev);
- icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex);
+ icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif);
+ if (oif != skb->dev->ifindex)
+ fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
dst = icmp6_dst_alloc(skb->dev, &fl6);
if (IS_ERR(dst)) {
kfree_skb(skb);
@@ -465,7 +470,7 @@ static void ndisc_send_skb(struct sk_buff *skb,
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, dst->dev,
- dst_output_okfn);
+ dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
@@ -766,7 +771,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
if (ifp) {
-
+have_ifp:
if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
if (dad) {
/*
@@ -792,6 +797,18 @@ static void ndisc_recv_ns(struct sk_buff *skb)
} else {
struct net *net = dev_net(dev);
+ /* perhaps an address on the master device */
+ if (netif_is_l3_slave(dev)) {
+ struct net_device *mdev;
+
+ mdev = netdev_master_upper_dev_get_rcu(dev);
+ if (mdev) {
+ ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1);
+ if (ifp)
+ goto have_ifp;
+ }
+ }
+
idev = in6_dev_get(dev);
if (!idev) {
/* XXX: count this drop? */
@@ -1483,6 +1500,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
struct flowi6 fl6;
int rd_len;
u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
+ int oif = l3mdev_fib_oif(dev);
bool ret;
if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
@@ -1499,7 +1517,10 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
}
icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT,
- &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex);
+ &saddr_buf, &ipv6_hdr(skb)->saddr, oif);
+
+ if (oif != skb->dev->ifindex)
+ fl6.flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 3426d9df1be7..3deed5860a42 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -76,7 +76,7 @@ synproxy_send_tcp(const struct synproxy_net *snet,
nf_conntrack_get(nfct);
}
- ip6_local_out(nskb);
+ ip6_local_out(net, nskb->sk, nskb);
return;
free_nskb:
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index deab0a1608d6..056f5d4a852a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -563,12 +563,10 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
return 0;
}
-struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
+struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
struct sk_buff *clone;
struct net_device *dev = skb->dev;
- struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev)
- : dev_net(skb->dev);
struct frag_hdr *fhdr;
struct frag_queue *fq;
struct ipv6hdr *hdr;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index b6ddca746109..4fdbed5ebfb6 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -63,7 +63,8 @@ static unsigned int ipv6_defrag(void *priv,
return NF_ACCEPT;
#endif
- reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(state->hook, skb));
+ reasm = nf_ct_frag6_gather(state->net, skb,
+ nf_ct6_defrag_user(state->hook, skb));
/* queued */
if (reasm == NULL)
return NF_STOLEN;
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index ee0d9a5b16c3..6989c70ae29f 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -68,7 +68,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
}
if (nf_dup_ipv6_route(net, skb, gw, oif)) {
__this_cpu_write(nf_skb_duplicated, true);
- ip6_local_out(skb);
+ ip6_local_out(net, skb->sk, skb);
__this_cpu_write(nf_skb_duplicated, false);
} else {
kfree_skb(skb);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 5629db84c047..e0f922b777e3 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -206,7 +206,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
dev_queue_xmit(nskb);
} else
#endif
- ip6_local_out(nskb);
+ ip6_local_out(net, nskb->sk, nskb);
}
EXPORT_SYMBOL_GPL(nf_send_reset6);
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index e77102c4f804..462f2a76b5c2 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -138,9 +138,8 @@ int ip6_dst_hoplimit(struct dst_entry *dst)
EXPORT_SYMBOL(ip6_dst_hoplimit);
#endif
-static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb)
+int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
int len;
len = skb->len - sizeof(struct ipv6hdr);
@@ -151,29 +150,18 @@ static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb)
return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, skb_dst(skb)->dev,
- dst_output_okfn);
-}
-
-int __ip6_local_out(struct sk_buff *skb)
-{
- return __ip6_local_out_sk(skb->sk, skb);
+ dst_output);
}
EXPORT_SYMBOL_GPL(__ip6_local_out);
-int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb)
+int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
int err;
- err = __ip6_local_out_sk(sk, skb);
+ err = __ip6_local_out(net, sk, skb);
if (likely(err == 1))
- err = dst_output(sk, skb);
+ err = dst_output(net, sk, skb);
return err;
}
-EXPORT_SYMBOL_GPL(ip6_local_out_sk);
-
-int ip6_local_out(struct sk_buff *skb)
-{
- return ip6_local_out_sk(skb->sk, skb);
-}
EXPORT_SYMBOL_GPL(ip6_local_out);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index fec0151522a2..dc65ec198f7c 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -655,7 +655,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
- NULL, rt->dst.dev, dst_output_okfn);
+ NULL, rt->dst.dev, dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d3d946773a3e..5fc1149fe91d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -61,6 +61,7 @@
#include <net/nexthop.h>
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>
+#include <net/l3mdev.h>
#include <asm/uaccess.h>
@@ -86,9 +87,9 @@ static void ip6_dst_ifdown(struct dst_entry *,
static int ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
-static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb);
+static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static int ip6_pkt_prohibit(struct sk_buff *skb);
-static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb);
+static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
@@ -308,7 +309,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -EINVAL,
.input = dst_discard,
- .output = dst_discard_sk,
+ .output = dst_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
.rt6i_protocol = RTPROT_KERNEL,
@@ -1044,6 +1045,9 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
+ if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+ oif = 0;
+
redo_rt6_select:
rt = rt6_select(fn, oif, strict);
if (rt->rt6i_nsiblings)
@@ -1141,7 +1145,7 @@ void ip6_route_input(struct sk_buff *skb)
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct ip_tunnel_info *tun_info;
struct flowi6 fl6 = {
- .flowi6_iif = skb->dev->ifindex,
+ .flowi6_iif = l3mdev_fib_oif(skb->dev),
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
@@ -1165,8 +1169,13 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
struct flowi6 *fl6)
{
+ struct dst_entry *dst;
int flags = 0;
+ dst = l3mdev_rt6_dst_by_oif(net, fl6);
+ if (dst)
+ return dst;
+
fl6->flowi6_iif = LOOPBACK_IFINDEX;
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
@@ -1195,7 +1204,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
new->__use = 1;
new->input = dst_discard;
- new->output = dst_discard_sk;
+ new->output = dst_discard_out;
if (dst_metrics_read_only(&ort->dst))
new->_metrics = ort->dst._metrics;
@@ -1724,21 +1733,21 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
return -EINVAL;
}
-int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
+static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
{
- int err;
struct net *net = cfg->fc_nlinfo.nl_net;
struct rt6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
struct fib6_table *table;
int addr_type;
+ int err = -EINVAL;
if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
- return -EINVAL;
+ goto out;
#ifndef CONFIG_IPV6_SUBTREES
if (cfg->fc_src_len)
- return -EINVAL;
+ goto out;
#endif
if (cfg->fc_ifindex) {
err = -ENODEV;
@@ -1853,7 +1862,7 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
switch (cfg->fc_type) {
case RTN_BLACKHOLE:
rt->dst.error = -EINVAL;
- rt->dst.output = dst_discard_sk;
+ rt->dst.output = dst_discard_out;
rt->dst.input = dst_discard;
break;
case RTN_PROHIBIT:
@@ -1958,9 +1967,7 @@ install_route:
cfg->fc_nlinfo.nl_net = dev_net(dev);
- *rt_ret = rt;
-
- return 0;
+ return rt;
out:
if (dev)
dev_put(dev);
@@ -1969,20 +1976,21 @@ out:
if (rt)
dst_free(&rt->dst);
- *rt_ret = NULL;
-
- return err;
+ return ERR_PTR(err);
}
int ip6_route_add(struct fib6_config *cfg)
{
struct mx6_config mxc = { .mx = NULL, };
- struct rt6_info *rt = NULL;
+ struct rt6_info *rt;
int err;
- err = ip6_route_info_create(cfg, &rt);
- if (err)
+ rt = ip6_route_info_create(cfg);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ rt = NULL;
goto out;
+ }
err = ip6_convert_metrics(&mxc, cfg);
if (err)
@@ -2264,7 +2272,6 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_INFO,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = ifindex,
.fc_dst_len = prefixlen,
@@ -2275,6 +2282,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
.fc_nlinfo.nl_net = net,
};
+ cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
@@ -2315,7 +2323,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_DFLT,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2362,7 +2370,8 @@ static void rtmsg_to_fib6_config(struct net *net,
{
memset(cfg, 0, sizeof(*cfg));
- cfg->fc_table = RT6_TABLE_MAIN;
+ cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
+ : RT6_TABLE_MAIN;
cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
cfg->fc_metric = rtmsg->rtmsg_metric;
cfg->fc_expires = rtmsg->rtmsg_info;
@@ -2446,7 +2455,7 @@ static int ip6_pkt_discard(struct sk_buff *skb)
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
}
-static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb)
+static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
@@ -2457,7 +2466,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb)
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
}
-static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb)
+static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
@@ -2471,6 +2480,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr,
bool anycast)
{
+ u32 tb_id;
struct net *net = dev_net(idev->dev);
struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
DST_NOCOUNT);
@@ -2493,7 +2503,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
- rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
+ tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
+ rt->rt6i_table = fib6_get_table(net, tb_id);
rt->dst.flags |= DST_NOCACHE;
atomic_set(&rt->dst.__refcnt, 1);
@@ -2871,9 +2882,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg)
r_cfg.fc_encap_type = nla_get_u16(nla);
}
- err = ip6_route_info_create(&r_cfg, &rt);
- if (err)
+ rt = ip6_route_info_create(&r_cfg);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ rt = NULL;
goto cleanup;
+ }
err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
if (err) {
@@ -3252,6 +3266,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
} else {
fl6.flowi6_oif = oif;
+ if (netif_index_is_l3_master(net, oif)) {
+ fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC |
+ FLOWI_FLAG_SKIP_NH_OIF;
+ }
+
rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7606eba83e7b..bb8f2fa1c7fb 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -170,7 +170,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
goto out;
ret = NULL;
- req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk);
+ req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk, false);
if (!req)
goto out;
@@ -235,9 +235,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
goto out_free;
}
- req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
+ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
- &req->rcv_wnd, &req->window_clamp,
+ &req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 33334f0c217d..acb06f86f372 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -931,7 +931,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
*/
tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
- tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
+ tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
0, 0);
@@ -1363,6 +1363,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
th = tcp_hdr(skb);
hdr = ipv6_hdr(skb);
+lookup:
sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest,
inet6_iif(skb));
if (!sk)
@@ -1382,8 +1383,12 @@ process:
reqsk_put(req);
goto discard_it;
}
- if (sk->sk_state == TCP_LISTEN)
+ if (likely(sk->sk_state == TCP_LISTEN)) {
nsk = tcp_check_req(sk, skb, req, false);
+ } else {
+ inet_csk_reqsk_queue_drop_and_put(sk, req);
+ goto lookup;
+ }
if (!nsk) {
reqsk_put(req);
goto discard_it;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0aba654f5b91..01bcb49619ee 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -182,10 +182,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
score++;
}
+ if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ score++;
+
return score;
}
-#define SCORE2_MAX (1 + 1 + 1)
static inline int compute_score2(struct sock *sk, struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr,
@@ -223,6 +225,9 @@ static inline int compute_score2(struct sock *sk, struct net *net,
score++;
}
+ if (sk->sk_incoming_cpu == raw_smp_processor_id())
+ score++;
+
return score;
}
@@ -251,8 +256,7 @@ begin:
hash = udp6_ehashfn(net, daddr, hnum,
saddr, sport);
matches = 1;
- } else if (score == SCORE2_MAX)
- goto exact_match;
+ }
} else if (score == badness && reuseport) {
matches++;
if (reciprocal_scale(hash, matches) == 0)
@@ -269,7 +273,6 @@ begin:
goto begin;
if (result) {
-exact_match:
if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
result = NULL;
else if (unlikely(compute_score2(result, net, saddr, sport,
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 0c3e9ffcf231..9db067a11b52 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -131,6 +131,13 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
return xfrm_output(sk, skb);
}
+static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct xfrm_state *x = skb_dst(skb)->xfrm;
+
+ return x->outer_mode->afinfo->output_finish(sk, skb);
+}
+
static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -140,7 +147,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
#ifdef CONFIG_NETFILTER
if (!x) {
IP6CB(skb)->flags |= IP6SKB_REROUTED;
- return dst_output(sk, skb);
+ return dst_output(net, sk, skb);
}
#endif
@@ -160,16 +167,14 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (x->props.mode == XFRM_MODE_TUNNEL &&
((skb->len > mtu && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)))) {
- return ip6_fragment(sk, skb,
- x->outer_mode->afinfo->output_finish);
+ return ip6_fragment(net, sk, skb,
+ __xfrm6_output_finish);
}
return x->outer_mode->afinfo->output_finish(sk, skb);
}
-int xfrm6_output(struct sock *sk, struct sk_buff *skb)
+int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
-
return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
net, sk, skb, NULL, skb_dst(skb)->dev,
__xfrm6_output,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 69cee4e0d728..08c9c93f3527 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -37,6 +37,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
+ fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index ddf75ad41713..8e5ead366e7f 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -26,11 +26,11 @@ int l3mdev_master_ifindex_rcu(struct net_device *dev)
if (netif_is_l3_master(dev)) {
ifindex = dev->ifindex;
- } else if (dev->flags & IFF_SLAVE) {
+ } else if (netif_is_l3_slave(dev)) {
struct net_device *master;
master = netdev_master_upper_dev_get_rcu(dev);
- if (master && netif_is_l3_master(master))
+ if (master)
ifindex = master->ifindex;
}
@@ -54,7 +54,7 @@ u32 l3mdev_fib_table_rcu(const struct net_device *dev)
if (netif_is_l3_master(dev)) {
if (dev->l3mdev_ops->l3mdev_fib_table)
tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev);
- } else if (dev->flags & IFF_SLAVE) {
+ } else if (netif_is_l3_slave(dev)) {
/* Users of netdev_master_upper_dev_get_rcu need non-const,
* but current inet_*type functions take a const
*/
@@ -62,7 +62,7 @@ u32 l3mdev_fib_table_rcu(const struct net_device *dev)
const struct net_device *master;
master = netdev_master_upper_dev_get_rcu(_dev);
- if (master && netif_is_l3_master(master) &&
+ if (master &&
master->l3mdev_ops->l3mdev_fib_table)
tb_id = master->l3mdev_ops->l3mdev_fib_table(master);
}
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 5c564a68fb50..10ad4ac1fa0b 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -79,7 +79,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
(int)reason);
if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP,
- &sta->sta, tid, NULL, 0))
+ &sta->sta, tid, NULL, 0, false))
sdata_info(sta->sdata,
"HW problem - can not stop rx aggregation for %pM tid %d\n",
sta->sta.addr, tid);
@@ -189,6 +189,7 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d
struct ieee80211_local *local = sdata->local;
struct sk_buff *skb;
struct ieee80211_mgmt *mgmt;
+ bool amsdu = ieee80211_hw_check(&local->hw, SUPPORTS_AMSDU_IN_AMPDU);
u16 capab;
skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom);
@@ -217,7 +218,8 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d
mgmt->u.action.u.addba_resp.action_code = WLAN_ACTION_ADDBA_RESP;
mgmt->u.action.u.addba_resp.dialog_token = dialog_token;
- capab = (u16)(policy << 1); /* bit 1 aggregation policy */
+ capab = (u16)(amsdu << 0); /* bit 0 A-MSDU support */
+ capab |= (u16)(policy << 1); /* bit 1 aggregation policy */
capab |= (u16)(tid << 2); /* bit 5:2 TID number */
capab |= (u16)(buf_size << 6); /* bit 15:6 max size of aggregation */
@@ -321,7 +323,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
__skb_queue_head_init(&tid_agg_rx->reorder_buf[i]);
ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START,
- &sta->sta, tid, &start_seq_num, 0);
+ &sta->sta, tid, &start_seq_num, 0, false);
ht_dbg(sta->sdata, "Rx A-MPDU request on %pM tid %d result %d\n",
sta->sta.addr, tid, ret);
if (ret) {
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index c8ba2e77737c..a758eb84e8f0 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -97,7 +97,8 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ;
mgmt->u.action.u.addba_req.dialog_token = dialog_token;
- capab = (u16)(1 << 1); /* bit 1 aggregation policy */
+ capab = (u16)(1 << 0); /* bit 0 A-MSDU support */
+ capab |= (u16)(1 << 1); /* bit 1 aggregation policy */
capab |= (u16)(tid << 2); /* bit 5:2 TID number */
capab |= (u16)(agg_size << 6); /* bit 15:6 max size of aggergation */
@@ -331,7 +332,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
return -EALREADY;
ret = drv_ampdu_action(local, sta->sdata,
IEEE80211_AMPDU_TX_STOP_FLUSH_CONT,
- &sta->sta, tid, NULL, 0);
+ &sta->sta, tid, NULL, 0, false);
WARN_ON_ONCE(ret);
return 0;
}
@@ -381,7 +382,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
tid_tx->tx_stop = reason == AGG_STOP_LOCAL_REQUEST;
ret = drv_ampdu_action(local, sta->sdata, action,
- &sta->sta, tid, NULL, 0);
+ &sta->sta, tid, NULL, 0, false);
/* HW shall not deny going back to legacy */
if (WARN_ON(ret)) {
@@ -469,7 +470,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
start_seq_num = sta->tid_seq[tid] >> 4;
ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START,
- &sta->sta, tid, &start_seq_num, 0);
+ &sta->sta, tid, &start_seq_num, 0, false);
if (ret) {
ht_dbg(sdata,
"BA request denied - HW unavailable for %pM tid %d\n",
@@ -693,7 +694,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
drv_ampdu_action(local, sta->sdata,
IEEE80211_AMPDU_TX_OPERATIONAL,
- &sta->sta, tid, NULL, tid_tx->buf_size);
+ &sta->sta, tid, NULL, tid_tx->buf_size,
+ tid_tx->amsdu);
/*
* synchronize with TX path, while splicing the TX path
@@ -918,8 +920,10 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
struct tid_ampdu_tx *tid_tx;
u16 capab, tid;
u8 buf_size;
+ bool amsdu;
capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab);
+ amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK;
tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6;
@@ -968,6 +972,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
}
tid_tx->buf_size = buf_size;
+ tid_tx->amsdu = amsdu;
if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state))
ieee80211_agg_tx_operational(local, sta, tid);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 7a77a1470f25..68e551e263c6 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -981,7 +981,7 @@ static int sta_apply_auth_flags(struct ieee80211_local *local,
* well. Some drivers require rate control initialized
* before drv_sta_state() is called.
*/
- if (test_sta_flag(sta, WLAN_STA_TDLS_PEER))
+ if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
rate_control_rate_init(sta);
ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
@@ -1120,8 +1120,11 @@ static int sta_apply_parameters(struct ieee80211_local *local,
local->hw.queues >= IEEE80211_NUM_ACS)
sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME);
- /* auth flags will be set later for TDLS stations */
- if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
+ /* auth flags will be set later for TDLS,
+ * and for unassociated stations that move to assocaited */
+ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
+ !((mask & BIT(NL80211_STA_FLAG_ASSOCIATED)) &&
+ (set & BIT(NL80211_STA_FLAG_ASSOCIATED)))) {
ret = sta_apply_auth_flags(local, sta, mask, set);
if (ret)
return ret;
@@ -1156,6 +1159,7 @@ static int sta_apply_parameters(struct ieee80211_local *local,
set_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH);
if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
+ !sdata->u.mgd.tdls_wider_bw_prohibited &&
ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) &&
params->ext_capab_len >= 8 &&
params->ext_capab[7] & WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED)
@@ -1212,7 +1216,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
sta_apply_mesh_params(local, sta, params);
/* set the STA state after all sta info from usermode has been set */
- if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
+ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) ||
+ set & BIT(NL80211_STA_FLAG_ASSOCIATED)) {
ret = sta_apply_auth_flags(local, sta, mask, set);
if (ret)
return ret;
@@ -1254,12 +1259,14 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
* defaults -- if userspace wants something else we'll
* change it accordingly in sta_apply_parameters()
*/
- if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) {
+ if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) &&
+ !(params->sta_flags_set & (BIT(NL80211_STA_FLAG_AUTHENTICATED) |
+ BIT(NL80211_STA_FLAG_ASSOCIATED)))) {
sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
- } else {
- sta->sta.tdls = true;
}
+ if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))
+ sta->sta.tdls = true;
err = sta_apply_parameters(local, sta, params);
if (err) {
@@ -1268,10 +1275,12 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
}
/*
- * for TDLS, rate control should be initialized only when
- * rates are known and station is marked authorized
+ * for TDLS and for unassociated station, rate control should be
+ * initialized only when rates are known and station is marked
+ * authorized/associated
*/
- if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER))
+ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
+ test_sta_flag(sta, WLAN_STA_ASSOC))
rate_control_rate_init(sta);
layer2_update = sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
@@ -1346,7 +1355,10 @@ static int ieee80211_change_station(struct wiphy *wiphy,
break;
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_AP_VLAN:
- statype = CFG80211_STA_AP_CLIENT;
+ if (test_sta_flag(sta, WLAN_STA_ASSOC))
+ statype = CFG80211_STA_AP_CLIENT;
+ else
+ statype = CFG80211_STA_AP_CLIENT_UNASSOC;
break;
default:
err = -EOPNOTSUPP;
@@ -3522,18 +3534,32 @@ static void ieee80211_mgmt_frame_register(struct wiphy *wiphy,
u16 frame_type, bool reg)
{
struct ieee80211_local *local = wiphy_priv(wiphy);
+ struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
switch (frame_type) {
case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ:
- if (reg)
+ if (reg) {
local->probe_req_reg++;
- else
- local->probe_req_reg--;
+ sdata->vif.probe_req_reg++;
+ } else {
+ if (local->probe_req_reg)
+ local->probe_req_reg--;
+
+ if (sdata->vif.probe_req_reg)
+ sdata->vif.probe_req_reg--;
+ }
if (!local->open_count)
break;
- ieee80211_queue_work(&local->hw, &local->reconfig_filter);
+ if (sdata->vif.probe_req_reg == 1)
+ drv_config_iface_filter(local, sdata, FIF_PROBE_REQ,
+ FIF_PROBE_REQ);
+ else if (sdata->vif.probe_req_reg == 0)
+ drv_config_iface_filter(local, sdata, 0,
+ FIF_PROBE_REQ);
+
+ ieee80211_configure_filter(local);
break;
default:
break;
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index ced6bf3be8d6..3636b45440ab 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -123,6 +123,8 @@ static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = {
FLAG(SUPPORTS_CLONED_SKBS),
FLAG(SINGLE_SCAN_ON_ALL_BANDS),
FLAG(TDLS_WIDER_BW),
+ FLAG(SUPPORTS_AMSDU_IN_AMPDU),
+ FLAG(BEACON_TX_STATUS),
/* keep last for the build bug below */
(void *)0x1
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 702ca122c498..7961e7d0b61e 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -2,6 +2,7 @@
* Copyright 2003-2005 Devicescape Software, Inc.
* Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (C) 2015 Intel Deutschland GmbH
*
* 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
@@ -34,6 +35,14 @@ static const struct file_operations key_ ##name## _ops = { \
.llseek = generic_file_llseek, \
}
+#define KEY_OPS_W(name) \
+static const struct file_operations key_ ##name## _ops = { \
+ .read = key_##name##_read, \
+ .write = key_##name##_write, \
+ .open = simple_open, \
+ .llseek = generic_file_llseek, \
+}
+
#define KEY_FILE(name, format) \
KEY_READ_##format(name) \
KEY_OPS(name)
@@ -74,6 +83,41 @@ static ssize_t key_algorithm_read(struct file *file,
}
KEY_OPS(algorithm);
+static ssize_t key_tx_spec_write(struct file *file, const char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ struct ieee80211_key *key = file->private_data;
+ u64 pn;
+ int ret;
+
+ switch (key->conf.cipher) {
+ case WLAN_CIPHER_SUITE_WEP40:
+ case WLAN_CIPHER_SUITE_WEP104:
+ return -EINVAL;
+ case WLAN_CIPHER_SUITE_TKIP:
+ /* not supported yet */
+ return -EOPNOTSUPP;
+ case WLAN_CIPHER_SUITE_CCMP:
+ case WLAN_CIPHER_SUITE_CCMP_256:
+ case WLAN_CIPHER_SUITE_AES_CMAC:
+ case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+ case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+ case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+ case WLAN_CIPHER_SUITE_GCMP:
+ case WLAN_CIPHER_SUITE_GCMP_256:
+ ret = kstrtou64_from_user(userbuf, count, 16, &pn);
+ if (ret)
+ return ret;
+ /* PN is a 48-bit counter */
+ if (pn >= (1ULL << 48))
+ return -ERANGE;
+ atomic64_set(&key->conf.tx_pn, pn);
+ return count;
+ default:
+ return 0;
+ }
+}
+
static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
{
@@ -110,7 +154,7 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
}
return simple_read_from_buffer(userbuf, count, ppos, buf, len);
}
-KEY_OPS(tx_spec);
+KEY_OPS_W(tx_spec);
static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
@@ -278,6 +322,9 @@ KEY_OPS(key);
#define DEBUGFS_ADD(name) \
debugfs_create_file(#name, 0400, key->debugfs.dir, \
key, &key_##name##_ops);
+#define DEBUGFS_ADD_W(name) \
+ debugfs_create_file(#name, 0600, key->debugfs.dir, \
+ key, &key_##name##_ops);
void ieee80211_debugfs_key_add(struct ieee80211_key *key)
{
@@ -310,7 +357,7 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key)
DEBUGFS_ADD(keyidx);
DEBUGFS_ADD(hw_key_idx);
DEBUGFS_ADD(algorithm);
- DEBUGFS_ADD(tx_spec);
+ DEBUGFS_ADD_W(tx_spec);
DEBUGFS_ADD(rx_spec);
DEBUGFS_ADD(replays);
DEBUGFS_ADD(icverrors);
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 1021e87c051f..37ea30e0754c 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -114,14 +114,6 @@ static ssize_t ieee80211_if_fmt_##name( \
return scnprintf(buf, buflen, "%pM\n", sdata->field); \
}
-#define IEEE80211_IF_FMT_DEC_DIV_16(name, field) \
-static ssize_t ieee80211_if_fmt_##name( \
- const struct ieee80211_sub_if_data *sdata, \
- char *buf, int buflen) \
-{ \
- return scnprintf(buf, buflen, "%d\n", sdata->field / 16); \
-}
-
#define IEEE80211_IF_FMT_JIFFIES_TO_MS(name, field) \
static ssize_t ieee80211_if_fmt_##name( \
const struct ieee80211_sub_if_data *sdata, \
@@ -247,8 +239,6 @@ IEEE80211_IF_FILE_R(hw_queues);
/* STA attributes */
IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC);
IEEE80211_IF_FILE(aid, u.mgd.aid, DEC);
-IEEE80211_IF_FILE(last_beacon, u.mgd.last_beacon_signal, DEC);
-IEEE80211_IF_FILE(ave_beacon, u.mgd.ave_beacon_signal, DEC_DIV_16);
IEEE80211_IF_FILE(beacon_timeout, u.mgd.beacon_timeout, JIFFIES_TO_MS);
static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata,
@@ -455,6 +445,34 @@ static ssize_t ieee80211_if_parse_uapsd_max_sp_len(
}
IEEE80211_IF_FILE_RW(uapsd_max_sp_len);
+static ssize_t ieee80211_if_fmt_tdls_wider_bw(
+ const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
+{
+ const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+ bool tdls_wider_bw;
+
+ tdls_wider_bw = ieee80211_hw_check(&sdata->local->hw, TDLS_WIDER_BW) &&
+ !ifmgd->tdls_wider_bw_prohibited;
+
+ return snprintf(buf, buflen, "%d\n", tdls_wider_bw);
+}
+
+static ssize_t ieee80211_if_parse_tdls_wider_bw(
+ struct ieee80211_sub_if_data *sdata, const char *buf, int buflen)
+{
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+ u8 val;
+ int ret;
+
+ ret = kstrtou8(buf, 0, &val);
+ if (ret)
+ return ret;
+
+ ifmgd->tdls_wider_bw_prohibited = !val;
+ return buflen;
+}
+IEEE80211_IF_FILE_RW(tdls_wider_bw);
+
/* AP attributes */
IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC);
IEEE80211_IF_FILE(num_sta_ps, u.ap.ps.num_sta_ps, ATOMIC);
@@ -606,14 +624,13 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata)
{
DEBUGFS_ADD(bssid);
DEBUGFS_ADD(aid);
- DEBUGFS_ADD(last_beacon);
- DEBUGFS_ADD(ave_beacon);
DEBUGFS_ADD(beacon_timeout);
DEBUGFS_ADD_MODE(smps, 0600);
DEBUGFS_ADD_MODE(tkip_mic_test, 0200);
DEBUGFS_ADD_MODE(beacon_loss, 0200);
DEBUGFS_ADD_MODE(uapsd_queues, 0600);
DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600);
+ DEBUGFS_ADD_MODE(tdls_wider_bw, 0600);
}
static void add_ap_files(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 267c3b1ca047..a1d54318f16c 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -8,6 +8,60 @@
#include "trace.h"
#include "driver-ops.h"
+int drv_add_interface(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
+{
+ int ret;
+
+ might_sleep();
+
+ if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+ (sdata->vif.type == NL80211_IFTYPE_MONITOR &&
+ !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
+ !(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))))
+ return -EINVAL;
+
+ trace_drv_add_interface(local, sdata);
+ ret = local->ops->add_interface(&local->hw, &sdata->vif);
+ trace_drv_return_int(local, ret);
+
+ if (ret == 0)
+ sdata->flags |= IEEE80211_SDATA_IN_DRIVER;
+
+ return ret;
+}
+
+int drv_change_interface(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ enum nl80211_iftype type, bool p2p)
+{
+ int ret;
+
+ might_sleep();
+
+ if (!check_sdata_in_driver(sdata))
+ return -EIO;
+
+ trace_drv_change_interface(local, sdata, type, p2p);
+ ret = local->ops->change_interface(&local->hw, &sdata->vif, type, p2p);
+ trace_drv_return_int(local, ret);
+ return ret;
+}
+
+void drv_remove_interface(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
+{
+ might_sleep();
+
+ if (!check_sdata_in_driver(sdata))
+ return;
+
+ trace_drv_remove_interface(local, sdata);
+ local->ops->remove_interface(&local->hw, &sdata->vif);
+ sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
+ trace_drv_return_void(local);
+}
+
__must_check
int drv_sta_state(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
@@ -39,3 +93,171 @@ int drv_sta_state(struct ieee80211_local *local,
trace_drv_return_int(local, ret);
return ret;
}
+
+void drv_sta_rc_update(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_sta *sta, u32 changed)
+{
+ sdata = get_bss_sdata(sdata);
+ if (!check_sdata_in_driver(sdata))
+ return;
+
+ WARN_ON(changed & IEEE80211_RC_SUPP_RATES_CHANGED &&
+ (sdata->vif.type != NL80211_IFTYPE_ADHOC &&
+ sdata->vif.type != NL80211_IFTYPE_MESH_POINT));
+
+ trace_drv_sta_rc_update(local, sdata, sta, changed);
+ if (local->ops->sta_rc_update)
+ local->ops->sta_rc_update(&local->hw, &sdata->vif,
+ sta, changed);
+
+ trace_drv_return_void(local);
+}
+
+int drv_conf_tx(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata, u16 ac,
+ const struct ieee80211_tx_queue_params *params)
+{
+ int ret = -EOPNOTSUPP;
+
+ might_sleep();
+
+ if (!check_sdata_in_driver(sdata))
+ return -EIO;
+
+ if (WARN_ONCE(params->cw_min == 0 ||
+ params->cw_min > params->cw_max,
+ "%s: invalid CW_min/CW_max: %d/%d\n",
+ sdata->name, params->cw_min, params->cw_max))
+ return -EINVAL;
+
+ trace_drv_conf_tx(local, sdata, ac, params);
+ if (local->ops->conf_tx)
+ ret = local->ops->conf_tx(&local->hw, &sdata->vif,
+ ac, params);
+ trace_drv_return_int(local, ret);
+ return ret;
+}
+
+u64 drv_get_tsf(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
+{
+ u64 ret = -1ULL;
+
+ might_sleep();
+
+ if (!check_sdata_in_driver(sdata))
+ return ret;
+
+ trace_drv_get_tsf(local, sdata);
+ if (local->ops->get_tsf)
+ ret = local->ops->get_tsf(&local->hw, &sdata->vif);
+ trace_drv_return_u64(local, ret);
+ return ret;
+}
+
+void drv_set_tsf(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ u64 tsf)
+{
+ might_sleep();
+
+ if (!check_sdata_in_driver(sdata))
+ return;
+
+ trace_drv_set_tsf(local, sdata, tsf);
+ if (local->ops->set_tsf)
+ local->ops->set_tsf(&local->hw, &sdata->vif, tsf);
+ trace_drv_return_void(local);
+}
+
+void drv_reset_tsf(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
+{
+ might_sleep();
+
+ if (!check_sdata_in_driver(sdata))
+ return;
+
+ trace_drv_reset_tsf(local, sdata);
+ if (local->ops->reset_tsf)
+ local->ops->reset_tsf(&local->hw, &sdata->vif);
+ trace_drv_return_void(local);
+}
+
+int drv_switch_vif_chanctx(struct ieee80211_local *local,
+ struct ieee80211_vif_chanctx_switch *vifs,
+ int n_vifs, enum ieee80211_chanctx_switch_mode mode)
+{
+ int ret = 0;
+ int i;
+
+ if (!local->ops->switch_vif_chanctx)
+ return -EOPNOTSUPP;
+
+ for (i = 0; i < n_vifs; i++) {
+ struct ieee80211_chanctx *new_ctx =
+ container_of(vifs[i].new_ctx,
+ struct ieee80211_chanctx,
+ conf);
+ struct ieee80211_chanctx *old_ctx =
+ container_of(vifs[i].old_ctx,
+ struct ieee80211_chanctx,
+ conf);
+
+ WARN_ON_ONCE(!old_ctx->driver_present);
+ WARN_ON_ONCE((mode == CHANCTX_SWMODE_SWAP_CONTEXTS &&
+ new_ctx->driver_present) ||
+ (mode == CHANCTX_SWMODE_REASSIGN_VIF &&
+ !new_ctx->driver_present));
+ }
+
+ trace_drv_switch_vif_chanctx(local, vifs, n_vifs, mode);
+ ret = local->ops->switch_vif_chanctx(&local->hw,
+ vifs, n_vifs, mode);
+ trace_drv_return_int(local, ret);
+
+ if (!ret && mode == CHANCTX_SWMODE_SWAP_CONTEXTS) {
+ for (i = 0; i < n_vifs; i++) {
+ struct ieee80211_chanctx *new_ctx =
+ container_of(vifs[i].new_ctx,
+ struct ieee80211_chanctx,
+ conf);
+ struct ieee80211_chanctx *old_ctx =
+ container_of(vifs[i].old_ctx,
+ struct ieee80211_chanctx,
+ conf);
+
+ new_ctx->driver_present = true;
+ old_ctx->driver_present = false;
+ }
+ }
+
+ return ret;
+}
+
+int drv_ampdu_action(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ enum ieee80211_ampdu_mlme_action action,
+ struct ieee80211_sta *sta, u16 tid,
+ u16 *ssn, u8 buf_size, bool amsdu)
+{
+ int ret = -EOPNOTSUPP;
+
+ might_sleep();
+
+ sdata = get_bss_sdata(sdata);
+ if (!check_sdata_in_driver(sdata))
+ return -EIO;
+
+ trace_drv_ampdu_action(local, sdata, action, sta, tid,
+ ssn, buf_size, amsdu);
+
+ if (local->ops->ampdu_action)
+ ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action,
+ sta, tid, ssn, buf_size, amsdu);
+
+ trace_drv_return_int(local, ret);
+
+ return ret;
+}
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 02d91332d7dd..30987099eb8f 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -137,59 +137,15 @@ static inline void drv_set_wakeup(struct ieee80211_local *local,
}
#endif
-static inline int drv_add_interface(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
-{
- int ret;
-
- might_sleep();
-
- if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
- (sdata->vif.type == NL80211_IFTYPE_MONITOR &&
- !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
- !(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))))
- return -EINVAL;
-
- trace_drv_add_interface(local, sdata);
- ret = local->ops->add_interface(&local->hw, &sdata->vif);
- trace_drv_return_int(local, ret);
-
- if (ret == 0)
- sdata->flags |= IEEE80211_SDATA_IN_DRIVER;
-
- return ret;
-}
-
-static inline int drv_change_interface(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata,
- enum nl80211_iftype type, bool p2p)
-{
- int ret;
+int drv_add_interface(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
- might_sleep();
-
- if (!check_sdata_in_driver(sdata))
- return -EIO;
-
- trace_drv_change_interface(local, sdata, type, p2p);
- ret = local->ops->change_interface(&local->hw, &sdata->vif, type, p2p);
- trace_drv_return_int(local, ret);
- return ret;
-}
-
-static inline void drv_remove_interface(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
-{
- might_sleep();
-
- if (!check_sdata_in_driver(sdata))
- return;
+int drv_change_interface(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ enum nl80211_iftype type, bool p2p);
- trace_drv_remove_interface(local, sdata);
- local->ops->remove_interface(&local->hw, &sdata->vif);
- sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
- trace_drv_return_void(local);
-}
+void drv_remove_interface(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
static inline int drv_config(struct ieee80211_local *local, u32 changed)
{
@@ -260,6 +216,22 @@ static inline void drv_configure_filter(struct ieee80211_local *local,
trace_drv_return_void(local);
}
+static inline void drv_config_iface_filter(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ unsigned int filter_flags,
+ unsigned int changed_flags)
+{
+ might_sleep();
+
+ trace_drv_config_iface_filter(local, sdata, filter_flags,
+ changed_flags);
+ if (local->ops->config_iface_filter)
+ local->ops->config_iface_filter(&local->hw, &sdata->vif,
+ filter_flags,
+ changed_flags);
+ trace_drv_return_void(local);
+}
+
static inline int drv_set_tim(struct ieee80211_local *local,
struct ieee80211_sta *sta, bool set)
{
@@ -580,25 +552,9 @@ int drv_sta_state(struct ieee80211_local *local,
enum ieee80211_sta_state old_state,
enum ieee80211_sta_state new_state);
-static inline void drv_sta_rc_update(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata,
- struct ieee80211_sta *sta, u32 changed)
-{
- sdata = get_bss_sdata(sdata);
- if (!check_sdata_in_driver(sdata))
- return;
-
- WARN_ON(changed & IEEE80211_RC_SUPP_RATES_CHANGED &&
- (sdata->vif.type != NL80211_IFTYPE_ADHOC &&
- sdata->vif.type != NL80211_IFTYPE_MESH_POINT));
-
- trace_drv_sta_rc_update(local, sdata, sta, changed);
- if (local->ops->sta_rc_update)
- local->ops->sta_rc_update(&local->hw, &sdata->vif,
- sta, changed);
-
- trace_drv_return_void(local);
-}
+void drv_sta_rc_update(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_sta *sta, u32 changed);
static inline void drv_sta_rate_tbl_update(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
@@ -630,76 +586,17 @@ static inline void drv_sta_statistics(struct ieee80211_local *local,
trace_drv_return_void(local);
}
-static inline int drv_conf_tx(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata, u16 ac,
- const struct ieee80211_tx_queue_params *params)
-{
- int ret = -EOPNOTSUPP;
-
- might_sleep();
-
- if (!check_sdata_in_driver(sdata))
- return -EIO;
-
- if (WARN_ONCE(params->cw_min == 0 ||
- params->cw_min > params->cw_max,
- "%s: invalid CW_min/CW_max: %d/%d\n",
- sdata->name, params->cw_min, params->cw_max))
- return -EINVAL;
-
- trace_drv_conf_tx(local, sdata, ac, params);
- if (local->ops->conf_tx)
- ret = local->ops->conf_tx(&local->hw, &sdata->vif,
- ac, params);
- trace_drv_return_int(local, ret);
- return ret;
-}
-
-static inline u64 drv_get_tsf(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
-{
- u64 ret = -1ULL;
-
- might_sleep();
-
- if (!check_sdata_in_driver(sdata))
- return ret;
-
- trace_drv_get_tsf(local, sdata);
- if (local->ops->get_tsf)
- ret = local->ops->get_tsf(&local->hw, &sdata->vif);
- trace_drv_return_u64(local, ret);
- return ret;
-}
-
-static inline void drv_set_tsf(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata,
- u64 tsf)
-{
- might_sleep();
-
- if (!check_sdata_in_driver(sdata))
- return;
-
- trace_drv_set_tsf(local, sdata, tsf);
- if (local->ops->set_tsf)
- local->ops->set_tsf(&local->hw, &sdata->vif, tsf);
- trace_drv_return_void(local);
-}
-
-static inline void drv_reset_tsf(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
-{
- might_sleep();
+int drv_conf_tx(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata, u16 ac,
+ const struct ieee80211_tx_queue_params *params);
- if (!check_sdata_in_driver(sdata))
- return;
-
- trace_drv_reset_tsf(local, sdata);
- if (local->ops->reset_tsf)
- local->ops->reset_tsf(&local->hw, &sdata->vif);
- trace_drv_return_void(local);
-}
+u64 drv_get_tsf(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
+void drv_set_tsf(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ u64 tsf);
+void drv_reset_tsf(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
static inline int drv_tx_last_beacon(struct ieee80211_local *local)
{
@@ -714,30 +611,11 @@ static inline int drv_tx_last_beacon(struct ieee80211_local *local)
return ret;
}
-static inline int drv_ampdu_action(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata,
- enum ieee80211_ampdu_mlme_action action,
- struct ieee80211_sta *sta, u16 tid,
- u16 *ssn, u8 buf_size)
-{
- int ret = -EOPNOTSUPP;
-
- might_sleep();
-
- sdata = get_bss_sdata(sdata);
- if (!check_sdata_in_driver(sdata))
- return -EIO;
-
- trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size);
-
- if (local->ops->ampdu_action)
- ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action,
- sta, tid, ssn, buf_size);
-
- trace_drv_return_int(local, ret);
-
- return ret;
-}
+int drv_ampdu_action(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ enum ieee80211_ampdu_mlme_action action,
+ struct ieee80211_sta *sta, u16 tid,
+ u16 *ssn, u8 buf_size, bool amsdu);
static inline int drv_get_survey(struct ieee80211_local *local, int idx,
struct survey_info *survey)
@@ -1066,58 +944,9 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
trace_drv_return_void(local);
}
-static inline int
-drv_switch_vif_chanctx(struct ieee80211_local *local,
- struct ieee80211_vif_chanctx_switch *vifs,
- int n_vifs,
- enum ieee80211_chanctx_switch_mode mode)
-{
- int ret = 0;
- int i;
-
- if (!local->ops->switch_vif_chanctx)
- return -EOPNOTSUPP;
-
- for (i = 0; i < n_vifs; i++) {
- struct ieee80211_chanctx *new_ctx =
- container_of(vifs[i].new_ctx,
- struct ieee80211_chanctx,
- conf);
- struct ieee80211_chanctx *old_ctx =
- container_of(vifs[i].old_ctx,
- struct ieee80211_chanctx,
- conf);
-
- WARN_ON_ONCE(!old_ctx->driver_present);
- WARN_ON_ONCE((mode == CHANCTX_SWMODE_SWAP_CONTEXTS &&
- new_ctx->driver_present) ||
- (mode == CHANCTX_SWMODE_REASSIGN_VIF &&
- !new_ctx->driver_present));
- }
-
- trace_drv_switch_vif_chanctx(local, vifs, n_vifs, mode);
- ret = local->ops->switch_vif_chanctx(&local->hw,
- vifs, n_vifs, mode);
- trace_drv_return_int(local, ret);
-
- if (!ret && mode == CHANCTX_SWMODE_SWAP_CONTEXTS) {
- for (i = 0; i < n_vifs; i++) {
- struct ieee80211_chanctx *new_ctx =
- container_of(vifs[i].new_ctx,
- struct ieee80211_chanctx,
- conf);
- struct ieee80211_chanctx *old_ctx =
- container_of(vifs[i].old_ctx,
- struct ieee80211_chanctx,
- conf);
-
- new_ctx->driver_present = true;
- old_ctx->driver_present = false;
- }
- }
-
- return ret;
-}
+int drv_switch_vif_chanctx(struct ieee80211_local *local,
+ struct ieee80211_vif_chanctx_switch *vifs,
+ int n_vifs, enum ieee80211_chanctx_switch_mode mode);
static inline int drv_start_ap(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 6e52659f923f..f9605f13def9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -419,6 +419,8 @@ struct ieee80211_sta_tx_tspec {
bool downgraded;
};
+DECLARE_EWMA(beacon_signal, 16, 4)
+
struct ieee80211_if_managed {
struct timer_list timer;
struct timer_list conn_mon_timer;
@@ -490,16 +492,7 @@ struct ieee80211_if_managed {
s16 p2p_noa_index;
- /* Signal strength from the last Beacon frame in the current BSS. */
- int last_beacon_signal;
-
- /*
- * Weighted average of the signal strength from Beacon frames in the
- * current BSS. This is in units of 1/16 of the signal unit to maintain
- * accuracy and to speed up calculations, i.e., the value need to be
- * divided by 16 to get the actual value.
- */
- int ave_beacon_signal;
+ struct ewma_beacon_signal ave_beacon_signal;
/*
* Number of Beacon frames used in ave_beacon_signal. This can be used
@@ -535,6 +528,7 @@ struct ieee80211_if_managed {
struct sk_buff *teardown_skb; /* A copy to send through the AP */
spinlock_t teardown_lock; /* To lock changing teardown_skb */
bool tdls_chan_switch_prohibited;
+ bool tdls_wider_bw_prohibited;
/* WMM-AC TSPEC support */
struct ieee80211_sta_tx_tspec tx_tspec[IEEE80211_NUM_ACS];
@@ -1641,6 +1635,9 @@ void ieee80211_purge_tx_queue(struct ieee80211_hw *hw,
struct sk_buff *
ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb, u32 info_flags);
+void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
+ struct ieee80211_supported_band *sband,
+ int retry_count, int shift, bool send_to_cooked);
void ieee80211_check_fast_xmit(struct sta_info *sta);
void ieee80211_check_fast_xmit_all(struct ieee80211_local *local);
@@ -1853,7 +1850,7 @@ void ieee80211_dynamic_ps_disable_work(struct work_struct *work);
void ieee80211_dynamic_ps_timer(unsigned long data);
void ieee80211_send_nullfunc(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
- int powersave);
+ bool powersave);
void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata,
struct ieee80211_hdr *hdr);
void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 6964fc6a8ea2..42d7f0f65bd6 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1204,7 +1204,7 @@ static void ieee80211_iface_work(struct work_struct *work)
if (!ieee80211_sdata_running(sdata))
return;
- if (local->scanning)
+ if (test_bit(SCAN_SW_SCANNING, &local->scanning))
return;
if (!ieee80211_can_run_worker(local))
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index ff79a13d231d..9b813a2f3a75 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -543,7 +543,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
NL80211_FEATURE_HT_IBSS |
NL80211_FEATURE_VIF_TXPOWER |
NL80211_FEATURE_MAC_ON_CREATE |
- NL80211_FEATURE_USERSPACE_MPM;
+ NL80211_FEATURE_USERSPACE_MPM |
+ NL80211_FEATURE_FULL_AP_CLIENT_STATE;
if (!ops->hw_scan)
wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index e06a5ca7c9a9..626e8de70842 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -94,6 +94,9 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
ieee80211_ht_oper_to_chandef(sdata->vif.bss_conf.chandef.chan,
ie->ht_operation, &sta_chan_def);
+ ieee80211_vht_oper_to_chandef(sdata->vif.bss_conf.chandef.chan,
+ ie->vht_operation, &sta_chan_def);
+
if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chandef,
&sta_chan_def))
return false;
@@ -436,8 +439,6 @@ int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_chanctx_conf *chanctx_conf;
struct ieee80211_channel *channel;
- enum nl80211_channel_type channel_type =
- cfg80211_get_chandef_type(&sdata->vif.bss_conf.chandef);
struct ieee80211_supported_band *sband;
struct ieee80211_sta_ht_cap *ht_cap;
u8 *pos;
@@ -454,7 +455,10 @@ int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata,
sband = local->hw.wiphy->bands[channel->band];
ht_cap = &sband->ht_cap;
- if (!ht_cap->ht_supported || channel_type == NL80211_CHAN_NO_HT)
+ if (!ht_cap->ht_supported ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
return 0;
if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_operation))
@@ -467,6 +471,68 @@ int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata,
return 0;
}
+int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata,
+ struct sk_buff *skb)
+{
+ struct ieee80211_local *local = sdata->local;
+ enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
+ struct ieee80211_supported_band *sband;
+ u8 *pos;
+
+ sband = local->hw.wiphy->bands[band];
+ if (!sband->vht_cap.vht_supported ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
+ return 0;
+
+ if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_vht_cap))
+ return -ENOMEM;
+
+ pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_cap));
+ ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, sband->vht_cap.cap);
+
+ return 0;
+}
+
+int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata,
+ struct sk_buff *skb)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct ieee80211_chanctx_conf *chanctx_conf;
+ struct ieee80211_channel *channel;
+ struct ieee80211_supported_band *sband;
+ struct ieee80211_sta_vht_cap *vht_cap;
+ u8 *pos;
+
+ rcu_read_lock();
+ chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
+ if (WARN_ON(!chanctx_conf)) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+ channel = chanctx_conf->def.chan;
+ rcu_read_unlock();
+
+ sband = local->hw.wiphy->bands[channel->band];
+ vht_cap = &sband->vht_cap;
+
+ if (!vht_cap->vht_supported ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
+ return 0;
+
+ if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_vht_operation))
+ return -ENOMEM;
+
+ pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_operation));
+ ieee80211_ie_build_vht_oper(pos, vht_cap,
+ &sdata->vif.bss_conf.chandef);
+
+ return 0;
+}
+
static void ieee80211_mesh_path_timer(unsigned long data)
{
struct ieee80211_sub_if_data *sdata =
@@ -540,9 +606,9 @@ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc,
*
* Return the header length.
*/
-int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata,
- struct ieee80211s_hdr *meshhdr,
- const char *addr4or5, const char *addr6)
+unsigned int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211s_hdr *meshhdr,
+ const char *addr4or5, const char *addr6)
{
if (WARN_ON(!addr4or5 && addr6))
return 0;
@@ -637,6 +703,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
2 + ifmsh->mesh_id_len +
2 + sizeof(struct ieee80211_meshconf_ie) +
2 + sizeof(__le16) + /* awake window */
+ 2 + sizeof(struct ieee80211_vht_cap) +
+ 2 + sizeof(struct ieee80211_vht_operation) +
ifmsh->ie_len;
bcn = kzalloc(sizeof(*bcn) + head_len + tail_len, GFP_KERNEL);
@@ -718,6 +786,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
mesh_add_meshid_ie(sdata, skb) ||
mesh_add_meshconf_ie(sdata, skb) ||
mesh_add_awake_window_ie(sdata, skb) ||
+ mesh_add_vht_cap_ie(sdata, skb) ||
+ mesh_add_vht_oper_ie(sdata, skb) ||
mesh_add_vendor_ies(sdata, skb))
goto out_free;
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 50c8473cf9dc..a1596344c3ba 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -207,9 +207,9 @@ struct mesh_rmc {
/* Various */
int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc,
const u8 *da, const u8 *sa);
-int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata,
- struct ieee80211s_hdr *meshhdr,
- const char *addr4or5, const char *addr6);
+unsigned int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211s_hdr *meshhdr,
+ const char *addr4or5, const char *addr6);
int mesh_rmc_check(struct ieee80211_sub_if_data *sdata,
const u8 *addr, struct ieee80211s_hdr *mesh_hdr);
bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
@@ -227,6 +227,10 @@ int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
+int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata,
+ struct sk_buff *skb);
+int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata,
+ struct sk_buff *skb);
void mesh_rmc_free(struct ieee80211_sub_if_data *sdata);
int mesh_rmc_init(struct ieee80211_sub_if_data *sdata);
void ieee80211s_init(void);
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 58384642e03c..a360b24b7df8 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -226,6 +226,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata,
2 + sizeof(struct ieee80211_meshconf_ie) +
2 + sizeof(struct ieee80211_ht_cap) +
2 + sizeof(struct ieee80211_ht_operation) +
+ 2 + sizeof(struct ieee80211_vht_cap) +
+ 2 + sizeof(struct ieee80211_vht_operation) +
2 + 8 + /* peering IE */
sdata->u.mesh.ie_len);
if (!skb)
@@ -306,7 +308,9 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata,
if (action != WLAN_SP_MESH_PEERING_CLOSE) {
if (mesh_add_ht_cap_ie(sdata, skb) ||
- mesh_add_ht_oper_ie(sdata, skb))
+ mesh_add_ht_oper_ie(sdata, skb) ||
+ mesh_add_vht_cap_ie(sdata, skb) ||
+ mesh_add_vht_oper_ie(sdata, skb))
goto free;
}
@@ -402,6 +406,9 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata,
elems->ht_cap_elem, sta))
changed |= IEEE80211_RC_BW_CHANGED;
+ ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
+ elems->vht_cap_elem, sta);
+
if (bw != sta->sta.bandwidth)
changed |= IEEE80211_RC_BW_CHANGED;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index cd7e55e08a23..56ef9a8e151c 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -82,13 +82,6 @@ MODULE_PARM_DESC(probe_wait_ms,
" before disconnecting (reason 4).");
/*
- * Weight given to the latest Beacon frame when calculating average signal
- * strength for Beacon frames received in the current BSS. This must be
- * between 1 and 15.
- */
-#define IEEE80211_SIGNAL_AVE_WEIGHT 3
-
-/*
* How many Beacon frames need to have been used in average signal strength
* before starting to indicate signal change events.
*/
@@ -943,7 +936,7 @@ void ieee80211_send_pspoll(struct ieee80211_local *local,
void ieee80211_send_nullfunc(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
- int powersave)
+ bool powersave)
{
struct sk_buff *skb;
struct ieee80211_hdr_3addr *nullfunc;
@@ -1427,7 +1420,7 @@ static void ieee80211_enable_ps(struct ieee80211_local *local,
msecs_to_jiffies(conf->dynamic_ps_timeout));
} else {
if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK))
- ieee80211_send_nullfunc(local, sdata, 1);
+ ieee80211_send_nullfunc(local, sdata, true);
if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK) &&
ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
@@ -1642,7 +1635,7 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work)
msecs_to_jiffies(
local->hw.conf.dynamic_ps_timeout));
} else {
- ieee80211_send_nullfunc(local, sdata, 1);
+ ieee80211_send_nullfunc(local, sdata, true);
/* Flush to get the tx status of nullfunc frame */
ieee80211_flush_queues(local, sdata, false);
}
@@ -2275,7 +2268,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) {
ifmgd->nullfunc_failed = false;
- ieee80211_send_nullfunc(sdata->local, sdata, 0);
+ ieee80211_send_nullfunc(sdata->local, sdata, false);
} else {
int ssid_len;
@@ -3262,16 +3255,6 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata,
if (ifmgd->associated &&
ether_addr_equal(mgmt->bssid, ifmgd->associated->bssid))
ieee80211_reset_ap_probe(sdata);
-
- if (ifmgd->auth_data && !ifmgd->auth_data->bss->proberesp_ies &&
- ether_addr_equal(mgmt->bssid, ifmgd->auth_data->bss->bssid)) {
- /* got probe response, continue with auth */
- sdata_info(sdata, "direct probe responded\n");
- ifmgd->auth_data->tries = 0;
- ifmgd->auth_data->timeout = jiffies;
- ifmgd->auth_data->timeout_started = true;
- run_again(sdata, ifmgd->auth_data->timeout);
- }
}
/*
@@ -3374,24 +3357,21 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
bssid = ifmgd->associated->bssid;
/* Track average RSSI from the Beacon frames of the current AP */
- ifmgd->last_beacon_signal = rx_status->signal;
if (ifmgd->flags & IEEE80211_STA_RESET_SIGNAL_AVE) {
ifmgd->flags &= ~IEEE80211_STA_RESET_SIGNAL_AVE;
- ifmgd->ave_beacon_signal = rx_status->signal * 16;
+ ewma_beacon_signal_init(&ifmgd->ave_beacon_signal);
ifmgd->last_cqm_event_signal = 0;
ifmgd->count_beacon_signal = 1;
ifmgd->last_ave_beacon_signal = 0;
} else {
- ifmgd->ave_beacon_signal =
- (IEEE80211_SIGNAL_AVE_WEIGHT * rx_status->signal * 16 +
- (16 - IEEE80211_SIGNAL_AVE_WEIGHT) *
- ifmgd->ave_beacon_signal) / 16;
ifmgd->count_beacon_signal++;
}
+ ewma_beacon_signal_add(&ifmgd->ave_beacon_signal, -rx_status->signal);
+
if (ifmgd->rssi_min_thold != ifmgd->rssi_max_thold &&
ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT) {
- int sig = ifmgd->ave_beacon_signal;
+ int sig = -ewma_beacon_signal_read(&ifmgd->ave_beacon_signal);
int last_sig = ifmgd->last_ave_beacon_signal;
struct ieee80211_event event = {
.type = RSSI_EVENT,
@@ -3418,10 +3398,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
if (bss_conf->cqm_rssi_thold &&
ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT &&
!(sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) {
- int sig = ifmgd->ave_beacon_signal / 16;
+ int sig = -ewma_beacon_signal_read(&ifmgd->ave_beacon_signal);
int last_event = ifmgd->last_cqm_event_signal;
int thold = bss_conf->cqm_rssi_thold;
int hyst = bss_conf->cqm_rssi_hyst;
+
if (sig < thold &&
(last_event == 0 || sig < last_event - hyst)) {
ifmgd->last_cqm_event_signal = sig;
@@ -3456,31 +3437,27 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
len - baselen, false, &elems,
care_about_ies, ncrc);
- if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK)) {
- bool directed_tim = ieee80211_check_tim(elems.tim,
- elems.tim_len,
- ifmgd->aid);
- if (directed_tim) {
- if (local->hw.conf.dynamic_ps_timeout > 0) {
- if (local->hw.conf.flags & IEEE80211_CONF_PS) {
- local->hw.conf.flags &= ~IEEE80211_CONF_PS;
- ieee80211_hw_config(local,
- IEEE80211_CONF_CHANGE_PS);
- }
- ieee80211_send_nullfunc(local, sdata, 0);
- } else if (!local->pspolling && sdata->u.mgd.powersave) {
- local->pspolling = true;
-
- /*
- * Here is assumed that the driver will be
- * able to send ps-poll frame and receive a
- * response even though power save mode is
- * enabled, but some drivers might require
- * to disable power save here. This needs
- * to be investigated.
- */
- ieee80211_send_pspoll(local, sdata);
+ if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK) &&
+ ieee80211_check_tim(elems.tim, elems.tim_len, ifmgd->aid)) {
+ if (local->hw.conf.dynamic_ps_timeout > 0) {
+ if (local->hw.conf.flags & IEEE80211_CONF_PS) {
+ local->hw.conf.flags &= ~IEEE80211_CONF_PS;
+ ieee80211_hw_config(local,
+ IEEE80211_CONF_CHANGE_PS);
}
+ ieee80211_send_nullfunc(local, sdata, false);
+ } else if (!local->pspolling && sdata->u.mgd.powersave) {
+ local->pspolling = true;
+
+ /*
+ * Here is assumed that the driver will be
+ * able to send ps-poll frame and receive a
+ * response even though power save mode is
+ * enabled, but some drivers might require
+ * to disable power save here. This needs
+ * to be investigated.
+ */
+ ieee80211_send_pspoll(local, sdata);
}
}
@@ -3717,12 +3694,14 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata,
reason);
}
-static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
+static int ieee80211_auth(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_mgd_auth_data *auth_data = ifmgd->auth_data;
u32 tx_flags = 0;
+ u16 trans = 1;
+ u16 status = 0;
sdata_assert_lock(sdata);
@@ -3746,54 +3725,27 @@ static int ieee80211_probe_auth(struct ieee80211_sub_if_data *sdata)
drv_mgd_prepare_tx(local, sdata);
- if (auth_data->bss->proberesp_ies) {
- u16 trans = 1;
- u16 status = 0;
-
- sdata_info(sdata, "send auth to %pM (try %d/%d)\n",
- auth_data->bss->bssid, auth_data->tries,
- IEEE80211_AUTH_MAX_TRIES);
+ sdata_info(sdata, "send auth to %pM (try %d/%d)\n",
+ auth_data->bss->bssid, auth_data->tries,
+ IEEE80211_AUTH_MAX_TRIES);
- auth_data->expected_transaction = 2;
+ auth_data->expected_transaction = 2;
- if (auth_data->algorithm == WLAN_AUTH_SAE) {
- trans = auth_data->sae_trans;
- status = auth_data->sae_status;
- auth_data->expected_transaction = trans;
- }
-
- if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
- tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
- IEEE80211_TX_INTFL_MLME_CONN_TX;
-
- ieee80211_send_auth(sdata, trans, auth_data->algorithm, status,
- auth_data->data, auth_data->data_len,
- auth_data->bss->bssid,
- auth_data->bss->bssid, NULL, 0, 0,
- tx_flags);
- } else {
- const u8 *ssidie;
+ if (auth_data->algorithm == WLAN_AUTH_SAE) {
+ trans = auth_data->sae_trans;
+ status = auth_data->sae_status;
+ auth_data->expected_transaction = trans;
+ }
- sdata_info(sdata, "direct probe to %pM (try %d/%i)\n",
- auth_data->bss->bssid, auth_data->tries,
- IEEE80211_AUTH_MAX_TRIES);
+ if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
+ tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS |
+ IEEE80211_TX_INTFL_MLME_CONN_TX;
- rcu_read_lock();
- ssidie = ieee80211_bss_get_ie(auth_data->bss, WLAN_EID_SSID);
- if (!ssidie) {
- rcu_read_unlock();
- return -EINVAL;
- }
- /*
- * Direct probe is sent to broadcast address as some APs
- * will not answer to direct packet in unassociated state.
- */
- ieee80211_send_probe_req(sdata, sdata->vif.addr, NULL,
- ssidie + 2, ssidie[1],
- NULL, 0, (u32) -1, true, 0,
- auth_data->bss->channel, false);
- rcu_read_unlock();
- }
+ ieee80211_send_auth(sdata, trans, auth_data->algorithm, status,
+ auth_data->data, auth_data->data_len,
+ auth_data->bss->bssid,
+ auth_data->bss->bssid, NULL, 0, 0,
+ tx_flags);
if (tx_flags == 0) {
auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
@@ -3874,8 +3826,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
bool status_acked = ifmgd->status_acked;
ifmgd->status_received = false;
- if (ifmgd->auth_data &&
- (ieee80211_is_probe_req(fc) || ieee80211_is_auth(fc))) {
+ if (ifmgd->auth_data && ieee80211_is_auth(fc)) {
if (status_acked) {
ifmgd->auth_data->timeout =
jiffies + IEEE80211_AUTH_TIMEOUT_SHORT;
@@ -3906,7 +3857,7 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
* so let's just kill the auth data
*/
ieee80211_destroy_auth_data(sdata, false);
- } else if (ieee80211_probe_auth(sdata)) {
+ } else if (ieee80211_auth(sdata)) {
u8 bssid[ETH_ALEN];
struct ieee80211_event event = {
.type = MLME_EVENT,
@@ -4613,7 +4564,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
if (err)
goto err_clear;
- err = ieee80211_probe_auth(sdata);
+ err = ieee80211_auth(sdata);
if (err) {
sta_info_destroy_addr(sdata, req->bss->bssid);
goto err_clear;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index f2c75cf491fc..04401037140e 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -57,7 +57,7 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
* to send a new nullfunc frame to inform the AP that we
* are again sleeping.
*/
- ieee80211_send_nullfunc(local, sdata, 1);
+ ieee80211_send_nullfunc(local, sdata, true);
}
/* inform AP that we are awake again, unless power save is enabled */
@@ -66,7 +66,7 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata)
struct ieee80211_local *local = sdata->local;
if (!local->ps_sdata)
- ieee80211_send_nullfunc(local, sdata, 0);
+ ieee80211_send_nullfunc(local, sdata, false);
else if (local->offchannel_ps_enabled) {
/*
* In !IEEE80211_HW_PS_NULLFUNC_STACK case the hardware
@@ -93,7 +93,7 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata)
* restart the timer now and send a nullfunc frame to inform
* the AP that we are awake.
*/
- ieee80211_send_nullfunc(local, sdata, 0);
+ ieee80211_send_nullfunc(local, sdata, false);
mod_timer(&local->dynamic_ps_timer, jiffies +
msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout));
}
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index b676b9fa707b..ad88ad4e8eb1 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -23,7 +23,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
ieee80211_del_virtual_monitor(local);
- if (ieee80211_hw_check(hw, AMPDU_AGGREGATION)) {
+ if (ieee80211_hw_check(hw, AMPDU_AGGREGATION) &&
+ !(wowlan && wowlan->any)) {
mutex_lock(&local->sta_mtx);
list_for_each_entry(sta, &local->sta_list, list) {
set_sta_flag(sta, WLAN_STA_BLOCK_BA);
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 9ce8883d5f44..b07e2f748f93 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -305,7 +305,10 @@ static void __rate_control_send_low(struct ieee80211_hw *hw,
info->control.rates[0].idx = i;
break;
}
- WARN_ON_ONCE(i == sband->n_bitrates);
+ WARN_ONCE(i == sband->n_bitrates,
+ "no supported rates (0x%x) in rate_mask 0x%x with flags 0x%x\n",
+ sta ? sta->supp_rates[sband->band] : 0,
+ rate_mask, rate_flags);
info->control.rates[0].count =
(info->flags & IEEE80211_TX_CTL_NO_ACK) ?
diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c
index 1db5f7c3318a..820b0abc9c0d 100644
--- a/net/mac80211/rc80211_minstrel_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_debugfs.c
@@ -85,12 +85,10 @@ minstrel_stats_open(struct inode *inode, struct file *file)
file->private_data = ms;
p = ms->buf;
p += sprintf(p, "\n");
- p += sprintf(p, "best __________rate_________ ______"
- "statistics______ ________last_______ "
- "______sum-of________\n");
- p += sprintf(p, "rate [name idx airtime max_tp] [ ø(tp) ø(prob) "
- "sd(prob)] [prob.|retry|suc|att] "
- "[#success | #attempts]\n");
+ p += sprintf(p,
+ "best __________rate_________ ________statistics________ ________last_______ ______sum-of________\n");
+ p += sprintf(p,
+ "rate [name idx airtime max_tp] [avg(tp) avg(prob) sd(prob)] [prob.|retry|suc|att] [#success | #attempts]\n");
for (i = 0; i < mi->n_rates; i++) {
struct minstrel_rate *mr = &mi->r[i];
@@ -112,7 +110,7 @@ minstrel_stats_open(struct inode *inode, struct file *file)
prob = MINSTREL_TRUNC(mrs->cur_prob * 1000);
eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
- p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u %3u.%1u"
+ p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u %3u.%1u"
" %3u.%1u %3u %3u %-3u "
"%9llu %-9llu\n",
tp_max / 10, tp_max % 10,
diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c
index 6822ce0f95e5..5320e35ed3d0 100644
--- a/net/mac80211/rc80211_minstrel_ht_debugfs.c
+++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c
@@ -86,7 +86,7 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p)
prob = MINSTREL_TRUNC(mrs->cur_prob * 1000);
eprob = MINSTREL_TRUNC(mrs->prob_ewma * 1000);
- p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u %3u.%1u"
+ p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u %3u.%1u"
" %3u.%1u %3u %3u %-3u "
"%9llu %-9llu\n",
tp_max / 10, tp_max % 10,
@@ -129,12 +129,10 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file)
p = ms->buf;
p += sprintf(p, "\n");
- p += sprintf(p, " best ____________rate__________ "
- "______statistics______ ________last_______ "
- "______sum-of________\n");
- p += sprintf(p, "mode guard # rate [name idx airtime max_tp] "
- "[ ø(tp) ø(prob) sd(prob)] [prob.|retry|suc|att] [#success | "
- "#attempts]\n");
+ p += sprintf(p,
+ " best ____________rate__________ ________statistics________ ________last_______ ______sum-of________\n");
+ p += sprintf(p,
+ "mode guard # rate [name idx airtime max_tp] [avg(tp) avg(prob) sd(prob)] [prob.|retry|suc|att] [#success | #attempts]\n");
p = minstrel_ht_stats_dump(mi, MINSTREL_CCK_GROUP, p);
for (i = 0; i < MINSTREL_CCK_GROUP; i++)
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 64f1936350c6..c3644458e2ee 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -303,7 +303,6 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_hw *hw = &local->hw;
struct sta_info *sta;
- struct timespec uptime;
int i;
sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp);
@@ -339,8 +338,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
/* Mark TID as unreserved */
sta->reserved_tid = IEEE80211_TID_UNRESERVED;
- ktime_get_ts(&uptime);
- sta->last_connected = uptime.tv_sec;
+ sta->last_connected = ktime_get_seconds();
ewma_signal_init(&sta->avg_signal);
for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++)
ewma_signal_init(&sta->chain_signal_avg[i]);
@@ -1813,7 +1811,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
struct ieee80211_sub_if_data *sdata = sta->sdata;
struct ieee80211_local *local = sdata->local;
struct rate_control_ref *ref = NULL;
- struct timespec uptime;
u32 thr = 0;
int i, ac;
@@ -1838,8 +1835,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
BIT(NL80211_STA_INFO_RX_DROP_MISC) |
BIT(NL80211_STA_INFO_BEACON_LOSS);
- ktime_get_ts(&uptime);
- sinfo->connected_time = uptime.tv_sec - sta->last_connected;
+ sinfo->connected_time = ktime_get_seconds() - sta->last_connected;
sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx);
if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) |
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index b087c71ff7fe..d5ded8749ac4 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -133,6 +133,7 @@ enum ieee80211_agg_stop_reason {
* @buf_size: reorder buffer size at receiver
* @failed_bar_ssn: ssn of the last failed BAR tx attempt
* @bar_pending: BAR needs to be re-sent
+ * @amsdu: support A-MSDU withing A-MDPU
*
* This structure's lifetime is managed by RCU, assignments to
* the array holding it must hold the aggregation mutex.
@@ -158,6 +159,7 @@ struct tid_ampdu_tx {
u16 failed_bar_ssn;
bool bar_pending;
+ bool amsdu;
};
/**
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 8ba583243509..98fd04c4b2a0 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -668,16 +668,70 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
}
EXPORT_SYMBOL(ieee80211_tx_status_noskb);
-void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
+ struct ieee80211_supported_band *sband,
+ int retry_count, int shift, bool send_to_cooked)
{
struct sk_buff *skb2;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ struct ieee80211_sub_if_data *sdata;
+ struct net_device *prev_dev = NULL;
+ int rtap_len;
+
+ /* send frame to monitor interfaces now */
+ rtap_len = ieee80211_tx_radiotap_len(info);
+ if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) {
+ pr_err("ieee80211_tx_status: headroom too small\n");
+ dev_kfree_skb(skb);
+ return;
+ }
+ ieee80211_add_tx_radiotap_header(local, sband, skb, retry_count,
+ rtap_len, shift);
+
+ /* XXX: is this sufficient for BPF? */
+ skb_set_mac_header(skb, 0);
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->pkt_type = PACKET_OTHERHOST;
+ skb->protocol = htons(ETH_P_802_2);
+ memset(skb->cb, 0, sizeof(skb->cb));
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+ if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+ if (!ieee80211_sdata_running(sdata))
+ continue;
+
+ if ((sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) &&
+ !send_to_cooked)
+ continue;
+
+ if (prev_dev) {
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (skb2) {
+ skb2->dev = prev_dev;
+ netif_rx(skb2);
+ }
+ }
+
+ prev_dev = sdata->dev;
+ }
+ }
+ if (prev_dev) {
+ skb->dev = prev_dev;
+ netif_rx(skb);
+ skb = NULL;
+ }
+ rcu_read_unlock();
+ dev_kfree_skb(skb);
+}
+
+void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
struct ieee80211_local *local = hw_to_local(hw);
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
__le16 fc;
struct ieee80211_supported_band *sband;
- struct ieee80211_sub_if_data *sdata;
- struct net_device *prev_dev = NULL;
struct sta_info *sta;
struct rhash_head *tmp;
int retry_count;
@@ -685,7 +739,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
bool send_to_cooked;
bool acked;
struct ieee80211_bar *bar;
- int rtap_len;
int shift = 0;
int tid = IEEE80211_NUM_TIDS;
const struct bucket_table *tbl;
@@ -878,51 +931,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
return;
}
- /* send frame to monitor interfaces now */
- rtap_len = ieee80211_tx_radiotap_len(info);
- if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) {
- pr_err("ieee80211_tx_status: headroom too small\n");
- dev_kfree_skb(skb);
- return;
- }
- ieee80211_add_tx_radiotap_header(local, sband, skb, retry_count,
- rtap_len, shift);
-
- /* XXX: is this sufficient for BPF? */
- skb_set_mac_header(skb, 0);
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->pkt_type = PACKET_OTHERHOST;
- skb->protocol = htons(ETH_P_802_2);
- memset(skb->cb, 0, sizeof(skb->cb));
-
- rcu_read_lock();
- list_for_each_entry_rcu(sdata, &local->interfaces, list) {
- if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
- if (!ieee80211_sdata_running(sdata))
- continue;
-
- if ((sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) &&
- !send_to_cooked)
- continue;
-
- if (prev_dev) {
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (skb2) {
- skb2->dev = prev_dev;
- netif_rx(skb2);
- }
- }
-
- prev_dev = sdata->dev;
- }
- }
- if (prev_dev) {
- skb->dev = prev_dev;
- netif_rx(skb);
- skb = NULL;
- }
- rcu_read_unlock();
- dev_kfree_skb(skb);
+ /* send to monitor interfaces */
+ ieee80211_tx_monitor(local, skb, sband, retry_count, shift, send_to_cooked);
}
EXPORT_SYMBOL(ieee80211_tx_status);
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 4e202d0679b2..ecc5e2a8f80b 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -41,9 +41,11 @@ static void ieee80211_tdls_add_ext_capab(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb)
{
struct ieee80211_local *local = sdata->local;
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
bool chan_switch = local->hw.wiphy->features &
NL80211_FEATURE_TDLS_CHANNEL_SWITCH;
- bool wider_band = ieee80211_hw_check(&local->hw, TDLS_WIDER_BW);
+ bool wider_band = ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) &&
+ !ifmgd->tdls_wider_bw_prohibited;
enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
bool vht = sband && sband->vht_cap.vht_supported;
@@ -331,8 +333,8 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata,
/* proceed to downgrade the chandef until usable or the same */
while (uc.width > max_width &&
- !cfg80211_reg_can_beacon(sdata->local->hw.wiphy,
- &uc, sdata->wdev.iftype))
+ !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc,
+ sdata->wdev.iftype))
ieee80211_chandef_downgrade(&uc);
if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) {
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 6f14591d8ca9..314e3bd7fbdb 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -497,6 +497,36 @@ TRACE_EVENT(drv_configure_filter,
)
);
+TRACE_EVENT(drv_config_iface_filter,
+ TP_PROTO(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ unsigned int filter_flags,
+ unsigned int changed_flags),
+
+ TP_ARGS(local, sdata, filter_flags, changed_flags),
+
+ TP_STRUCT__entry(
+ LOCAL_ENTRY
+ VIF_ENTRY
+ __field(unsigned int, filter_flags)
+ __field(unsigned int, changed_flags)
+ ),
+
+ TP_fast_assign(
+ LOCAL_ASSIGN;
+ VIF_ASSIGN;
+ __entry->filter_flags = filter_flags;
+ __entry->changed_flags = changed_flags;
+ ),
+
+ TP_printk(
+ LOCAL_PR_FMT VIF_PR_FMT
+ " filter_flags: %#x changed_flags: %#x",
+ LOCAL_PR_ARG, VIF_PR_ARG, __entry->filter_flags,
+ __entry->changed_flags
+ )
+);
+
TRACE_EVENT(drv_set_tim,
TP_PROTO(struct ieee80211_local *local,
struct ieee80211_sta *sta, bool set),
@@ -944,9 +974,9 @@ TRACE_EVENT(drv_ampdu_action,
struct ieee80211_sub_if_data *sdata,
enum ieee80211_ampdu_mlme_action action,
struct ieee80211_sta *sta, u16 tid,
- u16 *ssn, u8 buf_size),
+ u16 *ssn, u8 buf_size, bool amsdu),
- TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size),
+ TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size, amsdu),
TP_STRUCT__entry(
LOCAL_ENTRY
@@ -955,6 +985,7 @@ TRACE_EVENT(drv_ampdu_action,
__field(u16, tid)
__field(u16, ssn)
__field(u8, buf_size)
+ __field(bool, amsdu)
VIF_ENTRY
),
@@ -966,12 +997,13 @@ TRACE_EVENT(drv_ampdu_action,
__entry->tid = tid;
__entry->ssn = ssn ? *ssn : 0;
__entry->buf_size = buf_size;
+ __entry->amsdu = amsdu;
),
TP_printk(
- LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d",
+ LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d amsdu:%d",
LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action,
- __entry->tid, __entry->buf_size
+ __entry->tid, __entry->buf_size, __entry->amsdu
)
);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 84e0e8c7fb23..464ba1a625bd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2767,7 +2767,8 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
*ieee80211_get_qos_ctl(hdr) = tid;
- hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
+ if (!sta->sta.txq[0])
+ hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
} else {
info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
hdr->seq_ctrl = cpu_to_le16(sdata->sequence_number);
@@ -3512,6 +3513,12 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
{
struct ieee80211_mutable_offsets offs = {};
struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false);
+ struct sk_buff *copy;
+ struct ieee80211_supported_band *sband;
+ int shift;
+
+ if (!bcn)
+ return bcn;
if (tim_offset)
*tim_offset = offs.tim_offset;
@@ -3519,6 +3526,19 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
if (tim_length)
*tim_length = offs.tim_length;
+ if (ieee80211_hw_check(hw, BEACON_TX_STATUS) ||
+ !hw_to_local(hw)->monitors)
+ return bcn;
+
+ /* send a copy to monitor interfaces */
+ copy = skb_copy(bcn, GFP_ATOMIC);
+ if (!copy)
+ return bcn;
+
+ shift = ieee80211_vif_get_shift(vif);
+ sband = hw->wiphy->bands[ieee80211_get_sdata_band(vif_to_sdata(vif))];
+ ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false);
+
return bcn;
}
EXPORT_SYMBOL(ieee80211_beacon_get_tim);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 1104421bc525..60c4dbf92625 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1966,7 +1966,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
if (!sdata->u.mgd.associated)
continue;
- ieee80211_send_nullfunc(local, sdata, 0);
+ ieee80211_send_nullfunc(local, sdata, false);
}
}
@@ -2017,8 +2017,9 @@ int ieee80211_reconfig(struct ieee80211_local *local)
mutex_lock(&local->sta_mtx);
list_for_each_entry(sta, &local->sta_list, list) {
- ieee80211_sta_tear_down_BA_sessions(
- sta, AGG_STOP_LOCAL_REQUEST);
+ if (!local->resuming)
+ ieee80211_sta_tear_down_BA_sessions(
+ sta, AGG_STOP_LOCAL_REQUEST);
clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
}
@@ -2324,6 +2325,8 @@ u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
if (chandef->center_freq2)
vht_oper->center_freq_seg2_idx =
ieee80211_frequency_to_channel(chandef->center_freq2);
+ else
+ vht_oper->center_freq_seg2_idx = 0x00;
switch (chandef->width) {
case NL80211_CHAN_WIDTH_160:
@@ -2541,7 +2544,7 @@ int ieee80211_ave_rssi(struct ieee80211_vif *vif)
/* non-managed type inferfaces */
return 0;
}
- return ifmgd->ave_beacon_signal / 16;
+ return -ewma_beacon_signal_read(&ifmgd->ave_beacon_signal);
}
EXPORT_SYMBOL_GPL(ieee80211_ave_rssi);
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index c865ebb2ace2..57b5e94471af 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -266,6 +266,195 @@ ieee802154_set_ackreq_default(struct wpan_phy *wpan_phy,
return 0;
}
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+static void
+ieee802154_get_llsec_table(struct wpan_phy *wpan_phy,
+ struct wpan_dev *wpan_dev,
+ struct ieee802154_llsec_table **table)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+
+ *table = &sdata->sec.table;
+}
+
+static void
+ieee802154_lock_llsec_table(struct wpan_phy *wpan_phy,
+ struct wpan_dev *wpan_dev)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+
+ mutex_lock(&sdata->sec_mtx);
+}
+
+static void
+ieee802154_unlock_llsec_table(struct wpan_phy *wpan_phy,
+ struct wpan_dev *wpan_dev)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+
+ mutex_unlock(&sdata->sec_mtx);
+}
+
+static int
+ieee802154_set_llsec_params(struct wpan_phy *wpan_phy,
+ struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_params *params,
+ int changed)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_set_params(&sdata->sec, params, changed);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_get_llsec_params(struct wpan_phy *wpan_phy,
+ struct wpan_dev *wpan_dev,
+ struct ieee802154_llsec_params *params)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_get_params(&sdata->sec, params);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_add_llsec_key(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_key_id *id,
+ const struct ieee802154_llsec_key *key)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_key_add(&sdata->sec, id, key);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_del_llsec_key(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_key_id *id)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_key_del(&sdata->sec, id);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_add_seclevel(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_seclevel *sl)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_seclevel_add(&sdata->sec, sl);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_del_seclevel(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_seclevel *sl)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_seclevel_del(&sdata->sec, sl);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_add_device(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ const struct ieee802154_llsec_device *dev_desc)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_dev_add(&sdata->sec, dev_desc);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_del_device(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ __le64 extended_addr)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_dev_del(&sdata->sec, extended_addr);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_add_devkey(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ __le64 extended_addr,
+ const struct ieee802154_llsec_device_key *key)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_devkey_add(&sdata->sec, extended_addr, key);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+
+static int
+ieee802154_del_devkey(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
+ __le64 extended_addr,
+ const struct ieee802154_llsec_device_key *key)
+{
+ struct net_device *dev = wpan_dev->netdev;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ int res;
+
+ mutex_lock(&sdata->sec_mtx);
+ res = mac802154_llsec_devkey_del(&sdata->sec, extended_addr, key);
+ mutex_unlock(&sdata->sec_mtx);
+
+ return res;
+}
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
+
const struct cfg802154_ops mac802154_config_ops = {
.add_virtual_intf_deprecated = ieee802154_add_iface_deprecated,
.del_virtual_intf_deprecated = ieee802154_del_iface_deprecated,
@@ -284,4 +473,20 @@ const struct cfg802154_ops mac802154_config_ops = {
.set_max_frame_retries = ieee802154_set_max_frame_retries,
.set_lbt_mode = ieee802154_set_lbt_mode,
.set_ackreq_default = ieee802154_set_ackreq_default,
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+ .get_llsec_table = ieee802154_get_llsec_table,
+ .lock_llsec_table = ieee802154_lock_llsec_table,
+ .unlock_llsec_table = ieee802154_unlock_llsec_table,
+ /* TODO above */
+ .set_llsec_params = ieee802154_set_llsec_params,
+ .get_llsec_params = ieee802154_get_llsec_params,
+ .add_llsec_key = ieee802154_add_llsec_key,
+ .del_llsec_key = ieee802154_del_llsec_key,
+ .add_seclevel = ieee802154_add_seclevel,
+ .del_seclevel = ieee802154_del_seclevel,
+ .add_device = ieee802154_add_device,
+ .del_device = ieee802154_del_device,
+ .add_devkey = ieee802154_add_devkey,
+ .del_devkey = ieee802154_del_devkey,
+#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
};
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index ed26952f9e14..7079cd32a7ad 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -367,12 +367,11 @@ static int mac802154_set_header_security(struct ieee802154_sub_if_data *sdata,
return 0;
}
-static int mac802154_header_create(struct sk_buff *skb,
- struct net_device *dev,
- unsigned short type,
- const void *daddr,
- const void *saddr,
- unsigned len)
+static int ieee802154_header_create(struct sk_buff *skb,
+ struct net_device *dev,
+ const struct ieee802154_addr *daddr,
+ const struct ieee802154_addr *saddr,
+ unsigned len)
{
struct ieee802154_hdr hdr;
struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
@@ -423,24 +422,89 @@ static int mac802154_header_create(struct sk_buff *skb,
return hlen;
}
+static const struct wpan_dev_header_ops ieee802154_header_ops = {
+ .create = ieee802154_header_create,
+};
+
+/* This header create functionality assumes a 8 byte array for
+ * source and destination pointer at maximum. To adapt this for
+ * the 802.15.4 dataframe header we use extended address handling
+ * here only and intra pan connection. fc fields are mostly fallback
+ * handling. For provide dev_hard_header for dgram sockets.
+ */
+static int mac802154_header_create(struct sk_buff *skb,
+ struct net_device *dev,
+ unsigned short type,
+ const void *daddr,
+ const void *saddr,
+ unsigned len)
+{
+ struct ieee802154_hdr hdr;
+ struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
+ struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+ struct ieee802154_mac_cb cb = { };
+ int hlen;
+
+ if (!daddr)
+ return -EINVAL;
+
+ memset(&hdr.fc, 0, sizeof(hdr.fc));
+ hdr.fc.type = IEEE802154_FC_TYPE_DATA;
+ hdr.fc.ack_request = wpan_dev->ackreq;
+ hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF;
+
+ /* TODO currently a workaround to give zero cb block to set
+ * security parameters defaults according MIB.
+ */
+ if (mac802154_set_header_security(sdata, &hdr, &cb) < 0)
+ return -EINVAL;
+
+ hdr.dest.pan_id = wpan_dev->pan_id;
+ hdr.dest.mode = IEEE802154_ADDR_LONG;
+ ieee802154_be64_to_le64(&hdr.dest.extended_addr, daddr);
+
+ hdr.source.pan_id = hdr.dest.pan_id;
+ hdr.source.mode = IEEE802154_ADDR_LONG;
+
+ if (!saddr)
+ hdr.source.extended_addr = wpan_dev->extended_addr;
+ else
+ ieee802154_be64_to_le64(&hdr.source.extended_addr, saddr);
+
+ hlen = ieee802154_hdr_push(skb, &hdr);
+ if (hlen < 0)
+ return -EINVAL;
+
+ skb_reset_mac_header(skb);
+ skb->mac_len = hlen;
+
+ if (len > ieee802154_max_payload(&hdr))
+ return -EMSGSIZE;
+
+ return hlen;
+}
+
static int
mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
struct ieee802154_hdr hdr;
- struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr;
if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) {
pr_debug("malformed packet\n");
return 0;
}
- *addr = hdr.source;
- return sizeof(*addr);
+ if (hdr.source.mode == IEEE802154_ADDR_LONG) {
+ ieee802154_le64_to_be64(haddr, &hdr.source.extended_addr);
+ return IEEE802154_EXTENDED_ADDR_LEN;
+ }
+
+ return 0;
}
-static struct header_ops mac802154_header_ops = {
- .create = mac802154_header_create,
- .parse = mac802154_header_parse,
+static const struct header_ops mac802154_header_ops = {
+ .create = mac802154_header_create,
+ .parse = mac802154_header_parse,
};
static const struct net_device_ops mac802154_wpan_ops = {
@@ -471,9 +535,29 @@ static void ieee802154_if_setup(struct net_device *dev)
dev->addr_len = IEEE802154_EXTENDED_ADDR_LEN;
memset(dev->broadcast, 0xff, IEEE802154_EXTENDED_ADDR_LEN);
- dev->hard_header_len = MAC802154_FRAME_HARD_HEADER_LEN;
- dev->needed_tailroom = 2 + 16; /* FCS + MIC */
- dev->mtu = IEEE802154_MTU;
+ /* Let hard_header_len set to IEEE802154_MIN_HEADER_LEN. AF_PACKET
+ * will not send frames without any payload, but ack frames
+ * has no payload, so substract one that we can send a 3 bytes
+ * frame. The xmit callback assumes at least a hard header where two
+ * bytes fc and sequence field are set.
+ */
+ dev->hard_header_len = IEEE802154_MIN_HEADER_LEN - 1;
+ /* The auth_tag header is for security and places in private payload
+ * room of mac frame which stucks between payload and FCS field.
+ */
+ dev->needed_tailroom = IEEE802154_MAX_AUTH_TAG_LEN +
+ IEEE802154_FCS_LEN;
+ /* The mtu size is the payload without mac header in this case.
+ * We have a dynamic length header with a minimum header length
+ * which is hard_header_len. In this case we let mtu to the size
+ * of maximum payload which is IEEE802154_MTU - IEEE802154_FCS_LEN -
+ * hard_header_len. The FCS which is set by hardware or ndo_start_xmit
+ * and the minimum mac header which can be evaluated inside driver
+ * layer. The rest of mac header will be part of payload if greater
+ * than hard_header_len.
+ */
+ dev->mtu = IEEE802154_MTU - IEEE802154_FCS_LEN -
+ dev->hard_header_len;
dev->tx_queue_len = 300;
dev->flags = IFF_NOARP | IFF_BROADCAST;
}
@@ -513,6 +597,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
sdata->dev->netdev_ops = &mac802154_wpan_ops;
sdata->dev->ml_priv = &mac802154_mlme_wpan;
wpan_dev->promiscuous_mode = false;
+ wpan_dev->header_ops = &ieee802154_header_ops;
mutex_init(&sdata->sec_mtx);
@@ -550,7 +635,8 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name,
if (!ndev)
return ERR_PTR(-ENOMEM);
- ndev->needed_headroom = local->hw.extra_tx_headroom;
+ ndev->needed_headroom = local->hw.extra_tx_headroom +
+ IEEE802154_MAX_HEADER_LEN;
ret = dev_alloc_name(ndev, ndev->name);
if (ret < 0)
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index 985e9394e2af..7799d3c41fe2 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -401,6 +401,7 @@ int mac802154_llsec_dev_del(struct mac802154_llsec *sec, __le64 device_addr)
hash_del_rcu(&pos->bucket_s);
hash_del_rcu(&pos->bucket_hw);
+ list_del_rcu(&pos->dev.list);
call_rcu(&pos->rcu, llsec_dev_free_rcu);
return 0;
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index d1c33c1d6b9b..42e96729dae6 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -87,6 +87,10 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
skb->dev = sdata->dev;
+ /* TODO this should be moved after netif_receive_skb call, otherwise
+ * wireshark will show a mac header with security fields and the
+ * payload is already decrypted.
+ */
rc = mac802154_llsec_decrypt(&sdata->sec, skb);
if (rc) {
pr_debug("decryption failed: %i\n", rc);
diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index 7ed439172f30..3827f359b336 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -77,9 +77,6 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
put_unaligned_le16(crc, skb_put(skb, 2));
}
- if (skb_cow_head(skb, local->hw.extra_tx_headroom))
- goto err_tx;
-
/* Stop the netif queue on each sub_if_data object. */
ieee802154_stop_queue(&local->hw);
@@ -121,6 +118,10 @@ ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev)
struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
int rc;
+ /* TODO we should move it to wpan_dev_hard_header and dev_hard_header
+ * functions. The reason is wireshark will show a mac header which is
+ * with security fields but the payload is not encrypted.
+ */
rc = mac802154_llsec_encrypt(&sdata->sec, skb);
if (rc) {
netdev_warn(dev, "encryption failed: %i\n", rc);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 21e70bc9af98..67591aef9cae 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -37,7 +37,7 @@ static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en)
return en->labels * sizeof(struct mpls_shim_hdr);
}
-int mpls_output(struct sock *sk, struct sk_buff *skb)
+int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct mpls_iptunnel_encap *tun_encap_info;
struct mpls_shim_hdr *hdr;
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index ce37d204fcf1..1e24fff53e4b 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -692,7 +692,7 @@ static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs,
int err;
local_bh_disable();
- err = ip_defrag(skb, user);
+ err = ip_defrag(ipvs->net, skb, user);
local_bh_enable();
if (!err)
ip_send_check(ip_hdr(skb));
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 77182b9750cd..3264cb49b333 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -576,7 +576,7 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
if (!skb->sk)
skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
- NULL, skb_dst(skb)->dev, dst_output_okfn);
+ NULL, skb_dst(skb)->dev, dst_output);
} else
ret = NF_ACCEPT;
@@ -598,7 +598,7 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
if (!skb->sk)
skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
- NULL, skb_dst(skb)->dev, dst_output_okfn);
+ NULL, skb_dst(skb)->dev, dst_output);
} else
ret = NF_ACCEPT;
return ret;
@@ -1049,7 +1049,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
- ip_local_out(skb);
+ ip_local_out(net, skb->sk, skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
@@ -1141,7 +1141,7 @@ 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(skb);
+ ip6_local_out(cp->ipvs->net, skb->sk, skb);
else if (ret == NF_DROP)
kfree_skb(skb);
rcu_read_unlock();
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 70277b11f742..f1d9e887f5b1 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -64,7 +64,7 @@ void nfnl_unlock(__u8 subsys_id)
EXPORT_SYMBOL_GPL(nfnl_unlock);
#ifdef CONFIG_PROVE_LOCKING
-int lockdep_nfnl_is_held(u8 subsys_id)
+bool lockdep_nfnl_is_held(u8 subsys_id)
{
return lockdep_is_held(&table[subsys_id].mutex);
}
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index a5b9680a1821..06eb48fceb42 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -541,9 +541,9 @@ __build_packet_message(struct nfnl_log_net *log,
if (skb->tstamp.tv64) {
struct nfulnl_msg_packet_timestamp ts;
- struct timeval tv = ktime_to_timeval(skb->tstamp);
- ts.sec = cpu_to_be64(tv.tv_sec);
- ts.usec = cpu_to_be64(tv.tv_usec);
+ struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
+ ts.sec = cpu_to_be64(kts.tv_sec);
+ ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);
if (nla_put(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts))
goto nla_put_failure;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 75724a96aef2..bc0e504f33a6 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -39,7 +39,7 @@ void genl_unlock(void)
EXPORT_SYMBOL(genl_unlock);
#ifdef CONFIG_LOCKDEP
-int lockdep_genl_is_held(void)
+bool lockdep_genl_is_held(void)
{
return lockdep_is_held(&genl_mutex);
}
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 315f5330b6e5..1d21ab9d2b5c 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -620,7 +620,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
return 0;
}
-static int ovs_vport_output(struct sock *sock, struct sk_buff *skb)
+static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
struct vport *vport = data->vport;
@@ -679,8 +679,8 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb)
skb_pull(skb, hlen);
}
-static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
- __be16 ethertype)
+static void ovs_fragment(struct net *net, struct vport *vport,
+ struct sk_buff *skb, u16 mru, __be16 ethertype)
{
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
@@ -700,7 +700,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
skb_dst_set_noref(skb, &ovs_dst);
IPCB(skb)->frag_max_size = mru;
- ip_do_fragment(skb->sk, skb, ovs_vport_output);
+ ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
} else if (ethertype == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
@@ -722,7 +722,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
skb_dst_set_noref(skb, &ovs_rt.dst);
IP6CB(skb)->frag_max_size = mru;
- v6ops->fragment(skb->sk, skb, ovs_vport_output);
+ v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
@@ -743,6 +743,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
ovs_vport_send(vport, skb);
} else if (mru <= vport->dev->mtu) {
+ struct net *net = read_pnet(&dp->net);
__be16 ethertype = key->eth.type;
if (!is_flow_key_valid(key)) {
@@ -752,7 +753,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
ethertype = vlan_get_protocol(skb);
}
- ovs_fragment(vport, skb, mru, ethertype);
+ ovs_fragment(net, vport, skb, mru, ethertype);
} else {
kfree_skb(skb);
}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index eb759e3a88ca..ad614267cc2a 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -304,7 +304,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
int err;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
- err = ip_defrag(skb, user);
+ err = ip_defrag(net, skb, user);
if (err)
return err;
@@ -315,7 +315,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
struct sk_buff *reasm;
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
- reasm = nf_ct_frag6_gather(skb, user);
+ reasm = nf_ct_frag6_gather(net, skb, user);
if (!reasm)
return -EINPROGRESS;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index c8db44ab2ee7..0ea128eeeab2 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -698,8 +698,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
{
/* Extract metadata from packet. */
if (tun_info) {
- if (ip_tunnel_info_af(tun_info) != AF_INET)
- return -EINVAL;
+ key->tun_proto = ip_tunnel_info_af(tun_info);
memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key));
if (tun_info->options_len) {
@@ -714,6 +713,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
key->tun_opts_len = 0;
}
} else {
+ key->tun_proto = 0;
key->tun_opts_len = 0;
memset(&key->tun_key, 0, sizeof(key->tun_key));
}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index fe527d2dd4b7..5688e33e2de6 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -63,6 +63,7 @@ struct sw_flow_key {
u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
} __packed phy; /* Safe when right after 'tun_key'. */
+ u8 tun_proto; /* Protocol of encapsulating tunnel. */
u32 ovs_flow_hash; /* Datapath computed hash value. */
u32 recirc_id; /* Recirculation ID. */
struct {
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 5c030a4d7338..77850f177a47 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -262,8 +262,8 @@ size_t ovs_tun_key_attr_size(void)
* updating this function.
*/
return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */
+ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
@@ -323,6 +323,8 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE },
[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED,
.next = ovs_vxlan_ext_key_lens },
+ [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
+ [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) },
};
/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */
@@ -542,14 +544,14 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
return 0;
}
-static int ipv4_tun_from_nlattr(const struct nlattr *attr,
- struct sw_flow_match *match, bool is_mask,
- bool log)
+static int ip_tun_from_nlattr(const struct nlattr *attr,
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
{
struct nlattr *a;
int rem;
bool ttl = false;
- __be16 tun_flags = 0;
+ __be16 tun_flags = 0, ipv4 = false, ipv6 = false;
int opts_type = 0;
nla_for_each_nested(a, attr, rem) {
@@ -578,10 +580,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
case OVS_TUNNEL_KEY_ATTR_IPV4_SRC:
SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src,
nla_get_in_addr(a), is_mask);
+ ipv4 = true;
break;
case OVS_TUNNEL_KEY_ATTR_IPV4_DST:
SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst,
nla_get_in_addr(a), is_mask);
+ ipv4 = true;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ nla_get_in6_addr(a), is_mask);
+ ipv6 = true;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_IPV6_DST:
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ nla_get_in6_addr(a), is_mask);
+ ipv6 = true;
break;
case OVS_TUNNEL_KEY_ATTR_TOS:
SW_FLOW_KEY_PUT(match, tun_key.tos,
@@ -636,28 +650,46 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
opts_type = type;
break;
default:
- OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
+ OVS_NLERR(log, "Unknown IP tunnel attribute %d",
type);
return -EINVAL;
}
}
SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
+ if (is_mask)
+ SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true);
+ else
+ SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET,
+ false);
if (rem > 0) {
- OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+ OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.",
rem);
return -EINVAL;
}
+ if (ipv4 && ipv6) {
+ OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes");
+ return -EINVAL;
+ }
+
if (!is_mask) {
- if (!match->key->tun_key.u.ipv4.dst) {
+ if (!ipv4 && !ipv6) {
+ OVS_NLERR(log, "IP tunnel dst address not specified");
+ return -EINVAL;
+ }
+ if (ipv4 && !match->key->tun_key.u.ipv4.dst) {
OVS_NLERR(log, "IPv4 tunnel dst address is zero");
return -EINVAL;
}
+ if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
+ OVS_NLERR(log, "IPv6 tunnel dst address is zero");
+ return -EINVAL;
+ }
if (!ttl) {
- OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
+ OVS_NLERR(log, "IP tunnel TTL not specified.");
return -EINVAL;
}
}
@@ -682,21 +714,36 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb,
return 0;
}
-static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ip_tunnel_key *output,
- const void *tun_opts, int swkey_tun_opts_len)
+static int __ip_tun_to_nlattr(struct sk_buff *skb,
+ const struct ip_tunnel_key *output,
+ const void *tun_opts, int swkey_tun_opts_len,
+ unsigned short tun_proto)
{
if (output->tun_flags & TUNNEL_KEY &&
nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
return -EMSGSIZE;
- if (output->u.ipv4.src &&
- nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
- output->u.ipv4.src))
- return -EMSGSIZE;
- if (output->u.ipv4.dst &&
- nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
- output->u.ipv4.dst))
- return -EMSGSIZE;
+ switch (tun_proto) {
+ case AF_INET:
+ if (output->u.ipv4.src &&
+ nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
+ output->u.ipv4.src))
+ return -EMSGSIZE;
+ if (output->u.ipv4.dst &&
+ nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
+ output->u.ipv4.dst))
+ return -EMSGSIZE;
+ break;
+ case AF_INET6:
+ if (!ipv6_addr_any(&output->u.ipv6.src) &&
+ nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC,
+ &output->u.ipv6.src))
+ return -EMSGSIZE;
+ if (!ipv6_addr_any(&output->u.ipv6.dst) &&
+ nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST,
+ &output->u.ipv6.dst))
+ return -EMSGSIZE;
+ break;
+ }
if (output->tos &&
nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos))
return -EMSGSIZE;
@@ -730,9 +777,10 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
return 0;
}
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ip_tunnel_key *output,
- const void *tun_opts, int swkey_tun_opts_len)
+static int ip_tun_to_nlattr(struct sk_buff *skb,
+ const struct ip_tunnel_key *output,
+ const void *tun_opts, int swkey_tun_opts_len,
+ unsigned short tun_proto)
{
struct nlattr *nla;
int err;
@@ -741,7 +789,8 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
if (!nla)
return -EMSGSIZE;
- err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+ err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
+ tun_proto);
if (err)
return err;
@@ -753,9 +802,10 @@ int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
const struct ip_tunnel_info *egress_tun_info,
const void *egress_tun_opts)
{
- return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key,
- egress_tun_opts,
- egress_tun_info->options_len);
+ return __ip_tun_to_nlattr(skb, &egress_tun_info->key,
+ egress_tun_opts,
+ egress_tun_info->options_len,
+ ip_tunnel_info_af(egress_tun_info));
}
static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
@@ -806,8 +856,8 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
*attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK);
}
if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
- if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
- is_mask, log) < 0)
+ if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
+ is_mask, log) < 0)
return -EINVAL;
*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
}
@@ -1194,7 +1244,7 @@ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match,
/* The userspace does not send tunnel attributes that
* are 0, but we should not wildcard them nonetheless.
*/
- if (match->key->tun_key.u.ipv4.dst)
+ if (match->key->tun_proto)
SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
0xff, true);
@@ -1367,14 +1417,14 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
- if ((swkey->tun_key.u.ipv4.dst || is_mask)) {
+ if ((swkey->tun_proto || is_mask)) {
const void *opts = NULL;
if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
- if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
- swkey->tun_opts_len))
+ if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
+ swkey->tun_opts_len, swkey->tun_proto))
goto nla_put_failure;
}
@@ -1877,7 +1927,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
int err = 0, start, opts_type;
ovs_match_init(&match, &key, NULL);
- opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+ opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
if (opts_type < 0)
return opts_type;
@@ -1913,6 +1963,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
tun_info = &tun_dst->u.tun_info;
tun_info->mode = IP_TUNNEL_INFO_TX;
+ if (key.tun_proto == AF_INET6)
+ tun_info->mode |= IP_TUNNEL_INFO_IPV6;
tun_info->key = key.tun_key;
/* We need to store the options in the action itself since
@@ -2374,10 +2426,11 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
if (!start)
return -EMSGSIZE;
- err = ipv4_tun_to_nlattr(skb, &tun_info->key,
- tun_info->options_len ?
+ err = ip_tun_to_nlattr(skb, &tun_info->key,
+ tun_info->options_len ?
ip_tunnel_info_opts(tun_info) : NULL,
- tun_info->options_len);
+ tun_info->options_len,
+ ip_tunnel_info_af(tun_info));
if (err)
return err;
nla_nest_end(skb, start);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index f2ea83ba4763..95dbcedf0bd4 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -427,7 +427,7 @@ static u32 flow_hash(const struct sw_flow_key *key,
static int flow_key_start(const struct sw_flow_key *key)
{
- if (key->tun_key.u.ipv4.dst)
+ if (key->tun_proto)
return 0;
else
return rounddown(offsetof(struct sw_flow_key, phy),
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index aa4b15c35884..691660b9b7ef 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1423,7 +1423,7 @@ static unsigned int fanout_demux_bpf(struct packet_fanout *f,
rcu_read_lock();
prog = rcu_dereference(f->bpf_prog);
if (prog)
- ret = BPF_PROG_RUN(prog, skb) % num;
+ ret = bpf_prog_run_clear_cb(prog, skb) % num;
rcu_read_unlock();
return ret;
@@ -1439,17 +1439,17 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
{
struct packet_fanout *f = pt->af_packet_priv;
unsigned int num = READ_ONCE(f->num_members);
+ struct net *net = read_pnet(&f->net);
struct packet_sock *po;
unsigned int idx;
- if (!net_eq(dev_net(dev), read_pnet(&f->net)) ||
- !num) {
+ if (!net_eq(dev_net(dev), net) || !num) {
kfree_skb(skb);
return 0;
}
if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
- skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
+ skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET);
if (!skb)
return 0;
}
@@ -1519,10 +1519,10 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
static bool match_fanout_group(struct packet_type *ptype, struct sock *sk)
{
- if (ptype->af_packet_priv == (void *)((struct packet_sock *)sk)->fanout)
- return true;
+ if (sk->sk_family != PF_PACKET)
+ return false;
- return false;
+ return ptype->af_packet_priv == pkt_sk(sk)->fanout;
}
static void fanout_init_data(struct packet_fanout *f)
@@ -1567,7 +1567,7 @@ static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data,
if (copy_from_user(&fprog, data, len))
return -EFAULT;
- ret = bpf_prog_create_from_user(&new, &fprog, NULL);
+ ret = bpf_prog_create_from_user(&new, &fprog, NULL, false);
if (ret)
return ret;
@@ -1939,16 +1939,16 @@ out_free:
return err;
}
-static unsigned int run_filter(const struct sk_buff *skb,
- const struct sock *sk,
- unsigned int res)
+static unsigned int run_filter(struct sk_buff *skb,
+ const struct sock *sk,
+ unsigned int res)
{
struct sk_filter *filter;
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter != NULL)
- res = SK_RUN_FILTER(filter, skb);
+ res = bpf_prog_run_clear_cb(filter->prog, skb);
rcu_read_unlock();
return res;
@@ -2630,6 +2630,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
__be16 proto;
unsigned char *addr;
int err, reserve = 0;
+ struct sockcm_cookie sockc;
struct virtio_net_hdr vnet_hdr = { 0 };
int offset = 0;
int vnet_hdr_len;
@@ -2665,6 +2666,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
if (unlikely(!(dev->flags & IFF_UP)))
goto out_unlock;
+ sockc.mark = sk->sk_mark;
+ if (msg->msg_controllen) {
+ err = sock_cmsg_send(sk, msg, &sockc);
+ if (unlikely(err))
+ goto out_unlock;
+ }
+
if (sock->type == SOCK_RAW)
reserve = dev->hard_header_len;
if (po->has_vnet_hdr) {
@@ -2774,7 +2782,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
skb->protocol = proto;
skb->dev = dev;
skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
+ skb->mark = sockc.mark;
packet_pick_tx_queue(dev, skb);
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index a2f28a6d4dc5..384ea1e3cd69 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -72,13 +72,7 @@ static int rds_release(struct socket *sock)
rds_clear_recv_queue(rs);
rds_cong_remove_socket(rs);
- /*
- * the binding lookup hash uses rcu, we need to
- * make sure we synchronize_rcu before we free our
- * entry
- */
rds_remove_bound(rs);
- synchronize_rcu();
rds_send_drop_to(rs, NULL);
rds_rdma_drop_keys(rs);
@@ -588,6 +582,8 @@ static int rds_init(void)
{
int ret;
+ rds_bind_lock_init();
+
ret = rds_conn_init();
if (ret)
goto out;
diff --git a/net/rds/bind.c b/net/rds/bind.c
index dd666fb9b4e1..61925667b7a4 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -38,48 +38,50 @@
#include <linux/ratelimit.h>
#include "rds.h"
+struct bind_bucket {
+ rwlock_t lock;
+ struct hlist_head head;
+};
+
#define BIND_HASH_SIZE 1024
-static struct hlist_head bind_hash_table[BIND_HASH_SIZE];
-static DEFINE_SPINLOCK(rds_bind_lock);
+static struct bind_bucket bind_hash_table[BIND_HASH_SIZE];
-static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
+static struct bind_bucket *hash_to_bucket(__be32 addr, __be16 port)
{
return bind_hash_table + (jhash_2words((u32)addr, (u32)port, 0) &
(BIND_HASH_SIZE - 1));
}
-static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
+/* must hold either read or write lock (write lock for insert != NULL) */
+static struct rds_sock *rds_bind_lookup(struct bind_bucket *bucket,
+ __be32 addr, __be16 port,
struct rds_sock *insert)
{
struct rds_sock *rs;
- struct hlist_head *head = hash_to_bucket(addr, port);
+ struct hlist_head *head = &bucket->head;
u64 cmp;
u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port);
- rcu_read_lock();
- hlist_for_each_entry_rcu(rs, head, rs_bound_node) {
+ hlist_for_each_entry(rs, head, rs_bound_node) {
cmp = ((u64)be32_to_cpu(rs->rs_bound_addr) << 32) |
be16_to_cpu(rs->rs_bound_port);
if (cmp == needle) {
- rcu_read_unlock();
+ rds_sock_addref(rs);
return rs;
}
}
- rcu_read_unlock();
if (insert) {
/*
* make sure our addr and port are set before
- * we are added to the list, other people
- * in rcu will find us as soon as the
- * hlist_add_head_rcu is done
+ * we are added to the list.
*/
insert->rs_bound_addr = addr;
insert->rs_bound_port = port;
rds_sock_addref(insert);
- hlist_add_head_rcu(&insert->rs_bound_node, head);
+ hlist_add_head(&insert->rs_bound_node, head);
}
return NULL;
}
@@ -93,16 +95,21 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
{
struct rds_sock *rs;
+ unsigned long flags;
+ struct bind_bucket *bucket = hash_to_bucket(addr, port);
- rs = rds_bind_lookup(addr, port, NULL);
+ read_lock_irqsave(&bucket->lock, flags);
+ rs = rds_bind_lookup(bucket, addr, port, NULL);
+ read_unlock_irqrestore(&bucket->lock, flags);
- if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
- rds_sock_addref(rs);
- else
+ if (rs && sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) {
+ rds_sock_put(rs);
rs = NULL;
+ }
rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr,
ntohs(port));
+
return rs;
}
@@ -112,6 +119,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
unsigned long flags;
int ret = -EADDRINUSE;
u16 rover, last;
+ struct bind_bucket *bucket;
if (*port != 0) {
rover = be16_to_cpu(*port);
@@ -121,42 +129,48 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
last = rover - 1;
}
- spin_lock_irqsave(&rds_bind_lock, flags);
-
do {
+ struct rds_sock *rrs;
if (rover == 0)
rover++;
- if (!rds_bind_lookup(addr, cpu_to_be16(rover), rs)) {
+
+ bucket = hash_to_bucket(addr, cpu_to_be16(rover));
+ write_lock_irqsave(&bucket->lock, flags);
+ rrs = rds_bind_lookup(bucket, addr, cpu_to_be16(rover), rs);
+ write_unlock_irqrestore(&bucket->lock, flags);
+ if (!rrs) {
*port = rs->rs_bound_port;
ret = 0;
rdsdebug("rs %p binding to %pI4:%d\n",
rs, &addr, (int)ntohs(*port));
break;
+ } else {
+ rds_sock_put(rrs);
}
} while (rover++ != last);
- spin_unlock_irqrestore(&rds_bind_lock, flags);
-
return ret;
}
void rds_remove_bound(struct rds_sock *rs)
{
unsigned long flags;
+ struct bind_bucket *bucket =
+ hash_to_bucket(rs->rs_bound_addr, rs->rs_bound_port);
- spin_lock_irqsave(&rds_bind_lock, flags);
+ write_lock_irqsave(&bucket->lock, flags);
if (rs->rs_bound_addr) {
rdsdebug("rs %p unbinding from %pI4:%d\n",
rs, &rs->rs_bound_addr,
ntohs(rs->rs_bound_port));
- hlist_del_init_rcu(&rs->rs_bound_node);
+ hlist_del_init(&rs->rs_bound_node);
rds_sock_put(rs);
rs->rs_bound_addr = 0;
}
- spin_unlock_irqrestore(&rds_bind_lock, flags);
+ write_unlock_irqrestore(&bucket->lock, flags);
}
int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
@@ -182,7 +196,14 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
if (rs->rs_transport) { /* previously bound */
- ret = 0;
+ trans = rs->rs_transport;
+ if (trans->laddr_check(sock_net(sock->sk),
+ sin->sin_addr.s_addr) != 0) {
+ ret = -ENOPROTOOPT;
+ rds_remove_bound(rs);
+ } else {
+ ret = 0;
+ }
goto out;
}
trans = rds_trans_get_preferred(sock_net(sock->sk),
@@ -200,9 +221,13 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
out:
release_sock(sk);
-
- /* we might have called rds_remove_bound on error */
- if (ret)
- synchronize_rcu();
return ret;
}
+
+void rds_bind_lock_init(void)
+{
+ int i;
+
+ for (i = 0; i < BIND_HASH_SIZE; i++)
+ rwlock_init(&bind_hash_table[i].lock);
+}
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 49adeef8090c..d4564036a339 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -128,10 +128,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
struct rds_transport *loop_trans;
unsigned long flags;
int ret;
- struct rds_transport *otrans = trans;
- if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP)
- goto new_conn;
rcu_read_lock();
conn = rds_conn_lookup(net, head, laddr, faddr, trans);
if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
@@ -147,7 +144,6 @@ static struct rds_connection *__rds_conn_create(struct net *net,
if (conn)
goto out;
-new_conn:
conn = kmem_cache_zalloc(rds_conn_slab, gfp);
if (!conn) {
conn = ERR_PTR(-ENOMEM);
@@ -207,6 +203,7 @@ new_conn:
atomic_set(&conn->c_state, RDS_CONN_DOWN);
conn->c_send_gen = 0;
+ conn->c_outgoing = (is_outgoing ? 1 : 0);
conn->c_reconnect_jiffies = 0;
INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker);
INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker);
@@ -243,22 +240,13 @@ new_conn:
/* Creating normal conn */
struct rds_connection *found;
- if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP)
- found = NULL;
- else
- found = rds_conn_lookup(net, head, laddr, faddr, trans);
+ found = rds_conn_lookup(net, head, laddr, faddr, trans);
if (found) {
trans->conn_free(conn->c_transport_data);
kmem_cache_free(rds_conn_slab, conn);
conn = found;
} else {
- if ((is_outgoing && otrans->t_type == RDS_TRANS_TCP) ||
- (otrans->t_type != RDS_TRANS_TCP)) {
- /* Only the active side should be added to
- * reconnect list for TCP.
- */
- hlist_add_head_rcu(&conn->c_hash_node, head);
- }
+ hlist_add_head_rcu(&conn->c_hash_node, head);
rds_cong_add_conn(conn);
rds_conn_count++;
}
@@ -337,7 +325,9 @@ void rds_conn_shutdown(struct rds_connection *conn)
rcu_read_lock();
if (!hlist_unhashed(&conn->c_hash_node)) {
rcu_read_unlock();
- rds_queue_reconnect(conn);
+ if (conn->c_trans->t_type != RDS_TRANS_TCP ||
+ conn->c_outgoing == 1)
+ rds_queue_reconnect(conn);
} else {
rcu_read_unlock();
}
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 2d3f2ab475df..a833ab7898fe 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -43,14 +43,14 @@
#include "rds.h"
#include "ib.h"
-static unsigned int fmr_pool_size = RDS_FMR_POOL_SIZE;
-unsigned int fmr_message_size = RDS_FMR_SIZE + 1; /* +1 allows for unaligned MRs */
+unsigned int rds_ib_fmr_1m_pool_size = RDS_FMR_1M_POOL_SIZE;
+unsigned int rds_ib_fmr_8k_pool_size = RDS_FMR_8K_POOL_SIZE;
unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT;
-module_param(fmr_pool_size, int, 0444);
-MODULE_PARM_DESC(fmr_pool_size, " Max number of fmr per HCA");
-module_param(fmr_message_size, int, 0444);
-MODULE_PARM_DESC(fmr_message_size, " Max size of a RDMA transfer");
+module_param(rds_ib_fmr_1m_pool_size, int, 0444);
+MODULE_PARM_DESC(rds_ib_fmr_1m_pool_size, " Max number of 1M fmr per HCA");
+module_param(rds_ib_fmr_8k_pool_size, int, 0444);
+MODULE_PARM_DESC(rds_ib_fmr_8k_pool_size, " Max number of 8K fmr per HCA");
module_param(rds_ib_retry_count, int, 0444);
MODULE_PARM_DESC(rds_ib_retry_count, " Number of hw retries before reporting an error");
@@ -97,8 +97,10 @@ static void rds_ib_dev_free(struct work_struct *work)
struct rds_ib_device *rds_ibdev = container_of(work,
struct rds_ib_device, free_work);
- if (rds_ibdev->mr_pool)
- rds_ib_destroy_mr_pool(rds_ibdev->mr_pool);
+ if (rds_ibdev->mr_8k_pool)
+ rds_ib_destroy_mr_pool(rds_ibdev->mr_8k_pool);
+ if (rds_ibdev->mr_1m_pool)
+ rds_ib_destroy_mr_pool(rds_ibdev->mr_1m_pool);
if (rds_ibdev->pd)
ib_dealloc_pd(rds_ibdev->pd);
@@ -148,9 +150,13 @@ static void rds_ib_add_one(struct ib_device *device)
rds_ibdev->max_sge = min(dev_attr->max_sge, RDS_IB_MAX_SGE);
rds_ibdev->fmr_max_remaps = dev_attr->max_map_per_fmr?: 32;
- rds_ibdev->max_fmrs = dev_attr->max_fmr ?
- min_t(unsigned int, dev_attr->max_fmr, fmr_pool_size) :
- fmr_pool_size;
+ rds_ibdev->max_1m_fmrs = dev_attr->max_mr ?
+ min_t(unsigned int, (dev_attr->max_mr / 2),
+ rds_ib_fmr_1m_pool_size) : rds_ib_fmr_1m_pool_size;
+
+ rds_ibdev->max_8k_fmrs = dev_attr->max_mr ?
+ min_t(unsigned int, ((dev_attr->max_mr / 2) * RDS_MR_8K_SCALE),
+ rds_ib_fmr_8k_pool_size) : rds_ib_fmr_8k_pool_size;
rds_ibdev->max_initiator_depth = dev_attr->max_qp_init_rd_atom;
rds_ibdev->max_responder_resources = dev_attr->max_qp_rd_atom;
@@ -162,12 +168,25 @@ static void rds_ib_add_one(struct ib_device *device)
goto put_dev;
}
- rds_ibdev->mr_pool = rds_ib_create_mr_pool(rds_ibdev);
- if (IS_ERR(rds_ibdev->mr_pool)) {
- rds_ibdev->mr_pool = NULL;
+ rds_ibdev->mr_1m_pool =
+ rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_1M_POOL);
+ if (IS_ERR(rds_ibdev->mr_1m_pool)) {
+ rds_ibdev->mr_1m_pool = NULL;
goto put_dev;
}
+ rds_ibdev->mr_8k_pool =
+ rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_8K_POOL);
+ if (IS_ERR(rds_ibdev->mr_8k_pool)) {
+ rds_ibdev->mr_8k_pool = NULL;
+ goto put_dev;
+ }
+
+ rdsdebug("RDS/IB: max_mr = %d, max_wrs = %d, max_sge = %d, fmr_max_remaps = %d, max_1m_fmrs = %d, max_8k_fmrs = %d\n",
+ dev_attr->max_fmr, rds_ibdev->max_wrs, rds_ibdev->max_sge,
+ rds_ibdev->fmr_max_remaps, rds_ibdev->max_1m_fmrs,
+ rds_ibdev->max_8k_fmrs);
+
INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
INIT_LIST_HEAD(&rds_ibdev->conn_list);
diff --git a/net/rds/ib.h b/net/rds/ib.h
index aae60fda77f6..f17d09567890 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -9,8 +9,11 @@
#include "rds.h"
#include "rdma_transport.h"
-#define RDS_FMR_SIZE 256
-#define RDS_FMR_POOL_SIZE 8192
+#define RDS_FMR_1M_POOL_SIZE (8192 / 2)
+#define RDS_FMR_1M_MSG_SIZE 256
+#define RDS_FMR_8K_MSG_SIZE 2
+#define RDS_MR_8K_SCALE (256 / (RDS_FMR_8K_MSG_SIZE + 1))
+#define RDS_FMR_8K_POOL_SIZE (RDS_MR_8K_SCALE * (8192 / 2))
#define RDS_IB_MAX_SGE 8
#define RDS_IB_RECV_SGE 2
@@ -24,6 +27,9 @@
#define RDS_IB_RECYCLE_BATCH_COUNT 32
+#define RDS_IB_WC_MAX 32
+#define RDS_IB_SEND_OP BIT_ULL(63)
+
extern struct rw_semaphore rds_ib_devices_lock;
extern struct list_head rds_ib_devices;
@@ -89,6 +95,20 @@ struct rds_ib_work_ring {
atomic_t w_free_ctr;
};
+/* Rings are posted with all the allocations they'll need to queue the
+ * incoming message to the receiving socket so this can't fail.
+ * All fragments start with a header, so we can make sure we're not receiving
+ * garbage, and we can tell a small 8 byte fragment from an ACK frame.
+ */
+struct rds_ib_ack_state {
+ u64 ack_next;
+ u64 ack_recv;
+ unsigned int ack_required:1;
+ unsigned int ack_next_valid:1;
+ unsigned int ack_recv_valid:1;
+};
+
+
struct rds_ib_device;
struct rds_ib_connection {
@@ -102,6 +122,12 @@ struct rds_ib_connection {
struct ib_pd *i_pd;
struct ib_cq *i_send_cq;
struct ib_cq *i_recv_cq;
+ struct ib_wc i_send_wc[RDS_IB_WC_MAX];
+ struct ib_wc i_recv_wc[RDS_IB_WC_MAX];
+
+ /* interrupt handling */
+ struct tasklet_struct i_send_tasklet;
+ struct tasklet_struct i_recv_tasklet;
/* tx */
struct rds_ib_work_ring i_send_ring;
@@ -112,7 +138,6 @@ struct rds_ib_connection {
atomic_t i_signaled_sends;
/* rx */
- struct tasklet_struct i_recv_tasklet;
struct mutex i_recv_mutex;
struct rds_ib_work_ring i_recv_ring;
struct rds_ib_incoming *i_ibinc;
@@ -164,6 +189,12 @@ struct rds_ib_connection {
struct rds_ib_ipaddr {
struct list_head list;
__be32 ipaddr;
+ struct rcu_head rcu;
+};
+
+enum {
+ RDS_IB_MR_8K_POOL,
+ RDS_IB_MR_1M_POOL,
};
struct rds_ib_device {
@@ -172,9 +203,12 @@ struct rds_ib_device {
struct list_head conn_list;
struct ib_device *dev;
struct ib_pd *pd;
- struct rds_ib_mr_pool *mr_pool;
- unsigned int fmr_max_remaps;
unsigned int max_fmrs;
+ struct rds_ib_mr_pool *mr_1m_pool;
+ struct rds_ib_mr_pool *mr_8k_pool;
+ unsigned int fmr_max_remaps;
+ unsigned int max_8k_fmrs;
+ unsigned int max_1m_fmrs;
int max_sge;
unsigned int max_wrs;
unsigned int max_initiator_depth;
@@ -197,14 +231,14 @@ struct rds_ib_device {
struct rds_ib_statistics {
uint64_t s_ib_connect_raced;
uint64_t s_ib_listen_closed_stale;
- uint64_t s_ib_tx_cq_call;
+ uint64_t s_ib_evt_handler_call;
+ uint64_t s_ib_tasklet_call;
uint64_t s_ib_tx_cq_event;
uint64_t s_ib_tx_ring_full;
uint64_t s_ib_tx_throttle;
uint64_t s_ib_tx_sg_mapping_failure;
uint64_t s_ib_tx_stalled;
uint64_t s_ib_tx_credit_updates;
- uint64_t s_ib_rx_cq_call;
uint64_t s_ib_rx_cq_event;
uint64_t s_ib_rx_ring_empty;
uint64_t s_ib_rx_refill_from_cq;
@@ -216,12 +250,18 @@ struct rds_ib_statistics {
uint64_t s_ib_ack_send_delayed;
uint64_t s_ib_ack_send_piggybacked;
uint64_t s_ib_ack_received;
- uint64_t s_ib_rdma_mr_alloc;
- uint64_t s_ib_rdma_mr_free;
- uint64_t s_ib_rdma_mr_used;
- uint64_t s_ib_rdma_mr_pool_flush;
- uint64_t s_ib_rdma_mr_pool_wait;
- uint64_t s_ib_rdma_mr_pool_depleted;
+ uint64_t s_ib_rdma_mr_8k_alloc;
+ uint64_t s_ib_rdma_mr_8k_free;
+ uint64_t s_ib_rdma_mr_8k_used;
+ uint64_t s_ib_rdma_mr_8k_pool_flush;
+ uint64_t s_ib_rdma_mr_8k_pool_wait;
+ uint64_t s_ib_rdma_mr_8k_pool_depleted;
+ uint64_t s_ib_rdma_mr_1m_alloc;
+ uint64_t s_ib_rdma_mr_1m_free;
+ uint64_t s_ib_rdma_mr_1m_used;
+ uint64_t s_ib_rdma_mr_1m_pool_flush;
+ uint64_t s_ib_rdma_mr_1m_pool_wait;
+ uint64_t s_ib_rdma_mr_1m_pool_depleted;
uint64_t s_ib_atomic_cswp;
uint64_t s_ib_atomic_fadd;
};
@@ -273,7 +313,8 @@ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device);
void rds_ib_dev_put(struct rds_ib_device *rds_ibdev);
extern struct ib_client rds_ib_client;
-extern unsigned int fmr_message_size;
+extern unsigned int rds_ib_fmr_1m_pool_size;
+extern unsigned int rds_ib_fmr_8k_pool_size;
extern unsigned int rds_ib_retry_count;
extern spinlock_t ib_nodev_conns_lock;
@@ -303,7 +344,8 @@ int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr);
void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
void rds_ib_destroy_nodev_conns(void);
-struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *);
+struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev,
+ int npages);
void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo);
void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
@@ -323,7 +365,8 @@ void rds_ib_recv_free_caches(struct rds_ib_connection *ic);
void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp);
void rds_ib_inc_free(struct rds_incoming *inc);
int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
-void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context);
+void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc,
+ struct rds_ib_ack_state *state);
void rds_ib_recv_tasklet_fn(unsigned long data);
void rds_ib_recv_init_ring(struct rds_ib_connection *ic);
void rds_ib_recv_clear_ring(struct rds_ib_connection *ic);
@@ -331,6 +374,7 @@ void rds_ib_recv_init_ack(struct rds_ib_connection *ic);
void rds_ib_attempt_ack(struct rds_ib_connection *ic);
void rds_ib_ack_send_complete(struct rds_ib_connection *ic);
u64 rds_ib_piggyb_ack(struct rds_ib_connection *ic);
+void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq, int ack_required);
/* ib_ring.c */
void rds_ib_ring_init(struct rds_ib_work_ring *ring, u32 nr);
@@ -348,7 +392,7 @@ extern wait_queue_head_t rds_ib_ring_empty_wait;
void rds_ib_xmit_complete(struct rds_connection *conn);
int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
unsigned int hdr_off, unsigned int sg, unsigned int off);
-void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context);
+void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc);
void rds_ib_send_init_ring(struct rds_ib_connection *ic);
void rds_ib_send_clear_ring(struct rds_ib_connection *ic);
int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 9043f5c04787..2b2370e7f356 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -216,6 +216,96 @@ static void rds_ib_cq_event_handler(struct ib_event *event, void *data)
event->event, ib_event_msg(event->event), data);
}
+/* Plucking the oldest entry from the ring can be done concurrently with
+ * the thread refilling the ring. Each ring operation is protected by
+ * spinlocks and the transient state of refilling doesn't change the
+ * recording of which entry is oldest.
+ *
+ * This relies on IB only calling one cq comp_handler for each cq so that
+ * there will only be one caller of rds_recv_incoming() per RDS connection.
+ */
+static void rds_ib_cq_comp_handler_recv(struct ib_cq *cq, void *context)
+{
+ struct rds_connection *conn = context;
+ struct rds_ib_connection *ic = conn->c_transport_data;
+
+ rdsdebug("conn %p cq %p\n", conn, cq);
+
+ rds_ib_stats_inc(s_ib_evt_handler_call);
+
+ tasklet_schedule(&ic->i_recv_tasklet);
+}
+
+static void poll_cq(struct rds_ib_connection *ic, struct ib_cq *cq,
+ struct ib_wc *wcs,
+ struct rds_ib_ack_state *ack_state)
+{
+ int nr;
+ int i;
+ struct ib_wc *wc;
+
+ while ((nr = ib_poll_cq(cq, RDS_IB_WC_MAX, wcs)) > 0) {
+ for (i = 0; i < nr; i++) {
+ wc = wcs + i;
+ rdsdebug("wc wr_id 0x%llx status %u byte_len %u imm_data %u\n",
+ (unsigned long long)wc->wr_id, wc->status,
+ wc->byte_len, be32_to_cpu(wc->ex.imm_data));
+
+ if (wc->wr_id & RDS_IB_SEND_OP)
+ rds_ib_send_cqe_handler(ic, wc);
+ else
+ rds_ib_recv_cqe_handler(ic, wc, ack_state);
+ }
+ }
+}
+
+static void rds_ib_tasklet_fn_send(unsigned long data)
+{
+ struct rds_ib_connection *ic = (struct rds_ib_connection *)data;
+ struct rds_connection *conn = ic->conn;
+ struct rds_ib_ack_state state;
+
+ rds_ib_stats_inc(s_ib_tasklet_call);
+
+ memset(&state, 0, sizeof(state));
+ poll_cq(ic, ic->i_send_cq, ic->i_send_wc, &state);
+ ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP);
+ poll_cq(ic, ic->i_send_cq, ic->i_send_wc, &state);
+
+ if (rds_conn_up(conn) &&
+ (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags) ||
+ test_bit(0, &conn->c_map_queued)))
+ rds_send_xmit(ic->conn);
+}
+
+static void rds_ib_tasklet_fn_recv(unsigned long data)
+{
+ struct rds_ib_connection *ic = (struct rds_ib_connection *)data;
+ struct rds_connection *conn = ic->conn;
+ struct rds_ib_device *rds_ibdev = ic->rds_ibdev;
+ struct rds_ib_ack_state state;
+
+ if (!rds_ibdev)
+ rds_conn_drop(conn);
+
+ rds_ib_stats_inc(s_ib_tasklet_call);
+
+ memset(&state, 0, sizeof(state));
+ poll_cq(ic, ic->i_recv_cq, ic->i_recv_wc, &state);
+ ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
+ poll_cq(ic, ic->i_recv_cq, ic->i_recv_wc, &state);
+
+ if (state.ack_next_valid)
+ rds_ib_set_ack(ic, state.ack_next, state.ack_required);
+ if (state.ack_recv_valid && state.ack_recv > ic->i_ack_recv) {
+ rds_send_drop_acked(conn, state.ack_recv, NULL);
+ ic->i_ack_recv = state.ack_recv;
+ }
+
+ if (rds_conn_up(conn))
+ rds_ib_attempt_ack(ic);
+}
+
static void rds_ib_qp_event_handler(struct ib_event *event, void *data)
{
struct rds_connection *conn = data;
@@ -238,6 +328,18 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data)
}
}
+static void rds_ib_cq_comp_handler_send(struct ib_cq *cq, void *context)
+{
+ struct rds_connection *conn = context;
+ struct rds_ib_connection *ic = conn->c_transport_data;
+
+ rdsdebug("conn %p cq %p\n", conn, cq);
+
+ rds_ib_stats_inc(s_ib_evt_handler_call);
+
+ tasklet_schedule(&ic->i_send_tasklet);
+}
+
/*
* This needs to be very careful to not leave IS_ERR pointers around for
* cleanup to trip over.
@@ -271,7 +373,8 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_pd = rds_ibdev->pd;
cq_attr.cqe = ic->i_send_ring.w_nr + 1;
- ic->i_send_cq = ib_create_cq(dev, rds_ib_send_cq_comp_handler,
+
+ ic->i_send_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_send,
rds_ib_cq_event_handler, conn,
&cq_attr);
if (IS_ERR(ic->i_send_cq)) {
@@ -282,7 +385,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
}
cq_attr.cqe = ic->i_recv_ring.w_nr;
- ic->i_recv_cq = ib_create_cq(dev, rds_ib_recv_cq_comp_handler,
+ ic->i_recv_cq = ib_create_cq(dev, rds_ib_cq_comp_handler_recv,
rds_ib_cq_event_handler, conn,
&cq_attr);
if (IS_ERR(ic->i_recv_cq)) {
@@ -637,6 +740,7 @@ void rds_ib_conn_shutdown(struct rds_connection *conn)
wait_event(rds_ib_ring_empty_wait,
rds_ib_ring_empty(&ic->i_recv_ring) &&
(atomic_read(&ic->i_signaled_sends) == 0));
+ tasklet_kill(&ic->i_send_tasklet);
tasklet_kill(&ic->i_recv_tasklet);
/* first destroy the ib state that generates callbacks */
@@ -743,8 +847,10 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
}
INIT_LIST_HEAD(&ic->ib_node);
- tasklet_init(&ic->i_recv_tasklet, rds_ib_recv_tasklet_fn,
- (unsigned long) ic);
+ tasklet_init(&ic->i_send_tasklet, rds_ib_tasklet_fn_send,
+ (unsigned long)ic);
+ tasklet_init(&ic->i_recv_tasklet, rds_ib_tasklet_fn_recv,
+ (unsigned long)ic);
mutex_init(&ic->i_recv_mutex);
#ifndef KERNEL_HAS_ATOMIC64
spin_lock_init(&ic->i_ack_lock);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 251d1ce0b7c7..a2340748ec86 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -65,6 +65,7 @@ struct rds_ib_mr {
* Our own little FMR pool
*/
struct rds_ib_mr_pool {
+ unsigned int pool_type;
struct mutex flush_lock; /* serialize fmr invalidate */
struct delayed_work flush_worker; /* flush worker */
@@ -83,7 +84,7 @@ struct rds_ib_mr_pool {
struct ib_fmr_attr fmr_attr;
};
-struct workqueue_struct *rds_ib_fmr_wq;
+static struct workqueue_struct *rds_ib_fmr_wq;
int rds_ib_fmr_init(void)
{
@@ -159,10 +160,8 @@ static void rds_ib_remove_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
}
spin_unlock_irq(&rds_ibdev->spinlock);
- if (to_free) {
- synchronize_rcu();
- kfree(to_free);
- }
+ if (to_free)
+ kfree_rcu(to_free, rcu);
}
int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
@@ -236,7 +235,8 @@ void rds_ib_destroy_nodev_conns(void)
rds_conn_destroy(ic->conn);
}
-struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev)
+struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev,
+ int pool_type)
{
struct rds_ib_mr_pool *pool;
@@ -244,6 +244,7 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev)
if (!pool)
return ERR_PTR(-ENOMEM);
+ pool->pool_type = pool_type;
init_llist_head(&pool->free_list);
init_llist_head(&pool->drop_list);
init_llist_head(&pool->clean_list);
@@ -251,28 +252,30 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev)
init_waitqueue_head(&pool->flush_wait);
INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker);
- pool->fmr_attr.max_pages = fmr_message_size;
+ if (pool_type == RDS_IB_MR_1M_POOL) {
+ /* +1 allows for unaligned MRs */
+ pool->fmr_attr.max_pages = RDS_FMR_1M_MSG_SIZE + 1;
+ pool->max_items = RDS_FMR_1M_POOL_SIZE;
+ } else {
+ /* pool_type == RDS_IB_MR_8K_POOL */
+ pool->fmr_attr.max_pages = RDS_FMR_8K_MSG_SIZE + 1;
+ pool->max_items = RDS_FMR_8K_POOL_SIZE;
+ }
+
+ pool->max_free_pinned = pool->max_items * pool->fmr_attr.max_pages / 4;
pool->fmr_attr.max_maps = rds_ibdev->fmr_max_remaps;
pool->fmr_attr.page_shift = PAGE_SHIFT;
- pool->max_free_pinned = rds_ibdev->max_fmrs * fmr_message_size / 4;
-
- /* We never allow more than max_items MRs to be allocated.
- * When we exceed more than max_items_soft, we start freeing
- * items more aggressively.
- * Make sure that max_items > max_items_soft > max_items / 2
- */
pool->max_items_soft = rds_ibdev->max_fmrs * 3 / 4;
- pool->max_items = rds_ibdev->max_fmrs;
return pool;
}
void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo)
{
- struct rds_ib_mr_pool *pool = rds_ibdev->mr_pool;
+ struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool;
- iinfo->rdma_mr_max = pool->max_items;
- iinfo->rdma_mr_size = pool->fmr_attr.max_pages;
+ iinfo->rdma_mr_max = pool_1m->max_items;
+ iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages;
}
void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool)
@@ -314,14 +317,28 @@ static inline void wait_clean_list_grace(void)
}
}
-static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev)
+static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev,
+ int npages)
{
- struct rds_ib_mr_pool *pool = rds_ibdev->mr_pool;
+ struct rds_ib_mr_pool *pool;
struct rds_ib_mr *ibmr = NULL;
int err = 0, iter = 0;
+ if (npages <= RDS_FMR_8K_MSG_SIZE)
+ pool = rds_ibdev->mr_8k_pool;
+ else
+ pool = rds_ibdev->mr_1m_pool;
+
if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
- schedule_delayed_work(&pool->flush_worker, 10);
+ queue_delayed_work(rds_ib_fmr_wq, &pool->flush_worker, 10);
+
+ /* Switch pools if one of the pool is reaching upper limit */
+ if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) {
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ pool = rds_ibdev->mr_1m_pool;
+ else
+ pool = rds_ibdev->mr_8k_pool;
+ }
while (1) {
ibmr = rds_ib_reuse_fmr(pool);
@@ -343,12 +360,18 @@ static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev)
atomic_dec(&pool->item_count);
if (++iter > 2) {
- rds_ib_stats_inc(s_ib_rdma_mr_pool_depleted);
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_depleted);
+ else
+ rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_depleted);
return ERR_PTR(-EAGAIN);
}
/* We do have some empty MRs. Flush them out. */
- rds_ib_stats_inc(s_ib_rdma_mr_pool_wait);
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_wait);
+ else
+ rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_wait);
rds_ib_flush_mr_pool(pool, 0, &ibmr);
if (ibmr)
return ibmr;
@@ -373,7 +396,12 @@ static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev)
goto out_no_cigar;
}
- rds_ib_stats_inc(s_ib_rdma_mr_alloc);
+ ibmr->pool = pool;
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ rds_ib_stats_inc(s_ib_rdma_mr_8k_alloc);
+ else
+ rds_ib_stats_inc(s_ib_rdma_mr_1m_alloc);
+
return ibmr;
out_no_cigar:
@@ -429,7 +457,7 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibm
}
page_cnt += len >> PAGE_SHIFT;
- if (page_cnt > fmr_message_size)
+ if (page_cnt > ibmr->pool->fmr_attr.max_pages)
return -EINVAL;
dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC,
@@ -461,7 +489,10 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, struct rds_ib_mr *ibm
ibmr->sg_dma_len = sg_dma_len;
ibmr->remap_count++;
- rds_ib_stats_inc(s_ib_rdma_mr_used);
+ if (ibmr->pool->pool_type == RDS_IB_MR_8K_POOL)
+ rds_ib_stats_inc(s_ib_rdma_mr_8k_used);
+ else
+ rds_ib_stats_inc(s_ib_rdma_mr_1m_used);
ret = 0;
out:
@@ -524,8 +555,7 @@ static void rds_ib_teardown_mr(struct rds_ib_mr *ibmr)
__rds_ib_teardown_mr(ibmr);
if (pinned) {
- struct rds_ib_device *rds_ibdev = ibmr->device;
- struct rds_ib_mr_pool *pool = rds_ibdev->mr_pool;
+ struct rds_ib_mr_pool *pool = ibmr->pool;
atomic_sub(pinned, &pool->free_pinned);
}
@@ -594,7 +624,7 @@ static void list_to_llist_nodes(struct rds_ib_mr_pool *pool,
* to free as many MRs as needed to get back to this limit.
*/
static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
- int free_all, struct rds_ib_mr **ibmr_ret)
+ int free_all, struct rds_ib_mr **ibmr_ret)
{
struct rds_ib_mr *ibmr, *next;
struct llist_node *clean_nodes;
@@ -605,11 +635,14 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
unsigned int nfreed = 0, dirty_to_clean = 0, free_goal;
int ret = 0;
- rds_ib_stats_inc(s_ib_rdma_mr_pool_flush);
+ if (pool->pool_type == RDS_IB_MR_8K_POOL)
+ rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_flush);
+ else
+ rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_flush);
if (ibmr_ret) {
DEFINE_WAIT(wait);
- while(!mutex_trylock(&pool->flush_lock)) {
+ while (!mutex_trylock(&pool->flush_lock)) {
ibmr = rds_ib_reuse_fmr(pool);
if (ibmr) {
*ibmr_ret = ibmr;
@@ -666,8 +699,12 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
list_for_each_entry_safe(ibmr, next, &unmap_list, unmap_list) {
unpinned += ibmr->sg_len;
__rds_ib_teardown_mr(ibmr);
- if (nfreed < free_goal || ibmr->remap_count >= pool->fmr_attr.max_maps) {
- rds_ib_stats_inc(s_ib_rdma_mr_free);
+ if (nfreed < free_goal ||
+ ibmr->remap_count >= pool->fmr_attr.max_maps) {
+ if (ibmr->pool->pool_type == RDS_IB_MR_8K_POOL)
+ rds_ib_stats_inc(s_ib_rdma_mr_8k_free);
+ else
+ rds_ib_stats_inc(s_ib_rdma_mr_1m_free);
list_del(&ibmr->unmap_list);
ib_dealloc_fmr(ibmr->fmr);
kfree(ibmr);
@@ -719,8 +756,8 @@ static void rds_ib_mr_pool_flush_worker(struct work_struct *work)
void rds_ib_free_mr(void *trans_private, int invalidate)
{
struct rds_ib_mr *ibmr = trans_private;
+ struct rds_ib_mr_pool *pool = ibmr->pool;
struct rds_ib_device *rds_ibdev = ibmr->device;
- struct rds_ib_mr_pool *pool = rds_ibdev->mr_pool;
rdsdebug("RDS/IB: free_mr nents %u\n", ibmr->sg_len);
@@ -759,10 +796,11 @@ void rds_ib_flush_mrs(void)
down_read(&rds_ib_devices_lock);
list_for_each_entry(rds_ibdev, &rds_ib_devices, list) {
- struct rds_ib_mr_pool *pool = rds_ibdev->mr_pool;
+ if (rds_ibdev->mr_8k_pool)
+ rds_ib_flush_mr_pool(rds_ibdev->mr_8k_pool, 0, NULL);
- if (pool)
- rds_ib_flush_mr_pool(pool, 0, NULL);
+ if (rds_ibdev->mr_1m_pool)
+ rds_ib_flush_mr_pool(rds_ibdev->mr_1m_pool, 0, NULL);
}
up_read(&rds_ib_devices_lock);
}
@@ -780,12 +818,12 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
goto out;
}
- if (!rds_ibdev->mr_pool) {
+ if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) {
ret = -ENODEV;
goto out;
}
- ibmr = rds_ib_alloc_fmr(rds_ibdev);
+ ibmr = rds_ib_alloc_fmr(rds_ibdev, nents);
if (IS_ERR(ibmr)) {
rds_ib_dev_put(rds_ibdev);
return ibmr;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index f43831e4186a..96744b75db93 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -596,8 +596,7 @@ void rds_ib_recv_init_ack(struct rds_ib_connection *ic)
* wr_id and avoids working with the ring in that case.
*/
#ifndef KERNEL_HAS_ATOMIC64
-static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq,
- int ack_required)
+void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq, int ack_required)
{
unsigned long flags;
@@ -622,8 +621,7 @@ static u64 rds_ib_get_ack(struct rds_ib_connection *ic)
return seq;
}
#else
-static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq,
- int ack_required)
+void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq, int ack_required)
{
atomic64_set(&ic->i_ack_next, seq);
if (ack_required) {
@@ -830,20 +828,6 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
rds_cong_map_updated(map, uncongested);
}
-/*
- * Rings are posted with all the allocations they'll need to queue the
- * incoming message to the receiving socket so this can't fail.
- * All fragments start with a header, so we can make sure we're not receiving
- * garbage, and we can tell a small 8 byte fragment from an ACK frame.
- */
-struct rds_ib_ack_state {
- u64 ack_next;
- u64 ack_recv;
- unsigned int ack_required:1;
- unsigned int ack_next_valid:1;
- unsigned int ack_recv_valid:1;
-};
-
static void rds_ib_process_recv(struct rds_connection *conn,
struct rds_ib_recv_work *recv, u32 data_len,
struct rds_ib_ack_state *state)
@@ -969,96 +953,50 @@ static void rds_ib_process_recv(struct rds_connection *conn,
}
}
-/*
- * Plucking the oldest entry from the ring can be done concurrently with
- * the thread refilling the ring. Each ring operation is protected by
- * spinlocks and the transient state of refilling doesn't change the
- * recording of which entry is oldest.
- *
- * This relies on IB only calling one cq comp_handler for each cq so that
- * there will only be one caller of rds_recv_incoming() per RDS connection.
- */
-void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context)
-{
- struct rds_connection *conn = context;
- struct rds_ib_connection *ic = conn->c_transport_data;
-
- rdsdebug("conn %p cq %p\n", conn, cq);
-
- rds_ib_stats_inc(s_ib_rx_cq_call);
-
- tasklet_schedule(&ic->i_recv_tasklet);
-}
-
-static inline void rds_poll_cq(struct rds_ib_connection *ic,
- struct rds_ib_ack_state *state)
+void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
+ struct ib_wc *wc,
+ struct rds_ib_ack_state *state)
{
struct rds_connection *conn = ic->conn;
- struct ib_wc wc;
struct rds_ib_recv_work *recv;
- while (ib_poll_cq(ic->i_recv_cq, 1, &wc) > 0) {
- rdsdebug("wc wr_id 0x%llx status %u (%s) byte_len %u imm_data %u\n",
- (unsigned long long)wc.wr_id, wc.status,
- ib_wc_status_msg(wc.status), wc.byte_len,
- be32_to_cpu(wc.ex.imm_data));
- rds_ib_stats_inc(s_ib_rx_cq_event);
+ rdsdebug("wc wr_id 0x%llx status %u (%s) byte_len %u imm_data %u\n",
+ (unsigned long long)wc->wr_id, wc->status,
+ ib_wc_status_msg(wc->status), wc->byte_len,
+ be32_to_cpu(wc->ex.imm_data));
- recv = &ic->i_recvs[rds_ib_ring_oldest(&ic->i_recv_ring)];
-
- ib_dma_unmap_sg(ic->i_cm_id->device, &recv->r_frag->f_sg, 1, DMA_FROM_DEVICE);
-
- /*
- * Also process recvs in connecting state because it is possible
- * to get a recv completion _before_ the rdmacm ESTABLISHED
- * event is processed.
- */
- if (wc.status == IB_WC_SUCCESS) {
- rds_ib_process_recv(conn, recv, wc.byte_len, state);
- } else {
- /* We expect errors as the qp is drained during shutdown */
- if (rds_conn_up(conn) || rds_conn_connecting(conn))
- rds_ib_conn_error(conn, "recv completion on %pI4 had "
- "status %u (%s), disconnecting and "
- "reconnecting\n", &conn->c_faddr,
- wc.status,
- ib_wc_status_msg(wc.status));
- }
+ rds_ib_stats_inc(s_ib_rx_cq_event);
+ recv = &ic->i_recvs[rds_ib_ring_oldest(&ic->i_recv_ring)];
+ ib_dma_unmap_sg(ic->i_cm_id->device, &recv->r_frag->f_sg, 1,
+ DMA_FROM_DEVICE);
- /*
- * rds_ib_process_recv() doesn't always consume the frag, and
- * we might not have called it at all if the wc didn't indicate
- * success. We already unmapped the frag's pages, though, and
- * the following rds_ib_ring_free() call tells the refill path
- * that it will not find an allocated frag here. Make sure we
- * keep that promise by freeing a frag that's still on the ring.
- */
- if (recv->r_frag) {
- rds_ib_frag_free(ic, recv->r_frag);
- recv->r_frag = NULL;
- }
- rds_ib_ring_free(&ic->i_recv_ring, 1);
+ /* Also process recvs in connecting state because it is possible
+ * to get a recv completion _before_ the rdmacm ESTABLISHED
+ * event is processed.
+ */
+ if (wc->status == IB_WC_SUCCESS) {
+ rds_ib_process_recv(conn, recv, wc->byte_len, state);
+ } else {
+ /* We expect errors as the qp is drained during shutdown */
+ if (rds_conn_up(conn) || rds_conn_connecting(conn))
+ rds_ib_conn_error(conn, "recv completion on %pI4 had status %u (%s), disconnecting and reconnecting\n",
+ &conn->c_faddr,
+ wc->status,
+ ib_wc_status_msg(wc->status));
}
-}
-void rds_ib_recv_tasklet_fn(unsigned long data)
-{
- struct rds_ib_connection *ic = (struct rds_ib_connection *) data;
- struct rds_connection *conn = ic->conn;
- struct rds_ib_ack_state state = { 0, };
-
- rds_poll_cq(ic, &state);
- ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED);
- rds_poll_cq(ic, &state);
-
- if (state.ack_next_valid)
- rds_ib_set_ack(ic, state.ack_next, state.ack_required);
- if (state.ack_recv_valid && state.ack_recv > ic->i_ack_recv) {
- rds_send_drop_acked(conn, state.ack_recv, NULL);
- ic->i_ack_recv = state.ack_recv;
+ /* rds_ib_process_recv() doesn't always consume the frag, and
+ * we might not have called it at all if the wc didn't indicate
+ * success. We already unmapped the frag's pages, though, and
+ * the following rds_ib_ring_free() call tells the refill path
+ * that it will not find an allocated frag here. Make sure we
+ * keep that promise by freeing a frag that's still on the ring.
+ */
+ if (recv->r_frag) {
+ rds_ib_frag_free(ic, recv->r_frag);
+ recv->r_frag = NULL;
}
- if (rds_conn_up(conn))
- rds_ib_attempt_ack(ic);
+ rds_ib_ring_free(&ic->i_recv_ring, 1);
/* If we ever end up with a really empty receive ring, we're
* in deep trouble, as the sender will definitely see RNR
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 4e88047086b6..670882c752e9 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -195,7 +195,7 @@ void rds_ib_send_init_ring(struct rds_ib_connection *ic)
send->s_op = NULL;
- send->s_wr.wr_id = i;
+ send->s_wr.wr_id = i | RDS_IB_SEND_OP;
send->s_wr.sg_list = send->s_sge;
send->s_wr.ex.imm_data = 0;
@@ -237,81 +237,73 @@ static void rds_ib_sub_signaled(struct rds_ib_connection *ic, int nr)
* unallocs the next free entry in the ring it doesn't alter which is
* the next to be freed, which is what this is concerned with.
*/
-void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context)
+void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
{
- struct rds_connection *conn = context;
- struct rds_ib_connection *ic = conn->c_transport_data;
struct rds_message *rm = NULL;
- struct ib_wc wc;
+ struct rds_connection *conn = ic->conn;
struct rds_ib_send_work *send;
u32 completed;
u32 oldest;
u32 i = 0;
- int ret;
int nr_sig = 0;
- rdsdebug("cq %p conn %p\n", cq, conn);
- rds_ib_stats_inc(s_ib_tx_cq_call);
- ret = ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
- if (ret)
- rdsdebug("ib_req_notify_cq send failed: %d\n", ret);
-
- while (ib_poll_cq(cq, 1, &wc) > 0) {
- rdsdebug("wc wr_id 0x%llx status %u (%s) byte_len %u imm_data %u\n",
- (unsigned long long)wc.wr_id, wc.status,
- ib_wc_status_msg(wc.status), wc.byte_len,
- be32_to_cpu(wc.ex.imm_data));
- rds_ib_stats_inc(s_ib_tx_cq_event);
-
- if (wc.wr_id == RDS_IB_ACK_WR_ID) {
- if (time_after(jiffies, ic->i_ack_queued + HZ/2))
- rds_ib_stats_inc(s_ib_tx_stalled);
- rds_ib_ack_send_complete(ic);
- continue;
- }
- oldest = rds_ib_ring_oldest(&ic->i_send_ring);
+ rdsdebug("wc wr_id 0x%llx status %u (%s) byte_len %u imm_data %u\n",
+ (unsigned long long)wc->wr_id, wc->status,
+ ib_wc_status_msg(wc->status), wc->byte_len,
+ be32_to_cpu(wc->ex.imm_data));
+ rds_ib_stats_inc(s_ib_tx_cq_event);
- completed = rds_ib_ring_completed(&ic->i_send_ring, wc.wr_id, oldest);
+ if (wc->wr_id == RDS_IB_ACK_WR_ID) {
+ if (time_after(jiffies, ic->i_ack_queued + HZ / 2))
+ rds_ib_stats_inc(s_ib_tx_stalled);
+ rds_ib_ack_send_complete(ic);
+ return;
+ }
- for (i = 0; i < completed; i++) {
- send = &ic->i_sends[oldest];
- if (send->s_wr.send_flags & IB_SEND_SIGNALED)
- nr_sig++;
+ oldest = rds_ib_ring_oldest(&ic->i_send_ring);
- rm = rds_ib_send_unmap_op(ic, send, wc.status);
+ completed = rds_ib_ring_completed(&ic->i_send_ring,
+ (wc->wr_id & ~RDS_IB_SEND_OP),
+ oldest);
- if (time_after(jiffies, send->s_queued + HZ/2))
- rds_ib_stats_inc(s_ib_tx_stalled);
+ for (i = 0; i < completed; i++) {
+ send = &ic->i_sends[oldest];
+ if (send->s_wr.send_flags & IB_SEND_SIGNALED)
+ nr_sig++;
- if (send->s_op) {
- if (send->s_op == rm->m_final_op) {
- /* If anyone waited for this message to get flushed out, wake
- * them up now */
- rds_message_unmapped(rm);
- }
- rds_message_put(rm);
- send->s_op = NULL;
- }
+ rm = rds_ib_send_unmap_op(ic, send, wc->status);
- oldest = (oldest + 1) % ic->i_send_ring.w_nr;
- }
+ if (time_after(jiffies, send->s_queued + HZ / 2))
+ rds_ib_stats_inc(s_ib_tx_stalled);
- rds_ib_ring_free(&ic->i_send_ring, completed);
- rds_ib_sub_signaled(ic, nr_sig);
- nr_sig = 0;
-
- if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags) ||
- test_bit(0, &conn->c_map_queued))
- queue_delayed_work(rds_wq, &conn->c_send_w, 0);
-
- /* We expect errors as the qp is drained during shutdown */
- if (wc.status != IB_WC_SUCCESS && rds_conn_up(conn)) {
- rds_ib_conn_error(conn, "send completion on %pI4 had status "
- "%u (%s), disconnecting and reconnecting\n",
- &conn->c_faddr, wc.status,
- ib_wc_status_msg(wc.status));
+ if (send->s_op) {
+ if (send->s_op == rm->m_final_op) {
+ /* If anyone waited for this message to get
+ * flushed out, wake them up now
+ */
+ rds_message_unmapped(rm);
+ }
+ rds_message_put(rm);
+ send->s_op = NULL;
}
+
+ oldest = (oldest + 1) % ic->i_send_ring.w_nr;
+ }
+
+ rds_ib_ring_free(&ic->i_send_ring, completed);
+ rds_ib_sub_signaled(ic, nr_sig);
+ nr_sig = 0;
+
+ if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags) ||
+ test_bit(0, &conn->c_map_queued))
+ queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+
+ /* We expect errors as the qp is drained during shutdown */
+ if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) {
+ rds_ib_conn_error(conn, "send completion on %pI4 had status %u (%s), disconnecting and reconnecting\n",
+ &conn->c_faddr, wc->status,
+ ib_wc_status_msg(wc->status));
}
}
diff --git a/net/rds/ib_stats.c b/net/rds/ib_stats.c
index 2d5965d6e97c..d77e04473056 100644
--- a/net/rds/ib_stats.c
+++ b/net/rds/ib_stats.c
@@ -42,14 +42,14 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats);
static const char *const rds_ib_stat_names[] = {
"ib_connect_raced",
"ib_listen_closed_stale",
- "ib_tx_cq_call",
+ "s_ib_evt_handler_call",
+ "ib_tasklet_call",
"ib_tx_cq_event",
"ib_tx_ring_full",
"ib_tx_throttle",
"ib_tx_sg_mapping_failure",
"ib_tx_stalled",
"ib_tx_credit_updates",
- "ib_rx_cq_call",
"ib_rx_cq_event",
"ib_rx_ring_empty",
"ib_rx_refill_from_cq",
@@ -61,12 +61,18 @@ static const char *const rds_ib_stat_names[] = {
"ib_ack_send_delayed",
"ib_ack_send_piggybacked",
"ib_ack_received",
- "ib_rdma_mr_alloc",
- "ib_rdma_mr_free",
- "ib_rdma_mr_used",
- "ib_rdma_mr_pool_flush",
- "ib_rdma_mr_pool_wait",
- "ib_rdma_mr_pool_depleted",
+ "ib_rdma_mr_8k_alloc",
+ "ib_rdma_mr_8k_free",
+ "ib_rdma_mr_8k_used",
+ "ib_rdma_mr_8k_pool_flush",
+ "ib_rdma_mr_8k_pool_wait",
+ "ib_rdma_mr_8k_pool_depleted",
+ "ib_rdma_mr_1m_alloc",
+ "ib_rdma_mr_1m_free",
+ "ib_rdma_mr_1m_used",
+ "ib_rdma_mr_1m_pool_flush",
+ "ib_rdma_mr_1m_pool_wait",
+ "ib_rdma_mr_1m_pool_depleted",
"ib_atomic_cswp",
"ib_atomic_fadd",
};
diff --git a/net/rds/rds.h b/net/rds/rds.h
index afb4048d0cfd..543c308fcc2a 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -86,7 +86,9 @@ struct rds_connection {
struct hlist_node c_hash_node;
__be32 c_laddr;
__be32 c_faddr;
- unsigned int c_loopback:1;
+ unsigned int c_loopback:1,
+ c_outgoing:1,
+ c_pad_to_32:30;
struct rds_connection *c_passive;
struct rds_cong_map *c_lcong;
@@ -603,6 +605,7 @@ extern wait_queue_head_t rds_poll_waitq;
int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
void rds_remove_bound(struct rds_sock *rs);
struct rds_sock *rds_find_bound(__be32 addr, __be16 port);
+void rds_bind_lock_init(void);
/* cong.c */
int rds_cong_get_maps(struct rds_connection *conn);
diff --git a/net/rds/send.c b/net/rds/send.c
index 4df61a515b83..ee49c2556f47 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -38,6 +38,7 @@
#include <linux/list.h>
#include <linux/ratelimit.h>
#include <linux/export.h>
+#include <linux/sizes.h>
#include "rds.h"
@@ -51,7 +52,7 @@
* it to 0 will restore the old behavior (where we looped until we had
* drained the queue).
*/
-static int send_batch_count = 64;
+static int send_batch_count = SZ_1K;
module_param(send_batch_count, int, 0444);
MODULE_PARM_DESC(send_batch_count, " batch factor when working the send queue");
@@ -223,7 +224,7 @@ restart:
* through a lot of messages, lets back off and see
* if anyone else jumps in
*/
- if (batch_count >= 1024)
+ if (batch_count >= send_batch_count)
goto over_batch;
spin_lock_irqsave(&conn->c_lock, flags);
@@ -423,12 +424,15 @@ over_batch:
!list_empty(&conn->c_send_queue)) &&
send_gen == conn->c_send_gen) {
rds_stats_inc(s_send_lock_queue_raced);
- goto restart;
+ if (batch_count < send_batch_count)
+ goto restart;
+ queue_delayed_work(rds_wq, &conn->c_send_w, 1);
}
}
out:
return ret;
}
+EXPORT_SYMBOL_GPL(rds_send_xmit);
static void rds_send_sndbuf_remove(struct rds_sock *rs, struct rds_message *rm)
{
@@ -1120,8 +1124,9 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
*/
rds_stats_inc(s_send_queued);
- if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
- rds_send_xmit(conn);
+ ret = rds_send_xmit(conn);
+ if (ret == -ENOMEM || ret == -EAGAIN)
+ queue_delayed_work(rds_wq, &conn->c_send_w, 1);
rds_message_put(rm);
return payload_len;
@@ -1177,8 +1182,9 @@ rds_send_pong(struct rds_connection *conn, __be16 dport)
rds_stats_inc(s_send_queued);
rds_stats_inc(s_send_pong);
- if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
- queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+ ret = rds_send_xmit(conn);
+ if (ret == -ENOMEM || ret == -EAGAIN)
+ queue_delayed_work(rds_wq, &conn->c_send_w, 1);
rds_message_put(rm);
return 0;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index c42b60bf4c68..9d6ddbacd875 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -67,21 +67,13 @@ void rds_tcp_nonagle(struct socket *sock)
set_fs(oldfs);
}
+/* All module specific customizations to the RDS-TCP socket should be done in
+ * rds_tcp_tune() and applied after socket creation. In general these
+ * customizations should be tunable via module_param()
+ */
void rds_tcp_tune(struct socket *sock)
{
- struct sock *sk = sock->sk;
-
rds_tcp_nonagle(sock);
-
- /*
- * We're trying to saturate gigabit with the default,
- * see svc_sock_setbufsize().
- */
- lock_sock(sk);
- sk->sk_sndbuf = RDS_TCP_DEFAULT_BUFSIZE;
- sk->sk_rcvbuf = RDS_TCP_DEFAULT_BUFSIZE;
- sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
- release_sock(sk);
}
u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc)
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 444d78d0bd77..0936a4a32b47 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -110,28 +110,27 @@ int rds_tcp_accept_one(struct socket *sock)
goto out;
}
/* An incoming SYN request came in, and TCP just accepted it.
- * We always create a new conn for listen side of TCP, and do not
- * add it to the c_hash_list.
*
* If the client reboots, this conn will need to be cleaned up.
* rds_tcp_state_change() will do that cleanup
*/
rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
- WARN_ON(!rs_tcp || rs_tcp->t_sock);
-
- /*
- * see the comment above rds_queue_delayed_reconnect()
- */
- if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) {
- if (rds_conn_state(conn) == RDS_CONN_UP)
- rds_tcp_stats_inc(s_tcp_listen_closed_stale);
- else
- rds_tcp_stats_inc(s_tcp_connect_raced);
- rds_conn_drop(conn);
+ if (rs_tcp->t_sock &&
+ ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) {
+ struct sock *nsk = new_sock->sk;
+
+ nsk->sk_user_data = NULL;
+ nsk->sk_prot->disconnect(nsk, 0);
+ tcp_done(nsk);
+ new_sock = NULL;
ret = 0;
goto out;
+ } else if (rs_tcp->t_sock) {
+ rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
+ conn->c_outgoing = 0;
}
+ rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
rds_tcp_set_callbacks(new_sock, conn);
rds_connect_complete(conn);
new_sock = NULL;
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 53b17ca0dff5..2894e6095e3b 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -83,6 +83,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
struct rds_tcp_connection *tc = conn->c_transport_data;
int done = 0;
int ret = 0;
+ int more;
if (hdr_off == 0) {
/*
@@ -116,12 +117,15 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
goto out;
}
+ more = rm->data.op_nents > 1 ? (MSG_MORE | MSG_SENDPAGE_NOTLAST) : 0;
while (sg < rm->data.op_nents) {
+ int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
+
ret = tc->t_sock->ops->sendpage(tc->t_sock,
sg_page(&rm->data.op_sg[sg]),
rm->data.op_sg[sg].offset + off,
rm->data.op_sg[sg].length - off,
- MSG_DONTWAIT|MSG_NOSIGNAL);
+ flags);
rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->data.op_sg[sg]),
rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off,
ret);
@@ -134,6 +138,8 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
off = 0;
sg++;
}
+ if (sg == rm->data.op_nents - 1)
+ more = 0;
}
out:
diff --git a/net/rds/threads.c b/net/rds/threads.c
index dc2402e871fd..454aa6d23327 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -162,7 +162,9 @@ void rds_send_worker(struct work_struct *work)
int ret;
if (rds_conn_state(conn) == RDS_CONN_UP) {
+ clear_bit(RDS_LL_SEND_FULL, &conn->c_flags);
ret = rds_send_xmit(conn);
+ cond_resched();
rdsdebug("conn %p ret %d\n", conn, ret);
switch (ret) {
case -EAGAIN:
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index 094a874b48bc..3fee70d9814f 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -11,7 +11,7 @@
* Note: Quantum tunneling is not supported.
*/
-#include <linux/module.h>
+#include <linux/init.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
@@ -37,17 +37,8 @@ static struct Qdisc_ops blackhole_qdisc_ops __read_mostly = {
.owner = THIS_MODULE,
};
-static int __init blackhole_module_init(void)
+static int __init blackhole_init(void)
{
return register_qdisc(&blackhole_qdisc_ops);
}
-
-static void __exit blackhole_module_exit(void)
-{
- unregister_qdisc(&blackhole_qdisc_ops);
-}
-
-module_init(blackhole_module_init)
-module_exit(blackhole_module_exit)
-
-MODULE_LICENSE("GPL");
+device_initcall(blackhole_init)
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 3386cce4751e..109b2322778f 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -225,6 +225,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
return &q->internal;
/* SYNACK messages are attached to a TCP_NEW_SYN_RECV request socket
+ * or a listener (SYNCOOKIE mode)
* 1) request sockets are not full blown,
* they do not contain sk_pacing_rate
* 2) They are not part of a 'flow' yet
@@ -232,7 +233,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
* especially if the listener set SO_MAX_PACING_RATE
* 4) We pretend they are orphaned
*/
- if (!sk || sk->sk_state == TCP_NEW_SYN_RECV) {
+ if (!sk || sk_listener(sk)) {
unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
/* By forcing low order bit to 1, we make sure to not
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 7954c52e1794..763e06a55155 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2494,7 +2494,7 @@ static int sctp_process_param(struct sctp_association *asoc,
__u16 sat;
int retval = 1;
sctp_scope_t scope;
- time_t stale;
+ u32 stale;
struct sctp_af *af;
union sctp_addr_param *addr_param;
struct sctp_transport *t;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index d7eaa7354cf7..6f46aa16cb76 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2306,7 +2306,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(struct net *net,
sctp_cmd_seq_t *commands)
{
struct sctp_chunk *chunk = arg;
- time_t stale;
+ u32 stale;
sctp_cookie_preserve_param_t bht;
sctp_errhdr_t *err;
struct sctp_chunk *reply;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 6e4a4f9ad927..73e3895175cf 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -15,8 +15,10 @@
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
#include <linux/list.h>
+#include <linux/workqueue.h>
#include <net/ip_fib.h>
#include <net/switchdev.h>
@@ -92,6 +94,85 @@ static void switchdev_trans_items_warn_destroy(struct net_device *dev,
switchdev_trans_items_destroy(trans);
}
+static LIST_HEAD(deferred);
+static DEFINE_SPINLOCK(deferred_lock);
+
+typedef void switchdev_deferred_func_t(struct net_device *dev,
+ const void *data);
+
+struct switchdev_deferred_item {
+ struct list_head list;
+ struct net_device *dev;
+ switchdev_deferred_func_t *func;
+ unsigned long data[0];
+};
+
+static struct switchdev_deferred_item *switchdev_deferred_dequeue(void)
+{
+ struct switchdev_deferred_item *dfitem;
+
+ spin_lock_bh(&deferred_lock);
+ if (list_empty(&deferred)) {
+ dfitem = NULL;
+ goto unlock;
+ }
+ dfitem = list_first_entry(&deferred,
+ struct switchdev_deferred_item, list);
+ list_del(&dfitem->list);
+unlock:
+ spin_unlock_bh(&deferred_lock);
+ return dfitem;
+}
+
+/**
+ * switchdev_deferred_process - Process ops in deferred queue
+ *
+ * Called to flush the ops currently queued in deferred ops queue.
+ * rtnl_lock must be held.
+ */
+void switchdev_deferred_process(void)
+{
+ struct switchdev_deferred_item *dfitem;
+
+ ASSERT_RTNL();
+
+ while ((dfitem = switchdev_deferred_dequeue())) {
+ dfitem->func(dfitem->dev, dfitem->data);
+ dev_put(dfitem->dev);
+ kfree(dfitem);
+ }
+}
+EXPORT_SYMBOL_GPL(switchdev_deferred_process);
+
+static void switchdev_deferred_process_work(struct work_struct *work)
+{
+ rtnl_lock();
+ switchdev_deferred_process();
+ rtnl_unlock();
+}
+
+static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work);
+
+static int switchdev_deferred_enqueue(struct net_device *dev,
+ const void *data, size_t data_len,
+ switchdev_deferred_func_t *func)
+{
+ struct switchdev_deferred_item *dfitem;
+
+ dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC);
+ if (!dfitem)
+ return -ENOMEM;
+ dfitem->dev = dev;
+ dfitem->func = func;
+ memcpy(dfitem->data, data, data_len);
+ dev_hold(dev);
+ spin_lock_bh(&deferred_lock);
+ list_add_tail(&dfitem->list, &deferred);
+ spin_unlock_bh(&deferred_lock);
+ schedule_work(&deferred_process_work);
+ return 0;
+}
+
/**
* switchdev_port_attr_get - Get port attribute
*
@@ -135,7 +216,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
static int __switchdev_port_attr_set(struct net_device *dev,
- struct switchdev_attr *attr,
+ const struct switchdev_attr *attr,
struct switchdev_trans *trans)
{
const struct switchdev_ops *ops = dev->switchdev_ops;
@@ -147,7 +228,7 @@ static int __switchdev_port_attr_set(struct net_device *dev,
return ops->switchdev_port_attr_set(dev, attr, trans);
if (attr->flags & SWITCHDEV_F_NO_RECURSE)
- return err;
+ goto done;
/* Switch device port(s) may be stacked under
* bond/team/vlan dev, so recurse down to set attr on
@@ -156,81 +237,26 @@ static int __switchdev_port_attr_set(struct net_device *dev,
netdev_for_each_lower_dev(dev, lower_dev, iter) {
err = __switchdev_port_attr_set(lower_dev, attr, trans);
+ if (err == -EOPNOTSUPP &&
+ attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
+ continue;
if (err)
break;
}
- return err;
-}
-
-struct switchdev_attr_set_work {
- struct work_struct work;
- struct net_device *dev;
- struct switchdev_attr attr;
-};
-
-static void switchdev_port_attr_set_work(struct work_struct *work)
-{
- struct switchdev_attr_set_work *asw =
- container_of(work, struct switchdev_attr_set_work, work);
- int err;
-
- rtnl_lock();
- err = switchdev_port_attr_set(asw->dev, &asw->attr);
- if (err && err != -EOPNOTSUPP)
- netdev_err(asw->dev, "failed (err=%d) to set attribute (id=%d)\n",
- err, asw->attr.id);
- rtnl_unlock();
-
- dev_put(asw->dev);
- kfree(work);
-}
-
-static int switchdev_port_attr_set_defer(struct net_device *dev,
- struct switchdev_attr *attr)
-{
- struct switchdev_attr_set_work *asw;
-
- asw = kmalloc(sizeof(*asw), GFP_ATOMIC);
- if (!asw)
- return -ENOMEM;
-
- INIT_WORK(&asw->work, switchdev_port_attr_set_work);
-
- dev_hold(dev);
- asw->dev = dev;
- memcpy(&asw->attr, attr, sizeof(asw->attr));
-
- schedule_work(&asw->work);
+done:
+ if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
+ err = 0;
- return 0;
+ return err;
}
-/**
- * switchdev_port_attr_set - Set port attribute
- *
- * @dev: port device
- * @attr: attribute to set
- *
- * Use a 2-phase prepare-commit transaction model to ensure
- * system is not left in a partially updated state due to
- * failure from driver/device.
- */
-int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
+static int switchdev_port_attr_set_now(struct net_device *dev,
+ const struct switchdev_attr *attr)
{
struct switchdev_trans trans;
int err;
- if (!rtnl_is_locked()) {
- /* Running prepare-commit transaction across stacked
- * devices requires nothing moves, so if rtnl_lock is
- * not held, schedule a worker thread to hold rtnl_lock
- * while setting attr.
- */
-
- return switchdev_port_attr_set_defer(dev, attr);
- }
-
switchdev_trans_init(&trans);
/* Phase I: prepare for attr set. Driver/device should fail
@@ -267,6 +293,47 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
return err;
}
+
+static void switchdev_port_attr_set_deferred(struct net_device *dev,
+ const void *data)
+{
+ const struct switchdev_attr *attr = data;
+ int err;
+
+ err = switchdev_port_attr_set_now(dev, attr);
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n",
+ err, attr->id);
+}
+
+static int switchdev_port_attr_set_defer(struct net_device *dev,
+ const struct switchdev_attr *attr)
+{
+ return switchdev_deferred_enqueue(dev, attr, sizeof(*attr),
+ switchdev_port_attr_set_deferred);
+}
+
+/**
+ * switchdev_port_attr_set - Set port attribute
+ *
+ * @dev: port device
+ * @attr: attribute to set
+ *
+ * Use a 2-phase prepare-commit transaction model to ensure
+ * system is not left in a partially updated state due to
+ * failure from driver/device.
+ *
+ * rtnl_lock must be held and must not be in atomic section,
+ * in case SWITCHDEV_F_DEFER flag is not set.
+ */
+int switchdev_port_attr_set(struct net_device *dev,
+ const struct switchdev_attr *attr)
+{
+ if (attr->flags & SWITCHDEV_F_DEFER)
+ return switchdev_port_attr_set_defer(dev, attr);
+ ASSERT_RTNL();
+ return switchdev_port_attr_set_now(dev, attr);
+}
EXPORT_SYMBOL_GPL(switchdev_port_attr_set);
static int __switchdev_port_obj_add(struct net_device *dev,
@@ -295,21 +362,8 @@ static int __switchdev_port_obj_add(struct net_device *dev,
return err;
}
-/**
- * switchdev_port_obj_add - Add port object
- *
- * @dev: port device
- * @id: object ID
- * @obj: object to add
- *
- * Use a 2-phase prepare-commit transaction model to ensure
- * system is not left in a partially updated state due to
- * failure from driver/device.
- *
- * rtnl_lock must be held.
- */
-int switchdev_port_obj_add(struct net_device *dev,
- const struct switchdev_obj *obj)
+static int switchdev_port_obj_add_now(struct net_device *dev,
+ const struct switchdev_obj *obj)
{
struct switchdev_trans trans;
int err;
@@ -351,18 +405,53 @@ int switchdev_port_obj_add(struct net_device *dev,
return err;
}
-EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
+
+static void switchdev_port_obj_add_deferred(struct net_device *dev,
+ const void *data)
+{
+ const struct switchdev_obj *obj = data;
+ int err;
+
+ err = switchdev_port_obj_add_now(dev, obj);
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(dev, "failed (err=%d) to add object (id=%d)\n",
+ err, obj->id);
+}
+
+static int switchdev_port_obj_add_defer(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ return switchdev_deferred_enqueue(dev, obj, sizeof(*obj),
+ switchdev_port_obj_add_deferred);
+}
/**
- * switchdev_port_obj_del - Delete port object
+ * switchdev_port_obj_add - Add port object
*
* @dev: port device
* @id: object ID
- * @obj: object to delete
+ * @obj: object to add
+ *
+ * Use a 2-phase prepare-commit transaction model to ensure
+ * system is not left in a partially updated state due to
+ * failure from driver/device.
+ *
+ * rtnl_lock must be held and must not be in atomic section,
+ * in case SWITCHDEV_F_DEFER flag is not set.
*/
-int switchdev_port_obj_del(struct net_device *dev,
+int switchdev_port_obj_add(struct net_device *dev,
const struct switchdev_obj *obj)
{
+ if (obj->flags & SWITCHDEV_F_DEFER)
+ return switchdev_port_obj_add_defer(dev, obj);
+ ASSERT_RTNL();
+ return switchdev_port_obj_add_now(dev, obj);
+}
+EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
+
+static int switchdev_port_obj_del_now(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
const struct switchdev_ops *ops = dev->switchdev_ops;
struct net_device *lower_dev;
struct list_head *iter;
@@ -377,13 +466,51 @@ int switchdev_port_obj_del(struct net_device *dev,
*/
netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = switchdev_port_obj_del(lower_dev, obj);
+ err = switchdev_port_obj_del_now(lower_dev, obj);
if (err)
break;
}
return err;
}
+
+static void switchdev_port_obj_del_deferred(struct net_device *dev,
+ const void *data)
+{
+ const struct switchdev_obj *obj = data;
+ int err;
+
+ err = switchdev_port_obj_del_now(dev, obj);
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(dev, "failed (err=%d) to del object (id=%d)\n",
+ err, obj->id);
+}
+
+static int switchdev_port_obj_del_defer(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ return switchdev_deferred_enqueue(dev, obj, sizeof(*obj),
+ switchdev_port_obj_del_deferred);
+}
+
+/**
+ * switchdev_port_obj_del - Delete port object
+ *
+ * @dev: port device
+ * @id: object ID
+ * @obj: object to delete
+ *
+ * rtnl_lock must be held and must not be in atomic section,
+ * in case SWITCHDEV_F_DEFER flag is not set.
+ */
+int switchdev_port_obj_del(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ if (obj->flags & SWITCHDEV_F_DEFER)
+ return switchdev_port_obj_del_defer(dev, obj);
+ ASSERT_RTNL();
+ return switchdev_port_obj_del_now(dev, obj);
+}
EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
/**
@@ -393,6 +520,8 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
* @id: object ID
* @obj: object to dump
* @cb: function to call with a filled object
+ *
+ * rtnl_lock must be held.
*/
int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
switchdev_obj_dump_cb_t *cb)
@@ -402,6 +531,8 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
struct list_head *iter;
int err = -EOPNOTSUPP;
+ ASSERT_RTNL();
+
if (ops && ops->switchdev_port_obj_dump)
return ops->switchdev_port_obj_dump(dev, obj, cb);
@@ -720,6 +851,9 @@ static int switchdev_port_br_afspec(struct net_device *dev,
if (vlan.vid_begin)
return -EINVAL;
vlan.vid_begin = vinfo->vid;
+ /* don't allow range of pvids */
+ if (vlan.flags & BRIDGE_VLAN_INFO_PVID)
+ return -EINVAL;
} else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) {
if (!vlan.vid_begin)
return -EINVAL;
@@ -822,10 +956,10 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
{
struct switchdev_obj_port_fdb fdb = {
.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
- .addr = addr,
.vid = vid,
};
+ ether_addr_copy(fdb.addr, addr);
return switchdev_port_obj_add(dev, &fdb.obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_add);
@@ -847,10 +981,10 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
{
struct switchdev_obj_port_fdb fdb = {
.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
- .addr = addr,
.vid = vid,
};
+ ether_addr_copy(fdb.addr, addr);
return switchdev_port_obj_del(dev, &fdb.obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_del);
@@ -967,6 +1101,8 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi)
struct net_device *dev = NULL;
int nhsel;
+ ASSERT_RTNL();
+
/* For this route, all nexthop devs must be on the same switch. */
for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
@@ -1012,7 +1148,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
.dst = dst,
.dst_len = dst_len,
- .fi = fi,
.tos = tos,
.type = type,
.nlflags = nlflags,
@@ -1021,6 +1156,8 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
struct net_device *dev;
int err = 0;
+ memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
+
/* Don't offload route if using custom ip rules or if
* IPv4 FIB offloading has been disabled completely.
*/
@@ -1064,7 +1201,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
.dst = dst,
.dst_len = dst_len,
- .fi = fi,
.tos = tos,
.type = type,
.nlflags = 0,
@@ -1073,6 +1209,8 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
struct net_device *dev;
int err = 0;
+ memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
+
if (!(fi->fib_flags & RTNH_F_OFFLOAD))
return 0;
@@ -1195,10 +1333,11 @@ void switchdev_port_fwd_mark_set(struct net_device *dev,
u32 mark = dev->ifindex;
u32 reset_mark = 0;
- if (group_dev && joining) {
- mark = switchdev_port_fwd_mark_get(dev, group_dev);
- } else if (group_dev && !joining) {
- if (dev->offload_fwd_mark == mark)
+ if (group_dev) {
+ ASSERT_RTNL();
+ if (joining)
+ mark = switchdev_port_fwd_mark_get(dev, group_dev);
+ else if (dev->offload_fwd_mark == mark)
/* Ohoh, this port was the mark reference port,
* but it's leaving the group, so reset the
* mark for the remaining ports in the group.
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index ce9f7bfc0b92..82b278668ab7 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -362,6 +362,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr)
b_ptr->media->disable_media(b_ptr);
tipc_node_delete_links(net, b_ptr->identity);
+ RCU_INIT_POINTER(b_ptr->media_ptr, NULL);
if (b_ptr->link_req)
tipc_disc_delete(b_ptr->link_req);
@@ -399,16 +400,13 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
/* tipc_disable_l2_media - detach TIPC bearer from an L2 interface
*
- * Mark L2 bearer as inactive so that incoming buffers are thrown away,
- * then get worker thread to complete bearer cleanup. (Can't do cleanup
- * here because cleanup code needs to sleep and caller holds spinlocks.)
+ * Mark L2 bearer as inactive so that incoming buffers are thrown away
*/
void tipc_disable_l2_media(struct tipc_bearer *b)
{
struct net_device *dev;
dev = (struct net_device *)rtnl_dereference(b->media_ptr);
- RCU_INIT_POINTER(b->media_ptr, NULL);
RCU_INIT_POINTER(dev->tipc_ptr, NULL);
synchronize_net();
dev_put(dev);
@@ -554,7 +552,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
case NETDEV_CHANGE:
if (netif_carrier_ok(dev))
break;
- case NETDEV_DOWN:
+ case NETDEV_GOING_DOWN:
case NETDEV_CHANGEMTU:
tipc_reset_bearer(net, b_ptr);
break;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 75db07c78a69..ff9b0b92e62e 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -120,11 +120,21 @@ bool tipc_link_is_up(struct tipc_link *l)
return link_is_up(l);
}
+bool tipc_link_peer_is_down(struct tipc_link *l)
+{
+ return l->state == LINK_PEER_RESET;
+}
+
bool tipc_link_is_reset(struct tipc_link *l)
{
return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING);
}
+bool tipc_link_is_establishing(struct tipc_link *l)
+{
+ return l->state == LINK_ESTABLISHING;
+}
+
bool tipc_link_is_synching(struct tipc_link *l)
{
return l->state == LINK_SYNCHING;
@@ -321,14 +331,15 @@ int tipc_link_fsm_evt(struct tipc_link *l, int evt)
switch (evt) {
case LINK_ESTABLISH_EVT:
l->state = LINK_ESTABLISHED;
- rc |= TIPC_LINK_UP_EVT;
break;
case LINK_FAILOVER_BEGIN_EVT:
l->state = LINK_FAILINGOVER;
break;
- case LINK_PEER_RESET_EVT:
case LINK_RESET_EVT:
+ l->state = LINK_RESET;
+ break;
case LINK_FAILURE_EVT:
+ case LINK_PEER_RESET_EVT:
case LINK_SYNCH_BEGIN_EVT:
case LINK_FAILOVER_END_EVT:
break;
@@ -578,8 +589,6 @@ void tipc_link_purge_queues(struct tipc_link *l_ptr)
void tipc_link_reset(struct tipc_link *l)
{
- tipc_link_fsm_evt(l, LINK_RESET_EVT);
-
/* Link is down, accept any session */
l->peer_session = WILDCARD_SESSION;
@@ -953,7 +962,7 @@ static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb,
case TIPC_HIGH_IMPORTANCE:
case TIPC_CRITICAL_IMPORTANCE:
case CONN_MANAGER:
- __skb_queue_tail(inputq, skb);
+ skb_queue_tail(inputq, skb);
return true;
case NAME_DISTRIBUTOR:
node->bclink.recv_permitted = true;
@@ -982,6 +991,7 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb,
struct tipc_msg *hdr = buf_msg(skb);
struct sk_buff **reasm_skb = &l->reasm_buf;
struct sk_buff *iskb;
+ struct sk_buff_head tmpq;
int usr = msg_user(hdr);
int rc = 0;
int pos = 0;
@@ -1006,10 +1016,12 @@ static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb,
}
if (usr == MSG_BUNDLER) {
+ skb_queue_head_init(&tmpq);
l->stats.recv_bundles++;
l->stats.recv_bundled += msg_msgcnt(hdr);
while (tipc_msg_extract(skb, &iskb, &pos))
- tipc_data_input(l, iskb, inputq);
+ tipc_data_input(l, iskb, &tmpq);
+ tipc_skb_queue_splice_tail(&tmpq, inputq);
return 0;
} else if (usr == MSG_FRAGMENTER) {
l->stats.recv_fragments++;
@@ -1044,49 +1056,76 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked)
return released;
}
+/* tipc_link_build_ack_msg: prepare link acknowledge message for transmission
+ */
+void tipc_link_build_ack_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
+{
+ l->rcv_unacked = 0;
+ l->stats.sent_acks++;
+ tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq);
+}
+
+/* tipc_link_build_reset_msg: prepare link RESET or ACTIVATE message
+ */
+void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq)
+{
+ int mtyp = RESET_MSG;
+
+ if (l->state == LINK_ESTABLISHING)
+ mtyp = ACTIVATE_MSG;
+
+ tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, xmitq);
+}
+
+/* tipc_link_build_nack_msg: prepare link nack message for transmission
+ */
+static void tipc_link_build_nack_msg(struct tipc_link *l,
+ struct sk_buff_head *xmitq)
+{
+ u32 def_cnt = ++l->stats.deferred_recv;
+
+ if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV))
+ tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq);
+}
+
/* tipc_link_rcv - process TIPC packets/messages arriving from off-node
- * @link: the link that should handle the message
+ * @l: the link that should handle the message
* @skb: TIPC packet
* @xmitq: queue to place packets to be sent after this call
*/
int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
struct sk_buff_head *xmitq)
{
- struct sk_buff_head *arrvq = &l->deferdq;
- struct sk_buff_head tmpq;
+ struct sk_buff_head *defq = &l->deferdq;
struct tipc_msg *hdr;
- u16 seqno, rcv_nxt;
+ u16 seqno, rcv_nxt, win_lim;
int rc = 0;
- __skb_queue_head_init(&tmpq);
-
- if (unlikely(!__tipc_skb_queue_sorted(arrvq, skb))) {
- if (!(skb_queue_len(arrvq) % TIPC_NACK_INTV))
- tipc_link_build_proto_msg(l, STATE_MSG, 0,
- 0, 0, 0, xmitq);
- return rc;
- }
-
- while ((skb = skb_peek(arrvq))) {
+ do {
hdr = buf_msg(skb);
+ seqno = msg_seqno(hdr);
+ rcv_nxt = l->rcv_nxt;
+ win_lim = rcv_nxt + TIPC_MAX_LINK_WIN;
/* Verify and update link state */
- if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) {
- __skb_dequeue(arrvq);
- rc = tipc_link_proto_rcv(l, skb, xmitq);
- continue;
- }
+ if (unlikely(msg_user(hdr) == LINK_PROTOCOL))
+ return tipc_link_proto_rcv(l, skb, xmitq);
if (unlikely(!link_is_up(l))) {
- rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);
- if (!link_is_up(l)) {
- kfree_skb(__skb_dequeue(arrvq));
- goto exit;
- }
+ if (l->state == LINK_ESTABLISHING)
+ rc = TIPC_LINK_UP_EVT;
+ goto drop;
}
+ /* Don't send probe at next timeout expiration */
l->silent_intv_cnt = 0;
+ /* Drop if outside receive window */
+ if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) {
+ l->stats.duplicates++;
+ goto drop;
+ }
+
/* Forward queues and wake up waiting users */
if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
tipc_link_advance_backlog(l, xmitq);
@@ -1094,39 +1133,28 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
link_prepare_wakeup(l);
}
- /* Defer reception if there is a gap in the sequence */
- seqno = msg_seqno(hdr);
- rcv_nxt = l->rcv_nxt;
- if (unlikely(less(rcv_nxt, seqno))) {
- l->stats.deferred_recv++;
- goto exit;
- }
-
- __skb_dequeue(arrvq);
-
- /* Drop if packet already received */
- if (unlikely(more(rcv_nxt, seqno))) {
- l->stats.duplicates++;
- kfree_skb(skb);
- goto exit;
+ /* Defer delivery if sequence gap */
+ if (unlikely(seqno != rcv_nxt)) {
+ __tipc_skb_queue_sorted(defq, seqno, skb);
+ tipc_link_build_nack_msg(l, xmitq);
+ break;
}
- /* Packet can be delivered */
+ /* Deliver packet */
l->rcv_nxt++;
l->stats.recv_info++;
- if (unlikely(!tipc_data_input(l, skb, &tmpq)))
- rc = tipc_link_input(l, skb, &tmpq);
+ if (!tipc_data_input(l, skb, l->inputq))
+ rc = tipc_link_input(l, skb, l->inputq);
+ if (unlikely(rc))
+ break;
+ if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN))
+ tipc_link_build_ack_msg(l, xmitq);
+
+ } while ((skb = __skb_dequeue(defq)));
- /* Ack at regular intervals */
- if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) {
- l->rcv_unacked = 0;
- l->stats.sent_acks++;
- tipc_link_build_proto_msg(l, STATE_MSG,
- 0, 0, 0, 0, xmitq);
- }
- }
-exit:
- tipc_skb_queue_splice_tail(&tmpq, l->inputq);
+ return rc;
+drop:
+ kfree_skb(skb);
return rc;
}
@@ -1250,7 +1278,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
}
/* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets
- * with contents of the link's tranmsit and backlog queues.
+ * with contents of the link's transmit and backlog queues.
*/
void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
int mtyp, struct sk_buff_head *xmitq)
@@ -1331,6 +1359,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
u16 peers_tol = msg_link_tolerance(hdr);
u16 peers_prio = msg_linkprio(hdr);
u16 rcv_nxt = l->rcv_nxt;
+ int mtyp = msg_type(hdr);
char *if_name;
int rc = 0;
@@ -1340,7 +1369,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
if (link_own_addr(l) > msg_prevnode(hdr))
l->net_plane = msg_net_plane(hdr);
- switch (msg_type(hdr)) {
+ switch (mtyp) {
case RESET_MSG:
/* Ignore duplicate RESET with old session number */
@@ -1367,12 +1396,14 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
l->priority = peers_prio;
- if (msg_type(hdr) == RESET_MSG) {
- rc |= tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
- } else if (!link_is_up(l)) {
- tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
- rc |= tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);
- }
+ /* ACTIVATE_MSG serves as PEER_RESET if link is already down */
+ if ((mtyp == RESET_MSG) || !link_is_up(l))
+ rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
+
+ /* ACTIVATE_MSG takes up link if it was already locally reset */
+ if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING))
+ rc = TIPC_LINK_UP_EVT;
+
l->peer_session = msg_session(hdr);
l->peer_bearer_id = msg_bearer_id(hdr);
if (l->mtu > msg_max_pkt(hdr))
@@ -1389,9 +1420,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
l->stats.recv_states++;
if (msg_probe(hdr))
l->stats.recv_probes++;
- rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);
- if (!link_is_up(l))
+
+ if (!link_is_up(l)) {
+ if (l->state == LINK_ESTABLISHING)
+ rc = TIPC_LINK_UP_EVT;
break;
+ }
/* Send NACK if peer has sent pkts we haven't received yet */
if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 39ff8b6919a4..0201212cb49a 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -185,7 +185,7 @@ struct tipc_link {
} backlog[5];
u16 snd_nxt;
u16 last_retransm;
- u32 window;
+ u16 window;
u32 stale_count;
/* Reception */
@@ -213,10 +213,13 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
int mtyp, struct sk_buff_head *xmitq);
void tipc_link_build_bcast_sync_msg(struct tipc_link *l,
struct sk_buff_head *xmitq);
+void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq);
int tipc_link_fsm_evt(struct tipc_link *l, int evt);
void tipc_link_reset_fragments(struct tipc_link *l_ptr);
bool tipc_link_is_up(struct tipc_link *l);
+bool tipc_link_peer_is_down(struct tipc_link *l);
bool tipc_link_is_reset(struct tipc_link *l);
+bool tipc_link_is_establishing(struct tipc_link *l);
bool tipc_link_is_synching(struct tipc_link *l);
bool tipc_link_is_failingover(struct tipc_link *l);
bool tipc_link_is_blocked(struct tipc_link *l);
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index c5ac436235e0..454f5ec275c8 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -590,3 +590,34 @@ error:
kfree_skb(head);
return NULL;
}
+
+/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number
+ * @list: list to be appended to
+ * @seqno: sequence number of buffer to add
+ * @skb: buffer to add
+ */
+void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
+ struct sk_buff *skb)
+{
+ struct sk_buff *_skb, *tmp;
+
+ if (skb_queue_empty(list) || less(seqno, buf_seqno(skb_peek(list)))) {
+ __skb_queue_head(list, skb);
+ return;
+ }
+
+ if (more(seqno, buf_seqno(skb_peek_tail(list)))) {
+ __skb_queue_tail(list, skb);
+ return;
+ }
+
+ skb_queue_walk_safe(list, _skb, tmp) {
+ if (more(seqno, buf_seqno(_skb)))
+ continue;
+ if (seqno == buf_seqno(_skb))
+ break;
+ __skb_queue_before(list, _skb, skb);
+ return;
+ }
+ kfree_skb(skb);
+}
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index a82c5848d4bc..c784ba05f2aa 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -790,6 +790,8 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m,
int offset, int dsz, int mtu, struct sk_buff_head *list);
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err);
struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list);
+void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
+ struct sk_buff *skb);
static inline u16 buf_seqno(struct sk_buff *skb)
{
@@ -862,38 +864,6 @@ static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list,
return skb;
}
-/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number
- * @list: list to be appended to
- * @skb: buffer to add
- * Returns true if queue should treated further, otherwise false
- */
-static inline bool __tipc_skb_queue_sorted(struct sk_buff_head *list,
- struct sk_buff *skb)
-{
- struct sk_buff *_skb, *tmp;
- struct tipc_msg *hdr = buf_msg(skb);
- u16 seqno = msg_seqno(hdr);
-
- if (skb_queue_empty(list) || (msg_user(hdr) == LINK_PROTOCOL)) {
- __skb_queue_head(list, skb);
- return true;
- }
- if (likely(less(seqno, buf_seqno(skb_peek(list))))) {
- __skb_queue_head(list, skb);
- return true;
- }
- if (!more(seqno, buf_seqno(skb_peek_tail(list)))) {
- skb_queue_walk_safe(list, _skb, tmp) {
- if (likely(less(seqno, buf_seqno(_skb)))) {
- __skb_queue_before(list, _skb, skb);
- return true;
- }
- }
- }
- __skb_queue_tail(list, skb);
- return false;
-}
-
/* tipc_skb_queue_splice_tail - append an skb list to lock protected list
* @list: the new list to append. Not lock protected
* @head: target list. Lock protected.
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 703875fd6cde..d1f340116c84 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -317,7 +317,11 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
struct tipc_link *ol = node_active_link(n, 0);
struct tipc_link *nl = n->links[bearer_id].link;
- if (!nl || !tipc_link_is_up(nl))
+ if (!nl)
+ return;
+
+ tipc_link_fsm_evt(nl, LINK_ESTABLISH_EVT);
+ if (!tipc_link_is_up(nl))
return;
n->working_links++;
@@ -416,7 +420,13 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
}
if (!tipc_node_is_up(n)) {
+ if (tipc_link_peer_is_down(l))
+ tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
+ tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_reset(l);
+ tipc_link_build_reset_msg(l, xmitq);
+ *maddr = &n->links[*bearer_id].maddr;
node_lost_contact(n, &le->inputq);
return;
}
@@ -428,6 +438,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
n->sync_point = tnl->rcv_nxt + (U16_MAX / 2 - 1);
tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq);
tipc_link_reset(l);
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT);
*maddr = &n->links[tnl->bearer_id].maddr;
@@ -437,20 +448,28 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
{
struct tipc_link_entry *le = &n->links[bearer_id];
+ struct tipc_link *l = le->link;
struct tipc_media_addr *maddr;
struct sk_buff_head xmitq;
+ if (!l)
+ return;
+
__skb_queue_head_init(&xmitq);
tipc_node_lock(n);
- __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
- if (delete && le->link) {
- kfree(le->link);
- le->link = NULL;
- n->link_cnt--;
+ if (!tipc_link_is_establishing(l)) {
+ __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
+ if (delete) {
+ kfree(l);
+ le->link = NULL;
+ n->link_cnt--;
+ }
+ } else {
+ /* Defuse pending tipc_node_link_up() */
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
}
tipc_node_unlock(n);
-
tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
tipc_sk_rcv(n->net, &le->inputq);
}
@@ -567,6 +586,7 @@ void tipc_node_check_dest(struct net *net, u32 onode,
goto exit;
}
tipc_link_reset(l);
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
if (n->state == NODE_FAILINGOVER)
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
le->link = l;
@@ -579,7 +599,7 @@ void tipc_node_check_dest(struct net *net, u32 onode,
memcpy(&le->maddr, maddr, sizeof(*maddr));
exit:
tipc_node_unlock(n);
- if (reset)
+ if (reset && !tipc_link_is_reset(l))
tipc_node_link_down(n, b->identity, false);
tipc_node_put(n);
}
@@ -686,10 +706,10 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt)
break;
case SELF_ESTABL_CONTACT_EVT:
case PEER_LOST_CONTACT_EVT:
- break;
case NODE_SYNCH_END_EVT:
- case NODE_SYNCH_BEGIN_EVT:
case NODE_FAILOVER_BEGIN_EVT:
+ break;
+ case NODE_SYNCH_BEGIN_EVT:
case NODE_FAILOVER_END_EVT:
default:
goto illegal_evt;
@@ -849,9 +869,6 @@ static void node_lost_contact(struct tipc_node *n_ptr,
tipc_link_fsm_evt(l, LINK_FAILOVER_END_EVT);
}
- /* Prevent re-contact with node until cleanup is done */
- tipc_node_fsm_evt(n_ptr, SELF_LOST_CONTACT_EVT);
-
/* Notify publications from this node */
n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN;
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index c170d3138953..9bc0b1e515fa 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -425,7 +425,6 @@ static void tipc_udp_disable(struct tipc_bearer *b)
}
if (ub->ubsock)
sock_set_flag(ub->ubsock->sk, SOCK_DEAD);
- RCU_INIT_POINTER(b->media_ptr, NULL);
RCU_INIT_POINTER(ub->bearer, NULL);
/* sock_release need to be done outside of rtnl lock */
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 3893409dee95..f223026ddb03 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -419,6 +419,7 @@ use_default_name:
device_initialize(&rdev->wiphy.dev);
rdev->wiphy.dev.class = &ieee80211_class;
rdev->wiphy.dev.platform_data = rdev;
+ device_enable_async_suspend(&rdev->wiphy.dev);
INIT_LIST_HEAD(&rdev->destroy_list);
spin_lock_init(&rdev->destroy_list_lock);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5d8748b4c8a2..f05ba8b7af61 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3,6 +3,7 @@
*
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
+ * Copyright 2015 Intel Deutschland GmbH
*/
#include <linux/if.h>
@@ -2403,6 +2404,16 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
}
}
+ if (rdev->ops->get_tx_power) {
+ int dbm, ret;
+
+ ret = rdev_get_tx_power(rdev, wdev, &dbm);
+ if (ret == 0 &&
+ nla_put_u32(msg, NL80211_ATTR_WIPHY_TX_POWER_LEVEL,
+ DBM_TO_MBM(dbm)))
+ goto nla_put_failure;
+ }
+
if (wdev->ssid_len) {
if (nla_put(msg, NL80211_ATTR_SSID, wdev->ssid_len, wdev->ssid))
goto nla_put_failure;
@@ -3998,7 +4009,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
params->sta_flags_mask &= ~BIT(NL80211_STA_FLAG_TDLS_PEER);
}
- if (statype != CFG80211_STA_TDLS_PEER_SETUP) {
+ if (statype != CFG80211_STA_TDLS_PEER_SETUP &&
+ statype != CFG80211_STA_AP_CLIENT_UNASSOC) {
/* reject other things that can't change */
if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD)
return -EINVAL;
@@ -4010,7 +4022,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
return -EINVAL;
}
- if (statype != CFG80211_STA_AP_CLIENT) {
+ if (statype != CFG80211_STA_AP_CLIENT &&
+ statype != CFG80211_STA_AP_CLIENT_UNASSOC) {
if (params->vlan)
return -EINVAL;
}
@@ -4022,6 +4035,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
return -EOPNOTSUPP;
break;
case CFG80211_STA_AP_CLIENT:
+ case CFG80211_STA_AP_CLIENT_UNASSOC:
/* accept only the listed bits */
if (params->sta_flags_mask &
~(BIT(NL80211_STA_FLAG_AUTHORIZED) |
@@ -9938,6 +9952,9 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
if (!wdev->netdev && !wdev->p2p_started)
return -ENETDOWN;
}
+
+ if (!vcmd->doit)
+ return -EOPNOTSUPP;
} else {
wdev = NULL;
}
@@ -9957,6 +9974,193 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
return -EOPNOTSUPP;
}
+static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct cfg80211_registered_device **rdev,
+ struct wireless_dev **wdev)
+{
+ u32 vid, subcmd;
+ unsigned int i;
+ int vcmd_idx = -1;
+ int err;
+ void *data = NULL;
+ unsigned int data_len = 0;
+
+ rtnl_lock();
+
+ if (cb->args[0]) {
+ /* subtract the 1 again here */
+ struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
+ struct wireless_dev *tmp;
+
+ if (!wiphy) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
+ *rdev = wiphy_to_rdev(wiphy);
+ *wdev = NULL;
+
+ if (cb->args[1]) {
+ list_for_each_entry(tmp, &(*rdev)->wdev_list, list) {
+ if (tmp->identifier == cb->args[1] - 1) {
+ *wdev = tmp;
+ break;
+ }
+ }
+ }
+
+ /* keep rtnl locked in successful case */
+ return 0;
+ }
+
+ err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
+ nl80211_fam.attrbuf, nl80211_fam.maxattr,
+ nl80211_policy);
+ if (err)
+ goto out_unlock;
+
+ if (!nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID] ||
+ !nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk),
+ nl80211_fam.attrbuf);
+ if (IS_ERR(*wdev))
+ *wdev = NULL;
+
+ *rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk),
+ nl80211_fam.attrbuf);
+ if (IS_ERR(*rdev)) {
+ err = PTR_ERR(*rdev);
+ goto out_unlock;
+ }
+
+ vid = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_ID]);
+ subcmd = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_SUBCMD]);
+
+ for (i = 0; i < (*rdev)->wiphy.n_vendor_commands; i++) {
+ const struct wiphy_vendor_command *vcmd;
+
+ vcmd = &(*rdev)->wiphy.vendor_commands[i];
+
+ if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
+ continue;
+
+ if (!vcmd->dumpit) {
+ err = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+
+ vcmd_idx = i;
+ break;
+ }
+
+ if (vcmd_idx < 0) {
+ err = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+
+ if (nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]) {
+ data = nla_data(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]);
+ data_len = nla_len(nl80211_fam.attrbuf[NL80211_ATTR_VENDOR_DATA]);
+ }
+
+ /* 0 is the first index - add 1 to parse only once */
+ cb->args[0] = (*rdev)->wiphy_idx + 1;
+ /* add 1 to know if it was NULL */
+ cb->args[1] = *wdev ? (*wdev)->identifier + 1 : 0;
+ cb->args[2] = vcmd_idx;
+ cb->args[3] = (unsigned long)data;
+ cb->args[4] = data_len;
+
+ /* keep rtnl locked in successful case */
+ return 0;
+ out_unlock:
+ rtnl_unlock();
+ return err;
+}
+
+static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct cfg80211_registered_device *rdev;
+ struct wireless_dev *wdev;
+ unsigned int vcmd_idx;
+ const struct wiphy_vendor_command *vcmd;
+ void *data;
+ int data_len;
+ int err;
+ struct nlattr *vendor_data;
+
+ err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev);
+ if (err)
+ return err;
+
+ vcmd_idx = cb->args[2];
+ data = (void *)cb->args[3];
+ data_len = cb->args[4];
+ vcmd = &rdev->wiphy.vendor_commands[vcmd_idx];
+
+ if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
+ WIPHY_VENDOR_CMD_NEED_NETDEV)) {
+ if (!wdev)
+ return -EINVAL;
+ if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
+ !wdev->netdev)
+ return -EINVAL;
+
+ if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
+ if (wdev->netdev &&
+ !netif_running(wdev->netdev))
+ return -ENETDOWN;
+ if (!wdev->netdev && !wdev->p2p_started)
+ return -ENETDOWN;
+ }
+ }
+
+ while (1) {
+ void *hdr = nl80211hdr_put(skb, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ NL80211_CMD_VENDOR);
+ if (!hdr)
+ break;
+
+ if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+ (wdev && nla_put_u64(skb, NL80211_ATTR_WDEV,
+ wdev_id(wdev)))) {
+ genlmsg_cancel(skb, hdr);
+ break;
+ }
+
+ vendor_data = nla_nest_start(skb, NL80211_ATTR_VENDOR_DATA);
+ if (!vendor_data) {
+ genlmsg_cancel(skb, hdr);
+ break;
+ }
+
+ err = vcmd->dumpit(&rdev->wiphy, wdev, skb, data, data_len,
+ (unsigned long *)&cb->args[5]);
+ nla_nest_end(skb, vendor_data);
+
+ if (err == -ENOBUFS || err == -ENOENT) {
+ genlmsg_cancel(skb, hdr);
+ break;
+ } else if (err) {
+ genlmsg_cancel(skb, hdr);
+ goto out;
+ }
+
+ genlmsg_end(skb, hdr);
+ }
+
+ err = skb->len;
+ out:
+ rtnl_unlock();
+ return err;
+}
+
struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
enum nl80211_commands cmd,
enum nl80211_attrs attr,
@@ -10994,6 +11198,7 @@ static const struct genl_ops nl80211_ops[] = {
{
.cmd = NL80211_CMD_VENDOR,
.doit = nl80211_vendor_cmd,
+ .dumpit = nl80211_vendor_cmd_dump,
.policy = nl80211_policy,
.flags = GENL_ADMIN_PERM,
.internal_flags = NL80211_FLAG_NEED_WIPHY |
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2510b231451e..7258246b7458 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1040,8 +1040,8 @@ freq_reg_info_regd(struct wiphy *wiphy, u32 center_freq,
return ERR_PTR(-EINVAL);
}
-const struct ieee80211_reg_rule *__freq_reg_info(struct wiphy *wiphy,
- u32 center_freq, u32 min_bw)
+static const struct ieee80211_reg_rule *
+__freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw)
{
const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy);
const struct ieee80211_reg_rule *reg_rule = NULL;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index c48a4b8582bb..cc3676eb6239 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -136,12 +136,12 @@ int xfrm_output_resume(struct sk_buff *skb, int err)
while (likely((err = xfrm_output_one(skb, err)) == 0)) {
nf_reset(skb);
- err = skb_dst(skb)->ops->local_out(skb);
+ err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
if (unlikely(err != 1))
goto out;
if (!skb_dst(skb)->xfrm)
- return dst_output(skb->sk, skb);
+ return dst_output(net, skb->sk, skb);
err = nf_hook(skb_dst(skb)->ops->family,
NF_INET_POST_ROUTING, net, skb->sk, skb,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 418daa038edf..09bfcbac63bb 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1887,6 +1887,7 @@ static void xfrm_policy_queue_process(unsigned long arg)
struct sock *sk;
struct dst_entry *dst;
struct xfrm_policy *pol = (struct xfrm_policy *)arg;
+ struct net *net = xp_net(pol);
struct xfrm_policy_queue *pq = &pol->polq;
struct flowi fl;
struct sk_buff_head list;
@@ -1903,8 +1904,7 @@ static void xfrm_policy_queue_process(unsigned long arg)
spin_unlock(&pq->hold_queue.lock);
dst_hold(dst->path);
- dst = xfrm_lookup(xp_net(pol), dst->path, &fl,
- sk, 0);
+ dst = xfrm_lookup(net, dst->path, &fl, sk, 0);
if (IS_ERR(dst))
goto purge_queue;
@@ -1934,8 +1934,7 @@ static void xfrm_policy_queue_process(unsigned long arg)
xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
dst_hold(skb_dst(skb)->path);
- dst = xfrm_lookup(xp_net(pol), skb_dst(skb)->path,
- &fl, skb->sk, 0);
+ dst = xfrm_lookup(net, skb_dst(skb)->path, &fl, skb->sk, 0);
if (IS_ERR(dst)) {
kfree_skb(skb);
continue;
@@ -1945,7 +1944,7 @@ static void xfrm_policy_queue_process(unsigned long arg)
skb_dst_drop(skb);
skb_dst_set(skb, dst);
- dst_output(skb->sk, skb);
+ dst_output(net, skb->sk, skb);
}
out:
@@ -1958,7 +1957,7 @@ purge_queue:
xfrm_pol_put(pol);
}
-static int xdst_queue_output(struct sock *sk, struct sk_buff *skb)
+static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
unsigned long sched_next;
struct dst_entry *dst = skb_dst(skb);