summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan.c18
-rw-r--r--net/bluetooth/Makefile2
-rw-r--r--net/bluetooth/af_bluetooth.c41
-rw-r--r--net/bluetooth/hci_conn.c4
-rw-r--r--net/bluetooth/hci_core.c189
-rw-r--r--net/bluetooth/hci_event.c17
-rw-r--r--net/bluetooth/hci_sock.c204
-rw-r--r--net/bluetooth/l2cap_core.c162
-rw-r--r--net/bluetooth/l2cap_sock.c20
-rw-r--r--net/bluetooth/mgmt.c562
-rw-r--r--net/bluetooth/rfcomm/sock.c7
-rw-r--r--net/bluetooth/smp.c15
-rw-r--r--net/bridge/br_multicast.c4
-rw-r--r--net/bridge/netfilter/ebt_among.c2
-rw-r--r--net/core/dev.c500
-rw-r--r--net/core/flow_dissector.c39
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/netprio_cgroup.c3
-rw-r--r--net/core/rtnetlink.c3
-rw-r--r--net/core/sock.c12
-rw-r--r--net/ethernet/eth.c30
-rw-r--r--net/ipv4/af_inet.c1
-rw-r--r--net/ipv4/fib_trie.c9
-rw-r--r--net/ipv4/icmp.c5
-rw-r--r--net/ipv4/inet_connection_sock.c31
-rw-r--r--net/ipv4/inet_diag.c6
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/inet_timewait_sock.c4
-rw-r--r--net/ipv4/ip_output.c13
-rw-r--r--net/ipv4/ip_sockglue.c25
-rw-r--r--net/ipv4/ip_vti.c67
-rw-r--r--net/ipv4/ping.c8
-rw-r--r--net/ipv4/raw.c6
-rw-r--r--net/ipv4/syncookies.c53
-rw-r--r--net/ipv4/sysctl_net_ipv4.c52
-rw-r--r--net/ipv4/tcp_input.c126
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/udp.c215
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c16
-rw-r--r--net/ipv6/af_inet6.c48
-rw-r--r--net/ipv6/ip6_fib.c205
-rw-r--r--net/ipv6/route.c49
-rw-r--r--net/ipv6/syncookies.c39
-rw-r--r--net/ipv6/tcp_ipv6.c2
-rw-r--r--net/ipv6/udp.c11
-rw-r--r--net/mac80211/trace.h4
-rw-r--r--net/netfilter/ipset/Kconfig20
-rw-r--r--net/netfilter/ipset/Makefile2
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_gen.h163
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ip.c125
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_ipmac.c156
-rw-r--r--net/netfilter/ipset/ip_set_bitmap_port.c112
-rw-r--r--net/netfilter/ipset/ip_set_core.c361
-rw-r--r--net/netfilter/ipset/ip_set_getport.c18
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h526
-rw-r--r--net/netfilter/ipset/ip_set_hash_ip.c58
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipport.c80
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportip.c86
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportnet.c108
-rw-r--r--net/netfilter/ipset/ip_set_hash_net.c85
-rw-r--r--net/netfilter/ipset/ip_set_hash_netiface.c98
-rw-r--r--net/netfilter/ipset/ip_set_hash_netnet.c483
-rw-r--r--net/netfilter/ipset/ip_set_hash_netport.c92
-rw-r--r--net/netfilter/ipset/ip_set_hash_netportnet.c588
-rw-r--r--net/netfilter/ipset/ip_set_list_set.c263
-rw-r--r--net/netfilter/nf_conntrack_sip.c133
-rw-r--r--net/netfilter/nf_nat_sip.c35
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c161
-rw-r--r--net/netfilter/nfnetlink_log.c11
-rw-r--r--net/netfilter/nfnetlink_queue_core.c6
-rw-r--r--net/netfilter/xt_TCPMSS.c72
-rw-r--r--net/netfilter/xt_set.c222
-rw-r--r--net/openvswitch/vport-vxlan.c2
-rw-r--r--net/sched/act_police.c4
-rw-r--r--net/sched/cls_basic.c2
-rw-r--r--net/sched/cls_cgroup.c4
-rw-r--r--net/sched/em_ipset.c7
-rw-r--r--net/sched/em_meta.c4
-rw-r--r--net/sched/sch_api.c3
-rw-r--r--net/sched/sch_generic.c11
-rw-r--r--net/sched/sch_htb.c17
-rw-r--r--net/sched/sch_tbf.c4
-rw-r--r--net/sctp/socket.c2
-rw-r--r--net/xfrm/xfrm_state.c2
84 files changed, 4414 insertions, 2547 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 61fc573f1142..b3d17d1c49c3 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -98,14 +98,14 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
vlan_gvrp_request_leave(dev);
vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL);
+
+ netdev_upper_dev_unlink(real_dev, dev);
/* Because unregister_netdevice_queue() makes sure at least one rcu
* grace period is respected before device freeing,
* we dont need to call synchronize_net() here.
*/
unregister_netdevice_queue(dev, head);
- netdev_upper_dev_unlink(real_dev, dev);
-
if (grp->nr_vlan_devs == 0) {
vlan_mvrp_uninit_applicant(real_dev);
vlan_gvrp_uninit_applicant(real_dev);
@@ -169,13 +169,13 @@ int register_vlan_dev(struct net_device *dev)
if (err < 0)
goto out_uninit_mvrp;
- err = netdev_upper_dev_link(real_dev, dev);
- if (err)
- goto out_uninit_mvrp;
-
err = register_netdevice(dev);
if (err < 0)
- goto out_upper_dev_unlink;
+ goto out_uninit_mvrp;
+
+ err = netdev_upper_dev_link(real_dev, dev);
+ if (err)
+ goto out_unregister_netdev;
/* Account for reference in struct vlan_dev_priv */
dev_hold(real_dev);
@@ -191,8 +191,8 @@ int register_vlan_dev(struct net_device *dev)
return 0;
-out_upper_dev_unlink:
- netdev_upper_dev_unlink(real_dev, dev);
+out_unregister_netdev:
+ unregister_netdevice(dev);
out_uninit_mvrp:
if (grp->nr_vlan_devs == 0)
vlan_mvrp_uninit_applicant(real_dev);
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index dea6a287daca..6a791e73e39d 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -11,3 +11,5 @@ obj-$(CONFIG_BT_HIDP) += hidp/
bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \
hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \
a2mp.o amp.o
+
+subdir-ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 9096137c889c..e6e1278dca89 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -490,6 +490,7 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
}
EXPORT_SYMBOL(bt_sock_ioctl);
+/* This function expects the sk lock to be held when called */
int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo)
{
DECLARE_WAITQUEUE(wait, current);
@@ -525,6 +526,46 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo)
}
EXPORT_SYMBOL(bt_sock_wait_state);
+/* This function expects the sk lock to be held when called */
+int bt_sock_wait_ready(struct sock *sk, unsigned long flags)
+{
+ DECLARE_WAITQUEUE(wait, current);
+ unsigned long timeo;
+ int err = 0;
+
+ BT_DBG("sk %p", sk);
+
+ timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags)) {
+ if (!timeo) {
+ err = -EAGAIN;
+ break;
+ }
+
+ if (signal_pending(current)) {
+ err = sock_intr_errno(timeo);
+ break;
+ }
+
+ release_sock(sk);
+ timeo = schedule_timeout(timeo);
+ lock_sock(sk);
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ err = sock_error(sk);
+ if (err)
+ break;
+ }
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(sk_sleep(sk), &wait);
+
+ return err;
+}
+EXPORT_SYMBOL(bt_sock_wait_ready);
+
#ifdef CONFIG_PROC_FS
struct bt_seq_state {
struct bt_sock_list *l;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index f0817121ec5e..514148b7a66b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -518,6 +518,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src)
list_for_each_entry(d, &hci_dev_list, list) {
if (!test_bit(HCI_UP, &d->flags) ||
test_bit(HCI_RAW, &d->flags) ||
+ test_bit(HCI_USER_CHANNEL, &d->dev_flags) ||
d->dev_type != HCI_BREDR)
continue;
@@ -580,6 +581,9 @@ static struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
{
struct hci_conn *acl;
+ if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+ return ERR_PTR(-ENOTSUPP);
+
acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
if (!acl) {
acl = hci_conn_add(hdev, ACL_LINK, dst);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index fb7356fcfe51..82dbdc6a7e9e 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -519,6 +519,8 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
if (lmp_bredr_capable(hdev))
bredr_setup(req);
+ else
+ clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
if (lmp_le_capable(hdev))
le_setup(req);
@@ -607,6 +609,34 @@ static void hci_set_le_support(struct hci_request *req)
&cp);
}
+static void hci_set_event_mask_page_2(struct hci_request *req)
+{
+ struct hci_dev *hdev = req->hdev;
+ u8 events[8] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
+
+ /* If Connectionless Slave Broadcast master role is supported
+ * enable all necessary events for it.
+ */
+ if (hdev->features[2][0] & 0x01) {
+ events[1] |= 0x40; /* Triggered Clock Capture */
+ events[1] |= 0x80; /* Synchronization Train Complete */
+ events[2] |= 0x10; /* Slave Page Response Timeout */
+ events[2] |= 0x20; /* CSB Channel Map Change */
+ }
+
+ /* If Connectionless Slave Broadcast slave role is supported
+ * enable all necessary events for it.
+ */
+ if (hdev->features[2][0] & 0x02) {
+ events[2] |= 0x01; /* Synchronization Train Received */
+ events[2] |= 0x02; /* CSB Receive */
+ events[2] |= 0x04; /* CSB Timeout */
+ events[2] |= 0x08; /* Truncated Page Complete */
+ }
+
+ hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events);
+}
+
static void hci_init3_req(struct hci_request *req, unsigned long opt)
{
struct hci_dev *hdev = req->hdev;
@@ -648,6 +678,19 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
}
}
+static void hci_init4_req(struct hci_request *req, unsigned long opt)
+{
+ struct hci_dev *hdev = req->hdev;
+
+ /* Set event mask page 2 if the HCI command for it is supported */
+ if (hdev->commands[22] & 0x04)
+ hci_set_event_mask_page_2(req);
+
+ /* Check for Synchronization Train support */
+ if (hdev->features[2][0] & 0x04)
+ hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL);
+}
+
static int __hci_init(struct hci_dev *hdev)
{
int err;
@@ -667,7 +710,11 @@ static int __hci_init(struct hci_dev *hdev)
if (err < 0)
return err;
- return __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT);
+ err = __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT);
+ if (err < 0)
+ return err;
+
+ return __hci_req_sync(hdev, hci_init4_req, 0, HCI_INIT_TIMEOUT);
}
static void hci_scan_req(struct hci_request *req, unsigned long opt)
@@ -984,6 +1031,16 @@ int hci_inquiry(void __user *arg)
if (!hdev)
return -ENODEV;
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ err = -EBUSY;
+ goto done;
+ }
+
+ if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+ err = -EOPNOTSUPP;
+ goto done;
+ }
+
hci_dev_lock(hdev);
if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX ||
inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) {
@@ -1051,14 +1108,14 @@ static u8 create_ad(struct hci_dev *hdev, u8 *ptr)
if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
flags |= LE_AD_GENERAL;
- if (!lmp_bredr_capable(hdev))
+ if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+ if (lmp_le_br_capable(hdev))
+ flags |= LE_AD_SIM_LE_BREDR_CTRL;
+ if (lmp_host_le_br_capable(hdev))
+ flags |= LE_AD_SIM_LE_BREDR_HOST;
+ } else {
flags |= LE_AD_NO_BREDR;
-
- if (lmp_le_br_capable(hdev))
- flags |= LE_AD_SIM_LE_BREDR_CTRL;
-
- if (lmp_host_le_br_capable(hdev))
- flags |= LE_AD_SIM_LE_BREDR_HOST;
+ }
if (flags) {
BT_DBG("adv flags 0x%02x", flags);
@@ -1126,17 +1183,10 @@ void hci_update_ad(struct hci_request *req)
hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
}
-/* ---- HCI ioctl helpers ---- */
-
-int hci_dev_open(__u16 dev)
+static int hci_dev_do_open(struct hci_dev *hdev)
{
- struct hci_dev *hdev;
int ret = 0;
- hdev = hci_dev_get(dev);
- if (!hdev)
- return -ENODEV;
-
BT_DBG("%s %p", hdev->name, hdev);
hci_req_lock(hdev);
@@ -1172,16 +1222,11 @@ int hci_dev_open(__u16 dev)
ret = hdev->setup(hdev);
if (!ret) {
- /* Treat all non BR/EDR controllers as raw devices if
- * enable_hs is not set.
- */
- if (hdev->dev_type != HCI_BREDR && !enable_hs)
- set_bit(HCI_RAW, &hdev->flags);
-
if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
set_bit(HCI_RAW, &hdev->flags);
- if (!test_bit(HCI_RAW, &hdev->flags))
+ if (!test_bit(HCI_RAW, &hdev->flags) &&
+ !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
ret = __hci_init(hdev);
}
@@ -1192,6 +1237,7 @@ int hci_dev_open(__u16 dev)
set_bit(HCI_UP, &hdev->flags);
hci_notify(hdev, HCI_DEV_UP);
if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
+ !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
mgmt_valid_hdev(hdev)) {
hci_dev_lock(hdev);
mgmt_powered(hdev, 1);
@@ -1220,10 +1266,37 @@ int hci_dev_open(__u16 dev)
done:
hci_req_unlock(hdev);
- hci_dev_put(hdev);
return ret;
}
+/* ---- HCI ioctl helpers ---- */
+
+int hci_dev_open(__u16 dev)
+{
+ struct hci_dev *hdev;
+ int err;
+
+ hdev = hci_dev_get(dev);
+ if (!hdev)
+ return -ENODEV;
+
+ /* We need to ensure that no other power on/off work is pending
+ * before proceeding to call hci_dev_do_open. This is
+ * particularly important if the setup procedure has not yet
+ * completed.
+ */
+ if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+ cancel_delayed_work(&hdev->power_off);
+
+ flush_workqueue(hdev->req_workqueue);
+
+ err = hci_dev_do_open(hdev);
+
+ hci_dev_put(hdev);
+
+ return err;
+}
+
static int hci_dev_do_close(struct hci_dev *hdev)
{
BT_DBG("%s %p", hdev->name, hdev);
@@ -1328,11 +1401,17 @@ int hci_dev_close(__u16 dev)
if (!hdev)
return -ENODEV;
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ err = -EBUSY;
+ goto done;
+ }
+
if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags))
cancel_delayed_work(&hdev->power_off);
err = hci_dev_do_close(hdev);
+done:
hci_dev_put(hdev);
return err;
}
@@ -1348,8 +1427,15 @@ int hci_dev_reset(__u16 dev)
hci_req_lock(hdev);
- if (!test_bit(HCI_UP, &hdev->flags))
+ if (!test_bit(HCI_UP, &hdev->flags)) {
+ ret = -ENETDOWN;
goto done;
+ }
+
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ ret = -EBUSY;
+ goto done;
+ }
/* Drop queues */
skb_queue_purge(&hdev->rx_q);
@@ -1384,10 +1470,15 @@ int hci_dev_reset_stat(__u16 dev)
if (!hdev)
return -ENODEV;
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ ret = -EBUSY;
+ goto done;
+ }
+
memset(&hdev->stat, 0, sizeof(struct hci_dev_stats));
+done:
hci_dev_put(hdev);
-
return ret;
}
@@ -1404,6 +1495,16 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
if (!hdev)
return -ENODEV;
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ err = -EBUSY;
+ goto done;
+ }
+
+ if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+ err = -EOPNOTSUPP;
+ goto done;
+ }
+
switch (cmd) {
case HCISETAUTH:
err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt,
@@ -1462,6 +1563,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
break;
}
+done:
hci_dev_put(hdev);
return err;
}
@@ -1534,7 +1636,7 @@ int hci_get_dev_info(void __user *arg)
strcpy(di.name, hdev->name);
di.bdaddr = hdev->bdaddr;
- di.type = (hdev->bus & 0x0f) | (hdev->dev_type << 4);
+ di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4);
di.flags = hdev->flags;
di.pkt_type = hdev->pkt_type;
if (lmp_bredr_capable(hdev)) {
@@ -1570,6 +1672,9 @@ static int hci_rfkill_set_block(void *data, bool blocked)
BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked);
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+ return -EBUSY;
+
if (blocked) {
set_bit(HCI_RFKILLED, &hdev->dev_flags);
if (!test_bit(HCI_SETUP, &hdev->dev_flags))
@@ -1592,7 +1697,7 @@ static void hci_power_on(struct work_struct *work)
BT_DBG("%s", hdev->name);
- err = hci_dev_open(hdev->id);
+ err = hci_dev_do_open(hdev);
if (err < 0) {
mgmt_set_powered_failed(hdev, err);
return;
@@ -2225,8 +2330,13 @@ int hci_register_dev(struct hci_dev *hdev)
set_bit(HCI_SETUP, &hdev->dev_flags);
- if (hdev->dev_type != HCI_AMP)
+ if (hdev->dev_type != HCI_AMP) {
set_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+ /* Assume BR/EDR support until proven otherwise (such as
+ * through reading supported features during init.
+ */
+ set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+ }
write_lock(&hci_dev_list_lock);
list_add(&hdev->list, &hci_dev_list);
@@ -3272,15 +3382,13 @@ static void hci_tx_work(struct work_struct *work)
BT_DBG("%s acl %d sco %d le %d", hdev->name, hdev->acl_cnt,
hdev->sco_cnt, hdev->le_cnt);
- /* Schedule queues and send stuff to HCI driver */
-
- hci_sched_acl(hdev);
-
- hci_sched_sco(hdev);
-
- hci_sched_esco(hdev);
-
- hci_sched_le(hdev);
+ if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ /* Schedule queues and send stuff to HCI driver */
+ hci_sched_acl(hdev);
+ hci_sched_sco(hdev);
+ hci_sched_esco(hdev);
+ hci_sched_le(hdev);
+ }
/* Send next queued raw (unknown type) packet */
while ((skb = skb_dequeue(&hdev->raw_q)))
@@ -3471,7 +3579,8 @@ static void hci_rx_work(struct work_struct *work)
hci_send_to_sock(hdev, skb);
}
- if (test_bit(HCI_RAW, &hdev->flags)) {
+ if (test_bit(HCI_RAW, &hdev->flags) ||
+ test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
kfree_skb(skb);
continue;
}
@@ -3526,7 +3635,7 @@ static void hci_cmd_work(struct work_struct *work)
kfree_skb(hdev->sent_cmd);
- hdev->sent_cmd = skb_clone(skb, GFP_ATOMIC);
+ hdev->sent_cmd = skb_clone(skb, GFP_KERNEL);
if (hdev->sent_cmd) {
atomic_dec(&hdev->cmd_cnt);
hci_send_frame(skb);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 8db3e89fae35..4785ab0795f5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -297,6 +297,11 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb)
goto done;
}
+ /* We need to ensure that we set this back on if someone changed
+ * the scan mode through a raw HCI socket.
+ */
+ set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
old_pscan = test_and_clear_bit(HCI_PSCAN, &hdev->flags);
old_iscan = test_and_clear_bit(HCI_ISCAN, &hdev->flags);
@@ -994,20 +999,20 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
return;
if (!status) {
- if (sent->le)
+ if (sent->le) {
hdev->features[1][0] |= LMP_HOST_LE;
- else
+ set_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+ } else {
hdev->features[1][0] &= ~LMP_HOST_LE;
+ clear_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+ clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+ }
if (sent->simul)
hdev->features[1][0] |= LMP_HOST_LE_BREDR;
else
hdev->features[1][0] &= ~LMP_HOST_LE_BREDR;
}
-
- if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
- !test_bit(HCI_INIT, &hdev->flags))
- mgmt_le_enable_complete(hdev, sent->le, status);
}
static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev,
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 9bd7d959e384..579886186c3a 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -66,6 +66,46 @@ static struct bt_sock_list hci_sk_list = {
.lock = __RW_LOCK_UNLOCKED(hci_sk_list.lock)
};
+static bool is_filtered_packet(struct sock *sk, struct sk_buff *skb)
+{
+ struct hci_filter *flt;
+ int flt_type, flt_event;
+
+ /* Apply filter */
+ flt = &hci_pi(sk)->filter;
+
+ if (bt_cb(skb)->pkt_type == HCI_VENDOR_PKT)
+ flt_type = 0;
+ else
+ flt_type = bt_cb(skb)->pkt_type & HCI_FLT_TYPE_BITS;
+
+ if (!test_bit(flt_type, &flt->type_mask))
+ return true;
+
+ /* Extra filter for event packets only */
+ if (bt_cb(skb)->pkt_type != HCI_EVENT_PKT)
+ return false;
+
+ flt_event = (*(__u8 *)skb->data & HCI_FLT_EVENT_BITS);
+
+ if (!hci_test_bit(flt_event, &flt->event_mask))
+ return true;
+
+ /* Check filter only when opcode is set */
+ if (!flt->opcode)
+ return false;
+
+ if (flt_event == HCI_EV_CMD_COMPLETE &&
+ flt->opcode != get_unaligned((__le16 *)(skb->data + 3)))
+ return true;
+
+ if (flt_event == HCI_EV_CMD_STATUS &&
+ flt->opcode != get_unaligned((__le16 *)(skb->data + 4)))
+ return true;
+
+ return false;
+}
+
/* Send frame to RAW socket */
void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
{
@@ -77,7 +117,6 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
read_lock(&hci_sk_list.lock);
sk_for_each(sk, &hci_sk_list.head) {
- struct hci_filter *flt;
struct sk_buff *nskb;
if (sk->sk_state != BT_BOUND || hci_pi(sk)->hdev != hdev)
@@ -87,31 +126,19 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
if (skb->sk == sk)
continue;
- if (hci_pi(sk)->channel != HCI_CHANNEL_RAW)
- continue;
-
- /* Apply filter */
- flt = &hci_pi(sk)->filter;
-
- if (!test_bit((bt_cb(skb)->pkt_type == HCI_VENDOR_PKT) ?
- 0 : (bt_cb(skb)->pkt_type & HCI_FLT_TYPE_BITS),
- &flt->type_mask))
- continue;
-
- if (bt_cb(skb)->pkt_type == HCI_EVENT_PKT) {
- int evt = (*(__u8 *)skb->data & HCI_FLT_EVENT_BITS);
-
- if (!hci_test_bit(evt, &flt->event_mask))
+ if (hci_pi(sk)->channel == HCI_CHANNEL_RAW) {
+ if (is_filtered_packet(sk, skb))
continue;
-
- if (flt->opcode &&
- ((evt == HCI_EV_CMD_COMPLETE &&
- flt->opcode !=
- get_unaligned((__le16 *)(skb->data + 3))) ||
- (evt == HCI_EV_CMD_STATUS &&
- flt->opcode !=
- get_unaligned((__le16 *)(skb->data + 4)))))
+ } else if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+ if (!bt_cb(skb)->incoming)
+ continue;
+ 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)
continue;
+ } else {
+ /* Don't send frame to other channel types */
+ continue;
}
if (!skb_copy) {
@@ -426,6 +453,12 @@ static int hci_sock_release(struct socket *sock)
bt_sock_unlink(&hci_sk_list, sk);
if (hdev) {
+ if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+ mgmt_index_added(hdev);
+ clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags);
+ hci_dev_close(hdev->id);
+ }
+
atomic_dec(&hdev->promisc);
hci_dev_put(hdev);
}
@@ -482,6 +515,9 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
if (!hdev)
return -EBADFD;
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+ return -EBUSY;
+
switch (cmd) {
case HCISETRAW:
if (!capable(CAP_NET_ADMIN))
@@ -512,23 +548,32 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
if (!capable(CAP_NET_ADMIN))
return -EPERM;
return hci_sock_blacklist_del(hdev, (void __user *) arg);
-
- default:
- if (hdev->ioctl)
- return hdev->ioctl(hdev, cmd, arg);
- return -EINVAL;
}
+
+ if (hdev->ioctl)
+ return hdev->ioctl(hdev, cmd, arg);
+
+ return -EINVAL;
}
static int hci_sock_ioctl(struct socket *sock, unsigned int cmd,
unsigned long arg)
{
- struct sock *sk = sock->sk;
void __user *argp = (void __user *) arg;
+ struct sock *sk = sock->sk;
int err;
BT_DBG("cmd %x arg %lx", cmd, arg);
+ lock_sock(sk);
+
+ if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) {
+ err = -EBADFD;
+ goto done;
+ }
+
+ release_sock(sk);
+
switch (cmd) {
case HCIGETDEVLIST:
return hci_get_dev_list(argp);
@@ -573,13 +618,15 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd,
case HCIINQUIRY:
return hci_inquiry(argp);
-
- default:
- lock_sock(sk);
- err = hci_sock_bound_ioctl(sk, cmd, arg);
- release_sock(sk);
- return err;
}
+
+ lock_sock(sk);
+
+ err = hci_sock_bound_ioctl(sk, cmd, arg);
+
+done:
+ release_sock(sk);
+ return err;
}
static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
@@ -629,6 +676,56 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
hci_pi(sk)->hdev = hdev;
break;
+ case HCI_CHANNEL_USER:
+ if (hci_pi(sk)->hdev) {
+ err = -EALREADY;
+ goto done;
+ }
+
+ if (haddr.hci_dev == HCI_DEV_NONE) {
+ err = -EINVAL;
+ goto done;
+ }
+
+ if (!capable(CAP_NET_ADMIN)) {
+ err = -EPERM;
+ goto done;
+ }
+
+ hdev = hci_dev_get(haddr.hci_dev);
+ if (!hdev) {
+ err = -ENODEV;
+ goto done;
+ }
+
+ if (test_bit(HCI_UP, &hdev->flags) ||
+ test_bit(HCI_INIT, &hdev->flags) ||
+ test_bit(HCI_SETUP, &hdev->dev_flags)) {
+ err = -EBUSY;
+ hci_dev_put(hdev);
+ goto done;
+ }
+
+ if (test_and_set_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ err = -EUSERS;
+ hci_dev_put(hdev);
+ goto done;
+ }
+
+ mgmt_index_removed(hdev);
+
+ err = hci_dev_open(hdev->id);
+ if (err) {
+ clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags);
+ hci_dev_put(hdev);
+ goto done;
+ }
+
+ atomic_inc(&hdev->promisc);
+
+ hci_pi(sk)->hdev = hdev;
+ break;
+
case HCI_CHANNEL_CONTROL:
if (haddr.hci_dev != HCI_DEV_NONE) {
err = -EINVAL;
@@ -677,22 +774,30 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr,
{
struct sockaddr_hci *haddr = (struct sockaddr_hci *) addr;
struct sock *sk = sock->sk;
- struct hci_dev *hdev = hci_pi(sk)->hdev;
+ struct hci_dev *hdev;
+ int err = 0;
BT_DBG("sock %p sk %p", sock, sk);
- if (!hdev)
- return -EBADFD;
+ if (peer)
+ return -EOPNOTSUPP;
lock_sock(sk);
+ hdev = hci_pi(sk)->hdev;
+ if (!hdev) {
+ err = -EBADFD;
+ goto done;
+ }
+
*addr_len = sizeof(*haddr);
haddr->hci_family = AF_BLUETOOTH;
haddr->hci_dev = hdev->id;
- haddr->hci_channel= 0;
+ haddr->hci_channel= hci_pi(sk)->channel;
+done:
release_sock(sk);
- return 0;
+ return err;
}
static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg,
@@ -767,6 +872,7 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
case HCI_CHANNEL_RAW:
hci_sock_cmsg(sk, msg, skb);
break;
+ case HCI_CHANNEL_USER:
case HCI_CHANNEL_CONTROL:
case HCI_CHANNEL_MONITOR:
sock_recv_timestamp(msg, sk, skb);
@@ -801,6 +907,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
switch (hci_pi(sk)->channel) {
case HCI_CHANNEL_RAW:
+ case HCI_CHANNEL_USER:
break;
case HCI_CHANNEL_CONTROL:
err = mgmt_control(sk, msg, len);
@@ -837,7 +944,8 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
skb_pull(skb, 1);
skb->dev = (void *) hdev;
- if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
+ if (hci_pi(sk)->channel == HCI_CHANNEL_RAW &&
+ bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
u16 opcode = get_unaligned_le16(skb->data);
u16 ogf = hci_opcode_ogf(opcode);
u16 ocf = hci_opcode_ocf(opcode);
@@ -868,6 +976,14 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
goto drop;
}
+ if (hci_pi(sk)->channel == HCI_CHANNEL_USER &&
+ bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
+ bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+ bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+ err = -EINVAL;
+ goto drop;
+ }
+
skb_queue_tail(&hdev->raw_q, skb);
queue_work(hdev->workqueue, &hdev->tx_work);
}
@@ -895,7 +1011,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname,
lock_sock(sk);
if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) {
- err = -EINVAL;
+ err = -EBADFD;
goto done;
}
@@ -981,7 +1097,7 @@ static int hci_sock_getsockopt(struct socket *sock, int level, int optname,
lock_sock(sk);
if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) {
- err = -EINVAL;
+ err = -EBADFD;
goto done;
}
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 63fa11109a1c..02dba4e6df96 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1016,13 +1016,12 @@ static bool __amp_capable(struct l2cap_chan *chan)
{
struct l2cap_conn *conn = chan->conn;
- if (enable_hs &&
- hci_amp_capable() &&
+ if (conn->hs_enabled && hci_amp_capable() &&
chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED &&
conn->fixed_chan_mask & L2CAP_FC_A2MP)
return true;
- else
- return false;
+
+ return false;
}
static bool l2cap_check_efs(struct l2cap_chan *chan)
@@ -1638,6 +1637,10 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
conn->feat_mask = 0;
+ if (hcon->type == ACL_LINK)
+ conn->hs_enabled = test_bit(HCI_HS_ENABLED,
+ &hcon->hdev->dev_flags);
+
spin_lock_init(&conn->lock);
mutex_init(&conn->chan_lock);
@@ -3084,14 +3087,14 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask)
}
}
-static inline bool __l2cap_ews_supported(struct l2cap_chan *chan)
+static inline bool __l2cap_ews_supported(struct l2cap_conn *conn)
{
- return enable_hs && chan->conn->feat_mask & L2CAP_FEAT_EXT_WINDOW;
+ return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_WINDOW;
}
-static inline bool __l2cap_efs_supported(struct l2cap_chan *chan)
+static inline bool __l2cap_efs_supported(struct l2cap_conn *conn)
{
- return enable_hs && chan->conn->feat_mask & L2CAP_FEAT_EXT_FLOW;
+ return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_FLOW;
}
static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
@@ -3135,7 +3138,7 @@ static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
static inline void l2cap_txwin_setup(struct l2cap_chan *chan)
{
if (chan->tx_win > L2CAP_DEFAULT_TX_WINDOW &&
- __l2cap_ews_supported(chan)) {
+ __l2cap_ews_supported(chan->conn)) {
/* use extended control field */
set_bit(FLAG_EXT_CTRL, &chan->flags);
chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW;
@@ -3165,7 +3168,7 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data)
if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state))
break;
- if (__l2cap_efs_supported(chan))
+ if (__l2cap_efs_supported(chan->conn))
set_bit(FLAG_EFS_ENABLE, &chan->flags);
/* fall through */
@@ -3317,7 +3320,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
break;
case L2CAP_CONF_EWS:
- if (!enable_hs)
+ if (!chan->conn->hs_enabled)
return -ECONNREFUSED;
set_bit(FLAG_EXT_CTRL, &chan->flags);
@@ -3349,7 +3352,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
}
if (remote_efs) {
- if (__l2cap_efs_supported(chan))
+ if (__l2cap_efs_supported(chan->conn))
set_bit(FLAG_EFS_ENABLE, &chan->flags);
else
return -ECONNREFUSED;
@@ -3891,13 +3894,13 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn,
if (scid) {
chan = __l2cap_get_chan_by_scid(conn, scid);
if (!chan) {
- err = -EFAULT;
+ err = -EBADSLT;
goto unlock;
}
} else {
chan = __l2cap_get_chan_by_ident(conn, cmd->ident);
if (!chan) {
- err = -EFAULT;
+ err = -EBADSLT;
goto unlock;
}
}
@@ -3985,7 +3988,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
chan = l2cap_get_chan_by_scid(conn, dcid);
if (!chan)
- return -ENOENT;
+ return -EBADSLT;
if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) {
struct l2cap_cmd_rej_cid rej;
@@ -4213,7 +4216,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn,
chan = __l2cap_get_chan_by_scid(conn, dcid);
if (!chan) {
mutex_unlock(&conn->chan_lock);
- return 0;
+ return -EBADSLT;
}
l2cap_chan_lock(chan);
@@ -4303,7 +4306,7 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
if (!disable_ertm)
feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING
| L2CAP_FEAT_FCS;
- if (enable_hs)
+ if (conn->hs_enabled)
feat_mask |= L2CAP_FEAT_EXT_FLOW
| L2CAP_FEAT_EXT_WINDOW;
@@ -4314,7 +4317,7 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
u8 buf[12];
struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf;
- if (enable_hs)
+ if (conn->hs_enabled)
l2cap_fixed_chan[0] |= L2CAP_FC_A2MP;
else
l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP;
@@ -4411,7 +4414,7 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
if (cmd_len != sizeof(*req))
return -EPROTO;
- if (!enable_hs)
+ if (!conn->hs_enabled)
return -EINVAL;
psm = le16_to_cpu(req->psm);
@@ -4445,7 +4448,7 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
hs_hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, conn->dst);
if (!hs_hcon) {
hci_dev_put(hdev);
- return -EFAULT;
+ return -EBADSLT;
}
BT_DBG("mgr %p bredr_chan %p hs_hcon %p", mgr, chan, hs_hcon);
@@ -4469,7 +4472,7 @@ error:
l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP,
sizeof(rsp), &rsp);
- return -EFAULT;
+ return 0;
}
static void l2cap_send_move_chan_req(struct l2cap_chan *chan, u8 dest_amp_id)
@@ -4838,7 +4841,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id);
- if (!enable_hs)
+ if (!conn->hs_enabled)
return -EINVAL;
chan = l2cap_get_chan_by_dcid(conn, icid);
@@ -5219,7 +5222,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
case L2CAP_CONN_RSP:
case L2CAP_CREATE_CHAN_RSP:
- err = l2cap_connect_create_rsp(conn, cmd, cmd_len, data);
+ l2cap_connect_create_rsp(conn, cmd, cmd_len, data);
break;
case L2CAP_CONF_REQ:
@@ -5227,7 +5230,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
break;
case L2CAP_CONF_RSP:
- err = l2cap_config_rsp(conn, cmd, cmd_len, data);
+ l2cap_config_rsp(conn, cmd, cmd_len, data);
break;
case L2CAP_DISCONN_REQ:
@@ -5235,7 +5238,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
break;
case L2CAP_DISCONN_RSP:
- err = l2cap_disconnect_rsp(conn, cmd, cmd_len, data);
+ l2cap_disconnect_rsp(conn, cmd, cmd_len, data);
break;
case L2CAP_ECHO_REQ:
@@ -5250,7 +5253,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
break;
case L2CAP_INFO_RSP:
- err = l2cap_information_rsp(conn, cmd, cmd_len, data);
+ l2cap_information_rsp(conn, cmd, cmd_len, data);
break;
case L2CAP_CREATE_CHAN_REQ:
@@ -5262,7 +5265,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
break;
case L2CAP_MOVE_CHAN_RSP:
- err = l2cap_move_channel_rsp(conn, cmd, cmd_len, data);
+ l2cap_move_channel_rsp(conn, cmd, cmd_len, data);
break;
case L2CAP_MOVE_CHAN_CFM:
@@ -5270,7 +5273,7 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
break;
case L2CAP_MOVE_CHAN_CFM_RSP:
- err = l2cap_move_channel_confirm_rsp(conn, cmd, cmd_len, data);
+ l2cap_move_channel_confirm_rsp(conn, cmd, cmd_len, data);
break;
default:
@@ -5301,54 +5304,65 @@ static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn,
}
}
+static __le16 l2cap_err_to_reason(int err)
+{
+ switch (err) {
+ case -EBADSLT:
+ return __constant_cpu_to_le16(L2CAP_REJ_INVALID_CID);
+ case -EMSGSIZE:
+ return __constant_cpu_to_le16(L2CAP_REJ_MTU_EXCEEDED);
+ case -EINVAL:
+ case -EPROTO:
+ default:
+ return __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+ }
+}
+
static inline void l2cap_le_sig_channel(struct l2cap_conn *conn,
struct sk_buff *skb)
{
- u8 *data = skb->data;
- int len = skb->len;
- struct l2cap_cmd_hdr cmd;
+ struct hci_conn *hcon = conn->hcon;
+ struct l2cap_cmd_hdr *cmd;
+ u16 len;
int err;
- l2cap_raw_recv(conn, skb);
+ if (hcon->type != LE_LINK)
+ goto drop;
- while (len >= L2CAP_CMD_HDR_SIZE) {
- u16 cmd_len;
- memcpy(&cmd, data, L2CAP_CMD_HDR_SIZE);
- data += L2CAP_CMD_HDR_SIZE;
- len -= L2CAP_CMD_HDR_SIZE;
+ if (skb->len < L2CAP_CMD_HDR_SIZE)
+ goto drop;
- cmd_len = le16_to_cpu(cmd.len);
+ cmd = (void *) skb->data;
+ skb_pull(skb, L2CAP_CMD_HDR_SIZE);
- BT_DBG("code 0x%2.2x len %d id 0x%2.2x", cmd.code, cmd_len,
- cmd.ident);
+ len = le16_to_cpu(cmd->len);
- if (cmd_len > len || !cmd.ident) {
- BT_DBG("corrupted command");
- break;
- }
+ BT_DBG("code 0x%2.2x len %d id 0x%2.2x", cmd->code, len, cmd->ident);
- err = l2cap_le_sig_cmd(conn, &cmd, data);
- if (err) {
- struct l2cap_cmd_rej_unk rej;
+ if (len != skb->len || !cmd->ident) {
+ BT_DBG("corrupted command");
+ goto drop;
+ }
- BT_ERR("Wrong link type (%d)", err);
+ err = l2cap_le_sig_cmd(conn, cmd, skb->data);
+ if (err) {
+ struct l2cap_cmd_rej_unk rej;
- /* FIXME: Map err to a valid reason */
- rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
- l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ,
- sizeof(rej), &rej);
- }
+ BT_ERR("Wrong link type (%d)", err);
- data += cmd_len;
- len -= cmd_len;
+ rej.reason = l2cap_err_to_reason(err);
+ l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
+ sizeof(rej), &rej);
}
+drop:
kfree_skb(skb);
}
static inline void l2cap_sig_channel(struct l2cap_conn *conn,
struct sk_buff *skb)
{
+ struct hci_conn *hcon = conn->hcon;
u8 *data = skb->data;
int len = skb->len;
struct l2cap_cmd_hdr cmd;
@@ -5356,6 +5370,9 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
l2cap_raw_recv(conn, skb);
+ if (hcon->type != ACL_LINK)
+ goto drop;
+
while (len >= L2CAP_CMD_HDR_SIZE) {
u16 cmd_len;
memcpy(&cmd, data, L2CAP_CMD_HDR_SIZE);
@@ -5378,8 +5395,7 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
BT_ERR("Wrong link type (%d)", err);
- /* FIXME: Map err to a valid reason */
- rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+ rej.reason = l2cap_err_to_reason(err);
l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ,
sizeof(rej), &rej);
}
@@ -5388,6 +5404,7 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
len -= cmd_len;
}
+drop:
kfree_skb(skb);
}
@@ -5784,7 +5801,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan,
struct sk_buff *skb, u8 event)
{
int err = 0;
- bool skb_in_use = 0;
+ bool skb_in_use = false;
BT_DBG("chan %p, control %p, skb %p, event %d", chan, control, skb,
event);
@@ -5805,7 +5822,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan,
control->txseq);
chan->buffer_seq = chan->expected_tx_seq;
- skb_in_use = 1;
+ skb_in_use = true;
err = l2cap_reassemble_sdu(chan, skb, control);
if (err)
@@ -5841,7 +5858,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan,
* current frame is stored for later use.
*/
skb_queue_tail(&chan->srej_q, skb);
- skb_in_use = 1;
+ skb_in_use = true;
BT_DBG("Queued %p (queue len %d)", skb,
skb_queue_len(&chan->srej_q));
@@ -5919,7 +5936,7 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan,
{
int err = 0;
u16 txseq = control->txseq;
- bool skb_in_use = 0;
+ bool skb_in_use = false;
BT_DBG("chan %p, control %p, skb %p, event %d", chan, control, skb,
event);
@@ -5931,7 +5948,7 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan,
/* Keep frame for reassembly later */
l2cap_pass_to_tx(chan, control);
skb_queue_tail(&chan->srej_q, skb);
- skb_in_use = 1;
+ skb_in_use = true;
BT_DBG("Queued %p (queue len %d)", skb,
skb_queue_len(&chan->srej_q));
@@ -5942,7 +5959,7 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan,
l2cap_pass_to_tx(chan, control);
skb_queue_tail(&chan->srej_q, skb);
- skb_in_use = 1;
+ skb_in_use = true;
BT_DBG("Queued %p (queue len %d)", skb,
skb_queue_len(&chan->srej_q));
@@ -5957,7 +5974,7 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan,
* the missing frames.
*/
skb_queue_tail(&chan->srej_q, skb);
- skb_in_use = 1;
+ skb_in_use = true;
BT_DBG("Queued %p (queue len %d)", skb,
skb_queue_len(&chan->srej_q));
@@ -5971,7 +5988,7 @@ static int l2cap_rx_state_srej_sent(struct l2cap_chan *chan,
* SREJ'd frames.
*/
skb_queue_tail(&chan->srej_q, skb);
- skb_in_use = 1;
+ skb_in_use = true;
BT_DBG("Queued %p (queue len %d)", skb,
skb_queue_len(&chan->srej_q));
@@ -6380,8 +6397,12 @@ done:
static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
struct sk_buff *skb)
{
+ struct hci_conn *hcon = conn->hcon;
struct l2cap_chan *chan;
+ if (hcon->type != ACL_LINK)
+ goto drop;
+
chan = l2cap_global_chan_by_psm(0, psm, conn->src, conn->dst);
if (!chan)
goto drop;
@@ -6404,8 +6425,12 @@ drop:
static void l2cap_att_channel(struct l2cap_conn *conn,
struct sk_buff *skb)
{
+ struct hci_conn *hcon = conn->hcon;
struct l2cap_chan *chan;
+ if (hcon->type != LE_LINK)
+ goto drop;
+
chan = l2cap_global_chan_by_scid(BT_CONNECTED, L2CAP_CID_ATT,
conn->src, conn->dst);
if (!chan)
@@ -6441,9 +6466,6 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
BT_DBG("len %d, cid 0x%4.4x", len, cid);
switch (cid) {
- case L2CAP_CID_LE_SIGNALING:
- l2cap_le_sig_channel(conn, skb);
- break;
case L2CAP_CID_SIGNALING:
l2cap_sig_channel(conn, skb);
break;
@@ -6458,6 +6480,10 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
l2cap_att_channel(conn, skb);
break;
+ case L2CAP_CID_LE_SIGNALING:
+ l2cap_le_sig_channel(conn, skb);
+ break;
+
case L2CAP_CID_SMP:
if (smp_sig_channel(conn, skb))
l2cap_conn_del(conn->hcon, EACCES);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 0098af80b213..9119898ef040 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -445,11 +445,6 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname,
break;
case BT_CHANNEL_POLICY:
- if (!enable_hs) {
- err = -ENOPROTOOPT;
- break;
- }
-
if (put_user(chan->chan_policy, (u32 __user *) optval))
err = -EFAULT;
break;
@@ -720,11 +715,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_CHANNEL_POLICY:
- if (!enable_hs) {
- err = -ENOPROTOOPT;
- break;
- }
-
if (get_user(opt, (u32 __user *) optval)) {
err = -EFAULT;
break;
@@ -777,6 +767,12 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
if (sk->sk_state != BT_CONNECTED)
return -ENOTCONN;
+ lock_sock(sk);
+ err = bt_sock_wait_ready(sk, msg->msg_flags);
+ release_sock(sk);
+ if (err)
+ return err;
+
l2cap_chan_lock(chan);
err = l2cap_chan_send(chan, msg, len, sk->sk_priority);
l2cap_chan_unlock(chan);
@@ -799,8 +795,8 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
pi->chan->state = BT_CONFIG;
__l2cap_connect_rsp_defer(pi->chan);
- release_sock(sk);
- return 0;
+ err = 0;
+ goto done;
}
release_sock(sk);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index fedc5399d465..16125ff918f1 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -32,10 +32,8 @@
#include <net/bluetooth/mgmt.h>
#include <net/bluetooth/smp.h>
-bool enable_hs;
-
#define MGMT_VERSION 1
-#define MGMT_REVISION 3
+#define MGMT_REVISION 4
static const u16 mgmt_commands[] = {
MGMT_OP_READ_INDEX_LIST,
@@ -76,6 +74,9 @@ static const u16 mgmt_commands[] = {
MGMT_OP_BLOCK_DEVICE,
MGMT_OP_UNBLOCK_DEVICE,
MGMT_OP_SET_DEVICE_ID,
+ MGMT_OP_SET_ADVERTISING,
+ MGMT_OP_SET_BREDR,
+ MGMT_OP_SET_STATIC_ADDRESS,
};
static const u16 mgmt_events[] = {
@@ -339,6 +340,9 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
if (test_bit(HCI_SETUP, &d->dev_flags))
continue;
+ if (test_bit(HCI_USER_CHANNEL, &d->dev_flags))
+ continue;
+
if (!mgmt_valid_hdev(d))
continue;
@@ -376,13 +380,13 @@ static u32 get_supported_settings(struct hci_dev *hdev)
settings |= MGMT_SETTING_DISCOVERABLE;
settings |= MGMT_SETTING_BREDR;
settings |= MGMT_SETTING_LINK_SECURITY;
- }
-
- if (enable_hs)
settings |= MGMT_SETTING_HS;
+ }
- if (lmp_le_capable(hdev))
+ if (lmp_le_capable(hdev)) {
settings |= MGMT_SETTING_LE;
+ settings |= MGMT_SETTING_ADVERTISING;
+ }
return settings;
}
@@ -406,7 +410,7 @@ static u32 get_current_settings(struct hci_dev *hdev)
if (test_bit(HCI_PAIRABLE, &hdev->dev_flags))
settings |= MGMT_SETTING_PAIRABLE;
- if (lmp_bredr_capable(hdev))
+ if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
settings |= MGMT_SETTING_BREDR;
if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
@@ -421,6 +425,9 @@ static u32 get_current_settings(struct hci_dev *hdev)
if (test_bit(HCI_HS_ENABLED, &hdev->dev_flags))
settings |= MGMT_SETTING_HS;
+ if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
+ settings |= MGMT_SETTING_ADVERTISING;
+
return settings;
}
@@ -804,6 +811,12 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data,
hci_dev_lock(hdev);
+ if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED,
+ MGMT_STATUS_BUSY);
+ goto failed;
+ }
+
if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags)) {
cancel_delayed_work(&hdev->power_off);
@@ -820,12 +833,6 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data,
goto failed;
}
- if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) {
- err = cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED,
- MGMT_STATUS_BUSY);
- goto failed;
- }
-
cmd = mgmt_pending_add(sk, MGMT_OP_SET_POWERED, hdev, data, len);
if (!cmd) {
err = -ENOMEM;
@@ -883,20 +890,71 @@ static int new_settings(struct hci_dev *hdev, struct sock *skip)
return mgmt_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, sizeof(ev), skip);
}
+struct cmd_lookup {
+ struct sock *sk;
+ struct hci_dev *hdev;
+ u8 mgmt_status;
+};
+
+static void settings_rsp(struct pending_cmd *cmd, void *data)
+{
+ struct cmd_lookup *match = data;
+
+ send_settings_rsp(cmd->sk, cmd->opcode, match->hdev);
+
+ list_del(&cmd->list);
+
+ if (match->sk == NULL) {
+ match->sk = cmd->sk;
+ sock_hold(match->sk);
+ }
+
+ mgmt_pending_free(cmd);
+}
+
+static void cmd_status_rsp(struct pending_cmd *cmd, void *data)
+{
+ u8 *status = data;
+
+ cmd_status(cmd->sk, cmd->index, cmd->opcode, *status);
+ mgmt_pending_remove(cmd);
+}
+
+static u8 mgmt_bredr_support(struct hci_dev *hdev)
+{
+ if (!lmp_bredr_capable(hdev))
+ return MGMT_STATUS_NOT_SUPPORTED;
+ else if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+ return MGMT_STATUS_REJECTED;
+ else
+ return MGMT_STATUS_SUCCESS;
+}
+
+static u8 mgmt_le_support(struct hci_dev *hdev)
+{
+ if (!lmp_le_capable(hdev))
+ return MGMT_STATUS_NOT_SUPPORTED;
+ else if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+ return MGMT_STATUS_REJECTED;
+ else
+ return MGMT_STATUS_SUCCESS;
+}
+
static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
u16 len)
{
struct mgmt_cp_set_discoverable *cp = data;
struct pending_cmd *cmd;
u16 timeout;
- u8 scan;
+ u8 scan, status;
int err;
BT_DBG("request for %s", hdev->name);
- if (!lmp_bredr_capable(hdev))
+ status = mgmt_bredr_support(hdev);
+ if (status)
return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
- MGMT_STATUS_NOT_SUPPORTED);
+ status);
if (cp->val != 0x00 && cp->val != 0x01)
return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
@@ -1045,14 +1103,15 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data,
struct mgmt_mode *cp = data;
struct pending_cmd *cmd;
struct hci_request req;
- u8 scan;
+ u8 scan, status;
int err;
BT_DBG("request for %s", hdev->name);
- if (!lmp_bredr_capable(hdev))
+ status = mgmt_bredr_support(hdev);
+ if (status)
return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
- MGMT_STATUS_NOT_SUPPORTED);
+ status);
if (cp->val != 0x00 && cp->val != 0x01)
return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
@@ -1168,14 +1227,15 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data,
{
struct mgmt_mode *cp = data;
struct pending_cmd *cmd;
- u8 val;
+ u8 val, status;
int err;
BT_DBG("request for %s", hdev->name);
- if (!lmp_bredr_capable(hdev))
+ status = mgmt_bredr_support(hdev);
+ if (status)
return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
- MGMT_STATUS_NOT_SUPPORTED);
+ status);
if (cp->val != 0x00 && cp->val != 0x01)
return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
@@ -1236,11 +1296,15 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
{
struct mgmt_mode *cp = data;
struct pending_cmd *cmd;
- u8 val;
+ u8 val, status;
int err;
BT_DBG("request for %s", hdev->name);
+ status = mgmt_bredr_support(hdev);
+ if (status)
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP, status);
+
if (!lmp_ssp_capable(hdev))
return cmd_status(sk, hdev->id, MGMT_OP_SET_SSP,
MGMT_STATUS_NOT_SUPPORTED);
@@ -1302,23 +1366,64 @@ failed:
static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
{
struct mgmt_mode *cp = data;
+ bool changed;
+ u8 status;
+ int err;
BT_DBG("request for %s", hdev->name);
- if (!enable_hs)
- return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
- MGMT_STATUS_NOT_SUPPORTED);
+ status = mgmt_bredr_support(hdev);
+ if (status)
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status);
if (cp->val != 0x00 && cp->val != 0x01)
return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
MGMT_STATUS_INVALID_PARAMS);
- if (cp->val)
- set_bit(HCI_HS_ENABLED, &hdev->dev_flags);
- else
- clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+ hci_dev_lock(hdev);
+
+ if (cp->val) {
+ changed = !test_and_set_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+ } else {
+ if (hdev_is_powered(hdev)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+ MGMT_STATUS_REJECTED);
+ goto unlock;
+ }
+
+ changed = test_and_clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+ }
+
+ err = send_settings_rsp(sk, MGMT_OP_SET_HS, hdev);
+ if (err < 0)
+ goto unlock;
+
+ if (changed)
+ err = new_settings(hdev, sk);
+
+unlock:
+ hci_dev_unlock(hdev);
+ return err;
+}
+
+static void le_enable_complete(struct hci_dev *hdev, u8 status)
+{
+ struct cmd_lookup match = { NULL, hdev };
- return send_settings_rsp(sk, MGMT_OP_SET_HS, hdev);
+ if (status) {
+ u8 mgmt_err = mgmt_status(status);
+
+ mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
+ &mgmt_err);
+ return;
+ }
+
+ mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
+
+ new_settings(hdev, match.sk);
+
+ if (match.sk)
+ sock_put(match.sk);
}
static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
@@ -1326,6 +1431,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
struct mgmt_mode *cp = data;
struct hci_cp_write_le_host_supported hci_cp;
struct pending_cmd *cmd;
+ struct hci_request req;
int err;
u8 val, enabled;
@@ -1340,7 +1446,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
MGMT_STATUS_INVALID_PARAMS);
/* LE-only devices do not allow toggling LE on/off */
- if (!lmp_bredr_capable(hdev))
+ if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
return cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
MGMT_STATUS_REJECTED);
@@ -1357,6 +1463,11 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
changed = true;
}
+ if (!val && test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+ clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+ changed = true;
+ }
+
err = send_settings_rsp(sk, MGMT_OP_SET_LE, hdev);
if (err < 0)
goto unlock;
@@ -1367,7 +1478,8 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
goto unlock;
}
- if (mgmt_pending_find(MGMT_OP_SET_LE, hdev)) {
+ if (mgmt_pending_find(MGMT_OP_SET_LE, hdev) ||
+ mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev)) {
err = cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
MGMT_STATUS_BUSY);
goto unlock;
@@ -1386,8 +1498,15 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
hci_cp.simul = lmp_le_br_capable(hdev);
}
- err = hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
- &hci_cp);
+ hci_req_init(&req, hdev);
+
+ if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags) && !val)
+ hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(val), &val);
+
+ hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
+ &hci_cp);
+
+ err = hci_req_run(&req, le_enable_complete);
if (err < 0)
mgmt_pending_remove(cmd);
@@ -1706,6 +1825,12 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
u16 key_count, expected_len;
int i;
+ BT_DBG("request for %s", hdev->name);
+
+ if (!lmp_bredr_capable(hdev))
+ return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
+ MGMT_STATUS_NOT_SUPPORTED);
+
key_count = __le16_to_cpu(cp->key_count);
expected_len = sizeof(*cp) + key_count *
@@ -2685,6 +2810,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
struct hci_request req;
/* General inquiry access code (GIAC) */
u8 lap[3] = { 0x33, 0x8b, 0x9e };
+ u8 status;
int err;
BT_DBG("%s", hdev->name);
@@ -2721,9 +2847,10 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
switch (hdev->discovery.type) {
case DISCOV_TYPE_BREDR:
- if (!lmp_bredr_capable(hdev)) {
+ status = mgmt_bredr_support(hdev);
+ if (status) {
err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
- MGMT_STATUS_NOT_SUPPORTED);
+ status);
mgmt_pending_remove(cmd);
goto failed;
}
@@ -2745,15 +2872,16 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
case DISCOV_TYPE_LE:
case DISCOV_TYPE_INTERLEAVED:
- if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
+ status = mgmt_le_support(hdev);
+ if (status) {
err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
- MGMT_STATUS_NOT_SUPPORTED);
+ status);
mgmt_pending_remove(cmd);
goto failed;
}
if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED &&
- !lmp_bredr_capable(hdev)) {
+ !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
MGMT_STATUS_NOT_SUPPORTED);
mgmt_pending_remove(cmd);
@@ -3065,6 +3193,135 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data,
return err;
}
+static void set_advertising_complete(struct hci_dev *hdev, u8 status)
+{
+ struct cmd_lookup match = { NULL, hdev };
+
+ if (status) {
+ u8 mgmt_err = mgmt_status(status);
+
+ mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev,
+ cmd_status_rsp, &mgmt_err);
+ return;
+ }
+
+ mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp,
+ &match);
+
+ new_settings(hdev, match.sk);
+
+ if (match.sk)
+ sock_put(match.sk);
+}
+
+static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
+{
+ struct mgmt_mode *cp = data;
+ struct pending_cmd *cmd;
+ struct hci_request req;
+ u8 val, enabled, status;
+ int err;
+
+ BT_DBG("request for %s", hdev->name);
+
+ status = mgmt_le_support(hdev);
+ if (status)
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+ status);
+
+ if (cp->val != 0x00 && cp->val != 0x01)
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+ MGMT_STATUS_INVALID_PARAMS);
+
+ hci_dev_lock(hdev);
+
+ val = !!cp->val;
+ enabled = test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+
+ if (!hdev_is_powered(hdev) || val == enabled) {
+ bool changed = false;
+
+ if (val != test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+ change_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+ changed = true;
+ }
+
+ err = send_settings_rsp(sk, MGMT_OP_SET_ADVERTISING, hdev);
+ if (err < 0)
+ goto unlock;
+
+ if (changed)
+ err = new_settings(hdev, sk);
+
+ goto unlock;
+ }
+
+ if (mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev) ||
+ mgmt_pending_find(MGMT_OP_SET_LE, hdev)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+ MGMT_STATUS_BUSY);
+ goto unlock;
+ }
+
+ cmd = mgmt_pending_add(sk, MGMT_OP_SET_ADVERTISING, hdev, data, len);
+ if (!cmd) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ hci_req_init(&req, hdev);
+
+ hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(val), &val);
+
+ err = hci_req_run(&req, set_advertising_complete);
+ if (err < 0)
+ mgmt_pending_remove(cmd);
+
+unlock:
+ hci_dev_unlock(hdev);
+ return err;
+}
+
+static int set_static_address(struct sock *sk, struct hci_dev *hdev,
+ void *data, u16 len)
+{
+ struct mgmt_cp_set_static_address *cp = data;
+ int err;
+
+ BT_DBG("%s", hdev->name);
+
+ if (!lmp_le_capable(hdev))
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
+ MGMT_STATUS_NOT_SUPPORTED);
+
+ if (hdev_is_powered(hdev))
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
+ MGMT_STATUS_REJECTED);
+
+ if (bacmp(&cp->bdaddr, BDADDR_ANY)) {
+ if (!bacmp(&cp->bdaddr, BDADDR_NONE))
+ return cmd_status(sk, hdev->id,
+ MGMT_OP_SET_STATIC_ADDRESS,
+ MGMT_STATUS_INVALID_PARAMS);
+
+ /* Two most significant bits shall be set */
+ if ((cp->bdaddr.b[5] & 0xc0) != 0xc0)
+ return cmd_status(sk, hdev->id,
+ MGMT_OP_SET_STATIC_ADDRESS,
+ MGMT_STATUS_INVALID_PARAMS);
+ }
+
+ hci_dev_lock(hdev);
+
+ bacpy(&hdev->static_addr, &cp->bdaddr);
+
+ err = cmd_complete(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, 0, NULL, 0);
+
+ hci_dev_unlock(hdev);
+
+ return err;
+}
+
static void fast_connectable_complete(struct hci_dev *hdev, u8 status)
{
struct pending_cmd *cmd;
@@ -3108,7 +3365,8 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev,
BT_DBG("%s", hdev->name);
- if (!lmp_bredr_capable(hdev) || hdev->hci_ver < BLUETOOTH_VER_1_2)
+ if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) ||
+ hdev->hci_ver < BLUETOOTH_VER_1_2)
return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
MGMT_STATUS_NOT_SUPPORTED);
@@ -3162,6 +3420,121 @@ unlock:
return err;
}
+static void set_bredr_complete(struct hci_dev *hdev, u8 status)
+{
+ struct pending_cmd *cmd;
+
+ BT_DBG("status 0x%02x", status);
+
+ hci_dev_lock(hdev);
+
+ cmd = mgmt_pending_find(MGMT_OP_SET_BREDR, hdev);
+ if (!cmd)
+ goto unlock;
+
+ if (status) {
+ u8 mgmt_err = mgmt_status(status);
+
+ /* We need to restore the flag if related HCI commands
+ * failed.
+ */
+ clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
+ cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+ } else {
+ send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev);
+ new_settings(hdev, cmd->sk);
+ }
+
+ mgmt_pending_remove(cmd);
+
+unlock:
+ hci_dev_unlock(hdev);
+}
+
+static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
+{
+ struct mgmt_mode *cp = data;
+ struct pending_cmd *cmd;
+ struct hci_request req;
+ int err;
+
+ BT_DBG("request for %s", hdev->name);
+
+ if (!lmp_bredr_capable(hdev) || !lmp_le_capable(hdev))
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+ MGMT_STATUS_NOT_SUPPORTED);
+
+ if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+ MGMT_STATUS_REJECTED);
+
+ if (cp->val != 0x00 && cp->val != 0x01)
+ return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+ MGMT_STATUS_INVALID_PARAMS);
+
+ hci_dev_lock(hdev);
+
+ if (cp->val == test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+ err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev);
+ goto unlock;
+ }
+
+ if (!hdev_is_powered(hdev)) {
+ if (!cp->val) {
+ clear_bit(HCI_CONNECTABLE, &hdev->dev_flags);
+ clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+ clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
+ clear_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
+ clear_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags);
+ clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+ }
+
+ change_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
+ err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev);
+ if (err < 0)
+ goto unlock;
+
+ err = new_settings(hdev, sk);
+ goto unlock;
+ }
+
+ /* Reject disabling when powered on */
+ if (!cp->val) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+ MGMT_STATUS_REJECTED);
+ goto unlock;
+ }
+
+ if (mgmt_pending_find(MGMT_OP_SET_BREDR, hdev)) {
+ err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+ MGMT_STATUS_BUSY);
+ goto unlock;
+ }
+
+ cmd = mgmt_pending_add(sk, MGMT_OP_SET_BREDR, hdev, data, len);
+ if (!cmd) {
+ err = -ENOMEM;
+ goto unlock;
+ }
+
+ /* We need to flip the bit already here so that hci_update_ad
+ * generates the correct flags.
+ */
+ set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
+ hci_req_init(&req, hdev);
+ hci_update_ad(&req);
+ err = hci_req_run(&req, set_bredr_complete);
+ if (err < 0)
+ mgmt_pending_remove(cmd);
+
+unlock:
+ hci_dev_unlock(hdev);
+ return err;
+}
+
static bool ltk_is_valid(struct mgmt_ltk_info *key)
{
if (key->authenticated != 0x00 && key->authenticated != 0x01)
@@ -3180,6 +3553,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
u16 key_count, expected_len;
int i, err;
+ BT_DBG("request for %s", hdev->name);
+
+ if (!lmp_le_capable(hdev))
+ return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
+ MGMT_STATUS_NOT_SUPPORTED);
+
key_count = __le16_to_cpu(cp->key_count);
expected_len = sizeof(*cp) + key_count *
@@ -3276,6 +3655,9 @@ static const struct mgmt_handler {
{ block_device, false, MGMT_BLOCK_DEVICE_SIZE },
{ unblock_device, false, MGMT_UNBLOCK_DEVICE_SIZE },
{ set_device_id, false, MGMT_SET_DEVICE_ID_SIZE },
+ { set_advertising, false, MGMT_SETTING_SIZE },
+ { set_bredr, false, MGMT_SETTING_SIZE },
+ { set_static_address, false, MGMT_SET_STATIC_ADDRESS_SIZE },
};
@@ -3320,6 +3702,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
MGMT_STATUS_INVALID_INDEX);
goto done;
}
+
+ if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+ err = cmd_status(sk, index, opcode,
+ MGMT_STATUS_INVALID_INDEX);
+ goto done;
+ }
}
if (opcode >= ARRAY_SIZE(mgmt_handlers) ||
@@ -3365,14 +3753,6 @@ done:
return err;
}
-static void cmd_status_rsp(struct pending_cmd *cmd, void *data)
-{
- u8 *status = data;
-
- cmd_status(cmd->sk, cmd->index, cmd->opcode, *status);
- mgmt_pending_remove(cmd);
-}
-
int mgmt_index_added(struct hci_dev *hdev)
{
if (!mgmt_valid_hdev(hdev))
@@ -3393,28 +3773,6 @@ int mgmt_index_removed(struct hci_dev *hdev)
return mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL);
}
-struct cmd_lookup {
- struct sock *sk;
- struct hci_dev *hdev;
- u8 mgmt_status;
-};
-
-static void settings_rsp(struct pending_cmd *cmd, void *data)
-{
- struct cmd_lookup *match = data;
-
- send_settings_rsp(cmd->sk, cmd->opcode, match->hdev);
-
- list_del(&cmd->list);
-
- if (match->sk == NULL) {
- match->sk = cmd->sk;
- sock_hold(match->sk);
- }
-
- mgmt_pending_free(cmd);
-}
-
static void set_bredr_scan(struct hci_request *req)
{
struct hci_dev *hdev = req->hdev;
@@ -3481,6 +3839,22 @@ static int powered_update_hci(struct hci_dev *hdev)
cp.simul != lmp_host_le_br_capable(hdev))
hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED,
sizeof(cp), &cp);
+
+ /* In case BR/EDR was toggled during the AUTO_OFF phase */
+ hci_update_ad(&req);
+ }
+
+ if (lmp_le_capable(hdev)) {
+ /* Set random address to static address if configured */
+ if (bacmp(&hdev->static_addr, BDADDR_ANY))
+ hci_req_add(&req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
+ &hdev->static_addr);
+ }
+
+ if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+ u8 adv = 0x01;
+
+ hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(adv), &adv);
}
link_sec = test_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
@@ -3489,7 +3863,8 @@ static int powered_update_hci(struct hci_dev *hdev)
sizeof(link_sec), &link_sec);
if (lmp_bredr_capable(hdev)) {
- set_bredr_scan(&req);
+ if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+ set_bredr_scan(&req);
update_class(&req);
update_name(&req);
update_eir(&req);
@@ -4132,44 +4507,6 @@ int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
return err;
}
-int mgmt_le_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
-{
- struct cmd_lookup match = { NULL, hdev };
- bool changed = false;
- int err = 0;
-
- if (status) {
- u8 mgmt_err = mgmt_status(status);
-
- if (enable && test_and_clear_bit(HCI_LE_ENABLED,
- &hdev->dev_flags))
- err = new_settings(hdev, NULL);
-
- mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
- &mgmt_err);
-
- return err;
- }
-
- if (enable) {
- if (!test_and_set_bit(HCI_LE_ENABLED, &hdev->dev_flags))
- changed = true;
- } else {
- if (test_and_clear_bit(HCI_LE_ENABLED, &hdev->dev_flags))
- changed = true;
- }
-
- mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
-
- if (changed)
- err = new_settings(hdev, match.sk);
-
- if (match.sk)
- sock_put(match.sk);
-
- return err;
-}
-
int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, u8
ssp, u8 *eir, u16 eir_len)
@@ -4286,6 +4623,3 @@ int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
return mgmt_event(MGMT_EV_DEVICE_UNBLOCKED, hdev, &ev, sizeof(ev),
cmd ? cmd->sk : NULL);
}
-
-module_param(enable_hs, bool, 0644);
-MODULE_PARM_DESC(enable_hs, "Enable High Speed support");
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 30b3721dc6d7..072938dc527d 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -544,7 +544,7 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
struct sock *sk = sock->sk;
struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc;
struct sk_buff *skb;
- int sent = 0;
+ int sent;
if (test_bit(RFCOMM_DEFER_SETUP, &d->flags))
return -ENOTCONN;
@@ -559,6 +559,10 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
lock_sock(sk);
+ sent = bt_sock_wait_ready(sk, msg->msg_flags);
+ if (sent)
+ goto done;
+
while (len) {
size_t size = min_t(size_t, len, d->mtu);
int err;
@@ -594,6 +598,7 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
len -= size;
}
+done:
release_sock(sk);
return sent;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index b5562abdd6e0..884b2081a262 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -847,16 +847,27 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb)
{
- __u8 code = skb->data[0];
- __u8 reason;
+ struct hci_conn *hcon = conn->hcon;
+ __u8 code, reason;
int err = 0;
+ if (hcon->type != LE_LINK) {
+ kfree_skb(skb);
+ return -ENOTSUPP;
+ }
+
+ if (skb->len < 1) {
+ kfree_skb(skb);
+ return -EILSEQ;
+ }
+
if (!test_bit(HCI_LE_ENABLED, &conn->hcon->hdev->dev_flags)) {
err = -ENOTSUPP;
reason = SMP_PAIRING_NOTSUPP;
goto done;
}
+ code = skb->data[0];
skb_pull(skb, sizeof(code));
/*
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d1c578630678..005d876dd86c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -363,7 +363,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
- memcpy(eth->h_source, br->dev->dev_addr, 6);
+ memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN);
eth->h_dest[0] = 1;
eth->h_dest[1] = 0;
eth->h_dest[2] = 0x5e;
@@ -433,7 +433,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
- memcpy(eth->h_source, br->dev->dev_addr, 6);
+ memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN);
eth->h_proto = htons(ETH_P_IPV6);
skb_put(skb, sizeof(*eth));
diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c
index 8b84c581be30..3fb3c848affe 100644
--- a/net/bridge/netfilter/ebt_among.c
+++ b/net/bridge/netfilter/ebt_among.c
@@ -28,7 +28,7 @@ static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh,
uint32_t cmp[2] = { 0, 0 };
int key = ((const unsigned char *)mac)[5];
- memcpy(((char *) cmp) + 2, mac, 6);
+ memcpy(((char *) cmp) + 2, mac, ETH_ALEN);
start = wh->table[key];
limit = wh->table[key + 1];
if (ip) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 3430b1ed12e5..1b6eadf69289 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1307,7 +1307,7 @@ static int __dev_close_many(struct list_head *head)
ASSERT_RTNL();
might_sleep();
- list_for_each_entry(dev, head, unreg_list) {
+ list_for_each_entry(dev, head, close_list) {
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1323,7 +1323,7 @@ static int __dev_close_many(struct list_head *head)
dev_deactivate_many(head);
- list_for_each_entry(dev, head, unreg_list) {
+ list_for_each_entry(dev, head, close_list) {
const struct net_device_ops *ops = dev->netdev_ops;
/*
@@ -1351,7 +1351,7 @@ static int __dev_close(struct net_device *dev)
/* Temporarily disable netpoll until the interface is down */
netpoll_rx_disable(dev);
- list_add(&dev->unreg_list, &single);
+ list_add(&dev->close_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
@@ -1362,21 +1362,20 @@ static int __dev_close(struct net_device *dev)
static int dev_close_many(struct list_head *head)
{
struct net_device *dev, *tmp;
- LIST_HEAD(tmp_list);
- list_for_each_entry_safe(dev, tmp, head, unreg_list)
+ /* Remove the devices that don't need to be closed */
+ list_for_each_entry_safe(dev, tmp, head, close_list)
if (!(dev->flags & IFF_UP))
- list_move(&dev->unreg_list, &tmp_list);
+ list_del_init(&dev->close_list);
__dev_close_many(head);
- list_for_each_entry(dev, head, unreg_list) {
+ list_for_each_entry_safe(dev, tmp, head, close_list) {
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
call_netdevice_notifiers(NETDEV_DOWN, dev);
+ list_del_init(&dev->close_list);
}
- /* rollback_registered_many needs the complete original list */
- list_splice(&tmp_list, head);
return 0;
}
@@ -1397,7 +1396,7 @@ int dev_close(struct net_device *dev)
/* Block netpoll rx while the interface is going down */
netpoll_rx_disable(dev);
- list_add(&dev->unreg_list, &single);
+ list_add(&dev->close_list, &single);
dev_close_many(&single);
list_del(&single);
@@ -4374,42 +4373,40 @@ struct netdev_adjacent {
/* upper master flag, there can only be one master device per list */
bool master;
- /* indicates that this dev is our first-level lower/upper device */
- bool neighbour;
-
/* counter for the number of times this device was added to us */
u16 ref_nr;
+ /* private field for the users */
+ void *private;
+
struct list_head list;
struct rcu_head rcu;
};
-static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
- struct net_device *adj_dev,
- bool upper)
+static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *adj_list)
{
struct netdev_adjacent *adj;
- struct list_head *dev_list;
- dev_list = upper ? &dev->upper_dev_list : &dev->lower_dev_list;
-
- list_for_each_entry(adj, dev_list, list) {
+ list_for_each_entry_rcu(adj, adj_list, list) {
if (adj->dev == adj_dev)
return adj;
}
return NULL;
}
-static inline struct netdev_adjacent *__netdev_find_upper(struct net_device *dev,
- struct net_device *udev)
+static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *adj_list)
{
- return __netdev_find_adj(dev, udev, true);
-}
+ struct netdev_adjacent *adj;
-static inline struct netdev_adjacent *__netdev_find_lower(struct net_device *dev,
- struct net_device *ldev)
-{
- return __netdev_find_adj(dev, ldev, false);
+ list_for_each_entry(adj, adj_list, list) {
+ if (adj->dev == adj_dev)
+ return adj;
+ }
+ return NULL;
}
/**
@@ -4426,7 +4423,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return __netdev_find_upper(dev, upper_dev);
+ return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -4441,7 +4438,7 @@ bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
- return !list_empty(&dev->upper_dev_list);
+ return !list_empty(&dev->all_adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_any_upper_dev);
@@ -4458,10 +4455,10 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
ASSERT_RTNL();
- if (list_empty(&dev->upper_dev_list))
+ if (list_empty(&dev->adj_list.upper))
return NULL;
- upper = list_first_entry(&dev->upper_dev_list,
+ upper = list_first_entry(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (likely(upper->master))
return upper->dev;
@@ -4469,15 +4466,26 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
-/* netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+void *netdev_adjacent_get_private(struct list_head *adj_list)
+{
+ struct netdev_adjacent *adj;
+
+ adj = list_entry(adj_list, struct netdev_adjacent, list);
+
+ return adj->private;
+}
+EXPORT_SYMBOL(netdev_adjacent_get_private);
+
+/**
+ * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
* @dev: device
* @iter: list_head ** of the current position
*
* Gets the next device from the dev's upper list, starting from iter
* position. The caller must hold RCU read lock.
*/
-struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
- struct list_head **iter)
+struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
{
struct netdev_adjacent *upper;
@@ -4485,14 +4493,71 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
- if (&upper->list == &dev->upper_dev_list)
+ if (&upper->list == &dev->all_adj_list.upper)
return NULL;
*iter = &upper->list;
return upper->dev;
}
-EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
+
+/**
+ * netdev_lower_get_next_private - Get the next ->private from the
+ * lower neighbour list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent->private from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold either hold the
+ * RTNL lock or its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next_private(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry(*iter, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ if (iter)
+ *iter = lower->list.next;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_get_next_private);
+
+/**
+ * netdev_lower_get_next_private_rcu - Get the next ->private from the
+ * lower neighbour list, RCU
+ * variant
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent->private from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RCU read lock.
+ */
+void *netdev_lower_get_next_private_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ if (iter)
+ *iter = &lower->list;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
* netdev_master_upper_dev_get_rcu - Get master upper device
@@ -4505,7 +4570,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
{
struct netdev_adjacent *upper;
- upper = list_first_or_null_rcu(&dev->upper_dev_list,
+ upper = list_first_or_null_rcu(&dev->adj_list.upper,
struct netdev_adjacent, list);
if (upper && likely(upper->master))
return upper->dev;
@@ -4515,15 +4580,16 @@ EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
- bool neighbour, bool master,
- bool upper)
+ struct list_head *dev_list,
+ void *private, bool master)
{
struct netdev_adjacent *adj;
+ char linkname[IFNAMSIZ+7];
+ int ret;
- adj = __netdev_find_adj(dev, adj_dev, upper);
+ adj = __netdev_find_adj(dev, adj_dev, dev_list);
if (adj) {
- BUG_ON(neighbour);
adj->ref_nr++;
return 0;
}
@@ -4534,124 +4600,178 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->dev = adj_dev;
adj->master = master;
- adj->neighbour = neighbour;
adj->ref_nr = 1;
-
+ adj->private = private;
dev_hold(adj_dev);
- pr_debug("dev_hold for %s, because of %s link added from %s to %s\n",
- adj_dev->name, upper ? "upper" : "lower", dev->name,
- adj_dev->name);
- if (!upper) {
- list_add_tail_rcu(&adj->list, &dev->lower_dev_list);
- return 0;
+ pr_debug("dev_hold for %s, because of link added from %s to %s\n",
+ adj_dev->name, dev->name, adj_dev->name);
+
+ if (dev_list == &dev->adj_list.lower) {
+ sprintf(linkname, "lower_%s", adj_dev->name);
+ ret = sysfs_create_link(&(dev->dev.kobj),
+ &(adj_dev->dev.kobj), linkname);
+ if (ret)
+ goto free_adj;
+ } else if (dev_list == &dev->adj_list.upper) {
+ sprintf(linkname, "upper_%s", adj_dev->name);
+ ret = sysfs_create_link(&(dev->dev.kobj),
+ &(adj_dev->dev.kobj), linkname);
+ if (ret)
+ goto free_adj;
}
- /* Ensure that master upper link is always the first item in list. */
- if (master)
- list_add_rcu(&adj->list, &dev->upper_dev_list);
- else
- list_add_tail_rcu(&adj->list, &dev->upper_dev_list);
+ /* Ensure that master link is always the first item in list. */
+ if (master) {
+ ret = sysfs_create_link(&(dev->dev.kobj),
+ &(adj_dev->dev.kobj), "master");
+ if (ret)
+ goto remove_symlinks;
+
+ list_add_rcu(&adj->list, dev_list);
+ } else {
+ list_add_tail_rcu(&adj->list, dev_list);
+ }
return 0;
-}
-static inline int __netdev_upper_dev_insert(struct net_device *dev,
- struct net_device *udev,
- bool master, bool neighbour)
-{
- return __netdev_adjacent_dev_insert(dev, udev, neighbour, master,
- true);
-}
+remove_symlinks:
+ if (dev_list == &dev->adj_list.lower) {
+ sprintf(linkname, "lower_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ } else if (dev_list == &dev->adj_list.upper) {
+ sprintf(linkname, "upper_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ }
-static inline int __netdev_lower_dev_insert(struct net_device *dev,
- struct net_device *ldev,
- bool neighbour)
-{
- return __netdev_adjacent_dev_insert(dev, ldev, neighbour, false,
- false);
+free_adj:
+ kfree(adj);
+
+ return ret;
}
void __netdev_adjacent_dev_remove(struct net_device *dev,
- struct net_device *adj_dev, bool upper)
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
{
struct netdev_adjacent *adj;
+ char linkname[IFNAMSIZ+7];
- if (upper)
- adj = __netdev_find_upper(dev, adj_dev);
- else
- adj = __netdev_find_lower(dev, adj_dev);
+ adj = __netdev_find_adj(dev, adj_dev, dev_list);
- if (!adj)
+ if (!adj) {
+ pr_err("tried to remove device %s from %s\n",
+ dev->name, adj_dev->name);
BUG();
+ }
if (adj->ref_nr > 1) {
+ pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
+ adj->ref_nr-1);
adj->ref_nr--;
return;
}
+ if (adj->master)
+ sysfs_remove_link(&(dev->dev.kobj), "master");
+
+ if (dev_list == &dev->adj_list.lower) {
+ sprintf(linkname, "lower_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ } else if (dev_list == &dev->adj_list.upper) {
+ sprintf(linkname, "upper_%s", adj_dev->name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+ }
+
list_del_rcu(&adj->list);
- pr_debug("dev_put for %s, because of %s link removed from %s to %s\n",
- adj_dev->name, upper ? "upper" : "lower", dev->name,
- adj_dev->name);
+ pr_debug("dev_put for %s, because link removed from %s to %s\n",
+ adj_dev->name, dev->name, adj_dev->name);
dev_put(adj_dev);
kfree_rcu(adj, rcu);
}
-static inline void __netdev_upper_dev_remove(struct net_device *dev,
- struct net_device *udev)
-{
- return __netdev_adjacent_dev_remove(dev, udev, true);
-}
-
-static inline void __netdev_lower_dev_remove(struct net_device *dev,
- struct net_device *ldev)
-{
- return __netdev_adjacent_dev_remove(dev, ldev, false);
-}
-
-int __netdev_adjacent_dev_insert_link(struct net_device *dev,
- struct net_device *upper_dev,
- bool master, bool neighbour)
+int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list,
+ void *private, bool master)
{
int ret;
- ret = __netdev_upper_dev_insert(dev, upper_dev, master, neighbour);
+ ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
+ master);
if (ret)
return ret;
- ret = __netdev_lower_dev_insert(upper_dev, dev, neighbour);
+ ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
+ false);
if (ret) {
- __netdev_upper_dev_remove(dev, upper_dev);
+ __netdev_adjacent_dev_remove(dev, upper_dev, up_list);
return ret;
}
return 0;
}
-static inline int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *udev)
+int __netdev_adjacent_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
- return __netdev_adjacent_dev_insert_link(dev, udev, false, false);
+ return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+ &dev->all_adj_list.upper,
+ &upper_dev->all_adj_list.lower,
+ NULL, false);
}
-static inline int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
- struct net_device *udev,
- bool master)
+void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list)
{
- return __netdev_adjacent_dev_insert_link(dev, udev, master, true);
+ __netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+ __netdev_adjacent_dev_remove(upper_dev, dev, down_list);
}
void __netdev_adjacent_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
- __netdev_upper_dev_remove(dev, upper_dev);
- __netdev_lower_dev_remove(upper_dev, dev);
+ __netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+ &dev->all_adj_list.upper,
+ &upper_dev->all_adj_list.lower);
}
+int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private, bool master)
+{
+ int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+
+ if (ret)
+ return ret;
+
+ ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+ &dev->adj_list.upper,
+ &upper_dev->adj_list.lower,
+ private, master);
+ if (ret) {
+ __netdev_adjacent_dev_unlink(dev, upper_dev);
+ return ret;
+ }
+
+ return 0;
+}
+
+void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+ &dev->adj_list.upper,
+ &upper_dev->adj_list.lower);
+}
static int __netdev_upper_dev_link(struct net_device *dev,
- struct net_device *upper_dev, bool master)
+ struct net_device *upper_dev, bool master,
+ void *private)
{
struct netdev_adjacent *i, *j, *to_i, *to_j;
int ret = 0;
@@ -4662,26 +4782,29 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (__netdev_find_upper(upper_dev, dev))
+ if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
return -EBUSY;
- if (__netdev_find_upper(dev, upper_dev))
+ if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
return -EBUSY;
- ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, master);
+ ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
+ master);
if (ret)
return ret;
/* Now that we linked these devs, make all the upper_dev's
- * upper_dev_list visible to every dev's lower_dev_list and vice
+ * all_adj_list.upper visible to every dev's all_adj_list.lower an
* versa, and don't forget the devices itself. All of these
* links are non-neighbours.
*/
- list_for_each_entry(i, &dev->lower_dev_list, list) {
- list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+ list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
+ pr_debug("Interlinking %s with %s, non-neighbour\n",
+ i->dev->name, j->dev->name);
ret = __netdev_adjacent_dev_link(i->dev, j->dev);
if (ret)
goto rollback_mesh;
@@ -4689,14 +4812,18 @@ static int __netdev_upper_dev_link(struct net_device *dev,
}
/* add dev to every upper_dev's upper device */
- list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
+ pr_debug("linking %s's upper device %s with %s\n",
+ upper_dev->name, i->dev->name, dev->name);
ret = __netdev_adjacent_dev_link(dev, i->dev);
if (ret)
goto rollback_upper_mesh;
}
/* add upper_dev to every dev's lower device */
- list_for_each_entry(i, &dev->lower_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+ pr_debug("linking %s's lower device %s with %s\n", dev->name,
+ i->dev->name, upper_dev->name);
ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
if (ret)
goto rollback_lower_mesh;
@@ -4707,7 +4834,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
rollback_lower_mesh:
to_i = i;
- list_for_each_entry(i, &dev->lower_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
if (i == to_i)
break;
__netdev_adjacent_dev_unlink(i->dev, upper_dev);
@@ -4717,7 +4844,7 @@ rollback_lower_mesh:
rollback_upper_mesh:
to_i = i;
- list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
if (i == to_i)
break;
__netdev_adjacent_dev_unlink(dev, i->dev);
@@ -4728,8 +4855,8 @@ rollback_upper_mesh:
rollback_mesh:
to_i = i;
to_j = j;
- list_for_each_entry(i, &dev->lower_dev_list, list) {
- list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+ list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+ list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
if (i == to_i && j == to_j)
break;
__netdev_adjacent_dev_unlink(i->dev, j->dev);
@@ -4738,7 +4865,7 @@ rollback_mesh:
break;
}
- __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
return ret;
}
@@ -4756,7 +4883,7 @@ rollback_mesh:
int netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev)
{
- return __netdev_upper_dev_link(dev, upper_dev, false);
+ return __netdev_upper_dev_link(dev, upper_dev, false, NULL);
}
EXPORT_SYMBOL(netdev_upper_dev_link);
@@ -4774,10 +4901,18 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
int netdev_master_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev)
{
- return __netdev_upper_dev_link(dev, upper_dev, true);
+ return __netdev_upper_dev_link(dev, upper_dev, true, NULL);
}
EXPORT_SYMBOL(netdev_master_upper_dev_link);
+int netdev_master_upper_dev_link_private(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private)
+{
+ return __netdev_upper_dev_link(dev, upper_dev, true, private);
+}
+EXPORT_SYMBOL(netdev_master_upper_dev_link_private);
+
/**
* netdev_upper_dev_unlink - Removes a link to upper device
* @dev: device
@@ -4792,29 +4927,59 @@ void netdev_upper_dev_unlink(struct net_device *dev,
struct netdev_adjacent *i, *j;
ASSERT_RTNL();
- __netdev_adjacent_dev_unlink(dev, upper_dev);
+ __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
/* Here is the tricky part. We must remove all dev's lower
* devices from all upper_dev's upper devices and vice
* versa, to maintain the graph relationship.
*/
- list_for_each_entry(i, &dev->lower_dev_list, list)
- list_for_each_entry(j, &upper_dev->upper_dev_list, list)
+ list_for_each_entry(i, &dev->all_adj_list.lower, list)
+ list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
__netdev_adjacent_dev_unlink(i->dev, j->dev);
/* remove also the devices itself from lower/upper device
* list
*/
- list_for_each_entry(i, &dev->lower_dev_list, list)
+ list_for_each_entry(i, &dev->all_adj_list.lower, list)
__netdev_adjacent_dev_unlink(i->dev, upper_dev);
- list_for_each_entry(i, &upper_dev->upper_dev_list, list)
+ list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
__netdev_adjacent_dev_unlink(dev, i->dev);
call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
+void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
+ struct net_device *lower_dev)
+{
+ struct netdev_adjacent *lower;
+
+ if (!lower_dev)
+ return NULL;
+ lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
+ if (!lower)
+ return NULL;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
+
+void *netdev_lower_dev_get_private(struct net_device *dev,
+ struct net_device *lower_dev)
+{
+ struct netdev_adjacent *lower;
+
+ if (!lower_dev)
+ return NULL;
+ lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower);
+ if (!lower)
+ return NULL;
+
+ return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_dev_get_private);
+
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -4823,7 +4988,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags)
ops->ndo_change_rx_flags(dev, flags);
}
-static int __dev_set_promiscuity(struct net_device *dev, int inc)
+static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
{
unsigned int old_flags = dev->flags;
kuid_t uid;
@@ -4866,6 +5031,8 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc)
dev_change_rx_flags(dev, IFF_PROMISC);
}
+ if (notify)
+ __dev_notify_flags(dev, old_flags, IFF_PROMISC);
return 0;
}
@@ -4885,7 +5052,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
unsigned int old_flags = dev->flags;
int err;
- err = __dev_set_promiscuity(dev, inc);
+ err = __dev_set_promiscuity(dev, inc, true);
if (err < 0)
return err;
if (dev->flags != old_flags)
@@ -4894,22 +5061,9 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
}
EXPORT_SYMBOL(dev_set_promiscuity);
-/**
- * dev_set_allmulti - update allmulti count on a device
- * @dev: device
- * @inc: modifier
- *
- * Add or remove reception of all multicast frames to a device. While the
- * count in the device remains above zero the interface remains listening
- * to all interfaces. Once it hits zero the device reverts back to normal
- * filtering operation. A negative @inc value is used to drop the counter
- * when releasing a resource needing all multicasts.
- * Return 0 if successful or a negative errno code on error.
- */
-
-int dev_set_allmulti(struct net_device *dev, int inc)
+static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify)
{
- unsigned int old_flags = dev->flags;
+ unsigned int old_flags = dev->flags, old_gflags = dev->gflags;
ASSERT_RTNL();
@@ -4932,9 +5086,30 @@ int dev_set_allmulti(struct net_device *dev, int inc)
if (dev->flags ^ old_flags) {
dev_change_rx_flags(dev, IFF_ALLMULTI);
dev_set_rx_mode(dev);
+ if (notify)
+ __dev_notify_flags(dev, old_flags,
+ dev->gflags ^ old_gflags);
}
return 0;
}
+
+/**
+ * dev_set_allmulti - update allmulti count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove reception of all multicast frames to a device. While the
+ * count in the device remains above zero the interface remains listening
+ * to all interfaces. Once it hits zero the device reverts back to normal
+ * filtering operation. A negative @inc value is used to drop the counter
+ * when releasing a resource needing all multicasts.
+ * Return 0 if successful or a negative errno code on error.
+ */
+
+int dev_set_allmulti(struct net_device *dev, int inc)
+{
+ return __dev_set_allmulti(dev, inc, true);
+}
EXPORT_SYMBOL(dev_set_allmulti);
/*
@@ -4959,10 +5134,10 @@ void __dev_set_rx_mode(struct net_device *dev)
* therefore calling __dev_set_promiscuity here is safe.
*/
if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
- __dev_set_promiscuity(dev, 1);
+ __dev_set_promiscuity(dev, 1, false);
dev->uc_promisc = true;
} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
- __dev_set_promiscuity(dev, -1);
+ __dev_set_promiscuity(dev, -1, false);
dev->uc_promisc = false;
}
}
@@ -5051,9 +5226,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
if ((flags ^ dev->gflags) & IFF_PROMISC) {
int inc = (flags & IFF_PROMISC) ? 1 : -1;
+ unsigned int old_flags = dev->flags;
dev->gflags ^= IFF_PROMISC;
- dev_set_promiscuity(dev, inc);
+
+ if (__dev_set_promiscuity(dev, inc, false) >= 0)
+ if (dev->flags != old_flags)
+ dev_set_rx_mode(dev);
}
/* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
@@ -5064,16 +5243,20 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
dev->gflags ^= IFF_ALLMULTI;
- dev_set_allmulti(dev, inc);
+ __dev_set_allmulti(dev, inc, false);
}
return ret;
}
-void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
+void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
+ unsigned int gchanges)
{
unsigned int changes = dev->flags ^ old_flags;
+ if (gchanges)
+ rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges);
+
if (changes & IFF_UP) {
if (dev->flags & IFF_UP)
call_netdevice_notifiers(NETDEV_UP, dev);
@@ -5102,17 +5285,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
int dev_change_flags(struct net_device *dev, unsigned int flags)
{
int ret;
- unsigned int changes, old_flags = dev->flags;
+ unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
ret = __dev_change_flags(dev, flags);
if (ret < 0)
return ret;
- changes = old_flags ^ dev->flags;
- if (changes)
- rtmsg_ifinfo(RTM_NEWLINK, dev, changes);
-
- __dev_notify_flags(dev, old_flags);
+ changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags);
+ __dev_notify_flags(dev, old_flags, changes);
return ret;
}
EXPORT_SYMBOL(dev_change_flags);
@@ -5259,6 +5439,7 @@ static void net_set_todo(struct net_device *dev)
static void rollback_registered_many(struct list_head *head)
{
struct net_device *dev, *tmp;
+ LIST_HEAD(close_head);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
@@ -5281,7 +5462,9 @@ static void rollback_registered_many(struct list_head *head)
}
/* If device is running, close it first. */
- dev_close_many(head);
+ list_for_each_entry(dev, head, unreg_list)
+ list_add_tail(&dev->close_list, &close_head);
+ dev_close_many(&close_head);
list_for_each_entry(dev, head, unreg_list) {
/* And unlink it from device chain. */
@@ -6077,9 +6260,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
+ INIT_LIST_HEAD(&dev->close_list);
INIT_LIST_HEAD(&dev->link_watch_list);
- INIT_LIST_HEAD(&dev->upper_dev_list);
- INIT_LIST_HEAD(&dev->lower_dev_list);
+ INIT_LIST_HEAD(&dev->adj_list.upper);
+ INIT_LIST_HEAD(&dev->adj_list.lower);
+ INIT_LIST_HEAD(&dev->all_adj_list.upper);
+ INIT_LIST_HEAD(&dev->all_adj_list.lower);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 8d7d0dd72db2..f8e25ac41c6c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -25,9 +25,35 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
}
+/**
+ * skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: buffer to extract the ports from
+ * @thoff: transport header offset
+ * @ip_proto: protocol for which to get port offset
+ *
+ * The function will try to retrieve the ports at offset thoff + poff where poff
+ * is the protocol port offset returned from proto_ports_offset
+ */
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+{
+ int poff = proto_ports_offset(ip_proto);
+
+ if (poff >= 0) {
+ __be32 *ports, _ports;
+
+ ports = skb_header_pointer(skb, thoff + poff,
+ sizeof(_ports), &_ports);
+ if (ports)
+ return *ports;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(skb_flow_get_ports);
+
bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
{
- int poff, nhoff = skb_network_offset(skb);
+ int nhoff = skb_network_offset(skb);
u8 ip_proto;
__be16 proto = skb->protocol;
@@ -150,16 +176,7 @@ ipv6:
}
flow->ip_proto = ip_proto;
- poff = proto_ports_offset(ip_proto);
- if (poff >= 0) {
- __be32 *ports, _ports;
-
- ports = skb_header_pointer(skb, nhoff + poff,
- sizeof(_ports), &_ports);
- if (ports)
- flow->ports = *ports;
- }
-
+ flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
flow->thoff = (u16) nhoff;
return true;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6072610a8672..ca15f32821fb 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -867,7 +867,7 @@ static void neigh_invalidate(struct neighbour *neigh)
static void neigh_probe(struct neighbour *neigh)
__releases(neigh->lock)
{
- struct sk_buff *skb = skb_peek(&neigh->arp_queue);
+ struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue);
/* keep skb alive even if arp_queue overflows */
if (skb)
skb = skb_copy(skb, GFP_ATOMIC);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index d9cd627e6a16..9b7cf6c85f82 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -222,11 +222,10 @@ static void net_prio_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p;
- void *v;
+ void *v = (void *)(unsigned long)css->cgroup->id;
cgroup_taskset_for_each(p, css, tset) {
task_lock(p);
- v = (void *)(unsigned long)task_netprioidx(p);
iterate_fd(p->files, 0, update_netprio, v);
task_unlock(p);
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2a0e21de3060..4aedf03da052 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1647,9 +1647,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
}
dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
- rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
- __dev_notify_flags(dev, old_flags);
+ __dev_notify_flags(dev, old_flags, ~0U);
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
diff --git a/net/core/sock.c b/net/core/sock.c
index 0b39e7ae4383..fd6afa267475 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -914,6 +914,13 @@ set_rcvbuf:
}
break;
#endif
+
+ case SO_MAX_PACING_RATE:
+ sk->sk_max_pacing_rate = val;
+ sk->sk_pacing_rate = min(sk->sk_pacing_rate,
+ sk->sk_max_pacing_rate);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1177,6 +1184,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
#endif
+ case SO_MAX_PACING_RATE:
+ v.val = sk->sk_max_pacing_rate;
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -2319,6 +2330,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_ll_usec = sysctl_net_busy_read;
#endif
+ sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index be1f64d35358..8f032bae60ad 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -58,7 +58,7 @@
#include <net/ipv6.h>
#include <net/ip.h>
#include <net/dsa.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
__setup("ether=", netdev_boot_setup);
@@ -133,7 +133,7 @@ int eth_rebuild_header(struct sk_buff *skb)
return arp_find(eth->h_dest, skb);
#endif
default:
- printk(KERN_DEBUG
+ netdev_dbg(dev,
"%s: unable to resolve type %X addresses.\n",
dev->name, ntohs(eth->h_proto));
@@ -169,20 +169,9 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
else
skb->pkt_type = PACKET_MULTICAST;
}
-
- /*
- * This ALLMULTI check should be redundant by 1.4
- * so don't forget to remove it.
- *
- * Seems, you forgot to remove it. All silly devices
- * seems to set IFF_PROMISC.
- */
-
- else if (1 /*dev->flags&IFF_PROMISC */ ) {
- if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
- dev->dev_addr)))
- skb->pkt_type = PACKET_OTHERHOST;
- }
+ else if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
+ dev->dev_addr)))
+ skb->pkt_type = PACKET_OTHERHOST;
/*
* Some variants of DSA tagging don't have an ethertype field
@@ -190,12 +179,13 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
* variants has been configured on the receiving interface,
* and if so, set skb->protocol without looking at the packet.
*/
- if (netdev_uses_dsa_tags(dev))
+ if (unlikely(netdev_uses_dsa_tags(dev)))
return htons(ETH_P_DSA);
- if (netdev_uses_trailer_tags(dev))
+
+ if (unlikely(netdev_uses_trailer_tags(dev)))
return htons(ETH_P_TRAILER);
- if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN)
+ if (likely(ntohs(eth->h_proto) >= ETH_P_802_3_MIN))
return eth->h_proto;
/*
@@ -204,7 +194,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
* layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
* won't work for fault tolerant netware but does for the rest.
*/
- if (skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF)
+ if (unlikely(skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF))
return htons(ETH_P_802_3);
/*
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cfeb85cff4f0..35913fb77dc8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1546,6 +1546,7 @@ static const struct net_protocol tcp_protocol = {
};
static const struct net_protocol udp_protocol = {
+ .early_demux = udp_v4_early_demux,
.handler = udp_rcv,
.err_handler = udp_err,
.no_policy = 1,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3df6d3edb2a1..45c74ba03970 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -762,12 +762,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn)
if (IS_LEAF(node) || ((struct tnode *) node)->pos >
tn->pos + tn->bits - 1) {
- if (tkey_extract_bits(node->key,
- oldtnode->pos + oldtnode->bits,
- 1) == 0)
- put_child(tn, 2*i, node);
- else
- put_child(tn, 2*i+1, node);
+ put_child(tn,
+ tkey_extract_bits(node->key, oldtnode->pos, oldtnode->bits + 1),
+ node);
continue;
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5f7d11a45871..5c0e8bc6e5ba 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,6 +353,9 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
saddr = fib_compute_spec_dst(skb);
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
+
if (icmp_param->replyopts.opt.opt.optlen) {
ipc.opt = &icmp_param->replyopts.opt;
if (ipc.opt->opt.srr)
@@ -608,6 +611,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
ipc.addr = iph->saddr;
ipc.opt = &icmp_param->replyopts.opt;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
type, code, icmp_param);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6acb541c9091..56e82a4027b4 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,27 +29,19 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
EXPORT_SYMBOL(inet_csk_timer_bug_msg);
#endif
-/*
- * This struct holds the first and last local port number.
- */
-struct local_ports sysctl_local_ports __read_mostly = {
- .lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock),
- .range = { 32768, 61000 },
-};
-
unsigned long *sysctl_local_reserved_ports;
EXPORT_SYMBOL(sysctl_local_reserved_ports);
-void inet_get_local_port_range(int *low, int *high)
+void inet_get_local_port_range(struct net *net, int *low, int *high)
{
unsigned int seq;
do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
- *low = sysctl_local_ports.range[0];
- *high = sysctl_local_ports.range[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ *low = net->ipv4.sysctl_local_ports.range[0];
+ *high = net->ipv4.sysctl_local_ports.range[1];
+ } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
}
EXPORT_SYMBOL(inet_get_local_port_range);
@@ -79,17 +71,16 @@ int inet_csk_bind_conflict(const struct sock *sk,
(!reuseport || !sk2->sk_reuseport ||
(sk2->sk_state != TCP_TIME_WAIT &&
!uid_eq(uid, sock_i_uid(sk2))))) {
- const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
- if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
- sk2_rcv_saddr == sk_rcv_saddr(sk))
+
+ if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
+ sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
break;
}
if (!relax && reuse && sk2->sk_reuse &&
sk2->sk_state != TCP_LISTEN) {
- const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
- if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
- sk2_rcv_saddr == sk_rcv_saddr(sk))
+ if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
+ sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
break;
}
}
@@ -116,7 +107,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
int remaining, rover, low, high;
again:
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
smallest_rover = rover = net_random() % remaining + low;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5f648751fce2..22000279efc8 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -222,7 +222,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
- long tmo;
+ s32 tmo;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
@@ -234,7 +234,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
- tmo = tw->tw_ttd - jiffies;
+ tmo = tw->tw_ttd - inet_tw_time_stamp();
if (tmo < 0)
tmo = 0;
@@ -248,7 +248,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
r->id.idiag_dst[0] = tw->tw_daddr;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
- r->idiag_expires = DIV_ROUND_UP(tmo * 1000, HZ);
+ r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 96da9c77deca..ae199596b9b0 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -494,7 +494,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
u32 offset = hint + port_offset;
struct inet_timewait_sock *tw = NULL;
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
local_bh_disable();
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1f27c9f4afd0..9bcd8f7234ec 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -387,11 +387,11 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw,
if (slot >= INET_TWDR_TWKILL_SLOTS)
slot = INET_TWDR_TWKILL_SLOTS - 1;
}
- tw->tw_ttd = jiffies + timeo;
+ tw->tw_ttd = inet_tw_time_stamp() + timeo;
slot = (twdr->slot + slot) & (INET_TWDR_TWKILL_SLOTS - 1);
list = &twdr->cells[slot];
} else {
- tw->tw_ttd = jiffies + (slot << INET_TWDR_RECYCLE_TICK);
+ tw->tw_ttd = inet_tw_time_stamp() + (slot << INET_TWDR_RECYCLE_TICK);
if (twdr->twcal_hand < 0) {
twdr->twcal_hand = 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a04d872c54f9..7d8357bb2ba6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1060,6 +1060,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
rt->dst.dev->mtu : dst_mtu(&rt->dst);
cork->dst = &rt->dst;
cork->length = 0;
+ cork->ttl = ipc->ttl;
+ cork->tos = ipc->tos;
+ cork->priority = ipc->priority;
cork->tx_flags = ipc->tx_flags;
return 0;
@@ -1311,7 +1314,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
if (cork->flags & IPCORK_OPT)
opt = cork->opt;
- if (rt->rt_type == RTN_MULTICAST)
+ if (cork->ttl != 0)
+ ttl = cork->ttl;
+ else if (rt->rt_type == RTN_MULTICAST)
ttl = inet->mc_ttl;
else
ttl = ip_select_ttl(inet, &rt->dst);
@@ -1319,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
- iph->tos = inet->tos;
+ iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
iph->frag_off = df;
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
@@ -1331,7 +1336,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
ip_options_build(skb, opt, cork->addr, rt, 0);
}
- skb->priority = sk->sk_priority;
+ skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
skb->mark = sk->sk_mark;
/*
* Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1481,6 +1486,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
ipc.addr = daddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
if (replyopts.opt.opt.optlen) {
ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f113d709..0626f2cb192e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(ip_cmsg_recv);
int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
{
- int err;
+ int err, val;
struct cmsghdr *cmsg;
for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
@@ -215,6 +215,24 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
ipc->addr = info->ipi_spec_dst.s_addr;
break;
}
+ case IP_TTL:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 1 || val > 255)
+ return -EINVAL;
+ ipc->ttl = val;
+ break;
+ case IP_TOS:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+ return -EINVAL;
+ val = *(int *)CMSG_DATA(cmsg);
+ if (val < 0 || val > 255)
+ return -EINVAL;
+ ipc->tos = val;
+ ipc->priority = rt_tos2priority(ipc->tos);
+ break;
+
default:
return -EINVAL;
}
@@ -1034,11 +1052,12 @@ e_inval:
* destination in skb->cb[] before dst drop.
* This way, receiver doesnt make cache line misses to read rtable.
*/
-void ipv4_pktinfo_prepare(struct sk_buff *skb)
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
{
struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
- if (skb_rtable(skb)) {
+ if ((inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) &&
+ skb_rtable(skb)) {
pktinfo->ipi_ifindex = inet_iif(skb);
pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
} else {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e805e7b3030e..91f69bc883fe 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -49,70 +49,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly;
static int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
-static int vti_err(struct sk_buff *skb, u32 info)
-{
-
- /* All the routers (except for Linux) return only
- * 8 bytes of packet payload. It means, that precise relaying of
- * ICMP in the real Internet is absolutely infeasible.
- */
- struct net *net = dev_net(skb->dev);
- struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- struct iphdr *iph = (struct iphdr *)skb->data;
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
- struct ip_tunnel *t;
- int err;
-
- switch (type) {
- default:
- case ICMP_PARAMETERPROB:
- return 0;
-
- case ICMP_DEST_UNREACH:
- switch (code) {
- case ICMP_SR_FAILED:
- case ICMP_PORT_UNREACH:
- /* Impossible event. */
- return 0;
- default:
- /* All others are translated to HOST_UNREACH. */
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return 0;
- break;
- }
-
- err = -ENOENT;
-
- t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
- iph->daddr, iph->saddr, 0);
- if (t == NULL)
- goto out;
-
- if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, IPPROTO_IPIP, 0);
- err = 0;
- goto out;
- }
-
- err = 0;
- if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
- goto out;
-
- if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
- t->err_count++;
- else
- t->err_count = 1;
- t->err_time = jiffies;
-out:
- return err;
-}
-
/* We dont digest the packet therefore let the packet pass */
static int vti_rcv(struct sk_buff *skb)
{
@@ -296,9 +232,8 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev)
iph->ihl = 5;
}
-static struct xfrm_tunnel vti_handler __read_mostly = {
+static struct xfrm_tunnel_notifier vti_handler __read_mostly = {
.handler = vti_rcv,
- .err_handler = vti_err,
.priority = 1,
};
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index d7d9882d4cae..a62610443152 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -237,11 +237,11 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
unsigned int seq;
do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
}
@@ -713,6 +713,8 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.opt = NULL;
ipc.oif = sk->sk_bound_dev_if;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
sock_tx_timestamp(sk, &ipc.tx_flags);
@@ -744,7 +746,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
return -EINVAL;
faddr = ipc.opt->opt.faddr;
}
- tos = RT_TOS(inet->tos);
+ tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 193db03540ad..41e1d2845c8f 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -299,7 +299,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
/* Charge it to the socket. */
- ipv4_pktinfo_prepare(skb);
+ ipv4_pktinfo_prepare(sk, skb);
if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
@@ -519,6 +519,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
@@ -558,7 +560,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
daddr = ipc.opt->opt.faddr;
}
}
- tos = RT_CONN_FLAGS(sk);
+ tos = get_rtconn_flags(&ipc, sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 14a15c49129d..15e024105f91 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -89,8 +89,7 @@ __u32 cookie_init_timestamp(struct request_sock *req)
static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
- __be16 dport, __u32 sseq, __u32 count,
- __u32 data)
+ __be16 dport, __u32 sseq, __u32 data)
{
/*
* Compute the secure sequence number.
@@ -102,7 +101,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
* As an extra hack, we add a small "data" value that encodes the
* MSS into the second hash value.
*/
-
+ u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -114,22 +113,21 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
* If the syncookie is bad, the data returned will be out of
* range. This must be checked by the caller.
*
- * The count value used to generate the cookie must be within
- * "maxdiff" if the current (passed-in) "count". The return value
- * is (__u32)-1 if this test fails.
+ * The count value used to generate the cookie must be less than
+ * MAX_SYNCOOKIE_AGE minutes in the past.
+ * The return value (__u32)-1 if this test fails.
*/
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
- __be16 sport, __be16 dport, __u32 sseq,
- __u32 count, __u32 maxdiff)
+ __be16 sport, __be16 dport, __u32 sseq)
{
- __u32 diff;
+ u32 diff, count = tcp_cookie_time();
/* Strip away the layers from the cookie */
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
- if (diff >= maxdiff)
+ if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
@@ -138,22 +136,22 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
}
/*
- * MSS Values are taken from the 2009 paper
- * 'Measuring TCP Maximum Segment Size' by S. Alcock and R. Nelson:
- * - values 1440 to 1460 accounted for 80% of observed mss values
- * - values outside the 536-1460 range are rare (<0.2%).
+ * MSS Values are chosen based on the 2011 paper
+ * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
+ * Values ..
+ * .. lower than 536 are rare (< 0.2%)
+ * .. between 537 and 1299 account for less than < 1.5% of observed values
+ * .. in the 1300-1349 range account for about 15 to 20% of observed mss values
+ * .. exceeding 1460 are very rare (< 0.04%)
*
- * Table must be sorted.
+ * 1460 is the single most frequently announced mss value (30 to 46% depending
+ * on monitor location). Table must be sorted.
*/
static __u16 const msstab[] = {
- 64,
- 512,
536,
- 1024,
- 1440,
+ 1300,
+ 1440, /* 1440, 1452: PPPoE */
1460,
- 4312,
- 8960,
};
/*
@@ -173,7 +171,7 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
th->source, th->dest, ntohl(th->seq),
- jiffies / (HZ * 60), mssind);
+ mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
@@ -189,13 +187,6 @@ __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
}
/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-/*
* Check if a ack sequence number is a valid syncookie.
* Return the decoded mss if it is, or 0 if not.
*/
@@ -204,9 +195,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
- th->source, th->dest, seq,
- jiffies / (HZ * 60),
- COUNTER_TRIES);
+ th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 540279f4c531..c08f096d46b5 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -43,12 +43,12 @@ static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
/* Update system visible IP port range */
-static void set_local_port_range(int range[2])
+static void set_local_port_range(struct net *net, int range[2])
{
- write_seqlock(&sysctl_local_ports.lock);
- sysctl_local_ports.range[0] = range[0];
- sysctl_local_ports.range[1] = range[1];
- write_sequnlock(&sysctl_local_ports.lock);
+ write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+ net->ipv4.sysctl_local_ports.range[0] = range[0];
+ net->ipv4.sysctl_local_ports.range[1] = range[1];
+ write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
}
/* Validate changes from /proc interface. */
@@ -56,6 +56,8 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ struct net *net =
+ container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
int ret;
int range[2];
struct ctl_table tmp = {
@@ -66,14 +68,15 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
.extra2 = &ip_local_port_range_max,
};
- inet_get_local_port_range(range, range + 1);
+ inet_get_local_port_range(net, &range[0], &range[1]);
+
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && ret == 0) {
if (range[1] < range[0])
ret = -EINVAL;
else
- set_local_port_range(range);
+ set_local_port_range(net, range);
}
return ret;
@@ -83,23 +86,27 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
{
kgid_t *data = table->data;
+ struct net *net =
+ container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
unsigned int seq;
do {
- seq = read_seqbegin(&sysctl_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&sysctl_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
}
/* Update system visible IP port range */
static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
{
kgid_t *data = table->data;
- write_seqlock(&sysctl_local_ports.lock);
+ struct net *net =
+ container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+ write_seqlock(&net->ipv4.sysctl_local_ports.lock);
data[0] = low;
data[1] = high;
- write_sequnlock(&sysctl_local_ports.lock);
+ write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
}
/* Validate changes from /proc interface. */
@@ -475,13 +482,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "ip_local_port_range",
- .data = &sysctl_local_ports.range,
- .maxlen = sizeof(sysctl_local_ports.range),
- .mode = 0644,
- .proc_handler = ipv4_local_port_range,
- },
- {
.procname = "ip_local_reserved_ports",
.data = NULL, /* initialized in sysctl_ipv4_init */
.maxlen = 65536,
@@ -854,6 +854,13 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "ip_local_port_range",
+ .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range),
+ .data = &init_net.ipv4.sysctl_local_ports.range,
+ .mode = 0644,
+ .proc_handler = ipv4_local_port_range,
+ },
+ {
.procname = "tcp_mem",
.maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem),
.mode = 0644,
@@ -888,6 +895,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
&net->ipv4.sysctl_ping_group_range;
table[7].data =
&net->ipv4.sysctl_tcp_ecn;
+ table[8].data =
+ &net->ipv4.sysctl_local_ports.range;
/* Don't export sysctls to unprivileged users */
if (net->user_ns != &init_user_ns)
@@ -901,6 +910,13 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
+ /*
+ * Set defaults for local port range
+ */
+ seqlock_init(&net->ipv4.sysctl_local_ports.lock);
+ net->ipv4.sysctl_local_ports.range[0] = 32768;
+ net->ipv4.sysctl_local_ports.range[1] = 61000;
+
tcp_init_mem(net);
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 113dc5f17d47..47b8ab7dce9c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -267,11 +267,31 @@ static bool TCP_ECN_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
* 1. Tuning sk->sk_sndbuf, when connection enters established state.
*/
-static void tcp_fixup_sndbuf(struct sock *sk)
+static void tcp_sndbuf_expand(struct sock *sk)
{
- int sndmem = SKB_TRUESIZE(tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER);
+ const struct tcp_sock *tp = tcp_sk(sk);
+ int sndmem, per_mss;
+ u32 nr_segs;
+
+ /* Worst case is non GSO/TSO : each frame consumes one skb
+ * and skb->head is kmalloced using power of two area of memory
+ */
+ per_mss = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
+ MAX_TCP_HEADER +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ per_mss = roundup_pow_of_two(per_mss) +
+ SKB_DATA_ALIGN(sizeof(struct sk_buff));
+
+ nr_segs = max_t(u32, TCP_INIT_CWND, tp->snd_cwnd);
+ nr_segs = max_t(u32, nr_segs, tp->reordering + 1);
+
+ /* Fast Recovery (RFC 5681 3.2) :
+ * Cubic needs 1.7 factor, rounded to 2 to include
+ * extra cushion (application might react slowly to POLLOUT)
+ */
+ sndmem = 2 * nr_segs * per_mss;
- sndmem *= TCP_INIT_CWND;
if (sk->sk_sndbuf < sndmem)
sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
}
@@ -355,6 +375,12 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
tcp_default_init_rwnd(mss);
+ /* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
+ * Allow enough cushion so that sender is not limited by our window
+ */
+ if (sysctl_tcp_moderate_rcvbuf)
+ rcvmem <<= 2;
+
if (sk->sk_rcvbuf < rcvmem)
sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
}
@@ -370,9 +396,11 @@ void tcp_init_buffer_space(struct sock *sk)
if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
tcp_fixup_rcvbuf(sk);
if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
- tcp_fixup_sndbuf(sk);
+ tcp_sndbuf_expand(sk);
tp->rcvq_space.space = tp->rcv_wnd;
+ tp->rcvq_space.time = tcp_time_stamp;
+ tp->rcvq_space.seq = tp->copied_seq;
maxwin = tcp_full_space(sk);
@@ -512,48 +540,62 @@ void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int time;
- int space;
-
- if (tp->rcvq_space.time == 0)
- goto new_measure;
+ int copied;
time = tcp_time_stamp - tp->rcvq_space.time;
if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0)
return;
- space = 2 * (tp->copied_seq - tp->rcvq_space.seq);
+ /* Number of bytes copied to user in last RTT */
+ copied = tp->copied_seq - tp->rcvq_space.seq;
+ if (copied <= tp->rcvq_space.space)
+ goto new_measure;
+
+ /* A bit of theory :
+ * copied = bytes received in previous RTT, our base window
+ * To cope with packet losses, we need a 2x factor
+ * To cope with slow start, and sender growing its cwin by 100 %
+ * every RTT, we need a 4x factor, because the ACK we are sending
+ * now is for the next RTT, not the current one :
+ * <prev RTT . ><current RTT .. ><next RTT .... >
+ */
- space = max(tp->rcvq_space.space, space);
+ if (sysctl_tcp_moderate_rcvbuf &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int rcvwin, rcvmem, rcvbuf;
- if (tp->rcvq_space.space != space) {
- int rcvmem;
+ /* minimal window to cope with packet losses, assuming
+ * steady state. Add some cushion because of small variations.
+ */
+ rcvwin = (copied << 1) + 16 * tp->advmss;
+
+ /* If rate increased by 25%,
+ * assume slow start, rcvwin = 3 * copied
+ * If rate increased by 50%,
+ * assume sender can use 2x growth, rcvwin = 4 * copied
+ */
+ if (copied >=
+ tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) {
+ if (copied >=
+ tp->rcvq_space.space + (tp->rcvq_space.space >> 1))
+ rcvwin <<= 1;
+ else
+ rcvwin += (rcvwin >> 1);
+ }
- tp->rcvq_space.space = space;
+ rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
+ while (tcp_win_from_space(rcvmem) < tp->advmss)
+ rcvmem += 128;
- if (sysctl_tcp_moderate_rcvbuf &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- int new_clamp = space;
+ rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]);
+ if (rcvbuf > sk->sk_rcvbuf) {
+ sk->sk_rcvbuf = rcvbuf;
- /* Receive space grows, normalize in order to
- * take into account packet headers and sk_buff
- * structure overhead.
- */
- space /= tp->advmss;
- if (!space)
- space = 1;
- rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
- while (tcp_win_from_space(rcvmem) < tp->advmss)
- rcvmem += 128;
- space *= rcvmem;
- space = min(space, sysctl_tcp_rmem[2]);
- if (space > sk->sk_rcvbuf) {
- sk->sk_rcvbuf = space;
-
- /* Make the window clamp follow along. */
- tp->window_clamp = new_clamp;
- }
+ /* Make the window clamp follow along. */
+ tp->window_clamp = rcvwin;
}
}
+ tp->rcvq_space.space = copied;
new_measure:
tp->rcvq_space.seq = tp->copied_seq;
@@ -713,7 +755,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
if (tp->srtt > 8 + 2)
do_div(rate, tp->srtt);
- sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+ sk->sk_pacing_rate = min_t(u64, rate, sk->sk_max_pacing_rate);
}
/* Calculate rto without backoff. This is the second half of Van Jacobson's
@@ -2973,7 +3015,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
const struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_buff *skb;
u32 now = tcp_time_stamp;
- int fully_acked = true;
+ bool fully_acked = true;
int flag = 0;
u32 pkts_acked = 0;
u32 reord = tp->packets_out;
@@ -4704,15 +4746,7 @@ static void tcp_new_space(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_should_expand_sndbuf(sk)) {
- int sndmem = SKB_TRUESIZE(max_t(u32,
- tp->rx_opt.mss_clamp,
- tp->mss_cache) +
- MAX_TCP_HEADER);
- int demanded = max_t(unsigned int, tp->snd_cwnd,
- tp->reordering + 1);
- sndmem *= 2 * demanded;
- if (sndmem > sk->sk_sndbuf)
- sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
+ tcp_sndbuf_expand(sk);
tp->snd_cwnd_stamp = tcp_time_stamp;
}
@@ -5677,8 +5711,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
tcp_init_congestion_control(sk);
tcp_mtup_init(sk);
- tcp_init_buffer_space(sk);
tp->copied_seq = tp->rcv_nxt;
+ tcp_init_buffer_space(sk);
}
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b14266bb91eb..5d6b1a609da8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1410,8 +1410,8 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
- tcp_init_buffer_space(child);
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.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0ca44df51ee9..4226c53daaed 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -103,6 +103,7 @@
#include <linux/seq_file.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
+#include <net/inet_hashtables.h>
#include <net/route.h>
#include <net/checksum.h>
#include <net/xfrm.h>
@@ -219,7 +220,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
unsigned short first, last;
DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
rand = net_random();
@@ -565,6 +566,26 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
}
EXPORT_SYMBOL_GPL(udp4_lib_lookup);
+static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
+ __be16 loc_port, __be32 loc_addr,
+ __be16 rmt_port, __be32 rmt_addr,
+ int dif, unsigned short hnum)
+{
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (!net_eq(sock_net(sk), net) ||
+ udp_sk(sk)->udp_port_hash != hnum ||
+ (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
+ (inet->inet_dport != rmt_port && inet->inet_dport) ||
+ (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
+ ipv6_only_sock(sk) ||
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ return false;
+ if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
+ return false;
+ return true;
+}
+
static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
@@ -575,20 +596,11 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
unsigned short hnum = ntohs(loc_port);
sk_nulls_for_each_from(s, node) {
- struct inet_sock *inet = inet_sk(s);
-
- if (!net_eq(sock_net(s), net) ||
- udp_sk(s)->udp_port_hash != hnum ||
- (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
- (inet->inet_dport != rmt_port && inet->inet_dport) ||
- (inet->inet_rcv_saddr &&
- inet->inet_rcv_saddr != loc_addr) ||
- ipv6_only_sock(s) ||
- (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
- continue;
- if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
- continue;
- goto found;
+ if (__udp_is_mcast_sock(net, s,
+ loc_port, loc_addr,
+ rmt_port, rmt_addr,
+ dif, hnum))
+ goto found;
}
s = NULL;
found:
@@ -855,6 +867,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
@@ -938,7 +952,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
faddr = ipc.opt->opt.faddr;
connected = 0;
}
- tos = RT_TOS(inet->tos);
+ tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {
@@ -1403,8 +1417,10 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
- if (inet_sk(sk)->inet_daddr)
+ if (inet_sk(sk)->inet_daddr) {
sock_rps_save_rxhash(sk, skb);
+ sk_mark_napi_id(sk, skb);
+ }
rc = sock_queue_rcv_skb(sk, skb);
if (rc < 0) {
@@ -1528,7 +1544,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
rc = 0;
- ipv4_pktinfo_prepare(skb);
+ ipv4_pktinfo_prepare(sk, skb);
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
rc = __udp_queue_rcv_skb(sk, skb);
@@ -1577,6 +1593,14 @@ static void flush_stack(struct sock **stack, unsigned int count,
kfree_skb(skb1);
}
+static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ dst_hold(dst);
+ sk->sk_rx_dst = dst;
+}
+
/*
* Multicasts and broadcasts go to each listener.
*
@@ -1705,16 +1729,32 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
- if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
- return __udp4_lib_mcast_deliver(net, skb, uh,
- saddr, daddr, udptable);
+ if (skb->sk) {
+ int ret;
+ sk = skb->sk;
+
+ if (unlikely(sk->sk_rx_dst == NULL))
+ udp_sk_rx_dst_set(sk, skb);
+
+ ret = udp_queue_rcv_skb(sk, skb);
+
+ /* a return value > 0 means to resubmit the input, but
+ * it wants the return to be -protocol, or 0
+ */
+ if (ret > 0)
+ return -ret;
+ return 0;
+ } else {
+ if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
+ return __udp4_lib_mcast_deliver(net, skb, uh,
+ saddr, daddr, udptable);
- sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+ sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+ }
if (sk != NULL) {
int ret;
- sk_mark_napi_id(sk, skb);
ret = udp_queue_rcv_skb(sk, skb);
sock_put(sk);
@@ -1768,6 +1808,135 @@ drop:
return 0;
}
+/* We can only early demux multicast if there is a single matching socket.
+ * If more than one socket found returns NULL
+ */
+static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
+ __be16 loc_port, __be32 loc_addr,
+ __be16 rmt_port, __be32 rmt_addr,
+ int dif)
+{
+ struct sock *sk, *result;
+ struct hlist_nulls_node *node;
+ unsigned short hnum = ntohs(loc_port);
+ unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
+ struct udp_hslot *hslot = &udp_table.hash[slot];
+
+ rcu_read_lock();
+begin:
+ count = 0;
+ result = NULL;
+ sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+ if (__udp_is_mcast_sock(net, sk,
+ loc_port, loc_addr,
+ rmt_port, rmt_addr,
+ dif, hnum)) {
+ result = sk;
+ ++count;
+ }
+ }
+ /*
+ * if the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(node) != slot)
+ goto begin;
+
+ if (result) {
+ if (count != 1 ||
+ unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
+ result = NULL;
+ else if (unlikely(!__udp_is_mcast_sock(net, sk,
+ loc_port, loc_addr,
+ rmt_port, rmt_addr,
+ dif, hnum))) {
+ sock_put(result);
+ result = NULL;
+ }
+ }
+ rcu_read_unlock();
+ return result;
+}
+
+/* For unicast we should only early demux connected sockets or we can
+ * break forwarding setups. The chains here can be long so only check
+ * if the first socket is an exact match and if not move on.
+ */
+static struct sock *__udp4_lib_demux_lookup(struct net *net,
+ __be16 loc_port, __be32 loc_addr,
+ __be16 rmt_port, __be32 rmt_addr,
+ int dif)
+{
+ struct sock *sk, *result;
+ struct hlist_nulls_node *node;
+ unsigned short hnum = ntohs(loc_port);
+ unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
+ unsigned int slot2 = hash2 & udp_table.mask;
+ struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
+ INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr)
+ const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+
+ rcu_read_lock();
+ result = NULL;
+ udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+ if (INET_MATCH(sk, net, acookie,
+ rmt_addr, loc_addr, ports, dif))
+ result = sk;
+ /* Only check first socket in chain */
+ break;
+ }
+
+ if (result) {
+ if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
+ result = NULL;
+ else if (unlikely(!INET_MATCH(sk, net, acookie,
+ rmt_addr, loc_addr,
+ ports, dif))) {
+ sock_put(result);
+ result = NULL;
+ }
+ }
+ rcu_read_unlock();
+ return result;
+}
+
+void udp_v4_early_demux(struct sk_buff *skb)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ const struct udphdr *uh = udp_hdr(skb);
+ struct sock *sk;
+ struct dst_entry *dst;
+ struct net *net = dev_net(skb->dev);
+ int dif = skb->dev->ifindex;
+
+ /* validate the packet */
+ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
+ return;
+
+ if (skb->pkt_type == PACKET_BROADCAST ||
+ skb->pkt_type == PACKET_MULTICAST)
+ sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
+ uh->source, iph->saddr, dif);
+ else if (skb->pkt_type == PACKET_HOST)
+ sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
+ uh->source, iph->saddr, dif);
+ else
+ return;
+
+ if (!sk)
+ return;
+
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+ dst = sk->sk_rx_dst;
+
+ if (dst)
+ dst = dst_check(dst, 0);
+ if (dst)
+ skb_dst_set_noref(skb, dst);
+}
+
int udp_rcv(struct sk_buff *skb)
{
return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index b5663c37f089..31b18152528f 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -16,13 +16,13 @@
#include <net/xfrm.h>
/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel __rcu *rcv_notify_handlers __read_mostly;
+static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex);
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
{
- struct xfrm_tunnel __rcu **pprev;
- struct xfrm_tunnel *t;
+ struct xfrm_tunnel_notifier __rcu **pprev;
+ struct xfrm_tunnel_notifier *t;
int ret = -EEXIST;
int priority = handler->priority;
@@ -50,10 +50,10 @@ err:
}
EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register);
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
{
- struct xfrm_tunnel __rcu **pprev;
- struct xfrm_tunnel *t;
+ struct xfrm_tunnel_notifier __rcu **pprev;
+ struct xfrm_tunnel_notifier *t;
int ret = -ENOENT;
mutex_lock(&xfrm4_mode_tunnel_input_mutex);
@@ -134,7 +134,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
{
- struct xfrm_tunnel *handler;
+ struct xfrm_tunnel_notifier *handler;
int err = -EINVAL;
if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7c96100b021e..4966b124dc2e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1028,52 +1028,4 @@ out_unregister_tcp_proto:
}
module_init(inet6_init);
-static void __exit inet6_exit(void)
-{
- if (disable_ipv6_mod)
- return;
-
- /* First of all disallow new sockets creation. */
- sock_unregister(PF_INET6);
- /* Disallow any further netlink messages */
- rtnl_unregister_all(PF_INET6);
-
- udpv6_exit();
- udplitev6_exit();
- tcpv6_exit();
-
- /* Cleanup code parts. */
- ipv6_packet_cleanup();
- ipv6_frag_exit();
- ipv6_exthdrs_exit();
- addrconf_cleanup();
- ip6_flowlabel_cleanup();
- ndisc_late_cleanup();
- ip6_route_cleanup();
-#ifdef CONFIG_PROC_FS
-
- /* Cleanup code parts. */
- if6_proc_exit();
- ipv6_misc_proc_exit();
- udplite6_proc_exit();
- raw6_proc_exit();
-#endif
- ipv6_netfilter_fini();
- ipv6_stub = NULL;
- igmp6_cleanup();
- ndisc_cleanup();
- ip6_mr_cleanup();
- icmpv6_cleanup();
- rawv6_exit();
-
- unregister_pernet_subsys(&inet6_net_ops);
- proto_unregister(&rawv6_prot);
- proto_unregister(&udplitev6_prot);
- proto_unregister(&udpv6_prot);
- proto_unregister(&tcpv6_prot);
-
- rcu_barrier(); /* Wait for completion of call_rcu()'s */
-}
-module_exit(inet6_exit);
-
MODULE_ALIAS_NETPROTO(PF_INET6);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5bec666aba61..5550a8113a6d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1529,25 +1529,6 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
fib6_walk(&c.w);
}
-void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg),
- int prune, void *arg)
-{
- struct fib6_table *table;
- struct hlist_head *head;
- unsigned int h;
-
- rcu_read_lock();
- for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
- head = &net->ipv6.fib_table_hash[h];
- hlist_for_each_entry_rcu(table, head, tb6_hlist) {
- read_lock_bh(&table->tb6_lock);
- fib6_clean_tree(net, &table->tb6_root,
- func, prune, arg);
- read_unlock_bh(&table->tb6_lock);
- }
- }
- rcu_read_unlock();
-}
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
int prune, void *arg)
{
@@ -1782,3 +1763,189 @@ void fib6_gc_cleanup(void)
unregister_pernet_subsys(&fib6_net_ops);
kmem_cache_destroy(fib6_node_kmem);
}
+
+#ifdef CONFIG_PROC_FS
+
+struct ipv6_route_iter {
+ struct seq_net_private p;
+ struct fib6_walker_t w;
+ loff_t skip;
+ struct fib6_table *tbl;
+ __u32 sernum;
+};
+
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+ struct rt6_info *rt = v;
+ struct ipv6_route_iter *iter = seq->private;
+
+ seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
+
+#ifdef CONFIG_IPV6_SUBTREES
+ seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
+#else
+ seq_puts(seq, "00000000000000000000000000000000 00 ");
+#endif
+ if (rt->rt6i_flags & RTF_GATEWAY)
+ seq_printf(seq, "%pi6", &rt->rt6i_gateway);
+ else
+ seq_puts(seq, "00000000000000000000000000000000");
+
+ seq_printf(seq, " %08x %08x %08x %08x %8s\n",
+ rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
+ rt->dst.__use, rt->rt6i_flags,
+ rt->dst.dev ? rt->dst.dev->name : "");
+ iter->w.leaf = NULL;
+ return 0;
+}
+
+static int ipv6_route_yield(struct fib6_walker_t *w)
+{
+ struct ipv6_route_iter *iter = w->args;
+
+ if (!iter->skip)
+ return 1;
+
+ do {
+ iter->w.leaf = iter->w.leaf->dst.rt6_next;
+ iter->skip--;
+ if (!iter->skip && iter->w.leaf)
+ return 1;
+ } while (iter->w.leaf);
+
+ return 0;
+}
+
+static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter)
+{
+ memset(&iter->w, 0, sizeof(iter->w));
+ iter->w.func = ipv6_route_yield;
+ iter->w.root = &iter->tbl->tb6_root;
+ iter->w.state = FWS_INIT;
+ iter->w.node = iter->w.root;
+ iter->w.args = iter;
+ iter->sernum = iter->w.root->fn_sernum;
+ INIT_LIST_HEAD(&iter->w.lh);
+ fib6_walker_link(&iter->w);
+}
+
+static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl,
+ struct net *net)
+{
+ unsigned int h;
+ struct hlist_node *node;
+
+ if (tbl) {
+ h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1;
+ node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist));
+ } else {
+ h = 0;
+ node = NULL;
+ }
+
+ while (!node && h < FIB6_TABLE_HASHSZ) {
+ node = rcu_dereference_bh(
+ hlist_first_rcu(&net->ipv6.fib_table_hash[h++]));
+ }
+ return hlist_entry_safe(node, struct fib6_table, tb6_hlist);
+}
+
+static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
+{
+ if (iter->sernum != iter->w.root->fn_sernum) {
+ iter->sernum = iter->w.root->fn_sernum;
+ iter->w.state = FWS_INIT;
+ iter->w.node = iter->w.root;
+ WARN_ON(iter->w.skip);
+ iter->w.skip = iter->w.count;
+ }
+}
+
+static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ int r;
+ struct rt6_info *n;
+ struct net *net = seq_file_net(seq);
+ struct ipv6_route_iter *iter = seq->private;
+
+ if (!v)
+ goto iter_table;
+
+ n = ((struct rt6_info *)v)->dst.rt6_next;
+ if (n) {
+ ++*pos;
+ return n;
+ }
+
+iter_table:
+ ipv6_route_check_sernum(iter);
+ read_lock(&iter->tbl->tb6_lock);
+ r = fib6_walk_continue(&iter->w);
+ read_unlock(&iter->tbl->tb6_lock);
+ if (r > 0) {
+ if (v)
+ ++*pos;
+ return iter->w.leaf;
+ } else if (r < 0) {
+ fib6_walker_unlink(&iter->w);
+ return NULL;
+ }
+ fib6_walker_unlink(&iter->w);
+
+ iter->tbl = ipv6_route_seq_next_table(iter->tbl, net);
+ if (!iter->tbl)
+ return NULL;
+
+ ipv6_route_seq_setup_walk(iter);
+ goto iter_table;
+}
+
+static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU_BH)
+{
+ struct net *net = seq_file_net(seq);
+ struct ipv6_route_iter *iter = seq->private;
+
+ rcu_read_lock_bh();
+ iter->tbl = ipv6_route_seq_next_table(NULL, net);
+ iter->skip = *pos;
+
+ if (iter->tbl) {
+ ipv6_route_seq_setup_walk(iter);
+ return ipv6_route_seq_next(seq, NULL, pos);
+ } else {
+ return NULL;
+ }
+}
+
+static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
+{
+ struct fib6_walker_t *w = &iter->w;
+ return w->node && !(w->state == FWS_U && w->node == w->root);
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU_BH)
+{
+ struct ipv6_route_iter *iter = seq->private;
+
+ if (ipv6_route_iter_active(iter))
+ fib6_walker_unlink(&iter->w);
+
+ rcu_read_unlock_bh();
+}
+
+static const struct seq_operations ipv6_route_seq_ops = {
+ .start = ipv6_route_seq_start,
+ .next = ipv6_route_seq_next,
+ .stop = ipv6_route_seq_stop,
+ .show = ipv6_route_seq_show
+};
+
+int ipv6_route_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &ipv6_route_seq_ops,
+ sizeof(struct ipv6_route_iter));
+}
+
+#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c979dd96d82a..c3130ffc3bca 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1137,7 +1137,6 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
- fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
@@ -1236,7 +1235,6 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
- fl6.flowi6_flags = 0;
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
@@ -1258,7 +1256,6 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.flowi6_mark = mark;
- fl6.flowi6_flags = 0;
fl6.daddr = msg->dest;
fl6.saddr = iph->daddr;
@@ -2800,56 +2797,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
#ifdef CONFIG_PROC_FS
-struct rt6_proc_arg
-{
- char *buffer;
- int offset;
- int length;
- int skip;
- int len;
-};
-
-static int rt6_info_route(struct rt6_info *rt, void *p_arg)
-{
- struct seq_file *m = p_arg;
-
- seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
-
-#ifdef CONFIG_IPV6_SUBTREES
- seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
-#else
- seq_puts(m, "00000000000000000000000000000000 00 ");
-#endif
- if (rt->rt6i_flags & RTF_GATEWAY) {
- seq_printf(m, "%pi6", &rt->rt6i_gateway);
- } else {
- seq_puts(m, "00000000000000000000000000000000");
- }
- seq_printf(m, " %08x %08x %08x %08x %8s\n",
- rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
- rt->dst.__use, rt->rt6i_flags,
- rt->dst.dev ? rt->dst.dev->name : "");
- return 0;
-}
-
-static int ipv6_route_show(struct seq_file *m, void *v)
-{
- struct net *net = (struct net *)m->private;
- fib6_clean_all_ro(net, rt6_info_route, 0, m);
- return 0;
-}
-
-static int ipv6_route_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, ipv6_route_show);
-}
-
static const struct file_operations ipv6_route_proc_fops = {
.owner = THIS_MODULE,
.open = ipv6_route_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release_net,
+ .release = seq_release_net,
};
static int rt6_stats_seq_show(struct seq_file *seq, void *v)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bf63ac8a49b9..d703218a653b 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,26 +24,21 @@
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
-/* Table must be sorted. */
+/* RFC 2460, Section 8.3:
+ * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
+ *
+ * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows
+ * using higher values than ipv4 tcp syncookies.
+ * The other values are chosen based on ethernet (1500 and 9k MTU), plus
+ * one that accounts for common encap (PPPoe) overhead. Table must be sorted.
+ */
static __u16 const msstab[] = {
- 64,
- 512,
- 536,
- 1280 - 60,
+ 1280 - 60, /* IPV6_MIN_MTU - 60 */
1480 - 60,
1500 - 60,
- 4460 - 60,
9000 - 60,
};
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-
static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
@@ -86,8 +81,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__be16 sport, __be16 dport, __u32 sseq,
- __u32 count, __u32 data)
+ __u32 data)
{
+ u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -96,15 +92,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
const struct in6_addr *daddr, __be16 sport,
- __be16 dport, __u32 sseq, __u32 count,
- __u32 maxdiff)
+ __be16 dport, __u32 sseq)
{
- __u32 diff;
+ __u32 diff, count = tcp_cookie_time();
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
- if (diff >= maxdiff)
+ if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
@@ -125,8 +120,7 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
*mssp = msstab[mssind];
return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
- th->dest, ntohl(th->seq),
- jiffies / (HZ * 60), mssind);
+ th->dest, ntohl(th->seq), mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
@@ -146,8 +140,7 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
- th->source, th->dest, seq,
- jiffies / (HZ * 60), COUNTER_TRIES);
+ th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5c71501fc917..dde8bad04481 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1811,7 +1811,7 @@ static void get_timewait6_sock(struct seq_file *seq,
const struct in6_addr *dest, *src;
__u16 destp, srcp;
const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
- long delta = tw->tw_ttd - jiffies;
+ s32 delta = tw->tw_ttd - inet_tw_time_stamp();
dest = &tw6->tw_v6_daddr;
src = &tw6->tw_v6_rcv_saddr;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 72b7eaaf3ca0..37532478e3ba 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -57,8 +57,6 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
{
const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
- __be32 sk1_rcv_saddr = sk_rcv_saddr(sk);
- __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
int sk_ipv6only = ipv6_only_sock(sk);
int sk2_ipv6only = inet_v6_ipv6only(sk2);
int addr_type = ipv6_addr_type(sk_rcv_saddr6);
@@ -67,8 +65,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
/* if both are mapped, treat as IPv4 */
if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
return (!sk2_ipv6only &&
- (!sk1_rcv_saddr || !sk2_rcv_saddr ||
- sk1_rcv_saddr == sk2_rcv_saddr));
+ (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr ||
+ sk->sk_rcv_saddr == sk2->sk_rcv_saddr));
if (addr_type2 == IPV6_ADDR_ANY &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
@@ -551,8 +549,10 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
- if (!ipv6_addr_any(&inet6_sk(sk)->daddr))
+ if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) {
sock_rps_save_rxhash(sk, skb);
+ sk_mark_napi_id(sk, skb);
+ }
rc = sock_queue_rcv_skb(sk, skb);
if (rc < 0) {
@@ -846,7 +846,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (sk != NULL) {
int ret;
- sk_mark_napi_id(sk, skb);
ret = udpv6_queue_rcv_skb(sk, skb);
sock_put(sk);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 1aba645882bd..3fb9dd6d02fc 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -77,13 +77,13 @@ DECLARE_EVENT_CLASS(local_sdata_addr_evt,
TP_STRUCT__entry(
LOCAL_ENTRY
VIF_ENTRY
- __array(char, addr, 6)
+ __array(char, addr, ETH_ALEN)
),
TP_fast_assign(
LOCAL_ASSIGN;
VIF_ASSIGN;
- memcpy(__entry->addr, sdata->vif.addr, 6);
+ memcpy(__entry->addr, sdata->vif.addr, ETH_ALEN);
),
TP_printk(
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index ba36c283d837..a2d6263b6c64 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -1,7 +1,7 @@
menuconfig IP_SET
tristate "IP set support"
depends on INET && NETFILTER
- depends on NETFILTER_NETLINK
+ select NETFILTER_NETLINK
help
This option adds IP set support to the kernel.
In order to define and use the sets, you need the userspace utility
@@ -90,6 +90,15 @@ config IP_SET_HASH_IPPORTNET
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_NETPORTNET
+ tristate "hash:net,port,net set support"
+ depends on IP_SET
+ help
+ This option adds the hash:net,port,net set type support, by which
+ one can store two IPv4/IPv6 subnets, and a protocol/port in a set.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_NET
tristate "hash:net set support"
depends on IP_SET
@@ -99,6 +108,15 @@ config IP_SET_HASH_NET
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_NETNET
+ tristate "hash:net,net set support"
+ depends on IP_SET
+ help
+ This option adds the hash:net,net set type support, by which
+ one can store IPv4/IPv6 network address/prefix pairs in a set.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_NETPORT
tristate "hash:net,port set support"
depends on IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 6e965ecd5444..44b2d38476fa 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -20,6 +20,8 @@ obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o
obj-$(CONFIG_IP_SET_HASH_NET) += ip_set_hash_net.o
obj-$(CONFIG_IP_SET_HASH_NETPORT) += ip_set_hash_netport.o
obj-$(CONFIG_IP_SET_HASH_NETIFACE) += ip_set_hash_netiface.o
+obj-$(CONFIG_IP_SET_HASH_NETNET) += ip_set_hash_netnet.o
+obj-$(CONFIG_IP_SET_HASH_NETPORTNET) += ip_set_hash_netportnet.o
# list types
obj-$(CONFIG_IP_SET_LIST_SET) += ip_set_list_set.o
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 25243379b887..a13e15be7911 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -8,38 +8,32 @@
#ifndef __IP_SET_BITMAP_IP_GEN_H
#define __IP_SET_BITMAP_IP_GEN_H
-#define CONCAT(a, b) a##b
-#define TOKEN(a,b) CONCAT(a, b)
-
-#define mtype_do_test TOKEN(MTYPE, _do_test)
-#define mtype_gc_test TOKEN(MTYPE, _gc_test)
-#define mtype_is_filled TOKEN(MTYPE, _is_filled)
-#define mtype_do_add TOKEN(MTYPE, _do_add)
-#define mtype_do_del TOKEN(MTYPE, _do_del)
-#define mtype_do_list TOKEN(MTYPE, _do_list)
-#define mtype_do_head TOKEN(MTYPE, _do_head)
-#define mtype_adt_elem TOKEN(MTYPE, _adt_elem)
-#define mtype_add_timeout TOKEN(MTYPE, _add_timeout)
-#define mtype_gc_init TOKEN(MTYPE, _gc_init)
-#define mtype_kadt TOKEN(MTYPE, _kadt)
-#define mtype_uadt TOKEN(MTYPE, _uadt)
-#define mtype_destroy TOKEN(MTYPE, _destroy)
-#define mtype_flush TOKEN(MTYPE, _flush)
-#define mtype_head TOKEN(MTYPE, _head)
-#define mtype_same_set TOKEN(MTYPE, _same_set)
-#define mtype_elem TOKEN(MTYPE, _elem)
-#define mtype_test TOKEN(MTYPE, _test)
-#define mtype_add TOKEN(MTYPE, _add)
-#define mtype_del TOKEN(MTYPE, _del)
-#define mtype_list TOKEN(MTYPE, _list)
-#define mtype_gc TOKEN(MTYPE, _gc)
+#define mtype_do_test IPSET_TOKEN(MTYPE, _do_test)
+#define mtype_gc_test IPSET_TOKEN(MTYPE, _gc_test)
+#define mtype_is_filled IPSET_TOKEN(MTYPE, _is_filled)
+#define mtype_do_add IPSET_TOKEN(MTYPE, _do_add)
+#define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup)
+#define mtype_do_del IPSET_TOKEN(MTYPE, _do_del)
+#define mtype_do_list IPSET_TOKEN(MTYPE, _do_list)
+#define mtype_do_head IPSET_TOKEN(MTYPE, _do_head)
+#define mtype_adt_elem IPSET_TOKEN(MTYPE, _adt_elem)
+#define mtype_add_timeout IPSET_TOKEN(MTYPE, _add_timeout)
+#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_kadt IPSET_TOKEN(MTYPE, _kadt)
+#define mtype_uadt IPSET_TOKEN(MTYPE, _uadt)
+#define mtype_destroy IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_flush IPSET_TOKEN(MTYPE, _flush)
+#define mtype_head IPSET_TOKEN(MTYPE, _head)
+#define mtype_same_set IPSET_TOKEN(MTYPE, _same_set)
+#define mtype_elem IPSET_TOKEN(MTYPE, _elem)
+#define mtype_test IPSET_TOKEN(MTYPE, _test)
+#define mtype_add IPSET_TOKEN(MTYPE, _add)
+#define mtype_del IPSET_TOKEN(MTYPE, _del)
+#define mtype_list IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc IPSET_TOKEN(MTYPE, _gc)
#define mtype MTYPE
-#define ext_timeout(e, m) \
- (unsigned long *)((e) + (m)->offset[IPSET_OFFSET_TIMEOUT])
-#define ext_counter(e, m) \
- (struct ip_set_counter *)((e) + (m)->offset[IPSET_OFFSET_COUNTER])
-#define get_ext(map, id) ((map)->extensions + (map)->dsize * (id))
+#define get_ext(set, map, id) ((map)->extensions + (set)->dsize * (id))
static void
mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
@@ -49,11 +43,22 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
init_timer(&map->gc);
map->gc.data = (unsigned long) set;
map->gc.function = gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&map->gc);
}
static void
+mtype_ext_cleanup(struct ip_set *set)
+{
+ struct mtype *map = set->data;
+ u32 id;
+
+ for (id = 0; id < map->elements; id++)
+ if (test_bit(id, map->members))
+ ip_set_ext_destroy(set, get_ext(set, map, id));
+}
+
+static void
mtype_destroy(struct ip_set *set)
{
struct mtype *map = set->data;
@@ -62,8 +67,11 @@ mtype_destroy(struct ip_set *set)
del_timer_sync(&map->gc);
ip_set_free(map->members);
- if (map->dsize)
+ if (set->dsize) {
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set);
ip_set_free(map->extensions);
+ }
kfree(map);
set->data = NULL;
@@ -74,6 +82,8 @@ mtype_flush(struct ip_set *set)
{
struct mtype *map = set->data;
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set);
memset(map->members, 0, map->memsize);
}
@@ -91,12 +101,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
htonl(sizeof(*map) +
map->memsize +
- map->dsize * map->elements)) ||
- (SET_WITH_TIMEOUT(set) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))) ||
- (SET_WITH_COUNTER(set) &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS,
- htonl(IPSET_FLAG_WITH_COUNTERS))))
+ set->dsize * map->elements)))
+ goto nla_put_failure;
+ if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
ipset_nest_end(skb, nested);
@@ -111,16 +118,16 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
{
struct mtype *map = set->data;
const struct mtype_adt_elem *e = value;
- void *x = get_ext(map, e->id);
- int ret = mtype_do_test(e, map);
+ void *x = get_ext(set, map, e->id);
+ int ret = mtype_do_test(e, map, set->dsize);
if (ret <= 0)
return ret;
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(x, map)))
+ ip_set_timeout_expired(ext_timeout(x, set)))
return 0;
if (SET_WITH_COUNTER(set))
- ip_set_update_counter(ext_counter(x, map), ext, mext, flags);
+ ip_set_update_counter(ext_counter(x, set), ext, mext, flags);
return 1;
}
@@ -130,26 +137,30 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
{
struct mtype *map = set->data;
const struct mtype_adt_elem *e = value;
- void *x = get_ext(map, e->id);
- int ret = mtype_do_add(e, map, flags);
+ void *x = get_ext(set, map, e->id);
+ int ret = mtype_do_add(e, map, flags, set->dsize);
if (ret == IPSET_ADD_FAILED) {
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(x, map)))
+ ip_set_timeout_expired(ext_timeout(x, set)))
ret = 0;
else if (!(flags & IPSET_FLAG_EXIST))
return -IPSET_ERR_EXIST;
+ /* Element is re-added, cleanup extensions */
+ ip_set_ext_destroy(set, x);
}
if (SET_WITH_TIMEOUT(set))
#ifdef IP_SET_BITMAP_STORED_TIMEOUT
- mtype_add_timeout(ext_timeout(x, map), e, ext, map, ret);
+ mtype_add_timeout(ext_timeout(x, set), e, ext, set, map, ret);
#else
- ip_set_timeout_set(ext_timeout(x, map), ext->timeout);
+ ip_set_timeout_set(ext_timeout(x, set), ext->timeout);
#endif
if (SET_WITH_COUNTER(set))
- ip_set_init_counter(ext_counter(x, map), ext);
+ ip_set_init_counter(ext_counter(x, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(x, set), ext);
return 0;
}
@@ -159,16 +170,27 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
{
struct mtype *map = set->data;
const struct mtype_adt_elem *e = value;
- const void *x = get_ext(map, e->id);
+ void *x = get_ext(set, map, e->id);
- if (mtype_do_del(e, map) ||
- (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(x, map))))
+ if (mtype_do_del(e, map))
+ return -IPSET_ERR_EXIST;
+
+ ip_set_ext_destroy(set, x);
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(x, set)))
return -IPSET_ERR_EXIST;
return 0;
}
+#ifndef IP_SET_BITMAP_STORED_TIMEOUT
+static inline bool
+mtype_is_filled(const struct mtype_elem *x)
+{
+ return true;
+}
+#endif
+
static int
mtype_list(const struct ip_set *set,
struct sk_buff *skb, struct netlink_callback *cb)
@@ -183,13 +205,13 @@ mtype_list(const struct ip_set *set,
return -EMSGSIZE;
for (; cb->args[2] < map->elements; cb->args[2]++) {
id = cb->args[2];
- x = get_ext(map, id);
+ x = get_ext(set, map, id);
if (!test_bit(id, map->members) ||
(SET_WITH_TIMEOUT(set) &&
#ifdef IP_SET_BITMAP_STORED_TIMEOUT
mtype_is_filled((const struct mtype_elem *) x) &&
#endif
- ip_set_timeout_expired(ext_timeout(x, map))))
+ ip_set_timeout_expired(ext_timeout(x, set))))
continue;
nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
if (!nested) {
@@ -199,23 +221,10 @@ mtype_list(const struct ip_set *set,
} else
goto nla_put_failure;
}
- if (mtype_do_list(skb, map, id))
+ if (mtype_do_list(skb, map, id, set->dsize))
goto nla_put_failure;
- if (SET_WITH_TIMEOUT(set)) {
-#ifdef IP_SET_BITMAP_STORED_TIMEOUT
- if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_stored(map, id,
- ext_timeout(x, map)))))
- goto nla_put_failure;
-#else
- if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(
- ext_timeout(x, map)))))
- goto nla_put_failure;
-#endif
- }
- if (SET_WITH_COUNTER(set) &&
- ip_set_put_counter(skb, ext_counter(x, map)))
+ if (ip_set_put_extensions(skb, set, x,
+ mtype_is_filled((const struct mtype_elem *) x)))
goto nla_put_failure;
ipset_nest_end(skb, nested);
}
@@ -228,11 +237,11 @@ mtype_list(const struct ip_set *set,
nla_put_failure:
nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, adt);
if (unlikely(id == first)) {
cb->args[2] = 0;
return -EMSGSIZE;
}
+ ipset_nest_end(skb, adt);
return 0;
}
@@ -241,21 +250,23 @@ mtype_gc(unsigned long ul_set)
{
struct ip_set *set = (struct ip_set *) ul_set;
struct mtype *map = set->data;
- const void *x;
+ void *x;
u32 id;
/* We run parallel with other readers (test element)
* but adding/deleting new entries is locked out */
read_lock_bh(&set->lock);
for (id = 0; id < map->elements; id++)
- if (mtype_gc_test(id, map)) {
- x = get_ext(map, id);
- if (ip_set_timeout_expired(ext_timeout(x, map)))
+ if (mtype_gc_test(id, map, set->dsize)) {
+ x = get_ext(set, map, id);
+ if (ip_set_timeout_expired(ext_timeout(x, set))) {
clear_bit(id, map->members);
+ ip_set_ext_destroy(set, x);
+ }
}
read_unlock_bh(&set->lock);
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&map->gc);
}
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index f1a8128bef01..6f1f9f494808 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -25,12 +25,13 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_bitmap.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* Counter support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counter support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comment support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_bitmap:ip");
#define MTYPE bitmap_ip
@@ -44,10 +45,7 @@ struct bitmap_ip {
u32 elements; /* number of max elements in the set */
u32 hosts; /* number of hosts in a subnet */
size_t memsize; /* members size */
- size_t dsize; /* extensions struct size */
- size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
u8 netmask; /* subnet netmask */
- u32 timeout; /* timeout parameter */
struct timer_list gc; /* garbage collection */
};
@@ -65,20 +63,21 @@ ip_to_id(const struct bitmap_ip *m, u32 ip)
/* Common functions */
static inline int
-bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map)
+bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e,
+ struct bitmap_ip *map, size_t dsize)
{
return !!test_bit(e->id, map->members);
}
static inline int
-bitmap_ip_gc_test(u16 id, const struct bitmap_ip *map)
+bitmap_ip_gc_test(u16 id, const struct bitmap_ip *map, size_t dsize)
{
return !!test_bit(id, map->members);
}
static inline int
bitmap_ip_do_add(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map,
- u32 flags)
+ u32 flags, size_t dsize)
{
return !!test_and_set_bit(e->id, map->members);
}
@@ -90,7 +89,8 @@ bitmap_ip_do_del(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map)
}
static inline int
-bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id)
+bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id,
+ size_t dsize)
{
return nla_put_ipaddr4(skb, IPSET_ATTR_IP,
htonl(map->first_ip + id * map->hosts));
@@ -113,7 +113,7 @@ bitmap_ip_kadt(struct ip_set *set, const struct sk_buff *skb,
struct bitmap_ip *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct bitmap_ip_adt_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
u32 ip;
ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC));
@@ -131,9 +131,9 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[],
{
struct bitmap_ip *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- u32 ip, ip_to;
+ u32 ip = 0, ip_to = 0;
struct bitmap_ip_adt_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -200,7 +200,7 @@ bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
return x->first_ip == y->first_ip &&
x->last_ip == y->last_ip &&
x->netmask == y->netmask &&
- x->timeout == y->timeout &&
+ a->timeout == b->timeout &&
a->extensions == b->extensions;
}
@@ -209,25 +209,6 @@ bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
struct bitmap_ip_elem {
};
-/* Timeout variant */
-
-struct bitmap_ipt_elem {
- unsigned long timeout;
-};
-
-/* Plain variant with counter */
-
-struct bitmap_ipc_elem {
- struct ip_set_counter counter;
-};
-
-/* Timeout variant with counter */
-
-struct bitmap_ipct_elem {
- unsigned long timeout;
- struct ip_set_counter counter;
-};
-
#include "ip_set_bitmap_gen.h"
/* Create bitmap:ip type of sets */
@@ -240,8 +221,8 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
map->members = ip_set_alloc(map->memsize);
if (!map->members)
return false;
- if (map->dsize) {
- map->extensions = ip_set_alloc(map->dsize * elements);
+ if (set->dsize) {
+ map->extensions = ip_set_alloc(set->dsize * elements);
if (!map->extensions) {
kfree(map->members);
return false;
@@ -252,7 +233,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
map->elements = elements;
map->hosts = hosts;
map->netmask = netmask;
- map->timeout = IPSET_NO_TIMEOUT;
+ set->timeout = IPSET_NO_TIMEOUT;
set->data = map;
set->family = NFPROTO_IPV4;
@@ -261,10 +242,11 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
}
static int
-bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+ u32 flags)
{
struct bitmap_ip *map;
- u32 first_ip, last_ip, hosts, cadt_flags = 0;
+ u32 first_ip = 0, last_ip = 0, hosts;
u64 elements;
u8 netmask = 32;
int ret;
@@ -336,61 +318,15 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
map->memsize = bitmap_bytes(0, elements - 1);
set->variant = &bitmap_ip;
- if (tb[IPSET_ATTR_CADT_FLAGS])
- cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
- if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
- set->extensions |= IPSET_EXT_COUNTER;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct bitmap_ipct_elem);
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct bitmap_ipct_elem, timeout);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct bitmap_ipct_elem, counter);
-
- if (!init_map_ip(set, map, first_ip, last_ip,
- elements, hosts, netmask)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout = ip_set_timeout_uget(
- tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
-
- bitmap_ip_gc_init(set, bitmap_ip_gc);
- } else {
- map->dsize = sizeof(struct bitmap_ipc_elem);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct bitmap_ipc_elem, counter);
-
- if (!init_map_ip(set, map, first_ip, last_ip,
- elements, hosts, netmask)) {
- kfree(map);
- return -ENOMEM;
- }
- }
- } else if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct bitmap_ipt_elem);
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct bitmap_ipt_elem, timeout);
-
- if (!init_map_ip(set, map, first_ip, last_ip,
- elements, hosts, netmask)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
-
+ set->dsize = ip_set_elem_len(set, tb, 0);
+ if (!init_map_ip(set, map, first_ip, last_ip,
+ elements, hosts, netmask)) {
+ kfree(map);
+ return -ENOMEM;
+ }
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
bitmap_ip_gc_init(set, bitmap_ip_gc);
- } else {
- map->dsize = 0;
- if (!init_map_ip(set, map, first_ip, last_ip,
- elements, hosts, netmask)) {
- kfree(map);
- return -ENOMEM;
- }
}
return 0;
}
@@ -401,8 +337,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = {
.features = IPSET_TYPE_IP,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_IPV4,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = bitmap_ip_create,
.create_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -420,6 +356,7 @@ static struct ip_set_type bitmap_ip_type __read_mostly = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 3b30e0bef890..740eabededd9 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -25,12 +25,13 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_bitmap.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* Counter support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counter support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comment support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:ip,mac", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:ip,mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_bitmap:ip,mac");
#define MTYPE bitmap_ipmac
@@ -48,11 +49,8 @@ struct bitmap_ipmac {
u32 first_ip; /* host byte order, included in range */
u32 last_ip; /* host byte order, included in range */
u32 elements; /* number of max elements in the set */
- u32 timeout; /* timeout value */
- struct timer_list gc; /* garbage collector */
size_t memsize; /* members size */
- size_t dsize; /* size of element */
- size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
+ struct timer_list gc; /* garbage collector */
};
/* ADT structure for generic function args */
@@ -82,13 +80,13 @@ get_elem(void *extensions, u16 id, size_t dsize)
static inline int
bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
- const struct bitmap_ipmac *map)
+ const struct bitmap_ipmac *map, size_t dsize)
{
const struct bitmap_ipmac_elem *elem;
if (!test_bit(e->id, map->members))
return 0;
- elem = get_elem(map->extensions, e->id, map->dsize);
+ elem = get_elem(map->extensions, e->id, dsize);
if (elem->filled == MAC_FILLED)
return e->ether == NULL ||
ether_addr_equal(e->ether, elem->ether);
@@ -97,13 +95,13 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
}
static inline int
-bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map)
+bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize)
{
const struct bitmap_ipmac_elem *elem;
if (!test_bit(id, map->members))
return 0;
- elem = get_elem(map->extensions, id, map->dsize);
+ elem = get_elem(map->extensions, id, dsize);
/* Timer not started for the incomplete elements */
return elem->filled == MAC_FILLED;
}
@@ -117,13 +115,13 @@ bitmap_ipmac_is_filled(const struct bitmap_ipmac_elem *elem)
static inline int
bitmap_ipmac_add_timeout(unsigned long *timeout,
const struct bitmap_ipmac_adt_elem *e,
- const struct ip_set_ext *ext,
+ const struct ip_set_ext *ext, struct ip_set *set,
struct bitmap_ipmac *map, int mode)
{
u32 t = ext->timeout;
if (mode == IPSET_ADD_START_STORED_TIMEOUT) {
- if (t == map->timeout)
+ if (t == set->timeout)
/* Timeout was not specified, get stored one */
t = *timeout;
ip_set_timeout_set(timeout, t);
@@ -142,11 +140,11 @@ bitmap_ipmac_add_timeout(unsigned long *timeout,
static inline int
bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e,
- struct bitmap_ipmac *map, u32 flags)
+ struct bitmap_ipmac *map, u32 flags, size_t dsize)
{
struct bitmap_ipmac_elem *elem;
- elem = get_elem(map->extensions, e->id, map->dsize);
+ elem = get_elem(map->extensions, e->id, dsize);
if (test_and_set_bit(e->id, map->members)) {
if (elem->filled == MAC_FILLED) {
if (e->ether && (flags & IPSET_FLAG_EXIST))
@@ -178,22 +176,12 @@ bitmap_ipmac_do_del(const struct bitmap_ipmac_adt_elem *e,
return !test_and_clear_bit(e->id, map->members);
}
-static inline unsigned long
-ip_set_timeout_stored(struct bitmap_ipmac *map, u32 id, unsigned long *timeout)
-{
- const struct bitmap_ipmac_elem *elem =
- get_elem(map->extensions, id, map->dsize);
-
- return elem->filled == MAC_FILLED ? ip_set_timeout_get(timeout) :
- *timeout;
-}
-
static inline int
bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map,
- u32 id)
+ u32 id, size_t dsize)
{
const struct bitmap_ipmac_elem *elem =
- get_elem(map->extensions, id, map->dsize);
+ get_elem(map->extensions, id, dsize);
return nla_put_ipaddr4(skb, IPSET_ATTR_IP,
htonl(map->first_ip + id)) ||
@@ -216,7 +204,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
struct bitmap_ipmac *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct bitmap_ipmac_adt_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
u32 ip;
/* MAC can be src only */
@@ -245,8 +233,8 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[],
const struct bitmap_ipmac *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct bitmap_ipmac_adt_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
- u32 ip;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0;
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -285,43 +273,12 @@ bitmap_ipmac_same_set(const struct ip_set *a, const struct ip_set *b)
return x->first_ip == y->first_ip &&
x->last_ip == y->last_ip &&
- x->timeout == y->timeout &&
+ a->timeout == b->timeout &&
a->extensions == b->extensions;
}
/* Plain variant */
-/* Timeout variant */
-
-struct bitmap_ipmact_elem {
- struct {
- unsigned char ether[ETH_ALEN];
- unsigned char filled;
- } __attribute__ ((aligned));
- unsigned long timeout;
-};
-
-/* Plain variant with counter */
-
-struct bitmap_ipmacc_elem {
- struct {
- unsigned char ether[ETH_ALEN];
- unsigned char filled;
- } __attribute__ ((aligned));
- struct ip_set_counter counter;
-};
-
-/* Timeout variant with counter */
-
-struct bitmap_ipmacct_elem {
- struct {
- unsigned char ether[ETH_ALEN];
- unsigned char filled;
- } __attribute__ ((aligned));
- unsigned long timeout;
- struct ip_set_counter counter;
-};
-
#include "ip_set_bitmap_gen.h"
/* Create bitmap:ip,mac type of sets */
@@ -330,11 +287,11 @@ static bool
init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
u32 first_ip, u32 last_ip, u32 elements)
{
- map->members = ip_set_alloc((last_ip - first_ip + 1) * map->dsize);
+ map->members = ip_set_alloc(map->memsize);
if (!map->members)
return false;
- if (map->dsize) {
- map->extensions = ip_set_alloc(map->dsize * elements);
+ if (set->dsize) {
+ map->extensions = ip_set_alloc(set->dsize * elements);
if (!map->extensions) {
kfree(map->members);
return false;
@@ -343,7 +300,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
map->first_ip = first_ip;
map->last_ip = last_ip;
map->elements = elements;
- map->timeout = IPSET_NO_TIMEOUT;
+ set->timeout = IPSET_NO_TIMEOUT;
set->data = map;
set->family = NFPROTO_IPV4;
@@ -352,10 +309,10 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
}
static int
-bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
+bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
u32 flags)
{
- u32 first_ip, last_ip, cadt_flags = 0;
+ u32 first_ip = 0, last_ip = 0;
u64 elements;
struct bitmap_ipmac *map;
int ret;
@@ -399,57 +356,15 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
map->memsize = bitmap_bytes(0, elements - 1);
set->variant = &bitmap_ipmac;
- if (tb[IPSET_ATTR_CADT_FLAGS])
- cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
- if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
- set->extensions |= IPSET_EXT_COUNTER;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct bitmap_ipmacct_elem);
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct bitmap_ipmacct_elem, timeout);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct bitmap_ipmacct_elem, counter);
-
- if (!init_map_ipmac(set, map, first_ip, last_ip,
- elements)) {
- kfree(map);
- return -ENOMEM;
- }
- map->timeout = ip_set_timeout_uget(
- tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
- bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
- } else {
- map->dsize = sizeof(struct bitmap_ipmacc_elem);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct bitmap_ipmacc_elem, counter);
-
- if (!init_map_ipmac(set, map, first_ip, last_ip,
- elements)) {
- kfree(map);
- return -ENOMEM;
- }
- }
- } else if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct bitmap_ipmact_elem);
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct bitmap_ipmact_elem, timeout);
-
- if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
- kfree(map);
- return -ENOMEM;
- }
- map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
+ set->dsize = ip_set_elem_len(set, tb,
+ sizeof(struct bitmap_ipmac_elem));
+ if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
+ kfree(map);
+ return -ENOMEM;
+ }
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
- } else {
- map->dsize = sizeof(struct bitmap_ipmac_elem);
-
- if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
- kfree(map);
- return -ENOMEM;
- }
- set->variant = &bitmap_ipmac;
}
return 0;
}
@@ -460,8 +375,8 @@ static struct ip_set_type bitmap_ipmac_type = {
.features = IPSET_TYPE_IP | IPSET_TYPE_MAC,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_IPV4,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = bitmap_ipmac_create,
.create_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -478,6 +393,7 @@ static struct ip_set_type bitmap_ipmac_type = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 8207d1fda528..e7603c5b53d7 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -20,12 +20,13 @@
#include <linux/netfilter/ipset/ip_set_bitmap.h>
#include <linux/netfilter/ipset/ip_set_getport.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* Counter support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counter support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comment support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_bitmap:port");
#define MTYPE bitmap_port
@@ -38,9 +39,6 @@ struct bitmap_port {
u16 last_port; /* host byte order, included in range */
u32 elements; /* number of max elements in the set */
size_t memsize; /* members size */
- size_t dsize; /* extensions struct size */
- size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
- u32 timeout; /* timeout parameter */
struct timer_list gc; /* garbage collection */
};
@@ -59,20 +57,20 @@ port_to_id(const struct bitmap_port *m, u16 port)
static inline int
bitmap_port_do_test(const struct bitmap_port_adt_elem *e,
- const struct bitmap_port *map)
+ const struct bitmap_port *map, size_t dsize)
{
return !!test_bit(e->id, map->members);
}
static inline int
-bitmap_port_gc_test(u16 id, const struct bitmap_port *map)
+bitmap_port_gc_test(u16 id, const struct bitmap_port *map, size_t dsize)
{
return !!test_bit(id, map->members);
}
static inline int
bitmap_port_do_add(const struct bitmap_port_adt_elem *e,
- struct bitmap_port *map, u32 flags)
+ struct bitmap_port *map, u32 flags, size_t dsize)
{
return !!test_and_set_bit(e->id, map->members);
}
@@ -85,7 +83,8 @@ bitmap_port_do_del(const struct bitmap_port_adt_elem *e,
}
static inline int
-bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id)
+bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id,
+ size_t dsize)
{
return nla_put_net16(skb, IPSET_ATTR_PORT,
htons(map->first_port + id));
@@ -106,7 +105,7 @@ bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb,
struct bitmap_port *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct bitmap_port_adt_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
__be16 __port;
u16 port = 0;
@@ -131,7 +130,7 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[],
struct bitmap_port *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct bitmap_port_adt_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port; /* wraparound */
u16 port_to;
int ret = 0;
@@ -191,7 +190,7 @@ bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b)
return x->first_port == y->first_port &&
x->last_port == y->last_port &&
- x->timeout == y->timeout &&
+ a->timeout == b->timeout &&
a->extensions == b->extensions;
}
@@ -200,25 +199,6 @@ bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b)
struct bitmap_port_elem {
};
-/* Timeout variant */
-
-struct bitmap_portt_elem {
- unsigned long timeout;
-};
-
-/* Plain variant with counter */
-
-struct bitmap_portc_elem {
- struct ip_set_counter counter;
-};
-
-/* Timeout variant with counter */
-
-struct bitmap_portct_elem {
- unsigned long timeout;
- struct ip_set_counter counter;
-};
-
#include "ip_set_bitmap_gen.h"
/* Create bitmap:ip type of sets */
@@ -230,8 +210,8 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
map->members = ip_set_alloc(map->memsize);
if (!map->members)
return false;
- if (map->dsize) {
- map->extensions = ip_set_alloc(map->dsize * map->elements);
+ if (set->dsize) {
+ map->extensions = ip_set_alloc(set->dsize * map->elements);
if (!map->extensions) {
kfree(map->members);
return false;
@@ -239,7 +219,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
}
map->first_port = first_port;
map->last_port = last_port;
- map->timeout = IPSET_NO_TIMEOUT;
+ set->timeout = IPSET_NO_TIMEOUT;
set->data = map;
set->family = NFPROTO_UNSPEC;
@@ -248,11 +228,11 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
}
static int
-bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+ u32 flags)
{
struct bitmap_port *map;
u16 first_port, last_port;
- u32 cadt_flags = 0;
if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) ||
@@ -276,53 +256,14 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
map->elements = last_port - first_port + 1;
map->memsize = map->elements * sizeof(unsigned long);
set->variant = &bitmap_port;
- if (tb[IPSET_ATTR_CADT_FLAGS])
- cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
- if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
- set->extensions |= IPSET_EXT_COUNTER;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct bitmap_portct_elem);
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct bitmap_portct_elem, timeout);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct bitmap_portct_elem, counter);
- if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout =
- ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
- bitmap_port_gc_init(set, bitmap_port_gc);
- } else {
- map->dsize = sizeof(struct bitmap_portc_elem);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct bitmap_portc_elem, counter);
- if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
- return -ENOMEM;
- }
- }
- } else if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct bitmap_portt_elem);
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct bitmap_portt_elem, timeout);
- if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
+ set->dsize = ip_set_elem_len(set, tb, 0);
+ if (!init_map_port(set, map, first_port, last_port)) {
+ kfree(map);
+ return -ENOMEM;
+ }
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
bitmap_port_gc_init(set, bitmap_port_gc);
- } else {
- map->dsize = 0;
- if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
- return -ENOMEM;
- }
-
}
return 0;
}
@@ -333,8 +274,8 @@ static struct ip_set_type bitmap_port_type = {
.features = IPSET_TYPE_PORT,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = bitmap_port_create,
.create_policy = {
[IPSET_ATTR_PORT] = { .type = NLA_U16 },
@@ -349,6 +290,7 @@ static struct ip_set_type bitmap_port_type = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index f2e30fb31e78..dc9284bdd2dd 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -17,6 +17,8 @@
#include <linux/spinlock.h>
#include <linux/rculist.h>
#include <net/netlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include <linux/netfilter.h>
#include <linux/netfilter/x_tables.h>
@@ -27,8 +29,17 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */
static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */
static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */
-static struct ip_set * __rcu *ip_set_list; /* all individual sets */
-static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */
+struct ip_set_net {
+ struct ip_set * __rcu *ip_set_list; /* all individual sets */
+ ip_set_id_t ip_set_max; /* max number of sets */
+ int is_deleted; /* deleted by ip_set_net_exit */
+};
+static int ip_set_net_id __read_mostly;
+
+static inline struct ip_set_net *ip_set_pernet(struct net *net)
+{
+ return net_generic(net, ip_set_net_id);
+}
#define IP_SET_INC 64
#define STREQ(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0)
@@ -45,8 +56,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
/* When the nfnl mutex is held: */
#define nfnl_dereference(p) \
rcu_dereference_protected(p, 1)
-#define nfnl_set(id) \
- nfnl_dereference(ip_set_list)[id]
+#define nfnl_set(inst, id) \
+ nfnl_dereference((inst)->ip_set_list)[id]
/*
* The set types are implemented in modules and registered set types
@@ -315,6 +326,60 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
}
EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
+typedef void (*destroyer)(void *);
+/* ipset data extension types, in size order */
+
+const struct ip_set_ext_type ip_set_extensions[] = {
+ [IPSET_EXT_ID_COUNTER] = {
+ .type = IPSET_EXT_COUNTER,
+ .flag = IPSET_FLAG_WITH_COUNTERS,
+ .len = sizeof(struct ip_set_counter),
+ .align = __alignof__(struct ip_set_counter),
+ },
+ [IPSET_EXT_ID_TIMEOUT] = {
+ .type = IPSET_EXT_TIMEOUT,
+ .len = sizeof(unsigned long),
+ .align = __alignof__(unsigned long),
+ },
+ [IPSET_EXT_ID_COMMENT] = {
+ .type = IPSET_EXT_COMMENT | IPSET_EXT_DESTROY,
+ .flag = IPSET_FLAG_WITH_COMMENT,
+ .len = sizeof(struct ip_set_comment),
+ .align = __alignof__(struct ip_set_comment),
+ .destroy = (destroyer) ip_set_comment_free,
+ },
+};
+EXPORT_SYMBOL_GPL(ip_set_extensions);
+
+static inline bool
+add_extension(enum ip_set_ext_id id, u32 flags, struct nlattr *tb[])
+{
+ return ip_set_extensions[id].flag ?
+ (flags & ip_set_extensions[id].flag) :
+ !!tb[IPSET_ATTR_TIMEOUT];
+}
+
+size_t
+ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len)
+{
+ enum ip_set_ext_id id;
+ size_t offset = 0;
+ u32 cadt_flags = 0;
+
+ if (tb[IPSET_ATTR_CADT_FLAGS])
+ cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
+ if (!add_extension(id, cadt_flags, tb))
+ continue;
+ offset += ALIGN(len + offset, ip_set_extensions[id].align);
+ set->offset[id] = offset;
+ set->extensions |= ip_set_extensions[id].type;
+ offset += ip_set_extensions[id].len;
+ }
+ return len + offset;
+}
+EXPORT_SYMBOL_GPL(ip_set_elem_len);
+
int
ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
struct ip_set_ext *ext)
@@ -334,6 +399,12 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
ext->packets = be64_to_cpu(nla_get_be64(
tb[IPSET_ATTR_PACKETS]));
}
+ if (tb[IPSET_ATTR_COMMENT]) {
+ if (!(set->extensions & IPSET_EXT_COMMENT))
+ return -IPSET_ERR_COMMENT;
+ ext->comment = ip_set_comment_uget(tb[IPSET_ATTR_COMMENT]);
+ }
+
return 0;
}
EXPORT_SYMBOL_GPL(ip_set_get_extensions);
@@ -374,13 +445,14 @@ __ip_set_put(struct ip_set *set)
*/
static inline struct ip_set *
-ip_set_rcu_get(ip_set_id_t index)
+ip_set_rcu_get(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
+ struct ip_set_net *inst = ip_set_pernet(net);
rcu_read_lock();
/* ip_set_list itself needs to be protected */
- set = rcu_dereference(ip_set_list)[index];
+ set = rcu_dereference(inst->ip_set_list)[index];
rcu_read_unlock();
return set;
@@ -390,7 +462,8 @@ int
ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(index);
+ struct ip_set *set = ip_set_rcu_get(
+ dev_net(par->in ? par->in : par->out), index);
int ret = 0;
BUG_ON(set == NULL);
@@ -428,7 +501,8 @@ int
ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(index);
+ struct ip_set *set = ip_set_rcu_get(
+ dev_net(par->in ? par->in : par->out), index);
int ret;
BUG_ON(set == NULL);
@@ -450,7 +524,8 @@ int
ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(index);
+ struct ip_set *set = ip_set_rcu_get(
+ dev_net(par->in ? par->in : par->out), index);
int ret = 0;
BUG_ON(set == NULL);
@@ -474,14 +549,15 @@ EXPORT_SYMBOL_GPL(ip_set_del);
*
*/
ip_set_id_t
-ip_set_get_byname(const char *name, struct ip_set **set)
+ip_set_get_byname(struct net *net, const char *name, struct ip_set **set)
{
ip_set_id_t i, index = IPSET_INVALID_ID;
struct ip_set *s;
+ struct ip_set_net *inst = ip_set_pernet(net);
rcu_read_lock();
- for (i = 0; i < ip_set_max; i++) {
- s = rcu_dereference(ip_set_list)[i];
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = rcu_dereference(inst->ip_set_list)[i];
if (s != NULL && STREQ(s->name, name)) {
__ip_set_get(s);
index = i;
@@ -501,17 +577,26 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname);
* to be valid, after calling this function.
*
*/
-void
-ip_set_put_byindex(ip_set_id_t index)
+
+static inline void
+__ip_set_put_byindex(struct ip_set_net *inst, ip_set_id_t index)
{
struct ip_set *set;
rcu_read_lock();
- set = rcu_dereference(ip_set_list)[index];
+ set = rcu_dereference(inst->ip_set_list)[index];
if (set != NULL)
__ip_set_put(set);
rcu_read_unlock();
}
+
+void
+ip_set_put_byindex(struct net *net, ip_set_id_t index)
+{
+ struct ip_set_net *inst = ip_set_pernet(net);
+
+ __ip_set_put_byindex(inst, index);
+}
EXPORT_SYMBOL_GPL(ip_set_put_byindex);
/*
@@ -522,9 +607,9 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex);
*
*/
const char *
-ip_set_name_byindex(ip_set_id_t index)
+ip_set_name_byindex(struct net *net, ip_set_id_t index)
{
- const struct ip_set *set = ip_set_rcu_get(index);
+ const struct ip_set *set = ip_set_rcu_get(net, index);
BUG_ON(set == NULL);
BUG_ON(set->ref == 0);
@@ -546,14 +631,15 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex);
* The nfnl mutex is used in the function.
*/
ip_set_id_t
-ip_set_nfnl_get(const char *name)
+ip_set_nfnl_get(struct net *net, const char *name)
{
ip_set_id_t i, index = IPSET_INVALID_ID;
struct ip_set *s;
+ struct ip_set_net *inst = ip_set_pernet(net);
nfnl_lock(NFNL_SUBSYS_IPSET);
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = nfnl_set(inst, i);
if (s != NULL && STREQ(s->name, name)) {
__ip_set_get(s);
index = i;
@@ -573,15 +659,16 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get);
* The nfnl mutex is used in the function.
*/
ip_set_id_t
-ip_set_nfnl_get_byindex(ip_set_id_t index)
+ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
+ struct ip_set_net *inst = ip_set_pernet(net);
- if (index > ip_set_max)
+ if (index > inst->ip_set_max)
return IPSET_INVALID_ID;
nfnl_lock(NFNL_SUBSYS_IPSET);
- set = nfnl_set(index);
+ set = nfnl_set(inst, index);
if (set)
__ip_set_get(set);
else
@@ -600,13 +687,17 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex);
* The nfnl mutex is used in the function.
*/
void
-ip_set_nfnl_put(ip_set_id_t index)
+ip_set_nfnl_put(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
+ struct ip_set_net *inst = ip_set_pernet(net);
+
nfnl_lock(NFNL_SUBSYS_IPSET);
- set = nfnl_set(index);
- if (set != NULL)
- __ip_set_put(set);
+ if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */
+ set = nfnl_set(inst, index);
+ if (set != NULL)
+ __ip_set_put(set);
+ }
nfnl_unlock(NFNL_SUBSYS_IPSET);
}
EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
@@ -664,14 +755,14 @@ static const struct nla_policy ip_set_create_policy[IPSET_ATTR_CMD_MAX + 1] = {
};
static struct ip_set *
-find_set_and_id(const char *name, ip_set_id_t *id)
+find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id)
{
struct ip_set *set = NULL;
ip_set_id_t i;
*id = IPSET_INVALID_ID;
- for (i = 0; i < ip_set_max; i++) {
- set = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = nfnl_set(inst, i);
if (set != NULL && STREQ(set->name, name)) {
*id = i;
break;
@@ -681,22 +772,23 @@ find_set_and_id(const char *name, ip_set_id_t *id)
}
static inline struct ip_set *
-find_set(const char *name)
+find_set(struct ip_set_net *inst, const char *name)
{
ip_set_id_t id;
- return find_set_and_id(name, &id);
+ return find_set_and_id(inst, name, &id);
}
static int
-find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set)
+find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index,
+ struct ip_set **set)
{
struct ip_set *s;
ip_set_id_t i;
*index = IPSET_INVALID_ID;
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = nfnl_set(inst, i);
if (s == NULL) {
if (*index == IPSET_INVALID_ID)
*index = i;
@@ -725,6 +817,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct net *net = sock_net(ctnl);
+ struct ip_set_net *inst = ip_set_pernet(net);
struct ip_set *set, *clash = NULL;
ip_set_id_t index = IPSET_INVALID_ID;
struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {};
@@ -783,7 +877,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
goto put_out;
}
- ret = set->type->create(set, tb, flags);
+ ret = set->type->create(net, set, tb, flags);
if (ret != 0)
goto put_out;
@@ -794,7 +888,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
* by the nfnl mutex. Find the first free index in ip_set_list
* and check clashing.
*/
- ret = find_free_id(set->name, &index, &clash);
+ ret = find_free_id(inst, set->name, &index, &clash);
if (ret == -EEXIST) {
/* If this is the same set and requested, ignore error */
if ((flags & IPSET_FLAG_EXIST) &&
@@ -807,9 +901,9 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
goto cleanup;
} else if (ret == -IPSET_ERR_MAX_SETS) {
struct ip_set **list, **tmp;
- ip_set_id_t i = ip_set_max + IP_SET_INC;
+ ip_set_id_t i = inst->ip_set_max + IP_SET_INC;
- if (i < ip_set_max || i == IPSET_INVALID_ID)
+ if (i < inst->ip_set_max || i == IPSET_INVALID_ID)
/* Wraparound */
goto cleanup;
@@ -817,14 +911,14 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
if (!list)
goto cleanup;
/* nfnl mutex is held, both lists are valid */
- tmp = nfnl_dereference(ip_set_list);
- memcpy(list, tmp, sizeof(struct ip_set *) * ip_set_max);
- rcu_assign_pointer(ip_set_list, list);
+ tmp = nfnl_dereference(inst->ip_set_list);
+ memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max);
+ rcu_assign_pointer(inst->ip_set_list, list);
/* Make sure all current packets have passed through */
synchronize_net();
/* Use new list */
- index = ip_set_max;
- ip_set_max = i;
+ index = inst->ip_set_max;
+ inst->ip_set_max = i;
kfree(tmp);
ret = 0;
} else if (ret)
@@ -834,7 +928,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
* Finally! Add our shiny new set to the list, and be done.
*/
pr_debug("create: '%s' created with index %u!\n", set->name, index);
- nfnl_set(index) = set;
+ nfnl_set(inst, index) = set;
return ret;
@@ -857,12 +951,12 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
};
static void
-ip_set_destroy_set(ip_set_id_t index)
+ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index)
{
- struct ip_set *set = nfnl_set(index);
+ struct ip_set *set = nfnl_set(inst, index);
pr_debug("set: %s\n", set->name);
- nfnl_set(index) = NULL;
+ nfnl_set(inst, index) = NULL;
/* Must call it without holding any lock */
set->variant->destroy(set);
@@ -875,6 +969,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *s;
ip_set_id_t i;
int ret = 0;
@@ -894,21 +989,22 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
*/
read_lock_bh(&ip_set_ref_lock);
if (!attr[IPSET_ATTR_SETNAME]) {
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = nfnl_set(inst, i);
if (s != NULL && s->ref) {
ret = -IPSET_ERR_BUSY;
goto out;
}
}
read_unlock_bh(&ip_set_ref_lock);
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = nfnl_set(inst, i);
if (s != NULL)
- ip_set_destroy_set(i);
+ ip_set_destroy_set(inst, i);
}
} else {
- s = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &i);
+ s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
+ &i);
if (s == NULL) {
ret = -ENOENT;
goto out;
@@ -918,7 +1014,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
}
read_unlock_bh(&ip_set_ref_lock);
- ip_set_destroy_set(i);
+ ip_set_destroy_set(inst, i);
}
return 0;
out:
@@ -943,6 +1039,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *s;
ip_set_id_t i;
@@ -950,13 +1047,13 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
return -IPSET_ERR_PROTOCOL;
if (!attr[IPSET_ATTR_SETNAME]) {
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = nfnl_set(inst, i);
if (s != NULL)
ip_set_flush_set(s);
}
} else {
- s = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ s = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (s == NULL)
return -ENOENT;
@@ -982,6 +1079,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set, *s;
const char *name2;
ip_set_id_t i;
@@ -992,7 +1090,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_SETNAME2] == NULL))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1003,8 +1101,8 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
}
name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = nfnl_set(inst, i);
if (s != NULL && STREQ(s->name, name2)) {
ret = -IPSET_ERR_EXIST_SETNAME2;
goto out;
@@ -1031,6 +1129,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *from, *to;
ip_set_id_t from_id, to_id;
char from_name[IPSET_MAXNAMELEN];
@@ -1040,11 +1139,13 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_SETNAME2] == NULL))
return -IPSET_ERR_PROTOCOL;
- from = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &from_id);
+ from = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
+ &from_id);
if (from == NULL)
return -ENOENT;
- to = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME2]), &to_id);
+ to = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME2]),
+ &to_id);
if (to == NULL)
return -IPSET_ERR_EXIST_SETNAME2;
@@ -1061,8 +1162,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
write_lock_bh(&ip_set_ref_lock);
swap(from->ref, to->ref);
- nfnl_set(from_id) = to;
- nfnl_set(to_id) = from;
+ nfnl_set(inst, from_id) = to;
+ nfnl_set(inst, to_id) = from;
write_unlock_bh(&ip_set_ref_lock);
return 0;
@@ -1081,9 +1182,10 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
static int
ip_set_dump_done(struct netlink_callback *cb)
{
+ struct ip_set_net *inst = (struct ip_set_net *)cb->data;
if (cb->args[2]) {
- pr_debug("release set %s\n", nfnl_set(cb->args[1])->name);
- ip_set_put_byindex((ip_set_id_t) cb->args[1]);
+ pr_debug("release set %s\n", nfnl_set(inst, cb->args[1])->name);
+ __ip_set_put_byindex(inst, (ip_set_id_t) cb->args[1]);
}
return 0;
}
@@ -1109,6 +1211,7 @@ dump_init(struct netlink_callback *cb)
struct nlattr *attr = (void *)nlh + min_len;
u32 dump_type;
ip_set_id_t index;
+ struct ip_set_net *inst = (struct ip_set_net *)cb->data;
/* Second pass, so parser can't fail */
nla_parse(cda, IPSET_ATTR_CMD_MAX,
@@ -1122,7 +1225,7 @@ dump_init(struct netlink_callback *cb)
if (cda[IPSET_ATTR_SETNAME]) {
struct ip_set *set;
- set = find_set_and_id(nla_data(cda[IPSET_ATTR_SETNAME]),
+ set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]),
&index);
if (set == NULL)
return -ENOENT;
@@ -1150,6 +1253,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0;
u32 dump_type, dump_flags;
int ret = 0;
+ struct ip_set_net *inst = (struct ip_set_net *)cb->data;
if (!cb->args[0]) {
ret = dump_init(cb);
@@ -1163,18 +1267,18 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
}
}
- if (cb->args[1] >= ip_set_max)
+ if (cb->args[1] >= inst->ip_set_max)
goto out;
dump_type = DUMP_TYPE(cb->args[0]);
dump_flags = DUMP_FLAGS(cb->args[0]);
- max = dump_type == DUMP_ONE ? cb->args[1] + 1 : ip_set_max;
+ max = dump_type == DUMP_ONE ? cb->args[1] + 1 : inst->ip_set_max;
dump_last:
pr_debug("args[0]: %u %u args[1]: %ld\n",
dump_type, dump_flags, cb->args[1]);
for (; cb->args[1] < max; cb->args[1]++) {
index = (ip_set_id_t) cb->args[1];
- set = nfnl_set(index);
+ set = nfnl_set(inst, index);
if (set == NULL) {
if (dump_type == DUMP_ONE) {
ret = -ENOENT;
@@ -1252,8 +1356,8 @@ next_set:
release_refcount:
/* If there was an error or set is done, release set */
if (ret || !cb->args[2]) {
- pr_debug("release set %s\n", nfnl_set(index)->name);
- ip_set_put_byindex(index);
+ pr_debug("release set %s\n", nfnl_set(inst, index)->name);
+ __ip_set_put_byindex(inst, index);
cb->args[2] = 0;
}
out:
@@ -1271,6 +1375,8 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
+
if (unlikely(protocol_failed(attr)))
return -IPSET_ERR_PROTOCOL;
@@ -1278,6 +1384,7 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
struct netlink_dump_control c = {
.dump = ip_set_dump_start,
.done = ip_set_dump_done,
+ .data = (void *)inst
};
return netlink_dump_start(ctnl, skb, nlh, &c);
}
@@ -1356,6 +1463,7 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
const struct nlattr *nla;
@@ -1374,7 +1482,7 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_LINENO] == NULL))))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1410,6 +1518,7 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
const struct nlattr *nla;
@@ -1428,7 +1537,7 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_LINENO] == NULL))))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1464,6 +1573,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
int ret = 0;
@@ -1474,7 +1584,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
!flag_nested(attr[IPSET_ATTR_DATA])))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1499,6 +1609,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
const struct ip_set *set;
struct sk_buff *skb2;
struct nlmsghdr *nlh2;
@@ -1508,7 +1619,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_SETNAME] == NULL))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1733,8 +1844,10 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
unsigned int *op;
void *data;
int copylen = *len, ret = 0;
+ struct net *net = sock_net(sk);
+ struct ip_set_net *inst = ip_set_pernet(net);
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (optval != SO_IP_SET)
return -EBADF;
@@ -1783,22 +1896,39 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
}
req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
nfnl_lock(NFNL_SUBSYS_IPSET);
- find_set_and_id(req_get->set.name, &id);
+ find_set_and_id(inst, req_get->set.name, &id);
req_get->set.index = id;
nfnl_unlock(NFNL_SUBSYS_IPSET);
goto copy;
}
+ case IP_SET_OP_GET_FNAME: {
+ struct ip_set_req_get_set_family *req_get = data;
+ ip_set_id_t id;
+
+ if (*len != sizeof(struct ip_set_req_get_set_family)) {
+ ret = -EINVAL;
+ goto done;
+ }
+ req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
+ nfnl_lock(NFNL_SUBSYS_IPSET);
+ find_set_and_id(inst, req_get->set.name, &id);
+ req_get->set.index = id;
+ if (id != IPSET_INVALID_ID)
+ req_get->family = nfnl_set(inst, id)->family;
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
+ goto copy;
+ }
case IP_SET_OP_GET_BYINDEX: {
struct ip_set_req_get_set *req_get = data;
struct ip_set *set;
if (*len != sizeof(struct ip_set_req_get_set) ||
- req_get->set.index >= ip_set_max) {
+ req_get->set.index >= inst->ip_set_max) {
ret = -EINVAL;
goto done;
}
nfnl_lock(NFNL_SUBSYS_IPSET);
- set = nfnl_set(req_get->set.index);
+ set = nfnl_set(inst, req_get->set.index);
strncpy(req_get->set.name, set ? set->name : "",
IPSET_MAXNAMELEN);
nfnl_unlock(NFNL_SUBSYS_IPSET);
@@ -1827,49 +1957,82 @@ static struct nf_sockopt_ops so_set __read_mostly = {
.owner = THIS_MODULE,
};
-static int __init
-ip_set_init(void)
+static int __net_init
+ip_set_net_init(struct net *net)
{
+ struct ip_set_net *inst = ip_set_pernet(net);
+
struct ip_set **list;
- int ret;
- if (max_sets)
- ip_set_max = max_sets;
- if (ip_set_max >= IPSET_INVALID_ID)
- ip_set_max = IPSET_INVALID_ID - 1;
+ inst->ip_set_max = max_sets ? max_sets : CONFIG_IP_SET_MAX;
+ if (inst->ip_set_max >= IPSET_INVALID_ID)
+ inst->ip_set_max = IPSET_INVALID_ID - 1;
- list = kzalloc(sizeof(struct ip_set *) * ip_set_max, GFP_KERNEL);
+ list = kzalloc(sizeof(struct ip_set *) * inst->ip_set_max, GFP_KERNEL);
if (!list)
return -ENOMEM;
+ inst->is_deleted = 0;
+ rcu_assign_pointer(inst->ip_set_list, list);
+ pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
+ return 0;
+}
+
+static void __net_exit
+ip_set_net_exit(struct net *net)
+{
+ struct ip_set_net *inst = ip_set_pernet(net);
+
+ struct ip_set *set = NULL;
+ ip_set_id_t i;
+
+ inst->is_deleted = 1; /* flag for ip_set_nfnl_put */
+
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = nfnl_set(inst, i);
+ if (set != NULL)
+ ip_set_destroy_set(inst, i);
+ }
+ kfree(rcu_dereference_protected(inst->ip_set_list, 1));
+}
+
+static struct pernet_operations ip_set_net_ops = {
+ .init = ip_set_net_init,
+ .exit = ip_set_net_exit,
+ .id = &ip_set_net_id,
+ .size = sizeof(struct ip_set_net)
+};
+
- rcu_assign_pointer(ip_set_list, list);
- ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+static int __init
+ip_set_init(void)
+{
+ int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
if (ret != 0) {
pr_err("ip_set: cannot register with nfnetlink.\n");
- kfree(list);
return ret;
}
ret = nf_register_sockopt(&so_set);
if (ret != 0) {
pr_err("SO_SET registry failed: %d\n", ret);
nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
- kfree(list);
return ret;
}
-
- pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
+ ret = register_pernet_subsys(&ip_set_net_ops);
+ if (ret) {
+ pr_err("ip_set: cannot register pernet_subsys.\n");
+ nf_unregister_sockopt(&so_set);
+ nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+ return ret;
+ }
return 0;
}
static void __exit
ip_set_fini(void)
{
- struct ip_set **list = rcu_dereference_protected(ip_set_list, 1);
-
- /* There can't be any existing set */
+ unregister_pernet_subsys(&ip_set_net_ops);
nf_unregister_sockopt(&so_set);
nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
- kfree(list);
pr_debug("these are the famous last words\n");
}
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
index dac156f819ac..29fb01ddff93 100644
--- a/net/netfilter/ipset/ip_set_getport.c
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -102,9 +102,25 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
int protocol = iph->protocol;
/* See comments at tcp_match in ip_tables.c */
- if (protocol <= 0 || (ntohs(iph->frag_off) & IP_OFFSET))
+ if (protocol <= 0)
return false;
+ if (ntohs(iph->frag_off) & IP_OFFSET)
+ switch (protocol) {
+ case IPPROTO_TCP:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDP:
+ case IPPROTO_UDPLITE:
+ case IPPROTO_ICMP:
+ /* Port info not available for fragment offset > 0 */
+ return false;
+ default:
+ /* Other protocols doesn't have ports,
+ so we can match fragments */
+ *proto = protocol;
+ return true;
+ }
+
return get_port(skb, protocol, protooff, src, port, proto);
}
EXPORT_SYMBOL_GPL(ip_set_get_ip4_port);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 707bc520d629..6a80dbd30df7 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -15,8 +15,7 @@
#define rcu_dereference_bh(p) rcu_dereference(p)
#endif
-#define CONCAT(a, b) a##b
-#define TOKEN(a, b) CONCAT(a, b)
+#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1)
/* Hashing which uses arrays to resolve clashing. The hash table is resized
* (doubled) when searching becomes too long.
@@ -78,10 +77,14 @@ struct htable {
#define hbucket(h, i) (&((h)->bucket[i]))
+#ifndef IPSET_NET_COUNT
+#define IPSET_NET_COUNT 1
+#endif
+
/* Book-keeping of the prefixes added to the set */
struct net_prefixes {
- u8 cidr; /* the different cidr values in the set */
- u32 nets; /* number of elements per cidr */
+ u32 nets[IPSET_NET_COUNT]; /* number of elements per cidr */
+ u8 cidr[IPSET_NET_COUNT]; /* the different cidr values in the set */
};
/* Compute the hash table size */
@@ -114,23 +117,6 @@ htable_bits(u32 hashsize)
return bits;
}
-/* Destroy the hashtable part of the set */
-static void
-ahash_destroy(struct htable *t)
-{
- struct hbucket *n;
- u32 i;
-
- for (i = 0; i < jhash_size(t->htable_bits); i++) {
- n = hbucket(t, i);
- if (n->size)
- /* FIXME: use slab cache */
- kfree(n->value);
- }
-
- ip_set_free(t);
-}
-
static int
hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
{
@@ -156,30 +142,30 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
}
#ifdef IP_SET_HASH_WITH_NETS
+#if IPSET_NET_COUNT > 1
+#define __CIDR(cidr, i) (cidr[i])
+#else
+#define __CIDR(cidr, i) (cidr)
+#endif
#ifdef IP_SET_HASH_WITH_NETS_PACKED
/* When cidr is packed with nomatch, cidr - 1 is stored in the entry */
-#define CIDR(cidr) (cidr + 1)
+#define CIDR(cidr, i) (__CIDR(cidr, i) + 1)
#else
-#define CIDR(cidr) (cidr)
+#define CIDR(cidr, i) (__CIDR(cidr, i))
#endif
#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128)
#ifdef IP_SET_HASH_WITH_MULTI
-#define NETS_LENGTH(family) (SET_HOST_MASK(family) + 1)
+#define NLEN(family) (SET_HOST_MASK(family) + 1)
#else
-#define NETS_LENGTH(family) SET_HOST_MASK(family)
+#define NLEN(family) SET_HOST_MASK(family)
#endif
#else
-#define NETS_LENGTH(family) 0
+#define NLEN(family) 0
#endif /* IP_SET_HASH_WITH_NETS */
-#define ext_timeout(e, h) \
-(unsigned long *)(((void *)(e)) + (h)->offset[IPSET_OFFSET_TIMEOUT])
-#define ext_counter(e, h) \
-(struct ip_set_counter *)(((void *)(e)) + (h)->offset[IPSET_OFFSET_COUNTER])
-
#endif /* _IP_SET_HASH_GEN_H */
/* Family dependent templates */
@@ -194,6 +180,8 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
#undef mtype_data_next
#undef mtype_elem
+#undef mtype_ahash_destroy
+#undef mtype_ext_cleanup
#undef mtype_add_cidr
#undef mtype_del_cidr
#undef mtype_ahash_memsize
@@ -220,41 +208,44 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
#undef HKEY
-#define mtype_data_equal TOKEN(MTYPE, _data_equal)
+#define mtype_data_equal IPSET_TOKEN(MTYPE, _data_equal)
#ifdef IP_SET_HASH_WITH_NETS
-#define mtype_do_data_match TOKEN(MTYPE, _do_data_match)
+#define mtype_do_data_match IPSET_TOKEN(MTYPE, _do_data_match)
#else
#define mtype_do_data_match(d) 1
#endif
-#define mtype_data_set_flags TOKEN(MTYPE, _data_set_flags)
-#define mtype_data_reset_flags TOKEN(MTYPE, _data_reset_flags)
-#define mtype_data_netmask TOKEN(MTYPE, _data_netmask)
-#define mtype_data_list TOKEN(MTYPE, _data_list)
-#define mtype_data_next TOKEN(MTYPE, _data_next)
-#define mtype_elem TOKEN(MTYPE, _elem)
-#define mtype_add_cidr TOKEN(MTYPE, _add_cidr)
-#define mtype_del_cidr TOKEN(MTYPE, _del_cidr)
-#define mtype_ahash_memsize TOKEN(MTYPE, _ahash_memsize)
-#define mtype_flush TOKEN(MTYPE, _flush)
-#define mtype_destroy TOKEN(MTYPE, _destroy)
-#define mtype_gc_init TOKEN(MTYPE, _gc_init)
-#define mtype_same_set TOKEN(MTYPE, _same_set)
-#define mtype_kadt TOKEN(MTYPE, _kadt)
-#define mtype_uadt TOKEN(MTYPE, _uadt)
+#define mtype_data_set_flags IPSET_TOKEN(MTYPE, _data_set_flags)
+#define mtype_data_reset_elem IPSET_TOKEN(MTYPE, _data_reset_elem)
+#define mtype_data_reset_flags IPSET_TOKEN(MTYPE, _data_reset_flags)
+#define mtype_data_netmask IPSET_TOKEN(MTYPE, _data_netmask)
+#define mtype_data_list IPSET_TOKEN(MTYPE, _data_list)
+#define mtype_data_next IPSET_TOKEN(MTYPE, _data_next)
+#define mtype_elem IPSET_TOKEN(MTYPE, _elem)
+#define mtype_ahash_destroy IPSET_TOKEN(MTYPE, _ahash_destroy)
+#define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup)
+#define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr)
+#define mtype_del_cidr IPSET_TOKEN(MTYPE, _del_cidr)
+#define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize)
+#define mtype_flush IPSET_TOKEN(MTYPE, _flush)
+#define mtype_destroy IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_same_set IPSET_TOKEN(MTYPE, _same_set)
+#define mtype_kadt IPSET_TOKEN(MTYPE, _kadt)
+#define mtype_uadt IPSET_TOKEN(MTYPE, _uadt)
#define mtype MTYPE
-#define mtype_elem TOKEN(MTYPE, _elem)
-#define mtype_add TOKEN(MTYPE, _add)
-#define mtype_del TOKEN(MTYPE, _del)
-#define mtype_test_cidrs TOKEN(MTYPE, _test_cidrs)
-#define mtype_test TOKEN(MTYPE, _test)
-#define mtype_expire TOKEN(MTYPE, _expire)
-#define mtype_resize TOKEN(MTYPE, _resize)
-#define mtype_head TOKEN(MTYPE, _head)
-#define mtype_list TOKEN(MTYPE, _list)
-#define mtype_gc TOKEN(MTYPE, _gc)
-#define mtype_variant TOKEN(MTYPE, _variant)
-#define mtype_data_match TOKEN(MTYPE, _data_match)
+#define mtype_elem IPSET_TOKEN(MTYPE, _elem)
+#define mtype_add IPSET_TOKEN(MTYPE, _add)
+#define mtype_del IPSET_TOKEN(MTYPE, _del)
+#define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs)
+#define mtype_test IPSET_TOKEN(MTYPE, _test)
+#define mtype_expire IPSET_TOKEN(MTYPE, _expire)
+#define mtype_resize IPSET_TOKEN(MTYPE, _resize)
+#define mtype_head IPSET_TOKEN(MTYPE, _head)
+#define mtype_list IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc IPSET_TOKEN(MTYPE, _gc)
+#define mtype_variant IPSET_TOKEN(MTYPE, _variant)
+#define mtype_data_match IPSET_TOKEN(MTYPE, _data_match)
#ifndef HKEY_DATALEN
#define HKEY_DATALEN sizeof(struct mtype_elem)
@@ -269,13 +260,10 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
/* The generic hash structure */
struct htype {
- struct htable *table; /* the hash table */
+ struct htable __rcu *table; /* the hash table */
u32 maxelem; /* max elements in the hash */
u32 elements; /* current element (vs timeout) */
u32 initval; /* random jhash init value */
- u32 timeout; /* timeout value, if enabled */
- size_t dsize; /* data struct size */
- size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
struct timer_list gc; /* garbage collection when timeout enabled */
struct mtype_elem next; /* temporary storage for uadd */
#ifdef IP_SET_HASH_WITH_MULTI
@@ -297,49 +285,49 @@ struct htype {
/* Network cidr size book keeping when the hash stores different
* sized networks */
static void
-mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length)
+mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
{
int i, j;
/* Add in increasing prefix order, so larger cidr first */
- for (i = 0, j = -1; i < nets_length && h->nets[i].nets; i++) {
+ for (i = 0, j = -1; i < nets_length && h->nets[i].nets[n]; i++) {
if (j != -1)
continue;
- else if (h->nets[i].cidr < cidr)
+ else if (h->nets[i].cidr[n] < cidr)
j = i;
- else if (h->nets[i].cidr == cidr) {
- h->nets[i].nets++;
+ else if (h->nets[i].cidr[n] == cidr) {
+ h->nets[i].nets[n]++;
return;
}
}
if (j != -1) {
for (; i > j; i--) {
- h->nets[i].cidr = h->nets[i - 1].cidr;
- h->nets[i].nets = h->nets[i - 1].nets;
+ h->nets[i].cidr[n] = h->nets[i - 1].cidr[n];
+ h->nets[i].nets[n] = h->nets[i - 1].nets[n];
}
}
- h->nets[i].cidr = cidr;
- h->nets[i].nets = 1;
+ h->nets[i].cidr[n] = cidr;
+ h->nets[i].nets[n] = 1;
}
static void
-mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length)
+mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
{
u8 i, j, net_end = nets_length - 1;
for (i = 0; i < nets_length; i++) {
- if (h->nets[i].cidr != cidr)
+ if (h->nets[i].cidr[n] != cidr)
continue;
- if (h->nets[i].nets > 1 || i == net_end ||
- h->nets[i + 1].nets == 0) {
- h->nets[i].nets--;
+ if (h->nets[i].nets[n] > 1 || i == net_end ||
+ h->nets[i + 1].nets[n] == 0) {
+ h->nets[i].nets[n]--;
return;
}
- for (j = i; j < net_end && h->nets[j].nets; j++) {
- h->nets[j].cidr = h->nets[j + 1].cidr;
- h->nets[j].nets = h->nets[j + 1].nets;
+ for (j = i; j < net_end && h->nets[j].nets[n]; j++) {
+ h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
+ h->nets[j].nets[n] = h->nets[j + 1].nets[n];
}
- h->nets[j].nets = 0;
+ h->nets[j].nets[n] = 0;
return;
}
}
@@ -347,10 +335,10 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length)
/* Calculate the actual memory size of the set data */
static size_t
-mtype_ahash_memsize(const struct htype *h, u8 nets_length)
+mtype_ahash_memsize(const struct htype *h, const struct htable *t,
+ u8 nets_length, size_t dsize)
{
u32 i;
- struct htable *t = h->table;
size_t memsize = sizeof(*h)
+ sizeof(*t)
#ifdef IP_SET_HASH_WITH_NETS
@@ -359,35 +347,70 @@ mtype_ahash_memsize(const struct htype *h, u8 nets_length)
+ jhash_size(t->htable_bits) * sizeof(struct hbucket);
for (i = 0; i < jhash_size(t->htable_bits); i++)
- memsize += t->bucket[i].size * h->dsize;
+ memsize += t->bucket[i].size * dsize;
return memsize;
}
+/* Get the ith element from the array block n */
+#define ahash_data(n, i, dsize) \
+ ((struct mtype_elem *)((n)->value + ((i) * (dsize))))
+
+static void
+mtype_ext_cleanup(struct ip_set *set, struct hbucket *n)
+{
+ int i;
+
+ for (i = 0; i < n->pos; i++)
+ ip_set_ext_destroy(set, ahash_data(n, i, set->dsize));
+}
+
/* Flush a hash type of set: destroy all elements */
static void
mtype_flush(struct ip_set *set)
{
struct htype *h = set->data;
- struct htable *t = h->table;
+ struct htable *t;
struct hbucket *n;
u32 i;
+ t = rcu_dereference_bh_nfnl(h->table);
for (i = 0; i < jhash_size(t->htable_bits); i++) {
n = hbucket(t, i);
if (n->size) {
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set, n);
n->size = n->pos = 0;
/* FIXME: use slab cache */
kfree(n->value);
}
}
#ifdef IP_SET_HASH_WITH_NETS
- memset(h->nets, 0, sizeof(struct net_prefixes)
- * NETS_LENGTH(set->family));
+ memset(h->nets, 0, sizeof(struct net_prefixes) * NLEN(set->family));
#endif
h->elements = 0;
}
+/* Destroy the hashtable part of the set */
+static void
+mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
+{
+ struct hbucket *n;
+ u32 i;
+
+ for (i = 0; i < jhash_size(t->htable_bits); i++) {
+ n = hbucket(t, i);
+ if (n->size) {
+ if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
+ mtype_ext_cleanup(set, n);
+ /* FIXME: use slab cache */
+ kfree(n->value);
+ }
+ }
+
+ ip_set_free(t);
+}
+
/* Destroy a hash type of set */
static void
mtype_destroy(struct ip_set *set)
@@ -397,7 +420,7 @@ mtype_destroy(struct ip_set *set)
if (set->extensions & IPSET_EXT_TIMEOUT)
del_timer_sync(&h->gc);
- ahash_destroy(h->table);
+ mtype_ahash_destroy(set, rcu_dereference_bh_nfnl(h->table), true);
#ifdef IP_SET_HASH_WITH_RBTREE
rbtree_destroy(&h->rbtree);
#endif
@@ -414,10 +437,10 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
init_timer(&h->gc);
h->gc.data = (unsigned long) set;
h->gc.function = gc;
- h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
+ h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&h->gc);
pr_debug("gc initialized, run in every %u\n",
- IPSET_GC_PERIOD(h->timeout));
+ IPSET_GC_PERIOD(set->timeout));
}
static bool
@@ -428,37 +451,40 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
/* Resizing changes htable_bits, so we ignore it */
return x->maxelem == y->maxelem &&
- x->timeout == y->timeout &&
+ a->timeout == b->timeout &&
#ifdef IP_SET_HASH_WITH_NETMASK
x->netmask == y->netmask &&
#endif
a->extensions == b->extensions;
}
-/* Get the ith element from the array block n */
-#define ahash_data(n, i, dsize) \
- ((struct mtype_elem *)((n)->value + ((i) * (dsize))))
-
/* Delete expired elements from the hashtable */
static void
-mtype_expire(struct htype *h, u8 nets_length, size_t dsize)
+mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
{
- struct htable *t = h->table;
+ struct htable *t;
struct hbucket *n;
struct mtype_elem *data;
u32 i;
int j;
+#ifdef IP_SET_HASH_WITH_NETS
+ u8 k;
+#endif
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
for (i = 0; i < jhash_size(t->htable_bits); i++) {
n = hbucket(t, i);
for (j = 0; j < n->pos; j++) {
data = ahash_data(n, j, dsize);
- if (ip_set_timeout_expired(ext_timeout(data, h))) {
+ if (ip_set_timeout_expired(ext_timeout(data, set))) {
pr_debug("expired %u/%u\n", i, j);
#ifdef IP_SET_HASH_WITH_NETS
- mtype_del_cidr(h, CIDR(data->cidr),
- nets_length);
+ for (k = 0; k < IPSET_NET_COUNT; k++)
+ mtype_del_cidr(h, CIDR(data->cidr, k),
+ nets_length, k);
#endif
+ ip_set_ext_destroy(set, data);
if (j != n->pos - 1)
/* Not last one */
memcpy(data,
@@ -481,6 +507,7 @@ mtype_expire(struct htype *h, u8 nets_length, size_t dsize)
n->value = tmp;
}
}
+ rcu_read_unlock_bh();
}
static void
@@ -491,10 +518,10 @@ mtype_gc(unsigned long ul_set)
pr_debug("called\n");
write_lock_bh(&set->lock);
- mtype_expire(h, NETS_LENGTH(set->family), h->dsize);
+ mtype_expire(set, h, NLEN(set->family), set->dsize);
write_unlock_bh(&set->lock);
- h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
+ h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&h->gc);
}
@@ -505,7 +532,7 @@ static int
mtype_resize(struct ip_set *set, bool retried)
{
struct htype *h = set->data;
- struct htable *t, *orig = h->table;
+ struct htable *t, *orig = rcu_dereference_bh_nfnl(h->table);
u8 htable_bits = orig->htable_bits;
#ifdef IP_SET_HASH_WITH_NETS
u8 flags;
@@ -520,8 +547,7 @@ mtype_resize(struct ip_set *set, bool retried)
if (SET_WITH_TIMEOUT(set) && !retried) {
i = h->elements;
write_lock_bh(&set->lock);
- mtype_expire(set->data, NETS_LENGTH(set->family),
- h->dsize);
+ mtype_expire(set, set->data, NLEN(set->family), set->dsize);
write_unlock_bh(&set->lock);
if (h->elements < i)
return 0;
@@ -548,25 +574,25 @@ retry:
for (i = 0; i < jhash_size(orig->htable_bits); i++) {
n = hbucket(orig, i);
for (j = 0; j < n->pos; j++) {
- data = ahash_data(n, j, h->dsize);
+ data = ahash_data(n, j, set->dsize);
#ifdef IP_SET_HASH_WITH_NETS
flags = 0;
mtype_data_reset_flags(data, &flags);
#endif
m = hbucket(t, HKEY(data, h->initval, htable_bits));
- ret = hbucket_elem_add(m, AHASH_MAX(h), h->dsize);
+ ret = hbucket_elem_add(m, AHASH_MAX(h), set->dsize);
if (ret < 0) {
#ifdef IP_SET_HASH_WITH_NETS
mtype_data_reset_flags(data, &flags);
#endif
read_unlock_bh(&set->lock);
- ahash_destroy(t);
+ mtype_ahash_destroy(set, t, false);
if (ret == -EAGAIN)
goto retry;
return ret;
}
- d = ahash_data(m, m->pos++, h->dsize);
- memcpy(d, data, h->dsize);
+ d = ahash_data(m, m->pos++, set->dsize);
+ memcpy(d, data, set->dsize);
#ifdef IP_SET_HASH_WITH_NETS
mtype_data_reset_flags(d, &flags);
#endif
@@ -581,7 +607,7 @@ retry:
pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
orig->htable_bits, orig, t->htable_bits, t);
- ahash_destroy(orig);
+ mtype_ahash_destroy(set, orig, false);
return 0;
}
@@ -604,7 +630,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
/* FIXME: when set is full, we slow down here */
- mtype_expire(h, NETS_LENGTH(set->family), h->dsize);
+ mtype_expire(set, h, NLEN(set->family), set->dsize);
if (h->elements >= h->maxelem) {
if (net_ratelimit())
@@ -618,11 +644,11 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
key = HKEY(value, h->initval, t->htable_bits);
n = hbucket(t, key);
for (i = 0; i < n->pos; i++) {
- data = ahash_data(n, i, h->dsize);
+ data = ahash_data(n, i, set->dsize);
if (mtype_data_equal(data, d, &multi)) {
if (flag_exist ||
(SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, h)))) {
+ ip_set_timeout_expired(ext_timeout(data, set)))) {
/* Just the extensions could be overwritten */
j = i;
goto reuse_slot;
@@ -633,30 +659,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
}
/* Reuse first timed out entry */
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, h)) &&
+ ip_set_timeout_expired(ext_timeout(data, set)) &&
j != AHASH_MAX(h) + 1)
j = i;
}
reuse_slot:
if (j != AHASH_MAX(h) + 1) {
/* Fill out reused slot */
- data = ahash_data(n, j, h->dsize);
+ data = ahash_data(n, j, set->dsize);
#ifdef IP_SET_HASH_WITH_NETS
- mtype_del_cidr(h, CIDR(data->cidr), NETS_LENGTH(set->family));
- mtype_add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family));
+ for (i = 0; i < IPSET_NET_COUNT; i++) {
+ mtype_del_cidr(h, CIDR(data->cidr, i),
+ NLEN(set->family), i);
+ mtype_add_cidr(h, CIDR(d->cidr, i),
+ NLEN(set->family), i);
+ }
#endif
+ ip_set_ext_destroy(set, data);
} else {
/* Use/create a new slot */
TUNE_AHASH_MAX(h, multi);
- ret = hbucket_elem_add(n, AHASH_MAX(h), h->dsize);
+ ret = hbucket_elem_add(n, AHASH_MAX(h), set->dsize);
if (ret != 0) {
if (ret == -EAGAIN)
mtype_data_next(&h->next, d);
goto out;
}
- data = ahash_data(n, n->pos++, h->dsize);
+ data = ahash_data(n, n->pos++, set->dsize);
#ifdef IP_SET_HASH_WITH_NETS
- mtype_add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family));
+ for (i = 0; i < IPSET_NET_COUNT; i++)
+ mtype_add_cidr(h, CIDR(d->cidr, i), NLEN(set->family),
+ i);
#endif
h->elements++;
}
@@ -665,9 +698,11 @@ reuse_slot:
mtype_data_set_flags(data, flags);
#endif
if (SET_WITH_TIMEOUT(set))
- ip_set_timeout_set(ext_timeout(data, h), ext->timeout);
+ ip_set_timeout_set(ext_timeout(data, set), ext->timeout);
if (SET_WITH_COUNTER(set))
- ip_set_init_counter(ext_counter(data, h), ext);
+ ip_set_init_counter(ext_counter(data, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(data, set), ext);
out:
rcu_read_unlock_bh();
@@ -682,47 +717,60 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
struct ip_set_ext *mext, u32 flags)
{
struct htype *h = set->data;
- struct htable *t = h->table;
+ struct htable *t;
const struct mtype_elem *d = value;
struct mtype_elem *data;
struct hbucket *n;
- int i;
+ int i, ret = -IPSET_ERR_EXIST;
+#ifdef IP_SET_HASH_WITH_NETS
+ u8 j;
+#endif
u32 key, multi = 0;
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
key = HKEY(value, h->initval, t->htable_bits);
n = hbucket(t, key);
for (i = 0; i < n->pos; i++) {
- data = ahash_data(n, i, h->dsize);
+ data = ahash_data(n, i, set->dsize);
if (!mtype_data_equal(data, d, &multi))
continue;
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, h)))
- return -IPSET_ERR_EXIST;
+ ip_set_timeout_expired(ext_timeout(data, set)))
+ goto out;
if (i != n->pos - 1)
/* Not last one */
- memcpy(data, ahash_data(n, n->pos - 1, h->dsize),
- h->dsize);
+ memcpy(data, ahash_data(n, n->pos - 1, set->dsize),
+ set->dsize);
n->pos--;
h->elements--;
#ifdef IP_SET_HASH_WITH_NETS
- mtype_del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family));
+ for (j = 0; j < IPSET_NET_COUNT; j++)
+ mtype_del_cidr(h, CIDR(d->cidr, j), NLEN(set->family),
+ j);
#endif
+ ip_set_ext_destroy(set, data);
if (n->pos + AHASH_INIT_SIZE < n->size) {
void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
- * h->dsize,
+ * set->dsize,
GFP_ATOMIC);
- if (!tmp)
- return 0;
+ if (!tmp) {
+ ret = 0;
+ goto out;
+ }
n->size -= AHASH_INIT_SIZE;
- memcpy(tmp, n->value, n->size * h->dsize);
+ memcpy(tmp, n->value, n->size * set->dsize);
kfree(n->value);
n->value = tmp;
}
- return 0;
+ ret = 0;
+ goto out;
}
- return -IPSET_ERR_EXIST;
+out:
+ rcu_read_unlock_bh();
+ return ret;
}
static inline int
@@ -730,8 +778,7 @@ mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext,
struct ip_set_ext *mext, struct ip_set *set, u32 flags)
{
if (SET_WITH_COUNTER(set))
- ip_set_update_counter(ext_counter(data,
- (struct htype *)(set->data)),
+ ip_set_update_counter(ext_counter(data, set),
ext, mext, flags);
return mtype_do_data_match(data);
}
@@ -745,25 +792,38 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
struct ip_set_ext *mext, u32 flags)
{
struct htype *h = set->data;
- struct htable *t = h->table;
+ struct htable *t = rcu_dereference_bh(h->table);
struct hbucket *n;
struct mtype_elem *data;
+#if IPSET_NET_COUNT == 2
+ struct mtype_elem orig = *d;
+ int i, j = 0, k;
+#else
int i, j = 0;
+#endif
u32 key, multi = 0;
- u8 nets_length = NETS_LENGTH(set->family);
+ u8 nets_length = NLEN(set->family);
pr_debug("test by nets\n");
- for (; j < nets_length && h->nets[j].nets && !multi; j++) {
- mtype_data_netmask(d, h->nets[j].cidr);
+ for (; j < nets_length && h->nets[j].nets[0] && !multi; j++) {
+#if IPSET_NET_COUNT == 2
+ mtype_data_reset_elem(d, &orig);
+ mtype_data_netmask(d, h->nets[j].cidr[0], false);
+ for (k = 0; k < nets_length && h->nets[k].nets[1] && !multi;
+ k++) {
+ mtype_data_netmask(d, h->nets[k].cidr[1], true);
+#else
+ mtype_data_netmask(d, h->nets[j].cidr[0]);
+#endif
key = HKEY(d, h->initval, t->htable_bits);
n = hbucket(t, key);
for (i = 0; i < n->pos; i++) {
- data = ahash_data(n, i, h->dsize);
+ data = ahash_data(n, i, set->dsize);
if (!mtype_data_equal(data, d, &multi))
continue;
if (SET_WITH_TIMEOUT(set)) {
if (!ip_set_timeout_expired(
- ext_timeout(data, h)))
+ ext_timeout(data, set)))
return mtype_data_match(data, ext,
mext, set,
flags);
@@ -774,6 +834,9 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
return mtype_data_match(data, ext,
mext, set, flags);
}
+#if IPSET_NET_COUNT == 2
+ }
+#endif
}
return 0;
}
@@ -785,30 +848,41 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
struct ip_set_ext *mext, u32 flags)
{
struct htype *h = set->data;
- struct htable *t = h->table;
+ struct htable *t;
struct mtype_elem *d = value;
struct hbucket *n;
struct mtype_elem *data;
- int i;
+ int i, ret = 0;
u32 key, multi = 0;
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
#ifdef IP_SET_HASH_WITH_NETS
/* If we test an IP address and not a network address,
* try all possible network sizes */
- if (CIDR(d->cidr) == SET_HOST_MASK(set->family))
- return mtype_test_cidrs(set, d, ext, mext, flags);
+ for (i = 0; i < IPSET_NET_COUNT; i++)
+ if (CIDR(d->cidr, i) != SET_HOST_MASK(set->family))
+ break;
+ if (i == IPSET_NET_COUNT) {
+ ret = mtype_test_cidrs(set, d, ext, mext, flags);
+ goto out;
+ }
#endif
key = HKEY(d, h->initval, t->htable_bits);
n = hbucket(t, key);
for (i = 0; i < n->pos; i++) {
- data = ahash_data(n, i, h->dsize);
+ data = ahash_data(n, i, set->dsize);
if (mtype_data_equal(data, d, &multi) &&
!(SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(data, h))))
- return mtype_data_match(data, ext, mext, set, flags);
+ ip_set_timeout_expired(ext_timeout(data, set)))) {
+ ret = mtype_data_match(data, ext, mext, set, flags);
+ goto out;
+ }
}
- return 0;
+out:
+ rcu_read_unlock_bh();
+ return ret;
}
/* Reply a HEADER request: fill out the header part of the set */
@@ -816,18 +890,18 @@ static int
mtype_head(struct ip_set *set, struct sk_buff *skb)
{
const struct htype *h = set->data;
+ const struct htable *t;
struct nlattr *nested;
size_t memsize;
- read_lock_bh(&set->lock);
- memsize = mtype_ahash_memsize(h, NETS_LENGTH(set->family));
- read_unlock_bh(&set->lock);
+ t = rcu_dereference_bh_nfnl(h->table);
+ memsize = mtype_ahash_memsize(h, t, NLEN(set->family), set->dsize);
nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
if (!nested)
goto nla_put_failure;
if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE,
- htonl(jhash_size(h->table->htable_bits))) ||
+ htonl(jhash_size(t->htable_bits))) ||
nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem)))
goto nla_put_failure;
#ifdef IP_SET_HASH_WITH_NETMASK
@@ -836,12 +910,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
goto nla_put_failure;
#endif
if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
- ((set->extensions & IPSET_EXT_TIMEOUT) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout))) ||
- ((set->extensions & IPSET_EXT_COUNTER) &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS,
- htonl(IPSET_FLAG_WITH_COUNTERS))))
+ nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)))
+ goto nla_put_failure;
+ if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
ipset_nest_end(skb, nested);
@@ -856,7 +927,7 @@ mtype_list(const struct ip_set *set,
struct sk_buff *skb, struct netlink_callback *cb)
{
const struct htype *h = set->data;
- const struct htable *t = h->table;
+ const struct htable *t = rcu_dereference_bh_nfnl(h->table);
struct nlattr *atd, *nested;
const struct hbucket *n;
const struct mtype_elem *e;
@@ -874,9 +945,9 @@ mtype_list(const struct ip_set *set,
n = hbucket(t, cb->args[2]);
pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n);
for (i = 0; i < n->pos; i++) {
- e = ahash_data(n, i, h->dsize);
+ e = ahash_data(n, i, set->dsize);
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, h)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
pr_debug("list hash %lu hbucket %p i %u, data %p\n",
cb->args[2], n, i, e);
@@ -890,13 +961,7 @@ mtype_list(const struct ip_set *set,
}
if (mtype_data_list(skb, e))
goto nla_put_failure;
- if (SET_WITH_TIMEOUT(set) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(
- ext_timeout(e, h)))))
- goto nla_put_failure;
- if (SET_WITH_COUNTER(set) &&
- ip_set_put_counter(skb, ext_counter(e, h)))
+ if (ip_set_put_extensions(skb, set, e, true))
goto nla_put_failure;
ipset_nest_end(skb, nested);
}
@@ -909,24 +974,24 @@ mtype_list(const struct ip_set *set,
nla_put_failure:
nlmsg_trim(skb, incomplete);
- ipset_nest_end(skb, atd);
if (unlikely(first == cb->args[2])) {
pr_warning("Can't list set %s: one bucket does not fit into "
"a message. Please report it!\n", set->name);
cb->args[2] = 0;
return -EMSGSIZE;
}
+ ipset_nest_end(skb, atd);
return 0;
}
static int
-TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb,
- const struct xt_action_param *par,
- enum ipset_adt adt, struct ip_set_adt_opt *opt);
+IPSET_TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt);
static int
-TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[],
- enum ipset_adt adt, u32 *lineno, u32 flags, bool retried);
+IPSET_TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried);
static const struct ip_set_type_variant mtype_variant = {
.kadt = mtype_kadt,
@@ -946,16 +1011,17 @@ static const struct ip_set_type_variant mtype_variant = {
#ifdef IP_SET_EMIT_CREATE
static int
-TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
+IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
+ struct nlattr *tb[], u32 flags)
{
u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u32 cadt_flags = 0;
u8 hbits;
#ifdef IP_SET_HASH_WITH_NETMASK
u8 netmask;
#endif
size_t hsize;
struct HTYPE *h;
+ struct htable *t;
if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
return -IPSET_ERR_INVALID_FAMILY;
@@ -1005,7 +1071,7 @@ TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
h->netmask = netmask;
#endif
get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
+ set->timeout = IPSET_NO_TIMEOUT;
hbits = htable_bits(hashsize);
hsize = htable_size(hbits);
@@ -1013,91 +1079,37 @@ TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
kfree(h);
return -ENOMEM;
}
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
+ t = ip_set_alloc(hsize);
+ if (!t) {
kfree(h);
return -ENOMEM;
}
- h->table->htable_bits = hbits;
+ t->htable_bits = hbits;
+ rcu_assign_pointer(h->table, t);
set->data = h;
- if (set->family == NFPROTO_IPV4)
- set->variant = &TOKEN(HTYPE, 4_variant);
- else
- set->variant = &TOKEN(HTYPE, 6_variant);
-
- if (tb[IPSET_ATTR_CADT_FLAGS])
- cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
- if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
- set->extensions |= IPSET_EXT_COUNTER;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout =
- ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
- if (set->family == NFPROTO_IPV4) {
- h->dsize =
- sizeof(struct TOKEN(HTYPE, 4ct_elem));
- h->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct TOKEN(HTYPE, 4ct_elem),
- timeout);
- h->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct TOKEN(HTYPE, 4ct_elem),
- counter);
- TOKEN(HTYPE, 4_gc_init)(set,
- TOKEN(HTYPE, 4_gc));
- } else {
- h->dsize =
- sizeof(struct TOKEN(HTYPE, 6ct_elem));
- h->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct TOKEN(HTYPE, 6ct_elem),
- timeout);
- h->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct TOKEN(HTYPE, 6ct_elem),
- counter);
- TOKEN(HTYPE, 6_gc_init)(set,
- TOKEN(HTYPE, 6_gc));
- }
- } else {
- if (set->family == NFPROTO_IPV4) {
- h->dsize =
- sizeof(struct TOKEN(HTYPE, 4c_elem));
- h->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct TOKEN(HTYPE, 4c_elem),
- counter);
- } else {
- h->dsize =
- sizeof(struct TOKEN(HTYPE, 6c_elem));
- h->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct TOKEN(HTYPE, 6c_elem),
- counter);
- }
- }
- } else if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->extensions |= IPSET_EXT_TIMEOUT;
- if (set->family == NFPROTO_IPV4) {
- h->dsize = sizeof(struct TOKEN(HTYPE, 4t_elem));
- h->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct TOKEN(HTYPE, 4t_elem),
- timeout);
- TOKEN(HTYPE, 4_gc_init)(set, TOKEN(HTYPE, 4_gc));
- } else {
- h->dsize = sizeof(struct TOKEN(HTYPE, 6t_elem));
- h->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct TOKEN(HTYPE, 6t_elem),
- timeout);
- TOKEN(HTYPE, 6_gc_init)(set, TOKEN(HTYPE, 6_gc));
- }
+ if (set->family == NFPROTO_IPV4) {
+ set->variant = &IPSET_TOKEN(HTYPE, 4_variant);
+ set->dsize = ip_set_elem_len(set, tb,
+ sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)));
} else {
+ set->variant = &IPSET_TOKEN(HTYPE, 6_variant);
+ set->dsize = ip_set_elem_len(set, tb,
+ sizeof(struct IPSET_TOKEN(HTYPE, 6_elem)));
+ }
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
if (set->family == NFPROTO_IPV4)
- h->dsize = sizeof(struct TOKEN(HTYPE, 4_elem));
+ IPSET_TOKEN(HTYPE, 4_gc_init)(set,
+ IPSET_TOKEN(HTYPE, 4_gc));
else
- h->dsize = sizeof(struct TOKEN(HTYPE, 6_elem));
+ IPSET_TOKEN(HTYPE, 6_gc_init)(set,
+ IPSET_TOKEN(HTYPE, 6_gc));
}
pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
+ set->name, jhash_size(t->htable_bits),
+ t->htable_bits, h->maxelem, set->data, t);
return 0;
}
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index c74e6e14cd93..e65fc2423d56 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -23,19 +23,20 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* Counters support */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counters support */
+#define IPSET_TYPE_REV_MAX 2 /* Comments support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip");
/* Type specific function prefix */
#define HTYPE hash_ip
#define IP_SET_HASH_WITH_NETMASK
-/* IPv4 variants */
+/* IPv4 variant */
/* Member elements */
struct hash_ip4_elem {
@@ -43,22 +44,6 @@ struct hash_ip4_elem {
__be32 ip;
};
-struct hash_ip4t_elem {
- __be32 ip;
- unsigned long timeout;
-};
-
-struct hash_ip4c_elem {
- __be32 ip;
- struct ip_set_counter counter;
-};
-
-struct hash_ip4ct_elem {
- __be32 ip;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -99,7 +84,7 @@ hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
__be32 ip;
ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip);
@@ -118,8 +103,8 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 ip, ip_to, hosts;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, hosts;
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -178,29 +163,13 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
/* Member elements */
struct hash_ip6_elem {
union nf_inet_addr ip;
};
-struct hash_ip6t_elem {
- union nf_inet_addr ip;
- unsigned long timeout;
-};
-
-struct hash_ip6c_elem {
- union nf_inet_addr ip;
- struct ip_set_counter counter;
-};
-
-struct hash_ip6ct_elem {
- union nf_inet_addr ip;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -253,7 +222,7 @@ hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip6_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
hash_ip6_netmask(&e.ip, h->netmask);
@@ -270,7 +239,7 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip6_elem e = {};
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -304,8 +273,8 @@ static struct ip_set_type hash_ip_type __read_mostly = {
.features = IPSET_TYPE_IP,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -324,6 +293,7 @@ static struct ip_set_type hash_ip_type __read_mostly = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 7a2d2bd98d04..525a595dd1fe 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -24,19 +24,20 @@
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 SCTP and UDPLITE support added */
-#define REVISION_MAX 2 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Counters support added */
+#define IPSET_TYPE_REV_MAX 3 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip,port");
/* Type specific function prefix */
#define HTYPE hash_ipport
-/* IPv4 variants */
+/* IPv4 variant */
/* Member elements */
struct hash_ipport4_elem {
@@ -46,31 +47,6 @@ struct hash_ipport4_elem {
u8 padding;
};
-struct hash_ipport4t_elem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
-
-struct hash_ipport4c_elem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
-};
-
-struct hash_ipport4ct_elem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -116,10 +92,9 @@ hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
&e.port, &e.proto))
@@ -136,8 +111,8 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ipport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 ip, ip_to, p = 0, port, port_to;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip, ip_to = 0, p = 0, port, port_to;
bool with_ports = false;
int ret;
@@ -222,7 +197,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
struct hash_ipport6_elem {
union nf_inet_addr ip;
@@ -231,31 +206,6 @@ struct hash_ipport6_elem {
u8 padding;
};
-struct hash_ipport6t_elem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
-
-struct hash_ipport6c_elem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
-};
-
-struct hash_ipport6ct_elem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -306,10 +256,9 @@ hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport6_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
&e.port, &e.proto))
@@ -326,7 +275,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ipport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport6_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
bool with_ports = false;
int ret;
@@ -396,8 +345,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
.features = IPSET_TYPE_IP | IPSET_TYPE_PORT,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ipport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -419,6 +368,7 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 34e8a1acce42..f5636631466e 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -24,19 +24,20 @@
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 SCTP and UDPLITE support added */
-#define REVISION_MAX 2 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Counters support added */
+#define IPSET_TYPE_REV_MAX 3 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port,ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port,ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip,port,ip");
/* Type specific function prefix */
#define HTYPE hash_ipportip
-/* IPv4 variants */
+/* IPv4 variant */
/* Member elements */
struct hash_ipportip4_elem {
@@ -47,34 +48,6 @@ struct hash_ipportip4_elem {
u8 padding;
};
-struct hash_ipportip4t_elem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
-
-struct hash_ipportip4c_elem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
-};
-
-struct hash_ipportip4ct_elem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
static inline bool
hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1,
const struct hash_ipportip4_elem *ip2,
@@ -120,10 +93,9 @@ hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipportip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
&e.port, &e.proto))
@@ -141,8 +113,8 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ipportip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 ip, ip_to, p = 0, port, port_to;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip, ip_to = 0, p = 0, port, port_to;
bool with_ports = false;
int ret;
@@ -231,7 +203,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
struct hash_ipportip6_elem {
union nf_inet_addr ip;
@@ -241,34 +213,6 @@ struct hash_ipportip6_elem {
u8 padding;
};
-struct hash_ipportip6t_elem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
-
-struct hash_ipportip6c_elem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
-};
-
-struct hash_ipportip6ct_elem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -319,10 +263,9 @@ hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipportip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip6_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
&e.port, &e.proto))
@@ -340,7 +283,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ipportip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip6_elem e = { };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
bool with_ports = false;
int ret;
@@ -414,8 +357,8 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
.features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2,
.dimension = IPSET_DIM_THREE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ipportip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -437,6 +380,7 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index f15f3e28b9c3..5d87fe8a41ff 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -24,15 +24,16 @@
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 SCTP and UDPLITE support added */
-/* 2 Range as input support for IPv4 added */
-/* 3 nomatch flag support added */
-#define REVISION_MAX 4 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Range as input support for IPv4 added */
+/* 3 nomatch flag support added */
+/* 4 Counters support added */
+#define IPSET_TYPE_REV_MAX 5 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port,net", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip,port,net");
/* Type specific function prefix */
@@ -46,7 +47,7 @@ MODULE_ALIAS("ip_set_hash:ip,port,net");
#define IP_SET_HASH_WITH_PROTO
#define IP_SET_HASH_WITH_NETS
-/* IPv4 variants */
+/* IPv4 variant */
/* Member elements */
struct hash_ipportnet4_elem {
@@ -58,37 +59,6 @@ struct hash_ipportnet4_elem {
u8 proto;
};
-struct hash_ipportnet4t_elem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- unsigned long timeout;
-};
-
-struct hash_ipportnet4c_elem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- struct ip_set_counter counter;
-};
-
-struct hash_ipportnet4ct_elem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -170,9 +140,9 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
e.cidr = HOST_MASK - 1;
@@ -195,9 +165,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 ip, ip_to, p = 0, port, port_to;
- u32 ip2_from, ip2_to, ip2_last, ip2;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, p = 0, port, port_to;
+ u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
bool with_ports = false;
u8 cidr;
int ret;
@@ -272,7 +242,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
if (ip > ip_to)
swap(ip, ip_to);
} else if (tb[IPSET_ATTR_CIDR]) {
- u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
if (!cidr || cidr > 32)
return -IPSET_ERR_INVALID_CIDR;
@@ -306,9 +276,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
: port;
for (; p <= port_to; p++) {
e.port = htons(p);
- ip2 = retried
- && ip == ntohl(h->next.ip)
- && p == ntohs(h->next.port)
+ ip2 = retried &&
+ ip == ntohl(h->next.ip) &&
+ p == ntohs(h->next.port)
? ntohl(h->next.ip2) : ip2_from;
while (!after(ip2, ip2_to)) {
e.ip2 = htonl(ip2);
@@ -328,7 +298,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
struct hash_ipportnet6_elem {
union nf_inet_addr ip;
@@ -339,37 +309,6 @@ struct hash_ipportnet6_elem {
u8 proto;
};
-struct hash_ipportnet6t_elem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- unsigned long timeout;
-};
-
-struct hash_ipportnet6c_elem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- struct ip_set_counter counter;
-};
-
-struct hash_ipportnet6ct_elem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -454,9 +393,9 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet6_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
e.cidr = HOST_MASK - 1;
@@ -479,7 +418,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet6_elem e = { .cidr = HOST_MASK - 1 };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
bool with_ports = false;
u8 cidr;
@@ -574,8 +513,8 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_THREE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ipportnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -600,6 +539,7 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 223e9f546d0f..8295cf4f9fdc 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -22,21 +22,22 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 Range as input support for IPv4 added */
-/* 2 nomatch flag support added */
-#define REVISION_MAX 3 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Range as input support for IPv4 added */
+/* 2 nomatch flag support added */
+/* 3 Counters support added */
+#define IPSET_TYPE_REV_MAX 4 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:net");
/* Type specific function prefix */
#define HTYPE hash_net
#define IP_SET_HASH_WITH_NETS
-/* IPv4 variants */
+/* IPv4 variant */
/* Member elements */
struct hash_net4_elem {
@@ -46,31 +47,6 @@ struct hash_net4_elem {
u8 cidr;
};
-struct hash_net4t_elem {
- __be32 ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- unsigned long timeout;
-};
-
-struct hash_net4c_elem {
- __be32 ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- struct ip_set_counter counter;
-};
-
-struct hash_net4ct_elem {
- __be32 ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -143,9 +119,9 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (e.cidr == 0)
return -EINVAL;
@@ -165,8 +141,8 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = { .cidr = HOST_MASK };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 ip = 0, ip_to, last;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, last;
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -228,7 +204,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
struct hash_net6_elem {
union nf_inet_addr ip;
@@ -237,31 +213,6 @@ struct hash_net6_elem {
u8 cidr;
};
-struct hash_net6t_elem {
- union nf_inet_addr ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- unsigned long timeout;
-};
-
-struct hash_net6c_elem {
- union nf_inet_addr ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- struct ip_set_counter counter;
-};
-
-struct hash_net6ct_elem {
- union nf_inet_addr ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -338,9 +289,9 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net6_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (e.cidr == 0)
return -EINVAL;
@@ -357,10 +308,9 @@ static int
hash_net6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net6_elem e = { .cidr = HOST_MASK };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -406,8 +356,8 @@ static struct ip_set_type hash_net_type __read_mostly = {
.features = IPSET_TYPE_IP | IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_net_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -425,6 +375,7 @@ static struct ip_set_type hash_net_type __read_mostly = {
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 7d798d5d5cd3..3f64a66bf5d9 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -23,14 +23,15 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 nomatch flag support added */
-/* 2 /0 support added */
-#define REVISION_MAX 3 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 nomatch flag support added */
+/* 2 /0 support added */
+/* 3 Counters support added */
+#define IPSET_TYPE_REV_MAX 4 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net,iface", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net,iface", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:net,iface");
/* Interface name rbtree */
@@ -134,7 +135,7 @@ iface_add(struct rb_root *root, const char **iface)
#define STREQ(a, b) (strcmp(a, b) == 0)
-/* IPv4 variants */
+/* IPv4 variant */
struct hash_netiface4_elem_hashed {
__be32 ip;
@@ -144,7 +145,7 @@ struct hash_netiface4_elem_hashed {
u8 elem;
};
-/* Member elements without timeout */
+/* Member elements */
struct hash_netiface4_elem {
__be32 ip;
u8 physdev;
@@ -154,37 +155,6 @@ struct hash_netiface4_elem {
const char *iface;
};
-struct hash_netiface4t_elem {
- __be32 ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- unsigned long timeout;
-};
-
-struct hash_netiface4c_elem {
- __be32 ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- struct ip_set_counter counter;
-};
-
-struct hash_netiface4ct_elem {
- __be32 ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -265,10 +235,10 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK,
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
.elem = 1,
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
int ret;
if (e.cidr == 0)
@@ -319,8 +289,8 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 ip = 0, ip_to, last;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, last;
char iface[IFNAMSIZ];
int ret;
@@ -399,7 +369,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
struct hash_netiface6_elem_hashed {
union nf_inet_addr ip;
@@ -418,37 +388,6 @@ struct hash_netiface6_elem {
const char *iface;
};
-struct hash_netiface6t_elem {
- union nf_inet_addr ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- unsigned long timeout;
-};
-
-struct hash_netiface6c_elem {
- union nf_inet_addr ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- struct ip_set_counter counter;
-};
-
-struct hash_netiface6ct_elem {
- union nf_inet_addr ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -534,10 +473,10 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface6_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK,
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
.elem = 1,
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
int ret;
if (e.cidr == 0)
@@ -584,7 +523,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface6_elem e = { .cidr = HOST_MASK, .elem = 1 };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
char iface[IFNAMSIZ];
int ret;
@@ -645,8 +584,8 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_netiface_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -668,6 +607,7 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
new file mode 100644
index 000000000000..426032706ca9
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -0,0 +1,483 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2013 Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:net type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+#define IPSET_TYPE_REV_MAX 0
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
+IP_SET_MODULE_DESC("hash:net,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:net,net");
+
+/* Type specific function prefix */
+#define HTYPE hash_netnet
+#define IP_SET_HASH_WITH_NETS
+#define IPSET_NET_COUNT 2
+
+/* IPv4 variants */
+
+/* Member elements */
+struct hash_netnet4_elem {
+ union {
+ __be32 ip[2];
+ __be64 ipcmp;
+ };
+ u8 nomatch;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+};
+
+/* Common functions */
+
+static inline bool
+hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1,
+ const struct hash_netnet4_elem *ip2,
+ u32 *multi)
+{
+ return ip1->ipcmp == ip2->ipcmp &&
+ ip2->ccmp == ip2->ccmp;
+}
+
+static inline int
+hash_netnet4_do_data_match(const struct hash_netnet4_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netnet4_data_set_flags(struct hash_netnet4_elem *elem, u32 flags)
+{
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
+}
+
+static inline void
+hash_netnet4_data_reset_flags(struct hash_netnet4_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netnet4_data_reset_elem(struct hash_netnet4_elem *elem,
+ struct hash_netnet4_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netnet4_data_netmask(struct hash_netnet4_elem *elem, u8 cidr, bool inner)
+{
+ if (inner) {
+ elem->ip[1] &= ip_set_netmask(cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ elem->ip[0] &= ip_set_netmask(cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netnet4_data_list(struct sk_buff *skb,
+ const struct hash_netnet4_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip[0]) ||
+ nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip[1]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_netnet4_data_next(struct hash_netnet4_elem *next,
+ const struct hash_netnet4_elem *d)
+{
+ next->ipcmp = d->ipcmp;
+}
+
+#define MTYPE hash_netnet4
+#define PF 4
+#define HOST_MASK 32
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet4_elem e = {
+ .cidr[0] = h->nets[0].cidr[0] ? h->nets[0].cidr[0] : HOST_MASK,
+ .cidr[1] = h->nets[0].cidr[1] ? h->nets[0].cidr[1] : HOST_MASK,
+ };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1]);
+ e.ip[0] &= ip_set_netmask(e.cidr[0]);
+ e.ip[1] &= ip_set_netmask(e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_netnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet4_elem e = { .cidr[0] = HOST_MASK,
+ .cidr[1] = HOST_MASK };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, last;
+ u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2;
+ u8 cidr, cidr2;
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR]) {
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (!cidr || cidr > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[0] = cidr;
+ }
+
+ if (tb[IPSET_ATTR_CIDR2]) {
+ cidr2 = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+ if (!cidr2 || cidr2 > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[1] = cidr2;
+ }
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] &&
+ tb[IPSET_ATTR_IP2_TO])) {
+ e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0]));
+ e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1]));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ip_to = ip;
+ if (tb[IPSET_ATTR_IP_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+ if (ret)
+ return ret;
+ if (ip_to < ip)
+ swap(ip, ip_to);
+ if (ip + UINT_MAX == ip_to)
+ return -IPSET_ERR_HASH_RANGE;
+ }
+
+ ip2_to = ip2_from;
+ if (tb[IPSET_ATTR_IP2_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
+ if (ret)
+ return ret;
+ if (ip2_to < ip2_from)
+ swap(ip2_from, ip2_to);
+ if (ip2_from + UINT_MAX == ip2_to)
+ return -IPSET_ERR_HASH_RANGE;
+
+ }
+
+ if (retried)
+ ip = ntohl(h->next.ip[0]);
+
+ while (!after(ip, ip_to)) {
+ e.ip[0] = htonl(ip);
+ last = ip_set_range_to_cidr(ip, ip_to, &cidr);
+ e.cidr[0] = cidr;
+ ip2 = (retried &&
+ ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1])
+ : ip2_from;
+ while (!after(ip2, ip2_to)) {
+ e.ip[1] = htonl(ip2);
+ last2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr2);
+ e.cidr[1] = cidr2;
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ ip2 = last2 + 1;
+ }
+ ip = last + 1;
+ }
+ return ret;
+}
+
+/* IPv6 variants */
+
+struct hash_netnet6_elem {
+ union nf_inet_addr ip[2];
+ u8 nomatch;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+};
+
+/* Common functions */
+
+static inline bool
+hash_netnet6_data_equal(const struct hash_netnet6_elem *ip1,
+ const struct hash_netnet6_elem *ip2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) &&
+ ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) &&
+ ip1->ccmp == ip2->ccmp;
+}
+
+static inline int
+hash_netnet6_do_data_match(const struct hash_netnet6_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netnet6_data_set_flags(struct hash_netnet6_elem *elem, u32 flags)
+{
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
+}
+
+static inline void
+hash_netnet6_data_reset_flags(struct hash_netnet6_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netnet6_data_reset_elem(struct hash_netnet6_elem *elem,
+ struct hash_netnet6_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netnet6_data_netmask(struct hash_netnet6_elem *elem, u8 cidr, bool inner)
+{
+ if (inner) {
+ ip6_netmask(&elem->ip[1], cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ ip6_netmask(&elem->ip[0], cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netnet6_data_list(struct sk_buff *skb,
+ const struct hash_netnet6_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip[0].in6) ||
+ nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip[1].in6) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_netnet6_data_next(struct hash_netnet4_elem *next,
+ const struct hash_netnet6_elem *d)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+
+#define MTYPE hash_netnet6
+#define PF 6
+#define HOST_MASK 128
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet6_elem e = {
+ .cidr[0] = h->nets[0].cidr[0] ? h->nets[0].cidr[0] : HOST_MASK,
+ .cidr[1] = h->nets[0].cidr[1] ? h->nets[0].cidr[1] : HOST_MASK
+ };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(u8)*8)) | HOST_MASK;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1].in6);
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet6_elem e = { .cidr[0] = HOST_MASK,
+ .cidr[1] = HOST_MASK };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+ if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO]))
+ return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) ||
+ ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR])
+ e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+ if (tb[IPSET_ATTR_CIDR2])
+ e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+
+ if (!e.cidr[0] || e.cidr[0] > HOST_MASK || !e.cidr[1] ||
+ e.cidr[1] > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ ret = adtfn(set, &e, &ext, &ext, flags);
+
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+}
+
+static struct ip_set_type hash_netnet_type __read_mostly = {
+ .name = "hash:net,net",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_IP2 | IPSET_TYPE_NOMATCH,
+ .dimension = IPSET_DIM_TWO,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_netnet_create,
+ .create_policy = {
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_CIDR] = { .type = NLA_U8 },
+ [IPSET_ATTR_CIDR2] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_netnet_init(void)
+{
+ return ip_set_type_register(&hash_netnet_type);
+}
+
+static void __exit
+hash_netnet_fini(void)
+{
+ ip_set_type_unregister(&hash_netnet_type);
+}
+
+module_init(hash_netnet_init);
+module_exit(hash_netnet_fini);
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 09d6690bee6f..7097fb0141bf 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -23,15 +23,16 @@
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 SCTP and UDPLITE support added */
-/* 2 Range as input support for IPv4 added */
-/* 3 nomatch flag support added */
-#define REVISION_MAX 4 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Range as input support for IPv4 added */
+/* 3 nomatch flag support added */
+/* 4 Counters support added */
+#define IPSET_TYPE_REV_MAX 5 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net,port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:net,port");
/* Type specific function prefix */
@@ -45,7 +46,7 @@ MODULE_ALIAS("ip_set_hash:net,port");
*/
#define IP_SET_HASH_WITH_NETS_PACKED
-/* IPv4 variants */
+/* IPv4 variant */
/* Member elements */
struct hash_netport4_elem {
@@ -56,34 +57,6 @@ struct hash_netport4_elem {
u8 nomatch:1;
};
-struct hash_netport4t_elem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- unsigned long timeout;
-};
-
-struct hash_netport4c_elem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- struct ip_set_counter counter;
-};
-
-struct hash_netport4ct_elem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -162,9 +135,9 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
e.cidr = HOST_MASK - 1;
@@ -186,8 +159,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
- u32 port, port_to, p = 0, ip = 0, ip_to, last;
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 port, port_to, p = 0, ip = 0, ip_to = 0, last;
bool with_ports = false;
u8 cidr;
int ret;
@@ -287,7 +260,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* IPv6 variants */
+/* IPv6 variant */
struct hash_netport6_elem {
union nf_inet_addr ip;
@@ -297,34 +270,6 @@ struct hash_netport6_elem {
u8 nomatch:1;
};
-struct hash_netport6t_elem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- unsigned long timeout;
-};
-
-struct hash_netport6c_elem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- struct ip_set_counter counter;
-};
-
-struct hash_netport6ct_elem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
/* Common functions */
static inline bool
@@ -407,9 +352,9 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport6_elem e = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1,
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
e.cidr = HOST_MASK - 1;
@@ -431,7 +376,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport6_elem e = { .cidr = HOST_MASK - 1 };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
bool with_ports = false;
u8 cidr;
@@ -518,8 +463,8 @@ static struct ip_set_type hash_netport_type __read_mostly = {
.features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_netport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -542,6 +487,7 @@ static struct ip_set_type hash_netport_type __read_mostly = {
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
new file mode 100644
index 000000000000..363fab933d48
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -0,0 +1,588 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,port,net type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_getport.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+#define IPSET_TYPE_REV_MAX 0 /* Comments support added */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
+IP_SET_MODULE_DESC("hash:net,port,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:net,port,net");
+
+/* Type specific function prefix */
+#define HTYPE hash_netportnet
+#define IP_SET_HASH_WITH_PROTO
+#define IP_SET_HASH_WITH_NETS
+#define IPSET_NET_COUNT 2
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_netportnet4_elem {
+ union {
+ __be32 ip[2];
+ __be64 ipcmp;
+ };
+ __be16 port;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+ u8 nomatch:1;
+ u8 proto;
+};
+
+/* Common functions */
+
+static inline bool
+hash_netportnet4_data_equal(const struct hash_netportnet4_elem *ip1,
+ const struct hash_netportnet4_elem *ip2,
+ u32 *multi)
+{
+ return ip1->ipcmp == ip2->ipcmp &&
+ ip1->ccmp == ip2->ccmp &&
+ ip1->port == ip2->port &&
+ ip1->proto == ip2->proto;
+}
+
+static inline int
+hash_netportnet4_do_data_match(const struct hash_netportnet4_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netportnet4_data_set_flags(struct hash_netportnet4_elem *elem, u32 flags)
+{
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netportnet4_data_reset_flags(struct hash_netportnet4_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netportnet4_data_reset_elem(struct hash_netportnet4_elem *elem,
+ struct hash_netportnet4_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netportnet4_data_netmask(struct hash_netportnet4_elem *elem,
+ u8 cidr, bool inner)
+{
+ if (inner) {
+ elem->ip[1] &= ip_set_netmask(cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ elem->ip[0] &= ip_set_netmask(cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netportnet4_data_list(struct sk_buff *skb,
+ const struct hash_netportnet4_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip[0]) ||
+ nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip[1]) ||
+ nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_netportnet4_data_next(struct hash_netportnet4_elem *next,
+ const struct hash_netportnet4_elem *d)
+{
+ next->ipcmp = d->ipcmp;
+ next->port = d->port;
+}
+
+#define MTYPE hash_netportnet4
+#define PF 4
+#define HOST_MASK 32
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet4_elem e = {
+ .cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
+ .cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK),
+ };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK;
+
+ if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
+ &e.port, &e.proto))
+ return -EINVAL;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip[1]);
+ e.ip[0] &= ip_set_netmask(e.cidr[0]);
+ e.ip[1] &= ip_set_netmask(e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet4_elem e = { .cidr[0] = HOST_MASK,
+ .cidr[1] = HOST_MASK };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to;
+ u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
+ bool with_ports = false;
+ u8 cidr, cidr2;
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR]) {
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (!cidr || cidr > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[0] = cidr;
+ }
+
+ if (tb[IPSET_ATTR_CIDR2]) {
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+ if (!cidr || cidr > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[1] = cidr;
+ }
+
+ if (tb[IPSET_ATTR_PORT])
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ else
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_PROTO]) {
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
+
+ if (e.proto == 0)
+ return -IPSET_ERR_INVALID_PROTO;
+ } else
+ return -IPSET_ERR_MISSING_PROTO;
+
+ if (!(with_ports || e.proto == IPPROTO_ICMP))
+ e.port = 0;
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ with_ports = with_ports && tb[IPSET_ATTR_PORT_TO];
+ if (adt == IPSET_TEST ||
+ !(tb[IPSET_ATTR_IP_TO] || with_ports || tb[IPSET_ATTR_IP2_TO])) {
+ e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0]));
+ e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1]));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ip_to = ip;
+ if (tb[IPSET_ATTR_IP_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+ if (ret)
+ return ret;
+ if (ip > ip_to)
+ swap(ip, ip_to);
+ if (unlikely(ip + UINT_MAX == ip_to))
+ return -IPSET_ERR_HASH_RANGE;
+ }
+
+ port_to = port = ntohs(e.port);
+ if (tb[IPSET_ATTR_PORT_TO]) {
+ port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
+ if (port > port_to)
+ swap(port, port_to);
+ }
+
+ ip2_to = ip2_from;
+ if (tb[IPSET_ATTR_IP2_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
+ if (ret)
+ return ret;
+ if (ip2_from > ip2_to)
+ swap(ip2_from, ip2_to);
+ if (unlikely(ip2_from + UINT_MAX == ip2_to))
+ return -IPSET_ERR_HASH_RANGE;
+ }
+
+ if (retried)
+ ip = ntohl(h->next.ip[0]);
+
+ while (!after(ip, ip_to)) {
+ e.ip[0] = htonl(ip);
+ ip_last = ip_set_range_to_cidr(ip, ip_to, &cidr);
+ e.cidr[0] = cidr;
+ p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port)
+ : port;
+ for (; p <= port_to; p++) {
+ e.port = htons(p);
+ ip2 = (retried && ip == ntohl(h->next.ip[0]) &&
+ p == ntohs(h->next.port)) ? ntohl(h->next.ip[1])
+ : ip2_from;
+ while (!after(ip2, ip2_to)) {
+ e.ip[1] = htonl(ip2);
+ ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
+ &cidr2);
+ e.cidr[1] = cidr2;
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ ip2 = ip2_last + 1;
+ }
+ }
+ ip = ip_last + 1;
+ }
+ return ret;
+}
+
+/* IPv6 variant */
+
+struct hash_netportnet6_elem {
+ union nf_inet_addr ip[2];
+ __be16 port;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+ u8 nomatch:1;
+ u8 proto;
+};
+
+/* Common functions */
+
+static inline bool
+hash_netportnet6_data_equal(const struct hash_netportnet6_elem *ip1,
+ const struct hash_netportnet6_elem *ip2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) &&
+ ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) &&
+ ip1->ccmp == ip2->ccmp &&
+ ip1->port == ip2->port &&
+ ip1->proto == ip2->proto;
+}
+
+static inline int
+hash_netportnet6_do_data_match(const struct hash_netportnet6_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netportnet6_data_set_flags(struct hash_netportnet6_elem *elem, u32 flags)
+{
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netportnet6_data_reset_flags(struct hash_netportnet6_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netportnet6_data_reset_elem(struct hash_netportnet6_elem *elem,
+ struct hash_netportnet6_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netportnet6_data_netmask(struct hash_netportnet6_elem *elem,
+ u8 cidr, bool inner)
+{
+ if (inner) {
+ ip6_netmask(&elem->ip[1], cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ ip6_netmask(&elem->ip[0], cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netportnet6_data_list(struct sk_buff *skb,
+ const struct hash_netportnet6_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip[0].in6) ||
+ nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip[1].in6) ||
+ nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_netportnet6_data_next(struct hash_netportnet4_elem *next,
+ const struct hash_netportnet6_elem *d)
+{
+ next->port = d->port;
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+
+#define MTYPE hash_netportnet6
+#define PF 6
+#define HOST_MASK 128
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet6_elem e = {
+ .cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
+ .cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK),
+ };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK;
+
+ if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
+ &e.port, &e.proto))
+ return -EINVAL;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip[1].in6);
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet6_elem e = { .cidr[0] = HOST_MASK,
+ .cidr[1] = HOST_MASK };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 port, port_to;
+ bool with_ports = false;
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+ if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO]))
+ return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) ||
+ ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR])
+ e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+ if (tb[IPSET_ATTR_CIDR2])
+ e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+
+ if (unlikely(!e.cidr[0] || e.cidr[0] > HOST_MASK || !e.cidr[1] ||
+ e.cidr[1] > HOST_MASK))
+ return -IPSET_ERR_INVALID_CIDR;
+
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ if (tb[IPSET_ATTR_PORT])
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ else
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_PROTO]) {
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
+
+ if (e.proto == 0)
+ return -IPSET_ERR_INVALID_PROTO;
+ } else
+ return -IPSET_ERR_MISSING_PROTO;
+
+ if (!(with_ports || e.proto == IPPROTO_ICMPV6))
+ e.port = 0;
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ port = ntohs(e.port);
+ port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
+ if (port > port_to)
+ swap(port, port_to);
+
+ if (retried)
+ port = ntohs(h->next.port);
+ for (; port <= port_to; port++) {
+ e.port = htons(port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
+
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ }
+ return ret;
+}
+
+static struct ip_set_type hash_netportnet_type __read_mostly = {
+ .name = "hash:net,port,net",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2 |
+ IPSET_TYPE_NOMATCH,
+ .dimension = IPSET_DIM_THREE,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_netportnet_create,
+ .create_policy = {
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_PORT] = { .type = NLA_U16 },
+ [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 },
+ [IPSET_ATTR_CIDR] = { .type = NLA_U8 },
+ [IPSET_ATTR_CIDR2] = { .type = NLA_U8 },
+ [IPSET_ATTR_PROTO] = { .type = NLA_U8 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_netportnet_init(void)
+{
+ return ip_set_type_register(&hash_netportnet_type);
+}
+
+static void __exit
+hash_netportnet_fini(void)
+{
+ ip_set_type_unregister(&hash_netportnet_type);
+}
+
+module_init(hash_netportnet_init);
+module_exit(hash_netportnet_fini);
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 979b8c90e422..ec6f6d15dded 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -15,12 +15,13 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_list.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* Counters support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counters support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("list:set", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("list:set", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_list:set");
/* Member elements */
@@ -28,28 +29,6 @@ struct set_elem {
ip_set_id_t id;
};
-struct sett_elem {
- struct {
- ip_set_id_t id;
- } __attribute__ ((aligned));
- unsigned long timeout;
-};
-
-struct setc_elem {
- struct {
- ip_set_id_t id;
- } __attribute__ ((aligned));
- struct ip_set_counter counter;
-};
-
-struct setct_elem {
- struct {
- ip_set_id_t id;
- } __attribute__ ((aligned));
- struct ip_set_counter counter;
- unsigned long timeout;
-};
-
struct set_adt_elem {
ip_set_id_t id;
ip_set_id_t refid;
@@ -58,24 +37,14 @@ struct set_adt_elem {
/* Type structure */
struct list_set {
- size_t dsize; /* element size */
- size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
u32 size; /* size of set list array */
- u32 timeout; /* timeout value */
struct timer_list gc; /* garbage collection */
+ struct net *net; /* namespace */
struct set_elem members[0]; /* the set members */
};
-static inline struct set_elem *
-list_set_elem(const struct list_set *map, u32 id)
-{
- return (struct set_elem *)((void *)map->members + id * map->dsize);
-}
-
-#define ext_timeout(e, m) \
-(unsigned long *)((void *)(e) + (m)->offset[IPSET_OFFSET_TIMEOUT])
-#define ext_counter(e, m) \
-(struct ip_set_counter *)((void *)(e) + (m)->offset[IPSET_OFFSET_COUNTER])
+#define list_set_elem(set, map, id) \
+ (struct set_elem *)((void *)(map)->members + (id) * (set)->dsize)
static int
list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
@@ -92,16 +61,16 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
return 0;
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
ret = ip_set_test(e->id, skb, par, opt);
if (ret > 0) {
if (SET_WITH_COUNTER(set))
- ip_set_update_counter(ext_counter(e, map),
+ ip_set_update_counter(ext_counter(e, set),
ext, &opt->ext,
cmdflags);
return ret;
@@ -121,11 +90,11 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb,
int ret;
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
return 0;
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
ret = ip_set_add(e->id, skb, par, opt);
if (ret == 0)
@@ -145,11 +114,11 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb,
int ret;
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
return 0;
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
ret = ip_set_del(e->id, skb, par, opt);
if (ret == 0)
@@ -163,8 +132,7 @@ list_set_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- struct list_set *map = set->data;
- struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
switch (adt) {
case IPSET_TEST:
@@ -188,10 +156,10 @@ id_eq(const struct ip_set *set, u32 i, ip_set_id_t id)
if (i >= map->size)
return 0;
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
return !!(e->id == id &&
!(SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map))));
+ ip_set_timeout_expired(ext_timeout(e, set))));
}
static int
@@ -199,28 +167,36 @@ list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d,
const struct ip_set_ext *ext)
{
struct list_set *map = set->data;
- struct set_elem *e = list_set_elem(map, i);
+ struct set_elem *e = list_set_elem(set, map, i);
if (e->id != IPSET_INVALID_ID) {
- if (i == map->size - 1)
+ if (i == map->size - 1) {
/* Last element replaced: e.g. add new,before,last */
- ip_set_put_byindex(e->id);
- else {
- struct set_elem *x = list_set_elem(map, map->size - 1);
+ ip_set_put_byindex(map->net, e->id);
+ ip_set_ext_destroy(set, e);
+ } else {
+ struct set_elem *x = list_set_elem(set, map,
+ map->size - 1);
/* Last element pushed off */
- if (x->id != IPSET_INVALID_ID)
- ip_set_put_byindex(x->id);
- memmove(list_set_elem(map, i + 1), e,
- map->dsize * (map->size - (i + 1)));
+ if (x->id != IPSET_INVALID_ID) {
+ ip_set_put_byindex(map->net, x->id);
+ ip_set_ext_destroy(set, x);
+ }
+ memmove(list_set_elem(set, map, i + 1), e,
+ set->dsize * (map->size - (i + 1)));
+ /* Extensions must be initialized to zero */
+ memset(e, 0, set->dsize);
}
}
e->id = d->id;
if (SET_WITH_TIMEOUT(set))
- ip_set_timeout_set(ext_timeout(e, map), ext->timeout);
+ ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
if (SET_WITH_COUNTER(set))
- ip_set_init_counter(ext_counter(e, map), ext);
+ ip_set_init_counter(ext_counter(e, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(e, set), ext);
return 0;
}
@@ -228,16 +204,17 @@ static int
list_set_del(struct ip_set *set, u32 i)
{
struct list_set *map = set->data;
- struct set_elem *e = list_set_elem(map, i);
+ struct set_elem *e = list_set_elem(set, map, i);
- ip_set_put_byindex(e->id);
+ ip_set_put_byindex(map->net, e->id);
+ ip_set_ext_destroy(set, e);
if (i < map->size - 1)
- memmove(e, list_set_elem(map, i + 1),
- map->dsize * (map->size - (i + 1)));
+ memmove(e, list_set_elem(set, map, i + 1),
+ set->dsize * (map->size - (i + 1)));
/* Last element */
- e = list_set_elem(map, map->size - 1);
+ e = list_set_elem(set, map, map->size - 1);
e->id = IPSET_INVALID_ID;
return 0;
}
@@ -247,13 +224,16 @@ set_cleanup_entries(struct ip_set *set)
{
struct list_set *map = set->data;
struct set_elem *e;
- u32 i;
+ u32 i = 0;
- for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ while (i < map->size) {
+ e = list_set_elem(set, map, i);
if (e->id != IPSET_INVALID_ID &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
list_set_del(set, i);
+ /* Check element moved to position i in next loop */
+ else
+ i++;
}
}
@@ -268,11 +248,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
int ret;
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
return 0;
else if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
else if (e->id != d->id)
continue;
@@ -299,14 +279,14 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
bool flag_exist = flags & IPSET_FLAG_EXIST;
u32 i, ret = 0;
+ if (SET_WITH_TIMEOUT(set))
+ set_cleanup_entries(set);
+
/* Check already added element */
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
goto insert;
- else if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
- continue;
else if (e->id != d->id)
continue;
@@ -319,18 +299,22 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
/* Can't re-add */
return -IPSET_ERR_EXIST;
/* Update extensions */
+ ip_set_ext_destroy(set, e);
+
if (SET_WITH_TIMEOUT(set))
- ip_set_timeout_set(ext_timeout(e, map), ext->timeout);
+ ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
if (SET_WITH_COUNTER(set))
- ip_set_init_counter(ext_counter(e, map), ext);
+ ip_set_init_counter(ext_counter(e, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(e, set), ext);
/* Set is already added to the list */
- ip_set_put_byindex(d->id);
+ ip_set_put_byindex(map->net, d->id);
return 0;
}
insert:
ret = -IPSET_ERR_LIST_FULL;
for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
ret = d->before != 0 ? -IPSET_ERR_REF_EXIST
: list_set_add(set, i, d, ext);
@@ -355,12 +339,12 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext,
u32 i;
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
return d->before != 0 ? -IPSET_ERR_REF_EXIST
: -IPSET_ERR_EXIST;
else if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
else if (e->id != d->id)
continue;
@@ -386,7 +370,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
struct list_set *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct set_adt_elem e = { .refid = IPSET_INVALID_ID };
- struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
struct ip_set *s;
int ret = 0;
@@ -403,7 +387,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
ret = ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
- e.id = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAME]), &s);
+ e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s);
if (e.id == IPSET_INVALID_ID)
return -IPSET_ERR_NAME;
/* "Loop detection" */
@@ -423,7 +407,8 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
}
if (tb[IPSET_ATTR_NAMEREF]) {
- e.refid = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAMEREF]),
+ e.refid = ip_set_get_byname(map->net,
+ nla_data(tb[IPSET_ATTR_NAMEREF]),
&s);
if (e.refid == IPSET_INVALID_ID) {
ret = -IPSET_ERR_NAMEREF;
@@ -439,9 +424,9 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
finish:
if (e.refid != IPSET_INVALID_ID)
- ip_set_put_byindex(e.refid);
+ ip_set_put_byindex(map->net, e.refid);
if (adt != IPSET_ADD || ret)
- ip_set_put_byindex(e.id);
+ ip_set_put_byindex(map->net, e.id);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
@@ -454,9 +439,10 @@ list_set_flush(struct ip_set *set)
u32 i;
for (i = 0; i < map->size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id != IPSET_INVALID_ID) {
- ip_set_put_byindex(e->id);
+ ip_set_put_byindex(map->net, e->id);
+ ip_set_ext_destroy(set, e);
e->id = IPSET_INVALID_ID;
}
}
@@ -485,14 +471,11 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
if (!nested)
goto nla_put_failure;
if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) ||
- (SET_WITH_TIMEOUT(set) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))) ||
- (SET_WITH_COUNTER(set) &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS,
- htonl(IPSET_FLAG_WITH_COUNTERS))) ||
nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
- htonl(sizeof(*map) + map->size * map->dsize)))
+ htonl(sizeof(*map) + map->size * set->dsize)))
+ goto nla_put_failure;
+ if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
ipset_nest_end(skb, nested);
@@ -515,11 +498,11 @@ list_set_list(const struct ip_set *set,
return -EMSGSIZE;
for (; cb->args[2] < map->size; cb->args[2]++) {
i = cb->args[2];
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
goto finish;
if (SET_WITH_TIMEOUT(set) &&
- ip_set_timeout_expired(ext_timeout(e, map)))
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
if (!nested) {
@@ -530,15 +513,9 @@ list_set_list(const struct ip_set *set,
goto nla_put_failure;
}
if (nla_put_string(skb, IPSET_ATTR_NAME,
- ip_set_name_byindex(e->id)))
- goto nla_put_failure;
- if (SET_WITH_TIMEOUT(set) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(
- ext_timeout(e, map)))))
+ ip_set_name_byindex(map->net, e->id)))
goto nla_put_failure;
- if (SET_WITH_COUNTER(set) &&
- ip_set_put_counter(skb, ext_counter(e, map)))
+ if (ip_set_put_extensions(skb, set, e, true))
goto nla_put_failure;
ipset_nest_end(skb, nested);
}
@@ -550,11 +527,11 @@ finish:
nla_put_failure:
nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, atd);
if (unlikely(i == first)) {
cb->args[2] = 0;
return -EMSGSIZE;
}
+ ipset_nest_end(skb, atd);
return 0;
}
@@ -565,7 +542,7 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
const struct list_set *y = b->data;
return x->size == y->size &&
- x->timeout == y->timeout &&
+ a->timeout == b->timeout &&
a->extensions == b->extensions;
}
@@ -594,7 +571,7 @@ list_set_gc(unsigned long ul_set)
set_cleanup_entries(set);
write_unlock_bh(&set->lock);
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&map->gc);
}
@@ -606,43 +583,40 @@ list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
init_timer(&map->gc);
map->gc.data = (unsigned long) set;
map->gc.function = gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&map->gc);
}
/* Create list:set type of sets */
-static struct list_set *
-init_list_set(struct ip_set *set, u32 size, size_t dsize,
- unsigned long timeout)
+static bool
+init_list_set(struct net *net, struct ip_set *set, u32 size)
{
struct list_set *map;
struct set_elem *e;
u32 i;
- map = kzalloc(sizeof(*map) + size * dsize, GFP_KERNEL);
+ map = kzalloc(sizeof(*map) + size * set->dsize, GFP_KERNEL);
if (!map)
- return NULL;
+ return false;
map->size = size;
- map->dsize = dsize;
- map->timeout = timeout;
+ map->net = net;
set->data = map;
for (i = 0; i < size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
e->id = IPSET_INVALID_ID;
}
- return map;
+ return true;
}
static int
-list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+ u32 flags)
{
- struct list_set *map;
- u32 size = IP_SET_LIST_DEFAULT_SIZE, cadt_flags = 0;
- unsigned long timeout = 0;
+ u32 size = IP_SET_LIST_DEFAULT_SIZE;
if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
@@ -654,45 +628,13 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
if (size < IP_SET_LIST_MIN_SIZE)
size = IP_SET_LIST_MIN_SIZE;
- if (tb[IPSET_ATTR_CADT_FLAGS])
- cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
- if (tb[IPSET_ATTR_TIMEOUT])
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
set->variant = &set_variant;
- if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
- set->extensions |= IPSET_EXT_COUNTER;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- map = init_list_set(set, size,
- sizeof(struct setct_elem), timeout);
- if (!map)
- return -ENOMEM;
- set->extensions |= IPSET_EXT_TIMEOUT;
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct setct_elem, timeout);
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct setct_elem, counter);
- list_set_gc_init(set, list_set_gc);
- } else {
- map = init_list_set(set, size,
- sizeof(struct setc_elem), 0);
- if (!map)
- return -ENOMEM;
- map->offset[IPSET_OFFSET_COUNTER] =
- offsetof(struct setc_elem, counter);
- }
- } else if (tb[IPSET_ATTR_TIMEOUT]) {
- map = init_list_set(set, size,
- sizeof(struct sett_elem), timeout);
- if (!map)
- return -ENOMEM;
- set->extensions |= IPSET_EXT_TIMEOUT;
- map->offset[IPSET_OFFSET_TIMEOUT] =
- offsetof(struct sett_elem, timeout);
+ set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem));
+ if (!init_list_set(net, set, size))
+ return -ENOMEM;
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
list_set_gc_init(set, list_set_gc);
- } else {
- map = init_list_set(set, size, sizeof(struct set_elem), 0);
- if (!map)
- return -ENOMEM;
}
return 0;
}
@@ -703,8 +645,8 @@ static struct ip_set_type list_set_type __read_mostly = {
.features = IPSET_TYPE_NAME | IPSET_DUMP_LAST,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = list_set_create,
.create_policy = {
[IPSET_ATTR_SIZE] = { .type = NLA_U32 },
@@ -721,6 +663,7 @@ static struct ip_set_type list_set_type __read_mostly = {
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index e0c4373b4747..466410eaa482 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -52,66 +52,8 @@ module_param(sip_direct_media, int, 0600);
MODULE_PARM_DESC(sip_direct_media, "Expect Media streams between signalling "
"endpoints only (default 1)");
-unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int protoff,
- unsigned int dataoff, const char **dptr,
- unsigned int *datalen) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sip_hook);
-
-void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, unsigned int protoff,
- s16 off) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sip_seq_adjust_hook);
-
-unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb,
- unsigned int protoff,
- unsigned int dataoff,
- const char **dptr,
- unsigned int *datalen,
- struct nf_conntrack_expect *exp,
- unsigned int matchoff,
- unsigned int matchlen) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sip_expect_hook);
-
-unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int protoff,
- unsigned int dataoff,
- const char **dptr,
- unsigned int *datalen,
- unsigned int sdpoff,
- enum sdp_header_types type,
- enum sdp_header_types term,
- const union nf_inet_addr *addr)
- __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_addr_hook);
-
-unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int protoff,
- unsigned int dataoff,
- const char **dptr,
- unsigned int *datalen,
- unsigned int matchoff,
- unsigned int matchlen,
- u_int16_t port) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_port_hook);
-
-unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb,
- unsigned int protoff,
- unsigned int dataoff,
- const char **dptr,
- unsigned int *datalen,
- unsigned int sdpoff,
- const union nf_inet_addr *addr)
- __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_session_hook);
-
-unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int protoff,
- unsigned int dataoff,
- const char **dptr,
- unsigned int *datalen,
- struct nf_conntrack_expect *rtp_exp,
- struct nf_conntrack_expect *rtcp_exp,
- unsigned int mediaoff,
- unsigned int medialen,
- union nf_inet_addr *rtp_addr)
- __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_media_hook);
+const struct nf_nat_sip_hooks *nf_nat_sip_hooks;
+EXPORT_SYMBOL_GPL(nf_nat_sip_hooks);
static int string_len(const struct nf_conn *ct, const char *dptr,
const char *limit, int *shift)
@@ -914,8 +856,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
int direct_rtp = 0, skip_expect = 0, ret = NF_DROP;
u_int16_t base_port;
__be16 rtp_port, rtcp_port;
- typeof(nf_nat_sdp_port_hook) nf_nat_sdp_port;
- typeof(nf_nat_sdp_media_hook) nf_nat_sdp_media;
+ const struct nf_nat_sip_hooks *hooks;
saddr = NULL;
if (sip_direct_media) {
@@ -966,22 +907,23 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
#endif
skip_expect = 1;
} while (!skip_expect);
- rcu_read_unlock();
base_port = ntohs(tuple.dst.u.udp.port) & ~1;
rtp_port = htons(base_port);
rtcp_port = htons(base_port + 1);
if (direct_rtp) {
- nf_nat_sdp_port = rcu_dereference(nf_nat_sdp_port_hook);
- if (nf_nat_sdp_port &&
- !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen,
+ hooks = rcu_dereference(nf_nat_sip_hooks);
+ if (hooks &&
+ !hooks->sdp_port(skb, protoff, dataoff, dptr, datalen,
mediaoff, medialen, ntohs(rtp_port)))
goto err1;
}
- if (skip_expect)
+ if (skip_expect) {
+ rcu_read_unlock();
return NF_ACCEPT;
+ }
rtp_exp = nf_ct_expect_alloc(ct);
if (rtp_exp == NULL)
@@ -995,10 +937,10 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
nf_ct_expect_init(rtcp_exp, class, nf_ct_l3num(ct), saddr, daddr,
IPPROTO_UDP, NULL, &rtcp_port);
- nf_nat_sdp_media = rcu_dereference(nf_nat_sdp_media_hook);
- if (nf_nat_sdp_media && ct->status & IPS_NAT_MASK && !direct_rtp)
- ret = nf_nat_sdp_media(skb, protoff, dataoff, dptr, datalen,
- rtp_exp, rtcp_exp,
+ hooks = rcu_dereference(nf_nat_sip_hooks);
+ if (hooks && ct->status & IPS_NAT_MASK && !direct_rtp)
+ ret = hooks->sdp_media(skb, protoff, dataoff, dptr,
+ datalen, rtp_exp, rtcp_exp,
mediaoff, medialen, daddr);
else {
if (nf_ct_expect_related(rtp_exp) == 0) {
@@ -1012,6 +954,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
err2:
nf_ct_expect_put(rtp_exp);
err1:
+ rcu_read_unlock();
return ret;
}
@@ -1051,13 +994,12 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
unsigned int caddr_len, maddr_len;
unsigned int i;
union nf_inet_addr caddr, maddr, rtp_addr;
+ const struct nf_nat_sip_hooks *hooks;
unsigned int port;
const struct sdp_media_type *t;
int ret = NF_ACCEPT;
- typeof(nf_nat_sdp_addr_hook) nf_nat_sdp_addr;
- typeof(nf_nat_sdp_session_hook) nf_nat_sdp_session;
- nf_nat_sdp_addr = rcu_dereference(nf_nat_sdp_addr_hook);
+ hooks = rcu_dereference(nf_nat_sip_hooks);
/* Find beginning of session description */
if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen,
@@ -1125,10 +1067,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
}
/* Update media connection address if present */
- if (maddr_len && nf_nat_sdp_addr && ct->status & IPS_NAT_MASK) {
- ret = nf_nat_sdp_addr(skb, protoff, dataoff,
+ if (maddr_len && hooks && ct->status & IPS_NAT_MASK) {
+ ret = hooks->sdp_addr(skb, protoff, dataoff,
dptr, datalen, mediaoff,
- SDP_HDR_CONNECTION, SDP_HDR_MEDIA,
+ SDP_HDR_CONNECTION,
+ SDP_HDR_MEDIA,
&rtp_addr);
if (ret != NF_ACCEPT) {
nf_ct_helper_log(skb, ct, "cannot mangle SDP");
@@ -1139,10 +1082,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
}
/* Update session connection and owner addresses */
- nf_nat_sdp_session = rcu_dereference(nf_nat_sdp_session_hook);
- if (nf_nat_sdp_session && ct->status & IPS_NAT_MASK)
- ret = nf_nat_sdp_session(skb, protoff, dataoff,
- dptr, datalen, sdpoff, &rtp_addr);
+ hooks = rcu_dereference(nf_nat_sip_hooks);
+ if (hooks && ct->status & IPS_NAT_MASK)
+ ret = hooks->sdp_session(skb, protoff, dataoff,
+ dptr, datalen, sdpoff,
+ &rtp_addr);
return ret;
}
@@ -1242,11 +1186,11 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
unsigned int matchoff, matchlen;
struct nf_conntrack_expect *exp;
union nf_inet_addr *saddr, daddr;
+ const struct nf_nat_sip_hooks *hooks;
__be16 port;
u8 proto;
unsigned int expires = 0;
int ret;
- typeof(nf_nat_sip_expect_hook) nf_nat_sip_expect;
/* Expected connections can not register again. */
if (ct->status & IPS_EXPECTED)
@@ -1309,10 +1253,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
exp->helper = nfct_help(ct)->helper;
exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
- nf_nat_sip_expect = rcu_dereference(nf_nat_sip_expect_hook);
- if (nf_nat_sip_expect && ct->status & IPS_NAT_MASK)
- ret = nf_nat_sip_expect(skb, protoff, dataoff, dptr, datalen,
- exp, matchoff, matchlen);
+ hooks = rcu_dereference(nf_nat_sip_hooks);
+ if (hooks && ct->status & IPS_NAT_MASK)
+ ret = hooks->expect(skb, protoff, dataoff, dptr, datalen,
+ exp, matchoff, matchlen);
else {
if (nf_ct_expect_related(exp) != 0) {
nf_ct_helper_log(skb, ct, "cannot add expectation");
@@ -1515,7 +1459,7 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct,
unsigned int protoff, unsigned int dataoff,
const char **dptr, unsigned int *datalen)
{
- typeof(nf_nat_sip_hook) nf_nat_sip;
+ const struct nf_nat_sip_hooks *hooks;
int ret;
if (strnicmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0)
@@ -1524,9 +1468,9 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct,
ret = process_sip_response(skb, protoff, dataoff, dptr, datalen);
if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) {
- nf_nat_sip = rcu_dereference(nf_nat_sip_hook);
- if (nf_nat_sip && !nf_nat_sip(skb, protoff, dataoff,
- dptr, datalen)) {
+ hooks = rcu_dereference(nf_nat_sip_hooks);
+ if (hooks && !hooks->msg(skb, protoff, dataoff,
+ dptr, datalen)) {
nf_ct_helper_log(skb, ct, "cannot NAT SIP message");
ret = NF_DROP;
}
@@ -1546,7 +1490,6 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
s16 diff, tdiff = 0;
int ret = NF_ACCEPT;
bool term;
- typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust;
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY)
@@ -1610,9 +1553,11 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
}
if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) {
- nf_nat_sip_seq_adjust = rcu_dereference(nf_nat_sip_seq_adjust_hook);
- if (nf_nat_sip_seq_adjust)
- nf_nat_sip_seq_adjust(skb, protoff, tdiff);
+ const struct nf_nat_sip_hooks *hooks;
+
+ hooks = rcu_dereference(nf_nat_sip_hooks);
+ if (hooks)
+ hooks->seq_adjust(skb, protoff, tdiff);
}
return ret;
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index f9790405b7ff..b4d691db955e 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -625,33 +625,26 @@ static struct nf_ct_helper_expectfn sip_nat = {
static void __exit nf_nat_sip_fini(void)
{
- RCU_INIT_POINTER(nf_nat_sip_hook, NULL);
- RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL);
- RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL);
- RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL);
- RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL);
- RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL);
- RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL);
+ RCU_INIT_POINTER(nf_nat_sip_hooks, NULL);
+
nf_ct_helper_expectfn_unregister(&sip_nat);
synchronize_rcu();
}
+static const struct nf_nat_sip_hooks sip_hooks = {
+ .msg = nf_nat_sip,
+ .seq_adjust = nf_nat_sip_seq_adjust,
+ .expect = nf_nat_sip_expect,
+ .sdp_addr = nf_nat_sdp_addr,
+ .sdp_port = nf_nat_sdp_port,
+ .sdp_session = nf_nat_sdp_session,
+ .sdp_media = nf_nat_sdp_media,
+};
+
static int __init nf_nat_sip_init(void)
{
- BUG_ON(nf_nat_sip_hook != NULL);
- BUG_ON(nf_nat_sip_seq_adjust_hook != NULL);
- BUG_ON(nf_nat_sip_expect_hook != NULL);
- BUG_ON(nf_nat_sdp_addr_hook != NULL);
- BUG_ON(nf_nat_sdp_port_hook != NULL);
- BUG_ON(nf_nat_sdp_session_hook != NULL);
- BUG_ON(nf_nat_sdp_media_hook != NULL);
- RCU_INIT_POINTER(nf_nat_sip_hook, nf_nat_sip);
- RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, nf_nat_sip_seq_adjust);
- RCU_INIT_POINTER(nf_nat_sip_expect_hook, nf_nat_sip_expect);
- RCU_INIT_POINTER(nf_nat_sdp_addr_hook, nf_nat_sdp_addr);
- RCU_INIT_POINTER(nf_nat_sdp_port_hook, nf_nat_sdp_port);
- RCU_INIT_POINTER(nf_nat_sdp_session_hook, nf_nat_sdp_session);
- RCU_INIT_POINTER(nf_nat_sdp_media_hook, nf_nat_sdp_media);
+ BUG_ON(nf_nat_sip_hooks != NULL);
+ RCU_INIT_POINTER(nf_nat_sip_hooks, &sip_hooks);
nf_ct_helper_expectfn_register(&sip_nat);
return 0;
}
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 50580494148d..476accd17145 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -49,10 +49,8 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = {
};
static int
-ctnl_timeout_parse_policy(struct ctnl_timeout *timeout,
- struct nf_conntrack_l4proto *l4proto,
- struct net *net,
- const struct nlattr *attr)
+ctnl_timeout_parse_policy(void *timeouts, struct nf_conntrack_l4proto *l4proto,
+ struct net *net, const struct nlattr *attr)
{
int ret = 0;
@@ -64,8 +62,7 @@ ctnl_timeout_parse_policy(struct ctnl_timeout *timeout,
if (ret < 0)
return ret;
- ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net,
- &timeout->data);
+ ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts);
}
return ret;
}
@@ -123,7 +120,8 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
goto err_proto_put;
}
- ret = ctnl_timeout_parse_policy(matching, l4proto, net,
+ ret = ctnl_timeout_parse_policy(&matching->data,
+ l4proto, net,
cda[CTA_TIMEOUT_DATA]);
return ret;
}
@@ -138,7 +136,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
goto err_proto_put;
}
- ret = ctnl_timeout_parse_policy(timeout, l4proto, net,
+ ret = ctnl_timeout_parse_policy(&timeout->data, l4proto, net,
cda[CTA_TIMEOUT_DATA]);
if (ret < 0)
goto err;
@@ -342,6 +340,147 @@ cttimeout_del_timeout(struct sock *ctnl, struct sk_buff *skb,
return ret;
}
+static int
+cttimeout_default_set(struct sock *ctnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
+{
+ __u16 l3num;
+ __u8 l4num;
+ struct nf_conntrack_l4proto *l4proto;
+ struct net *net = sock_net(skb->sk);
+ unsigned int *timeouts;
+ int ret;
+
+ if (!cda[CTA_TIMEOUT_L3PROTO] ||
+ !cda[CTA_TIMEOUT_L4PROTO] ||
+ !cda[CTA_TIMEOUT_DATA])
+ return -EINVAL;
+
+ l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO]));
+ l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]);
+ l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+ /* This protocol is not supported, skip. */
+ if (l4proto->l4proto != l4num) {
+ ret = -EOPNOTSUPP;
+ goto err;
+ }
+
+ timeouts = l4proto->get_timeouts(net);
+
+ ret = ctnl_timeout_parse_policy(timeouts, l4proto, net,
+ cda[CTA_TIMEOUT_DATA]);
+ if (ret < 0)
+ goto err;
+
+ nf_ct_l4proto_put(l4proto);
+ return 0;
+err:
+ nf_ct_l4proto_put(l4proto);
+ return ret;
+}
+
+static int
+cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
+ u32 seq, u32 type, int event,
+ struct nf_conntrack_l4proto *l4proto)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+ unsigned int flags = portid ? NLM_F_MULTI : 0;
+
+ event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8;
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = AF_UNSPEC;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ if (nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(l4proto->l3proto)) ||
+ nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto))
+ goto nla_put_failure;
+
+ if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
+ struct nlattr *nest_parms;
+ unsigned int *timeouts = l4proto->get_timeouts(net);
+ int ret;
+
+ nest_parms = nla_nest_start(skb,
+ CTA_TIMEOUT_DATA | NLA_F_NESTED);
+ if (!nest_parms)
+ goto nla_put_failure;
+
+ ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts);
+ if (ret < 0)
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest_parms);
+ }
+
+ nlmsg_end(skb, nlh);
+ return skb->len;
+
+nlmsg_failure:
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -1;
+}
+
+static int cttimeout_default_get(struct sock *ctnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ const struct nlattr * const cda[])
+{
+ __u16 l3num;
+ __u8 l4num;
+ struct nf_conntrack_l4proto *l4proto;
+ struct net *net = sock_net(skb->sk);
+ struct sk_buff *skb2;
+ int ret, err;
+
+ if (!cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO])
+ return -EINVAL;
+
+ l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO]));
+ l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]);
+ l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+ /* This protocol is not supported, skip. */
+ if (l4proto->l4proto != l4num) {
+ err = -EOPNOTSUPP;
+ goto err;
+ }
+
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
+ err = -ENOMEM;
+ goto err;
+ }
+
+ ret = cttimeout_default_fill_info(net, skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ IPCTNL_MSG_TIMEOUT_DEFAULT_SET,
+ l4proto);
+ if (ret <= 0) {
+ kfree_skb(skb2);
+ err = -ENOMEM;
+ goto err;
+ }
+ ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT);
+ if (ret > 0)
+ ret = 0;
+
+ /* this avoids a loop in nfnetlink. */
+ return ret == -EAGAIN ? -ENOBUFS : ret;
+err:
+ nf_ct_l4proto_put(l4proto);
+ return err;
+}
+
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
static struct ctnl_timeout *ctnl_timeout_find_get(const char *name)
{
@@ -384,6 +523,12 @@ static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = {
[IPCTNL_MSG_TIMEOUT_DELETE] = { .call = cttimeout_del_timeout,
.attr_count = CTA_TIMEOUT_MAX,
.policy = cttimeout_nla_policy },
+ [IPCTNL_MSG_TIMEOUT_DEFAULT_SET]= { .call = cttimeout_default_set,
+ .attr_count = CTA_TIMEOUT_MAX,
+ .policy = cttimeout_nla_policy },
+ [IPCTNL_MSG_TIMEOUT_DEFAULT_GET]= { .call = cttimeout_default_get,
+ .attr_count = CTA_TIMEOUT_MAX,
+ .policy = cttimeout_nla_policy },
};
static const struct nfnetlink_subsystem cttimeout_subsys = {
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index d92cc317bf8b..3c4b69e5fe17 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -319,7 +319,8 @@ nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags)
}
static struct sk_buff *
-nfulnl_alloc_skb(u32 peer_portid, unsigned int inst_size, unsigned int pkt_size)
+nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size,
+ unsigned int pkt_size)
{
struct sk_buff *skb;
unsigned int n;
@@ -328,13 +329,13 @@ nfulnl_alloc_skb(u32 peer_portid, unsigned int inst_size, unsigned int pkt_size)
* message. WARNING: has to be <= 128k due to slab restrictions */
n = max(inst_size, pkt_size);
- skb = nfnetlink_alloc_skb(&init_net, n, peer_portid, GFP_ATOMIC);
+ skb = nfnetlink_alloc_skb(net, n, peer_portid, GFP_ATOMIC);
if (!skb) {
if (n > pkt_size) {
/* try to allocate only as much as we need for current
* packet */
- skb = nfnetlink_alloc_skb(&init_net, pkt_size,
+ skb = nfnetlink_alloc_skb(net, pkt_size,
peer_portid, GFP_ATOMIC);
if (!skb)
pr_err("nfnetlink_log: can't even alloc %u bytes\n",
@@ -702,8 +703,8 @@ nfulnl_log_packet(struct net *net,
}
if (!inst->skb) {
- inst->skb = nfulnl_alloc_skb(inst->peer_portid, inst->nlbufsiz,
- size);
+ inst->skb = nfulnl_alloc_skb(net, inst->peer_portid,
+ inst->nlbufsiz, size);
if (!inst->skb)
goto alloc_failure;
}
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index ae2e5c11d01a..21258cf70091 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -298,7 +298,7 @@ nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet,
}
static struct sk_buff *
-nfqnl_build_packet_message(struct nfqnl_instance *queue,
+nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
struct nf_queue_entry *entry,
__be32 **packet_id_ptr)
{
@@ -372,7 +372,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
if (queue->flags & NFQA_CFG_F_CONNTRACK)
ct = nfqnl_ct_get(entskb, &size, &ctinfo);
- skb = nfnetlink_alloc_skb(&init_net, size, queue->peer_portid,
+ skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
GFP_ATOMIC);
if (!skb)
return NULL;
@@ -525,7 +525,7 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue,
__be32 *packet_id_ptr;
int failopen = 0;
- nskb = nfqnl_build_packet_message(queue, entry, &packet_id_ptr);
+ nskb = nfqnl_build_packet_message(net, queue, entry, &packet_id_ptr);
if (nskb == NULL) {
err = -ENOMEM;
goto err_out;
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index cd24290f3b2f..e762de5ee89b 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -43,10 +43,42 @@ optlen(const u_int8_t *opt, unsigned int offset)
return opt[offset+1];
}
+static u_int32_t tcpmss_reverse_mtu(struct net *net,
+ const struct sk_buff *skb,
+ unsigned int family)
+{
+ struct flowi fl;
+ const struct nf_afinfo *ai;
+ struct rtable *rt = NULL;
+ u_int32_t mtu = ~0U;
+
+ if (family == PF_INET) {
+ struct flowi4 *fl4 = &fl.u.ip4;
+ memset(fl4, 0, sizeof(*fl4));
+ fl4->daddr = ip_hdr(skb)->saddr;
+ } else {
+ struct flowi6 *fl6 = &fl.u.ip6;
+
+ memset(fl6, 0, sizeof(*fl6));
+ fl6->daddr = ipv6_hdr(skb)->saddr;
+ }
+ rcu_read_lock();
+ ai = nf_get_afinfo(family);
+ if (ai != NULL)
+ ai->route(net, (struct dst_entry **)&rt, &fl, false);
+ rcu_read_unlock();
+
+ if (rt != NULL) {
+ mtu = dst_mtu(&rt->dst);
+ dst_release(&rt->dst);
+ }
+ return mtu;
+}
+
static int
tcpmss_mangle_packet(struct sk_buff *skb,
const struct xt_action_param *par,
- unsigned int in_mtu,
+ unsigned int family,
unsigned int tcphoff,
unsigned int minlen)
{
@@ -76,6 +108,9 @@ tcpmss_mangle_packet(struct sk_buff *skb,
return -1;
if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
+ struct net *net = dev_net(par->in ? par->in : par->out);
+ unsigned int in_mtu = tcpmss_reverse_mtu(net, skb, family);
+
if (dst_mtu(skb_dst(skb)) <= minlen) {
net_err_ratelimited("unknown or invalid path-MTU (%u)\n",
dst_mtu(skb_dst(skb)));
@@ -165,37 +200,6 @@ tcpmss_mangle_packet(struct sk_buff *skb,
return TCPOLEN_MSS;
}
-static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
- unsigned int family)
-{
- struct flowi fl;
- const struct nf_afinfo *ai;
- struct rtable *rt = NULL;
- u_int32_t mtu = ~0U;
-
- if (family == PF_INET) {
- struct flowi4 *fl4 = &fl.u.ip4;
- memset(fl4, 0, sizeof(*fl4));
- fl4->daddr = ip_hdr(skb)->saddr;
- } else {
- struct flowi6 *fl6 = &fl.u.ip6;
-
- memset(fl6, 0, sizeof(*fl6));
- fl6->daddr = ipv6_hdr(skb)->saddr;
- }
- rcu_read_lock();
- ai = nf_get_afinfo(family);
- if (ai != NULL)
- ai->route(&init_net, (struct dst_entry **)&rt, &fl, false);
- rcu_read_unlock();
-
- if (rt != NULL) {
- mtu = dst_mtu(&rt->dst);
- dst_release(&rt->dst);
- }
- return mtu;
-}
-
static unsigned int
tcpmss_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
@@ -204,7 +208,7 @@ tcpmss_tg4(struct sk_buff *skb, const struct xt_action_param *par)
int ret;
ret = tcpmss_mangle_packet(skb, par,
- tcpmss_reverse_mtu(skb, PF_INET),
+ PF_INET,
iph->ihl * 4,
sizeof(*iph) + sizeof(struct tcphdr));
if (ret < 0)
@@ -233,7 +237,7 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par)
if (tcphoff < 0)
return NF_DROP;
ret = tcpmss_mangle_packet(skb, par,
- tcpmss_reverse_mtu(skb, PF_INET6),
+ PF_INET6,
tcphoff,
sizeof(*ipv6h) + sizeof(struct tcphdr));
if (ret < 0)
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 31790e789e22..e7c4e0e01ff5 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -81,7 +81,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par)
struct xt_set_info_match_v0 *info = par->matchinfo;
ip_set_id_t index;
- index = ip_set_nfnl_get_byindex(info->match_set.index);
+ index = ip_set_nfnl_get_byindex(par->net, info->match_set.index);
if (index == IPSET_INVALID_ID) {
pr_warning("Cannot find set indentified by id %u to match\n",
@@ -91,7 +91,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par)
if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) {
pr_warning("Protocol error: set match dimension "
"is over the limit!\n");
- ip_set_nfnl_put(info->match_set.index);
+ ip_set_nfnl_put(par->net, info->match_set.index);
return -ERANGE;
}
@@ -106,9 +106,104 @@ set_match_v0_destroy(const struct xt_mtdtor_param *par)
{
struct xt_set_info_match_v0 *info = par->matchinfo;
- ip_set_nfnl_put(info->match_set.index);
+ ip_set_nfnl_put(par->net, info->match_set.index);
}
+/* Revision 1 match */
+
+static bool
+set_match_v1(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_set_info_match_v1 *info = par->matchinfo;
+ ADT_OPT(opt, par->family, info->match_set.dim,
+ info->match_set.flags, 0, UINT_MAX);
+
+ if (opt.flags & IPSET_RETURN_NOMATCH)
+ opt.cmdflags |= IPSET_FLAG_RETURN_NOMATCH;
+
+ return match_set(info->match_set.index, skb, par, &opt,
+ info->match_set.flags & IPSET_INV_MATCH);
+}
+
+static int
+set_match_v1_checkentry(const struct xt_mtchk_param *par)
+{
+ struct xt_set_info_match_v1 *info = par->matchinfo;
+ ip_set_id_t index;
+
+ index = ip_set_nfnl_get_byindex(par->net, info->match_set.index);
+
+ if (index == IPSET_INVALID_ID) {
+ pr_warning("Cannot find set indentified by id %u to match\n",
+ info->match_set.index);
+ return -ENOENT;
+ }
+ if (info->match_set.dim > IPSET_DIM_MAX) {
+ pr_warning("Protocol error: set match dimension "
+ "is over the limit!\n");
+ ip_set_nfnl_put(par->net, info->match_set.index);
+ return -ERANGE;
+ }
+
+ return 0;
+}
+
+static void
+set_match_v1_destroy(const struct xt_mtdtor_param *par)
+{
+ struct xt_set_info_match_v1 *info = par->matchinfo;
+
+ ip_set_nfnl_put(par->net, info->match_set.index);
+}
+
+/* Revision 3 match */
+
+static bool
+match_counter(u64 counter, const struct ip_set_counter_match *info)
+{
+ switch (info->op) {
+ case IPSET_COUNTER_NONE:
+ return true;
+ case IPSET_COUNTER_EQ:
+ return counter == info->value;
+ case IPSET_COUNTER_NE:
+ return counter != info->value;
+ case IPSET_COUNTER_LT:
+ return counter < info->value;
+ case IPSET_COUNTER_GT:
+ return counter > info->value;
+ }
+ return false;
+}
+
+static bool
+set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_set_info_match_v3 *info = par->matchinfo;
+ ADT_OPT(opt, par->family, info->match_set.dim,
+ info->match_set.flags, info->flags, UINT_MAX);
+ int ret;
+
+ if (info->packets.op != IPSET_COUNTER_NONE ||
+ info->bytes.op != IPSET_COUNTER_NONE)
+ opt.cmdflags |= IPSET_FLAG_MATCH_COUNTERS;
+
+ ret = match_set(info->match_set.index, skb, par, &opt,
+ info->match_set.flags & IPSET_INV_MATCH);
+
+ if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
+ return ret;
+
+ if (!match_counter(opt.ext.packets, &info->packets))
+ return 0;
+ return match_counter(opt.ext.bytes, &info->bytes);
+}
+
+#define set_match_v3_checkentry set_match_v1_checkentry
+#define set_match_v3_destroy set_match_v1_destroy
+
+/* Revision 0 interface: backward compatible with netfilter/iptables */
+
static unsigned int
set_target_v0(struct sk_buff *skb, const struct xt_action_param *par)
{
@@ -133,7 +228,7 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
ip_set_id_t index;
if (info->add_set.index != IPSET_INVALID_ID) {
- index = ip_set_nfnl_get_byindex(info->add_set.index);
+ index = ip_set_nfnl_get_byindex(par->net, info->add_set.index);
if (index == IPSET_INVALID_ID) {
pr_warning("Cannot find add_set index %u as target\n",
info->add_set.index);
@@ -142,12 +237,12 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
}
if (info->del_set.index != IPSET_INVALID_ID) {
- index = ip_set_nfnl_get_byindex(info->del_set.index);
+ index = ip_set_nfnl_get_byindex(par->net, info->del_set.index);
if (index == IPSET_INVALID_ID) {
pr_warning("Cannot find del_set index %u as target\n",
info->del_set.index);
if (info->add_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->add_set.index);
+ ip_set_nfnl_put(par->net, info->add_set.index);
return -ENOENT;
}
}
@@ -156,9 +251,9 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
pr_warning("Protocol error: SET target dimension "
"is over the limit!\n");
if (info->add_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->add_set.index);
+ ip_set_nfnl_put(par->net, info->add_set.index);
if (info->del_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->del_set.index);
+ ip_set_nfnl_put(par->net, info->del_set.index);
return -ERANGE;
}
@@ -175,57 +270,12 @@ set_target_v0_destroy(const struct xt_tgdtor_param *par)
const struct xt_set_info_target_v0 *info = par->targinfo;
if (info->add_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->add_set.index);
+ ip_set_nfnl_put(par->net, info->add_set.index);
if (info->del_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->del_set.index);
+ ip_set_nfnl_put(par->net, info->del_set.index);
}
-/* Revision 1 match and target */
-
-static bool
-set_match_v1(const struct sk_buff *skb, struct xt_action_param *par)
-{
- const struct xt_set_info_match_v1 *info = par->matchinfo;
- ADT_OPT(opt, par->family, info->match_set.dim,
- info->match_set.flags, 0, UINT_MAX);
-
- if (opt.flags & IPSET_RETURN_NOMATCH)
- opt.cmdflags |= IPSET_FLAG_RETURN_NOMATCH;
-
- return match_set(info->match_set.index, skb, par, &opt,
- info->match_set.flags & IPSET_INV_MATCH);
-}
-
-static int
-set_match_v1_checkentry(const struct xt_mtchk_param *par)
-{
- struct xt_set_info_match_v1 *info = par->matchinfo;
- ip_set_id_t index;
-
- index = ip_set_nfnl_get_byindex(info->match_set.index);
-
- if (index == IPSET_INVALID_ID) {
- pr_warning("Cannot find set indentified by id %u to match\n",
- info->match_set.index);
- return -ENOENT;
- }
- if (info->match_set.dim > IPSET_DIM_MAX) {
- pr_warning("Protocol error: set match dimension "
- "is over the limit!\n");
- ip_set_nfnl_put(info->match_set.index);
- return -ERANGE;
- }
-
- return 0;
-}
-
-static void
-set_match_v1_destroy(const struct xt_mtdtor_param *par)
-{
- struct xt_set_info_match_v1 *info = par->matchinfo;
-
- ip_set_nfnl_put(info->match_set.index);
-}
+/* Revision 1 target */
static unsigned int
set_target_v1(struct sk_buff *skb, const struct xt_action_param *par)
@@ -251,7 +301,7 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par)
ip_set_id_t index;
if (info->add_set.index != IPSET_INVALID_ID) {
- index = ip_set_nfnl_get_byindex(info->add_set.index);
+ index = ip_set_nfnl_get_byindex(par->net, info->add_set.index);
if (index == IPSET_INVALID_ID) {
pr_warning("Cannot find add_set index %u as target\n",
info->add_set.index);
@@ -260,12 +310,12 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par)
}
if (info->del_set.index != IPSET_INVALID_ID) {
- index = ip_set_nfnl_get_byindex(info->del_set.index);
+ index = ip_set_nfnl_get_byindex(par->net, info->del_set.index);
if (index == IPSET_INVALID_ID) {
pr_warning("Cannot find del_set index %u as target\n",
info->del_set.index);
if (info->add_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->add_set.index);
+ ip_set_nfnl_put(par->net, info->add_set.index);
return -ENOENT;
}
}
@@ -274,9 +324,9 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par)
pr_warning("Protocol error: SET target dimension "
"is over the limit!\n");
if (info->add_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->add_set.index);
+ ip_set_nfnl_put(par->net, info->add_set.index);
if (info->del_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->del_set.index);
+ ip_set_nfnl_put(par->net, info->del_set.index);
return -ERANGE;
}
@@ -289,9 +339,9 @@ set_target_v1_destroy(const struct xt_tgdtor_param *par)
const struct xt_set_info_target_v1 *info = par->targinfo;
if (info->add_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->add_set.index);
+ ip_set_nfnl_put(par->net, info->add_set.index);
if (info->del_set.index != IPSET_INVALID_ID)
- ip_set_nfnl_put(info->del_set.index);
+ ip_set_nfnl_put(par->net, info->del_set.index);
}
/* Revision 2 target */
@@ -320,52 +370,6 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
#define set_target_v2_checkentry set_target_v1_checkentry
#define set_target_v2_destroy set_target_v1_destroy
-/* Revision 3 match */
-
-static bool
-match_counter(u64 counter, const struct ip_set_counter_match *info)
-{
- switch (info->op) {
- case IPSET_COUNTER_NONE:
- return true;
- case IPSET_COUNTER_EQ:
- return counter == info->value;
- case IPSET_COUNTER_NE:
- return counter != info->value;
- case IPSET_COUNTER_LT:
- return counter < info->value;
- case IPSET_COUNTER_GT:
- return counter > info->value;
- }
- return false;
-}
-
-static bool
-set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
-{
- const struct xt_set_info_match_v3 *info = par->matchinfo;
- ADT_OPT(opt, par->family, info->match_set.dim,
- info->match_set.flags, info->flags, UINT_MAX);
- int ret;
-
- if (info->packets.op != IPSET_COUNTER_NONE ||
- info->bytes.op != IPSET_COUNTER_NONE)
- opt.cmdflags |= IPSET_FLAG_MATCH_COUNTERS;
-
- ret = match_set(info->match_set.index, skb, par, &opt,
- info->match_set.flags & IPSET_INV_MATCH);
-
- if (!(ret && opt.cmdflags & IPSET_FLAG_MATCH_COUNTERS))
- return ret;
-
- if (!match_counter(opt.ext.packets, &info->packets))
- return 0;
- return match_counter(opt.ext.bytes, &info->bytes);
-}
-
-#define set_match_v3_checkentry set_match_v1_checkentry
-#define set_match_v3_destroy set_match_v1_destroy
-
static struct xt_match set_matches[] __read_mostly = {
{
.name = "set",
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index a481c03e2861..56e22b74cf96 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -173,7 +173,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
skb->local_df = 1;
- inet_get_local_port_range(&port_min, &port_max);
+ inet_get_local_port_range(net, &port_min, &port_max);
src_port = vxlan_src_port(port_min, port_max, skb);
err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 189e3c5b3d09..272d8e924cf6 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -231,14 +231,14 @@ override:
}
if (R_tab) {
police->rate_present = true;
- psched_ratecfg_precompute(&police->rate, &R_tab->rate);
+ psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0);
qdisc_put_rtab(R_tab);
} else {
police->rate_present = false;
}
if (P_tab) {
police->peak_present = true;
- psched_ratecfg_precompute(&police->peak, &P_tab->rate);
+ psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0);
qdisc_put_rtab(P_tab);
} else {
police->peak_present = false;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index d76a35d0dc85..636d9131d870 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -137,7 +137,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
struct nlattr **tb,
struct nlattr *est)
{
- int err = -EINVAL;
+ int err;
struct tcf_exts e;
struct tcf_ematch_tree t;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 867b4a3e3980..16006c92c3fd 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -72,11 +72,11 @@ static void cgrp_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p;
- void *v;
+ struct cgroup_cls_state *cs = css_cls_state(css);
+ void *v = (void *)(unsigned long)cs->classid;
cgroup_taskset_for_each(p, css, tset) {
task_lock(p);
- v = (void *)(unsigned long)task_cls_classid(p);
iterate_fd(p->files, 0, update_classid, v);
task_unlock(p);
}
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index 938b7cbf5627..1ac41d3de5c3 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -24,11 +24,12 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
{
struct xt_set_info *set = data;
ip_set_id_t index;
+ struct net *net = qdisc_dev(tp->q)->nd_net;
if (data_len != sizeof(*set))
return -EINVAL;
- index = ip_set_nfnl_get_byindex(set->index);
+ index = ip_set_nfnl_get_byindex(net, set->index);
if (index == IPSET_INVALID_ID)
return -ENOENT;
@@ -37,7 +38,7 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
if (em->data)
return 0;
- ip_set_nfnl_put(index);
+ ip_set_nfnl_put(net, index);
return -ENOMEM;
}
@@ -45,7 +46,7 @@ static void em_ipset_destroy(struct tcf_proto *p, struct tcf_ematch *em)
{
const struct xt_set_info *set = (const void *) em->data;
if (set) {
- ip_set_nfnl_put(set->index);
+ ip_set_nfnl_put(qdisc_dev(p->q)->nd_net, set->index);
kfree((void *) em->data);
}
}
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 7c3de6ffa516..e5cef9567225 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -793,8 +793,10 @@ static int em_meta_change(struct tcf_proto *tp, void *data, int len,
goto errout;
meta = kzalloc(sizeof(*meta), GFP_KERNEL);
- if (meta == NULL)
+ if (meta == NULL) {
+ err = -ENOMEM;
goto errout;
+ }
memcpy(&meta->lvalue.hdr, &hdr->left, sizeof(hdr->left));
memcpy(&meta->rvalue.hdr, &hdr->right, sizeof(hdr->right));
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2adda7fa2d39..cd81505662b8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -737,9 +737,11 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
const struct Qdisc_class_ops *cops;
unsigned long cl;
u32 parentid;
+ int drops;
if (n == 0)
return;
+ drops = max_t(int, n, 0);
while ((parentid = sch->parent)) {
if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
return;
@@ -756,6 +758,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
cops->put(sch, cl);
}
sch->q.qlen -= n;
+ sch->qstats.drops += drops;
}
}
EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a74e278654aa..7fc899a943a8 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -829,7 +829,7 @@ void dev_deactivate_many(struct list_head *head)
struct net_device *dev;
bool sync_needed = false;
- list_for_each_entry(dev, head, unreg_list) {
+ list_for_each_entry(dev, head, close_list) {
netdev_for_each_tx_queue(dev, dev_deactivate_queue,
&noop_qdisc);
if (dev_ingress_queue(dev))
@@ -848,7 +848,7 @@ void dev_deactivate_many(struct list_head *head)
synchronize_net();
/* Wait for outstanding qdisc_run calls. */
- list_for_each_entry(dev, head, unreg_list)
+ list_for_each_entry(dev, head, close_list)
while (some_qdisc_is_busy(dev))
yield();
}
@@ -857,7 +857,7 @@ void dev_deactivate(struct net_device *dev)
{
LIST_HEAD(single);
- list_add(&dev->unreg_list, &single);
+ list_add(&dev->close_list, &single);
dev_deactivate_many(&single);
list_del(&single);
}
@@ -910,11 +910,12 @@ void dev_shutdown(struct net_device *dev)
}
void psched_ratecfg_precompute(struct psched_ratecfg *r,
- const struct tc_ratespec *conf)
+ const struct tc_ratespec *conf,
+ u64 rate64)
{
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
- r->rate_bytes_ps = conf->rate;
+ r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
r->mult = 1;
/*
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 863846cc5513..0e1e38b40025 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -997,6 +997,8 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
[TCA_HTB_CTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
[TCA_HTB_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
[TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 },
+ [TCA_HTB_RATE64] = { .type = NLA_U64 },
+ [TCA_HTB_CEIL64] = { .type = NLA_U64 },
};
static void htb_work_func(struct work_struct *work)
@@ -1114,6 +1116,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
opt.level = cl->level;
if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
+ if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) &&
+ nla_put_u64(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps))
+ goto nla_put_failure;
+ if ((cl->ceil.rate_bytes_ps >= (1ULL << 32)) &&
+ nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps))
+ goto nla_put_failure;
nla_nest_end(skb, nest);
spin_unlock_bh(root_lock);
@@ -1332,6 +1340,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_opt *hopt;
+ u64 rate64, ceil64;
/* extract all subattrs from opt attr */
if (!opt)
@@ -1491,8 +1500,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
cl->prio = TC_HTB_NUMPRIO - 1;
}
- psched_ratecfg_precompute(&cl->rate, &hopt->rate);
- psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
+ rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
+
+ ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;
+
+ psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
+ psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);
cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1aaf1b6e51a2..b0571224f3c9 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -341,9 +341,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
q->tokens = q->buffer;
q->ptokens = q->mtu;
- psched_ratecfg_precompute(&q->rate, &rtab->rate);
+ psched_ratecfg_precompute(&q->rate, &rtab->rate, 0);
if (ptab) {
- psched_ratecfg_precompute(&q->peak, &ptab->rate);
+ psched_ratecfg_precompute(&q->peak, &ptab->rate, 0);
q->peak_present = true;
} else {
q->peak_present = false;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 911b71b26b0e..72046b9729a8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5890,7 +5890,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
int low, high, remaining, index;
unsigned int rover;
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(sock_net(sk), &low, &high);
remaining = (high - low) + 1;
rover = net_random() % remaining + low;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b9c3f9e943a9..d6e7f98fbfbf 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -468,7 +468,7 @@ expired:
}
err = __xfrm_state_delete(x);
- if (!err && x->id.spi)
+ if (!err)
km_state_expired(x, 1, 0);
xfrm_audit_state_delete(x, err ? 0 : 1,