summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--net/8021q/vlan_core.c9
-rw-r--r--net/9p/protocol.c17
-rw-r--r--net/9p/trans_virtio.c2
-rw-r--r--net/appletalk/ddp.c9
-rw-r--r--net/atm/ioctl.c7
-rw-r--r--net/batman-adv/bat_v_elp.c3
-rw-r--r--net/batman-adv/bat_v_ogm.c7
-rw-r--r--net/batman-adv/hard-interface.c14
-rw-r--r--net/batman-adv/soft-interface.c3
-rw-r--r--net/batman-adv/translation-table.c1
-rw-r--r--net/batman-adv/types.h6
-rw-r--r--net/bluetooth/hci_conn.c78
-rw-r--r--net/bluetooth/hci_core.c8
-rw-r--r--net/bluetooth/hci_event.c36
-rw-r--r--net/bluetooth/hci_sock.c3
-rw-r--r--net/bluetooth/hci_sysfs.c23
-rw-r--r--net/bluetooth/l2cap_core.c5
-rw-r--r--net/bluetooth/l2cap_sock.c2
-rw-r--r--net/bridge/br_forward.c4
-rw-r--r--net/bridge/br_if.c5
-rw-r--r--net/bridge/br_input.c4
-rw-r--r--net/can/bcm.c12
-rw-r--r--net/ceph/messenger.c79
-rw-r--r--net/ceph/osd_client.c20
-rw-r--r--net/core/dev.c22
-rw-r--r--net/core/drop_monitor.c4
-rw-r--r--net/core/pktgen.c14
-rw-r--r--net/core/rtnetlink.c15
-rw-r--r--net/core/skbuff.c34
-rw-r--r--net/core/sock.c36
-rw-r--r--net/dccp/ipv4.c18
-rw-r--r--net/dccp/ipv6.c20
-rw-r--r--net/dccp/options.c2
-rw-r--r--net/dccp/output.c2
-rw-r--r--net/dccp/proto.c30
-rw-r--r--net/ife/ife.c1
-rw-r--r--net/ipv4/esp4.c4
-rw-r--r--net/ipv4/igmp.c9
-rw-r--r--net/ipv4/inet_hashtables.c17
-rw-r--r--net/ipv4/inet_timewait_sock.c8
-rw-r--r--net/ipv4/ip_gre.c11
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_vti.c4
-rw-r--r--net/ipv4/netfilter/nf_socket_ipv4.c6
-rw-r--r--net/ipv4/route.c6
-rw-r--r--net/ipv4/tcp.c27
-rw-r--r--net/ipv4/tcp_fastopen.c6
-rw-r--r--net/ipv4/tcp_input.c34
-rw-r--r--net/ipv4/tcp_metrics.c85
-rw-r--r--net/ipv4/tcp_output.c40
-rw-r--r--net/ipv4/tcp_recovery.c2
-rw-r--r--net/ipv4/tcp_timer.c4
-rw-r--r--net/ipv6/addrconf.c19
-rw-r--r--net/ipv6/esp6.c4
-rw-r--r--net/ipv6/icmp.c22
-rw-r--r--net/ipv6/ip6_fib.c6
-rw-r--r--net/ipv6/ip6_flowlabel.c2
-rw-r--r--net/ipv6/ip6_gre.c3
-rw-r--r--net/ipv6/ip6_output.c10
-rw-r--r--net/ipv6/ip6_vti.c4
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/ndisc.c3
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c2
-rw-r--r--net/ipv6/reassembly.c4
-rw-r--r--net/ipv6/syncookies.c7
-rw-r--r--net/ipv6/udp.c2
-rw-r--r--net/ipv6/xfrm6_policy.c4
-rw-r--r--net/kcm/kcmsock.c15
-rw-r--r--net/key/af_key.c4
-rw-r--r--net/l2tp/l2tp_ip6.c2
-rw-r--r--net/llc/llc_input.c13
-rw-r--r--net/llc/llc_s_ac.c3
-rw-r--r--net/llc/llc_station.c3
-rw-r--r--net/mac80211/cfg.c4
-rw-r--r--net/mac80211/mesh_plink.c10
-rw-r--r--net/mac80211/tx.c3
-rw-r--r--net/netfilter/ipset/ip_set_core.c31
-rw-r--r--net/netfilter/ipset/ip_set_hash_netportnet.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c74
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c8
-rw-r--r--net/netfilter/nf_conntrack_ftp.c2
-rw-r--r--net/netfilter/nf_conntrack_helper.c4
-rw-r--r--net/netfilter/nf_conntrack_netlink.c77
-rw-r--r--net/netfilter/nf_conntrack_proto_sctp.c6
-rw-r--r--net/netfilter/nf_conntrack_sip.c2
-rw-r--r--net/netfilter/nf_queue.c2
-rw-r--r--net/netfilter/nf_tables_api.c664
-rw-r--r--net/netfilter/nf_tables_trace.c9
-rw-r--r--net/netfilter/nfnetlink_acct.c11
-rw-r--r--net/netfilter/nfnetlink_cthelper.c11
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c22
-rw-r--r--net/netfilter/nfnetlink_log.c13
-rw-r--r--net/netfilter/nfnetlink_osf.c8
-rw-r--r--net/netfilter/nfnetlink_queue.c16
-rw-r--r--net/netfilter/nft_byteorder.c14
-rw-r--r--net/netfilter/nft_chain_filter.c11
-rw-r--r--net/netfilter/nft_compat.c11
-rw-r--r--net/netfilter/nft_dynset.c9
-rw-r--r--net/netfilter/nft_flow_offload.c26
-rw-r--r--net/netfilter/nft_objref.c8
-rw-r--r--net/netfilter/nft_payload.c2
-rw-r--r--net/netfilter/nft_set_rbtree.c2
-rw-r--r--net/netfilter/xt_owner.c37
-rw-r--r--net/netfilter/xt_recent.c2
-rw-r--r--net/netfilter/xt_sctp.c2
-rw-r--r--net/netfilter/xt_u32.c21
-rw-r--r--net/netlabel/netlabel_kapi.c3
-rw-r--r--net/netlink/af_netlink.c9
-rw-r--r--net/netlink/diag.c7
-rw-r--r--net/netlink/genetlink.c35
-rw-r--r--net/netrom/af_netrom.c5
-rw-r--r--net/nfc/core.c4
-rw-r--r--net/nfc/hci/llc_shdlc.c10
-rw-r--r--net/nfc/llcp.h8
-rw-r--r--net/nfc/llcp_commands.c47
-rw-r--r--net/nfc/llcp_core.c72
-rw-r--r--net/nfc/nci/core.c5
-rw-r--r--net/nfc/nci/spi.c2
-rw-r--r--net/nfc/nfc.h2
-rw-r--r--net/packet/af_packet.c32
-rw-r--r--net/packet/internal.h2
-rw-r--r--net/psample/psample.c3
-rw-r--r--net/rds/tcp_connect.c4
-rw-r--r--net/rds/tcp_listen.c2
-rw-r--r--net/rfkill/rfkill-gpio.c12
-rw-r--r--net/rose/af_rose.c43
-rw-r--r--net/sched/Kconfig28
-rw-r--r--net/sched/Makefile2
-rw-r--r--net/sched/act_pedit.c1
-rw-r--r--net/sched/cls_flow.c2
-rw-r--r--net/sched/cls_fw.c11
-rw-r--r--net/sched/cls_route.c1
-rw-r--r--net/sched/cls_rsvp.c28
-rw-r--r--net/sched/cls_rsvp.h775
-rw-r--r--net/sched/cls_rsvp6.c28
-rw-r--r--net/sched/cls_u32.c77
-rw-r--r--net/sched/sch_api.c58
-rw-r--r--net/sched/sch_cake.c2
-rw-r--r--net/sched/sch_cbq.c2
-rw-r--r--net/sched/sch_fq_codel.c2
-rw-r--r--net/sched/sch_hfsc.c14
-rw-r--r--net/sched/sch_mqprio.c144
-rw-r--r--net/sched/sch_netem.c59
-rw-r--r--net/sched/sch_plug.c2
-rw-r--r--net/sched/sch_qfq.c29
-rw-r--r--net/sched/sch_sfq.c2
-rw-r--r--net/sctp/associola.c3
-rw-r--r--net/sctp/sm_sideeffect.c5
-rw-r--r--net/sctp/socket.c7
-rw-r--r--net/smc/af_smc.c43
-rw-r--r--net/smc/smc.h5
-rw-r--r--net/smc/smc_cdc.c2
-rw-r--r--net/smc/smc_close.c26
-rw-r--r--net/smc/smc_close.h1
-rw-r--r--net/socket.c83
-rw-r--r--net/sunrpc/svcsock.c27
-rw-r--r--net/tipc/netlink.c4
-rw-r--r--net/tipc/netlink_compat.c1
-rw-r--r--net/unix/af_unix.c13
-rw-r--r--net/unix/scm.c6
-rw-r--r--net/vmw_vsock/virtio_transport_common.c2
-rw-r--r--net/wireless/certs/wens.hex87
-rw-r--r--net/wireless/nl80211.c2
-rw-r--r--net/wireless/wext-core.c6
-rw-r--r--net/xfrm/Makefile2
-rw-r--r--net/xfrm/xfrm_interface_core.c (renamed from net/xfrm/xfrm_interface.c)26
-rw-r--r--net/xfrm/xfrm_policy.c6
-rw-r--r--net/xfrm/xfrm_user.c13
168 files changed, 1975 insertions, 2046 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 4f60e86f4..e92c91431 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -380,6 +380,8 @@ int vlan_vids_add_by_dev(struct net_device *dev,
return 0;
list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+ if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+ continue;
err = vlan_vid_add(dev, vid_info->proto, vid_info->vid);
if (err)
goto unwind;
@@ -390,6 +392,8 @@ unwind:
list_for_each_entry_continue_reverse(vid_info,
&vlan_info->vid_list,
list) {
+ if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+ continue;
vlan_vid_del(dev, vid_info->proto, vid_info->vid);
}
@@ -409,8 +413,11 @@ void vlan_vids_del_by_dev(struct net_device *dev,
if (!vlan_info)
return;
- list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+ list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+ if (!vlan_hw_filter_capable(by_dev, vid_info->proto))
+ continue;
vlan_vid_del(dev, vid_info->proto, vid_info->vid);
+ }
}
EXPORT_SYMBOL(vlan_vids_del_by_dev);
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 462ba144c..9104a2fce 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -243,6 +243,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
uint16_t *nwname = va_arg(ap, uint16_t *);
char ***wnames = va_arg(ap, char ***);
+ *wnames = NULL;
+
errcode = p9pdu_readf(pdu, proto_version,
"w", nwname);
if (!errcode) {
@@ -252,6 +254,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
GFP_NOFS);
if (!*wnames)
errcode = -ENOMEM;
+ else
+ (*wnames)[0] = NULL;
}
if (!errcode) {
@@ -263,8 +267,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
proto_version,
"s",
&(*wnames)[i]);
- if (errcode)
+ if (errcode) {
+ (*wnames)[i] = NULL;
break;
+ }
}
}
@@ -272,11 +278,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt,
if (*wnames) {
int i;
- for (i = 0; i < *nwname; i++)
+ for (i = 0; i < *nwname; i++) {
+ if (!(*wnames)[i])
+ break;
kfree((*wnames)[i]);
+ }
+ kfree(*wnames);
+ *wnames = NULL;
}
- kfree(*wnames);
- *wnames = NULL;
}
}
break;
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index f7cd8e018..6b3357a77 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -409,7 +409,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
struct page **in_pages = NULL, **out_pages = NULL;
struct virtio_chan *chan = client->trans;
struct scatterlist *sgs[4];
- size_t offs;
+ size_t offs = 0;
int need_drop = 0;
int kicked = 0;
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 20ec8e7f9..c4f1bfe6e 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1808,15 +1808,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
}
case TIOCINQ: {
- /*
- * These two are safe on a single CPU system as only
- * user tasks fiddle here
- */
- struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+ struct sk_buff *skb;
long amount = 0;
+ spin_lock_irq(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
if (skb)
amount = skb->len - sizeof(struct ddpehdr);
+ spin_unlock_irq(&sk->sk_receive_queue.lock);
rc = put_user(amount, (int __user *)argp);
break;
}
diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c
index 2ff0e5e47..38f7f164e 100644
--- a/net/atm/ioctl.c
+++ b/net/atm/ioctl.c
@@ -71,14 +71,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd,
case SIOCINQ:
{
struct sk_buff *skb;
+ int amount;
if (sock->state != SS_CONNECTED) {
error = -EINVAL;
goto done;
}
+ spin_lock_irq(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
- error = put_user(skb ? skb->len : 0,
- (int __user *)argp) ? -EFAULT : 0;
+ amount = skb ? skb->len : 0;
+ spin_unlock_irq(&sk->sk_receive_queue.lock);
+ error = put_user(amount, (int __user *)argp) ? -EFAULT : 0;
goto done;
}
case SIOCGSTAMP: /* borrowed from IP */
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index af3da6cdf..17100d9ce 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -513,7 +513,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb,
struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
struct batadv_elp_packet *elp_packet;
struct batadv_hard_iface *primary_if;
- struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb);
+ struct ethhdr *ethhdr;
bool res;
int ret = NET_RX_DROP;
@@ -521,6 +521,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb,
if (!res)
goto free_skb;
+ ethhdr = eth_hdr(skb);
if (batadv_is_my_mac(bat_priv, ethhdr->h_source))
goto free_skb;
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 04a620fd1..5d4232d8d 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -119,8 +119,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb,
{
struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- if (hard_iface->if_status != BATADV_IF_ACTIVE)
+ if (hard_iface->if_status != BATADV_IF_ACTIVE) {
+ kfree_skb(skb);
return;
+ }
batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX);
batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES,
@@ -832,7 +834,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
{
struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
struct batadv_ogm2_packet *ogm_packet;
- struct ethhdr *ethhdr = eth_hdr(skb);
+ struct ethhdr *ethhdr;
int ogm_offset;
u8 *packet_pos;
int ret = NET_RX_DROP;
@@ -846,6 +848,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN))
goto free_skb;
+ ethhdr = eth_hdr(skb);
if (batadv_is_my_mac(bat_priv, ethhdr->h_source))
goto free_skb;
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 6d68cdb9d..0d5519fcb 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -643,7 +643,19 @@ out:
*/
void batadv_update_min_mtu(struct net_device *soft_iface)
{
- soft_iface->mtu = batadv_hardif_min_mtu(soft_iface);
+ struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+ int limit_mtu;
+ int mtu;
+
+ mtu = batadv_hardif_min_mtu(soft_iface);
+
+ if (bat_priv->mtu_set_by_user)
+ limit_mtu = bat_priv->mtu_set_by_user;
+ else
+ limit_mtu = ETH_DATA_LEN;
+
+ mtu = min(mtu, limit_mtu);
+ dev_set_mtu(soft_iface, mtu);
/* Check if the local translate table should be cleaned up to match a
* new (and smaller) MTU.
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 1003abb8c..7447dbd30 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -167,11 +167,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
{
+ struct batadv_priv *bat_priv = netdev_priv(dev);
+
/* check ranges */
if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev))
return -EINVAL;
dev->mtu = new_mtu;
+ bat_priv->mtu_set_by_user = new_mtu;
return 0;
}
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 6bdb70c93..c64d58c1b 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -793,7 +793,6 @@ check_roaming:
if (roamed_back) {
batadv_tt_global_free(bat_priv, tt_global,
"Roaming canceled");
- tt_global = NULL;
} else {
/* The global entry has to be marked as ROAMING and
* has to be kept for consistency purpose
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 37598ae1d..34c18f72a 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1515,6 +1515,12 @@ struct batadv_priv {
struct net_device *soft_iface;
/**
+ * @mtu_set_by_user: MTU was set once by user
+ * protected by rtnl_lock
+ */
+ int mtu_set_by_user;
+
+ /**
* @bat_counters: mesh internal traffic statistic counters (see
* batadv_counters)
*/
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 1b50e4ef2..0e837feaa 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -125,13 +125,11 @@ static void hci_conn_cleanup(struct hci_conn *conn)
if (hdev->notify)
hdev->notify(hdev, HCI_NOTIFY_CONN_DEL);
- hci_conn_del_sysfs(conn);
-
debugfs_remove_recursive(conn->debugfs);
- hci_dev_put(hdev);
+ hci_conn_del_sysfs(conn);
- hci_conn_put(conn);
+ hci_dev_put(hdev);
}
static void le_scan_cleanup(struct work_struct *work)
@@ -1204,6 +1202,15 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
return ERR_PTR(-EOPNOTSUPP);
}
+ /* Reject outgoing connection to device with same BD ADDR against
+ * CVE-2020-26555
+ */
+ if (!bacmp(&hdev->bdaddr, dst)) {
+ bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n",
+ dst);
+ return ERR_PTR(-ECONNREFUSED);
+ }
+
acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
if (!acl) {
acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER);
@@ -1379,34 +1386,41 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type,
if (!test_bit(HCI_CONN_AUTH, &conn->flags))
goto auth;
- /* An authenticated FIPS approved combination key has sufficient
- * security for security level 4. */
- if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 &&
- sec_level == BT_SECURITY_FIPS)
- goto encrypt;
-
- /* An authenticated combination key has sufficient security for
- security level 3. */
- if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 ||
- conn->key_type == HCI_LK_AUTH_COMBINATION_P256) &&
- sec_level == BT_SECURITY_HIGH)
- goto encrypt;
-
- /* An unauthenticated combination key has sufficient security for
- security level 1 and 2. */
- if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 ||
- conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) &&
- (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW))
- goto encrypt;
-
- /* A combination key has always sufficient security for the security
- levels 1 or 2. High security level requires the combination key
- is generated using maximum PIN code length (16).
- For pre 2.1 units. */
- if (conn->key_type == HCI_LK_COMBINATION &&
- (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW ||
- conn->pin_length == 16))
- goto encrypt;
+ switch (conn->key_type) {
+ case HCI_LK_AUTH_COMBINATION_P256:
+ /* An authenticated FIPS approved combination key has
+ * sufficient security for security level 4 or lower.
+ */
+ if (sec_level <= BT_SECURITY_FIPS)
+ goto encrypt;
+ break;
+ case HCI_LK_AUTH_COMBINATION_P192:
+ /* An authenticated combination key has sufficient security for
+ * security level 3 or lower.
+ */
+ if (sec_level <= BT_SECURITY_HIGH)
+ goto encrypt;
+ break;
+ case HCI_LK_UNAUTH_COMBINATION_P192:
+ case HCI_LK_UNAUTH_COMBINATION_P256:
+ /* An unauthenticated combination key has sufficient security
+ * for security level 2 or lower.
+ */
+ if (sec_level <= BT_SECURITY_MEDIUM)
+ goto encrypt;
+ break;
+ case HCI_LK_COMBINATION:
+ /* A combination key has always sufficient security for the
+ * security levels 2 or lower. High security level requires the
+ * combination key is generated using maximum PIN code length
+ * (16). For pre 2.1 units.
+ */
+ if (sec_level <= BT_SECURITY_MEDIUM || conn->pin_length == 16)
+ goto encrypt;
+ break;
+ default:
+ break;
+ }
auth:
if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags))
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 9fdc772ab..4d89e38dc 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3193,7 +3193,11 @@ int hci_register_dev(struct hci_dev *hdev)
if (id < 0)
return id;
- snprintf(hdev->name, sizeof(hdev->name), "hci%d", id);
+ error = dev_set_name(&hdev->dev, "hci%u", id);
+ if (error)
+ return error;
+
+ hdev->name = dev_name(&hdev->dev);
hdev->id = id;
BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
@@ -3215,8 +3219,6 @@ int hci_register_dev(struct hci_dev *hdev)
if (!IS_ERR_OR_NULL(bt_debugfs))
hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs);
- dev_set_name(&hdev->dev, "%s", hdev->name);
-
error = device_add(&hdev->dev);
if (error < 0)
goto err_wqueue;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index dd7bf437d..7ce6932d9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -25,6 +25,8 @@
/* Bluetooth HCI event handling. */
#include <asm/unaligned.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -1699,7 +1701,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
return;
}
- set_bit(HCI_INQUIRY, &hdev->flags);
+ if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY))
+ set_bit(HCI_INQUIRY, &hdev->flags);
}
static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status)
@@ -2510,6 +2513,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
BT_DBG("%s bdaddr %pMR type 0x%x", hdev->name, &ev->bdaddr,
ev->link_type);
+ /* Reject incoming connection from device with same BD ADDR against
+ * CVE-2020-26555
+ */
+ if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) {
+ bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n",
+ &ev->bdaddr);
+ hci_reject_conn(hdev, &ev->bdaddr);
+ return;
+ }
+
mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type,
&flags);
@@ -3816,6 +3829,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb)
if (!conn)
goto unlock;
+ /* Ignore NULL link key against CVE-2020-26555 */
+ if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) {
+ bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR",
+ &ev->bdaddr);
+ hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
+ hci_conn_drop(conn);
+ goto unlock;
+ }
+
hci_conn_hold(conn);
conn->disc_timeout = HCI_DISCONN_TIMEOUT;
hci_conn_drop(conn);
@@ -4294,8 +4316,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn)
* available, then do not declare that OOB data is
* present.
*/
- if (!memcmp(data->rand256, ZERO_KEY, 16) ||
- !memcmp(data->hash256, ZERO_KEY, 16))
+ if (!crypto_memneq(data->rand256, ZERO_KEY, 16) ||
+ !crypto_memneq(data->hash256, ZERO_KEY, 16))
return 0x00;
return 0x02;
@@ -4305,8 +4327,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn)
* not supported by the hardware, then check that if
* P-192 data values are present.
*/
- if (!memcmp(data->rand192, ZERO_KEY, 16) ||
- !memcmp(data->hash192, ZERO_KEY, 16))
+ if (!crypto_memneq(data->rand192, ZERO_KEY, 16) ||
+ !crypto_memneq(data->hash192, ZERO_KEY, 16))
return 0x00;
return 0x01;
@@ -4322,7 +4344,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
hci_dev_lock(hdev);
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
- if (!conn)
+ if (!conn || !hci_conn_ssp_enabled(conn))
goto unlock;
hci_conn_hold(conn);
@@ -4557,7 +4579,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev,
hci_dev_lock(hdev);
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
- if (!conn)
+ if (!conn || !hci_conn_ssp_enabled(conn))
goto unlock;
/* Reset the authentication requirement to unknown */
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 182c3c5b8..a7e5bca9f 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -430,7 +430,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
ni->type = hdev->dev_type;
ni->bus = hdev->bus;
bacpy(&ni->bdaddr, &hdev->bdaddr);
- memcpy(ni->name, hdev->name, 8);
+ memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name,
+ strnlen(hdev->name, sizeof(ni->name)), '\0');
opcode = cpu_to_le16(HCI_MON_NEW_INDEX);
break;
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index ccd2c377b..266112c96 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -33,7 +33,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn)
{
struct hci_dev *hdev = conn->hdev;
- BT_DBG("conn %p", conn);
+ bt_dev_dbg(hdev, "conn %p", conn);
conn->dev.type = &bt_link;
conn->dev.class = bt_class;
@@ -46,27 +46,30 @@ void hci_conn_add_sysfs(struct hci_conn *conn)
{
struct hci_dev *hdev = conn->hdev;
- BT_DBG("conn %p", conn);
+ bt_dev_dbg(hdev, "conn %p", conn);
if (device_is_registered(&conn->dev))
return;
dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
- if (device_add(&conn->dev) < 0) {
+ if (device_add(&conn->dev) < 0)
bt_dev_err(hdev, "failed to register connection device");
- return;
- }
-
- hci_dev_hold(hdev);
}
void hci_conn_del_sysfs(struct hci_conn *conn)
{
struct hci_dev *hdev = conn->hdev;
- if (!device_is_registered(&conn->dev))
+ bt_dev_dbg(hdev, "conn %p", conn);
+
+ if (!device_is_registered(&conn->dev)) {
+ /* If device_add() has *not* succeeded, use *only* put_device()
+ * to drop the reference count.
+ */
+ put_device(&conn->dev);
return;
+ }
while (1) {
struct device *dev;
@@ -78,9 +81,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn)
put_device(dev);
}
- device_del(&conn->dev);
-
- hci_dev_put(hdev);
+ device_unregister(&conn->dev);
}
static void bt_host_release(struct device *dev)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fcc471f92..9346fae5d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5705,9 +5705,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn,
if (!chan)
goto done;
+ chan = l2cap_chan_hold_unless_zero(chan);
+ if (!chan)
+ goto done;
+
l2cap_chan_lock(chan);
l2cap_chan_del(chan, ECONNREFUSED);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
done:
mutex_unlock(&conn->chan_lock);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1c6d01a27..b831e5fe3 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -45,6 +45,7 @@ static const struct proto_ops l2cap_sock_ops;
static void l2cap_sock_init(struct sock *sk, struct sock *parent);
static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
int proto, gfp_t prio, int kern);
+static void l2cap_sock_cleanup_listen(struct sock *parent);
bool l2cap_is_socket(struct socket *sock)
{
@@ -1205,6 +1206,7 @@ static int l2cap_sock_release(struct socket *sock)
if (!sk)
return 0;
+ l2cap_sock_cleanup_listen(sk);
bt_sock_unlink(&l2cap_sk_list, sk);
err = l2cap_sock_shutdown(sock, 2);
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 48ddc60b4..c07a47d65 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -122,7 +122,7 @@ static int deliver_clone(const struct net_bridge_port *prev,
skb = skb_clone(skb, GFP_ATOMIC);
if (!skb) {
- dev->stats.tx_dropped++;
+ DEV_STATS_INC(dev, tx_dropped);
return -ENOMEM;
}
@@ -261,7 +261,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb,
skb = skb_copy(skb, GFP_ATOMIC);
if (!skb) {
- dev->stats.tx_dropped++;
+ DEV_STATS_INC(dev, tx_dropped);
return;
}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index b5fb2b682..ab539551b 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -161,8 +161,9 @@ void br_manage_promisc(struct net_bridge *br)
* This lets us disable promiscuous mode and write
* this config to hw.
*/
- if (br->auto_cnt == 0 ||
- (br->auto_cnt == 1 && br_auto_port(p)))
+ if ((p->dev->priv_flags & IFF_UNICAST_FLT) &&
+ (br->auto_cnt == 0 ||
+ (br->auto_cnt == 1 && br_auto_port(p))))
br_port_clear_promisc(p);
else
br_port_set_promisc(p);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 14c2fdc26..f3938337f 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -146,12 +146,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
if ((mdst && mdst->host_joined) ||
br_multicast_is_router(br)) {
local_rcv = true;
- br->dev->stats.multicast++;
+ DEV_STATS_INC(br->dev, multicast);
}
mcast_hit = true;
} else {
local_rcv = true;
- br->dev->stats.multicast++;
+ DEV_STATS_INC(br->dev, multicast);
}
break;
case BR_PKT_UNICAST:
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 61269cc2f..1c9953c68 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1520,6 +1520,12 @@ static int bcm_release(struct socket *sock)
lock_sock(sk);
+#if IS_ENABLED(CONFIG_PROC_FS)
+ /* remove procfs entry */
+ if (net->can.bcmproc_dir && bo->bcm_proc_read)
+ remove_proc_entry(bo->procname, net->can.bcmproc_dir);
+#endif /* CONFIG_PROC_FS */
+
list_for_each_entry_safe(op, next, &bo->tx_ops, list)
bcm_remove_op(op);
@@ -1555,12 +1561,6 @@ static int bcm_release(struct socket *sock)
list_for_each_entry_safe(op, next, &bo->rx_ops, list)
bcm_remove_op(op);
-#if IS_ENABLED(CONFIG_PROC_FS)
- /* remove procfs entry */
- if (net->can.bcmproc_dir && bo->bcm_proc_read)
- remove_proc_entry(bo->procname, net->can.bcmproc_dir);
-#endif /* CONFIG_PROC_FS */
-
/* remove device reference */
if (bo->bound) {
bo->bound = 0;
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 21bd37ec5..7fd18e107 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -462,7 +462,7 @@ static void set_sock_callbacks(struct socket *sock,
*/
static int ceph_tcp_connect(struct ceph_connection *con)
{
- struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
+ struct sockaddr_storage ss = con->peer_addr.in_addr; /* align */
struct socket *sock;
unsigned int noio_flag;
int ret;
@@ -471,7 +471,7 @@ static int ceph_tcp_connect(struct ceph_connection *con)
/* sock_create_kern() allocates with GFP_KERNEL */
noio_flag = memalloc_noio_save();
- ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
+ ret = sock_create_kern(read_pnet(&con->msgr->net), ss.ss_family,
SOCK_STREAM, IPPROTO_TCP, &sock);
memalloc_noio_restore(noio_flag);
if (ret)
@@ -487,8 +487,8 @@ static int ceph_tcp_connect(struct ceph_connection *con)
dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
con_sock_state_connecting(con);
- ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
- O_NONBLOCK);
+ ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss),
+ O_NONBLOCK);
if (ret == -EINPROGRESS) {
dout("connect %s EINPROGRESS sk_state = %u\n",
ceph_pr_addr(&con->peer_addr.in_addr),
@@ -1824,14 +1824,15 @@ static int verify_hello(struct ceph_connection *con)
return 0;
}
-static bool addr_is_blank(struct sockaddr_storage *ss)
+static bool addr_is_blank(struct ceph_entity_addr *addr)
{
- struct in_addr *addr = &((struct sockaddr_in *)ss)->sin_addr;
- struct in6_addr *addr6 = &((struct sockaddr_in6 *)ss)->sin6_addr;
+ struct sockaddr_storage ss = addr->in_addr; /* align */
+ struct in_addr *addr4 = &((struct sockaddr_in *)&ss)->sin_addr;
+ struct in6_addr *addr6 = &((struct sockaddr_in6 *)&ss)->sin6_addr;
- switch (ss->ss_family) {
+ switch (ss.ss_family) {
case AF_INET:
- return addr->s_addr == htonl(INADDR_ANY);
+ return addr4->s_addr == htonl(INADDR_ANY);
case AF_INET6:
return ipv6_addr_any(addr6);
default:
@@ -1839,25 +1840,25 @@ static bool addr_is_blank(struct sockaddr_storage *ss)
}
}
-static int addr_port(struct sockaddr_storage *ss)
+static int addr_port(struct ceph_entity_addr *addr)
{
- switch (ss->ss_family) {
+ switch (get_unaligned(&addr->in_addr.ss_family)) {
case AF_INET:
- return ntohs(((struct sockaddr_in *)ss)->sin_port);
+ return ntohs(get_unaligned(&((struct sockaddr_in *)&addr->in_addr)->sin_port));
case AF_INET6:
- return ntohs(((struct sockaddr_in6 *)ss)->sin6_port);
+ return ntohs(get_unaligned(&((struct sockaddr_in6 *)&addr->in_addr)->sin6_port));
}
return 0;
}
-static void addr_set_port(struct sockaddr_storage *ss, int p)
+static void addr_set_port(struct ceph_entity_addr *addr, int p)
{
- switch (ss->ss_family) {
+ switch (get_unaligned(&addr->in_addr.ss_family)) {
case AF_INET:
- ((struct sockaddr_in *)ss)->sin_port = htons(p);
+ put_unaligned(htons(p), &((struct sockaddr_in *)&addr->in_addr)->sin_port);
break;
case AF_INET6:
- ((struct sockaddr_in6 *)ss)->sin6_port = htons(p);
+ put_unaligned(htons(p), &((struct sockaddr_in6 *)&addr->in_addr)->sin6_port);
break;
}
}
@@ -1865,21 +1866,18 @@ static void addr_set_port(struct sockaddr_storage *ss, int p)
/*
* Unlike other *_pton function semantics, zero indicates success.
*/
-static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss,
+static int ceph_pton(const char *str, size_t len, struct ceph_entity_addr *addr,
char delim, const char **ipend)
{
- struct sockaddr_in *in4 = (struct sockaddr_in *) ss;
- struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) ss;
-
- memset(ss, 0, sizeof(*ss));
+ memset(&addr->in_addr, 0, sizeof(addr->in_addr));
- if (in4_pton(str, len, (u8 *)&in4->sin_addr.s_addr, delim, ipend)) {
- ss->ss_family = AF_INET;
+ if (in4_pton(str, len, (u8 *)&((struct sockaddr_in *)&addr->in_addr)->sin_addr.s_addr, delim, ipend)) {
+ put_unaligned(AF_INET, &addr->in_addr.ss_family);
return 0;
}
- if (in6_pton(str, len, (u8 *)&in6->sin6_addr.s6_addr, delim, ipend)) {
- ss->ss_family = AF_INET6;
+ if (in6_pton(str, len, (u8 *)&((struct sockaddr_in6 *)&addr->in_addr)->sin6_addr.s6_addr, delim, ipend)) {
+ put_unaligned(AF_INET6, &addr->in_addr.ss_family);
return 0;
}
@@ -1891,7 +1889,7 @@ static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss,
*/
#ifdef CONFIG_CEPH_LIB_USE_DNS_RESOLVER
static int ceph_dns_resolve_name(const char *name, size_t namelen,
- struct sockaddr_storage *ss, char delim, const char **ipend)
+ struct ceph_entity_addr *addr, char delim, const char **ipend)
{
const char *end, *delim_p;
char *colon_p, *ip_addr = NULL;
@@ -1920,7 +1918,7 @@ static int ceph_dns_resolve_name(const char *name, size_t namelen,
/* do dns_resolve upcall */
ip_len = dns_query(NULL, name, end - name, NULL, &ip_addr, NULL);
if (ip_len > 0)
- ret = ceph_pton(ip_addr, ip_len, ss, -1, NULL);
+ ret = ceph_pton(ip_addr, ip_len, addr, -1, NULL);
else
ret = -ESRCH;
@@ -1929,13 +1927,13 @@ static int ceph_dns_resolve_name(const char *name, size_t namelen,
*ipend = end;
pr_info("resolve '%.*s' (ret=%d): %s\n", (int)(end - name), name,
- ret, ret ? "failed" : ceph_pr_addr(ss));
+ ret, ret ? "failed" : ceph_pr_addr(&addr->in_addr));
return ret;
}
#else
static inline int ceph_dns_resolve_name(const char *name, size_t namelen,
- struct sockaddr_storage *ss, char delim, const char **ipend)
+ struct ceph_entity_addr *addr, char delim, const char **ipend)
{
return -EINVAL;
}
@@ -1946,13 +1944,13 @@ static inline int ceph_dns_resolve_name(const char *name, size_t namelen,
* then try to extract a hostname to resolve using userspace DNS upcall.
*/
static int ceph_parse_server_name(const char *name, size_t namelen,
- struct sockaddr_storage *ss, char delim, const char **ipend)
+ struct ceph_entity_addr *addr, char delim, const char **ipend)
{
int ret;
- ret = ceph_pton(name, namelen, ss, delim, ipend);
+ ret = ceph_pton(name, namelen, addr, delim, ipend);
if (ret)
- ret = ceph_dns_resolve_name(name, namelen, ss, delim, ipend);
+ ret = ceph_dns_resolve_name(name, namelen, addr, delim, ipend);
return ret;
}
@@ -1971,7 +1969,6 @@ int ceph_parse_ips(const char *c, const char *end,
dout("parse_ips on '%.*s'\n", (int)(end-c), c);
for (i = 0; i < max_count; i++) {
const char *ipend;
- struct sockaddr_storage *ss = &addr[i].in_addr;
int port;
char delim = ',';
@@ -1980,7 +1977,7 @@ int ceph_parse_ips(const char *c, const char *end,
p++;
}
- ret = ceph_parse_server_name(p, end - p, ss, delim, &ipend);
+ ret = ceph_parse_server_name(p, end - p, &addr[i], delim, &ipend);
if (ret)
goto bad;
ret = -EINVAL;
@@ -2011,9 +2008,9 @@ int ceph_parse_ips(const char *c, const char *end,
port = CEPH_MON_PORT;
}
- addr_set_port(ss, port);
+ addr_set_port(&addr[i], port);
- dout("parse_ips got %s\n", ceph_pr_addr(ss));
+ dout("parse_ips got %s\n", ceph_pr_addr(&addr[i].in_addr));
if (p == end)
break;
@@ -2052,7 +2049,7 @@ static int process_banner(struct ceph_connection *con)
*/
if (memcmp(&con->peer_addr, &con->actual_peer_addr,
sizeof(con->peer_addr)) != 0 &&
- !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
+ !(addr_is_blank(&con->actual_peer_addr) &&
con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
pr_warn("wrong peer, want %s/%d, got %s/%d\n",
ceph_pr_addr(&con->peer_addr.in_addr),
@@ -2066,13 +2063,13 @@ static int process_banner(struct ceph_connection *con)
/*
* did we learn our address?
*/
- if (addr_is_blank(&con->msgr->inst.addr.in_addr)) {
- int port = addr_port(&con->msgr->inst.addr.in_addr);
+ if (addr_is_blank(&con->msgr->inst.addr)) {
+ int port = addr_port(&con->msgr->inst.addr);
memcpy(&con->msgr->inst.addr.in_addr,
&con->peer_addr_for_me.in_addr,
sizeof(con->peer_addr_for_me.in_addr));
- addr_set_port(&con->msgr->inst.addr.in_addr, port);
+ addr_set_port(&con->msgr->inst.addr, port);
encode_my_addr(con->msgr);
dout("process_banner learned my addr is %s\n",
ceph_pr_addr(&con->msgr->inst.addr.in_addr));
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 713fe1fbc..90ebb0ba9 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3137,17 +3137,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq)
int ret;
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
- ret = wait_for_completion_interruptible(&lreq->reg_commit_wait);
+ ret = wait_for_completion_killable(&lreq->reg_commit_wait);
return ret ?: lreq->reg_commit_error;
}
-static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq)
+static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq,
+ unsigned long timeout)
{
- int ret;
+ long left;
dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id);
- ret = wait_for_completion_interruptible(&lreq->notify_finish_wait);
- return ret ?: lreq->notify_finish_error;
+ left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait,
+ ceph_timeout_jiffies(timeout));
+ if (left <= 0)
+ left = left ?: -ETIMEDOUT;
+ else
+ left = lreq->notify_finish_error; /* completed */
+
+ return left;
}
/*
@@ -4760,7 +4767,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
ret = linger_reg_commit_wait(lreq);
if (!ret)
- ret = linger_notify_finish_wait(lreq);
+ ret = linger_notify_finish_wait(lreq,
+ msecs_to_jiffies(2 * timeout * MSEC_PER_SEC));
else
dout("lreq %p failed to initiate notify %d\n", lreq, ret);
diff --git a/net/core/dev.c b/net/core/dev.c
index a9c8660a2..b5c9648c2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3200,6 +3200,14 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
if (gso_segs > dev->gso_max_segs)
return features & ~NETIF_F_GSO_MASK;
+ if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+ return features & ~NETIF_F_GSO_MASK;
+
+ if (!skb_shinfo(skb)->gso_type) {
+ skb_warn_bad_offload(skb);
+ return features & ~NETIF_F_GSO_MASK;
+ }
+
/* Support for GSO partial features requires software
* intervention before we can actually process the packets
* so we need to strip support for any partial features now
@@ -9035,24 +9043,16 @@ void netdev_run_todo(void)
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats)
{
-#if BITS_PER_LONG == 64
- BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
- memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
- /* zero out counters that only exist in rtnl_link_stats64 */
- memset((char *)stats64 + sizeof(*netdev_stats), 0,
- sizeof(*stats64) - sizeof(*netdev_stats));
-#else
- size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long);
- const unsigned long *src = (const unsigned long *)netdev_stats;
+ size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t);
+ const atomic_long_t *src = (atomic_long_t *)netdev_stats;
u64 *dst = (u64 *)stats64;
BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
for (i = 0; i < n; i++)
- dst[i] = src[i];
+ dst[i] = (unsigned long)atomic_long_read(&src[i]);
/* zero out counters that only exist in rtnl_link_stats64 */
memset((char *)stats64 + n * sizeof(u64), 0,
sizeof(*stats64) - n * sizeof(u64));
-#endif
}
EXPORT_SYMBOL(netdev_stats_to_stats64);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 2ed600012..52e559252 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -122,7 +122,7 @@ out:
}
static const struct genl_multicast_group dropmon_mcgrps[] = {
- { .name = "events", },
+ { .name = "events", .cap_sys_admin = 1 },
};
static void send_dm_alert(struct work_struct *work)
@@ -370,10 +370,12 @@ static const struct genl_ops dropmon_ops[] = {
{
.cmd = NET_DM_CMD_START,
.doit = net_dm_cmd_trace,
+ .flags = GENL_ADMIN_PERM,
},
{
.cmd = NET_DM_CMD_STOP,
.doit = net_dm_cmd_trace,
+ .flags = GENL_ADMIN_PERM,
},
};
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 3714cd9e3..3ade60ec4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -651,19 +651,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_puts(seq, " Flags: ");
for (i = 0; i < NR_PKT_FLAGS; i++) {
- if (i == F_FLOW_SEQ)
+ if (i == FLOW_SEQ_SHIFT)
if (!pkt_dev->cflows)
continue;
- if (pkt_dev->flags & (1 << i))
+ if (pkt_dev->flags & (1 << i)) {
seq_printf(seq, "%s ", pkt_flag_names[i]);
- else if (i == F_FLOW_SEQ)
- seq_puts(seq, "FLOW_RND ");
-
#ifdef CONFIG_XFRM
- if (i == F_IPSEC && pkt_dev->spi)
- seq_printf(seq, "spi:%u", pkt_dev->spi);
+ if (i == IPSEC_SHIFT && pkt_dev->spi)
+ seq_printf(seq, "spi:%u ", pkt_dev->spi);
#endif
+ } else if (i == FLOW_SEQ_SHIFT) {
+ seq_puts(seq, "FLOW_RND ");
+ }
}
seq_puts(seq, "\n");
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2837cc03f..0d3f724da 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2970,9 +2970,12 @@ replay:
ifname[0] = '\0';
ifm = nlmsg_data(nlh);
- if (ifm->ifi_index > 0)
+ if (ifm->ifi_index > 0) {
dev = __dev_get_by_index(net, ifm->ifi_index);
- else {
+ } else if (ifm->ifi_index < 0) {
+ NL_SET_ERR_MSG(extack, "ifindex can't be negative");
+ return -EINVAL;
+ } else {
if (ifname[0])
dev = __dev_get_by_name(net, ifname);
else
@@ -3436,7 +3439,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
ndm->ndm_ifindex = dev->ifindex;
ndm->ndm_state = ndm_state;
- if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
+ if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr))
goto nla_put_failure;
if (vid)
if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid))
@@ -3450,10 +3453,10 @@ nla_put_failure:
return -EMSGSIZE;
}
-static inline size_t rtnl_fdb_nlmsg_size(void)
+static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev)
{
return NLMSG_ALIGN(sizeof(struct ndmsg)) +
- nla_total_size(ETH_ALEN) + /* NDA_LLADDR */
+ nla_total_size(dev->addr_len) + /* NDA_LLADDR */
nla_total_size(sizeof(u16)) + /* NDA_VLAN */
0;
}
@@ -3465,7 +3468,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
struct sk_buff *skb;
int err = -ENOBUFS;
- skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC);
+ skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC);
if (!skb)
goto errout;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b7314a6cf..e03cd719b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3546,21 +3546,20 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
- skb_frag_t *frag = skb_shinfo(head_skb)->frags;
unsigned int mss = skb_shinfo(head_skb)->gso_size;
unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
- struct sk_buff *frag_skb = head_skb;
unsigned int offset = doffset;
unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
unsigned int partial_segs = 0;
unsigned int headroom;
unsigned int len = head_skb->len;
+ struct sk_buff *frag_skb;
+ skb_frag_t *frag;
__be16 proto;
bool csum, sg;
- int nfrags = skb_shinfo(head_skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
- int pos;
+ int nfrags, pos;
int dummy;
if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
@@ -3638,6 +3637,13 @@ normal:
headroom = skb_headroom(head_skb);
pos = skb_headlen(head_skb);
+ if (skb_orphan_frags(head_skb, GFP_ATOMIC))
+ return ERR_PTR(-ENOMEM);
+
+ nfrags = skb_shinfo(head_skb)->nr_frags;
+ frag = skb_shinfo(head_skb)->frags;
+ frag_skb = head_skb;
+
do {
struct sk_buff *nskb;
skb_frag_t *nskb_frag;
@@ -3662,6 +3668,10 @@ normal:
(skb_headlen(list_skb) == len || sg)) {
BUG_ON(skb_headlen(list_skb) > len);
+ nskb = skb_clone(list_skb, GFP_ATOMIC);
+ if (unlikely(!nskb))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3680,12 +3690,8 @@ normal:
frag++;
}
- nskb = skb_clone(list_skb, GFP_ATOMIC);
list_skb = list_skb->next;
- if (unlikely(!nskb))
- goto err;
-
if (unlikely(pskb_trim(nskb, len))) {
kfree_skb(nskb);
goto err;
@@ -3750,12 +3756,16 @@ normal:
skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+ if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
goto err;
while (pos < offset + len) {
if (i >= nfrags) {
+ if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
+ skb_zerocopy_clone(nskb, list_skb,
+ GFP_ATOMIC))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3769,10 +3779,6 @@ normal:
i--;
frag--;
}
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb,
- GFP_ATOMIC))
- goto err;
list_skb = list_skb->next;
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 347a55519..62d169bcf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -496,7 +496,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
sk_tx_queue_clear(sk);
- sk->sk_dst_pending_confirm = 0;
+ WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
dst_release(dst);
return NULL;
@@ -632,7 +632,8 @@ bool sk_mc_loop(struct sock *sk)
return false;
if (!sk)
return true;
- switch (sk->sk_family) {
+ /* IPV6_ADDRFORM can change sk->sk_family under us. */
+ switch (READ_ONCE(sk->sk_family)) {
case AF_INET:
return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
@@ -1319,7 +1320,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
if (!sock->ops->set_peek_off)
return -EOPNOTSUPP;
- v.val = sk->sk_peek_off;
+ v.val = READ_ONCE(sk->sk_peek_off);
break;
case SO_NOFCS:
v.val = sock_flag(sk, SOCK_NOFCS);
@@ -1349,7 +1350,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
- v.val = sk->sk_ll_usec;
+ v.val = READ_ONCE(sk->sk_ll_usec);
break;
#endif
@@ -1939,13 +1940,24 @@ kuid_t sock_i_uid(struct sock *sk)
}
EXPORT_SYMBOL(sock_i_uid);
-unsigned long sock_i_ino(struct sock *sk)
+unsigned long __sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock_bh(&sk->sk_callback_lock);
+ read_lock(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock_bh(&sk->sk_callback_lock);
+ read_unlock(&sk->sk_callback_lock);
+ return ino;
+}
+EXPORT_SYMBOL(__sock_i_ino);
+
+unsigned long sock_i_ino(struct sock *sk)
+{
+ unsigned long ino;
+
+ local_bh_disable();
+ ino = __sock_i_ino(sk);
+ local_bh_enable();
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
@@ -2060,9 +2072,9 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
break;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
break;
- if (sk->sk_err)
+ if (READ_ONCE(sk->sk_err))
break;
timeo = schedule_timeout(timeo);
}
@@ -2090,7 +2102,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
goto failure;
err = -EPIPE;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
goto failure;
if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
@@ -2527,7 +2539,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount)
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
- if (sk_under_memory_pressure(sk) &&
+ if (sk_under_global_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
sk_leave_memory_pressure(sk);
}
@@ -2548,7 +2560,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim);
int sk_set_peek_off(struct sock *sk, int val)
{
- sk->sk_peek_off = val;
+ WRITE_ONCE(sk->sk_peek_off, val);
return 0;
}
EXPORT_SYMBOL_GPL(sk_set_peek_off);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index c021d5dde..5281ac326 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -247,12 +247,12 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
int err;
struct net *net = dev_net(skb->dev);
- /* Only need dccph_dport & dccph_sport which are the first
- * 4 bytes in dccp header.
- * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
- */
- BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
- BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+ if (!pskb_may_pull(skb, offset + sizeof(*dh)))
+ return;
+ dh = (struct dccp_hdr *)(skb->data + offset);
+ if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh)))
+ return;
+ iph = (struct iphdr *)skb->data;
dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet_lookup_established(net, &dccp_hashinfo,
@@ -612,9 +612,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
- if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
-
ireq = inet_rsk(req);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
@@ -622,6 +619,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
ireq->ireq_family = AF_INET;
ireq->ir_iif = sk->sk_bound_dev_if;
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
/*
* Step 3: Process LISTEN state
*
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 88732ab48..72ceefbf2 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -71,7 +71,7 @@ static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
- const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
+ const struct ipv6hdr *hdr;
const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct ipv6_pinfo *np;
@@ -80,12 +80,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
__u64 seq;
struct net *net = dev_net(skb->dev);
- /* Only need dccph_dport & dccph_sport which are the first
- * 4 bytes in dccp header.
- * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
- */
- BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
- BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+ if (!pskb_may_pull(skb, offset + sizeof(*dh)))
+ return;
+ dh = (struct dccp_hdr *)(skb->data + offset);
+ if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh)))
+ return;
+ hdr = (const struct ipv6hdr *)skb->data;
dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet6_lookup_established(net, &dccp_hashinfo,
@@ -349,15 +349,15 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
- if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
-
ireq = inet_rsk(req);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
ireq->ireq_family = AF_INET6;
ireq->ir_mark = inet_request_mark(sk, skb);
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 4e40db017..3c464d63b 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -60,7 +60,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
(dh->dccph_doff * 4);
struct dccp_options_received *opt_recv = &dp->dccps_options_received;
unsigned char opt, len;
- unsigned char *uninitialized_var(value);
+ unsigned char *value;
u32 elapsed_time;
__be32 opt_val;
int rc;
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 91a15b3c4..d872dd1cf 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -189,7 +189,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
/* And store cached results */
icsk->icsk_pmtu_cookie = pmtu;
- dp->dccps_mss_cache = cur_mps;
+ WRITE_ONCE(dp->dccps_mss_cache, cur_mps);
return cur_mps;
}
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 673502779..c4ea0159c 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -328,11 +328,15 @@ EXPORT_SYMBOL_GPL(dccp_disconnect);
__poll_t dccp_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
- __poll_t mask;
struct sock *sk = sock->sk;
+ __poll_t mask;
+ u8 shutdown;
+ int state;
sock_poll_wait(file, sock, wait);
- if (sk->sk_state == DCCP_LISTEN)
+
+ state = inet_sk_state_load(sk);
+ if (state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
/* Socket is not locked. We are protected from async events
@@ -341,20 +345,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
*/
mask = 0;
- if (sk->sk_err)
+ if (READ_ONCE(sk->sk_err))
mask = EPOLLERR;
+ shutdown = READ_ONCE(sk->sk_shutdown);
- if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
+ if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED)
mask |= EPOLLHUP;
- if (sk->sk_shutdown & RCV_SHUTDOWN)
+ if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected? */
- if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
+ if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
if (atomic_read(&sk->sk_rmem_alloc) > 0)
mask |= EPOLLIN | EPOLLRDNORM;
- if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+ if (!(shutdown & SEND_SHUTDOWN)) {
if (sk_stream_is_writeable(sk)) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
@@ -372,7 +377,6 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
}
return mask;
}
-
EXPORT_SYMBOL_GPL(dccp_poll);
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
@@ -648,7 +652,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
return dccp_getsockopt_service(sk, len,
(__be32 __user *)optval, optlen);
case DCCP_SOCKOPT_GET_CUR_MPS:
- val = dp->dccps_mss_cache;
+ val = READ_ONCE(dp->dccps_mss_cache);
break;
case DCCP_SOCKOPT_AVAILABLE_CCIDS:
return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
@@ -770,7 +774,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
trace_dccp_probe(sk, len);
- if (len > dp->dccps_mss_cache)
+ if (len > READ_ONCE(dp->dccps_mss_cache))
return -EMSGSIZE;
lock_sock(sk);
@@ -803,6 +807,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto out_discard;
}
+ /* We need to check dccps_mss_cache after socket is locked. */
+ if (len > dp->dccps_mss_cache) {
+ rc = -EMSGSIZE;
+ goto out_discard;
+ }
+
skb_reserve(skb, sk->sk_prot->max_header);
rc = memcpy_from_msg(skb_put(skb, len), msg, len);
if (rc != 0)
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 13bbf8cb6..be05b690b 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
if (unlikely(!pskb_may_pull(skb, total_pull)))
return NULL;
+ ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len);
skb_set_mac_header(skb, total_pull);
__skb_pull(skb, total_pull);
*metalen = ifehdrln - IFE_METAHDRLEN;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 203569500..24cd5c9c7 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -565,7 +565,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a08acb54b..5edf426fa 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -221,8 +221,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
int tv = prandom_u32() % max_delay;
im->tm_running = 1;
- if (!mod_timer(&im->timer, jiffies+tv+2))
- refcount_inc(&im->refcnt);
+ if (refcount_inc_not_zero(&im->refcnt)) {
+ if (mod_timer(&im->timer, jiffies + tv + 2))
+ ip_ma_put(im);
+ }
}
static void igmp_gq_start_timer(struct in_device *in_dev)
@@ -357,8 +359,9 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
struct flowi4 fl4;
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
- unsigned int size = mtu;
+ unsigned int size;
+ size = min(mtu, IP_MAX_MTU);
while (1) {
skb = alloc_skb(size + hlen + tlen,
GFP_ATOMIC | __GFP_NOWARN);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 5a272d09b..c6d670cd8 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -579,20 +579,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
- ret = sk_hashed(osk);
- if (ret) {
- /* Before deleting the node, we insert a new one to make
- * sure that the look-up-sk process would not miss either
- * of them and that at least one node would exist in ehash
- * table all the time. Otherwise there's a tiny chance
- * that lookup process could find nothing in ehash table.
- */
- __sk_nulls_add_node_tail_rcu(sk, list);
- sk_nulls_del_node_init_rcu(osk);
- }
- goto unlock;
- }
- if (found_dup_sk) {
+ ret = sk_nulls_del_node_init_rcu(osk);
+ } else if (found_dup_sk) {
*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
if (*found_dup_sk)
ret = false;
@@ -601,7 +589,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
if (ret)
__sk_nulls_add_node_rcu(sk, list);
-unlock:
spin_unlock(lock);
return ret;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index fedd19c22..88c5069b5 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -80,10 +80,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
-static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw,
- struct hlist_nulls_head *list)
+static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+ struct hlist_nulls_head *list)
{
- hlist_nulls_add_tail_rcu(&tw->tw_node, list);
+ hlist_nulls_add_head_rcu(&tw->tw_node, list);
}
static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
@@ -119,7 +119,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
spin_lock(lock);
- inet_twsk_add_node_tail_rcu(tw, &ehead->chain);
+ inet_twsk_add_node_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e16373640..38c8db78c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -683,15 +683,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
}
if (dev->header_ops) {
+ int pull_len = tunnel->hlen + sizeof(struct iphdr);
+
if (skb_cow_head(skb, 0))
goto free_skb;
tnl_params = (const struct iphdr *)skb->data;
- /* Pull skb since ip_tunnel_xmit() needs skb->data pointing
- * to gre header.
- */
- skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+ if (!pskb_network_may_pull(skb, pull_len))
+ goto free_skb;
+
+ /* ip_tunnel_xmit() needs skb->data pointing to gre header. */
+ skb_pull(skb, pull_len);
skb_reset_mac_header(skb);
if (skb->ip_summed == CHECKSUM_PARTIAL &&
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 92fa11e75..6936f7037 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -221,7 +221,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
if (lwtunnel_xmit_redirect(dst->lwtstate)) {
int res = lwtunnel_xmit(skb);
- if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+ if (res != LWTUNNEL_XMIT_CONTINUE)
return res;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 15c71b08c..a3536dfe9 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -319,12 +319,12 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
switch (skb->protocol) {
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
break;
case htons(ETH_P_IPV6):
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
break;
default:
goto tx_err;
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index 4824b1e18..bff2b85c5 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -96,11 +96,11 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
const struct net_device *indev)
{
- __be32 uninitialized_var(daddr), uninitialized_var(saddr);
- __be16 uninitialized_var(dport), uninitialized_var(sport);
+ __be32 daddr, saddr;
+ __be16 dport, sport;
const struct iphdr *iph = ip_hdr(skb);
struct sk_buff *data_skb = NULL;
- u8 uninitialized_var(protocol);
+ u8 protocol;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
enum ip_conntrack_info ctinfo;
struct nf_conn const *ct;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 57e231652..f4d41ceef 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -791,7 +791,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
goto reject_redirect;
}
- n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+ n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw);
if (!n)
n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
if (!IS_ERR(n)) {
@@ -1215,6 +1215,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
static void ipv4_send_dest_unreach(struct sk_buff *skb)
{
+ struct net_device *dev;
struct ip_options opt;
int res;
@@ -1232,7 +1233,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb)
opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
rcu_read_lock();
- res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+ dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev;
+ res = __ip_options_compile(dev_net(dev), &opt, skb, NULL);
rcu_read_unlock();
if (res)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cb96775fc..00648a478 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3000,18 +3000,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_LINGER2:
if (val < 0)
- tp->linger2 = -1;
- else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ)
- tp->linger2 = 0;
+ WRITE_ONCE(tp->linger2, -1);
+ else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
+ WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX);
else
- tp->linger2 = val * HZ;
+ WRITE_ONCE(tp->linger2, val * HZ);
break;
case TCP_DEFER_ACCEPT:
/* Translate value in seconds to number of retransmits */
- icsk->icsk_accept_queue.rskq_defer_accept =
- secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
- TCP_RTO_MAX / HZ);
+ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
+ secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+ TCP_RTO_MAX / HZ));
break;
case TCP_WINDOW_CLAMP:
@@ -3099,7 +3099,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = tcp_repair_set_window(tp, optval, optlen);
break;
case TCP_NOTSENT_LOWAT:
- tp->notsent_lowat = val;
+ WRITE_ONCE(tp->notsent_lowat, val);
sk->sk_write_space(sk);
break;
case TCP_INQ:
@@ -3401,13 +3401,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
break;
case TCP_LINGER2:
- val = tp->linger2;
+ val = READ_ONCE(tp->linger2);
if (val >= 0)
val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
break;
case TCP_DEFER_ACCEPT:
- val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
- TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
+ val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept);
+ val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ,
+ TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
val = tp->window_clamp;
@@ -3553,7 +3554,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
break;
case TCP_FASTOPEN:
- val = icsk->icsk_accept_queue.fastopenq.max_qlen;
+ val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen);
break;
case TCP_FASTOPEN_CONNECT:
@@ -3568,7 +3569,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = tcp_time_stamp_raw() + tp->tsoffset;
break;
case TCP_NOTSENT_LOWAT:
- val = tp->notsent_lowat;
+ val = READ_ONCE(tp->notsent_lowat);
break;
case TCP_INQ:
val = tp->recvmsg_inq;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f726591de..f7bb78b44 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -276,6 +276,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
static bool tcp_fastopen_queue_check(struct sock *sk)
{
struct fastopen_queue *fastopenq;
+ int max_qlen;
/* Make sure the listener has enabled fastopen, and we don't
* exceed the max # of pending TFO requests allowed before trying
@@ -288,10 +289,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
* temporarily vs a server not supporting Fast Open at all.
*/
fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq;
- if (fastopenq->max_qlen == 0)
+ max_qlen = READ_ONCE(fastopenq->max_qlen);
+ if (max_qlen == 0)
return false;
- if (fastopenq->qlen >= fastopenq->max_qlen) {
+ if (fastopenq->qlen >= max_qlen) {
struct request_sock *req1;
spin_lock(&fastopenq->lock);
req1 = fastopenq->rskq_rst_head;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bd921fa7b..407ad07dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -172,6 +172,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
if (unlikely(len > icsk->icsk_ack.rcv_mss +
MAX_TCP_OPTION_SPACE))
tcp_gro_dev_warn(sk, skb, len);
+ /* If the skb has a len of exactly 1*MSS and has the PSH bit
+ * set then it is likely the end of an application write. So
+ * more data may not be arriving soon, and yet the data sender
+ * may be waiting for an ACK if cwnd-bound or using TX zero
+ * copy. So we set ICSK_ACK_PUSHED here so that
+ * tcp_cleanup_rbuf() will send an ACK immediately if the app
+ * reads all of the data and is not ping-pong. If len > MSS
+ * then this logic does not matter (and does not hurt) because
+ * tcp_cleanup_rbuf() will always ACK immediately if the app
+ * reads data and there is more than an MSS of unACKed data.
+ */
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH)
+ icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
@@ -216,7 +229,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
icsk->icsk_ack.quick = quickacks;
}
-void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
{
struct inet_connection_sock *icsk = inet_csk(sk);
@@ -224,7 +237,6 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
-EXPORT_SYMBOL(tcp_enter_quickack_mode);
/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
@@ -3429,8 +3441,11 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
u32 *last_oow_ack_time)
{
- if (*last_oow_ack_time) {
- s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
+ /* Paired with the WRITE_ONCE() in this function. */
+ u32 val = READ_ONCE(*last_oow_ack_time);
+
+ if (val) {
+ s32 elapsed = (s32)(tcp_jiffies32 - val);
if (0 <= elapsed &&
elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
@@ -3439,7 +3454,10 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
}
}
- *last_oow_ack_time = tcp_jiffies32;
+ /* Paired with the prior READ_ONCE() and with itself,
+ * as we might be lockless.
+ */
+ WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32);
return false; /* not rate-limited: go ahead, send dupack now! */
}
@@ -3622,8 +3640,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
* then we can probably ignore it.
*/
if (before(ack, prior_snd_una)) {
+ u32 max_window;
+
+ /* do not accept ACK for bytes we never sent. */
+ max_window = min_t(u64, tp->max_window, tp->bytes_acked);
/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
- if (before(ack, prior_snd_una - tp->max_window)) {
+ if (before(ack, prior_snd_una - max_window)) {
if (!(flag & FLAG_NO_CHALLENGE_ACK))
tcp_send_challenge_ack(sk, skb);
return -1;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4960e2b6b..60619b1f4 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -40,7 +40,7 @@ struct tcp_fastopen_metrics {
struct tcp_metrics_block {
struct tcp_metrics_block __rcu *tcpm_next;
- possible_net_t tcpm_net;
+ struct net *tcpm_net;
struct inetpeer_addr tcpm_saddr;
struct inetpeer_addr tcpm_daddr;
unsigned long tcpm_stamp;
@@ -51,34 +51,38 @@ struct tcp_metrics_block {
struct rcu_head rcu_head;
};
-static inline struct net *tm_net(struct tcp_metrics_block *tm)
+static inline struct net *tm_net(const struct tcp_metrics_block *tm)
{
- return read_pnet(&tm->tcpm_net);
+ /* Paired with the WRITE_ONCE() in tcpm_new() */
+ return READ_ONCE(tm->tcpm_net);
}
static bool tcp_metric_locked(struct tcp_metrics_block *tm,
enum tcp_metric_index idx)
{
- return tm->tcpm_lock & (1 << idx);
+ /* Paired with WRITE_ONCE() in tcpm_suck_dst() */
+ return READ_ONCE(tm->tcpm_lock) & (1 << idx);
}
-static u32 tcp_metric_get(struct tcp_metrics_block *tm,
+static u32 tcp_metric_get(const struct tcp_metrics_block *tm,
enum tcp_metric_index idx)
{
- return tm->tcpm_vals[idx];
+ /* Paired with WRITE_ONCE() in tcp_metric_set() */
+ return READ_ONCE(tm->tcpm_vals[idx]);
}
static void tcp_metric_set(struct tcp_metrics_block *tm,
enum tcp_metric_index idx,
u32 val)
{
- tm->tcpm_vals[idx] = val;
+ /* Paired with READ_ONCE() in tcp_metric_get() */
+ WRITE_ONCE(tm->tcpm_vals[idx], val);
}
static bool addr_same(const struct inetpeer_addr *a,
const struct inetpeer_addr *b)
{
- return inetpeer_addr_cmp(a, b) == 0;
+ return (a->family == b->family) && !inetpeer_addr_cmp(a, b);
}
struct tcpm_hash_bucket {
@@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly;
static unsigned int tcp_metrics_hash_log __read_mostly;
static DEFINE_SPINLOCK(tcp_metrics_lock);
+static DEFINE_SEQLOCK(fastopen_seqlock);
static void tcpm_suck_dst(struct tcp_metrics_block *tm,
const struct dst_entry *dst,
@@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
u32 msval;
u32 val;
- tm->tcpm_stamp = jiffies;
+ WRITE_ONCE(tm->tcpm_stamp, jiffies);
val = 0;
if (dst_metric_locked(dst, RTAX_RTT))
@@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
val |= 1 << TCP_METRIC_CWND;
if (dst_metric_locked(dst, RTAX_REORDERING))
val |= 1 << TCP_METRIC_REORDERING;
- tm->tcpm_lock = val;
+ /* Paired with READ_ONCE() in tcp_metric_locked() */
+ WRITE_ONCE(tm->tcpm_lock, val);
msval = dst_metric_raw(dst, RTAX_RTT);
- tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC;
+ tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC);
msval = dst_metric_raw(dst, RTAX_RTTVAR);
- tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC;
- tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
- tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
- tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
+ tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC);
+ tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
+ dst_metric_raw(dst, RTAX_SSTHRESH));
+ tcp_metric_set(tm, TCP_METRIC_CWND,
+ dst_metric_raw(dst, RTAX_CWND));
+ tcp_metric_set(tm, TCP_METRIC_REORDERING,
+ dst_metric_raw(dst, RTAX_REORDERING));
if (fastopen_clear) {
+ write_seqlock(&fastopen_seqlock);
tm->tcpm_fastopen.mss = 0;
tm->tcpm_fastopen.syn_loss = 0;
tm->tcpm_fastopen.try_exp = 0;
tm->tcpm_fastopen.cookie.exp = false;
tm->tcpm_fastopen.cookie.len = 0;
+ write_sequnlock(&fastopen_seqlock);
}
}
#define TCP_METRICS_TIMEOUT (60 * 60 * HZ)
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+static void tcpm_check_stamp(struct tcp_metrics_block *tm,
+ const struct dst_entry *dst)
{
- if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+ unsigned long limit;
+
+ if (!tm)
+ return;
+ limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT;
+ if (unlikely(time_after(jiffies, limit)))
tcpm_suck_dst(tm, dst, false);
}
@@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
oldest = deref_locked(tcp_metrics_hash[hash].chain);
for (tm = deref_locked(oldest->tcpm_next); tm;
tm = deref_locked(tm->tcpm_next)) {
- if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp))
+ if (time_before(READ_ONCE(tm->tcpm_stamp),
+ READ_ONCE(oldest->tcpm_stamp)))
oldest = tm;
}
tm = oldest;
} else {
- tm = kmalloc(sizeof(*tm), GFP_ATOMIC);
+ tm = kzalloc(sizeof(*tm), GFP_ATOMIC);
if (!tm)
goto out_unlock;
}
- write_pnet(&tm->tcpm_net, net);
+ /* Paired with the READ_ONCE() in tm_net() */
+ WRITE_ONCE(tm->tcpm_net, net);
+
tm->tcpm_saddr = *saddr;
tm->tcpm_daddr = *daddr;
- tcpm_suck_dst(tm, dst, true);
+ tcpm_suck_dst(tm, dst, reclaim);
if (likely(!reclaim)) {
tm->tcpm_next = tcp_metrics_hash[hash].chain;
@@ -431,7 +451,7 @@ void tcp_update_metrics(struct sock *sk)
tp->reordering);
}
}
- tm->tcpm_stamp = jiffies;
+ WRITE_ONCE(tm->tcpm_stamp, jiffies);
out_unlock:
rcu_read_unlock();
}
@@ -446,11 +466,15 @@ void tcp_init_metrics(struct sock *sk)
u32 val, crtt = 0; /* cached RTT scaled by 8 */
sk_dst_confirm(sk);
+ /* ssthresh may have been reduced unnecessarily during.
+ * 3WHS. Restore it back to its initial default.
+ */
+ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
if (!dst)
goto reset;
rcu_read_lock();
- tm = tcp_get_metrics(sk, dst, true);
+ tm = tcp_get_metrics(sk, dst, false);
if (!tm) {
rcu_read_unlock();
goto reset;
@@ -464,11 +488,6 @@ void tcp_init_metrics(struct sock *sk)
tp->snd_ssthresh = val;
if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
tp->snd_ssthresh = tp->snd_cwnd_clamp;
- } else {
- /* ssthresh may have been reduced unnecessarily during.
- * 3WHS. Restore it back to its initial default.
- */
- tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
}
val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
if (val && tp->reordering != val)
@@ -544,8 +563,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
return ret;
}
-static DEFINE_SEQLOCK(fastopen_seqlock);
-
void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie)
{
@@ -652,7 +669,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
}
if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE,
- jiffies - tm->tcpm_stamp,
+ jiffies - READ_ONCE(tm->tcpm_stamp),
TCP_METRICS_ATTR_PAD) < 0)
goto nla_put_failure;
@@ -663,7 +680,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
if (!nest)
goto nla_put_failure;
for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
- u32 val = tm->tcpm_vals[i];
+ u32 val = tcp_metric_get(tm, i);
if (!val)
continue;
@@ -895,7 +912,7 @@ static void tcp_metrics_flush_all(struct net *net)
match = net ? net_eq(tm_net(tm), net) :
!refcount_read(&tm_net(tm)->count);
if (match) {
- *pp = tm->tcpm_next;
+ rcu_assign_pointer(*pp, tm->tcpm_next);
kfree_rcu(tm, rcu_head);
} else {
pp = &tm->tcpm_next;
@@ -936,7 +953,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
if (addr_same(&tm->tcpm_daddr, &daddr) &&
(!src || addr_same(&tm->tcpm_saddr, &saddr)) &&
net_eq(tm_net(tm), net)) {
- *pp = tm->tcpm_next;
+ rcu_assign_pointer(*pp, tm->tcpm_next);
kfree_rcu(tm, rcu_head);
found = true;
} else {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9299de0da..670804d4c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -164,8 +164,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
}
/* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
- u32 rcv_nxt)
+static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -179,7 +178,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
if (unlikely(rcv_nxt != tp->rcv_nxt))
return; /* Special ACK sent by DCTCP to reflect ECN */
- tcp_dec_quickack_mode(sk, pkts);
+ tcp_dec_quickack_mode(sk);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
@@ -1091,7 +1090,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
skb_set_hash_from_sk(skb, sk);
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
- skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm);
+ skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm));
/* Build TCP header and checksum it. */
th = (struct tcphdr *)skb->data;
@@ -1139,7 +1138,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
- tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
+ tcp_event_ack_sent(sk, rcv_nxt);
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
@@ -2221,6 +2220,18 @@ static int tcp_mtu_probe(struct sock *sk)
return -1;
}
+static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk)
+{
+ const struct rb_node *node = sk->tcp_rtx_queue.rb_node;
+
+ /* No skb in the rtx queue. */
+ if (!node)
+ return true;
+
+ /* Only one skb in rtx queue. */
+ return !node->rb_left && !node->rb_right;
+}
+
/* TCP Small Queues :
* Control number of packets in qdisc/devices to two packets / or ~1 ms.
* (These limits are doubled for retransmits)
@@ -2243,12 +2254,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
limit <<= factor;
if (refcount_read(&sk->sk_wmem_alloc) > limit) {
- /* Always send skb if rtx queue is empty.
+ /* Always send skb if rtx queue is empty or has one skb.
* No need to wait for TX completion to call us back,
* after softirq/tasklet schedule.
* This helps when TX completions are delayed too much.
*/
- if (tcp_rtx_queue_empty(sk))
+ if (tcp_rtx_queue_empty_or_single_skb(sk))
return false;
set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2450,7 +2461,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- u32 timeout, rto_delta_us;
+ u32 timeout, timeout_us, rto_delta_us;
int early_retrans;
/* Don't do any loss probe on a Fast Open connection before 3WHS
@@ -2474,11 +2485,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
* sample is available then probe after TCP_TIMEOUT_INIT.
*/
if (tp->srtt_us) {
- timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+ timeout_us = tp->srtt_us >> 2;
if (tp->packets_out == 1)
- timeout += TCP_RTO_MIN;
+ timeout_us += tcp_rto_min_us(sk);
else
- timeout += TCP_TIMEOUT_MIN;
+ timeout_us += TCP_TIMEOUT_MIN_US;
+ timeout = usecs_to_jiffies(timeout_us);
} else {
timeout = TCP_TIMEOUT_INIT;
}
@@ -2878,7 +2890,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
if (skb_still_in_host_queue(sk, skb))
return -EBUSY;
+start:
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+ TCP_SKB_CB(skb)->seq++;
+ goto start;
+ }
if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
WARN_ON_ONCE(1);
return -EINVAL;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 61969bb93..844ff390f 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -122,7 +122,7 @@ bool tcp_rack_mark_lost(struct sock *sk)
tp->rack.advanced = 0;
tcp_rack_detect_loss(sk, &timeout);
if (timeout) {
- timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN;
+ timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
timeout, inet_csk(sk)->icsk_rto);
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 84069db04..d8d28ba16 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -549,7 +549,9 @@ out_reset_timer:
tcp_stream_is_thin(tp) &&
icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
icsk->icsk_backoff = 0;
- icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
+ icsk->icsk_rto = clamp(__tcp_set_rto(tp),
+ tcp_rto_min(sk),
+ TCP_RTO_MAX);
} else {
/* Use normal (exponential) backoff */
icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f261c6d7f..5ffa8777a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -316,9 +316,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
static void addrconf_mod_rs_timer(struct inet6_dev *idev,
unsigned long when)
{
- if (!timer_pending(&idev->rs_timer))
+ if (!mod_timer(&idev->rs_timer, jiffies + when))
in6_dev_hold(idev);
- mod_timer(&idev->rs_timer, jiffies + when);
}
static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
@@ -1322,7 +1321,7 @@ retry:
* idev->desync_factor if it's larger
*/
cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
- max_desync_factor = min_t(__u32,
+ max_desync_factor = min_t(long,
idev->cnf.max_desync_factor,
cnf_temp_preferred_lft - regen_advance);
@@ -2489,12 +2488,18 @@ static void manage_tempaddrs(struct inet6_dev *idev,
ipv6_ifa_notify(0, ift);
}
- if ((create || list_empty(&idev->tempaddr_list)) &&
- idev->cnf.use_tempaddr > 0) {
+ /* Also create a temporary address if it's enabled but no temporary
+ * address currently exists.
+ * However, we get called with valid_lft == 0, prefered_lft == 0, create == false
+ * as part of cleanup (ie. deleting the mngtmpaddr).
+ * We don't want that to result in creating a new temporary ip address.
+ */
+ if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft))
+ create = true;
+
+ if (create && idev->cnf.use_tempaddr > 0) {
/* When a new public address is created as described
* in [ADDRCONF], also create a new temporary address.
- * Also create a temporary address if it's enabled but
- * no temporary address currently exists.
*/
read_unlock_bh(&idev->lock);
ipv6_create_tempaddr(ifp, NULL, false);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index d847ffbe9..6529e46ad 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -517,7 +517,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index fbc874637..bfafd7649 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -395,23 +395,31 @@ relookup_failed:
return ERR_PTR(err);
}
-static int icmp6_iif(const struct sk_buff *skb)
+static struct net_device *icmp6_dev(const struct sk_buff *skb)
{
- int iif = skb->dev->ifindex;
+ struct net_device *dev = skb->dev;
/* for local traffic to local address, skb dev is the loopback
* device. Check if there is a dst attached to the skb and if so
* get the real device index. Same is needed for replies to a link
* local address on a device enslaved to an L3 master device
*/
- if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
+ if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
const struct rt6_info *rt6 = skb_rt6_info(skb);
- if (rt6)
- iif = rt6->rt6i_idev->dev->ifindex;
+ /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.),
+ * and ip6_null_entry could be set to skb if no route is found.
+ */
+ if (rt6 && rt6->rt6i_idev)
+ dev = rt6->rt6i_idev->dev;
}
- return iif;
+ return dev;
+}
+
+static int icmp6_iif(const struct sk_buff *skb)
+{
+ return icmp6_dev(skb)->ifindex;
}
/*
@@ -800,7 +808,7 @@ out:
static int icmpv6_rcv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
- struct net_device *dev = skb->dev;
+ struct net_device *dev = icmp6_dev(skb);
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
struct icmp6hdr *hdr;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5ff67cb8b..92bc56028 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1351,13 +1351,9 @@ out:
if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
pn_leaf = fib6_find_prefix(info->nl_net, table,
pn);
-#if RT6_DEBUG >= 2
- if (!pn_leaf) {
- WARN_ON(!pn_leaf);
+ if (!pn_leaf)
pn_leaf =
info->nl_net->ipv6.fib6_null_entry;
- }
-#endif
fib6_info_hold(pn_leaf);
rcu_assign_pointer(pn->leaf, pn_leaf);
}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index f994f50e1..1858cf783 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -518,7 +518,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
{
- int uninitialized_var(err);
+ int err;
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 45c304b51..aa8ada354 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -960,7 +960,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
goto tx_err;
if (skb->len > dev->mtu + dev->hard_header_len) {
- pskb_trim(skb, dev->mtu + dev->hard_header_len);
+ if (pskb_trim(skb, dev->mtu + dev->hard_header_len))
+ goto tx_err;
truncate = true;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4f31a781a..0872df066 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -106,7 +106,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
if (lwtunnel_xmit_redirect(dst->lwtstate)) {
int res = lwtunnel_xmit(skb);
- if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+ if (res != LWTUNNEL_XMIT_CONTINUE)
return res;
}
@@ -153,7 +153,13 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
int err;
skb_mark_not_on_list(segs);
- err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+ /* Last GSO segment can be smaller than gso_size (and MTU).
+ * Adding a fragment header would produce an "atomic fragment",
+ * which is considered harmful (RFC-8021). Avoid that.
+ */
+ err = segs->len > mtu ?
+ ip6_fragment(net, sk, segs, ip6_finish_output2) :
+ ip6_finish_output2(net, sk, segs);
if (err && ret == 0)
ret = err;
}
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 866ce8156..a64050e77 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -562,12 +562,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
vti6_addr_conflict(t, ipv6_hdr(skb)))
goto tx_err;
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
break;
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
break;
default:
goto tx_err;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e9eb91734..329bad6cb 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1064,7 +1064,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
- skb_push(skb, -skb_network_offset(pkt));
+ __skb_pull(skb, skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 673a4a932..a640deb9a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -195,7 +195,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
static inline int ndisc_is_useropt(const struct net_device *dev,
struct nd_opt_hdr *opt)
{
- return opt->nd_opt_type == ND_OPT_RDNSS ||
+ return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+ opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL ||
ndisc_ops_is_useropt(dev, opt->nd_opt_type);
}
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index 58e839e2c..5e5463459 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -102,7 +102,7 @@ nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
const struct net_device *indev)
{
- __be16 uninitialized_var(dport), uninitialized_var(sport);
+ __be16 dport, sport;
const struct in6_addr *daddr = NULL, *saddr = NULL;
struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var;
struct sk_buff *data_skb = NULL;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 60dfd0d11..b596727f0 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -302,7 +302,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
skb_network_header_len(skb));
rcu_read_lock();
- __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
+ __IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS);
rcu_read_unlock();
fq->q.fragments = NULL;
fq->q.rb_fragments = RB_ROOT;
@@ -317,7 +317,7 @@ out_oom:
net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
out_fail:
rcu_read_lock();
- __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+ __IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS);
rcu_read_unlock();
inet_frag_kill(&fq->q);
return -1;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index ca291e342..ab073ac3d 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -184,14 +184,15 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
treq->af_specific = &tcp_request_sock_ipv6_ops;
treq->tfo_listener = false;
- if (security_inet_conn_request(sk, skb, req))
- goto out_free;
-
req->mss = mss;
ireq->ir_rmt_port = th->source;
ireq->ir_num = ntohs(th->dest);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+
+ if (security_inet_conn_request(sk, skb, req))
+ goto out_free;
+
if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 927460351..cf0bbe2e3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -99,7 +99,7 @@ static u32 udp6_ehashfn(const struct net *net,
fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
return __inet6_ehashfn(lhash, lport, fhash, fport,
- udp_ipv6_hash_secret + net_hash_mix(net));
+ udp6_ehash_secret + net_hash_mix(net));
}
int udp_v6_get_port(struct sock *sk, unsigned short snum)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 1925fb91e..a1dfe4f5e 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -243,11 +243,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- if (likely(xdst->u.rt6.rt6i_idev))
- in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
if (xdst->u.rt6.rt6i_uncached_list)
rt6_uncached_list_del(&xdst->u.rt6);
+ if (likely(xdst->u.rt6.rt6i_idev))
+ in6_dev_put(xdst->u.rt6.rt6i_idev);
xfrm_dst_destroy(xdst);
}
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index c0034546a..a82892c28 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1065,15 +1065,18 @@ partial_message:
out_error:
kcm_push(kcm);
- if (copied && sock->type == SOCK_SEQPACKET) {
+ if (sock->type == SOCK_SEQPACKET) {
/* Wrote some bytes before encountering an
* error, return partial success.
*/
- goto partial_message;
- }
-
- if (head != kcm->seq_skb)
+ if (copied)
+ goto partial_message;
+ if (head != kcm->seq_skb)
+ kfree_skb(head);
+ } else {
kfree_skb(head);
+ kcm->seq_skb = NULL;
+ }
err = sk_stream_error(sk, msg->msg_flags, err);
@@ -1983,6 +1986,8 @@ static __net_exit void kcm_exit_net(struct net *net)
* that all multiplexors and psocks have been destroyed.
*/
WARN_ON(!list_empty(&knet->mux_list));
+
+ mutex_destroy(&knet->mutex);
}
static struct pernet_operations kcm_net_ops = {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index b8456e2f1..47ffa69ca 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1858,9 +1858,9 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
- if ((xfilter->sadb_x_filter_splen >=
+ if ((xfilter->sadb_x_filter_splen >
(sizeof(xfrm_address_t) << 3)) ||
- (xfilter->sadb_x_filter_dplen >=
+ (xfilter->sadb_x_filter_dplen >
(sizeof(xfrm_address_t) << 3))) {
mutex_unlock(&pfk->dump_lock);
return -EINVAL;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index f3f0b4b7c..7342344d9 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -525,7 +525,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
*/
if (len > INT_MAX - transhdrlen)
return -EMSGSIZE;
- ulen = len + transhdrlen;
/* Mirror BSD error message compatibility */
if (msg->msg_flags & MSG_OOB)
@@ -649,6 +648,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
back_from_confirm:
lock_sock(sk);
+ ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0;
err = ip6_append_data(sk, ip_generic_getfrag, msg,
ulen, transhdrlen, &ipc6,
&fl6, (struct rt6_info *)dst,
diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c
index 82cb93f66..f4fb30918 100644
--- a/net/llc/llc_input.c
+++ b/net/llc/llc_input.c
@@ -127,8 +127,14 @@ static inline int llc_fixup_skb(struct sk_buff *skb)
skb->transport_header += llc_len;
skb_pull(skb, llc_len);
if (skb->protocol == htons(ETH_P_802_2)) {
- __be16 pdulen = eth_hdr(skb)->h_proto;
- s32 data_size = ntohs(pdulen) - llc_len;
+ __be16 pdulen;
+ s32 data_size;
+
+ if (skb->mac_len < ETH_HLEN)
+ return 0;
+
+ pdulen = eth_hdr(skb)->h_proto;
+ data_size = ntohs(pdulen) - llc_len;
if (data_size < 0 ||
!pskb_may_pull(skb, data_size))
@@ -162,9 +168,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev,
void (*sta_handler)(struct sk_buff *skb);
void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb);
- if (!net_eq(dev_net(dev), &init_net))
- goto drop;
-
/*
* When the interface is in promisc. mode, drop all the crap that it
* receives, do not try to analyse it.
diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index 9fa3342c7..df26557a0 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -153,6 +153,9 @@ int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb)
int rc = 1;
u32 data_size;
+ if (skb->mac_len < ETH_HLEN)
+ return 1;
+
llc_pdu_decode_sa(skb, mac_da);
llc_pdu_decode_da(skb, mac_sa);
llc_pdu_decode_ssap(skb, &dsap);
diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c
index c29170e76..64e2c67e1 100644
--- a/net/llc/llc_station.c
+++ b/net/llc/llc_station.c
@@ -77,6 +77,9 @@ static int llc_station_ac_send_test_r(struct sk_buff *skb)
u32 data_size;
struct sk_buff *nskb;
+ if (skb->mac_len < ETH_HLEN)
+ goto out;
+
/* The test request command is type U (llc_len = 3) */
data_size = ntohs(eth_hdr(skb)->h_proto) - 3;
nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 5659af1be..77d8ed184 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2452,6 +2452,10 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
else
*dbm = sdata->vif.bss_conf.txpower;
+ /* INT_MIN indicates no power level was set yet */
+ if (*dbm == INT_MIN)
+ return -EINVAL;
+
return 0;
}
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 5b5b0f95f..c7f47dba8 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -1022,8 +1022,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata,
case WLAN_SP_MESH_PEERING_OPEN:
if (!matches_local)
event = OPN_RJCT;
- if (!mesh_plink_free_count(sdata) ||
- (sta->mesh->plid && sta->mesh->plid != plid))
+ else if (!mesh_plink_free_count(sdata) ||
+ (sta->mesh->plid && sta->mesh->plid != plid))
event = OPN_IGNR;
else
event = OPN_ACPT;
@@ -1031,9 +1031,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata,
case WLAN_SP_MESH_PEERING_CONFIRM:
if (!matches_local)
event = CNF_RJCT;
- if (!mesh_plink_free_count(sdata) ||
- sta->mesh->llid != llid ||
- (sta->mesh->plid && sta->mesh->plid != plid))
+ else if (!mesh_plink_free_count(sdata) ||
+ sta->mesh->llid != llid ||
+ (sta->mesh->plid && sta->mesh->plid != plid))
event = CNF_IGNR;
else
event = CNF_ACPT;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 74045e927..3a0aadf88 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -654,7 +654,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
}
if (unlikely(tx->key && tx->key->flags & KEY_FLAG_TAINTED &&
- !ieee80211_is_deauth(hdr->frame_control)))
+ !ieee80211_is_deauth(hdr->frame_control)) &&
+ tx->skb->protocol != tx->sdata->control_port_protocol)
return TX_DROP;
if (!skip_hw && tx->key &&
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 0427e66bc..031bb83ae 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -64,6 +64,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
ip_set_dereference((inst)->ip_set_list)[id]
#define ip_set_ref_netlink(inst,id) \
rcu_dereference_raw((inst)->ip_set_list)[id]
+#define ip_set_dereference_nfnl(p) \
+ rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
/* The set types are implemented in modules and registered set types
* can be found in ip_set_type_list. Adding/deleting types is
@@ -552,15 +554,10 @@ __ip_set_put_netlink(struct ip_set *set)
static inline struct ip_set *
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(inst->ip_set_list)[index];
- rcu_read_unlock();
-
- return set;
+ /* ip_set_list and the set pointer need to be protected */
+ return ip_set_dereference_nfnl(inst->ip_set_list)[index];
}
int
@@ -791,20 +788,9 @@ static struct nlmsghdr *
start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags,
enum ipset_cmd cmd)
{
- struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
-
- nlh = nlmsg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd),
- sizeof(*nfmsg), flags);
- if (!nlh)
- return NULL;
-
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = NFPROTO_IPV4;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
- return nlh;
+ return nfnl_msg_put(skb, portid, seq,
+ nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd), flags,
+ NFPROTO_IPV4, NFNETLINK_V0, 0);
}
/* Create a set */
@@ -1238,6 +1224,9 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb,
ip_set(inst, to_id) = from;
write_unlock_bh(&ip_set_ref_lock);
+ /* Make sure all readers of the old set pointers are completed. */
+ synchronize_rcu();
+
return 0;
}
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 613e18e72..9290a4d7b 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -39,6 +39,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net");
#define IP_SET_HASH_WITH_PROTO
#define IP_SET_HASH_WITH_NETS
#define IPSET_NET_COUNT 2
+#define IP_SET_HASH_WITH_NET0
/* IPv4 variant */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 3bf8d7f3c..0909f32ea 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1656,6 +1656,7 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs)
#ifdef CONFIG_SYSCTL
static int zero;
+static int one = 1;
static int three = 3;
static int
@@ -1667,12 +1668,18 @@ proc_do_defense_mode(struct ctl_table *table, int write,
int val = *valp;
int rc;
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
+ struct ctl_table tmp = {
+ .data = &val,
+ .maxlen = sizeof(int),
+ .mode = table->mode,
+ };
+
+ rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
if (write && (*valp != val)) {
- if ((*valp < 0) || (*valp > 3)) {
- /* Restore the correct value */
- *valp = val;
+ if (val < 0 || val > 3) {
+ rc = -EINVAL;
} else {
+ *valp = val;
update_defense_level(ipvs);
}
}
@@ -1683,37 +1690,27 @@ static int
proc_do_sync_threshold(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
+ struct netns_ipvs *ipvs = table->extra2;
int *valp = table->data;
int val[2];
int rc;
+ struct ctl_table tmp = {
+ .data = &val,
+ .maxlen = table->maxlen,
+ .mode = table->mode,
+ };
- /* backup the value first */
+ mutex_lock(&ipvs->sync_mutex);
memcpy(val, valp, sizeof(val));
-
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (valp[0] < 0 || valp[1] < 0 ||
- (valp[0] >= valp[1] && valp[1]))) {
- /* Restore the correct value */
- memcpy(valp, val, sizeof(val));
- }
- return rc;
-}
-
-static int
-proc_do_sync_mode(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
-{
- int *valp = table->data;
- int val = *valp;
- int rc;
-
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
- if (write && (*valp != val)) {
- if ((*valp < 0) || (*valp > 1)) {
- /* Restore the correct value */
- *valp = val;
- }
+ rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+ if (write) {
+ if (val[0] < 0 || val[1] < 0 ||
+ (val[0] >= val[1] && val[1]))
+ rc = -EINVAL;
+ else
+ memcpy(valp, val, sizeof(val));
}
+ mutex_unlock(&ipvs->sync_mutex);
return rc;
}
@@ -1725,12 +1722,18 @@ proc_do_sync_ports(struct ctl_table *table, int write,
int val = *valp;
int rc;
- rc = proc_dointvec(table, write, buffer, lenp, ppos);
+ struct ctl_table tmp = {
+ .data = &val,
+ .maxlen = sizeof(int),
+ .mode = table->mode,
+ };
+
+ rc = proc_dointvec(&tmp, write, buffer, lenp, ppos);
if (write && (*valp != val)) {
- if (*valp < 1 || !is_power_of_2(*valp)) {
- /* Restore the correct value */
+ if (val < 1 || !is_power_of_2(val))
+ rc = -EINVAL;
+ else
*valp = val;
- }
}
return rc;
}
@@ -1790,7 +1793,9 @@ static struct ctl_table vs_vars[] = {
.procname = "sync_version",
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_do_sync_mode,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
},
{
.procname = "sync_ports",
@@ -3942,6 +3947,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
tbl[idx].data = &ipvs->sysctl_sync_threshold;
+ tbl[idx].extra2 = ipvs;
tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD;
tbl[idx++].data = &ipvs->sysctl_sync_refresh_period;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f6af13c16..c133ce825 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1444,7 +1444,7 @@ static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
sin.sin_addr.s_addr = addr;
sin.sin_port = 0;
- return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin));
+ return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin));
}
static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen,
@@ -1510,8 +1510,8 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id,
}
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id);
- result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr,
- salen, 0);
+ result = kernel_connect(sock, (struct sockaddr *)&mcast_addr,
+ salen, 0);
if (result < 0) {
pr_err("Error connecting to the multicast addr\n");
goto error;
@@ -1551,7 +1551,7 @@ static int make_receive_sock(struct netns_ipvs *ipvs, int id,
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
sock->sk->sk_bound_dev_if = dev->ifindex;
- result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
+ result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
goto error;
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index efc14c7b4..c2fece059 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -383,7 +383,7 @@ static int help(struct sk_buff *skb,
int ret;
u32 seq;
int dir = CTINFO2DIR(ctinfo);
- unsigned int uninitialized_var(matchlen), uninitialized_var(matchoff);
+ unsigned int matchlen, matchoff;
struct nf_ct_ftp_master *ct_ftp_info = nfct_help_data(ct);
struct nf_conntrack_expect *exp;
union nf_inet_addr *daddr;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index e24b762ff..06c70d458 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -400,6 +400,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1);
+ if (!nf_ct_helper_hash)
+ return -ENOENT;
+
if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT)
return -EINVAL;
@@ -570,4 +573,5 @@ void nf_conntrack_helper_fini(void)
{
nf_ct_extend_unregister(&helper_extend);
kvfree(nf_ct_helper_hash);
+ nf_ct_helper_hash = NULL;
}
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index b710889a9..83e8566ec 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -517,20 +517,15 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
{
const struct nf_conntrack_zone *zone;
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
struct nlattr *nest_parms;
unsigned int flags = portid ? NLM_F_MULTI : 0, event;
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, nf_ct_l3num(ct),
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = nf_ct_l3num(ct);
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
zone = nf_ct_zone(ct);
nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
@@ -687,7 +682,6 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
const struct nf_conntrack_zone *zone;
struct net *net;
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
struct nlattr *nest_parms;
struct nf_conn *ct = item->ct;
struct sk_buff *skb;
@@ -717,15 +711,11 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
goto errout;
type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type);
- nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, nf_ct_l3num(ct),
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = nf_ct_l3num(ct);
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
zone = nf_ct_zone(ct);
nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
@@ -2170,20 +2160,15 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
__u16 cpu, const struct ip_conntrack_stat *st)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0, event;
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK,
IPCTNL_MSG_CT_GET_STATS_CPU);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, htons(cpu));
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(cpu);
-
if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) ||
nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) ||
nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) ||
@@ -2254,20 +2239,15 @@ ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
struct net *net)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0, event;
unsigned int nr_conntracks = atomic_read(&net->ct.count);
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks)))
goto nla_put_failure;
@@ -2780,19 +2760,14 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
int event, const struct nf_conntrack_expect *exp)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0;
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags,
+ exp->tuple.src.l3num, NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = exp->tuple.src.l3num;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (ctnetlink_exp_dump_expect(skb, exp) < 0)
goto nla_put_failure;
@@ -2812,7 +2787,6 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item)
struct nf_conntrack_expect *exp = item->exp;
struct net *net = nf_ct_exp_net(exp);
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
struct sk_buff *skb;
unsigned int type, group;
int flags = 0;
@@ -2835,15 +2809,11 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item)
goto errout;
type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type);
- nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, item->portid, 0, type, flags,
+ exp->tuple.src.l3num, NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = exp->tuple.src.l3num;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (ctnetlink_exp_dump_expect(skb, exp) < 0)
goto nla_put_failure;
@@ -3413,20 +3383,15 @@ ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu,
const struct ip_conntrack_stat *st)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0, event;
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK,
IPCTNL_MSG_EXP_GET_STATS_CPU);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, htons(cpu));
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(cpu);
-
if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) ||
nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) ||
nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete)))
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index cadeb22a4..8453e9293 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -58,8 +58,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
[SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS,
[SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS,
[SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS,
- [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000,
- [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000,
+ [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS,
+ [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS,
[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS,
[SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS,
[SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS,
@@ -119,7 +119,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
+/* init */ {sCW, sCW, sCW, sCE, sES, sCL, sCL, sSA, sCW, sHA},
/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 046f118de..d16aa43eb 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -605,7 +605,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr,
start += strlen(name);
*val = simple_strtoul(start, &end, 0);
if (start == end)
- return 0;
+ return -1;
if (matchoff && matchlen) {
*matchoff = start - dptr;
*matchlen = end - start;
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 84c59de27..b3a038529 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -93,8 +93,6 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry)
dev_hold(state->in);
if (state->out)
dev_hold(state->out);
- if (state->sk)
- sock_hold(state->sk);
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (entry->skb->nf_bridge) {
struct net_device *physdev;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2968f2191..3e3044116 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -22,10 +22,13 @@
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tables.h>
#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include <net/sock.h>
#define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-"))
+unsigned int nf_tables_net_id __read_mostly;
+
static LIST_HEAD(nf_tables_expressions);
static LIST_HEAD(nf_tables_objects);
static LIST_HEAD(nf_tables_flowtables);
@@ -53,7 +56,9 @@ static const struct rhashtable_params nft_chain_ht_params = {
static void nft_validate_state_update(struct net *net, u8 new_validate_state)
{
- switch (net->nft.validate_state) {
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
+
+ switch (nft_net->validate_state) {
case NFT_VALIDATE_SKIP:
WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO);
break;
@@ -64,7 +69,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state)
return;
}
- net->nft.validate_state = new_validate_state;
+ nft_net->validate_state = new_validate_state;
}
static void nft_ctx_init(struct nft_ctx *ctx,
@@ -97,6 +102,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
return NULL;
INIT_LIST_HEAD(&trans->list);
+ INIT_LIST_HEAD(&trans->binding_list);
trans->msg_type = msg_type;
trans->ctx = *ctx;
@@ -109,34 +115,68 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx,
return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL);
}
-static void nft_trans_destroy(struct nft_trans *trans)
+static void nft_trans_list_del(struct nft_trans *trans)
{
list_del(&trans->list);
+ list_del(&trans->binding_list);
+}
+
+static void nft_trans_destroy(struct nft_trans *trans)
+{
+ nft_trans_list_del(trans);
kfree(trans);
}
-static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set,
+ bool bind)
{
+ struct nftables_pernet *nft_net;
struct net *net = ctx->net;
struct nft_trans *trans;
if (!nft_set_is_anonymous(set))
return;
- list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
+ nft_net = net_generic(net, nf_tables_net_id);
+ list_for_each_entry_reverse(trans, &nft_net->commit_list, list) {
switch (trans->msg_type) {
case NFT_MSG_NEWSET:
if (nft_trans_set(trans) == set)
- nft_trans_set_bound(trans) = true;
+ nft_trans_set_bound(trans) = bind;
break;
case NFT_MSG_NEWSETELEM:
if (nft_trans_elem_set(trans) == set)
- nft_trans_elem_set_bound(trans) = true;
+ nft_trans_elem_set_bound(trans) = bind;
break;
}
}
}
+static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ return __nft_set_trans_bind(ctx, set, true);
+}
+
+static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ return __nft_set_trans_bind(ctx, set, false);
+}
+
+static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans)
+{
+ struct nftables_pernet *nft_net;
+
+ nft_net = net_generic(net, nf_tables_net_id);
+ switch (trans->msg_type) {
+ case NFT_MSG_NEWSET:
+ if (nft_set_is_anonymous(nft_trans_set(trans)))
+ list_add_tail(&trans->binding_list, &nft_net->binding_list);
+ break;
+ }
+
+ list_add_tail(&trans->list, &nft_net->commit_list);
+}
+
static int nf_tables_register_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
@@ -187,7 +227,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type)
if (msg_type == NFT_MSG_NEWTABLE)
nft_activate_next(ctx->net, ctx->table);
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
@@ -214,7 +254,7 @@ static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type)
if (msg_type == NFT_MSG_NEWCHAIN)
nft_activate_next(ctx->net, ctx->chain);
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
@@ -226,7 +266,7 @@ static int nft_delchain(struct nft_ctx *ctx)
if (err < 0)
return err;
- ctx->table->use--;
+ nft_use_dec(&ctx->table->use);
nft_deactivate_next(ctx->net, ctx->chain);
return err;
@@ -267,7 +307,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule)
/* You cannot delete the same rule twice */
if (nft_is_active_next(ctx->net, rule)) {
nft_deactivate_next(ctx->net, rule);
- ctx->chain->use--;
+ nft_use_dec(&ctx->chain->use);
return 0;
}
return -ENOENT;
@@ -287,7 +327,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type,
ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID]));
}
nft_trans_rule(trans) = rule;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return trans;
}
@@ -342,7 +382,7 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
nft_activate_next(ctx->net, set);
}
nft_trans_set(trans) = set;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
@@ -356,7 +396,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
return err;
nft_deactivate_next(ctx->net, set);
- ctx->table->use--;
+ nft_use_dec(&ctx->table->use);
return err;
}
@@ -374,7 +414,7 @@ static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type,
nft_activate_next(ctx->net, obj);
nft_trans_obj(trans) = obj;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
@@ -388,7 +428,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj)
return err;
nft_deactivate_next(ctx->net, obj);
- ctx->table->use--;
+ nft_use_dec(&ctx->table->use);
return err;
}
@@ -407,7 +447,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type,
nft_activate_next(ctx->net, flowtable);
nft_trans_flowtable(trans) = flowtable;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
@@ -422,7 +462,7 @@ static int nft_delflowtable(struct nft_ctx *ctx,
return err;
nft_deactivate_next(ctx->net, flowtable);
- ctx->table->use--;
+ nft_use_dec(&ctx->table->use);
return err;
}
@@ -435,12 +475,14 @@ static struct nft_table *nft_table_lookup(const struct net *net,
const struct nlattr *nla,
u8 family, u8 genmask)
{
+ struct nftables_pernet *nft_net;
struct nft_table *table;
if (nla == NULL)
return ERR_PTR(-EINVAL);
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ nft_net = net_generic(net, nf_tables_net_id);
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (!nla_strcmp(nla, table->name) &&
table->family == family &&
nft_active_genmask(table, genmask))
@@ -454,9 +496,11 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net,
const struct nlattr *nla,
u8 genmask)
{
+ struct nftables_pernet *nft_net;
struct nft_table *table;
- list_for_each_entry(table, &net->nft.tables, list) {
+ nft_net = net_generic(net, nf_tables_net_id);
+ list_for_each_entry(table, &nft_net->tables, list) {
if (be64_to_cpu(nla_get_be64(nla)) == table->handle &&
nft_active_genmask(table, genmask))
return table;
@@ -509,11 +553,13 @@ __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
static void nft_request_module(struct net *net, const char *fmt, ...)
{
char module_name[MODULE_NAME_LEN];
+ struct nftables_pernet *nft_net;
LIST_HEAD(commit_list);
va_list args;
int ret;
- list_splice_init(&net->nft.commit_list, &commit_list);
+ nft_net = net_generic(net, nf_tables_net_id);
+ list_splice_init(&nft_net->commit_list, &commit_list);
va_start(args, fmt);
ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
@@ -521,12 +567,12 @@ static void nft_request_module(struct net *net, const char *fmt, ...)
if (ret >= MODULE_NAME_LEN)
return;
- mutex_unlock(&net->nft.commit_mutex);
+ mutex_unlock(&nft_net->commit_mutex);
request_module("%s", module_name);
- mutex_lock(&net->nft.commit_mutex);
+ mutex_lock(&nft_net->commit_mutex);
- WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
- list_splice(&commit_list, &net->nft.commit_list);
+ WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+ list_splice(&commit_list, &nft_net->commit_list);
}
#endif
@@ -561,6 +607,13 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
return ERR_PTR(-ENOENT);
}
+static __be16 nft_base_seq(const struct net *net)
+{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
+
+ return htons(nft_net->base_seq & 0xffff);
+}
+
static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
[NFTA_TABLE_NAME] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
@@ -573,18 +626,13 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
int family, const struct nft_table *table)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
+ NFNETLINK_V0, nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) ||
@@ -631,15 +679,17 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+ struct nftables_pernet *nft_net;
const struct nft_table *table;
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
rcu_read_lock();
- cb->seq = net->nft.base_seq;
+ nft_net = net_generic(net, nf_tables_net_id);
+ cb->seq = nft_net->base_seq;
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
@@ -743,7 +793,7 @@ static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt)
if (cnt && i++ == cnt)
break;
- nf_unregister_net_hook(net, &nft_base_chain(chain)->ops);
+ nf_tables_unregister_hook(net, table, chain);
}
}
@@ -758,7 +808,7 @@ static int nf_tables_table_enable(struct net *net, struct nft_table *table)
if (!nft_is_base_chain(chain))
continue;
- err = nf_register_net_hook(net, &nft_base_chain(chain)->ops);
+ err = nf_tables_register_hook(net, table, chain);
if (err < 0)
goto err;
@@ -802,17 +852,18 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
nft_trans_table_enable(trans) = false;
} else if (!(flags & NFT_TABLE_F_DORMANT) &&
ctx->table->flags & NFT_TABLE_F_DORMANT) {
+ ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
ret = nf_tables_table_enable(ctx->net, ctx->table);
- if (ret >= 0) {
- ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
+ if (ret >= 0)
nft_trans_table_enable(trans) = true;
- }
+ else
+ ctx->table->flags |= NFT_TABLE_F_DORMANT;
}
if (ret < 0)
goto err;
nft_trans_table_update(trans) = true;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
err:
nft_trans_destroy(trans);
@@ -847,6 +898,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
@@ -856,7 +908,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
struct nft_ctx ctx;
int err;
- lockdep_assert_held(&net->nft.commit_mutex);
+ lockdep_assert_held(&nft_net->commit_mutex);
attr = nla[NFTA_TABLE_NAME];
table = nft_table_lookup(net, attr, family, genmask);
if (IS_ERR(table)) {
@@ -906,7 +958,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
if (err < 0)
goto err_trans;
- list_add_tail_rcu(&table->list, &net->nft.tables);
+ list_add_tail_rcu(&table->list, &nft_net->tables);
return 0;
err_trans:
rhltable_destroy(&table->chains_ht);
@@ -941,8 +993,7 @@ static int nft_flush_table(struct nft_ctx *ctx)
if (!nft_is_active_next(ctx->net, set))
continue;
- if (nft_set_is_anonymous(set) &&
- !list_empty(&set->bindings))
+ if (nft_set_is_anonymous(set))
continue;
err = nft_delset(ctx, set);
@@ -986,11 +1037,12 @@ out:
static int nft_flush(struct nft_ctx *ctx, int family)
{
+ struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id);
struct nft_table *table, *nt;
const struct nlattr * const *nla = ctx->nla;
int err = 0;
- list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) {
+ list_for_each_entry_safe(table, nt, &nft_net->tables, list) {
if (family != AF_UNSPEC && table->family != family)
continue;
@@ -1104,7 +1156,9 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask)
static bool lockdep_commit_lock_is_held(struct net *net)
{
#ifdef CONFIG_PROVE_LOCKING
- return lockdep_is_held(&net->nft.commit_mutex);
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
+
+ return lockdep_is_held(&nft_net->commit_mutex);
#else
return true;
#endif
@@ -1207,18 +1261,13 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
const struct nft_chain *chain)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
+ NFNETLINK_V0, nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name))
goto nla_put_failure;
if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle),
@@ -1306,11 +1355,13 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
+ struct nftables_pernet *nft_net;
rcu_read_lock();
- cb->seq = net->nft.base_seq;
+ nft_net = net_generic(net, nf_tables_net_id);
+ cb->seq = nft_net->base_seq;
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
@@ -1503,12 +1554,13 @@ static int nft_chain_parse_hook(struct net *net,
struct nft_chain_hook *hook, u8 family,
bool autoload)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nlattr *ha[NFTA_HOOK_MAX + 1];
const struct nft_chain_type *type;
struct net_device *dev;
int err;
- lockdep_assert_held(&net->nft.commit_mutex);
+ lockdep_assert_held(&nft_net->commit_mutex);
lockdep_nfnl_nft_mutex_not_held();
err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
@@ -1607,9 +1659,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
struct nft_rule **rules;
int err;
- if (table->use == UINT_MAX)
- return -EOVERFLOW;
-
if (nla[NFTA_CHAIN_HOOK]) {
struct nft_chain_hook hook;
struct nf_hook_ops *ops;
@@ -1681,6 +1730,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
if (err < 0)
goto err1;
+ if (!nft_use_inc(&table->use)) {
+ err = -EMFILE;
+ goto err_use;
+ }
+
err = rhltable_insert_key(&table->chains_ht, chain->name,
&chain->rhlhead, nft_chain_ht_params);
if (err)
@@ -1693,11 +1747,12 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
goto err2;
}
- table->use++;
list_add_tail_rcu(&chain->list, &table->chains);
return 0;
err2:
+ nft_use_dec_restore(&table->use);
+err_use:
nf_tables_unregister_hook(net, table, chain);
err1:
nf_tables_chain_destroy(ctx);
@@ -1777,6 +1832,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy)
if (nla[NFTA_CHAIN_HANDLE] &&
nla[NFTA_CHAIN_NAME]) {
+ struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id);
struct nft_trans *tmp;
char *name;
@@ -1786,7 +1842,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy)
goto err;
err = -EEXIST;
- list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) {
+ list_for_each_entry(tmp, &nft_net->commit_list, list) {
if (tmp->msg_type == NFT_MSG_NEWCHAIN &&
tmp->ctx.table == table &&
nft_trans_chain_update(tmp) &&
@@ -1799,7 +1855,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy)
nft_trans_chain_name(trans) = name;
}
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
err:
@@ -1813,6 +1869,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
@@ -1823,7 +1880,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
struct nft_ctx ctx;
u64 handle = 0;
- lockdep_assert_held(&net->nft.commit_mutex);
+ lockdep_assert_held(&nft_net->commit_mutex);
table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
if (IS_ERR(table)) {
@@ -2251,21 +2308,16 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
const struct nft_rule *rule)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
const struct nft_expr *expr, *next;
struct nlattr *list;
const struct nft_rule *prule;
u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0,
+ nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_RULE_TABLE, table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name))
@@ -2351,11 +2403,13 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
+ struct nftables_pernet *nft_net;
rcu_read_lock();
- cb->seq = net->nft.base_seq;
+ nft_net = net_generic(net, nf_tables_net_id);
+ cb->seq = nft_net->base_seq;
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
@@ -2508,7 +2562,6 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
{
struct nft_expr *expr, *next;
- lockdep_assert_held(&ctx->net->nft.commit_mutex);
/*
* Careful: some expressions might not be initialized in case this
* is called on error from nf_tables_newrule().
@@ -2574,6 +2627,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table)
err = nft_chain_validate(&ctx, chain);
if (err < 0)
return err;
+
+ cond_resched();
}
return 0;
@@ -2586,6 +2641,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
struct nft_expr_info *info = NULL;
@@ -2602,7 +2658,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
int err, rem;
u64 handle, pos_handle;
- lockdep_assert_held(&net->nft.commit_mutex);
+ lockdep_assert_held(&nft_net->commit_mutex);
table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
if (IS_ERR(table)) {
@@ -2638,9 +2694,6 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
return -EINVAL;
handle = nf_tables_alloc_handle(table);
- if (chain->use == UINT_MAX)
- return -EOVERFLOW;
-
if (nla[NFTA_RULE_POSITION]) {
pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
old_rule = __nft_rule_lookup(chain, pos_handle);
@@ -2716,23 +2769,28 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
expr = nft_expr_next(expr);
}
+ if (!nft_use_inc(&chain->use)) {
+ err = -EMFILE;
+ goto err2;
+ }
+
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
if (trans == NULL) {
err = -ENOMEM;
- goto err2;
+ goto err_destroy_flow_rule;
}
err = nft_delrule(&ctx, old_rule);
if (err < 0) {
nft_trans_destroy(trans);
- goto err2;
+ goto err_destroy_flow_rule;
}
list_add_tail_rcu(&rule->list, &old_rule->list);
} else {
if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
err = -ENOMEM;
- goto err2;
+ goto err_destroy_flow_rule;
}
if (nlh->nlmsg_flags & NLM_F_APPEND) {
@@ -2748,14 +2806,17 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
}
}
kvfree(info);
- chain->use++;
- if (net->nft.validate_state == NFT_VALIDATE_DO)
+ if (nft_net->validate_state == NFT_VALIDATE_DO)
return nft_table_validate(net, table);
return 0;
+
+err_destroy_flow_rule:
+ nft_use_dec_restore(&chain->use);
err2:
- nf_tables_rule_release(&ctx, rule);
+ nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR);
+ nf_tables_rule_destroy(&ctx, rule);
err1:
for (i = 0; i < n; i++) {
if (info[i].ops) {
@@ -2772,10 +2833,11 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
const struct nft_chain *chain,
const struct nlattr *nla)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
u32 id = ntohl(nla_get_be32(nla));
struct nft_trans *trans;
- list_for_each_entry(trans, &net->nft.commit_list, list) {
+ list_for_each_entry(trans, &nft_net->commit_list, list) {
struct nft_rule *rule = nft_trans_rule(trans);
if (trans->msg_type == NFT_MSG_NEWRULE &&
@@ -2894,12 +2956,13 @@ nft_select_set_ops(const struct nft_ctx *ctx,
const struct nft_set_desc *desc,
enum nft_set_policies policy)
{
+ struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id);
const struct nft_set_ops *ops, *bops;
struct nft_set_estimate est, best;
const struct nft_set_type *type;
u32 flags = 0;
- lockdep_assert_held(&ctx->net->nft.commit_mutex);
+ lockdep_assert_held(&nft_net->commit_mutex);
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
if (list_empty(&nf_tables_set_types)) {
@@ -3045,10 +3108,11 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net,
const struct nft_table *table,
const struct nlattr *nla, u8 genmask)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nft_trans *trans;
u32 id = ntohl(nla_get_be32(nla));
- list_for_each_entry(trans, &net->nft.commit_list, list) {
+ list_for_each_entry(trans, &nft_net->commit_list, list) {
if (trans->msg_type == NFT_MSG_NEWSET) {
struct nft_set *set = nft_trans_set(trans);
@@ -3158,23 +3222,17 @@ static __be64 nf_jiffies64_to_msecs(u64 input)
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
- struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
struct nlattr *desc;
u32 portid = ctx->portid;
u32 seq = ctx->seq;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
- flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family,
+ NFNETLINK_V0, nft_base_seq(ctx->net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = ctx->family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_SET_NAME, set->name))
@@ -3270,14 +3328,16 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
struct net *net = sock_net(skb->sk);
struct nft_ctx *ctx = cb->data, ctx_set;
+ struct nftables_pernet *nft_net;
if (cb->args[1])
return skb->len;
rcu_read_lock();
- cb->seq = net->nft.base_seq;
+ nft_net = net_generic(net, nf_tables_net_id);
+ cb->seq = nft_net->base_seq;
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (ctx->family != NFPROTO_UNSPEC &&
ctx->family != table->family)
continue;
@@ -3571,10 +3631,15 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
if (ops->privsize != NULL)
size = ops->privsize(nla, &desc);
+ if (!nft_use_inc(&table->use)) {
+ err = -EMFILE;
+ goto err1;
+ }
+
set = kvzalloc(sizeof(*set) + size + udlen, GFP_KERNEL);
if (!set) {
err = -ENOMEM;
- goto err1;
+ goto err_alloc;
}
name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL);
@@ -3621,7 +3686,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
goto err4;
list_add_tail_rcu(&set->list, &table->sets);
- table->use++;
+
return 0;
err4:
@@ -3630,6 +3695,8 @@ err3:
kfree(set->name);
err2:
kvfree(set);
+err_alloc:
+ nft_use_dec_restore(&table->use);
err1:
module_put(to_set_type(ops)->owner);
return err;
@@ -3716,9 +3783,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *i;
struct nft_set_iter iter;
- if (set->use == UINT_MAX)
- return -EOVERFLOW;
-
if (!list_empty(&set->bindings) && nft_set_is_anonymous(set))
return -EBUSY;
@@ -3743,10 +3807,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
return iter.err;
}
bind:
+ if (!nft_use_inc(&set->use))
+ return -EMFILE;
+
binding->chain = ctx->chain;
list_add_tail_rcu(&binding->list, &set->bindings);
nft_set_trans_bind(ctx, set);
- set->use++;
return 0;
}
@@ -3771,7 +3837,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set)
if (nft_set_is_anonymous(set))
nft_clear(ctx->net, set);
- set->use++;
+ nft_use_inc_restore(&set->use);
}
EXPORT_SYMBOL_GPL(nf_tables_activate_set);
@@ -3780,15 +3846,24 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
enum nft_trans_phase phase)
{
switch (phase) {
+ case NFT_TRANS_PREPARE_ERROR:
+ nft_set_trans_unbind(ctx, set);
+ if (nft_set_is_anonymous(set))
+ nft_deactivate_next(ctx->net, set);
+ else
+ list_del_rcu(&binding->list);
+
+ nft_use_dec(&set->use);
+ break;
case NFT_TRANS_PREPARE:
if (nft_set_is_anonymous(set))
nft_deactivate_next(ctx->net, set);
- set->use--;
+ nft_use_dec(&set->use);
return;
case NFT_TRANS_ABORT:
case NFT_TRANS_RELEASE:
- set->use--;
+ nft_use_dec(&set->use);
/* fall through */
default:
nf_tables_unbind_set(ctx, set, binding,
@@ -3984,18 +4059,19 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
{
struct nft_set_dump_ctx *dump_ctx = cb->data;
struct net *net = sock_net(skb->sk);
+ struct nftables_pernet *nft_net;
struct nft_table *table;
struct nft_set *set;
struct nft_set_dump_args args;
bool set_found = false;
- struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
struct nlattr *nest;
u32 portid, seq;
int event;
rcu_read_lock();
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ nft_net = net_generic(net, nf_tables_net_id);
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
dump_ctx->ctx.family != table->family)
continue;
@@ -4021,16 +4097,11 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
portid = NETLINK_CB(cb->skb).portid;
seq = cb->nlh->nlmsg_seq;
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
- NLM_F_MULTI);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI,
+ table->family, NFNETLINK_V0, nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = table->family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name))
@@ -4087,22 +4158,16 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
- struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
struct nlattr *nest;
int err;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
- flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family,
+ NFNETLINK_V0, nft_base_seq(ctx->net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = ctx->family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_SET_NAME, set->name))
@@ -4380,7 +4445,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
}
}
if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
- (*nft_set_ext_obj(ext))->use--;
+ nft_use_dec(&(*nft_set_ext_obj(ext))->use);
kfree(elem);
}
EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
@@ -4489,8 +4554,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
set->objtype, genmask);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
+ obj = NULL;
+ goto err2;
+ }
+
+ if (!nft_use_inc(&obj->use)) {
+ err = -EMFILE;
+ obj = NULL;
goto err2;
}
+
nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
}
@@ -4555,10 +4628,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
udata->len = ulen - 1;
nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen);
}
- if (obj) {
+ if (obj)
*nft_set_ext_obj(ext) = obj;
- obj->use++;
- }
trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
if (trans == NULL)
@@ -4596,7 +4667,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
}
nft_trans_elem(trans) = elem;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
err6:
@@ -4604,13 +4675,14 @@ err6:
err5:
kfree(trans);
err4:
- if (obj)
- obj->use--;
kfree(elem.priv);
err3:
if (nla[NFTA_SET_ELEM_DATA] != NULL)
nft_data_release(&elem.data.val, desc.type);
err2:
+ if (obj)
+ nft_use_dec_restore(&obj->use);
+
nft_data_release(&elem.key.val, NFT_DATA_VALUE);
err1:
return err;
@@ -4621,6 +4693,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
u8 genmask = nft_genmask_next(net);
const struct nlattr *attr;
struct nft_set *set;
@@ -4650,7 +4723,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
return err;
}
- if (net->nft.validate_state == NFT_VALIDATE_DO)
+ if (nft_net->validate_state == NFT_VALIDATE_DO)
return nft_table_validate(net, ctx.table);
return 0;
@@ -4669,11 +4742,14 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
*/
void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
{
+ struct nft_chain *chain;
+
if (type == NFT_DATA_VERDICT) {
switch (data->verdict.code) {
case NFT_JUMP:
case NFT_GOTO:
- data->verdict.chain->use++;
+ chain = data->verdict.chain;
+ nft_use_inc_restore(&chain->use);
break;
}
}
@@ -4688,7 +4764,7 @@ static void nft_set_elem_activate(const struct net *net,
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
nft_data_hold(nft_set_ext_data(ext), set->dtype);
if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
- (*nft_set_ext_obj(ext))->use++;
+ nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use);
}
static void nft_set_elem_deactivate(const struct net *net,
@@ -4700,7 +4776,7 @@ static void nft_set_elem_deactivate(const struct net *net,
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
nft_data_release(nft_set_ext_data(ext), set->dtype);
if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
- (*nft_set_ext_obj(ext))->use--;
+ nft_use_dec(&(*nft_set_ext_obj(ext))->use);
}
static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
@@ -4763,7 +4839,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
nft_set_elem_deactivate(ctx->net, set, &elem);
nft_trans_elem(trans) = elem;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
fail_ops:
@@ -4797,7 +4873,7 @@ static int nft_flush_set(const struct nft_ctx *ctx,
nft_set_elem_deactivate(ctx->net, set, elem);
nft_trans_elem_set(trans) = set;
nft_trans_elem(trans) = *elem;
- list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+ nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
err1:
@@ -4825,8 +4901,10 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
if (IS_ERR(set))
return PTR_ERR(set);
- if (!list_empty(&set->bindings) &&
- (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS)))
+ if (nft_set_is_anonymous(set))
+ return -EOPNOTSUPP;
+
+ if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT))
return -EBUSY;
if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) {
@@ -5097,9 +5175,14 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
+ if (!nft_use_inc(&table->use))
+ return -EMFILE;
+
type = nft_obj_type_get(net, objtype);
- if (IS_ERR(type))
- return PTR_ERR(type);
+ if (IS_ERR(type)) {
+ err = PTR_ERR(type);
+ goto err_type;
+ }
obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
if (IS_ERR(obj)) {
@@ -5120,7 +5203,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
goto err3;
list_add_tail_rcu(&obj->list, &table->objects);
- table->use++;
+
return 0;
err3:
kfree(obj->name);
@@ -5130,6 +5213,9 @@ err2:
kfree(obj);
err1:
module_put(type->owner);
+err_type:
+ nft_use_dec_restore(&table->use);
+
return err;
}
@@ -5138,19 +5224,14 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
int family, const struct nft_table *table,
struct nft_object *obj, bool reset)
{
- struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
+ NFNETLINK_V0, nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) ||
nla_put_string(skb, NFTA_OBJ_NAME, obj->name) ||
nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) ||
@@ -5181,6 +5262,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
struct nft_obj_filter *filter = cb->data;
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
+ struct nftables_pernet *nft_net;
struct nft_object *obj;
bool reset = false;
@@ -5188,9 +5270,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
reset = true;
rcu_read_lock();
- cb->seq = net->nft.base_seq;
+ nft_net = net_generic(net, nf_tables_net_id);
+ cb->seq = nft_net->base_seq;
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
@@ -5468,6 +5551,23 @@ struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
}
EXPORT_SYMBOL_GPL(nft_flowtable_lookup);
+void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx,
+ struct nft_flowtable *flowtable,
+ enum nft_trans_phase phase)
+{
+ switch (phase) {
+ case NFT_TRANS_PREPARE_ERROR:
+ case NFT_TRANS_PREPARE:
+ case NFT_TRANS_ABORT:
+ case NFT_TRANS_RELEASE:
+ nft_use_dec(&flowtable->use);
+ /* fall through */
+ default:
+ return;
+ }
+}
+EXPORT_SYMBOL_GPL(nf_tables_deactivate_flowtable);
+
static struct nft_flowtable *
nft_flowtable_lookup_byhandle(const struct nft_table *table,
const struct nlattr *nla, u8 genmask)
@@ -5667,9 +5767,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
+ if (!nft_use_inc(&table->use))
+ return -EMFILE;
+
flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL);
- if (!flowtable)
- return -ENOMEM;
+ if (!flowtable) {
+ err = -ENOMEM;
+ goto flowtable_alloc;
+ }
flowtable->table = table;
flowtable->handle = nf_tables_alloc_handle(table);
@@ -5723,7 +5828,6 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
goto err6;
list_add_tail_rcu(&flowtable->list, &table->flowtables);
- table->use++;
return 0;
err6:
@@ -5741,6 +5845,9 @@ err2:
kfree(flowtable->name);
err1:
kfree(flowtable);
+flowtable_alloc:
+ nft_use_dec_restore(&table->use);
+
return err;
}
@@ -5798,20 +5905,15 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
struct nft_flowtable *flowtable)
{
struct nlattr *nest, *nest_devs;
- struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
int i;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
+ NFNETLINK_V0, nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) ||
nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) ||
nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) ||
@@ -5861,12 +5963,14 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
struct nft_flowtable *flowtable;
+ struct nftables_pernet *nft_net;
const struct nft_table *table;
rcu_read_lock();
- cb->seq = net->nft.base_seq;
+ nft_net = net_generic(net, nf_tables_net_id);
+ cb->seq = nft_net->base_seq;
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
+ list_for_each_entry_rcu(table, &nft_net->tables, list) {
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
@@ -6036,21 +6140,17 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
char buf[TASK_COMM_LEN];
int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC,
+ NFNETLINK_V0, nft_base_seq(net));
+ if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
-
- if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) ||
+ if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) ||
nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) ||
nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current)))
goto nla_put_failure;
@@ -6083,6 +6183,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this,
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct nft_flowtable *flowtable;
+ struct nftables_pernet *nft_net;
struct nft_table *table;
struct net *net;
@@ -6090,13 +6191,14 @@ static int nf_tables_flowtable_event(struct notifier_block *this,
return 0;
net = dev_net(dev);
- mutex_lock(&net->nft.commit_mutex);
- list_for_each_entry(table, &net->nft.tables, list) {
+ nft_net = net_generic(net, nf_tables_net_id);
+ mutex_lock(&nft_net->commit_mutex);
+ list_for_each_entry(table, &nft_net->tables, list) {
list_for_each_entry(flowtable, &table->flowtables, list) {
nft_flowtable_event(event, dev, flowtable);
}
}
- mutex_unlock(&net->nft.commit_mutex);
+ mutex_unlock(&nft_net->commit_mutex);
return NOTIFY_DONE;
}
@@ -6277,16 +6379,17 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
static int nf_tables_validate(struct net *net)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nft_table *table;
- switch (net->nft.validate_state) {
+ switch (nft_net->validate_state) {
case NFT_VALIDATE_SKIP:
break;
case NFT_VALIDATE_NEED:
nft_validate_state_update(net, NFT_VALIDATE_DO);
/* fall through */
case NFT_VALIDATE_DO:
- list_for_each_entry(table, &net->nft.tables, list) {
+ list_for_each_entry(table, &nft_net->tables, list) {
if (nft_table_validate(net, table) < 0)
return -EAGAIN;
}
@@ -6363,15 +6466,16 @@ static void nft_commit_release(struct nft_trans *trans)
static void nf_tables_commit_release(struct net *net)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nft_trans *trans, *next;
- if (list_empty(&net->nft.commit_list))
+ if (list_empty(&nft_net->commit_list))
return;
synchronize_rcu();
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
- list_del(&trans->list);
+ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) {
+ nft_trans_list_del(trans);
nft_commit_release(trans);
}
}
@@ -6409,9 +6513,10 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha
static void nf_tables_commit_chain_prepare_cancel(struct net *net)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nft_trans *trans, *next;
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) {
struct nft_chain *chain = trans->ctx.chain;
if (trans->msg_type == NFT_MSG_NEWRULE ||
@@ -6503,17 +6608,30 @@ static void nft_chain_del(struct nft_chain *chain)
static int nf_tables_commit(struct net *net, struct sk_buff *skb)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
struct nft_chain *chain;
struct nft_table *table;
+ list_for_each_entry(trans, &nft_net->binding_list, binding_list) {
+ switch (trans->msg_type) {
+ case NFT_MSG_NEWSET:
+ if (nft_set_is_anonymous(nft_trans_set(trans)) &&
+ !nft_trans_set_bound(trans)) {
+ pr_warn_once("nftables ruleset with unbound set\n");
+ return -EINVAL;
+ }
+ break;
+ }
+ }
+
/* 0. Validate ruleset, otherwise roll back for error reporting. */
if (nf_tables_validate(net) < 0)
return -EAGAIN;
/* 1. Allocate space for next generation rules_gen_X[] */
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) {
int ret;
if (trans->msg_type == NFT_MSG_NEWRULE ||
@@ -6529,7 +6647,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
}
/* step 2. Make rules_gen_X visible to packet path */
- list_for_each_entry(table, &net->nft.tables, list) {
+ list_for_each_entry(table, &nft_net->tables, list) {
list_for_each_entry(chain, &table->chains, list)
nf_tables_commit_chain(net, chain);
}
@@ -6538,12 +6656,13 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
* Bump generation counter, invalidate any dump in progress.
* Cannot fail after this point.
*/
- while (++net->nft.base_seq == 0);
+ while (++nft_net->base_seq == 0)
+ ;
/* step 3. Start new generation, rules_gen_X now in use. */
net->nft.gencursor = nft_gencursor_next(net);
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) {
switch (trans->msg_type) {
case NFT_MSG_NEWTABLE:
if (nft_trans_table_update(trans)) {
@@ -6603,7 +6722,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
*/
if (nft_set_is_anonymous(nft_trans_set(trans)) &&
!list_empty(&nft_trans_set(trans)->bindings))
- trans->ctx.table->use--;
+ nft_use_dec(&trans->ctx.table->use);
nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
NFT_MSG_NEWSET, GFP_KERNEL);
@@ -6664,7 +6783,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_commit_release(net);
nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
- mutex_unlock(&net->nft.commit_mutex);
+ mutex_unlock(&nft_net->commit_mutex);
return 0;
}
@@ -6700,10 +6819,11 @@ static void nf_tables_abort_release(struct nft_trans *trans)
static int __nf_tables_abort(struct net *net)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
- list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
+ list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list,
list) {
switch (trans->msg_type) {
case NFT_MSG_NEWTABLE:
@@ -6728,7 +6848,7 @@ static int __nf_tables_abort(struct net *net)
kfree(nft_trans_chain_name(trans));
nft_trans_destroy(trans);
} else {
- trans->ctx.table->use--;
+ nft_use_dec_restore(&trans->ctx.table->use);
nft_chain_del(trans->ctx.chain);
nf_tables_unregister_hook(trans->ctx.net,
trans->ctx.table,
@@ -6736,25 +6856,25 @@ static int __nf_tables_abort(struct net *net)
}
break;
case NFT_MSG_DELCHAIN:
- trans->ctx.table->use++;
+ nft_use_inc_restore(&trans->ctx.table->use);
nft_clear(trans->ctx.net, trans->ctx.chain);
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWRULE:
- trans->ctx.chain->use--;
+ nft_use_dec_restore(&trans->ctx.chain->use);
list_del_rcu(&nft_trans_rule(trans)->list);
nft_rule_expr_deactivate(&trans->ctx,
nft_trans_rule(trans),
NFT_TRANS_ABORT);
break;
case NFT_MSG_DELRULE:
- trans->ctx.chain->use++;
+ nft_use_inc_restore(&trans->ctx.chain->use);
nft_clear(trans->ctx.net, nft_trans_rule(trans));
nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans));
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSET:
- trans->ctx.table->use--;
+ nft_use_dec_restore(&trans->ctx.table->use);
if (nft_trans_set_bound(trans)) {
nft_trans_destroy(trans);
break;
@@ -6762,7 +6882,7 @@ static int __nf_tables_abort(struct net *net)
list_del_rcu(&nft_trans_set(trans)->list);
break;
case NFT_MSG_DELSET:
- trans->ctx.table->use++;
+ nft_use_inc_restore(&trans->ctx.table->use);
nft_clear(trans->ctx.net, nft_trans_set(trans));
nft_trans_destroy(trans);
break;
@@ -6785,22 +6905,22 @@ static int __nf_tables_abort(struct net *net)
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWOBJ:
- trans->ctx.table->use--;
+ nft_use_dec_restore(&trans->ctx.table->use);
list_del_rcu(&nft_trans_obj(trans)->list);
break;
case NFT_MSG_DELOBJ:
- trans->ctx.table->use++;
+ nft_use_inc_restore(&trans->ctx.table->use);
nft_clear(trans->ctx.net, nft_trans_obj(trans));
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWFLOWTABLE:
- trans->ctx.table->use--;
+ nft_use_dec_restore(&trans->ctx.table->use);
list_del_rcu(&nft_trans_flowtable(trans)->list);
nft_unregister_flowtable_net_hooks(net,
nft_trans_flowtable(trans));
break;
case NFT_MSG_DELFLOWTABLE:
- trans->ctx.table->use++;
+ nft_use_inc_restore(&trans->ctx.table->use);
nft_clear(trans->ctx.net, nft_trans_flowtable(trans));
nft_trans_destroy(trans);
break;
@@ -6810,8 +6930,8 @@ static int __nf_tables_abort(struct net *net)
synchronize_rcu();
list_for_each_entry_safe_reverse(trans, next,
- &net->nft.commit_list, list) {
- list_del(&trans->list);
+ &nft_net->commit_list, list) {
+ nft_trans_list_del(trans);
nf_tables_abort_release(trans);
}
@@ -6820,22 +6940,24 @@ static int __nf_tables_abort(struct net *net)
static int nf_tables_abort(struct net *net, struct sk_buff *skb)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
int ret = __nf_tables_abort(net);
- mutex_unlock(&net->nft.commit_mutex);
+ mutex_unlock(&nft_net->commit_mutex);
return ret;
}
static bool nf_tables_valid_genid(struct net *net, u32 genid)
{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
bool genid_ok;
- mutex_lock(&net->nft.commit_mutex);
+ mutex_lock(&nft_net->commit_mutex);
- genid_ok = genid == 0 || net->nft.base_seq == genid;
+ genid_ok = genid == 0 || nft_net->base_seq == genid;
if (!genid_ok)
- mutex_unlock(&net->nft.commit_mutex);
+ mutex_unlock(&nft_net->commit_mutex);
/* else, commit mutex has to be released by commit or abort function */
return genid_ok;
@@ -7182,6 +7304,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
if (!tb[NFTA_VERDICT_CODE])
return -EINVAL;
+
+ /* zero padding hole for memcmp */
+ memset(data, 0, sizeof(*data));
data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
switch (data->verdict.code) {
@@ -7209,8 +7334,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
return PTR_ERR(chain);
if (nft_is_base_chain(chain))
return -EOPNOTSUPP;
+ if (!nft_use_inc(&chain->use))
+ return -EMFILE;
- chain->use++;
data->verdict.chain = chain;
break;
}
@@ -7222,10 +7348,13 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
static void nft_verdict_uninit(const struct nft_data *data)
{
+ struct nft_chain *chain;
+
switch (data->verdict.code) {
case NFT_JUMP:
case NFT_GOTO:
- data->verdict.chain->use--;
+ chain = data->verdict.chain;
+ nft_use_dec(&chain->use);
break;
}
}
@@ -7378,21 +7507,20 @@ int __nft_release_basechain(struct nft_ctx *ctx)
nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain);
list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
list_del(&rule->list);
- ctx->chain->use--;
+ nft_use_dec(&ctx->chain->use);
nf_tables_rule_release(ctx, rule);
}
nft_chain_del(ctx->chain);
- ctx->table->use--;
+ nft_use_dec(&ctx->table->use);
nf_tables_chain_destroy(ctx);
return 0;
}
EXPORT_SYMBOL_GPL(__nft_release_basechain);
-static void __nft_release_tables(struct net *net)
+static void __nft_release_table(struct net *net, struct nft_table *table)
{
struct nft_flowtable *flowtable, *nf;
- struct nft_table *table, *nt;
struct nft_chain *chain, *nc;
struct nft_object *obj, *ne;
struct nft_rule *rule, *nr;
@@ -7402,71 +7530,85 @@ static void __nft_release_tables(struct net *net)
.family = NFPROTO_NETDEV,
};
- list_for_each_entry_safe(table, nt, &net->nft.tables, list) {
- ctx.family = table->family;
+ ctx.family = table->family;
- list_for_each_entry(chain, &table->chains, list)
- nf_tables_unregister_hook(net, table, chain);
- /* No packets are walking on these chains anymore. */
- ctx.table = table;
- list_for_each_entry(chain, &table->chains, list) {
- ctx.chain = chain;
- list_for_each_entry_safe(rule, nr, &chain->rules, list) {
- list_del(&rule->list);
- chain->use--;
- nf_tables_rule_release(&ctx, rule);
- }
- }
- list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
- list_del(&flowtable->list);
- table->use--;
- nf_tables_flowtable_destroy(flowtable);
- }
- list_for_each_entry_safe(set, ns, &table->sets, list) {
- list_del(&set->list);
- table->use--;
- nft_set_destroy(set);
- }
- list_for_each_entry_safe(obj, ne, &table->objects, list) {
- list_del(&obj->list);
- table->use--;
- nft_obj_destroy(&ctx, obj);
- }
- list_for_each_entry_safe(chain, nc, &table->chains, list) {
- ctx.chain = chain;
- nft_chain_del(chain);
- table->use--;
- nf_tables_chain_destroy(&ctx);
+ list_for_each_entry(chain, &table->chains, list)
+ nf_tables_unregister_hook(net, table, chain);
+ /* No packets are walking on these chains anymore. */
+ ctx.table = table;
+ list_for_each_entry(chain, &table->chains, list) {
+ ctx.chain = chain;
+ list_for_each_entry_safe(rule, nr, &chain->rules, list) {
+ list_del(&rule->list);
+ nft_use_dec(&chain->use);
+ nf_tables_rule_release(&ctx, rule);
}
- list_del(&table->list);
- nf_tables_table_destroy(&ctx);
}
+ list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
+ list_del(&flowtable->list);
+ nft_use_dec(&table->use);
+ nf_tables_flowtable_destroy(flowtable);
+ }
+ list_for_each_entry_safe(set, ns, &table->sets, list) {
+ list_del(&set->list);
+ nft_use_dec(&table->use);
+ nft_set_destroy(set);
+ }
+ list_for_each_entry_safe(obj, ne, &table->objects, list) {
+ list_del(&obj->list);
+ nft_use_dec(&table->use);
+ nft_obj_destroy(&ctx, obj);
+ }
+ list_for_each_entry_safe(chain, nc, &table->chains, list) {
+ ctx.chain = chain;
+ nft_chain_del(chain);
+ nft_use_dec(&table->use);
+ nf_tables_chain_destroy(&ctx);
+ }
+ list_del(&table->list);
+ nf_tables_table_destroy(&ctx);
+}
+
+static void __nft_release_tables(struct net *net)
+{
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
+ struct nft_table *table, *nt;
+
+ list_for_each_entry_safe(table, nt, &nft_net->tables, list)
+ __nft_release_table(net, table);
}
static int __net_init nf_tables_init_net(struct net *net)
{
- INIT_LIST_HEAD(&net->nft.tables);
- INIT_LIST_HEAD(&net->nft.commit_list);
- mutex_init(&net->nft.commit_mutex);
- net->nft.base_seq = 1;
- net->nft.validate_state = NFT_VALIDATE_SKIP;
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
+
+ INIT_LIST_HEAD(&nft_net->tables);
+ INIT_LIST_HEAD(&nft_net->commit_list);
+ INIT_LIST_HEAD(&nft_net->binding_list);
+ mutex_init(&nft_net->commit_mutex);
+ nft_net->base_seq = 1;
+ nft_net->validate_state = NFT_VALIDATE_SKIP;
return 0;
}
static void __net_exit nf_tables_exit_net(struct net *net)
{
- mutex_lock(&net->nft.commit_mutex);
- if (!list_empty(&net->nft.commit_list))
+ struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id);
+
+ mutex_lock(&nft_net->commit_mutex);
+ if (!list_empty(&nft_net->commit_list))
__nf_tables_abort(net);
__nft_release_tables(net);
- mutex_unlock(&net->nft.commit_mutex);
- WARN_ON_ONCE(!list_empty(&net->nft.tables));
+ mutex_unlock(&nft_net->commit_mutex);
+ WARN_ON_ONCE(!list_empty(&nft_net->tables));
}
static struct pernet_operations nf_tables_net_ops = {
.init = nf_tables_init_net,
.exit = nf_tables_exit_net,
+ .id = &nf_tables_net_id,
+ .size = sizeof(struct nftables_pernet),
};
static int __init nf_tables_module_init(void)
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index e1dc527a4..7a19c517b 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -186,7 +186,6 @@ static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info)
void nft_trace_notify(struct nft_traceinfo *info)
{
const struct nft_pktinfo *pkt = info->pkt;
- struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
struct sk_buff *skb;
unsigned int size;
@@ -222,15 +221,11 @@ void nft_trace_notify(struct nft_traceinfo *info)
return;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_TRACE);
- nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct nfgenmsg), 0);
+ nlh = nfnl_msg_put(skb, 0, 0, event, 0, info->basechain->type->family,
+ NFNETLINK_V0, 0);
if (!nlh)
goto nla_put_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = info->basechain->type->family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(nft_pf(pkt))))
goto nla_put_failure;
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 8fa8bf7c4..7c5f428dc 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -135,21 +135,16 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
int event, struct nf_acct *acct)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0;
u64 pkts, bytes;
u32 old_flags;
event = nfnl_msg_type(NFNL_SUBSYS_ACCT, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (nla_put_string(skb, NFACCT_NAME, acct->name))
goto nla_put_failure;
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index c8b0f1122..720177721 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -532,20 +532,15 @@ nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
int event, struct nf_conntrack_helper *helper)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0;
int status;
event = nfnl_msg_type(NFNL_SUBSYS_CTHELPER, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (nla_put_string(skb, NFCTH_NAME, helper->name))
goto nla_put_failure;
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 70a7382b9..ae01e9ad5 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -164,20 +164,15 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
int event, struct ctnl_timeout *timeout)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0;
const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto;
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = AF_UNSPEC;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) ||
nla_put_be16(skb, CTA_TIMEOUT_L3PROTO,
htons(timeout->timeout.l3num)) ||
@@ -396,19 +391,14 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
const unsigned int *timeouts)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0;
event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC,
+ NFNETLINK_V0, 0);
+ if (!nlh)
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;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 17ca9a681..1735bcb07 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -404,20 +404,15 @@ __build_packet_message(struct nfnl_log_net *log,
{
struct nfulnl_msg_packet_hdr pmsg;
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
sk_buff_data_t old_tail = inst->skb->tail;
struct sock *sk;
const unsigned char *hwhdrp;
- nlh = nlmsg_put(inst->skb, 0, 0,
- nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET),
- sizeof(struct nfgenmsg), 0);
+ nlh = nfnl_msg_put(inst->skb, 0, 0,
+ nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET),
+ 0, pf, NFNETLINK_V0, htons(inst->group_num));
if (!nlh)
return -1;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = pf;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(inst->group_num);
memset(&pmsg, 0, sizeof(pmsg));
pmsg.hw_protocol = skb->protocol;
@@ -636,8 +631,8 @@ nfulnl_log_packet(struct net *net,
unsigned int plen = 0;
struct nfnl_log_net *log = nfnl_log_pernet(net);
const struct nfnl_ct_hook *nfnl_ct = NULL;
+ enum ip_conntrack_info ctinfo = 0;
struct nf_conn *ct = NULL;
- enum ip_conntrack_info uninitialized_var(ctinfo);
if (li_user && li_user->type == NF_LOG_TYPE_ULOG)
li = li_user;
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 21e4554c7..f3676238e 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -318,6 +318,14 @@ static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl,
f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
+ if (f->opt_num > ARRAY_SIZE(f->opt))
+ return -EINVAL;
+
+ if (!memchr(f->genre, 0, MAXGENRELEN) ||
+ !memchr(f->subtype, 0, MAXGENRELEN) ||
+ !memchr(f->version, 0, MAXGENRELEN))
+ return -EINVAL;
+
kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL);
if (!kf)
return -ENOMEM;
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index cd496b074..1aacc31a6 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -387,12 +387,11 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
struct nlattr *nla;
struct nfqnl_msg_packet_hdr *pmsg;
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
struct sk_buff *entskb = entry->skb;
struct net_device *indev;
struct net_device *outdev;
struct nf_conn *ct = NULL;
- enum ip_conntrack_info uninitialized_var(ctinfo);
+ enum ip_conntrack_info ctinfo;
struct nfnl_ct_hook *nfnl_ct;
bool csum_verify;
char *secdata = NULL;
@@ -473,18 +472,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
goto nlmsg_failure;
}
- nlh = nlmsg_put(skb, 0, 0,
- nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET),
- sizeof(struct nfgenmsg), 0);
+ nlh = nfnl_msg_put(skb, 0, 0,
+ nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET),
+ 0, entry->state.pf, NFNETLINK_V0,
+ htons(queue->queue_num));
if (!nlh) {
skb_tx_error(entskb);
kfree_skb(skb);
goto nlmsg_failure;
}
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = entry->state.pf;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = htons(queue->queue_num);
nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg));
pmsg = nla_data(nla);
@@ -1191,7 +1187,7 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl,
struct nfqnl_instance *queue;
unsigned int verdict;
struct nf_queue_entry *entry;
- enum ip_conntrack_info uninitialized_var(ctinfo);
+ enum ip_conntrack_info ctinfo;
struct nfnl_ct_hook *nfnl_ct;
struct nf_conn *ct = NULL;
struct nfnl_queue_net *q = nfnl_queue_pernet(net);
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 5e1fbdd7b..dba16126c 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -33,11 +33,11 @@ static void nft_byteorder_eval(const struct nft_expr *expr,
const struct nft_byteorder *priv = nft_expr_priv(expr);
u32 *src = &regs->data[priv->sreg];
u32 *dst = &regs->data[priv->dreg];
- union { u32 u32; u16 u16; } *s, *d;
+ u16 *s16, *d16;
unsigned int i;
- s = (void *)src;
- d = (void *)dst;
+ s16 = (void *)src;
+ d16 = (void *)dst;
switch (priv->size) {
case 8: {
@@ -63,11 +63,11 @@ static void nft_byteorder_eval(const struct nft_expr *expr,
switch (priv->op) {
case NFT_BYTEORDER_NTOH:
for (i = 0; i < priv->len / 4; i++)
- d[i].u32 = ntohl((__force __be32)s[i].u32);
+ dst[i] = ntohl((__force __be32)src[i]);
break;
case NFT_BYTEORDER_HTON:
for (i = 0; i < priv->len / 4; i++)
- d[i].u32 = (__force __u32)htonl(s[i].u32);
+ dst[i] = (__force __u32)htonl(src[i]);
break;
}
break;
@@ -75,11 +75,11 @@ static void nft_byteorder_eval(const struct nft_expr *expr,
switch (priv->op) {
case NFT_BYTEORDER_NTOH:
for (i = 0; i < priv->len / 2; i++)
- d[i].u16 = ntohs((__force __be16)s[i].u16);
+ d16[i] = ntohs((__force __be16)s16[i]);
break;
case NFT_BYTEORDER_HTON:
for (i = 0; i < priv->len / 2; i++)
- d[i].u16 = (__force __u16)htons(s[i].u16);
+ d16[i] = (__force __u16)htons(s16[i]);
break;
}
break;
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 3fd540b2c..a308d45ee 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -2,6 +2,7 @@
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include <net/netfilter/nf_tables.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
@@ -10,6 +11,8 @@
#include <net/netfilter/nf_tables_ipv4.h>
#include <net/netfilter/nf_tables_ipv6.h>
+extern unsigned int nf_tables_net_id;
+
#ifdef CONFIG_NF_TABLES_IPV4
static unsigned int nft_do_chain_ipv4(void *priv,
struct sk_buff *skb,
@@ -315,6 +318,7 @@ static int nf_tables_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct nftables_pernet *nft_net;
struct nft_table *table;
struct nft_chain *chain, *nr;
struct nft_ctx ctx = {
@@ -325,8 +329,9 @@ static int nf_tables_netdev_event(struct notifier_block *this,
event != NETDEV_CHANGENAME)
return NOTIFY_DONE;
- mutex_lock(&ctx.net->nft.commit_mutex);
- list_for_each_entry(table, &ctx.net->nft.tables, list) {
+ nft_net = net_generic(ctx.net, nf_tables_net_id);
+ mutex_lock(&nft_net->commit_mutex);
+ list_for_each_entry(table, &nft_net->tables, list) {
if (table->family != NFPROTO_NETDEV)
continue;
@@ -340,7 +345,7 @@ static int nf_tables_netdev_event(struct notifier_block *this,
nft_netdev_event(event, dev, &ctx);
}
}
- mutex_unlock(&ctx.net->nft.commit_mutex);
+ mutex_unlock(&nft_net->commit_mutex);
return NOTIFY_DONE;
}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 469f9da50..2846d6465 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -575,19 +575,14 @@ nfnl_compat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
int rev, int target)
{
struct nlmsghdr *nlh;
- struct nfgenmsg *nfmsg;
unsigned int flags = portid ? NLM_F_MULTI : 0;
event = nfnl_msg_type(NFNL_SUBSYS_NFT_COMPAT, event);
- nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
- if (nlh == NULL)
+ nlh = nfnl_msg_put(skb, portid, seq, event, flags, family,
+ NFNETLINK_V0, 0);
+ if (!nlh)
goto nlmsg_failure;
- nfmsg = nlmsg_data(nlh);
- nfmsg->nfgen_family = family;
- nfmsg->version = NFNETLINK_V0;
- nfmsg->res_id = 0;
-
if (nla_put_string(skb, NFTA_COMPAT_NAME, name) ||
nla_put_be32(skb, NFTA_COMPAT_REV, htonl(rev)) ||
nla_put_be32(skb, NFTA_COMPAT_TYPE, htonl(target)))
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index c5d42e704..a4c6aba7d 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -15,6 +15,9 @@
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
+#include <net/netns/generic.h>
+
+extern unsigned int nf_tables_net_id;
struct nft_dynset {
struct nft_set *set;
@@ -112,13 +115,14 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
{
+ struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id);
struct nft_dynset *priv = nft_expr_priv(expr);
u8 genmask = nft_genmask_next(ctx->net);
struct nft_set *set;
u64 timeout;
int err;
- lockdep_assert_held(&ctx->net->nft.commit_mutex);
+ lockdep_assert_held(&nft_net->commit_mutex);
if (tb[NFTA_DYNSET_SET_NAME] == NULL ||
tb[NFTA_DYNSET_OP] == NULL ||
@@ -140,6 +144,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
if (IS_ERR(set))
return PTR_ERR(set);
+ if (set->flags & NFT_SET_OBJECT)
+ return -EOPNOTSUPP;
+
if (set->ops->update == NULL)
return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 166edea0e..ec35a41c7 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -169,18 +169,34 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx,
if (IS_ERR(flowtable))
return PTR_ERR(flowtable);
+ if (!nft_use_inc(&flowtable->use))
+ return -EMFILE;
+
priv->flowtable = flowtable;
- flowtable->use++;
return nf_ct_netns_get(ctx->net, ctx->family);
}
-static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+static void nft_flow_offload_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_flow_offload *priv = nft_expr_priv(expr);
- priv->flowtable->use--;
+ nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase);
+}
+
+static void nft_flow_offload_activate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
+ struct nft_flow_offload *priv = nft_expr_priv(expr);
+
+ nft_use_inc_restore(&priv->flowtable->use);
+}
+
+static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
+ const struct nft_expr *expr)
+{
nf_ct_netns_put(ctx->net, ctx->family);
}
@@ -203,6 +219,8 @@ static const struct nft_expr_ops nft_flow_offload_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)),
.eval = nft_flow_offload_eval,
.init = nft_flow_offload_init,
+ .activate = nft_flow_offload_activate,
+ .deactivate = nft_flow_offload_deactivate,
.destroy = nft_flow_offload_destroy,
.validate = nft_flow_offload_validate,
.dump = nft_flow_offload_dump,
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 615f0fcf7..2401e9fa1 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -43,8 +43,10 @@ static int nft_objref_init(const struct nft_ctx *ctx,
if (IS_ERR(obj))
return -ENOENT;
+ if (!nft_use_inc(&obj->use))
+ return -EMFILE;
+
nft_objref_priv(expr) = obj;
- obj->use++;
return 0;
}
@@ -73,7 +75,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx,
if (phase == NFT_TRANS_COMMIT)
return;
- obj->use--;
+ nft_use_dec(&obj->use);
}
static void nft_objref_activate(const struct nft_ctx *ctx,
@@ -81,7 +83,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx,
{
struct nft_object *obj = nft_objref_priv(expr);
- obj->use++;
+ nft_use_inc_restore(&obj->use);
}
static struct nft_expr_type nft_objref_type;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 77cfd5182..0ef51c81e 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -84,7 +84,7 @@ static void nft_payload_eval(const struct nft_expr *expr,
switch (priv->base) {
case NFT_PAYLOAD_LL_HEADER:
- if (!skb_mac_header_was_set(skb))
+ if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0)
goto err;
if (skb_vlan_tag_present(skb)) {
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 78a0f4283..9c7ec2ec1 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -326,6 +326,8 @@ static void *nft_rbtree_deactivate(const struct net *net,
nft_rbtree_interval_end(this)) {
parent = parent->rb_right;
continue;
+ } else if (nft_set_elem_expired(&rbe->ext)) {
+ break;
} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index 46686fb73..0c101b25c 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -76,29 +76,54 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
*/
return false;
- filp = sk->sk_socket->file;
- if (filp == NULL)
+ read_lock_bh(&sk->sk_callback_lock);
+ filp = sk->sk_socket ? sk->sk_socket->file : NULL;
+ if (filp == NULL) {
+ read_unlock_bh(&sk->sk_callback_lock);
return ((info->match ^ info->invert) &
(XT_OWNER_UID | XT_OWNER_GID)) == 0;
+ }
if (info->match & XT_OWNER_UID) {
kuid_t uid_min = make_kuid(net->user_ns, info->uid_min);
kuid_t uid_max = make_kuid(net->user_ns, info->uid_max);
if ((uid_gte(filp->f_cred->fsuid, uid_min) &&
uid_lte(filp->f_cred->fsuid, uid_max)) ^
- !(info->invert & XT_OWNER_UID))
+ !(info->invert & XT_OWNER_UID)) {
+ read_unlock_bh(&sk->sk_callback_lock);
return false;
+ }
}
if (info->match & XT_OWNER_GID) {
+ unsigned int i, match = false;
kgid_t gid_min = make_kgid(net->user_ns, info->gid_min);
kgid_t gid_max = make_kgid(net->user_ns, info->gid_max);
- if ((gid_gte(filp->f_cred->fsgid, gid_min) &&
- gid_lte(filp->f_cred->fsgid, gid_max)) ^
- !(info->invert & XT_OWNER_GID))
+ struct group_info *gi = filp->f_cred->group_info;
+
+ if (gid_gte(filp->f_cred->fsgid, gid_min) &&
+ gid_lte(filp->f_cred->fsgid, gid_max))
+ match = true;
+
+ if (!match && (info->match & XT_OWNER_SUPPL_GROUPS) && gi) {
+ for (i = 0; i < gi->ngroups; ++i) {
+ kgid_t group = gi->gid[i];
+
+ if (gid_gte(group, gid_min) &&
+ gid_lte(group, gid_max)) {
+ match = true;
+ break;
+ }
+ }
+ }
+
+ if (match ^ !(info->invert & XT_OWNER_GID)) {
+ read_unlock_bh(&sk->sk_callback_lock);
return false;
+ }
}
+ read_unlock_bh(&sk->sk_callback_lock);
return true;
}
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index cb58bc7ae..2dbf92346 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -566,7 +566,7 @@ recent_mt_proc_write(struct file *file, const char __user *input,
{
struct recent_table *t = PDE_DATA(file_inode(file));
struct recent_entry *e;
- char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")];
+ char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:255.255.255.255")];
const char *c = buf;
union nf_inet_addr addr = {};
u_int16_t family;
diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c
index 2d2fa1d53..05495d3f4 100644
--- a/net/netfilter/xt_sctp.c
+++ b/net/netfilter/xt_sctp.c
@@ -149,6 +149,8 @@ static int sctp_mt_check(const struct xt_mtchk_param *par)
{
const struct xt_sctp_info *info = par->matchinfo;
+ if (info->flag_count > ARRAY_SIZE(info->flag_info))
+ return -EINVAL;
if (info->flags & ~XT_SCTP_VALID_FLAGS)
return -EINVAL;
if (info->invflags & ~XT_SCTP_VALID_FLAGS)
diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c
index a95b50342..58ba402bc 100644
--- a/net/netfilter/xt_u32.c
+++ b/net/netfilter/xt_u32.c
@@ -95,11 +95,32 @@ static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par)
return ret ^ data->invert;
}
+static int u32_mt_checkentry(const struct xt_mtchk_param *par)
+{
+ const struct xt_u32 *data = par->matchinfo;
+ const struct xt_u32_test *ct;
+ unsigned int i;
+
+ if (data->ntests > ARRAY_SIZE(data->tests))
+ return -EINVAL;
+
+ for (i = 0; i < data->ntests; ++i) {
+ ct = &data->tests[i];
+
+ if (ct->nnums > ARRAY_SIZE(ct->location) ||
+ ct->nvalues > ARRAY_SIZE(ct->value))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static struct xt_match xt_u32_mt_reg __read_mostly = {
.name = "u32",
.revision = 0,
.family = NFPROTO_UNSPEC,
.match = u32_mt,
+ .checkentry = u32_mt_checkentry,
.matchsize = sizeof(struct xt_u32),
.me = THIS_MODULE,
};
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 15fe2120b..14c3d640f 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -871,7 +871,8 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap,
offset -= iter->startbit;
idx = offset / NETLBL_CATMAP_MAPSIZE;
- iter->bitmap[idx] |= bitmap << (offset % NETLBL_CATMAP_MAPSIZE);
+ iter->bitmap[idx] |= (NETLBL_CATMAP_MAPTYPE)bitmap
+ << (offset % NETLBL_CATMAP_MAPSIZE);
return 0;
}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 57fd9b7cf..e91489b32 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1030,7 +1030,6 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
return -EINVAL;
}
- netlink_lock_table();
if (nlk->netlink_bind && groups) {
int group;
@@ -1042,13 +1041,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
if (!err)
continue;
netlink_undo_bind(group, groups, sk);
- goto unlock;
+ return err;
}
}
/* No need for barriers here as we return to user-space without
* using any of the bound attributes.
*/
+ netlink_lock_table();
if (!bound) {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
@@ -1603,6 +1603,7 @@ out:
int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
{
struct netlink_set_err_data info;
+ unsigned long flags;
struct sock *sk;
int ret = 0;
@@ -1612,12 +1613,12 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
/* sk->sk_err wants a positive error value */
info.code = -code;
- read_lock(&nl_table_lock);
+ read_lock_irqsave(&nl_table_lock, flags);
sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list)
ret += do_one_set_err(sk, &info);
- read_unlock(&nl_table_lock);
+ read_unlock_irqrestore(&nl_table_lock, flags);
return ret;
}
EXPORT_SYMBOL(netlink_set_err);
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 7dda33b9b..85ee4891c 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -93,6 +93,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct net *net = sock_net(skb->sk);
struct netlink_diag_req *req;
struct netlink_sock *nlsk;
+ unsigned long flags;
struct sock *sk;
int num = 2;
int ret = 0;
@@ -151,7 +152,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
num++;
mc_list:
- read_lock(&nl_table_lock);
+ read_lock_irqsave(&nl_table_lock, flags);
sk_for_each_bound(sk, &tbl->mc_list) {
if (sk_hashed(sk))
continue;
@@ -166,13 +167,13 @@ mc_list:
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NLM_F_MULTI,
- sock_i_ino(sk)) < 0) {
+ __sock_i_ino(sk)) < 0) {
ret = 1;
break;
}
num++;
}
- read_unlock(&nl_table_lock);
+ read_unlock_irqrestore(&nl_table_lock, flags);
done:
cb->args[0] = num;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index ede73ecfb..f449be93b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -961,11 +961,46 @@ static struct genl_family genl_ctrl __ro_after_init = {
.netnsok = true,
};
+static int genl_bind(struct net *net, int group)
+{
+ const struct genl_family *family;
+ unsigned int id;
+ int ret = 0;
+
+ genl_lock_all();
+
+ idr_for_each_entry(&genl_fam_idr, family, id) {
+ const struct genl_multicast_group *grp;
+ int i;
+
+ if (family->n_mcgrps == 0)
+ continue;
+
+ i = group - family->mcgrp_offset;
+ if (i < 0 || i >= family->n_mcgrps)
+ continue;
+
+ grp = &family->mcgrps[i];
+ if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
+ !ns_capable(net->user_ns, CAP_NET_ADMIN))
+ ret = -EPERM;
+ if (grp->cap_sys_admin &&
+ !ns_capable(net->user_ns, CAP_SYS_ADMIN))
+ ret = -EPERM;
+
+ break;
+ }
+
+ genl_unlock_all();
+ return ret;
+}
+
static int __net_init genl_pernet_init(struct net *net)
{
struct netlink_kernel_cfg cfg = {
.input = genl_rcv,
.flags = NL_CFG_F_NONROOT_RECV,
+ .bind = genl_bind,
};
/* we'll bump the group number right afterwards */
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index a5d819fa7..146550ce0 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -663,6 +663,11 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr,
goto out_release;
}
+ if (sock->state == SS_CONNECTING) {
+ err = -EALREADY;
+ goto out_release;
+ }
+
sk->sk_state = TCP_CLOSE;
sock->state = SS_UNCONNECTED;
diff --git a/net/nfc/core.c b/net/nfc/core.c
index a84f824da..dd12ee46a 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -646,7 +646,7 @@ error:
return rc;
}
-int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len)
+int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gb, u8 gb_len)
{
pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len);
@@ -675,7 +675,7 @@ int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb)
EXPORT_SYMBOL(nfc_tm_data_received);
int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode,
- u8 *gb, size_t gb_len)
+ const u8 *gb, size_t gb_len)
{
int rc;
diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c
index fe988936a..e6863c71f 100644
--- a/net/nfc/hci/llc_shdlc.c
+++ b/net/nfc/hci/llc_shdlc.c
@@ -134,7 +134,7 @@ static bool llc_shdlc_x_lteq_y_lt_z(int x, int y, int z)
return ((y >= x) || (y < z)) ? true : false;
}
-static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc,
+static struct sk_buff *llc_shdlc_alloc_skb(const struct llc_shdlc *shdlc,
int payload_len)
{
struct sk_buff *skb;
@@ -148,7 +148,7 @@ static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc,
}
/* immediately sends an S frame. */
-static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc,
+static int llc_shdlc_send_s_frame(const struct llc_shdlc *shdlc,
enum sframe_type sframe_type, int nr)
{
int r;
@@ -170,7 +170,7 @@ static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc,
}
/* immediately sends an U frame. skb may contain optional payload */
-static int llc_shdlc_send_u_frame(struct llc_shdlc *shdlc,
+static int llc_shdlc_send_u_frame(const struct llc_shdlc *shdlc,
struct sk_buff *skb,
enum uframe_modifier uframe_modifier)
{
@@ -372,7 +372,7 @@ static void llc_shdlc_connect_complete(struct llc_shdlc *shdlc, int r)
wake_up(shdlc->connect_wq);
}
-static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc)
+static int llc_shdlc_connect_initiate(const struct llc_shdlc *shdlc)
{
struct sk_buff *skb;
@@ -388,7 +388,7 @@ static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc)
return llc_shdlc_send_u_frame(shdlc, skb, U_FRAME_RSET);
}
-static int llc_shdlc_connect_send_ua(struct llc_shdlc *shdlc)
+static int llc_shdlc_connect_send_ua(const struct llc_shdlc *shdlc)
{
struct sk_buff *skb;
diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h
index 1f68724d4..a070a57fc 100644
--- a/net/nfc/llcp.h
+++ b/net/nfc/llcp.h
@@ -233,15 +233,15 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *sk, struct socket *newsock);
/* TLV API */
int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local,
- u8 *tlv_array, u16 tlv_array_len);
+ const u8 *tlv_array, u16 tlv_array_len);
int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock,
- u8 *tlv_array, u16 tlv_array_len);
+ const u8 *tlv_array, u16 tlv_array_len);
/* Commands API */
void nfc_llcp_recv(void *data, struct sk_buff *skb, int err);
-u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length);
+u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length);
struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap);
-struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri,
+struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri,
size_t uri_len);
void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp);
void nfc_llcp_free_sdp_tlv_list(struct hlist_head *sdp_head);
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index d1fc019e9..737c7aa38 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -27,7 +27,7 @@
#include "nfc.h"
#include "llcp.h"
-static u8 llcp_tlv_length[LLCP_TLV_MAX] = {
+static const u8 llcp_tlv_length[LLCP_TLV_MAX] = {
0,
1, /* VERSION */
2, /* MIUX */
@@ -41,7 +41,7 @@ static u8 llcp_tlv_length[LLCP_TLV_MAX] = {
};
-static u8 llcp_tlv8(u8 *tlv, u8 type)
+static u8 llcp_tlv8(const u8 *tlv, u8 type)
{
if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]])
return 0;
@@ -49,7 +49,7 @@ static u8 llcp_tlv8(u8 *tlv, u8 type)
return tlv[2];
}
-static u16 llcp_tlv16(u8 *tlv, u8 type)
+static u16 llcp_tlv16(const u8 *tlv, u8 type)
{
if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]])
return 0;
@@ -58,37 +58,37 @@ static u16 llcp_tlv16(u8 *tlv, u8 type)
}
-static u8 llcp_tlv_version(u8 *tlv)
+static u8 llcp_tlv_version(const u8 *tlv)
{
return llcp_tlv8(tlv, LLCP_TLV_VERSION);
}
-static u16 llcp_tlv_miux(u8 *tlv)
+static u16 llcp_tlv_miux(const u8 *tlv)
{
return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff;
}
-static u16 llcp_tlv_wks(u8 *tlv)
+static u16 llcp_tlv_wks(const u8 *tlv)
{
return llcp_tlv16(tlv, LLCP_TLV_WKS);
}
-static u16 llcp_tlv_lto(u8 *tlv)
+static u16 llcp_tlv_lto(const u8 *tlv)
{
return llcp_tlv8(tlv, LLCP_TLV_LTO);
}
-static u8 llcp_tlv_opt(u8 *tlv)
+static u8 llcp_tlv_opt(const u8 *tlv)
{
return llcp_tlv8(tlv, LLCP_TLV_OPT);
}
-static u8 llcp_tlv_rw(u8 *tlv)
+static u8 llcp_tlv_rw(const u8 *tlv)
{
return llcp_tlv8(tlv, LLCP_TLV_RW) & 0xf;
}
-u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length)
+u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length)
{
u8 *tlv, length;
@@ -142,7 +142,7 @@ struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap)
return sdres;
}
-struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri,
+struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri,
size_t uri_len)
{
struct nfc_llcp_sdp_tlv *sdreq;
@@ -202,9 +202,10 @@ void nfc_llcp_free_sdp_tlv_list(struct hlist_head *head)
}
int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local,
- u8 *tlv_array, u16 tlv_array_len)
+ const u8 *tlv_array, u16 tlv_array_len)
{
- u8 *tlv = tlv_array, type, length, offset = 0;
+ const u8 *tlv = tlv_array;
+ u8 type, length, offset = 0;
pr_debug("TLV array length %d\n", tlv_array_len);
@@ -251,9 +252,10 @@ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local,
}
int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock,
- u8 *tlv_array, u16 tlv_array_len)
+ const u8 *tlv_array, u16 tlv_array_len)
{
- u8 *tlv = tlv_array, type, length, offset = 0;
+ const u8 *tlv = tlv_array;
+ u8 type, length, offset = 0;
pr_debug("TLV array length %d\n", tlv_array_len);
@@ -307,7 +309,7 @@ static struct sk_buff *llcp_add_header(struct sk_buff *pdu,
return pdu;
}
-static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, u8 *tlv,
+static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, const u8 *tlv,
u8 tlv_length)
{
/* XXX Add an skb length check */
@@ -401,9 +403,11 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
{
struct nfc_llcp_local *local;
struct sk_buff *skb;
- u8 *service_name_tlv = NULL, service_name_tlv_length;
- u8 *miux_tlv = NULL, miux_tlv_length;
- u8 *rw_tlv = NULL, rw_tlv_length, rw;
+ const u8 *service_name_tlv = NULL;
+ const u8 *miux_tlv = NULL;
+ const u8 *rw_tlv = NULL;
+ u8 service_name_tlv_length = 0;
+ u8 miux_tlv_length, rw_tlv_length, rw;
int err;
u16 size = 0;
__be16 miux;
@@ -477,8 +481,9 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock)
{
struct nfc_llcp_local *local;
struct sk_buff *skb;
- u8 *miux_tlv = NULL, miux_tlv_length;
- u8 *rw_tlv = NULL, rw_tlv_length, rw;
+ const u8 *miux_tlv = NULL;
+ const u8 *rw_tlv = NULL;
+ u8 miux_tlv_length, rw_tlv_length, rw;
int err;
u16 size = 0;
__be16 miux;
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index 3290f2275..c30b28465 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -216,17 +216,13 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local,
if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) {
llcp_sock = tmp_sock;
+ sock_hold(&llcp_sock->sk);
break;
}
}
read_unlock(&local->sockets.lock);
- if (llcp_sock == NULL)
- return NULL;
-
- sock_hold(&llcp_sock->sk);
-
return llcp_sock;
}
@@ -314,7 +310,7 @@ static char *wks[] = {
"urn:nfc:sn:snep",
};
-static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len)
+static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len)
{
int sap, num_wks;
@@ -338,7 +334,8 @@ static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len)
static
struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local,
- u8 *sn, size_t sn_len)
+ const u8 *sn, size_t sn_len,
+ bool needref)
{
struct sock *sk;
struct nfc_llcp_sock *llcp_sock, *tmp_sock;
@@ -374,6 +371,8 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local,
if (memcmp(sn, tmp_sock->service_name, sn_len) == 0) {
llcp_sock = tmp_sock;
+ if (needref)
+ sock_hold(&llcp_sock->sk);
break;
}
}
@@ -415,7 +414,8 @@ u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local,
* to this service name.
*/
if (nfc_llcp_sock_from_sn(local, sock->service_name,
- sock->service_name_len) != NULL) {
+ sock->service_name_len,
+ false) != NULL) {
mutex_unlock(&local->sdp_lock);
return LLCP_SAP_MAX;
@@ -535,7 +535,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
{
u8 *gb_cur, version, version_length;
u8 lto_length, wks_length, miux_length;
- u8 *version_tlv = NULL, *lto_tlv = NULL,
+ const u8 *version_tlv = NULL, *lto_tlv = NULL,
*wks_tlv = NULL, *miux_tlv = NULL;
__be16 wks = cpu_to_be16(local->local_wks);
u8 gb_len = 0;
@@ -625,7 +625,7 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len)
return local->gb;
}
-int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len)
+int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len)
{
struct nfc_llcp_local *local;
@@ -652,27 +652,27 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len)
local->remote_gb_len - 3);
}
-static u8 nfc_llcp_dsap(struct sk_buff *pdu)
+static u8 nfc_llcp_dsap(const struct sk_buff *pdu)
{
return (pdu->data[0] & 0xfc) >> 2;
}
-static u8 nfc_llcp_ptype(struct sk_buff *pdu)
+static u8 nfc_llcp_ptype(const struct sk_buff *pdu)
{
return ((pdu->data[0] & 0x03) << 2) | ((pdu->data[1] & 0xc0) >> 6);
}
-static u8 nfc_llcp_ssap(struct sk_buff *pdu)
+static u8 nfc_llcp_ssap(const struct sk_buff *pdu)
{
return pdu->data[1] & 0x3f;
}
-static u8 nfc_llcp_ns(struct sk_buff *pdu)
+static u8 nfc_llcp_ns(const struct sk_buff *pdu)
{
return pdu->data[2] >> 4;
}
-static u8 nfc_llcp_nr(struct sk_buff *pdu)
+static u8 nfc_llcp_nr(const struct sk_buff *pdu)
{
return pdu->data[2] & 0xf;
}
@@ -814,23 +814,15 @@ out:
}
static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local,
- u8 *sn, size_t sn_len)
+ const u8 *sn, size_t sn_len)
{
- struct nfc_llcp_sock *llcp_sock;
-
- llcp_sock = nfc_llcp_sock_from_sn(local, sn, sn_len);
-
- if (llcp_sock == NULL)
- return NULL;
-
- sock_hold(&llcp_sock->sk);
-
- return llcp_sock;
+ return nfc_llcp_sock_from_sn(local, sn, sn_len, true);
}
-static u8 *nfc_llcp_connect_sn(struct sk_buff *skb, size_t *sn_len)
+static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len)
{
- u8 *tlv = &skb->data[2], type, length;
+ u8 type, length;
+ const u8 *tlv = &skb->data[2];
size_t tlv_array_len = skb->len - LLCP_HEADER_SIZE, offset = 0;
while (offset < tlv_array_len) {
@@ -888,7 +880,7 @@ static void nfc_llcp_recv_ui(struct nfc_llcp_local *local,
}
static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
- struct sk_buff *skb)
+ const struct sk_buff *skb)
{
struct sock *new_sk, *parent;
struct nfc_llcp_sock *sock, *new_sock;
@@ -906,7 +898,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
goto fail;
}
} else {
- u8 *sn;
+ const u8 *sn;
size_t sn_len;
sn = nfc_llcp_connect_sn(skb, &sn_len);
@@ -1125,7 +1117,7 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local,
}
static void nfc_llcp_recv_disc(struct nfc_llcp_local *local,
- struct sk_buff *skb)
+ const struct sk_buff *skb)
{
struct nfc_llcp_sock *llcp_sock;
struct sock *sk;
@@ -1168,7 +1160,8 @@ static void nfc_llcp_recv_disc(struct nfc_llcp_local *local,
nfc_llcp_sock_put(llcp_sock);
}
-static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb)
+static void nfc_llcp_recv_cc(struct nfc_llcp_local *local,
+ const struct sk_buff *skb)
{
struct nfc_llcp_sock *llcp_sock;
struct sock *sk;
@@ -1201,7 +1194,8 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb)
nfc_llcp_sock_put(llcp_sock);
}
-static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb)
+static void nfc_llcp_recv_dm(struct nfc_llcp_local *local,
+ const struct sk_buff *skb)
{
struct nfc_llcp_sock *llcp_sock;
struct sock *sk;
@@ -1239,12 +1233,13 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb)
}
static void nfc_llcp_recv_snl(struct nfc_llcp_local *local,
- struct sk_buff *skb)
+ const struct sk_buff *skb)
{
struct nfc_llcp_sock *llcp_sock;
- u8 dsap, ssap, *tlv, type, length, tid, sap;
+ u8 dsap, ssap, type, length, tid, sap;
+ const u8 *tlv;
u16 tlv_len, offset;
- char *service_name;
+ const char *service_name;
size_t service_name_len;
struct nfc_llcp_sdp_tlv *sdp;
HLIST_HEAD(llc_sdres_list);
@@ -1286,7 +1281,8 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local,
}
llcp_sock = nfc_llcp_sock_from_sn(local, service_name,
- service_name_len);
+ service_name_len,
+ true);
if (!llcp_sock) {
sap = 0;
goto add_snl;
@@ -1306,6 +1302,7 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local,
if (sap == LLCP_SAP_MAX) {
sap = 0;
+ nfc_llcp_sock_put(llcp_sock);
goto add_snl;
}
@@ -1323,6 +1320,7 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local,
pr_debug("%p %d\n", llcp_sock, sap);
+ nfc_llcp_sock_put(llcp_sock);
add_snl:
sdp = nfc_llcp_build_sdres_tlv(tid, sap);
if (sdp == NULL)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 66608e6c5..33723d843 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -906,6 +906,11 @@ static int nci_activate_target(struct nfc_dev *nfc_dev,
return -EINVAL;
}
+ if (protocol >= NFC_PROTO_MAX) {
+ pr_err("the requested nfc protocol is invalid\n");
+ return -EINVAL;
+ }
+
if (!(nci_target->supported_protocols & (1 << protocol))) {
pr_err("target does not support the requested protocol 0x%x\n",
protocol);
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index 452f4c16b..d2de7fc22 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -163,6 +163,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge)
int ret;
skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
/* add the NCI SPI header to the start of the buffer */
hdr = skb_push(skb, NCI_SPI_HDR_LEN);
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index 6c6f76b37..c792165f5 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -60,7 +60,7 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx,
u8 comm_mode, u8 rf_mode);
int nfc_llcp_register_device(struct nfc_dev *dev);
void nfc_llcp_unregister_device(struct nfc_dev *dev);
-int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len);
+int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len);
u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len);
int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb);
struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index fb165286e..377832981 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -370,18 +370,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
{
union tpacket_uhdr h;
+ /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */
+
h.raw = frame;
switch (po->tp_version) {
case TPACKET_V1:
- h.h1->tp_status = status;
+ WRITE_ONCE(h.h1->tp_status, status);
flush_dcache_page(pgv_to_page(&h.h1->tp_status));
break;
case TPACKET_V2:
- h.h2->tp_status = status;
+ WRITE_ONCE(h.h2->tp_status, status);
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
break;
case TPACKET_V3:
- h.h3->tp_status = status;
+ WRITE_ONCE(h.h3->tp_status, status);
flush_dcache_page(pgv_to_page(&h.h3->tp_status));
break;
default:
@@ -398,17 +400,19 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
smp_rmb();
+ /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */
+
h.raw = frame;
switch (po->tp_version) {
case TPACKET_V1:
flush_dcache_page(pgv_to_page(&h.h1->tp_status));
- return h.h1->tp_status;
+ return READ_ONCE(h.h1->tp_status);
case TPACKET_V2:
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
- return h.h2->tp_status;
+ return READ_ONCE(h.h2->tp_status);
case TPACKET_V3:
flush_dcache_page(pgv_to_page(&h.h3->tp_status));
- return h.h3->tp_status;
+ return READ_ONCE(h.h3->tp_status);
default:
WARN(1, "TPACKET version not supported.\n");
BUG();
@@ -4210,7 +4214,7 @@ static void packet_mm_open(struct vm_area_struct *vma)
struct sock *sk = sock->sk;
if (sk)
- atomic_inc(&pkt_sk(sk)->mapped);
+ atomic_long_inc(&pkt_sk(sk)->mapped);
}
static void packet_mm_close(struct vm_area_struct *vma)
@@ -4220,7 +4224,7 @@ static void packet_mm_close(struct vm_area_struct *vma)
struct sock *sk = sock->sk;
if (sk)
- atomic_dec(&pkt_sk(sk)->mapped);
+ atomic_long_dec(&pkt_sk(sk)->mapped);
}
static const struct vm_operations_struct packet_mmap_ops = {
@@ -4315,7 +4319,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
err = -EBUSY;
if (!closing) {
- if (atomic_read(&po->mapped))
+ if (atomic_long_read(&po->mapped))
goto out;
if (packet_read_pending(rb))
goto out;
@@ -4418,7 +4422,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
err = -EBUSY;
mutex_lock(&po->pg_vec_lock);
- if (closing || atomic_read(&po->mapped) == 0) {
+ if (closing || atomic_long_read(&po->mapped) == 0) {
err = 0;
spin_lock_bh(&rb_queue->lock);
swap(rb->pg_vec, pg_vec);
@@ -4436,9 +4440,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
po->prot_hook.func = (po->rx_ring.pg_vec) ?
tpacket_rcv : packet_rcv;
skb_queue_purge(rb_queue);
- if (atomic_read(&po->mapped))
- pr_err("packet_mmap: vma is busy: %d\n",
- atomic_read(&po->mapped));
+ if (atomic_long_read(&po->mapped))
+ pr_err("packet_mmap: vma is busy: %ld\n",
+ atomic_long_read(&po->mapped));
}
mutex_unlock(&po->pg_vec_lock);
@@ -4516,7 +4520,7 @@ static int packet_mmap(struct file *file, struct socket *sock,
}
}
- atomic_inc(&po->mapped);
+ atomic_long_inc(&po->mapped);
vma->vm_ops = &packet_mmap_ops;
err = 0;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 3d871cae8..7f2d5eed5 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -125,7 +125,7 @@ struct packet_sock {
__be16 num;
struct packet_rollover *rollover;
struct packet_mclist *mclist;
- atomic_t mapped;
+ atomic_long_t mapped;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 30e8239bd..196fbf674 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -31,7 +31,8 @@ enum psample_nl_multicast_groups {
static const struct genl_multicast_group psample_nl_mcgrps[] = {
[PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME },
- [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME },
+ [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME,
+ .flags = GENL_UNS_ADMIN_PERM },
};
static struct genl_family psample_nl_family __ro_after_init;
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index 008f50fb2..63efe60fd 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -141,7 +141,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
addrlen = sizeof(sin);
}
- ret = sock->ops->bind(sock, addr, addrlen);
+ ret = kernel_bind(sock, addr, addrlen);
if (ret) {
rdsdebug("bind failed with %d at address %pI6c\n",
ret, &conn->c_laddr);
@@ -169,7 +169,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
* own the socket
*/
rds_tcp_set_callbacks(sock, cp);
- ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK);
+ ret = kernel_connect(sock, addr, addrlen, O_NONBLOCK);
rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret);
if (ret == -EINPROGRESS)
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 0d095d3f5..37f4a8ca3 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -332,7 +332,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6)
addr_len = sizeof(*sin);
}
- ret = sock->ops->bind(sock, (struct sockaddr *)&ss, addr_len);
+ ret = kernel_bind(sock, (struct sockaddr *)&ss, addr_len);
if (ret < 0) {
rdsdebug("could not bind %s listener socket: %d\n",
isv6 ? "IPv6" : "IPv4", ret);
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 0f8465852..7524544a9 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -112,13 +112,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
rfkill->clk = devm_clk_get(&pdev->dev, NULL);
- gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW);
+ gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS);
if (IS_ERR(gpio))
return PTR_ERR(gpio);
rfkill->reset_gpio = gpio;
- gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW);
+ gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS);
if (IS_ERR(gpio))
return PTR_ERR(gpio);
@@ -130,6 +130,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
return -EINVAL;
}
+ ret = gpiod_direction_output(rfkill->reset_gpio, true);
+ if (ret)
+ return ret;
+
+ ret = gpiod_direction_output(rfkill->shutdown_gpio, true);
+ if (ret)
+ return ret;
+
rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev,
rfkill->type, &rfkill_gpio_ops,
rfkill);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 4edd127bb..015e475f5 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -184,21 +184,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh)
*/
static void rose_kill_by_device(struct net_device *dev)
{
- struct sock *s;
+ struct sock *sk, *array[16];
+ struct rose_sock *rose;
+ bool rescan;
+ int i, cnt;
+start:
+ rescan = false;
+ cnt = 0;
spin_lock_bh(&rose_list_lock);
- sk_for_each(s, &rose_list) {
- struct rose_sock *rose = rose_sk(s);
+ sk_for_each(sk, &rose_list) {
+ rose = rose_sk(sk);
+ if (rose->device == dev) {
+ if (cnt == ARRAY_SIZE(array)) {
+ rescan = true;
+ break;
+ }
+ sock_hold(sk);
+ array[cnt++] = sk;
+ }
+ }
+ spin_unlock_bh(&rose_list_lock);
+ for (i = 0; i < cnt; i++) {
+ sk = array[cnt];
+ rose = rose_sk(sk);
+ lock_sock(sk);
+ spin_lock_bh(&rose_list_lock);
if (rose->device == dev) {
- rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
+ rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
if (rose->neighbour)
rose->neighbour->use--;
dev_put(rose->device);
rose->device = NULL;
}
+ spin_unlock_bh(&rose_list_lock);
+ release_sock(sk);
+ sock_put(sk);
+ cond_resched();
}
- spin_unlock_bh(&rose_list_lock);
+ if (rescan)
+ goto start;
}
/*
@@ -658,7 +684,10 @@ static int rose_release(struct socket *sock)
break;
}
+ spin_lock_bh(&rose_list_lock);
dev_put(rose->device);
+ rose->device = NULL;
+ spin_unlock_bh(&rose_list_lock);
sock->sk = NULL;
release_sock(sk);
sock_put(sk);
@@ -1308,9 +1337,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case TIOCINQ: {
struct sk_buff *skb;
long amount = 0L;
- /* These two are safe on a single CPU system as only user tasks fiddle here */
+
+ spin_lock_irq(&sk->sk_receive_queue.lock);
if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL)
amount = skb->len;
+ spin_unlock_irq(&sk->sk_receive_queue.lock);
return put_user(amount, (unsigned int __user *) argp);
}
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 4547022ed..7698a8974 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -503,34 +503,6 @@ config CLS_U32_MARK
---help---
Say Y here to be able to use netfilter marks as u32 key.
-config NET_CLS_RSVP
- tristate "IPv4 Resource Reservation Protocol (RSVP)"
- select NET_CLS
- ---help---
- The Resource Reservation Protocol (RSVP) permits end systems to
- request a minimum and maximum data flow rate for a connection; this
- is important for real time data such as streaming sound or video.
-
- Say Y here if you want to be able to classify outgoing packets based
- on their RSVP requests.
-
- To compile this code as a module, choose M here: the
- module will be called cls_rsvp.
-
-config NET_CLS_RSVP6
- tristate "IPv6 Resource Reservation Protocol (RSVP6)"
- select NET_CLS
- ---help---
- The Resource Reservation Protocol (RSVP) permits end systems to
- request a minimum and maximum data flow rate for a connection; this
- is important for real time data such as streaming sound or video.
-
- Say Y here if you want to be able to classify outgoing packets based
- on their RSVP requests and you are using the IPv6 protocol.
-
- To compile this code as a module, choose M here: the
- module will be called cls_rsvp6.
-
config NET_CLS_FLOW
tristate "Flow classifier"
select NET_CLS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 5eed580cd..3139c32e1 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -61,8 +61,6 @@ obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
obj-$(CONFIG_NET_CLS_FW) += cls_fw.o
-obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o
-obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o
obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o
obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o
obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index aeb8f84cb..255d4ecf6 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -29,6 +29,7 @@ static struct tc_action_ops act_pedit_ops;
static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
[TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) },
+ [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) },
[TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED },
};
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 55bf75cb1..164049d20 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -229,7 +229,7 @@ static u32 flow_get_skgid(const struct sk_buff *skb)
static u32 flow_get_vlan_tag(const struct sk_buff *skb)
{
- u16 uninitialized_var(tag);
+ u16 tag;
if (vlan_get_tag(skb, &tag) < 0)
return 0;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index cb2c62605..f15089c24 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -221,11 +221,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
if (err < 0)
return err;
- if (tb[TCA_FW_CLASSID]) {
- f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
- tcf_bind_filter(tp, &f->res, base);
- }
-
#ifdef CONFIG_NET_CLS_IND
if (tb[TCA_FW_INDEV]) {
int ret;
@@ -244,6 +239,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
} else if (head->mask != 0xFFFFFFFF)
return err;
+ if (tb[TCA_FW_CLASSID]) {
+ f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
+ tcf_bind_filter(tp, &f->res, base);
+ }
+
return 0;
}
@@ -277,7 +277,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
return -ENOBUFS;
fnew->id = f->id;
- fnew->res = f->res;
#ifdef CONFIG_NET_CLS_IND
fnew->ifindex = f->ifindex;
#endif /* CONFIG_NET_CLS_IND */
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 4c7fa1cfd..a92429262 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -513,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
if (fold) {
f->id = fold->id;
f->iif = fold->iif;
- f->res = fold->res;
f->handle = fold->handle;
f->tp = fold->tp;
diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c
deleted file mode 100644
index cbb5e0d60..000000000
--- a/net/sched/cls_rsvp.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/skbuff.h>
-#include <net/ip.h>
-#include <net/netlink.h>
-#include <net/act_api.h>
-#include <net/pkt_cls.h>
-
-#define RSVP_DST_LEN 1
-#define RSVP_ID "rsvp"
-#define RSVP_OPS cls_rsvp_ops
-
-#include "cls_rsvp.h"
-MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
deleted file mode 100644
index eb1dd2afc..000000000
--- a/net/sched/cls_rsvp.h
+++ /dev/null
@@ -1,775 +0,0 @@
-/*
- * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-/*
- Comparing to general packet classification problem,
- RSVP needs only sevaral relatively simple rules:
-
- * (dst, protocol) are always specified,
- so that we are able to hash them.
- * src may be exact, or may be wildcard, so that
- we can keep a hash table plus one wildcard entry.
- * source port (or flow label) is important only if src is given.
-
- IMPLEMENTATION.
-
- We use a two level hash table: The top level is keyed by
- destination address and protocol ID, every bucket contains a list
- of "rsvp sessions", identified by destination address, protocol and
- DPI(="Destination Port ID"): triple (key, mask, offset).
-
- Every bucket has a smaller hash table keyed by source address
- (cf. RSVP flowspec) and one wildcard entry for wildcard reservations.
- Every bucket is again a list of "RSVP flows", selected by
- source address and SPI(="Source Port ID" here rather than
- "security parameter index"): triple (key, mask, offset).
-
-
- NOTE 1. All the packets with IPv6 extension headers (but AH and ESP)
- and all fragmented packets go to the best-effort traffic class.
-
-
- NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires
- only one "Generalized Port Identifier". So that for classic
- ah, esp (and udp,tcp) both *pi should coincide or one of them
- should be wildcard.
-
- At first sight, this redundancy is just a waste of CPU
- resources. But DPI and SPI add the possibility to assign different
- priorities to GPIs. Look also at note 4 about tunnels below.
-
-
- NOTE 3. One complication is the case of tunneled packets.
- We implement it as following: if the first lookup
- matches a special session with "tunnelhdr" value not zero,
- flowid doesn't contain the true flow ID, but the tunnel ID (1...255).
- In this case, we pull tunnelhdr bytes and restart lookup
- with tunnel ID added to the list of keys. Simple and stupid 8)8)
- It's enough for PIMREG and IPIP.
-
-
- NOTE 4. Two GPIs make it possible to parse even GRE packets.
- F.e. DPI can select ETH_P_IP (and necessary flags to make
- tunnelhdr correct) in GRE protocol field and SPI matches
- GRE key. Is it not nice? 8)8)
-
-
- Well, as result, despite its simplicity, we get a pretty
- powerful classification engine. */
-
-
-struct rsvp_head {
- u32 tmap[256/32];
- u32 hgenerator;
- u8 tgenerator;
- struct rsvp_session __rcu *ht[256];
- struct rcu_head rcu;
-};
-
-struct rsvp_session {
- struct rsvp_session __rcu *next;
- __be32 dst[RSVP_DST_LEN];
- struct tc_rsvp_gpi dpi;
- u8 protocol;
- u8 tunnelid;
- /* 16 (src,sport) hash slots, and one wildcard source slot */
- struct rsvp_filter __rcu *ht[16 + 1];
- struct rcu_head rcu;
-};
-
-
-struct rsvp_filter {
- struct rsvp_filter __rcu *next;
- __be32 src[RSVP_DST_LEN];
- struct tc_rsvp_gpi spi;
- u8 tunnelhdr;
-
- struct tcf_result res;
- struct tcf_exts exts;
-
- u32 handle;
- struct rsvp_session *sess;
- struct rcu_work rwork;
-};
-
-static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid)
-{
- unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1];
-
- h ^= h>>16;
- h ^= h>>8;
- return (h ^ protocol ^ tunnelid) & 0xFF;
-}
-
-static inline unsigned int hash_src(__be32 *src)
-{
- unsigned int h = (__force __u32)src[RSVP_DST_LEN-1];
-
- h ^= h>>16;
- h ^= h>>8;
- h ^= h>>4;
- return h & 0xF;
-}
-
-#define RSVP_APPLY_RESULT() \
-{ \
- int r = tcf_exts_exec(skb, &f->exts, res); \
- if (r < 0) \
- continue; \
- else if (r > 0) \
- return r; \
-}
-
-static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res)
-{
- struct rsvp_head *head = rcu_dereference_bh(tp->root);
- struct rsvp_session *s;
- struct rsvp_filter *f;
- unsigned int h1, h2;
- __be32 *dst, *src;
- u8 protocol;
- u8 tunnelid = 0;
- u8 *xprt;
-#if RSVP_DST_LEN == 4
- struct ipv6hdr *nhptr;
-
- if (!pskb_network_may_pull(skb, sizeof(*nhptr)))
- return -1;
- nhptr = ipv6_hdr(skb);
-#else
- struct iphdr *nhptr;
-
- if (!pskb_network_may_pull(skb, sizeof(*nhptr)))
- return -1;
- nhptr = ip_hdr(skb);
-#endif
-restart:
-
-#if RSVP_DST_LEN == 4
- src = &nhptr->saddr.s6_addr32[0];
- dst = &nhptr->daddr.s6_addr32[0];
- protocol = nhptr->nexthdr;
- xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr);
-#else
- src = &nhptr->saddr;
- dst = &nhptr->daddr;
- protocol = nhptr->protocol;
- xprt = ((u8 *)nhptr) + (nhptr->ihl<<2);
- if (ip_is_fragment(nhptr))
- return -1;
-#endif
-
- h1 = hash_dst(dst, protocol, tunnelid);
- h2 = hash_src(src);
-
- for (s = rcu_dereference_bh(head->ht[h1]); s;
- s = rcu_dereference_bh(s->next)) {
- if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] &&
- protocol == s->protocol &&
- !(s->dpi.mask &
- (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) &&
-#if RSVP_DST_LEN == 4
- dst[0] == s->dst[0] &&
- dst[1] == s->dst[1] &&
- dst[2] == s->dst[2] &&
-#endif
- tunnelid == s->tunnelid) {
-
- for (f = rcu_dereference_bh(s->ht[h2]); f;
- f = rcu_dereference_bh(f->next)) {
- if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] &&
- !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key))
-#if RSVP_DST_LEN == 4
- &&
- src[0] == f->src[0] &&
- src[1] == f->src[1] &&
- src[2] == f->src[2]
-#endif
- ) {
- *res = f->res;
- RSVP_APPLY_RESULT();
-
-matched:
- if (f->tunnelhdr == 0)
- return 0;
-
- tunnelid = f->res.classid;
- nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr));
- goto restart;
- }
- }
-
- /* And wildcard bucket... */
- for (f = rcu_dereference_bh(s->ht[16]); f;
- f = rcu_dereference_bh(f->next)) {
- *res = f->res;
- RSVP_APPLY_RESULT();
- goto matched;
- }
- return -1;
- }
- }
- return -1;
-}
-
-static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- struct rsvp_session *s;
- struct rsvp_filter __rcu **ins;
- struct rsvp_filter *pins;
- unsigned int h1 = h & 0xFF;
- unsigned int h2 = (h >> 8) & 0xFF;
-
- for (s = rtnl_dereference(head->ht[h1]); s;
- s = rtnl_dereference(s->next)) {
- for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ;
- ins = &pins->next, pins = rtnl_dereference(*ins)) {
- if (pins->handle == h) {
- RCU_INIT_POINTER(n->next, pins->next);
- rcu_assign_pointer(*ins, n);
- return;
- }
- }
- }
-
- /* Something went wrong if we are trying to replace a non-existant
- * node. Mind as well halt instead of silently failing.
- */
- BUG_ON(1);
-}
-
-static void *rsvp_get(struct tcf_proto *tp, u32 handle)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- struct rsvp_session *s;
- struct rsvp_filter *f;
- unsigned int h1 = handle & 0xFF;
- unsigned int h2 = (handle >> 8) & 0xFF;
-
- if (h2 > 16)
- return NULL;
-
- for (s = rtnl_dereference(head->ht[h1]); s;
- s = rtnl_dereference(s->next)) {
- for (f = rtnl_dereference(s->ht[h2]); f;
- f = rtnl_dereference(f->next)) {
- if (f->handle == handle)
- return f;
- }
- }
- return NULL;
-}
-
-static int rsvp_init(struct tcf_proto *tp)
-{
- struct rsvp_head *data;
-
- data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL);
- if (data) {
- rcu_assign_pointer(tp->root, data);
- return 0;
- }
- return -ENOBUFS;
-}
-
-static void __rsvp_delete_filter(struct rsvp_filter *f)
-{
- tcf_exts_destroy(&f->exts);
- tcf_exts_put_net(&f->exts);
- kfree(f);
-}
-
-static void rsvp_delete_filter_work(struct work_struct *work)
-{
- struct rsvp_filter *f = container_of(to_rcu_work(work),
- struct rsvp_filter,
- rwork);
- rtnl_lock();
- __rsvp_delete_filter(f);
- rtnl_unlock();
-}
-
-static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
-{
- tcf_unbind_filter(tp, &f->res);
- /* all classifiers are required to call tcf_exts_destroy() after rcu
- * grace period, since converted-to-rcu actions are relying on that
- * in cleanup() callback
- */
- if (tcf_exts_get_net(&f->exts))
- tcf_queue_work(&f->rwork, rsvp_delete_filter_work);
- else
- __rsvp_delete_filter(f);
-}
-
-static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
-{
- struct rsvp_head *data = rtnl_dereference(tp->root);
- int h1, h2;
-
- if (data == NULL)
- return;
-
- for (h1 = 0; h1 < 256; h1++) {
- struct rsvp_session *s;
-
- while ((s = rtnl_dereference(data->ht[h1])) != NULL) {
- RCU_INIT_POINTER(data->ht[h1], s->next);
-
- for (h2 = 0; h2 <= 16; h2++) {
- struct rsvp_filter *f;
-
- while ((f = rtnl_dereference(s->ht[h2])) != NULL) {
- rcu_assign_pointer(s->ht[h2], f->next);
- rsvp_delete_filter(tp, f);
- }
- }
- kfree_rcu(s, rcu);
- }
- }
- kfree_rcu(data, rcu);
-}
-
-static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last,
- struct netlink_ext_ack *extack)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- struct rsvp_filter *nfp, *f = arg;
- struct rsvp_filter __rcu **fp;
- unsigned int h = f->handle;
- struct rsvp_session __rcu **sp;
- struct rsvp_session *nsp, *s = f->sess;
- int i, h1;
-
- fp = &s->ht[(h >> 8) & 0xFF];
- for (nfp = rtnl_dereference(*fp); nfp;
- fp = &nfp->next, nfp = rtnl_dereference(*fp)) {
- if (nfp == f) {
- RCU_INIT_POINTER(*fp, f->next);
- rsvp_delete_filter(tp, f);
-
- /* Strip tree */
-
- for (i = 0; i <= 16; i++)
- if (s->ht[i])
- goto out;
-
- /* OK, session has no flows */
- sp = &head->ht[h & 0xFF];
- for (nsp = rtnl_dereference(*sp); nsp;
- sp = &nsp->next, nsp = rtnl_dereference(*sp)) {
- if (nsp == s) {
- RCU_INIT_POINTER(*sp, s->next);
- kfree_rcu(s, rcu);
- goto out;
- }
- }
-
- break;
- }
- }
-
-out:
- *last = true;
- for (h1 = 0; h1 < 256; h1++) {
- if (rcu_access_pointer(head->ht[h1])) {
- *last = false;
- break;
- }
- }
-
- return 0;
-}
-
-static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt)
-{
- struct rsvp_head *data = rtnl_dereference(tp->root);
- int i = 0xFFFF;
-
- while (i-- > 0) {
- u32 h;
-
- if ((data->hgenerator += 0x10000) == 0)
- data->hgenerator = 0x10000;
- h = data->hgenerator|salt;
- if (!rsvp_get(tp, h))
- return h;
- }
- return 0;
-}
-
-static int tunnel_bts(struct rsvp_head *data)
-{
- int n = data->tgenerator >> 5;
- u32 b = 1 << (data->tgenerator & 0x1F);
-
- if (data->tmap[n] & b)
- return 0;
- data->tmap[n] |= b;
- return 1;
-}
-
-static void tunnel_recycle(struct rsvp_head *data)
-{
- struct rsvp_session __rcu **sht = data->ht;
- u32 tmap[256/32];
- int h1, h2;
-
- memset(tmap, 0, sizeof(tmap));
-
- for (h1 = 0; h1 < 256; h1++) {
- struct rsvp_session *s;
- for (s = rtnl_dereference(sht[h1]); s;
- s = rtnl_dereference(s->next)) {
- for (h2 = 0; h2 <= 16; h2++) {
- struct rsvp_filter *f;
-
- for (f = rtnl_dereference(s->ht[h2]); f;
- f = rtnl_dereference(f->next)) {
- if (f->tunnelhdr == 0)
- continue;
- data->tgenerator = f->res.classid;
- tunnel_bts(data);
- }
- }
- }
- }
-
- memcpy(data->tmap, tmap, sizeof(tmap));
-}
-
-static u32 gen_tunnel(struct rsvp_head *data)
-{
- int i, k;
-
- for (k = 0; k < 2; k++) {
- for (i = 255; i > 0; i--) {
- if (++data->tgenerator == 0)
- data->tgenerator = 1;
- if (tunnel_bts(data))
- return data->tgenerator;
- }
- tunnel_recycle(data);
- }
- return 0;
-}
-
-static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
- [TCA_RSVP_CLASSID] = { .type = NLA_U32 },
- [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) },
- [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) },
- [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) },
-};
-
-static int rsvp_change(struct net *net, struct sk_buff *in_skb,
- struct tcf_proto *tp, unsigned long base,
- u32 handle,
- struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
-{
- struct rsvp_head *data = rtnl_dereference(tp->root);
- struct rsvp_filter *f, *nfp;
- struct rsvp_filter __rcu **fp;
- struct rsvp_session *nsp, *s;
- struct rsvp_session __rcu **sp;
- struct tc_rsvp_pinfo *pinfo = NULL;
- struct nlattr *opt = tca[TCA_OPTIONS];
- struct nlattr *tb[TCA_RSVP_MAX + 1];
- struct tcf_exts e;
- unsigned int h1, h2;
- __be32 *dst;
- int err;
-
- if (opt == NULL)
- return handle ? -EINVAL : 0;
-
- err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy, NULL);
- if (err < 0)
- return err;
-
- err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE);
- if (err < 0)
- return err;
- err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack);
- if (err < 0)
- goto errout2;
-
- f = *arg;
- if (f) {
- /* Node exists: adjust only classid */
- struct rsvp_filter *n;
-
- if (f->handle != handle && handle)
- goto errout2;
-
- n = kmemdup(f, sizeof(*f), GFP_KERNEL);
- if (!n) {
- err = -ENOMEM;
- goto errout2;
- }
-
- err = tcf_exts_init(&n->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE);
- if (err < 0) {
- kfree(n);
- goto errout2;
- }
-
- if (tb[TCA_RSVP_CLASSID]) {
- n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]);
- tcf_bind_filter(tp, &n->res, base);
- }
-
- tcf_exts_change(&n->exts, &e);
- rsvp_replace(tp, n, handle);
- return 0;
- }
-
- /* Now more serious part... */
- err = -EINVAL;
- if (handle)
- goto errout2;
- if (tb[TCA_RSVP_DST] == NULL)
- goto errout2;
-
- err = -ENOBUFS;
- f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL);
- if (f == NULL)
- goto errout2;
-
- err = tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE);
- if (err < 0)
- goto errout;
- h2 = 16;
- if (tb[TCA_RSVP_SRC]) {
- memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src));
- h2 = hash_src(f->src);
- }
- if (tb[TCA_RSVP_PINFO]) {
- pinfo = nla_data(tb[TCA_RSVP_PINFO]);
- f->spi = pinfo->spi;
- f->tunnelhdr = pinfo->tunnelhdr;
- }
- if (tb[TCA_RSVP_CLASSID])
- f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]);
-
- dst = nla_data(tb[TCA_RSVP_DST]);
- h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0);
-
- err = -ENOMEM;
- if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0)
- goto errout;
-
- if (f->tunnelhdr) {
- err = -EINVAL;
- if (f->res.classid > 255)
- goto errout;
-
- err = -ENOMEM;
- if (f->res.classid == 0 &&
- (f->res.classid = gen_tunnel(data)) == 0)
- goto errout;
- }
-
- for (sp = &data->ht[h1];
- (s = rtnl_dereference(*sp)) != NULL;
- sp = &s->next) {
- if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] &&
- pinfo && pinfo->protocol == s->protocol &&
- memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 &&
-#if RSVP_DST_LEN == 4
- dst[0] == s->dst[0] &&
- dst[1] == s->dst[1] &&
- dst[2] == s->dst[2] &&
-#endif
- pinfo->tunnelid == s->tunnelid) {
-
-insert:
- /* OK, we found appropriate session */
-
- fp = &s->ht[h2];
-
- f->sess = s;
- if (f->tunnelhdr == 0)
- tcf_bind_filter(tp, &f->res, base);
-
- tcf_exts_change(&f->exts, &e);
-
- fp = &s->ht[h2];
- for (nfp = rtnl_dereference(*fp); nfp;
- fp = &nfp->next, nfp = rtnl_dereference(*fp)) {
- __u32 mask = nfp->spi.mask & f->spi.mask;
-
- if (mask != f->spi.mask)
- break;
- }
- RCU_INIT_POINTER(f->next, nfp);
- rcu_assign_pointer(*fp, f);
-
- *arg = f;
- return 0;
- }
- }
-
- /* No session found. Create new one. */
-
- err = -ENOBUFS;
- s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL);
- if (s == NULL)
- goto errout;
- memcpy(s->dst, dst, sizeof(s->dst));
-
- if (pinfo) {
- s->dpi = pinfo->dpi;
- s->protocol = pinfo->protocol;
- s->tunnelid = pinfo->tunnelid;
- }
- sp = &data->ht[h1];
- for (nsp = rtnl_dereference(*sp); nsp;
- sp = &nsp->next, nsp = rtnl_dereference(*sp)) {
- if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask)
- break;
- }
- RCU_INIT_POINTER(s->next, nsp);
- rcu_assign_pointer(*sp, s);
-
- goto insert;
-
-errout:
- tcf_exts_destroy(&f->exts);
- kfree(f);
-errout2:
- tcf_exts_destroy(&e);
- return err;
-}
-
-static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg)
-{
- struct rsvp_head *head = rtnl_dereference(tp->root);
- unsigned int h, h1;
-
- if (arg->stop)
- return;
-
- for (h = 0; h < 256; h++) {
- struct rsvp_session *s;
-
- for (s = rtnl_dereference(head->ht[h]); s;
- s = rtnl_dereference(s->next)) {
- for (h1 = 0; h1 <= 16; h1++) {
- struct rsvp_filter *f;
-
- for (f = rtnl_dereference(s->ht[h1]); f;
- f = rtnl_dereference(f->next)) {
- if (arg->count < arg->skip) {
- arg->count++;
- continue;
- }
- if (arg->fn(tp, f, arg) < 0) {
- arg->stop = 1;
- return;
- }
- arg->count++;
- }
- }
- }
- }
-}
-
-static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
-{
- struct rsvp_filter *f = fh;
- struct rsvp_session *s;
- struct nlattr *nest;
- struct tc_rsvp_pinfo pinfo;
-
- if (f == NULL)
- return skb->len;
- s = f->sess;
-
- t->tcm_handle = f->handle;
-
- nest = nla_nest_start(skb, TCA_OPTIONS);
- if (nest == NULL)
- goto nla_put_failure;
-
- if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst))
- goto nla_put_failure;
- pinfo.dpi = s->dpi;
- pinfo.spi = f->spi;
- pinfo.protocol = s->protocol;
- pinfo.tunnelid = s->tunnelid;
- pinfo.tunnelhdr = f->tunnelhdr;
- pinfo.pad = 0;
- if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo))
- goto nla_put_failure;
- if (f->res.classid &&
- nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid))
- goto nla_put_failure;
- if (((f->handle >> 8) & 0xFF) != 16 &&
- nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src))
- goto nla_put_failure;
-
- if (tcf_exts_dump(skb, &f->exts) < 0)
- goto nla_put_failure;
-
- nla_nest_end(skb, nest);
-
- if (tcf_exts_dump_stats(skb, &f->exts) < 0)
- goto nla_put_failure;
- return skb->len;
-
-nla_put_failure:
- nla_nest_cancel(skb, nest);
- return -1;
-}
-
-static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
- unsigned long base)
-{
- struct rsvp_filter *f = fh;
-
- if (f && f->res.classid == classid) {
- if (cl)
- __tcf_bind_filter(q, &f->res, base);
- else
- __tcf_unbind_filter(q, &f->res);
- }
-}
-
-static struct tcf_proto_ops RSVP_OPS __read_mostly = {
- .kind = RSVP_ID,
- .classify = rsvp_classify,
- .init = rsvp_init,
- .destroy = rsvp_destroy,
- .get = rsvp_get,
- .change = rsvp_change,
- .delete = rsvp_delete,
- .walk = rsvp_walk,
- .dump = rsvp_dump,
- .bind_class = rsvp_bind_class,
- .owner = THIS_MODULE,
-};
-
-static int __init init_rsvp(void)
-{
- return register_tcf_proto_ops(&RSVP_OPS);
-}
-
-static void __exit exit_rsvp(void)
-{
- unregister_tcf_proto_ops(&RSVP_OPS);
-}
-
-module_init(init_rsvp)
-module_exit(exit_rsvp)
diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c
deleted file mode 100644
index dd08aea2a..000000000
--- a/net/sched/cls_rsvp6.c
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/ipv6.h>
-#include <linux/skbuff.h>
-#include <net/act_api.h>
-#include <net/pkt_cls.h>
-#include <net/netlink.h>
-
-#define RSVP_DST_LEN 4
-#define RSVP_ID "rsvp6"
-#define RSVP_OPS cls_rsvp6_ops
-
-#include "cls_rsvp.h"
-MODULE_LICENSE("GPL");
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index d30256ac3..1e71ff093 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -778,11 +778,22 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
int err;
+#ifdef CONFIG_NET_CLS_IND
+ int ifindex = -1;
+#endif
err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack);
if (err < 0)
return err;
+#ifdef CONFIG_NET_CLS_IND
+ if (tb[TCA_U32_INDEV]) {
+ ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack);
+ if (ifindex < 0)
+ return -EINVAL;
+ }
+#endif
+
if (tb[TCA_U32_LINK]) {
u32 handle = nla_get_u32(tb[TCA_U32_LINK]);
struct tc_u_hnode *ht_down = NULL, *ht_old;
@@ -814,13 +825,8 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
}
#ifdef CONFIG_NET_CLS_IND
- if (tb[TCA_U32_INDEV]) {
- int ret;
- ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack);
- if (ret < 0)
- return -EINVAL;
- n->ifindex = ret;
- }
+ if (ifindex >= 0)
+ n->ifindex = ifindex;
#endif
return 0;
}
@@ -873,7 +879,6 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
new->ifindex = n->ifindex;
#endif
new->fshift = n->fshift;
- new->res = n->res;
new->flags = n->flags;
RCU_INIT_POINTER(new->ht_down, ht);
@@ -1061,18 +1066,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return -EINVAL;
}
+ /* At this point, we need to derive the new handle that will be used to
+ * uniquely map the identity of this table match entry. The
+ * identity of the entry that we need to construct is 32 bits made of:
+ * htid(12b):bucketid(8b):node/entryid(12b)
+ *
+ * At this point _we have the table(ht)_ in which we will insert this
+ * entry. We carry the table's id in variable "htid".
+ * Note that earlier code picked the ht selection either by a) the user
+ * providing the htid specified via TCA_U32_HASH attribute or b) when
+ * no such attribute is passed then the root ht, is default to at ID
+ * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0.
+ * If OTOH the user passed us the htid, they may also pass a bucketid of
+ * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is
+ * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be
+ * passed via the htid, so even if it was non-zero it will be ignored.
+ *
+ * We may also have a handle, if the user passed one. The handle also
+ * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b).
+ * Rule: the bucketid on the handle is ignored even if one was passed;
+ * rather the value on "htid" is always assumed to be the bucketid.
+ */
if (handle) {
+ /* Rule: The htid from handle and tableid from htid must match */
if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) {
NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch");
return -EINVAL;
}
- handle = htid | TC_U32_NODE(handle);
- err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle,
- GFP_KERNEL);
- if (err)
- return err;
- } else
+ /* Ok, so far we have a valid htid(12b):bucketid(8b) but we
+ * need to finalize the table entry identification with the last
+ * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for
+ * entries. Rule: nodeid of 0 is reserved only for tables(see
+ * earlier code which processes TC_U32_DIVISOR attribute).
+ * Rule: The nodeid can only be derived from the handle (and not
+ * htid).
+ * Rule: if the handle specified zero for the node id example
+ * 0x60000000, then pick a new nodeid from the pool of IDs
+ * this hash table has been allocating from.
+ * If OTOH it is specified (i.e for example the user passed a
+ * handle such as 0x60000123), then we use it generate our final
+ * handle which is used to uniquely identify the match entry.
+ */
+ if (!TC_U32_NODE(handle)) {
+ handle = gen_new_kid(ht, htid);
+ } else {
+ handle = htid | TC_U32_NODE(handle);
+ err = idr_alloc_u32(&ht->handle_idr, NULL, &handle,
+ handle, GFP_KERNEL);
+ if (err)
+ return err;
+ }
+ } else {
+ /* The user did not give us a handle; lets just generate one
+ * from the table's pool of nodeids.
+ */
handle = gen_new_kid(ht, htid);
+ }
if (tb[TCA_U32_SEL] == NULL) {
NL_SET_ERR_MSG_MOD(extack, "Selector not specified");
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 5a0e71873..ab57c0ee9 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1004,12 +1004,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
skip:
if (!ingress) {
- notify_and_destroy(net, skb, n, classid,
- dev->qdisc, new);
+ old = dev->qdisc;
if (new && !new->ops->attach)
qdisc_refcount_inc(new);
dev->qdisc = new ? : &noop_qdisc;
+ notify_and_destroy(net, skb, n, classid, old, new);
+
if (new && new->ops->attach)
new->ops->attach(new);
} else {
@@ -1438,10 +1439,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
return 0;
}
+static bool req_create_or_replace(struct nlmsghdr *n)
+{
+ return (n->nlmsg_flags & NLM_F_CREATE &&
+ n->nlmsg_flags & NLM_F_REPLACE);
+}
+
+static bool req_create_exclusive(struct nlmsghdr *n)
+{
+ return (n->nlmsg_flags & NLM_F_CREATE &&
+ n->nlmsg_flags & NLM_F_EXCL);
+}
+
+static bool req_change(struct nlmsghdr *n)
+{
+ return (!(n->nlmsg_flags & NLM_F_CREATE) &&
+ !(n->nlmsg_flags & NLM_F_REPLACE) &&
+ !(n->nlmsg_flags & NLM_F_EXCL));
+}
+
/*
* Create/change qdisc.
*/
-
static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
@@ -1538,27 +1557,35 @@ replay:
*
* We know, that some child q is already
* attached to this parent and have choice:
- * either to change it or to create/graft new one.
+ * 1) change it or 2) create/graft new one.
+ * If the requested qdisc kind is different
+ * than the existing one, then we choose graft.
+ * If they are the same then this is "change"
+ * operation - just let it fallthrough..
*
* 1. We are allowed to create/graft only
- * if CREATE and REPLACE flags are set.
+ * if the request is explicitly stating
+ * "please create if it doesn't exist".
*
- * 2. If EXCL is set, requestor wanted to say,
- * that qdisc tcm_handle is not expected
+ * 2. If the request is to exclusive create
+ * then the qdisc tcm_handle is not expected
* to exist, so that we choose create/graft too.
*
* 3. The last case is when no flags are set.
+ * This will happen when for example tc
+ * utility issues a "change" command.
* Alas, it is sort of hole in API, we
* cannot decide what to do unambiguously.
- * For now we select create/graft, if
- * user gave KIND, which does not match existing.
+ * For now we select create/graft.
*/
- if ((n->nlmsg_flags & NLM_F_CREATE) &&
- (n->nlmsg_flags & NLM_F_REPLACE) &&
- ((n->nlmsg_flags & NLM_F_EXCL) ||
- (tca[TCA_KIND] &&
- nla_strcmp(tca[TCA_KIND], q->ops->id))))
- goto create_n_graft;
+ if (tca[TCA_KIND] &&
+ nla_strcmp(tca[TCA_KIND], q->ops->id)) {
+ if (req_create_or_replace(n) ||
+ req_create_exclusive(n))
+ goto create_n_graft;
+ else if (req_change(n))
+ goto create_n_graft2;
+ }
}
}
} else {
@@ -1592,6 +1619,7 @@ create_n_graft:
NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag");
return -ENOENT;
}
+create_n_graft2:
if (clid == TC_H_INGRESS) {
if (dev_ingress_queue(dev)) {
q = qdisc_create(dev, dev_ingress_queue(dev), p,
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 01a177cfa..d91665ea7 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1649,7 +1649,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
{
struct cake_sched_data *q = qdisc_priv(sch);
int len = qdisc_pkt_len(skb);
- int uninitialized_var(ret);
+ int ret;
struct sk_buff *ack = NULL;
ktime_t now = ktime_get();
struct cake_tin_data *b;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 2974f7262..7f0a5d22d 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -365,7 +365,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct cbq_sched_data *q = qdisc_priv(sch);
- int uninitialized_var(ret);
+ int ret;
struct cbq_class *cl = cbq_classify(skb, sch, &ret);
#ifdef CONFIG_NET_CLS_ACT
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index e4f69c779..7a4777ee0 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -192,7 +192,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct fq_codel_sched_data *q = qdisc_priv(sch);
unsigned int idx, prev_backlog, prev_qlen;
struct fq_codel_flow *flow;
- int uninitialized_var(ret);
+ int ret;
unsigned int pkt_len;
bool memory_limited;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index b18ec1f6d..e71443623 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -913,6 +913,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc,
cl->cl_flags |= HFSC_USC;
}
+static void
+hfsc_upgrade_rt(struct hfsc_class *cl)
+{
+ cl->cl_fsc = cl->cl_rsc;
+ rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total);
+ cl->cl_flags |= HFSC_FSC;
+}
+
static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = {
[TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) },
[TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) },
@@ -1073,6 +1081,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->cf_tree = RB_ROOT;
sch_tree_lock(sch);
+ /* Check if the inner class is a misconfigured 'rt' */
+ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
+ NL_SET_ERR_MSG(extack,
+ "Forced curve change on parent 'rt' to 'sc'");
+ hfsc_upgrade_rt(parent);
+ }
qdisc_class_hash_insert(&q->clhash, &cl->cl_common);
list_add_tail(&cl->siblings, &parent->children);
if (parent->level == 0)
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 64d7f876d..c0ab1e38e 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,6 +132,97 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
return 0;
}
+static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
+ struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct mqprio_sched *priv = qdisc_priv(sch);
+ struct nlattr *tb[TCA_MQPRIO_MAX + 1];
+ struct nlattr *attr;
+ int i, rem, err;
+
+ err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
+ sizeof(*qopt));
+ if (err < 0)
+ return err;
+
+ if (!qopt->hw) {
+ NL_SET_ERR_MSG(extack,
+ "mqprio TCA_OPTIONS can only contain netlink attributes in hardware mode");
+ return -EINVAL;
+ }
+
+ if (tb[TCA_MQPRIO_MODE]) {
+ priv->flags |= TC_MQPRIO_F_MODE;
+ priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
+ }
+
+ if (tb[TCA_MQPRIO_SHAPER]) {
+ priv->flags |= TC_MQPRIO_F_SHAPER;
+ priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
+ }
+
+ if (tb[TCA_MQPRIO_MIN_RATE64]) {
+ if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MIN_RATE64],
+ "min_rate accepted only when shaper is in bw_rlimit mode");
+ return -EINVAL;
+ }
+ i = 0;
+ nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
+ rem) {
+ if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute type expected to be TCA_MQPRIO_MIN_RATE64");
+ return -EINVAL;
+ }
+
+ if (nla_len(attr) != sizeof(u64)) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length");
+ return -EINVAL;
+ }
+
+ if (i >= qopt->num_tc)
+ break;
+ priv->min_rate[i] = *(u64 *)nla_data(attr);
+ i++;
+ }
+ priv->flags |= TC_MQPRIO_F_MIN_RATE;
+ }
+
+ if (tb[TCA_MQPRIO_MAX_RATE64]) {
+ if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MAX_RATE64],
+ "max_rate accepted only when shaper is in bw_rlimit mode");
+ return -EINVAL;
+ }
+ i = 0;
+ nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
+ rem) {
+ if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute type expected to be TCA_MQPRIO_MAX_RATE64");
+ return -EINVAL;
+ }
+
+ if (nla_len(attr) != sizeof(u64)) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length");
+ return -EINVAL;
+ }
+
+ if (i >= qopt->num_tc)
+ break;
+ priv->max_rate[i] = *(u64 *)nla_data(attr);
+ i++;
+ }
+ priv->flags |= TC_MQPRIO_F_MAX_RATE;
+ }
+
+ return 0;
+}
+
static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
@@ -141,9 +232,6 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
struct Qdisc *qdisc;
int i, err = -EOPNOTSUPP;
struct tc_mqprio_qopt *qopt = NULL;
- struct nlattr *tb[TCA_MQPRIO_MAX + 1];
- struct nlattr *attr;
- int rem;
int len;
BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
@@ -168,55 +256,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
if (len > 0) {
- err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
- sizeof(*qopt));
- if (err < 0)
+ err = mqprio_parse_nlattr(sch, qopt, opt, extack);
+ if (err)
return err;
-
- if (!qopt->hw)
- return -EINVAL;
-
- if (tb[TCA_MQPRIO_MODE]) {
- priv->flags |= TC_MQPRIO_F_MODE;
- priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
- }
-
- if (tb[TCA_MQPRIO_SHAPER]) {
- priv->flags |= TC_MQPRIO_F_SHAPER;
- priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
- }
-
- if (tb[TCA_MQPRIO_MIN_RATE64]) {
- if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
- return -EINVAL;
- i = 0;
- nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
- rem) {
- if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64)
- return -EINVAL;
- if (i >= qopt->num_tc)
- break;
- priv->min_rate[i] = *(u64 *)nla_data(attr);
- i++;
- }
- priv->flags |= TC_MQPRIO_F_MIN_RATE;
- }
-
- if (tb[TCA_MQPRIO_MAX_RATE64]) {
- if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
- return -EINVAL;
- i = 0;
- nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
- rem) {
- if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64)
- return -EINVAL;
- if (i >= qopt->num_tc)
- break;
- priv->max_rate[i] = *(u64 *)nla_data(attr);
- i++;
- }
- priv->flags |= TC_MQPRIO_F_MAX_RATE;
- }
}
/* pre-allocate qdisc, attachment can't fail */
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 93548b9e0..cf93dbe3d 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -748,12 +748,10 @@ static void dist_free(struct disttable *d)
* signed 16 bit values.
*/
-static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
- const struct nlattr *attr)
+static int get_dist_table(struct disttable **tbl, const struct nlattr *attr)
{
size_t n = nla_len(attr)/sizeof(__s16);
const __s16 *data = nla_data(attr);
- spinlock_t *root_lock;
struct disttable *d;
int i;
@@ -768,13 +766,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
for (i = 0; i < n; i++)
d->table[i] = data[i];
- root_lock = qdisc_root_sleeping_lock(sch);
-
- spin_lock_bh(root_lock);
- swap(*tbl, d);
- spin_unlock_bh(root_lock);
-
- dist_free(d);
+ *tbl = d;
return 0;
}
@@ -930,6 +922,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
{
struct netem_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_NETEM_MAX + 1];
+ struct disttable *delay_dist = NULL;
+ struct disttable *slot_dist = NULL;
struct tc_netem_qopt *qopt;
struct clgstate old_clg;
int old_loss_model = CLG_RANDOM;
@@ -943,6 +937,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
if (ret < 0)
return ret;
+ if (tb[TCA_NETEM_DELAY_DIST]) {
+ ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]);
+ if (ret)
+ goto table_free;
+ }
+
+ if (tb[TCA_NETEM_SLOT_DIST]) {
+ ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]);
+ if (ret)
+ goto table_free;
+ }
+
sch_tree_lock(sch);
/* backup q->clg and q->loss_model */
old_clg = q->clg;
@@ -952,26 +958,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
if (ret) {
q->loss_model = old_loss_model;
+ q->clg = old_clg;
goto unlock;
}
} else {
q->loss_model = CLG_RANDOM;
}
- if (tb[TCA_NETEM_DELAY_DIST]) {
- ret = get_dist_table(sch, &q->delay_dist,
- tb[TCA_NETEM_DELAY_DIST]);
- if (ret)
- goto get_table_failure;
- }
-
- if (tb[TCA_NETEM_SLOT_DIST]) {
- ret = get_dist_table(sch, &q->slot_dist,
- tb[TCA_NETEM_SLOT_DIST]);
- if (ret)
- goto get_table_failure;
- }
-
+ if (delay_dist)
+ swap(q->delay_dist, delay_dist);
+ if (slot_dist)
+ swap(q->slot_dist, slot_dist);
sch->limit = qopt->limit;
q->latency = PSCHED_TICKS2NS(qopt->latency);
@@ -1021,17 +1018,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
unlock:
sch_tree_unlock(sch);
- return ret;
-get_table_failure:
- /* recover clg and loss_model, in case of
- * q->clg and q->loss_model were modified
- * in get_loss_clg()
- */
- q->clg = old_clg;
- q->loss_model = old_loss_model;
-
- goto unlock;
+table_free:
+ dist_free(delay_dist);
+ dist_free(slot_dist);
+ return ret;
}
static int netem_init(struct Qdisc *sch, struct nlattr *opt,
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index 5619d2eb1..4ddb4af61 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -214,7 +214,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct plug_sched_data),
.enqueue = plug_enqueue,
.dequeue = plug_dequeue,
- .peek = qdisc_peek_head,
+ .peek = qdisc_peek_dequeued,
.init = plug_init,
.change = plug_change,
.reset = qdisc_reset_queue,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index c2a68f6e4..4f2465997 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -387,8 +387,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight,
u32 lmax)
{
struct qfq_sched *q = qdisc_priv(sch);
- struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight);
+ struct qfq_aggregate *new_agg;
+ /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */
+ if (lmax > (1UL << QFQ_MTU_SHIFT))
+ return -EINVAL;
+
+ new_agg = qfq_find_agg(q, lmax, weight);
if (new_agg == NULL) { /* create new aggregate */
new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC);
if (new_agg == NULL)
@@ -983,10 +988,13 @@ static void qfq_update_eligible(struct qfq_sched *q)
}
/* Dequeue head packet of the head class in the DRR queue of the aggregate. */
-static void agg_dequeue(struct qfq_aggregate *agg,
- struct qfq_class *cl, unsigned int len)
+static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
+ struct qfq_class *cl, unsigned int len)
{
- qdisc_dequeue_peeked(cl->qdisc);
+ struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc);
+
+ if (!skb)
+ return NULL;
cl->deficit -= (int) len;
@@ -996,6 +1004,8 @@ static void agg_dequeue(struct qfq_aggregate *agg,
cl->deficit += agg->lmax;
list_move_tail(&cl->alist, &agg->active);
}
+
+ return skb;
}
static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
@@ -1141,11 +1151,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
if (!skb)
return NULL;
- qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
+
+ skb = agg_dequeue(in_serv_agg, cl, len);
+
+ if (!skb) {
+ sch->q.qlen++;
+ return NULL;
+ }
+
+ qdisc_qstats_backlog_dec(sch, skb);
qdisc_bstats_update(sch, skb);
- agg_dequeue(in_serv_agg, cl, len);
/* If lmax is lowered, through qfq_change_class, for a class
* owning pending packets with larger size than the new value
* of lmax, then the following condition may hold.
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 1bfdf90fa..07721a1e9 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -353,7 +353,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
unsigned int hash, dropped;
sfq_index x, qlen;
struct sfq_slot *slot;
- int uninitialized_var(ret);
+ int ret;
struct sk_buff *head;
int delta;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index d17708800..78c1429d1 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1181,8 +1181,7 @@ int sctp_assoc_update(struct sctp_association *asoc,
/* Add any peer addresses from the new association. */
list_for_each_entry(trans, &new->peer.transport_addr_list,
transports)
- if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) &&
- !sctp_assoc_add_peer(asoc, &trans->ipaddr,
+ if (!sctp_assoc_add_peer(asoc, &trans->ipaddr,
GFP_ATOMIC, trans->state))
return -ENOMEM;
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 82d96441e..c4a2d647e 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1255,7 +1255,10 @@ static int sctp_side_effects(enum sctp_event event_type,
default:
pr_err("impossible disposition %d in state %d, event_type %d, event_id %d\n",
status, state, event_type, subtype.chunk);
- BUG();
+ error = status;
+ if (error >= 0)
+ error = -EINVAL;
+ WARN_ON_ONCE(1);
break;
}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a68f3d6b7..f954d3c88 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -112,7 +112,7 @@ struct percpu_counter sctp_sockets_allocated;
static void sctp_enter_memory_pressure(struct sock *sk)
{
- sctp_memory_pressure = 1;
+ WRITE_ONCE(sctp_memory_pressure, 1);
}
@@ -380,9 +380,9 @@ static void sctp_auto_asconf_init(struct sctp_sock *sp)
struct net *net = sock_net(&sp->inet.sk);
if (net->sctp.default_auto_asconf) {
- spin_lock(&net->sctp.addr_wq_lock);
+ spin_lock_bh(&net->sctp.addr_wq_lock);
list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist);
- spin_unlock(&net->sctp.addr_wq_lock);
+ spin_unlock_bh(&net->sctp.addr_wq_lock);
sp->do_auto_asconf = 1;
}
}
@@ -2578,6 +2578,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
if (trans) {
trans->hbinterval =
msecs_to_jiffies(params->spp_hbinterval);
+ sctp_transport_reset_hb_timer(trans);
} else if (asoc) {
asoc->hbinterval =
msecs_to_jiffies(params->spp_hbinterval);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index dcd00b514..ad0ac657f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -141,34 +141,34 @@ static int smc_release(struct socket *sock)
if (!smc->use_fallback) {
rc = smc_close_active(smc);
- sock_set_flag(sk, SOCK_DEAD);
+ smc_sock_set_flag(sk, SOCK_DEAD);
sk->sk_shutdown |= SHUTDOWN_MASK;
- }
-
- sk->sk_prot->unhash(sk);
-
- if (smc->clcsock) {
- if (smc->use_fallback && sk->sk_state == SMC_LISTEN) {
+ } else {
+ if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+ sock_put(sk); /* passive closing */
+ if (sk->sk_state == SMC_LISTEN) {
/* wake up clcsock accept */
rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
}
- mutex_lock(&smc->clcsock_release_lock);
- sock_release(smc->clcsock);
- smc->clcsock = NULL;
- mutex_unlock(&smc->clcsock_release_lock);
- }
- if (smc->use_fallback) {
- if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
- sock_put(sk); /* passive closing */
sk->sk_state = SMC_CLOSED;
sk->sk_state_change(sk);
}
+ sk->sk_prot->unhash(sk);
+
+ if (sk->sk_state == SMC_CLOSED) {
+ if (smc->clcsock) {
+ release_sock(sk);
+ smc_clcsock_release(smc);
+ lock_sock(sk);
+ }
+ if (!smc->use_fallback)
+ smc_conn_free(&smc->conn);
+ }
+
/* detach socket */
sock_orphan(sk);
sock->sk = NULL;
- if (!smc->use_fallback && sk->sk_state == SMC_CLOSED)
- smc_conn_free(&smc->conn);
release_sock(sk);
sock_put(sk); /* final sock_put */
@@ -852,7 +852,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
- sock_set_flag(new_sk, SOCK_DEAD);
+ smc_sock_set_flag(new_sk, SOCK_DEAD);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
@@ -1013,13 +1013,13 @@ static void smc_listen_out(struct smc_sock *new_smc)
struct smc_sock *lsmc = new_smc->listen_smc;
struct sock *newsmcsk = &new_smc->sk;
- lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
if (lsmc->sk.sk_state == SMC_LISTEN) {
+ lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
smc_accept_enqueue(&lsmc->sk, newsmcsk);
+ release_sock(&lsmc->sk);
} else { /* no longer listening */
smc_close_non_accepted(newsmcsk);
}
- release_sock(&lsmc->sk);
/* Wake up accept */
lsmc->sk.sk_data_ready(&lsmc->sk);
@@ -1215,6 +1215,9 @@ static void smc_listen_work(struct work_struct *work)
int rc = 0;
u8 ibport;
+ if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+ return smc_listen_out_err(new_smc);
+
if (new_smc->use_fallback) {
smc_listen_out_connected(new_smc);
return;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index adbdf195e..c3b0e1e3f 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -268,4 +268,9 @@ static inline bool using_ipsec(struct smc_sock *smc)
struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock);
void smc_close_non_accepted(struct sock *sk);
+static inline void smc_sock_set_flag(struct sock *sk, enum sock_flags flag)
+{
+ set_bit(flag, &sk->sk_flags);
+}
+
#endif /* __SMC_H */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 333e43534..c657fd29f 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -304,7 +304,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
smc->sk.sk_shutdown |= RCV_SHUTDOWN;
if (smc->clcsock && smc->clcsock->sk)
smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
- sock_set_flag(&smc->sk, SOCK_DONE);
+ smc_sock_set_flag(&smc->sk, SOCK_DONE);
sock_hold(&smc->sk); /* sock_put in close_work */
if (!schedule_work(&conn->close_work))
sock_put(&smc->sk);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 092696d73..4ea28ec7a 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -21,6 +21,22 @@
#define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+ struct socket *tcp;
+
+ if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+ cancel_work_sync(&smc->smc_listen_work);
+ mutex_lock(&smc->clcsock_release_lock);
+ if (smc->clcsock) {
+ tcp = smc->clcsock;
+ smc->clcsock = NULL;
+ sock_release(tcp);
+ }
+ mutex_unlock(&smc->clcsock_release_lock);
+}
+
static void smc_close_cleanup_listen(struct sock *parent)
{
struct sock *sk;
@@ -148,7 +164,7 @@ static void smc_close_active_abort(struct smc_sock *smc)
break;
}
- sock_set_flag(sk, SOCK_DEAD);
+ smc_sock_set_flag(sk, SOCK_DEAD);
sk->sk_state_change(sk);
}
@@ -331,6 +347,7 @@ static void smc_close_passive_work(struct work_struct *work)
close_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
struct smc_cdc_conn_state_flags *rxflags;
+ bool release_clcsock = false;
struct sock *sk = &smc->sk;
int old_state;
@@ -415,10 +432,15 @@ wakeup:
if (old_state != sk->sk_state) {
sk->sk_state_change(sk);
if ((sk->sk_state == SMC_CLOSED) &&
- (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket))
+ (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
smc_conn_free(conn);
+ if (smc->clcsock)
+ release_clcsock = true;
+ }
}
release_sock(sk);
+ if (release_clcsock)
+ smc_clcsock_release(smc);
sock_put(sk); /* sock_hold done by schedulers of close_work */
}
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 19eb6a211..e0e3b5df2 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc);
int smc_close_active(struct smc_sock *smc);
int smc_close_shutdown_write(struct smc_sock *smc);
void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
#endif /* SMC_CLOSE_H */
diff --git a/net/socket.c b/net/socket.c
index ce70c01eb..328f58434 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -90,6 +90,7 @@
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/nospec.h>
+#include <linux/indirect_call_wrapper.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
@@ -108,6 +109,13 @@
#include <net/busy_poll.h>
#include <linux/errqueue.h>
+/* proto_ops for ipv4 and ipv6 use the same {recv,send}msg function */
+#if IS_ENABLED(CONFIG_INET)
+#define INDIRECT_CALL_INET4(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
+#else
+#define INDIRECT_CALL_INET4(f, f1, ...) f(__VA_ARGS__)
+#endif
+
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
unsigned int sysctl_net_busy_poll __read_mostly;
@@ -637,29 +645,48 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
}
EXPORT_SYMBOL(__sock_tx_timestamp);
-/**
- * sock_sendmsg - send a message through @sock
- * @sock: socket
- * @msg: message to send
- *
- * Sends @msg through @sock, passing through LSM.
- * Returns the number of bytes sent, or an error code.
- */
-
+INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *,
+ size_t));
static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
{
- int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg));
+ int ret = INDIRECT_CALL_INET4(sock->ops->sendmsg, inet_sendmsg, sock,
+ msg, msg_data_left(msg));
BUG_ON(ret == -EIOCBQUEUED);
return ret;
}
-int sock_sendmsg(struct socket *sock, struct msghdr *msg)
+static int __sock_sendmsg(struct socket *sock, struct msghdr *msg)
{
int err = security_socket_sendmsg(sock, msg,
msg_data_left(msg));
return err ?: sock_sendmsg_nosec(sock, msg);
}
+
+/**
+ * sock_sendmsg - send a message through @sock
+ * @sock: socket
+ * @msg: message to send
+ *
+ * Sends @msg through @sock, passing through LSM.
+ * Returns the number of bytes sent, or an error code.
+ */
+int sock_sendmsg(struct socket *sock, struct msghdr *msg)
+{
+ struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name;
+ struct sockaddr_storage address;
+ int ret;
+
+ if (msg->msg_name) {
+ memcpy(&address, msg->msg_name, msg->msg_namelen);
+ msg->msg_name = &address;
+ }
+
+ ret = __sock_sendmsg(sock, msg);
+ msg->msg_name = save_addr;
+
+ return ret;
+}
EXPORT_SYMBOL(sock_sendmsg);
/**
@@ -843,6 +870,15 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
}
EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
+INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *,
+ size_t , int ));
+static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
+ int flags)
+{
+ return INDIRECT_CALL_INET4(sock->ops->recvmsg, inet_recvmsg, sock, msg,
+ msg_data_left(msg), flags);
+}
+
/**
* sock_recvmsg - receive a message from @sock
* @sock: socket
@@ -852,13 +888,6 @@ EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
* Receives @msg from @sock, passing through LSM. Returns the total number
* of bytes received, or an error.
*/
-
-static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
- int flags)
-{
- return sock->ops->recvmsg(sock, msg, msg_data_left(msg), flags);
-}
-
int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags)
{
int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags);
@@ -963,7 +992,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (sock->type == SOCK_SEQPACKET)
msg.msg_flags |= MSG_EOR;
- res = sock_sendmsg(sock, &msg);
+ res = __sock_sendmsg(sock, &msg);
*from = msg.msg_iter;
return res;
}
@@ -1896,7 +1925,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
msg.msg_flags = flags;
- err = sock_sendmsg(sock, &msg);
+ err = __sock_sendmsg(sock, &msg);
out_put:
fput_light(sock->file, fput_needed);
@@ -2224,7 +2253,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
err = sock_sendmsg_nosec(sock, msg_sys);
goto out_freectl;
}
- err = sock_sendmsg(sock, msg_sys);
+ err = __sock_sendmsg(sock, msg_sys);
/*
* If this is sendmmsg() and sending to current destination address was
* successful, remember it.
@@ -3398,7 +3427,11 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd,
int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
{
- return sock->ops->bind(sock, addr, addrlen);
+ struct sockaddr_storage address;
+
+ memcpy(&address, addr, addrlen);
+
+ return sock->ops->bind(sock, (struct sockaddr *)&address, addrlen);
}
EXPORT_SYMBOL(kernel_bind);
@@ -3468,7 +3501,11 @@ EXPORT_SYMBOL(kernel_accept);
int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
int flags)
{
- return sock->ops->connect(sock, addr, addrlen, flags);
+ struct sockaddr_storage address;
+
+ memcpy(&address, addr, addrlen);
+
+ return sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, flags);
}
EXPORT_SYMBOL(kernel_connect);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index d0b5a1c47..b5ee21d5d 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -757,12 +757,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
dprintk("svc: socket %p TCP (listen) state change %d\n",
sk, sk->sk_state);
- if (svsk) {
- /* Refer to svc_setup_socket() for details. */
- rmb();
- svsk->sk_odata(sk);
- }
-
/*
* This callback may called twice when a new connection
* is established as a child socket inherits everything
@@ -771,15 +765,20 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
* when one of child sockets become ESTABLISHED.
* 2) data_ready method of the child socket may be called
* when it receives data before the socket is accepted.
- * In case of 2, we should ignore it silently.
+ * In case of 2, we should ignore it silently and DO NOT
+ * dereference svsk.
*/
- if (sk->sk_state == TCP_LISTEN) {
- if (svsk) {
- set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
- svc_xprt_enqueue(&svsk->sk_xprt);
- } else
- printk("svc: socket %p: no user data\n", sk);
- }
+ if (sk->sk_state != TCP_LISTEN)
+ return;
+
+ if (svsk) {
+ /* Refer to svc_setup_socket() for details. */
+ rmb();
+ svsk->sk_odata(sk);
+ set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
+ svc_xprt_enqueue(&svsk->sk_xprt);
+ } else
+ printk("svc: socket %p: no user data\n", sk);
}
/*
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9b36163d9..bf11d57ef 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -87,7 +87,7 @@ const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
[TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_LINK_NAME] = { .type = NLA_STRING,
+ [TIPC_NLA_LINK_NAME] = { .type = NLA_NUL_STRING,
.len = TIPC_MAX_LINK_NAME },
[TIPC_NLA_LINK_MTU] = { .type = NLA_U32 },
[TIPC_NLA_LINK_BROADCAST] = { .type = NLA_FLAG },
@@ -116,7 +116,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = {
[TIPC_NLA_BEARER_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_BEARER_NAME] = { .type = NLA_STRING,
+ [TIPC_NLA_BEARER_NAME] = { .type = NLA_NUL_STRING,
.len = TIPC_MAX_BEARER_NAME },
[TIPC_NLA_BEARER_PROP] = { .type = NLA_NESTED },
[TIPC_NLA_BEARER_DOMAIN] = { .type = NLA_U32 }
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 59e8e17d8..2276a0704 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -101,6 +101,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
return -EMSGSIZE;
skb_put(skb, TLV_SPACE(len));
+ memset(tlv, 0, TLV_SPACE(len));
tlv->tlv_type = htons(type);
tlv->tlv_len = htons(TLV_LENGTH(len));
if (len && data)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b0dcbb08e..0632b494d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -594,7 +594,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
* What the above comment does talk about? --ANK(980817)
*/
- if (unix_tot_inflight)
+ if (READ_ONCE(unix_tot_inflight))
unix_gc(); /* Garbage collect fds */
}
@@ -706,7 +706,7 @@ static int unix_set_peek_off(struct sock *sk, int val)
if (mutex_lock_interruptible(&u->iolock))
return -EINTR;
- sk->sk_peek_off = val;
+ WRITE_ONCE(sk->sk_peek_off, val);
mutex_unlock(&u->iolock);
return 0;
@@ -1984,6 +1984,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
if (false) {
alloc_skb:
+ spin_unlock(&other->sk_receive_queue.lock);
unix_state_unlock(other);
mutex_unlock(&unix_sk(other)->iolock);
newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
@@ -2023,6 +2024,7 @@ alloc_skb:
init_scm = false;
}
+ spin_lock(&other->sk_receive_queue.lock);
skb = skb_peek_tail(&other->sk_receive_queue);
if (tail && tail == skb) {
skb = newskb;
@@ -2053,14 +2055,11 @@ alloc_skb:
refcount_add(size, &sk->sk_wmem_alloc);
if (newskb) {
- err = unix_scm_to_skb(&scm, skb, false);
- if (err)
- goto err_state_unlock;
- spin_lock(&other->sk_receive_queue.lock);
+ unix_scm_to_skb(&scm, skb, false);
__skb_queue_tail(&other->sk_receive_queue, newskb);
- spin_unlock(&other->sk_receive_queue.lock);
}
+ spin_unlock(&other->sk_receive_queue.lock);
unix_state_unlock(other);
mutex_unlock(&unix_sk(other)->iolock);
diff --git a/net/unix/scm.c b/net/unix/scm.c
index a07b2efbf..ac206bfdb 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -59,7 +59,7 @@ void unix_inflight(struct user_struct *user, struct file *fp)
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
}
- user->unix_inflight++;
+ WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1);
spin_unlock(&unix_gc_lock);
}
@@ -80,7 +80,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
}
- user->unix_inflight--;
+ WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1);
spin_unlock(&unix_gc_lock);
}
@@ -94,7 +94,7 @@ static inline bool too_many_unix_fds(struct task_struct *p)
{
struct user_struct *user = current_user();
- if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+ if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
return false;
}
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 449b5261e..187d0f725 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -348,7 +348,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk)
struct virtio_vsock_sock *vvs = vsk->trans;
s64 bytes;
- bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+ bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
if (bytes < 0)
bytes = 0;
diff --git a/net/wireless/certs/wens.hex b/net/wireless/certs/wens.hex
new file mode 100644
index 000000000..0d50369be
--- /dev/null
+++ b/net/wireless/certs/wens.hex
@@ -0,0 +1,87 @@
+/* Chen-Yu Tsai's regdb certificate */
+0x30, 0x82, 0x02, 0xa7, 0x30, 0x82, 0x01, 0x8f,
+0x02, 0x14, 0x61, 0xc0, 0x38, 0x65, 0x1a, 0xab,
+0xdc, 0xf9, 0x4b, 0xd0, 0xac, 0x7f, 0xf0, 0x6c,
+0x72, 0x48, 0xdb, 0x18, 0xc6, 0x00, 0x30, 0x0d,
+0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d,
+0x01, 0x01, 0x0b, 0x05, 0x00, 0x30, 0x0f, 0x31,
+0x0d, 0x30, 0x0b, 0x06, 0x03, 0x55, 0x04, 0x03,
+0x0c, 0x04, 0x77, 0x65, 0x6e, 0x73, 0x30, 0x20,
+0x17, 0x0d, 0x32, 0x33, 0x31, 0x32, 0x30, 0x31,
+0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, 0x18,
+0x0f, 0x32, 0x31, 0x32, 0x33, 0x31, 0x31, 0x30,
+0x37, 0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a,
+0x30, 0x0f, 0x31, 0x0d, 0x30, 0x0b, 0x06, 0x03,
+0x55, 0x04, 0x03, 0x0c, 0x04, 0x77, 0x65, 0x6e,
+0x73, 0x30, 0x82, 0x01, 0x22, 0x30, 0x0d, 0x06,
+0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01,
+0x01, 0x01, 0x05, 0x00, 0x03, 0x82, 0x01, 0x0f,
+0x00, 0x30, 0x82, 0x01, 0x0a, 0x02, 0x82, 0x01,
+0x01, 0x00, 0xa9, 0x7a, 0x2c, 0x78, 0x4d, 0xa7,
+0x19, 0x2d, 0x32, 0x52, 0xa0, 0x2e, 0x6c, 0xef,
+0x88, 0x7f, 0x15, 0xc5, 0xb6, 0x69, 0x54, 0x16,
+0x43, 0x14, 0x79, 0x53, 0xb7, 0xae, 0x88, 0xfe,
+0xc0, 0xb7, 0x5d, 0x47, 0x8e, 0x1a, 0xe1, 0xef,
+0xb3, 0x90, 0x86, 0xda, 0xd3, 0x64, 0x81, 0x1f,
+0xce, 0x5d, 0x9e, 0x4b, 0x6e, 0x58, 0x02, 0x3e,
+0xb2, 0x6f, 0x5e, 0x42, 0x47, 0x41, 0xf4, 0x2c,
+0xb8, 0xa8, 0xd4, 0xaa, 0xc0, 0x0e, 0xe6, 0x48,
+0xf0, 0xa8, 0xce, 0xcb, 0x08, 0xae, 0x37, 0xaf,
+0xf6, 0x40, 0x39, 0xcb, 0x55, 0x6f, 0x5b, 0x4f,
+0x85, 0x34, 0xe6, 0x69, 0x10, 0x50, 0x72, 0x5e,
+0x4e, 0x9d, 0x4c, 0xba, 0x38, 0x36, 0x0d, 0xce,
+0x73, 0x38, 0xd7, 0x27, 0x02, 0x2a, 0x79, 0x03,
+0xe1, 0xac, 0xcf, 0xb0, 0x27, 0x85, 0x86, 0x93,
+0x17, 0xab, 0xec, 0x42, 0x77, 0x37, 0x65, 0x8a,
+0x44, 0xcb, 0xd6, 0x42, 0x93, 0x92, 0x13, 0xe3,
+0x39, 0x45, 0xc5, 0x6e, 0x00, 0x4a, 0x7f, 0xcb,
+0x42, 0x17, 0x2b, 0x25, 0x8c, 0xb8, 0x17, 0x3b,
+0x15, 0x36, 0x59, 0xde, 0x42, 0xce, 0x21, 0xe6,
+0xb6, 0xc7, 0x6e, 0x5e, 0x26, 0x1f, 0xf7, 0x8a,
+0x57, 0x9e, 0xa5, 0x96, 0x72, 0xb7, 0x02, 0x32,
+0xeb, 0x07, 0x2b, 0x73, 0xe2, 0x4f, 0x66, 0x58,
+0x9a, 0xeb, 0x0f, 0x07, 0xb6, 0xab, 0x50, 0x8b,
+0xc3, 0x8f, 0x17, 0xfa, 0x0a, 0x99, 0xc2, 0x16,
+0x25, 0xbf, 0x2d, 0x6b, 0x1a, 0xaa, 0xe6, 0x3e,
+0x5f, 0xeb, 0x6d, 0x9b, 0x5d, 0x4d, 0x42, 0x83,
+0x2d, 0x39, 0xb8, 0xc9, 0xac, 0xdb, 0x3a, 0x91,
+0x50, 0xdf, 0xbb, 0xb1, 0x76, 0x6d, 0x15, 0x73,
+0xfd, 0xc6, 0xe6, 0x6b, 0x71, 0x9e, 0x67, 0x36,
+0x22, 0x83, 0x79, 0xb1, 0xd6, 0xb8, 0x84, 0x52,
+0xaf, 0x96, 0x5b, 0xc3, 0x63, 0x02, 0x4e, 0x78,
+0x70, 0x57, 0x02, 0x03, 0x01, 0x00, 0x01, 0x30,
+0x0d, 0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7,
+0x0d, 0x01, 0x01, 0x0b, 0x05, 0x00, 0x03, 0x82,
+0x01, 0x01, 0x00, 0x24, 0x28, 0xee, 0x22, 0x74,
+0x7f, 0x7c, 0xfa, 0x6c, 0x1f, 0xb3, 0x18, 0xd1,
+0xc2, 0x3d, 0x7d, 0x29, 0x42, 0x88, 0xad, 0x82,
+0xa5, 0xb1, 0x8a, 0x05, 0xd0, 0xec, 0x5c, 0x91,
+0x20, 0xf6, 0x82, 0xfd, 0xd5, 0x67, 0x60, 0x5f,
+0x31, 0xf5, 0xbd, 0x88, 0x91, 0x70, 0xbd, 0xb8,
+0xb9, 0x8c, 0x88, 0xfe, 0x53, 0xc9, 0x54, 0x9b,
+0x43, 0xc4, 0x7a, 0x43, 0x74, 0x6b, 0xdd, 0xb0,
+0xb1, 0x3b, 0x33, 0x45, 0x46, 0x78, 0xa3, 0x1c,
+0xef, 0x54, 0x68, 0xf7, 0x85, 0x9c, 0xe4, 0x51,
+0x6f, 0x06, 0xaf, 0x81, 0xdb, 0x2a, 0x7b, 0x7b,
+0x6f, 0xa8, 0x9c, 0x67, 0xd8, 0xcb, 0xc9, 0x91,
+0x40, 0x00, 0xae, 0xd9, 0xa1, 0x9f, 0xdd, 0xa6,
+0x43, 0x0e, 0x28, 0x7b, 0xaa, 0x1b, 0xe9, 0x84,
+0xdb, 0x76, 0x64, 0x42, 0x70, 0xc9, 0xc0, 0xeb,
+0xae, 0x84, 0x11, 0x16, 0x68, 0x4e, 0x84, 0x9e,
+0x7e, 0x92, 0x36, 0xee, 0x1c, 0x3b, 0x08, 0x63,
+0xeb, 0x79, 0x84, 0x15, 0x08, 0x9d, 0xaf, 0xc8,
+0x9a, 0xc7, 0x34, 0xd3, 0x94, 0x4b, 0xd1, 0x28,
+0x97, 0xbe, 0xd1, 0x45, 0x75, 0xdc, 0x35, 0x62,
+0xac, 0x1d, 0x1f, 0xb7, 0xb7, 0x15, 0x87, 0xc8,
+0x98, 0xc0, 0x24, 0x31, 0x56, 0x8d, 0xed, 0xdb,
+0x06, 0xc6, 0x46, 0xbf, 0x4b, 0x6d, 0xa6, 0xd5,
+0xab, 0xcc, 0x60, 0xfc, 0xe5, 0x37, 0xb6, 0x53,
+0x7d, 0x58, 0x95, 0xa9, 0x56, 0xc7, 0xf7, 0xee,
+0xc3, 0xa0, 0x76, 0xf7, 0x65, 0x4d, 0x53, 0xfa,
+0xff, 0x5f, 0x76, 0x33, 0x5a, 0x08, 0xfa, 0x86,
+0x92, 0x5a, 0x13, 0xfa, 0x1a, 0xfc, 0xf2, 0x1b,
+0x8c, 0x7f, 0x42, 0x6d, 0xb7, 0x7e, 0xb7, 0xb4,
+0xf0, 0xc7, 0x83, 0xbb, 0xa2, 0x81, 0x03, 0x2d,
+0xd4, 0x2a, 0x63, 0x3f, 0xf7, 0x31, 0x2e, 0x40,
+0x33, 0x5c, 0x46, 0xbc, 0x9b, 0xc1, 0x05, 0xa5,
+0x45, 0x4e, 0xc3,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 534f57363..e33c1175b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6504,7 +6504,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb,
struct cfg80211_registered_device *rdev = info->user_ptr[0];
struct net_device *dev = info->user_ptr[1];
struct wireless_dev *wdev = dev->ieee80211_ptr;
- struct mesh_config cfg;
+ struct mesh_config cfg = {};
u32 mask;
int err;
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 76a80a416..a57f54bc0 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -796,6 +796,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd,
}
}
+ /* Sanity-check to ensure we never end up _allocating_ zero
+ * bytes of data for extra.
+ */
+ if (extra_size <= 0)
+ return -EFAULT;
+
/* kzalloc() ensures NULL-termination for essid_compat. */
extra = kzalloc(extra_size, GFP_KERNEL);
if (!extra)
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index fbc4552d1..6e5e307f9 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -3,6 +3,8 @@
# Makefile for the XFRM subsystem.
#
+xfrm_interface-$(CONFIG_XFRM_INTERFACE) += xfrm_interface_core.o
+
obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
xfrm_input.o xfrm_output.o \
xfrm_sysctl.o xfrm_replay.o xfrm_device.o
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface_core.c
index 3c642328a..10fa26103 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -219,8 +219,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
skb->dev = dev;
if (err) {
- dev->stats.rx_errors++;
- dev->stats.rx_dropped++;
+ DEV_STATS_INC(dev, rx_errors);
+ DEV_STATS_INC(dev, rx_dropped);
return 0;
}
@@ -260,7 +260,6 @@ static int
xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
{
struct xfrm_if *xi = netdev_priv(dev);
- struct net_device_stats *stats = &xi->dev->stats;
struct dst_entry *dst = skb_dst(skb);
unsigned int length = skb->len;
struct net_device *tdev;
@@ -286,7 +285,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
tdev = dst->dev;
if (tdev == dev) {
- stats->collisions++;
+ DEV_STATS_INC(dev, collisions);
net_warn_ratelimited("%s: Local routing loop detected!\n",
dev->name);
goto tx_err_dst_release;
@@ -329,13 +328,13 @@ xmit:
tstats->tx_packets++;
u64_stats_update_end(&tstats->syncp);
} else {
- stats->tx_errors++;
- stats->tx_aborted_errors++;
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_aborted_errors);
}
return 0;
tx_err_link_failure:
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
@@ -345,7 +344,6 @@ tx_err_dst_release:
static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
- struct net_device_stats *stats = &xi->dev->stats;
struct dst_entry *dst = skb_dst(skb);
struct flowi fl;
int ret;
@@ -354,23 +352,23 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
switch (skb->protocol) {
case htons(ETH_P_IPV6):
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
if (!dst) {
fl.u.ip6.flowi6_oif = dev->ifindex;
fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
if (dst->error) {
dst_release(dst);
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
goto tx_err;
}
skb_dst_set(skb, dst);
}
break;
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
if (!dst) {
struct rtable *rt;
@@ -378,7 +376,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
if (IS_ERR(rt)) {
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
goto tx_err;
}
skb_dst_set(skb, &rt->dst);
@@ -397,8 +395,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
tx_err:
- stats->tx_errors++;
- stats->tx_dropped++;
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_dropped);
kfree_skb(skb);
return NETDEV_TX_OK;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 6fe578773..c8a7a5739 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -654,8 +654,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
* of an absolute inpredictability of ordering of rules. This will not pass. */
static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
{
- static u32 idx_generator;
-
for (;;) {
struct hlist_head *list;
struct xfrm_policy *p;
@@ -663,8 +661,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
int found;
if (!index) {
- idx = (idx_generator | dir);
- idx_generator += 8;
+ idx = (net->xfrm.idx_generator | dir);
+ net->xfrm.idx_generator += 8;
} else {
idx = index;
index = 0;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 94c7ebc26..699e544b4 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -521,7 +521,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
struct nlattr *et = attrs[XFRMA_ETIMER_THRESH];
struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH];
- if (re) {
+ if (re && x->replay_esn && x->preplay_esn) {
struct xfrm_replay_state_esn *replay_esn;
replay_esn = nla_data(re);
memcpy(x->replay_esn, replay_esn,
@@ -1036,6 +1036,15 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
sizeof(*filter), GFP_KERNEL);
if (filter == NULL)
return -ENOMEM;
+
+ /* see addr_match(), (prefix length >> 5) << 2
+ * will be used to compare xfrm_address_t
+ */
+ if (filter->splen > (sizeof(xfrm_address_t) << 3) ||
+ filter->dplen > (sizeof(xfrm_address_t) << 3)) {
+ kfree(filter);
+ return -EINVAL;
+ }
}
if (attrs[XFRMA_PROTO])
@@ -2573,7 +2582,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
[XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) },
[XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) },
[XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) },
- [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) },
+ [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) },
[XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) },
[XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) },
[XFRMA_REPLAY_THRESH] = { .type = NLA_U32 },