summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorTakashi Iwai <tiwai@suse.de>2021-08-30 15:57:03 +0300
committerTakashi Iwai <tiwai@suse.de>2021-08-30 15:57:03 +0300
commita8729efbbb847f6ea9b06e73491ec8ddb560465e (patch)
treec2e172452158457ab238080405060110934ad9d1 /net
parentf7b82b12626e10a2f5332b699cc79819ac8decc7 (diff)
parent38b7673000949ca784fcb8a9feb70d2a802befa6 (diff)
downloadlinux-a8729efbbb847f6ea9b06e73491ec8ddb560465e.tar.xz
Merge tag 'asoc-v5.15' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus
ASoC: Updates for v5.15 Quite a quiet release this time, mostly a combination of cleanups and a good set of new drivers. - Lots of cleanups and improvements to the Intel drivers, including some new systems support. - New support for AMD Vangoh, CUI CMM-4030D-261, Mediatek Mt8195, Renesas RZ/G2L Mediatek Mt8195, RealTek RT101P, Renesas RZ/G2L,, Rockchip RK3568 S/PDIF.
Diffstat (limited to 'net')
-rw-r--r--net/802/garp.c14
-rw-r--r--net/802/mrp.c14
-rw-r--r--net/bluetooth/hci_core.c16
-rw-r--r--net/bluetooth/hci_sock.c49
-rw-r--r--net/bluetooth/hci_sysfs.c3
-rw-r--r--net/bpf/test_run.c7
-rw-r--r--net/bridge/br_fdb.c25
-rw-r--r--net/bridge/br_if.c19
-rw-r--r--net/bridge/br_multicast.c6
-rw-r--r--net/bridge/netfilter/nf_conntrack_bridge.c6
-rw-r--r--net/caif/caif_socket.c3
-rw-r--r--net/can/j1939/transport.c11
-rw-r--r--net/can/raw.c20
-rw-r--r--net/core/dev.c50
-rw-r--r--net/core/devlink.c10
-rw-r--r--net/core/flow_dissector.c18
-rw-r--r--net/core/link_watch.c5
-rw-r--r--net/core/page_pool.c10
-rw-r--r--net/core/skbuff.c19
-rw-r--r--net/core/skmsg.c55
-rw-r--r--net/core/sock.c71
-rw-r--r--net/dccp/dccp.h6
-rw-r--r--net/decnet/af_decnet.c27
-rw-r--r--net/dsa/slave.c16
-rw-r--r--net/dsa/switch.c8
-rw-r--r--net/dsa/tag_ksz.c9
-rw-r--r--net/ethtool/Makefile2
-rw-r--r--net/ethtool/common.c14
-rw-r--r--net/ethtool/netlink.c10
-rw-r--r--net/ethtool/netlink.h2
-rw-r--r--net/ethtool/phc_vclocks.c94
-rw-r--r--net/ieee802154/socket.c7
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/igmp.c21
-rw-r--r--net/ipv4/inet_diag.c5
-rw-r--r--net/ipv4/ip_tunnel.c20
-rw-r--r--net/ipv4/ipmr.c2
-rw-r--r--net/ipv4/raw_diag.c7
-rw-r--r--net/ipv4/tcp.c3
-rw-r--r--net/ipv4/tcp_bbr.c2
-rw-r--r--net/ipv4/tcp_bpf.c2
-rw-r--r--net/ipv4/tcp_fastopen.c28
-rw-r--r--net/ipv4/tcp_input.c21
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv4/tcp_offload.c3
-rw-r--r--net/ipv4/tcp_output.c1
-rw-r--r--net/ipv4/udp.c31
-rw-r--r--net/ipv4/udp_bpf.c2
-rw-r--r--net/ipv4/udp_diag.c6
-rw-r--r--net/ipv4/udp_offload.c10
-rw-r--r--net/ipv6/ip6_output.c37
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/tcp_ipv6.c21
-rw-r--r--net/ipv6/udp.c27
-rw-r--r--net/ipv6/xfrm6_output.c2
-rw-r--r--net/iucv/iucv.c22
-rw-r--r--net/llc/af_llc.c10
-rw-r--r--net/llc/llc_s_ac.c2
-rw-r--r--net/mac80211/cfg.c19
-rw-r--r--net/mac80211/ieee80211_i.h2
-rw-r--r--net/mac80211/main.c2
-rw-r--r--net/mac80211/mlme.c4
-rw-r--r--net/mac80211/rx.c3
-rw-r--r--net/mac80211/tx.c57
-rw-r--r--net/mptcp/mib.c1
-rw-r--r--net/mptcp/mib.h1
-rw-r--r--net/mptcp/mptcp_diag.c6
-rw-r--r--net/mptcp/options.c29
-rw-r--r--net/mptcp/pm_netlink.c45
-rw-r--r--net/mptcp/protocol.c12
-rw-r--r--net/mptcp/protocol.h10
-rw-r--r--net/mptcp/sockopt.c68
-rw-r--r--net/mptcp/subflow.c11
-rw-r--r--net/mptcp/syncookies.c16
-rw-r--r--net/ncsi/Kconfig6
-rw-r--r--net/ncsi/internal.h5
-rw-r--r--net/ncsi/ncsi-manage.c51
-rw-r--r--net/ncsi/ncsi-rsp.c11
-rw-r--r--net/netfilter/ipset/ip_set_hash_ip.c9
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipmark.c10
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipport.c3
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportip.c3
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportnet.c3
-rw-r--r--net/netfilter/ipset/ip_set_hash_net.c11
-rw-r--r--net/netfilter/ipset/ip_set_hash_netiface.c10
-rw-r--r--net/netfilter/ipset/ip_set_hash_netnet.c16
-rw-r--r--net/netfilter/ipset/ip_set_hash_netport.c11
-rw-r--r--net/netfilter/ipset/ip_set_hash_netportnet.c16
-rw-r--r--net/netfilter/nf_conntrack_core.c89
-rw-r--r--net/netfilter/nf_conntrack_netlink.c3
-rw-r--r--net/netfilter/nf_conntrack_proto.c7
-rw-r--r--net/netfilter/nf_conntrack_proto_gre.c13
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c70
-rw-r--r--net/netfilter/nf_conntrack_proto_udp.c1
-rw-r--r--net/netfilter/nf_conntrack_standalone.c26
-rw-r--r--net/netfilter/nf_flow_table_core.c17
-rw-r--r--net/netfilter/nf_tables_api.c15
-rw-r--r--net/netfilter/nfnetlink_hook.c26
-rw-r--r--net/netfilter/nft_last.c32
-rw-r--r--net/netfilter/nft_nat.c4
-rw-r--r--net/netlink/af_netlink.c2
-rw-r--r--net/netrom/nr_timer.c20
-rw-r--r--net/openvswitch/flow.c13
-rw-r--r--net/openvswitch/flow_table.c6
-rw-r--r--net/openvswitch/vport.c1
-rw-r--r--net/qrtr/mhi.c16
-rw-r--r--net/qrtr/qrtr.c6
-rw-r--r--net/rds/ib_frmr.c4
-rw-r--r--net/sched/act_ct.c14
-rw-r--r--net/sched/act_mirred.c3
-rw-r--r--net/sched/act_skbmod.c12
-rw-r--r--net/sched/cls_api.c2
-rw-r--r--net/sched/cls_tcindex.c5
-rw-r--r--net/sched/sch_cake.c2
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_taprio.c4
-rw-r--r--net/sctp/auth.c12
-rw-r--r--net/sctp/diag.c6
-rw-r--r--net/sctp/input.c2
-rw-r--r--net/sctp/ipv6.c5
-rw-r--r--net/sctp/output.c4
-rw-r--r--net/sctp/protocol.c3
-rw-r--r--net/sctp/sm_make_chunk.c2
-rw-r--r--net/sctp/sm_statefuns.c15
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/sctp/transport.c36
-rw-r--r--net/smc/af_smc.c2
-rw-r--r--net/smc/smc_core.c4
-rw-r--r--net/smc/smc_core.h4
-rw-r--r--net/smc/smc_llc.c10
-rw-r--r--net/smc/smc_tx.c18
-rw-r--r--net/smc/smc_wr.c10
-rw-r--r--net/socket.c19
-rw-r--r--net/tipc/crypto.c14
-rw-r--r--net/tipc/link.c6
-rw-r--r--net/tipc/socket.c30
-rw-r--r--net/unix/af_unix.c51
-rw-r--r--net/unix/diag.c6
-rw-r--r--net/vmw_vsock/virtio_transport.c7
-rw-r--r--net/vmw_vsock/virtio_transport_common.c3
-rw-r--r--net/wireless/nl80211.c5
-rw-r--r--net/wireless/scan.c6
-rw-r--r--net/xfrm/xfrm_compat.c49
-rw-r--r--net/xfrm/xfrm_ipcomp.c2
-rw-r--r--net/xfrm/xfrm_policy.c32
-rw-r--r--net/xfrm/xfrm_user.c10
146 files changed, 1566 insertions, 598 deletions
diff --git a/net/802/garp.c b/net/802/garp.c
index 400bd857e5f5..f6012f8e59f0 100644
--- a/net/802/garp.c
+++ b/net/802/garp.c
@@ -203,6 +203,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr
kfree(attr);
}
+static void garp_attr_destroy_all(struct garp_applicant *app)
+{
+ struct rb_node *node, *next;
+ struct garp_attr *attr;
+
+ for (node = rb_first(&app->gid);
+ next = node ? rb_next(node) : NULL, node != NULL;
+ node = next) {
+ attr = rb_entry(node, struct garp_attr, node);
+ garp_attr_destroy(app, attr);
+ }
+}
+
static int garp_pdu_init(struct garp_applicant *app)
{
struct sk_buff *skb;
@@ -609,6 +622,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl
spin_lock_bh(&app->lock);
garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU);
+ garp_attr_destroy_all(app);
garp_pdu_queue(app);
spin_unlock_bh(&app->lock);
diff --git a/net/802/mrp.c b/net/802/mrp.c
index bea6e43d45a0..35e04cc5390c 100644
--- a/net/802/mrp.c
+++ b/net/802/mrp.c
@@ -292,6 +292,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr)
kfree(attr);
}
+static void mrp_attr_destroy_all(struct mrp_applicant *app)
+{
+ struct rb_node *node, *next;
+ struct mrp_attr *attr;
+
+ for (node = rb_first(&app->mad);
+ next = node ? rb_next(node) : NULL, node != NULL;
+ node = next) {
+ attr = rb_entry(node, struct mrp_attr, node);
+ mrp_attr_destroy(app, attr);
+ }
+}
+
static int mrp_pdu_init(struct mrp_applicant *app)
{
struct sk_buff *skb;
@@ -895,6 +908,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl)
spin_lock_bh(&app->lock);
mrp_mad_event(app, MRP_EVENT_TX);
+ mrp_attr_destroy_all(app);
mrp_pdu_queue(app);
spin_unlock_bh(&app->lock);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 2560ed2f144d..e1a545c8a69f 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3996,14 +3996,10 @@ EXPORT_SYMBOL(hci_register_dev);
/* Unregister HCI device */
void hci_unregister_dev(struct hci_dev *hdev)
{
- int id;
-
BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
hci_dev_set_flag(hdev, HCI_UNREGISTER);
- id = hdev->id;
-
write_lock(&hci_dev_list_lock);
list_del(&hdev->list);
write_unlock(&hci_dev_list_lock);
@@ -4038,7 +4034,14 @@ void hci_unregister_dev(struct hci_dev *hdev)
}
device_del(&hdev->dev);
+ /* Actual cleanup is deferred until hci_cleanup_dev(). */
+ hci_dev_put(hdev);
+}
+EXPORT_SYMBOL(hci_unregister_dev);
+/* Cleanup HCI device */
+void hci_cleanup_dev(struct hci_dev *hdev)
+{
debugfs_remove_recursive(hdev->debugfs);
kfree_const(hdev->hw_info);
kfree_const(hdev->fw_info);
@@ -4063,11 +4066,8 @@ void hci_unregister_dev(struct hci_dev *hdev)
hci_blocked_keys_clear(hdev);
hci_dev_unlock(hdev);
- hci_dev_put(hdev);
-
- ida_simple_remove(&hci_index_ida, id);
+ ida_simple_remove(&hci_index_ida, hdev->id);
}
-EXPORT_SYMBOL(hci_unregister_dev);
/* Suspend HCI device */
int hci_suspend_dev(struct hci_dev *hdev)
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index b04a5a02ecf3..f1128c2134f0 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -59,6 +59,17 @@ struct hci_pinfo {
char comm[TASK_COMM_LEN];
};
+static struct hci_dev *hci_hdev_from_sock(struct sock *sk)
+{
+ struct hci_dev *hdev = hci_pi(sk)->hdev;
+
+ if (!hdev)
+ return ERR_PTR(-EBADFD);
+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+ return ERR_PTR(-EPIPE);
+ return hdev;
+}
+
void hci_sock_set_flag(struct sock *sk, int nr)
{
set_bit(nr, &hci_pi(sk)->flags);
@@ -759,19 +770,13 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event)
if (event == HCI_DEV_UNREG) {
struct sock *sk;
- /* Detach sockets from device */
+ /* Wake up sockets using this dead device */
read_lock(&hci_sk_list.lock);
sk_for_each(sk, &hci_sk_list.head) {
- lock_sock(sk);
if (hci_pi(sk)->hdev == hdev) {
- hci_pi(sk)->hdev = NULL;
sk->sk_err = EPIPE;
- sk->sk_state = BT_OPEN;
sk->sk_state_change(sk);
-
- hci_dev_put(hdev);
}
- release_sock(sk);
}
read_unlock(&hci_sk_list.lock);
}
@@ -930,10 +935,10 @@ static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg)
static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
unsigned long arg)
{
- struct hci_dev *hdev = hci_pi(sk)->hdev;
+ struct hci_dev *hdev = hci_hdev_from_sock(sk);
- if (!hdev)
- return -EBADFD;
+ if (IS_ERR(hdev))
+ return PTR_ERR(hdev);
if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
return -EBUSY;
@@ -1103,6 +1108,18 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
lock_sock(sk);
+ /* Allow detaching from dead device and attaching to alive device, if
+ * the caller wants to re-bind (instead of close) this socket in
+ * response to hci_sock_dev_event(HCI_DEV_UNREG) notification.
+ */
+ hdev = hci_pi(sk)->hdev;
+ if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
+ hci_pi(sk)->hdev = NULL;
+ sk->sk_state = BT_OPEN;
+ hci_dev_put(hdev);
+ }
+ hdev = NULL;
+
if (sk->sk_state == BT_BOUND) {
err = -EALREADY;
goto done;
@@ -1379,9 +1396,9 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr,
lock_sock(sk);
- hdev = hci_pi(sk)->hdev;
- if (!hdev) {
- err = -EBADFD;
+ hdev = hci_hdev_from_sock(sk);
+ if (IS_ERR(hdev)) {
+ err = PTR_ERR(hdev);
goto done;
}
@@ -1743,9 +1760,9 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg,
goto done;
}
- hdev = hci_pi(sk)->hdev;
- if (!hdev) {
- err = -EBADFD;
+ hdev = hci_hdev_from_sock(sk);
+ if (IS_ERR(hdev)) {
+ err = PTR_ERR(hdev);
goto done;
}
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 9874844a95a9..b69d88b88d2e 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -83,6 +83,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn)
static void bt_host_release(struct device *dev)
{
struct hci_dev *hdev = to_hci_dev(dev);
+
+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+ hci_cleanup_dev(hdev);
kfree(hdev);
module_put(THIS_MODULE);
}
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aa47af349ba8..caa16bf30fb5 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -7,6 +7,7 @@
#include <linux/vmalloc.h>
#include <linux/etherdevice.h>
#include <linux/filter.h>
+#include <linux/rcupdate_trace.h>
#include <linux/sched/signal.h>
#include <net/bpf_sk_storage.h>
#include <net/sock.h>
@@ -701,6 +702,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
void *data;
int ret;
+ if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
+ prog->expected_attach_type == BPF_XDP_CPUMAP)
+ return -EINVAL;
if (kattr->test.ctx_in || kattr->test.ctx_out)
return -EINVAL;
@@ -948,7 +952,10 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog,
goto out;
}
}
+
+ rcu_read_lock_trace();
retval = bpf_prog_run_pin_on_cpu(prog, ctx);
+ rcu_read_unlock_trace();
if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) {
err = -EFAULT;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 2b862cffc03a..5dee30966ed3 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -780,7 +780,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev,
struct net_device *dst_dev;
dst_dev = dst ? dst->dev : br->dev;
- if (dst_dev != br_dev && dst_dev != dev)
+ if (dst_dev && dst_dev != dev)
continue;
err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx);
@@ -1019,7 +1019,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
struct net_bridge_port *p, const unsigned char *addr,
- u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[])
+ u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[],
+ struct netlink_ext_ack *extack)
{
int err = 0;
@@ -1038,6 +1039,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
rcu_read_unlock();
local_bh_enable();
} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
+ if (!p && !(ndm->ndm_state & NUD_PERMANENT)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "FDB entry towards bridge must be permanent");
+ return -EINVAL;
+ }
err = br_fdb_external_learn_add(br, p, addr, vid, true);
} else {
spin_lock_bh(&br->hash_lock);
@@ -1110,9 +1116,11 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
}
/* VID was specified, so use it. */
- err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb,
+ extack);
} else {
- err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb,
+ extack);
if (err || !vg || !vg->num_vlans)
goto out;
@@ -1124,7 +1132,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
if (!br_vlan_should_use(v))
continue;
err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid,
- nfea_tb);
+ nfea_tb, extack);
if (err)
goto out;
}
@@ -1281,6 +1289,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
if (swdev_notify)
flags |= BIT(BR_FDB_ADDED_BY_USER);
+
+ if (!p)
+ flags |= BIT(BR_FDB_LOCAL);
+
fdb = fdb_create(br, p, addr, vid, flags);
if (!fdb) {
err = -ENOMEM;
@@ -1307,6 +1319,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
if (swdev_notify)
set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+ if (!p)
+ set_bit(BR_FDB_LOCAL, &fdb->flags);
+
if (modified)
fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f7d2f472ae24..14cd6ef96111 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -562,7 +562,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
struct net_bridge_port *p;
int err = 0;
unsigned br_hr, dev_hr;
- bool changed_addr;
+ bool changed_addr, fdb_synced = false;
/* Don't allow bridging non-ethernet like devices. */
if ((dev->flags & IFF_LOOPBACK) ||
@@ -616,6 +616,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
err = dev_set_allmulti(dev, 1);
if (err) {
+ br_multicast_del_port(p);
kfree(p); /* kobject not yet init'd, manually free */
goto err1;
}
@@ -652,6 +653,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
list_add_rcu(&p->list, &br->port_list);
nbp_update_port_count(br);
+ if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) {
+ /* When updating the port count we also update all ports'
+ * promiscuous mode.
+ * A port leaving promiscuous mode normally gets the bridge's
+ * fdb synced to the unicast filter (if supported), however,
+ * `br_port_clear_promisc` does not distinguish between
+ * non-promiscuous ports and *new* ports, so we need to
+ * sync explicitly here.
+ */
+ fdb_synced = br_fdb_sync_static(br, p) == 0;
+ if (!fdb_synced)
+ netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n");
+ }
netdev_update_features(br->dev);
@@ -701,6 +715,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
return 0;
err7:
+ if (fdb_synced)
+ br_fdb_unsync_static(br, p);
list_del_rcu(&p->list);
br_fdb_delete_by_port(br, p, 0, 1);
nbp_update_port_count(br);
@@ -714,6 +730,7 @@ err4:
err3:
sysfs_remove_link(br->ifobj, p->dev->name);
err2:
+ br_multicast_del_port(p);
kobject_put(&p->kobj);
dev_set_allmulti(dev, -1);
err1:
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 53c3a9d80d9c..d0434dc8c03b 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -3264,7 +3264,9 @@ static void br_multicast_pim(struct net_bridge *br,
pim_hdr_type(pimhdr) != PIM_TYPE_HELLO)
return;
+ spin_lock(&br->multicast_lock);
br_ip4_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
}
static int br_ip4_multicast_mrd_rcv(struct net_bridge *br,
@@ -3275,7 +3277,9 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br,
igmp_hdr(skb)->type != IGMP_MRDISC_ADV)
return -ENOMSG;
+ spin_lock(&br->multicast_lock);
br_ip4_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
return 0;
}
@@ -3343,7 +3347,9 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br,
if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV)
return;
+ spin_lock(&br->multicast_lock);
br_ip6_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
}
static int br_multicast_ipv6_rcv(struct net_bridge *br,
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 8d033a75a766..fdbed3158555 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -88,6 +88,12 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
skb = ip_fraglist_next(&iter);
}
+
+ if (!err)
+ return 0;
+
+ kfree_skb_list(iter.frag);
+
return err;
}
slow_path:
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 647554c9813b..e12fd3cad619 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg,
goto err;
ret = -EINVAL;
- if (unlikely(msg->msg_iter.iov->iov_base == NULL))
+ if (unlikely(msg->msg_iter.nr_segs == 0) ||
+ unlikely(msg->msg_iter.iov->iov_base == NULL))
goto err;
noblock = msg->msg_flags & MSG_DONTWAIT;
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index c3946c355882..bdc95bd7a851 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1075,11 +1075,16 @@ static bool j1939_session_deactivate_locked(struct j1939_session *session)
static bool j1939_session_deactivate(struct j1939_session *session)
{
+ struct j1939_priv *priv = session->priv;
bool active;
- j1939_session_list_lock(session->priv);
+ j1939_session_list_lock(priv);
+ /* This function should be called with a session ref-count of at
+ * least 2.
+ */
+ WARN_ON_ONCE(kref_read(&session->kref) < 2);
active = j1939_session_deactivate_locked(session);
- j1939_session_list_unlock(session->priv);
+ j1939_session_list_unlock(priv);
return active;
}
@@ -1869,7 +1874,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
if (!session->transmission)
j1939_tp_schedule_txtimer(session, 0);
} else {
- j1939_tp_set_rxtimeout(session, 250);
+ j1939_tp_set_rxtimeout(session, 750);
}
session->last_cmd = 0xff;
consume_skb(se_skb);
diff --git a/net/can/raw.c b/net/can/raw.c
index ed4fcb7ab0c3..cd5a49380116 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -546,10 +546,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
}
+ rtnl_lock();
lock_sock(sk);
- if (ro->bound && ro->ifindex)
+ if (ro->bound && ro->ifindex) {
dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+ if (!dev) {
+ if (count > 1)
+ kfree(filter);
+ err = -ENODEV;
+ goto out_fil;
+ }
+ }
if (ro->bound) {
/* (try to) register the new filters */
@@ -588,6 +596,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
dev_put(dev);
release_sock(sk);
+ rtnl_unlock();
break;
@@ -600,10 +609,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
err_mask &= CAN_ERR_MASK;
+ rtnl_lock();
lock_sock(sk);
- if (ro->bound && ro->ifindex)
+ if (ro->bound && ro->ifindex) {
dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_err;
+ }
+ }
/* remove current error mask */
if (ro->bound) {
@@ -627,6 +642,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
dev_put(dev);
release_sock(sk);
+ rtnl_unlock();
break;
diff --git a/net/core/dev.c b/net/core/dev.c
index c253c2aafe97..8f1a47ad6781 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -131,6 +131,7 @@
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
+#include <trace/events/qdisc.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
@@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
}
}
+static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q,
+ struct sk_buff **to_free,
+ struct netdev_queue *txq)
+{
+ int rc;
+
+ rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK;
+ if (rc == NET_XMIT_SUCCESS)
+ trace_qdisc_enqueue(q, txq, skb);
+ return rc;
+}
+
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev,
struct netdev_queue *txq)
@@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
* of q->seqlock to protect from racing with requeuing.
*/
if (unlikely(!nolock_qdisc_is_empty(q))) {
- rc = q->enqueue(skb, q, &to_free) &
- NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
__qdisc_run(q);
qdisc_run_end(q);
@@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
return NET_XMIT_SUCCESS;
}
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
qdisc_run(q);
no_lock_out:
@@ -3923,7 +3935,7 @@ no_lock_out:
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
@@ -6008,6 +6020,19 @@ static void gro_list_prepare(const struct list_head *head,
diffs = memcmp(skb_mac_header(p),
skb_mac_header(skb),
maclen);
+
+ diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb);
+#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ if (!diffs) {
+ struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT);
+ struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT);
+
+ diffs |= (!!p_ext) ^ (!!skb_ext);
+ if (!diffs && unlikely(skb_ext))
+ diffs |= p_ext->chain ^ skb_ext->chain;
+ }
+#endif
+
NAPI_GRO_CB(p)->same_flow = !diffs;
}
}
@@ -6221,6 +6246,8 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
case GRO_MERGED_FREE:
if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
napi_skb_free_stolen_head(skb);
+ else if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
+ __kfree_skb(skb);
else
__kfree_skb_defer(skb);
break;
@@ -6270,6 +6297,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
skb_shinfo(skb)->gso_type = 0;
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
skb_ext_reset(skb);
+ nf_reset_ct(skb);
napi->skb = skb;
}
@@ -9684,14 +9712,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
struct net_device *dev;
int err, fd;
+ rtnl_lock();
dev = dev_get_by_index(net, attr->link_create.target_ifindex);
- if (!dev)
+ if (!dev) {
+ rtnl_unlock();
return -EINVAL;
+ }
link = kzalloc(sizeof(*link), GFP_USER);
if (!link) {
err = -ENOMEM;
- goto out_put_dev;
+ goto unlock;
}
bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
@@ -9701,14 +9732,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
err = bpf_link_prime(&link->link, &link_primer);
if (err) {
kfree(link);
- goto out_put_dev;
+ goto unlock;
}
- rtnl_lock();
err = dev_xdp_attach_link(dev, NULL, link);
rtnl_unlock();
if (err) {
+ link->dev = NULL;
bpf_link_cleanup(&link_primer);
goto out_put_dev;
}
@@ -9718,6 +9749,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
dev_put(dev);
return fd;
+unlock:
+ rtnl_unlock();
+
out_put_dev:
dev_put(dev);
return err;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8fdd04f00fd7..85032626de24 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -9328,18 +9328,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
switch (attrs->flavour) {
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
- case DEVLINK_PORT_FLAVOUR_VIRTUAL:
n = snprintf(name, len, "p%u", attrs->phys.port_number);
if (n < len && attrs->split)
n += snprintf(name + n, len - n, "s%u",
attrs->phys.split_subport_number);
- if (!attrs->split)
- n = snprintf(name, len, "p%u", attrs->phys.port_number);
- else
- n = snprintf(name, len, "p%us%u",
- attrs->phys.port_number,
- attrs->phys.split_subport_number);
-
break;
case DEVLINK_PORT_FLAVOUR_CPU:
case DEVLINK_PORT_FLAVOUR_DSA:
@@ -9381,6 +9373,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
attrs->pci_sf.sf);
break;
+ case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+ return -EOPNOTSUPP;
}
if (n >= len)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2aadbfc5193b..4b2415d34873 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1504,7 +1504,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow)
}
EXPORT_SYMBOL(flow_get_u32_dst);
-/* Sort the source and destination IP (and the ports if the IP are the same),
+/* Sort the source and destination IP and the ports,
* to have consistent hash within the two directions
*/
static inline void __flow_hash_consistentify(struct flow_keys *keys)
@@ -1515,11 +1515,11 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
addr_diff = (__force u32)keys->addrs.v4addrs.dst -
(__force u32)keys->addrs.v4addrs.src;
- if ((addr_diff < 0) ||
- (addr_diff == 0 &&
- ((__force u16)keys->ports.dst <
- (__force u16)keys->ports.src))) {
+ if (addr_diff < 0)
swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
+
+ if ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src) {
swap(keys->ports.src, keys->ports.dst);
}
break;
@@ -1527,13 +1527,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
addr_diff = memcmp(&keys->addrs.v6addrs.dst,
&keys->addrs.v6addrs.src,
sizeof(keys->addrs.v6addrs.dst));
- if ((addr_diff < 0) ||
- (addr_diff == 0 &&
- ((__force u16)keys->ports.dst <
- (__force u16)keys->ports.src))) {
+ if (addr_diff < 0) {
for (i = 0; i < 4; i++)
swap(keys->addrs.v6addrs.src.s6_addr32[i],
keys->addrs.v6addrs.dst.s6_addr32[i]);
+ }
+ if ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src) {
swap(keys->ports.src, keys->ports.dst);
}
break;
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 75431ca9300f..1a455847da54 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -158,7 +158,7 @@ static void linkwatch_do_dev(struct net_device *dev)
clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state);
rfc2863_policy(dev);
- if (dev->flags & IFF_UP && netif_device_present(dev)) {
+ if (dev->flags & IFF_UP) {
if (netif_carrier_ok(dev))
dev_activate(dev);
else
@@ -204,7 +204,8 @@ static void __linkwatch_run_queue(int urgent_only)
dev = list_first_entry(&wrk, struct net_device, link_watch_list);
list_del_init(&dev->link_watch_list);
- if (urgent_only && !linkwatch_urgent_event(dev)) {
+ if (!netif_device_present(dev) ||
+ (urgent_only && !linkwatch_urgent_event(dev))) {
list_add_tail(&dev->link_watch_list, &lweventlist);
continue;
}
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5e4eb45b139c..8ab7b402244c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -634,7 +634,15 @@ bool page_pool_return_skb_page(struct page *page)
struct page_pool *pp;
page = compound_head(page);
- if (unlikely(page->pp_magic != PP_SIGNATURE))
+
+ /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
+ * in order to preserve any existing bits, such as bit 0 for the
+ * head page of compound page and bit 1 for pfmemalloc page, so
+ * mask those bits for freeing side when doing below checking,
+ * and page_is_pfmemalloc() is checked in __page_pool_put_page()
+ * to avoid recycling the pfmemalloc page.
+ */
+ if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE))
return false;
pp = page->pp;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 12aabcda6db2..fc7942c0dddc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb)
if (skb->cloned &&
atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&shinfo->dataref))
- return;
+ goto exit;
skb_zcopy_clear(skb, true);
@@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb)
kfree_skb_list(shinfo->frag_list);
skb_free_head(skb);
+exit:
+ /* When we clone an SKB we copy the reycling bit. The pp_recycle
+ * bit is only set on the head though, so in order to avoid races
+ * while trying to recycle fragments on __skb_frag_unref() we need
+ * to make one SKB responsible for triggering the recycle path.
+ * So disable the recycling bit if an SKB is cloned and we have
+ * additional references to to the fragmented part of the SKB.
+ * Eventually the last SKB will have the recycling bit set and it's
+ * dataref set to 0, which will trigger the recycling
+ */
+ skb->pp_recycle = 0;
}
/*
@@ -943,6 +954,7 @@ void __kfree_skb_defer(struct sk_buff *skb)
void napi_skb_free_stolen_head(struct sk_buff *skb)
{
+ nf_reset_ct(skb);
skb_dst_drop(skb);
skb_ext_put(skb);
napi_skb_cache_put(skb);
@@ -3010,8 +3022,11 @@ skb_zerocopy_headlen(const struct sk_buff *from)
if (!from->head_frag ||
skb_headlen(from) < L1_CACHE_BYTES ||
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) {
hlen = skb_headlen(from);
+ if (!hlen)
+ hlen = from->len;
+ }
if (skb_has_frag_list(from))
hlen = from->len;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 9b6160a191f8..2d6249b28928 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -508,10 +508,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
if (skb_linearize(skb))
return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
- if (unlikely(num_sge < 0)) {
- kfree(msg);
+ if (unlikely(num_sge < 0))
return num_sge;
- }
copied = skb->len;
msg->sg.start = 0;
@@ -530,6 +528,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
{
struct sock *sk = psock->sk;
struct sk_msg *msg;
+ int err;
/* If we are receiving on the same sock skb->sk is already assigned,
* skip memory accounting and owner transition seeing it already set
@@ -548,7 +547,10 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
* into user buffers.
*/
skb_set_owner_r(skb, sk);
- return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ if (err < 0)
+ kfree(msg);
+ return err;
}
/* Puts an skb on the ingress queue of the socket already assigned to the
@@ -559,12 +561,16 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
{
struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
struct sock *sk = psock->sk;
+ int err;
if (unlikely(!msg))
return -EAGAIN;
sk_msg_init(msg);
skb_set_owner_r(skb, sk);
- return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ if (err < 0)
+ kfree(msg);
+ return err;
}
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
@@ -578,29 +584,42 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
return sk_psock_skb_ingress(psock, skb);
}
-static void sock_drop(struct sock *sk, struct sk_buff *skb)
+static void sk_psock_skb_state(struct sk_psock *psock,
+ struct sk_psock_work_state *state,
+ struct sk_buff *skb,
+ int len, int off)
{
- sk_drops_add(sk, skb);
- kfree_skb(skb);
+ spin_lock_bh(&psock->ingress_lock);
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+ state->skb = skb;
+ state->len = len;
+ state->off = off;
+ } else {
+ sock_drop(psock->sk, skb);
+ }
+ spin_unlock_bh(&psock->ingress_lock);
}
static void sk_psock_backlog(struct work_struct *work)
{
struct sk_psock *psock = container_of(work, struct sk_psock, work);
struct sk_psock_work_state *state = &psock->work_state;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
bool ingress;
u32 len, off;
int ret;
mutex_lock(&psock->work_mutex);
- if (state->skb) {
+ if (unlikely(state->skb)) {
+ spin_lock_bh(&psock->ingress_lock);
skb = state->skb;
len = state->len;
off = state->off;
state->skb = NULL;
- goto start;
+ spin_unlock_bh(&psock->ingress_lock);
}
+ if (skb)
+ goto start;
while ((skb = skb_dequeue(&psock->ingress_skb))) {
len = skb->len;
@@ -615,9 +634,8 @@ start:
len, ingress);
if (ret <= 0) {
if (ret == -EAGAIN) {
- state->skb = skb;
- state->len = len;
- state->off = off;
+ sk_psock_skb_state(psock, state, skb,
+ len, off);
goto end;
}
/* Hard errors break pipe and stop xmit. */
@@ -716,6 +734,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock)
skb_bpf_redirect_clear(skb);
sock_drop(psock->sk, skb);
}
+ kfree_skb(psock->work_state.skb);
+ /* We null the skb here to ensure that calls to sk_psock_backlog
+ * do not pick up the free'd skb.
+ */
+ psock->work_state.skb = NULL;
__sk_psock_purge_ingress_msg(psock);
}
@@ -767,8 +790,6 @@ static void sk_psock_destroy(struct work_struct *work)
void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
- sk_psock_stop(psock, false);
-
write_lock_bh(&sk->sk_callback_lock);
sk_psock_restore_proto(sk, psock);
rcu_assign_sk_user_data(sk, NULL);
@@ -778,6 +799,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
sk_psock_stop_verdict(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
+ sk_psock_stop(psock, false);
+
INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
queue_rcu_work(system_wq, &psock->rwork);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index ba1c0f75cd45..a3eea6e0b30a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -139,6 +139,8 @@
#include <net/tcp.h>
#include <net/busy_poll.h>
+#include <linux/ethtool.h>
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
@@ -810,8 +812,47 @@ void sock_set_timestamp(struct sock *sk, int optname, bool valbool)
}
}
-int sock_set_timestamping(struct sock *sk, int optname, int val)
+static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
+{
+ struct net *net = sock_net(sk);
+ struct net_device *dev = NULL;
+ bool match = false;
+ int *vclock_index;
+ int i, num;
+
+ if (sk->sk_bound_dev_if)
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+
+ if (!dev) {
+ pr_err("%s: sock not bind to device\n", __func__);
+ return -EOPNOTSUPP;
+ }
+
+ num = ethtool_get_phc_vclocks(dev, &vclock_index);
+ for (i = 0; i < num; i++) {
+ if (*(vclock_index + i) == phc_index) {
+ match = true;
+ break;
+ }
+ }
+
+ if (num > 0)
+ kfree(vclock_index);
+
+ if (!match)
+ return -EINVAL;
+
+ sk->sk_bind_phc = phc_index;
+
+ return 0;
+}
+
+int sock_set_timestamping(struct sock *sk, int optname,
+ struct so_timestamping timestamping)
{
+ int val = timestamping.flags;
+ int ret;
+
if (val & ~SOF_TIMESTAMPING_MASK)
return -EINVAL;
@@ -832,6 +873,12 @@ int sock_set_timestamping(struct sock *sk, int optname, int val)
!(val & SOF_TIMESTAMPING_OPT_TSONLY))
return -EINVAL;
+ if (val & SOF_TIMESTAMPING_BIND_PHC) {
+ ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc);
+ if (ret)
+ return ret;
+ }
+
sk->sk_tsflags = val;
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
@@ -907,6 +954,7 @@ EXPORT_SYMBOL(sock_set_mark);
int sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
+ struct so_timestamping timestamping;
struct sock_txtime sk_txtime;
struct sock *sk = sock->sk;
int val;
@@ -1068,12 +1116,22 @@ set_sndbuf:
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, valbool, optname);
+ sock_set_timestamp(sk, optname, valbool);
break;
case SO_TIMESTAMPING_NEW:
case SO_TIMESTAMPING_OLD:
- ret = sock_set_timestamping(sk, optname, val);
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(&timestamping, optval,
+ sizeof(timestamping))) {
+ ret = -EFAULT;
+ break;
+ }
+ } else {
+ memset(&timestamping, 0, sizeof(timestamping));
+ timestamping.flags = val;
+ }
+ ret = sock_set_timestamping(sk, optname, timestamping);
break;
case SO_RCVLOWAT:
@@ -1201,7 +1259,7 @@ set_sndbuf:
if (val < 0)
ret = -EINVAL;
else
- sk->sk_ll_usec = val;
+ WRITE_ONCE(sk->sk_ll_usec, val);
}
break;
case SO_PREFER_BUSY_POLL:
@@ -1348,6 +1406,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
struct __kernel_old_timeval tm;
struct __kernel_sock_timeval stm;
struct sock_txtime txtime;
+ struct so_timestamping timestamping;
} v;
int lv = sizeof(int);
@@ -1451,7 +1510,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_TIMESTAMPING_OLD:
- v.val = sk->sk_tsflags;
+ lv = sizeof(v.timestamping);
+ v.timestamping.flags = sk->sk_tsflags;
+ v.timestamping.bind_phc = sk->sk_bind_phc;
break;
case SO_RCVTIMEO_OLD:
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 9cc9d1ee6cdb..c5c1d2b8045e 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -41,9 +41,9 @@ extern bool dccp_debug;
#define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a)
#define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a)
#else
-#define dccp_pr_debug(format, a...)
-#define dccp_pr_debug_cat(format, a...)
-#define dccp_debug(format, a...)
+#define dccp_pr_debug(format, a...) do {} while (0)
+#define dccp_pr_debug_cat(format, a...) do {} while (0)
+#define dccp_debug(format, a...) do {} while (0)
#endif
extern struct inet_hashinfo dccp_hashinfo;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 5dbd45dc35ad..dc92a67baea3 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -816,7 +816,7 @@ static int dn_auto_bind(struct socket *sock)
static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
{
struct dn_scp *scp = DN_SK(sk);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err;
if (scp->state != DN_CR)
@@ -826,11 +826,11 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk));
dn_send_conn_conf(sk, allocation);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
if (scp->state == DN_CC)
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
lock_sock(sk);
err = 0;
if (scp->state == DN_RUN)
@@ -844,9 +844,8 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
} else if (scp->state != DN_CC) {
@@ -858,7 +857,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
static int dn_wait_run(struct sock *sk, long *timeo)
{
struct dn_scp *scp = DN_SK(sk);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err = 0;
if (scp->state == DN_RUN)
@@ -867,11 +866,11 @@ static int dn_wait_run(struct sock *sk, long *timeo)
if (!*timeo)
return -EALREADY;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
if (scp->state == DN_CI || scp->state == DN_CC)
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
lock_sock(sk);
err = 0;
if (scp->state == DN_RUN)
@@ -885,9 +884,8 @@ static int dn_wait_run(struct sock *sk, long *timeo)
err = -ETIMEDOUT;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
out:
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
@@ -1032,16 +1030,16 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt)
static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sk_buff *skb = NULL;
int err = 0;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
skb = skb_dequeue(&sk->sk_receive_queue);
if (skb == NULL) {
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
skb = skb_dequeue(&sk->sk_receive_queue);
}
lock_sock(sk);
@@ -1056,9 +1054,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return skb == NULL ? ERR_PTR(err) : skb;
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ffbba1e71551..23be8e01026b 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1808,6 +1808,7 @@ void dsa_slave_setup_tagger(struct net_device *slave)
struct dsa_slave_priv *p = netdev_priv(slave);
const struct dsa_port *cpu_dp = dp->cpu_dp;
struct net_device *master = cpu_dp->master;
+ const struct dsa_switch *ds = dp->ds;
slave->needed_headroom = cpu_dp->tag_ops->needed_headroom;
slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom;
@@ -1819,6 +1820,14 @@ void dsa_slave_setup_tagger(struct net_device *slave)
slave->needed_tailroom += master->needed_tailroom;
p->xmit = cpu_dp->tag_ops->xmit;
+
+ slave->features = master->vlan_features | NETIF_F_HW_TC;
+ if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
+ slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ slave->hw_features |= NETIF_F_HW_TC;
+ slave->features |= NETIF_F_LLTX;
+ if (slave->needed_tailroom)
+ slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST);
}
static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
@@ -1881,11 +1890,6 @@ int dsa_slave_create(struct dsa_port *port)
if (slave_dev == NULL)
return -ENOMEM;
- slave_dev->features = master->vlan_features | NETIF_F_HW_TC;
- if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
- slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
- slave_dev->hw_features |= NETIF_F_HW_TC;
- slave_dev->features |= NETIF_F_LLTX;
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
if (!is_zero_ether_addr(port->mac))
ether_addr_copy(slave_dev->dev_addr, port->mac);
@@ -2287,8 +2291,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
static void
dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work)
{
+ struct switchdev_notifier_fdb_info info = {};
struct dsa_switch *ds = switchdev_work->ds;
- struct switchdev_notifier_fdb_info info;
struct dsa_port *dp;
if (!dsa_is_user_port(ds, switchdev_work->port))
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index af71b8638098..5ece05dfd8f2 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -113,11 +113,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
int err, port;
if (dst->index == info->tree_index && ds->index == info->sw_index &&
- ds->ops->port_bridge_join)
+ ds->ops->port_bridge_leave)
ds->ops->port_bridge_leave(ds, info->port, info->br);
if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
- ds->ops->crosschip_bridge_join)
+ ds->ops->crosschip_bridge_leave)
ds->ops->crosschip_bridge_leave(ds, info->tree_index,
info->sw_index, info->port,
info->br);
@@ -427,7 +427,7 @@ static int dsa_switch_lag_join(struct dsa_switch *ds,
info->port, info->lag,
info->info);
- return 0;
+ return -EOPNOTSUPP;
}
static int dsa_switch_lag_leave(struct dsa_switch *ds,
@@ -440,7 +440,7 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds,
return ds->ops->crosschip_lag_leave(ds, info->sw_index,
info->port, info->lag);
- return 0;
+ return -EOPNOTSUPP;
}
static int dsa_switch_mdb_add(struct dsa_switch *ds,
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 53565f48934c..a201ccf2435d 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -53,6 +53,9 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
u8 *tag;
u8 *addr;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
@@ -114,6 +117,9 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
u8 *addr;
u16 val;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
@@ -164,6 +170,9 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
u8 *addr;
u8 *tag;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 723c9a8a8cdf..0a19470efbfb 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o
ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \
linkstate.o debug.o wol.o features.o privflags.o rings.o \
channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
- tunnels.o fec.o eeprom.o stats.o
+ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index f9dcbad84788..c63e0739dc6a 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -4,6 +4,7 @@
#include <linux/net_tstamp.h>
#include <linux/phy.h>
#include <linux/rtnetlink.h>
+#include <linux/ptp_clock_kernel.h>
#include "common.h"
@@ -397,6 +398,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = {
[const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats",
[const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo",
[const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw",
+ [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc",
};
static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT);
@@ -554,6 +556,18 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
return 0;
}
+int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index)
+{
+ struct ethtool_ts_info info = { };
+ int num = 0;
+
+ if (!__ethtool_get_ts_info(dev, &info))
+ num = ptp_get_vclocks_index(info.phc_index, vclock_index);
+
+ return num;
+}
+EXPORT_SYMBOL(ethtool_get_phc_vclocks);
+
const struct ethtool_phy_ops *ethtool_phy_ops;
void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index a7346346114f..73e0f5b626bf 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -248,6 +248,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
[ETHTOOL_MSG_TSINFO_GET] = &ethnl_tsinfo_request_ops,
[ETHTOOL_MSG_MODULE_EEPROM_GET] = &ethnl_module_eeprom_request_ops,
[ETHTOOL_MSG_STATS_GET] = &ethnl_stats_request_ops,
+ [ETHTOOL_MSG_PHC_VCLOCKS_GET] = &ethnl_phc_vclocks_request_ops,
};
static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -958,6 +959,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
.policy = ethnl_stats_get_policy,
.maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1,
},
+ {
+ .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET,
+ .doit = ethnl_default_doit,
+ .start = ethnl_default_start,
+ .dumpit = ethnl_default_dumpit,
+ .done = ethnl_default_done,
+ .policy = ethnl_phc_vclocks_get_policy,
+ .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1,
+ },
};
static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 3e25a47fd482..3fc395c86702 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -347,6 +347,7 @@ extern const struct ethnl_request_ops ethnl_tsinfo_request_ops;
extern const struct ethnl_request_ops ethnl_fec_request_ops;
extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops;
extern const struct ethnl_request_ops ethnl_stats_request_ops;
+extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops;
extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
@@ -382,6 +383,7 @@ extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1];
extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1];
extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1];
extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1];
+extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1];
int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info);
int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c
new file mode 100644
index 000000000000..637b2f5297d5
--- /dev/null
+++ b/net/ethtool/phc_vclocks.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2021 NXP
+ */
+#include "netlink.h"
+#include "common.h"
+
+struct phc_vclocks_req_info {
+ struct ethnl_req_info base;
+};
+
+struct phc_vclocks_reply_data {
+ struct ethnl_reply_data base;
+ int num;
+ int *index;
+};
+
+#define PHC_VCLOCKS_REPDATA(__reply_base) \
+ container_of(__reply_base, struct phc_vclocks_reply_data, base)
+
+const struct nla_policy ethnl_phc_vclocks_get_policy[] = {
+ [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base,
+ struct ethnl_reply_data *reply_base,
+ struct genl_info *info)
+{
+ struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base);
+ struct net_device *dev = reply_base->dev;
+ int ret;
+
+ ret = ethnl_ops_begin(dev);
+ if (ret < 0)
+ return ret;
+ data->num = ethtool_get_phc_vclocks(dev, &data->index);
+ ethnl_ops_complete(dev);
+
+ return ret;
+}
+
+static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+ int len = 0;
+
+ if (data->num > 0) {
+ len += nla_total_size(sizeof(u32));
+ len += nla_total_size(sizeof(s32) * data->num);
+ }
+
+ return len;
+}
+
+static int phc_vclocks_fill_reply(struct sk_buff *skb,
+ const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+
+ if (data->num <= 0)
+ return 0;
+
+ if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) ||
+ nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX,
+ sizeof(s32) * data->num, data->index))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+
+ kfree(data->index);
+}
+
+const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = {
+ .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET,
+ .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY,
+ .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER,
+ .req_info_size = sizeof(struct phc_vclocks_req_info),
+ .reply_data_size = sizeof(struct phc_vclocks_reply_data),
+
+ .prepare_data = phc_vclocks_prepare_data,
+ .reply_size = phc_vclocks_reply_size,
+ .fill_reply = phc_vclocks_fill_reply,
+ .cleanup_data = phc_vclocks_cleanup_data,
+};
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a45a0401adc5..c25f7617770c 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -984,6 +984,11 @@ static const struct proto_ops ieee802154_dgram_ops = {
.sendpage = sock_no_sendpage,
};
+static void ieee802154_sock_destruct(struct sock *sk)
+{
+ skb_queue_purge(&sk->sk_receive_queue);
+}
+
/* Create a socket. Initialise the socket, blank the addresses
* set the state.
*/
@@ -1024,7 +1029,7 @@ static int ieee802154_create(struct net *net, struct socket *sock,
sock->ops = ops;
sock_init_data(sock, sk);
- /* FIXME: sk->sk_destruct */
+ sk->sk_destruct = ieee802154_sock_destruct;
sk->sk_family = PF_IEEE802154;
/* Checksums on by default */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a933bd6345b1..9fe13e4f5d08 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1376,7 +1376,7 @@ static void nl_fib_input(struct sk_buff *skb)
portid = NETLINK_CB(skb).portid; /* netlink portid */
NETLINK_CB(skb).portid = 0; /* from kernel */
NETLINK_CB(skb).dst_group = 0; /* unicast */
- netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT);
+ nlmsg_unicast(net->ipv4.fibnl, skb, portid);
}
static int __net_init nl_fib_lookup_init(struct net *net)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6b3c558a4f23..00576bae183d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t)
static void igmp_ifc_timer_expire(struct timer_list *t)
{
struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer);
+ u32 mr_ifc_count;
igmpv3_send_cr(in_dev);
- if (in_dev->mr_ifc_count) {
- in_dev->mr_ifc_count--;
+restart:
+ mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count);
+
+ if (mr_ifc_count) {
+ if (cmpxchg(&in_dev->mr_ifc_count,
+ mr_ifc_count,
+ mr_ifc_count - 1) != mr_ifc_count)
+ goto restart;
igmp_ifc_start_timer(in_dev,
unsolicited_report_interval(in_dev));
}
@@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
igmp_ifc_start_timer(in_dev, 1);
}
@@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
in_dev->mr_qri;
}
/* cancel the interface change timer */
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
/* clear deleted report items */
@@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev)
igmp_group_dropped(pmc);
#ifdef CONFIG_IP_MULTICAST
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
in_dev->mr_gq_running = 0;
@@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(pmc->interface);
@@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* else no filters; keep old mode for reports */
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(in_dev);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e65f4ef024a4..ef7897226f08 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -580,10 +580,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
nlmsg_free(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
out:
if (sk)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index f6cc26de5ed3..be75b409445c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
}
dev->needed_headroom = t_hlen + hlen;
- mtu -= t_hlen;
+ mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0);
if (mtu < IPV4_MIN_MTU)
mtu = IPV4_MIN_MTU;
@@ -348,6 +348,9 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
t_hlen = nt->hlen + sizeof(struct iphdr);
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ dev->max_mtu -= dev->hard_header_len;
+
ip_tunnel_add(itn, nt);
return nt;
@@ -387,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
- skb_reset_network_header(skb);
+ skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
@@ -489,11 +492,14 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
pkt_size = skb->len - tunnel_hlen;
+ pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
- if (df)
+ if (df) {
mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
- else
+ mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
+ } else {
mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+ }
if (skb_valid_dst(skb))
skb_dst_update_pmtu_no_confirm(skb, mtu);
@@ -972,6 +978,9 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
int max_mtu = IP_MAX_MTU - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ max_mtu -= dev->hard_header_len;
+
if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
@@ -1149,6 +1158,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
if (tb[IFLA_MTU]) {
unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
+ if (dev->type == ARPHRD_ETHER)
+ max -= dev->hard_header_len;
+
mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 7b12a40dd465..2dda856ca260 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2119,7 +2119,7 @@ int ip_mr_input(struct sk_buff *skb)
raw_rcv(mroute_sk, skb);
return 0;
}
- }
+ }
}
/* already under rcu_read_lock() */
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index 1b5b8af27aaf..ccacbde30a2c 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -119,11 +119,8 @@ static int raw_diag_dump_one(struct netlink_callback *cb,
return err;
}
- err = netlink_unicast(net->diag_nlsk, rep,
- NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
return err;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d5ab5f243640..8cb44040ec68 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1375,6 +1375,9 @@ new_segment:
}
pfrag->offset += copy;
} else {
+ if (!sk_wmem_schedule(sk, copy))
+ goto wait_for_space;
+
err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
if (err == -EMSGSIZE || err == -EEXIST) {
tcp_mark_push(tp, skb);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 6ea3dc2e4219..6274462b86b4 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -1041,7 +1041,7 @@ static void bbr_init(struct sock *sk)
bbr->prior_cwnd = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
bbr->rtt_cnt = 0;
- bbr->next_rtt_delivered = 0;
+ bbr->next_rtt_delivered = tp->delivered;
bbr->prev_ca_state = TCP_CA_Open;
bbr->packet_conservation = 0;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index f26916a62f25..d3e9386b493e 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -503,7 +503,7 @@ static int __init tcp_bpf_v4_build_proto(void)
tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot);
return 0;
}
-core_initcall(tcp_bpf_v4_build_proto);
+late_initcall(tcp_bpf_v4_build_proto);
static int tcp_bpf_assert_proto_ops(struct proto *ops)
{
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 47c32604d38f..25fa4c01a17f 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -507,8 +507,18 @@ void tcp_fastopen_active_disable(struct sock *sk)
{
struct net *net = sock_net(sk);
+ if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
+ return;
+
+ /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
+ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies);
+
+ /* Paired with smp_rmb() in tcp_fastopen_active_should_disable().
+ * We want net->ipv4.tfo_active_disable_stamp to be updated first.
+ */
+ smp_mb__before_atomic();
atomic_inc(&net->ipv4.tfo_active_disable_times);
- net->ipv4.tfo_active_disable_stamp = jiffies;
+
NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
}
@@ -519,17 +529,27 @@ void tcp_fastopen_active_disable(struct sock *sk)
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
- int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
unsigned long timeout;
+ int tfo_da_times;
int multiplier;
+ if (!tfo_bh_timeout)
+ return false;
+
+ tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
if (!tfo_da_times)
return false;
+ /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */
+ smp_rmb();
+
/* Limit timeout to max: 2^6 * initial timeout */
multiplier = 1 << min(tfo_da_times - 1, 6);
- timeout = multiplier * tfo_bh_timeout * HZ;
- if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
+
+ /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */
+ timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) +
+ multiplier * tfo_bh_timeout * HZ;
+ if (time_before(jiffies, timeout))
return true;
/* Mark check bit so we can check for successful active TFO
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e6ca5a1f3b59..149ceb5c94ff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4247,6 +4247,9 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb)
{
trace_tcp_receive_reset(sk);
+ /* mptcp can't tell us to ignore reset pkts,
+ * so just ignore the return value of mptcp_incoming_options().
+ */
if (sk_is_mptcp(sk))
mptcp_incoming_options(sk, skb);
@@ -4941,8 +4944,13 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
bool fragstolen;
int eaten;
- if (sk_is_mptcp(sk))
- mptcp_incoming_options(sk, skb);
+ /* If a subflow has been reset, the packet should not continue
+ * to be processed, drop the packet.
+ */
+ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) {
+ __kfree_skb(skb);
+ return;
+ }
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
__kfree_skb(skb);
@@ -5922,8 +5930,8 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
tp->snd_cwnd_stamp = tcp_jiffies32;
- icsk->icsk_ca_initialized = 0;
bpf_skops_established(sk, bpf_op, skb);
+ /* Initialize congestion control unless BPF initialized it already: */
if (!icsk->icsk_ca_initialized)
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
@@ -6523,8 +6531,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
case TCP_CLOSING:
case TCP_LAST_ACK:
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
- if (sk_is_mptcp(sk))
- mptcp_incoming_options(sk, skb);
+ /* If a subflow has been reset, the packet should not
+ * continue to be processed, drop the packet.
+ */
+ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb))
+ goto discard;
break;
}
fallthrough;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e66ad6bfe808..a692626c19e4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -342,7 +342,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- mtu = tcp_sk(sk)->mtu_info;
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -546,7 +546,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
if (sk->sk_state == TCP_LISTEN)
goto out;
- tp->mtu_info = info;
+ WRITE_ONCE(tp->mtu_info, info);
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
} else {
@@ -2965,7 +2965,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_comp_sack_nr = 44;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
- net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+ net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0;
atomic_set(&net->ipv4.tfo_active_disable_times, 0);
/* Reno is always built in */
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index e09147ac9a99..fc61cd3fea65 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -298,6 +298,9 @@ int tcp_gro_complete(struct sk_buff *skb)
if (th->cwr)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+ if (skb->encapsulation)
+ skb->inner_transport_header = skb->transport_header;
+
return 0;
}
EXPORT_SYMBOL(tcp_gro_complete);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bde781f46b41..29553fce8502 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1732,6 +1732,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu)
return __tcp_mtu_to_mss(sk, pmtu) -
(tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
}
+EXPORT_SYMBOL(tcp_mtu_to_mss);
/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 62682807b4b2..1a742b710e54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
const struct iphdr *iph,
struct udphdr *uh,
struct udp_table *udptable,
+ struct sock *sk,
struct sk_buff *skb, u32 info)
{
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct sock *sk;
+ struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
@@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, iph->ihl << 2);
+ if (sk) {
+ up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (lookup && lookup(sk, skb))
+ sk = NULL;
+
+ goto out;
+ }
+
sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
iph->saddr, uh->dest, skb->dev->ifindex, 0,
udptable, NULL);
if (sk) {
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
- struct udp_sock *up = udp_sk(sk);
+ up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
+out:
if (!sk)
sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
@@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
+
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
- sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udp_encap_needed_key)) {
- sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+ sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
info);
if (!sk)
return 0;
- }
+ } else
+ sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
@@ -1102,7 +1115,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
ipcm_init_sk(&ipc, inet);
- ipc.gso_size = up->gso_size;
+ ipc.gso_size = READ_ONCE(up->gso_size);
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
@@ -2695,7 +2708,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
case UDP_SEGMENT:
if (val < 0 || val > USHRT_MAX)
return -EINVAL;
- up->gso_size = val;
+ WRITE_ONCE(up->gso_size, val);
break;
case UDP_GRO:
@@ -2790,7 +2803,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
break;
case UDP_SEGMENT:
- val = up->gso_size;
+ val = READ_ONCE(up->gso_size);
break;
case UDP_GRO:
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 45b8782aec0c..9f5a5cdc38e6 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -134,7 +134,7 @@ static int __init udp_bpf_v4_build_proto(void)
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
return 0;
}
-core_initcall(udp_bpf_v4_build_proto);
+late_initcall(udp_bpf_v4_build_proto);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index b2cee9a307d4..1ed8c4d78e5c 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -77,10 +77,8 @@ static int udp_dump_one(struct udp_table *tbl,
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
if (sk)
sock_put(sk);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 54e06b88af69..1380a6b6f4ff 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -525,8 +525,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
(sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist)
- pp = call_gro_receive(udp_gro_receive_segment, head, skb);
- return pp;
+ return call_gro_receive(udp_gro_receive_segment, head, skb);
+
+ /* no GRO, be sure flush the current packet */
+ goto out;
}
if (NAPI_GRO_CB(skb)->encap_mark ||
@@ -622,6 +624,10 @@ static int udp_gro_complete_segment(struct sk_buff *skb)
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+
+ if (skb->encapsulation)
+ skb->inner_transport_header = skb->transport_header;
+
return 0;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 984050f35c61..8e6ca9ad6812 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -60,10 +60,38 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
+ unsigned int hh_len = LL_RESERVED_SPACE(dev);
+ int delta = hh_len - skb_headroom(skb);
const struct in6_addr *nexthop;
struct neighbour *neigh;
int ret;
+ /* Be paranoid, rather than too clever. */
+ if (unlikely(delta > 0) && dev->header_ops) {
+ /* pskb_expand_head() might crash, if skb is shared */
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (likely(nskb)) {
+ if (skb->sk)
+ skb_set_owner_w(nskb, skb->sk);
+ consume_skb(skb);
+ } else {
+ kfree_skb(skb);
+ }
+ skb = nskb;
+ }
+ if (skb &&
+ pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ skb = NULL;
+ }
+ if (!skb) {
+ IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+ return -ENOMEM;
+ }
+ }
+
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
@@ -479,7 +507,9 @@ int ip6_forward(struct sk_buff *skb)
if (skb_warn_if_lro(skb))
goto drop;
- if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
+ if (!net->ipv6.devconf_all->disable_policy &&
+ !idev->cnf.disable_policy &&
+ !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
@@ -519,9 +549,10 @@ int ip6_forward(struct sk_buff *skb)
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
- if (proxied > 0)
+ if (proxied > 0) {
+ hdr->hop_limit--;
return ip6_input(skb);
- else if (proxied < 0) {
+ } else if (proxied < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7b756a7dc036..b6ddf23d3833 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3769,7 +3769,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
err = PTR_ERR(rt->fib6_metrics);
/* Do not leave garbage there. */
rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
- goto out;
+ goto out_free;
}
if (cfg->fc_flags & RTF_ADDRCONF)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 578ab6305c3f..0ce52d46e4f8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -348,11 +348,20 @@ failure:
static void tcp_v6_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
+ u32 mtu;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info);
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
+
+ /* Drop requests trying to increase our current mss.
+ * Check done in __ip6_rt_update_pmtu() is too late.
+ */
+ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache)
+ return;
+
+ dst = inet6_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -433,6 +442,8 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
if (type == ICMPV6_PKT_TOOBIG) {
+ u32 mtu = ntohl(info);
+
/* We are not interested in TCP_LISTEN and open_requests
* (SYN-ACKs send out by Linux are always <576bytes so
* they should go through unfragmented).
@@ -443,7 +454,11 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!ip6_sk_accept_pmtu(sk))
goto out;
- tp->mtu_info = ntohl(info);
+ if (mtu < IPV6_MIN_MTU)
+ goto out;
+
+ WRITE_ONCE(tp->mtu_info, mtu);
+
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
@@ -540,7 +555,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
+ err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 368972dbd919..c5e15e94bb00 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
const struct ipv6hdr *hdr, int offset,
struct udphdr *uh,
struct udp_table *udptable,
+ struct sock *sk,
struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, __be32 info)
{
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct sock *sk;
+ struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
@@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, offset);
+ if (sk) {
+ up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (lookup && lookup(sk, skb))
+ sk = NULL;
+
+ goto out;
+ }
+
sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
&hdr->saddr, uh->dest,
inet6_iif(skb), 0, udptable, skb);
if (sk) {
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
- struct udp_sock *up = udp_sk(sk);
+ up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
+out:
if (!sk) {
sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
offset, info));
@@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
+
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
- sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
- udptable, skb,
+ udptable, sk, skb,
opt, type, code, info);
if (!sk)
return 0;
- }
+ } else
+ sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
@@ -1296,7 +1309,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
ipcm6_init(&ipc6);
- ipc6.gso_size = up->gso_size;
+ ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = sk->sk_tsflags;
ipc6.sockc.mark = sk->sk_mark;
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 57fa27c1cdf9..d0d280077721 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -49,7 +49,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct xfrm_state *x = dst->xfrm;
- int mtu;
+ unsigned int mtu;
bool toobig;
#ifdef CONFIG_NETFILTER
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 349c6ac3313f..e6795d5a546a 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -1635,14 +1635,16 @@ struct iucv_message_pending {
u8 iptype;
u32 ipmsgid;
u32 iptrgcls;
- union {
- u32 iprmmsg1_u32;
- u8 iprmmsg1[4];
- } ln1msg1;
- union {
- u32 ipbfln1f;
- u8 iprmmsg2[4];
- } ln1msg2;
+ struct {
+ union {
+ u32 iprmmsg1_u32;
+ u8 iprmmsg1[4];
+ } ln1msg1;
+ union {
+ u32 ipbfln1f;
+ u8 iprmmsg2[4];
+ } ln1msg2;
+ } rmmsg;
u32 res1[3];
u32 ipbfln2f;
u8 ippollfg;
@@ -1660,10 +1662,10 @@ static void iucv_message_pending(struct iucv_irq_data *data)
msg.id = imp->ipmsgid;
msg.class = imp->iptrgcls;
if (imp->ipflags1 & IUCV_IPRMDATA) {
- memcpy(msg.rmmsg, imp->ln1msg1.iprmmsg1, 8);
+ memcpy(msg.rmmsg, &imp->rmmsg, 8);
msg.length = 8;
} else
- msg.length = imp->ln1msg2.ipbfln1f;
+ msg.length = imp->rmmsg.ln1msg2.ipbfln1f;
msg.reply_size = imp->ipbfln2f;
path->handler->message_pending(path, &msg);
}
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 7180979114e4..ac5cadd02cfa 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr)
{
u8 rc = LLC_PDU_LEN_U;
- if (addr->sllc_test || addr->sllc_xid)
+ if (addr->sllc_test)
rc = LLC_PDU_LEN_U;
+ else if (addr->sllc_xid)
+ /* We need to expand header to sizeof(struct llc_xid_info)
+ * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header
+ * as XID PDU. In llc_ui_sendmsg() we reserved header size and then
+ * filled all other space with user data. If we won't reserve this
+ * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data
+ */
+ rc = LLC_PDU_LEN_U_XID;
else if (sk->sk_type == SOCK_STREAM)
rc = LLC_PDU_LEN_I;
return rc;
diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index b554f26c68ee..79d1cef8f15a 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb)
struct llc_sap_state_ev *ev = llc_sap_ev(skb);
int rc;
- llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
+ llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap,
ev->daddr.lsap, LLC_PDU_CMD);
llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 84cc7733ea66..4e6f11e63df3 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -152,6 +152,8 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
struct vif_params *params)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+ struct ieee80211_local *local = sdata->local;
+ struct sta_info *sta;
int ret;
ret = ieee80211_if_change_type(sdata, type);
@@ -162,7 +164,24 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
RCU_INIT_POINTER(sdata->u.vlan.sta, NULL);
ieee80211_check_fast_rx_iface(sdata);
} else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) {
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+
+ if (params->use_4addr == ifmgd->use_4addr)
+ return 0;
+
sdata->u.mgd.use_4addr = params->use_4addr;
+ if (!ifmgd->associated)
+ return 0;
+
+ mutex_lock(&local->sta_mtx);
+ sta = sta_info_get(sdata, ifmgd->bssid);
+ if (sta)
+ drv_sta_set_4addr(local, sdata, &sta->sta,
+ params->use_4addr);
+ mutex_unlock(&local->sta_mtx);
+
+ if (params->use_4addr)
+ ieee80211_send_4addr_nullfunc(local, sdata);
}
if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 22549b95d1aa..30ce6d2ec7ce 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2201,6 +2201,8 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t);
void ieee80211_send_nullfunc(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
bool powersave);
+void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
struct ieee80211_hdr *hdr, bool ack, u16 tx_time);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 05f4c3c72619..fcae76ddd586 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -260,6 +260,8 @@ static void ieee80211_restart_work(struct work_struct *work)
flush_work(&local->radar_detected_work);
rtnl_lock();
+ /* we might do interface manipulations, so need both */
+ wiphy_lock(local->hw.wiphy);
WARN(test_bit(SCAN_HW_SCANNING, &local->scanning),
"%s called with hardware scan in progress\n", __func__);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a00f11a33699..c0ea3b1aa9e1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1095,8 +1095,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
ieee80211_tx_skb(sdata, skb);
}
-static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
+void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
{
struct sk_buff *skb;
struct ieee80211_hdr *nullfunc;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 771921c057e8..2563473b5cf1 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -730,7 +730,8 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local,
* Need to make a copy and possibly remove radiotap header
* and FCS from the original.
*/
- skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC);
+ skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD,
+ 0, GFP_ATOMIC);
if (!skb)
return NULL;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e96981144358..8509778ff31f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1147,6 +1147,29 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
return queued;
}
+static void
+ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
+ struct sta_info *sta,
+ struct sk_buff *skb)
+{
+ struct rate_control_ref *ref = sdata->local->rate_ctrl;
+ u16 tid;
+
+ if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
+ return;
+
+ if (!sta || !sta->sta.ht_cap.ht_supported ||
+ !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
+ skb->protocol == sdata->control_port_protocol)
+ return;
+
+ tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
+ if (likely(sta->ampdu_mlme.tid_tx[tid]))
+ return;
+
+ ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
+}
+
/*
* initialises @tx
* pass %NULL for the station if unknown, a valid pointer if known
@@ -1160,6 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_hdr *hdr;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ bool aggr_check = false;
int tid;
memset(tx, 0, sizeof(*tx));
@@ -1188,8 +1212,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
} else if (tx->sdata->control_port_protocol == tx->skb->protocol) {
tx->sta = sta_info_get_bss(sdata, hdr->addr1);
}
- if (!tx->sta && !is_multicast_ether_addr(hdr->addr1))
+ if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) {
tx->sta = sta_info_get(sdata, hdr->addr1);
+ aggr_check = true;
+ }
}
if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) &&
@@ -1199,8 +1225,12 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
struct tid_ampdu_tx *tid_tx;
tid = ieee80211_get_tid(hdr);
-
tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
+ if (!tid_tx && aggr_check) {
+ ieee80211_aggr_check(sdata, tx->sta, skb);
+ tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
+ }
+
if (tid_tx) {
bool queued;
@@ -4120,29 +4150,6 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
}
EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-static void
-ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
- struct sta_info *sta,
- struct sk_buff *skb)
-{
- struct rate_control_ref *ref = sdata->local->rate_ctrl;
- u16 tid;
-
- if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
- return;
-
- if (!sta || !sta->sta.ht_cap.ht_supported ||
- !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
- skb->protocol == sdata->control_port_protocol)
- return;
-
- tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
- if (likely(sta->ampdu_mlme.tid_tx[tid]))
- return;
-
- ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
-}
-
void __ieee80211_subif_start_xmit(struct sk_buff *skb,
struct net_device *dev,
u32 info_flags,
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 52ea2517e856..ff2cc0e3273d 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -44,6 +44,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
+ SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
SNMP_MIB_SENTINEL
};
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 193466c9b549..0663cb12b448 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -37,6 +37,7 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */
MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */
MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */
+ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */
__MPTCP_MIB_MAX
};
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 8f88ddeab6a2..f48eb6315bbb 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -57,10 +57,8 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb,
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
sock_put(sk);
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index b5850afea343..7adcbc1f7d49 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -885,20 +885,16 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
return subflow->mp_capable;
}
- if (mp_opt->dss && mp_opt->use_ack) {
+ if ((mp_opt->dss && mp_opt->use_ack) ||
+ (mp_opt->add_addr && !mp_opt->echo)) {
/* subflows are fully established as soon as we get any
- * additional ack.
+ * additional ack, including ADD_ADDR.
*/
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
goto fully_established;
}
- if (mp_opt->add_addr) {
- WRITE_ONCE(msk->fully_established, true);
- return true;
- }
-
/* If the first established packet does not contain MP_CAPABLE + data
* then fallback to TCP. Fallback scenarios requires a reset for
* MP_JOIN subflows.
@@ -1035,7 +1031,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
return hmac == mp_opt->ahmac;
}
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
+/* Return false if a subflow has been reset, else return true */
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
@@ -1053,12 +1050,16 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
__mptcp_check_push(subflow->conn, sk);
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
- return;
+ return true;
}
mptcp_get_options(sk, skb, &mp_opt);
+
+ /* The subflow can be in close state only if check_fully_established()
+ * just sent a reset. If so, tell the caller to ignore the current packet.
+ */
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
- return;
+ return sk->sk_state != TCP_CLOSE;
if (mp_opt.fastclose &&
msk->local_key == mp_opt.rcvr_key) {
@@ -1100,7 +1101,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
}
if (!mp_opt.dss)
- return;
+ return true;
/* we can't wait for recvmsg() to update the ack_seq, otherwise
* monodirectional flows will stuck
@@ -1119,12 +1120,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
schedule_work(&msk->work))
sock_hold(subflow->conn);
- return;
+ return true;
}
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
- return;
+ return true;
memset(mpext, 0, sizeof(*mpext));
@@ -1153,6 +1154,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
if (mpext->csum_reqd)
mpext->csum = mp_opt.csum;
}
+
+ return true;
}
static void mptcp_set_rwin(const struct tcp_sock *tp)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index d2591ebf01d9..7b3794459783 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -27,7 +27,6 @@ struct mptcp_pm_addr_entry {
struct mptcp_addr_info addr;
u8 flags;
int ifindex;
- struct rcu_head rcu;
struct socket *lsk;
};
@@ -1136,36 +1135,12 @@ next:
return 0;
}
-struct addr_entry_release_work {
- struct rcu_work rwork;
- struct mptcp_pm_addr_entry *entry;
-};
-
-static void mptcp_pm_release_addr_entry(struct work_struct *work)
+/* caller must ensure the RCU grace period is already elapsed */
+static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
{
- struct addr_entry_release_work *w;
- struct mptcp_pm_addr_entry *entry;
-
- w = container_of(to_rcu_work(work), struct addr_entry_release_work, rwork);
- entry = w->entry;
- if (entry) {
- if (entry->lsk)
- sock_release(entry->lsk);
- kfree(entry);
- }
- kfree(w);
-}
-
-static void mptcp_pm_free_addr_entry(struct mptcp_pm_addr_entry *entry)
-{
- struct addr_entry_release_work *w;
-
- w = kmalloc(sizeof(*w), GFP_ATOMIC);
- if (w) {
- INIT_RCU_WORK(&w->rwork, mptcp_pm_release_addr_entry);
- w->entry = entry;
- queue_rcu_work(system_wq, &w->rwork);
- }
+ if (entry->lsk)
+ sock_release(entry->lsk);
+ kfree(entry);
}
static int mptcp_nl_remove_id_zero_address(struct net *net,
@@ -1245,7 +1220,8 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
spin_unlock_bh(&pernet->lock);
mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr);
- mptcp_pm_free_addr_entry(entry);
+ synchronize_rcu();
+ __mptcp_pm_release_addr_entry(entry);
return ret;
}
@@ -1298,6 +1274,7 @@ static void mptcp_nl_remove_addrs_list(struct net *net,
}
}
+/* caller must ensure the RCU grace period is already elapsed */
static void __flush_addrs(struct list_head *list)
{
while (!list_empty(list)) {
@@ -1306,7 +1283,7 @@ static void __flush_addrs(struct list_head *list)
cur = list_entry(list->next,
struct mptcp_pm_addr_entry, list);
list_del_rcu(&cur->list);
- mptcp_pm_free_addr_entry(cur);
+ __mptcp_pm_release_addr_entry(cur);
}
}
@@ -1330,6 +1307,7 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info)
bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1);
spin_unlock_bh(&pernet->lock);
mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list);
+ synchronize_rcu();
__flush_addrs(&free_list);
return 0;
}
@@ -1940,7 +1918,8 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list)
struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
/* net is removed from namespace list, can't race with
- * other modifiers
+ * other modifiers, also netns core already waited for a
+ * RCU grace period.
*/
__flush_addrs(&pernet->local_addr_list);
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7a5afa8c6866..a88924947815 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -474,7 +474,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
bool cleanup, rx_empty;
cleanup = (space > 0) && (space >= (old_space << 1));
- rx_empty = !atomic_read(&sk->sk_rmem_alloc);
+ rx_empty = !__mptcp_rmem(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -720,8 +720,10 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
+ if (__mptcp_rmem(sk) > sk_rbuf) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
return;
+ }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
@@ -1754,7 +1756,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
if (!(flags & MSG_PEEK)) {
/* we will bulk release the skb memory later */
skb->destructor = NULL;
- msk->rmem_released += skb->truesize;
+ WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
__skb_unlink(skb, &msk->receive_queue);
__kfree_skb(skb);
}
@@ -1873,7 +1875,7 @@ static void __mptcp_update_rmem(struct sock *sk)
atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, msk->rmem_released);
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
}
static void __mptcp_splice_receive_queue(struct sock *sk)
@@ -2380,7 +2382,7 @@ static int __mptcp_init_sock(struct sock *sk)
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
msk->wmem_reserved = 0;
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
msk->tx_pending_data = 0;
msk->first = NULL;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 426ed80fe72f..0f0c026c5f8b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -296,9 +296,17 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
return (struct mptcp_sock *)sk;
}
+/* the msk socket don't use the backlog, also account for the bulk
+ * free memory
+ */
+static inline int __mptcp_rmem(const struct sock *sk)
+{
+ return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
+}
+
static inline int __mptcp_space(const struct sock *sk)
{
- return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released);
+ return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
}
static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 092d1f635d27..8c03afac5ca0 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -157,19 +157,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast(ssk);
- switch (optname) {
- case SO_TIMESTAMP_OLD:
- case SO_TIMESTAMP_NEW:
- case SO_TIMESTAMPNS_OLD:
- case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, optname, !!val);
- break;
- case SO_TIMESTAMPING_NEW:
- case SO_TIMESTAMPING_OLD:
- sock_set_timestamping(sk, optname, val);
- break;
- }
-
+ sock_set_timestamp(sk, optname, !!val);
unlock_sock_fast(ssk, slow);
}
@@ -178,7 +166,8 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam
}
static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
- sockptr_t optval, unsigned int optlen)
+ sockptr_t optval,
+ unsigned int optlen)
{
int val, ret;
@@ -205,14 +194,56 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- case SO_TIMESTAMPING_OLD:
- case SO_TIMESTAMPING_NEW:
return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
}
return -ENOPROTOOPT;
}
+static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,
+ int optname,
+ sockptr_t optval,
+ unsigned int optlen)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ struct so_timestamping timestamping;
+ int ret;
+
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(&timestamping, optval,
+ sizeof(timestamping)))
+ return -EFAULT;
+ } else if (optlen == sizeof(int)) {
+ memset(&timestamping, 0, sizeof(timestamping));
+
+ if (copy_from_sockptr(&timestamping.flags, optval, sizeof(int)))
+ return -EFAULT;
+ } else {
+ return -EINVAL;
+ }
+
+ ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+ KERNEL_SOCKPTR(&timestamping),
+ sizeof(timestamping));
+ if (ret)
+ return ret;
+
+ lock_sock(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow = lock_sock_fast(ssk);
+
+ sock_set_timestamping(sk, optname, timestamping);
+ unlock_sock_fast(ssk, slow);
+ }
+
+ release_sock(sk);
+
+ return 0;
+}
+
static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
unsigned int optlen)
{
@@ -299,9 +330,12 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
+ return mptcp_setsockopt_sol_socket_int(msk, optname, optval,
+ optlen);
case SO_TIMESTAMPING_OLD:
case SO_TIMESTAMPING_NEW:
- return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
+ return mptcp_setsockopt_sol_socket_timestamping(msk, optname,
+ optval, optlen);
case SO_LINGER:
return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
case SO_RCVLOWAT:
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 66d0b1893d26..966f777d35ce 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -214,11 +214,6 @@ again:
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
- sock_put((struct sock *)subflow_req->msk);
- mptcp_token_destroy_request(req);
- tcp_request_sock_ops.destructor(req);
- subflow_req->msk = NULL;
- subflow_req->mp_join = 0;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
return -EPERM;
}
@@ -230,6 +225,8 @@ again:
if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
+ else
+ return -EPERM;
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
@@ -269,9 +266,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
return -EINVAL;
- if (mptcp_can_accept_new_subflow(subflow_req->msk))
- subflow_req->mp_join = 1;
-
+ subflow_req->mp_join = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
}
diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c
index abe0fd099746..37127781aee9 100644
--- a/net/mptcp/syncookies.c
+++ b/net/mptcp/syncookies.c
@@ -37,7 +37,21 @@ static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp
static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net)
{
- u32 i = skb_get_hash(skb) ^ net_hash_mix(net);
+ static u32 mptcp_join_hash_secret __read_mostly;
+ struct tcphdr *th = tcp_hdr(skb);
+ u32 seq, i;
+
+ net_get_random_once(&mptcp_join_hash_secret,
+ sizeof(mptcp_join_hash_secret));
+
+ if (th->syn)
+ seq = TCP_SKB_CB(skb)->seq;
+ else
+ seq = TCP_SKB_CB(skb)->seq - 1;
+
+ i = jhash_3words(seq, net_hash_mix(net),
+ (__force __u32)th->source << 16 | (__force __u32)th->dest,
+ mptcp_join_hash_secret);
return i % ARRAY_SIZE(join_entries);
}
diff --git a/net/ncsi/Kconfig b/net/ncsi/Kconfig
index 93309081f5a4..ea1dd32b6b1f 100644
--- a/net/ncsi/Kconfig
+++ b/net/ncsi/Kconfig
@@ -17,3 +17,9 @@ config NCSI_OEM_CMD_GET_MAC
help
This allows to get MAC address from NCSI firmware and set them back to
controller.
+config NCSI_OEM_CMD_KEEP_PHY
+ bool "Keep PHY Link up"
+ depends on NET_NCSI
+ help
+ This allows to keep PHY link up and prevents any channel resets during
+ the host load.
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index cbbb0de4750a..0b6cfd3b31e0 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -78,6 +78,9 @@ enum {
/* OEM Vendor Manufacture ID */
#define NCSI_OEM_MFR_MLX_ID 0x8119
#define NCSI_OEM_MFR_BCM_ID 0x113d
+#define NCSI_OEM_MFR_INTEL_ID 0x157
+/* Intel specific OEM command */
+#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */
/* Broadcom specific OEM Command */
#define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */
/* Mellanox specific OEM Command */
@@ -86,6 +89,7 @@ enum {
#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */
#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */
/* OEM Command payload lengths*/
+#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7
#define NCSI_OEM_BCM_CMD_GMA_LEN 12
#define NCSI_OEM_MLX_CMD_GMA_LEN 8
#define NCSI_OEM_MLX_CMD_SMAF_LEN 60
@@ -271,6 +275,7 @@ enum {
ncsi_dev_state_probe_mlx_gma,
ncsi_dev_state_probe_mlx_smaf,
ncsi_dev_state_probe_cis,
+ ncsi_dev_state_probe_keep_phy,
ncsi_dev_state_probe_gvi,
ncsi_dev_state_probe_gc,
ncsi_dev_state_probe_gls,
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index ca04b6df1341..89c7742cd72e 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -689,6 +689,35 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,
return 0;
}
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
+
+static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca)
+{
+ unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN];
+ int ret = 0;
+
+ nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN;
+
+ memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID);
+
+ data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY;
+
+ /* PHY Link up attribute */
+ data[6] = 0x1;
+
+ nca->data = data;
+
+ ret = ncsi_xmit_cmd(nca);
+ if (ret)
+ netdev_err(nca->ndp->ndev.dev,
+ "NCSI: Failed to transmit cmd 0x%x during configure\n",
+ nca->type);
+ return ret;
+}
+
+#endif
+
#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
/* NCSI OEM Command APIs */
@@ -700,7 +729,7 @@ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca)
nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN;
memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN);
- *(unsigned int *)data = ntohl(NCSI_OEM_MFR_BCM_ID);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID);
data[5] = NCSI_OEM_BCM_CMD_GMA;
nca->data = data;
@@ -724,7 +753,7 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca)
nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN;
memset(&u, 0, sizeof(u));
- u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID);
u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA;
u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM;
@@ -747,7 +776,7 @@ static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca)
int ret = 0;
memset(&u, 0, sizeof(u));
- u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID);
u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF;
u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM;
memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET],
@@ -1392,7 +1421,23 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
}
nd->state = ncsi_dev_state_probe_gvi;
+ if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY))
+ nd->state = ncsi_dev_state_probe_keep_phy;
+ break;
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
+ case ncsi_dev_state_probe_keep_phy:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_OEM;
+ nca.package = ndp->active_package->id;
+ nca.channel = 0;
+ ret = ncsi_oem_keep_phy_intel(&nca);
+ if (ret)
+ goto error;
+
+ nd->state = ncsi_dev_state_probe_gvi;
break;
+#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */
case ncsi_dev_state_probe_gvi:
case ncsi_dev_state_probe_gc:
case ncsi_dev_state_probe_gls:
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 888ccc2d4e34..d48374894817 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -403,7 +403,7 @@ static int ncsi_rsp_handler_ev(struct ncsi_request *nr)
/* Update to VLAN mode */
cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd);
ncm->enable = 1;
- ncm->data[0] = ntohl(cmd->mode);
+ ncm->data[0] = ntohl((__force __be32)cmd->mode);
return 0;
}
@@ -699,12 +699,19 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr)
return 0;
}
+/* Response handler for Intel card */
+static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr)
+{
+ return 0;
+}
+
static struct ncsi_rsp_oem_handler {
unsigned int mfr_id;
int (*handler)(struct ncsi_request *nr);
} ncsi_rsp_oem_handlers[] = {
{ NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx },
- { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }
+ { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm },
+ { NCSI_OEM_MFR_INTEL_ID, ncsi_rsp_handler_oem_intel }
};
/* Response handler for OEM command */
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index d1bef23fd4f5..dd30c03d5a23 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -132,8 +132,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
if (ret)
return ret;
- if (ip > ip_to)
+ if (ip > ip_to) {
+ if (ip_to == 0)
+ return -IPSET_ERR_HASH_ELEM;
swap(ip, ip_to);
+ }
} else if (tb[IPSET_ATTR_CIDR]) {
u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
@@ -144,6 +147,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
+ /* 64bit division is not allowed on 32bit */
+ if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE)
+ return -ERANGE;
+
if (retried) {
ip = ntohl(h->next.ip);
e.ip = htonl(ip);
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index 18346d18aa16..153de3457423 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -121,6 +121,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK]));
e.mark &= h->markmask;
+ if (e.mark == 0 && e.ip == 0)
+ return -IPSET_ERR_HASH_ELEM;
if (adt == IPSET_TEST ||
!(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) {
@@ -133,8 +135,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
if (ret)
return ret;
- if (ip > ip_to)
+ if (ip > ip_to) {
+ if (e.mark == 0 && ip_to == 0)
+ return -IPSET_ERR_HASH_ELEM;
swap(ip, ip_to);
+ }
} else if (tb[IPSET_ATTR_CIDR]) {
u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
@@ -143,6 +148,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
ip_set_mask_from_to(ip, ip_to, cidr);
}
+ if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE)
+ return -ERANGE;
+
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index e1ca11196515..7303138e46be 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -173,6 +173,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(port, port_to);
}
+ if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
+ return -ERANGE;
+
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index ab179e064597..334fb1ad0e86 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -180,6 +180,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(port, port_to);
}
+ if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
+ return -ERANGE;
+
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 8f075b44cf64..7df94f437f60 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -253,6 +253,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(port, port_to);
}
+ if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
+ return -ERANGE;
+
ip2_to = ip2_from;
if (tb[IPSET_ATTR_IP2_TO]) {
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index c1a11f041ac6..1422739d9aa2 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -140,7 +140,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = { .cidr = HOST_MASK };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0;
+ u32 ip = 0, ip_to = 0, ipn, n = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -188,6 +188,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
if (ip + UINT_MAX == ip_to)
return -IPSET_ERR_HASH_RANGE;
}
+ ipn = ip;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
+ n++;
+ } while (ipn++ < ip_to);
+
+ if (n > IPSET_MAX_RANGE)
+ return -ERANGE;
+
if (retried)
ip = ntohl(h->next.ip);
do {
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index ddd51c2e1cb3..9810f5bf63f5 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0;
+ u32 ip = 0, ip_to = 0, ipn, n = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -256,6 +256,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr);
}
+ ipn = ip;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
+ n++;
+ } while (ipn++ < ip_to);
+
+ if (n > IPSET_MAX_RANGE)
+ return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index 6532f0505e66..3d09eefe998a 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -168,7 +168,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
struct hash_netnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0;
- u32 ip2 = 0, ip2_from = 0, ip2_to = 0;
+ u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn;
+ u64 n = 0, m = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -244,6 +245,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
+ ipn = ip;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
+ n++;
+ } while (ipn++ < ip_to);
+ ipn = ip2_from;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
+ m++;
+ } while (ipn++ < ip2_to);
+
+ if (n*m > IPSET_MAX_RANGE)
+ return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index ec1564a1cb5a..09cf72eb37f8 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -158,7 +158,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 port, port_to, p = 0, ip = 0, ip_to = 0;
+ u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn;
+ u64 n = 0;
bool with_ports = false;
u8 cidr;
int ret;
@@ -235,6 +236,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr + 1);
}
+ ipn = ip;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr);
+ n++;
+ } while (ipn++ < ip_to);
+
+ if (n*(port_to - port + 1) > IPSET_MAX_RANGE)
+ return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip);
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 0e91d1e82f1c..19bcdb3141f6 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -182,7 +182,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
struct hash_netportnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2;
+ u32 ip2_from = 0, ip2_to = 0, ip2, ipn;
+ u64 n = 0, m = 0;
bool with_ports = false;
int ret;
@@ -284,6 +285,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
+ ipn = ip;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
+ n++;
+ } while (ipn++ < ip_to);
+ ipn = ip2_from;
+ do {
+ ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
+ m++;
+ } while (ipn++ < ip2_to);
+
+ if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE)
+ return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 96ba19fc8155..d31dbccbe7bd 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -66,22 +66,17 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash);
struct conntrack_gc_work {
struct delayed_work dwork;
- u32 last_bucket;
+ u32 next_bucket;
bool exiting;
bool early_drop;
- long next_gc_run;
};
static __read_mostly struct kmem_cache *nf_conntrack_cachep;
static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;
-/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
-#define GC_MAX_BUCKETS_DIV 128u
-/* upper bound of full table scan */
-#define GC_MAX_SCAN_JIFFIES (16u * HZ)
-/* desired ratio of entries found to be expired */
-#define GC_EVICT_RATIO 50u
+#define GC_SCAN_INTERVAL (120u * HZ)
+#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
static struct conntrack_gc_work conntrack_gc_work;
@@ -149,7 +144,15 @@ static void nf_conntrack_all_lock(void)
spin_lock(&nf_conntrack_locks_all_lock);
- nf_conntrack_locks_all = true;
+ /* For nf_contrack_locks_all, only the latest time when another
+ * CPU will see an update is controlled, by the "release" of the
+ * spin_lock below.
+ * The earliest time is not controlled, an thus KCSAN could detect
+ * a race when nf_conntract_lock() reads the variable.
+ * WRITE_ONCE() is used to ensure the compiler will not
+ * optimize the write.
+ */
+ WRITE_ONCE(nf_conntrack_locks_all, true);
for (i = 0; i < CONNTRACK_LOCKS; i++) {
spin_lock(&nf_conntrack_locks[i]);
@@ -662,8 +665,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
return false;
tstamp = nf_conn_tstamp_find(ct);
- if (tstamp && tstamp->stop == 0)
+ if (tstamp) {
+ s32 timeout = ct->timeout - nfct_time_stamp;
+
tstamp->stop = ktime_get_real_ns();
+ if (timeout < 0)
+ tstamp->stop -= jiffies_to_nsecs(-timeout);
+ }
if (nf_conntrack_event_report(IPCT_DESTROY, ct,
portid, report) < 0) {
@@ -1350,17 +1358,13 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)
static void gc_worker(struct work_struct *work)
{
- unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
- unsigned int i, goal, buckets = 0, expired_count = 0;
- unsigned int nf_conntrack_max95 = 0;
+ unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION;
+ unsigned int i, hashsz, nf_conntrack_max95 = 0;
+ unsigned long next_run = GC_SCAN_INTERVAL;
struct conntrack_gc_work *gc_work;
- unsigned int ratio, scanned = 0;
- unsigned long next_run;
-
gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
- goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;
- i = gc_work->last_bucket;
+ i = gc_work->next_bucket;
if (gc_work->early_drop)
nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;
@@ -1368,15 +1372,15 @@ static void gc_worker(struct work_struct *work)
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_head *ct_hash;
struct hlist_nulls_node *n;
- unsigned int hashsz;
struct nf_conn *tmp;
- i++;
rcu_read_lock();
nf_conntrack_get_ht(&ct_hash, &hashsz);
- if (i >= hashsz)
- i = 0;
+ if (i >= hashsz) {
+ rcu_read_unlock();
+ break;
+ }
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
struct nf_conntrack_net *cnet;
@@ -1384,7 +1388,6 @@ static void gc_worker(struct work_struct *work)
tmp = nf_ct_tuplehash_to_ctrack(h);
- scanned++;
if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
nf_ct_offload_timeout(tmp);
continue;
@@ -1392,7 +1395,6 @@ static void gc_worker(struct work_struct *work)
if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp);
- expired_count++;
continue;
}
@@ -1425,7 +1427,14 @@ static void gc_worker(struct work_struct *work)
*/
rcu_read_unlock();
cond_resched();
- } while (++buckets < goal);
+ i++;
+
+ if (time_after(jiffies, end_time) && i < hashsz) {
+ gc_work->next_bucket = i;
+ next_run = 0;
+ break;
+ }
+ } while (i < hashsz);
if (gc_work->exiting)
return;
@@ -1436,40 +1445,17 @@ static void gc_worker(struct work_struct *work)
*
* This worker is only here to reap expired entries when system went
* idle after a busy period.
- *
- * The heuristics below are supposed to balance conflicting goals:
- *
- * 1. Minimize time until we notice a stale entry
- * 2. Maximize scan intervals to not waste cycles
- *
- * Normally, expire ratio will be close to 0.
- *
- * As soon as a sizeable fraction of the entries have expired
- * increase scan frequency.
*/
- ratio = scanned ? expired_count * 100 / scanned : 0;
- if (ratio > GC_EVICT_RATIO) {
- gc_work->next_gc_run = min_interval;
- } else {
- unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;
-
- BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);
-
- gc_work->next_gc_run += min_interval;
- if (gc_work->next_gc_run > max)
- gc_work->next_gc_run = max;
+ if (next_run) {
+ gc_work->early_drop = false;
+ gc_work->next_bucket = 0;
}
-
- next_run = gc_work->next_gc_run;
- gc_work->last_bucket = i;
- gc_work->early_drop = false;
queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);
}
static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);
- gc_work->next_gc_run = HZ;
gc_work->exiting = false;
}
@@ -2457,7 +2443,6 @@ i_see_dead_people:
}
list_for_each_entry(net, net_exit_list, exit_list) {
- nf_conntrack_proto_pernet_fini(net);
nf_conntrack_ecache_pernet_fini(net);
nf_conntrack_expect_pernet_fini(net);
free_percpu(net->ct.stat);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 4e1a9dba7077..e81af33b233b 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -218,6 +218,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb,
if (!help)
return 0;
+ rcu_read_lock();
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
@@ -233,9 +234,11 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb,
nla_nest_end(skb, nest_helper);
out:
+ rcu_read_unlock();
return 0;
nla_put_failure:
+ rcu_read_unlock();
return -1;
}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 55647409a9be..8f7a9837349c 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -697,13 +697,6 @@ void nf_conntrack_proto_pernet_init(struct net *net)
#endif
}
-void nf_conntrack_proto_pernet_fini(struct net *net)
-{
-#ifdef CONFIG_NF_CT_PROTO_GRE
- nf_ct_gre_keymap_flush(net);
-#endif
-}
-
module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
&nf_conntrack_htable_size, 0600);
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index db11e403d818..728eeb0aea87 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -55,19 +55,6 @@ static inline struct nf_gre_net *gre_pernet(struct net *net)
return &net->ct.nf_ct_proto.gre;
}
-void nf_ct_gre_keymap_flush(struct net *net)
-{
- struct nf_gre_net *net_gre = gre_pernet(net);
- struct nf_ct_gre_keymap *km, *tmp;
-
- spin_lock_bh(&keymap_lock);
- list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) {
- list_del_rcu(&km->list);
- kfree_rcu(km, rcu);
- }
- spin_unlock_bh(&keymap_lock);
-}
-
static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km,
const struct nf_conntrack_tuple *t)
{
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index f7e8baf59b51..af5115e127cf 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -823,6 +823,22 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
return true;
}
+static bool tcp_can_early_drop(const struct nf_conn *ct)
+{
+ switch (ct->proto.tcp.state) {
+ case TCP_CONNTRACK_FIN_WAIT:
+ case TCP_CONNTRACK_LAST_ACK:
+ case TCP_CONNTRACK_TIME_WAIT:
+ case TCP_CONNTRACK_CLOSE:
+ case TCP_CONNTRACK_CLOSE_WAIT:
+ return true;
+ default:
+ break;
+ }
+
+ return false;
+}
+
/* Returns verdict for packet, or -1 for invalid. */
int nf_conntrack_tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
@@ -1030,10 +1046,30 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
if (index != TCP_RST_SET)
break;
- if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) {
+ /* If we are closing, tuple might have been re-used already.
+ * last_index, last_ack, and all other ct fields used for
+ * sequence/window validation are outdated in that case.
+ *
+ * As the conntrack can already be expired by GC under pressure,
+ * just skip validation checks.
+ */
+ if (tcp_can_early_drop(ct))
+ goto in_window;
+
+ /* td_maxack might be outdated if we let a SYN through earlier */
+ if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) &&
+ ct->proto.tcp.last_index != TCP_SYN_SET) {
u32 seq = ntohl(th->seq);
- if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) {
+ /* If we are not in established state and SEQ=0 this is most
+ * likely an answer to a SYN we let go through above (last_index
+ * can be updated due to out-of-order ACKs).
+ */
+ if (seq == 0 && !nf_conntrack_tcp_established(ct))
+ break;
+
+ if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) &&
+ !tn->tcp_ignore_invalid_rst) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst");
@@ -1134,6 +1170,16 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
+
+ if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) {
+ /* do not renew timeout on SYN retransmit.
+ *
+ * Else port reuse by client or NAT middlebox can keep
+ * entry alive indefinitely (including nat info).
+ */
+ return NF_ACCEPT;
+ }
+
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
@@ -1155,22 +1201,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
return NF_ACCEPT;
}
-static bool tcp_can_early_drop(const struct nf_conn *ct)
-{
- switch (ct->proto.tcp.state) {
- case TCP_CONNTRACK_FIN_WAIT:
- case TCP_CONNTRACK_LAST_ACK:
- case TCP_CONNTRACK_TIME_WAIT:
- case TCP_CONNTRACK_CLOSE:
- case TCP_CONNTRACK_CLOSE_WAIT:
- return true;
- default:
- break;
- }
-
- return false;
-}
-
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
@@ -1437,6 +1467,9 @@ void nf_conntrack_tcp_init_net(struct net *net)
*/
tn->tcp_be_liberal = 0;
+ /* If it's non-zero, we turn off RST sequence number check */
+ tn->tcp_ignore_invalid_rst = 0;
+
/* Max number of the retransmitted packets without receiving an (acceptable)
* ACK from the destination. If this number is reached, a shorter timer
* will be started.
@@ -1445,7 +1478,6 @@ void nf_conntrack_tcp_init_net(struct net *net)
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
tn->offload_timeout = 30 * HZ;
- tn->offload_pickup = 120 * HZ;
#endif
}
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 698fee49e732..f8e3c0d2602f 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -271,7 +271,6 @@ void nf_conntrack_udp_init_net(struct net *net)
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
un->offload_timeout = 30 * HZ;
- un->offload_pickup = 30 * HZ;
#endif
}
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index f57a951c9b5e..e84b499b7bfa 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -575,16 +575,15 @@ enum nf_ct_sysctl_index {
NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK,
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD,
- NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP,
#endif
NF_SYSCTL_CT_PROTO_TCP_LOOSE,
NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
+ NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST,
NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS,
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP,
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD,
- NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP,
#endif
NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP,
NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6,
@@ -775,12 +774,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = {
- .procname = "nf_flowtable_tcp_pickup",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
#endif
[NF_SYSCTL_CT_PROTO_TCP_LOOSE] = {
.procname = "nf_conntrack_tcp_loose",
@@ -798,6 +791,14 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
+ [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = {
+ .procname = "nf_conntrack_tcp_ignore_invalid_rst",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
[NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = {
.procname = "nf_conntrack_tcp_max_retrans",
.maxlen = sizeof(u8),
@@ -823,12 +824,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = {
- .procname = "nf_flowtable_udp_pickup",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
#endif
[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = {
.procname = "nf_conntrack_icmp_timeout",
@@ -1004,11 +999,11 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net,
XASSIGN(LOOSE, &tn->tcp_loose);
XASSIGN(LIBERAL, &tn->tcp_be_liberal);
XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans);
+ XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst);
#undef XASSIGN
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout;
- table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup;
#endif
}
@@ -1101,7 +1096,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED];
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout;
- table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup;
#endif
nf_conntrack_standalone_init_tcp_sysctl(net, table);
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 1e50908b1b7e..8788b519255e 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -183,7 +183,7 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
const struct nf_conntrack_l4proto *l4proto;
struct net *net = nf_ct_net(ct);
int l4num = nf_ct_protonum(ct);
- unsigned int timeout;
+ s32 timeout;
l4proto = nf_ct_l4proto_find(l4num);
if (!l4proto)
@@ -192,15 +192,20 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
if (l4num == IPPROTO_TCP) {
struct nf_tcp_net *tn = nf_tcp_pernet(net);
- timeout = tn->offload_pickup;
+ timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED];
+ timeout -= tn->offload_timeout;
} else if (l4num == IPPROTO_UDP) {
struct nf_udp_net *tn = nf_udp_pernet(net);
- timeout = tn->offload_pickup;
+ timeout = tn->timeouts[UDP_CT_REPLIED];
+ timeout -= tn->offload_timeout;
} else {
return;
}
+ if (timeout < 0)
+ timeout = 0;
+
if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
ct->timeout = nfct_time_stamp + timeout;
}
@@ -331,7 +336,11 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
void flow_offload_refresh(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
- flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+ u32 timeout;
+
+ timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+ if (READ_ONCE(flow->timeout) != timeout)
+ WRITE_ONCE(flow->timeout, timeout);
if (likely(!nf_flowtable_hw_offload(flow_table)))
return;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 390d4466567f..081437dd75b7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3446,7 +3446,8 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info,
return 0;
err_destroy_flow_rule:
- nft_flow_rule_destroy(flow);
+ if (flow)
+ nft_flow_rule_destroy(flow);
err_release_rule:
nf_tables_rule_release(&ctx, rule);
err_release_expr:
@@ -8444,6 +8445,16 @@ static int nf_tables_commit_audit_alloc(struct list_head *adl,
return 0;
}
+static void nf_tables_commit_audit_free(struct list_head *adl)
+{
+ struct nft_audit_data *adp, *adn;
+
+ list_for_each_entry_safe(adp, adn, adl, list) {
+ list_del(&adp->list);
+ kfree(adp);
+ }
+}
+
static void nf_tables_commit_audit_collect(struct list_head *adl,
struct nft_table *table, u32 op)
{
@@ -8508,6 +8519,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table);
if (ret) {
nf_tables_commit_chain_prepare_cancel(net);
+ nf_tables_commit_audit_free(&adl);
return ret;
}
if (trans->msg_type == NFT_MSG_NEWRULE ||
@@ -8517,6 +8529,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
ret = nf_tables_commit_chain_prepare(net, chain);
if (ret < 0) {
nf_tables_commit_chain_prepare_cancel(net);
+ nf_tables_commit_audit_free(&adl);
return ret;
}
}
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index 50b4e3c9347a..f554e2ea32ee 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -89,11 +89,15 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
if (!nest2)
goto cancel_nest;
- ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name);
+ ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name);
if (ret)
goto cancel_nest;
- ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name);
+ ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name);
+ if (ret)
+ goto cancel_nest;
+
+ ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family);
if (ret)
goto cancel_nest;
@@ -109,18 +113,19 @@ cancel_nest:
static int nfnl_hook_dump_one(struct sk_buff *nlskb,
const struct nfnl_dump_hook_data *ctx,
const struct nf_hook_ops *ops,
- unsigned int seq)
+ int family, unsigned int seq)
{
u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET);
unsigned int portid = NETLINK_CB(nlskb).portid;
struct nlmsghdr *nlh;
int ret = -EMSGSIZE;
+ u32 hooknum;
#ifdef CONFIG_KALLSYMS
char sym[KSYM_SYMBOL_LEN];
char *module_name;
#endif
nlh = nfnl_msg_put(nlskb, portid, seq, event,
- NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0);
+ NLM_F_MULTI, family, NFNETLINK_V0, 0);
if (!nlh)
goto nla_put_failure;
@@ -135,6 +140,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb,
if (module_name) {
char *end;
+ *module_name = '\0';
module_name += 2;
end = strchr(module_name, ']');
if (end) {
@@ -151,7 +157,12 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb,
goto nla_put_failure;
#endif
- ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum));
+ if (ops->pf == NFPROTO_INET && ops->hooknum == NF_INET_INGRESS)
+ hooknum = NF_NETDEV_INGRESS;
+ else
+ hooknum = ops->hooknum;
+
+ ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(hooknum));
if (ret)
goto nla_put_failure;
@@ -174,7 +185,9 @@ static const struct nf_hook_entries *
nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev)
{
const struct nf_hook_entries *hook_head = NULL;
+#ifdef CONFIG_NETFILTER_INGRESS
struct net_device *netdev;
+#endif
switch (pf) {
case NFPROTO_IPV4:
@@ -257,7 +270,8 @@ static int nfnl_hook_dump(struct sk_buff *nlskb,
ops = nf_hook_entries_get_hook_ops(e);
for (; i < e->num_hook_entries; i++) {
- err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq);
+ err = nfnl_hook_dump_one(nlskb, ctx, ops[i], family,
+ cb->nlh->nlmsg_seq);
if (err)
break;
}
diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c
index 913ac45167f2..304e33cbed9b 100644
--- a/net/netfilter/nft_last.c
+++ b/net/netfilter/nft_last.c
@@ -23,15 +23,21 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
{
struct nft_last_priv *priv = nft_expr_priv(expr);
u64 last_jiffies;
+ u32 last_set = 0;
int err;
- if (tb[NFTA_LAST_MSECS]) {
+ if (tb[NFTA_LAST_SET]) {
+ last_set = ntohl(nla_get_be32(tb[NFTA_LAST_SET]));
+ if (last_set == 1)
+ priv->last_set = 1;
+ }
+
+ if (last_set && tb[NFTA_LAST_MSECS]) {
err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies);
if (err < 0)
return err;
- priv->last_jiffies = jiffies + (unsigned long)last_jiffies;
- priv->last_set = 1;
+ priv->last_jiffies = jiffies - (unsigned long)last_jiffies;
}
return 0;
@@ -42,24 +48,30 @@ static void nft_last_eval(const struct nft_expr *expr,
{
struct nft_last_priv *priv = nft_expr_priv(expr);
- priv->last_jiffies = jiffies;
- priv->last_set = 1;
+ if (READ_ONCE(priv->last_jiffies) != jiffies)
+ WRITE_ONCE(priv->last_jiffies, jiffies);
+ if (READ_ONCE(priv->last_set) == 0)
+ WRITE_ONCE(priv->last_set, 1);
}
static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_last_priv *priv = nft_expr_priv(expr);
+ unsigned long last_jiffies = READ_ONCE(priv->last_jiffies);
+ u32 last_set = READ_ONCE(priv->last_set);
__be64 msecs;
- if (time_before(jiffies, priv->last_jiffies))
- priv->last_set = 0;
+ if (time_before(jiffies, last_jiffies)) {
+ WRITE_ONCE(priv->last_set, 0);
+ last_set = 0;
+ }
- if (priv->last_set)
- msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies);
+ if (last_set)
+ msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies);
else
msecs = 0;
- if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) ||
+ if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) ||
nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD))
goto nla_put_failure;
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 0840c635b752..be1595d6979d 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -201,7 +201,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
alen = sizeof_field(struct nf_nat_range, min_addr.ip6);
break;
default:
- return -EAFNOSUPPORT;
+ if (tb[NFTA_NAT_REG_ADDR_MIN])
+ return -EAFNOSUPPORT;
+ break;
}
priv->family = family;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d233ac4a91b6..380f95aacdec 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2471,7 +2471,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
nlmsg_end(skb, rep);
- netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT);
+ nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid);
}
EXPORT_SYMBOL(netlink_ack);
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index 9115f8a7dd45..a8da88db7893 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t)
is accepted() it isn't 'dead' so doesn't get removed. */
if (sock_flag(sk, SOCK_DESTROY) ||
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
- sock_hold(sk);
bh_unlock_sock(sk);
nr_destroy_socket(sk);
- sock_put(sk);
- return;
+ goto out;
}
break;
@@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t)
nr_start_heartbeat(sk);
bh_unlock_sock(sk);
+out:
+ sock_put(sk);
}
static void nr_t2timer_expiry(struct timer_list *t)
@@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t)
nr_enquiry_response(sk);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_t4timer_expiry(struct timer_list *t)
@@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t)
bh_lock_sock(sk);
nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY;
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_idletimer_expiry(struct timer_list *t)
@@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t)
sock_set_flag(sk, SOCK_DEAD);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_t1timer_expiry(struct timer_list *t)
@@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_1:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_write_internal(sk, NR_CONNREQ);
@@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_2:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_write_internal(sk, NR_DISCREQ);
@@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_3:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_requeue_frames(sk);
@@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
}
nr_start_t1timer(sk);
+out:
bh_unlock_sock(sk);
+ sock_put(sk);
}
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index e586424d8b04..9713035b89e3 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -293,14 +293,14 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
}
/**
- * Parse vlan tag from vlan header.
+ * parse_vlan_tag - Parse vlan tag from vlan header.
* @skb: skb containing frame to parse
* @key_vh: pointer to parsed vlan tag
* @untag_vlan: should the vlan header be removed from the frame
*
- * Returns ERROR on memory error.
- * Returns 0 if it encounters a non-vlan or incomplete packet.
- * Returns 1 after successfully parsing vlan tag.
+ * Return: ERROR on memory error.
+ * %0 if it encounters a non-vlan or incomplete packet.
+ * %1 after successfully parsing vlan tag.
*/
static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
bool untag_vlan)
@@ -532,6 +532,7 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key)
* L3 header
* @key: output flow key
*
+ * Return: %0 if successful, otherwise a negative errno value.
*/
static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
{
@@ -748,8 +749,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
*
* The caller must ensure that skb->len >= ETH_HLEN.
*
- * Returns 0 if successful, otherwise a negative errno value.
- *
* Initializes @skb header fields as follows:
*
* - skb->mac_header: the L2 header.
@@ -764,6 +763,8 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
*
* - skb->protocol: the type of the data starting at skb->network_header.
* Equals to key->eth.type.
+ *
+ * Return: %0 if successful, otherwise a negative errno value.
*/
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index c89c8da99f1a..d4a2db0b2299 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -670,13 +670,13 @@ static bool cmp_key(const struct sw_flow_key *key1,
{
const long *cp1 = (const long *)((const u8 *)key1 + key_start);
const long *cp2 = (const long *)((const u8 *)key2 + key_start);
- long diffs = 0;
int i;
for (i = key_start; i < key_end; i += sizeof(long))
- diffs |= *cp1++ ^ *cp2++;
+ if (*cp1++ ^ *cp2++)
+ return false;
- return diffs == 0;
+ return true;
}
static bool flow_cmp_masked_key(const struct sw_flow *flow,
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 88deb5b41429..cf2ce5812489 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -507,6 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
}
skb->dev = vport->dev;
+ skb->tstamp = 0;
vport->ops->send(skb);
return;
diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c
index fa611678af05..1dc955ca57d3 100644
--- a/net/qrtr/mhi.c
+++ b/net/qrtr/mhi.c
@@ -15,6 +15,7 @@ struct qrtr_mhi_dev {
struct qrtr_endpoint ep;
struct mhi_device *mhi_dev;
struct device *dev;
+ struct completion ready;
};
/* From MHI to QRTR */
@@ -50,6 +51,10 @@ static int qcom_mhi_qrtr_send(struct qrtr_endpoint *ep, struct sk_buff *skb)
struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep);
int rc;
+ rc = wait_for_completion_interruptible(&qdev->ready);
+ if (rc)
+ goto free_skb;
+
if (skb->sk)
sock_hold(skb->sk);
@@ -79,7 +84,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
int rc;
/* start channels */
- rc = mhi_prepare_for_transfer(mhi_dev);
+ rc = mhi_prepare_for_transfer(mhi_dev, 0);
if (rc)
return rc;
@@ -96,6 +101,15 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
if (rc)
return rc;
+ /* start channels */
+ rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS);
+ if (rc) {
+ qrtr_endpoint_unregister(&qdev->ep);
+ dev_set_drvdata(&mhi_dev->dev, NULL);
+ return rc;
+ }
+
+ complete_all(&qdev->ready);
dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n");
return 0;
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index e6f4a6202f82..171b7f3be6ef 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -518,8 +518,10 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
if (!ipc)
goto err;
- if (sock_queue_rcv_skb(&ipc->sk, skb))
+ if (sock_queue_rcv_skb(&ipc->sk, skb)) {
+ qrtr_port_put(ipc);
goto err;
+ }
qrtr_port_put(ipc);
}
@@ -839,6 +841,8 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
ipc = qrtr_port_lookup(to->sq_port);
if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */
+ if (ipc)
+ qrtr_port_put(ipc);
kfree_skb(skb);
return -ENODEV;
}
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 9b6ffff72f2d..28c1b0022178 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -131,9 +131,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
cpu_relax();
}
- ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len,
+ ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len,
&off, PAGE_SIZE);
- if (unlikely(ret != ibmr->sg_len))
+ if (unlikely(ret != ibmr->sg_dma_len))
return ret < 0 ? ret : -EINVAL;
if (cmpxchg(&frmr->fr_state,
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index a656baa321fe..1b4b3514c94f 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -322,11 +322,22 @@ err_alloc:
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
+ struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
+ struct flow_block *block;
ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
+
+ /* Remove any remaining callbacks before cleanup */
+ block = &ct_ft->nf_ft.flow_block;
+ down_write(&ct_ft->nf_ft.flow_block_lock);
+ list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
+ list_del(&block_cb->list);
+ flow_block_cb_free(block_cb);
+ }
+ up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);
module_put(THIS_MODULE);
@@ -1026,7 +1037,8 @@ do_nat:
/* This will take care of sending queued events
* even if the connection is already confirmed.
*/
- nf_conntrack_confirm(skb);
+ if (nf_conntrack_confirm(skb) != NF_ACCEPT)
+ goto drop;
}
if (!skip_add)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 7153c67f641e..2ef4cd2c848b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -273,6 +273,9 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
goto out;
}
+ /* All mirred/redirected skbs should clear previous ct info */
+ nf_reset_ct(skb2);
+
want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
expects_nh = want_ingress || !m_mac_header_xmit;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 81a1c67335be..8d17a543cc9f 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -6,6 +6,7 @@
*/
#include <linux/module.h>
+#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
@@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
tcf_lastuse_update(&d->tcf_tm);
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
+ action = READ_ONCE(d->tcf_action);
+ if (unlikely(action == TC_ACT_SHOT))
+ goto drop;
+
+ if (!skb->dev || skb->dev->type != ARPHRD_ETHER)
+ return action;
+
/* XXX: if you are going to edit more fields beyond ethernet header
* (example when you add IP header replacement or vlan swap)
* then MAX_EDIT_LEN needs to change appropriately
@@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
if (unlikely(err)) /* best policy is to drop on the floor */
goto drop;
- action = READ_ONCE(d->tcf_action);
- if (unlikely(action == TC_ACT_SHOT))
- goto drop;
-
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
if (flags & SKBMOD_F_DMAC)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d73b5c5514a9..e3e79e9bd706 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2904,7 +2904,7 @@ replay:
break;
case RTM_GETCHAIN:
err = tc_chain_notify(chain, skb, n->nlmsg_seq,
- n->nlmsg_seq, n->nlmsg_type, true);
+ n->nlmsg_flags, n->nlmsg_type, true);
if (err < 0)
NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
break;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 5b274534264c..e9a8a2c86bbd 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r,
TCA_TCINDEX_POLICE);
}
+static void tcindex_free_perfect_hash(struct tcindex_data *cp);
+
static void tcindex_partial_destroy_work(struct work_struct *work)
{
struct tcindex_data *p = container_of(to_rcu_work(work),
@@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work)
rwork);
rtnl_lock();
- kfree(p->perfect);
+ if (p->perfect)
+ tcindex_free_perfect_hash(p);
kfree(p);
rtnl_unlock();
}
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 951542843cab..28af8b1e1bb1 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -720,7 +720,7 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
skip_hash:
if (flow_override)
flow_hash = flow_override - 1;
- else if (use_skbhash)
+ else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS))
flow_hash = skb->hash;
if (host_override) {
dsthost_hash = host_override - 1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index d9ac60ffe927..a8dd06c74e31 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -913,7 +913,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
/* seqlock has the same scope of busylock, for NOLOCK qdisc */
spin_lock_init(&sch->seqlock);
- lockdep_set_class(&sch->busylock,
+ lockdep_set_class(&sch->seqlock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
seqcount_init(&sch->running);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 66fe2b82af9a..9c79374457a0 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -564,7 +564,7 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch)
/* if there's no entry, it means that the schedule didn't
* start yet, so force all gates to be open, this is in
* accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5
- * "AdminGateSates"
+ * "AdminGateStates"
*/
gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN;
@@ -1739,8 +1739,6 @@ static void taprio_attach(struct Qdisc *sch)
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
- if (ntx < dev->real_num_tx_queues)
- qdisc_hash_add(qdisc, false);
} else {
old = dev_graft_qdisc(qdisc->dev_queue, sch);
qdisc_refcount_inc(sch);
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 6f8319b828b0..db6b7373d16c 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -857,12 +857,18 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength);
cur_key->key = key;
- if (replace) {
- list_del_init(&shkey->key_list);
- sctp_auth_shkey_release(shkey);
+ if (!replace) {
+ list_add(&cur_key->key_list, sh_keys);
+ return 0;
}
+
+ list_del_init(&shkey->key_list);
+ sctp_auth_shkey_release(shkey);
list_add(&cur_key->key_list, sh_keys);
+ if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
+ sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+
return 0;
}
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 493fc01e5d2b..760b367644c1 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -284,10 +284,8 @@ static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p)
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
return err;
}
diff --git a/net/sctp/input.c b/net/sctp/input.c
index eb3c2a34a31c..5ef86fdb1176 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -1203,7 +1203,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
if (unlikely(!af))
return NULL;
- if (af->from_addr_param(&paddr, param, peer_port, 0))
+ if (!af->from_addr_param(&paddr, param, peer_port, 0))
return NULL;
return __sctp_lookup_association(net, laddr, &paddr, transportp);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e48dd909dee5..470dbdc27d58 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -100,8 +100,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
list_for_each_entry_safe(addr, temp,
&net->sctp.local_addr_list, list) {
if (addr->a.sa.sa_family == AF_INET6 &&
- ipv6_addr_equal(&addr->a.v6.sin6_addr,
- &ifa->addr)) {
+ ipv6_addr_equal(&addr->a.v6.sin6_addr,
+ &ifa->addr) &&
+ addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) {
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
found = 1;
addr->valid = 0;
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 9032ce60d50e..4dfb5ea82b05 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -104,8 +104,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
if (asoc->param_flags & SPP_PMTUD_ENABLE)
sctp_assoc_sync_pmtu(asoc);
} else if (!sctp_transport_pl_enabled(tp) &&
- !sctp_transport_pmtu_check(tp)) {
- if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ asoc->param_flags & SPP_PMTUD_ENABLE) {
+ if (!sctp_transport_pmtu_check(tp))
sctp_assoc_sync_pmtu(asoc);
}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 3c1fbf38f4f7..ec0f52567c16 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -398,7 +398,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
retval = SCTP_SCOPE_LINK;
} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
- ipv4_is_private_192(addr->v4.sin_addr.s_addr)) {
+ ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
+ ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_PRIVATE;
} else {
retval = SCTP_SCOPE_GLOBAL;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 6c08e5048d38..b8fa8f1a7277 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1163,7 +1163,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
const struct sctp_transport *transport,
__u32 probe_size)
{
- struct sctp_sender_hb_info hbinfo;
+ struct sctp_sender_hb_info hbinfo = {};
struct sctp_chunk *retval;
retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0,
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 09a8f23ec709..32df65f68c12 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1109,12 +1109,12 @@ enum sctp_disposition sctp_sf_send_probe(struct net *net,
if (!sctp_transport_pl_enabled(transport))
return SCTP_DISPOSITION_CONSUME;
- sctp_transport_pl_send(transport);
-
- reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
- if (!reply)
- return SCTP_DISPOSITION_NOMEM;
- sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ if (sctp_transport_pl_send(transport)) {
+ reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
+ if (!reply)
+ return SCTP_DISPOSITION_NOMEM;
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ }
sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE,
SCTP_TRANSPORT(transport));
@@ -1274,8 +1274,7 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net,
!sctp_transport_pl_enabled(link))
return SCTP_DISPOSITION_DISCARD;
- sctp_transport_pl_recv(link);
- if (link->pl.state == SCTP_PL_COMPLETE)
+ if (sctp_transport_pl_recv(link))
return SCTP_DISPOSITION_CONSUME;
return sctp_sf_send_probe(net, ep, asoc, type, link, commands);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index e64e01f61b11..6b937bfd4751 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4577,6 +4577,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
}
if (optlen > 0) {
+ /* Trim it to the biggest size sctp sockopt may need if necessary */
+ optlen = min_t(unsigned int, optlen,
+ PAGE_ALIGN(USHRT_MAX +
+ sizeof(__u16) * sizeof(struct sctp_reset_streams)));
kopt = memdup_sockptr(optval, optlen);
if (IS_ERR(kopt))
return PTR_ERR(kopt);
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 5f23804f21c7..a3d3ca6dd63d 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -258,16 +258,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
sctp_transport_pl_update(transport);
}
-void sctp_transport_pl_send(struct sctp_transport *t)
+bool sctp_transport_pl_send(struct sctp_transport *t)
{
- pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
- __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
-
- if (t->pl.probe_count < SCTP_MAX_PROBES) {
- t->pl.probe_count++;
- return;
- }
+ if (t->pl.probe_count < SCTP_MAX_PROBES)
+ goto out;
+ t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks;
+ t->pl.probe_count = 0;
if (t->pl.state == SCTP_PL_BASE) {
if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
@@ -299,14 +296,27 @@ void sctp_transport_pl_send(struct sctp_transport *t)
sctp_assoc_sync_pmtu(t->asoc);
}
}
- t->pl.probe_count = 1;
+
+out:
+ if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 &&
+ !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) {
+ t->pl.raise_count++;
+ return false;
+ }
+
+ pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+ __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+
+ t->pl.probe_count++;
+ return true;
}
-void sctp_transport_pl_recv(struct sctp_transport *t)
+bool sctp_transport_pl_recv(struct sctp_transport *t)
{
pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
__func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+ t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks;
t->pl.pmtu = t->pl.probe_size;
t->pl.probe_count = 0;
if (t->pl.state == SCTP_PL_BASE) {
@@ -323,7 +333,7 @@ void sctp_transport_pl_recv(struct sctp_transport *t)
if (!t->pl.probe_high) {
t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP,
SCTP_MAX_PLPMTU);
- return;
+ return false;
}
t->pl.probe_size += SCTP_PL_MIN_STEP;
if (t->pl.probe_size >= t->pl.probe_high) {
@@ -335,11 +345,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t)
t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
sctp_assoc_sync_pmtu(t->asoc);
}
- } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) {
+ } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) {
/* Raise probe_size again after 30 * interval in Search Complete */
t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
t->pl.probe_size += SCTP_PL_MIN_STEP;
}
+
+ return t->pl.state == SCTP_PL_COMPLETE;
}
static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 898389611ae8..c038efc23ce3 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -795,7 +795,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
reason_code = SMC_CLC_DECL_NOSRVLINK;
goto connect_abort;
}
- smc->conn.lnk = link;
+ smc_switch_link_and_count(&smc->conn, link);
}
/* create send buffer and rmb */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index cd0d7c908b2a..c160ff50c053 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -917,8 +917,8 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend,
return rc;
}
-static void smc_switch_link_and_count(struct smc_connection *conn,
- struct smc_link *to_lnk)
+void smc_switch_link_and_count(struct smc_connection *conn,
+ struct smc_link *to_lnk)
{
atomic_dec(&conn->lnk->conn_cnt);
conn->lnk = to_lnk;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 6d6fd1397c87..c043ecdca5c4 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -97,6 +97,7 @@ struct smc_link {
unsigned long *wr_tx_mask; /* bit mask of used indexes */
u32 wr_tx_cnt; /* number of WR send buffers */
wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */
+ atomic_t wr_tx_refcnt; /* tx refs to link */
struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */
struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */
@@ -109,6 +110,7 @@ struct smc_link {
struct ib_reg_wr wr_reg; /* WR register memory region */
wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */
+ atomic_t wr_reg_refcnt; /* reg refs to link */
enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */
u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/
@@ -444,6 +446,8 @@ void smc_core_exit(void);
int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
u8 link_idx, struct smc_init_info *ini);
void smcr_link_clear(struct smc_link *lnk, bool log);
+void smc_switch_link_and_count(struct smc_connection *conn,
+ struct smc_link *to_lnk);
int smcr_buf_map_lgr(struct smc_link *lnk);
int smcr_buf_reg_lgr(struct smc_link *lnk);
void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type);
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 273eaf1bfe49..2e7560eba981 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -888,6 +888,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry)
if (!rc)
goto out;
out_clear_lnk:
+ lnk_new->state = SMC_LNK_INACTIVE;
smcr_link_clear(lnk_new, false);
out_reject:
smc_llc_cli_add_link_reject(qentry);
@@ -1184,6 +1185,7 @@ int smc_llc_srv_add_link(struct smc_link *link)
goto out_err;
return 0;
out_err:
+ link_new->state = SMC_LNK_INACTIVE;
smcr_link_clear(link_new, false);
return rc;
}
@@ -1286,10 +1288,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr)
del_llc->reason = 0;
smc_llc_send_message(lnk, &qentry->msg); /* response */
- if (smc_link_downing(&lnk_del->state)) {
- if (smc_switch_conns(lgr, lnk_del, false))
- smc_wr_tx_wait_no_pending_sends(lnk_del);
- }
+ if (smc_link_downing(&lnk_del->state))
+ smc_switch_conns(lgr, lnk_del, false);
smcr_link_clear(lnk_del, true);
active_links = smc_llc_active_link_count(lgr);
@@ -1805,8 +1805,6 @@ void smc_llc_link_clear(struct smc_link *link, bool log)
link->smcibdev->ibdev->name, link->ibport);
complete(&link->llc_testlink_resp);
cancel_delayed_work_sync(&link->llc_testlink_wrk);
- smc_wr_wakeup_reg_wait(link);
- smc_wr_wakeup_tx_wait(link);
}
/* register a new rtoken at the remote peer (for all links) */
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 289025cd545a..c79361dfcdfb 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -496,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn,
/* Wakeup sndbuf consumers from any context (IRQ or process)
* since there is more data to transmit; usable snd_wnd as max transmit
*/
-static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
+static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{
struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
struct smc_link *link = conn->lnk;
@@ -550,6 +550,22 @@ out_unlock:
return rc;
}
+static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+ struct smc_link *link = conn->lnk;
+ int rc = -ENOLINK;
+
+ if (!link)
+ return rc;
+
+ atomic_inc(&link->wr_tx_refcnt);
+ if (smc_link_usable(link))
+ rc = _smcr_tx_sndbuf_nonempty(conn);
+ if (atomic_dec_and_test(&link->wr_tx_refcnt))
+ wake_up_all(&link->wr_tx_wait);
+ return rc;
+}
+
static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
{
struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index cbc73a7e4d59..a419e9af36b9 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -322,9 +322,12 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
if (rc)
return rc;
+ atomic_inc(&link->wr_reg_refcnt);
rc = wait_event_interruptible_timeout(link->wr_reg_wait,
(link->wr_reg_state != POSTED),
SMC_WR_REG_MR_WAIT_TIME);
+ if (atomic_dec_and_test(&link->wr_reg_refcnt))
+ wake_up_all(&link->wr_reg_wait);
if (!rc) {
/* timeout - terminate link */
smcr_link_down_cond_sched(link);
@@ -566,10 +569,15 @@ void smc_wr_free_link(struct smc_link *lnk)
return;
ibdev = lnk->smcibdev->ibdev;
+ smc_wr_wakeup_reg_wait(lnk);
+ smc_wr_wakeup_tx_wait(lnk);
+
if (smc_wr_tx_wait_no_pending_sends(lnk))
memset(lnk->wr_tx_mask, 0,
BITS_TO_LONGS(SMC_WR_BUF_CNT) *
sizeof(*lnk->wr_tx_mask));
+ wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt)));
+ wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt)));
if (lnk->wr_rx_dma_addr) {
ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr,
@@ -728,7 +736,9 @@ int smc_wr_create_link(struct smc_link *lnk)
memset(lnk->wr_tx_mask, 0,
BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask));
init_waitqueue_head(&lnk->wr_tx_wait);
+ atomic_set(&lnk->wr_tx_refcnt, 0);
init_waitqueue_head(&lnk->wr_reg_wait);
+ atomic_set(&lnk->wr_reg_refcnt, 0);
return rc;
dma_unmap:
diff --git a/net/socket.c b/net/socket.c
index bd9233da2497..0b2dad3bdf7f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -104,6 +104,7 @@
#include <linux/sockios.h>
#include <net/busy_poll.h>
#include <linux/errqueue.h>
+#include <linux/ptp_clock_kernel.h>
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
@@ -873,12 +874,18 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
empty = 0;
if (shhwtstamps &&
(sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
- !skb_is_swtx_tstamp(skb, false_tstamp) &&
- ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) {
- empty = 0;
- if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
- !skb_is_err_queue(skb))
- put_ts_pktinfo(msg, skb);
+ !skb_is_swtx_tstamp(skb, false_tstamp)) {
+ if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
+ ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc);
+
+ if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp,
+ tss.ts + 2)) {
+ empty = 0;
+
+ if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+ !skb_is_err_queue(skb))
+ put_ts_pktinfo(msg, skb);
+ }
}
if (!empty) {
if (sock_flag(sk, SOCK_TSTAMP_NEW))
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index e5c43d4d5a75..c9391d38de85 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -898,16 +898,10 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
if (unlikely(!aead))
return -ENOKEY;
- /* Cow skb data if needed */
- if (likely(!skb_cloned(skb) &&
- (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) {
- nsg = 1 + skb_shinfo(skb)->nr_frags;
- } else {
- nsg = skb_cow_data(skb, 0, &unused);
- if (unlikely(nsg < 0)) {
- pr_err("RX: skb_cow_data() returned %d\n", nsg);
- return nsg;
- }
+ nsg = skb_cow_data(skb, 0, &unused);
+ if (unlikely(nsg < 0)) {
+ pr_err("RX: skb_cow_data() returned %d\n", nsg);
+ return nsg;
}
/* Allocate memory for the AEAD operation */
diff --git a/net/tipc/link.c b/net/tipc/link.c
index cf586840caeb..1b7a487c8841 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0,
dnode, l->addr, dport, 0, 0);
if (!skb)
- return -ENOMEM;
+ return -ENOBUFS;
msg_set_dest_droppable(buf_msg(skb), true);
TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr);
skb_queue_tail(&l->wakeupq, skb);
@@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l)
*
* Consumes the buffer chain.
* Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
- * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM
+ * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
*/
int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
struct sk_buff_head *xmitq)
@@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
if (!_skb) {
kfree_skb(skb);
__skb_queue_purge(list);
- return -ENOMEM;
+ return -ENOBUFS;
}
__skb_queue_tail(transmq, skb);
tipc_link_set_skb_retransmit_time(skb, l);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 34a97ea36cc8..8754bd885169 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -158,6 +158,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack);
+static int tipc_wait_for_connect(struct socket *sock, long *timeo_p);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
@@ -1515,8 +1516,13 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
rc = 0;
}
- if (unlikely(syn && !rc))
+ if (unlikely(syn && !rc)) {
tipc_set_sk_state(sk, TIPC_CONNECTING);
+ if (dlen && timeout) {
+ timeout = msecs_to_jiffies(timeout);
+ tipc_wait_for_connect(sock, &timeout);
+ }
+ }
return rc ? rc : dlen;
}
@@ -1564,7 +1570,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
return -EMSGSIZE;
/* Handle implicit connection setup */
- if (unlikely(dest)) {
+ if (unlikely(dest && sk->sk_state == TIPC_OPEN)) {
rc = __tipc_sendmsg(sock, m, dlen);
if (dlen && dlen == rc) {
tsk->peer_caps = tipc_node_get_capabilities(net, dnode);
@@ -2646,7 +2652,7 @@ static int tipc_listen(struct socket *sock, int len)
static int tipc_wait_for_accept(struct socket *sock, long timeo)
{
struct sock *sk = sock->sk;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err;
/* True wake-one mechanism for incoming connections: only
@@ -2655,12 +2661,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
* anymore, the common case will execute the loop only once.
*/
for (;;) {
- prepare_to_wait_exclusive(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
+ add_wait_queue(sk_sleep(sk), &wait);
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -2672,7 +2678,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
if (signal_pending(current))
break;
}
- finish_wait(sk_sleep(sk), &wait);
return err;
}
@@ -2689,9 +2694,10 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
bool kern)
{
struct sock *new_sk, *sk = sock->sk;
- struct sk_buff *buf;
struct tipc_sock *new_tsock;
+ struct msghdr m = {NULL,};
struct tipc_msg *msg;
+ struct sk_buff *buf;
long timeo;
int res;
@@ -2737,19 +2743,17 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
}
/*
- * Respond to 'SYN-' by discarding it & returning 'ACK'-.
- * Respond to 'SYN+' by queuing it on new socket.
+ * Respond to 'SYN-' by discarding it & returning 'ACK'.
+ * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'.
*/
if (!msg_data_sz(msg)) {
- struct msghdr m = {NULL,};
-
tsk_advance_rx_queue(sk);
- __tipc_sendstream(new_sock, &m, 0);
} else {
__skb_dequeue(&sk->sk_receive_queue);
__skb_queue_head(&new_sk->sk_receive_queue, buf);
skb_set_owner_r(buf, new_sk);
}
+ __tipc_sendstream(new_sock, &m, 0);
release_sock(new_sk);
exit:
release_sock(sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 23c92ad15c61..ba7ced947e51 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1526,6 +1526,53 @@ out:
return err;
}
+static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+
+ /*
+ * Garbage collection of unix sockets starts by selecting a set of
+ * candidate sockets which have reference only from being in flight
+ * (total_refs == inflight_refs). This condition is checked once during
+ * the candidate collection phase, and candidates are marked as such, so
+ * that non-candidates can later be ignored. While inflight_refs is
+ * protected by unix_gc_lock, total_refs (file count) is not, hence this
+ * is an instantaneous decision.
+ *
+ * Once a candidate, however, the socket must not be reinstalled into a
+ * file descriptor while the garbage collection is in progress.
+ *
+ * If the above conditions are met, then the directed graph of
+ * candidates (*) does not change while unix_gc_lock is held.
+ *
+ * Any operations that changes the file count through file descriptors
+ * (dup, close, sendmsg) does not change the graph since candidates are
+ * not installed in fds.
+ *
+ * Dequeing a candidate via recvmsg would install it into an fd, but
+ * that takes unix_gc_lock to decrement the inflight count, so it's
+ * serialized with garbage collection.
+ *
+ * MSG_PEEK is special in that it does not change the inflight count,
+ * yet does install the socket into an fd. The following lock/unlock
+ * pair is to ensure serialization with garbage collection. It must be
+ * done between incrementing the file count and installing the file into
+ * an fd.
+ *
+ * If garbage collection starts after the barrier provided by the
+ * lock/unlock, then it will see the elevated refcount and not mark this
+ * as a candidate. If a garbage collection is already in progress
+ * before the file count was incremented, then the lock/unlock pair will
+ * ensure that garbage collection is finished before progressing to
+ * installing the fd.
+ *
+ * (*) A -> B where B is on the queue of A or B is on the queue of C
+ * which is on the queue of listening socket A.
+ */
+ spin_lock(&unix_gc_lock);
+ spin_unlock(&unix_gc_lock);
+}
+
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
@@ -2175,7 +2222,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
sk_peek_offset_fwd(sk, size);
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
}
err = (flags & MSG_TRUNC) ? skb->len - skip : size;
@@ -2418,7 +2465,7 @@ unlock:
/* It is questionable, see note in unix_dgram_recvmsg.
*/
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
sk_peek_offset_fwd(sk, chunk);
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 9ff64f9df1f3..7e7d7f45685a 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -295,10 +295,8 @@ again:
goto again;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
if (sk)
sock_put(sk);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index e0c2c992ad9c..4f7c99dfd16c 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -357,11 +357,14 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock)
static void virtio_vsock_reset_sock(struct sock *sk)
{
- lock_sock(sk);
+ /* vmci_transport.c doesn't take sk_lock here either. At least we're
+ * under vsock_table_lock so the sock cannot disappear while we're
+ * executing.
+ */
+
sk->sk_state = TCP_CLOSE;
sk->sk_err = ECONNRESET;
sk_error_report(sk);
- release_sock(sk);
}
static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 169ba8b72a63..081e7ae93cb1 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1079,6 +1079,9 @@ virtio_transport_recv_connected(struct sock *sk,
virtio_transport_recv_enqueue(vsk, pkt);
sk->sk_data_ready(sk);
return err;
+ case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
+ virtio_transport_send_credit_update(vsk);
+ break;
case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
sk->sk_write_space(sk);
break;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 50eb405b0690..16c88beea48b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2351,7 +2351,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
goto nla_put_failure;
for (band = state->band_start;
- band < NUM_NL80211_BANDS; band++) {
+ band < (state->split ?
+ NUM_NL80211_BANDS :
+ NL80211_BAND_60GHZ + 1);
+ band++) {
struct ieee80211_supported_band *sband;
/* omit higher bands for ancient software */
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index f03c7ac8e184..7897b1478c3c 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1754,16 +1754,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
* be grouped with this beacon for updates ...
*/
if (!cfg80211_combine_bsses(rdev, new)) {
- kfree(new);
+ bss_ref_put(rdev, new);
goto drop;
}
}
if (rdev->bss_entries >= bss_entries_limit &&
!cfg80211_bss_expire_oldest(rdev)) {
- if (!list_empty(&new->hidden_list))
- list_del(&new->hidden_list);
- kfree(new);
+ bss_ref_put(rdev, new);
goto drop;
}
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index a20aec9d7393..2bf269390163 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -298,8 +298,16 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
nla_for_each_attr(nla, attrs, len, remaining) {
- int err = xfrm_xlate64_attr(dst, nla);
+ int err;
+ switch (type) {
+ case XFRM_MSG_NEWSPDINFO:
+ err = xfrm_nla_cpy(dst, nla, nla_len(nla));
+ break;
+ default:
+ err = xfrm_xlate64_attr(dst, nla);
+ break;
+ }
if (err)
return err;
}
@@ -341,7 +349,8 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src
/* Calculates len of translated 64-bit message. */
static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
- struct nlattr *attrs[XFRMA_MAX+1])
+ struct nlattr *attrs[XFRMA_MAX + 1],
+ int maxtype)
{
size_t len = nlmsg_len(src);
@@ -358,10 +367,20 @@ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
case XFRM_MSG_POLEXPIRE:
len += 8;
break;
+ case XFRM_MSG_NEWSPDINFO:
+ /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+ return len;
default:
break;
}
+ /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please
+ * correct both 64=>32-bit and 32=>64-bit translators to copy
+ * new attributes.
+ */
+ if (WARN_ON_ONCE(maxtype))
+ return len;
+
if (attrs[XFRMA_SA])
len += 4;
if (attrs[XFRMA_POLICY])
@@ -440,7 +459,8 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
struct nlattr *attrs[XFRMA_MAX+1],
- size_t size, u8 type, struct netlink_ext_ack *extack)
+ size_t size, u8 type, int maxtype,
+ struct netlink_ext_ack *extack)
{
size_t pos;
int i;
@@ -520,6 +540,25 @@ static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
}
pos = dst->nlmsg_len;
+ if (maxtype) {
+ /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+ WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO);
+
+ for (i = 1; i <= maxtype; i++) {
+ int err;
+
+ if (!attrs[i])
+ continue;
+
+ /* just copy - no need for translation */
+ err = xfrm_attr_cpy32(dst, &pos, attrs[i], size,
+ nla_len(attrs[i]), nla_len(attrs[i]));
+ if (err)
+ return err;
+ }
+ return 0;
+ }
+
for (i = 1; i < XFRMA_MAX + 1; i++) {
int err;
@@ -564,7 +603,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
if (err < 0)
return ERR_PTR(err);
- len = xfrm_user_rcv_calculate_len64(h32, attrs);
+ len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype);
/* The message doesn't need translation */
if (len == nlmsg_len(h32))
return NULL;
@@ -574,7 +613,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
if (!h64)
return ERR_PTR(-ENOMEM);
- err = xfrm_xlate32(h64, h32, attrs, len, type, extack);
+ err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack);
if (err < 0) {
kvfree(h64);
return ERR_PTR(err);
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 2e8afe078d61..cb40ff0ff28d 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -241,7 +241,7 @@ static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms)
break;
}
- WARN_ON(!pos);
+ WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list));
if (--pos->users)
return;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 827d84255021..7f881f5a5897 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -155,7 +155,6 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
__read_mostly;
static struct kmem_cache *xfrm_dst_cache __ro_after_init;
-static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation;
static struct rhashtable xfrm_policy_inexact_table;
static const struct rhashtable_params xfrm_pol_inexact_params;
@@ -585,7 +584,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
return;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- write_seqcount_begin(&xfrm_policy_hash_generation);
+ write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock));
@@ -596,7 +595,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
net->xfrm.policy_bydst[dir].hmask = nhashmask;
- write_seqcount_end(&xfrm_policy_hash_generation);
+ write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
synchronize_rcu();
@@ -1245,7 +1244,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- write_seqcount_begin(&xfrm_policy_hash_generation);
+ write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
/* make sure that we can insert the indirect policies again before
* we start with destructive action.
@@ -1354,7 +1353,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
out_unlock:
__xfrm_policy_inexact_flush(net);
- write_seqcount_end(&xfrm_policy_hash_generation);
+ write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
@@ -2091,15 +2090,12 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
if (unlikely(!daddr || !saddr))
return NULL;
- retry:
- sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
rcu_read_lock();
-
- chain = policy_hash_direct(net, daddr, saddr, family, dir);
- if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
- rcu_read_unlock();
- goto retry;
- }
+ retry:
+ do {
+ sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
+ chain = policy_hash_direct(net, daddr, saddr, family, dir);
+ } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence));
ret = NULL;
hlist_for_each_entry_rcu(pol, chain, bydst) {
@@ -2130,15 +2126,11 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
}
skip_inexact:
- if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
- rcu_read_unlock();
+ if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence))
goto retry;
- }
- if (ret && !xfrm_pol_hold_rcu(ret)) {
- rcu_read_unlock();
+ if (ret && !xfrm_pol_hold_rcu(ret))
goto retry;
- }
fail:
rcu_read_unlock();
@@ -4089,6 +4081,7 @@ static int __net_init xfrm_net_init(struct net *net)
/* Initialize the per-net locks here */
spin_lock_init(&net->xfrm.xfrm_state_lock);
spin_lock_init(&net->xfrm.xfrm_policy_lock);
+ seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock);
mutex_init(&net->xfrm.xfrm_cfg_mutex);
rv = xfrm_statistics_init(net);
@@ -4133,7 +4126,6 @@ void __init xfrm_init(void)
{
register_pernet_subsys(&xfrm_net_ops);
xfrm_dev_init();
- seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex);
xfrm_input_init();
#ifdef CONFIG_XFRM_ESPINTCP
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b47d613409b7..7aff641c717d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2811,6 +2811,16 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
err = link->doit(skb, nlh, attrs);
+ /* We need to free skb allocated in xfrm_alloc_compat() before
+ * returning from this function, because consume_skb() won't take
+ * care of frag_list since netlink destructor sets
+ * sbk->head to NULL. (see netlink_skb_destructor())
+ */
+ if (skb_has_frag_list(skb)) {
+ kfree_skb(skb_shinfo(skb)->frag_list);
+ skb_shinfo(skb)->frag_list = NULL;
+ }
+
err:
kvfree(nlh64);
return err;