diff options
Diffstat (limited to 'net')
65 files changed, 595 insertions, 463 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index 4f62f299da0c..0a9019da18f3 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1623,10 +1623,6 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, } p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); - if (!count) { - p9_tag_remove(clnt, req); - return 0; - } if (non_zc) { int n = copy_to_iter(dataptr, count, to); diff --git a/net/can/af_can.c b/net/can/af_can.c index 837bb8af0ec3..cce2af10eb3e 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -304,8 +304,8 @@ static struct can_dev_rcv_lists *can_dev_rcv_lists_find(struct net *net, struct net_device *dev) { if (dev) { - struct can_ml_priv *ml_priv = dev->ml_priv; - return &ml_priv->dev_rcv_lists; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + return &can_ml->dev_rcv_lists; } else { return net->can.rx_alldev_list; } @@ -790,25 +790,6 @@ void can_proto_unregister(const struct can_proto *cp) } EXPORT_SYMBOL(can_proto_unregister); -/* af_can notifier to create/remove CAN netdevice specific structs */ -static int can_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; - - switch (msg) { - case NETDEV_REGISTER: - WARN(!dev->ml_priv, - "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); - break; - } - - return NOTIFY_DONE; -} - static int can_pernet_init(struct net *net) { spin_lock_init(&net->can.rcvlists_lock); @@ -876,11 +857,6 @@ static const struct net_proto_family can_family_ops = { .owner = THIS_MODULE, }; -/* notifier block for netdevice event */ -static struct notifier_block can_netdev_notifier __read_mostly = { - .notifier_call = can_notifier, -}; - static struct pernet_operations can_pernet_ops __read_mostly = { .init = can_pernet_init, .exit = can_pernet_exit, @@ -911,17 +887,12 @@ static __init int can_init(void) err = sock_register(&can_family_ops); if (err) goto out_sock; - err = register_netdevice_notifier(&can_netdev_notifier); - if (err) - goto out_notifier; dev_add_pack(&can_packet); dev_add_pack(&canfd_packet); return 0; -out_notifier: - sock_unregister(PF_CAN); out_sock: unregister_pernet_subsys(&can_pernet_ops); out_pernet: @@ -935,7 +906,6 @@ static __exit void can_exit(void) /* protocol unregister */ dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); - unregister_netdevice_notifier(&can_netdev_notifier); sock_unregister(PF_CAN); unregister_pernet_subsys(&can_pernet_ops); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index bb914d8b4216..da3a7a7bcff2 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -140,9 +140,9 @@ static struct j1939_priv *j1939_priv_create(struct net_device *ndev) static inline void j1939_priv_set(struct net_device *ndev, struct j1939_priv *priv) { - struct can_ml_priv *can_ml_priv = ndev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); - can_ml_priv->j1939_priv = priv; + can_ml->j1939_priv = priv; } static void __j1939_priv_release(struct kref *kref) @@ -211,12 +211,9 @@ static void __j1939_rx_release(struct kref *kref) /* get pointer to priv without increasing ref counter */ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { - struct can_ml_priv *can_ml_priv = ndev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); - if (!can_ml_priv) - return NULL; - - return can_ml_priv->j1939_priv; + return can_ml->j1939_priv; } static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) @@ -225,9 +222,6 @@ static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) lockdep_assert_held(&j1939_netdev_lock); - if (ndev->type != ARPHRD_CAN) - return NULL; - priv = j1939_ndev_to_priv(ndev); if (priv) j1939_priv_get(priv); @@ -348,15 +342,16 @@ static int j1939_netdev_notify(struct notifier_block *nb, unsigned long msg, void *data) { struct net_device *ndev = netdev_notifier_info_to_dev(data); + struct can_ml_priv *can_ml = can_get_ml_priv(ndev); struct j1939_priv *priv; + if (!can_ml) + goto notify_done; + priv = j1939_priv_get_by_ndev(ndev); if (!priv) goto notify_done; - if (ndev->type != ARPHRD_CAN) - goto notify_put; - switch (msg) { case NETDEV_DOWN: j1939_cancel_active_session(priv, NULL); @@ -365,7 +360,6 @@ static int j1939_netdev_notify(struct notifier_block *nb, break; } -notify_put: j1939_priv_put(priv); notify_done: diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index f23966526a88..56aa66147d5a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/can/can-ml.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/errqueue.h> @@ -453,6 +454,7 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) j1939_jsk_del(priv, jsk); j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); } else { + struct can_ml_priv *can_ml; struct net_device *ndev; ndev = dev_get_by_index(net, addr->can_ifindex); @@ -461,15 +463,8 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } - if (ndev->type != ARPHRD_CAN) { - dev_put(ndev); - ret = -ENODEV; - goto out_release_sock; - } - - if (!ndev->ml_priv) { - netdev_warn_once(ndev, - "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + can_ml = can_get_ml_priv(ndev); + if (!can_ml) { dev_put(ndev); ret = -ENODEV; goto out_release_sock; diff --git a/net/can/proc.c b/net/can/proc.c index 5ea8695f507e..b15760b5c1cc 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -322,8 +322,11 @@ static int can_rcvlist_proc_show(struct seq_file *m, void *v) /* receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) - can_rcvlist_proc_show_one(m, idx, dev, dev->ml_priv); + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) + can_rcvlist_proc_show_one(m, idx, dev, + &can_ml->dev_rcv_lists); } rcu_read_unlock(); @@ -375,8 +378,10 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) /* sff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - dev_rcv_lists = dev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) { + dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); } @@ -406,8 +411,10 @@ static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) /* eff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { - if (dev->type == ARPHRD_CAN && dev->ml_priv) { - dev_rcv_lists = dev->ml_priv; + struct can_ml_priv *can_ml = can_get_ml_priv(dev); + + if (can_ml) { + dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 271287c5ec12..97d6ea763e32 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -252,7 +252,6 @@ static int parse_fsid(const char *str, struct ceph_fsid *fsid) * ceph options */ enum { - Opt_osdtimeout, Opt_osdkeepalivetimeout, Opt_mount_timeout, Opt_osd_idle_ttl, @@ -307,7 +306,8 @@ static const struct constant_table ceph_param_ms_mode[] = { static const struct fs_parameter_spec ceph_parameters[] = { fsparam_flag ("abort_on_full", Opt_abort_on_full), - fsparam_flag_no ("cephx_require_signatures", Opt_cephx_require_signatures), + __fsparam (NULL, "cephx_require_signatures", Opt_cephx_require_signatures, + fs_param_neg_with_no|fs_param_deprecated, NULL), fsparam_flag_no ("cephx_sign_messages", Opt_cephx_sign_messages), fsparam_flag_no ("crc", Opt_crc), fsparam_string ("crush_location", Opt_crush_location), @@ -319,8 +319,6 @@ static const struct fs_parameter_spec ceph_parameters[] = { fsparam_u32 ("osd_idle_ttl", Opt_osd_idle_ttl), fsparam_u32 ("osd_request_timeout", Opt_osd_request_timeout), fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout), - __fsparam (fs_param_is_s32, "osdtimeout", Opt_osdtimeout, - fs_param_deprecated, NULL), fsparam_enum ("read_from_replica", Opt_read_from_replica, ceph_param_read_from_replica), fsparam_enum ("ms_mode", Opt_ms_mode, @@ -552,9 +550,6 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, } break; - case Opt_osdtimeout: - warn_plog(&log, "Ignoring osdtimeout"); - break; case Opt_osdkeepalivetimeout: /* 0 isn't well defined right now, reject it */ if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) @@ -596,9 +591,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, break; case Opt_cephx_require_signatures: if (!result.negated) - opt->flags &= ~CEPH_OPT_NOMSGAUTH; + warn_plog(&log, "Ignoring cephx_require_signatures"); else - opt->flags |= CEPH_OPT_NOMSGAUTH; + warn_plog(&log, "Ignoring nocephx_require_signatures, use nocephx_sign_messages"); break; case Opt_cephx_sign_messages: if (!result.negated) @@ -686,8 +681,6 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, seq_puts(m, "noshare,"); if (opt->flags & CEPH_OPT_NOCRC) seq_puts(m, "nocrc,"); - if (opt->flags & CEPH_OPT_NOMSGAUTH) - seq_puts(m, "nocephx_require_signatures,"); if (opt->flags & CEPH_OPT_NOMSGSIGN) seq_puts(m, "nocephx_sign_messages,"); if ((opt->flags & CEPH_OPT_TCP_NODELAY) == 0) @@ -756,7 +749,7 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT; client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT; - if (!ceph_test_opt(client, NOMSGAUTH)) + if (!ceph_test_opt(client, NOMSGSIGN)) client->required_features |= CEPH_FEATURE_MSG_AUTH; /* msgr */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0edc0b2baaa4..1bdcb33fb561 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2147,7 +2147,7 @@ out: out_err: cb->args[1] = idx; cb->args[0] = h; - cb->seq = net->dev_base_seq; + cb->seq = tgt_net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); if (netnsid >= 0) put_net(tgt_net); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 545a472273a5..c421c8f80925 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3659,6 +3659,8 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, struct ts_state state; unsigned int ret; + BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb)); + config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index a45572cfb71a..58b8fc82cd3c 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,6 +9,7 @@ menuconfig NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n + depends on HSR || HSR=n select GRO_CELLS select NET_SWITCHDEV select PHYLINK @@ -117,6 +118,8 @@ config NET_DSA_TAG_OCELOT config NET_DSA_TAG_OCELOT_8021Q tristate "Tag driver for Ocelot family of switches, using VLAN" + depends on MSCC_OCELOT_SWITCH_LIB || \ + (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) select NET_DSA_TAG_8021Q help Say Y or M if you want to enable support for tagging frames with a diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2eeaa42f2e08..9d4b0e9b1aa1 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -230,8 +230,8 @@ int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; -static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, - struct net_device *dev) +static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, + struct net_device *dev) { /* Switchdev offloading can be configured on: */ @@ -241,12 +241,6 @@ static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, */ return true; - if (dp->bridge_dev == dev) - /* DSA ports connected to a bridge, and event was emitted - * for the bridge. - */ - return true; - if (dp->lag_dev == dev) /* DSA ports connected to a bridge via a LAG */ return true; @@ -254,14 +248,23 @@ static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, return false; } +static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, + struct net_device *bridge_dev) +{ + /* DSA ports connected to a bridge, and event was emitted + * for the bridge. + */ + return dp->bridge_dev == bridge_dev; +} + /* Returns true if any port of this tree offloads the given net_device */ -static inline bool dsa_tree_offloads_netdev(struct dsa_switch_tree *dst, - struct net_device *dev) +static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, + struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_offloads_netdev(dp, dev)) + if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 491e3761b5f4..992fcab4b552 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -278,28 +278,43 @@ static int dsa_slave_port_attr_set(struct net_device *dev, struct dsa_port *dp = dsa_slave_to_port(dev); int ret; - if (!dsa_port_offloads_netdev(dp, attr->orig_dev)) - return -EOPNOTSUPP; - switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_set_state(dp, attr->u.stp_state); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: + if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + return -EOPNOTSUPP; + ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack); break; default: @@ -341,9 +356,6 @@ static int dsa_slave_vlan_add(struct net_device *dev, struct switchdev_obj_port_vlan vlan; int err; - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) - return -EOPNOTSUPP; - if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; @@ -391,27 +403,36 @@ static int dsa_slave_port_obj_add(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + return -EOPNOTSUPP; + /* DSA can directly translate this to a normal MDB add, * but on the CPU port. */ err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_slave_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; @@ -431,9 +452,6 @@ static int dsa_slave_vlan_del(struct net_device *dev, struct switchdev_obj_port_vlan *vlan; int err; - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) - return -EOPNOTSUPP; - if (dsa_port_skip_vlan_configuration(dp)) return 0; @@ -459,27 +477,36 @@ static int dsa_slave_port_obj_del(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + return -EOPNOTSUPP; + /* DSA can directly translate this to a normal MDB add, * but on the CPU port. */ err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_slave_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: - if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; + err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; @@ -2298,7 +2325,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, * other ports bridged with the LAG should be able to * autonomously forward towards it. */ - if (dsa_tree_offloads_netdev(dp->ds->dst, dev)) + if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev)) return NOTIFY_DONE; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 38dcdded74c0..59748487664f 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -13,6 +13,7 @@ #define MTK_HDR_LEN 4 #define MTK_HDR_XMIT_UNTAGGED 0 #define MTK_HDR_XMIT_TAGGED_TPID_8100 1 +#define MTK_HDR_XMIT_TAGGED_TPID_88A8 2 #define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) #define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0) #define MTK_HDR_XMIT_SA_DIS BIT(6) @@ -21,8 +22,8 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); + u8 xmit_tpid; u8 *mtk_tag; - bool is_vlan_skb = true; unsigned char *dest = eth_hdr(skb)->h_dest; bool is_multicast_skb = is_multicast_ether_addr(dest) && !is_broadcast_ether_addr(dest); @@ -33,10 +34,17 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, * the both special and VLAN tag at the same time and then look up VLAN * table with VID. */ - if (!skb_vlan_tagged(skb)) { + switch (skb->protocol) { + case htons(ETH_P_8021Q): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_8100; + break; + case htons(ETH_P_8021AD): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_88A8; + break; + default: + xmit_tpid = MTK_HDR_XMIT_UNTAGGED; skb_push(skb, MTK_HDR_LEN); memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); - is_vlan_skb = false; } mtk_tag = skb->data + 2 * ETH_ALEN; @@ -44,8 +52,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, /* Mark tag attribute on special tag insertion to notify hardware * whether that's a combined special tag with 802.1Q header. */ - mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 : - MTK_HDR_XMIT_UNTAGGED; + mtk_tag[0] = xmit_tpid; mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; /* Disable SA learning for multicast frames */ @@ -53,7 +60,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS; /* Tag control information is kept for 802.1Q */ - if (!is_vlan_skb) { + if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) { mtk_tag[2] = 0; mtk_tag[3] = 0; } diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index c17d39b4a1a0..e9176475bac8 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -35,14 +35,12 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); + __be16 *p; u8 *tag; - u16 *p; u16 out; /* Pad out to at least 60 bytes */ - if (unlikely(eth_skb_pad(skb))) - return NULL; - if (skb_cow_head(skb, RTL4_A_HDR_LEN) < 0) + if (unlikely(__skb_put_padto(skb, ETH_ZLEN, false))) return NULL; netdev_dbg(dev, "add realtek tag to package to port %d\n", @@ -53,13 +51,13 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, tag = skb->data + 2 * ETH_ALEN; /* Set Ethertype */ - p = (u16 *)tag; + p = (__be16 *)tag; *p = htons(RTL4_A_ETHERTYPE); out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8); - /* The lower bits is the port numer */ + /* The lower bits is the port number */ out |= (u8)dp->index; - p = (u16 *)(tag + 2); + p = (__be16 *)(tag + 2); *p = htons(out); return skb; diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 25a9e566ef5c..6a070dc8e4b0 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -116,10 +116,9 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) struct ethtool_channels channels = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; - const struct nlattr *err_attr; + u32 err_attr, max_rx_in_use = 0; const struct ethtool_ops *ops; struct net_device *dev; - u32 max_rx_in_use = 0; int ret; ret = ethnl_parse_header_dev_get(&req_info, @@ -157,34 +156,35 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) /* ensure new channel counts are within limits */ if (channels.rx_count > channels.max_rx) - err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (channels.tx_count > channels.max_tx) - err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else if (channels.other_count > channels.max_other) - err_attr = tb[ETHTOOL_A_CHANNELS_OTHER_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT; else if (channels.combined_count > channels.max_combined) - err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; else - err_attr = NULL; + err_attr = 0; if (err_attr) { ret = -EINVAL; - NL_SET_ERR_MSG_ATTR(info->extack, err_attr, + NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel count exceeds maximum"); goto out_ops; } /* ensure there is at least one RX and one TX channel */ if (!channels.combined_count && !channels.rx_count) - err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (!channels.combined_count && !channels.tx_count) - err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else - err_attr = NULL; + err_attr = 0; if (err_attr) { if (mod_combined) - err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT]; + err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; ret = -EINVAL; - NL_SET_ERR_MSG_ATTR(info->extack, err_attr, "requested channel counts would result in no RX or TX channel being configured"); + NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], + "requested channel counts would result in no RX or TX channel being configured"); goto out_ops; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index f9a8cc82ae2e..bb1351c38397 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -164,8 +164,10 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; - for (i = 0; i < HSR_PT_PORTS; i++) + for (i = 0; i < HSR_PT_PORTS; i++) { new_node->time_in[i] = now; + new_node->time_out[i] = now; + } for (i = 0; i < HSR_PT_PORTS; i++) new_node->seq_out[i] = seq_out; @@ -413,9 +415,12 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr) { - if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type])) + if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) && + time_is_after_jiffies(node->time_out[port->type] + + msecs_to_jiffies(HSR_ENTRY_FORGET_TIME))) return 1; + node->time_out[port->type] = jiffies; node->seq_out[port->type] = sequence_nr; return 0; } diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 86b43f539f2c..d9628e7a5f05 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -75,6 +75,7 @@ struct hsr_node { enum hsr_port_type addr_B_port; unsigned long time_in[HSR_PT_PORTS]; bool time_in_stale[HSR_PT_PORTS]; + unsigned long time_out[HSR_PT_PORTS]; /* if the node is a SAN */ bool san_a; bool san_b; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index a169808ee78a..8f264672b70b 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -22,6 +22,7 @@ #define HSR_LIFE_CHECK_INTERVAL 2000 /* ms */ #define HSR_NODE_FORGET_TIME 60000 /* ms */ #define HSR_ANNOUNCE_INTERVAL 100 /* ms */ +#define HSR_ENTRY_FORGET_TIME 400 /* ms */ /* By how much may slave1 and slave2 timestamps of latest received frame from * each node differ before we notify of communication problem? diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a02ce89b56b5..1355e6c0d567 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1021,7 +1021,6 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 471d33a0d095..bfaf327e9d12 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -519,16 +519,10 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&cipso_v4_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&cipso_v4_doi_list_lock); - cipso_v4_cache_invalidate(); - call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu); + cipso_v4_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -585,9 +579,6 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&cipso_v4_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&cipso_v4_doi_list_lock); cipso_v4_cache_invalidate(); call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu); @@ -1162,7 +1153,7 @@ static void cipso_v4_gentag_hdr(const struct cipso_v4_doi *doi_def, { buf[0] = IPOPT_CIPSO; buf[1] = CIPSO_V4_HDR_LEN + len; - *(__be32 *)&buf[2] = htonl(doi_def->doi); + put_unaligned_be32(doi_def->doi, &buf[2]); } /** diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 396b492c804f..616e2dc1c8fa 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -775,13 +775,14 @@ EXPORT_SYMBOL(__icmp_send); void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct sk_buff *cloned_skb = NULL; + struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; struct nf_conn *ct; __be32 orig_ip; ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); return; } @@ -796,7 +797,7 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) orig_ip = ip_hdr(skb_in)->saddr; ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; - icmp_send(skb_in, type, code, info); + __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index ff327a62c9ce..da21dfce24d7 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(inet_peer_base_init); #define PEER_MAX_GC 32 /* Exported for sysctl_net_ipv4. */ -int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more +int inet_peer_threshold __read_mostly; /* start to throw entries more * aggressively at this stage */ int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */ @@ -73,20 +73,13 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min /* Called from ip_output.c:ip_init */ void __init inet_initpeers(void) { - struct sysinfo si; + u64 nr_entries; - /* Use the straight interface to information about memory. */ - si_meminfo(&si); - /* The values below were suggested by Alexey Kuznetsov - * <kuznet@ms2.inr.ac.ru>. I don't have any opinion about the values - * myself. --SAW - */ - if (si.totalram <= (32768*1024)/PAGE_SIZE) - inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */ - if (si.totalram <= (16384*1024)/PAGE_SIZE) - inet_peer_threshold >>= 1; /* about 512KB */ - if (si.totalram <= (8192*1024)/PAGE_SIZE) - inet_peer_threshold >>= 2; /* about 128KB */ + /* 1% of physical memory */ + nr_entries = div64_ul((u64)totalram_pages() << PAGE_SHIFT, + 100 * L1_CACHE_ALIGN(sizeof(struct inet_peer))); + + inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128); peer_cachep = kmem_cache_create("inet_peer_cache", sizeof(struct inet_peer), diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 76a420c76f16..f6cc26de5ed3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -502,8 +502,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, if (!skb_is_gso(skb) && (inner_iph->frag_off & htons(IP_DF)) && mtu < pkt_size) { - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; } } @@ -527,7 +526,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU && mtu < pkt_size) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -E2BIG; } } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index abc171e79d3e..eb207089ece0 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -238,13 +238,13 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } else { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } dst_release(dst); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f1c6cbdb9e43..743777bce179 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1399,7 +1399,7 @@ out: /* rtnl */ /* remove all nexthops tied to a device being deleted */ -static void nexthop_flush_dev(struct net_device *dev) +static void nexthop_flush_dev(struct net_device *dev, unsigned long event) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); @@ -1411,6 +1411,10 @@ static void nexthop_flush_dev(struct net_device *dev) if (nhi->fib_nhc.nhc_dev != dev) continue; + if (nhi->reject_nh && + (event == NETDEV_DOWN || event == NETDEV_CHANGE)) + continue; + remove_nexthop(net, nhi->nh_parent, NULL); } } @@ -2189,11 +2193,11 @@ static int nh_netdev_event(struct notifier_block *this, switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: - nexthop_flush_dev(dev); + nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) - nexthop_flush_dev(dev); + nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: info_ext = ptr; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a3422e42784e..de7cc8445ac0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3469,16 +3469,23 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_QUEUE_SEQ: - if (sk->sk_state != TCP_CLOSE) + if (sk->sk_state != TCP_CLOSE) { err = -EPERM; - else if (tp->repair_queue == TCP_SEND_QUEUE) - WRITE_ONCE(tp->write_seq, val); - else if (tp->repair_queue == TCP_RECV_QUEUE) { - WRITE_ONCE(tp->rcv_nxt, val); - WRITE_ONCE(tp->copied_seq, val); - } - else + } else if (tp->repair_queue == TCP_SEND_QUEUE) { + if (!tcp_rtx_queue_empty(sk)) + err = -EPERM; + else + WRITE_ONCE(tp->write_seq, val); + } else if (tp->repair_queue == TCP_RECV_QUEUE) { + if (tp->rcv_nxt != tp->copied_seq) { + err = -EPERM; + } else { + WRITE_ONCE(tp->rcv_nxt, val); + WRITE_ONCE(tp->copied_seq, val); + } + } else { err = -EINVAL; + } break; case TCP_REPAIR_OPTIONS: @@ -4143,7 +4150,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - if (len < offsetofend(struct tcp_zerocopy_receive, length)) + if (len < 0 || + len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_user(optval + sizeof(zc), diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b76c48efd37e..c5b4b586570f 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -526,7 +526,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, } if (!sk || NAPI_GRO_CB(skb)->encap_mark || - (skb->ip_summed != CHECKSUM_PARTIAL && + (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid) || !udp_sk(sk)->gro_receive) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 1fb75f01756c..802f5111805a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -665,7 +665,6 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 51184a70ac7e..1578ed9e97d8 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -83,6 +83,9 @@ struct calipso_map_cache_entry { static struct calipso_map_cache_bkt *calipso_cache; +static void calipso_cache_invalidate(void); +static void calipso_doi_putdef(struct calipso_doi *doi_def); + /* Label Mapping Cache Functions */ @@ -444,15 +447,10 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&calipso_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&calipso_doi_list_lock); - call_rcu(&doi_def->rcu, calipso_doi_free_rcu); + calipso_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -508,10 +506,8 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&calipso_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&calipso_doi_list_lock); + calipso_cache_invalidate(); call_rcu(&doi_def->rcu, calipso_doi_free_rcu); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f3d05866692e..fd1f896115c1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -331,10 +331,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st } #if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -351,7 +350,7 @@ static void mip6_addr_swap(struct sk_buff *skb) } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -446,7 +445,8 @@ static int icmp6_iif(const struct sk_buff *skb) * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -542,7 +542,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) goto out_bh_enable; - mip6_addr_swap(skb); + mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) @@ -559,7 +559,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, /* select a more meaningful saddr from input if */ struct net_device *in_netdev; - in_netdev = dev_get_by_index(net, IP6CB(skb)->iif); + in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, @@ -640,7 +640,7 @@ EXPORT_SYMBOL(icmp6_send); */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); } @@ -697,10 +697,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c3bc89b6b1a1..1baf43aacb2e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -678,8 +678,8 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); return -1; } *encap_limit = tel->encap_limit - 1; @@ -805,8 +805,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); return -1; } @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) &mtu, skb->protocol); if (err != 0) { if (err == -EMSGSIZE) - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -1; } @@ -1063,10 +1063,10 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) { if (skb->protocol == htons(ETH_P_IP)) - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); else - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } goto tx_err; diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 70c8c2f36c98..9e3574880cb0 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) } EXPORT_SYMBOL(inet6_unregister_icmp_sender); -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send; rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); if (send) - send(skb, type, code, info, NULL); + send(skb, type, code, info, NULL, parm); rcu_read_unlock(); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(__icmpv6_send); #endif #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { + struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; struct in6_addr orig_ip; @@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); return; } @@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) orig_ip = ipv6_hdr(skb_in)->saddr; ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a7950baa05e5..3fa0eca5a06f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1332,8 +1332,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, tel = (void *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; @@ -1385,11 +1385,11 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, if (err == -EMSGSIZE) switch (protocol) { case IPPROTO_IPIP: - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); break; case IPPROTO_IPV6: - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); break; default: break; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0225fd694192..f10e7a72ea62 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -521,10 +521,10 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } err = -EMSGSIZE; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 93636867aee2..63ccd9f2dccc 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -987,7 +987,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 7be5103ff2a8..203890e378cb 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -649,9 +649,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, - session->session_id); + pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } @@ -702,8 +702,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -718,8 +718,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -809,9 +809,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - pr_warn_ratelimited("%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); - goto error; + pr_debug_ratelimited("%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); + goto invalid; } /* Point to L2TP header */ @@ -824,9 +824,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto error; + pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); + goto invalid; } /* Get length of L2TP packet */ @@ -834,7 +834,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) - goto error; + goto pass; /* Skip flags */ ptr += 2; @@ -863,21 +863,24 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); - goto error; + pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); + goto pass; } if (tunnel->version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) - goto error; + goto invalid; l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); return 0; -error: +invalid: + atomic_long_inc(&tunnel->stats.rx_invalid); + +pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index cb21d906343e..98ea98eb9567 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -39,6 +39,7 @@ struct l2tp_stats { atomic_long_t rx_oos_packets; atomic_long_t rx_errors; atomic_long_t rx_cookie_discards; + atomic_long_t rx_invalid; }; struct l2tp_tunnel; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 83956c9ee1fc..96eb91be9238 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -428,6 +428,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla L2TP_ATTR_STATS_PAD) || nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS, atomic_long_read(&tunnel->stats.rx_errors), + L2TP_ATTR_STATS_PAD) || + nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID, + atomic_long_read(&tunnel->stats.rx_invalid), L2TP_ATTR_STATS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); @@ -771,6 +774,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl L2TP_ATTR_STATS_PAD) || nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS, atomic_long_read(&session->stats.rx_errors), + L2TP_ATTR_STATS_PAD) || + nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID, + atomic_long_read(&session->stats.rx_invalid), L2TP_ATTR_STATS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index b1690149b6fa..1482259de9b5 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -14,6 +14,7 @@ #include <linux/netdev_features.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/mpls.h> static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -27,6 +28,8 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); + if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) + goto out; if (unlikely(!pskb_may_pull(skb, mpls_hlen))) goto out; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b63574d6b812..444a38681e93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -411,6 +411,7 @@ static void clear_3rdack_retransmission(struct sock *sk) } static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) @@ -428,9 +429,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, if (!skb) return false; - /* MPC/MPJ needed only on 3rd ack packet */ - if (subflow->fully_established || - subflow->snd_isn != TCP_SKB_CB(skb)->seq) + /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ + if (subflow->fully_established || snd_data_fin_enable || + subflow->snd_isn != TCP_SKB_CB(skb)->seq || + sk->sk_state != TCP_ESTABLISHED) return false; if (subflow->mp_capable) { @@ -502,20 +504,20 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, } static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - u64 snd_data_fin_enable, ack_seq; unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; + u64 ack_seq; mpext = skb ? mptcp_get_ext(skb) : NULL; - snd_data_fin_enable = mptcp_data_fin_enabled(msk); if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size; @@ -717,12 +719,15 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int opt_size = 0; + bool snd_data_fin; bool ret = false; opts->suboptions = 0; - if (unlikely(mptcp_check_fallback(sk))) + if (unlikely(__mptcp_check_fallback(msk))) return false; /* prevent adding of any MPTCP related options on reset packet @@ -731,10 +736,10 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) return false; - if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) + snd_data_fin = mptcp_data_fin_enabled(msk); + if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; - else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, - opts)) + else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; /* we reserved enough space for the above options, and exceeding the diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a57f3eab7b6a..76958570ae7f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> +#include <linux/igmp.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> @@ -19,6 +20,7 @@ #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> +#include <net/addrconf.h> #endif #include <net/mptcp.h> #include <net/xfrm.h> @@ -1059,6 +1061,12 @@ out: } } +static void __mptcp_clean_una_wakeup(struct sock *sk) +{ + __mptcp_clean_una(sk); + mptcp_write_space(sk); +} + static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1187,6 +1195,7 @@ static bool mptcp_tx_cache_refill(struct sock *sk, int size, */ while (skbs->qlen > 1) { skb = __skb_dequeue_tail(skbs); + *total_ts -= skb->truesize; __kfree_skb(skb); } return skbs->qlen > 0; @@ -1442,7 +1451,7 @@ static void mptcp_push_release(struct sock *sk, struct sock *ssk, release_sock(ssk); } -static void mptcp_push_pending(struct sock *sk, unsigned int flags) +static void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; struct mptcp_sock *msk = mptcp_sk(sk); @@ -1694,14 +1703,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) wait_for_memory: mptcp_set_nospace(sk); - mptcp_push_pending(sk, msg->msg_flags); + __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) goto out; } if (copied) - mptcp_push_pending(sk, msg->msg_flags); + __mptcp_push_pending(sk, msg->msg_flags); out: release_sock(sk); @@ -2113,6 +2122,14 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) return backup; } +static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) +{ + if (msk->subflow) { + iput(SOCK_INODE(msk->subflow)); + msk->subflow = NULL; + } +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2124,6 +2141,8 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + struct mptcp_sock *msk = mptcp_sk(sk); + list_del(&subflow->node); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); @@ -2152,6 +2171,18 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, release_sock(ssk); sock_put(ssk); + + if (ssk == msk->last_snd) + msk->last_snd = NULL; + + if (ssk == msk->ack_hint) + msk->ack_hint = NULL; + + if (ssk == msk->first) + msk->first = NULL; + + if (msk->subflow && ssk == msk->subflow->sk) + mptcp_dispose_initial_subflow(msk); } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2236,60 +2267,23 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) mptcp_close_wake_up(sk); } -static void mptcp_worker(struct work_struct *work) +static void __mptcp_retrans(struct sock *sk) { - struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); - struct sock *ssk, *sk = &msk->sk.icsk_inet.sk; + struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = {}; struct mptcp_data_frag *dfrag; size_t copied = 0; - int state, ret; - - lock_sock(sk); - state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) - goto unlock; - - mptcp_check_data_fin_ack(sk); - __mptcp_flush_join_list(msk); - - mptcp_check_fastclose(msk); - - if (msk->pm.status) - mptcp_pm_nl_work(msk); - - if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) - mptcp_check_for_eof(msk); - - __mptcp_check_send_data_fin(sk); - mptcp_check_data_fin(sk); - - /* if the msk data is completely acked, or the socket timedout, - * there is no point in keeping around an orphaned sk - */ - if (sock_flag(sk, SOCK_DEAD) && - (mptcp_check_close_timeout(sk) || - (state != sk->sk_state && - ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) { - inet_sk_state_store(sk, TCP_CLOSE); - __mptcp_destroy_sock(sk); - goto unlock; - } - - if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - __mptcp_close_subflow(msk); - - if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) - goto unlock; + struct sock *ssk; + int ret; - __mptcp_clean_una(sk); + __mptcp_clean_una_wakeup(sk); dfrag = mptcp_rtx_head(sk); if (!dfrag) - goto unlock; + return; ssk = mptcp_subflow_get_retrans(msk); if (!ssk) - goto reset_unlock; + goto reset_timer; lock_sock(ssk); @@ -2315,9 +2309,52 @@ static void mptcp_worker(struct work_struct *work) mptcp_set_timeout(sk, ssk); release_sock(ssk); -reset_unlock: +reset_timer: if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); +} + +static void mptcp_worker(struct work_struct *work) +{ + struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); + struct sock *sk = &msk->sk.icsk_inet.sk; + int state; + + lock_sock(sk); + state = sk->sk_state; + if (unlikely(state == TCP_CLOSE)) + goto unlock; + + mptcp_check_data_fin_ack(sk); + __mptcp_flush_join_list(msk); + + mptcp_check_fastclose(msk); + + if (msk->pm.status) + mptcp_pm_nl_work(msk); + + if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) + mptcp_check_for_eof(msk); + + __mptcp_check_send_data_fin(sk); + mptcp_check_data_fin(sk); + + /* There is no point in keeping around an orphaned sk timedout or + * closed, but we need the msk around to reply to incoming DATA_FIN, + * even if it is orphaned and in FIN_WAIT2 state + */ + if (sock_flag(sk, SOCK_DEAD) && + (mptcp_check_close_timeout(sk) || sk->sk_state == TCP_CLOSE)) { + inet_sk_state_store(sk, TCP_CLOSE); + __mptcp_destroy_sock(sk); + goto unlock; + } + + if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + __mptcp_close_subflow(msk); + + if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) + __mptcp_retrans(sk); unlock: release_sock(sk); @@ -2522,12 +2559,6 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - /* dispose the ancillatory tcp socket, if any */ - if (msk->subflow) { - iput(SOCK_INODE(msk->subflow)); - msk->subflow = NULL; - } - /* be sure to always acquire the join list lock, to sync vs * mptcp_finish_join(). */ @@ -2552,6 +2583,7 @@ static void __mptcp_destroy_sock(struct sock *sk) sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + mptcp_dispose_initial_subflow(msk); sock_put(sk); } @@ -2933,13 +2965,14 @@ static void mptcp_release_cb(struct sock *sk) { unsigned long flags, nflags; - /* push_pending may touch wmem_reserved, do it before the later - * cleanup - */ - if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) - __mptcp_clean_una(sk); - if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) { - /* mptcp_push_pending() acquires the subflow socket lock + for (;;) { + flags = 0; + if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) + flags |= MPTCP_PUSH_PENDING; + if (!flags) + break; + + /* the following actions acquire the subflow socket lock * * 1) can't be invoked in atomic scope * 2) must avoid ABBA deadlock with msk socket spinlock: the RX @@ -2948,13 +2981,21 @@ static void mptcp_release_cb(struct sock *sk) */ spin_unlock_bh(&sk->sk_lock.slock); - mptcp_push_pending(sk, 0); + if (flags & MPTCP_PUSH_PENDING) + __mptcp_push_pending(sk, 0); + + cond_resched(); spin_lock_bh(&sk->sk_lock.slock); } + + if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) + __mptcp_clean_una_wakeup(sk); if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags)) __mptcp_error_report(sk); - /* clear any wmem reservation and errors */ + /* push_pending may touch wmem_reserved, ensure we do the cleanup + * later + */ __mptcp_update_wmem(sk); __mptcp_update_rmem(sk); @@ -3284,6 +3325,9 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, /* PM/worker can now acquire the first subflow socket * lock without racing with listener queue cleanup, * we can notify it, if needed. + * + * Even if remote has reset the initial subflow by now + * the refcnt is still at least one. */ subflow = mptcp_subflow_ctx(msk->first); list_add(&subflow->node, &msk->conn_list); @@ -3375,10 +3419,34 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, return mask; } +static int mptcp_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = sock->sk; + struct mptcp_sock *msk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + } + + release_sock(sk); + + return inet_release(sock); +} + static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, - .release = inet_release, + .release = mptcp_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, @@ -3470,10 +3538,35 @@ void __init mptcp_proto_init(void) } #if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int mptcp6_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + struct sock *sk = sock->sk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + ipv6_sock_mc_close(ssk); + ipv6_sock_ac_close(ssk); + } + + release_sock(sk); + return inet6_release(sock); +} + static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, - .release = inet6_release, + .release = mptcp6_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 91827d949766..e21a5bc36cf0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -52,14 +52,15 @@ #define TCPOLEN_MPTCP_DSS_MAP64 14 #define TCPOLEN_MPTCP_DSS_CHECKSUM 2 #define TCPOLEN_MPTCP_ADD_ADDR 16 -#define TCPOLEN_MPTCP_ADD_ADDR_PORT 20 +#define TCPOLEN_MPTCP_ADD_ADDR_PORT 18 #define TCPOLEN_MPTCP_ADD_ADDR_BASE 8 -#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 12 +#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 10 #define TCPOLEN_MPTCP_ADD_ADDR6 28 -#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 32 +#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 30 #define TCPOLEN_MPTCP_ADD_ADDR6_BASE 20 -#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 24 -#define TCPOLEN_MPTCP_PORT_LEN 4 +#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 22 +#define TCPOLEN_MPTCP_PORT_LEN 2 +#define TCPOLEN_MPTCP_PORT_ALIGN 2 #define TCPOLEN_MPTCP_RM_ADDR_BASE 4 #define TCPOLEN_MPTCP_PRIO 3 #define TCPOLEN_MPTCP_PRIO_ALIGN 4 @@ -701,8 +702,9 @@ static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port) len = TCPOLEN_MPTCP_ADD_ADDR6_BASE; if (!echo) len += MPTCPOPT_THMAC_LEN; + /* account for 2 trailing 'nop' options */ if (port) - len += TCPOLEN_MPTCP_PORT_LEN; + len += TCPOLEN_MPTCP_PORT_LEN + TCPOLEN_MPTCP_PORT_ALIGN; return len; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 06e233410e0e..3d47d670e665 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -687,11 +687,6 @@ create_child: /* move the msk reference ownership to the subflow */ subflow_req->msk = NULL; ctx->conn = (struct sock *)owner; - if (!mptcp_finish_join(child)) - goto dispose_child; - - SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); - tcp_rsk(req)->drop_req = true; if (subflow_use_different_sport(owner, sk)) { pr_debug("ack inet_sport=%d %d", @@ -699,10 +694,16 @@ create_child: ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); - goto out; + goto dispose_child; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); } + + if (!mptcp_finish_join(child)) + goto dispose_child; + + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); + tcp_rsk(req)->drop_req = true; } } @@ -1096,6 +1097,12 @@ static void subflow_data_ready(struct sock *sk) msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + set_bit(MPTCP_DATA_READY, &msk->flags); parent->sk_data_ready(parent); return; @@ -1291,6 +1298,7 @@ failed_unlink: spin_lock_bh(&msk->join_list_lock); list_del(&subflow->node); spin_unlock_bh(&msk->join_list_lock); + sock_put(mptcp_subflow_tcp_sock(subflow)); failed: subflow->disposable = 1; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 118f415928ae..b055187235f8 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -219,7 +219,7 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) return NULL; pr_info("nf_conntrack: default automatic helper assignment " "has been turned off for security reasons and CT-based " - " firewall rule not found. Use the iptables CT target " + "firewall rule not found. Use the iptables CT target " "to attach helpers instead.\n"); net->ct.auto_assign_helper_warned = 1; return NULL; @@ -228,7 +228,6 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) return __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); } - int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1d7e1c595546..ec23330687a5 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -982,8 +982,10 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in " - "state %s ", tcp_conntrack_names[old_state]); + nf_ct_l4proto_log_invalid(skb, ct, + "packet (index %d) in dir %d ignored, state %s", + index, dir, + tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: /* Special case for SYN proxy: when the SYN to the server or diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index e87b6bd6b3cd..4731d21fc3ad 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -646,8 +646,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, } static unsigned int -nf_nat_ipv4_in(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) +nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; @@ -660,6 +660,23 @@ nf_nat_ipv4_in(void *priv, struct sk_buff *skb, } static unsigned int +nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + __be32 saddr = ip_hdr(skb)->saddr; + struct sock *sk = skb->sk; + unsigned int ret; + + ret = nf_nat_ipv4_fn(priv, skb, state); + + if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr && + !inet_sk_transparent(sk)) + skb_orphan(skb); /* TCP edemux obtained wrong socket */ + + return ret; +} + +static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -736,7 +753,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { - .hook = nf_nat_ipv4_in, + .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, @@ -757,7 +774,7 @@ static const struct nf_hook_ops nf_nat_ipv4_ops[] = { }, /* After packet filtering, change source */ { - .hook = nf_nat_ipv4_fn, + .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c1eb5cdb3033..224c8e537cb3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -916,6 +916,12 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags == ctx->table->flags) return 0; + if ((nft_table_has_owner(ctx->table) && + !(flags & NFT_TABLE_F_OWNER)) || + (!nft_table_has_owner(ctx->table) && + flags & NFT_TABLE_F_OWNER)) + return -EOPNOTSUPP; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -9022,8 +9028,12 @@ static void __nft_release_hooks(struct net *net) { struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) + list_for_each_entry(table, &net->nft.tables, list) { + if (nft_table_has_owner(table)) + continue; + __nft_release_hook(net, table); + } } static void __nft_release_table(struct net *net, struct nft_table *table) @@ -9073,13 +9083,12 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nf_tables_table_destroy(&ctx); } -static void __nft_release_tables(struct net *net, u32 nlpid) +static void __nft_release_tables(struct net *net) { struct nft_table *table, *nt; list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - if (nft_table_has_owner(table) && - nlpid != table->nlpid) + if (nft_table_has_owner(table)) continue; __nft_release_table(net, table); @@ -9145,7 +9154,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); - __nft_release_tables(net, 0); + __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); WARN_ON_ONCE(!list_empty(&net->nft.module_list)); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index acce622582e3..bce6ca203d46 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -330,6 +330,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) const struct xt_match *m; int have_rev = 0; + mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) @@ -338,6 +339,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); @@ -350,6 +352,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) const struct xt_target *t; int have_rev = 0; + mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) @@ -358,6 +361,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); @@ -371,12 +375,10 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, { int have_rev, best = -1; - mutex_lock(&xt[af].mutex); if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); - mutex_unlock(&xt[af].mutex); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 726dda95934c..4f50a64315cf 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -575,6 +575,7 @@ list_start: break; } + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); genlmsg_end(ans_skb, data); @@ -583,12 +584,14 @@ list_start: list_retry: /* XXX - this limit is a guesstimate */ if (nlsze_mult < 4) { + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); kfree_skb(ans_skb); nlsze_mult *= 2; goto list_start; } list_failure_lock: + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); list_failure: kfree_skb(ans_skb); diff --git a/net/psample/psample.c b/net/psample/psample.c index 33e238c965bd..482c07f2766b 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -309,10 +309,10 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) unsigned short tun_proto = ip_tunnel_info_af(tun_info); const struct ip_tunnel_key *tun_key = &tun_info->key; int tun_opts_len = tun_info->options_len; - int sum = 0; + int sum = nla_total_size(0); /* PSAMPLE_ATTR_TUNNEL */ if (tun_key->tun_flags & TUNNEL_KEY) - sum += nla_total_size(sizeof(u64)); + sum += nla_total_size_64bit(sizeof(u64)); if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE) sum += nla_total_size(0); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b34358282f37..edb6ac17ceca 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -439,7 +439,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (len == 0 || len & 3) return -EINVAL; - skb = netdev_alloc_skb(NULL, len); + skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN); if (!skb) return -ENOMEM; @@ -958,8 +958,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) plen = (len + 3) & ~3; skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE, msg->msg_flags & MSG_DONTWAIT, &rc); - if (!skb) + if (!skb) { + rc = -ENOMEM; goto out_node; + } skb_reserve(skb, QRTR_HDR_MAX_SIZE); diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c index b238c40a9984..304b41fea5ab 100644 --- a/net/qrtr/tun.c +++ b/net/qrtr/tun.c @@ -31,6 +31,7 @@ static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) static int qrtr_tun_open(struct inode *inode, struct file *filp) { struct qrtr_tun *tun; + int ret; tun = kzalloc(sizeof(*tun), GFP_KERNEL); if (!tun) @@ -43,7 +44,16 @@ static int qrtr_tun_open(struct inode *inode, struct file *filp) filp->private_data = tun; - return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + ret = qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + if (ret) + goto out; + + return 0; + +out: + filp->private_data = NULL; + kfree(tun); + return ret; } static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2409e522c68f..d097b5c15faa 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1417,6 +1417,21 @@ static int fl_validate_ct_state(u16 state, struct nlattr *tb, return -EINVAL; } + if (state & TCA_FLOWER_KEY_CT_FLAGS_INVALID && + state & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID)) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "when inv is set, only trk may be set"); + return -EINVAL; + } + + if (state & TCA_FLOWER_KEY_CT_FLAGS_NEW && + state & TCA_FLOWER_KEY_CT_FLAGS_REPLY) { + NL_SET_ERR_MSG_ATTR(extack, tb, + "new and rpl are mutually exclusive"); + return -EINVAL; + } + return 0; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e2e4353db8a7..f87d07736a14 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -2168,7 +2168,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, - int *t_p, int s_t) + int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; @@ -2179,7 +2179,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; - if (!qdisc_dev(root)) + if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { @@ -2214,13 +2214,13 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; t = 0; - if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t) < 0) + &t, s_t, false) < 0) goto done; done: diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index a9c6af5795d8..5ba456727f63 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -75,7 +75,7 @@ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn) return 1; /* Verify that we can hold this TSN and that it will not - * overlfow our map + * overflow our map */ if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE)) return -1; diff --git a/net/socket.c b/net/socket.c index 7f0617ab5437..84a8049c2b09 100644 --- a/net/socket.c +++ b/net/socket.c @@ -334,6 +334,7 @@ static const struct xattr_handler sockfs_xattr_handler = { }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) @@ -537,9 +538,10 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, return used; } -static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) +static int sockfs_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) { - int err = simple_setattr(dentry, iattr); + int err = simple_setattr(&init_user_ns, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); @@ -2411,10 +2413,6 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; - return ____sys_sendmsg(sock, msg, flags, NULL, 0); } @@ -2623,12 +2621,6 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - if (msg->msg_control || msg->msg_controllen) { - /* disallow ancillary data reqs unless cmsg is plain data */ - if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) - return -EINVAL; - } - return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 8241f5a4a01c..09c000d490a1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -478,6 +478,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode) inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); + break; default: break; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5a809c64dc7b..2e2f007dfc9f 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1078,9 +1078,8 @@ static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec, * In addition, the logic assumes that * .bv_len is never larger * than PAGE_SIZE. */ -static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg, - struct xdr_buf *xdr, rpc_fraghdr marker, - unsigned int *sentp) +static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr, + rpc_fraghdr marker, unsigned int *sentp) { const struct kvec *head = xdr->head; const struct kvec *tail = xdr->tail; @@ -1088,21 +1087,22 @@ static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg, .iov_base = &marker, .iov_len = sizeof(marker), }; - int flags, ret; + struct msghdr msg = { + .msg_flags = 0, + }; + int ret; *sentp = 0; xdr_alloc_bvec(xdr, GFP_KERNEL); - msg->msg_flags = MSG_MORE; - ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len); + ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len); if (ret < 0) return ret; *sentp += ret; if (ret != rm.iov_len) return -EAGAIN; - flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0; - ret = svc_tcp_send_kvec(sock, head, flags); + ret = svc_tcp_send_kvec(sock, head, 0); if (ret < 0) return ret; *sentp += ret; @@ -1116,15 +1116,11 @@ static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg, bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT); offset = offset_in_page(xdr->page_base); remaining = xdr->page_len; - flags = MSG_MORE | MSG_SENDPAGE_NOTLAST; while (remaining > 0) { - if (remaining <= PAGE_SIZE && tail->iov_len == 0) - flags = 0; - len = min(remaining, bvec->bv_len - offset); ret = kernel_sendpage(sock, bvec->bv_page, bvec->bv_offset + offset, - len, flags); + len, 0); if (ret < 0) return ret; *sentp += ret; @@ -1163,26 +1159,28 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) struct xdr_buf *xdr = &rqstp->rq_res; rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | (u32)xdr->len); - struct msghdr msg = { - .msg_flags = 0, - }; unsigned int sent; int err; svc_tcp_release_rqst(rqstp); + atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); if (svc_xprt_is_dead(xprt)) goto out_notconn; - err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent); + tcp_sock_set_cork(svsk->sk_sk, true); + err = svc_tcp_sendmsg(svsk->sk_sock, xdr, marker, &sent); xdr_free_bvec(xdr); trace_svcsock_tcp_send(xprt, err < 0 ? err : sent); if (err < 0 || sent != (xdr->len + sizeof(marker))) goto out_close; + if (atomic_dec_and_test(&svsk->sk_sendqlen)) + tcp_sock_set_cork(svsk->sk_sk, false); mutex_unlock(&xprt->xpt_mutex); return sent; out_notconn: + atomic_dec(&svsk->sk_sendqlen); mutex_unlock(&xprt->xpt_mutex); return -ENOTCONN; out_close: @@ -1192,6 +1190,7 @@ out_close: (err < 0) ? err : sent, xdr->len); set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + atomic_dec(&svsk->sk_sendqlen); mutex_unlock(&xprt->xpt_mutex); return -EAGAIN; } @@ -1261,7 +1260,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) svsk->sk_datalen = 0; memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages)); - tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; + tcp_sock_set_nodelay(sk); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); switch (sk->sk_state) { diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 946edf2db646..a249837d6a55 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2015-2020, Oracle and/or its affiliates. * - * Support for backward direction RPCs on RPC/RDMA. + * Support for reverse-direction RPCs on RPC/RDMA. */ #include <linux/sunrpc/xprt.h> @@ -208,7 +208,7 @@ create_req: } /** - * rpcrdma_bc_receive_call - Handle a backward direction call + * rpcrdma_bc_receive_call - Handle a reverse-direction Call * @r_xprt: transport receiving the call * @rep: receive buffer containing the call * diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index baca49fe83af..766a1048a48a 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -306,20 +306,14 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, if (nsegs > ep->re_max_fr_depth) nsegs = ep->re_max_fr_depth; for (i = 0; i < nsegs;) { - if (seg->mr_page) - sg_set_page(&mr->mr_sg[i], - seg->mr_page, - seg->mr_len, - offset_in_page(seg->mr_offset)); - else - sg_set_buf(&mr->mr_sg[i], seg->mr_offset, - seg->mr_len); + sg_set_page(&mr->mr_sg[i], seg->mr_page, + seg->mr_len, seg->mr_offset); ++seg; ++i; if (ep->re_mrtype == IB_MR_TYPE_SG_GAPS) continue; - if ((i < nsegs && offset_in_page(seg->mr_offset)) || + if ((i < nsegs && seg->mr_offset) || offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8f5d0cb68360..292f066d006e 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -204,9 +204,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf) return 0; } -/* Split @vec on page boundaries into SGEs. FMR registers pages, not - * a byte range. Other modes coalesce these SGEs into a single MR - * when they can. +/* Convert @vec to a single SGL element. * * Returns pointer to next available SGE, and bumps the total number * of SGEs consumed. @@ -215,22 +213,11 @@ static struct rpcrdma_mr_seg * rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, unsigned int *n) { - u32 remaining, page_offset; - char *base; - - base = vec->iov_base; - page_offset = offset_in_page(base); - remaining = vec->iov_len; - while (remaining) { - seg->mr_page = NULL; - seg->mr_offset = base; - seg->mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining); - remaining -= seg->mr_len; - base += seg->mr_len; - ++seg; - ++(*n); - page_offset = 0; - } + seg->mr_page = virt_to_page(vec->iov_base); + seg->mr_offset = offset_in_page(vec->iov_base); + seg->mr_len = vec->iov_len; + ++seg; + ++(*n); return seg; } @@ -259,7 +246,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = offset_in_page(xdrbuf->page_base); while (len) { seg->mr_page = *ppages; - seg->mr_offset = (char *)page_base; + seg->mr_offset = page_base; seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len); len -= seg->mr_len; ++ppages; @@ -268,10 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = 0; } - /* When encoding a Read chunk, the tail iovec contains an - * XDR pad and may be omitted. - */ - if (type == rpcrdma_readch && r_xprt->rx_ep->re_implicit_roundup) + if (type == rpcrdma_readch) goto out; /* When encoding a Write chunk, some servers need to see an @@ -283,7 +267,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, goto out; if (xdrbuf->tail[0].iov_len) - seg = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n); + rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n); out: if (unlikely(n > RPCRDMA_MAX_SEGS)) @@ -644,9 +628,8 @@ out_mapping_err: return false; } -/* The tail iovec may include an XDR pad for the page list, - * as well as additional content, and may not reside in the - * same page as the head iovec. +/* The tail iovec might not reside in the same page as the + * head iovec. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -764,27 +747,19 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) { + struct kvec *tail = &xdr->tail[0]; + if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) return false; - /* If there is a Read chunk, the page list is being handled + /* If there is a Read chunk, the page list is handled * via explicit RDMA, and thus is skipped here. */ - /* Do not include the tail if it is only an XDR pad */ - if (xdr->tail[0].iov_len > 3) { - unsigned int page_base, len; - - /* If the content in the page list is an odd length, - * xdr_write_pages() adds a pad at the beginning of - * the tail iovec. Force the tail's non-pad content to - * land at the next XDR position in the Send message. - */ - page_base = offset_in_page(xdr->tail[0].iov_base); - len = xdr->tail[0].iov_len; - page_base += len & 3; - len -= len & 3; - if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) + if (tail->iov_len) { + if (!rpcrdma_prepare_tail_iov(req, xdr, + offset_in_page(tail->iov_base), + tail->iov_len)) return false; kref_get(&req->rl_kref); } @@ -1164,14 +1139,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) */ p = xdr_inline_decode(xdr, 3 * sizeof(*p)); if (unlikely(!p)) - goto out_short; + return true; rpcrdma_bc_receive_call(r_xprt, rep); return true; - -out_short: - pr_warn("RPC/RDMA short backward direction call\n"); - return true; } #else /* CONFIG_SUNRPC_BACKCHANNEL */ { diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 63f8be974df2..4a1edbb4028e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2015-2018 Oracle. All rights reserved. * - * Support for backward direction RPCs on RPC/RDMA (server-side). + * Support for reverse-direction RPCs on RPC/RDMA (server-side). */ #include <linux/sunrpc/svc_rdma.h> @@ -59,7 +59,7 @@ out_unlock: spin_unlock(&xprt->queue_lock); } -/* Send a backwards direction RPC call. +/* Send a reverse-direction RPC Call. * * Caller holds the connection's mutex and has already marshaled * the RPC/RDMA request. diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index afba4e9d5425..c895f80df659 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -475,9 +475,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) if (!svc_rdma_post_recvs(newxprt)) goto errout; - /* Swap out the handler */ - newxprt->sc_cm_id->event_handler = svc_rdma_cma_handler; - /* Construct RDMA-CM private message */ pmsg.cp_magic = rpcrdma_cmp_magic; pmsg.cp_version = RPCRDMA_CMP_VERSION; @@ -498,7 +495,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) } conn_param.private_data = &pmsg; conn_param.private_data_len = sizeof(pmsg); + rdma_lock_handler(newxprt->sc_cm_id); + newxprt->sc_cm_id->event_handler = svc_rdma_cma_handler; ret = rdma_accept(newxprt->sc_cm_id, &conn_param); + rdma_unlock_handler(newxprt->sc_cm_id); if (ret) { trace_svcrdma_accept_err(newxprt, ret); goto errout; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 94b28657aeeb..fe3be985e239 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -98,9 +98,9 @@ struct rpcrdma_ep { atomic_t re_completion_ids; }; -/* Pre-allocate extra Work Requests for handling backward receives - * and sends. This is a fixed value because the Work Queues are - * allocated when the forward channel is set up, long before the +/* Pre-allocate extra Work Requests for handling reverse-direction + * Receives and Sends. This is a fixed value because the Work Queues + * are allocated when the forward channel is set up, long before the * backchannel is provisioned. This value is two times * NFS4_DEF_CB_SLOT_TABLE_SIZE. */ @@ -283,10 +283,11 @@ enum { RPCRDMA_MAX_IOV_SEGS, }; -struct rpcrdma_mr_seg { /* chunk descriptors */ - u32 mr_len; /* length of chunk or segment */ - struct page *mr_page; /* owning page, if any */ - char *mr_offset; /* kva if no page, else offset */ +/* Arguments for DMA mapping and registration */ +struct rpcrdma_mr_seg { + u32 mr_len; /* length of segment */ + struct page *mr_page; /* underlying struct page */ + u64 mr_offset; /* IN: page offset, OUT: iova */ }; /* The Send SGE array is provisioned to send a maximum size diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c56a66cdf4ac..e35760f238a4 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -829,7 +829,7 @@ xs_stream_record_marker(struct xdr_buf *xdr) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent */ static int xs_local_send_request(struct rpc_rqst *req) { @@ -1665,7 +1665,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) * This ensures that we can continue to establish TCP * connections even when all local ephemeral ports are already * a part of some TCP connection. This makes no difference - * for UDP sockets, but also doens't harm them. + * for UDP sockets, but also doesn't harm them. * * If we're asking for any reserved port (i.e. port == 0 && * transport->xprt.resvport == 1) xs_get_srcport above will @@ -1875,6 +1875,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; xprt_set_connected(xprt); + break; case -ENOBUFS: break; case -ENOENT: @@ -2276,10 +2277,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: - /* - * xs_tcp_force_close() wakes tasks with -EIO. - * We need to wake them first to ensure the - * correct error code. + /* xs_tcp_force_close() wakes tasks with a fixed error code. + * We need to wake them first to ensure the correct error code. */ xprt_wake_pending_tasks(xprt, status); xs_tcp_force_close(xprt); @@ -2380,7 +2379,7 @@ static void xs_error_handle(struct work_struct *work) } /** - * xs_local_print_stats - display AF_LOCAL socket-specifc stats + * xs_local_print_stats - display AF_LOCAL socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2409,7 +2408,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_udp_print_stats - display UDP socket-specifc stats + * xs_udp_print_stats - display UDP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2433,7 +2432,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_tcp_print_stats - display TCP socket-specifc stats + * xs_tcp_print_stats - display TCP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 41c3303c3357..5a31307ceb76 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -936,7 +936,7 @@ static struct sock *unix_find_other(struct net *net, if (err) goto fail; inode = d_backing_inode(path.dentry); - err = inode_permission(inode, MAY_WRITE); + err = path_permission(&path, MAY_WRITE); if (err) goto put_fail; @@ -996,7 +996,8 @@ static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) */ err = security_path_mknod(&path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); + err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry), + dentry, mode, 0); if (!err) { res->mnt = mntget(path.mnt); res->dentry = dget(dentry); |