diff options
Diffstat (limited to 'net')
127 files changed, 3681 insertions, 1053 deletions
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index e3f6ff05a528..1a705a4ef7fa 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -108,7 +108,8 @@ static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) netdev_features_t ret; ret = real_dev->hw_enc_features & - (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL); + (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index be18af481d7d..c7236daa2415 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -768,7 +768,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, if (a && a->status & ATIF_PROBE) { a->status |= ATIF_PROBE_FAIL; /* - * we do not respond to probe or request packets for + * we do not respond to probe or request packets of * this address while we are probing this address */ goto unlock; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 680def809838..12022378f892 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -409,8 +409,10 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) if (WARN_ON(!forw_packet->if_outgoing)) return; - if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) + if (forw_packet->if_outgoing->soft_iface != soft_iface) { + pr_warn("%s: soft interface switch for queued OGM\n", __func__); return; + } if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) return; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 93144e0c7efa..4d93c6c32a71 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3229,7 +3229,7 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) { struct l2cap_chan *chan; - bt_dev_dbg(pchan->conn->hcon->hdev, "pchan %p", pchan); + BT_DBG("pchan %p", pchan); chan = l2cap_chan_create(); if (!chan) @@ -3250,7 +3250,7 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) */ atomic_set(&chan->nesting, L2CAP_NESTING_SMP); - bt_dev_dbg(pchan->conn->hcon->hdev, "created chan %p", chan); + BT_DBG("created chan %p", chan); return chan; } @@ -3354,7 +3354,7 @@ static void smp_del_chan(struct l2cap_chan *chan) { struct smp_dev *smp; - bt_dev_dbg(chan->conn->hcon->hdev, "chan %p", chan); + BT_DBG("chan %p", chan); smp = chan->data; if (smp) { diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index 001064f7583d..a3c755d0a09d 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -142,7 +142,7 @@ static void br_cfm_notify(int event, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_CFM_STATUS; - return br_info_notify(event, port->br, NULL, filter); + br_info_notify(event, port->br, NULL, filter); } static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index ec661130c2d0..a684d0cfc58c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -90,8 +90,8 @@ struct bridge_mcast_stats { #endif struct br_tunnel_info { - __be64 tunnel_id; - struct metadata_dst *tunnel_dst; + __be64 tunnel_id; + struct metadata_dst __rcu *tunnel_dst; }; /* private vlan flags */ diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index da3256a3eed0..8789a57af543 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -113,9 +113,7 @@ static void __vlan_add_list(struct net_bridge_vlan *v) headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); - if (v->vid < vent->vid) - continue; - else + if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 0d3a8c01552e..01017448ebde 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -41,26 +41,33 @@ static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, br_vlan_tunnel_rht_params); } +static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) +{ + struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); + + WRITE_ONCE(vlan->tinfo.tunnel_id, 0); + RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); + dst_release(&tdst->dst); +} + void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { - if (!vlan->tinfo.tunnel_dst) + if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); - vlan->tinfo.tunnel_id = 0; - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; + vlan_tunnel_info_release(vlan); } static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { - struct metadata_dst *metadata = NULL; + struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); int err; - if (vlan->tinfo.tunnel_dst) + if (metadata) return -EEXIST; metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, @@ -69,8 +76,8 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return -EINVAL; metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; - vlan->tinfo.tunnel_dst = metadata; - vlan->tinfo.tunnel_id = key; + rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); + WRITE_ONCE(vlan->tinfo.tunnel_id, key); err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); @@ -79,9 +86,7 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return 0; out: - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; - vlan->tinfo.tunnel_id = 0; + vlan_tunnel_info_release(vlan); return err; } @@ -182,12 +187,15 @@ int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + struct metadata_dst *tunnel_dst; + __be64 tunnel_id; int err; - if (!vlan || !vlan->tinfo.tunnel_id) + if (!vlan) return 0; - if (unlikely(!skb_vlan_tag_present(skb))) + tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); + if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0; skb_dst_drop(skb); @@ -195,7 +203,9 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, if (err) return err; - skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); + if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) + skb_dst_set(skb, &tunnel_dst->dst); return 0; } diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index cac30e676ac9..23267c8db7c4 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -480,7 +480,7 @@ got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); if (!phyinfo) { res = -ENOMEM; - goto out_err; + goto out; } phy_layer->id = phyid; diff --git a/net/can/bcm.c b/net/can/bcm.c index 909b9e684e04..f3e4d9528fa3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -125,7 +125,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -133,6 +133,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ }; +static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -402,6 +406,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; @@ -439,6 +444,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) /* this element is not throttled anymore */ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; @@ -560,6 +566,7 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) } /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; @@ -1378,20 +1385,15 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; switch (msg) { @@ -1426,7 +1428,28 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); } } +} +static int bcm_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; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } @@ -1446,9 +1469,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock); return 0; } @@ -1471,7 +1494,14 @@ static int bcm_release(struct socket *sock) /* remove bcm_ops, timer, rx_unregister(), etc. */ - unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock); lock_sock(sk); @@ -1692,6 +1722,10 @@ static struct pernet_operations canbcm_pernet_ops __read_mostly = { .exit = canbcm_pernet_exit, }; +static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1705,12 +1739,14 @@ static int __init bcm_module_init(void) } register_pernet_subsys(&canbcm_pernet_ops); + register_netdevice_notifier(&canbcm_notifier); return 0; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); + unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } diff --git a/net/can/isotp.c b/net/can/isotp.c index f995eaef5d7b..bd49299319a1 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -143,10 +143,14 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; struct tpcon rx, tx; - struct notifier_block notifier; + struct list_head notifier; wait_queue_head_t wait; }; +static LIST_HEAD(isotp_notifier_list); +static DEFINE_SPINLOCK(isotp_notifier_lock); +static struct isotp_sock *isotp_busy_notifier; + static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; @@ -1015,7 +1019,14 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - unregister_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + while (isotp_busy_notifier == so) { + spin_unlock(&isotp_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&isotp_notifier_lock); + } + list_del(&so->notifier); + spin_unlock(&isotp_notifier_lock); lock_sock(sk); @@ -1319,21 +1330,16 @@ static int isotp_getsockopt(struct socket *sock, int level, int optname, return 0; } -static int isotp_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void isotp_notify(struct isotp_sock *so, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier); struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (so->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -1359,7 +1365,28 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); break; } +} +static int isotp_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; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&isotp_notifier_lock); + list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { + spin_unlock(&isotp_notifier_lock); + isotp_notify(isotp_busy_notifier, msg, dev); + spin_lock(&isotp_notifier_lock); + } + isotp_busy_notifier = NULL; + spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } @@ -1396,8 +1423,9 @@ static int isotp_init(struct sock *sk) init_waitqueue_head(&so->wait); - so->notifier.notifier_call = isotp_notifier; - register_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + list_add_tail(&so->notifier, &isotp_notifier_list); + spin_unlock(&isotp_notifier_lock); return 0; } @@ -1444,6 +1472,10 @@ static const struct can_proto isotp_can_proto = { .prot = &isotp_proto, }; +static struct notifier_block canisotp_notifier = { + .notifier_call = isotp_notifier +}; + static __init int isotp_module_init(void) { int err; @@ -1453,6 +1485,8 @@ static __init int isotp_module_init(void) err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); + else + register_netdevice_notifier(&canisotp_notifier); return err; } @@ -1460,6 +1494,7 @@ static __init int isotp_module_init(void) static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); + unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index e09d087ba240..c3946c355882 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -330,6 +330,9 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) if ((do_skcb->offset + do_skb->len) < offset_start) { __skb_unlink(do_skb, &session->skb_queue); + /* drop ref taken in j1939_session_skb_queue() */ + skb_unref(do_skb); + kfree_skb(do_skb); } spin_unlock_irqrestore(&session->skb_queue.lock, flags); @@ -349,12 +352,13 @@ void j1939_session_skb_queue(struct j1939_session *session, skcb->flags |= J1939_ECU_LOCAL_SRC; + skb_get(skb); skb_queue_tail(&session->skb_queue, skb); } static struct -sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, - unsigned int offset_start) +sk_buff *j1939_session_skb_get_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *do_skcb; @@ -371,6 +375,10 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, skb = do_skb; } } + + if (skb) + skb_get(skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); if (!skb) @@ -381,12 +389,12 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, return skb; } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct sk_buff *j1939_session_skb_get(struct j1939_session *session) { unsigned int offset_start; offset_start = session->pkt.dpo * 7; - return j1939_session_skb_find_by_offset(session, offset_start); + return j1939_session_skb_get_by_offset(session, offset_start); } /* see if we are receiver @@ -776,7 +784,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); + se_skb = j1939_session_skb_get_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -801,7 +809,8 @@ static int j1939_session_tx_dat(struct j1939_session *session) netdev_err_once(priv->ndev, "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", __func__, session, skcb->offset, se_skb->len , session->pkt.tx); - return -EOVERFLOW; + ret = -EOVERFLOW; + goto out_free; } if (!len) { @@ -835,6 +844,12 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (pkt_done) j1939_tp_set_rxtimeout(session, 250); + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + return ret; } @@ -1007,7 +1022,7 @@ static int j1939_xtp_txnext_receiver(struct j1939_session *session) static int j1939_simple_txnext(struct j1939_session *session) { struct j1939_priv *priv = session->priv; - struct sk_buff *se_skb = j1939_session_skb_find(session); + struct sk_buff *se_skb = j1939_session_skb_get(session); struct sk_buff *skb; int ret; @@ -1015,8 +1030,10 @@ static int j1939_simple_txnext(struct j1939_session *session) return 0; skb = skb_clone(se_skb, GFP_ATOMIC); - if (!skb) - return -ENOMEM; + if (!skb) { + ret = -ENOMEM; + goto out_free; + } can_skb_set_owner(skb, se_skb->sk); @@ -1024,12 +1041,18 @@ static int j1939_simple_txnext(struct j1939_session *session) ret = j1939_send_one(priv, skb); if (ret) - return ret; + goto out_free; j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED); j1939_sk_queue_activate_next(session); - return 0; + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + + return ret; } static bool j1939_session_deactivate_locked(struct j1939_session *session) @@ -1170,9 +1193,10 @@ static void j1939_session_completed(struct j1939_session *session) struct sk_buff *skb; if (!session->transmission) { - skb = j1939_session_skb_find(session); + skb = j1939_session_skb_get(session); /* distribute among j1939 receivers */ j1939_sk_recv(session->priv, skb); + consume_skb(skb); } j1939_session_deactivate_activate_next(session); @@ -1744,7 +1768,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *skcb; - struct sk_buff *se_skb; + struct sk_buff *se_skb = NULL; const u8 *dat; u8 *tpdat; int offset; @@ -1786,7 +1810,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, goto out_session_cancel; } - se_skb = j1939_session_skb_find_by_offset(session, packet * 7); + se_skb = j1939_session_skb_get_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1848,11 +1872,13 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_tp_set_rxtimeout(session, 250); } session->last_cmd = 0xff; + consume_skb(se_skb); j1939_session_put(session); return; out_session_cancel: + kfree_skb(se_skb); j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); diff --git a/net/can/raw.c b/net/can/raw.c index 139d9471ddcf..ac96fc210025 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -83,7 +83,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -95,6 +95,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; }; +static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. @@ -263,21 +267,16 @@ static int raw_enable_allfilters(struct net *net, struct net_device *dev, return err; } -static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -305,7 +304,28 @@ static int raw_notifier(struct notifier_block *nb, sk->sk_error_report(sk); break; } +} + +static int raw_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; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } @@ -334,9 +354,9 @@ static int raw_init(struct sock *sk) return -ENOMEM; /* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock); return 0; } @@ -351,7 +371,14 @@ static int raw_release(struct socket *sock) ro = raw_sk(sk); - unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock); lock_sock(sk); @@ -889,6 +916,10 @@ static const struct can_proto raw_can_proto = { .prot = &raw_proto, }; +static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -898,6 +929,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) pr_err("can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier); return err; } @@ -905,6 +938,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); diff --git a/net/core/dev.c b/net/core/dev.c index 50531a2d0b20..991d09b67bd9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3852,10 +3852,33 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { + if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && + qdisc_run_begin(q)) { + /* Retest nolock_qdisc_is_empty() within the protection + * of q->seqlock to protect from racing with requeuing. + */ + if (unlikely(!nolock_qdisc_is_empty(q))) { + rc = q->enqueue(skb, q, &to_free) & + NET_XMIT_MASK; + __qdisc_run(q); + qdisc_run_end(q); + + goto no_lock_out; + } + + qdisc_bstats_cpu_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && + !nolock_qdisc_is_empty(q)) + __qdisc_run(q); + + qdisc_run_end(q); + return NET_XMIT_SUCCESS; + } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - if (likely(!netif_xmit_frozen_or_stopped(txq))) - qdisc_run(q); + qdisc_run(q); +no_lock_out: if (unlikely(to_free)) kfree_skb_list(to_free); return rc; diff --git a/net/core/filter.c b/net/core/filter.c index 239de1306de9..0b13d8157a8f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3931,6 +3931,23 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +void bpf_clear_redirect_map(struct bpf_map *map) +{ + struct bpf_redirect_info *ri; + int cpu; + + for_each_possible_cpu(cpu) { + ri = per_cpu_ptr(&bpf_redirect_info, cpu); + /* Avoid polluting remote cacheline due to writes if + * not needed. Once we pass this test, we need the + * cmpxchg() to make sure it hasn't been changed in + * the meantime by remote CPU. + */ + if (unlikely(READ_ONCE(ri->map) == map)) + cmpxchg(&ri->map, map, NULL); + } +} + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { @@ -3938,6 +3955,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ @@ -3947,7 +3965,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_enqueue(fwd, xdp, dev); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_enqueue_multi(xdp, dev, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_enqueue(fwd, xdp, dev); + } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdp, dev); @@ -3989,13 +4014,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_generic_redirect(fwd, skb, xdp_prog); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_redirect_multi(dev, skb, xdp_prog, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_generic_redirect(fwd, skb, xdp_prog); + } if (unlikely(err)) goto err; break; @@ -10012,11 +10045,13 @@ out: static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; + reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; @@ -10025,12 +10060,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; - bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); + bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = BPF_PROG_RUN(prog, &reuse_kern); if (action == SK_PASS) @@ -10140,6 +10176,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_ptr_cookie_proto; default: return bpf_base_func_proto(func_id); } @@ -10169,6 +10207,14 @@ sk_reuseport_is_valid_access(int off, int size, case offsetof(struct sk_reuseport_md, hash): return size == size_default; + case offsetof(struct sk_reuseport_md, sk): + info->reg_type = PTR_TO_SOCKET; + return size == sizeof(__u64); + + case offsetof(struct sk_reuseport_md, migrating_sk): + info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; + return size == sizeof(__u64); + /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) @@ -10241,6 +10287,14 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; + + case offsetof(struct sk_reuseport_md, sk): + SK_REUSEPORT_LOAD_FIELD(sk); + break; + + case offsetof(struct sk_reuseport_md, migrating_sk): + SK_REUSEPORT_LOAD_FIELD(migrating_sk); + break; } return insn - insn_buf; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2b2f333bcdfe..53e85c70c6e5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -238,6 +238,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 43b6ac4c4439..9b5a767eddd5 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -641,6 +641,18 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net); +/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ +struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} +EXPORT_SYMBOL_GPL(get_net_ns); + struct net *get_net_ns_by_fd(int fd) { struct file *file; @@ -660,14 +672,8 @@ struct net *get_net_ns_by_fd(int fd) fput(file); return net; } - -#else -struct net *get_net_ns_by_fd(int fd) -{ - return ERR_PTR(-EINVAL); -} -#endif EXPORT_SYMBOL_GPL(get_net_ns_by_fd); +#endif struct net *get_net_ns_by_pid(pid_t pid) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5baa86bca876..745965e49f78 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4850,10 +4850,12 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout; - if (!skb->len) { - err = -EINVAL; + /* Notification info is only filled for bridge ports, not the bridge + * device itself. Therefore, a zero notification length is valid and + * should not result in an error. + */ + if (!skb->len) goto errout; - } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a0b1d4847efe..2531ac4ffa69 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1258,6 +1258,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; + bool is_zerocopy; u32 lo, hi; u16 len; @@ -1272,6 +1273,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; + is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); @@ -1279,7 +1281,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!uarg->zerocopy) + if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index b065f0a103ed..de5ee3ae86d5 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -17,6 +17,74 @@ DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); +static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, + struct sock_reuseport *reuse, bool bind_inany); + +static int reuseport_sock_index(struct sock *sk, + const struct sock_reuseport *reuse, + bool closed) +{ + int left, right; + + if (!closed) { + left = 0; + right = reuse->num_socks; + } else { + left = reuse->max_socks - reuse->num_closed_socks; + right = reuse->max_socks; + } + + for (; left < right; left++) + if (reuse->socks[left] == sk) + return left; + return -1; +} + +static void __reuseport_add_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + reuse->socks[reuse->num_socks] = sk; + /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ + smp_wmb(); + reuse->num_socks++; +} + +static bool __reuseport_detach_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + int i = reuseport_sock_index(sk, reuse, false); + + if (i == -1) + return false; + + reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; + reuse->num_socks--; + + return true; +} + +static void __reuseport_add_closed_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; + /* paired with READ_ONCE() in inet_csk_bind_conflict() */ + WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); +} + +static bool __reuseport_detach_closed_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + int i = reuseport_sock_index(sk, reuse, true); + + if (i == -1) + return false; + + reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; + /* paired with READ_ONCE() in inet_csk_bind_conflict() */ + WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); + + return true; +} static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { @@ -49,6 +117,12 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { + if (reuse->num_closed_socks) { + /* sk was shutdown()ed before */ + ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); + goto out; + } + /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. @@ -72,9 +146,9 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) } reuse->reuseport_id = id; + reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; - reuse->bind_inany = bind_inany; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: @@ -90,14 +164,30 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; - if (more_socks_size > U16_MAX) + if (more_socks_size > U16_MAX) { + if (reuse->num_closed_socks) { + /* Make room by removing a closed sk. + * The child has already been migrated. + * Only reqsk left at this point. + */ + struct sock *sk; + + sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; + RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); + __reuseport_detach_closed_sock(sk, reuse); + + return reuse; + } + return NULL; + } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; + more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; @@ -105,9 +195,13 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); + memcpy(more_reuse->socks + + (more_reuse->max_socks - more_reuse->num_closed_socks), + reuse->socks + (reuse->max_socks - reuse->num_closed_socks), + reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); - for (i = 0; i < reuse->num_socks; ++i) + for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); @@ -152,13 +246,21 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)); + lockdep_is_held(&reuseport_lock)); + if (old_reuse && old_reuse->num_closed_socks) { + /* sk was shutdown()ed before */ + int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); + + spin_unlock_bh(&reuseport_lock); + return err; + } + if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } - if (reuse->num_socks == reuse->max_socks) { + if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); @@ -166,10 +268,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) } } - reuse->socks[reuse->num_socks] = sk; - /* paired with smp_rmb() in reuseport_select_sock() */ - smp_wmb(); - reuse->num_socks++; + __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); @@ -180,15 +279,77 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) } EXPORT_SYMBOL(reuseport_add_sock); +static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, + struct sock_reuseport *reuse, bool bind_inany) +{ + if (old_reuse == reuse) { + /* If sk was in the same reuseport group, just pop sk out of + * the closed section and push sk into the listening section. + */ + __reuseport_detach_closed_sock(sk, old_reuse); + __reuseport_add_sock(sk, old_reuse); + return 0; + } + + if (!reuse) { + /* In bind()/listen() path, we cannot carry over the eBPF prog + * for the shutdown()ed socket. In setsockopt() path, we should + * not change the eBPF prog of listening sockets by attaching a + * prog to the shutdown()ed socket. Thus, we will allocate a new + * reuseport group and detach sk from the old group. + */ + int id; + + reuse = __reuseport_alloc(INIT_SOCKS); + if (!reuse) + return -ENOMEM; + + id = ida_alloc(&reuseport_ida, GFP_ATOMIC); + if (id < 0) { + kfree(reuse); + return id; + } + + reuse->reuseport_id = id; + reuse->bind_inany = bind_inany; + } else { + /* Move sk from the old group to the new one if + * - all the other listeners in the old group were close()d or + * shutdown()ed, and then sk2 has listen()ed on the same port + * OR + * - sk listen()ed without bind() (or with autobind), was + * shutdown()ed, and then listen()s on another port which + * sk2 listen()s on. + */ + if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { + reuse = reuseport_grow(reuse); + if (!reuse) + return -ENOMEM; + } + } + + __reuseport_detach_closed_sock(sk, old_reuse); + __reuseport_add_sock(sk, reuse); + rcu_assign_pointer(sk->sk_reuseport_cb, reuse); + + if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) + call_rcu(&old_reuse->rcu, reuseport_free_rcu); + + return 0; +} + void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; - int i; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + /* reuseport_grow() has detached a closed sk */ + if (!reuse) + goto out; + /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * @@ -201,19 +362,52 @@ void reuseport_detach_sock(struct sock *sk) rcu_assign_pointer(sk->sk_reuseport_cb, NULL); - for (i = 0; i < reuse->num_socks; i++) { - if (reuse->socks[i] == sk) { - reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; - reuse->num_socks--; - if (reuse->num_socks == 0) - call_rcu(&reuse->rcu, reuseport_free_rcu); - break; - } - } + if (!__reuseport_detach_closed_sock(sk, reuse)) + __reuseport_detach_sock(sk, reuse); + + if (reuse->num_socks + reuse->num_closed_socks == 0) + call_rcu(&reuse->rcu, reuseport_free_rcu); + +out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); +void reuseport_stop_listen_sock(struct sock *sk) +{ + if (sk->sk_protocol == IPPROTO_TCP) { + struct sock_reuseport *reuse; + struct bpf_prog *prog; + + spin_lock_bh(&reuseport_lock); + + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + prog = rcu_dereference_protected(reuse->prog, + lockdep_is_held(&reuseport_lock)); + + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req || + (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { + /* Migration capable, move sk from the listening section + * to the closed section. + */ + bpf_sk_reuseport_detach(sk); + + __reuseport_detach_sock(sk, reuse); + __reuseport_add_closed_sock(sk, reuse); + + spin_unlock_bh(&reuseport_lock); + return; + } + + spin_unlock_bh(&reuseport_lock); + } + + /* Not capable to do migration, detach immediately */ + reuseport_detach_sock(sk); +} +EXPORT_SYMBOL(reuseport_stop_listen_sock); + static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) @@ -244,6 +438,23 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, return reuse->socks[index]; } +static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, + u32 hash, u16 num_socks) +{ + int i, j; + + i = j = reciprocal_scale(hash, num_socks); + while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { + i++; + if (i >= num_socks) + i = 0; + if (i == j) + return NULL; + } + + return reuse->socks[i]; +} + /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. @@ -274,32 +485,21 @@ struct sock *reuseport_select_sock(struct sock *sk, prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { - /* paired with smp_wmb() in reuseport_add_sock() */ + /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) - sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash); + sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ - if (!sk2) { - int i, j; - - i = j = reciprocal_scale(hash, socks); - while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { - i++; - if (i >= socks) - i = 0; - if (i == j) - goto out; - } - sk2 = reuse->socks[i]; - } + if (!sk2) + sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: @@ -308,14 +508,84 @@ out: } EXPORT_SYMBOL(reuseport_select_sock); +/** + * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. + * @sk: close()ed or shutdown()ed socket in the group. + * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or + * NEW_SYN_RECV request socket during 3WHS. + * @skb: skb to run through BPF filter. + * Returns a socket (with sk_refcnt +1) that should accept the child socket + * (or NULL on error). + */ +struct sock *reuseport_migrate_sock(struct sock *sk, + struct sock *migrating_sk, + struct sk_buff *skb) +{ + struct sock_reuseport *reuse; + struct sock *nsk = NULL; + bool allocated = false; + struct bpf_prog *prog; + u16 socks; + u32 hash; + + rcu_read_lock(); + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (!reuse) + goto out; + + socks = READ_ONCE(reuse->num_socks); + if (unlikely(!socks)) + goto out; + + /* paired with smp_wmb() in __reuseport_add_sock() */ + smp_rmb(); + + hash = migrating_sk->sk_hash; + prog = rcu_dereference(reuse->prog); + if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + goto select_by_hash; + goto out; + } + + if (!skb) { + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) + goto out; + allocated = true; + } + + nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); + + if (allocated) + kfree_skb(skb); + +select_by_hash: + if (!nsk) + nsk = reuseport_select_sock_by_hash(reuse, hash, socks); + + if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) + nsk = NULL; + +out: + rcu_read_unlock(); + return nsk; +} +EXPORT_SYMBOL(reuseport_migrate_sock); + int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; - if (sk_unhashed(sk) && sk->sk_reuseport) { - int err = reuseport_alloc(sk, false); + if (sk_unhashed(sk)) { + int err; + if (!sk->sk_reuseport) + return -EINVAL; + + err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -341,13 +611,24 @@ int reuseport_detach_prog(struct sock *sk) struct sock_reuseport *reuse; struct bpf_prog *old_prog; - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return sk->sk_reuseport ? -ENOENT : -EINVAL; - old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + + /* reuse must be checked after acquiring the reuseport_lock + * because reuseport_grow() can detach a closed sk. + */ + if (!reuse) { + spin_unlock_bh(&reuseport_lock); + return sk->sk_reuseport ? -ENOENT : -EINVAL; + } + + if (sk_unhashed(sk) && reuse->num_closed_socks) { + spin_unlock_bh(&reuseport_lock); + return -ENOENT; + } + old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); diff --git a/net/core/xdp.c b/net/core/xdp.c index 858276e72c68..725d20f1b100 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -584,3 +584,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); + +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) +{ + unsigned int headroom, totalsize; + struct xdp_frame *nxdpf; + struct page *page; + void *addr; + + headroom = xdpf->headroom + sizeof(*xdpf); + totalsize = headroom + xdpf->len; + + if (unlikely(totalsize > PAGE_SIZE)) + return NULL; + page = dev_alloc_page(); + if (!page) + return NULL; + addr = page_to_virt(page); + + memcpy(addr, xdpf, totalsize); + + nxdpf = addr; + nxdpf->data = addr + headroom; + nxdpf->frame_sz = PAGE_SIZE; + nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + nxdpf->mem.id = 0; + + return nxdpf; +} diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index b71e87909f0e..9000a8c84baf 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -219,21 +219,6 @@ static void dsa_tree_put(struct dsa_switch_tree *dst) kref_put(&dst->refcount, dsa_tree_release); } -static bool dsa_port_is_dsa(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_DSA; -} - -static bool dsa_port_is_cpu(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_CPU; -} - -static bool dsa_port_is_user(struct dsa_port *dp) -{ - return dp->type == DSA_PORT_TYPE_USER; -} - static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, struct device_node *dn) { @@ -1259,6 +1244,13 @@ static int dsa_switch_parse_member_of(struct dsa_switch *ds, if (!ds->dst) return -ENOMEM; + if (dsa_switch_find(ds->dst->index, ds->index)) { + dev_err(ds->dev, + "A DSA switch with index %d already exists in tree %d\n", + ds->index, ds->dst->index); + return -EEXIST; + } + return 0; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index b8b17474b72b..b0811253d101 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -84,7 +84,7 @@ struct dsa_notifier_vlan_info { /* DSA_NOTIFIER_MTU */ struct dsa_notifier_mtu_info { - bool propagate_upstream; + bool targeted_match; int sw_index; int port; int mtu; @@ -200,7 +200,7 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream); + bool targeted_match); int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, diff --git a/net/dsa/port.c b/net/dsa/port.c index 6379d66a6bb3..5c93f1e1a03d 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -567,11 +567,11 @@ int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, } int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream) + bool targeted_match) { struct dsa_notifier_mtu_info info = { .sw_index = dp->ds->index, - .propagate_upstream = propagate_upstream, + .targeted_match = targeted_match, .port = dp->index, .mtu = new_mtu, }; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 798944aa847a..5e668e529575 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1528,6 +1528,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp_iter; struct dsa_port *cpu_dp; int port = p->dp->index; int largest_mtu = 0; @@ -1535,31 +1536,31 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) int old_master_mtu; int mtu_limit; int cpu_mtu; - int err, i; + int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; - for (i = 0; i < ds->num_ports; i++) { + list_for_each_entry(dp_iter, &ds->dst->ports, list) { int slave_mtu; - if (!dsa_is_user_port(ds, i)) + if (!dsa_port_is_user(dp_iter)) continue; /* During probe, this function will be called for each slave * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ - if (!dsa_to_port(ds, i)->slave) + if (!dp_iter->slave) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ - if (i == port) + if (dp_iter == dp) slave_mtu = new_mtu; else - slave_mtu = dsa_to_port(ds, i)->slave->mtu; + slave_mtu = dp_iter->slave->mtu; if (largest_mtu < slave_mtu) largest_mtu = slave_mtu; @@ -1585,14 +1586,15 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) goto out_master_failed; /* We only need to propagate the MTU of the CPU port to - * upstream switches. + * upstream switches, so create a non-targeted notifier which + * updates all switches. */ - err = dsa_port_mtu_change(cpu_dp, cpu_mtu, true); + err = dsa_port_mtu_change(cpu_dp, cpu_mtu, false); if (err) goto out_cpu_failed; } - err = dsa_port_mtu_change(dp, new_mtu, false); + err = dsa_port_mtu_change(dp, new_mtu, true); if (err) goto out_port_failed; @@ -1606,7 +1608,7 @@ out_port_failed: if (new_master_mtu != old_master_mtu) dsa_port_mtu_change(cpu_dp, old_master_mtu - dsa_tag_protocol_overhead(cpu_dp->tag_ops), - true); + false); out_cpu_failed: if (new_master_mtu != old_master_mtu) dev_set_mtu(master, old_master_mtu); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 9bf8e20ecdf3..c1e5afafe633 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -52,10 +52,13 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, struct dsa_notifier_mtu_info *info) { - if (ds->index == info->sw_index) - return (port == info->port) || dsa_is_dsa_port(ds, port); + if (ds->index == info->sw_index && port == info->port) + return true; - if (!info->propagate_upstream) + /* Do not propagate to other switches in the tree if the notifier was + * targeted for a single switch. + */ + if (info->targeted_match) return false; if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) @@ -232,36 +235,15 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mdb_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mdb_add(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { - int err = 0; - int port; + int port = dsa_towards_port(ds, info->sw_index, info->port); if (!ds->ops->port_mdb_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mdb_match(ds, port, info)) { - err = ds->ops->port_mdb_add(ds, port, info->mdb); - if (err) - break; - } - } - - return err; + return ds->ops->port_mdb_add(ds, port, info->mdb); } static int dsa_switch_mdb_del(struct dsa_switch *ds, @@ -364,36 +346,16 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mrp_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mrp_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mrp_add(struct dsa_switch *ds, struct dsa_notifier_mrp_info *info) { - int err = 0; - int port; - if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mrp_match(ds, port, info)) { - err = ds->ops->port_mrp_add(ds, port, info->mrp); - if (err) - break; - } - } + if (ds->index == info->sw_index) + return ds->ops->port_mrp_add(ds, info->port, info->mrp); - return err; + return 0; } static int dsa_switch_mrp_del(struct dsa_switch *ds, @@ -408,39 +370,18 @@ static int dsa_switch_mrp_del(struct dsa_switch *ds, return 0; } -static bool -dsa_switch_mrp_ring_role_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mrp_ring_role_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mrp_add_ring_role(struct dsa_switch *ds, struct dsa_notifier_mrp_ring_role_info *info) { - int err = 0; - int port; - if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mrp_ring_role_match(ds, port, info)) { - err = ds->ops->port_mrp_add_ring_role(ds, port, - info->mrp); - if (err) - break; - } - } + if (ds->index == info->sw_index) + return ds->ops->port_mrp_add_ring_role(ds, info->port, + info->mrp); - return err; + return 0; } static int diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 2a6733a6449a..7e6b37a54add 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -95,7 +95,7 @@ static int get_module_eeprom_by_page(struct net_device *dev, if (dev->sfp_bus) return sfp_get_module_eeprom_by_page(dev->sfp_bus, page_data, extack); - if (ops->get_module_info) + if (ops->get_module_eeprom_by_page) return ops->get_module_eeprom_by_page(dev, page_data, extack); return -EOPNOTSUPP; @@ -159,9 +159,6 @@ static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr * request->offset = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_OFFSET]); request->length = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_LENGTH]); - if (!request->length) - return -EINVAL; - /* The following set of conditions limit the API to only dump 1/2 * EEPROM page without crossing low page boundary located at offset 128. * This means user may only request dumps of length limited to 128 from @@ -180,10 +177,6 @@ static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr * NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross half page boundary is illegal"); return -EINVAL; - } else if (request->offset >= ETH_MODULE_EEPROM_PAGE_LEN * 2) { - NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_OFFSET], - "offset is out of bounds"); - return -EINVAL; } else if (request->offset + request->length > ETH_MODULE_EEPROM_PAGE_LEN * 2) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross page boundary is illegal"); @@ -236,8 +229,10 @@ const struct ethnl_request_ops ethnl_module_eeprom_request_ops = { const struct nla_policy ethnl_module_eeprom_get_policy[] = { [ETHTOOL_A_MODULE_EEPROM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), - [ETHTOOL_A_MODULE_EEPROM_OFFSET] = { .type = NLA_U32 }, - [ETHTOOL_A_MODULE_EEPROM_LENGTH] = { .type = NLA_U32 }, + [ETHTOOL_A_MODULE_EEPROM_OFFSET] = + NLA_POLICY_MAX(NLA_U32, ETH_MODULE_EEPROM_PAGE_LEN * 2 - 1), + [ETHTOOL_A_MODULE_EEPROM_LENGTH] = + NLA_POLICY_RANGE(NLA_U32, 1, ETH_MODULE_EEPROM_PAGE_LEN), [ETHTOOL_A_MODULE_EEPROM_PAGE] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_BANK] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS] = diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 3fa7a394eabf..baa5d10043cb 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1421,7 +1421,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, if (eeprom.offset + eeprom.len > total_len) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1486,7 +1486,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1765,7 +1765,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) return -EFAULT; test.len = test_len; - data = kmalloc_array(test_len, sizeof(u64), GFP_USER); + data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM; @@ -2293,7 +2293,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); @@ -2485,7 +2485,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; if (phy_drv_tunable) { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 90b10966b16b..3e25a47fd482 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -380,7 +380,7 @@ extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_T extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; -extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_DATA + 1]; +extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index b3029fff715d..2d51b7ab4dc5 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -353,6 +353,8 @@ static int strset_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret; + len += nla_total_size(0); /* ETHTOOL_A_STRSET_STRINGSETS */ + for (i = 0; i < ETH_SS_COUNT; i++) { const struct strset_info *set_info = &data->sets[i]; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index bb1351c38397..e31949479305 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -397,7 +397,8 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, * ensures entries of restarted nodes gets pruned so that they can * re-register and resume communications. */ - if (seq_nr_before(sequence_nr, node->seq_out[port->type])) + if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && + seq_nr_before(sequence_nr, node->seq_out[port->type])) return; node->time_in[port->type] = jiffies; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 750f388a4a68..54648181dd56 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -575,7 +575,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, return err; } - if (!inet_sk(sk)->inet_num && inet_autobind(sk)) + if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, uaddr, addr_len); } @@ -803,7 +803,7 @@ int inet_send_prepare(struct sock *sk) sock_rps_record_flow(sk); /* We may need to bind the socket. */ - if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind && + if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index d6e3a92841e3..099259fc826a 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -471,6 +471,7 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) kfree(doi_def->map.std->lvl.local); kfree(doi_def->map.std->cat.cipso); kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); break; } kfree(doi_def); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 50deeff48c8b..73721a4448bd 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1989,7 +1989,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 2e09d62d59e3..0a57f1892e7e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); + /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7b272bbed2b4..6b3c558a4f23 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1801,6 +1801,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; + ip_mc_clear_src(i); ip_ma_put(i); } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fd472eae4f5c..0eea878edc30 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -135,10 +135,18 @@ static int inet_csk_bind_conflict(const struct sock *sk, bool relax, bool reuseport_ok) { struct sock *sk2; + bool reuseport_cb_ok; bool reuse = sk->sk_reuse; bool reuseport = !!sk->sk_reuseport; + struct sock_reuseport *reuseport_cb; kuid_t uid = sock_i_uid((struct sock *)sk); + rcu_read_lock(); + reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); + /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ + reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); + rcu_read_unlock(); + /* * Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed @@ -156,14 +164,14 @@ static int inet_csk_bind_conflict(const struct sock *sk, if ((!relax || (!reuseport_ok && reuseport && sk2->sk_reuseport && - !rcu_access_pointer(sk->sk_reuseport_cb) && + reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || uid_eq(uid, sock_i_uid(sk2))))) && inet_rcv_saddr_equal(sk, sk2, true)) break; } else if (!reuseport_ok || !reuseport || !sk2->sk_reuseport || - rcu_access_pointer(sk->sk_reuseport_cb) || + !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid(sk2)))) { if (inet_rcv_saddr_equal(sk, sk2, true)) @@ -687,6 +695,64 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); +static struct request_sock *inet_reqsk_clone(struct request_sock *req, + struct sock *sk) +{ + struct sock *req_sk, *nreq_sk; + struct request_sock *nreq; + + nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN); + if (!nreq) { + /* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */ + sock_put(sk); + return NULL; + } + + req_sk = req_to_sk(req); + nreq_sk = req_to_sk(nreq); + + memcpy(nreq_sk, req_sk, + offsetof(struct sock, sk_dontcopy_begin)); + memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); + + sk_node_init(&nreq_sk->sk_node); + nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; +#ifdef CONFIG_XPS + nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; +#endif + nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; + + nreq->rsk_listener = sk; + + /* We need not acquire fastopenq->lock + * because the child socket is locked in inet_csk_listen_stop(). + */ + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) + rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); + + return nreq; +} + +static void reqsk_queue_migrated(struct request_sock_queue *queue, + const struct request_sock *req) +{ + if (req->num_timeout == 0) + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); +} + +static void reqsk_migrate_reset(struct request_sock *req) +{ + req->saved_syn = NULL; +#if IS_ENABLED(CONFIG_IPV6) + inet_rsk(req)->ipv6_opt = NULL; + inet_rsk(req)->pktopts = NULL; +#else + inet_rsk(req)->ireq_opt = NULL; +#endif +} + /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { @@ -727,15 +793,39 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { struct request_sock *req = from_timer(req, t, rsk_timer); + struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; - struct net *net = sock_net(sk_listener); - struct inet_connection_sock *icsk = inet_csk(sk_listener); - struct request_sock_queue *queue = &icsk->icsk_accept_queue; + struct inet_connection_sock *icsk; + struct request_sock_queue *queue; + struct net *net; int max_syn_ack_retries, qlen, expire = 0, resend = 0; - if (inet_sk_state_load(sk_listener) != TCP_LISTEN) - goto drop; + if (inet_sk_state_load(sk_listener) != TCP_LISTEN) { + struct sock *nsk; + + nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL); + if (!nsk) + goto drop; + + nreq = inet_reqsk_clone(req, nsk); + if (!nreq) + goto drop; + /* The new timer for the cloned req can decrease the 2 + * by calling inet_csk_reqsk_queue_drop_and_put(), so + * hold another count to prevent use-after-free and + * call reqsk_put() just before return. + */ + refcount_set(&nreq->rsk_refcnt, 2 + 1); + timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); + reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); + + req = nreq; + sk_listener = nsk; + } + + icsk = inet_csk(sk_listener); + net = sock_net(sk_listener); max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. @@ -754,6 +844,7 @@ static void reqsk_timer_handler(struct timer_list *t) * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ + queue = &icsk->icsk_accept_queue; qlen = reqsk_queue_len(queue); if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; @@ -778,10 +869,36 @@ static void reqsk_timer_handler(struct timer_list *t) atomic_dec(&queue->young); timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); mod_timer(&req->rsk_timer, jiffies + timeo); + + if (!nreq) + return; + + if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { + /* delete timer */ + inet_csk_reqsk_queue_drop(sk_listener, nreq); + goto drop; + } + + reqsk_migrate_reset(oreq); + reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq); + reqsk_put(oreq); + + reqsk_put(nreq); return; } + drop: - inet_csk_reqsk_queue_drop_and_put(sk_listener, req); + /* Even if we can clone the req, we may need not retransmit any more + * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another + * CPU may win the "own_req" race so that inet_ehash_insert() fails. + */ + if (nreq) { + reqsk_migrate_reset(nreq); + reqsk_queue_removed(queue, nreq); + __reqsk_free(nreq); + } + + inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } static void reqsk_queue_hash_req(struct request_sock *req, @@ -997,12 +1114,40 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req) { if (own_req) { - inet_csk_reqsk_queue_drop(sk, req); - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - if (inet_csk_reqsk_queue_add(sk, req, child)) + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); + + if (sk != req->rsk_listener) { + /* another listening sk has been selected, + * migrate the req to it. + */ + struct request_sock *nreq; + + /* hold a refcnt for the nreq->rsk_listener + * which is assigned in inet_reqsk_clone() + */ + sock_hold(sk); + nreq = inet_reqsk_clone(req, sk); + if (!nreq) { + inet_child_forget(sk, req, child); + goto child_put; + } + + refcount_set(&nreq->rsk_refcnt, 1); + if (inet_csk_reqsk_queue_add(sk, nreq, child)) { + reqsk_migrate_reset(req); + reqsk_put(req); + return child; + } + + reqsk_migrate_reset(nreq); + __reqsk_free(nreq); + } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; + } } /* Too bad, another child took ownership of the request, undo. */ +child_put: bh_unlock_sock(child); sock_put(child); return NULL; @@ -1028,14 +1173,36 @@ void inet_csk_listen_stop(struct sock *sk) * of the variants now. --ANK */ while ((req = reqsk_queue_remove(queue, sk)) != NULL) { - struct sock *child = req->sk; + struct sock *child = req->sk, *nsk; + struct request_sock *nreq; local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); sock_hold(child); + nsk = reuseport_migrate_sock(sk, child, NULL); + if (nsk) { + nreq = inet_reqsk_clone(req, nsk); + if (nreq) { + refcount_set(&nreq->rsk_refcnt, 1); + + if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { + reqsk_migrate_reset(req); + } else { + reqsk_migrate_reset(nreq); + __reqsk_free(nreq); + } + + /* inet_csk_reqsk_queue_add() has already + * called inet_child_forget() on failure case. + */ + goto skip_child_forget; + } + } + inet_child_forget(sk, req, child); +skip_child_forget: reqsk_put(req); bh_unlock_sock(child); local_bh_enable(); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c96866a53a66..80aeaf9e6e16 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -697,7 +697,7 @@ void inet_unhash(struct sock *sk) goto unlock; if (rcu_access_pointer(sk->sk_reuseport_cb)) - reuseport_detach_sock(sk); + reuseport_stop_listen_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); ilb->count--; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 1c9f71a37258..95a718397fd1 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -954,6 +954,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false; /* We assume the packet has already been checked by icmp_rcv */ @@ -968,14 +969,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n"); - return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4c477475f4c..66aacb939d3e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2179,6 +2179,19 @@ martian_source: return err; } +/* get device for dst_alloc with local routes */ +static struct net_device *ip_rt_get_dev(struct net *net, + const struct fib_result *res) +{ + struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; + struct net_device *dev = NULL; + + if (nhc) + dev = l3mdev_master_dev_rcu(nhc->nhc_dev); + + return dev ? : net->loopback_dev; +} + /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet @@ -2335,7 +2348,7 @@ local_input: } } - rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, + rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4fa77f182dcb..6f1e64d49232 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -961,6 +961,15 @@ static struct ctl_table ipv4_net_table[] = { }, #endif { + .procname = "tcp_migrate_req", + .data = &init_net.ipv4.sysctl_tcp_migrate_req, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4f5b68a90be9..6cb8e269f1ab 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2002,13 +2002,21 @@ process: goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { - inet_csk_reqsk_queue_drop_and_put(sk, req); - goto lookup; + nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); + if (!nsk) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sk = nsk; + /* reuseport_migrate_sock() has already held one sk_refcnt + * before returning. + */ + } else { + /* We own a reference on the listener, increase it again + * as we might lose it too soon. + */ + sock_hold(sk); } - /* We own a reference on the listener, increase it again - * as we might lose it too soon. - */ - sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7513ba45553d..f258a4c0da71 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -775,8 +775,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, goto listen_overflow; if (own_req && rsk_drop_req(req)) { - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_drop_and_put(sk, req); + reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); return child; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 15f5504adf5b..1307ad0d3b9e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2607,6 +2607,9 @@ void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key)) { @@ -2857,10 +2860,17 @@ int udp_abort(struct sock *sk, int err) { lock_sock(sk); + /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + sk->sk_err = err; sk->sk_error_report(sk); __udp_disconnect(sk, 0); +out: release_sock(sk); return 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 048570900fdf..3bf685fe64b9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5827,7 +5827,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL; if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index e204163c7036..92f3235fa287 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -135,6 +135,17 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, } EXPORT_SYMBOL_GPL(nft_fib6_eval_type); +static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) +{ + if (likely(next != IPPROTO_ICMPV6)) + return false; + + if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) + return false; + + return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; +} + void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -163,10 +174,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph); - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && - nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv, nft_in(pkt)); - return; + if (nft_hook(pkt) == NF_INET_PRE_ROUTING || + nft_hook(pkt) == NF_INET_INGRESS) { + if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) || + nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } } *dest = 0; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 4ff38cb08f4b..60bf3b877957 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -87,10 +87,10 @@ struct seg6_end_dt_info { int vrf_ifindex; int vrf_table; - /* tunneled packet proto and family (IPv4 or IPv6) */ - __be16 proto; + /* tunneled packet family (IPv4 or IPv6). + * Protocol and header length are inferred from family. + */ u16 family; - int hdrlen; }; struct pcpu_seg6_local_counters { @@ -521,19 +521,6 @@ static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg, info->net = net; info->vrf_ifindex = vrf_ifindex; - switch (family) { - case AF_INET: - info->proto = htons(ETH_P_IP); - info->hdrlen = sizeof(struct iphdr); - break; - case AF_INET6: - info->proto = htons(ETH_P_IPV6); - info->hdrlen = sizeof(struct ipv6hdr); - break; - default: - return -EINVAL; - } - info->family = family; info->mode = DT_VRF_MODE; @@ -622,22 +609,44 @@ error: } static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb, - struct seg6_local_lwt *slwt) + struct seg6_local_lwt *slwt, u16 family) { struct seg6_end_dt_info *info = &slwt->dt_info; struct net_device *vrf; + __be16 protocol; + int hdrlen; vrf = end_dt_get_vrf_rcu(skb, info); if (unlikely(!vrf)) goto drop; - skb->protocol = info->proto; + switch (family) { + case AF_INET: + protocol = htons(ETH_P_IP); + hdrlen = sizeof(struct iphdr); + break; + case AF_INET6: + protocol = htons(ETH_P_IPV6); + hdrlen = sizeof(struct ipv6hdr); + break; + case AF_UNSPEC: + fallthrough; + default: + goto drop; + } + + if (unlikely(info->family != AF_UNSPEC && info->family != family)) { + pr_warn_once("seg6local: SRv6 End.DT* family mismatch"); + goto drop; + } + + skb->protocol = protocol; skb_dst_drop(skb); - skb_set_transport_header(skb, info->hdrlen); + skb_set_transport_header(skb, hdrlen); - return end_dt_vrf_rcv(skb, info->family, vrf); + return end_dt_vrf_rcv(skb, family, vrf); drop: kfree_skb(skb); @@ -656,7 +665,7 @@ static int input_action_end_dt4(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; - skb = end_dt_vrf_core(skb, slwt); + skb = end_dt_vrf_core(skb, slwt, AF_INET); if (!skb) /* packet has been processed and consumed by the VRF */ return 0; @@ -739,7 +748,7 @@ static int input_action_end_dt6(struct sk_buff *skb, goto legacy_mode; /* DT6_VRF_MODE */ - skb = end_dt_vrf_core(skb, slwt); + skb = end_dt_vrf_core(skb, slwt, AF_INET6); if (!skb) /* packet has been processed and consumed by the VRF */ return 0; @@ -767,6 +776,36 @@ drop: return -EINVAL; } +#ifdef CONFIG_NET_L3_MASTER_DEV +static int seg6_end_dt46_build(struct seg6_local_lwt *slwt, const void *cfg, + struct netlink_ext_ack *extack) +{ + return __seg6_end_dt_vrf_build(slwt, cfg, AF_UNSPEC, extack); +} + +static int input_action_end_dt46(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + unsigned int off = 0; + int nexthdr; + + nexthdr = ipv6_find_hdr(skb, &off, -1, NULL, NULL); + if (unlikely(nexthdr < 0)) + goto drop; + + switch (nexthdr) { + case IPPROTO_IPIP: + return input_action_end_dt4(skb, slwt); + case IPPROTO_IPV6: + return input_action_end_dt6(skb, slwt); + } + +drop: + kfree_skb(skb); + return -EINVAL; +} +#endif + /* push an SRH on top of the current one */ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) { @@ -969,6 +1008,17 @@ static struct seg6_action_desc seg6_action_table[] = { .input = input_action_end_dt6, }, { + .action = SEG6_LOCAL_ACTION_END_DT46, + .attrs = SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), + .optattrs = SEG6_F_LOCAL_COUNTERS, +#ifdef CONFIG_NET_L3_MASTER_DEV + .input = input_action_end_dt46, + .slwt_ops = { + .build_state = seg6_end_dt46_build, + }, +#endif + }, + { .action = SEG6_LOCAL_ACTION_END_B6, .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), .optattrs = SEG6_F_LOCAL_COUNTERS, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4435fa342e7a..4d71464094b3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1664,10 +1664,18 @@ process: goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { - inet_csk_reqsk_queue_drop_and_put(sk, req); - goto lookup; + nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); + if (!nsk) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sk = nsk; + /* reuseport_migrate_sock() has already held one sk_refcnt + * before returning. + */ + } else { + sock_hold(sk); } - sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 199b080d418a..3fcd86f4dfdc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1598,6 +1598,9 @@ void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 1c572c8daced..6201965bd822 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1066,11 +1066,6 @@ out_error: goto partial_message; } - if (skb_has_frag_list(head)) { - kfree_skb_list(skb_shinfo(head)->frag_list); - skb_shinfo(head)->frag_list = NULL; - } - if (head != kcm->seq_skb) kfree_skb(head); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 9245c0421bda..fc34ae2b604c 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -4,7 +4,7 @@ * * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2019, 2021 Intel Corporation */ #include <linux/debugfs.h> @@ -387,10 +387,17 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; + int ret; rtnl_lock(); + wiphy_lock(local->hw.wiphy); __ieee80211_suspend(&local->hw, NULL); - __ieee80211_resume(&local->hw); + ret = __ieee80211_resume(&local->hw); + wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); return count; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 214404a558fb..648696b49f89 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1442,7 +1442,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (WARN_ON_ONCE(!chanctx_conf)) { + if (!chanctx_conf) { rcu_read_unlock(); return NULL; } diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 2e2f73a4aa73..137fa4c50e07 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -476,14 +476,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do GFP_KERNEL); } - /* APs need special treatment */ if (sdata->vif.type == NL80211_IFTYPE_AP) { - struct ieee80211_sub_if_data *vlan, *tmpsdata; - - /* down all dependent devices, that is VLANs */ - list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, - u.vlan.list) - dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); } else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* remove all packets in parent bc_buf pointing to this dev */ @@ -641,6 +634,15 @@ static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + /* close all dependent VLAN interfaces before locking wiphy */ + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct ieee80211_sub_if_data *vlan, *tmpsdata; + + list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, + u.vlan.list) + dev_close(vlan->dev); + } + wiphy_lock(sdata->local->hw.wiphy); ieee80211_do_stop(sdata, true); wiphy_unlock(sdata->local->hw.wiphy); @@ -1591,6 +1593,9 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: + if (!list_empty(&sdata->u.ap.vlans)) + return -EBUSY; + break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_OCB: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 62145e5f9628..f33a3acd7f96 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -252,6 +252,7 @@ static void ieee80211_restart_work(struct work_struct *work) struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); struct ieee80211_sub_if_data *sdata; + int ret; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -301,8 +302,12 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for all packet processing to be done */ synchronize_net(); - ieee80211_reconfig(local); + ret = ieee80211_reconfig(local); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2480bd0577bb..3f2aad2e7436 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4062,10 +4062,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (elems.mbssid_config_ie) bss_conf->profile_periodicity = elems.mbssid_config_ie->profile_periodicity; + else + bss_conf->profile_periodicity = 0; if (elems.ext_capab_len >= 11 && (elems.ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) bss_conf->ema_ap = true; + else + bss_conf->ema_ap = false; /* continue assoc process */ ifmgd->assoc_data->timeout = jiffies; @@ -5802,12 +5806,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 3) sdata->vif.bss_conf.profile_periodicity = elem->data[2]; + else + sdata->vif.bss_conf.profile_periodicity = 0; elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 11 && (elem->data[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) sdata->vif.bss_conf.ema_ap = true; + else + sdata->vif.bss_conf.ema_ap = false; } else { assoc_data->timeout = jiffies; assoc_data->timeout_started = true; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 6487b05da6fa..a6f3fb4a9197 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1514,7 +1514,7 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) return; - if (time_is_before_jiffies(mi->sample_time)) + if (time_is_after_jiffies(mi->sample_time)) return; mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1bb43edd47b6..af0ef456eb0f 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2240,17 +2240,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (is_multicast_ether_addr(hdr->addr1)) { - I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); - goto out_no_led; - } - if (rx->sta) cache = &rx->sta->frags; if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out; + if (is_multicast_ether_addr(hdr->addr1)) + return RX_DROP_MONITOR; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -2376,7 +2374,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) out: ieee80211_led_rx(rx->local); - out_no_led: if (rx->sta) rx->sta->rx_stats.packets++; return RX_CONTINUE; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d4cc9ac2d703..6b50cb5e0e3c 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -251,13 +251,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; + size_t min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); + + if (!ieee80211_is_probe_resp(mgmt->frame_control) && + !ieee80211_is_beacon(mgmt->frame_control) && + !ieee80211_is_s1g_beacon(mgmt->frame_control)) + return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { - if (skb->len < 15) - return; - } else if (skb->len < 24 || - (!ieee80211_is_probe_resp(mgmt->frame_control) && - !ieee80211_is_beacon(mgmt->frame_control))) + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon); + } + + if (skb->len < min_hdr_len) return; sdata1 = rcu_dereference(local->scan_sdata); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0b719f3d2dec..2651498d05e8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2014,6 +2014,26 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, ieee80211_tx(sdata, sta, skb, false); } +static bool ieee80211_validate_radiotap_len(struct sk_buff *skb) +{ + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *)skb->data; + + /* check for not even having the fixed radiotap header part */ + if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) + return false; /* too short to be possibly valid */ + + /* is it a header version we can trust to find length from? */ + if (unlikely(rthdr->it_version)) + return false; /* only version 0 is supported */ + + /* does the skb contain enough to deliver on the alleged length? */ + if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) + return false; /* skb too short for claimed rt header extent */ + + return true; +} + bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev) { @@ -2022,8 +2042,6 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[info->band]; int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, NULL); u16 txflags; @@ -2036,17 +2054,8 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, u8 vht_mcs = 0, vht_nss = 0; int i; - /* check for not even having the fixed radiotap header part */ - if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) - return false; /* too short to be possibly valid */ - - /* is it a header version we can trust to find length from? */ - if (unlikely(rthdr->it_version)) - return false; /* only version 0 is supported */ - - /* does the skb contain enough to deliver on the alleged length? */ - if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) - return false; /* skb too short for claimed rt header extent */ + if (!ieee80211_validate_radiotap_len(skb)) + return false; info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -2186,6 +2195,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, return false; if (rate_found) { + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[info->band]; + info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { @@ -2199,7 +2211,7 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(info->control.rates, vht_mcs, vht_nss); - } else { + } else if (sband) { for (i = 0; i < sband->n_bitrates; i++) { if (rate * 5 != sband->bitrates[i].bitrate) continue; @@ -2236,8 +2248,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_CTL_INJECTED; - /* Sanity-check and process the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(skb, dev)) + /* Sanity-check the length of the radiotap header */ + if (!ieee80211_validate_radiotap_len(skb)) goto fail; /* we now know there is a radiotap header with a length we can use */ @@ -2351,6 +2363,14 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, ieee80211_select_queue_80211(sdata, skb, hdr); skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority)); + /* + * Process the radiotap header. This will now take into account the + * selected chandef above to accurately set injection rates and + * retransmissions. + */ + if (!ieee80211_parse_tx_radiotap(skb, dev)) + goto fail_rcu; + /* remove the injection radiotap header */ skb_pull(skb, len_rthdr); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 0a0481f5af48..060059ef9668 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -947,7 +947,7 @@ static void ieee80211_parse_extension_element(u32 *crc, switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: - if (len == sizeof(*elems->mu_edca_param_set)) { + if (len >= sizeof(*elems->mu_edca_param_set)) { elems->mu_edca_param_set = data; if (crc) *crc = crc32_be(*crc, (void *)elem, @@ -968,7 +968,7 @@ static void ieee80211_parse_extension_element(u32 *crc, } break; case WLAN_EID_EXT_UORA: - if (len == 1) + if (len >= 1) elems->uora_element = data; break; case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: @@ -976,7 +976,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->max_channel_switch_time = data; break; case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: - if (len == sizeof(*elems->mbssid_config_ie)) + if (len >= sizeof(*elems->mbssid_config_ie)) elems->mbssid_config_ie = data; break; case WLAN_EID_EXT_HE_SPR: @@ -985,7 +985,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->he_spr = data; break; case WLAN_EID_EXT_HE_6GHZ_CAPA: - if (len == sizeof(*elems->he_6ghz_capa)) + if (len >= sizeof(*elems->he_6ghz_capa)) elems->he_6ghz_capa = data; break; } @@ -1074,14 +1074,14 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, switch (id) { case WLAN_EID_LINK_ID: - if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) { + if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { elem_parse_failed = true; break; } elems->lnk_id = (void *)(pos - 2); break; case WLAN_EID_CHAN_SWITCH_TIMING: - if (elen != sizeof(struct ieee80211_ch_switch_timing)) { + if (elen < sizeof(struct ieee80211_ch_switch_timing)) { elem_parse_failed = true; break; } @@ -1244,7 +1244,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->sec_chan_offs = (void *)pos; break; case WLAN_EID_CHAN_SWITCH_PARAM: - if (elen != + if (elen < sizeof(*elems->mesh_chansw_params_ie)) { elem_parse_failed = true; break; @@ -1253,7 +1253,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, break; case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: if (!action || - elen != sizeof(*elems->wide_bw_chansw_ie)) { + elen < sizeof(*elems->wide_bw_chansw_ie)) { elem_parse_failed = true; break; } @@ -1272,7 +1272,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, ie = cfg80211_find_ie(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, pos, elen); if (ie) { - if (ie[1] == sizeof(*elems->wide_bw_chansw_ie)) + if (ie[1] >= sizeof(*elems->wide_bw_chansw_ie)) elems->wide_bw_chansw_ie = (void *)(ie + 2); else @@ -1316,7 +1316,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; case WLAN_EID_ADDBA_EXT: - if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + if (elen < sizeof(struct ieee80211_addba_ext_ie)) { elem_parse_failed = true; break; } @@ -1342,7 +1342,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem, elems); break; case WLAN_EID_S1G_CAPABILITIES: - if (elen == sizeof(*elems->s1g_capab)) + if (elen >= sizeof(*elems->s1g_capab)) elems->s1g_capab = (void *)pos; else elem_parse_failed = true; @@ -2178,8 +2178,6 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) list_for_each_entry(ctx, &local->chanctx_list, list) ctx->driver_present = false; mutex_unlock(&local->chanctx_mtx); - - cfg80211_shutdown_all_interfaces(local->hw.wiphy); } static void ieee80211_assign_chanctx(struct ieee80211_local *local, diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 1ec4d36a39f0..7d738bd06f2c 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -23,6 +23,8 @@ struct mptcp_pernet { u8 mptcp_enabled; unsigned int add_addr_timeout; + u8 checksum_enabled; + u8 allow_join_initial_addr_port; }; static struct mptcp_pernet *mptcp_get_pernet(struct net *net) @@ -40,10 +42,22 @@ unsigned int mptcp_get_add_addr_timeout(struct net *net) return mptcp_get_pernet(net)->add_addr_timeout; } +int mptcp_is_checksum_enabled(struct net *net) +{ + return mptcp_get_pernet(net)->checksum_enabled; +} + +int mptcp_allow_join_id0(struct net *net) +{ + return mptcp_get_pernet(net)->allow_join_initial_addr_port; +} + static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->checksum_enabled = 0; + pernet->allow_join_initial_addr_port = 1; } #ifdef CONFIG_SYSCTL @@ -65,6 +79,22 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "checksum_enabled", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + { + .procname = "allow_join_initial_addr_port", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, {} }; @@ -82,6 +112,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[0].data = &pernet->mptcp_enabled; table[1].data = &pernet->add_addr_timeout; + table[2].data = &pernet->checksum_enabled; + table[3].data = &pernet->allow_join_initial_addr_port; hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table); if (!hdr) diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index eb2dc6dbe212..52ea2517e856 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -25,6 +25,8 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), + SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH), + SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR), SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index f0da4f060fe1..193466c9b549 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -18,6 +18,8 @@ enum linux_mptcp_mib_field { MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ + MPTCP_MIB_DSSTCPMISMATCH, /* DSS-mapping did not map with TCP's sequence numbers */ + MPTCP_MIB_DATACSUMERR, /* The data checksum fail */ MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */ MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */ MPTCP_MIB_OFOMERGE, /* Segments merged in OoO queue */ diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index f16d9b5ee978..8f88ddeab6a2 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -144,6 +144,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, info->mptcpi_write_seq = READ_ONCE(msk->write_seq); info->mptcpi_snd_una = READ_ONCE(msk->snd_una); info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); + info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); unlock_sock_fast(sk, slow); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 6b825fb3fa83..a05270996613 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -44,7 +44,20 @@ static void mptcp_parse_option(const struct sk_buff *skb, else expected_opsize = TCPOLEN_MPTCP_MPC_SYN; } - if (opsize != expected_opsize) + + /* Cfr RFC 8684 Section 3.3.0: + * If a checksum is present but its use had + * not been negotiated in the MP_CAPABLE handshake, the receiver MUST + * close the subflow with a RST, as it is not behaving as negotiated. + * If a checksum is not present when its use has been negotiated, the + * receiver MUST close the subflow with a RST, as it is considered + * broken + * We parse even option with mismatching csum presence, so that + * later in subflow_data_ready we can trigger the reset. + */ + if (opsize != expected_opsize && + (expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA || + opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM)) break; /* try to be gentle vs future versions on the initial syn */ @@ -66,16 +79,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, * host requires the use of checksums, checksums MUST be used. * In other words, the only way for checksums not to be used * is if both hosts in their SYNs set A=0." - * - * Section 3.3.0: - * "If a checksum is not present when its use has been - * negotiated, the receiver MUST close the subflow with a RST as - * it is considered broken." - * - * We don't implement DSS checksum - fall back to TCP. */ if (flags & MPTCP_CAP_CHECKSUM_REQD) - break; + mp_opt->csum_reqd = 1; + + if (flags & MPTCP_CAP_DENY_JOIN_ID0) + mp_opt->deny_join_id0 = 1; mp_opt->mp_capable = 1; if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { @@ -86,7 +95,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; } - if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) { + if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) { /* Section 3.1.: * "the data parameters in a MP_CAPABLE are semantically * equivalent to those in a DSS option and can be used @@ -98,9 +107,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } - pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d", + if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { + mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum_reqd = 1; + ptr += 2; + } + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", version, flags, opsize, mp_opt->sndr_key, - mp_opt->rcvr_key, mp_opt->data_len); + mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; case MPTCPOPT_MP_JOIN: @@ -171,10 +185,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, expected_opsize += TCPOLEN_MPTCP_DSS_MAP32; } - /* RFC 6824, Section 3.3: - * If a checksum is present, but its use had - * not been negotiated in the MP_CAPABLE handshake, - * the checksum field MUST be ignored. + /* Always parse any csum presence combination, we will enforce + * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) @@ -209,9 +221,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u", + if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { + mp_opt->csum_reqd = 1; + mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + ptr += 2; + } + + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", mp_opt->data_seq, mp_opt->subflow_seq, - mp_opt->data_len); + mp_opt->data_len, mp_opt->csum_reqd, mp_opt->csum); } break; @@ -323,9 +341,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); const struct tcphdr *th = tcp_hdr(skb); const unsigned char *ptr; int length; @@ -341,6 +362,8 @@ void mptcp_get_options(const struct sk_buff *skb, mp_opt->dss = 0; mp_opt->mp_prio = 0; mp_opt->reset = 0; + mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled); + mp_opt->deny_join_id0 = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -356,6 +379,8 @@ void mptcp_get_options(const struct sk_buff *skb, length--; continue; default: + if (length < 2) + return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; @@ -380,6 +405,8 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { opts->suboptions = OPTION_MPTCP_MPC_SYN; + opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk)); + opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { @@ -435,8 +462,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_ext *mpext; unsigned int data_len; + u8 len; /* When skb is not available, we better over-estimate the emitted * options len. A full DSS option (28 bytes) is longer than @@ -465,16 +494,27 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, opts->suboptions = OPTION_MPTCP_MPC_ACK; opts->sndr_key = subflow->local_key; opts->rcvr_key = subflow->remote_key; + opts->csum_reqd = READ_ONCE(msk->csum_enabled); + opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); /* Section 3.1. * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK * packets that start the first subflow of an MPTCP connection, * as well as the first packet that carries data */ - if (data_len > 0) - *size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4); - else + if (data_len > 0) { + len = TCPOLEN_MPTCP_MPC_ACK_DATA; + if (opts->csum_reqd) { + /* we need to propagate more info to csum the pseudo hdr */ + opts->ext_copy.data_seq = mpext->data_seq; + opts->ext_copy.subflow_seq = mpext->subflow_seq; + opts->ext_copy.csum = mpext->csum; + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } + *size = ALIGN(len, 4); + } else { *size = TCPOLEN_MPTCP_MPC_ACK; + } pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", subflow, subflow->local_key, subflow->remote_key, @@ -535,18 +575,21 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, bool ret = false; u64 ack_seq; + opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { - unsigned int map_size; + unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; - map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; + if (mpext) { + if (opts->csum_reqd) + map_size += TCPOLEN_MPTCP_DSS_CHECKSUM; - remaining -= map_size; - dss_size = map_size; - if (mpext) opts->ext_copy = *mpext; + } + remaining -= map_size; + dss_size = map_size; if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; @@ -789,6 +832,8 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, if (subflow_req->mp_capable) { opts->suboptions = OPTION_MPTCP_MPC_SYNACK; opts->sndr_key = subflow_req->local_key; + opts->csum_reqd = subflow_req->csum_reqd; + opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; pr_debug("subflow_req=%p, local_key=%llu", subflow_req, subflow_req->local_key); @@ -867,6 +912,9 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); mptcp_subflow_fully_established(subflow, mp_opt); @@ -1007,7 +1055,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return; } - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; @@ -1099,6 +1147,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } mpext->data_len = mp_opt.data_len; mpext->use_map = 1; + mpext->csum_reqd = mp_opt.csum_reqd; + + if (mpext->csum_reqd) + mpext->csum = mp_opt.csum; } } @@ -1118,25 +1170,53 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } +static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +{ + struct csum_pseudo_header header; + __wsum csum; + + /* cfr RFC 8684 3.3.1.: + * the data sequence number used in the pseudo-header is + * always the 64-bit value, irrespective of what length is used in the + * DSS option itself. + */ + header.data_seq = cpu_to_be64(mpext->data_seq); + header.subflow_seq = htonl(mpext->subflow_seq); + header.data_len = htons(mpext->data_len); + header.csum = 0; + + csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum)); + return (__force u16)csum_fold(csum); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions) { - u8 len; + u8 len, flag = MPTCP_CAP_HMAC_SHA256; - if (OPTION_MPTCP_MPC_SYN & opts->suboptions) + if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYN; - else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) + } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYNACK; - else if (opts->ext_copy.data_len) + } else if (opts->ext_copy.data_len) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; - else + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } else { len = TCPOLEN_MPTCP_MPC_ACK; + } + + if (opts->csum_reqd) + flag |= MPTCP_CAP_CHECKSUM_REQD; + + if (!opts->allow_join_id0) + flag |= MPTCP_CAP_DENY_JOIN_ID0; *ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len, MPTCP_SUPPORTED_VERSION, - MPTCP_CAP_HMAC_SHA256); + flag); if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions)) @@ -1152,8 +1232,13 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, if (!opts->ext_copy.data_len) goto mp_capable_done; - put_unaligned_be32(opts->ext_copy.data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + if (opts->csum_reqd) { + put_unaligned_be32(opts->ext_copy.data_len << 16 | + mptcp_make_csum(&opts->ext_copy), ptr); + } else { + put_unaligned_be32(opts->ext_copy.data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } ptr += 1; } @@ -1305,6 +1390,9 @@ mp_capable_done: flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; if (mpext->data_fin) flags |= MPTCP_DSS_DATA_FIN; + + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); @@ -1324,8 +1412,13 @@ mp_capable_done: ptr += 2; put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; - put_unaligned_be32(mpext->data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + if (opts->csum_reqd) { + put_unaligned_be32(mpext->data_len << 16 | + mptcp_make_csum(mpext), ptr); + } else { + put_unaligned_be32(mpext->data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } } } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 9d00fa6d22e9..639271e09604 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -320,6 +320,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk) WRITE_ONCE(msk->pm.addr_signal, 0); WRITE_ONCE(msk->pm.accept_addr, false); WRITE_ONCE(msk->pm.accept_subflow, false); + WRITE_ONCE(msk->pm.remote_deny_join_id0, false); msk->pm.status = 0; spin_lock_init(&msk->pm.lock); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 09722598994d..d2591ebf01d9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -451,7 +451,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check if should create a new subflow */ if (msk->pm.local_addr_used < local_addr_max && - msk->pm.subflows < subflows_max) { + msk->pm.subflows < subflows_max && + !READ_ONCE(msk->pm.remote_deny_join_id0)) { local = select_local_address(pernet, msk); if (local) { struct mptcp_addr_info remote = { 0 }; @@ -540,6 +541,7 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); if (subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for %s%s%s", @@ -547,9 +549,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "", mptcp_pm_should_add_signal_port(msk) ? " [port]" : ""); - lock_sock(ssk); + slow = lock_sock_fast(ssk); tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); spin_lock_bh(&msk->pm.lock); } } @@ -566,6 +568,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct sock *sk = (struct sock *)msk; struct mptcp_addr_info local; + bool slow; local_address((struct sock_common *)ssk, &local); if (!addresses_equal(&local, addr, addr->port)) @@ -578,9 +581,9 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for mp_prio"); - lock_sock(ssk); + slow = lock_sock_fast(ssk); tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); spin_lock_bh(&msk->pm.lock); return 0; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 993095089990..ce0c45dfb79e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -286,11 +286,13 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, /* try to fetch required memory from subflow */ if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - if (ssk->sk_forward_alloc < skb->truesize) - goto drop; - __sk_mem_reclaim(ssk, skb->truesize); - if (!sk_rmem_schedule(sk, skb, skb->truesize)) + int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT; + + if (ssk->sk_forward_alloc < amount) goto drop; + + ssk->sk_forward_alloc -= amount; + sk->sk_forward_alloc += amount; } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -431,56 +433,55 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; - lock_sock(ssk); + slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); } } -static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) { - int ret; + bool slow; - lock_sock(ssk); - ret = tcp_can_send_ack(ssk); - if (ret) + slow = lock_sock_fast(ssk); + if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, 1); - release_sock(ssk); - return ret; + unlock_sock_fast(ssk, slow); +} + +static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) +{ + const struct inet_connection_sock *icsk = inet_csk(ssk); + bool ack_pending = READ_ONCE(icsk->icsk_ack.pending); + const struct tcp_sock *tp = tcp_sk(ssk); + + return (ack_pending & ICSK_ACK_SCHED) && + ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > + READ_ONCE(icsk->icsk_ack.rcv_mss)) || + (rx_empty && ack_pending & + (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) { - struct sock *ack_hint = READ_ONCE(msk->ack_hint); int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - bool cleanup; + int space = __mptcp_space(sk); + bool cleanup, rx_empty; - /* this is a simple superset of what tcp_cleanup_rbuf() implements - * so that we don't have to acquire the ssk socket lock most of the time - * to do actually nothing - */ - cleanup = __mptcp_space(sk) - old_space >= max(0, old_space); - if (!cleanup) - return; + cleanup = (space > 0) && (space >= (old_space << 1)); + rx_empty = !atomic_read(&sk->sk_rmem_alloc); - /* if the hinted ssk is still active, try to use it */ - if (likely(ack_hint)) { - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk)) - return; - } + if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) + mptcp_subflow_cleanup_rbuf(ssk); } - - /* otherwise pick the first active subflow */ - mptcp_for_each_subflow(msk, subflow) - if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow))) - return; } static bool mptcp_check_data_fin(struct sock *sk) @@ -625,7 +626,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, break; } } while (more_data_avail); - WRITE_ONCE(msk->ack_hint, ssk); *bytes += moved; return done; @@ -677,18 +677,19 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ -static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; - if (inet_sk_state_load(sk) == TCP_CLOSE) - return; - - mptcp_data_lock(sk); - __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); + if (unlikely(ssk->sk_err)) { + if (!sock_owned_by_user(sk)) + __mptcp_error_report(sk); + else + set_bit(MPTCP_ERROR_REPORT, &msk->flags); + } /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but @@ -697,7 +698,7 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); - mptcp_data_unlock(sk); + return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) @@ -705,7 +706,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; - bool wake; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -714,28 +714,22 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - /* move_skbs_to_msk below can legitly clear the data_avail flag, - * but we will need later to properly woke the reader, cache its - * value - */ - wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL; - if (wake) - set_bit(MPTCP_DATA_READY, &msk->flags); - ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; - /* over limit? can't append more skbs to msk */ + /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) - goto wake; - - move_skbs_to_msk(msk, ssk); + return; -wake: - if (wake) + /* Wake-up the reader only for in-sequence data */ + mptcp_data_lock(sk); + if (move_skbs_to_msk(msk, ssk)) { + set_bit(MPTCP_DATA_READY, &msk->flags); sk->sk_data_ready(sk); + } + mptcp_data_unlock(sk); } static bool mptcp_do_flush_join_list(struct mptcp_sock *msk) @@ -867,7 +861,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) sock_owned_by_me(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->data_avail) + if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } @@ -903,22 +897,14 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, df->data_seq + df->data_len == msk->write_seq; } -static int mptcp_wmem_with_overhead(struct sock *sk, int size) +static int mptcp_wmem_with_overhead(int size) { - struct mptcp_sock *msk = mptcp_sk(sk); - int ret, skbs; - - ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT); - skbs = (msk->tx_pending_data + size) / msk->size_goal_cache; - if (skbs < msk->skb_tx_cache.qlen) - return ret; - - return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER); + return size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT); } static void __mptcp_wmem_reserve(struct sock *sk, int size) { - int amount = mptcp_wmem_with_overhead(sk, size); + int amount = mptcp_wmem_with_overhead(size); struct mptcp_sock *msk = mptcp_sk(sk); WARN_ON_ONCE(msk->wmem_reserved); @@ -1213,49 +1199,8 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) return NULL; } -static bool mptcp_tx_cache_refill(struct sock *sk, int size, - struct sk_buff_head *skbs, int *total_ts) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - struct sk_buff *skb; - int space_needed; - - if (unlikely(tcp_under_memory_pressure(sk))) { - mptcp_mem_reclaim_partial(sk); - - /* under pressure pre-allocate at most a single skb */ - if (msk->skb_tx_cache.qlen) - return true; - space_needed = msk->size_goal_cache; - } else { - space_needed = msk->tx_pending_data + size - - msk->skb_tx_cache.qlen * msk->size_goal_cache; - } - - while (space_needed > 0) { - skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation); - if (unlikely(!skb)) { - /* under memory pressure, try to pass the caller a - * single skb to allow forward progress - */ - while (skbs->qlen > 1) { - skb = __skb_dequeue_tail(skbs); - *total_ts -= skb->truesize; - __kfree_skb(skb); - } - return skbs->qlen > 0; - } - - *total_ts += skb->truesize; - __skb_queue_tail(skbs, skb); - space_needed -= msk->size_goal_cache; - } - return true; -} - static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { - struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb; if (ssk->sk_tx_skb_cache) { @@ -1266,22 +1211,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) return true; } - skb = skb_peek(&msk->skb_tx_cache); - if (skb) { - if (likely(sk_wmem_schedule(ssk, skb->truesize))) { - skb = __skb_dequeue(&msk->skb_tx_cache); - if (WARN_ON_ONCE(!skb)) - return false; - - mptcp_wmem_uncharge(sk, skb->truesize); - ssk->sk_tx_skb_cache = skb; - return true; - } - - /* over memory limit, no point to try to allocate a new skb */ - return false; - } - skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) return false; @@ -1297,7 +1226,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk) { return !ssk->sk_tx_skb_cache && - !skb_peek(&mptcp_sk(sk)->skb_tx_cache) && tcp_under_memory_pressure(sk); } @@ -1308,6 +1236,18 @@ static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk) return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation); } +/* note: this always recompute the csum on the whole skb, even + * if we just appended a single frag. More status info needed + */ +static void mptcp_update_data_checksum(struct sk_buff *skb, int added) +{ + struct mptcp_ext *mpext = mptcp_get_ext(skb); + __wsum csum = ~csum_unfold(mpext->csum); + int offset = skb->len - added; + + mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset)); +} + static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) @@ -1328,7 +1268,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, /* compute send limit */ info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); avail_size = info->size_goal; - msk->size_goal_cache = info->size_goal; skb = tcp_write_queue_tail(ssk); if (skb) { /* Limit the write to the size available in the @@ -1402,10 +1341,14 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (zero_window_probe) { mptcp_subflow_ctx(ssk)->rel_write_seq += ret; mpext->frozen = 1; - ret = 0; + if (READ_ONCE(msk->csum_enabled)) + mptcp_update_data_checksum(tail, ret); tcp_push_pending_frames(ssk); + return 0; } out: + if (READ_ONCE(msk->csum_enabled)) + mptcp_update_data_checksum(tail, ret); mptcp_subflow_ctx(ssk)->rel_write_seq += ret; return ret; } @@ -1673,7 +1616,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) while (msg_data_left(msg)) { int total_ts, frag_truesize = 0; struct mptcp_data_frag *dfrag; - struct sk_buff_head skbs; bool dfrag_collapsed; size_t psize, offset; @@ -1706,16 +1648,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); total_ts = psize + frag_truesize; - __skb_queue_head_init(&skbs); - if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts)) - goto wait_for_memory; - if (!mptcp_wmem_alloc(sk, total_ts)) { - __skb_queue_purge(&skbs); + if (!mptcp_wmem_alloc(sk, total_ts)) goto wait_for_memory; - } - skb_queue_splice_tail(&skbs, &msk->skb_tx_cache); if (copy_page_from_iter(dfrag->page, offset, psize, &msg->msg_iter) != psize) { mptcp_wmem_uncharge(sk, psize + frag_truesize); @@ -1772,7 +1708,7 @@ static void mptcp_wait_data(struct sock *sk, long *timeo) sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); sk_wait_event(sk, timeo, - test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + test_bit(MPTCP_DATA_READY, &msk->flags), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1970,7 +1906,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); - tcp_cleanup_rbuf(ssk, moved); + + if (unlikely(ssk->sk_err)) + __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); @@ -1983,7 +1921,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) ret |= __mptcp_ofo_queue(msk); __mptcp_splice_receive_queue(sk); mptcp_data_unlock(sk); - mptcp_cleanup_rbuf(msk); } if (ret) mptcp_check_data_fin((struct sock *)msk); @@ -2093,10 +2030,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, */ if (unlikely(__mptcp_move_skbs(msk))) set_bit(MPTCP_DATA_READY, &msk->flags); - } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) { - /* data to read but mptcp_wait_data() cleared DATA_READY */ - set_bit(MPTCP_DATA_READY, &msk->flags); } + out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS) @@ -2234,9 +2169,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *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; @@ -2308,13 +2240,14 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + bool slow; - lock_sock(tcp_sk); + slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { tcp_send_active_reset(tcp_sk, GFP_ATOMIC); tcp_set_state(tcp_sk, TCP_CLOSE); } - release_sock(tcp_sk); + unlock_sock_fast(tcp_sk, slow); } inet_sk_state_store(sk, TCP_CLOSE); @@ -2359,8 +2292,8 @@ static void __mptcp_retrans(struct sock *sk) /* limit retransmission to the bytes already sent on some subflows */ info.sent = 0; - info.limit = dfrag->already_sent; - while (info.sent < dfrag->already_sent) { + info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; + while (info.sent < info.limit) { if (!mptcp_alloc_tx_skb(sk, ssk)) break; @@ -2372,9 +2305,11 @@ static void __mptcp_retrans(struct sock *sk) copied += ret; info.sent += ret; } - if (copied) + if (copied) { + dfrag->already_sent = max(dfrag->already_sent, info.sent); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); + } mptcp_set_timeout(sk, ssk); release_sock(ssk); @@ -2442,17 +2377,15 @@ static int __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); __skb_queue_head_init(&msk->receive_queue); - __skb_queue_head_init(&msk->skb_tx_cache); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->wmem_reserved = 0; msk->rmem_released = 0; msk->tx_pending_data = 0; - msk->size_goal_cache = TCP_BASE_MSS; - msk->ack_hint = NULL; msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; + WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_init(msk); @@ -2504,15 +2437,10 @@ static void __mptcp_clear_xmit(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - struct sk_buff *skb; WRITE_ONCE(msk->first_pending, NULL); list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); - while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) { - sk->sk_forward_alloc += skb->truesize; - kfree_skb(skb); - } } static void mptcp_cancel_work(struct sock *sk) @@ -2793,6 +2721,8 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->token = subflow_req->token; msk->subflow = NULL; WRITE_ONCE(msk->fully_established, false); + if (mp_opt->csum_reqd) + WRITE_ONCE(msk->csum_enabled, true); msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 89f6b73783d5..d8ad3270dfab 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -68,6 +68,8 @@ #define TCPOLEN_MPTCP_FASTCLOSE 12 #define TCPOLEN_MPTCP_RST 4 +#define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM (TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA) + /* MPTCP MP_JOIN flags */ #define MPTCPOPT_BACKUP BIT(0) #define MPTCPOPT_HMAC_LEN 20 @@ -77,8 +79,9 @@ #define MPTCP_VERSION_MASK (0x0F) #define MPTCP_CAP_CHECKSUM_REQD BIT(7) #define MPTCP_CAP_EXTENSIBILITY BIT(6) +#define MPTCP_CAP_DENY_JOIN_ID0 BIT(5) #define MPTCP_CAP_HMAC_SHA256 BIT(0) -#define MPTCP_CAP_FLAG_MASK (0x3F) +#define MPTCP_CAP_FLAG_MASK (0x1F) /* MPTCP DSS flags */ #define MPTCP_DSS_DATA_FIN BIT(4) @@ -124,6 +127,7 @@ struct mptcp_options_received { u64 data_seq; u32 subflow_seq; u16 data_len; + __sum16 csum; u16 mp_capable : 1, mp_join : 1, fastclose : 1, @@ -133,7 +137,9 @@ struct mptcp_options_received { rm_addr : 1, mp_prio : 1, echo : 1, - backup : 1; + csum_reqd : 1, + backup : 1, + deny_join_id0 : 1; u32 token; u32 nonce; u64 thmac; @@ -188,6 +194,7 @@ struct mptcp_pm_data { bool work_pending; bool accept_addr; bool accept_subflow; + bool remote_deny_join_id0; u8 add_addr_signaled; u8 add_addr_accepted; u8 local_addr_used; @@ -234,15 +241,13 @@ struct mptcp_sock { bool snd_data_fin_enable; bool rcv_fastclose; bool use_64bit_ack; /* Set when we received a 64-bit DSN */ + bool csum_enabled; spinlock_t join_list_lock; - struct sock *ack_hint; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; struct sk_buff_head receive_queue; - struct sk_buff_head skb_tx_cache; /* this is wmem accounted */ int tx_pending_data; - int size_goal_cache; struct list_head conn_list; struct list_head rtx_queue; struct mptcp_data_frag *first_pending; @@ -335,11 +340,20 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk) return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); } +struct csum_pseudo_header { + __be64 data_seq; + __be32 subflow_seq; + __be16 data_len; + __sum16 csum; +}; + struct mptcp_subflow_request_sock { struct tcp_request_sock sk; u16 mp_capable : 1, mp_join : 1, - backup : 1; + backup : 1, + csum_reqd : 1, + allow_join_id0 : 1; u8 local_id; u8 remote_id; u64 local_key; @@ -362,7 +376,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) enum mptcp_data_avail { MPTCP_SUBFLOW_NODATA, MPTCP_SUBFLOW_DATA_AVAIL, - MPTCP_SUBFLOW_OOO_DATA }; struct mptcp_delegated_action { @@ -387,6 +400,8 @@ struct mptcp_subflow_context { u32 map_subflow_seq; u32 ssn_offset; u32 map_data_len; + __wsum map_data_csum; + u32 map_csum_len; u32 request_mptcp : 1, /* send MP_CAPABLE */ request_join : 1, /* send MP_JOIN */ request_bkup : 1, @@ -396,6 +411,8 @@ struct mptcp_subflow_context { pm_notified : 1, /* PM hook called for established status */ conn_finished : 1, map_valid : 1, + map_csum_reqd : 1, + map_data_fin : 1, mpc_map : 1, backup : 1, send_mp_prio : 1, @@ -525,6 +542,8 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su int mptcp_is_enabled(struct net *net); unsigned int mptcp_get_add_addr_timeout(struct net *net); +int mptcp_is_checksum_enabled(struct net *net); +int mptcp_allow_join_id0(struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); bool mptcp_subflow_data_available(struct sock *sk); @@ -576,7 +595,8 @@ int __init mptcp_proto_v6_init(void); struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req); -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 33956337c46b..d55f4ef736a5 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -108,6 +108,8 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis subflow_req->mp_capable = 0; subflow_req->mp_join = 0; + subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener)); + subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener)); subflow_req->msk = NULL; mptcp_token_init_request(req); } @@ -150,7 +152,7 @@ static int subflow_check_req(struct request_sock *req, return -EINVAL; #endif - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt); if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -247,7 +249,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, int err; subflow_init_req(req, sk_listener); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt); if (mp_opt.mp_capable && mp_opt.mp_join) return -EINVAL; @@ -394,7 +396,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (subflow->request_mptcp) { if (!mp_opt.mp_capable) { MPTCP_INC_STATS(sock_net(sk), @@ -404,6 +406,10 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) goto fallback; } + if (mp_opt.csum_reqd) + WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true); + if (mp_opt.deny_join_id0) + WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; subflow->can_ack = 1; subflow->remote_key = mp_opt.sndr_key; @@ -638,7 +644,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * reordered MPC will cause fallback, but we don't have other * options. */ - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_capable) { fallback = true; goto create_child; @@ -648,7 +654,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); @@ -784,10 +790,10 @@ static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); } -static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", - ssn, subflow->map_subflow_seq, subflow->map_data_len); + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); } static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) @@ -812,22 +818,104 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) /* Mapping covers data later in the subflow stream, * currently unsupported. */ - warn_bad_map(subflow, ssn); + dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ - warn_bad_map(subflow, ssn + skb->len); + dbg_bad_map(subflow, ssn); return false; } return true; } +static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb, + bool csum_reqd) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct csum_pseudo_header header; + u32 offset, seq, delta; + __wsum csum; + int len; + + if (!csum_reqd) + return MAPPING_OK; + + /* mapping already validated on previous traversal */ + if (subflow->map_csum_len == subflow->map_data_len) + return MAPPING_OK; + + /* traverse the receive queue, ensuring it contains a full + * DSS mapping and accumulating the related csum. + * Preserve the accoumlate csum across multiple calls, to compute + * the csum only once + */ + delta = subflow->map_data_len - subflow->map_csum_len; + for (;;) { + seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len; + offset = seq - TCP_SKB_CB(skb)->seq; + + /* if the current skb has not been accounted yet, csum its contents + * up to the amount covered by the current DSS + */ + if (offset < skb->len) { + __wsum csum; + + len = min(skb->len - offset, delta); + csum = skb_checksum(skb, offset, len, 0); + subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum, + subflow->map_csum_len); + + delta -= len; + subflow->map_csum_len += len; + } + if (delta == 0) + break; + + if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) { + /* if this subflow is closed, the partial mapping + * will be never completed; flush the pending skbs, so + * that subflow_sched_work_if_closed() can kick in + */ + if (unlikely(ssk->sk_state == TCP_CLOSE)) + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); + + /* not enough data to validate the csum */ + return MAPPING_EMPTY; + } + + /* the DSS mapping for next skbs will be validated later, + * when a get_mapping_status call will process such skb + */ + skb = skb->next; + } + + /* note that 'map_data_len' accounts only for the carried data, does + * not include the eventual seq increment due to the data fin, + * while the pseudo header requires the original DSS data len, + * including that + */ + header.data_seq = cpu_to_be64(subflow->map_seq); + header.subflow_seq = htonl(subflow->map_subflow_seq); + header.data_len = htons(subflow->map_data_len + subflow->map_data_fin); + header.csum = 0; + + csum = csum_partial(&header, sizeof(header), subflow->map_data_csum); + if (unlikely(csum_fold(csum))) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); + return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; + } + + return MAPPING_OK; +} + static enum mapping_status get_mapping_status(struct sock *ssk, struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + bool csum_reqd = READ_ONCE(msk->csum_enabled); struct mptcp_ext *mpext; struct sk_buff *skb; u16 data_len; @@ -920,9 +1008,10 @@ static enum mapping_status get_mapping_status(struct sock *ssk, /* Allow replacing only with an identical map */ if (subflow->map_seq == map_seq && subflow->map_subflow_seq == mpext->subflow_seq && - subflow->map_data_len == data_len) { + subflow->map_data_len == data_len && + subflow->map_csum_reqd == mpext->csum_reqd) { skb_ext_del(skb, SKB_EXT_MPTCP); - return MAPPING_OK; + goto validate_csum; } /* If this skb data are fully covered by the current mapping, @@ -934,27 +1023,41 @@ static enum mapping_status get_mapping_status(struct sock *ssk, } /* will validate the next map after consuming the current one */ - return MAPPING_OK; + goto validate_csum; } subflow->map_seq = map_seq; subflow->map_subflow_seq = mpext->subflow_seq; subflow->map_data_len = data_len; subflow->map_valid = 1; + subflow->map_data_fin = mpext->data_fin; subflow->mpc_map = mpext->mpc_map; - pr_debug("new map seq=%llu subflow_seq=%u data_len=%u", + subflow->map_csum_reqd = mpext->csum_reqd; + subflow->map_csum_len = 0; + subflow->map_data_csum = csum_unfold(mpext->csum); + + /* Cfr RFC 8684 Section 3.3.0 */ + if (unlikely(subflow->map_csum_reqd != csum_reqd)) + return MAPPING_INVALID; + + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", subflow->map_seq, subflow->map_subflow_seq, - subflow->map_data_len); + subflow->map_data_len, subflow->map_csum_reqd, + subflow->map_data_csum); validate_seq: /* we revalidate valid mapping on new skb, because we must ensure * the current skb is completely covered by the available mapping */ - if (!validate_mapping(ssk, skb)) + if (!validate_mapping(ssk, skb)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH); return MAPPING_INVALID; + } skb_ext_del(skb, SKB_EXT_MPTCP); - return MAPPING_OK; + +validate_csum: + return validate_data_csum(ssk, skb, csum_reqd); } static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, @@ -1000,7 +1103,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); if (subflow->data_avail) return true; @@ -1039,18 +1142,13 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) { - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - break; - } else if (after64(ack_seq, old_ack)) { - subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; - break; + if (unlikely(before64(ack_seq, old_ack))) { + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + continue; } - /* only accept in-sequence mapping. Old values are spurious - * retransmission - */ - mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + break; } return true; @@ -1065,12 +1163,11 @@ fallback: * subflow_error_report() will introduce the appropriate barriers */ ssk->sk_err = EBADMSG; - ssk->sk_error_report(ssk); tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; tcp_send_active_reset(ssk, GFP_ATOMIC); - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); return false; } @@ -1080,7 +1177,7 @@ fallback: subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1092,7 +1189,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1120,41 +1217,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); } -static void subflow_data_ready(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - u16 state = 1 << inet_sk_state_load(sk); - struct sock *parent = subflow->conn; - struct mptcp_sock *msk; - - 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; - } - - WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && - !subflow->mp_join && !(state & TCPF_CLOSE)); - - if (mptcp_subflow_data_available(sk)) - mptcp_data_ready(parent, sk); -} - -static void subflow_write_space(struct sock *ssk) -{ - struct sock *sk = mptcp_subflow_ctx(ssk)->conn; - - mptcp_propagate_sndbuf(sk, ssk); - mptcp_write_space(sk); -} - void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1195,6 +1257,43 @@ static void subflow_error_report(struct sock *ssk) mptcp_data_unlock(sk); } +static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); + struct sock *parent = subflow->conn; + struct mptcp_sock *msk; + + 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; + } + + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); +} + +static void subflow_write_space(struct sock *ssk) +{ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); +} + static struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { @@ -1505,6 +1604,8 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b100c04a0e43..3d6d49420db8 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -31,6 +31,9 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr; + if (unlikely(length < 0)) + return false; + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; @@ -47,6 +50,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length--; continue; default: + if (length < 2) + return true; opsize = *ptr++; if (opsize < 2) return true; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f20f6ae0e215..d6214242fe7f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4338,13 +4338,45 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) - goto err_set_alloc_name; + goto err_set_name; + + udata = NULL; + if (udlen) { + udata = set->data + size; + nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); + } + + INIT_LIST_HEAD(&set->bindings); + INIT_LIST_HEAD(&set->catchall_list); + set->table = table; + write_pnet(&set->net, net); + set->ops = ops; + set->ktype = ktype; + set->klen = desc.klen; + set->dtype = dtype; + set->objtype = objtype; + set->dlen = desc.dlen; + set->flags = flags; + set->size = desc.size; + set->policy = policy; + set->udlen = udlen; + set->udata = udata; + set->timeout = timeout; + set->gc_int = gc_int; + + set->field_count = desc.field_count; + for (i = 0; i < desc.field_count; i++) + set->field_len[i] = desc.field_len[i]; + + err = ops->init(set, &desc, nla); + if (err < 0) + goto err_set_init; if (nla[NFTA_SET_EXPR]) { expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_alloc_name; + goto err_set_expr_alloc; } set->exprs[0] = expr; set->num_exprs++; @@ -4355,75 +4387,44 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_EXPR)) { err = -EINVAL; - goto err_set_alloc_name; + goto err_set_expr_alloc; } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; - goto err_set_init; + goto err_set_expr_alloc; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; - goto err_set_init; + goto err_set_expr_alloc; } expr = nft_set_elem_expr_alloc(&ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_init; + goto err_set_expr_alloc; } set->exprs[i++] = expr; set->num_exprs++; } } - udata = NULL; - if (udlen) { - udata = set->data + size; - nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); - } - - INIT_LIST_HEAD(&set->bindings); - INIT_LIST_HEAD(&set->catchall_list); - set->table = table; - write_pnet(&set->net, net); - set->ops = ops; - set->ktype = ktype; - set->klen = desc.klen; - set->dtype = dtype; - set->objtype = objtype; - set->dlen = desc.dlen; - set->flags = flags; - set->size = desc.size; - set->policy = policy; - set->udlen = udlen; - set->udata = udata; - set->timeout = timeout; - set->gc_int = gc_int; set->handle = nf_tables_alloc_handle(table); - set->field_count = desc.field_count; - for (i = 0; i < desc.field_count; i++) - set->field_len[i] = desc.field_len[i]; - - err = ops->init(set, &desc, nla); - if (err < 0) - goto err_set_init; - err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err_set_trans; + goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err_set_trans: - ops->destroy(set); -err_set_init: +err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); -err_set_alloc_name: + + ops->destroy(set); +err_set_init: kfree(set->name); err_set_name: kvfree(set); diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 41109c326f3a..28982630bef3 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -13,6 +13,7 @@ openvswitch-y := \ flow_netlink.o \ flow_table.o \ meter.o \ + openvswitch_trace.o \ vport.o \ vport-internal_dev.o \ vport-netdev.o @@ -24,3 +25,5 @@ endif obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o + +CFLAGS_openvswitch_trace.o = -I$(src) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 77d924ab8cdb..ef15d9eb4774 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -30,6 +30,7 @@ #include "conntrack.h" #include "vport.h" #include "flow_netlink.h" +#include "openvswitch_trace.h" struct deferred_action { struct sk_buff *skb; @@ -1242,6 +1243,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { int err = 0; + if (trace_ovs_do_execute_action_enabled()) + trace_ovs_do_execute_action(dp, skb, key, a, rem); + switch (nla_type(a)) { case OVS_ACTION_ATTR_OUTPUT: { int port = nla_get_u32(a); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9d6ef6cb9b26..bc164b35e67d 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -43,6 +43,7 @@ #include "flow_table.h" #include "flow_netlink.h" #include "meter.h" +#include "openvswitch_trace.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -275,6 +276,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, struct dp_stats_percpu *stats; int err; + if (trace_ovs_dp_upcall_enabled()) + trace_ovs_dp_upcall(dp, skb, key, upcall_info); + if (upcall_info->portid == 0) { err = -ENOTCONN; goto err; diff --git a/net/openvswitch/openvswitch_trace.c b/net/openvswitch/openvswitch_trace.c new file mode 100644 index 000000000000..62c5f7d6f023 --- /dev/null +++ b/net/openvswitch/openvswitch_trace.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* bug in tracepoint.h, it should include this */ +#include <linux/module.h> + +/* sparse isn't too happy with all macros... */ +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "openvswitch_trace.h" + +#endif diff --git a/net/openvswitch/openvswitch_trace.h b/net/openvswitch/openvswitch_trace.h new file mode 100644 index 000000000000..3eb35d9eb700 --- /dev/null +++ b/net/openvswitch/openvswitch_trace.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM openvswitch + +#if !defined(_TRACE_OPENVSWITCH_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_OPENVSWITCH_H + +#include <linux/tracepoint.h> + +#include "datapath.h" + +TRACE_EVENT(ovs_do_execute_action, + + TP_PROTO(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, const struct nlattr *a, int rem), + + TP_ARGS(dp, skb, key, a, rem), + + TP_STRUCT__entry( + __field( void *, dpaddr ) + __string( dp_name, ovs_dp_name(dp) ) + __string( dev_name, skb->dev->name ) + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( u8, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + __field( u32, ovs_flow_hash ) + __field( u32, recirc_id ) + __field( void *, keyaddr ) + __field( u16, key_eth_type ) + __field( u8, key_ct_state ) + __field( u8, key_ct_orig_proto ) + __field( u16, key_ct_zone ) + __field( unsigned int, flow_key_valid ) + __field( u8, action_type ) + __field( unsigned int, action_len ) + __field( void *, action_data ) + __field( u8, is_last ) + ), + + TP_fast_assign( + __entry->dpaddr = dp; + __assign_str(dp_name, ovs_dp_name(dp)); + __assign_str(dev_name, skb->dev->name); + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->ovs_flow_hash = key->ovs_flow_hash; + __entry->recirc_id = key->recirc_id; + __entry->keyaddr = key; + __entry->key_eth_type = key->eth.type; + __entry->key_ct_state = key->ct_state; + __entry->key_ct_orig_proto = key->ct_orig_proto; + __entry->key_ct_zone = key->ct_zone; + __entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID); + __entry->action_type = nla_type(a); + __entry->action_len = nla_len(a); + __entry->action_data = nla_data(a); + __entry->is_last = nla_is_last(a, rem); + ), + + TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_Zone=%04x flow_key_valid=%d action_type=%u action_len=%u action_data=%p is_last=%d", + __entry->dpaddr, __get_str(dp_name), __get_str(dev_name), + __entry->skbaddr, __entry->len, __entry->data_len, + __entry->truesize, __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->ovs_flow_hash, + __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type, + __entry->key_ct_state, __entry->key_ct_orig_proto, + __entry->key_ct_zone, + __entry->flow_key_valid, + __entry->action_type, __entry->action_len, + __entry->action_data, __entry->is_last) +); + +TRACE_EVENT(ovs_dp_upcall, + + TP_PROTO(struct datapath *dp, struct sk_buff *skb, + const struct sw_flow_key *key, + const struct dp_upcall_info *upcall_info), + + TP_ARGS(dp, skb, key, upcall_info), + + TP_STRUCT__entry( + __field( void *, dpaddr ) + __string( dp_name, ovs_dp_name(dp) ) + __string( dev_name, skb->dev->name ) + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( u8, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + __field( u32, ovs_flow_hash ) + __field( u32, recirc_id ) + __field( const void *, keyaddr ) + __field( u16, key_eth_type ) + __field( u8, key_ct_state ) + __field( u8, key_ct_orig_proto ) + __field( u16, key_ct_zone ) + __field( unsigned int, flow_key_valid ) + __field( u8, upcall_cmd ) + __field( u32, upcall_port ) + __field( u16, upcall_mru ) + ), + + TP_fast_assign( + __entry->dpaddr = dp; + __assign_str(dp_name, ovs_dp_name(dp)); + __assign_str(dev_name, skb->dev->name); + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->ovs_flow_hash = key->ovs_flow_hash; + __entry->recirc_id = key->recirc_id; + __entry->keyaddr = key; + __entry->key_eth_type = key->eth.type; + __entry->key_ct_state = key->ct_state; + __entry->key_ct_orig_proto = key->ct_orig_proto; + __entry->key_ct_zone = key->ct_zone; + __entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID); + __entry->upcall_cmd = upcall_info->cmd; + __entry->upcall_port = upcall_info->portid; + __entry->upcall_mru = upcall_info->mru; + ), + + TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_zone=%04x flow_key_valid=%d upcall_cmd=%u upcall_port=%u upcall_mru=%u", + __entry->dpaddr, __get_str(dp_name), __get_str(dev_name), + __entry->skbaddr, __entry->len, __entry->data_len, + __entry->truesize, __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->ovs_flow_hash, + __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type, + __entry->key_ct_state, __entry->key_ct_orig_proto, + __entry->key_ct_zone, + __entry->flow_key_valid, + __entry->upcall_cmd, __entry->upcall_port, + __entry->upcall_mru) +); + +#endif /* _TRACE_OPENVSWITCH_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE openvswitch_trace +#include <trace/define_trace.h> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 71dd6b910f7c..77b0cdab3810 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2683,7 +2683,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2896,7 +2896,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -3034,10 +3034,13 @@ static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - if (po->tx_ring.pg_vec) + /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. + * tpacket_snd() will redo the check safely. + */ + if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); - else - return packet_snd(sock, msg, len); + + return packet_snd(sock, msg, len); } /* @@ -3168,7 +3171,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, /* prevents packet_notifier() from calling * register_prot_hook() */ - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); dev_curr = po->prot_hook.dev; @@ -3178,17 +3181,17 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } BUG_ON(po->running); - po->num = proto; + WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3502,7 +3505,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3517,16 +3520,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex; if (peer) return -EOPNOTSUPP; + ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; - sll->sll_protocol = po->num; + sll->sll_ifindex = ifindex; + sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -4102,7 +4107,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4408,7 +4413,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, was_running = po->running; num = po->num; if (was_running) { - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -4443,7 +4448,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, spin_lock(&po->bind_lock); if (was_running) { - po->num = num; + WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); @@ -4613,8 +4618,8 @@ static int packet_seq_show(struct seq_file *seq, void *v) s, refcount_read(&s->sk_refcnt), s->sk_type, - ntohs(po->num), - po->ifindex, + ntohs(READ_ONCE(po->num)), + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index c0477bec09bd..f2efaa4225f9 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -436,7 +436,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_sock *ipc; struct sk_buff *skb; struct qrtr_cb *cb; - unsigned int size; + size_t size; unsigned int ver; size_t hdrlen; diff --git a/net/rds/recv.c b/net/rds/recv.c index 4db109fb6ec2..5b426dc3634d 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -714,7 +714,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; - goto out; + break; } rds_recvmsg_zcookie(rs, msg); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f6d5755d669e..d17a66aab8ee 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -381,7 +381,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, } mutex_unlock(&idrinfo->lock); - if (nla_put_u32(skb, TCA_FCNT, n_i)) + ret = nla_put_u32(skb, TCA_FCNT, n_i); + if (ret) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 18edd9ad1410..a656baa321fe 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -904,14 +904,19 @@ static int tcf_ct_act_nat(struct sk_buff *skb, } err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } return err; #else diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2e704c7a105a..d7869a984881 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1531,13 +1531,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb, &mask->basic.n_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto)); - mask->basic.n_proto = cpu_to_be16(0); } else { key->basic.n_proto = ethertype; + mask->basic.n_proto = cpu_to_be16(~0); } } } else { key->basic.n_proto = ethertype; + mask->basic.n_proto = cpu_to_be16(~0); } } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 7d37638ee1c7..951542843cab 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -943,7 +943,7 @@ static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (!tcph) + if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, @@ -967,6 +967,8 @@ static const void *cake_get_tcpopt(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -1104,6 +1106,8 @@ static bool cake_tcph_may_drop(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -2338,7 +2342,7 @@ static int cake_config_precedence(struct Qdisc *sch) /* List of known Diffserv codepoints: * - * Least Effort (CS1) + * Least Effort (CS1, LE) * Best Effort (CS0) * Max Reliability & LLT "Lo" (TOS1) * Max Throughput (TOS2) @@ -2360,7 +2364,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 25 codepoints. */ -/* List of traffic classes in RFC 4594: +/* List of traffic classes in RFC 4594, updated by RFC 8622: * (roughly descending order of contended priority) * (roughly ascending order of uncontended throughput) * @@ -2375,7 +2379,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Ops, Admin, Management (CS2,TOS1) - eg. ssh * Standard Service (CS0 & unrecognised codepoints) * High Throughput Data (AF1x,TOS2) - eg. web traffic - * Low Priority Data (CS1) - eg. BitTorrent + * Low Priority Data (CS1,LE) - eg. BitTorrent * Total 12 traffic classes. */ @@ -2391,7 +2395,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) * Video Streaming (AF4x, AF3x, CS3) * Bog Standard (CS0 etc.) * High Throughput (AF1x, TOS2) - * Background Traffic (CS1) + * Background Traffic (CS1, LE) * * Total 8 traffic classes. */ @@ -2435,7 +2439,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1) * Best Effort (CS0, AF1x, TOS2, and those not specified) - * Background Traffic (CS1) + * Background Traffic (CS1, LE) * * Total 4 traffic classes. */ @@ -2473,7 +2477,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. - * Low Priority (CS1) + * Low Priority (CS1, LE) * Best Effort * Latency Sensitive (TOS4, VA, EF, CS6, CS7) */ diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e9c0afc8becc..d9ac60ffe927 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -52,6 +52,8 @@ static void qdisc_maybe_clear_missed(struct Qdisc *q, */ if (!netif_xmit_frozen_or_stopped(txq)) set_bit(__QDISC_STATE_MISSED, &q->state); + else + set_bit(__QDISC_STATE_DRAINING, &q->state); } /* Main transmission queue. */ @@ -164,9 +166,13 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) skb = next; } - if (lock) + + if (lock) { spin_unlock(lock); - __netif_schedule(q); + set_bit(__QDISC_STATE_MISSED, &q->state); + } else { + __netif_schedule(q); + } } static void try_bulk_dequeue_skb(struct Qdisc *q, @@ -409,7 +415,11 @@ void __qdisc_run(struct Qdisc *q) while (qdisc_restart(q, &packets)) { quota -= packets; if (quota <= 0) { - __netif_schedule(q); + if (q->flags & TCQ_F_NOLOCK) + set_bit(__QDISC_STATE_MISSED, &q->state); + else + __netif_schedule(q); + break; } } @@ -698,13 +708,14 @@ retry: if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else if (need_retry && - test_bit(__QDISC_STATE_MISSED, &qdisc->state)) { + READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { /* Delay clearing the STATE_MISSED here to reduce * the overhead of the second spin_trylock() in * qdisc_run_begin() and __netif_schedule() calling * in qdisc_run_end(). */ clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); /* Make sure dequeuing happens after clearing * STATE_MISSED. @@ -714,8 +725,6 @@ retry: need_retry = false; goto retry; - } else { - WRITE_ONCE(qdisc->empty, true); } return skb; @@ -916,7 +925,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - sch->empty = true; dev_hold(dev); refcount_set(&sch->refcnt, 1); @@ -1222,6 +1230,7 @@ static void dev_reset_queue(struct net_device *dev, spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 336df4b36655..be29da09cc7a 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -98,6 +98,7 @@ static struct sctp_association *sctp_association_init( * sock configured value. */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); + asoc->probe_interval = msecs_to_jiffies(sp->probe_interval); asoc->encap_port = sp->encap_port; @@ -625,6 +626,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, * association configured value. */ peer->hbinterval = asoc->hbinterval; + peer->probe_interval = asoc->probe_interval; peer->encap_port = asoc->encap_port; @@ -714,6 +716,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return NULL; } + sctp_transport_pl_reset(peer); + /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; @@ -812,6 +816,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, spc_state = SCTP_ADDR_CONFIRMED; transport->state = SCTP_ACTIVE; + sctp_transport_pl_reset(transport); break; case SCTP_TRANSPORT_DOWN: @@ -821,6 +826,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, */ if (transport->state != SCTP_UNCONFIRMED) { transport->state = SCTP_INACTIVE; + sctp_transport_pl_reset(transport); spc_state = SCTP_ADDR_UNREACHABLE; } else { sctp_transport_dst_release(transport); diff --git a/net/sctp/debug.c b/net/sctp/debug.c index c4d9c7feffb9..ccd773e4c371 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -154,6 +154,7 @@ static const char *const sctp_timer_tbl[] = { "TIMEOUT_T5_SHUTDOWN_GUARD", "TIMEOUT_HEARTBEAT", "TIMEOUT_RECONF", + "TIMEOUT_PROBE", "TIMEOUT_SACK", "TIMEOUT_AUTOCLOSE", }; diff --git a/net/sctp/input.c b/net/sctp/input.c index d508f6f3dd08..fe6429cc012f 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -385,7 +385,9 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu) { - if (!t || (t->pathmtu <= pmtu)) + if (!t || + (t->pathmtu <= pmtu && + t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu)) return; if (sock_owned_by_user(sk)) { @@ -554,6 +556,49 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) sctp_transport_put(t); } +static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, + __u8 type, __u8 code, __u32 info) +{ + struct sctp_association *asoc = t->asoc; + struct sock *sk = asoc->base.sk; + int err = 0; + + switch (type) { + case ICMP_PARAMETERPROB: + err = EPROTO; + break; + case ICMP_DEST_UNREACH: + if (code > NR_ICMP_UNREACH) + return; + if (code == ICMP_FRAG_NEEDED) { + sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info)); + return; + } + if (code == ICMP_PROT_UNREACH) { + sctp_icmp_proto_unreachable(sk, asoc, t); + return; + } + err = icmp_err_convert[code].errno; + break; + case ICMP_TIME_EXCEEDED: + if (code == ICMP_EXC_FRAGTIME) + return; + + err = EHOSTUNREACH; + break; + case ICMP_REDIRECT: + sctp_icmp_redirect(sk, t, skb); + default: + return; + } + if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { + sk->sk_err = err; + sk->sk_error_report(sk); + } else { /* Only an error on timeout */ + sk->sk_err_soft = err; + } +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -572,22 +617,19 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) int sctp_v4_err(struct sk_buff *skb, __u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; - const int ihlen = iph->ihl * 4; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - struct sock *sk; - struct sctp_association *asoc = NULL; + struct net *net = dev_net(skb->dev); struct sctp_transport *transport; - struct inet_sock *inet; + struct sctp_association *asoc; __u16 saveip, savesctp; - int err; - struct net *net = dev_net(skb->dev); + struct sock *sk; /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; skb_reset_network_header(skb); - skb_set_transport_header(skb, ihlen); + skb_set_transport_header(skb, iph->ihl * 4); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport); /* Put back, the original values. */ skb->network_header = saveip; @@ -596,59 +638,41 @@ int sctp_v4_err(struct sk_buff *skb, __u32 info) __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } - /* Warning: The sock lock is held. Remember to call - * sctp_err_finish! - */ - switch (type) { - case ICMP_PARAMETERPROB: - err = EPROTO; - break; - case ICMP_DEST_UNREACH: - if (code > NR_ICMP_UNREACH) - goto out_unlock; + sctp_v4_err_handle(transport, skb, type, code, info); + sctp_err_finish(sk, transport); - /* PMTU discovery (RFC1191) */ - if (ICMP_FRAG_NEEDED == code) { - sctp_icmp_frag_needed(sk, asoc, transport, - SCTP_TRUNC4(info)); - goto out_unlock; - } else { - if (ICMP_PROT_UNREACH == code) { - sctp_icmp_proto_unreachable(sk, asoc, - transport); - goto out_unlock; - } - } - err = icmp_err_convert[code].errno; - break; - case ICMP_TIME_EXCEEDED: - /* Ignore any time exceeded errors due to fragment reassembly - * timeouts. - */ - if (ICMP_EXC_FRAGTIME == code) - goto out_unlock; + return 0; +} - err = EHOSTUNREACH; - break; - case ICMP_REDIRECT: - sctp_icmp_redirect(sk, transport, skb); - /* Fall through to out_unlock. */ - default: - goto out_unlock; +int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sctp_association *asoc; + struct sctp_transport *t; + struct icmphdr *hdr; + __u32 info = 0; + + skb->transport_header += sizeof(struct udphdr); + sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t); + if (!sk) { + __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); + return -ENOENT; } - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { - sk->sk_err = err; - sk->sk_error_report(sk); - } else { /* Only an error on timeout */ - sk->sk_err_soft = err; + skb->transport_header -= sizeof(struct udphdr); + hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr)); + if (hdr->type == ICMP_REDIRECT) { + /* can't be handled without outer iphdr known, leave it to udp_err */ + sctp_err_finish(sk, t); + return 0; } + if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED) + info = ntohs(hdr->un.frag.mtu); + sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info); -out_unlock: - sctp_err_finish(sk, transport); - return 0; + sctp_err_finish(sk, t); + return 1; } /* diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index bd08807c9e44..05f81a4d0ee7 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -122,54 +122,28 @@ static struct notifier_block sctp_inet6addr_notifier = { .notifier_call = sctp_inet6addr_event, }; -/* ICMP error handler. */ -static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) +static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, + __u8 type, __u8 code, __u32 info) { - struct inet6_dev *idev; - struct sock *sk; - struct sctp_association *asoc; - struct sctp_transport *transport; + struct sctp_association *asoc = t->asoc; + struct sock *sk = asoc->base.sk; struct ipv6_pinfo *np; - __u16 saveip, savesctp; - int err, ret = 0; - struct net *net = dev_net(skb->dev); - - idev = in6_dev_get(skb->dev); - - /* Fix up skb to look at the embedded net header. */ - saveip = skb->network_header; - savesctp = skb->transport_header; - skb_reset_network_header(skb); - skb_set_transport_header(skb, offset); - sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport); - /* Put back, the original pointers. */ - skb->network_header = saveip; - skb->transport_header = savesctp; - if (!sk) { - __ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS); - ret = -ENOENT; - goto out; - } - - /* Warning: The sock lock is held. Remember to call - * sctp_err_finish! - */ + int err = 0; switch (type) { case ICMPV6_PKT_TOOBIG: if (ip6_sk_accept_pmtu(sk)) - sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info)); - goto out_unlock; + sctp_icmp_frag_needed(sk, asoc, t, info); + return; case ICMPV6_PARAMPROB: if (ICMPV6_UNK_NEXTHDR == code) { - sctp_icmp_proto_unreachable(sk, asoc, transport); - goto out_unlock; + sctp_icmp_proto_unreachable(sk, asoc, t); + return; } break; case NDISC_REDIRECT: - sctp_icmp_redirect(sk, transport, skb); - goto out_unlock; + sctp_icmp_redirect(sk, t, skb); + return; default: break; } @@ -179,17 +153,69 @@ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); - } else { /* Only an error on timeout */ + } else { sk->sk_err_soft = err; } +} + +/* ICMP error handler. */ +static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct net *net = dev_net(skb->dev); + struct sctp_transport *transport; + struct sctp_association *asoc; + __u16 saveip, savesctp; + struct sock *sk; + + /* Fix up skb to look at the embedded net header. */ + saveip = skb->network_header; + savesctp = skb->transport_header; + skb_reset_network_header(skb); + skb_set_transport_header(skb, offset); + sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport); + /* Put back, the original pointers. */ + skb->network_header = saveip; + skb->transport_header = savesctp; + if (!sk) { + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return -ENOENT; + } -out_unlock: + sctp_v6_err_handle(transport, skb, type, code, ntohl(info)); sctp_err_finish(sk, transport); -out: - if (likely(idev != NULL)) - in6_dev_put(idev); - return ret; + return 0; +} + +int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sctp_association *asoc; + struct sctp_transport *t; + struct icmp6hdr *hdr; + __u32 info = 0; + + skb->transport_header += sizeof(struct udphdr); + sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &t); + if (!sk) { + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return -ENOENT; + } + + skb->transport_header -= sizeof(struct udphdr); + hdr = (struct icmp6hdr *)(skb_network_header(skb) - sizeof(struct icmp6hdr)); + if (hdr->icmp6_type == NDISC_REDIRECT) { + /* can't be handled without outer ip6hdr known, leave it to udpv6_err */ + sctp_err_finish(sk, t); + return 0; + } + if (hdr->icmp6_type == ICMPV6_PKT_TOOBIG) + info = ntohl(hdr->icmp6_mtu); + sctp_v6_err_handle(t, skb, hdr->icmp6_type, hdr->icmp6_code, info); + + sctp_err_finish(sk, t); + return 1; } static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) diff --git a/net/sctp/output.c b/net/sctp/output.c index a6aa17df09ef..9032ce60d50e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -103,7 +103,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, sctp_transport_route(tp, NULL, sp); if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); - } else if (!sctp_transport_pmtu_check(tp)) { + } else if (!sctp_transport_pl_enabled(tp) && + !sctp_transport_pmtu_check(tp)) { if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } @@ -211,6 +212,30 @@ enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet, return retval; } +/* Try to bundle a pad chunk into a packet with a heartbeat chunk for PLPMTUTD probe */ +static enum sctp_xmit sctp_packet_bundle_pad(struct sctp_packet *pkt, struct sctp_chunk *chunk) +{ + struct sctp_transport *t = pkt->transport; + struct sctp_chunk *pad; + int overhead = 0; + + if (!chunk->pmtu_probe) + return SCTP_XMIT_OK; + + /* calculate the Padding Data size for the pad chunk */ + overhead += sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr); + overhead += sizeof(struct sctp_sender_hb_info) + sizeof(struct sctp_pad_chunk); + pad = sctp_make_pad(t->asoc, t->pl.probe_size - overhead); + if (!pad) + return SCTP_XMIT_DELAY; + + list_add_tail(&pad->list, &pkt->chunk_list); + pkt->size += SCTP_PAD4(ntohs(pad->chunk_hdr->length)); + chunk->transport = t; + + return SCTP_XMIT_OK; +} + /* Try to bundle an auth chunk into the packet. */ static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt, struct sctp_chunk *chunk) @@ -382,6 +407,10 @@ enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet, goto finish; retval = __sctp_packet_append_chunk(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + + retval = sctp_packet_bundle_pad(packet, chunk); finish: return retval; @@ -553,7 +582,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sk = chunk->skb->sk; /* check gso */ - if (packet->size > tp->pathmtu && !packet->ipfragok) { + if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) { if (!sk_can_gso(sk)) { pr_err_once("Trying to GSO but underlying device doesn't support it."); goto out; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 5cb1aa5f067b..ff47091c385e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -769,7 +769,11 @@ static int sctp_packet_singleton(struct sctp_transport *transport, sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); - sctp_packet_append_chunk(&singleton, chunk); + if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { + list_del_init(&chunk->list); + sctp_chunk_free(chunk); + return -ENOMEM; + } return sctp_packet_transmit(&singleton, gfp); } @@ -929,8 +933,13 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) one_packet = 1; fallthrough; - case SCTP_CID_SACK: case SCTP_CID_HEARTBEAT: + if (chunk->pmtu_probe) { + sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + break; + } + fallthrough; + case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index baa4e770e4ba..bc5db0b404ce 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -850,23 +850,6 @@ static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb) return 0; } -static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb) -{ - struct sctp_association *asoc; - struct sctp_transport *t; - int family; - - skb->transport_header += sizeof(struct udphdr); - family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6; - sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb), - &asoc, &t); - if (!sk) - return -ENOENT; - - sctp_err_finish(sk, t); - return 0; -} - int sctp_udp_sock_start(struct net *net) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; @@ -885,7 +868,7 @@ int sctp_udp_sock_start(struct net *net) tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; - tuncfg.encap_err_lookup = sctp_udp_err_lookup; + tuncfg.encap_err_lookup = sctp_udp_v4_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp4_sock = sock->sk; @@ -907,7 +890,7 @@ int sctp_udp_sock_start(struct net *net) tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; - tuncfg.encap_err_lookup = sctp_udp_err_lookup; + tuncfg.encap_err_lookup = sctp_udp_v6_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp6_sock = sock->sk; #endif diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5b44d228b6ca..b0eaa93a9cc6 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1160,7 +1160,8 @@ nodata: /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport) + const struct sctp_transport *transport, + __u32 probe_size) { struct sctp_sender_hb_info hbinfo; struct sctp_chunk *retval; @@ -1176,6 +1177,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, hbinfo.daddr = transport->ipaddr; hbinfo.sent_at = jiffies; hbinfo.hb_nonce = transport->hb_nonce; + hbinfo.probe_size = probe_size; /* Cast away the 'const', as this is just telling the chunk * what transport it belongs to. @@ -1183,6 +1185,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, retval->transport = (struct sctp_transport *) transport; retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo), &hbinfo); + retval->pmtu_probe = !!probe_size; nodata: return retval; @@ -1218,6 +1221,32 @@ nodata: return retval; } +/* RFC4820 3. Padding Chunk (PAD) + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Type = 0x84 | Flags=0 | Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * \ Padding Data / + * / \ + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len) +{ + struct sctp_chunk *retval; + + retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC); + if (!retval) + return NULL; + + skb_put_zero(retval->skb, len); + retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len); + retval->chunk_end = skb_tail_pointer(retval->skb); + + return retval; +} + /* Create an Operation Error chunk with the specified space reserved. * This routine can be used for containing multiple causes in the chunk. */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index ce15d590a615..b3815b568e8e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -471,6 +471,38 @@ out_unlock: sctp_transport_put(transport); } +/* Handle the timeout of the probe timer. */ +void sctp_generate_probe_event(struct timer_list *t) +{ + struct sctp_transport *transport = from_timer(transport, t, probe_timer); + struct sctp_association *asoc = transport->asoc; + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); + int error = 0; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + pr_debug("%s: sock is busy\n", __func__); + + /* Try again later. */ + if (!mod_timer(&transport->probe_timer, jiffies + (HZ / 20))) + sctp_transport_hold(transport); + goto out_unlock; + } + + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, + SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_PROBE), + asoc->state, asoc->ep, asoc, + transport, GFP_ATOMIC); + + if (error) + sk->sk_err = -error; + +out_unlock: + bh_unlock_sock(sk); + sctp_transport_put(transport); +} + /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(struct timer_list *t) { @@ -1641,6 +1673,11 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, sctp_cmd_hb_timers_stop(commands, asoc); break; + case SCTP_CMD_PROBE_TIMER_UPDATE: + t = cmd->obj.transport; + sctp_transport_reset_probe_timer(t); + break; + case SCTP_CMD_REPORT_ERROR: error = cmd->obj.error; break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 4f30388a0dd0..d29b579da904 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1004,7 +1004,7 @@ static enum sctp_disposition sctp_sf_heartbeat( struct sctp_chunk *reply; /* Send a heartbeat to our peer. */ - reply = sctp_make_heartbeat(asoc, transport); + reply = sctp_make_heartbeat(asoc, transport, 0); if (!reply) return SCTP_DISPOSITION_NOMEM; @@ -1095,6 +1095,32 @@ enum sctp_disposition sctp_sf_send_reconf(struct net *net, return SCTP_DISPOSITION_CONSUME; } +/* send hb chunk with padding for PLPMUTD. */ +enum sctp_disposition sctp_sf_send_probe(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_transport *transport = (struct sctp_transport *)arg; + struct sctp_chunk *reply; + + if (!sctp_transport_pl_enabled(transport)) + return SCTP_DISPOSITION_CONSUME; + + sctp_transport_pl_send(transport); + + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, + SCTP_TRANSPORT(transport)); + + return SCTP_DISPOSITION_CONSUME; +} + /* * Process an heartbeat request. * @@ -1243,6 +1269,15 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, if (hbinfo->hb_nonce != link->hb_nonce) return SCTP_DISPOSITION_DISCARD; + if (hbinfo->probe_size) { + if (hbinfo->probe_size != link->pl.probe_size || + !sctp_transport_pl_enabled(link)) + return SCTP_DISPOSITION_DISCARD; + + sctp_transport_pl_recv(link); + return SCTP_DISPOSITION_CONSUME; + } + max_interval = link->hbinterval + link->rto; /* Check if the timestamp looks valid. */ diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 88ea87f4f0e7..1816a4410b2b 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -527,6 +527,26 @@ auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { }; /*state_fn_t auth_chunk_event_table[][] */ static const struct sctp_sm_table_entry +pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { + /* SCTP_STATE_CLOSED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_WAIT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_ECHOED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_ESTABLISHED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_PENDING */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_RECEIVED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), +}; /* chunk pad */ + +static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), @@ -947,6 +967,25 @@ other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } +#define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \ + /* SCTP_STATE_CLOSED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_COOKIE_WAIT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_COOKIE_ECHOED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_ESTABLISHED */ \ + TYPE_SCTP_FUNC(sctp_sf_send_probe), \ + /* SCTP_STATE_SHUTDOWN_PENDING */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_SENT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ +} + static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, @@ -958,6 +997,7 @@ timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT, TYPE_SCTP_EVENT_TIMEOUT_RECONF, + TYPE_SCTP_EVENT_TIMEOUT_PROBE, TYPE_SCTP_EVENT_TIMEOUT_SACK, TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; @@ -992,6 +1032,9 @@ static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; + + case SCTP_CID_PAD: + return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a79d193ff872..e64e01f61b11 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2496,6 +2496,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, sctp_transport_pmtu(trans, sctp_opt2sk(sp)); sctp_assoc_sync_pmtu(asoc); } + sctp_transport_pl_reset(trans); } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_PMTUD) | pmtud_change; @@ -4481,6 +4482,61 @@ static int sctp_setsockopt_encap_port(struct sock *sk, return 0; } +static int sctp_setsockopt_probe_interval(struct sock *sk, + struct sctp_probeinterval *params, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_transport *t; + __u32 probe_interval; + + if (optlen != sizeof(*params)) + return -EINVAL; + + probe_interval = params->spi_interval; + if (probe_interval && probe_interval < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spi_address)) { + t = sctp_addr_id2transport(sk, ¶ms->spi_address, + params->spi_assoc_id); + if (!t) + return -EINVAL; + + t->probe_interval = msecs_to_jiffies(probe_interval); + sctp_transport_pl_reset(t); + return 0; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, params->spi_assoc_id); + if (!asoc && params->spi_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + /* If changes are for association, also apply probe_interval to + * each transport. + */ + if (asoc) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { + t->probe_interval = msecs_to_jiffies(probe_interval); + sctp_transport_pl_reset(t); + } + + asoc->probe_interval = msecs_to_jiffies(probe_interval); + return 0; + } + + sctp_sk(sk)->probe_interval = probe_interval; + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4703,6 +4759,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_setsockopt_encap_port(sk, kopt, optlen); break; + case SCTP_PLPMTUD_PROBE_INTERVAL: + retval = sctp_setsockopt_probe_interval(sk, kopt, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -4989,6 +5048,7 @@ static int sctp_init_sock(struct sock *sk) atomic_set(&sp->pd_mode, 0); skb_queue_head_init(&sp->pd_lobby); sp->frag_interleave = 0; + sp->probe_interval = net->sctp.probe_interval; /* Create a per socket endpoint structure. Even if we * change the data structure relationships, this may still @@ -7905,6 +7965,66 @@ out: return 0; } +static int sctp_getsockopt_probe_interval(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_probeinterval params; + struct sctp_association *asoc; + struct sctp_transport *t; + __u32 probe_interval; + + if (len < sizeof(params)) + return -EINVAL; + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spi_address)) { + t = sctp_addr_id2transport(sk, ¶ms.spi_address, + params.spi_assoc_id); + if (!t) { + pr_debug("%s: failed no transport\n", __func__); + return -EINVAL; + } + + probe_interval = jiffies_to_msecs(t->probe_interval); + goto out; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, params.spi_assoc_id); + if (!asoc && params.spi_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + pr_debug("%s: failed no association\n", __func__); + return -EINVAL; + } + + if (asoc) { + probe_interval = jiffies_to_msecs(asoc->probe_interval); + goto out; + } + + probe_interval = sctp_sk(sk)->probe_interval; + +out: + params.spi_interval = probe_interval; + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + + if (put_user(len, optlen)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -8128,6 +8248,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); break; + case SCTP_PLPMTUD_PROBE_INTERVAL: + retval = sctp_getsockopt_probe_interval(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 55871b277f47..b46a416787ec 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -55,6 +55,8 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_auth(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sctp_table[] = { { @@ -294,6 +296,13 @@ static struct ctl_table sctp_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "plpmtud_probe_interval", + .data = &init_net.sctp.probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_probe_interval, + }, + { .procname = "udp_port", .data = &init_net.sctp.udp_port, .maxlen = sizeof(int), @@ -539,6 +548,32 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, return ret; } +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.probe_interval; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (new_value && new_value < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + net->sctp.probe_interval = new_value; + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index bf0ac467e757..f27b856ea8ce 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -75,6 +75,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net, timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0); timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0); timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0); + timer_setup(&peer->probe_timer, sctp_generate_probe_event, 0); timer_setup(&peer->proto_unreach_timer, sctp_generate_proto_unreach_event, 0); @@ -131,6 +132,9 @@ void sctp_transport_free(struct sctp_transport *transport) if (del_timer(&transport->reconf_timer)) sctp_transport_put(transport); + if (del_timer(&transport->probe_timer)) + sctp_transport_put(transport); + /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) sctp_transport_put(transport); @@ -207,6 +211,20 @@ void sctp_transport_reset_reconf_timer(struct sctp_transport *transport) sctp_transport_hold(transport); } +void sctp_transport_reset_probe_timer(struct sctp_transport *transport) +{ + int scale = 1; + + if (timer_pending(&transport->probe_timer)) + return; + if (transport->pl.state == SCTP_PL_COMPLETE && + transport->pl.probe_count == 1) + scale = 30; /* works as PMTU_RAISE_TIMER */ + if (!mod_timer(&transport->probe_timer, + jiffies + transport->probe_interval * scale)) + sctp_transport_hold(transport); +} + /* This transport has been assigned to an association. * Initialize fields from the association or from the sock itself. * Register the reference count in the association. @@ -241,12 +259,141 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = sctp_dst_mtu(transport->dst); else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + + sctp_transport_pl_update(transport); +} + +void sctp_transport_pl_send(struct sctp_transport *t) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + if (t->pl.probe_count < SCTP_MAX_PROBES) { + t->pl.probe_count++; + return; + } + + if (t->pl.state == SCTP_PL_BASE) { + if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ + t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ + + t->pl.pmtu = SCTP_MIN_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ + t->pl.state = SCTP_PL_BASE; /* Search -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_high = 0; + + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } else { /* Normal probe failure. */ + t->pl.probe_high = t->pl.probe_size; + t->pl.probe_size = t->pl.pmtu; + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ + t->pl.state = SCTP_PL_BASE; /* Search Complete -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } + t->pl.probe_count = 1; +} + +void sctp_transport_pl_recv(struct sctp_transport *t) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.pmtu = t->pl.probe_size; + t->pl.probe_count = 0; + if (t->pl.state == SCTP_PL_BASE) { + t->pl.state = SCTP_PL_SEARCH; /* Base -> Search */ + t->pl.probe_size += SCTP_PL_BIG_STEP; + } else if (t->pl.state == SCTP_PL_ERROR) { + t->pl.state = SCTP_PL_SEARCH; /* Error -> Search */ + + t->pl.pmtu = t->pl.probe_size; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + t->pl.probe_size += SCTP_PL_BIG_STEP; + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (!t->pl.probe_high) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return; + } + t->pl.probe_size += SCTP_PL_MIN_STEP; + if (t->pl.probe_size >= t->pl.probe_high) { + t->pl.probe_high = 0; + t->pl.state = SCTP_PL_COMPLETE; /* Search -> Search Complete */ + + t->pl.probe_size = t->pl.pmtu; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; + } +} + +static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu); + + if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size) + return false; + + if (t->pl.state == SCTP_PL_BASE) { + if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) { + t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ + + t->pl.pmtu = SCTP_MIN_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { + t->pl.state = SCTP_PL_BASE; /* Search -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_count = 0; + + t->pl.probe_high = 0; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) { + t->pl.probe_size = pmtu; + t->pl.probe_count = 0; + + return false; + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { + t->pl.state = SCTP_PL_BASE; /* Complete -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_count = 0; + + t->pl.probe_high = 0; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } + } + + return true; } bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { - struct dst_entry *dst = sctp_transport_dst_check(t); struct sock *sk = t->asoc->base.sk; + struct dst_entry *dst; bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { @@ -257,6 +404,10 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) } pmtu = SCTP_TRUNC4(pmtu); + if (sctp_transport_pl_enabled(t)) + return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t)); + + dst = sctp_transport_dst_check(t); if (dst) { struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family); union sctp_addr addr; diff --git a/net/smc/Makefile b/net/smc/Makefile index 77e54fe42b1c..99a0186cba5b 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -2,4 +2,4 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o -smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o +smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5eff7cccceff..e41fdac606d4 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -49,6 +49,7 @@ #include "smc_tx.h" #include "smc_rx.h" #include "smc_close.h" +#include "smc_stats.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -508,9 +509,44 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->r0.qp_mtu; } -static void smc_switch_to_fallback(struct smc_sock *smc) +static void smc_stat_inc_fback_rsn_cnt(struct smc_sock *smc, + struct smc_stats_fback *fback_arr) +{ + int cnt; + + for (cnt = 0; cnt < SMC_MAX_FBACK_RSN_CNT; cnt++) { + if (fback_arr[cnt].fback_code == smc->fallback_rsn) { + fback_arr[cnt].count++; + break; + } + if (!fback_arr[cnt].fback_code) { + fback_arr[cnt].fback_code = smc->fallback_rsn; + fback_arr[cnt].count++; + break; + } + } +} + +static void smc_stat_fallback(struct smc_sock *smc) +{ + struct net *net = sock_net(&smc->sk); + + mutex_lock(&net->smc.mutex_fback_rsn); + if (smc->listen_smc) { + smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->srv); + net->smc.fback_rsn->srv_fback_cnt++; + } else { + smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->clnt); + net->smc.fback_rsn->clnt_fback_cnt++; + } + mutex_unlock(&net->smc.mutex_fback_rsn); +} + +static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { smc->use_fallback = true; + smc->fallback_rsn = reason_code; + smc_stat_fallback(smc); if (smc->sk.sk_socket && smc->sk.sk_socket->file) { smc->clcsock->file = smc->sk.sk_socket->file; smc->clcsock->file->private_data = smc->clcsock; @@ -522,8 +558,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc) /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = reason_code; + smc_switch_to_fallback(smc, reason_code); smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) @@ -535,9 +570,11 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, u8 version) { + struct net *net = sock_net(&smc->sk); int rc; if (reason_code < 0) { /* error, fallback is not possible */ + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return reason_code; @@ -545,6 +582,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, if (reason_code != SMC_CLC_DECL_PEERDECL) { rc = smc_clc_send_decline(smc, reason_code, version); if (rc < 0) { + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return rc; @@ -992,6 +1030,7 @@ static int __smc_connect(struct smc_sock *smc) if (rc) goto vlan_cleanup; + SMC_STAT_CLNT_SUCC_INC(sock_net(smc->clcsock->sk), aclc); smc_connect_ism_vlan_cleanup(smc, ini); kfree(buf); kfree(ini); @@ -1307,7 +1346,9 @@ static void smc_listen_out_connected(struct smc_sock *new_smc) static void smc_listen_out_err(struct smc_sock *new_smc) { struct sock *newsmcsk = &new_smc->sk; + struct net *net = sock_net(newsmcsk); + this_cpu_inc(net->smc.smc_stats->srv_hshake_err_cnt); if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; @@ -1325,8 +1366,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, smc_listen_out_err(new_smc); return; } - smc_switch_to_fallback(new_smc); - new_smc->fallback_rsn = reason_code; + smc_switch_to_fallback(new_smc, reason_code); if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code, version) < 0) { smc_listen_out_err(new_smc); @@ -1699,8 +1739,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { - smc_switch_to_fallback(new_smc); - new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; + smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC); smc_listen_out_connected(new_smc); return; } @@ -1778,6 +1817,7 @@ static void smc_listen_work(struct work_struct *work) } smc_conn_save_peer_info(new_smc, cclc); smc_listen_out_connected(new_smc); + SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); goto out_free; out_unlock: @@ -1984,18 +2024,19 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; + smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; goto out; } } - if (smc->use_fallback) + if (smc->use_fallback) { rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len); - else + } else { rc = smc_tx_sendmsg(smc, msg, len); + SMC_STAT_TX_PAYLOAD(smc, len, rc); + } out: release_sock(sk); return rc; @@ -2030,6 +2071,7 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } else { msg->msg_namelen = 0; rc = smc_rx_recvmsg(smc, msg, NULL, len, flags); + SMC_STAT_RX_PAYLOAD(smc, rc, rc); } out: @@ -2194,8 +2236,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; + smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; } @@ -2204,18 +2245,22 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val) + if (val) { + SMC_STAT_INC(smc, ndly_cnt); mod_delayed_work(smc->conn.lgr->tx_wq, &smc->conn.tx_work, 0); + } } break; case TCP_CORK: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val) + if (!val) { + SMC_STAT_INC(smc, cork_cnt); mod_delayed_work(smc->conn.lgr->tx_wq, &smc->conn.tx_work, 0); + } } break; case TCP_DEFER_ACCEPT: @@ -2338,11 +2383,13 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, goto out; } release_sock(sk); - if (smc->use_fallback) + if (smc->use_fallback) { rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); - else + } else { + SMC_STAT_INC(smc, sendpage_cnt); rc = sock_no_sendpage(sock, page, offset, size, flags); + } out: return rc; @@ -2391,6 +2438,7 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, flags = MSG_DONTWAIT; else flags = 0; + SMC_STAT_INC(smc, splice_cnt); rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags); } out: @@ -2479,6 +2527,16 @@ static void __net_exit smc_net_exit(struct net *net) smc_pnet_net_exit(net); } +static __net_init int smc_net_stat_init(struct net *net) +{ + return smc_stats_init(net); +} + +static void __net_exit smc_net_stat_exit(struct net *net) +{ + smc_stats_exit(net); +} + static struct pernet_operations smc_net_ops = { .init = smc_net_init, .exit = smc_net_exit, @@ -2486,6 +2544,11 @@ static struct pernet_operations smc_net_ops = { .size = sizeof(struct smc_net), }; +static struct pernet_operations smc_net_stat_ops = { + .init = smc_net_stat_init, + .exit = smc_net_stat_exit, +}; + static int __init smc_init(void) { int rc; @@ -2494,6 +2557,10 @@ static int __init smc_init(void) if (rc) return rc; + rc = register_pernet_subsys(&smc_net_stat_ops); + if (rc) + return rc; + smc_ism_init(); smc_clc_init(); @@ -2595,6 +2662,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); + unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 317bc2c90fab..cd0d7c908b2a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -33,6 +33,7 @@ #include "smc_close.h" #include "smc_ism.h" #include "smc_netlink.h" +#include "smc_stats.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) @@ -2029,6 +2030,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + bool is_dgraded = false; struct mutex *lock; /* lock buffer list */ int sk_buf_size; @@ -2056,6 +2058,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); if (buf_desc) { + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); memset(buf_desc->cpu_addr, 0, bufsize); break; /* found reusable slot */ } @@ -2067,9 +2071,16 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (PTR_ERR(buf_desc) == -ENOMEM) break; - if (IS_ERR(buf_desc)) + if (IS_ERR(buf_desc)) { + if (!is_dgraded) { + is_dgraded = true; + SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb); + } continue; + } + SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; mutex_lock(lock); list_add(&buf_desc->list, buf_list); diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 140419a19dbf..6fb6f96c1d17 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -19,6 +19,7 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_ib.h" +#include "smc_stats.h" #include "smc_netlink.h" #define SMC_CMD_MAX_ATTR 1 @@ -55,6 +56,16 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcr_nl_get_device, }, + { + .cmd = SMC_NETLINK_GET_STATS, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_stats, + }, + { + .cmd = SMC_NETLINK_GET_FBACK_STATS, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_fback_stats, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 3477265cba6c..5ce2c0a89ccd 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -18,7 +18,7 @@ extern struct genl_family smc_gen_nl_family; struct smc_nl_dmp_ctx { - int pos[2]; + int pos[3]; }; static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index fcfac59f8b72..170b733bc736 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -21,6 +21,7 @@ #include "smc_cdc.h" #include "smc_tx.h" /* smc_tx_consumer_update() */ #include "smc_rx.h" +#include "smc_stats.h" /* callback implementation to wakeup consumers blocked with smc_rx_wait(). * indirectly called by smc_cdc_msg_recv_action(). @@ -227,6 +228,7 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, conn->urg_state == SMC_URG_READ) return -EINVAL; + SMC_STAT_INC(smc, urg_data_cnt); if (conn->urg_state == SMC_URG_VALID) { if (!(flags & MSG_PEEK)) smc->conn.urg_state = SMC_URG_READ; @@ -303,6 +305,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + readable = atomic_read(&conn->bytes_to_rcv); + if (readable >= conn->rmb_desc->len) + SMC_STAT_RMB_RX_FULL(smc, !conn->lnk); + + if (len < readable) + SMC_STAT_RMB_RX_SIZE_SMALL(smc, !conn->lnk); /* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */ rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr; diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c new file mode 100644 index 000000000000..e80e34f7ac15 --- /dev/null +++ b/net/smc/smc_stats.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * SMC statistics netlink routines + * + * Copyright IBM Corp. 2021 + * + * Author(s): Guvenc Gulce + */ +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/ctype.h> +#include <linux/smc.h> +#include <net/genetlink.h> +#include <net/sock.h> +#include "smc_netlink.h" +#include "smc_stats.h" + +int smc_stats_init(struct net *net) +{ + net->smc.fback_rsn = kzalloc(sizeof(*net->smc.fback_rsn), GFP_KERNEL); + if (!net->smc.fback_rsn) + goto err_fback; + net->smc.smc_stats = alloc_percpu(struct smc_stats); + if (!net->smc.smc_stats) + goto err_stats; + mutex_init(&net->smc.mutex_fback_rsn); + return 0; + +err_stats: + kfree(net->smc.fback_rsn); +err_fback: + return -ENOMEM; +} + +void smc_stats_exit(struct net *net) +{ + kfree(net->smc.fback_rsn); + if (net->smc.smc_stats) + free_percpu(net->smc.smc_stats); +} + +static int smc_nl_fill_stats_rmb_data(struct sk_buff *skb, + struct smc_stats *stats, int tech, + int type) +{ + struct smc_stats_rmbcnt *stats_rmb_cnt; + struct nlattr *attrs; + + if (type == SMC_NLA_STATS_T_TX_RMB_STATS) + stats_rmb_cnt = &stats->smc[tech].rmb_tx; + else + stats_rmb_cnt = &stats->smc[tech].rmb_rx; + + attrs = nla_nest_start(skb, type); + if (!attrs) + goto errout; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_REUSE_CNT, + stats_rmb_cnt->reuse_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT, + stats_rmb_cnt->buf_size_small_peer_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_CNT, + stats_rmb_cnt->buf_size_small_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_PEER_CNT, + stats_rmb_cnt->buf_full_peer_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_CNT, + stats_rmb_cnt->buf_full_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_ALLOC_CNT, + stats_rmb_cnt->alloc_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_DGRADE_CNT, + stats_rmb_cnt->dgrade_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_stats_bufsize_data(struct sk_buff *skb, + struct smc_stats *stats, int tech, + int type) +{ + struct smc_stats_memsize *stats_pload; + struct nlattr *attrs; + + if (type == SMC_NLA_STATS_T_TXPLOAD_SIZE) + stats_pload = &stats->smc[tech].tx_pd; + else if (type == SMC_NLA_STATS_T_RXPLOAD_SIZE) + stats_pload = &stats->smc[tech].rx_pd; + else if (type == SMC_NLA_STATS_T_TX_RMB_SIZE) + stats_pload = &stats->smc[tech].tx_rmbsize; + else if (type == SMC_NLA_STATS_T_RX_RMB_SIZE) + stats_pload = &stats->smc[tech].rx_rmbsize; + else + goto errout; + + attrs = nla_nest_start(skb, type); + if (!attrs) + goto errout; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_8K, + stats_pload->buf[SMC_BUF_8K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_16K, + stats_pload->buf[SMC_BUF_16K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_32K, + stats_pload->buf[SMC_BUF_32K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_64K, + stats_pload->buf[SMC_BUF_64K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_128K, + stats_pload->buf[SMC_BUF_128K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_256K, + stats_pload->buf[SMC_BUF_256K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_512K, + stats_pload->buf[SMC_BUF_512K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_1024K, + stats_pload->buf[SMC_BUF_1024K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_G_1024K, + stats_pload->buf[SMC_BUF_G_1024K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, + struct smc_stats *stats, int tech) +{ + struct smc_stats_tech *smc_tech; + struct nlattr *attrs; + + smc_tech = &stats->smc[tech]; + if (tech == SMC_TYPE_D) + attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCD_TECH); + else + attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCR_TECH); + + if (!attrs) + goto errout; + if (smc_nl_fill_stats_rmb_data(skb, stats, tech, + SMC_NLA_STATS_T_TX_RMB_STATS)) + goto errattr; + if (smc_nl_fill_stats_rmb_data(skb, stats, tech, + SMC_NLA_STATS_T_RX_RMB_STATS)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_TXPLOAD_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_RXPLOAD_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_TX_RMB_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_RX_RMB_SIZE)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V1_SUCC, + smc_tech->clnt_v1_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V2_SUCC, + smc_tech->clnt_v2_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V1_SUCC, + smc_tech->srv_v1_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V2_SUCC, + smc_tech->srv_v2_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_BYTES, + smc_tech->rx_bytes, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_BYTES, + smc_tech->tx_bytes, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, + smc_tech->rx_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_CNT, + smc_tech->tx_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT, + smc_tech->sendpage_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT, + smc_tech->cork_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_NDLY_CNT, + smc_tech->ndly_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SPLICE_CNT, + smc_tech->splice_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_URG_DATA_CNT, + smc_tech->urg_data_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +int smc_nl_get_stats(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + struct smc_stats *stats; + struct nlattr *attrs; + int cpu, i, size; + void *nlh; + u64 *src; + u64 *sum; + + if (cb_ctx->pos[0]) + goto errmsg; + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_STATS); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_STATS); + if (!attrs) + goto errnest; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); + if (!stats) + goto erralloc; + size = sizeof(*stats) / sizeof(u64); + for_each_possible_cpu(cpu) { + src = (u64 *)per_cpu_ptr(net->smc.smc_stats, cpu); + sum = (u64 *)stats; + for (i = 0; i < size; i++) + *(sum++) += *(src++); + } + if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_D)) + goto errattr; + if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_R)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_CLNT_HS_ERR_CNT, + stats->clnt_hshake_err_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_SRV_HS_ERR_CNT, + stats->srv_hshake_err_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + cb_ctx->pos[0] = 1; + kfree(stats); + return skb->len; + +errattr: + kfree(stats); +erralloc: + nla_nest_cancel(skb, attrs); +errnest: + genlmsg_cancel(skb, nlh); +errmsg: + return skb->len; +} + +static int smc_nl_get_fback_details(struct sk_buff *skb, + struct netlink_callback *cb, int pos, + bool is_srv) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + int cnt_reported = cb_ctx->pos[2]; + struct smc_stats_fback *trgt_arr; + struct nlattr *attrs; + int rc = 0; + void *nlh; + + if (is_srv) + trgt_arr = &net->smc.fback_rsn->srv[0]; + else + trgt_arr = &net->smc.fback_rsn->clnt[0]; + if (!trgt_arr[pos].fback_code) + return -ENODATA; + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_FBACK_STATS); + if (!nlh) + goto errmsg; + attrs = nla_nest_start(skb, SMC_GEN_FBACK_STATS); + if (!attrs) + goto errout; + if (nla_put_u8(skb, SMC_NLA_FBACK_STATS_TYPE, is_srv)) + goto errattr; + if (!cnt_reported) { + if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_SRV_CNT, + net->smc.fback_rsn->srv_fback_cnt, + SMC_NLA_FBACK_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_CLNT_CNT, + net->smc.fback_rsn->clnt_fback_cnt, + SMC_NLA_FBACK_STATS_PAD)) + goto errattr; + cnt_reported = 1; + } + + if (nla_put_u32(skb, SMC_NLA_FBACK_STATS_RSN_CODE, + trgt_arr[pos].fback_code)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_FBACK_STATS_RSN_CNT, + trgt_arr[pos].count)) + goto errattr; + + cb_ctx->pos[2] = cnt_reported; + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return rc; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + int rc_srv = 0, rc_clnt = 0, k; + int skip_serv = cb_ctx->pos[1]; + int snum = cb_ctx->pos[0]; + bool is_srv = true; + + mutex_lock(&net->smc.mutex_fback_rsn); + for (k = 0; k < SMC_MAX_FBACK_RSN_CNT; k++) { + if (k < snum) + continue; + if (!skip_serv) { + rc_srv = smc_nl_get_fback_details(skb, cb, k, is_srv); + if (rc_srv && rc_srv != -ENODATA) + break; + } else { + skip_serv = 0; + } + rc_clnt = smc_nl_get_fback_details(skb, cb, k, !is_srv); + if (rc_clnt && rc_clnt != -ENODATA) { + skip_serv = 1; + break; + } + if (rc_clnt == -ENODATA && rc_srv == -ENODATA) + break; + } + mutex_unlock(&net->smc.mutex_fback_rsn); + cb_ctx->pos[1] = skip_serv; + cb_ctx->pos[0] = k; + return skb->len; +} diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h new file mode 100644 index 000000000000..84b7ecd8c05c --- /dev/null +++ b/net/smc/smc_stats.h @@ -0,0 +1,266 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Macros for SMC statistics + * + * Copyright IBM Corp. 2021 + * + * Author(s): Guvenc Gulce + */ + +#ifndef NET_SMC_SMC_STATS_H_ +#define NET_SMC_SMC_STATS_H_ +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/ctype.h> +#include <linux/smc.h> + +#include "smc_clc.h" + +#define SMC_MAX_FBACK_RSN_CNT 30 + +enum { + SMC_BUF_8K, + SMC_BUF_16K, + SMC_BUF_32K, + SMC_BUF_64K, + SMC_BUF_128K, + SMC_BUF_256K, + SMC_BUF_512K, + SMC_BUF_1024K, + SMC_BUF_G_1024K, + SMC_BUF_MAX, +}; + +struct smc_stats_fback { + int fback_code; + u16 count; +}; + +struct smc_stats_rsn { + struct smc_stats_fback srv[SMC_MAX_FBACK_RSN_CNT]; + struct smc_stats_fback clnt[SMC_MAX_FBACK_RSN_CNT]; + u64 srv_fback_cnt; + u64 clnt_fback_cnt; +}; + +struct smc_stats_rmbcnt { + u64 buf_size_small_peer_cnt; + u64 buf_size_small_cnt; + u64 buf_full_peer_cnt; + u64 buf_full_cnt; + u64 reuse_cnt; + u64 alloc_cnt; + u64 dgrade_cnt; +}; + +struct smc_stats_memsize { + u64 buf[SMC_BUF_MAX]; +}; + +struct smc_stats_tech { + struct smc_stats_memsize tx_rmbsize; + struct smc_stats_memsize rx_rmbsize; + struct smc_stats_memsize tx_pd; + struct smc_stats_memsize rx_pd; + struct smc_stats_rmbcnt rmb_tx; + struct smc_stats_rmbcnt rmb_rx; + u64 clnt_v1_succ_cnt; + u64 clnt_v2_succ_cnt; + u64 srv_v1_succ_cnt; + u64 srv_v2_succ_cnt; + u64 sendpage_cnt; + u64 urg_data_cnt; + u64 splice_cnt; + u64 cork_cnt; + u64 ndly_cnt; + u64 rx_bytes; + u64 tx_bytes; + u64 rx_cnt; + u64 tx_cnt; +}; + +struct smc_stats { + struct smc_stats_tech smc[2]; + u64 clnt_hshake_err_cnt; + u64 srv_hshake_err_cnt; +}; + +#define SMC_STAT_PAYLOAD_SUB(_smc_stats, _tech, key, _len, _rc) \ +do { \ + typeof(_smc_stats) stats = (_smc_stats); \ + typeof(_tech) t = (_tech); \ + typeof(_len) l = (_len); \ + int _pos = fls64((l) >> 13); \ + typeof(_rc) r = (_rc); \ + int m = SMC_BUF_MAX - 1; \ + this_cpu_inc((*stats).smc[t].key ## _cnt); \ + if (r <= 0) \ + break; \ + _pos = (_pos < m) ? ((l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + this_cpu_inc((*stats).smc[t].key ## _pd.buf[_pos]); \ + this_cpu_add((*stats).smc[t].key ## _bytes, r); \ +} \ +while (0) + +#define SMC_STAT_TX_PAYLOAD(_smc, length, rcode) \ +do { \ + typeof(_smc) __smc = _smc; \ + struct net *_net = sock_net(&__smc->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(length) _len = (length); \ + typeof(rcode) _rc = (rcode); \ + bool is_smcd = !__smc->conn.lnk; \ + if (is_smcd) \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, tx, _len, _rc); \ + else \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, tx, _len, _rc); \ +} \ +while (0) + +#define SMC_STAT_RX_PAYLOAD(_smc, length, rcode) \ +do { \ + typeof(_smc) __smc = _smc; \ + struct net *_net = sock_net(&__smc->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(length) _len = (length); \ + typeof(rcode) _rc = (rcode); \ + bool is_smcd = !__smc->conn.lnk; \ + if (is_smcd) \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, rx, _len, _rc); \ + else \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, rx, _len, _rc); \ +} \ +while (0) + +#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \ +do { \ + typeof(_len) _l = (_len); \ + typeof(_tech) t = (_tech); \ + int _pos = fls((_l) >> 13); \ + int m = SMC_BUF_MAX - 1; \ + _pos = (_pos < m) ? ((_l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ +} \ +while (0) + +#define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \ + this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt) + +#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \ +do { \ + struct net *_net = sock_net(&(_smc)->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(_is_smcd) is_d = (_is_smcd); \ + typeof(_is_rx) is_r = (_is_rx); \ + typeof(_len) l = (_len); \ + if ((is_d) && (is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \ + if ((is_d) && !(is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \ + if (!(is_d) && (is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \ + if (!(is_d) && !(is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \ +} \ +while (0) + +#define SMC_STAT_RMB(_smc, type, _is_smcd, _is_rx) \ +do { \ + struct net *net = sock_net(&(_smc)->sk); \ + struct smc_stats __percpu *_smc_stats = net->smc.smc_stats; \ + typeof(_is_smcd) is_d = (_is_smcd); \ + typeof(_is_rx) is_r = (_is_rx); \ + if ((is_d) && (is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, rx); \ + if ((is_d) && !(is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, tx); \ + if (!(is_d) && (is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, rx); \ + if (!(is_d) && !(is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, tx); \ +} \ +while (0) + +#define SMC_STAT_BUF_REUSE(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, reuse, is_smcd, is_rx) + +#define SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, alloc, is_smcd, is_rx) + +#define SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, dgrade, is_smcd, is_rx) + +#define SMC_STAT_RMB_TX_PEER_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full_peer, is_smcd, false) + +#define SMC_STAT_RMB_TX_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full, is_smcd, false) + +#define SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small_peer, is_smcd, false) + +#define SMC_STAT_RMB_TX_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small, is_smcd, false) + +#define SMC_STAT_RMB_RX_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small, is_smcd, true) + +#define SMC_STAT_RMB_RX_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full, is_smcd, true) + +#define SMC_STAT_INC(_smc, type) \ +do { \ + typeof(_smc) __smc = _smc; \ + bool is_smcd = !(__smc)->conn.lnk; \ + struct net *net = sock_net(&(__smc)->sk); \ + struct smc_stats __percpu *smc_stats = net->smc.smc_stats; \ + if ((is_smcd)) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].type); \ + else \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].type); \ +} \ +while (0) + +#define SMC_STAT_CLNT_SUCC_INC(net, _aclc) \ +do { \ + typeof(_aclc) acl = (_aclc); \ + bool is_v2 = (acl->hdr.version == SMC_V2); \ + bool is_smcd = (acl->hdr.typev1 == SMC_TYPE_D); \ + struct smc_stats __percpu *smc_stats = (net)->smc.smc_stats; \ + if (is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v2_succ_cnt); \ + else if (is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v2_succ_cnt); \ + else if (!is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v1_succ_cnt); \ + else if (!is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v1_succ_cnt); \ +} \ +while (0) + +#define SMC_STAT_SERV_SUCC_INC(net, _ini) \ +do { \ + typeof(_ini) i = (_ini); \ + bool is_v2 = (i->smcd_version & SMC_V2); \ + bool is_smcd = (i->is_smcd); \ + typeof(net->smc.smc_stats) smc_stats = (net)->smc.smc_stats; \ + if (is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v2_succ_cnt); \ + else if (is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v2_succ_cnt); \ + else if (!is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v1_succ_cnt); \ + else if (!is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v1_succ_cnt); \ +} \ +while (0) + +int smc_nl_get_stats(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb); +int smc_stats_init(struct net *net); +void smc_stats_exit(struct net *net); + +#endif /* NET_SMC_SMC_STATS_H_ */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 4532c16bf85e..075c4f4b41cf 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -27,6 +27,7 @@ #include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" +#include "smc_stats.h" #define SMC_TX_WORK_DELAY 0 #define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ @@ -45,6 +46,8 @@ static void smc_tx_write_space(struct sock *sk) /* similar to sk_stream_write_space */ if (atomic_read(&smc->conn.sndbuf_space) && sock) { + if (test_bit(SOCK_NOSPACE, &sock->flags)) + SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk); clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); @@ -151,6 +154,15 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) goto out_err; } + if (len > conn->sndbuf_desc->len) + SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk); + + if (len > conn->peer_rmbe_size) + SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk); + + if (msg->msg_flags & MSG_OOB) + SMC_STAT_INC(smc, urg_data_cnt); + while (msg_data_left(msg)) { if (sk->sk_state == SMC_INIT) return -ENOTCONN; @@ -419,8 +431,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* destination: RMBE */ /* cf. snd_wnd */ rmbespace = atomic_read(&conn->peer_rmbe_space); - if (rmbespace <= 0) + if (rmbespace <= 0) { + struct smc_sock *smc = container_of(conn, struct smc_sock, + conn); + SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); return 0; + } smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); diff --git a/net/socket.c b/net/socket.c index 27e3e7d53f8e..bd9233da2497 100644 --- a/net/socket.c +++ b/net/socket.c @@ -165,6 +165,54 @@ static const struct file_operations socket_file_ops = { .show_fdinfo = sock_show_fdinfo, }; +static const char * const pf_family_names[] = { + [PF_UNSPEC] = "PF_UNSPEC", + [PF_UNIX] = "PF_UNIX/PF_LOCAL", + [PF_INET] = "PF_INET", + [PF_AX25] = "PF_AX25", + [PF_IPX] = "PF_IPX", + [PF_APPLETALK] = "PF_APPLETALK", + [PF_NETROM] = "PF_NETROM", + [PF_BRIDGE] = "PF_BRIDGE", + [PF_ATMPVC] = "PF_ATMPVC", + [PF_X25] = "PF_X25", + [PF_INET6] = "PF_INET6", + [PF_ROSE] = "PF_ROSE", + [PF_DECnet] = "PF_DECnet", + [PF_NETBEUI] = "PF_NETBEUI", + [PF_SECURITY] = "PF_SECURITY", + [PF_KEY] = "PF_KEY", + [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", + [PF_PACKET] = "PF_PACKET", + [PF_ASH] = "PF_ASH", + [PF_ECONET] = "PF_ECONET", + [PF_ATMSVC] = "PF_ATMSVC", + [PF_RDS] = "PF_RDS", + [PF_SNA] = "PF_SNA", + [PF_IRDA] = "PF_IRDA", + [PF_PPPOX] = "PF_PPPOX", + [PF_WANPIPE] = "PF_WANPIPE", + [PF_LLC] = "PF_LLC", + [PF_IB] = "PF_IB", + [PF_MPLS] = "PF_MPLS", + [PF_CAN] = "PF_CAN", + [PF_TIPC] = "PF_TIPC", + [PF_BLUETOOTH] = "PF_BLUETOOTH", + [PF_IUCV] = "PF_IUCV", + [PF_RXRPC] = "PF_RXRPC", + [PF_ISDN] = "PF_ISDN", + [PF_PHONET] = "PF_PHONET", + [PF_IEEE802154] = "PF_IEEE802154", + [PF_CAIF] = "PF_CAIF", + [PF_ALG] = "PF_ALG", + [PF_NFC] = "PF_NFC", + [PF_VSOCK] = "PF_VSOCK", + [PF_KCM] = "PF_KCM", + [PF_QIPCRTR] = "PF_QIPCRTR", + [PF_SMC] = "PF_SMC", + [PF_XDP] = "PF_XDP", +}; + /* * The protocol list. Each protocol is registered in here. */ @@ -1072,19 +1120,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -/** - * get_net_ns - increment the refcount of the network namespace - * @ns: common namespace (net) - * - * Returns the net's common namespace. - */ - -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; @@ -2988,7 +3023,7 @@ int sock_register(const struct net_proto_family *ops) } spin_unlock(&net_family_lock); - pr_info("NET: Registered protocol family %d\n", ops->family); + pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); @@ -3016,7 +3051,7 @@ void sock_unregister(int family) synchronize_rcu(); - pr_info("NET: Unregistered protocol family %d\n", family); + pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f555d335e910..42623d6b8f0e 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1677,13 +1677,6 @@ call_reserveresult(struct rpc_task *task) return; } - /* - * Even though there was an error, we may have acquired - * a request slot somehow. Make sure not to leak it. - */ - if (task->tk_rqstp) - xprt_release(task); - switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e5b5a960a69b..3509a7f139b9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -70,6 +70,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -1606,17 +1607,40 @@ xprt_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } -static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) +static void xprt_complete_request_init(struct rpc_task *task) +{ + if (task->tk_rqstp) + xprt_request_init(task); +} + +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) { set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); + rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init); +} +EXPORT_SYMBOL_GPL(xprt_add_backlog); + +static bool __xprt_set_rq(struct rpc_task *task, void *data) +{ + struct rpc_rqst *req = data; + + if (task->tk_rqstp == NULL) { + memset(req, 0, sizeof(*req)); /* mark unused */ + task->tk_rqstp = req; + return true; + } + return false; } -static void xprt_wake_up_backlog(struct rpc_xprt *xprt) +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (rpc_wake_up_next(&xprt->backlog) == NULL) + if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) { clear_bit(XPRT_CONGESTED, &xprt->state); + return false; + } + return true; } +EXPORT_SYMBOL_GPL(xprt_wake_up_backlog); static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task) { @@ -1626,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task goto out; spin_lock(&xprt->reserve_lock); if (test_bit(XPRT_CONGESTED, &xprt->state)) { - rpc_sleep_on(&xprt->backlog, task, NULL); + xprt_add_backlog(xprt, task); ret = true; } spin_unlock(&xprt->reserve_lock); @@ -1703,11 +1727,11 @@ EXPORT_SYMBOL_GPL(xprt_alloc_slot); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { spin_lock(&xprt->reserve_lock); - if (!xprt_dynamic_free_slot(xprt, req)) { + if (!xprt_wake_up_backlog(xprt, req) && + !xprt_dynamic_free_slot(xprt, req)) { memset(req, 0, sizeof(*req)); /* mark unused */ list_add(&req->rq_list, &xprt->free); } - xprt_wake_up_backlog(xprt); spin_unlock(&xprt->reserve_lock); } EXPORT_SYMBOL_GPL(xprt_free_slot); @@ -1894,10 +1918,10 @@ void xprt_release(struct rpc_task *task) xdr_free_bvec(&req->rq_snd_buf); if (req->rq_cred != NULL) put_rpccred(req->rq_cred); - task->tk_rqstp = NULL; if (req->rq_release_snd_buf) req->rq_release_snd_buf(req); + task->tk_rqstp = NULL; if (likely(!bc_prealloc(req))) xprt->ops->free_slot(xprt, req); else diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 649f7d8b9733..c335c1361564 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -628,8 +628,9 @@ out_mapping_err: return false; } -/* The tail iovec might not reside in the same page as the - * head iovec. +/* 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. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -747,19 +748,27 @@ 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 handled + /* If there is a Read chunk, the page list is being handled * via explicit RDMA, and thus is skipped here. */ - if (tail->iov_len) { - if (!rpcrdma_prepare_tail_iov(req, xdr, - offset_in_page(tail->iov_base), - tail->iov_len)) + /* 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)) return false; kref_get(&req->rl_kref); } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 09953597d055..19a49d26b1e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: - set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); task->tk_status = -EAGAIN; + xprt_add_backlog(xprt, task); } /** @@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = container_of(xprt, struct rpcrdma_xprt, rx_xprt); - memset(rqst, 0, sizeof(*rqst)); - rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); - if (unlikely(!rpc_wake_up_next(&xprt->backlog))) - clear_bit(XPRT_CONGESTED, &xprt->state); + rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + if (!xprt_wake_up_backlog(xprt, rqst)) { + memset(rqst, 0, sizeof(*rqst)); + rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + } } static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 1e965a380896..649c23518ec0 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1201,6 +1201,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt) } /** + * rpcrdma_reply_put - Put reply buffers back into pool + * @buffers: buffer pool + * @req: object to return + * + */ +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + if (req->rl_reply) { + rpcrdma_rep_put(buffers, req->rl_reply); + req->rl_reply = NULL; + } +} + +/** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer * @@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) */ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) { - if (req->rl_reply) - rpcrdma_rep_put(buffers, req->rl_reply); - req->rl_reply = NULL; + rpcrdma_reply_put(buffers, req); spin_lock(&buffers->rb_lock); list_add(&req->rl_list, &buffers->rb_send_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 436ad7312614..5d231d94e944 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep); +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 47aa47a2b07c..316d04945587 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1010,6 +1010,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) kernel_sock_shutdown(transport->sock, SHUT_RDWR); return -ENOTCONN; } + if (!transport->inet) + return -ENOTCONN; xs_pktdump("packet data:", req->rq_svec->iov_base, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4d4f24cbd86b..58c2f318b0a8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -262,6 +262,14 @@ static void __unix_insert_socket(struct hlist_head *list, struct sock *sk) sk_add_node(sk, list); } +static void __unix_set_addr(struct sock *sk, struct unix_address *addr, + unsigned hash) +{ + __unix_remove_socket(sk); + smp_store_release(&unix_sk(sk)->addr, addr); + __unix_insert_socket(&unix_socket_table[hash], sk); +} + static inline void unix_remove_socket(struct sock *sk) { spin_lock(&unix_table_lock); @@ -278,11 +286,11 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk) static struct sock *__unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, unsigned int hash) + int len, unsigned int hash) { struct sock *s; - sk_for_each(s, &unix_socket_table[hash ^ type]) { + sk_for_each(s, &unix_socket_table[hash]) { struct unix_sock *u = unix_sk(s); if (!net_eq(sock_net(s), net)) @@ -297,13 +305,12 @@ static struct sock *__unix_find_socket_byname(struct net *net, static inline struct sock *unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, - unsigned int hash) + int len, unsigned int hash) { struct sock *s; spin_lock(&unix_table_lock); - s = __unix_find_socket_byname(net, sunname, len, type, hash); + s = __unix_find_socket_byname(net, sunname, len, hash); if (s) sock_hold(s); spin_unlock(&unix_table_lock); @@ -535,12 +542,14 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk); wake_up_interruptible_all(&u->peer_wait); - skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); @@ -555,7 +564,6 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; } /* Try to flush out this socket. Throw out buffers at least */ @@ -890,12 +898,12 @@ static int unix_autobind(struct socket *sock) retry: addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short); addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0)); + addr->hash ^= sk->sk_type; spin_lock(&unix_table_lock); ordernum = (ordernum+1)&0xFFFFF; - if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, - addr->hash)) { + if (__unix_find_socket_byname(net, addr->name, addr->len, addr->hash)) { spin_unlock(&unix_table_lock); /* * __unix_find_socket_byname() may take long time if many names @@ -910,11 +918,8 @@ retry: } goto retry; } - addr->hash ^= sk->sk_type; - __unix_remove_socket(sk); - smp_store_release(&u->addr, addr); - __unix_insert_socket(&unix_socket_table[addr->hash], sk); + __unix_set_addr(sk, addr, addr->hash); spin_unlock(&unix_table_lock); err = 0; @@ -959,7 +964,7 @@ static struct sock *unix_find_other(struct net *net, } } else { err = -ECONNREFUSED; - u = unix_find_socket_byname(net, sunname, len, type, hash); + u = unix_find_socket_byname(net, sunname, len, type ^ hash); if (u) { struct dentry *dentry; dentry = unix_sk(u)->path.dentry; @@ -977,125 +982,125 @@ fail: return NULL; } -static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +static int unix_bind_bsd(struct sock *sk, struct unix_address *addr) { + struct unix_sock *u = unix_sk(sk); + umode_t mode = S_IFSOCK | + (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); + struct user_namespace *ns; // barf... + struct path parent; struct dentry *dentry; - struct path path; - int err = 0; + unsigned int hash; + int err; + /* * Get the parent directory, calculate the hash for last * component. */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); + dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0); if (IS_ERR(dentry)) - return err; + return PTR_ERR(dentry); + ns = mnt_user_ns(parent.mnt); /* * All right, let's create it. */ - err = security_path_mknod(&path, dentry, mode, 0); - if (!err) { - 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); - } - } - done_path_create(&path, dentry); + err = security_path_mknod(&parent, dentry, mode, 0); + if (!err) + err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0); + if (err) + goto out; + err = mutex_lock_interruptible(&u->bindlock); + if (err) + goto out_unlink; + if (u->addr) + goto out_unlock; + + addr->hash = UNIX_HASH_SIZE; + hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + spin_lock(&unix_table_lock); + u->path.mnt = mntget(parent.mnt); + u->path.dentry = dget(dentry); + __unix_set_addr(sk, addr, hash); + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + done_path_create(&parent, dentry); + return 0; + +out_unlock: + mutex_unlock(&u->bindlock); + err = -EINVAL; +out_unlink: + /* failed after successful mknod? unlink what we'd created... */ + vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL); +out: + done_path_create(&parent, dentry); return err; } +static int unix_bind_abstract(struct sock *sk, struct unix_address *addr) +{ + struct unix_sock *u = unix_sk(sk); + int err; + + err = mutex_lock_interruptible(&u->bindlock); + if (err) + return err; + + if (u->addr) { + mutex_unlock(&u->bindlock); + return -EINVAL; + } + + spin_lock(&unix_table_lock); + if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len, + addr->hash)) { + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + return -EADDRINUSE; + } + __unix_set_addr(sk, addr, addr->hash); + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + return 0; +} + static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - struct net *net = sock_net(sk); - struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; int err; unsigned int hash; struct unix_address *addr; - struct hlist_head *list; - struct path path = { }; - err = -EINVAL; if (addr_len < offsetofend(struct sockaddr_un, sun_family) || sunaddr->sun_family != AF_UNIX) - goto out; + return -EINVAL; - if (addr_len == sizeof(short)) { - err = unix_autobind(sock); - goto out; - } + if (addr_len == sizeof(short)) + return unix_autobind(sock); err = unix_mkname(sunaddr, addr_len, &hash); if (err < 0) - goto out; + return err; addr_len = err; - - if (sun_path[0]) { - umode_t mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); - if (err) { - if (err == -EEXIST) - err = -EADDRINUSE; - goto out; - } - } - - err = mutex_lock_interruptible(&u->bindlock); - if (err) - goto out_put; - - err = -EINVAL; - if (u->addr) - goto out_up; - - err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) - goto out_up; + return -ENOMEM; memcpy(addr->name, sunaddr, addr_len); addr->len = addr_len; addr->hash = hash ^ sk->sk_type; refcount_set(&addr->refcnt, 1); - if (sun_path[0]) { - addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); - spin_lock(&unix_table_lock); - u->path = path; - list = &unix_socket_table[hash]; - } else { - spin_lock(&unix_table_lock); - err = -EADDRINUSE; - if (__unix_find_socket_byname(net, sunaddr, addr_len, - sk->sk_type, hash)) { - unix_release_addr(addr); - goto out_unlock; - } - - list = &unix_socket_table[addr->hash]; - } - - err = 0; - __unix_remove_socket(sk); - smp_store_release(&u->addr, addr); - __unix_insert_socket(list, sk); - -out_unlock: - spin_unlock(&unix_table_lock); -out_up: - mutex_unlock(&u->bindlock); -out_put: + if (sun_path[0]) + err = unix_bind_bsd(sk, addr); + else + err = unix_bind_abstract(sk, addr); if (err) - path_put(&path); -out: - return err; + unix_release_addr(addr); + return err == -EEXIST ? -EADDRINUSE : err; } static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 67954afef4e1..21ccf450e249 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -860,7 +860,7 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_stream_has_data); -static s64 vsock_has_data(struct vsock_sock *vsk) +static s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); @@ -1866,10 +1866,11 @@ out: return err; } -static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, - long timeout, - struct vsock_transport_recv_notify_data *recv_data, - size_t target) +static int vsock_connectible_wait_data(struct sock *sk, + struct wait_queue_entry *wait, + long timeout, + struct vsock_transport_recv_notify_data *recv_data, + size_t target) { const struct vsock_transport *transport; struct vsock_sock *vsk; @@ -1880,7 +1881,7 @@ static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, err = 0; transport = vsk->transport; - while ((data = vsock_has_data(vsk)) == 0) { + while ((data = vsock_connectible_has_data(vsk)) == 0) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); if (sk->sk_err != 0 || @@ -1967,7 +1968,8 @@ static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, while (1) { ssize_t read; - err = vsock_wait_data(sk, &wait, timeout, &recv_data, target); + err = vsock_connectible_wait_data(sk, &wait, timeout, + &recv_data, target); if (err <= 0) break; @@ -2022,7 +2024,7 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - err = vsock_wait_data(sk, &wait, timeout, NULL, 0); + err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); if (err <= 0) goto out; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e73ce652bf3c..ed1664e7bd88 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -498,9 +498,11 @@ static bool virtio_transport_seqpacket_allow(u32 remote_cid) struct virtio_vsock *vsock; bool seqpacket_allow; + seqpacket_allow = false; rcu_read_lock(); vsock = rcu_dereference(the_virtio_vsock); - seqpacket_allow = vsock->seqpacket_allow; + if (vsock) + seqpacket_allow = vsock->seqpacket_allow; rcu_read_unlock(); return seqpacket_allow; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 23704a6bc437..f014ccfdd9c2 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -413,7 +413,6 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; int dequeued_len = 0; size_t user_buf_len = msg_data_left(msg); - bool copy_failed = false; bool msg_ready = false; spin_lock_bh(&vvs->rx_lock); @@ -426,7 +425,7 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, while (!msg_ready) { pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); - if (!copy_failed) { + if (dequeued_len >= 0) { size_t pkt_len; size_t bytes_to_copy; @@ -443,11 +442,9 @@ static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); if (err) { - /* Copy of message failed, set flag to skip - * copy path for rest of fragments. Rest of + /* Copy of message failed. Rest of * fragments will be freed without copy. */ - copy_failed = true; dequeued_len = err; } else { user_buf_len -= bytes_to_copy; diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 2eee93985ab0..af590ae606b6 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -28,7 +28,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" @(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ - cat $^ ; \ + echo | cat - $^ ; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@ diff --git a/net/wireless/core.c b/net/wireless/core.c index 6fbf7537faf5..8d0883e81093 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1340,6 +1340,11 @@ void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, rdev->devlist_generation++; wdev->registered = true; + if (wdev->netdev && + sysfs_create_link(&wdev->netdev->dev.kobj, &rdev->wiphy.dev.kobj, + "phy80211")) + pr_err("failed to add phy80211 symlink to netdev!\n"); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); } @@ -1365,14 +1370,6 @@ int cfg80211_register_netdevice(struct net_device *dev) if (ret) goto out; - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, - "phy80211")) { - pr_err("failed to add phy80211 symlink to netdev!\n"); - unregister_netdevice(dev); - ret = -EINVAL; - goto out; - } - cfg80211_register_wdev(rdev, wdev); ret = 0; out: diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 6bdd96408022..d245968b74cb 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -334,6 +334,7 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, gfp_t gfp) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_pmsr_request *tmp, *prev, *to_free = NULL; struct sk_buff *msg; void *hdr; @@ -364,9 +365,20 @@ free_msg: nlmsg_free(msg); free_request: spin_lock_bh(&wdev->pmsr_lock); - list_del(&req->list); + /* + * cfg80211_pmsr_process_abort() may have already moved this request + * to the free list, and will free it later. In this case, don't free + * it here. + */ + list_for_each_entry_safe(tmp, prev, &wdev->pmsr_list, list) { + if (tmp == req) { + list_del(&req->list); + to_free = req; + break; + } + } spin_unlock_bh(&wdev->pmsr_lock); - kfree(req); + kfree(to_free); } EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete); diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 9b959e3b09c6..0c3f05c9be27 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -133,6 +133,10 @@ static int wiphy_resume(struct device *dev) if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); wiphy_unlock(&rdev->wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(&rdev->wiphy); + rtnl_unlock(); return ret; diff --git a/net/wireless/util.c b/net/wireless/util.c index 7ec021a610ae..18dba3d7c638 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1059,6 +1059,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; } diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56a28a686988..f01ef6bda390 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -27,7 +27,7 @@ static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; } @@ -99,8 +99,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) long npgs; int err; - umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), - GFP_KERNEL | __GFP_NOWARN); + umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN); if (!umem->pgs) return -ENOMEM; @@ -123,7 +122,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) out_pin: xdp_umem_unpin_pages(umem); out_pgs: - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; return err; } diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 67b4ce504852..9df75ea4a567 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -226,7 +226,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __xsk_map_lookup_elem); } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, |