diff options
Diffstat (limited to 'net')
140 files changed, 1684 insertions, 788 deletions
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index 7b3341cef926..850d4a185f55 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -179,4 +179,5 @@ static void __exit lowpan_module_exit(void) module_init(lowpan_module_init); module_exit(lowpan_module_exit); +MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module"); MODULE_LICENSE("GPL"); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 033871e718a3..324e3ab96bb3 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1532,4 +1532,5 @@ static void __exit atm_mpoa_cleanup(void) module_init(atm_mpoa_init); module_exit(atm_mpoa_cleanup); +MODULE_DESCRIPTION("Multi-Protocol Over ATM (MPOA) driver"); MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 65601aa52e0d..2821a42cefdc 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1049,6 +1049,7 @@ static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); + hci_dev_hold(hdev); BT_DBG("%s", hdev->name); if (hdev->hw_error) @@ -1056,10 +1057,10 @@ static void hci_error_reset(struct work_struct *work) else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); - if (hci_dev_do_close(hdev)) - return; + if (!hci_dev_do_close(hdev)) + hci_dev_do_open(hdev); - hci_dev_do_open(hdev); + hci_dev_put(hdev); } void hci_uuids_clear(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ef8c3bed7361..2a5f5a7d2412 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5329,9 +5329,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn || !hci_conn_ssp_enabled(conn)) + if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock; + /* Assume remote supports SSP since it has triggered this event */ + set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); + hci_conn_hold(conn); if (!hci_dev_test_flag(hdev, HCI_MGMT)) @@ -6794,6 +6797,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID); + if (max > hcon->le_conn_max_interval) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); @@ -7420,10 +7427,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, * keep track of the bdaddr of the connection event that woke us up. */ if (event == HCI_EV_CONN_REQUEST) { - bacpy(&hdev->wake_addr, &conn_complete->bdaddr); + bacpy(&hdev->wake_addr, &conn_request->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_CONN_COMPLETE) { - bacpy(&hdev->wake_addr, &conn_request->bdaddr); + bacpy(&hdev->wake_addr, &conn_complete->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_LE_META) { struct hci_ev_le_meta *le_ev = (void *)skb->data; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a6fc8a2a5c67..5716345a26df 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2206,8 +2206,11 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, /* During suspend, only wakeable devices can be in acceptlist */ if (hdev->suspended && - !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) { + hci_le_del_accept_list_sync(hdev, ¶ms->addr, + params->addr_type); return 0; + } /* Select filter policy to accept all advertising */ if (*num_entries >= hdev->le_accept_list_size) @@ -5559,7 +5562,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length) bt_dev_dbg(hdev, ""); - if (hci_dev_test_flag(hdev, HCI_INQUIRY)) + if (test_bit(HCI_INQUIRY, &hdev->flags)) return 0; hci_dev_lock(hdev); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 60298975d5c4..656f49b299d2 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5613,7 +5613,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - err = hci_check_conn_params(min, max, latency, to_multiplier); + if (max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index bb72ff6eb22f..ee3b4aad8bd8 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1045,6 +1045,8 @@ static void rpa_expired(struct work_struct *work) hci_cmd_sync_queue(hdev, rpa_expired_sync, NULL, NULL); } +static int set_discoverable_sync(struct hci_dev *hdev, void *data); + static void discov_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -1063,7 +1065,7 @@ static void discov_off(struct work_struct *work) hci_dev_clear_flag(hdev, HCI_DISCOVERABLE); hdev->discov_timeout = 0; - hci_update_discoverable(hdev); + hci_cmd_sync_queue(hdev, set_discoverable_sync, NULL, NULL); mgmt_new_settings(hdev); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 053ef8f25fae..1d34d8497033 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1941,7 +1941,7 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) { + if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) { s = rfcomm_recv_frame(s, skb); if (!s) break; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index ed1720890757..35e10c5a766d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -43,6 +43,10 @@ #include <linux/sysctl.h> #endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack_core.h> +#endif + static unsigned int brnf_net_id __read_mostly; struct brnf_net { @@ -553,6 +557,90 @@ static unsigned int br_nf_pre_routing(void *priv, return NF_STOLEN; } +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +/* conntracks' nf_confirm logic cannot handle cloned skbs referencing + * the same nf_conn entry, which will happen for multicast (broadcast) + * Frames on bridges. + * + * Example: + * macvlan0 + * br0 + * ethX ethY + * + * ethX (or Y) receives multicast or broadcast packet containing + * an IP packet, not yet in conntrack table. + * + * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting. + * -> skb->_nfct now references a unconfirmed entry + * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge + * interface. + * 3. skb gets passed up the stack. + * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb + * and schedules a work queue to send them out on the lower devices. + * + * The clone skb->_nfct is not a copy, it is the same entry as the + * original skb. The macvlan rx handler then returns RX_HANDLER_PASS. + * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb. + * + * The Macvlan broadcast worker and normal confirm path will race. + * + * This race will not happen if step 2 already confirmed a clone. In that + * case later steps perform skb_clone() with skb->_nfct already confirmed (in + * hash table). This works fine. + * + * But such confirmation won't happen when eb/ip/nftables rules dropped the + * packets before they reached the nf_confirm step in postrouting. + * + * Work around this problem by explicit confirmation of the entry at + * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed + * entry. + * + */ +static unsigned int br_nf_local_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conntrack *nfct = skb_nfct(skb); + const struct nf_ct_hook *ct_hook; + struct nf_conn *ct; + int ret; + + if (!nfct || skb->pkt_type == PACKET_HOST) + return NF_ACCEPT; + + ct = container_of(nfct, struct nf_conn, ct_general); + if (likely(nf_ct_is_confirmed(ct))) + return NF_ACCEPT; + + WARN_ON_ONCE(skb_shared(skb)); + WARN_ON_ONCE(refcount_read(&nfct->use) != 1); + + /* We can't call nf_confirm here, it would create a dependency + * on nf_conntrack module. + */ + ct_hook = rcu_dereference(nf_ct_hook); + if (!ct_hook) { + skb->_nfct = 0ul; + nf_conntrack_put(nfct); + return NF_ACCEPT; + } + + nf_bridge_pull_encap_header(skb); + ret = ct_hook->confirm(skb); + switch (ret & NF_VERDICT_MASK) { + case NF_STOLEN: + return NF_STOLEN; + default: + nf_bridge_push_encap_header(skb); + break; + } + + ct = container_of(nfct, struct nf_conn, ct_general); + WARN_ON_ONCE(!nf_ct_is_confirmed(ct)); + + return ret; +} +#endif /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -964,6 +1052,14 @@ static const struct nf_hook_ops br_nf_ops[] = { .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + { + .hook = br_nf_local_in, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_BR_PRI_LAST, + }, +#endif { .hook = br_nf_forward, .pf = NFPROTO_BRIDGE, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index ee84e783e1df..7b41ee8740cb 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -595,21 +595,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, } static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, + struct net_device *dev, + unsigned long action, enum switchdev_obj_id id, const struct net_bridge_mdb_entry *mp, struct net_device *orig_dev) { - struct switchdev_obj_port_mdb *mdb; + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = id, + .orig_dev = orig_dev, + }, + }; + struct switchdev_obj_port_mdb *pmdb; - mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); - if (!mdb) - return -ENOMEM; + br_switchdev_mdb_populate(&mdb, mp); + + if (action == SWITCHDEV_PORT_OBJ_ADD && + switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) { + /* This event is already in the deferred queue of + * events, so this replay must be elided, lest the + * driver receives duplicate events for it. This can + * only happen when replaying additions, since + * modifications are always immediately visible in + * br->mdb_list, whereas actual event delivery may be + * delayed. + */ + return 0; + } - mdb->obj.id = id; - mdb->obj.orig_dev = orig_dev; - br_switchdev_mdb_populate(mdb, mp); - list_add_tail(&mdb->obj.list, mdb_list); + pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC); + if (!pmdb) + return -ENOMEM; + list_add_tail(&pmdb->obj.list, mdb_list); return 0; } @@ -677,51 +696,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; - /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, - * because the write-side protection is br->multicast_lock. But we - * need to emulate the [ blocking ] calling context of a regular - * switchdev event, so since both br->multicast_lock and RCU read side - * critical sections are atomic, we have no choice but to pick the RCU - * read side lock, queue up all our events, leave the critical section - * and notify switchdev from blocking context. + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + /* br_switchdev_mdb_queue_one() will take care to not queue a + * replay of an event that is already pending in the switchdev + * deferred queue. In order to safely determine that, there + * must be no new deferred MDB notifications enqueued for the + * duration of the MDB scan. Therefore, grab the write-side + * lock to avoid racing with any concurrent IGMP/MLD snooping. */ - rcu_read_lock(); + spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group __rcu * const *pp; const struct net_bridge_port_group *p; if (mp->host_joined) { - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_HOST_MDB, mp, br_dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } - for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port->dev != dev) continue; - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_PORT_MDB, mp, dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } } - rcu_read_unlock(); - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; + spin_unlock_bh(&br->multicast_lock); list_for_each_entry(obj, &mdb_list, list) { err = br_switchdev_mdb_replay_one(nb, dev, @@ -786,6 +804,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); + + /* Make sure that the device leaving this bridge has seen all + * relevant events before it is disassociated. In the normal + * case, when the device is directly attached to the bridge, + * this is covered by del_nbp(). If the association was indirect + * however, e.g. via a team or bond, and the device is leaving + * that intermediate device, then the bridge port remains in + * place. + */ + switchdev_deferred_process(); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index abb090f94ed2..6f877e31709b 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -291,6 +291,30 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, return nf_conntrack_in(skb, &bridge_state); } +static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + if (skb->pkt_type == PACKET_HOST) + return NF_ACCEPT; + + /* nf_conntrack_confirm() cannot handle concurrent clones, + * this happens for broad/multicast frames with e.g. macvlan on top + * of the bridge device. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + return NF_ACCEPT; + + /* let inet prerouting call conntrack again */ + skb->_nfct = 0; + nf_ct_put(ct); + + return NF_ACCEPT; +} + static void nf_ct_bridge_frag_save(struct sk_buff *skb, struct nf_bridge_frag_data *data) { @@ -386,6 +410,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = { .priority = NF_IP_PRI_CONNTRACK, }, { + .hook = nf_ct_bridge_in, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, + { .hook = nf_ct_bridge_post, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 16af1a7f80f6..31a93cae5111 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -86,7 +86,7 @@ struct j1939_priv { unsigned int tp_max_packet_size; /* lock for j1939_socks list */ - spinlock_t j1939_socks_lock; + rwlock_t j1939_socks_lock; struct list_head j1939_socks; struct kref rx_kref; @@ -301,6 +301,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index ecff1c947d68..a6fb89fa6278 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); - spin_lock_init(&priv->j1939_socks_lock); + rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 14c431663233..305dd72c844c 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); } static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) { - spin_lock_bh(&priv->j1939_socks_lock); + write_lock_bh(&priv->j1939_socks_lock); list_del_init(&jsk->list); - spin_unlock_bh(&priv->j1939_socks_lock); + write_unlock_bh(&priv->j1939_socks_lock); j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -329,13 +340,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb) struct j1939_sock *jsk; bool match = false; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { match = j1939_sk_recv_match_one(jsk, skcb); if (match) break; } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); return match; } @@ -344,11 +355,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sock *jsk; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { j1939_sk_recv_one(jsk, skb); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static void j1939_sk_sock_destruct(struct sock *sk) @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; @@ -1080,12 +1094,12 @@ void j1939_sk_errqueue(struct j1939_session *session, } /* spread RX notifications to all sockets subscribed to this session */ - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { if (j1939_sk_recv_match_one(jsk, &session->skcb)) __j1939_sk_errqueue(session, &jsk->sk, type); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); }; void j1939_sk_send_loop_abort(struct sock *sk, int err) @@ -1273,7 +1287,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) struct j1939_sock *jsk; int error_code = ENETDOWN; - spin_lock_bh(&priv->j1939_socks_lock); + read_lock_bh(&priv->j1939_socks_lock); list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) @@ -1281,7 +1295,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) j1939_sk_queue_drop_all(priv, jsk, error_code); } - spin_unlock_bh(&priv->j1939_socks_lock); + read_unlock_bh(&priv->j1939_socks_lock); } static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index f9a50d7f0d20..0cb61c76b9b8 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con) static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { /* Initialize data cursor if it's not a sparse read */ - if (!msg->sparse_read) - ceph_msg_data_cursor_init(&msg->cursor, msg, data_len); + u64 len = msg->sparse_read_total ? : data_len; + + ceph_msg_data_cursor_init(&msg->cursor, msg, len); } /* @@ -991,7 +992,7 @@ static inline int read_partial_message_section(struct ceph_connection *con, return read_partial_message_chunk(con, section, sec_len, crc); } -static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc) +static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc) { struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE); @@ -1026,7 +1027,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc) return 1; } -static int read_sparse_msg_data(struct ceph_connection *con) +static int read_partial_sparse_msg_data(struct ceph_connection *con) { struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); @@ -1036,31 +1037,31 @@ static int read_sparse_msg_data(struct ceph_connection *con) if (do_datacrc) crc = con->in_data_crc; - do { + while (cursor->total_resid) { if (con->v1.in_sr_kvec.iov_base) ret = read_partial_message_chunk(con, &con->v1.in_sr_kvec, con->v1.in_sr_len, &crc); else if (cursor->sr_resid > 0) - ret = read_sparse_msg_extent(con, &crc); - - if (ret <= 0) { - if (do_datacrc) - con->in_data_crc = crc; - return ret; - } + ret = read_partial_sparse_msg_extent(con, &crc); + if (ret <= 0) + break; memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec)); ret = con->ops->sparse_read(con, cursor, (char **)&con->v1.in_sr_kvec.iov_base); + if (ret <= 0) { + ret = ret ? ret : 1; /* must return > 0 to indicate success */ + break; + } con->v1.in_sr_len = ret; - } while (ret > 0); + } if (do_datacrc) con->in_data_crc = crc; - return ret < 0 ? ret : 1; /* must return > 0 to indicate success */ + return ret; } static int read_partial_msg_data(struct ceph_connection *con) @@ -1253,8 +1254,8 @@ static int read_partial_message(struct ceph_connection *con) if (!m->num_data_items) return -EIO; - if (m->sparse_read) - ret = read_sparse_msg_data(con); + if (m->sparse_read_total) + ret = read_partial_sparse_msg_data(con); else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) ret = read_partial_msg_data_bounce(con); else diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index f8ec60e1aba3..bd608ffa0627 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con) struct sg_table enc_sgt = {}; struct sg_table sgt = {}; struct page **pages = NULL; - bool sparse = con->in_msg->sparse_read; + bool sparse = !!con->in_msg->sparse_read_total; int dpos = 0; int tail_len; int ret; @@ -2034,6 +2034,9 @@ static int prepare_sparse_read_data(struct ceph_connection *con) if (!con_secure(con)) con->in_data_crc = -1; + ceph_msg_data_cursor_init(&con->v2.in_cursor, msg, + msg->sparse_read_total); + reset_in_kvecs(con); con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT; con->v2.data_len_remain = data_len(msg); @@ -2060,7 +2063,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con) } if (data_len(msg)) { - if (msg->sparse_read) + if (msg->sparse_read_total) con->v2.in_state = IN_S_PREPARE_SPARSE_DATA; else con->v2.in_state = IN_S_PREPARE_READ_DATA; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 625622016f57..9d078b37fe0b 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, } m = ceph_msg_get(req->r_reply); - m->sparse_read = (bool)srlen; + m->sparse_read_total = srlen; dout("get_reply tid %lld %p\n", tid, m); @@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con, } if (o->o_sparse_op_idx < 0) { - u64 srlen = sparse_data_requested(req); - - dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n", - __func__, o->o_osd, srlen); - ceph_msg_data_cursor_init(cursor, con->in_msg, srlen); + dout("%s: [%d] starting new sparse read req\n", + __func__, o->o_osd); } else { u64 end; @@ -5857,8 +5854,8 @@ static int osd_sparse_read(struct ceph_connection *con, struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; u32 count = sr->sr_count; - u64 eoff, elen; - int ret; + u64 eoff, elen, len = 0; + int i, ret; switch (sr->sr_state) { case CEPH_SPARSE_READ_HDR: @@ -5903,8 +5900,20 @@ next_op: convert_extent_map(sr); ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; - sr->sr_state = CEPH_SPARSE_READ_DATA; + sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; break; + case CEPH_SPARSE_READ_DATA_PRE: + /* Convert sr_datalen to host-endian */ + sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen); + for (i = 0; i < count; i++) + len += sr->sr_extent[i].len; + if (sr->sr_datalen != len) { + pr_warn_ratelimited("data len %u != extent len %llu\n", + sr->sr_datalen, len); + return -EREMOTEIO; + } + sr->sr_state = CEPH_SPARSE_READ_DATA; + fallthrough; case CEPH_SPARSE_READ_DATA: if (sr->sr_index >= count) { sr->sr_state = CEPH_SPARSE_READ_HDR; diff --git a/net/core/datagram.c b/net/core/datagram.c index 103d46fa0eeb..a8b625abe242 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -751,7 +751,7 @@ size_t memcpy_to_iter_csum(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { __wsum *csum = priv2; - __wsum next = csum_partial_copy_nocheck(from, iter_to, len); + __wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len); *csum = csum_block_add(*csum, next, progress); return 0; diff --git a/net/core/dev.c b/net/core/dev.c index cb2dab0feee0..76e6438f4858 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -336,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ - list_add_tail(&name_node->list, &dev->name_node->list); + list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } @@ -9074,28 +9074,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) } EXPORT_SYMBOL(netdev_port_same_parent_id); -static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) -{ -#if IS_ENABLED(CONFIG_DPLL) - rtnl_lock(); - dev->dpll_pin = dpll_pin; - rtnl_unlock(); -#endif -} - -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) -{ - WARN_ON(!dpll_pin); - netdev_dpll_pin_assign(dev, dpll_pin); -} -EXPORT_SYMBOL(netdev_dpll_pin_set); - -void netdev_dpll_pin_clear(struct net_device *dev) -{ - netdev_dpll_pin_assign(dev, NULL); -} -EXPORT_SYMBOL(netdev_dpll_pin_clear); - /** * dev_change_proto_down - set carrier according to proto_down. * @@ -11652,11 +11630,12 @@ static void __init net_dev_struct_check(void) CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160); /* TXRX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); - CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index ffe5244e5597..278294aca66a 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -94,11 +94,12 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, state->pp_id = pool->user.id; err = fill(skb, pool, info); if (err) - break; + goto out; } state->pp_id = 0; } +out: mutex_unlock(&page_pools_lock); rtnl_unlock(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f6f29eb03ec2..bd50e9fe3234 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1020,14 +1020,17 @@ static size_t rtnl_xdp_size(void) static size_t rtnl_prop_list_size(const struct net_device *dev) { struct netdev_name_node *name_node; - size_t size; + unsigned int cnt = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(name_node, &dev->name_node->list, list) + cnt++; + rcu_read_unlock(); - if (list_empty(&dev->name_node->list)) + if (!cnt) return 0; - size = nla_total_size(0); - list_for_each_entry(name_node, &dev->name_node->list, list) - size += nla_total_size(ALTIFNAMSIZ); - return size; + + return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ); } static size_t rtnl_proto_down_size(const struct net_device *dev) @@ -1054,7 +1057,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) { size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */ - size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev)); + size += dpll_netdev_pin_handle_size(dev); return size; } @@ -1789,7 +1792,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb, if (!dpll_pin_nest) return -EMSGSIZE; - ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev)); + ret = dpll_netdev_add_pin_handle(skb, dev); if (ret < 0) goto nest_cancel; @@ -5166,10 +5169,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct net_device *dev; - struct nlattr *br_spec, *attr = NULL; + struct nlattr *br_spec, *attr, *br_flags_attr = NULL; int rem, err = -EOPNOTSUPP; u16 flags = 0; - bool have_flags = false; if (nlmsg_len(nlh) < sizeof(*ifm)) return -EINVAL; @@ -5187,11 +5189,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; - have_flags = true; + br_flags_attr = attr; flags = nla_get_u16(attr); } @@ -5235,8 +5237,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, } } - if (have_flags) - memcpy(nla_data(attr), &flags, sizeof(flags)); + if (br_flags_attr) + memcpy(nla_data(br_flags_attr), &flags, sizeof(flags)); out: return err; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93ecfceac1bc..4d75ef9d24bf 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,8 +1226,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) - psock->saved_data_ready(sk); + if (psock) { + read_lock_bh(&sk->sk_callback_lock); + sk_psock_data_ready(sk, psock); + read_unlock_bh(&sk->sk_callback_lock); + } rcu_read_unlock(); } } diff --git a/net/core/sock.c b/net/core/sock.c index 0a7f46c37f0c..5e78798456fd 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1188,6 +1188,17 @@ int sk_setsockopt(struct sock *sk, int level, int optname, */ WRITE_ONCE(sk->sk_txrehash, (u8)val); return 0; + case SO_PEEK_OFF: + { + int (*set_peek_off)(struct sock *sk, int val); + + set_peek_off = READ_ONCE(sock->ops)->set_peek_off; + if (set_peek_off) + ret = set_peek_off(sk, val); + else + ret = -EOPNOTSUPP; + return ret; + } } sockopt_lock_sock(sk); @@ -1430,18 +1441,6 @@ set_sndbuf: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; - case SO_PEEK_OFF: - { - int (*set_peek_off)(struct sock *sk, int val); - - set_peek_off = READ_ONCE(sock->ops)->set_peek_off; - if (set_peek_off) - ret = set_peek_off(sk, val); - else - ret = -EOPNOTSUPP; - break; - } - case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; diff --git a/net/devlink/core.c b/net/devlink/core.c index 4275a2bc6d8e..7f0b093208d7 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -46,7 +46,7 @@ struct devlink_rel { u32 obj_index; devlink_rel_notify_cb_t *notify_cb; devlink_rel_cleanup_cb_t *cleanup_cb; - struct work_struct notify_work; + struct delayed_work notify_work; } nested_in; }; @@ -70,7 +70,7 @@ static void __devlink_rel_put(struct devlink_rel *rel) static void devlink_rel_nested_in_notify_work(struct work_struct *work) { struct devlink_rel *rel = container_of(work, struct devlink_rel, - nested_in.notify_work); + nested_in.notify_work.work); struct devlink *devlink; devlink = devlinks_xa_get(rel->nested_in.devlink_index); @@ -96,13 +96,13 @@ rel_put: return; reschedule_work: - schedule_work(&rel->nested_in.notify_work); + schedule_delayed_work(&rel->nested_in.notify_work, 1); } static void devlink_rel_nested_in_notify_work_schedule(struct devlink_rel *rel) { __devlink_rel_get(rel); - schedule_work(&rel->nested_in.notify_work); + schedule_delayed_work(&rel->nested_in.notify_work, 0); } static struct devlink_rel *devlink_rel_alloc(void) @@ -123,8 +123,8 @@ static struct devlink_rel *devlink_rel_alloc(void) } refcount_set(&rel->refcount, 1); - INIT_WORK(&rel->nested_in.notify_work, - &devlink_rel_nested_in_notify_work); + INIT_DELAYED_WORK(&rel->nested_in.notify_work, + &devlink_rel_nested_in_notify_work); return rel; } @@ -529,14 +529,20 @@ static int __init devlink_init(void) { int err; - err = genl_register_family(&devlink_nl_family); - if (err) - goto out; err = register_pernet_subsys(&devlink_pernet_ops); if (err) goto out; + err = genl_register_family(&devlink_nl_family); + if (err) + goto out_unreg_pernet_subsys; err = register_netdevice_notifier(&devlink_port_netdevice_nb); + if (!err) + return 0; + + genl_unregister_family(&devlink_nl_family); +out_unreg_pernet_subsys: + unregister_pernet_subsys(&devlink_pernet_ops); out: WARN_ON(err); return err; diff --git a/net/devlink/port.c b/net/devlink/port.c index 78592912f657..4b2d46ccfe48 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -583,7 +583,7 @@ devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) { err = devlink_nl_port_fill(msg, devlink_port, - DEVLINK_CMD_NEW, + DEVLINK_CMD_PORT_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index 16ed7bfd29e4..34fd1d9b2db8 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test) handshake_req_cancel(sock->sk); /* Act */ - fput(filp); + /* Ensure the close/release/put process has run to + * completion before checking the result. + */ + __fput_sync(filp); /* Assert */ KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 80cdc6f6b34c..5d68cb181695 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -83,7 +83,7 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) return false; /* Get next tlv */ - total_length += sizeof(struct hsr_sup_tlv) + hsr_sup_tag->tlv.HSR_TLV_length; + total_length += hsr_sup_tag->tlv.HSR_TLV_length; if (!pskb_may_pull(skb, total_length)) return false; skb_pull(skb, total_length); @@ -435,7 +435,7 @@ static void hsr_forward_do(struct hsr_frame_info *frame) continue; /* Don't send frame over port where it has been sent before. - * Also fro SAN, this shouldn't be done. + * Also for SAN, this shouldn't be done. */ if (!frame->is_from_san && hsr_register_frame_out(port, frame->node_src, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4e635dd3d3c8..a5a820ee2026 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1628,10 +1628,12 @@ EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { - if (sk->sk_family == AF_INET) + unsigned int family = READ_ONCE(sk->sk_family); + + if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) + if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a2e6e1fdf82b..64aec3dff8ec 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -597,5 +597,6 @@ static void __exit ah4_fini(void) module_init(ah4_init); module_exit(ah4_fini); +MODULE_DESCRIPTION("IPv4 AH transformation library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9456f5bb35e5..0d0d725b46ad 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ca0ff15dc8fa..bc74f131fe4d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1825,6 +1825,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1876,8 +1891,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2278,8 +2292,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4ccfc104f13a..4dd9e5040672 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void) module_init(esp4_init); module_exit(esp4_fini); +MODULE_DESCRIPTION("IPv4 ESP transformation library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 93e9193df544..308ff34002ea 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1130,10 +1130,33 @@ ok: return 0; error: + if (sk_hashed(sk)) { + spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash); + + sock_prot_inuse_add(net, sk->sk_prot, -1); + + spin_lock(lock); + sk_nulls_del_node_init_rcu(sk); + spin_unlock(lock); + + sk->sk_hash = 0; + inet_sk(sk)->inet_sport = 0; + inet_sk(sk)->inet_num = 0; + + if (tw) + inet_twsk_bind_unhash(tw, hinfo); + } + spin_unlock(&head2->lock); if (tb_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); + spin_unlock(&head->lock); + + if (tw) + inet_twsk_deschedule_put(tw); + + local_bh_enable(); + return -ENOMEM; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5169c3c72cff..6b9cf5a24c19 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1793,6 +1793,7 @@ static void __exit ipgre_fini(void) module_init(ipgre_init); module_exit(ipgre_fini); +MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 41537d18eecf..67d846622365 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); @@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); @@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk, cork->length += length; + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, @@ -1274,6 +1275,8 @@ error: cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index beeae624c412..1b6981de3f29 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -554,6 +554,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) +{ + /* we must cap headroom to some upperlimit, else pskb_expand_head + * will overflow header offsets in skb_headers_offset_update(). + */ + static const unsigned int max_allowed = 512; + + if (headroom > max_allowed) + headroom = max_allowed; + + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); +} + void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { @@ -632,13 +646,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, headroom); - - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } + + ip_tunnel_adj_headroom(dev, headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; @@ -818,16 +832,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return; } + ip_tunnel_adj_headroom(dev, max_headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; @@ -1298,4 +1312,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id) } EXPORT_SYMBOL_GPL(ip_tunnel_setup); +MODULE_DESCRIPTION("IPv4 tunnel implementation library"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 586b1b3e35b8..80ccd6661aa3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) }; skb_reset_network_header(skb); - csum = csum_partial(icmp6h, len, 0); + csum = skb_checksum(skb, skb_transport_offset(skb), len, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len, IPPROTO_ICMPV6, csum); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 9ab9b3ebe0cd..d1d6bb28ed6e 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -721,6 +721,7 @@ static void __exit vti_fini(void) module_init(vti_init); module_exit(vti_fini); +MODULE_DESCRIPTION("Virtual (secure) IP tunneling library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti"); MODULE_ALIAS_NETDEV("ip_vti0"); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 27b8f83c6ea2..03afa3871efc 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -658,6 +658,7 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); +MODULE_DESCRIPTION("IP/IP protocol decoder library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7e2481b9eae1..c82dc42f57c6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4615,7 +4615,8 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 5048c47c79b2..4c1f836aae38 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void) module_init(tunnel4_init); module_exit(tunnel4_fini); +MODULE_DESCRIPTION("IPv4 XFRM tunnel library"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f631b0a21af4..e474b201900f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1589,12 +1589,7 @@ int udp_init_sock(struct sock *sk) void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { - if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) { - bool slow = lock_sock_fast(sk); - - sk_peek_offset_bwd(sk, len); - unlock_sock_fast(sk, slow); - } + sk_peek_offset_bwd(sk, len); if (!skb_unref(skb)) return; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index a87defb2b167..860aff5f8599 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup); +MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 8489fa106583..8cb266af1393 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -114,5 +114,6 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); +MODULE_DESCRIPTION("IPv4 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 733ace18806c..055230b669cf 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -708,6 +708,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -741,8 +757,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5362,7 +5377,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; @@ -5494,9 +5509,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) - return -EINVAL; - + if (!addr) { + err = -EINVAL; + goto errout; + } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2016e90e6e1d..eb474f0987ae 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -800,5 +800,6 @@ static void __exit ah6_fini(void) module_init(ah6_init); module_exit(ah6_fini); +MODULE_DESCRIPTION("IPv6 AH transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 2cc1a45742d8..6e6efe026cdc 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void) module_init(esp6_init); module_exit(esp6_fini); +MODULE_DESCRIPTION("IPv6 ESP transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 4952ae792450..02e9ffb63af1 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -177,6 +177,8 @@ static bool ip6_parse_tlv(bool hopbyhop, case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; + + nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) @@ -943,6 +945,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (!skb_valid_dst(skb)) ip6_route_input(skb); + /* About to mangle packet header */ + if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) + goto drop; + + /* Trace pointer may have changed */ + trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + + optoff + sizeof(*hdr)); + ioam6_fill_trace_data(skb, ns, trace, true); break; default: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a722a43dd668..31b86fe661aa 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk, bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; + bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref = false; skb = skb_peek_tail(queue); if (!skb) { @@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; - if (cork->tx_flags & SKBTX_ANY_TSTAMP && - READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) - tskey = atomic_inc_return(&sk->sk_tskey) - 1; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + @@ -1538,6 +1534,11 @@ emsgsize: flags &= ~MSG_SPLICE_PAGES; } + hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; + if (hold_tskey) + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. @@ -1794,6 +1795,8 @@ error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index a7bf0327b380..c99053189ea8 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); +MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 83d2a8be263f..6a16a5bd0d91 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -405,6 +405,7 @@ static void __exit mip6_fini(void) module_init(mip6_init); module_exit(mip6_fini); +MODULE_DESCRIPTION("IPv6 Mobility driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ea1dec8448fc..ef815ba583a8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5332,19 +5332,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); - fib6_info_release(nh->fib6_info); - - if (!err) { - /* save reference to last route successfully inserted */ - rt_last = nh->fib6_info; - - /* save reference to first route for notification */ - if (!rt_notif) - rt_notif = nh->fib6_info; - } - /* nh->fib6_info is used or freed at this point, reset to NULL*/ - nh->fib6_info = NULL; if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, @@ -5352,6 +5340,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = nh; goto add_errout; } + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, @@ -5412,8 +5406,7 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->fib6_info) - fib6_info_release(nh->fib6_info); + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 29346a6eec9f..35508abd76f4 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -512,22 +512,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -548,11 +550,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index cc24cefdb85c..5e9f625b76e3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1956,6 +1956,7 @@ xfrm_tunnel_failed: module_init(sit_init); module_exit(sit_cleanup); +MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 00e8d8b1c9a7..dc4ea9b11794 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void) module_init(tunnel6_init); module_exit(tunnel6_fini); +MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 1323f2f6928e..f6cb94f82cc3 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void) module_init(xfrm6_tunnel_init); module_exit(xfrm6_tunnel_fini); +MODULE_DESCRIPTION("IPv6 XFRM tunnel driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 6334f64f04d5..b0b3e9c5af44 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID"; static LIST_HEAD(iucv_handler_list); /* - * iucv_path_table: an array of iucv_path structures. + * iucv_path_table: array of pointers to iucv_path structures. */ static struct iucv_path **iucv_path_table; static unsigned long iucv_max_pathid; @@ -544,7 +544,7 @@ static int iucv_enable(void) cpus_read_lock(); rc = -ENOMEM; - alloc_size = iucv_max_pathid * sizeof(struct iucv_path); + alloc_size = iucv_max_pathid * sizeof(*iucv_path_table); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); if (!iucv_path_table) goto out; diff --git a/net/key/af_key.c b/net/key/af_key.c index d68d01804dc7..f79fb99271ed 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3924,5 +3924,6 @@ out_unregister_key_proto: module_init(ipsec_pfkey_init); module_exit(ipsec_pfkey_exit); +MODULE_DESCRIPTION("PF_KEY socket helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_KEY); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index dd3153966173..7bf14cf9ffaa 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -627,7 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 489dd97f5172..327682995c92 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/ieee80211.h> @@ -987,7 +987,8 @@ static int ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, struct cfg80211_unsol_bcast_probe_resp *params, struct ieee80211_link_data *link, - struct ieee80211_bss_conf *link_conf) + struct ieee80211_bss_conf *link_conf, + u64 *changed) { struct unsol_bcast_probe_resp_data *new, *old = NULL; @@ -1011,7 +1012,8 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); } - return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; + *changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; + return 0; } static int ieee80211_set_ftm_responder_params( @@ -1450,10 +1452,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, - link, link_conf); + link, link_conf, &changed); if (err < 0) goto error; - changed |= err; err = drv_start_ap(sdata->local, sdata, link_conf); if (err) { @@ -1525,10 +1526,9 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, - link, link_conf); + link, link_conf, &changed); if (err < 0) return err; - changed |= err; if (beacon->he_bss_color_valid && beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) { @@ -1869,6 +1869,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } + ieee80211_sta_set_rx_nss(link_sta); + return ret; } diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index dce5606ed66d..68596ef78b15 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -997,8 +997,8 @@ static void add_link_files(struct ieee80211_link_data *link, } } -void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata, - bool mld_vif) +static void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata, + bool mld_vif) { char buf[10+IFNAMSIZ]; diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h index b226b1aae88a..a02ec0a413f6 100644 --- a/net/mac80211/debugfs_netdev.h +++ b/net/mac80211/debugfs_netdev.h @@ -11,8 +11,6 @@ #include "ieee80211_i.h" #ifdef CONFIG_MAC80211_DEBUGFS -void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata, - bool mld_vif); void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata, @@ -24,9 +22,6 @@ void ieee80211_link_debugfs_remove(struct ieee80211_link_data *link); void ieee80211_link_debugfs_drv_add(struct ieee80211_link_data *link); void ieee80211_link_debugfs_drv_remove(struct ieee80211_link_data *link); #else -static inline void ieee80211_debugfs_add_netdev( - struct ieee80211_sub_if_data *sdata, bool mld_vif) -{} static inline void ieee80211_debugfs_remove_netdev( struct ieee80211_sub_if_data *sdata) {} diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index e4e7c0b38cb6..11c4caa4748e 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1783,7 +1783,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, /* need to do this after the switch so vif.type is correct */ ieee80211_link_setup(&sdata->deflink); - ieee80211_debugfs_add_netdev(sdata, false); + ieee80211_debugfs_recreate_netdev(sdata, false); } static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 073105deb424..2022a26eb881 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation */ #include <linux/delay.h> @@ -2918,6 +2918,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, /* other links will be destroyed */ sdata->deflink.u.mgd.bss = NULL; + sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; netif_carrier_off(sdata->dev); @@ -5045,9 +5046,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, if (!link) return 0; - /* will change later if needed */ - link->smps_mode = IEEE80211_SMPS_OFF; - /* * If this fails (possibly due to channel context sharing * on incompatible channels, e.g. 80+80 and 160 sharing the @@ -7096,6 +7094,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link) link->u.mgd.p2p_noa_index = -1; link->u.mgd.conn_flags = 0; link->conf->bssid = link->u.mgd.bssid; + link->smps_mode = IEEE80211_SMPS_OFF; wiphy_work_init(&link->u.mgd.request_smps_work, ieee80211_request_smps_mgd_work); @@ -7309,6 +7308,75 @@ out_err: return err; } +static bool ieee80211_mgd_csa_present(struct ieee80211_sub_if_data *sdata, + const struct cfg80211_bss_ies *ies, + u8 cur_channel, bool ignore_ecsa) +{ + const struct element *csa_elem, *ecsa_elem; + struct ieee80211_channel_sw_ie *csa = NULL; + struct ieee80211_ext_chansw_ie *ecsa = NULL; + + if (!ies) + return false; + + csa_elem = cfg80211_find_elem(WLAN_EID_CHANNEL_SWITCH, + ies->data, ies->len); + if (csa_elem && csa_elem->datalen == sizeof(*csa)) + csa = (void *)csa_elem->data; + + ecsa_elem = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN, + ies->data, ies->len); + if (ecsa_elem && ecsa_elem->datalen == sizeof(*ecsa)) + ecsa = (void *)ecsa_elem->data; + + if (csa && csa->count == 0) + csa = NULL; + if (csa && !csa->mode && csa->new_ch_num == cur_channel) + csa = NULL; + + if (ecsa && ecsa->count == 0) + ecsa = NULL; + if (ecsa && !ecsa->mode && ecsa->new_ch_num == cur_channel) + ecsa = NULL; + + if (ignore_ecsa && ecsa) { + sdata_info(sdata, + "Ignoring ECSA in probe response - was considered stuck!\n"); + return csa; + } + + return csa || ecsa; +} + +static bool ieee80211_mgd_csa_in_process(struct ieee80211_sub_if_data *sdata, + struct cfg80211_bss *bss) +{ + u8 cur_channel; + bool ret; + + cur_channel = ieee80211_frequency_to_channel(bss->channel->center_freq); + + rcu_read_lock(); + if (ieee80211_mgd_csa_present(sdata, + rcu_dereference(bss->beacon_ies), + cur_channel, false)) { + ret = true; + goto out; + } + + if (ieee80211_mgd_csa_present(sdata, + rcu_dereference(bss->proberesp_ies), + cur_channel, bss->proberesp_ecsa_stuck)) { + ret = true; + goto out; + } + + ret = false; +out: + rcu_read_unlock(); + return ret; +} + /* config hooks */ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, struct cfg80211_auth_request *req) @@ -7317,7 +7385,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_mgd_auth_data *auth_data; struct ieee80211_link_data *link; - const struct element *csa_elem, *ecsa_elem; u16 auth_alg; int err; bool cont_auth; @@ -7360,21 +7427,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, if (ifmgd->assoc_data) return -EBUSY; - rcu_read_lock(); - csa_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_CHANNEL_SWITCH); - ecsa_elem = ieee80211_bss_get_elem(req->bss, - WLAN_EID_EXT_CHANSWITCH_ANN); - if ((csa_elem && - csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) && - ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) || - (ecsa_elem && - ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) && - ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) { - rcu_read_unlock(); + if (ieee80211_mgd_csa_in_process(sdata, req->bss)) { sdata_info(sdata, "AP is in CSA process, reject auth\n"); return -EINVAL; } - rcu_read_unlock(); auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len + req->ie_len, GFP_KERNEL); @@ -7684,7 +7740,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_mgd_assoc_data *assoc_data; - const struct element *ssid_elem, *csa_elem, *ecsa_elem; + const struct element *ssid_elem; struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg; ieee80211_conn_flags_t conn_flags = 0; struct ieee80211_link_data *link; @@ -7707,23 +7763,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, cbss = req->link_id < 0 ? req->bss : req->links[req->link_id].bss; - rcu_read_lock(); - ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID); - if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) { - rcu_read_unlock(); + if (ieee80211_mgd_csa_in_process(sdata, cbss)) { + sdata_info(sdata, "AP is in CSA process, reject assoc\n"); kfree(assoc_data); return -EINVAL; } - csa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_CHANNEL_SWITCH); - ecsa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_EXT_CHANSWITCH_ANN); - if ((csa_elem && - csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) && - ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) || - (ecsa_elem && - ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) && - ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) { - sdata_info(sdata, "AP is in CSA process, reject assoc\n"); + rcu_read_lock(); + ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID); + if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) { rcu_read_unlock(); kfree(assoc_data); return -EINVAL; @@ -7998,8 +8046,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); beacon_ies = rcu_dereference(req->bss->beacon_ies); - - if (beacon_ies) { + if (!beacon_ies) { /* * Wait up to one beacon interval ... * should this be more if we miss one? @@ -8080,6 +8127,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index d5ea5f5bcf3a..9d33fd2377c8 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -119,7 +119,8 @@ void rate_control_rate_update(struct ieee80211_local *local, rcu_read_unlock(); } - drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); + if (sta->uploaded) + drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); } int ieee80211_rate_control_register(const struct rate_control_ops *ops) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 645355e5f1bc..f9d5842601fa 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/if_arp.h> @@ -237,14 +237,18 @@ ieee80211_bss_info_update(struct ieee80211_local *local, } static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel *channel, u32 scan_flags, const u8 *da) { if (!sdata) return false; - /* accept broadcast for OCE */ - if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP && - is_broadcast_ether_addr(da)) + + /* accept broadcast on 6 GHz and for OCE */ + if (is_broadcast_ether_addr(da) && + (channel->band == NL80211_BAND_6GHZ || + scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP)) return true; + if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) return true; return ether_addr_equal(da, sdata->vif.addr); @@ -293,6 +297,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); } + channel = ieee80211_get_channel_khz(local->hw.wiphy, + ieee80211_rx_status_to_khz(rx_status)); + + if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) + return; + if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; @@ -310,19 +320,15 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) /* ignore ProbeResp to foreign address or non-bcast (OCE) * unless scanning with randomised address */ - if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags, + if (!ieee80211_scan_accept_presp(sdata1, channel, + scan_req_flags, mgmt->da) && - !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags, + !ieee80211_scan_accept_presp(sdata2, channel, + sched_scan_req_flags, mgmt->da)) return; } - channel = ieee80211_get_channel_khz(local->hw.wiphy, - ieee80211_rx_status_to_khz(rx_status)); - - if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) - return; - bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, channel); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 68a48abc7287..6fbb15b65902 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * Transmit and frame generation functions. */ @@ -3100,10 +3100,11 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) /* DA SA BSSID */ build.da_offs = offsetof(struct ieee80211_hdr, addr1); build.sa_offs = offsetof(struct ieee80211_hdr, addr2); + rcu_read_lock(); link = rcu_dereference(sdata->link[tdls_link_id]); - if (WARN_ON_ONCE(!link)) - break; - memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN); + if (!WARN_ON_ONCE(!link)) + memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN); + rcu_read_unlock(); build.hdr_len = 24; break; } @@ -3926,6 +3927,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3970,7 +3972,7 @@ begin: } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (tx.sta && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c index a05c5b971789..3a8612309137 100644 --- a/net/mac80211/wbrf.c +++ b/net/mac80211/wbrf.c @@ -23,8 +23,6 @@ void ieee80211_check_wbrf_support(struct ieee80211_local *local) return; local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev); - dev_dbg(dev, "WBRF is %s supported\n", - local->wbrf_supported ? "" : "not"); } static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end) diff --git a/net/mctp/route.c b/net/mctp/route.c index 7a47a58aa54b..ceee44ea09d9 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, spin_unlock_irqrestore(&mns->keys_lock, flags); if (!tagbits) { - kfree(key); + mctp_key_unref(key); return ERR_PTR(-EBUSY); } @@ -888,7 +888,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex); if (!dev) { rcu_read_unlock(); - return rc; + goto out_free; } rt->dev = __mctp_dev_get(dev); rcu_read_unlock(); @@ -903,7 +903,8 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rt->mtu = 0; } else { - return -EINVAL; + rc = -EINVAL; + goto out_free; } spin_lock_irqsave(&rt->dev->addrs_lock, flags); @@ -966,12 +967,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rc = mctp_do_fragment_route(rt, skb, mtu, tag); } + /* route output functions consume the skb, even on error */ + skb = NULL; + out_release: if (!ext_rt) mctp_route_release(rt); mctp_dev_put(tmp_rt.dev); +out_free: + kfree_skb(skb); return rc; } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a536586742f2..7017dd60659d 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,22 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; + if (inet_sk_state_load(sk) == TCP_LISTEN) + return 0; + start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -63,17 +68,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 74698582a285..ad28da655f8b 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_data_unlock(sk); } -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb; - mptcp_data_lock(sk); skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); @@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_ } pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); - mptcp_data_unlock(sk); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index d2527d189a79..63fc0758c22d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ - subflow->fully_established = 1; - WRITE_ONCE(msk->fully_established, true); - goto check_notify; + goto set_fully_established; } /* If the first established packet does not contain MP_CAPABLE + data @@ -983,10 +981,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (mp_opt->deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); -set_fully_established: 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); + +set_fully_established: + mptcp_data_lock((struct sock *)msk); + __mptcp_subflow_fully_established(msk, subflow, mp_opt); + mptcp_data_unlock((struct sock *)msk); check_notify: /* if the subflow is not already linked into the conn_list, we can't diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 287a60381eae..58d17d9604e7 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, - const struct mptcp_addr_info *addr) -{ - int i; - - for (i = 0; i < nr; i++) { - if (addrs[i].id == addr->id) - return true; - } - - return false; -} - /* Fill all the remote addresses into the array addrs[], * and return the array size. */ @@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, msk->pm.subflows++; addrs[i++] = remote; } else { + DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + + /* Forbid creation of new subflows matching existing + * ones, possibly already created by incoming ADD_ADDR + */ + bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->local_id) == local->id) + __set_bit(subflow->remote_id, unavail_id); + mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); - addrs[i].id = subflow->remote_id; + addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; + if (test_bit(addrs[i].id, unavail_id)) + continue; + if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) continue; - if (!lookup_address_in_vec(addrs, i, &addrs[i]) && - msk->pm.subflows < subflows_max) { + if (msk->pm.subflows < subflows_max) { + /* forbid creating multiple address towards + * this id + */ + __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } @@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow); - if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) + if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) continue; pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, - msk->mpc_endpoint_id); + i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); @@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -960,7 +964,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1092,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1285,6 +1289,18 @@ next: return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_address_nl_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; @@ -1326,7 +1342,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; @@ -1980,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL; - if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index efecbe3cf415..bc97cc30f013 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_pm_addr_entry *match = NULL; @@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); - if (addr_match && entry->addr.id == 0) + if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); if (addr_match && id_match) { @@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } *e = *entry; - if (!e->addr.id) + if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 1); @@ -130,10 +131,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { - struct mptcp_pm_addr_entry new_entry; + struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry; __be16 msk_sport = ((struct inet_sock *) inet_sk((struct sock *)msk))->inet_sport; + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&e->addr, skc, false)) { + entry = e; + break; + } + } + spin_unlock_bh(&msk->pm.lock); + if (entry) + return entry->addr.id; + memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry)); new_entry.addr = *skc; new_entry.addr.id = 0; @@ -142,7 +154,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, if (new_entry.addr.port == msk_sport) new_entry.addr.port = 0; - return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); + return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) @@ -187,7 +199,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val); + err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto announce_err; @@ -222,7 +234,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->local_id == 0) { + if (READ_ONCE(subflow->local_id) == 0) { has_id_0 = true; break; } @@ -367,7 +379,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) } local.addr = addr_l; - err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; @@ -483,6 +495,16 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info goto destroy_err; } +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { + ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6); + addr_l.family = AF_INET6; + } + if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) { + ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6); + addr_r.family = AF_INET6; + } +#endif if (addr_l.family != addr_r.family) { GENL_SET_ERR_MSG(info, "address families do not match"); err = -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 028e8b473626..7833a49f6214 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -85,7 +85,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); @@ -1260,6 +1260,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, mpext = mptcp_get_ext(skb); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; + tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } @@ -1505,8 +1506,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, @@ -1960,6 +1964,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (copied <= 0) return; + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -3142,7 +3149,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3158,6 +3164,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; + msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3171,8 +3178,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } + +static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) +{ + const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + struct ipv6_pinfo *newnp; + + newnp = inet6_sk(newsk); + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + if (!opt) + net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); + } + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); +} #endif +static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) +{ + struct ip_options_rcu *inet_opt, *newopt = NULL; + const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *newinet; + + newinet = inet_sk(newsk); + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + inet_opt->opt.optlen, GFP_ATOMIC); + if (newopt) + memcpy(newopt, inet_opt, sizeof(*inet_opt) + + inet_opt->opt.optlen); + else + net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newinet->inet_opt, newopt); + rcu_read_unlock(); +} + struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, @@ -3180,6 +3229,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) @@ -3192,6 +3242,13 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_init_sock(nsk); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (nsk->sk_family == AF_INET6) + mptcp_copy_ip6_options(nsk, sk); + else +#endif + mptcp_copy_ip_options(nsk, sk); + msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; @@ -3203,7 +3260,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; msk->snd_una = msk->write_seq; - msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; + msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; mptcp_init_sched(msk, mptcp_sk(sk)->sched); @@ -3220,7 +3277,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); - list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + subflow = mptcp_subflow_ctx(ssk); + list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly @@ -3235,6 +3293,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); + + if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) + __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3245,6 +3306,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); + msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; @@ -3255,8 +3317,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) @@ -3330,8 +3390,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { - unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) @@ -3347,7 +3406,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); @@ -3475,13 +3533,8 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->write_seq, subflow->idsn + 1); - WRITE_ONCE(msk->snd_nxt, msk->write_seq); - WRITE_ONCE(msk->snd_una, msk->write_seq); mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3517f2d24a22..07f6242afc1a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -286,7 +286,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; @@ -305,7 +304,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -491,10 +491,9 @@ struct mptcp_subflow_context { remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 9; + __unused : 10; bool data_avail; bool scheduled; u32 remote_nonce; @@ -505,7 +504,7 @@ struct mptcp_subflow_context { u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */ u64 iasn; /* initial ack sequence number, MPC subflows only */ }; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -556,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); } static inline u64 @@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net); unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); void mptcp_check_and_set_pending(struct sock *sk); void __mptcp_push_pending(struct sock *sk, unsigned int flags); @@ -789,6 +790,16 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } +static inline void mptcp_write_space(struct sock *sk) +{ + if (sk_stream_is_writeable(sk)) { + /* pairs with memory barrier in mptcp_poll */ + smp_mb(); + if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags)) + sk_stream_write_space(sk); + } +} + static inline void __mptcp_sync_sndbuf(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -807,6 +818,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk) /* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */ WRITE_ONCE(sk->sk_sndbuf, new_sndbuf); + mptcp_write_space(sk); } /* The called held both the msk socket and the subflow socket locks, @@ -837,16 +849,6 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) local_bh_enable(); } -static inline void mptcp_write_space(struct sock *sk) -{ - if (sk_stream_is_writeable(sk)) { - /* pairs with memory barrier in mptcp_poll */ - smp_mb(); - if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags)) - sk_stream_write_space(sk); - } -} - void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags); #define MPTCP_TOKEN_MAX_RETRIES 4 @@ -952,8 +954,8 @@ void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); @@ -1021,6 +1023,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, @@ -1128,7 +1139,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) && + return (1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) && is_active_ssk(subflow) && !subflow->conn_finished; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 0dcb721c89d1..71ba86246ff8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,29 +421,26 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_sync_state(struct sock *sk, int state) { + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk = msk->first; + + subflow = mptcp_subflow_ctx(ssk); + __mptcp_propagate_sndbuf(sk, ssk); + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, ssk); - __mptcp_propagate_sndbuf(sk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { + /* subflow->idsn is always available is TCP_SYN_SENT state, + * even for the FASTOPEN scenarios + */ + WRITE_ONCE(msk->write_seq, subflow->idsn + 1); + WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_set_state(sk, state); sk->sk_state_change(sk); } } -static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) { - __mptcp_sync_state(sk, ssk->sk_state); - } else { - msk->pending_state = ssk->sk_state; - __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); - } - mptcp_data_unlock(sk); -} - static void subflow_set_remote_key(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) @@ -465,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk, atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); } +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_data_lock(sk); + if (mp_opt) { + /* Options are available only in the non fallback cases + * avoid updating rx path fields otherwise + */ + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); + subflow_set_remote_key(msk, subflow, mp_opt); + } + + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state = ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -499,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (mp_opt.deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; - subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -514,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - subflow->remote_id = mp_opt.join_id; + WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -545,8 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(msk, sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } return; @@ -557,8 +577,8 @@ do_reset: static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) @@ -567,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; - if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -731,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) kfree_rcu(ctx, rcu); } -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); if (subflow->is_mptfo) - mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); + __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -834,7 +853,6 @@ create_child: * mpc option */ if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { - mptcp_subflow_fully_established(ctx, &mp_opt); mptcp_pm_fully_established(owner, child); ctx->pm_notified = 1; } @@ -1549,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->remote_id = remote_id; + WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); subflow->subflow_id = msk->subflow_id++; @@ -1713,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx); ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1); return ctx; } @@ -1744,10 +1763,9 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); - mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } /* as recvmsg() does not acquire the subflow socket for ssk selection @@ -1949,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; - new_ctx->remote_id = subflow_req->remote_id; + WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bcaad9c009fe..3184cc6be4c9 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1154,6 +1154,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, return ret; cleanup: + set->variant->cancel_gc(set); set->variant->destroy(set); put_out: module_put(set->type->me); @@ -2378,6 +2379,7 @@ ip_set_net_exit(struct net *net) set = ip_set(inst, i); if (set) { ip_set(inst, i) = NULL; + set->variant->cancel_gc(set); ip_set_destroy_set(set); } } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 1136510521a8..cf3ce72c3de6 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -432,7 +432,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference(hbucket(t, i)); + n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -452,7 +452,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2e5f3864d353..5b876fa7f9af 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2756,6 +2756,7 @@ static const struct nf_ct_hook nf_conntrack_hook = { .get_tuple_skb = nf_conntrack_get_tuple_skb, .attach = nf_conntrack_attach, .set_closing = nf_conntrack_set_closing, + .confirm = __nf_conntrack_confirm, }; void nf_conntrack_init_end(void) diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index e697a824b001..540d97715bd2 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Get fields bitmap */ if (nf_h323_error_boundary(bs, 0, f->sz)) return H323_ERROR_BOUND; + if (f->sz > 32) + return H323_ERROR_RANGE; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, bmp2_len = get_bits(bs, 7) + 1; if (nf_h323_error_boundary(bs, 0, bmp2_len)) return H323_ERROR_BOUND; + if (bmp2_len > 32) + return H323_ERROR_RANGE; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 0c22a02c2035..3b846cbdc050 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -876,6 +876,7 @@ struct ctnetlink_filter_u32 { struct ctnetlink_filter { u8 family; + bool zone_filter; u_int32_t orig_flags; u_int32_t reply_flags; @@ -992,9 +993,12 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) if (err) goto err_filter; - err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); - if (err < 0) - goto err_filter; + if (cda[CTA_ZONE]) { + err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); + if (err < 0) + goto err_filter; + filter->zone_filter = true; + } if (!cda[CTA_FILTER]) return filter; @@ -1148,7 +1152,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; - if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID && + if (filter->zone_filter && !nf_ct_zone_equal_any(ct, &filter->zone)) goto ignore_entry; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 920a5a29ae1d..a0571339239c 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) return 0; } +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { @@ -122,6 +132,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: @@ -146,7 +157,7 @@ static void nft_flow_dst_release(struct flow_offload *flow, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) + struct nf_flow_route *route) { flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index c3d7ecbc777c..016c816d91cb 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -551,8 +551,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, find_free_id: if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) off = (ntohs(*keyptr) - ntohs(range->base_proto.all)); - else + else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) || + maniptype != NF_NAT_MANIP_DST) off = get_random_u16(); + else + off = 0; attempts = range_size; if (attempts > NF_NAT_MAX_ATTEMPTS) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fc016befb46f..1683dc196b59 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -684,15 +684,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; } -static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, - struct nft_flowtable *flowtable) +static struct nft_trans * +nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, + struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); @@ -701,22 +702,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); - return 0; + return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { - int err; + struct nft_trans *trans; - err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); - if (err < 0) - return err; + trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); + if (IS_ERR(trans)) + return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); - return err; + return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) @@ -1251,6 +1252,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2080,7 +2082,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, struct nft_hook *hook; int err; - hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); + hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; @@ -2503,19 +2505,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); - err = nf_tables_register_hook(net, table, chain); - if (err < 0) - goto err_destroy_chain; - if (!nft_use_inc(&table->use)) { err = -EMFILE; - goto err_use; + goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - goto err_unregister_hook; + goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; @@ -2523,17 +2521,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); - if (err < 0) { - nft_trans_destroy(trans); - goto err_unregister_hook; - } + if (err < 0) + goto err_chain_add; + + /* This must be LAST to ensure no packets are walking over this chain. */ + err = nf_tables_register_hook(net, table, chain); + if (err < 0) + goto err_register_hook; return 0; -err_unregister_hook: +err_register_hook: + nft_chain_del(chain); +err_chain_add: + nft_trans_destroy(trans); +err_trans: nft_use_dec_restore(&table->use); -err_use: - nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -4998,6 +5001,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } desc.dtype = 0; @@ -5421,6 +5430,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); @@ -8455,9 +8465,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb, u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; - struct nft_hook *hook, *next; struct net *net = info->net; struct nft_table *table; + struct nft_trans *trans; struct nft_ctx ctx; int err; @@ -8537,34 +8547,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb, err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable, extack, true); if (err < 0) - goto err4; + goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; + trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto err_flowtable_trans; + } + + /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); - if (err < 0) { - nft_hooks_destroy(&flowtable->hook_list); - goto err4; - } - - err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; + goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; -err5: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } -err4: + +err_flowtable_hooks: + nft_trans_destroy(trans); +err_flowtable_trans: + nft_hooks_destroy(&flowtable->hook_list); +err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); @@ -9827,6 +9837,7 @@ dead_elem: struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) { struct nft_set_elem_catchall *catchall, *next; + u64 tstamp = nft_net_tstamp(gc->net); const struct nft_set *set = gc->set; struct nft_elem_priv *elem_priv; struct nft_set_ext *ext; @@ -9836,7 +9847,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_expired(ext)) + if (!__nft_set_elem_expired(ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); @@ -10622,6 +10633,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) bool genid_ok; mutex_lock(&nft_net->commit_mutex); + nft_net->tstamp = get_jiffies_64(); genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 171d1f52d3dd..5cf38fc0a366 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -232,18 +232,25 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { + unsigned int ct_verdict = verdict; + rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) - verdict = ct_hook->update(entry->state.net, entry->skb); + ct_verdict = ct_hook->update(entry->state.net, entry->skb); rcu_read_unlock(); - switch (verdict & NF_VERDICT_MASK) { + switch (ct_verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + /* follow userspace verdict, could be REPEAT */ + break; case NF_STOLEN: nf_queue_entry_free(entry); return; + default: + verdict = ct_verdict & NF_VERDICT_MASK; + break; } - } nf_reinject(entry, verdict); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f0eeda97bfcd..d3d11dede545 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = { [NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING }, - [NFTA_TARGET_REV] = { .type = NLA_U32 }, + [NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_TARGET_INFO] = { .type = NLA_BINARY }, }; @@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; + u32 l4proto; u32 flags; int err; @@ -212,12 +213,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; - *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + if (l4proto > U16_MAX) + return -EINVAL; + + *proto = l4proto; + return 0; } @@ -352,10 +359,20 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP; + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -419,7 +436,7 @@ static void nft_match_eval(const struct nft_expr *expr, static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING }, - [NFTA_MATCH_REV] = { .type = NLA_U32 }, + [NFTA_MATCH_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_MATCH_INFO] = { .type = NLA_BINARY }, }; @@ -603,10 +620,20 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP; + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -724,7 +751,7 @@ out_put: static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { [NFTA_COMPAT_NAME] = { .type = NLA_NUL_STRING, .len = NFT_COMPAT_NAME_MAX-1 }, - [NFTA_COMPAT_REV] = { .type = NLA_U32 }, + [NFTA_COMPAT_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_COMPAT_TYPE] = { .type = NLA_U32 }, }; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index aac98a3c966e..255640013ab8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -476,6 +476,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; #endif case NFT_CT_ID: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; + len = sizeof(u32); break; default: @@ -1253,14 +1256,13 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, switch (priv->l3num) { case NFPROTO_IPV4: case NFPROTO_IPV6: - if (priv->l3num != ctx->family) - return -EINVAL; + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; - fallthrough; - case NFPROTO_INET: - break; + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ default: - return -EOPNOTSUPP; + return -EAFNOSUPPORT; } priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 397351fa4d5f..ab9576098701 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -361,6 +361,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } + __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6c2061bfdae6..6968a3b34236 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -36,6 +36,7 @@ struct nft_rhash_cmp_arg { const struct nft_set *set; const u32 *key; u8 genmask; + u64 tstamp; }; static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed) @@ -62,7 +63,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, return 1; if (nft_set_elem_is_dead(&he->ext)) return 1; - if (nft_set_elem_expired(&he->ext)) + if (__nft_set_elem_expired(&he->ext, x->tstamp)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) return 1; @@ -87,6 +88,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -106,6 +108,7 @@ nft_rhash_get(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_cur(net), .set = set, .key = elem->key.val.data, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -131,6 +134,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, .genmask = NFT_GENMASK_ANY, .set = set, .key = key, + .tstamp = get_jiffies_64(), }; he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); @@ -175,6 +179,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; struct nft_rhash_elem *prev; @@ -216,6 +221,7 @@ nft_rhash_deactivate(const struct net *net, const struct nft_set *set, .genmask = nft_genmask_next(net), .set = set, .key = elem->key.val.data, + .tstamp = nft_net_tstamp(net), }; rcu_read_lock(); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index efd523496be4..aa1d9e93a9a0 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -342,9 +342,6 @@ #include "nft_set_pipapo_avx2.h" #include "nft_set_pipapo.h" -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index); - /** * pipapo_refill() - For each set bit, set bits from selected mapping table item * @map: Bitmap to be scanned for set bits @@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; @@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, local_bh_disable(); - map_index = raw_cpu_read(nft_pipapo_scratch_index); - m = rcu_dereference(priv->match); if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) goto out; - res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0); - fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max); + scratch = *raw_cpu_ptr(m->scratch); + + map_index = scratch->map_index; + + res_map = scratch->map + (map_index ? m->bsize_max : 0); + fill_map = scratch->map + (map_index ? 0 : m->bsize_max); memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); @@ -460,7 +460,7 @@ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) { - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return false; @@ -477,7 +477,7 @@ next_match: * current inactive bitmap is clean and can be reused as * *next* bitmap (not initial) for the next packet. */ - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return true; @@ -504,6 +504,7 @@ out: * @set: nftables API set representation * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask + * @tstamp: timestamp to check for expired elements * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for @@ -513,7 +514,8 @@ out: */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, - const u8 *data, u8 genmask) + const u8 *data, u8 genmask, + u64 tstamp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); @@ -566,7 +568,7 @@ next_match: goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext)) + if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) @@ -603,10 +605,10 @@ static struct nft_elem_priv * nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - static struct nft_pipapo_elem *e; + struct nft_pipapo_elem *e; e = pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + nft_genmask_cur(net), get_jiffies_64()); if (IS_ERR(e)) return ERR_CAST(e); @@ -1109,6 +1111,25 @@ static void pipapo_map(struct nft_pipapo_match *m, } /** + * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address + * @m: Matching data + * @cpu: CPU number + */ +static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu) +{ + struct nft_pipapo_scratch *s; + void *mem; + + s = *per_cpu_ptr(m->scratch, cpu); + if (!s) + return; + + mem = s; + mem -= s->align_off; + kfree(mem); +} + +/** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions * @bsize_max: Maximum bucket size, scratch maps cover two buckets @@ -1121,12 +1142,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, int i; for_each_possible_cpu(i) { - unsigned long *scratch; + struct nft_pipapo_scratch *scratch; #ifdef NFT_PIPAPO_ALIGN - unsigned long *scratch_aligned; + void *scratch_aligned; + u32 align_off; #endif - - scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 + + scratch = kzalloc_node(struct_size(scratch, map, + bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL, cpu_to_node(i)); if (!scratch) { @@ -1140,14 +1162,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, return -ENOMEM; } - kfree(*per_cpu_ptr(clone->scratch, i)); - - *per_cpu_ptr(clone->scratch, i) = scratch; + pipapo_free_scratch(clone, i); #ifdef NFT_PIPAPO_ALIGN - scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch); - *per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned; + /* Align &scratch->map (not the struct itself): the extra + * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node() + * above guarantee we can waste up to those bytes in order + * to align the map field regardless of its offset within + * the struct. + */ + BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM); + + scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map); + scratch_aligned -= offsetof(struct nft_pipapo_scratch, map); + align_off = scratch_aligned - (void *)scratch; + + scratch = scratch_aligned; + scratch->align_off = align_off; #endif + *per_cpu_ptr(clone->scratch, i) = scratch; } return 0; @@ -1173,6 +1206,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); struct nft_pipapo_elem *e, *dup; + u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1182,7 +1216,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, start, genmask); + dup = pipapo_get(net, set, start, genmask, tstamp); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1204,7 +1238,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net)); + dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp); } if (PTR_ERR(dup) != -ENOENT) { @@ -1301,11 +1335,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (!new->scratch) goto out_scratch; -#ifdef NFT_PIPAPO_ALIGN - new->scratch_aligned = alloc_percpu(*new->scratch_aligned); - if (!new->scratch_aligned) - goto out_scratch; -#endif for_each_possible_cpu(i) *per_cpu_ptr(new->scratch, i) = NULL; @@ -1357,10 +1386,7 @@ out_lt: } out_scratch_realloc: for_each_possible_cpu(i) - kfree(*per_cpu_ptr(new->scratch, i)); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(new->scratch_aligned); -#endif + pipapo_free_scratch(new, i); out_scratch: free_percpu(new->scratch); kfree(new); @@ -1560,6 +1586,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); + u64 tstamp = nft_net_tstamp(net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; struct nft_trans_gc *gc; @@ -1594,7 +1621,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) /* synchronous gc never fails, there is no need to set on * NFT_SET_ELEM_DEAD_BIT. */ - if (nft_set_elem_expired(&e->ext)) { + if (__nft_set_elem_expired(&e->ext, tstamp)) { priv->dirty = true; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); @@ -1640,13 +1667,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m) int i; for_each_possible_cpu(i) - kfree(*per_cpu_ptr(m->scratch, i)); + pipapo_free_scratch(m, i); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); - pipapo_free_fields(m); kfree(m); @@ -1769,7 +1792,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, { struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net)); + e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net)); if (IS_ERR(e)) return NULL; @@ -2132,7 +2155,7 @@ static int nft_pipapo_init(const struct nft_set *set, m->field_count = field_count; m->bsize_max = 0; - m->scratch = alloc_percpu(unsigned long *); + m->scratch = alloc_percpu(struct nft_pipapo_scratch *); if (!m->scratch) { err = -ENOMEM; goto out_scratch; @@ -2140,16 +2163,6 @@ static int nft_pipapo_init(const struct nft_set *set, for_each_possible_cpu(i) *per_cpu_ptr(m->scratch, i) = NULL; -#ifdef NFT_PIPAPO_ALIGN - m->scratch_aligned = alloc_percpu(unsigned long *); - if (!m->scratch_aligned) { - err = -ENOMEM; - goto out_free; - } - for_each_possible_cpu(i) - *per_cpu_ptr(m->scratch_aligned, i) = NULL; -#endif - rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { @@ -2180,9 +2193,6 @@ static int nft_pipapo_init(const struct nft_set *set, return 0; out_free: -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); out_scratch: kfree(m); @@ -2236,11 +2246,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(m->scratch, cpu)); + pipapo_free_scratch(m, cpu); free_percpu(m->scratch); pipapo_free_fields(m); kfree(m); @@ -2253,11 +2260,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->dirty) nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(priv->clone->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(priv->clone->scratch, cpu)); + pipapo_free_scratch(priv->clone, cpu); free_percpu(priv->clone->scratch); pipapo_free_fields(priv->clone); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 1040223da5fa..3842c7341a9f 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -131,20 +131,28 @@ struct nft_pipapo_field { }; /** + * struct nft_pipapo_scratch - percpu data used for lookup and matching + * @map_index: Current working bitmap index, toggled between field matches + * @align_off: Offset to get the originally allocated address + * @map: store partial matching results during lookup + */ +struct nft_pipapo_scratch { + u8 map_index; + u32 align_off; + unsigned long map[]; +}; + +/** * struct nft_pipapo_match - Data used for lookup and matching - * @field_count Amount of fields in set + * @field_count: Amount of fields in set * @scratch: Preallocated per-CPU maps for partial matching results - * @scratch_aligned: Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes * @bsize_max: Maximum lookup table bucket size of all fields, in longs - * @rcu Matching data is swapped on commits + * @rcu: Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { int field_count; -#ifdef NFT_PIPAPO_ALIGN - unsigned long * __percpu *scratch_aligned; -#endif - unsigned long * __percpu *scratch; + struct nft_pipapo_scratch * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; struct nft_pipapo_field f[] __counted_by(field_count); diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 52e0d026d30a..a3a8ddca9918 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -57,7 +57,7 @@ /* Jump to label if @reg is zero */ #define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \ - asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ + asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \ "je %l[" #label "]" : : : : label) /* Store 256 bits from YMM register into memory. Contrary to bucket load @@ -71,9 +71,6 @@ #define NFT_PIPAPO_AVX2_ZERO(reg) \ asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg) -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index); - /** * nft_pipapo_avx2_prepare() - Prepare before main algorithm body * @@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); - unsigned long *res, *fill, *scratch; + struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; struct nft_pipapo_match *m; struct nft_pipapo_field *f; + unsigned long *res, *fill; bool map_index; int i, ret = 0; @@ -1141,15 +1139,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, */ kernel_fpu_begin_mask(0); - scratch = *raw_cpu_ptr(m->scratch_aligned); + scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); return false; } - map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index); - res = scratch + (map_index ? m->bsize_max : 0); - fill = scratch + (map_index ? 0 : m->bsize_max); + map_index = scratch->map_index; + + res = scratch->map + (map_index ? m->bsize_max : 0); + fill = scratch->map + (map_index ? 0 : m->bsize_max); /* Starting map doesn't need to be set for this implementation */ @@ -1221,7 +1220,7 @@ next_match: out: if (i % 2) - raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index); + scratch->map_index = !map_index; kernel_fpu_end(); return ret >= 0; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index baa3fea4fe65..9944fe479e53 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -234,7 +234,7 @@ static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, u8 genmask) + struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -253,7 +253,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && - nft_set_elem_active(&rbe_prev->ext, genmask)) + nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); @@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; /* Descend the tree to search for an existing element greater than the @@ -360,11 +361,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* perform garbage collection to avoid bogus overlap reports * but skip new elements in this transaction. */ - if (nft_set_elem_expired(&rbe->ext) && + if (__nft_set_elem_expired(&rbe->ext, tstamp) && nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; - removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); @@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; u8 genmask = nft_genmask_next(net); + u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { @@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; - } else if (nft_set_elem_expired(&rbe->ext)) { + } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; @@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct net *net = read_pnet(&set->net); + u64 tstamp = nft_net_tstamp(net); struct rb_node *node, *next; struct nft_trans_gc *gc; - struct net *net; set = nft_set_container_of(priv); net = read_pnet(&set->net); @@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set) rbe_end = rbe; continue; } - if (!nft_set_elem_expired(&rbe->ext)) + if (!__nft_set_elem_expired(&rbe->ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9c962347cf85..ff315351269f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -167,7 +167,7 @@ static inline u32 netlink_group_mask(u32 group) static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { - unsigned int len = skb_end_offset(skb); + unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 0eed00184adf..104a80b75477 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, nr_init_timers(sk); nr->t1 = - msecs_to_jiffies(sysctl_netrom_transport_timeout); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = - msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = - msecs_to_jiffies(sysctl_netrom_transport_maximum_tries); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = - msecs_to_jiffies(sysctl_netrom_transport_busy_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = - msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout); - nr->window = sysctl_netrom_transport_requested_window_size; + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); + nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; @@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ - if (sysctl_netrom_reset_circuit && + if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 3aaac4a22b38..2c34389c3ce6 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev, buff[6] |= AX25_SSSID_SPARE; buff += AX25_ADDR_LEN; - *buff++ = sysctl_netrom_network_ttl_initialiser; + *buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); *buff++ = NR_PROTO_IP; *buff++ = NR_PROTO_IP; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 2f084b6f69d7..97944db6b5ac 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -262,7 +262,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 44929657f5b7..5e531394a724 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index baea3cbd76ca..70480869ad1c 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->digipeat = NULL; nr_neigh->ax25 = NULL; nr_neigh->dev = dev; - nr_neigh->quality = sysctl_netrom_default_path_quality; + nr_neigh->quality = READ_ONCE(sysctl_netrom_default_path_quality); nr_neigh->locked = 0; nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; @@ -728,7 +728,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) nr_neigh->ax25 = NULL; ax25_cb_put(ax25); - if (++nr_neigh->failed < sysctl_netrom_link_fails_count) { + if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) { nr_neigh_put(nr_neigh); return; } @@ -766,7 +766,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (ax25 != NULL) { ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat, ax25->ax25_dev->dev, 0, - sysctl_netrom_obsolescence_count_initialiser); + READ_ONCE(sysctl_netrom_obsolescence_count_initialiser)); if (ret) return ret; } @@ -780,7 +780,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) return ret; } - if (!sysctl_netrom_routing_control && ax25 != NULL) + if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL) return 0; /* Its Time-To-Live has expired */ diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index e2d2af924cff..c3bbd5880850 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype) *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; - if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; + if (nr->bpqext) + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); break; case NR_DISCREQ: @@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (mine) { *dptr++ = 0; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 88965e2068ac..ebc5728aab4e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 3aa50dc7535b..976fe250b509 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -34,10 +34,10 @@ static int pn_ioctl(struct sock *sk, int cmd, int *karg) switch (cmd) { case SIOCINQ: - lock_sock(sk); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); *karg = skb ? skb->len : 0; - release_sock(sk); + spin_unlock_bh(&sk->sk_receive_queue.lock); return 0; case SIOCPNADDRESOURCE: diff --git a/net/phonet/pep.c b/net/phonet/pep.c index faba31f2eff2..3dd5f52bc1b5 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) return 0; } +static unsigned int pep_first_packet_length(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + struct sk_buff_head *q; + struct sk_buff *skb; + unsigned int len = 0; + bool found = false; + + if (sock_flag(sk, SOCK_URGINLINE)) { + q = &pn->ctrlreq_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) { + len = skb->len; + found = true; + } + spin_unlock_bh(&q->lock); + } + + if (likely(!found)) { + q = &sk->sk_receive_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) + len = skb->len; + spin_unlock_bh(&q->lock); + } + + return len; +} + static int pep_ioctl(struct sock *sk, int cmd, int *karg) { struct pep_sock *pn = pep_sk(sk); @@ -929,15 +960,7 @@ static int pep_ioctl(struct sock *sk, int cmd, int *karg) break; } - lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) && - !skb_queue_empty(&pn->ctrlreq_queue)) - *karg = skb_peek(&pn->ctrlreq_queue)->len; - else if (!skb_queue_empty(&sk->sk_receive_queue)) - *karg = skb_peek(&sk->sk_receive_queue)->len; - else - *karg = 0; - release_sock(sk); + *karg = pep_first_packet_length(sk); ret = 0; break; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index fba82d36593a..a4e3c5de998b 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, kfree(sg); } ret = PTR_ERR(trans_private); + /* Trigger connection so that its ready for the next retry */ + if (ret == -ENODEV) + rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/recv.c b/net/rds/recv.c index c71b923764fd..5627f80013f8 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, struct sock *sk = rds_rs_to_sk(rs); int ret = 0; unsigned long flags; + struct rds_incoming *to_drop = NULL; write_lock_irqsave(&rs->rs_recv_lock, flags); if (!list_empty(&inc->i_item)) { @@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, -be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); list_del_init(&inc->i_item); - rds_inc_put(inc); + to_drop = inc; } } write_unlock_irqrestore(&rs->rs_recv_lock, flags); + if (to_drop) + rds_inc_put(to_drop); + rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop); return ret; } @@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs) struct sock *sk = rds_rs_to_sk(rs); struct rds_incoming *inc, *tmp; unsigned long flags; + LIST_HEAD(to_drop); write_lock_irqsave(&rs->rs_recv_lock, flags); list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) { rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong, -be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); + list_move(&inc->i_item, &to_drop); + } + write_unlock_irqrestore(&rs->rs_recv_lock, flags); + + list_for_each_entry_safe(inc, tmp, &to_drop, i_item) { list_del_init(&inc->i_item); rds_inc_put(inc); } - write_unlock_irqrestore(&rs->rs_recv_lock, flags); } /* diff --git a/net/rds/send.c b/net/rds/send.c index 5e57a1581dc6..2899def23865 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1313,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); - if (ret) { - /* Trigger connection so that its ready for the next retry */ - if (ret == -EAGAIN) - rds_conn_connect_if_down(conn); + if (ret) goto out; - } if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index dbeb75c29857..7818aae1be8e 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -199,11 +199,19 @@ struct rxrpc_host_header { */ struct rxrpc_skb_priv { struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ - u16 offset; /* Offset of data */ - u16 len; /* Length of data */ - u8 flags; + union { + struct { + u16 offset; /* Offset of data */ + u16 len; /* Length of data */ + u8 flags; #define RXRPC_RX_VERIFIED 0x01 - + }; + struct { + rxrpc_seq_t first_ack; /* First packet in acks table */ + u8 nr_acks; /* Number of acks+nacks */ + u8 nr_nacks; /* Number of nacks */ + }; + }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; @@ -510,7 +518,7 @@ struct rxrpc_connection { enum rxrpc_call_completion completion; /* Completion condition */ s32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ - atomic_t serial; /* packet serial number counter */ + rxrpc_serial_t tx_serial; /* Outgoing packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ u32 service_id; /* Service ID, possibly upgraded */ u32 security_level; /* Security level selected */ @@ -692,11 +700,11 @@ struct rxrpc_call { u8 cong_dup_acks; /* Count of ACKs showing missing packets */ u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ + struct sk_buff *cong_last_nack; /* Last ACK with nacks received */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ u16 ackr_sack_base; /* Starting slot in SACK table ring */ - rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ rxrpc_seq_t ackr_window; /* Base of SACK window */ rxrpc_seq_t ackr_wtop; /* Base of SACK window */ unsigned int ackr_nr_unacked; /* Number of unacked packets */ @@ -730,7 +738,8 @@ struct rxrpc_call { struct rxrpc_ack_summary { u16 nr_acks; /* Number of ACKs in packet */ u16 nr_new_acks; /* Number of new ACKs in packet */ - u16 nr_rot_new_acks; /* Number of rotated new ACKs */ + u16 nr_new_nacks; /* Number of new nacks in packet */ + u16 nr_retained_nacks; /* Number of nacks retained between ACKs */ u8 ack_reason; bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ @@ -823,6 +832,20 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) #include <trace/events/rxrpc.h> /* + * Allocate the next serial number on a connection. 0 must be skipped. + */ +static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn) +{ + rxrpc_serial_t serial; + + serial = conn->tx_serial; + if (serial == 0) + serial = 1; + conn->tx_serial = serial + 1; + return serial; +} + +/* * af_rxrpc.c */ extern atomic_t rxrpc_n_rx_skbs; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index e363f21a2014..0f78544d043b 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -43,8 +43,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, unsigned long expiry = rxrpc_soft_ack_delay; unsigned long now = jiffies, ack_at; - call->ackr_serial = serial; - if (rxrpc_soft_ack_delay < expiry) expiry = rxrpc_soft_ack_delay; if (call->peer->srtt_us != 0) @@ -114,6 +112,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) { struct rxrpc_ackpacket *ack = NULL; + struct rxrpc_skb_priv *sp; struct rxrpc_txbuf *txb; unsigned long resend_at; rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); @@ -141,14 +140,15 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) * explicitly NAK'd packets. */ if (ack_skb) { + sp = rxrpc_skb(ack_skb); ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); - for (i = 0; i < ack->nAcks; i++) { + for (i = 0; i < sp->nr_acks; i++) { rxrpc_seq_t seq; if (ack->acks[i] & 1) continue; - seq = ntohl(ack->firstPacket) + i; + seq = sp->first_ack + i; if (after(txb->seq, transmitted)) break; if (after(txb->seq, seq)) @@ -373,7 +373,6 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { unsigned long now, next, t; - rxrpc_serial_t ackr_serial; bool resend = false, expired = false; s32 abort_code; @@ -423,8 +422,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); - ackr_serial = xchg(&call->ackr_serial, 0); - rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial, + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0, rxrpc_propose_ack_ping_for_lost_ack); } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 0943e54370ba..9fc9a6c3f685 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -686,6 +686,7 @@ static void rxrpc_destroy_call(struct work_struct *work) del_timer_sync(&call->timer); + rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); rxrpc_cleanup_ring(call); while ((txb = list_first_entry_or_null(&call->tx_sendmsg, struct rxrpc_txbuf, call_link))) { diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 95f4bc206b3d..1f251d758cb9 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -95,6 +95,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _enter("%d", conn->debug_id); + if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), + &pkt.ack, sizeof(pkt.ack)) < 0) + return; + if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE) + return; + } + chan = &conn->channels[channel]; /* If the last call got moved on whilst we were waiting to run, just @@ -117,7 +125,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[2].iov_base = &ack_info; iov[2].iov_len = sizeof(ack_info); - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); pkt.whdr.epoch = htonl(conn->proto.epoch); pkt.whdr.cid = htonl(conn->proto.cid | channel); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 92495e73b869..9691de00ade7 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -45,11 +45,9 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } cumulative_acks += summary->nr_new_acks; - cumulative_acks += summary->nr_rot_new_acks; if (cumulative_acks > 255) cumulative_acks = 255; - summary->mode = call->cong_mode; summary->cwnd = call->cong_cwnd; summary->ssthresh = call->cong_ssthresh; summary->cumulative_acks = cumulative_acks; @@ -151,6 +149,7 @@ out_no_clear_ca: cwnd = RXRPC_TX_MAX_WINDOW; call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; + summary->mode = call->cong_mode; trace_rxrpc_congest(call, summary, acked_serial, change); if (resend) rxrpc_resend(call, skb); @@ -213,7 +212,6 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { if (before_eq(txb->seq, call->acks_hard_ack)) continue; - summary->nr_rot_new_acks++; if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; @@ -254,6 +252,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, { ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); + if (unlikely(call->cong_last_nack)) { + rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); + call->cong_last_nack = NULL; + } + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: @@ -703,6 +706,43 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, } /* + * Determine how many nacks from the previous ACK have now been satisfied. + */ +static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + rxrpc_seq_t seq) +{ + struct sk_buff *skb = call->cong_last_nack; + struct rxrpc_ackpacket ack; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + unsigned int i, new_acks = 0, retained_nacks = 0; + rxrpc_seq_t old_seq = sp->first_ack; + u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack); + + if (after_eq(seq, old_seq + sp->nr_acks)) { + summary->nr_new_acks += sp->nr_nacks; + summary->nr_new_acks += seq - (old_seq + sp->nr_acks); + summary->nr_retained_nacks = 0; + } else if (seq == old_seq) { + summary->nr_retained_nacks = sp->nr_nacks; + } else { + for (i = 0; i < sp->nr_acks; i++) { + if (acks[i] == RXRPC_ACK_TYPE_NACK) { + if (before(old_seq + i, seq)) + new_acks++; + else + retained_nacks++; + } + } + + summary->nr_new_acks += new_acks; + summary->nr_retained_nacks = retained_nacks; + } + + return old_seq + sp->nr_acks; +} + +/* * Process individual soft ACKs. * * Each ACK in the array corresponds to one packet and can be either an ACK or @@ -711,25 +751,51 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, * the timer on the basis that the peer might just not have processed them at * the time the ACK was sent. */ -static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, - rxrpc_seq_t seq, int nr_acks, - struct rxrpc_ack_summary *summary) +static void rxrpc_input_soft_acks(struct rxrpc_call *call, + struct rxrpc_ack_summary *summary, + struct sk_buff *skb, + rxrpc_seq_t seq, + rxrpc_seq_t since) { - unsigned int i; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + unsigned int i, old_nacks = 0; + rxrpc_seq_t lowest_nak = seq + sp->nr_acks; + u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - for (i = 0; i < nr_acks; i++) { + for (i = 0; i < sp->nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; - summary->nr_new_acks++; + if (after_eq(seq, since)) + summary->nr_new_acks++; } else { - if (!summary->saw_nacks && - call->acks_lowest_nak != seq + i) { - call->acks_lowest_nak = seq + i; - summary->new_low_nack = true; - } summary->saw_nacks = true; + if (before(seq, since)) { + /* Overlap with previous ACK */ + old_nacks++; + } else { + summary->nr_new_nacks++; + sp->nr_nacks++; + } + + if (before(seq, lowest_nak)) + lowest_nak = seq; } + seq++; + } + + if (lowest_nak != call->acks_lowest_nak) { + call->acks_lowest_nak = lowest_nak; + summary->new_low_nack = true; } + + /* We *can* have more nacks than we did - the peer is permitted to drop + * packets it has soft-acked and re-request them. Further, it is + * possible for the nack distribution to change whilst the number of + * nacks stays the same or goes down. + */ + if (old_nacks < summary->nr_retained_nacks) + summary->nr_new_acks += summary->nr_retained_nacks - old_nacks; + summary->nr_retained_nacks = old_nacks; } /* @@ -773,7 +839,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_ackinfo info; rxrpc_serial_t ack_serial, acked_serial; - rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; + rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since; int nr_acks, offset, ioffset; _enter(""); @@ -789,6 +855,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) prev_pkt = ntohl(ack.previousPacket); hard_ack = first_soft_ack - 1; nr_acks = ack.nAcks; + sp->first_ack = first_soft_ack; + sp->nr_acks = nr_acks; summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? ack.reason : RXRPC_ACK__INVALID); @@ -858,6 +926,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (nr_acks > 0) skb_condense(skb); + if (call->cong_last_nack) { + since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack); + rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); + call->cong_last_nack = NULL; + } else { + summary.nr_new_acks = first_soft_ack - call->acks_first_seq; + call->acks_lowest_nak = first_soft_ack + nr_acks; + since = first_soft_ack; + } + call->acks_latest_ts = skb->tstamp; call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; @@ -866,7 +944,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_ACK_PING: break; default: - if (after(acked_serial, call->acks_highest_serial)) + if (acked_serial && after(acked_serial, call->acks_highest_serial)) call->acks_highest_serial = acked_serial; break; } @@ -905,8 +983,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (nr_acks > 0) { if (offset > (int)skb->len - nr_acks) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack); - rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, - nr_acks, &summary); + rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since); + rxrpc_get_skb(skb, rxrpc_skb_get_last_nack); + call->cong_last_nack = skb; } if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index a0906145e829..4a292f860ae3 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -216,7 +216,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; len = iov[0].iov_len; - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(txb->ack.firstPacket), @@ -302,7 +302,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) iov[0].iov_base = &pkt; iov[0].iov_len = sizeof(pkt); - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); pkt.whdr.serial = htonl(serial); iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt)); @@ -334,7 +334,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) _enter("%x,{%d}", txb->seq, txb->len); /* Each transmission of a Tx packet needs a new serial number */ - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); txb->wire.serial = htonl(serial); if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && @@ -558,7 +558,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn) len = iov[0].iov_len + iov[1].iov_len; - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); whdr.serial = htonl(serial); iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 6c86cbb98d1d..26dc2f26d92d 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -181,7 +181,7 @@ print: atomic_read(&conn->active), state, key_serial(conn->key), - atomic_read(&conn->serial), + conn->tx_serial, conn->hi_serial, conn->channels[0].call_id, conn->channels[1].call_id, diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index b52dedcebce0..6b32d61d4cdc 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -664,7 +664,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) len = iov[0].iov_len + iov[1].iov_len; - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); whdr.serial = htonl(serial); ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len); @@ -721,7 +721,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn, len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len; - serial = atomic_inc_return(&conn->serial); + serial = rxrpc_get_next_serial(conn); whdr.serial = htonl(serial); rxrpc_local_dont_fragment(conn->local, false); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 12386f590b0f..6faa7d00da09 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -232,18 +232,14 @@ release_idr: return err; } -static bool is_mirred_nested(void) -{ - return unlikely(__this_cpu_read(mirred_nest_level) > 1); -} - -static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) +static int +tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = tcf_dev_queue_xmit(skb, dev_queue_xmit); - else if (is_mirred_nested()) + else if (!at_ingress) err = netif_rx(skb); else err = netif_receive_skb(skb); @@ -270,8 +266,7 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); - err = -ENODEV; - goto out; + goto err_cant_do; } /* we could easily avoid the clone only if called by ingress and clsact; @@ -283,10 +278,8 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, tcf_mirred_can_reinsert(retval); if (!dont_clone) { skb_to_send = skb_clone(skb, GFP_ATOMIC); - if (!skb_to_send) { - err = -ENOMEM; - goto out; - } + if (!skb_to_send) + goto err_cant_do; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); @@ -319,19 +312,20 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); - err = tcf_mirred_forward(want_ingress, skb_to_send); + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } else { - err = tcf_mirred_forward(want_ingress, skb_to_send); + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } - - if (err) { -out: + if (err) tcf_action_inc_overlimit_qstats(&m->common); - if (is_redirect) - retval = TC_ACT_SHOT; - } return retval; + +err_cant_do: + if (is_redirect) + retval = TC_ACT_SHOT; + tcf_action_inc_overlimit_qstats(&m->common); + return retval; } static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, @@ -533,8 +527,6 @@ static int mirred_device_event(struct notifier_block *unused, * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); - } else if (m->tcfm_blockid) { - m->tcfm_blockid = 0; } spin_unlock_bh(&m->tcf_lock); } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index efb9d2811b73..6ee7064c82fc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2460,8 +2460,11 @@ unbind_filter: } errout_idr: - if (!fold) + if (!fold) { + spin_lock(&tp->lock); idr_remove(&head->handle_idr, fnew->handle); + spin_unlock(&tp->lock); + } __fl_put(fnew); errout_tb: kfree(tb); diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c index 5ea84decec19..5337bc462755 100644 --- a/net/sched/em_canid.c +++ b/net/sched/em_canid.c @@ -222,6 +222,7 @@ static void __exit exit_em_canid(void) tcf_em_unregister(&em_canid_ops); } +MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames"); MODULE_LICENSE("GPL"); module_init(init_em_canid); diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index f17b049ea530..c90ad7ea26b4 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -87,6 +87,7 @@ static void __exit exit_em_cmp(void) tcf_em_unregister(&em_cmp_ops); } +MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data"); MODULE_LICENSE("GPL"); module_init(init_em_cmp); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 09d8afd04a2a..8996c73c9779 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void) tcf_em_unregister(&em_meta_ops); } +MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata"); MODULE_LICENSE("GPL"); module_init(init_em_meta); diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index a83b237cbeb0..4f9f21a05d5e 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -68,6 +68,7 @@ static void __exit exit_em_nbyte(void) tcf_em_unregister(&em_nbyte_ops); } +MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes"); MODULE_LICENSE("GPL"); module_init(init_em_nbyte); diff --git a/net/sched/em_text.c b/net/sched/em_text.c index f176afb70559..420c66203b17 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -147,6 +147,7 @@ static void __exit exit_em_text(void) tcf_em_unregister(&em_text_ops); } +MODULE_DESCRIPTION("ematch classifier for embedded text in skbs"); MODULE_LICENSE("GPL"); module_init(init_em_text); diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 71b070da0437..fdec4db5ec89 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -52,6 +52,7 @@ static void __exit exit_em_u32(void) tcf_em_unregister(&em_u32_ops); } +MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data"); MODULE_LICENSE("GPL"); module_init(init_em_u32); diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 7182c5a450fb..5c1652181805 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue) INIT_WORK(&queue->immediate, NULL); } +/* Properly release the chunk which is being worked on. */ +static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk) +{ + if (chunk->head_skb) + chunk->skb = chunk->head_skb; + sctp_chunk_free(chunk); +} + /* Release the memory associated with an SCTP inqueue. */ void sctp_inq_free(struct sctp_inq *queue) { @@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue) * free it as well. */ if (queue->in_progress) { - sctp_chunk_free(queue->in_progress); + sctp_inq_chunk_free(queue->in_progress); queue->in_progress = NULL; } } @@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) goto new_skb; } - if (chunk->head_skb) - chunk->skb = chunk->head_skb; - sctp_chunk_free(chunk); + sctp_inq_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a2cb30af46cb..0f53a5c6fd9d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -924,6 +924,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) smc->clcsock->file->private_data = smc->clcsock; smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; + smc->sk.sk_socket->wq.fasync_list = NULL; /* There might be some wait entries remaining * in smc sk->sk_wq and they should be woken up diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5b045284849e..c9189a970eec 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,35 @@ #include <linux/rtnetlink.h> #include <net/switchdev.h> +static bool switchdev_obj_eq(const struct switchdev_obj *a, + const struct switchdev_obj *b) +{ + const struct switchdev_obj_port_vlan *va, *vb; + const struct switchdev_obj_port_mdb *ma, *mb; + + if (a->id != b->id || a->orig_dev != b->orig_dev) + return false; + + switch (a->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + va = SWITCHDEV_OBJ_PORT_VLAN(a); + vb = SWITCHDEV_OBJ_PORT_VLAN(b); + return va->flags == vb->flags && + va->vid == vb->vid && + va->changed == vb->changed; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + ma = SWITCHDEV_OBJ_PORT_MDB(a); + mb = SWITCHDEV_OBJ_PORT_MDB(b); + return ma->vid == mb->vid && + ether_addr_equal(ma->addr, mb->addr); + default: + break; + } + + BUG(); +} + static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); +/** + * switchdev_port_obj_act_is_deferred - Is object action pending? + * + * @dev: port device + * @nt: type of action; add or delete + * @obj: object to test + * + * Returns true if a deferred item is pending, which is + * equivalent to the action @nt on an object @obj. + * + * rtnl_lock must be held. + */ +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj) +{ + struct switchdev_deferred_item *dfitem; + bool found = false; + + ASSERT_RTNL(); + + spin_lock_bh(&deferred_lock); + + list_for_each_entry(dfitem, &deferred, list) { + if (dfitem->dev != dev) + continue; + + if ((dfitem->func == switchdev_port_obj_add_deferred && + nt == SWITCHDEV_PORT_OBJ_ADD) || + (dfitem->func == switchdev_port_obj_del_deferred && + nt == SWITCHDEV_PORT_OBJ_DEL)) { + if (switchdev_obj_eq((const void *)dfitem->data, obj)) { + found = true; + break; + } + } + } + + spin_unlock_bh(&deferred_lock); + + return found; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); + static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 2cde375477e3..878415c43527 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1086,6 +1086,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); + return -EINVAL; + } + err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); if (err) { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 1c2c6800949d..b4674f03d71a 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1003,7 +1003,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return 0; } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 31e8a94dfc11..211f57164cb6 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -52,6 +52,7 @@ struct tls_decrypt_arg { struct_group(inargs, bool zc; bool async; + bool async_done; u8 tail; ); @@ -63,6 +64,7 @@ struct tls_decrypt_ctx { u8 iv[TLS_MAX_IV_SIZE]; u8 aad[TLS_MAX_AAD_SIZE]; u8 tail; + bool free_sgout; struct scatterlist sg[]; }; @@ -187,7 +189,6 @@ static void tls_decrypt_done(void *data, int err) struct aead_request *aead_req = data; struct crypto_aead *aead = crypto_aead_reqtfm(aead_req); struct scatterlist *sgout = aead_req->dst; - struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_decrypt_ctx *dctx; struct tls_context *tls_ctx; @@ -196,6 +197,17 @@ static void tls_decrypt_done(void *data, int err) struct sock *sk; int aead_size; + /* If requests get too backlogged crypto API returns -EBUSY and calls + * ->complete(-EINPROGRESS) immediately followed by ->complete(0) + * to make waiting for backlog to flush with crypto_wait_req() easier. + * First wait converts -EBUSY -> -EINPROGRESS, and the second one + * -EINPROGRESS -> 0. + * We have a single struct crypto_async_request per direction, this + * scheme doesn't help us, so just ignore the first ->complete(). + */ + if (err == -EINPROGRESS) + return; + aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead); aead_size = ALIGN(aead_size, __alignof__(*dctx)); dctx = (void *)((u8 *)aead_req + aead_size); @@ -213,7 +225,7 @@ static void tls_decrypt_done(void *data, int err) } /* Free the destination pages if skb was not decrypted inplace */ - if (sgout != sgin) { + if (dctx->free_sgout) { /* Skip the first S/G entry as it points to AAD */ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { if (!sg) @@ -224,10 +236,17 @@ static void tls_decrypt_done(void *data, int err) kfree(aead_req); - spin_lock_bh(&ctx->decrypt_compl_lock); - if (!atomic_dec_return(&ctx->decrypt_pending)) + if (atomic_dec_and_test(&ctx->decrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->decrypt_compl_lock); +} + +static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx) +{ + if (!atomic_dec_and_test(&ctx->decrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->decrypt_pending); + + return ctx->async_wait.err; } static int tls_do_decryption(struct sock *sk, @@ -253,20 +272,33 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_decrypt_done, aead_req); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1); atomic_inc(&ctx->decrypt_pending); } else { + DECLARE_CRYPTO_WAIT(wait); + aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &ctx->async_wait); + crypto_req_done, &wait); + ret = crypto_aead_decrypt(aead_req); + if (ret == -EINPROGRESS || ret == -EBUSY) + ret = crypto_wait_req(ret, &wait); + return ret; } ret = crypto_aead_decrypt(aead_req); - if (ret == -EINPROGRESS) { - if (darg->async) - return 0; + if (ret == -EINPROGRESS) + return 0; - ret = crypto_wait_req(ret, &ctx->async_wait); + if (ret == -EBUSY) { + ret = tls_decrypt_async_wait(ctx); + darg->async_done = true; + /* all completions have run, we're not doing async anymore */ + darg->async = false; + return ret; } + + atomic_dec(&ctx->decrypt_pending); darg->async = false; return ret; @@ -439,9 +471,10 @@ static void tls_encrypt_done(void *data, int err) struct tls_rec *rec = data; struct scatterlist *sge; struct sk_msg *msg_en; - bool ready = false; struct sock *sk; - int pending; + + if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */ + return; msg_en = &rec->msg_encrypted; @@ -476,23 +509,25 @@ static void tls_encrypt_done(void *data, int err) /* If received record is at head of tx_list, schedule tx */ first_rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - if (rec == first_rec) - ready = true; + if (rec == first_rec) { + /* Schedule the transmission */ + if (!test_and_set_bit(BIT_TX_SCHEDULED, + &ctx->tx_bitmask)) + schedule_delayed_work(&ctx->tx_work.work, 1); + } } - spin_lock_bh(&ctx->encrypt_compl_lock); - pending = atomic_dec_return(&ctx->encrypt_pending); - - if (!pending && ctx->async_notify) + if (atomic_dec_and_test(&ctx->encrypt_pending)) complete(&ctx->async_wait.completion); - spin_unlock_bh(&ctx->encrypt_compl_lock); +} - if (!ready) - return; +static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx) +{ + if (!atomic_dec_and_test(&ctx->encrypt_pending)) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + atomic_inc(&ctx->encrypt_pending); - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) - schedule_delayed_work(&ctx->tx_work.work, 1); + return ctx->async_wait.err; } static int tls_do_encryption(struct sock *sk, @@ -541,9 +576,14 @@ static int tls_do_encryption(struct sock *sk, /* Add the record in tx_list */ list_add_tail((struct list_head *)&rec->list, &ctx->tx_list); + DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1); atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); + if (rc == -EBUSY) { + rc = tls_encrypt_async_wait(ctx); + rc = rc ?: -EINPROGRESS; + } if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); sge->offset -= prot->prepend_size; @@ -984,7 +1024,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, int num_zc = 0; int orig_size; int ret = 0; - int pending; if (!eor && (msg->msg_flags & MSG_EOR)) return -EINVAL; @@ -1163,24 +1202,12 @@ trim_sgl: if (!num_async) { goto send_end; } else if (num_zc) { - /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no - * pending encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); + int err; - if (ctx->async_wait.err) { - ret = ctx->async_wait.err; + /* Wait for pending encryptions to get completed */ + err = tls_encrypt_async_wait(ctx); + if (err) { + ret = err; copied = 0; } } @@ -1229,7 +1256,6 @@ void tls_sw_splice_eof(struct socket *sock) ssize_t copied = 0; bool retrying = false; int ret = 0; - int pending; if (!ctx->open_rec) return; @@ -1264,22 +1290,7 @@ retry: } /* Wait for pending encryptions to get completed */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - else - reinit_completion(&ctx->async_wait.completion); - - /* There can be no concurrent accesses, since we have no pending - * encrypt operations - */ - WRITE_ONCE(ctx->async_notify, false); - - if (ctx->async_wait.err) + if (tls_encrypt_async_wait(ctx)) goto unlock; /* Transmit if any encryptions have completed */ @@ -1581,12 +1592,16 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, } else if (out_sg) { memcpy(sgout, out_sg, n_sgout * sizeof(*sgout)); } + dctx->free_sgout = !!pages; /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, sgin, sgout, dctx->iv, data_len + prot->tail_size, aead_req, darg); - if (err) + if (err) { + if (darg->async_done) + goto exit_free_skb; goto exit_free_pages; + } darg->skb = clear_skb ?: tls_strp_msg(ctx); clear_skb = NULL; @@ -1598,6 +1613,9 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov, return err; } + if (unlikely(darg->async_done)) + return 0; + if (prot->tail_size) darg->tail = dctx->tail; @@ -1769,7 +1787,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, u8 *control, size_t skip, size_t len, - bool is_peek) + bool is_peek, + bool *more) { struct sk_buff *skb = skb_peek(&ctx->rx_list); struct tls_msg *tlm; @@ -1782,7 +1801,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; if (skip < rxm->full_len) break; @@ -1800,12 +1819,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; err = skb_copy_datagram_msg(skb, rxm->offset + skip, msg, chunk); if (err < 0) - goto out; + goto more; len = len - chunk; copied = copied + chunk; @@ -1841,6 +1860,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, out: return copied ? : err; +more: + if (more) + *more = true; + goto out; } static bool @@ -1940,10 +1963,12 @@ int tls_sw_recvmsg(struct sock *sk, struct strp_msg *rxm; struct tls_msg *tlm; ssize_t copied = 0; + ssize_t peeked = 0; bool async = false; int target, err; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; + bool rx_more = false; bool released = true; bool bpf_strp_enabled; bool zc_capable; @@ -1963,12 +1988,12 @@ int tls_sw_recvmsg(struct sock *sk, goto end; /* Process pending decrypted records. It must be non-zero-copy */ - err = process_rx_list(ctx, msg, &control, 0, len, is_peek); + err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more); if (err < 0) goto end; copied = err; - if (len <= copied) + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); @@ -2061,6 +2086,8 @@ put_on_rx_list: decrypted += chunk; len -= chunk; __skb_queue_tail(&ctx->rx_list, skb); + if (unlikely(control != TLS_RECORD_TYPE_DATA)) + break; continue; } @@ -2084,8 +2111,10 @@ put_on_rx_list: if (err < 0) goto put_on_rx_list_err; - if (is_peek) + if (is_peek) { + peeked += chunk; goto put_on_rx_list; + } if (partially_consumed) { rxm->offset += chunk; @@ -2109,16 +2138,10 @@ put_on_rx_list: recv_end: if (async) { - int ret, pending; + int ret; /* Wait for all previously submitted records to be decrypted */ - spin_lock_bh(&ctx->decrypt_compl_lock); - reinit_completion(&ctx->async_wait.completion); - pending = atomic_read(&ctx->decrypt_pending); - spin_unlock_bh(&ctx->decrypt_compl_lock); - ret = 0; - if (pending) - ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + ret = tls_decrypt_async_wait(ctx); __skb_queue_purge(&ctx->async_hold); if (ret) { @@ -2130,12 +2153,11 @@ recv_end: /* Drain records from the rx_list & copy if required */ if (is_peek || is_kvec) - err = process_rx_list(ctx, msg, &control, copied, - decrypted, is_peek); + err = process_rx_list(ctx, msg, &control, copied + peeked, + decrypted - peeked, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, - async_copy_bytes, is_peek); - decrypted += max(err, 0); + async_copy_bytes, is_peek, NULL); } copied += decrypted; @@ -2435,16 +2457,9 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; - int pending; /* Wait for any pending async encryptions to complete */ - spin_lock_bh(&ctx->encrypt_compl_lock); - ctx->async_notify = true; - pending = atomic_read(&ctx->encrypt_pending); - spin_unlock_bh(&ctx->encrypt_compl_lock); - - if (pending) - crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + tls_encrypt_async_wait(ctx); tls_tx_records(sk, -1); @@ -2607,7 +2622,7 @@ static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct soc } crypto_init_wait(&sw_ctx_tx->async_wait); - spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); + atomic_set(&sw_ctx_tx->encrypt_pending, 1); INIT_LIST_HEAD(&sw_ctx_tx->tx_list); INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler); sw_ctx_tx->tx_work.sk = sk; @@ -2628,7 +2643,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) } crypto_init_wait(&sw_ctx_rx->async_wait); - spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); + atomic_set(&sw_ctx_rx->decrypt_pending, 1); init_waitqueue_head(&sw_ctx_rx->wq); skb_queue_head_init(&sw_ctx_rx->rx_list); skb_queue_head_init(&sw_ctx_rx->async_hold); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 30b178ebba60..0748e7ea5210 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -782,19 +782,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, int); -static int unix_set_peek_off(struct sock *sk, int val) -{ - struct unix_sock *u = unix_sk(sk); - - if (mutex_lock_interruptible(&u->iolock)) - return -EINTR; - - WRITE_ONCE(sk->sk_peek_off, val); - mutex_unlock(&u->iolock); - - return 0; -} - #ifdef CONFIG_PROC_FS static int unix_count_nr_fds(struct sock *sk) { @@ -862,7 +849,7 @@ static const struct proto_ops unix_stream_ops = { .read_skb = unix_stream_read_skb, .mmap = sock_no_mmap, .splice_read = unix_stream_splice_read, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -886,7 +873,7 @@ static const struct proto_ops unix_dgram_ops = { .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -909,7 +896,7 @@ static const struct proto_ops unix_seqpacket_ops = { .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2405f0f9af31..2a81880dac7b 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -284,9 +284,17 @@ void unix_gc(void) * which are creating the cycle(s). */ skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) + list_for_each_entry(u, &gc_candidates, link) { scan_children(&u->sk, inc_inflight, &hitlist); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + } + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ diff --git a/net/wireless/core.c b/net/wireless/core.c index 409d74c57ca0..3fb1b637352a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -1661,6 +1661,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy, unsigned long delay) { if (!delay) { + del_timer(&dwork->timer); wiphy_work_queue(wiphy, &dwork->work); return; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b09700400d09..bd54a928bab4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4197,6 +4197,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (ntype != NL80211_IFTYPE_MESH_POINT) return -EINVAL; + if (otype != NL80211_IFTYPE_MESH_POINT) + return -EINVAL; if (netif_running(dev)) return -EBUSY; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 2249b1a89d1c..389a52c29bfc 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1731,6 +1731,61 @@ static void cfg80211_update_hidden_bsses(struct cfg80211_internal_bss *known, } } +static void cfg80211_check_stuck_ecsa(struct cfg80211_registered_device *rdev, + struct cfg80211_internal_bss *known, + const struct cfg80211_bss_ies *old) +{ + const struct ieee80211_ext_chansw_ie *ecsa; + const struct element *elem_new, *elem_old; + const struct cfg80211_bss_ies *new, *bcn; + + if (known->pub.proberesp_ecsa_stuck) + return; + + new = rcu_dereference_protected(known->pub.proberesp_ies, + lockdep_is_held(&rdev->bss_lock)); + if (WARN_ON(!new)) + return; + + if (new->tsf - old->tsf < USEC_PER_SEC) + return; + + elem_old = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN, + old->data, old->len); + if (!elem_old) + return; + + elem_new = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN, + new->data, new->len); + if (!elem_new) + return; + + bcn = rcu_dereference_protected(known->pub.beacon_ies, + lockdep_is_held(&rdev->bss_lock)); + if (bcn && + cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN, + bcn->data, bcn->len)) + return; + + if (elem_new->datalen != elem_old->datalen) + return; + if (elem_new->datalen < sizeof(struct ieee80211_ext_chansw_ie)) + return; + if (memcmp(elem_new->data, elem_old->data, elem_new->datalen)) + return; + + ecsa = (void *)elem_new->data; + + if (!ecsa->mode) + return; + + if (ecsa->new_ch_num != + ieee80211_frequency_to_channel(known->pub.channel->center_freq)) + return; + + known->pub.proberesp_ecsa_stuck = 1; +} + static bool cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, struct cfg80211_internal_bss *known, @@ -1750,8 +1805,10 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, /* Override possible earlier Beacon frame IEs */ rcu_assign_pointer(known->pub.ies, new->pub.proberesp_ies); - if (old) + if (old) { + cfg80211_check_stuck_ecsa(rdev, known, old); kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); + } } if (rcu_access_pointer(new->pub.beacon_ies)) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 1eadfac03cc4..b78c0e095e22 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -722,7 +722,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, memcpy(vaddr, buffer, len); kunmap_local(vaddr); - skb_add_rx_frag(skb, nr_frags, page, 0, len, 0); + skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); + refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); } if (first_frag && desc->options & XDP_TX_METADATA) { diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 41533c631431..e6da7e8495c9 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -858,4 +858,5 @@ int xfrm_count_pfkey_enc_supported(void) } EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported); +MODULE_DESCRIPTION("XFRM Algorithm interface"); MODULE_LICENSE("GPL"); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 3784534c9185..653e51ae3964 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -407,7 +407,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; - if (!x->type_offload || x->encap) + if (!x->type_offload) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 662c83beb345..e5722c95b8bb 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -704,9 +704,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct xfrm_state *x = skb_dst(skb)->xfrm; + int family; int err; - switch (x->outer_mode.family) { + family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family + : skb_dst(skb)->ops->family; + + switch (family) { case AF_INET: memset(IPCB(skb), 0, sizeof(*IPCB(skb))); IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1b7e75159727..da6ecc6b3e15 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2694,7 +2694,9 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); - family = xfrm[i]->props.family; + if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET) + family = xfrm[i]->props.family; + oif = fl->flowi_oif ? : fl->flowi_l3mdev; dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); @@ -3416,7 +3418,7 @@ decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reve } fl4->flowi4_proto = flkeys->basic.ip_proto; - fl4->flowi4_tos = flkeys->ip.tos; + fl4->flowi4_tos = flkeys->ip.tos & ~INET_ECN_MASK; } #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ad01997c3aa9..912c1189ba41 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2017,6 +2017,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; @@ -3888,5 +3891,6 @@ static void __exit xfrm_user_exit(void) module_init(xfrm_user_init); module_exit(xfrm_user_exit); +MODULE_DESCRIPTION("XFRM User interface"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM); |