diff options
Diffstat (limited to '')
111 files changed, 1544 insertions, 3639 deletions
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 6a1db678d..a8932d449 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 56ecc5f97..452d839c1 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5282,9 +5282,12 @@ 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)) @@ -6716,6 +6719,10 @@ 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); @@ -7245,10 +7252,10 @@ 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 d74fe13f3..a33734046 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2251,8 +2251,11 @@ 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) @@ -3780,12 +3783,14 @@ static int hci_set_event_mask_sync(struct hci_dev *hdev) if (lmp_bredr_capable(hdev)) { events[4] |= 0x01; /* Flow Specification Complete */ - /* Don't set Disconnect Complete when suspended as that - * would wakeup the host when disconnecting due to - * suspend. + /* Don't set Disconnect Complete and mode change when + * suspended as that would wakeup the host when disconnecting + * due to suspend. */ - if (hdev->suspended) + if (hdev->suspended) { events[0] &= 0xef; + events[2] &= 0xf7; + } } else { /* Use a different default for LE-only devices */ memset(events, 0, sizeof(events)); @@ -5480,7 +5485,7 @@ 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 4c5793053..b4cba55be 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5614,7 +5614,13 @@ 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 @@ -6527,7 +6533,8 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (len > skb->len || !cmd->ident) { BT_DBG("corrupted command"); l2cap_sig_send_rej(conn, cmd->ident); - break; + skb_pull(skb, len > skb->len ? skb->len : len); + continue; } err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data); diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c index 5c4c369f8..2faab4465 100644 --- a/net/bridge/br_cfm_netlink.c +++ b/net/bridge/br_cfm_netlink.c @@ -362,7 +362,7 @@ static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr, memset(&tx_info, 0, sizeof(tx_info)); - instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]); nla_memcpy(&tx_info.dmac.addr, tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC], sizeof(tx_info.dmac.addr)); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index db4f2641d..9765f9f9b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1607,6 +1607,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t) } #endif +static void br_multicast_query_delay_expired(struct timer_list *t) +{ +} + static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, struct br_ip *ip, struct sk_buff *skb) @@ -3024,7 +3028,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, unsigned long max_delay) { if (!timer_pending(&query->timer)) - query->delay_time = jiffies + max_delay; + mod_timer(&query->delay_timer, jiffies + max_delay); mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); } @@ -3867,13 +3871,11 @@ void br_multicast_ctx_init(struct net_bridge *br, brmctx->multicast_querier_interval = 255 * HZ; brmctx->multicast_membership_interval = 260 * HZ; - brmctx->ip4_other_query.delay_time = 0; brmctx->ip4_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; - brmctx->ip6_other_query.delay_time = 0; brmctx->ip6_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif @@ -3882,6 +3884,8 @@ void br_multicast_ctx_init(struct net_bridge *br, br_ip4_multicast_local_router_expired, 0); timer_setup(&brmctx->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); + timer_setup(&brmctx->ip4_other_query.delay_timer, + br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) @@ -3889,6 +3893,8 @@ void br_multicast_ctx_init(struct net_bridge *br, br_ip6_multicast_local_router_expired, 0); timer_setup(&brmctx->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); + timer_setup(&brmctx->ip6_other_query.delay_timer, + br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip6_own_query.timer, br_ip6_multicast_query_expired, 0); #endif @@ -4023,10 +4029,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx) { del_timer_sync(&brmctx->ip4_mc_router_timer); del_timer_sync(&brmctx->ip4_other_query.timer); + del_timer_sync(&brmctx->ip4_other_query.delay_timer); del_timer_sync(&brmctx->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) del_timer_sync(&brmctx->ip6_mc_router_timer); del_timer_sync(&brmctx->ip6_other_query.timer); + del_timer_sync(&brmctx->ip6_other_query.delay_timer); del_timer_sync(&brmctx->ip6_own_query.timer); #endif } @@ -4469,13 +4477,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) max_delay = brmctx->multicast_query_response_interval; if (!timer_pending(&brmctx->ip4_other_query.timer)) - brmctx->ip4_other_query.delay_time = jiffies + max_delay; + mod_timer(&brmctx->ip4_other_query.delay_timer, + jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) if (!timer_pending(&brmctx->ip6_other_query.timer)) - brmctx->ip6_other_query.delay_time = jiffies + max_delay; + mod_timer(&brmctx->ip6_other_query.delay_timer, + jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); #endif diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 202ad43e3..bff48d576 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) @@ -962,6 +1050,14 @@ 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_ip, .pf = NFPROTO_BRIDGE, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06e5f6faa..51d010f64 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -77,7 +77,7 @@ struct bridge_mcast_own_query { /* other querier */ struct bridge_mcast_other_query { struct timer_list timer; - unsigned long delay_time; + struct timer_list delay_timer; }; /* selected querier */ @@ -1083,7 +1083,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx, own_querier_enabled = false; } - return time_is_before_jiffies(querier->delay_time) && + return !timer_pending(&querier->delay_timer) && (own_querier_enabled || timer_pending(&querier->timer)); } diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 4b3982c36..b61ef2dff 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -593,21 +593,40 @@ 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; } @@ -675,51 +694,50 @@ 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, @@ -780,6 +798,16 @@ 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 06d94b2c6..c7c27ada6 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) { @@ -416,6 +440,12 @@ 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 16af1a7f8..31a93cae5 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 ecff1c947..a6fb89fa6 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 b0be23559..58909b365 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/core/dev.c b/net/core/dev.c index 1ba3662fa..60619fe8a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8861,7 +8861,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 7674bb9f3..5cdbfbf9a 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -342,7 +342,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/core/filter.c b/net/core/filter.c index 3a6110ea4..cb7c4651e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5752,6 +5752,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; + if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5803,6 +5809,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) + params->ipv4_src = fib_result_prefsrc(net, &res); + /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ @@ -5885,6 +5894,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; + if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5939,6 +5954,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) { + if (res.f6i->fib6_prefsrc.plen) { + *src = res.f6i->fib6_prefsrc.addr; + } else { + err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, + &fl6.daddr, 0, + src); + if (err) + return BPF_FIB_LKUP_RET_NO_SRC_ADDR; + } + } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; @@ -5957,7 +5984,8 @@ set_fwd_params: #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ - BPF_FIB_LOOKUP_SKIP_NEIGH) + BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ + BPF_FIB_LOOKUP_SRC) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7cf1e42d7..ac379e459 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5026,10 +5026,9 @@ 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; @@ -5047,11 +5046,11 @@ 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); } @@ -5095,8 +5094,8 @@ 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/skbuff.c b/net/core/skbuff.c index 8a819d0a7..d4bd10f87 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4213,8 +4213,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 3818035ea..39643f78c 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1217,8 +1217,11 @@ 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/hsr/hsr_device.c b/net/hsr/hsr_device.c index b1e86a726..83906d093 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -291,7 +291,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -338,7 +338,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 80cdc6f6b..0323ab502 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); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2f646335d..9408dc3bb 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1637,10 +1637,12 @@ 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/arp.c b/net/ipv4/arp.c index 9456f5bb3..ccff96820 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, (unsigned char)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 35d6e74be..bb0d1252c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1804,6 +1804,21 @@ 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; @@ -1855,8 +1870,7 @@ 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; @@ -2257,8 +2271,7 @@ 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/inet_hashtables.c b/net/ipv4/inet_hashtables.c index f2ed2aed0..56776e1b1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1111,10 +1111,33 @@ 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_output.c b/net/ipv4/ip_output.c index e19ef88ae..a6d460aae 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1268,6 +1268,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(!rt)) return -EFAULT; + cork->fragsize = ip_sk_use_pmtu(sk) ? + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + /* * setup for corking. */ @@ -1284,12 +1290,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); - - if (!inetdev_valid_mtu(cork->fragsize)) - return -ENETUNREACH; - cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index c1fb7580e..a00ba2d51 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1406,12 +1406,13 @@ e_inval: * ipv4_pktinfo_prepare - transfer some info from rtable to skb * @sk: socket * @skb: buffer + * @drop_dst: if true, drops skb dst * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. * This way, receiver doesn't make cache line misses to read rtable. */ -void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) +void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || @@ -1440,7 +1441,8 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - skb_dst_drop(skb); + if (drop_dst) + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 24961b304..328f9068c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -540,6 +540,20 @@ 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) { @@ -614,13 +628,13 @@ 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; @@ -800,16 +814,16 @@ 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.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; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 586b1b3e3..80ccd6661 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/ipmr.c b/net/ipv4/ipmr.c index b80719747..d5421c38c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt, msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; - ipv4_pktinfo_prepare(mroute_sk, pkt); + ipv4_pktinfo_prepare(mroute_sk, pkt, false); memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 407376299..fc761915c 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -279,6 +279,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, goto free_nskb; nf_ct_attach(nskb, oldskb); + nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 639aa5abd..7c63b91ed 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -286,11 +286,13 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + /* Charge it to the socket. */ - ipv4_pktinfo_prepare(sk, skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + ipv4_pktinfo_prepare(sk, skb, true); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -301,7 +303,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 90e24c3f6..86e7695d9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1934,7 +1934,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, static bool can_map_frag(const skb_frag_t *frag) { - return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag); + struct page *page; + + if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) + return false; + + page = skb_frag_page(frag); + + if (PageCompound(page) || page->mapping) + return false; + + return true; } static int find_next_mappable_frag(const skb_frag_t *frag, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 11c0e1c66..87d759bab 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2196,7 +2196,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_csum_pull_header(skb); - ipv4_pktinfo_prepare(sk, skb); + ipv4_pktinfo_prepare(sk, skb, true); return __udp_queue_rcv_skb(sk, skb); csum_error: diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b8dc20fe7..164837369 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -706,6 +706,22 @@ 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) { @@ -739,8 +755,7 @@ 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; @@ -5326,7 +5341,7 @@ 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]; @@ -5458,9 +5473,10 @@ 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/addrconf_core.c b/net/ipv6/addrconf_core.c index 507a8353a..c008d2192 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) + = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) + = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0b42eb8c5..62247621c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1077,6 +1077,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { .udp6_lib_lookup = __udp6_lib_lookup, .ipv6_setsockopt = do_ipv6_setsockopt, .ipv6_getsockopt = do_ipv6_getsockopt, + .ipv6_dev_get_saddr = ipv6_dev_get_saddr, }; static int __init inet6_init(void) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5fa0e3730..1cfdd9d95 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -180,6 +180,8 @@ 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)) @@ -974,6 +976,14 @@ 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_tunnel.c b/net/ipv6/ip6_tunnel.c index 9125e92d9..2699915bb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - int err; + const struct ipv6hdr *ipv6h; + int nh, err; if ((!(tpi->flags & TUNNEL_CSUM) && (tunnel->parms.i_flags & TUNNEL_CSUM)) || @@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, goto drop; } - ipv6h = ipv6_hdr(skb); skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { @@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_reset_mac_header(skb); } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + ipv6h = (struct ipv6hdr *)(skb->head + nh); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 433d98bbe..71d692728 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -344,6 +344,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen); nf_ct_attach(nskb, oldskb); + nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip6_local_out for bridged traffic, the MAC source on diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7f65dc750..887599d35 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5335,19 +5335,7 @@ 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, @@ -5355,6 +5343,12 @@ 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, @@ -5415,8 +5409,7 @@ 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 29346a6ee..35508abd7 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/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 314ec3a51..bb92dc8b8 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -630,7 +630,7 @@ 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/llc/af_llc.c b/net/llc/af_llc.c index 19c478bd8..8e3be0009 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock) } netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); + sock_orphan(sk); + sock->sk = NULL; llc_sk_free(sk); out: return 0; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index a2c486608..6cf0b7783 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1775,6 +1775,8 @@ 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/mlme.c b/net/mac80211/mlme.c index c07645c99..f25dc6931 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7221,8 +7221,7 @@ 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? @@ -7295,6 +7294,7 @@ 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/sta_info.c b/net/mac80211/sta_info.c index f3d6c3e4c..bd56015b2 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -891,6 +891,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); + ieee80211_check_fast_xmit(sta); + return 0; out_remove: if (sta->sta.valid_links) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2db103a56..3d62e8b71 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. */ @@ -3044,7 +3044,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) sdata->vif.type == NL80211_IFTYPE_STATION) goto out; - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded) goto out; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -3838,6 +3838,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3882,7 +3883,7 @@ 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/mctp/route.c b/net/mctp/route.c index 68be8f2b6..0144d8ebd 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 a53658674..7017dd606 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/pm_netlink.c b/net/mptcp/pm_netlink.c index 980050f6b..3328870b0 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -407,23 +407,12 @@ 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. */ -static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh, +static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, + struct mptcp_addr_info *local, + bool fullmesh, struct mptcp_addr_info *addrs) { bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); @@ -446,15 +435,28 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm 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 (!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++; } @@ -603,7 +605,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); msk->pm.local_addr_used++; - nr = fill_remote_addresses_vec(msk, fullmesh, addrs); + nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); if (nr) __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); spin_unlock_bh(&msk->pm.lock); @@ -798,18 +800,18 @@ 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); @@ -900,7 +902,8 @@ 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; @@ -942,7 +945,7 @@ 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, @@ -953,7 +956,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1095,7 +1098,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *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); @@ -1311,6 +1314,18 @@ 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_addr_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -1352,7 +1367,8 @@ static int mptcp_nl_cmd_add_addr(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(info, "too many addresses or duplicate one"); goto out_free; @@ -2014,7 +2030,7 @@ 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 38cbdc66d..414ed70e7 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -25,8 +25,9 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } } -int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) +static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, + 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 @@ 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 @@ 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); @@ -132,10 +133,21 @@ 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; @@ -144,7 +156,7 @@ 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_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) @@ -186,7 +198,7 @@ int mptcp_nl_cmd_announce(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; @@ -210,6 +222,40 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } +static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, + struct genl_info *info) +{ + struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + bool has_id_0 = false; + int err = -EINVAL; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + if (READ_ONCE(subflow->local_id) == 0) { + has_id_0 = true; + break; + } + } + if (!has_id_0) { + GENL_SET_ERR_MSG(info, "address with id 0 not found"); + goto remove_err; + } + + list.ids[list.nr++] = 0; + + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &list); + spin_unlock_bh(&msk->pm.lock); + + err = 0; + +remove_err: + release_sock(sk); + return err; +} + int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -241,6 +287,11 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) goto remove_err; } + if (id_val == 0) { + err = mptcp_userspace_pm_remove_id_zero_address(msk, info); + goto remove_err; + } + lock_sock((struct sock *)msk); list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { @@ -324,7 +375,7 @@ int mptcp_nl_cmd_sf_create(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; @@ -438,6 +489,16 @@ int mptcp_nl_cmd_sf_destroy(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 76539d100..3bc215814 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -119,7 +119,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->request_mptcp = 1; /* 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); return 0; @@ -1319,6 +1319,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, mpext = skb_ext_find(skb, SKB_EXT_MPTCP); 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; } @@ -1582,8 +1583,11 @@ 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); + } } void __mptcp_push_pending(struct sock *sk, unsigned int flags) @@ -2336,9 +2340,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) if (__mptcp_check_fallback(mptcp_sk(sk))) return false; - if (tcp_rtx_and_write_queues_empty(sk)) - return false; - /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue @@ -2422,7 +2423,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out_release; } - dispose_it = !msk->subflow || ssk != msk->subflow->sk; + dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); @@ -2440,7 +2441,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); - msk->subflow->state = SS_UNCONNECTED; + if (msk->subflow && ssk == msk->subflow->sk) + msk->subflow->state = SS_UNCONNECTED; release_sock(ssk); goto out; @@ -3144,7 +3146,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->last_snd = NULL; WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; - msk->push_pending = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; @@ -3168,8 +3169,50 @@ 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, @@ -3190,6 +3233,13 @@ 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; @@ -3202,7 +3252,7 @@ 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; if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) { @@ -3341,10 +3391,10 @@ static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - /* clears msk->subflow, allowing the following to close - * even the initial subflow - */ mptcp_dispose_initial_subflow(msk); + + /* allow the following to close even the initial subflow */ + msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } @@ -3388,8 +3438,7 @@ 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) @@ -3405,7 +3454,6 @@ 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); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4ec8e0a81..2bc37773e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -272,7 +272,6 @@ 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; @@ -287,7 +286,8 @@ struct mptcp_sock { cork:1, nodelay:1, fastopening:1, - in_accept_queue:1; + in_accept_queue:1, + free_first:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -475,7 +475,6 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ 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 */ enum mptcp_data_avail data_avail; u32 remote_nonce; @@ -483,7 +482,7 @@ struct mptcp_subflow_context { u32 local_nonce; u32 remote_token; u8 hmac[MPTCPOPT_HMAC_LEN]; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -529,6 +528,7 @@ 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 @@ -834,8 +834,6 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); -int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry); void mptcp_free_local_addr_list(struct mptcp_sock *msk); int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); @@ -911,6 +909,15 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *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, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 45d20e20c..891c2f4fe 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -446,7 +446,7 @@ 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); @@ -489,8 +489,8 @@ 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) @@ -499,7 +499,7 @@ 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); @@ -1477,7 +1477,7 @@ 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); mptcp_info2sockaddr(remote, &addr, ssk->sk_family); @@ -1630,6 +1630,7 @@ 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; } @@ -1867,13 +1868,13 @@ 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->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/core.c b/net/netfilter/core.c index 55a7f72d5..edf920742 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -707,6 +707,22 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) } EXPORT_SYMBOL(nf_conntrack_destroy); +void nf_ct_set_closing(struct nf_conntrack *nfct) +{ + const struct nf_ct_hook *ct_hook; + + if (!nfct) + return; + + rcu_read_lock(); + ct_hook = rcu_dereference(nf_ct_hook); + if (ct_hook) + ct_hook->set_closing(nfct); + + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(nf_ct_set_closing); + bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e961..9523104a9 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -28,6 +28,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index d47dfdcb8..f645da82d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1156,6 +1156,7 @@ 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); @@ -1184,6 +1185,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const attr[]) { @@ -1195,8 +1204,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1208,8 +1215,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1223,6 +1232,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } @@ -1230,6 +1241,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, inst->is_destroyed = false; } else { u32 flags = flag_exist(info->nlh); + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1240,10 +1254,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1396,9 +1416,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2364,6 +2381,7 @@ 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); } } @@ -2411,8 +2429,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7499192af..ef04e556a 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -210,6 +210,7 @@ htable_size(u8 hbits) #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -254,6 +255,7 @@ htable_size(u8 hbits) #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -417,7 +419,7 @@ 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) @@ -437,10 +439,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - - 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); @@ -586,6 +585,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1416,6 +1424,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a67f7966..6bc701998 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 796026296..024f93fc8 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2772,11 +2772,24 @@ err_cachep: return ret; } +static void nf_conntrack_set_closing(struct nf_conntrack *nfct) +{ + struct nf_conn *ct = nf_ct_to_nf_conn(nfct); + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + nf_conntrack_tcp_set_closing(ct); + break; + } +} + static const struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, .destroy = nf_ct_destroy, .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 e697a824b..540d97715 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_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c94a9971d..7ffd69849 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -299,7 +299,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; - } else { + } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3ac1af6f5..9480e638e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, const struct sk_buff *skb, unsigned int dataoff, const struct tcphdr *tcph, - u32 end, u32 win) + u32 end, u32 win, + enum ip_conntrack_dir dir) { /* SYN-ACK in reply to a SYN * or SYN from reply direction in simultaneous open. @@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender, * Both sides must send the Window Scale option * to enable window scaling in either direction. */ - if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && + if (dir == IP_CT_DIR_REPLY && + !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) { sender->td_scale = 0; receiver->td_scale = 0; @@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, if (tcph->syn) { tcp_init_sender(sender, receiver, skb, dataoff, tcph, - end, win); + end, win, dir); if (!tcph->ack) /* Simultaneous open */ return NFCT_TCP_ACCEPT; @@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, */ tcp_init_sender(sender, receiver, skb, dataoff, tcph, - end, win); + end, win, dir); if (dir == IP_CT_DIR_REPLY && !tcph->ack) return NFCT_TCP_ACCEPT; @@ -911,6 +913,41 @@ static bool tcp_can_early_drop(const struct nf_conn *ct) return false; } +void nf_conntrack_tcp_set_closing(struct nf_conn *ct) +{ + enum tcp_conntrack old_state; + const unsigned int *timeouts; + u32 timeout; + + if (!nf_ct_is_confirmed(ct)) + return; + + spin_lock_bh(&ct->lock); + old_state = ct->proto.tcp.state; + ct->proto.tcp.state = TCP_CONNTRACK_CLOSE; + + if (old_state == TCP_CONNTRACK_CLOSE || + test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) { + spin_unlock_bh(&ct->lock); + return; + } + + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) { + const struct nf_tcp_net *tn; + + tn = nf_tcp_pernet(nf_ct_net(ct)); + timeouts = tn->timeouts; + } + + timeout = timeouts[TCP_CONNTRACK_CLOSE]; + WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); + + spin_unlock_bh(&ct->lock); + + nf_conntrack_event_cache(IPCT_PROTOINFO, ct); +} + static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state) { state->td_end = 0; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index c1d99cb37..99195cf6b 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) { @@ -122,12 +132,10 @@ 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: - if (!dst_hold_safe(route->tuple[dir].dst)) - return -1; - flow_tuple->dst_cache = dst; flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); break; @@ -148,27 +156,12 @@ static void nft_flow_dst_release(struct flow_offload *flow, dst_release(flow->tuplehash[dir].tuple.dst_cache); } -int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) +void flow_offload_route_init(struct flow_offload *flow, + struct nf_flow_route *route) { - int err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); - if (err < 0) - return err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); - if (err < 0) - goto err_route_reply; - + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); flow->type = NF_FLOW_OFFLOAD_ROUTE; - - return 0; - -err_route_reply: - nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); - - return err; } EXPORT_SYMBOL_GPL(flow_offload_route_init); diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 8a2929014..be93a0249 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -193,11 +193,12 @@ void nf_logger_put(int pf, enum nf_log_type type) return; } - BUG_ON(loggers[pf][type] == NULL); - rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); - module_put(logger->me); + if (!logger) + WARN_ON_ONCE(1); + else + module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1edb21382..d3ba947f4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -686,15 +686,16 @@ 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); @@ -703,22 +704,22 @@ 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) @@ -1245,6 +1246,7 @@ 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; } @@ -2057,7 +2059,7 @@ 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; @@ -2458,19 +2460,15 @@ 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; @@ -2478,17 +2476,22 @@ 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); @@ -4749,6 +4752,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; @@ -4757,6 +4763,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } @@ -7129,11 +7139,15 @@ nla_put_failure: return -1; } -static const struct nft_object_type *__nft_obj_type_get(u32 objtype) +static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; list_for_each_entry(type, &nf_tables_objects, list) { + if (type->family != NFPROTO_UNSPEC && + type->family != family) + continue; + if (objtype == type->type) return type; } @@ -7141,11 +7155,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype) } static const struct nft_object_type * -nft_obj_type_get(struct net *net, u32 objtype) +nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; - type = __nft_obj_type_get(objtype); + type = __nft_obj_type_get(objtype, family); if (type != NULL && try_module_get(type->owner)) return type; @@ -7238,7 +7252,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = __nft_obj_type_get(objtype); + type = __nft_obj_type_get(objtype, family); if (WARN_ON_ONCE(!type)) return -ENOENT; @@ -7252,7 +7266,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (!nft_use_inc(&table->use)) return -EMFILE; - type = nft_obj_type_get(net, objtype); + type = nft_obj_type_get(net, objtype, family); if (IS_ERR(type)) { err = PTR_ERR(type); goto err_type; @@ -7933,7 +7947,7 @@ err_unregister_net_hooks: return err; } -static void nft_flowtable_hooks_destroy(struct list_head *hook_list) +static void nft_hooks_destroy(struct list_head *hook_list) { struct nft_hook *hook, *next; @@ -8026,9 +8040,9 @@ 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; @@ -8108,34 +8122,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb, err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], &flowtable_hook, flowtable, 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_flowtable_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); @@ -8888,7 +8902,7 @@ static void nft_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; @@ -9845,7 +9859,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) - nft_flowtable_hooks_destroy(&nft_trans_flowtable_hooks(trans)); + nft_hooks_destroy(&nft_trans_flowtable_hooks(trans)); else nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); break; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6952da7df..e4b8c02c5 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; } @@ -351,10 +358,20 @@ 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); @@ -418,7 +435,7 @@ 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 }, }; @@ -600,10 +617,20 @@ 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); @@ -721,7 +748,7 @@ 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 641dc21f9..2bfe3cdfb 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -484,6 +484,9 @@ 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: @@ -1231,7 +1234,30 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_EXPECT_L3PROTO]) priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO])); + switch (priv->l3num) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; + + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ + default: + return -EAFNOSUPPORT; + } + priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); + switch (priv->l4proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + case IPPROTO_DCCP: + case IPPROTO_SCTP: + break; + default: + return -EOPNOTSUPP; + } + priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]); priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]); priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3d9f6dda5..7a8707632 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -250,9 +250,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, break; } + if (!dst_hold_safe(this_dst)) + return -ENOENT; + nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); - if (!other_dst) + if (!other_dst) { + dst_release(this_dst); return -ENOENT; + } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); @@ -349,8 +354,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (!flow) goto err_flow_alloc; - if (flow_offload_route_init(flow, &route) < 0) - goto err_flow_add; + flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; @@ -361,12 +365,12 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (ret < 0) goto err_flow_add; - dst_release(route.tuple[!dir].dst); return; err_flow_add: flow_offload_free(flow); err_flow_alloc: + dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 4e1cc3172..e1969209b 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; @@ -1102,6 +1102,25 @@ 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 @@ -1114,12 +1133,13 @@ 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) { @@ -1133,14 +1153,25 @@ 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; @@ -1294,11 +1325,6 @@ 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; @@ -1350,10 +1376,7 @@ 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); @@ -1638,13 +1661,9 @@ 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); @@ -2132,7 +2151,7 @@ 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 +2159,6 @@ 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 +2189,6 @@ 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 +2242,8 @@ 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 +2256,8 @@ 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 25a755915..30a3d092c 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 * @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 * @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[]; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 52e0d026d..a3a8ddca9 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 e34662f4a..5bf5572e9 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -235,7 +235,7 @@ static void nft_rbtree_gc_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); @@ -254,7 +254,7 @@ 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); @@ -365,7 +365,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, 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); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 983ade4be..efb505445 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = { static struct nft_object_type nft_tunnel_obj_type __read_mostly = { .type = NFT_OBJECT_TUNNEL, + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_obj_ops, .maxattr = NFTA_TUNNEL_KEY_MAX, .policy = nft_tunnel_key_policy, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6857a4965..e9b81cba1 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 ec5747969..f0879295d 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 3aaac4a22..2c34389c3 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 2f084b6f6..97944db6b 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 44929657f..5e531394a 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 baea3cbd7..70480869a 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 e2d2af924..c3bbd5880 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/nfc/nci/core.c b/net/nfc/nci/core.c index 7535afd15..b5071a2f5 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1207,6 +1207,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ead5418c1..e3c85ceb1 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,6 +47,7 @@ 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) { @@ -2543,13 +2544,15 @@ 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; @@ -2600,7 +2603,8 @@ 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; @@ -2615,7 +2619,8 @@ 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; @@ -2658,7 +2663,8 @@ 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; @@ -2672,7 +2678,8 @@ 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; @@ -2692,7 +2699,8 @@ 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; @@ -3061,7 +3069,7 @@ 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]; @@ -3109,7 +3117,8 @@ 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; @@ -3122,7 +3131,8 @@ 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; @@ -3150,12 +3160,16 @@ 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] = { @@ -3350,7 +3364,7 @@ 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; @@ -3421,7 +3435,7 @@ 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; @@ -3435,7 +3449,8 @@ 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; @@ -3445,7 +3460,8 @@ 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; @@ -3485,7 +3501,8 @@ 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/packet/af_packet.c b/net/packet/af_packet.c index 51882f07e..c3117350f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3284,7 +3284,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3295,8 +3295,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); + name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } @@ -3566,11 +3566,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index ff5f49ab2..39a6c5713 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -35,10 +35,10 @@ static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCINQ: - lock_sock(sk); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); answ = skb ? skb->len : 0; - release_sock(sk); + spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(answ, (int __user *)arg); case SIOCPNADDRESOURCE: diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 83ea13a50..607f54c23 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, unsigned long arg) { struct pep_sock *pn = pep_sk(sk); @@ -930,15 +961,7 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) break; } - lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) && - !skb_queue_empty(&pn->ctrlreq_queue)) - answ = skb_peek(&pn->ctrlreq_queue)->len; - else if (!skb_queue_empty(&sk->sk_receive_queue)) - answ = skb_peek(&sk->sk_receive_queue)->len; - else - answ = 0; - release_sock(sk); + answ = pep_first_packet_length(sk); ret = put_user(answ, (int __user *)arg); break; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index fba82d365..a4e3c5de9 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/send.c b/net/rds/send.c index 0c5504068..a4ba45c43 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1314,12 +1314,8 @@ 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/conn_event.c b/net/rxrpc/conn_event.c index aab069701..5d91ef562 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -41,6 +41,14 @@ static 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 diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 6e6aa02c6..249353417 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -31,7 +31,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rb_node *p; - unsigned int seq = 0; + unsigned int seq = 1; k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; @@ -41,6 +41,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&peer->service_conn_lock, &seq); p = rcu_dereference_raw(peer->service_conns.rb_node); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 24cf0bf7c..9c4a80fce 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -45,23 +45,6 @@ if NET_SCHED comment "Queueing/Scheduling" -config NET_SCH_CBQ - tristate "Class Based Queueing (CBQ)" - help - Say Y here if you want to use the Class-Based Queueing (CBQ) packet - scheduling algorithm. This algorithm classifies the waiting packets - into a tree-like hierarchy of classes; the leaves of this tree are - in turn scheduled by separate algorithms. - - See the top of <file:net/sched/sch_cbq.c> for more details. - - CBQ is a commonly used scheduler, so if you're unsure, you should - say Y here. Then say Y to all the queueing algorithms below that you - want to use as leaf disciplines. - - To compile this code as a module, choose M here: the - module will be called sch_cbq. - config NET_SCH_HTB tristate "Hierarchical Token Bucket (HTB)" help @@ -85,20 +68,6 @@ config NET_SCH_HFSC To compile this code as a module, choose M here: the module will be called sch_hfsc. -config NET_SCH_ATM - tristate "ATM Virtual Circuits (ATM)" - depends on ATM - help - Say Y here if you want to use the ATM pseudo-scheduler. This - provides a framework for invoking classifiers, which in turn - select classes of this queuing discipline. Each class maps - the flow(s) it is handling to a given virtual circuit. - - See the top of <file:net/sched/sch_atm.c> for more details. - - To compile this code as a module, choose M here: the - module will be called sch_atm. - config NET_SCH_PRIO tristate "Multi Band Priority Queueing (PRIO)" help @@ -217,17 +186,6 @@ config NET_SCH_GRED To compile this code as a module, choose M here: the module will be called sch_gred. -config NET_SCH_DSMARK - tristate "Differentiated Services marker (DSMARK)" - help - Say Y if you want to schedule packets according to the - Differentiated Services architecture proposed in RFC 2475. - Technical information on this method, with pointers to associated - RFCs, is available at <http://www.gta.ufrj.br/diffserv/>. - - To compile this code as a module, choose M here: the - module will be called sch_dsmark. - config NET_SCH_NETEM tristate "Network emulator (NETEM)" help diff --git a/net/sched/Makefile b/net/sched/Makefile index 8a33a35fc..a66ac1e7b 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -33,20 +33,17 @@ obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_ACT_CT) += act_ct.o obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o -obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o -obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o -obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c deleted file mode 100644 index 4a981ca90..000000000 --- a/net/sched/sch_atm.c +++ /dev/null @@ -1,706 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_atm.c - ATM VC selection "queueing discipline" */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/atmdev.h> -#include <linux/atmclip.h> -#include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - -/* - * The ATM queuing discipline provides a framework for invoking classifiers - * (aka "filters"), which in turn select classes of this queuing discipline. - * Each class maps the flow(s) it is handling to a given VC. Multiple classes - * may share the same VC. - * - * When creating a class, VCs are specified by passing the number of the open - * socket descriptor by which the calling process references the VC. The kernel - * keeps the VC open at least until all classes using it are removed. - * - * In this file, most functions are named atm_tc_* to avoid confusion with all - * the atm_* in net/atm. This naming convention differs from what's used in the - * rest of net/sched. - * - * Known bugs: - * - sometimes messes up the IP stack - * - any manipulations besides the few operations described in the README, are - * untested and likely to crash the system - * - should lock the flow while there is data in the queue (?) - */ - -#define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - -struct atm_flow_data { - struct Qdisc_class_common common; - struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc, - struct sk_buff *skb); /* chaining */ - struct atm_qdisc_data *parent; /* parent qdisc */ - struct socket *sock; /* for closing */ - int ref; /* reference count */ - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - struct list_head list; - struct atm_flow_data *excess; /* flow for excess traffic; - NULL to set CLP instead */ - int hdr_len; - unsigned char hdr[]; /* header data; MUST BE LAST */ -}; - -struct atm_qdisc_data { - struct atm_flow_data link; /* unclassified skbs go here */ - struct list_head flows; /* NB: "link" is also on this - list */ - struct tasklet_struct task; /* dequeue tasklet */ -}; - -/* ------------------------- Class/flow operations ------------------------- */ - -static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - list_for_each_entry(flow, &p->flows, list) { - if (flow->common.classid == classid) - return flow; - } - return NULL; -} - -static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", - sch, p, flow, new, old); - if (list_empty(&flow->list)) - return -EINVAL; - if (!new) - new = &noop_qdisc; - *old = flow->q; - flow->q = new; - if (*old) - qdisc_reset(*old); - return 0; -} - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); - return flow ? flow->q : NULL; -} - -static unsigned long atm_tc_find(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - if (flow) - flow->ref++; - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -/* - * atm_tc_put handles all destructions, including the ones that are explicitly - * requested (atm_tc_destroy, etc.). The assumption here is that we never drop - * anything that still seems to be in use. - */ -static void atm_tc_put(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (--flow->ref) - return; - pr_debug("atm_tc_put: destroying\n"); - list_del_init(&flow->list); - pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_put(flow->q); - tcf_block_put(flow->block); - if (flow->sock) { - pr_debug("atm_tc_put: f_count %ld\n", - file_count(flow->sock->file)); - flow->vcc->pop = flow->old_pop; - sockfd_put(flow->sock); - } - if (flow->excess) - atm_tc_put(sch, (unsigned long)flow->excess); - if (flow != &p->link) - kfree(flow); - /* - * If flow == &p->link, the qdisc no longer works at this point and - * needs to be removed. (By the caller of atm_tc_put.) - */ -} - -static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) -{ - struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - - pr_debug("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); - VCC2FLOW(vcc)->old_pop(vcc, skb); - tasklet_schedule(&p->task); -} - -static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ - 0x00, 0x00, - 0x08, 0x00 -}; /* Ethertype IP (0800) */ - -static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { - [TCA_ATM_FD] = { .type = NLA_U32 }, - [TCA_ATM_EXCESS] = { .type = NLA_U32 }, -}; - -static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)*arg; - struct atm_flow_data *excess = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_ATM_MAX + 1]; - struct socket *sock; - int fd, error, hdr_len; - void *hdr; - - pr_debug("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); - /* - * The concept of parents doesn't apply for this qdisc. - */ - if (parent && parent != TC_H_ROOT && parent != sch->handle) - return -EINVAL; - /* - * ATM classes cannot be changed. In order to change properties of the - * ATM connection, that socket needs to be modified directly (via the - * native ATM API. In order to send a flow to a different VC, the old - * class needs to be removed and a new one added. (This may be changed - * later.) - */ - if (flow) - return -EBUSY; - if (opt == NULL) - return -EINVAL; - - error = nla_parse_nested_deprecated(tb, TCA_ATM_MAX, opt, atm_policy, - NULL); - if (error < 0) - return error; - - if (!tb[TCA_ATM_FD]) - return -EINVAL; - fd = nla_get_u32(tb[TCA_ATM_FD]); - pr_debug("atm_tc_change: fd %d\n", fd); - if (tb[TCA_ATM_HDR]) { - hdr_len = nla_len(tb[TCA_ATM_HDR]); - hdr = nla_data(tb[TCA_ATM_HDR]); - } else { - hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ - } - if (!tb[TCA_ATM_EXCESS]) - excess = NULL; - else { - excess = (struct atm_flow_data *) - atm_tc_find(sch, nla_get_u32(tb[TCA_ATM_EXCESS])); - if (!excess) - return -ENOENT; - } - pr_debug("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->nla_type, nla_len(opt), hdr_len); - sock = sockfd_lookup(fd, &error); - if (!sock) - return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); - if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { - error = -EPROTOTYPE; - goto err_out; - } - /* @@@ should check if the socket is really operational or we'll crash - on vcc->send */ - if (classid) { - if (TC_H_MAJ(classid ^ sch->handle)) { - pr_debug("atm_tc_change: classid mismatch\n"); - error = -EINVAL; - goto err_out; - } - } else { - int i; - unsigned long cl; - - for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle, 0x8000 | i); - cl = atm_tc_find(sch, classid); - if (!cl) - break; - } - } - pr_debug("atm_tc_change: new id %x\n", classid); - flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); - pr_debug("atm_tc_change: flow %p\n", flow); - if (!flow) { - error = -ENOBUFS; - goto err_out; - } - - error = tcf_block_get(&flow->block, &flow->filter_list, sch, - extack); - if (error) { - kfree(flow); - goto err_out; - } - - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - extack); - if (!flow->q) - flow->q = &noop_qdisc; - pr_debug("atm_tc_change: qdisc %p\n", flow->q); - flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ - flow->vcc->user_back = flow; - pr_debug("atm_tc_change: vcc %p\n", flow->vcc); - flow->old_pop = flow->vcc->pop; - flow->parent = p; - flow->vcc->pop = sch_atm_pop; - flow->common.classid = classid; - flow->ref = 1; - flow->excess = excess; - list_add(&flow->list, &p->link.list); - flow->hdr_len = hdr_len; - if (hdr) - memcpy(flow->hdr, hdr, hdr_len); - else - memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); - *arg = (unsigned long)flow; - return 0; -err_out: - sockfd_put(sock); - return error; -} - -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (list_empty(&flow->list)) - return -EINVAL; - if (rcu_access_pointer(flow->filter_list) || flow == &p->link) - return -EBUSY; - /* - * Reference count must be 2: one for "keepalive" (set at class - * creation), and one for the reference held when calling delete. - */ - if (flow->ref < 2) { - pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); - return -EINVAL; - } - if (flow->ref > 2) - return -EBUSY; /* catch references via excess, etc. */ - atm_tc_put(sch, arg); - return 0; -} - -static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); - if (walker->stop) - return; - list_for_each_entry(flow, &p->flows, list) { - if (!tc_qdisc_stats_dump(sch, (unsigned long)flow, walker)) - break; - } -} - -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? flow->block : p->link.block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct tcf_result res; - int result; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - - pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - result = TC_ACT_OK; /* be nice to gcc */ - flow = NULL; - if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *)atm_tc_find(sch, skb->priority))) { - struct tcf_proto *fl; - - list_for_each_entry(flow, &p->flows, list) { - fl = rcu_dereference_bh(flow->filter_list); - if (fl) { - result = tcf_classify(skb, NULL, fl, &res, true); - if (result < 0) - continue; - if (result == TC_ACT_SHOT) - goto done; - - flow = (struct atm_flow_data *)res.class; - if (!flow) - flow = lookup_flow(sch, res.classid); - goto drop; - } - } - flow = NULL; -done: - ; - } - if (!flow) { - flow = &p->link; - } else { - if (flow->vcc) - ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-) */ -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - __qdisc_drop(skb, to_free); - goto drop; - case TC_ACT_RECLASSIFY: - if (flow->excess) - flow = flow->excess; - else - ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; - break; - } -#endif - } - - ret = qdisc_enqueue(skb, flow->q, to_free); - if (ret != NET_XMIT_SUCCESS) { -drop: __maybe_unused - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - if (flow) - flow->qstats.drops++; - } - return ret; - } - /* - * Okay, this may seem weird. We pretend we've dropped the packet if - * it goes via ATM. The reason for this is that the outer qdisc - * expects to be able to q->dequeue the packet later on if we return - * success at this place. Also, sch->q.qdisc needs to reflect whether - * there is a packet egligible for dequeuing or not. Note that the - * statistics of the outer qdisc are necessarily wrong because of all - * this. There's currently no correct solution for this. - */ - if (flow == &p->link) { - sch->q.qlen++; - return NET_XMIT_SUCCESS; - } - tasklet_schedule(&p->task); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -/* - * Dequeue packets and send them over ATM. Note that we quite deliberately - * avoid checking net_device's flow control here, simply because sch_atm - * uses its own channels, which have nothing to do with any CLIP/LANE/or - * non-ATM interfaces. - */ - -static void sch_atm_dequeue(struct tasklet_struct *t) -{ - struct atm_qdisc_data *p = from_tasklet(p, t, task); - struct Qdisc *sch = qdisc_from_priv(p); - struct atm_flow_data *flow; - struct sk_buff *skb; - - pr_debug("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow == &p->link) - continue; - /* - * If traffic is properly shaped, this won't generate nasty - * little bursts. Otherwise, it may ... (but that's okay) - */ - while ((skb = flow->q->ops->peek(flow->q))) { - if (!atm_may_send(flow->vcc, skb->truesize)) - break; - - skb = qdisc_dequeue_peeked(flow->q); - if (unlikely(!skb)) - break; - - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); - pr_debug("atm_tc_dequeue: sending on class %p\n", flow); - /* remove any LL header somebody else has attached */ - skb_pull(skb, skb_network_offset(skb)); - if (skb_headroom(skb) < flow->hdr_len) { - struct sk_buff *new; - - new = skb_realloc_headroom(skb, flow->hdr_len); - dev_kfree_skb(skb); - if (!new) - continue; - skb = new; - } - pr_debug("sch_atm_dequeue: ip %p, data %p\n", - skb_network_header(skb), skb->data); - ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb, flow->hdr_len), flow->hdr, - flow->hdr_len); - refcount_add(skb->truesize, - &sk_atm(flow->vcc)->sk_wmem_alloc); - /* atm.atm_options are already set by atm_tc_enqueue */ - flow->vcc->send(flow->vcc, skb); - } - } -} - -static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - - pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); - tasklet_schedule(&p->task); - skb = qdisc_dequeue_peeked(p->link.q); - if (skb) - sch->q.qlen--; - return skb; -} - -static struct sk_buff *atm_tc_peek(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - - pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p); - - return p->link.q->ops->peek(p->link.q); -} - -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); - INIT_LIST_HEAD(&p->flows); - INIT_LIST_HEAD(&p->link.list); - gnet_stats_basic_sync_init(&p->link.bstats); - list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle, extack); - if (!p->link.q) - p->link.q = &noop_qdisc; - pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; - - err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, - extack); - if (err) - return err; - - tasklet_setup(&p->task, sch_atm_dequeue); - return 0; -} - -static void atm_tc_reset(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - qdisc_reset(flow->q); -} - -static void atm_tc_destroy(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow, *tmp; - - pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - tcf_block_put(flow->block); - flow->block = NULL; - } - - list_for_each_entry_safe(flow, tmp, &p->flows, list) { - if (flow->ref > 1) - pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); - atm_tc_put(sch, (unsigned long)flow); - } - tasklet_kill(&p->task); -} - -static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - struct nlattr *nest; - - pr_debug("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch, p, flow, skb, tcm); - if (list_empty(&flow->list)) - return -EINVAL; - tcm->tcm_handle = flow->common.classid; - tcm->tcm_info = flow->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) - goto nla_put_failure; - if (flow->vcc) { - struct sockaddr_atmpvc pvc; - int state; - - memset(&pvc, 0, sizeof(pvc)); - pvc.sap_family = AF_ATMPVC; - pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; - pvc.sap_addr.vpi = flow->vcc->vpi; - pvc.sap_addr.vci = flow->vcc->vci; - if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) - goto nla_put_failure; - state = ATM_VF2VS(flow->vcc->flags); - if (nla_put_u32(skb, TCA_ATM_STATE, state)) - goto nla_put_failure; - } - if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->common.classid)) - goto nla_put_failure; - } else { - if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) - goto nla_put_failure; - } - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} -static int -atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - if (gnet_stats_copy_basic(d, NULL, &flow->bstats, true) < 0 || - gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) - return -1; - - return 0; -} - -static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - return 0; -} - -static const struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .find = atm_tc_find, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_block = atm_tc_tcf_block, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, -}; - -static struct Qdisc_ops atm_qdisc_ops __read_mostly = { - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .peek = atm_tc_peek, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .dump = atm_tc_dump, - .owner = THIS_MODULE, -}; - -static int __init atm_init(void) -{ - return register_qdisc(&atm_qdisc_ops); -} - -static void __exit atm_exit(void) -{ - unregister_qdisc(&atm_qdisc_ops); -} - -module_init(atm_init) -module_exit(atm_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c deleted file mode 100644 index 36db5f678..000000000 --- a/net/sched/sch_cbq.c +++ /dev/null @@ -1,1727 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/sch_cbq.c Class-Based Queueing discipline. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - - -/* Class-Based Queueing (CBQ) algorithm. - ======================================= - - Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource - Management Models for Packet Networks", - IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995 - - [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995 - - [3] Sally Floyd, "Notes on Class-Based Queueing: Setting - Parameters", 1996 - - [4] Sally Floyd and Michael Speer, "Experimental Results - for Class-Based Queueing", 1998, not published. - - ----------------------------------------------------------------------- - - Algorithm skeleton was taken from NS simulator cbq.cc. - If someone wants to check this code against the LBL version, - he should take into account that ONLY the skeleton was borrowed, - the implementation is different. Particularly: - - --- The WRR algorithm is different. Our version looks more - reasonable (I hope) and works when quanta are allowed to be - less than MTU, which is always the case when real time classes - have small rates. Note, that the statement of [3] is - incomplete, delay may actually be estimated even if class - per-round allotment is less than MTU. Namely, if per-round - allotment is W*r_i, and r_1+...+r_k = r < 1 - - delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B - - In the worst case we have IntServ estimate with D = W*r+k*MTU - and C = MTU*r. The proof (if correct at all) is trivial. - - - --- It seems that cbq-2.0 is not very accurate. At least, I cannot - interpret some places, which look like wrong translations - from NS. Anyone is advised to find these differences - and explain to me, why I am wrong 8). - - --- Linux has no EOI event, so that we cannot estimate true class - idle time. Workaround is to consider the next dequeue event - as sign that previous packet is finished. This is wrong because of - internal device queueing, but on a permanently loaded link it is true. - Moreover, combined with clock integrator, this scheme looks - very close to an ideal solution. */ - -struct cbq_sched_data; - - -struct cbq_class { - struct Qdisc_class_common common; - struct cbq_class *next_alive; /* next class with backlog in this priority band */ - -/* Parameters */ - unsigned char priority; /* class priority */ - unsigned char priority2; /* priority to be used after overlimit */ - unsigned char ewma_log; /* time constant for idle time calculation */ - - u32 defmap; - - /* Link-sharing scheduler parameters */ - long maxidle; /* Class parameters: see below. */ - long offtime; - long minidle; - u32 avpkt; - struct qdisc_rate_table *R_tab; - - /* General scheduler (WRR) parameters */ - long allot; - long quantum; /* Allotment per WRR round */ - long weight; /* Relative allotment: see below */ - - struct Qdisc *qdisc; /* Ptr to CBQ discipline */ - struct cbq_class *split; /* Ptr to split node */ - struct cbq_class *share; /* Ptr to LS parent in the class tree */ - struct cbq_class *tparent; /* Ptr to tree parent in the class tree */ - struct cbq_class *borrow; /* NULL if class is bandwidth limited; - parent otherwise */ - struct cbq_class *sibling; /* Sibling chain */ - struct cbq_class *children; /* Pointer to children chain */ - - struct Qdisc *q; /* Elementary queueing discipline */ - - -/* Variables */ - unsigned char cpriority; /* Effective priority */ - unsigned char delayed; - unsigned char level; /* level of the class in hierarchy: - 0 for leaf classes, and maximal - level of children + 1 for nodes. - */ - - psched_time_t last; /* Last end of service */ - psched_time_t undertime; - long avgidle; - long deficit; /* Saved deficit for WRR */ - psched_time_t penalized; - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - struct net_rate_estimator __rcu *rate_est; - struct tc_cbq_xstats xstats; - - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - - int filters; - - struct cbq_class *defaults[TC_PRIO_MAX + 1]; -}; - -struct cbq_sched_data { - struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO + 1]; - unsigned int quanta[TC_CBQ_MAXPRIO + 1]; - - struct cbq_class link; - - unsigned int activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes - with backlog */ - -#ifdef CONFIG_NET_CLS_ACT - struct cbq_class *rx_class; -#endif - struct cbq_class *tx_class; - struct cbq_class *tx_borrowed; - int tx_len; - psched_time_t now; /* Cached timestamp */ - unsigned int pmask; - - struct qdisc_watchdog watchdog; /* Watchdog timer, - started when CBQ has - backlog, but cannot - transmit just now */ - psched_tdiff_t wd_expires; - int toplevel; - u32 hgenerator; -}; - - -#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) - -static inline struct cbq_class * -cbq_class_lookup(struct cbq_sched_data *q, u32 classid) -{ - struct Qdisc_class_common *clc; - - clc = qdisc_class_find(&q->clhash, classid); - if (clc == NULL) - return NULL; - return container_of(clc, struct cbq_class, common); -} - -#ifdef CONFIG_NET_CLS_ACT - -static struct cbq_class * -cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) -{ - struct cbq_class *cl; - - for (cl = this->tparent; cl; cl = cl->tparent) { - struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; - - if (new != NULL && new != this) - return new; - } - return NULL; -} - -#endif - -/* Classify packet. The procedure is pretty complicated, but - * it allows us to combine link sharing and priority scheduling - * transparently. - * - * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - * so that it resolves to split nodes. Then packets are classified - * by logical priority, or a more specific classifier may be attached - * to the split node. - */ - -static struct cbq_class * -cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *head = &q->link; - struct cbq_class **defmap; - struct cbq_class *cl = NULL; - u32 prio = skb->priority; - struct tcf_proto *fl; - struct tcf_result res; - - /* - * Step 1. If skb->priority points to one of our classes, use it. - */ - if (TC_H_MAJ(prio ^ sch->handle) == 0 && - (cl = cbq_class_lookup(q, prio)) != NULL) - return cl; - - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - for (;;) { - int result = 0; - defmap = head->defaults; - - fl = rcu_dereference_bh(head->filter_list); - /* - * Step 2+n. Apply classifier. - */ - result = tcf_classify(skb, NULL, fl, &res, true); - if (!fl || result < 0) - goto fallback; - if (result == TC_ACT_SHOT) - return NULL; - - cl = (void *)res.class; - if (!cl) { - if (TC_H_MAJ(res.classid)) - cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) - cl = defmap[TC_PRIO_BESTEFFORT]; - - if (cl == NULL) - goto fallback; - } - if (cl->level >= head->level) - goto fallback; -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - fallthrough; - case TC_ACT_RECLASSIFY: - return cbq_reclassify(skb, cl); - } -#endif - if (cl->level == 0) - return cl; - - /* - * Step 3+n. If classifier selected a link sharing class, - * apply agency specific classifier. - * Repeat this procedure until we hit a leaf node. - */ - head = cl; - } - -fallback: - cl = head; - - /* - * Step 4. No success... - */ - if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio & TC_PRIO_MAX]) && - !(cl = head->defaults[TC_PRIO_BESTEFFORT])) - return head; - - return cl; -} - -/* - * A packet has just been enqueued on the empty class. - * cbq_activate_class adds it to the tail of active class list - * of its priority band. - */ - -static inline void cbq_activate_class(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - int prio = cl->cpriority; - struct cbq_class *cl_tail; - - cl_tail = q->active[prio]; - q->active[prio] = cl; - - if (cl_tail != NULL) { - cl->next_alive = cl_tail->next_alive; - cl_tail->next_alive = cl; - } else { - cl->next_alive = cl; - q->activemask |= (1<<prio); - } -} - -/* - * Unlink class from active chain. - * Note that this same procedure is done directly in cbq_dequeue* - * during round-robin procedure. - */ - -static void cbq_deactivate_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - int prio = this->cpriority; - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - - do { - cl = cl_prev->next_alive; - if (cl == this) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - return; - } - } - return; - } - } while ((cl_prev = cl) != q->active[prio]); -} - -static void -cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) -{ - int toplevel = q->toplevel; - - if (toplevel > cl->level) { - psched_time_t now = psched_get_time(); - - do { - if (cl->undertime < now) { - q->toplevel = cl->level; - return; - } - } while ((cl = cl->borrow) != NULL && toplevel > cl->level); - } -} - -static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - int ret; - struct cbq_class *cl = cbq_classify(skb, sch, &ret); - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = cl; -#endif - if (cl == NULL) { - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; - } - - ret = qdisc_enqueue(skb, cl->q, to_free); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - cbq_mark_toplevel(q, cl); - if (!cl->next_alive) - cbq_activate_class(cl); - return ret; - } - - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; - } - return ret; -} - -/* Overlimit action: penalize leaf class by adding offtime */ -static void cbq_overlimit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (!cl->delayed) { - delay += cl->offtime; - - /* - * Class goes to sleep, so that it will have no - * chance to work avgidle. Let's forgive it 8) - * - * BTW cbq-2.0 has a crap in this - * place, apparently they forgot to shift it by cl->ewma_log. - */ - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - if (delay <= 0) - delay = 1; - cl->undertime = q->now + delay; - - cl->xstats.overactions++; - cl->delayed = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; - - /* Dirty work! We must schedule wakeups based on - * real available rate, rather than leaf rate, - * which may be tiny (even zero). - */ - if (q->toplevel == TC_CBQ_MAXLEVEL) { - struct cbq_class *b; - psched_tdiff_t base_delay = q->wd_expires; - - for (b = cl->borrow; b; b = b->borrow) { - delay = b->undertime - q->now; - if (delay < base_delay) { - if (delay <= 0) - delay = 1; - base_delay = delay; - } - } - - q->wd_expires = base_delay; - } -} - -/* - * It is mission critical procedure. - * - * We "regenerate" toplevel cutoff, if transmitting class - * has backlog and it is not regulated. It is not part of - * original CBQ description, but looks more reasonable. - * Probably, it is wrong. This question needs further investigation. - */ - -static inline void -cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, - struct cbq_class *borrowed) -{ - if (cl && q->toplevel >= borrowed->level) { - if (cl->q->q.qlen > 1) { - do { - if (borrowed->undertime == PSCHED_PASTPERFECT) { - q->toplevel = borrowed->level; - return; - } - } while ((borrowed = borrowed->borrow) != NULL); - } -#if 0 - /* It is not necessary now. Uncommenting it - will save CPU cycles, but decrease fairness. - */ - q->toplevel = TC_CBQ_MAXLEVEL; -#endif - } -} - -static void -cbq_update(struct cbq_sched_data *q) -{ - struct cbq_class *this = q->tx_class; - struct cbq_class *cl = this; - int len = q->tx_len; - psched_time_t now; - - q->tx_class = NULL; - /* Time integrator. We calculate EOS time - * by adding expected packet transmission time. - */ - now = q->now + L2T(&q->link, len); - - for ( ; cl; cl = cl->share) { - long avgidle = cl->avgidle; - long idle; - - _bstats_update(&cl->bstats, len, 1); - - /* - * (now - last) is total time between packet right edges. - * (last_pktlen/rate) is "virtual" busy time, so that - * - * idle = (now - last) - last_pktlen/rate - */ - - idle = now - cl->last; - if ((unsigned long)idle > 128*1024*1024) { - avgidle = cl->maxidle; - } else { - idle -= L2T(cl, len); - - /* true_avgidle := (1-W)*true_avgidle + W*idle, - * where W=2^{-ewma_log}. But cl->avgidle is scaled: - * cl->avgidle == true_avgidle/W, - * hence: - */ - avgidle += idle - (avgidle>>cl->ewma_log); - } - - if (avgidle <= 0) { - /* Overlimit or at-limit */ - - if (avgidle < cl->minidle) - avgidle = cl->minidle; - - cl->avgidle = avgidle; - - /* Calculate expected time, when this class - * will be allowed to send. - * It will occur, when: - * (1-W)*true_avgidle + W*delay = 0, i.e. - * idle = (1/W - 1)*(-true_avgidle) - * or - * idle = (1 - W)*(-cl->avgidle); - */ - idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); - - /* - * That is not all. - * To maintain the rate allocated to the class, - * we add to undertime virtual clock, - * necessary to complete transmitted packet. - * (len/phys_bandwidth has been already passed - * to the moment of cbq_update) - */ - - idle -= L2T(&q->link, len); - idle += L2T(cl, len); - - cl->undertime = now + idle; - } else { - /* Underlimit */ - - cl->undertime = PSCHED_PASTPERFECT; - if (avgidle > cl->maxidle) - cl->avgidle = cl->maxidle; - else - cl->avgidle = avgidle; - } - if ((s64)(now - cl->last) > 0) - cl->last = now; - } - - cbq_update_toplevel(q, this, q->tx_borrowed); -} - -static inline struct cbq_class * -cbq_under_limit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this_cl = cl; - - if (cl->tparent == NULL) - return cl; - - if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) { - cl->delayed = 0; - return cl; - } - - do { - /* It is very suspicious place. Now overlimit - * action is generated for not bounded classes - * only if link is completely congested. - * Though it is in agree with ancestor-only paradigm, - * it looks very stupid. Particularly, - * it means that this chunk of code will either - * never be called or result in strong amplification - * of burstiness. Dangerous, silly, and, however, - * no another solution exists. - */ - cl = cl->borrow; - if (!cl) { - this_cl->qstats.overlimits++; - cbq_overlimit(this_cl); - return NULL; - } - if (cl->level > q->toplevel) - return NULL; - } while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime); - - cl->delayed = 0; - return cl; -} - -static inline struct sk_buff * -cbq_dequeue_prio(struct Qdisc *sch, int prio) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl_tail, *cl_prev, *cl; - struct sk_buff *skb; - int deficit; - - cl_tail = cl_prev = q->active[prio]; - cl = cl_prev->next_alive; - - do { - deficit = 0; - - /* Start round */ - do { - struct cbq_class *borrow = cl; - - if (cl->q->q.qlen && - (borrow = cbq_under_limit(cl)) == NULL) - goto skip_class; - - if (cl->deficit <= 0) { - /* Class exhausted its allotment per - * this round. Switch to the next one. - */ - deficit = 1; - cl->deficit += cl->quantum; - goto next_class; - } - - skb = cl->q->dequeue(cl->q); - - /* Class did not give us any skb :-( - * It could occur even if cl->q->q.qlen != 0 - * f.e. if cl->q == "tbf" - */ - if (skb == NULL) - goto skip_class; - - cl->deficit -= qdisc_pkt_len(skb); - q->tx_class = cl; - q->tx_borrowed = borrow; - if (borrow != cl) { -#ifndef CBQ_XSTATS_BORROWS_BYTES - borrow->xstats.borrows++; - cl->xstats.borrows++; -#else - borrow->xstats.borrows += qdisc_pkt_len(skb); - cl->xstats.borrows += qdisc_pkt_len(skb); -#endif - } - q->tx_len = qdisc_pkt_len(skb); - - if (cl->deficit <= 0) { - q->active[prio] = cl; - cl = cl->next_alive; - cl->deficit += cl->quantum; - } - return skb; - -skip_class: - if (cl->q->q.qlen == 0 || prio != cl->cpriority) { - /* Class is empty or penalized. - * Unlink it from active chain. - */ - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - /* Did cl_tail point to it? */ - if (cl == cl_tail) { - /* Repair it! */ - cl_tail = cl_prev; - - /* Was it the last class in this band? */ - if (cl == cl_tail) { - /* Kill the band! */ - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - if (cl->q->q.qlen) - cbq_activate_class(cl); - return NULL; - } - - q->active[prio] = cl_tail; - } - if (cl->q->q.qlen) - cbq_activate_class(cl); - - cl = cl_prev; - } - -next_class: - cl_prev = cl; - cl = cl->next_alive; - } while (cl_prev != cl_tail); - } while (deficit); - - q->active[prio] = cl_prev; - - return NULL; -} - -static inline struct sk_buff * -cbq_dequeue_1(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb; - unsigned int activemask; - - activemask = q->activemask & 0xFF; - while (activemask) { - int prio = ffz(~activemask); - activemask &= ~(1<<prio); - skb = cbq_dequeue_prio(sch, prio); - if (skb) - return skb; - } - return NULL; -} - -static struct sk_buff * -cbq_dequeue(struct Qdisc *sch) -{ - struct sk_buff *skb; - struct cbq_sched_data *q = qdisc_priv(sch); - psched_time_t now; - - now = psched_get_time(); - - if (q->tx_class) - cbq_update(q); - - q->now = now; - - for (;;) { - q->wd_expires = 0; - - skb = cbq_dequeue_1(sch); - if (skb) { - qdisc_bstats_update(sch, skb); - sch->q.qlen--; - return skb; - } - - /* All the classes are overlimit. - * - * It is possible, if: - * - * 1. Scheduler is empty. - * 2. Toplevel cutoff inhibited borrowing. - * 3. Root class is overlimit. - * - * Reset 2d and 3d conditions and retry. - * - * Note, that NS and cbq-2.0 are buggy, peeking - * an arbitrary class is appropriate for ancestor-only - * sharing, but not for toplevel algorithm. - * - * Our version is better, but slower, because it requires - * two passes, but it is unavoidable with top-level sharing. - */ - - if (q->toplevel == TC_CBQ_MAXLEVEL && - q->link.undertime == PSCHED_PASTPERFECT) - break; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->link.undertime = PSCHED_PASTPERFECT; - } - - /* No packets in scheduler or nobody wants to give them to us :-( - * Sigh... start watchdog timer in the last case. - */ - - if (sch->q.qlen) { - qdisc_qstats_overlimit(sch); - if (q->wd_expires) - qdisc_watchdog_schedule(&q->watchdog, - now + q->wd_expires); - } - return NULL; -} - -/* CBQ class maintenance routines */ - -static void cbq_adjust_levels(struct cbq_class *this) -{ - if (this == NULL) - return; - - do { - int level = 0; - struct cbq_class *cl; - - cl = this->children; - if (cl) { - do { - if (cl->level > level) - level = cl->level; - } while ((cl = cl->sibling) != this->children); - } - this->level = level + 1; - } while ((this = this->tparent) != NULL); -} - -static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) -{ - struct cbq_class *cl; - unsigned int h; - - if (q->quanta[prio] == 0) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - /* BUGGGG... Beware! This expression suffer of - * arithmetic overflows! - */ - if (cl->priority == prio) { - cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ - q->quanta[prio]; - } - if (cl->quantum <= 0 || - cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); - cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; - } - } - } -} - -static void cbq_sync_defmap(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *split = cl->split; - unsigned int h; - int i; - - if (split == NULL) - return; - - for (i = 0; i <= TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) - split->defaults[i] = NULL; - } - - for (i = 0; i <= TC_PRIO_MAX; i++) { - int level = split->level; - - if (split->defaults[i]) - continue; - - for (h = 0; h < q->clhash.hashsize; h++) { - struct cbq_class *c; - - hlist_for_each_entry(c, &q->clhash.hash[h], - common.hnode) { - if (c->split == split && c->level < level && - c->defmap & (1<<i)) { - split->defaults[i] = c; - level = c->level; - } - } - } - } -} - -static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask) -{ - struct cbq_class *split = NULL; - - if (splitid == 0) { - split = cl->split; - if (!split) - return; - splitid = split->common.classid; - } - - if (split == NULL || split->common.classid != splitid) { - for (split = cl->tparent; split; split = split->tparent) - if (split->common.classid == splitid) - break; - } - - if (split == NULL) - return; - - if (cl->split != split) { - cl->defmap = 0; - cbq_sync_defmap(cl); - cl->split = split; - cl->defmap = def & mask; - } else - cl->defmap = (cl->defmap & ~mask) | (def & mask); - - cbq_sync_defmap(cl); -} - -static void cbq_unlink_class(struct cbq_class *this) -{ - struct cbq_class *cl, **clp; - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - - qdisc_class_hash_remove(&q->clhash, &this->common); - - if (this->tparent) { - clp = &this->sibling; - cl = *clp; - do { - if (cl == this) { - *clp = cl->sibling; - break; - } - clp = &cl->sibling; - } while ((cl = *clp) != this->sibling); - - if (this->tparent->children == this) { - this->tparent->children = this->sibling; - if (this->sibling == this) - this->tparent->children = NULL; - } - } else { - WARN_ON(this->sibling != this); - } -} - -static void cbq_link_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - struct cbq_class *parent = this->tparent; - - this->sibling = this; - qdisc_class_hash_insert(&q->clhash, &this->common); - - if (parent == NULL) - return; - - if (parent->children == NULL) { - parent->children = this; - } else { - this->sibling = parent->children->sibling; - parent->children->sibling = this; - } -} - -static void -cbq_reset(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - int prio; - unsigned int h; - - q->activemask = 0; - q->pmask = 0; - q->tx_class = NULL; - q->tx_borrowed = NULL; - qdisc_watchdog_cancel(&q->watchdog); - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++) - q->active[prio] = NULL; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - qdisc_reset(cl->q); - - cl->next_alive = NULL; - cl->undertime = PSCHED_PASTPERFECT; - cl->avgidle = cl->maxidle; - cl->deficit = cl->quantum; - cl->cpriority = cl->priority; - } - } -} - - -static void cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) -{ - if (lss->change & TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; - } - if (lss->change & TCF_CBQ_LSS_EWMA) - cl->ewma_log = lss->ewma_log; - if (lss->change & TCF_CBQ_LSS_AVPKT) - cl->avpkt = lss->avpkt; - if (lss->change & TCF_CBQ_LSS_MINIDLE) - cl->minidle = -(long)lss->minidle; - if (lss->change & TCF_CBQ_LSS_MAXIDLE) { - cl->maxidle = lss->maxidle; - cl->avgidle = lss->maxidle; - } - if (lss->change & TCF_CBQ_LSS_OFFTIME) - cl->offtime = lss->offtime; -} - -static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]--; - q->quanta[cl->priority] -= cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]++; - q->quanta[cl->priority] += cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - if (wrr->allot) - cl->allot = wrr->allot; - if (wrr->weight) - cl->weight = wrr->weight; - if (wrr->priority) { - cl->priority = wrr->priority - 1; - cl->cpriority = cl->priority; - if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO - 1; - } - - cbq_addprio(q, cl); - return 0; -} - -static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) -{ - cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); - return 0; -} - -static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { - [TCA_CBQ_LSSOPT] = { .len = sizeof(struct tc_cbq_lssopt) }, - [TCA_CBQ_WRROPT] = { .len = sizeof(struct tc_cbq_wrropt) }, - [TCA_CBQ_FOPT] = { .len = sizeof(struct tc_cbq_fopt) }, - [TCA_CBQ_OVL_STRATEGY] = { .len = sizeof(struct tc_cbq_ovl) }, - [TCA_CBQ_RATE] = { .len = sizeof(struct tc_ratespec) }, - [TCA_CBQ_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, - [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, -}; - -static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], - struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - int err; - - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, - cbq_policy, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_WRROPT]) { - const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); - - if (wrr->priority > TC_CBQ_MAXPRIO) { - NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); - err = -EINVAL; - } - } - return err; -} - -static int cbq_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct tc_ratespec *r; - int err; - - qdisc_watchdog_init(&q->watchdog, sch); - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (!tb[TCA_CBQ_RTAB] || !tb[TCA_CBQ_RATE]) { - NL_SET_ERR_MSG(extack, "Rate specification missing or incomplete"); - return -EINVAL; - } - - r = nla_data(tb[TCA_CBQ_RATE]); - - q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB], extack); - if (!q->link.R_tab) - return -EINVAL; - - err = tcf_block_get(&q->link.block, &q->link.filter_list, sch, extack); - if (err) - goto put_rtab; - - err = qdisc_class_hash_init(&q->clhash); - if (err < 0) - goto put_block; - - q->link.sibling = &q->link; - q->link.common.classid = sch->handle; - q->link.qdisc = sch; - q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (!q->link.q) - q->link.q = &noop_qdisc; - else - qdisc_hash_add(q->link.q, true); - - q->link.priority = TC_CBQ_MAXPRIO - 1; - q->link.priority2 = TC_CBQ_MAXPRIO - 1; - q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.allot = psched_mtu(qdisc_dev(sch)); - q->link.quantum = q->link.allot; - q->link.weight = q->link.R_tab->rate.rate; - - q->link.ewma_log = TC_CBQ_DEF_EWMA; - q->link.avpkt = q->link.allot/2; - q->link.minidle = -0x7FFFFFFF; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - cbq_link_class(&q->link); - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(&q->link, nla_data(tb[TCA_CBQ_LSSOPT])); - - cbq_addprio(q, &q->link); - return 0; - -put_block: - tcf_block_put(q->link.block); - -put_rtab: - qdisc_put_rtab(q->link.R_tab); - return err; -} - -static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - - if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_lssopt opt; - - opt.flags = 0; - if (cl->borrow == NULL) - opt.flags |= TCF_CBQ_LSS_BOUNDED; - if (cl->share == NULL) - opt.flags |= TCF_CBQ_LSS_ISOLATED; - opt.ewma_log = cl->ewma_log; - opt.level = cl->level; - opt.avpkt = cl->avpkt; - opt.maxidle = cl->maxidle; - opt.minidle = (u32)(-cl->minidle); - opt.offtime = cl->offtime; - opt.change = ~0; - if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_wrropt opt; - - memset(&opt, 0, sizeof(opt)); - opt.flags = 0; - opt.allot = cl->allot; - opt.priority = cl->priority + 1; - opt.cpriority = cl->cpriority + 1; - opt.weight = cl->weight; - if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_fopt opt; - - if (cl->split || cl->defmap) { - opt.split = cl->split ? cl->split->common.classid : 0; - opt.defmap = cl->defmap; - opt.defchange = ~0; - if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) -{ - if (cbq_dump_lss(skb, cl) < 0 || - cbq_dump_rate(skb, cl) < 0 || - cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_fopt(skb, cl) < 0) - return -1; - return 0; -} - -static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *nest; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, &q->link) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - q->link.xstats.avgidle = q->link.avgidle; - return gnet_stats_copy_app(d, &q->link.xstats, sizeof(q->link.xstats)); -} - -static int -cbq_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - struct nlattr *nest; - - if (cl->tparent) - tcm->tcm_parent = cl->tparent->common.classid; - else - tcm->tcm_parent = TC_H_ROOT; - tcm->tcm_handle = cl->common.classid; - tcm->tcm_info = cl->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, cl) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - __u32 qlen; - - cl->xstats.avgidle = cl->avgidle; - cl->xstats.undertime = 0; - qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog); - - if (cl->undertime != PSCHED_PASTPERFECT) - cl->xstats.undertime = cl->undertime - q->now; - - if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) - return -1; - - return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); -} - -static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old, struct netlink_ext_ack *extack) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack); - if (new == NULL) - return -ENOBUFS; - } - - *old = qdisc_replace(sch, new, &cl->q); - return 0; -} - -static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - return cl->q; -} - -static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cbq_deactivate_class(cl); -} - -static unsigned long cbq_find(struct Qdisc *sch, u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - return (unsigned long)cbq_class_lookup(q, classid); -} - -static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - WARN_ON(cl->filters); - - tcf_block_put(cl->block); - qdisc_put(cl->q); - qdisc_put_rtab(cl->R_tab); - gen_kill_estimator(&cl->rate_est); - if (cl != &q->link) - kfree(cl); -} - -static void cbq_destroy(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *next; - struct cbq_class *cl; - unsigned int h; - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = NULL; -#endif - /* - * Filters must be destroyed first because we don't destroy the - * classes from root to leafs which means that filters can still - * be bound to classes which have been destroyed already. --TGR '04 - */ - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - tcf_block_put(cl->block); - cl->block = NULL; - } - } - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], - common.hnode) - cbq_destroy_class(sch, cl); - } - qdisc_class_hash_destroy(&q->clhash); -} - -static int -cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg, struct netlink_ext_ack *extack) -{ - int err; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)*arg; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct cbq_class *parent; - struct qdisc_rate_table *rtab = NULL; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) { - NL_SET_ERR_MSG(extack, "Neither overlimit strategy nor policing attributes can be used for changing class params"); - return -EOPNOTSUPP; - } - - if (cl) { - /* Check parent */ - if (parentid) { - if (cl->tparent && - cl->tparent->common.classid != parentid) { - NL_SET_ERR_MSG(extack, "Invalid parent id"); - return -EINVAL; - } - if (!cl->tparent && parentid != TC_H_ROOT) { - NL_SET_ERR_MSG(extack, "Parent must be root"); - return -EINVAL; - } - } - - if (tb[TCA_CBQ_RATE]) { - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB], extack); - if (rtab == NULL) - return -EINVAL; - } - - if (tca[TCA_RATE]) { - err = gen_replace_estimator(&cl->bstats, NULL, - &cl->rate_est, - NULL, - true, - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); - qdisc_put_rtab(rtab); - return err; - } - } - - /* Change class parameters */ - sch_tree_lock(sch); - - if (cl->next_alive != NULL) - cbq_deactivate_class(cl); - - if (rtab) { - qdisc_put_rtab(cl->R_tab); - cl->R_tab = rtab; - } - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - - if (tb[TCA_CBQ_WRROPT]) { - cbq_rmprio(q, cl); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - } - - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - - if (cl->q->q.qlen) - cbq_activate_class(cl); - - sch_tree_unlock(sch); - - return 0; - } - - if (parentid == TC_H_ROOT) - return -EINVAL; - - if (!tb[TCA_CBQ_WRROPT] || !tb[TCA_CBQ_RATE] || !tb[TCA_CBQ_LSSOPT]) { - NL_SET_ERR_MSG(extack, "One of the following attributes MUST be specified: WRR, rate or link sharing"); - return -EINVAL; - } - - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB], - extack); - if (rtab == NULL) - return -EINVAL; - - if (classid) { - err = -EINVAL; - if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) { - NL_SET_ERR_MSG(extack, "Specified class not found"); - goto failure; - } - } else { - int i; - classid = TC_H_MAKE(sch->handle, 0x8000); - - for (i = 0; i < 0x8000; i++) { - if (++q->hgenerator >= 0x8000) - q->hgenerator = 1; - if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) - break; - } - err = -ENOSR; - if (i >= 0x8000) { - NL_SET_ERR_MSG(extack, "Unable to generate classid"); - goto failure; - } - classid = classid|q->hgenerator; - } - - parent = &q->link; - if (parentid) { - parent = cbq_class_lookup(q, parentid); - err = -EINVAL; - if (!parent) { - NL_SET_ERR_MSG(extack, "Failed to find parentid"); - goto failure; - } - } - - err = -ENOBUFS; - cl = kzalloc(sizeof(*cl), GFP_KERNEL); - if (cl == NULL) - goto failure; - - gnet_stats_basic_sync_init(&cl->bstats); - err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); - if (err) { - kfree(cl); - goto failure; - } - - if (tca[TCA_RATE]) { - err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, true, tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } - } - - cl->R_tab = rtab; - rtab = NULL; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - NULL); - if (!cl->q) - cl->q = &noop_qdisc; - else - qdisc_hash_add(cl->q, true); - - cl->common.classid = classid; - cl->tparent = parent; - cl->qdisc = sch; - cl->allot = parent->allot; - cl->quantum = cl->allot; - cl->weight = cl->R_tab->rate.rate; - - sch_tree_lock(sch); - cbq_link_class(cl); - cl->borrow = cl->tparent; - if (cl->tparent != &q->link) - cl->share = cl->tparent; - cbq_adjust_levels(parent); - cl->minidle = -0x7FFFFFFF; - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log == 0) - cl->ewma_log = q->link.ewma_log; - if (cl->maxidle == 0) - cl->maxidle = q->link.maxidle; - if (cl->avpkt == 0) - cl->avpkt = q->link.avpkt; - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); - - *arg = (unsigned long)cl; - return 0; - -failure: - qdisc_put_rtab(rtab); - return err; -} - -static int cbq_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl->filters || cl->children || cl == &q->link) - return -EBUSY; - - sch_tree_lock(sch); - - qdisc_purge_queue(cl->q); - - if (cl->next_alive) - cbq_deactivate_class(cl); - - if (q->tx_borrowed == cl) - q->tx_borrowed = q->tx_class; - if (q->tx_class == cl) { - q->tx_class = NULL; - q->tx_borrowed = NULL; - } -#ifdef CONFIG_NET_CLS_ACT - if (q->rx_class == cl) - q->rx_class = NULL; -#endif - - cbq_unlink_class(cl); - cbq_adjust_levels(cl->tparent); - cl->defmap = 0; - cbq_sync_defmap(cl); - - cbq_rmprio(q, cl); - sch_tree_unlock(sch); - - cbq_destroy_class(sch, cl); - return 0; -} - -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl == NULL) - cl = &q->link; - - return cl->block; -} - -static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class *)parent; - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - if (p && p->level <= cl->level) - return 0; - cl->filters++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->filters--; -} - -static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - unsigned int h; - - if (arg->stop) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) - return; - } - } -} - -static const struct Qdisc_class_ops cbq_class_ops = { - .graft = cbq_graft, - .leaf = cbq_leaf, - .qlen_notify = cbq_qlen_notify, - .find = cbq_find, - .change = cbq_change_class, - .delete = cbq_delete, - .walk = cbq_walk, - .tcf_block = cbq_tcf_block, - .bind_tcf = cbq_bind_filter, - .unbind_tcf = cbq_unbind_filter, - .dump = cbq_dump_class, - .dump_stats = cbq_dump_class_stats, -}; - -static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &cbq_class_ops, - .id = "cbq", - .priv_size = sizeof(struct cbq_sched_data), - .enqueue = cbq_enqueue, - .dequeue = cbq_dequeue, - .peek = qdisc_peek_dequeued, - .init = cbq_init, - .reset = cbq_reset, - .destroy = cbq_destroy, - .change = NULL, - .dump = cbq_dump, - .dump_stats = cbq_dump_stats, - .owner = THIS_MODULE, -}; - -static int __init cbq_module_init(void) -{ - return register_qdisc(&cbq_qdisc_ops); -} -static void __exit cbq_module_exit(void) -{ - unregister_qdisc(&cbq_qdisc_ops); -} -module_init(cbq_module_init) -module_exit(cbq_module_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c deleted file mode 100644 index 401ffaf87..000000000 --- a/net/sched/sch_dsmark.c +++ /dev/null @@ -1,518 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_dsmark.c - Differentiated Services field marker */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/bitops.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <asm/byteorder.h> - -/* - * classid class marking - * ------- ----- ------- - * n/a 0 n/a - * x:0 1 use entry [0] - * ... ... ... - * x:y y>0 y+1 use entry [y] - * ... ... ... - * x:indices-1 indices use entry [indices-1] - * ... ... ... - * x:y y+1 use entry [y & (indices-1)] - * ... ... ... - * 0xffff 0x10000 use entry [indices-1] - */ - - -#define NO_DEFAULT_INDEX (1 << 16) - -struct mask_value { - u8 mask; - u8 value; -}; - -struct dsmark_qdisc_data { - struct Qdisc *q; - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct mask_value *mv; - u16 indices; - u8 set_tc_index; - u32 default_index; /* index range is 0...0xffff */ -#define DSMARK_EMBEDDED_SZ 16 - struct mask_value embedded[DSMARK_EMBEDDED_SZ]; -}; - -static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) -{ - return index <= p->indices && index > 0; -} - -/* ------------------------- Class/flow operations ------------------------- */ - -static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", - __func__, sch, p, new, old); - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (new == NULL) - new = &noop_qdisc; - } - - *old = qdisc_replace(sch, new, &p->q); - return 0; -} - -static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - return p->q; -} - -static unsigned long dsmark_find(struct Qdisc *sch, u32 classid) -{ - return TC_H_MIN(classid) + 1; -} - -static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", - __func__, sch, qdisc_priv(sch), classid); - - return dsmark_find(sch, classid); -} - -static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl) -{ -} - -static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { - [TCA_DSMARK_INDICES] = { .type = NLA_U16 }, - [TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 }, - [TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG }, - [TCA_DSMARK_MASK] = { .type = NLA_U8 }, - [TCA_DSMARK_VALUE] = { .type = NLA_U8 }, -}; - -static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - - pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", - __func__, sch, p, classid, parent, *arg); - - if (!dsmark_valid_index(p, *arg)) { - err = -ENOENT; - goto errout; - } - - if (!opt) - goto errout; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - if (tb[TCA_DSMARK_VALUE]) - p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); - - if (tb[TCA_DSMARK_MASK]) - p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - - err = 0; - -errout: - return err; -} - -static int dsmark_delete(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - if (!dsmark_valid_index(p, arg)) - return -EINVAL; - - p->mv[arg - 1].mask = 0xff; - p->mv[arg - 1].value = 0; - - return 0; -} - -static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int i; - - pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", - __func__, sch, p, walker); - - if (walker->stop) - return; - - for (i = 0; i < p->indices; i++) { - if (p->mv[i].mask == 0xff && !p->mv[i].value) { - walker->count++; - continue; - } - if (!tc_qdisc_stats_dump(sch, i + 1, walker)) - break; - } -} - -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - return p->block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - unsigned int len = qdisc_pkt_len(skb); - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); - - if (p->set_tc_index) { - int wlen = skb_network_offset(skb); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) - & ~INET_ECN_MASK; - break; - - case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) - & ~INET_ECN_MASK; - break; - default: - skb->tc_index = 0; - break; - } - } - - if (TC_H_MAJ(skb->priority) == sch->handle) - skb->tc_index = TC_H_MIN(skb->priority); - else { - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, NULL, fl, &res, false); - - pr_debug("result %d class 0x%04x\n", result, res.classid); - - switch (result) { -#ifdef CONFIG_NET_CLS_ACT - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - - case TC_ACT_SHOT: - goto drop; -#endif - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; - } - } - - err = qdisc_enqueue(skb, p->q, to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - return err; - } - - sch->qstats.backlog += len; - sch->q.qlen++; - - return NET_XMIT_SUCCESS; - -drop: - qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - u32 index; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - skb = qdisc_dequeue_peeked(p->q); - if (skb == NULL) - return NULL; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - index = skb->tc_index & (p->indices - 1); - pr_debug("index %d->%d\n", skb->tc_index, index); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - default: - /* - * Only complain if a change was actually attempted. - * This way, we can send non-IP traffic through dsmark - * and don't need yet another qdisc as a bypass. - */ - if (p->mv[index].mask != 0xff || p->mv[index].value) - pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(skb_protocol(skb, true))); - break; - } - - return skb; -} - -static struct sk_buff *dsmark_peek(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - return p->q->ops->peek(p->q); -} - -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - u32 default_index = NO_DEFAULT_INDEX; - u16 indices; - int i; - - pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); - - if (!opt) - goto errout; - - err = tcf_block_get(&p->block, &p->filter_list, sch, extack); - if (err) - return err; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - err = -EINVAL; - if (!tb[TCA_DSMARK_INDICES]) - goto errout; - indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); - - if (hweight32(indices) != 1) - goto errout; - - if (tb[TCA_DSMARK_DEFAULT_INDEX]) - default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - - if (indices <= DSMARK_EMBEDDED_SZ) - p->mv = p->embedded; - else - p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); - if (!p->mv) { - err = -ENOMEM; - goto errout; - } - for (i = 0; i < indices; i++) { - p->mv[i].mask = 0xff; - p->mv[i].value = 0; - } - p->indices = indices; - p->default_index = default_index; - p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, - NULL); - if (p->q == NULL) - p->q = &noop_qdisc; - else - qdisc_hash_add(p->q, true); - - pr_debug("%s: qdisc %p\n", __func__, p->q); - - err = 0; -errout: - return err; -} - -static void dsmark_reset(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - if (p->q) - qdisc_reset(p->q); -} - -static void dsmark_destroy(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - tcf_block_put(p->block); - qdisc_put(p->q); - if (p->mv != p->embedded) - kfree(p->mv); -} - -static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); - - if (!dsmark_valid_index(p, cl)) - return -EINVAL; - - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); - tcm->tcm_info = p->q->handle; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) - goto nla_put_failure; - - if (p->default_index != NO_DEFAULT_INDEX && - nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) - goto nla_put_failure; - - if (p->set_tc_index && - nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static const struct Qdisc_class_ops dsmark_class_ops = { - .graft = dsmark_graft, - .leaf = dsmark_leaf, - .find = dsmark_find, - .change = dsmark_change, - .delete = dsmark_delete, - .walk = dsmark_walk, - .tcf_block = dsmark_tcf_block, - .bind_tcf = dsmark_bind_filter, - .unbind_tcf = dsmark_unbind_filter, - .dump = dsmark_dump_class, -}; - -static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &dsmark_class_ops, - .id = "dsmark", - .priv_size = sizeof(struct dsmark_qdisc_data), - .enqueue = dsmark_enqueue, - .dequeue = dsmark_dequeue, - .peek = dsmark_peek, - .init = dsmark_init, - .reset = dsmark_reset, - .destroy = dsmark_destroy, - .change = NULL, - .dump = dsmark_dump, - .owner = THIS_MODULE, -}; - -static int __init dsmark_module_init(void) -{ - return register_qdisc(&dsmark_qdisc_ops); -} - -static void __exit dsmark_module_exit(void) -{ - unregister_qdisc(&dsmark_qdisc_ops); -} - -module_init(dsmark_module_init) -module_exit(dsmark_module_exit) - -MODULE_LICENSE("GPL"); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 9b8999e2a..867df4522 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -155,10 +155,12 @@ static int smc_clc_ueid_remove(char *ueid) rc = 0; } } +#if IS_ENABLED(CONFIG_S390) if (!rc && !smc_clc_eid_table.ueid_cnt) { smc_clc_eid_table.seid_enabled = 1; rc = -EAGAIN; /* indicate success and enabling of seid */ } +#endif write_unlock(&smc_clc_eid_table.lock); return rc; } @@ -273,22 +275,30 @@ err: int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) { +#if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); smc_clc_eid_table.seid_enabled = 1; write_unlock(&smc_clc_eid_table.lock); return 0; +#else + return -EOPNOTSUPP; +#endif } int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) { int rc = 0; +#if IS_ENABLED(CONFIG_S390) write_lock(&smc_clc_eid_table.lock); if (!smc_clc_eid_table.ueid_cnt) rc = -ENOENT; else smc_clc_eid_table.seid_enabled = 0; write_unlock(&smc_clc_eid_table.lock); +#else + rc = -EOPNOTSUPP; +#endif return rc; } @@ -1168,7 +1178,11 @@ void __init smc_clc_init(void) INIT_LIST_HEAD(&smc_clc_eid_table.list); rwlock_init(&smc_clc_eid_table.lock); smc_clc_eid_table.ueid_cnt = 0; +#if IS_ENABLED(CONFIG_S390) smc_clc_eid_table.seid_enabled = 1; +#else + smc_clc_eid_table.seid_enabled = 0; +#endif } void smc_clc_exit(void) diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index 74ee22712..720d3ba74 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -336,8 +336,9 @@ struct rpc_xprt *xprt_iter_current_entry_offline(struct rpc_xprt_iter *xpi) xprt_switch_find_current_entry_offline); } -bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, - const struct sockaddr *sap) +static +bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) { struct list_head *head; struct rpc_xprt *pos; @@ -356,6 +357,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, return false; } +bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) +{ + bool res; + + rcu_read_lock(); + res = __rpc_xprt_switch_has_addr(xps, sap); + rcu_read_unlock(); + + return res; +} + static struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, const struct rpc_xprt *cur, bool check_active) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8cc42aea1..2e14d4c37 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 cdcd27318..1cb993562 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1088,6 +1088,12 @@ 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.h b/net/tls/tls.h index 0672acab2..4922668fe 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -97,6 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +void tls_sw_splice_eof(struct socket *sock); int tls_sw_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tls_sw_sendpage(struct sock *sk, struct page *page, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 338a443fa..6b7189a52 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -922,6 +922,7 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] ops[TLS_BASE][TLS_BASE] = *base; ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof; ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; @@ -990,6 +991,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; + prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof; prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; @@ -1096,7 +1098,7 @@ 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 0323040d3..2bd27b777 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -62,6 +62,7 @@ struct tls_decrypt_ctx { u8 iv[MAX_IV_SIZE]; u8 aad[TLS_MAX_AAD_SIZE]; u8 tail; + bool free_sgout; struct scatterlist sg[]; }; @@ -186,7 +187,6 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) struct aead_request *aead_req = crypto_get_completion_data(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; @@ -212,7 +212,7 @@ static void tls_decrypt_done(crypto_completion_data_t *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) @@ -223,10 +223,17 @@ static void tls_decrypt_done(crypto_completion_data_t *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, @@ -252,6 +259,7 @@ 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 { aead_request_set_callback(aead_req, @@ -265,6 +273,8 @@ static int tls_do_decryption(struct sock *sk, return 0; ret = crypto_wait_req(ret, &ctx->async_wait); + } else if (darg->async) { + atomic_dec(&ctx->decrypt_pending); } darg->async = false; @@ -441,7 +451,6 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) struct tls_rec *rec; bool ready = false; struct sock *sk; - int pending; rec = container_of(aead_req, struct tls_rec, aead_req); msg_en = &rec->msg_encrypted; @@ -481,12 +490,8 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) ready = true; } - 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; @@ -496,6 +501,15 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) schedule_delayed_work(&ctx->tx_work.work, 1); } +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); + + return ctx->async_wait.err; +} + static int tls_do_encryption(struct sock *sk, struct tls_context *tls_ctx, struct tls_sw_context_tx *ctx, @@ -542,6 +556,7 @@ 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); @@ -953,7 +968,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int num_zc = 0; int orig_size; int ret = 0; - int pending; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_CMSG_COMPAT)) @@ -1122,24 +1136,12 @@ 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; } } @@ -1158,6 +1160,67 @@ send_end: return copied > 0 ? copied : ret; } +/* + * Handle unexpected EOF during splice without SPLICE_F_MORE set. + */ +void tls_sw_splice_eof(struct socket *sock) +{ + struct sock *sk = 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; + struct sk_msg *msg_pl; + ssize_t copied = 0; + bool retrying = false; + int ret = 0; + + if (!ctx->open_rec) + return; + + mutex_lock(&tls_ctx->tx_lock); + lock_sock(sk); + +retry: + /* same checks as in tls_sw_push_pending_record() */ + rec = ctx->open_rec; + if (!rec) + goto unlock; + + msg_pl = &rec->msg_plaintext; + if (msg_pl->sg.size == 0) + goto unlock; + + /* Check the BPF advisor and perform transmission. */ + ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA, + &copied, 0); + switch (ret) { + case 0: + case -EAGAIN: + if (retrying) + goto unlock; + retrying = true; + goto retry; + case -EINPROGRESS: + break; + default: + goto unlock; + } + + /* Wait for pending encryptions to get completed */ + if (tls_encrypt_async_wait(ctx)) + goto unlock; + + /* Transmit if any encryptions have completed */ + if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + cancel_delayed_work(&ctx->tx_work.work); + tls_tx_records(sk, 0); + } + +unlock: + release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); +} + static int tls_sw_do_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -1595,6 +1658,7 @@ 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, @@ -1783,7 +1847,8 @@ 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; @@ -1796,7 +1861,7 @@ 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; @@ -1814,12 +1879,12 @@ 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; @@ -1855,6 +1920,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, out: return copied ? : err; +more: + if (more) + *more = true; + goto out; } static bool @@ -1954,10 +2023,12 @@ 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; @@ -1977,12 +2048,12 @@ 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); @@ -2075,6 +2146,8 @@ put_on_rx_list: decrypted += chunk; len -= chunk; __skb_queue_tail(&ctx->rx_list, skb); + if (unlikely(control != TLS_RECORD_TYPE_DATA)) + break; continue; } @@ -2098,8 +2171,10 @@ 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; @@ -2123,16 +2198,10 @@ 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) { @@ -2144,12 +2213,11 @@ 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; @@ -2351,16 +2419,9 @@ 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); @@ -2513,6 +2574,48 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx) tls_ctx->prot_info.version != TLS_1_3_VERSION; } +static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct sock *sk) +{ + struct tls_sw_context_tx *sw_ctx_tx; + + if (!ctx->priv_ctx_tx) { + sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); + if (!sw_ctx_tx) + return NULL; + } else { + sw_ctx_tx = ctx->priv_ctx_tx; + } + + crypto_init_wait(&sw_ctx_tx->async_wait); + 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; + + return sw_ctx_tx; +} + +static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) +{ + struct tls_sw_context_rx *sw_ctx_rx; + + if (!ctx->priv_ctx_rx) { + sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); + if (!sw_ctx_rx) + return NULL; + } else { + sw_ctx_rx = ctx->priv_ctx_rx; + } + + crypto_init_wait(&sw_ctx_rx->async_wait); + 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); + + return sw_ctx_rx; +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2534,48 +2637,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } if (tx) { - if (!ctx->priv_ctx_tx) { - sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); - if (!sw_ctx_tx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_tx = sw_ctx_tx; - } else { - sw_ctx_tx = - (struct tls_sw_context_tx *)ctx->priv_ctx_tx; - } - } else { - if (!ctx->priv_ctx_rx) { - sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); - if (!sw_ctx_rx) { - rc = -ENOMEM; - goto out; - } - ctx->priv_ctx_rx = sw_ctx_rx; - } else { - sw_ctx_rx = - (struct tls_sw_context_rx *)ctx->priv_ctx_rx; - } - } + ctx->priv_ctx_tx = init_ctx_tx(ctx, sk); + if (!ctx->priv_ctx_tx) + return -ENOMEM; - if (tx) { - crypto_init_wait(&sw_ctx_tx->async_wait); - spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); + sw_ctx_tx = ctx->priv_ctx_tx; crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; - 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; } else { - crypto_init_wait(&sw_ctx_rx->async_wait); - spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); - init_waitqueue_head(&sw_ctx_rx->wq); + ctx->priv_ctx_rx = init_ctx_rx(ctx); + if (!ctx->priv_ctx_rx) + return -ENOMEM; + + sw_ctx_rx = ctx->priv_ctx_rx; crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; - skb_queue_head_init(&sw_ctx_rx->rx_list); - skb_queue_head_init(&sw_ctx_rx->async_hold); aead = &sw_ctx_rx->aead_recv; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index be2ed7b0f..e1af94393 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1322,13 +1322,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } - if (sk1 < sk2) { - unix_state_lock(sk1); - unix_state_lock_nested(sk2); - } else { - unix_state_lock(sk2); - unix_state_lock_nested(sk1); - } + if (sk1 > sk2) + swap(sk1, sk2); + + unix_state_lock(sk1); + unix_state_lock_nested(sk2, U_LOCK_SECOND); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1559,7 +1557,7 @@ restart: goto out_unlock; } - unix_state_lock_nested(sk); + unix_state_lock_nested(sk, U_LOCK_SECOND); if (sk->sk_state != st) { unix_state_unlock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index 616b55c5b..3438b7af0 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) * queue lock. With the other's queue locked it's * OK to lock the state. */ - unix_state_lock_nested(req); + unix_state_lock_nested(req, U_LOCK_DIAG); peer = unix_sk(req)->peer; buf[i++] = (peer ? sock_i_ino(peer) : 0); unix_state_unlock(req); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dc2763540..ab2c83d58 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 8809e668e..3fcddc868 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1671,6 +1671,7 @@ 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 70fb14b8b..1a3bd554e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3960,6 +3960,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx++; } + if_start = 0; wp_idx++; } out: @@ -4136,6 +4137,8 @@ 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 b7e1631b3..3ad4c1032 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1810,8 +1810,12 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, list_add(&new->hidden_list, &hidden->hidden_list); hidden->refcount++; + + ies = (void *)rcu_access_pointer(new->pub.beacon_ies); rcu_assign_pointer(new->pub.beacon_ies, hidden->pub.beacon_ies); + if (ies) + kfree_rcu(ies, rcu_head); } } else { /* diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index ac1a645af..d0320e35a 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -180,6 +180,8 @@ static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) int optlen = 0; int err = -EINVAL; + skb->protocol = htons(ETH_P_IP); + if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) { struct ip_beet_phdr *ph; int phlen; @@ -232,8 +234,7 @@ static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) - goto out; + skb->protocol = htons(ETH_P_IP); if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; @@ -270,8 +271,8 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) - goto out; + skb->protocol = htons(ETH_P_IPV6); + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; @@ -301,6 +302,8 @@ static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) int size = sizeof(struct ipv6hdr); int err; + skb->protocol = htons(ETH_P_IPV6); + err = skb_cow_head(skb, size + skb->mac_len); if (err) goto out; @@ -332,22 +335,26 @@ out: */ static int xfrm_inner_mode_encap_remove(struct xfrm_state *x, - const struct xfrm_mode *inner_mode, struct sk_buff *skb) { - switch (inner_mode->encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: - if (inner_mode->family == AF_INET) + switch (x->sel.family) { + case AF_INET: return xfrm4_remove_beet_encap(x, skb); - if (inner_mode->family == AF_INET6) + case AF_INET6: return xfrm6_remove_beet_encap(x, skb); + } break; case XFRM_MODE_TUNNEL: - if (inner_mode->family == AF_INET) + switch (XFRM_MODE_SKB_CB(skb)->protocol) { + case IPPROTO_IPIP: return xfrm4_remove_tunnel_encap(x, skb); - if (inner_mode->family == AF_INET6) + case IPPROTO_IPV6: return xfrm6_remove_tunnel_encap(x, skb); break; + } + return -EINVAL; } WARN_ON_ONCE(1); @@ -356,9 +363,7 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x, static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode = &x->inner_mode; - - switch (x->outer_mode.family) { + switch (x->props.family) { case AF_INET: xfrm4_extract_header(skb); break; @@ -370,25 +375,7 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) return -EAFNOSUPPORT; } - if (x->sel.family == AF_UNSPEC) { - inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); - if (!inner_mode) - return -EAFNOSUPPORT; - } - - switch (inner_mode->family) { - case AF_INET: - skb->protocol = htons(ETH_P_IP); - break; - case AF_INET6: - skb->protocol = htons(ETH_P_IPV6); - break; - default: - WARN_ON_ONCE(1); - break; - } - - return xfrm_inner_mode_encap_remove(x, inner_mode, skb); + return xfrm_inner_mode_encap_remove(x, skb); } /* Remove encapsulation header. @@ -434,17 +421,16 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) } static int xfrm_inner_mode_input(struct xfrm_state *x, - const struct xfrm_mode *inner_mode, struct sk_buff *skb) { - switch (inner_mode->encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: return xfrm_prepare_input(x, skb); case XFRM_MODE_TRANSPORT: - if (inner_mode->family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_transport_input(x, skb); - if (inner_mode->family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_transport_input(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: @@ -462,7 +448,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { const struct xfrm_state_afinfo *afinfo; struct net *net = dev_net(skb->dev); - const struct xfrm_mode *inner_mode; int err; __be32 seq; __be32 seq_hi; @@ -492,7 +477,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } - family = x->outer_mode.family; + family = x->props.family; /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { @@ -676,17 +661,7 @@ resume: XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; - inner_mode = &x->inner_mode; - - if (x->sel.family == AF_UNSPEC) { - inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); - if (inner_mode == NULL) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); - goto drop; - } - } - - if (xfrm_inner_mode_input(x, inner_mode, skb)) { + if (xfrm_inner_mode_input(x, skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } @@ -701,7 +676,7 @@ resume: * transport mode so the outer address is identical. */ daddr = &x->id.daddr; - family = x->outer_mode.family; + family = x->props.family; err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) { @@ -732,7 +707,7 @@ resume: err = -EAFNOSUPPORT; rcu_read_lock(); - afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode.family); + afinfo = xfrm_state_afinfo_get_rcu(x->props.family); if (likely(afinfo)) err = afinfo->transport_finish(skb, xfrm_gro || async); rcu_read_unlock(); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9a5e79a38..07a7ee43b 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -414,7 +414,7 @@ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE; skb->protocol = htons(ETH_P_IP); - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm4_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: @@ -437,7 +437,7 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) skb->ignore_df = 1; skb->protocol = htons(ETH_P_IPV6); - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: return xfrm6_beet_encap_add(x, skb); case XFRM_MODE_TUNNEL: @@ -453,22 +453,22 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb) { - switch (x->outer_mode.encap) { + switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: - if (x->outer_mode.family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_prepare_output(x, skb); - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_prepare_output(x, skb); break; case XFRM_MODE_TRANSPORT: - if (x->outer_mode.family == AF_INET) + if (x->props.family == AF_INET) return xfrm4_transport_output(x, skb); - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_transport_output(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: - if (x->outer_mode.family == AF_INET6) + if (x->props.family == AF_INET6) return xfrm6_ro_output(x, skb); WARN_ON_ONCE(1); break; @@ -866,21 +866,10 @@ static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb) { - const struct xfrm_mode *inner_mode; - - if (x->sel.family == AF_UNSPEC) - inner_mode = xfrm_ip2inner_mode(x, - xfrm_af2proto(skb_dst(skb)->ops->family)); - else - inner_mode = &x->inner_mode; - - if (inner_mode == NULL) - return -EAFNOSUPPORT; - - switch (inner_mode->family) { - case AF_INET: + switch (skb->protocol) { + case htons(ETH_P_IP): return xfrm4_extract_output(x, skb); - case AF_INET6: + case htons(ETH_P_IPV6): return xfrm6_extract_output(x, skb); } |