diff options
Diffstat (limited to 'net')
178 files changed, 5075 insertions, 3603 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c index f271a7bcf5b2..65f706e4344c 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -617,7 +617,7 @@ static void atmarpd_close(struct atm_vcc *vcc) module_put(THIS_MODULE); } -static struct atmdev_ops atmarpd_dev_ops = { +static const struct atmdev_ops atmarpd_dev_ops = { .close = atmarpd_close }; diff --git a/net/atm/lec.c b/net/atm/lec.c index 093fe8707731..a3d93a1bb133 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -486,7 +486,7 @@ static void lec_atm_close(struct atm_vcc *vcc) module_put(THIS_MODULE); } -static struct atmdev_ops lecdev_ops = { +static const struct atmdev_ops lecdev_ops = { .close = lec_atm_close, .send = lec_atm_send }; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 680a4b9095a1..5677147209e8 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -779,7 +779,7 @@ static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb) netif_rx(new_skb); } -static struct atmdev_ops mpc_ops = { /* only send is required */ +static const struct atmdev_ops mpc_ops = { /* only send is required */ .close = mpoad_close, .send = msg_from_mpoad }; diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 983c3a21a133..0a20f6e953ac 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -217,7 +217,7 @@ static void sigd_close(struct atm_vcc *vcc) read_unlock(&vcc_sklist_lock); } -static struct atmdev_ops sigd_dev_ops = { +static const struct atmdev_ops sigd_dev_ops = { .close = sigd_close, .send = sigd_send }; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a3501173e200..83ba5483455a 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -729,11 +729,9 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, const unsigned char *packet_buff, int packet_len, bool direct_link) { - unsigned char *skb_buff; unsigned long new_direct_link_flag; - skb_buff = skb_put_data(forw_packet_aggr->skb, packet_buff, - packet_len); + skb_put_data(forw_packet_aggr->skb, packet_buff, packet_len); forw_packet_aggr->packet_len += packet_len; forw_packet_aggr->num_packets++; @@ -1281,7 +1279,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, batadv_ogm_packet->tq = combined_tq; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, iface_penalty: %3i, total tq: %3i, if_incoming = %s, if_outgoing = %s\n", + "bidirectional: orig = %pM neigh = %pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, iface_penalty: %3i, total tq: %3i, if_incoming = %s, if_outgoing = %s\n", orig_node->orig, orig_neigh_node->orig, total_count, neigh_rq_count, tq_own, tq_asym_penalty, tq_iface_penalty, batadv_ogm_packet->tq, if_incoming->net_dev->name, diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 1e3dc374bfde..8be61734fc43 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -137,7 +137,7 @@ static void batadv_v_ogm_send(struct work_struct *work) struct batadv_priv *bat_priv; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; - unsigned char *ogm_buff, *pkt_buff; + unsigned char *ogm_buff; int ogm_buff_len; u16 tvlv_len = 0; int ret; @@ -166,7 +166,7 @@ static void batadv_v_ogm_send(struct work_struct *work) goto reschedule; skb_reserve(skb, ETH_HLEN); - pkt_buff = skb_put_data(skb, ogm_buff, ogm_buff_len); + skb_put_data(skb, ogm_buff, ogm_buff_len); ogm_packet = (struct batadv_ogm2_packet *)skb->data; ogm_packet->seqno = htonl(atomic_read(&bat_priv->bat_v.ogm_seqno)); @@ -200,7 +200,7 @@ static void batadv_v_ogm_send(struct work_struct *work) type = "unknown"; } - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "OGM2 from ourselve on %s surpressed: %s\n", + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "OGM2 from ourselves on %s suppressed: %s\n", hard_iface->net_dev->name, type); batadv_hardif_put(hard_iface); @@ -683,18 +683,18 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, ogm_throughput = ntohl(ogm_packet->throughput); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Received OGM2 packet via NB: %pM, IF: %s [%pM] (from OG: %pM, seqno %u, troughput %u, TTL %u, V %u, tvlv_len %u)\n", + "Received OGM2 packet via NB: %pM, IF: %s [%pM] (from OG: %pM, seqno %u, throughput %u, TTL %u, V %u, tvlv_len %u)\n", ethhdr->h_source, if_incoming->net_dev->name, if_incoming->net_dev->dev_addr, ogm_packet->orig, ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl, ogm_packet->version, ntohs(ogm_packet->tvlv_len)); - /* If the troughput metric is 0, immediately drop the packet. No need to - * create orig_node / neigh_node for an unusable route. + /* If the throughput metric is 0, immediately drop the packet. No need + * to create orig_node / neigh_node for an unusable route. */ if (ogm_throughput == 0) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Drop packet: originator packet with troughput metric of 0\n"); + "Drop packet: originator packet with throughput metric of 0\n"); return; } @@ -762,7 +762,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, type = "unknown"; } - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "OGM2 packet from %pM on %s surpressed: %s\n", + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "OGM2 packet from %pM on %s suppressed: %s\n", ogm_packet->orig, hard_iface->net_dev->name, type); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 6930d6b50f99..b6cfa78e9381 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -834,7 +834,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) last_seen_msecs = last_seen_msecs % 60000; last_seen_secs = last_seen_msecs / 1000; - seq_printf(seq, " * %15pI4 %14pM %4i %6i:%02i\n", + seq_printf(seq, " * %15pI4 %pM %4i %6i:%02i\n", &dat_entry->ip, dat_entry->mac_addr, batadv_print_vid(dat_entry->vid), last_seen_mins, last_seen_secs); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 2be8f1f46529..05cc7637c064 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2017.2" +#define BATADV_SOURCE_VERSION "2017.3" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index d239a9d72ac3..054a65e6eb68 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -911,7 +911,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) type = "unknown"; } - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s surpressed: %s\n", + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", bcast_packet->orig, hard_iface->net_dev->name, type); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index e1133bc634b5..8a3ce79b1307 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1549,9 +1549,41 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, return found; } +/** + * batadv_tt_global_sync_flags - update TT sync flags + * @tt_global: the TT global entry to update sync flags in + * + * Updates the sync flag bits in the tt_global flag attribute with a logical + * OR of all sync flags from any of its TT orig entries. + */ +static void +batadv_tt_global_sync_flags(struct batadv_tt_global_entry *tt_global) +{ + struct batadv_tt_orig_list_entry *orig_entry; + const struct hlist_head *head; + u16 flags = BATADV_NO_FLAGS; + + rcu_read_lock(); + head = &tt_global->orig_list; + hlist_for_each_entry_rcu(orig_entry, head, list) + flags |= orig_entry->flags; + rcu_read_unlock(); + + flags |= tt_global->common.flags & (~BATADV_TT_SYNC_MASK); + tt_global->common.flags = flags; +} + +/** + * batadv_tt_global_orig_entry_add - add or update a TT orig entry + * @tt_global: the TT global entry to add an orig entry in + * @orig_node: the originator to add an orig entry for + * @ttvn: translation table version number of this changeset + * @flags: TT sync flags + */ static void batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, - struct batadv_orig_node *orig_node, int ttvn) + struct batadv_orig_node *orig_node, int ttvn, + u8 flags) { struct batadv_tt_orig_list_entry *orig_entry; @@ -1561,7 +1593,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, * was added during a "temporary client detection" */ orig_entry->ttvn = ttvn; - goto out; + orig_entry->flags = flags; + goto sync_flags; } orig_entry = kmem_cache_zalloc(batadv_tt_orig_cache, GFP_ATOMIC); @@ -1573,6 +1606,7 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, batadv_tt_global_size_inc(orig_node, tt_global->common.vid); orig_entry->orig_node = orig_node; orig_entry->ttvn = ttvn; + orig_entry->flags = flags; kref_init(&orig_entry->refcount); spin_lock_bh(&tt_global->list_lock); @@ -1582,6 +1616,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, spin_unlock_bh(&tt_global->list_lock); atomic_inc(&tt_global->orig_list_count); +sync_flags: + batadv_tt_global_sync_flags(tt_global); out: if (orig_entry) batadv_tt_orig_list_entry_put(orig_entry); @@ -1703,10 +1739,10 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } /* the change can carry possible "attribute" flags like the - * TT_CLIENT_WIFI, therefore they have to be copied in the + * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ - common->flags |= flags; + common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a @@ -1723,7 +1759,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, } add_orig_entry: /* add the new orig_entry (if needed) or update it */ - batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn); + batadv_tt_global_orig_entry_add(tt_global_entry, orig_node, ttvn, + flags & BATADV_TT_SYNC_MASK); batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new global tt entry: %pM (vid: %d, via %pM)\n", @@ -1946,6 +1983,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_tt_orig_list_entry *orig, bool best) { + u16 flags = (common->flags & (~BATADV_TT_SYNC_MASK)) | orig->flags; void *hdr; struct batadv_orig_node_vlan *vlan; u8 last_ttvn; @@ -1975,7 +2013,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, nla_put_u8(msg, BATADV_ATTR_TT_LAST_TTVN, last_ttvn) || nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || - nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, flags)) goto nla_put_failure; if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) @@ -2589,6 +2627,7 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; + struct batadv_tt_orig_list_entry *tt_orig; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; @@ -2627,8 +2666,9 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* find out if this global entry is announced by this * originator */ - if (!batadv_tt_global_entry_has_orig(tt_global, - orig_node)) + tt_orig = batadv_tt_global_orig_entry_find(tt_global, + orig_node); + if (!tt_orig) continue; /* use network order to read the VID: this ensures that @@ -2640,10 +2680,12 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, /* compute the CRC on flags that have to be kept in sync * among nodes */ - flags = tt_common->flags & BATADV_TT_SYNC_MASK; + flags = tt_orig->flags; crc_tmp = crc32c(crc_tmp, &flags, sizeof(flags)); crc ^= crc32c(crc_tmp, tt_common->addr, ETH_ALEN); + + batadv_tt_orig_list_entry_put(tt_orig); } rcu_read_unlock(); } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ea43a6449247..a62795868794 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1260,6 +1260,7 @@ struct batadv_tt_global_entry { * struct batadv_tt_orig_list_entry - orig node announcing a non-mesh client * @orig_node: pointer to orig node announcing this non-mesh client * @ttvn: translation table version number which added the non-mesh client + * @flags: per orig entry TT sync flags * @list: list node for batadv_tt_global_entry::orig_list * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner @@ -1267,6 +1268,7 @@ struct batadv_tt_global_entry { struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; u8 ttvn; + u8 flags; struct hlist_node list; struct kref refcount; struct rcu_head rcu; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 68f951b3e85a..db82a40875e8 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -45,6 +45,11 @@ config BT_BREDR bool "Bluetooth Classic (BR/EDR) features" depends on BT default y + help + Bluetooth Classic includes support for Basic Rate (BR) + available with Bluetooth version 1.0b or later and support + for Enhanced Data Rate (EDR) available with Bluetooth + version 2.0 or later. source "net/bluetooth/rfcomm/Kconfig" @@ -58,11 +63,18 @@ config BT_HS bool "Bluetooth High Speed (HS) features" depends on BT_BREDR default y + help + Bluetooth High Speed includes support for off-loading + Bluetooth connections via 802.11 (wifi) physical layer + available with Bluetooth version 3.0 or later. config BT_LE bool "Bluetooth Low Energy (LE) features" depends on BT default y + help + Bluetooth Low Energy includes support low-energy physical + layer available with Bluetooth version 4.0 or later. config BT_6LOWPAN tristate "Bluetooth 6LoWPAN support" diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c index ee92c925ecc5..34a1227f4391 100644 --- a/net/bluetooth/selftest.c +++ b/net/bluetooth/selftest.c @@ -164,7 +164,7 @@ static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32], ret = -EINVAL; out: - kfree(dhkey_a); + kfree(tmp); return ret; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index a5e4a736a984..a79b648aac88 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -169,29 +169,11 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) } } -static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) -{ - struct switchdev_obj_port_fdb fdb = { - .obj = { - .orig_dev = f->dst->dev, - .id = SWITCHDEV_OBJ_ID_PORT_FDB, - .flags = SWITCHDEV_F_DEFER, - }, - .vid = f->vlan_id, - }; - - ether_addr_copy(fdb.addr, f->addr.addr); - switchdev_port_obj_del(f->dst->dev, &fdb.obj); -} - static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) { if (f->is_static) fdb_del_hw_addr(br, f->addr.addr); - if (f->added_by_external_learn) - fdb_del_external_learn(f); - hlist_del_init_rcu(&f->hlist); fdb_notify(br, f, RTM_DELNEIGH); call_rcu(&f->rcu, fdb_rcu_free); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index a0b11e7d67d9..ca01def49af0 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -713,9 +713,9 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void br_mdb_init(void) { - rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, NULL); - rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, NULL); - rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_GETMDB, NULL, br_mdb_dump, 0); + rtnl_register(PF_BRIDGE, RTM_NEWMDB, br_mdb_add, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_DELMDB, br_mdb_del, NULL, 0); } void br_mdb_uninit(void) diff --git a/net/can/gw.c b/net/can/gw.c index 29748d844c3f..73a02af4b5d7 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1031,15 +1031,15 @@ static __init int cgw_module_init(void) notifier.notifier_call = cgw_notifier; register_netdevice_notifier(¬ifier); - if (__rtnl_register(PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, NULL)) { + if (__rtnl_register(PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0)) { unregister_netdevice_notifier(¬ifier); kmem_cache_destroy(cgw_cache); return -ENOBUFS; } /* Only the first call to __rtnl_register can fail */ - __rtnl_register(PF_CAN, RTM_NEWROUTE, cgw_create_job, NULL, NULL); - __rtnl_register(PF_CAN, RTM_DELROUTE, cgw_remove_job, NULL, NULL); + __rtnl_register(PF_CAN, RTM_NEWROUTE, cgw_create_job, NULL, 0); + __rtnl_register(PF_CAN, RTM_DELROUTE, cgw_remove_job, NULL, 0); return 0; } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 746b145bfd11..417df675c71b 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -306,7 +306,7 @@ static __u32 *get_choose_arg_weights(const struct crush_bucket_straw2 *bucket, const struct crush_choose_arg *arg, int position) { - if (!arg || !arg->weight_set || arg->weight_set_size == 0) + if (!arg || !arg->weight_set) return bucket->item_weights; if (position >= arg->weight_set_size) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b7cc615d42ef..a67298c7e0cd 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1287,10 +1287,10 @@ static void prepare_write_message(struct ceph_connection *con) if (m->needs_out_seq) { m->hdr.seq = cpu_to_le64(++con->out_seq); m->needs_out_seq = false; - } - if (con->ops->reencode_message) - con->ops->reencode_message(m); + if (con->ops->reencode_message) + con->ops->reencode_message(m); + } dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n", m, con->out_seq, le16_to_cpu(m->hdr.type), diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 901bb8221366..dcfbdd74dfd1 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1337,6 +1337,8 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, bool legacy_change; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); + bool recovery_deletes = ceph_osdmap_flag(osdc, + CEPH_OSDMAP_RECOVERY_DELETES); enum calc_target_result ct_res; int ret; @@ -1399,6 +1401,8 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, pi->pg_num, t->sort_bitwise, sort_bitwise, + t->recovery_deletes, + recovery_deletes, &last_pgid)) force_resend = true; @@ -1421,6 +1425,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, t->pg_num = pi->pg_num; t->pg_num_mask = pi->pg_num_mask; t->sort_bitwise = sort_bitwise; + t->recovery_deletes = recovery_deletes; t->osd = acting.primary; } @@ -1918,10 +1923,12 @@ static void encode_request_partial(struct ceph_osd_request *req, } ceph_encode_32(&p, req->r_attempts); /* retry_attempt */ - BUG_ON(p != end - 8); /* space for features */ + BUG_ON(p > end - 8); /* space for features */ msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */ /* front_len is finalized in encode_request_finish() */ + msg->front.iov_len = p - msg->front.iov_base; + msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); msg->hdr.data_len = cpu_to_le32(data_len); /* * The header "data_off" is a hint to the receiver allowing it @@ -1937,11 +1944,12 @@ static void encode_request_partial(struct ceph_osd_request *req, static void encode_request_finish(struct ceph_msg *msg) { void *p = msg->front.iov_base; + void *const partial_end = p + msg->front.iov_len; void *const end = p + msg->front_alloc_len; if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) { /* luminous OSD -- encode features and be done */ - p = end - 8; + p = partial_end; ceph_encode_64(&p, msg->con->peer_features); } else { struct { @@ -1984,7 +1992,7 @@ static void encode_request_finish(struct ceph_msg *msg) oid_len = p - oid; tail = p; - tail_len = (end - p) - 8; + tail_len = partial_end - p; p = msg->front.iov_base; ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc)); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 64ae9f89773a..f358d0bfa76b 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -295,6 +295,10 @@ static int decode_choose_args(void **p, void *end, struct crush_map *c) ret = decode_choose_arg(p, end, arg); if (ret) goto fail; + + if (arg->ids_size && + arg->ids_size != c->buckets[bucket_index]->size) + goto e_inval; } insert_choose_arg_map(&c->choose_args, arg_map); @@ -2078,6 +2082,8 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting, u32 new_pg_num, bool old_sort_bitwise, bool new_sort_bitwise, + bool old_recovery_deletes, + bool new_recovery_deletes, const struct ceph_pg *pgid) { return !osds_equal(old_acting, new_acting) || @@ -2085,7 +2091,8 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting, old_size != new_size || old_min_size != new_min_size || ceph_pg_is_split(pgid, old_pg_num, new_pg_num) || - old_sort_bitwise != new_sort_bitwise; + old_sort_bitwise != new_sort_bitwise || + old_recovery_deletes != new_recovery_deletes; } static int calc_pg_rank(int osd, const struct ceph_osds *acting) @@ -2301,10 +2308,17 @@ static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi, } } +/* + * Magic value used for a "default" fallback choose_args, used if the + * crush_choose_arg_map passed to do_crush() does not exist. If this + * also doesn't exist, fall back to canonical weights. + */ +#define CEPH_DEFAULT_CHOOSE_ARGS -1 + static int do_crush(struct ceph_osdmap *map, int ruleno, int x, int *result, int result_max, const __u32 *weight, int weight_max, - u64 choose_args_index) + s64 choose_args_index) { struct crush_choose_arg_map *arg_map; int r; @@ -2313,6 +2327,9 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x, arg_map = lookup_choose_arg_map(&map->crush->choose_args, choose_args_index); + if (!arg_map) + arg_map = lookup_choose_arg_map(&map->crush->choose_args, + CEPH_DEFAULT_CHOOSE_ARGS); mutex_lock(&map->crush_workspace_mutex); r = crush_do_rule(map->crush, ruleno, x, result, result_max, @@ -2423,40 +2440,23 @@ static void apply_upmap(struct ceph_osdmap *osdmap, for (i = 0; i < pg->pg_upmap.len; i++) raw->osds[i] = pg->pg_upmap.osds[i]; raw->size = pg->pg_upmap.len; - return; + /* check and apply pg_upmap_items, if any */ } pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid); if (pg) { - /* - * Note: this approach does not allow a bidirectional swap, - * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1]. - */ - for (i = 0; i < pg->pg_upmap_items.len; i++) { - int from = pg->pg_upmap_items.from_to[i][0]; - int to = pg->pg_upmap_items.from_to[i][1]; - int pos = -1; - bool exists = false; - - /* make sure replacement doesn't already appear */ - for (j = 0; j < raw->size; j++) { - int osd = raw->osds[j]; - - if (osd == to) { - exists = true; + for (i = 0; i < raw->size; i++) { + for (j = 0; j < pg->pg_upmap_items.len; j++) { + int from = pg->pg_upmap_items.from_to[j][0]; + int to = pg->pg_upmap_items.from_to[j][1]; + + if (from == raw->osds[i]) { + if (!(to != CRUSH_ITEM_NONE && + to < osdmap->max_osd && + osdmap->osd_weight[to] == 0)) + raw->osds[i] = to; break; } - /* ignore mapping if target is marked out */ - if (osd == from && pos < 0 && - !(to != CRUSH_ITEM_NONE && - to < osdmap->max_osd && - osdmap->osd_weight[to] == 0)) { - pos = j; - } - } - if (!exists && pos >= 0) { - raw->osds[pos] = to; - return; } } } diff --git a/net/core/Makefile b/net/core/Makefile index d501c4278015..56d771a887b6 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -9,7 +9,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ - sock_diag.o dev_ioctl.o tso.o sock_reuseport.o + sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ + fib_notifier.o obj-y += net-sysfs.o obj-$(CONFIG_PROC_FS) += net-procfs.o diff --git a/net/core/datagram.c b/net/core/datagram.c index ee5647bd91b3..2f3277945d35 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -573,27 +573,12 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iter); -/** - * zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter - * @skb: buffer to copy - * @from: the source to copy from - * - * The function will first copy up to headlen, and then pin the userspace - * pages and build frags through them. - * - * Returns 0, -EFAULT or -EMSGSIZE. - */ -int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) +int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length) { - int len = iov_iter_count(from); - int copy = min_t(int, skb_headlen(skb), len); - int frag = 0; + int frag = skb_shinfo(skb)->nr_frags; - /* copy up to skb headlen */ - if (skb_copy_datagram_from_iter(skb, 0, from, copy)) - return -EFAULT; - - while (iov_iter_count(from)) { + while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; size_t start; ssize_t copied; @@ -603,18 +588,24 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; - copied = iov_iter_get_pages(from, pages, ~0U, + copied = iov_iter_get_pages(from, pages, length, MAX_SKB_FRAGS - frag, &start); if (copied < 0) return -EFAULT; iov_iter_advance(from, copied); + length -= copied; truesize = PAGE_ALIGN(copied + start); skb->data_len += copied; skb->len += copied; skb->truesize += truesize; - refcount_add(truesize, &skb->sk->sk_wmem_alloc); + if (sk && sk->sk_type == SOCK_STREAM) { + sk->sk_wmem_queued += truesize; + sk_mem_charge(sk, truesize); + } else { + refcount_add(truesize, &skb->sk->sk_wmem_alloc); + } while (copied) { int size = min_t(int, copied, PAGE_SIZE - start); skb_fill_page_desc(skb, frag++, pages[n], start, size); @@ -625,6 +616,28 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) } return 0; } +EXPORT_SYMBOL(__zerocopy_sg_from_iter); + +/** + * zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter + * @skb: buffer to copy + * @from: the source to copy from + * + * The function will first copy up to headlen, and then pin the userspace + * pages and build frags through them. + * + * Returns 0, -EFAULT or -EMSGSIZE. + */ +int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) +{ + int copy = min_t(int, skb_headlen(skb), iov_iter_count(from)); + + /* copy up to skb headlen */ + if (skb_copy_datagram_from_iter(skb, 0, from, copy)) + return -EFAULT; + + return __zerocopy_sg_from_iter(NULL, skb, from, ~0U); +} EXPORT_SYMBOL(zerocopy_sg_from_iter); static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, diff --git a/net/core/dev.c b/net/core/dev.c index 8ea6b4b42611..40b28e417072 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1853,7 +1853,7 @@ static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { - if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); @@ -2731,8 +2731,7 @@ EXPORT_SYMBOL(skb_mac_gso_segment); static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL && - skb->ip_summed != CHECKSUM_NONE; + return skb->ip_summed != CHECKSUM_PARTIAL; return skb->ip_summed == CHECKSUM_NONE; } @@ -3920,7 +3919,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* When doing generic XDP we have to bypass the qdisc layer and the * network taps in order to match in-driver-XDP behavior. */ -static void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) +void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -3941,13 +3940,12 @@ static void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) kfree_skb(skb); } } +EXPORT_SYMBOL_GPL(generic_xdp_tx); static struct static_key generic_xdp_needed __read_mostly; -static int do_xdp_generic(struct sk_buff *skb) +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) { - struct bpf_prog *xdp_prog = rcu_dereference(skb->dev->xdp_prog); - if (xdp_prog) { u32 act = netif_receive_generic_xdp(skb, xdp_prog); int err; @@ -3972,6 +3970,7 @@ out_redir: kfree_skb(skb); return XDP_DROP; } +EXPORT_SYMBOL_GPL(do_xdp_generic); static int netif_rx_internal(struct sk_buff *skb) { @@ -3982,7 +3981,8 @@ static int netif_rx_internal(struct sk_buff *skb) trace_netif_rx(skb); if (static_key_false(&generic_xdp_needed)) { - int ret = do_xdp_generic(skb); + int ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), + skb); /* Consider XDP consuming the packet a success from * the netdev point of view we do not want to count @@ -4412,7 +4412,7 @@ skip_classify: } if (pt_prev) { - if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; else ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); @@ -4503,7 +4503,8 @@ static int netif_receive_skb_internal(struct sk_buff *skb) rcu_read_lock(); if (static_key_false(&generic_xdp_needed)) { - int ret = do_xdp_generic(skb); + int ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), + skb); if (ret != XDP_PASS) { rcu_read_unlock(); diff --git a/net/core/dst.c b/net/core/dst.c index 00aa972ad1a1..d6ead757c258 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -55,7 +55,7 @@ const struct dst_metrics dst_default_metrics = { * We really want to avoid false sharing on this variable, and catch * any writes on it. */ - .refcnt = ATOMIC_INIT(1), + .refcnt = REFCOUNT_INIT(1), }; void dst_init(struct dst_entry *dst, struct dst_ops *ops, @@ -213,7 +213,7 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); unsigned long prev, new; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 1); memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); new = (unsigned long) p; @@ -225,7 +225,7 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) if (prev & DST_METRICS_READ_ONLY) p = NULL; } else if (prev & DST_METRICS_REFCOUNTED) { - if (atomic_dec_and_test(&old_p->refcnt)) + if (refcount_dec_and_test(&old_p->refcnt)) kfree(old_p); } } diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c new file mode 100644 index 000000000000..292aab83702f --- /dev/null +++ b/net/core/fib_notifier.c @@ -0,0 +1,164 @@ +#include <linux/rtnetlink.h> +#include <linux/notifier.h> +#include <linux/rcupdate.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <net/net_namespace.h> +#include <net/fib_notifier.h> + +static ATOMIC_NOTIFIER_HEAD(fib_chain); + +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->net = net; + return nb->notifier_call(nb, event_type, info); +} +EXPORT_SYMBOL(call_fib_notifier); + +int call_fib_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->net = net; + return atomic_notifier_call_chain(&fib_chain, event_type, info); +} +EXPORT_SYMBOL(call_fib_notifiers); + +static unsigned int fib_seq_sum(void) +{ + struct fib_notifier_ops *ops; + unsigned int fib_seq = 0; + struct net *net; + + rtnl_lock(); + for_each_net(net) { + list_for_each_entry(ops, &net->fib_notifier_ops, list) + fib_seq += ops->fib_seq_read(net); + } + rtnl_unlock(); + + return fib_seq; +} + +static int fib_net_dump(struct net *net, struct notifier_block *nb) +{ + struct fib_notifier_ops *ops; + + list_for_each_entry_rcu(ops, &net->fib_notifier_ops, list) { + int err = ops->fib_dump(net, nb); + + if (err) + return err; + } + + return 0; +} + +static bool fib_dump_is_consistent(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb), + unsigned int fib_seq) +{ + atomic_notifier_chain_register(&fib_chain, nb); + if (fib_seq == fib_seq_sum()) + return true; + atomic_notifier_chain_unregister(&fib_chain, nb); + if (cb) + cb(nb); + return false; +} + +#define FIB_DUMP_MAX_RETRIES 5 +int register_fib_notifier(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb)) +{ + int retries = 0; + int err; + + do { + unsigned int fib_seq = fib_seq_sum(); + struct net *net; + + rcu_read_lock(); + for_each_net_rcu(net) { + err = fib_net_dump(net, nb); + if (err) + goto err_fib_net_dump; + } + rcu_read_unlock(); + + if (fib_dump_is_consistent(nb, cb, fib_seq)) + return 0; + } while (++retries < FIB_DUMP_MAX_RETRIES); + + return -EBUSY; + +err_fib_net_dump: + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(register_fib_notifier); + +int unregister_fib_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&fib_chain, nb); +} +EXPORT_SYMBOL(unregister_fib_notifier); + +static int __fib_notifier_ops_register(struct fib_notifier_ops *ops, + struct net *net) +{ + struct fib_notifier_ops *o; + + list_for_each_entry(o, &net->fib_notifier_ops, list) + if (ops->family == o->family) + return -EEXIST; + list_add_tail_rcu(&ops->list, &net->fib_notifier_ops); + return 0; +} + +struct fib_notifier_ops * +fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net) +{ + struct fib_notifier_ops *ops; + int err; + + ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); + if (!ops) + return ERR_PTR(-ENOMEM); + + err = __fib_notifier_ops_register(ops, net); + if (err) + goto err_register; + + return ops; + +err_register: + kfree(ops); + return ERR_PTR(err); +} +EXPORT_SYMBOL(fib_notifier_ops_register); + +void fib_notifier_ops_unregister(struct fib_notifier_ops *ops) +{ + list_del_rcu(&ops->list); + kfree_rcu(ops, rcu); +} +EXPORT_SYMBOL(fib_notifier_ops_unregister); + +static int __net_init fib_notifier_net_init(struct net *net) +{ + INIT_LIST_HEAD(&net->fib_notifier_ops); + return 0; +} + +static struct pernet_operations fib_notifier_net_ops = { + .init = fib_notifier_net_init, +}; + +static int __init fib_notifier_init(void) +{ + return register_pernet_subsys(&fib_notifier_net_ops); +} + +subsys_initcall(fib_notifier_init); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index fdcb1bcd2afa..9a6d97c1d810 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -299,6 +299,67 @@ out: } EXPORT_SYMBOL_GPL(fib_rules_lookup); +static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_rule *rule, int family) +{ + struct fib_rule_notifier_info info = { + .info.family = family, + .rule = rule, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + +static int call_fib_rule_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib_rule *rule, + struct fib_rules_ops *ops) +{ + struct fib_rule_notifier_info info = { + .info.family = ops->family, + .rule = rule, + }; + + ops->fib_rules_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + +/* Called with rcu_read_lock() */ +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) +{ + struct fib_rules_ops *ops; + struct fib_rule *rule; + + ops = lookup_rules_ops(net, family); + if (!ops) + return -EAFNOSUPPORT; + list_for_each_entry_rcu(rule, &ops->rules_list, list) + call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule, + family); + rules_ops_put(ops); + + return 0; +} +EXPORT_SYMBOL_GPL(fib_rules_dump); + +unsigned int fib_rules_seq_read(struct net *net, int family) +{ + unsigned int fib_rules_seq; + struct fib_rules_ops *ops; + + ASSERT_RTNL(); + + ops = lookup_rules_ops(net, family); + if (!ops) + return 0; + fib_rules_seq = ops->fib_rules_seq; + rules_ops_put(ops); + + return fib_rules_seq; +} +EXPORT_SYMBOL_GPL(fib_rules_seq_read); + static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rules_ops *ops) { @@ -548,6 +609,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, if (rule->tun_id) ip_tunnel_need_metadata(); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); @@ -687,6 +749,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, } } + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); @@ -963,9 +1026,9 @@ static struct pernet_operations fib_rules_net_ops = { static int __init fib_rules_init(void) { int err; - rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) diff --git a/net/core/filter.c b/net/core/filter.c index 7e9708653c6f..fa2115695037 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -514,14 +514,27 @@ do_pass: break; } - /* Convert JEQ into JNE when 'jump_true' is next insn. */ - if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { - insn->code = BPF_JMP | BPF_JNE | bpf_src; + /* Convert some jumps when 'jump_true' is next insn. */ + if (fp->jt == 0) { + switch (BPF_OP(fp->code)) { + case BPF_JEQ: + insn->code = BPF_JMP | BPF_JNE | bpf_src; + break; + case BPF_JGT: + insn->code = BPF_JMP | BPF_JLE | bpf_src; + break; + case BPF_JGE: + insn->code = BPF_JMP | BPF_JLT | bpf_src; + break; + default: + goto jmp_rest; + } + target = i + fp->jf + 1; BPF_EMIT_JMP; break; } - +jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; @@ -1845,6 +1858,45 @@ static const struct bpf_func_proto bpf_redirect_map_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + if (unlikely(flags)) + return SK_ABORTED; + + ri->ifindex = key; + ri->flags = flags; + ri->map = map; + + return SK_REDIRECT; +} + +struct sock *do_sk_redirect_map(void) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct sock *sk = NULL; + + if (ri->map) { + sk = __sock_map_lookup_elem(ri->map, ri->ifindex); + + ri->ifindex = 0; + ri->map = NULL; + /* we do not clear flags for future lookup */ + } + + return sk; +} + +static const struct bpf_func_proto bpf_sk_redirect_map_proto = { + .func = bpf_sk_redirect_map, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@ -2483,14 +2535,16 @@ int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_map *map = ri->map; u32 index = ri->ifindex; struct net_device *fwd; - int err = -EINVAL; + int err; ri->ifindex = 0; ri->map = NULL; fwd = __dev_map_lookup_elem(map, index); - if (!fwd) + if (!fwd) { + err = -EINVAL; goto out; + } if (ri->map_to_flush && (ri->map_to_flush != map)) xdp_do_flush_map(); @@ -2500,7 +2554,7 @@ int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, ri->map_to_flush = map; out: - trace_xdp_redirect(dev, fwd, xdp_prog, XDP_REDIRECT); + trace_xdp_redirect(dev, fwd, xdp_prog, XDP_REDIRECT, err); return err; } @@ -2509,21 +2563,24 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, { struct redirect_info *ri = this_cpu_ptr(&redirect_info); struct net_device *fwd; + u32 index = ri->ifindex; + int err; if (ri->map) return xdp_do_redirect_map(dev, xdp, xdp_prog); - fwd = dev_get_by_index_rcu(dev_net(dev), ri->ifindex); + fwd = dev_get_by_index_rcu(dev_net(dev), index); ri->ifindex = 0; - ri->map = NULL; if (unlikely(!fwd)) { - bpf_warn_invalid_xdp_redirect(ri->ifindex); - return -EINVAL; + bpf_warn_invalid_xdp_redirect(index); + err = -EINVAL; + goto out; } - trace_xdp_redirect(dev, fwd, xdp_prog, XDP_REDIRECT); - - return __bpf_tx_xdp(fwd, NULL, xdp, 0); + err = __bpf_tx_xdp(fwd, NULL, xdp, 0); +out: + trace_xdp_redirect(dev, fwd, xdp_prog, XDP_REDIRECT, err); + return err; } EXPORT_SYMBOL_GPL(xdp_do_redirect); @@ -2531,11 +2588,12 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned int len; + u32 index = ri->ifindex; - dev = dev_get_by_index_rcu(dev_net(dev), ri->ifindex); + dev = dev_get_by_index_rcu(dev_net(dev), index); ri->ifindex = 0; if (unlikely(!dev)) { - bpf_warn_invalid_xdp_redirect(ri->ifindex); + bpf_warn_invalid_xdp_redirect(index); goto err; } @@ -3214,6 +3272,32 @@ static const struct bpf_func_proto * switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_setsockopt_proto; + case BPF_FUNC_sock_map_update: + return &bpf_sock_map_update_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_store_bytes: + return &bpf_skb_store_bytes_proto; + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; + case BPF_FUNC_skb_change_tail: + return &bpf_skb_change_tail_proto; + case BPF_FUNC_skb_change_head: + return &bpf_skb_change_head_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_proto; + case BPF_FUNC_get_socket_uid: + return &bpf_get_socket_uid_proto; + case BPF_FUNC_sk_redirect_map: + return &bpf_sk_redirect_map_proto; default: return bpf_base_func_proto(func_id); } @@ -3271,6 +3355,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; + case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): + case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): + case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): + case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) @@ -3299,6 +3387,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): + case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -3320,6 +3409,7 @@ static bool lwt_is_valid_access(int off, int size, { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -3370,8 +3460,8 @@ static bool sock_filter_is_valid_access(int off, int size, return true; } -static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, - const struct bpf_prog *prog) +static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog, int drop_verdict) { struct bpf_insn *insn = insn_buf; @@ -3398,7 +3488,7 @@ static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, * return TC_ACT_SHOT; */ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); - *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, TC_ACT_SHOT); + *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, drop_verdict); *insn++ = BPF_EXIT_INSN(); /* restore: */ @@ -3409,6 +3499,12 @@ static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, return insn - insn_buf; } +static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + return bpf_unclone_prologue(insn_buf, direct_write, prog, TC_ACT_SHOT); +} + static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) @@ -3433,6 +3529,8 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; + case bpf_ctx_range_till(struct __sk_buff, family, local_port): + return false; } return bpf_skb_is_valid_access(off, size, type, info); @@ -3510,6 +3608,41 @@ static bool sock_ops_is_valid_access(int off, int size, return __is_valid_sock_ops_access(off, size); } +static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + return bpf_unclone_prologue(insn_buf, direct_write, prog, SK_DROP); +} + +static bool sk_skb_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, mark): + case bpf_ctx_range(struct __sk_buff, tc_index): + case bpf_ctx_range(struct __sk_buff, priority): + break; + default: + return false; + } + } + + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + return false; + case bpf_ctx_range(struct __sk_buff, data): + info->reg_type = PTR_TO_PACKET; + break; + case bpf_ctx_range(struct __sk_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + break; + } + + return bpf_skb_is_valid_access(off, size, type, info); +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@ -3675,6 +3808,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else + *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else @@ -3690,9 +3824,110 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else + *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; + case offsetof(struct __sk_buff, family): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_family, + 2, target_size)); + break; + case offsetof(struct __sk_buff, remote_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_daddr, + 4, target_size)); + break; + case offsetof(struct __sk_buff, local_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_rcv_saddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_rcv_saddr, + 4, target_size)); + break; + case offsetof(struct __sk_buff, remote_ip6[0]) ... + offsetof(struct __sk_buff, remote_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_daddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct __sk_buff, remote_ip6[0]); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_daddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + case offsetof(struct __sk_buff, local_ip6[0]) ... + offsetof(struct __sk_buff, local_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct __sk_buff, local_ip6[0]); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct __sk_buff, remote_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_dport, + 2, target_size)); +#ifndef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); +#endif + break; + + case offsetof(struct __sk_buff, local_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_num, 2, target_size)); + break; } return insn - insn_buf; @@ -3977,6 +4212,13 @@ const struct bpf_verifier_ops sock_ops_prog_ops = { .convert_ctx_access = sock_ops_convert_ctx_access, }; +const struct bpf_verifier_ops sk_skb_prog_ops = { + .get_func_proto = sk_skb_func_proto, + .is_valid_access = sk_skb_is_valid_access, + .convert_ctx_access = bpf_convert_ctx_access, + .gen_prologue = sk_skb_prologue, +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index fc5fc4594c90..e2eaa1ff948d 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -4,6 +4,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> +#include <net/dsa.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> @@ -440,6 +441,19 @@ bool __skb_flow_dissect(const struct sk_buff *skb, skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); +#if IS_ENABLED(CONFIG_NET_DSA) + if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) { + const struct dsa_device_ops *ops; + int offset; + + ops = skb->dev->dsa_ptr->tag_ops; + if (ops->flow_dissect && + !ops->flow_dissect(skb, &proto, &offset)) { + hlen -= offset; + nhoff += offset; + } + } +#endif } /* It is ensured by skb_flow_dissector_init() that control key will @@ -998,51 +1012,6 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) } EXPORT_SYMBOL(skb_get_hash_perturb); -__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) -{ - struct flow_keys keys; - - memset(&keys, 0, sizeof(keys)); - - memcpy(&keys.addrs.v6addrs.src, &fl6->saddr, - sizeof(keys.addrs.v6addrs.src)); - memcpy(&keys.addrs.v6addrs.dst, &fl6->daddr, - sizeof(keys.addrs.v6addrs.dst)); - keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; - keys.ports.src = fl6->fl6_sport; - keys.ports.dst = fl6->fl6_dport; - keys.keyid.keyid = fl6->fl6_gre_key; - keys.tags.flow_label = (__force u32)fl6->flowlabel; - keys.basic.ip_proto = fl6->flowi6_proto; - - __skb_set_sw_hash(skb, flow_hash_from_keys(&keys), - flow_keys_have_l4(&keys)); - - return skb->hash; -} -EXPORT_SYMBOL(__skb_get_hash_flowi6); - -__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) -{ - struct flow_keys keys; - - memset(&keys, 0, sizeof(keys)); - - keys.addrs.v4addrs.src = fl4->saddr; - keys.addrs.v4addrs.dst = fl4->daddr; - keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; - keys.ports.src = fl4->fl4_sport; - keys.ports.dst = fl4->fl4_dport; - keys.keyid.keyid = fl4->fl4_gre_key; - keys.basic.ip_proto = fl4->flowi4_proto; - - __skb_set_sw_hash(skb, flow_hash_from_keys(&keys), - flow_keys_have_l4(&keys)); - - return skb->hash; -} -EXPORT_SYMBOL(__skb_get_hash_flowi4); - u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen) { diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index d9cb3532f1dd..0b171756453c 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -44,6 +44,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "SEG6"; case LWTUNNEL_ENCAP_BPF: return "BPF"; + case LWTUNNEL_ENCAP_SEG6_LOCAL: + return "SEG6LOCAL"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: @@ -65,7 +67,7 @@ struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) return lws; } -EXPORT_SYMBOL(lwtunnel_state_alloc); +EXPORT_SYMBOL_GPL(lwtunnel_state_alloc); static const struct lwtunnel_encap_ops __rcu * lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; @@ -80,7 +82,7 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, &lwtun_encaps[num], NULL, ops) ? 0 : -1; } -EXPORT_SYMBOL(lwtunnel_encap_add_ops); +EXPORT_SYMBOL_GPL(lwtunnel_encap_add_ops); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, unsigned int encap_type) @@ -99,7 +101,7 @@ int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, return ret; } -EXPORT_SYMBOL(lwtunnel_encap_del_ops); +EXPORT_SYMBOL_GPL(lwtunnel_encap_del_ops); int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, @@ -138,7 +140,7 @@ int lwtunnel_build_state(u16 encap_type, return ret; } -EXPORT_SYMBOL(lwtunnel_build_state); +EXPORT_SYMBOL_GPL(lwtunnel_build_state); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { @@ -175,7 +177,7 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) return ret; } -EXPORT_SYMBOL(lwtunnel_valid_encap_type); +EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, struct netlink_ext_ack *extack) @@ -205,7 +207,7 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, return 0; } -EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr); +EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type_attr); void lwtstate_free(struct lwtunnel_state *lws) { @@ -219,7 +221,7 @@ void lwtstate_free(struct lwtunnel_state *lws) } module_put(ops->owner); } -EXPORT_SYMBOL(lwtstate_free); +EXPORT_SYMBOL_GPL(lwtstate_free); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { @@ -259,7 +261,7 @@ nla_put_failure: return (ret == -EOPNOTSUPP ? 0 : ret); } -EXPORT_SYMBOL(lwtunnel_fill_encap); +EXPORT_SYMBOL_GPL(lwtunnel_fill_encap); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { @@ -281,7 +283,7 @@ int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) return ret; } -EXPORT_SYMBOL(lwtunnel_get_encap_size); +EXPORT_SYMBOL_GPL(lwtunnel_get_encap_size); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { @@ -309,7 +311,7 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) return ret; } -EXPORT_SYMBOL(lwtunnel_cmp_encap); +EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -343,7 +345,7 @@ drop: return ret; } -EXPORT_SYMBOL(lwtunnel_output); +EXPORT_SYMBOL_GPL(lwtunnel_output); int lwtunnel_xmit(struct sk_buff *skb) { @@ -378,7 +380,7 @@ drop: return ret; } -EXPORT_SYMBOL(lwtunnel_xmit); +EXPORT_SYMBOL_GPL(lwtunnel_xmit); int lwtunnel_input(struct sk_buff *skb) { @@ -412,4 +414,4 @@ drop: return ret; } -EXPORT_SYMBOL(lwtunnel_input); +EXPORT_SYMBOL_GPL(lwtunnel_input); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d0713627deb6..16a1a4c4eb57 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3261,13 +3261,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister); static int __init neigh_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, 0); rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, - NULL); - rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL); + 0); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, 0); return 0; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index b4f9922b6f23..927a6dcbad96 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -97,7 +97,8 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, return restart_syscall(); if (dev_isalive(netdev)) { - if ((ret = (*set)(netdev, new)) == 0) + ret = (*set)(netdev, new); + if (ret == 0) ret = len; } rtnl_unlock(); @@ -160,6 +161,7 @@ static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); + if (dev_isalive(ndev)) return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); return -EINVAL; @@ -170,7 +172,7 @@ static int change_carrier(struct net_device *dev, unsigned long new_carrier) { if (!netif_running(dev)) return -EINVAL; - return dev_change_carrier(dev, (bool) new_carrier); + return dev_change_carrier(dev, (bool)new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, @@ -183,9 +185,10 @@ static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); - if (netif_running(netdev)) { + + if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_carrier_ok(netdev)); - } + return -EINVAL; } static DEVICE_ATTR_RW(carrier); @@ -290,6 +293,7 @@ static ssize_t carrier_changes_show(struct device *dev, char *buf) { struct net_device *netdev = to_net_dev(dev); + return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_changes)); } @@ -299,7 +303,7 @@ static DEVICE_ATTR_RO(carrier_changes); static int change_mtu(struct net_device *dev, unsigned long new_mtu) { - return dev_set_mtu(dev, (int) new_mtu); + return dev_set_mtu(dev, (int)new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, @@ -311,7 +315,7 @@ NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *dev, unsigned long new_flags) { - return dev_change_flags(dev, (unsigned int) new_flags); + return dev_change_flags(dev, (unsigned int)new_flags); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, @@ -362,8 +366,8 @@ static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) } static ssize_t gro_flush_timeout_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) + struct device_attribute *attr, + const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -412,7 +416,7 @@ static DEVICE_ATTR_RW(ifalias); static int change_group(struct net_device *dev, unsigned long new_group) { - dev_set_group(dev, (int) new_group); + dev_set_group(dev, (int)new_group); return 0; } @@ -426,7 +430,7 @@ static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store); static int change_proto_down(struct net_device *dev, unsigned long proto_down) { - return dev_change_proto_down(dev, (bool) proto_down); + return dev_change_proto_down(dev, (bool)proto_down); } static ssize_t proto_down_store(struct device *dev, @@ -508,7 +512,7 @@ static ssize_t phys_switch_id_show(struct device *dev, } static DEVICE_ATTR_RO(phys_switch_id); -static struct attribute *net_class_attrs[] = { +static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, @@ -549,14 +553,14 @@ static ssize_t netstat_show(const struct device *d, ssize_t ret = -EINVAL; WARN_ON(offset > sizeof(struct rtnl_link_stats64) || - offset % sizeof(u64) != 0); + offset % sizeof(u64) != 0); read_lock(&dev_base_lock); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); - ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset)); + ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } read_unlock(&dev_base_lock); return ret; @@ -565,7 +569,7 @@ static ssize_t netstat_show(const struct device *d, /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ static ssize_t name##_show(struct device *d, \ - struct device_attribute *attr, char *buf) \ + struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ @@ -597,7 +601,7 @@ NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); NETSTAT_ENTRY(rx_nohandler); -static struct attribute *netstat_attrs[] = { +static struct attribute *netstat_attrs[] __ro_after_init = { &dev_attr_rx_packets.attr, &dev_attr_tx_packets.attr, &dev_attr_rx_bytes.attr, @@ -625,7 +629,6 @@ static struct attribute *netstat_attrs[] = { NULL }; - static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, @@ -647,33 +650,33 @@ static const struct attribute_group wireless_group = { #endif /* CONFIG_SYSFS */ #ifdef CONFIG_SYSFS -#define to_rx_queue_attr(_attr) container_of(_attr, \ - struct rx_queue_attribute, attr) +#define to_rx_queue_attr(_attr) \ + container_of(_attr, struct rx_queue_attribute, attr) #define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { - struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); + const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->show) return -EIO; - return attribute->show(queue, attribute, buf); + return attribute->show(queue, buf); } static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { - struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); + const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->store) return -EIO; - return attribute->store(queue, attribute, buf, count); + return attribute->store(queue, buf, count); } static const struct sysfs_ops rx_queue_sysfs_ops = { @@ -682,8 +685,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = { }; #ifdef CONFIG_RPS -static ssize_t show_rps_map(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attribute, char *buf) +static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) { struct rps_map *map; cpumask_var_t mask; @@ -706,8 +708,7 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, } static ssize_t store_rps_map(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attribute, - const char *buf, size_t len) + const char *buf, size_t len) { struct rps_map *old_map, *map; cpumask_var_t mask; @@ -727,8 +728,8 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, } map = kzalloc(max_t(unsigned int, - RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), - GFP_KERNEL); + RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), + GFP_KERNEL); if (!map) { free_cpumask_var(mask); return -ENOMEM; @@ -738,9 +739,9 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, for_each_cpu_and(cpu, mask, cpu_online_mask) map->cpus[i++] = cpu; - if (i) + if (i) { map->len = i; - else { + } else { kfree(map); map = NULL; } @@ -765,7 +766,6 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf) { struct rps_dev_flow_table *flow_table; @@ -788,8 +788,7 @@ static void rps_dev_flow_table_release(struct rcu_head *rcu) } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, - const char *buf, size_t len) + const char *buf, size_t len) { unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; @@ -831,8 +830,9 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, table->mask = mask; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; - } else + } else { table = NULL; + } spin_lock(&rps_dev_flow_lock); old_table = rcu_dereference_protected(queue->rps_flow_table, @@ -846,16 +846,15 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, return len; } -static struct rx_queue_attribute rps_cpus_attribute = - __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); - +static struct rx_queue_attribute rps_cpus_attribute __ro_after_init + = __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); -static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = - __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, - show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute __ro_after_init + = __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); #endif /* CONFIG_RPS */ -static struct attribute *rx_queue_default_attrs[] = { +static struct attribute *rx_queue_default_attrs[] __ro_after_init = { #ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, @@ -870,7 +869,6 @@ static void rx_queue_release(struct kobject *kobj) struct rps_map *map; struct rps_dev_flow_table *flow_table; - map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); @@ -900,7 +898,7 @@ static const void *rx_queue_namespace(struct kobject *kobj) return ns; } -static struct kobj_type rx_queue_ktype = { +static struct kobj_type rx_queue_ktype __ro_after_init = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_attrs = rx_queue_default_attrs, @@ -915,23 +913,22 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, - "rx-%u", index); + "rx-%u", index); if (error) - goto exit; + return error; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); - if (error) - goto exit; + if (error) { + kobject_put(kobj); + return error; + } } kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); return error; -exit: - kobject_put(kobj); - return error; } #endif /* CONFIG_SYSFS */ @@ -976,39 +973,40 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) */ struct netdev_queue_attribute { struct attribute attr; - ssize_t (*show)(struct netdev_queue *queue, - struct netdev_queue_attribute *attr, char *buf); + ssize_t (*show)(struct netdev_queue *queue, char *buf); ssize_t (*store)(struct netdev_queue *queue, - struct netdev_queue_attribute *attr, const char *buf, size_t len); + const char *buf, size_t len); }; -#define to_netdev_queue_attr(_attr) container_of(_attr, \ - struct netdev_queue_attribute, attr) +#define to_netdev_queue_attr(_attr) \ + container_of(_attr, struct netdev_queue_attribute, attr) #define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) static ssize_t netdev_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { - struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + const struct netdev_queue_attribute *attribute + = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->show) return -EIO; - return attribute->show(queue, attribute, buf); + return attribute->show(queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { - struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + const struct netdev_queue_attribute *attribute + = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->store) return -EIO; - return attribute->store(queue, attribute, buf, count); + return attribute->store(queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { @@ -1016,9 +1014,7 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = { .store = netdev_queue_attr_store, }; -static ssize_t show_trans_timeout(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, - char *buf) +static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) { unsigned long trans_timeout; @@ -1040,8 +1036,7 @@ static unsigned int get_netdev_queue_index(struct netdev_queue *queue) return i; } -static ssize_t show_traffic_class(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, +static ssize_t traffic_class_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; @@ -1055,16 +1050,14 @@ static ssize_t show_traffic_class(struct netdev_queue *queue, } #ifdef CONFIG_XPS -static ssize_t show_tx_maxrate(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, +static ssize_t tx_maxrate_show(struct netdev_queue *queue, char *buf) { return sprintf(buf, "%lu\n", queue->tx_maxrate); } -static ssize_t set_tx_maxrate(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, - const char *buf, size_t len) +static ssize_t tx_maxrate_store(struct netdev_queue *queue, + const char *buf, size_t len) { struct net_device *dev = queue->dev; int err, index = get_netdev_queue_index(queue); @@ -1089,16 +1082,15 @@ static ssize_t set_tx_maxrate(struct netdev_queue *queue, return err; } -static struct netdev_queue_attribute queue_tx_maxrate = - __ATTR(tx_maxrate, S_IRUGO | S_IWUSR, - show_tx_maxrate, set_tx_maxrate); +static struct netdev_queue_attribute queue_tx_maxrate __ro_after_init + = __ATTR_RW(tx_maxrate); #endif -static struct netdev_queue_attribute queue_trans_timeout = - __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); +static struct netdev_queue_attribute queue_trans_timeout __ro_after_init + = __ATTR_RO(tx_timeout); -static struct netdev_queue_attribute queue_traffic_class = - __ATTR(traffic_class, S_IRUGO, show_traffic_class, NULL); +static struct netdev_queue_attribute queue_traffic_class __ro_after_init + = __ATTR_RO(traffic_class); #ifdef CONFIG_BQL /* @@ -1115,9 +1107,9 @@ static ssize_t bql_set(const char *buf, const size_t count, unsigned int value; int err; - if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) + if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) { value = DQL_MAX_LIMIT; - else { + } else { err = kstrtouint(buf, 10, &value); if (err < 0) return err; @@ -1131,7 +1123,6 @@ static ssize_t bql_set(const char *buf, const size_t count, } static ssize_t bql_show_hold_time(struct netdev_queue *queue, - struct netdev_queue_attribute *attr, char *buf) { struct dql *dql = &queue->dql; @@ -1140,7 +1131,6 @@ static ssize_t bql_show_hold_time(struct netdev_queue *queue, } static ssize_t bql_set_hold_time(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, const char *buf, size_t len) { struct dql *dql = &queue->dql; @@ -1156,12 +1146,11 @@ static ssize_t bql_set_hold_time(struct netdev_queue *queue, return len; } -static struct netdev_queue_attribute bql_hold_time_attribute = - __ATTR(hold_time, S_IRUGO | S_IWUSR, bql_show_hold_time, - bql_set_hold_time); +static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init + = __ATTR(hold_time, S_IRUGO | S_IWUSR, + bql_show_hold_time, bql_set_hold_time); static ssize_t bql_show_inflight(struct netdev_queue *queue, - struct netdev_queue_attribute *attr, char *buf) { struct dql *dql = &queue->dql; @@ -1169,33 +1158,31 @@ static ssize_t bql_show_inflight(struct netdev_queue *queue, return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed); } -static struct netdev_queue_attribute bql_inflight_attribute = +static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, S_IRUGO, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ - struct netdev_queue_attribute *attr, \ char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ - struct netdev_queue_attribute *attr, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ } \ \ -static struct netdev_queue_attribute bql_ ## NAME ## _attribute = \ - __ATTR(NAME, S_IRUGO | S_IWUSR, bql_show_ ## NAME, \ - bql_set_ ## NAME); +static struct netdev_queue_attribute bql_ ## NAME ## _attribute __ro_after_init \ + = __ATTR(NAME, S_IRUGO | S_IWUSR, \ + bql_show_ ## NAME, bql_set_ ## NAME) -BQL_ATTR(limit, limit) -BQL_ATTR(limit_max, max_limit) -BQL_ATTR(limit_min, min_limit) +BQL_ATTR(limit, limit); +BQL_ATTR(limit_max, max_limit); +BQL_ATTR(limit_min, min_limit); -static struct attribute *dql_attrs[] = { +static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_attribute.attr, &bql_limit_max_attribute.attr, &bql_limit_min_attribute.attr, @@ -1211,8 +1198,8 @@ static const struct attribute_group dql_group = { #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS -static ssize_t show_xps_map(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, char *buf) +static ssize_t xps_cpus_show(struct netdev_queue *queue, + char *buf) { struct net_device *dev = queue->dev; int cpu, len, num_tc = 1, tc = 0; @@ -1258,9 +1245,8 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len < PAGE_SIZE ? len : -EINVAL; } -static ssize_t store_xps_map(struct netdev_queue *queue, - struct netdev_queue_attribute *attribute, - const char *buf, size_t len) +static ssize_t xps_cpus_store(struct netdev_queue *queue, + const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned long index; @@ -1288,11 +1274,11 @@ static ssize_t store_xps_map(struct netdev_queue *queue, return err ? : len; } -static struct netdev_queue_attribute xps_cpus_attribute = - __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); +static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init + = __ATTR_RW(xps_cpus); #endif /* CONFIG_XPS */ -static struct attribute *netdev_queue_default_attrs[] = { +static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_trans_timeout.attr, &queue_traffic_class.attr, #ifdef CONFIG_XPS @@ -1322,7 +1308,7 @@ static const void *netdev_queue_namespace(struct kobject *kobj) return ns; } -static struct kobj_type netdev_queue_ktype = { +static struct kobj_type netdev_queue_ktype __ro_after_init = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_attrs = netdev_queue_default_attrs, @@ -1337,23 +1323,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, - "tx-%u", index); + "tx-%u", index); if (error) - goto exit; + return error; #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); - if (error) - goto exit; + if (error) { + kobject_put(kobj); + return error; + } #endif kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); return 0; -exit: - kobject_put(kobj); - return error; } #endif /* CONFIG_SYSFS */ @@ -1395,7 +1380,7 @@ static int register_queue_kobjects(struct net_device *dev) #ifdef CONFIG_SYSFS dev->queues_kset = kset_create_and_add("queues", - NULL, &dev->dev.kobj); + NULL, &dev->dev.kobj); if (!dev->queues_kset) return -ENOMEM; real_rx = dev->real_num_rx_queues; @@ -1463,7 +1448,7 @@ static const void *net_netlink_ns(struct sock *sk) return sock_net(sk); } -struct kobj_ns_type_operations net_ns_type_operations = { +const struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, @@ -1485,7 +1470,8 @@ static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) /* pass ifindex to uevent. * ifindex is useful as it won't change (interface name may change) - * and is what RtNetlink uses natively. */ + * and is what RtNetlink uses natively. + */ retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); exit: @@ -1513,7 +1499,7 @@ static const void *net_namespace(struct device *d) return dev_net(dev); } -static struct class net_class = { +static struct class net_class __ro_after_init = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, @@ -1560,7 +1546,7 @@ EXPORT_SYMBOL(of_find_net_device_by_node); */ void netdev_unregister_kobject(struct net_device *ndev) { - struct device *dev = &(ndev->dev); + struct device *dev = &ndev->dev; if (!atomic_read(&dev_net(ndev)->count)) dev_set_uevent_suppress(dev, 1); @@ -1577,7 +1563,7 @@ void netdev_unregister_kobject(struct net_device *ndev) /* Create sysfs entries for network device. */ int netdev_register_kobject(struct net_device *ndev) { - struct device *dev = &(ndev->dev); + struct device *dev = &ndev->dev; const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; @@ -1620,14 +1606,14 @@ int netdev_register_kobject(struct net_device *ndev) return error; } -int netdev_class_create_file_ns(struct class_attribute *class_attr, +int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); -void netdev_class_remove_file_ns(struct class_attribute *class_attr, +void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns) { class_remove_file_ns(&net_class, class_attr, ns); diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 92da5e4ceb4f..4f1468ccd056 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -32,6 +32,7 @@ #include <trace/events/sock.h> #include <trace/events/udp.h> #include <trace/events/fib.h> +#include <trace/events/qdisc.h> #if IS_ENABLED(CONFIG_IPV6) #include <trace/events/fib6.h> EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 8726d051f31d..6cfdc7c84c48 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -855,9 +855,10 @@ static int __init net_ns_init(void) register_pernet_subsys(&net_ns_ops); - rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, + RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, - NULL); + RTNL_FLAG_DOIT_UNLOCKED); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9201e3621351..a78fd61da0ec 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -62,7 +62,7 @@ struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; - rtnl_calcit_func calcit; + unsigned int flags; }; static DEFINE_MUTEX(rtnl_mutex); @@ -127,7 +127,8 @@ bool lockdep_rtnl_is_held(void) EXPORT_SYMBOL(lockdep_rtnl_is_held); #endif /* #ifdef CONFIG_PROVE_LOCKING */ -static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; +static struct rtnl_link __rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; +static refcount_t rtnl_msg_handlers_ref[RTNL_FAMILY_MAX + 1]; static inline int rtm_msgindex(int msgtype) { @@ -143,58 +144,13 @@ static inline int rtm_msgindex(int msgtype) return msgindex; } -static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) -{ - struct rtnl_link *tab; - - if (protocol <= RTNL_FAMILY_MAX) - tab = rtnl_msg_handlers[protocol]; - else - tab = NULL; - - if (tab == NULL || tab[msgindex].doit == NULL) - tab = rtnl_msg_handlers[PF_UNSPEC]; - - return tab[msgindex].doit; -} - -static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) -{ - struct rtnl_link *tab; - - if (protocol <= RTNL_FAMILY_MAX) - tab = rtnl_msg_handlers[protocol]; - else - tab = NULL; - - if (tab == NULL || tab[msgindex].dumpit == NULL) - tab = rtnl_msg_handlers[PF_UNSPEC]; - - return tab[msgindex].dumpit; -} - -static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) -{ - struct rtnl_link *tab; - - if (protocol <= RTNL_FAMILY_MAX) - tab = rtnl_msg_handlers[protocol]; - else - tab = NULL; - - if (tab == NULL || tab[msgindex].calcit == NULL) - tab = rtnl_msg_handlers[PF_UNSPEC]; - - return tab[msgindex].calcit; -} - /** * __rtnl_register - Register a rtnetlink message type * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message - * @calcit: Function pointer to calc size of dump message + * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the @@ -208,7 +164,7 @@ static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) */ int __rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit, - rtnl_calcit_func calcit) + unsigned int flags) { struct rtnl_link *tab; int msgindex; @@ -216,23 +172,20 @@ int __rtnl_register(int protocol, int msgtype, BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); - tab = rtnl_msg_handlers[protocol]; + tab = rcu_dereference_raw(rtnl_msg_handlers[protocol]); if (tab == NULL) { tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL); if (tab == NULL) return -ENOBUFS; - rtnl_msg_handlers[protocol] = tab; + rcu_assign_pointer(rtnl_msg_handlers[protocol], tab); } if (doit) tab[msgindex].doit = doit; - if (dumpit) tab[msgindex].dumpit = dumpit; - - if (calcit) - tab[msgindex].calcit = calcit; + tab[msgindex].flags |= flags; return 0; } @@ -249,9 +202,9 @@ EXPORT_SYMBOL_GPL(__rtnl_register); */ void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit, - rtnl_calcit_func calcit) + unsigned int flags) { - if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0) + if (__rtnl_register(protocol, msgtype, doit, dumpit, flags) < 0) panic("Unable to register rtnetlink message handler, " "protocol = %d, message type = %d\n", protocol, msgtype); @@ -267,17 +220,23 @@ EXPORT_SYMBOL_GPL(rtnl_register); */ int rtnl_unregister(int protocol, int msgtype) { + struct rtnl_link *handlers; int msgindex; BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); - if (rtnl_msg_handlers[protocol] == NULL) + rtnl_lock(); + handlers = rtnl_dereference(rtnl_msg_handlers[protocol]); + if (!handlers) { + rtnl_unlock(); return -ENOENT; + } - rtnl_msg_handlers[protocol][msgindex].doit = NULL; - rtnl_msg_handlers[protocol][msgindex].dumpit = NULL; - rtnl_msg_handlers[protocol][msgindex].calcit = NULL; + handlers[msgindex].doit = NULL; + handlers[msgindex].dumpit = NULL; + handlers[msgindex].flags = 0; + rtnl_unlock(); return 0; } @@ -292,10 +251,20 @@ EXPORT_SYMBOL_GPL(rtnl_unregister); */ void rtnl_unregister_all(int protocol) { + struct rtnl_link *handlers; + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); - kfree(rtnl_msg_handlers[protocol]); - rtnl_msg_handlers[protocol] = NULL; + rtnl_lock(); + handlers = rtnl_dereference(rtnl_msg_handlers[protocol]); + RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL); + rtnl_unlock(); + + synchronize_net(); + + while (refcount_read(&rtnl_msg_handlers_ref[protocol]) > 1) + schedule(); + kfree(handlers); } EXPORT_SYMBOL_GPL(rtnl_unregister_all); @@ -433,16 +402,24 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) { struct net_device *master_dev; const struct rtnl_link_ops *ops; + size_t size = 0; - master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + rcu_read_lock(); + + master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev); if (!master_dev) - return 0; + goto out; + ops = master_dev->rtnl_link_ops; if (!ops || !ops->get_slave_size) - return 0; + goto out; /* IFLA_INFO_SLAVE_DATA + nested data */ - return nla_total_size(sizeof(struct nlattr)) + + size = nla_total_size(sizeof(struct nlattr)) + ops->get_slave_size(master_dev, dev); + +out: + rcu_read_unlock(); + return size; } static size_t rtnl_link_get_size(const struct net_device *dev) @@ -1644,8 +1621,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[0]; s_idx = cb->args[1]; - cb->seq = net->dev_base_seq; - /* A hack to preserve kernel<->userspace interface. * The correct header is ifinfomsg. It is consistent with rtnl_getlink. * However, before Linux v3.9 the code here assumed rtgenmsg and that's @@ -1691,8 +1666,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) goto out_err; } - - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } @@ -1702,6 +1675,8 @@ out: out_err: cb->args[1] = idx; cb->args[0] = h; + cb->seq = net->dev_base_seq; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } @@ -2831,11 +2806,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) * traverse the list of net devices and compute the minimum * buffer size based upon the filter mask. */ - list_for_each_entry(dev, &net->dev_base_head, dev_list) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, if_nlmsg_size(dev, ext_filter_mask)); } + rcu_read_unlock(); return nlmsg_total_size(min_ifinfo_dump_size); } @@ -2847,19 +2824,29 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) if (s_idx == 0) s_idx = 1; + for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { int type = cb->nlh->nlmsg_type-RTM_BASE; + struct rtnl_link *handlers; + rtnl_dumpit_func dumpit; + if (idx < s_idx || idx == PF_PACKET) continue; - if (rtnl_msg_handlers[idx] == NULL || - rtnl_msg_handlers[idx][type].dumpit == NULL) + + handlers = rtnl_dereference(rtnl_msg_handlers[idx]); + if (!handlers) continue; + + dumpit = READ_ONCE(handlers[type].dumpit); + if (!dumpit) + continue; + if (idx > s_idx) { memset(&cb->args[0], 0, sizeof(cb->args)); cb->prev_seq = 0; cb->seq = 0; } - if (rtnl_msg_handlers[idx][type].dumpit(skb, cb)) + if (dumpit(skb, cb)) break; } cb->family = idx; @@ -4162,11 +4149,13 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct rtnl_link *handlers; + int err = -EOPNOTSUPP; rtnl_doit_func doit; + unsigned int flags; int kind; int family; int type; - int err; type = nlh->nlmsg_type; if (type > RTM_MAX) @@ -4184,20 +4173,40 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; + if (family >= ARRAY_SIZE(rtnl_msg_handlers)) + family = PF_UNSPEC; + + rcu_read_lock(); + handlers = rcu_dereference(rtnl_msg_handlers[family]); + if (!handlers) { + family = PF_UNSPEC; + handlers = rcu_dereference(rtnl_msg_handlers[family]); + } + if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; - rtnl_calcit_func calcit; u16 min_dump_alloc = 0; - dumpit = rtnl_get_dumpit(family, type); - if (dumpit == NULL) - return -EOPNOTSUPP; - calcit = rtnl_get_calcit(family, type); - if (calcit) - min_dump_alloc = calcit(skb, nlh); + dumpit = READ_ONCE(handlers[type].dumpit); + if (!dumpit) { + family = PF_UNSPEC; + handlers = rcu_dereference(rtnl_msg_handlers[PF_UNSPEC]); + if (!handlers) + goto err_unlock; + + dumpit = READ_ONCE(handlers[type].dumpit); + if (!dumpit) + goto err_unlock; + } + + refcount_inc(&rtnl_msg_handlers_ref[family]); + + if (type == RTM_GETLINK - RTM_BASE) + min_dump_alloc = rtnl_calcit(skb, nlh); + + rcu_read_unlock(); - __rtnl_unlock(); rtnl = net->rtnl; { struct netlink_dump_control c = { @@ -4206,22 +4215,47 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, }; err = netlink_dump_start(rtnl, skb, nlh, &c); } - rtnl_lock(); + refcount_dec(&rtnl_msg_handlers_ref[family]); return err; } - doit = rtnl_get_doit(family, type); - if (doit == NULL) - return -EOPNOTSUPP; + doit = READ_ONCE(handlers[type].doit); + if (!doit) { + family = PF_UNSPEC; + handlers = rcu_dereference(rtnl_msg_handlers[family]); + } + + flags = READ_ONCE(handlers[type].flags); + if (flags & RTNL_FLAG_DOIT_UNLOCKED) { + refcount_inc(&rtnl_msg_handlers_ref[family]); + doit = READ_ONCE(handlers[type].doit); + rcu_read_unlock(); + if (doit) + err = doit(skb, nlh, extack); + refcount_dec(&rtnl_msg_handlers_ref[family]); + return err; + } - return doit(skb, nlh, extack); + rcu_read_unlock(); + + rtnl_lock(); + handlers = rtnl_dereference(rtnl_msg_handlers[family]); + if (handlers) { + doit = READ_ONCE(handlers[type].doit); + if (doit) + err = doit(skb, nlh, extack); + } + rtnl_unlock(); + return err; + +err_unlock: + rcu_read_unlock(); + return -EOPNOTSUPP; } static void rtnetlink_rcv(struct sk_buff *skb) { - rtnl_lock(); netlink_rcv_skb(skb, &rtnetlink_rcv_msg); - rtnl_unlock(); } static int rtnetlink_bind(struct net *net, int group) @@ -4294,29 +4328,34 @@ static struct pernet_operations rtnetlink_net_ops = { void __init rtnetlink_init(void) { + int i; + + for (i = 0; i < ARRAY_SIZE(rtnl_msg_handlers_ref); i++) + refcount_set(&rtnl_msg_handlers_ref[i], 1); + if (register_pernet_subsys(&rtnetlink_net_ops)) panic("rtnetlink_init: cannot initialize rtnetlink\n"); register_netdevice_notifier(&rtnetlink_dev_notifier); rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, - rtnl_dump_ifinfo, rtnl_calcit); - rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL); + rtnl_dump_ifinfo, 0); + rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); - rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL); + rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, 0); + rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0); + rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0); - rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL); - rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL); - rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, 0); - rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL); - rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); - rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0); + rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETSTATS, rtnl_stats_get, rtnl_stats_dump, - NULL); + 0); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0f0933b338d7..917da73d3ab3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -567,21 +567,10 @@ static void skb_release_data(struct sk_buff *skb) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i]); - /* - * If skb buf is from userspace, we need to notify the caller - * the lower device DMA has done; - */ - if (shinfo->tx_flags & SKBTX_DEV_ZEROCOPY) { - struct ubuf_info *uarg; - - uarg = shinfo->destructor_arg; - if (uarg->callback) - uarg->callback(uarg, true); - } - if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); + skb_zcopy_clear(skb, true); skb_free_head(skb); } @@ -695,14 +684,7 @@ EXPORT_SYMBOL(kfree_skb_list); */ void skb_tx_error(struct sk_buff *skb) { - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - struct ubuf_info *uarg; - - uarg = skb_shinfo(skb)->destructor_arg; - if (uarg->callback) - uarg->callback(uarg, false); - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; - } + skb_zcopy_clear(skb, true); } EXPORT_SYMBOL(skb_tx_error); @@ -915,6 +897,273 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); +static int mm_account_pinned_pages(struct mmpin *mmp, size_t size) +{ + unsigned long max_pg, num_pg, new_pg, old_pg; + struct user_struct *user; + + if (capable(CAP_IPC_LOCK) || !size) + return 0; + + num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ + max_pg = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + user = mmp->user ? : current_user(); + + do { + old_pg = atomic_long_read(&user->locked_vm); + new_pg = old_pg + num_pg; + if (new_pg > max_pg) + return -ENOBUFS; + } while (atomic_long_cmpxchg(&user->locked_vm, old_pg, new_pg) != + old_pg); + + if (!mmp->user) { + mmp->user = get_uid(user); + mmp->num_pg = num_pg; + } else { + mmp->num_pg += num_pg; + } + + return 0; +} + +static void mm_unaccount_pinned_pages(struct mmpin *mmp) +{ + if (mmp->user) { + atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); + free_uid(mmp->user); + } +} + +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) +{ + struct ubuf_info *uarg; + struct sk_buff *skb; + + WARN_ON_ONCE(!in_task()); + + if (!sock_flag(sk, SOCK_ZEROCOPY)) + return NULL; + + skb = sock_omalloc(sk, 0, GFP_KERNEL); + if (!skb) + return NULL; + + BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); + uarg = (void *)skb->cb; + uarg->mmp.user = NULL; + + if (mm_account_pinned_pages(&uarg->mmp, size)) { + kfree_skb(skb); + return NULL; + } + + uarg->callback = sock_zerocopy_callback; + uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; + uarg->len = 1; + uarg->bytelen = size; + uarg->zerocopy = 1; + atomic_set(&uarg->refcnt, 0); + sock_hold(sk); + + return uarg; +} +EXPORT_SYMBOL_GPL(sock_zerocopy_alloc); + +static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) +{ + return container_of((void *)uarg, struct sk_buff, cb); +} + +struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg) +{ + if (uarg) { + const u32 byte_limit = 1 << 19; /* limit to a few TSO */ + u32 bytelen, next; + + /* realloc only when socket is locked (TCP, UDP cork), + * so uarg->len and sk_zckey access is serialized + */ + if (!sock_owned_by_user(sk)) { + WARN_ON_ONCE(1); + return NULL; + } + + bytelen = uarg->bytelen + size; + if (uarg->len == USHRT_MAX - 1 || bytelen > byte_limit) { + /* TCP can create new skb to attach new uarg */ + if (sk->sk_type == SOCK_STREAM) + goto new_alloc; + return NULL; + } + + next = (u32)atomic_read(&sk->sk_zckey); + if ((u32)(uarg->id + uarg->len) == next) { + if (mm_account_pinned_pages(&uarg->mmp, size)) + return NULL; + uarg->len++; + uarg->bytelen = bytelen; + atomic_set(&sk->sk_zckey, ++next); + return uarg; + } + } + +new_alloc: + return sock_zerocopy_alloc(sk, size); +} +EXPORT_SYMBOL_GPL(sock_zerocopy_realloc); + +static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) +{ + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + u32 old_lo, old_hi; + u64 sum_len; + + old_lo = serr->ee.ee_info; + old_hi = serr->ee.ee_data; + sum_len = old_hi - old_lo + 1ULL + len; + + if (sum_len >= (1ULL << 32)) + return false; + + if (lo != old_hi + 1) + return false; + + serr->ee.ee_data += len; + return true; +} + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) +{ + struct sk_buff *tail, *skb = skb_from_uarg(uarg); + struct sock_exterr_skb *serr; + struct sock *sk = skb->sk; + struct sk_buff_head *q; + unsigned long flags; + u32 lo, hi; + u16 len; + + mm_unaccount_pinned_pages(&uarg->mmp); + + /* if !len, there was only 1 call, and it was aborted + * so do not queue a completion notification + */ + if (!uarg->len || sock_flag(sk, SOCK_DEAD)) + goto release; + + len = uarg->len; + lo = uarg->id; + hi = uarg->id + len - 1; + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = 0; + serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; + serr->ee.ee_data = hi; + serr->ee.ee_info = lo; + if (!success) + serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; + + q = &sk->sk_error_queue; + spin_lock_irqsave(&q->lock, flags); + tail = skb_peek_tail(q); + if (!tail || SKB_EXT_ERR(tail)->ee.ee_origin != SO_EE_ORIGIN_ZEROCOPY || + !skb_zerocopy_notify_extend(tail, lo, len)) { + __skb_queue_tail(q, skb); + skb = NULL; + } + spin_unlock_irqrestore(&q->lock, flags); + + sk->sk_error_report(sk); + +release: + consume_skb(skb); + sock_put(sk); +} +EXPORT_SYMBOL_GPL(sock_zerocopy_callback); + +void sock_zerocopy_put(struct ubuf_info *uarg) +{ + if (uarg && atomic_dec_and_test(&uarg->refcnt)) { + if (uarg->callback) + uarg->callback(uarg, uarg->zerocopy); + else + consume_skb(skb_from_uarg(uarg)); + } +} +EXPORT_SYMBOL_GPL(sock_zerocopy_put); + +void sock_zerocopy_put_abort(struct ubuf_info *uarg) +{ + if (uarg) { + struct sock *sk = skb_from_uarg(uarg)->sk; + + atomic_dec(&sk->sk_zckey); + uarg->len--; + + /* sock_zerocopy_put expects a ref. Most sockets take one per + * skb, which is zero on abort. tcp_sendmsg holds one extra, to + * avoid an skb send inside the main loop triggering uarg free. + */ + if (sk->sk_type != SOCK_STREAM) + atomic_inc(&uarg->refcnt); + + sock_zerocopy_put(uarg); + } +} +EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort); + +extern int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg) +{ + struct ubuf_info *orig_uarg = skb_zcopy(skb); + struct iov_iter orig_iter = msg->msg_iter; + int err, orig_len = skb->len; + + /* An skb can only point to one uarg. This edge case happens when + * TCP appends to an skb, but zerocopy_realloc triggered a new alloc. + */ + if (orig_uarg && uarg != orig_uarg) + return -EEXIST; + + err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); + if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { + /* Streams do not free skb on error. Reset to prev state. */ + msg->msg_iter = orig_iter; + ___pskb_trim(skb, orig_len); + return err; + } + + skb_zcopy_set(skb, uarg); + return skb->len - orig_len; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); + +static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, + gfp_t gfp_mask) +{ + if (skb_zcopy(orig)) { + if (skb_zcopy(nskb)) { + /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ + if (!gfp_mask) { + WARN_ON_ONCE(1); + return -ENOMEM; + } + if (skb_uarg(nskb) == skb_uarg(orig)) + return 0; + if (skb_copy_ubufs(nskb, GFP_ATOMIC)) + return -EIO; + } + skb_zcopy_set(nskb, skb_uarg(orig)); + } + return 0; +} + /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify @@ -932,17 +1181,19 @@ EXPORT_SYMBOL_GPL(skb_morph); */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { - int i; int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; - struct ubuf_info *uarg = skb_shinfo(skb)->destructor_arg; + int i, new_frags; + u32 d_off; - for (i = 0; i < num_frags; i++) { - skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - u32 p_off, p_len, copied; - struct page *p; - u8 *vaddr; + if (!num_frags) + return 0; + if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) + return -EINVAL; + + new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT; + for (i = 0; i < new_frags; i++) { page = alloc_page(gfp_mask); if (!page) { while (head) { @@ -952,33 +1203,51 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) } return -ENOMEM; } + set_page_private(page, (unsigned long)head); + head = page; + } + + page = head; + d_off = 0; + for (i = 0; i < num_frags; i++) { + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; + u32 p_off, p_len, copied; + struct page *p; + u8 *vaddr; skb_frag_foreach_page(f, f->page_offset, skb_frag_size(f), p, p_off, p_len, copied) { + u32 copy, done = 0; vaddr = kmap_atomic(p); - memcpy(page_address(page) + copied, vaddr + p_off, - p_len); + + while (done < p_len) { + if (d_off == PAGE_SIZE) { + d_off = 0; + page = (struct page *)page_private(page); + } + copy = min_t(u32, PAGE_SIZE - d_off, p_len - done); + memcpy(page_address(page) + d_off, + vaddr + p_off + done, copy); + done += copy; + d_off += copy; + } kunmap_atomic(vaddr); } - - set_page_private(page, (unsigned long)head); - head = page; } /* skb frags release userspace buffers */ for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); - uarg->callback(uarg, false); - /* skb frags point to kernel buffers */ - for (i = num_frags - 1; i >= 0; i--) { - __skb_fill_page_desc(skb, i, head, 0, - skb_shinfo(skb)->frags[i].size); + for (i = 0; i < new_frags - 1; i++) { + __skb_fill_page_desc(skb, i, head, 0, PAGE_SIZE); head = (struct page *)page_private(head); } + __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); + skb_shinfo(skb)->nr_frags = new_frags; - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); @@ -1139,7 +1408,8 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, if (skb_shinfo(skb)->nr_frags) { int i; - if (skb_orphan_frags(skb, gfp_mask)) { + if (skb_orphan_frags(skb, gfp_mask) || + skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; @@ -1216,9 +1486,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, * be since all we did is relocate the values */ if (skb_cloned(skb)) { - /* copy this zero copy skb frags */ if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; + if (skb_zcopy(skb)) + atomic_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); @@ -1713,6 +1984,9 @@ end: skb->tail += delta; skb->data_len -= delta; + if (!skb->data_len) + skb_zcopy_clear(skb, false); + return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); @@ -2011,7 +2285,7 @@ do_frag_list: slen = min_t(int, len, skb_headlen(skb) - offset); kv.iov_base = skb->data + offset; - kv.iov_len = len; + kv.iov_len = slen; memset(&msg, 0, sizeof(msg)); ret = kernel_sendmsg_locked(sk, &msg, &kv, 1, slen); @@ -2468,6 +2742,7 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) skb_tx_error(from); return -ENOMEM; } + skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { if (!len) @@ -2765,6 +3040,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) skb_shinfo(skb1)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2808,6 +3084,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) if (skb_headlen(skb)) return 0; + if (skb_zcopy(tgt) || skb_zcopy(skb)) + return 0; todo = shiftlen; from = 0; @@ -3381,6 +3659,8 @@ normal: skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & SKBTX_SHARED_FRAG; + if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC)) + goto err; while (pos < offset + len) { if (i >= nfrags) { @@ -4504,6 +4784,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_has_frag_list(to) || skb_has_frag_list(from)) return false; + if (skb_zcopy(to) || skb_zcopy(from)) + return false; if (skb_headlen(from) != 0) { struct page *page; diff --git a/net/core/sock.c b/net/core/sock.c index 564f835f408a..0f04d8bff607 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1055,6 +1055,20 @@ set_rcvbuf: if (val == 1) dst_negative_advice(sk); break; + + case SO_ZEROCOPY: + if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) + ret = -ENOTSUPP; + else if (sk->sk_protocol != IPPROTO_TCP) + ret = -ENOTSUPP; + else if (sk->sk_state != TCP_CLOSE) + ret = -EBUSY; + else if (val < 0 || val > 1) + ret = -EINVAL; + else + sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool); + break; + default: ret = -ENOPROTOOPT; break; @@ -1383,6 +1397,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val64 = sock_gen_cookie(sk); break; + case SO_ZEROCOPY: + v.val = sock_flag(sk, SOCK_ZEROCOPY); + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -1670,6 +1688,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; + atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); @@ -1923,6 +1942,33 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, } EXPORT_SYMBOL(sock_wmalloc); +static void sock_ofree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + + atomic_sub(skb->truesize, &sk->sk_omem_alloc); +} + +struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, + gfp_t priority) +{ + struct sk_buff *skb; + + /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ + if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > + sysctl_optmem_max) + return NULL; + + skb = alloc_skb(size, priority); + if (!skb) + return NULL; + + atomic_add(skb->truesize, &sk->sk_omem_alloc); + skb->sk = sk; + skb->destructor = sock_ofree; + return skb; +} + /* * Allocate a memory block from the socket's option memory buffer. */ @@ -2695,6 +2741,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; + atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 733f523707ac..bae7d78aa068 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1938,8 +1938,8 @@ static int __init dcbnl_init(void) { INIT_LIST_HEAD(&dcb_app_list); - rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0); return 0; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 1b202f16531f..001c08696334 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -256,7 +256,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) sk = __inet_lookup_established(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, iph->saddr, ntohs(dh->dccph_sport), - inet_iif(skb)); + inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return; @@ -804,7 +804,7 @@ static int dccp_v4_rcv(struct sk_buff *skb) lookup: sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), - dh->dccph_sport, dh->dccph_dport, &refcounted); + dh->dccph_sport, dh->dccph_dport, 0, &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 1b58eac8aad3..47a7b59b355e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -89,7 +89,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, ntohs(dh->dccph_sport), - inet6_iif(skb)); + inet6_iif(skb), 0); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), @@ -687,7 +687,7 @@ static int dccp_v6_rcv(struct sk_buff *skb) lookup: sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, - inet6_iif(skb), &refcounted); + inet6_iif(skb), 0, &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 9fe25bf63296..86bc40ba6ba5 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -201,10 +201,7 @@ void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - /* - * DCCP doesn't use sk_write_queue, just sk_send_head - * for retransmissions - */ + __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index fa0110b57ca1..4d339de56862 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1419,9 +1419,9 @@ void __init dn_dev_init(void) dn_dev_devices_on(); - rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL, NULL); - rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, NULL); - rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, NULL); + rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL, 0); + rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, 0); + rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, 0); proc_create("decnet_dev", S_IRUGO, init_net.proc_net, &dn_dev_seq_fops); diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index f9f6fb3f3c5b..3d37464c8b4a 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -791,8 +791,8 @@ void __init dn_fib_init(void) register_dnaddr_notifier(&dn_fib_dnaddr_notifier); - rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL, NULL); - rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL, NULL); + rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL, 0); + rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL, 0); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index bcbe548f8854..0bd3afd01dd2 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1922,10 +1922,10 @@ void __init dn_route_init(void) #ifdef CONFIG_DECNET_ROUTER rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, - dn_fib_dump, NULL); + dn_fib_dump, 0); #else rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, - dn_cache_dump, NULL); + dn_cache_dump, 0); #endif } diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index a55e2e4087a4..99e38af85fc5 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -67,17 +67,17 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { [DSA_TAG_PROTO_NONE] = &none_ops, }; -int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, - struct dsa_port *dport, int port) +int dsa_cpu_dsa_setup(struct dsa_port *port) { - struct device_node *port_dn = dport->dn; + struct device_node *port_dn = port->dn; + struct dsa_switch *ds = port->ds; struct phy_device *phydev; int ret, mode; if (of_phy_is_fixed_link(port_dn)) { ret = of_phy_register_fixed_link(port_dn); if (ret) { - dev_err(dev, "failed to register fixed PHY\n"); + dev_err(ds->dev, "failed to register fixed PHY\n"); return ret; } phydev = of_phy_find_device(port_dn); @@ -90,7 +90,7 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, genphy_config_init(phydev); genphy_read_status(phydev); if (ds->ops->adjust_link) - ds->ops->adjust_link(ds, port, phydev); + ds->ops->adjust_link(ds, port->index, phydev); put_device(&phydev->mdio.dev); } @@ -190,6 +190,8 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, { struct dsa_switch_tree *dst = dev->dsa_ptr; struct sk_buff *nskb = NULL; + struct pcpu_sw_netstats *s; + struct dsa_slave_priv *p; if (unlikely(dst == NULL)) { kfree_skb(skb); @@ -207,12 +209,16 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, } skb = nskb; + p = netdev_priv(skb->dev); skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; + s = this_cpu_ptr(p->stats64); + u64_stats_update_begin(&s->syncp); + s->rx_packets++; + s->rx_bytes += skb->len; + u64_stats_update_end(&s->syncp); netif_receive_skb(skb); @@ -276,10 +282,22 @@ static struct packet_type dsa_pack_type __read_mostly = { .func = dsa_switch_rcv, }; +static struct workqueue_struct *dsa_owq; + +bool dsa_schedule_work(struct work_struct *work) +{ + return queue_work(dsa_owq, work); +} + static int __init dsa_init_module(void) { int rc; + dsa_owq = alloc_ordered_workqueue("dsa_ordered", + WQ_MEM_RECLAIM); + if (!dsa_owq) + return -ENOMEM; + rc = dsa_slave_register_notifier(); if (rc) return rc; @@ -299,6 +317,7 @@ static void __exit dsa_cleanup_module(void) dsa_slave_unregister_notifier(); dev_remove_pack(&dsa_pack_type); dsa_legacy_unregister(); + destroy_workqueue(dsa_owq); } module_exit(dsa_cleanup_module); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index c442051d5a55..cceaa4dd9f53 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -219,7 +219,7 @@ static int dsa_dsa_port_apply(struct dsa_port *port) struct dsa_switch *ds = port->ds; int err; - err = dsa_cpu_dsa_setup(ds, ds->dev, port, port->index); + err = dsa_cpu_dsa_setup(port); if (err) { dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n", port->index, err); @@ -243,7 +243,7 @@ static int dsa_cpu_port_apply(struct dsa_port *port) struct dsa_switch *ds = port->ds; int err; - err = dsa_cpu_dsa_setup(ds, ds->dev, port, port->index); + err = dsa_cpu_dsa_setup(port); if (err) { dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n", port->index, err); @@ -275,7 +275,7 @@ static int dsa_user_port_apply(struct dsa_port *port) if (!name) name = "eth%d"; - err = dsa_slave_create(ds, ds->dev, port->index, name); + err = dsa_slave_create(port, name); if (err) { dev_warn(ds->dev, "Failed to create slave %d: %d\n", port->index, err); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 55982cc39b24..9c3eeb72462d 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -43,10 +43,10 @@ struct dsa_notifier_bridge_info { /* DSA_NOTIFIER_FDB_* */ struct dsa_notifier_fdb_info { - const struct switchdev_obj_port_fdb *fdb; - struct switchdev_trans *trans; int sw_index; int port; + const unsigned char *addr; + u16 vid; }; /* DSA_NOTIFIER_MDB_* */ @@ -65,18 +65,13 @@ struct dsa_notifier_vlan_info { int port; }; -struct dsa_device_ops { - struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); - struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, - struct net_device *orig_dev); -}; - struct dsa_slave_priv { /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); + struct pcpu_sw_netstats *stats64; + /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; @@ -99,16 +94,23 @@ struct dsa_slave_priv { }; /* dsa.c */ -int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, - struct dsa_port *dport, int port); +int dsa_cpu_dsa_setup(struct dsa_port *port); void dsa_cpu_dsa_destroy(struct dsa_port *dport); const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp); void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp); +bool dsa_schedule_work(struct work_struct *work); /* legacy.c */ int dsa_legacy_register(void); void dsa_legacy_unregister(void); +int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + u16 flags); +int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid); /* port.c */ int dsa_port_set_state(struct dsa_port *dp, u8 state, @@ -120,35 +122,25 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct switchdev_trans *trans); int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, struct switchdev_trans *trans); -int dsa_port_fdb_add(struct dsa_port *dp, - const struct switchdev_obj_port_fdb *fdb, - struct switchdev_trans *trans); -int dsa_port_fdb_del(struct dsa_port *dp, - const struct switchdev_obj_port_fdb *fdb); -int dsa_port_fdb_dump(struct dsa_port *dp, struct switchdev_obj_port_fdb *fdb, - switchdev_obj_dump_cb_t *cb); +int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); int dsa_port_mdb_add(struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans); int dsa_port_mdb_del(struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); -int dsa_port_mdb_dump(struct dsa_port *dp, struct switchdev_obj_port_mdb *mdb, - switchdev_obj_dump_cb_t *cb); int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan); -int dsa_port_vlan_dump(struct dsa_port *dp, - struct switchdev_obj_port_vlan *vlan, - switchdev_obj_dump_cb_t *cb); - /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops); -int dsa_slave_create(struct dsa_switch *ds, struct device *parent, - int port, const char *name); +int dsa_slave_create(struct dsa_port *port, const char *name); void dsa_slave_destroy(struct net_device *slave_dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 1d7a3282f2a7..91e6f7981d39 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -78,25 +78,23 @@ dsa_switch_probe(struct device *parent, struct device *host_dev, int sw_addr, } /* basic switch operations **************************************************/ -static int dsa_cpu_dsa_setups(struct dsa_switch *ds, struct device *dev) +static int dsa_cpu_dsa_setups(struct dsa_switch *ds) { - struct dsa_port *dport; int ret, port; for (port = 0; port < ds->num_ports; port++) { if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) continue; - dport = &ds->ports[port]; - ret = dsa_cpu_dsa_setup(ds, dev, dport, port); + ret = dsa_cpu_dsa_setup(&ds->ports[port]); if (ret) return ret; } return 0; } -static int dsa_switch_setup_one(struct dsa_switch *ds, struct net_device *master, - struct device *parent) +static int dsa_switch_setup_one(struct dsa_switch *ds, + struct net_device *master) { const struct dsa_switch_ops *ops = ds->ops; struct dsa_switch_tree *dst = ds->dst; @@ -176,7 +174,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct net_device *master } if (!ds->slave_mii_bus && ops->phy_read) { - ds->slave_mii_bus = devm_mdiobus_alloc(parent); + ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) return -ENOMEM; dsa_slave_mii_bus_init(ds); @@ -196,14 +194,14 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct net_device *master if (!(ds->enabled_port_mask & (1 << i))) continue; - ret = dsa_slave_create(ds, parent, i, cd->port_names[i]); + ret = dsa_slave_create(&ds->ports[i], cd->port_names[i]); if (ret < 0) netdev_err(master, "[%d]: can't create dsa slave device for port %d(%s): %d\n", index, i, cd->port_names[i], ret); } /* Perform configuration of the CPU and DSA ports */ - ret = dsa_cpu_dsa_setups(ds, parent); + ret = dsa_cpu_dsa_setups(ds); if (ret < 0) netdev_err(master, "[%d] : can't configure CPU and DSA ports\n", index); @@ -252,7 +250,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, struct net_device *master, ds->ops = ops; ds->priv = priv; - ret = dsa_switch_setup_one(ds, master, parent); + ret = dsa_switch_setup_one(ds, master); if (ret) return ERR_PTR(ret); @@ -741,6 +739,28 @@ static int dsa_resume(struct device *d) } #endif +/* legacy way, bypassing the bridge *****************************************/ +int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + u16 flags) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; + + return dsa_port_fdb_add(dp, addr, vid); +} + +int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; + + return dsa_port_fdb_del(dp, addr, vid); +} + static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume); static const struct of_device_id dsa_of_match_table[] = { diff --git a/net/dsa/port.c b/net/dsa/port.c index efc3bce3a89d..659676ba3f8b 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -146,43 +146,33 @@ int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); } -int dsa_port_fdb_add(struct dsa_port *dp, - const struct switchdev_obj_port_fdb *fdb, - struct switchdev_trans *trans) +int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid) { struct dsa_notifier_fdb_info info = { .sw_index = dp->ds->index, .port = dp->index, - .trans = trans, - .fdb = fdb, + .addr = addr, + .vid = vid, }; return dsa_port_notify(dp, DSA_NOTIFIER_FDB_ADD, &info); } -int dsa_port_fdb_del(struct dsa_port *dp, - const struct switchdev_obj_port_fdb *fdb) +int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid) { struct dsa_notifier_fdb_info info = { .sw_index = dp->ds->index, .port = dp->index, - .fdb = fdb, + .addr = addr, + .vid = vid, + }; return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); } -int dsa_port_fdb_dump(struct dsa_port *dp, struct switchdev_obj_port_fdb *fdb, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_switch *ds = dp->ds; - - if (ds->ops->port_fdb_dump) - return ds->ops->port_fdb_dump(ds, dp->index, fdb, cb); - - return -EOPNOTSUPP; -} - int dsa_port_mdb_add(struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans) @@ -209,17 +199,6 @@ int dsa_port_mdb_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_MDB_DEL, &info); } -int dsa_port_mdb_dump(struct dsa_port *dp, struct switchdev_obj_port_mdb *mdb, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_switch *ds = dp->ds; - - if (ds->ops->port_mdb_dump) - return ds->ops->port_mdb_dump(ds, dp->index, mdb, cb); - - return -EOPNOTSUPP; -} - int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans) @@ -245,15 +224,3 @@ int dsa_port_vlan_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); } - -int dsa_port_vlan_dump(struct dsa_port *dp, - struct switchdev_obj_port_vlan *vlan, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_switch *ds = dp->ds; - - if (ds->ops->port_vlan_dump) - return ds->ops->port_vlan_dump(ds, dp->index, vlan, cb); - - return -EOPNOTSUPP; -} diff --git a/net/dsa/slave.c b/net/dsa/slave.c index cc4bad3dadb4..78e78a6e6833 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -199,6 +199,83 @@ out: return 0; } +struct dsa_slave_dump_ctx { + struct net_device *dev; + struct sk_buff *skb; + struct netlink_callback *cb; + int idx; +}; + +static int +dsa_slave_port_fdb_do_dump(const unsigned char *addr, u16 vid, + bool is_static, void *data) +{ + struct dsa_slave_dump_ctx *dump = data; + u32 portid = NETLINK_CB(dump->cb->skb).portid; + u32 seq = dump->cb->nlh->nlmsg_seq; + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + if (dump->idx < dump->cb->args[2]) + goto skip; + + nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, + sizeof(*ndm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = NTF_SELF; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dump->dev->ifindex; + ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + + if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) + goto nla_put_failure; + + nlmsg_end(dump->skb, nlh); + +skip: + dump->idx++; + return 0; + +nla_put_failure: + nlmsg_cancel(dump->skb, nlh); + return -EMSGSIZE; +} + +static int +dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, struct net_device *filter_dev, + int *idx) +{ + struct dsa_slave_dump_ctx dump = { + .dev = dev, + .skb = skb, + .cb = cb, + .idx = *idx, + }; + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = p->dp; + struct dsa_switch *ds = dp->ds; + int err; + + if (!ds->ops->port_fdb_dump) + return -EOPNOTSUPP; + + err = ds->ops->port_fdb_dump(ds, dp->index, + dsa_slave_port_fdb_do_dump, + &dump); + *idx = dump.idx; + return err; +} + static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -250,9 +327,6 @@ static int dsa_slave_port_obj_add(struct net_device *dev, */ switch (obj->id) { - case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_port_fdb_add(dp, SWITCHDEV_OBJ_PORT_FDB(obj), trans); - break; case SWITCHDEV_OBJ_ID_PORT_MDB: err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans); break; @@ -276,9 +350,6 @@ static int dsa_slave_port_obj_del(struct net_device *dev, int err; switch (obj->id) { - case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_port_fdb_del(dp, SWITCHDEV_OBJ_PORT_FDB(obj)); - break; case SWITCHDEV_OBJ_ID_PORT_MDB: err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; @@ -293,32 +364,6 @@ static int dsa_slave_port_obj_del(struct net_device *dev, return err; } -static int dsa_slave_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj, - switchdev_obj_dump_cb_t *cb) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; - int err; - - switch (obj->id) { - case SWITCHDEV_OBJ_ID_PORT_FDB: - err = dsa_port_fdb_dump(dp, SWITCHDEV_OBJ_PORT_FDB(obj), cb); - break; - case SWITCHDEV_OBJ_ID_PORT_MDB: - err = dsa_port_mdb_dump(dp, SWITCHDEV_OBJ_PORT_MDB(obj), cb); - break; - case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_port_vlan_dump(dp, SWITCHDEV_OBJ_PORT_VLAN(obj), cb); - break; - default: - err = -EOPNOTSUPP; - break; - } - - return err; -} - static int dsa_slave_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { @@ -330,6 +375,9 @@ static int dsa_slave_port_attr_get(struct net_device *dev, attr->u.ppid.id_len = sizeof(ds->index); memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len); break; + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: + attr->u.brport_flags_support = 0; + break; default: return -EOPNOTSUPP; } @@ -352,10 +400,14 @@ static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p, static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); + struct pcpu_sw_netstats *s; struct sk_buff *nskb; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + s = this_cpu_ptr(p->stats64); + u64_stats_update_begin(&s->syncp); + s->tx_packets++; + s->tx_bytes += skb->len; + u64_stats_update_end(&s->syncp); /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. @@ -594,11 +646,26 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; - - data[0] = dev->stats.tx_packets; - data[1] = dev->stats.tx_bytes; - data[2] = dev->stats.rx_packets; - data[3] = dev->stats.rx_bytes; + struct pcpu_sw_netstats *s; + unsigned int start; + int i; + + for_each_possible_cpu(i) { + u64 tx_packets, tx_bytes, rx_packets, rx_bytes; + + s = per_cpu_ptr(p->stats64, i); + do { + start = u64_stats_fetch_begin_irq(&s->syncp); + tx_packets = s->tx_packets; + tx_bytes = s->tx_bytes; + rx_packets = s->rx_packets; + rx_bytes = s->rx_bytes; + } while (u64_stats_fetch_retry_irq(&s->syncp, start)); + data[0] += tx_packets; + data[1] += tx_bytes; + data[2] += rx_packets; + data[3] += rx_bytes; + } if (ds->ops->get_ethtool_stats) ds->ops->get_ethtool_stats(ds, p->dp->index, data + 4); } @@ -755,12 +822,12 @@ dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p, } static int dsa_slave_add_cls_matchall(struct net_device *dev, - __be16 protocol, struct tc_cls_matchall_offload *cls, bool ingress) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; + __be16 protocol = cls->common.protocol; struct dsa_switch *ds = p->dp->ds; struct net *net = dev_net(dev); struct dsa_slave_priv *to_p; @@ -773,7 +840,7 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, if (!ds->ops->port_mirror_add) return err; - if (!tc_single_action(cls->exts)) + if (!tcf_exts_has_one_action(cls->exts)) return err; tcf_exts_to_list(cls->exts, &actions); @@ -844,31 +911,71 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, kfree(mall_tc_entry); } -static int dsa_slave_setup_tc(struct net_device *dev, u32 handle, - u32 chain_index, __be16 protocol, - struct tc_to_netdev *tc) +static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls) { - bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS); + bool ingress; - if (chain_index) + if (is_classid_clsact_ingress(cls->common.classid)) + ingress = true; + else if (is_classid_clsact_egress(cls->common.classid)) + ingress = false; + else return -EOPNOTSUPP; - switch (tc->type) { - case TC_SETUP_MATCHALL: - switch (tc->cls_mall->command) { - case TC_CLSMATCHALL_REPLACE: - return dsa_slave_add_cls_matchall(dev, protocol, - tc->cls_mall, - ingress); - case TC_CLSMATCHALL_DESTROY: - dsa_slave_del_cls_matchall(dev, tc->cls_mall); - return 0; - } + if (cls->common.chain_index) + return -EOPNOTSUPP; + + switch (cls->command) { + case TC_CLSMATCHALL_REPLACE: + return dsa_slave_add_cls_matchall(dev, cls, ingress); + case TC_CLSMATCHALL_DESTROY: + dsa_slave_del_cls_matchall(dev, cls); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_CLSMATCHALL: + return dsa_slave_setup_tc_cls_matchall(dev, type_data); default: return -EOPNOTSUPP; } } +static void dsa_slave_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct pcpu_sw_netstats *s; + unsigned int start; + int i; + + netdev_stats_to_stats64(stats, &dev->stats); + for_each_possible_cpu(i) { + u64 tx_packets, tx_bytes, rx_packets, rx_bytes; + + s = per_cpu_ptr(p->stats64, i); + do { + start = u64_stats_fetch_begin_irq(&s->syncp); + tx_packets = s->tx_packets; + tx_bytes = s->tx_bytes; + rx_packets = s->rx_packets; + rx_bytes = s->rx_bytes; + } while (u64_stats_fetch_retry_irq(&s->syncp, start)); + + stats->tx_packets += tx_packets; + stats->tx_bytes += tx_bytes; + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + } +} + void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops) { ops->get_sset_count = dsa_cpu_port_get_sset_count; @@ -929,9 +1036,9 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_add = switchdev_port_fdb_add, - .ndo_fdb_del = switchdev_port_fdb_del, - .ndo_fdb_dump = switchdev_port_fdb_dump, + .ndo_fdb_add = dsa_legacy_fdb_add, + .ndo_fdb_del = dsa_legacy_fdb_del, + .ndo_fdb_dump = dsa_slave_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -939,11 +1046,9 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, .ndo_poll_controller = dsa_slave_poll_controller, #endif - .ndo_bridge_getlink = switchdev_port_bridge_getlink, - .ndo_bridge_setlink = switchdev_port_bridge_setlink, - .ndo_bridge_dellink = switchdev_port_bridge_dellink, .ndo_get_phys_port_name = dsa_slave_get_phys_port_name, .ndo_setup_tc = dsa_slave_setup_tc, + .ndo_get_stats64 = dsa_slave_get_stats64, }; static const struct switchdev_ops dsa_slave_switchdev_ops = { @@ -951,7 +1056,6 @@ static const struct switchdev_ops dsa_slave_switchdev_ops = { .switchdev_port_attr_set = dsa_slave_port_attr_set, .switchdev_port_obj_add = dsa_slave_port_obj_add, .switchdev_port_obj_del = dsa_slave_port_obj_del, - .switchdev_port_obj_dump = dsa_slave_port_obj_dump, }; static struct device_type dsa_type = { @@ -1142,9 +1246,9 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } -int dsa_slave_create(struct dsa_switch *ds, struct device *parent, - int port, const char *name) +int dsa_slave_create(struct dsa_port *port, const char *name) { + struct dsa_switch *ds = port->ds; struct dsa_switch_tree *dst = ds->dst; struct net_device *master; struct net_device *slave_dev; @@ -1174,12 +1278,17 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, NULL); - SET_NETDEV_DEV(slave_dev, parent); - slave_dev->dev.of_node = ds->ports[port].dn; + SET_NETDEV_DEV(slave_dev, port->ds->dev); + slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; p = netdev_priv(slave_dev); - p->dp = &ds->ports[port]; + p->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!p->stats64) { + free_netdev(slave_dev); + return -ENOMEM; + } + p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); p->xmit = dst->tag_ops->xmit; @@ -1187,12 +1296,13 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, p->old_link = -1; p->old_duplex = -1; - ds->ports[port].netdev = slave_dev; + port->netdev = slave_dev; ret = register_netdev(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); - ds->ports[port].netdev = NULL; + port->netdev = NULL; + free_percpu(p->stats64); free_netdev(slave_dev); return ret; } @@ -1203,6 +1313,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); unregister_netdev(slave_dev); + free_percpu(p->stats64); free_netdev(slave_dev); return ret; } @@ -1225,6 +1336,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) of_phy_deregister_fixed_link(port_dn); } unregister_netdev(slave_dev); + free_percpu(p->stats64); free_netdev(slave_dev); } @@ -1267,19 +1379,142 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, return NOTIFY_DONE; } +struct dsa_switchdev_event_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + unsigned long event; +}; + +static void dsa_slave_switchdev_event_work(struct work_struct *work) +{ + struct dsa_switchdev_event_work *switchdev_work = + container_of(work, struct dsa_switchdev_event_work, work); + struct net_device *dev = switchdev_work->dev; + struct switchdev_notifier_fdb_info *fdb_info; + struct dsa_slave_priv *p = netdev_priv(dev); + int err; + + rtnl_lock(); + switch (switchdev_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + fdb_info = &switchdev_work->fdb_info; + err = dsa_port_fdb_add(p->dp, fdb_info->addr, fdb_info->vid); + if (err) { + netdev_dbg(dev, "fdb add failed err=%d\n", err); + break; + } + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, + &fdb_info->info); + break; + + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = &switchdev_work->fdb_info; + err = dsa_port_fdb_del(p->dp, fdb_info->addr, fdb_info->vid); + if (err) { + netdev_dbg(dev, "fdb del failed err=%d\n", err); + dev_close(dev); + } + break; + } + rtnl_unlock(); + + kfree(switchdev_work->fdb_info.addr); + kfree(switchdev_work); + dev_put(dev); +} + +static int +dsa_slave_switchdev_fdb_work_init(struct dsa_switchdev_event_work * + switchdev_work, + const struct switchdev_notifier_fdb_info * + fdb_info) +{ + memcpy(&switchdev_work->fdb_info, fdb_info, + sizeof(switchdev_work->fdb_info)); + switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!switchdev_work->fdb_info.addr) + return -ENOMEM; + ether_addr_copy((u8 *)switchdev_work->fdb_info.addr, + fdb_info->addr); + return 0; +} + +/* Called under rcu_read_lock() */ +static int dsa_slave_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct dsa_switchdev_event_work *switchdev_work; + + if (!dsa_slave_dev_check(dev)) + return NOTIFY_DONE; + + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (!switchdev_work) + return NOTIFY_BAD; + + INIT_WORK(&switchdev_work->work, + dsa_slave_switchdev_event_work); + switchdev_work->dev = dev; + switchdev_work->event = event; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ + case SWITCHDEV_FDB_DEL_TO_DEVICE: + if (dsa_slave_switchdev_fdb_work_init(switchdev_work, + ptr)) + goto err_fdb_work_init; + dev_hold(dev); + break; + default: + kfree(switchdev_work); + return NOTIFY_DONE; + } + + dsa_schedule_work(&switchdev_work->work); + return NOTIFY_OK; + +err_fdb_work_init: + kfree(switchdev_work); + return NOTIFY_BAD; +} + static struct notifier_block dsa_slave_nb __read_mostly = { - .notifier_call = dsa_slave_netdevice_event, + .notifier_call = dsa_slave_netdevice_event, +}; + +static struct notifier_block dsa_slave_switchdev_notifier = { + .notifier_call = dsa_slave_switchdev_event, }; int dsa_slave_register_notifier(void) { - return register_netdevice_notifier(&dsa_slave_nb); + int err; + + err = register_netdevice_notifier(&dsa_slave_nb); + if (err) + return err; + + err = register_switchdev_notifier(&dsa_slave_switchdev_notifier); + if (err) + goto err_switchdev_nb; + + return 0; + +err_switchdev_nb: + unregister_netdevice_notifier(&dsa_slave_nb); + return err; } void dsa_slave_unregister_notifier(void) { int err; + err = unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); + if (err) + pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); + err = unregister_netdevice_notifier(&dsa_slave_nb); if (err) pr_err("DSA: failed to unregister slave notifier (%d)\n", err); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 97e2e9c8cf3f..e6c06aa349a6 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -83,30 +83,20 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, static int dsa_switch_fdb_add(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { - const struct switchdev_obj_port_fdb *fdb = info->fdb; - struct switchdev_trans *trans = info->trans; - /* Do not care yet about other switch chips of the fabric */ if (ds->index != info->sw_index) return 0; - if (switchdev_trans_ph_prepare(trans)) { - if (!ds->ops->port_fdb_prepare || !ds->ops->port_fdb_add) - return -EOPNOTSUPP; - - return ds->ops->port_fdb_prepare(ds, info->port, fdb, trans); - } - - ds->ops->port_fdb_add(ds, info->port, fdb, trans); + if (!ds->ops->port_fdb_add) + return -EOPNOTSUPP; - return 0; + return ds->ops->port_fdb_add(ds, info->port, info->addr, + info->vid); } static int dsa_switch_fdb_del(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { - const struct switchdev_obj_port_fdb *fdb = info->fdb; - /* Do not care yet about other switch chips of the fabric */ if (ds->index != info->sw_index) return 0; @@ -114,7 +104,8 @@ static int dsa_switch_fdb_del(struct dsa_switch *ds, if (!ds->ops->port_fdb_del) return -EOPNOTSUPP; - return ds->ops->port_fdb_del(ds, info->port, fdb); + return ds->ops->port_fdb_del(ds, info->port, info->addr, + info->vid); } static int dsa_switch_mdb_add(struct dsa_switch *ds, diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index fab41de8e983..de66ca8e6201 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -42,6 +42,9 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) { + if (skb_put_padto(skb, skb->len + padlen)) + return NULL; + nskb = skb; } else { nskb = alloc_skb(NET_IP_ALIGN + skb->len + @@ -56,13 +59,15 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head); skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); + + if (skb_put_padto(nskb, nskb->len + padlen)) { + kfree_skb(nskb); + return NULL; + } + kfree_skb(skb); } - /* skb is freed when it fails */ - if (skb_put_padto(nskb, nskb->len + padlen)) - return NULL; - tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); tag[0] = 0; tag[1] = 1 << p->dp->index; /* destination port */ diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 247774d149f9..e23e7635fa00 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -39,7 +39,6 @@ */ #define LAN9303_TAG_LEN 4 -#define LAN9303_MAX_PORTS 3 static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -104,7 +103,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, source_port = ntohs(lan9303_tag[1]) & 0x3; - if (source_port >= LAN9303_MAX_PORTS) { + if (source_port >= ds->num_ports) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 2f32b7ea3365..02163c045a96 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -87,7 +87,17 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } +static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + *offset = 4; + *proto = ((__be16 *)skb->data)[1]; + + return 0; +} + const struct dsa_device_ops mtk_netdev_ops = { - .xmit = mtk_tag_xmit, - .rcv = mtk_tag_rcv, + .xmit = mtk_tag_xmit, + .rcv = mtk_tag_rcv, + .flow_dissect = mtk_tag_flow_dissect, }; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f0103ffe1cdb..d678820e4306 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1725,6 +1725,13 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif + /* Some igmp sysctl, whose values are always used */ + net->ipv4.sysctl_igmp_max_memberships = 20; + net->ipv4.sysctl_igmp_max_msf = 10; + /* IGMP reports for link-local multicast groups are enabled by default */ + net->ipv4.sysctl_igmp_llm_reports = 1; + net->ipv4.sysctl_igmp_qrv = 2; + return 0; } @@ -1765,6 +1772,11 @@ static const struct net_offload ipip_offload = { }, }; +static int __init ipip_offload_init(void) +{ + return inet_add_offload(&ipip_offload, IPPROTO_IPIP); +} + static int __init ipv4_offload_init(void) { /* @@ -1774,9 +1786,10 @@ static int __init ipv4_offload_init(void) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (tcpv4_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); + if (ipip_offload_init() < 0) + pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); dev_add_offload(&ip_packet_offload); - inet_add_offload(&ipip_offload, IPPROTO_IPIP); return 0; } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c4c6e1969ed0..2ae8f54cb321 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1523,9 +1523,17 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) int taglen; for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) { - if (optptr[0] == IPOPT_CIPSO) + switch (optptr[0]) { + case IPOPT_CIPSO: return optptr; - taglen = optptr[1]; + case IPOPT_END: + return NULL; + case IPOPT_NOOP: + taglen = 1; + break; + default: + taglen = optptr[1]; + } optlen -= taglen; optptr += taglen; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 38d9af9b917c..d7adc0616599 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2491,9 +2491,9 @@ void __init devinet_init(void) rtnl_af_register(&inet_af_ops); - rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); - rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0); + rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0); + rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, 0); rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, - inet_netconf_dump_devconf, NULL); + inet_netconf_dump_devconf, 0); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 044d2a159a3c..37819ab4cc74 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1247,22 +1247,28 @@ static int __net_init ip_fib_net_init(struct net *net) int err; size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; - net->ipv4.fib_seq = 0; + err = fib4_notifier_init(net); + if (err) + return err; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); - if (!net->ipv4.fib_table_hash) - return -ENOMEM; + if (!net->ipv4.fib_table_hash) { + err = -ENOMEM; + goto err_table_hash_alloc; + } err = fib4_rules_init(net); if (err < 0) - goto fail; + goto err_rules_init; return 0; -fail: +err_rules_init: kfree(net->ipv4.fib_table_hash); +err_table_hash_alloc: + fib4_notifier_exit(net); return err; } @@ -1292,6 +1298,7 @@ static void ip_fib_net_exit(struct net *net) #endif rtnl_unlock(); kfree(net->ipv4.fib_table_hash); + fib4_notifier_exit(net); } static int __net_init fib_net_init(struct net *net) @@ -1341,7 +1348,7 @@ void __init ip_fib_init(void) register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, 0); } diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index e0714d975947..5d7afb145562 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -1,86 +1,71 @@ #include <linux/rtnetlink.h> #include <linux/notifier.h> -#include <linux/rcupdate.h> +#include <linux/socket.h> #include <linux/kernel.h> #include <net/net_namespace.h> +#include <net/fib_notifier.h> #include <net/netns/ipv4.h> #include <net/ip_fib.h> -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -int call_fib_notifier(struct notifier_block *nb, struct net *net, - enum fib_event_type event_type, - struct fib_notifier_info *info) +int call_fib4_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info) { - info->net = net; - return nb->notifier_call(nb, event_type, info); + info->family = AF_INET; + return call_fib_notifier(nb, net, event_type, info); } -int call_fib_notifiers(struct net *net, enum fib_event_type event_type, - struct fib_notifier_info *info) +int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info) { + ASSERT_RTNL(); + + info->family = AF_INET; net->ipv4.fib_seq++; - info->net = net; - return atomic_notifier_call_chain(&fib_chain, event_type, info); + return call_fib_notifiers(net, event_type, info); } -static unsigned int fib_seq_sum(void) +static unsigned int fib4_seq_read(struct net *net) { - unsigned int fib_seq = 0; - struct net *net; - - rtnl_lock(); - for_each_net(net) - fib_seq += net->ipv4.fib_seq; - rtnl_unlock(); + ASSERT_RTNL(); - return fib_seq; + return net->ipv4.fib_seq + fib4_rules_seq_read(net); } -static bool fib_dump_is_consistent(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb), - unsigned int fib_seq) +static int fib4_dump(struct net *net, struct notifier_block *nb) { - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) - return true; - atomic_notifier_chain_unregister(&fib_chain, nb); - if (cb) - cb(nb); - return false; + int err; + + err = fib4_rules_dump(net, nb); + if (err) + return err; + + fib_notify(net, nb); + + return 0; } -#define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) -{ - int retries = 0; +static const struct fib_notifier_ops fib4_notifier_ops_template = { + .family = AF_INET, + .fib_seq_read = fib4_seq_read, + .fib_dump = fib4_dump, +}; - do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; +int __net_init fib4_notifier_init(struct net *net) +{ + struct fib_notifier_ops *ops; - /* Mutex semantics guarantee that every change done to - * FIB tries before we read the change sequence counter - * is now visible to us. - */ - rcu_read_lock(); - for_each_net_rcu(net) { - fib_rules_notify(net, nb); - fib_notify(net, nb); - } - rcu_read_unlock(); + net->ipv4.fib_seq = 0; - if (fib_dump_is_consistent(nb, cb, fib_seq)) - return 0; - } while (++retries < FIB_DUMP_MAX_RETRIES); + ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv4.notifier_ops = ops; - return -EBUSY; + return 0; } -EXPORT_SYMBOL(register_fib_notifier); -int unregister_fib_notifier(struct notifier_block *nb) +void __net_exit fib4_notifier_exit(struct net *net) { - return atomic_notifier_chain_unregister(&fib_chain, nb); + fib_notifier_ops_unregister(net->ipv4.notifier_ops); } -EXPORT_SYMBOL(unregister_fib_notifier); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 778ecf977eb2..35d646a62ad4 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -68,6 +68,16 @@ bool fib4_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL_GPL(fib4_rule_default); +int fib4_rules_dump(struct net *net, struct notifier_block *nb) +{ + return fib_rules_dump(net, nb, AF_INET); +} + +unsigned int fib4_rules_seq_read(struct net *net) +{ + return fib_rules_seq_read(net, AF_INET); +} + int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { @@ -185,38 +195,6 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } -static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, - enum fib_event_type event_type, - struct fib_rule *rule) -{ - struct fib_rule_notifier_info info = { - .rule = rule, - }; - - return call_fib_notifier(nb, net, event_type, &info.info); -} - -static int call_fib_rule_notifiers(struct net *net, - enum fib_event_type event_type, - struct fib_rule *rule) -{ - struct fib_rule_notifier_info info = { - .rule = rule, - }; - - return call_fib_notifiers(net, event_type, &info.info); -} - -/* Called with rcu_read_lock() */ -void fib_rules_notify(struct net *net, struct notifier_block *nb) -{ - struct fib_rules_ops *ops = net->ipv4.rules_ops; - struct fib_rule *rule; - - list_for_each_entry_rcu(rule, &ops->rules_list, list) - call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule); -} - static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { FRA_GENERIC_POLICY, [FRA_FLOW] = { .type = NLA_U32 }, @@ -273,7 +251,6 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule); err = 0; errout: @@ -295,7 +272,6 @@ static int fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule); errout: return err; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b8d18171cca3..394d800db50c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -44,6 +44,7 @@ #include <net/netlink.h> #include <net/nexthop.h> #include <net/lwtunnel.h> +#include <net/fib_notifier.h> #include "fib_lookup.h" @@ -219,7 +220,7 @@ static void free_fib_info_rcu(struct rcu_head *head) } endfor_nexthops(fi); m = fi->fib_metrics; - if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt)) + if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) kfree(m); kfree(fi); } @@ -1083,15 +1084,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg, fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (!fi) goto failure; - fib_info_cnt++; if (cfg->fc_mx) { fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL); - if (!fi->fib_metrics) - goto failure; - atomic_set(&fi->fib_metrics->refcnt, 1); - } else + if (unlikely(!fi->fib_metrics)) { + kfree(fi); + return ERR_PTR(err); + } + refcount_set(&fi->fib_metrics->refcnt, 1); + } else { fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; - + } + fib_info_cnt++; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; @@ -1342,6 +1345,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rtm->rtm_flags |= RTNH_F_DEAD; } + if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; #ifdef CONFIG_IP_ROUTE_CLASSID if (fi->fib_nh[0].nh_tclassid && nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) @@ -1449,14 +1454,14 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) break; - return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type, - &info.info); + return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type, + &info.info); case FIB_EVENT_NH_DEL: if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) || (fib_nh->nh_flags & RTNH_F_DEAD)) - return call_fib_notifiers(dev_net(fib_nh->nh_dev), - event_type, &info.info); + return call_fib4_notifiers(dev_net(fib_nh->nh_dev), + event_type, &info.info); default: break; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 64668c69dda6..1a6ffb0dab9c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -81,6 +81,7 @@ #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> +#include <net/fib_notifier.h> #include <trace/events/fib.h> #include "fib_lookup.h" @@ -97,7 +98,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, .type = type, .tb_id = tb_id, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib4_notifier(nb, net, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, @@ -113,7 +114,7 @@ static int call_fib_entry_notifiers(struct net *net, .type = type, .tb_id = tb_id, }; - return call_fib_notifiers(net, event_type, &info.info); + return call_fib4_notifiers(net, event_type, &info.info); } #define MAX_STAT_DEPTH 32 diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 8e0257d01200..1540db65241a 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -450,6 +450,7 @@ out_unlock: out: NAPI_GRO_CB(skb)->flush |= flush; skb_gro_remcsum_cleanup(skb, &grc); + skb->remcsum_offload = 0; return pp; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c2be26b98b5f..681e33998e03 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -412,7 +412,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) int type = icmp_param->data.icmph.type; int code = icmp_param->data.icmph.code; - if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb)) + if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb)) return; /* Needed by both icmp_global_allow and icmp_xmit_lock */ @@ -694,7 +694,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); - if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in)) + if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in)) goto out_unlock; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 28f14afd0dd3..9f86b5133605 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2549,7 +2549,8 @@ done: /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ -int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) +int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, + int dif, int sdif) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; @@ -2564,7 +2565,8 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && - pmc->multi.imr_ifindex == dif) + (pmc->multi.imr_ifindex == dif || + (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet->mc_all; @@ -2974,12 +2976,6 @@ static int __net_init igmp_net_init(struct net *net) goto out_sock; } - /* Sysctl initialization */ - net->ipv4.sysctl_igmp_max_memberships = 20; - net->ipv4.sysctl_igmp_max_msf = 10; - /* IGMP reports for link-local multicast groups are enabled by default */ - net->ipv4.sysctl_igmp_llm_reports = 1; - net->ipv4.sysctl_igmp_qrv = 2; return 0; out_sock: diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 3828b3a805cd..67325d5832d7 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -274,6 +274,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } + if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + out: nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 2e3389d614d1..597bb4cfe805 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -170,7 +170,7 @@ EXPORT_SYMBOL_GPL(__inet_inherit_port); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const __be32 daddr, - const int dif, bool exact_dif) + const int dif, const int sdif, bool exact_dif) { int score = -1; struct inet_sock *inet = inet_sk(sk); @@ -185,9 +185,13 @@ static inline int compute_score(struct sock *sk, struct net *net, score += 4; } if (sk->sk_bound_dev_if || exact_dif) { - if (sk->sk_bound_dev_if != dif) + bool dev_match = (sk->sk_bound_dev_if == dif || + sk->sk_bound_dev_if == sdif); + + if (exact_dif && !dev_match) return -1; - score += 4; + if (sk->sk_bound_dev_if && dev_match) + score += 4; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) score++; @@ -208,7 +212,7 @@ struct sock *__inet_lookup_listener(struct net *net, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, - const int dif) + const int dif, const int sdif) { unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; @@ -218,7 +222,8 @@ struct sock *__inet_lookup_listener(struct net *net, u32 phash = 0; sk_for_each_rcu(sk, &ilb->head) { - score = compute_score(sk, net, hnum, daddr, dif, exact_dif); + score = compute_score(sk, net, hnum, daddr, + dif, sdif, exact_dif); if (score > hiscore) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -268,7 +273,7 @@ struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, - const int dif) + const int dif, const int sdif) { INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(sport, hnum); @@ -286,11 +291,12 @@ begin: if (sk->sk_hash != hash) continue; if (likely(INET_MATCH(sk, net, acookie, - saddr, daddr, ports, dif))) { + saddr, daddr, ports, dif, sdif))) { if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET_MATCH(sk, net, acookie, - saddr, daddr, ports, dif))) { + saddr, daddr, ports, + dif, sdif))) { sock_gen_put(sk); goto begin; } @@ -321,9 +327,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, __be32 daddr = inet->inet_rcv_saddr; __be32 saddr = inet->inet_daddr; int dif = sk->sk_bound_dev_if; + struct net *net = sock_net(sk); + int sdif = l3mdev_master_ifindex_by_index(net, dif); INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); - struct net *net = sock_net(sk); unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); @@ -339,7 +346,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, continue; if (likely(INET_MATCH(sk2, net, acookie, - saddr, daddr, ports, dif))) { + saddr, daddr, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 93157f2f4758..525ae88d1e58 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -86,8 +86,8 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, * NOTE: dopt cannot point to skb. */ -int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb, - const struct ip_options *sopt) +int __ip_options_echo(struct net *net, struct ip_options *dopt, + struct sk_buff *skb, const struct ip_options *sopt) { unsigned char *sptr, *dptr; int soffset, doffset; @@ -140,7 +140,7 @@ int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb, __be32 addr; memcpy(&addr, dptr+soffset-1, 4); - if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_UNICAST) { + if (inet_addr_type(net, addr) != RTN_UNICAST) { dopt->ts_needtime = 1; soffset += 8; } @@ -174,9 +174,6 @@ int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb, doffset -= 4; } if (doffset > 3) { - __be32 daddr = fib_compute_spec_dst(skb); - - memcpy(&start[doffset-1], &daddr, 4); dopt->faddr = faddr; dptr[0] = start[0]; dptr[1] = doffset+3; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b631ec685d77..73b0b15245b6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1525,7 +1525,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, int err; int oif; - if (__ip_options_echo(&replyopts.opt.opt, skb, sopt)) + if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; ipc.addr = daddr; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ecc4b4a2413e..e558e4f9597b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -80,7 +80,8 @@ static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) } -static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) +static void ip_cmsg_recv_retopts(struct net *net, struct msghdr *msg, + struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; @@ -88,7 +89,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) if (IPCB(skb)->opt.optlen == 0) return; - if (ip_options_echo(opt, skb)) { + if (ip_options_echo(net, opt, skb)) { msg->msg_flags |= MSG_CTRUNC; return; } @@ -204,7 +205,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, } if (flags & IP_CMSG_RETOPTS) { - ip_cmsg_recv_retopts(msg, skb); + ip_cmsg_recv_retopts(sock_net(sk), msg, skb); flags &= ~IP_CMSG_RETOPTS; if (!flags) @@ -1206,6 +1207,7 @@ e_inval: void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags); bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || ipv6_sk_rxinfo(sk); @@ -1219,7 +1221,7 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) * (e.g., process binds socket to eth0 for Tx which is * redirected to loopback in the rtable/dst). */ - if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX) + if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX || l3slave) pktinfo->ipi_ifindex = inet_iif(skb); pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); @@ -1227,14 +1229,7 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb) pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } - /* We need to keep the dst for __ip_options_echo() - * We could restrict the test to opt.ts_needtime || opt.srr, - * but the following is good enough as IP options are not often used. - */ - if (unlikely(IPCB(skb)->opt.optlen)) - skb_dst_force(skb); - else - skb_dst_drop(skb); + skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 06863ea3fc5b..c9b3e6e069ae 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -3114,14 +3114,14 @@ int __init ip_mr_init(void) } #endif rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, - ipmr_rtm_getroute, ipmr_rtm_dumproute, NULL); + ipmr_rtm_getroute, ipmr_rtm_dumproute, 0); rtnl_register(RTNL_FAMILY_IPMR, RTM_NEWROUTE, - ipmr_rtm_route, NULL, NULL); + ipmr_rtm_route, NULL, 0); rtnl_register(RTNL_FAMILY_IPMR, RTM_DELROUTE, - ipmr_rtm_route, NULL, NULL); + ipmr_rtm_route, NULL, 0); rtnl_register(RTNL_FAMILY_IPMR, RTM_GETLINK, - NULL, ipmr_rtm_dumplink, NULL); + NULL, ipmr_rtm_dumplink, 0); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index b0bb5d0a30bd..33b70bfd1122 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -122,7 +122,8 @@ void raw_unhash_sk(struct sock *sk) EXPORT_SYMBOL_GPL(raw_unhash_sk); struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, - unsigned short num, __be32 raddr, __be32 laddr, int dif) + unsigned short num, __be32 raddr, __be32 laddr, + int dif, int sdif) { sk_for_each_from(sk) { struct inet_sock *inet = inet_sk(sk); @@ -130,7 +131,8 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, if (net_eq(sock_net(sk), net) && inet->inet_num == num && !(inet->inet_daddr && inet->inet_daddr != raddr) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && + sk->sk_bound_dev_if != sdif)) goto found; /* gotcha */ } sk = NULL; @@ -171,6 +173,7 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) */ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) { + int sdif = inet_sdif(skb); struct sock *sk; struct hlist_head *head; int delivered = 0; @@ -184,13 +187,13 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) net = dev_net(skb->dev); sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol, iph->saddr, iph->daddr, - skb->dev->ifindex); + skb->dev->ifindex, sdif); while (sk) { delivered = 1; if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) && ip_mc_sf_allow(sk, iph->daddr, iph->saddr, - skb->dev->ifindex)) { + skb->dev->ifindex, sdif)) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ @@ -199,7 +202,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) } sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol, iph->saddr, iph->daddr, - skb->dev->ifindex); + skb->dev->ifindex, sdif); } out: read_unlock(&raw_v4_hashinfo.lock); @@ -297,12 +300,15 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) read_lock(&raw_v4_hashinfo.lock); raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]); if (raw_sk) { + int dif = skb->dev->ifindex; + int sdif = inet_sdif(skb); + iph = (const struct iphdr *)skb->data; net = dev_net(skb->dev); while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol, iph->daddr, iph->saddr, - skb->dev->ifindex)) != NULL) { + dif, sdif)) != NULL) { raw_err(raw_sk, skb, info); raw_sk = sk_next(raw_sk); iph = (const struct iphdr *)skb->data; diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index e1a51ca68d23..c200065ef9a5 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -46,13 +46,13 @@ static struct sock *raw_lookup(struct net *net, struct sock *from, sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol, r->id.idiag_dst[0], r->id.idiag_src[0], - r->id.idiag_if); + r->id.idiag_if, 0); #if IS_ENABLED(CONFIG_IPV6) else sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol, (const struct in6_addr *)r->id.idiag_src, (const struct in6_addr *)r->id.idiag_dst, - r->id.idiag_if); + r->id.idiag_if, 0); #endif return sk; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0383e66f59bc..872b4cb136d3 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1398,7 +1398,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst) struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); struct rtable *rt = (struct rtable *) dst; - if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt)) + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) kfree(p); if (!list_empty(&rt->rt_uncached)) { @@ -1456,7 +1456,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true); if (fi->fib_metrics != &dst_default_metrics) { rt->dst._metrics |= DST_METRICS_REFCOUNTED; - atomic_inc(&fi->fib_metrics->refcnt); + refcount_inc(&fi->fib_metrics->refcnt); } #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; @@ -2236,7 +2236,7 @@ add: if (!rth) return ERR_PTR(-ENOBUFS); - rth->rt_iif = orig_oif ? : 0; + rth->rt_iif = orig_oif; if (res->table) rth->rt_table_id = res->table->tb_id; @@ -2439,6 +2439,12 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, /* L3 master device is the loopback for that domain */ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; + + /* make sure orig_oif points to fib result device even + * though packet rx/tx happens over loopback or l3mdev + */ + orig_oif = FIB_RES_OIF(*res); + fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; @@ -2750,12 +2756,13 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); + else + skb_dst_set(skb, &rt->dst); } if (err) goto errout_free; - skb_dst_set(skb, &rt->dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -3067,7 +3074,8 @@ int __init ip_rt_init(void) xfrm_init(); xfrm4_init(); #endif - rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, + RTNL_FLAG_DOIT_UNLOCKED); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 03ad8778c395..b1bb1b3a1082 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ - ireq->opt = tcp_v4_save_options(skb); + ireq->opt = tcp_v4_save_options(sock_net(sk), skb); if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9dd6f4dba9b1..d25e3bcca66b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1058,6 +1058,7 @@ int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, return do_tcp_sendpages(sk, page, offset, size, flags); } +EXPORT_SYMBOL_GPL(tcp_sendpage_locked); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) @@ -1165,6 +1166,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); + struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct sockcm_cookie sockc; int flags, err, copied = 0; @@ -1174,6 +1176,26 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) long timeo; flags = msg->msg_flags; + + if (flags & MSG_ZEROCOPY && size) { + if (sk->sk_state != TCP_ESTABLISHED) { + err = -EINVAL; + goto out_err; + } + + skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL; + uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); + if (!uarg) { + err = -ENOBUFS; + goto out_err; + } + + /* skb may be freed in main loop, keep extra ref on uarg */ + sock_zerocopy_get(uarg); + if (!(sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG)) + uarg->zerocopy = 0; + } + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) @@ -1297,7 +1319,7 @@ new_segment: err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy); if (err) goto do_fault; - } else { + } else if (!uarg || !uarg->zerocopy) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); @@ -1335,6 +1357,13 @@ new_segment: page_ref_inc(pfrag->page); } pfrag->offset += copy; + } else { + err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); + if (err == -EMSGSIZE || err == -EEXIST) + goto new_segment; + if (err < 0) + goto do_error; + copy = err; } if (!copied) @@ -1381,6 +1410,7 @@ out: tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: + sock_zerocopy_put(uarg); return copied + copied_syn; do_fault: @@ -1397,6 +1427,7 @@ do_error: if (copied + copied_syn) goto out; out_err: + sock_zerocopy_put_abort(uarg); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && @@ -1406,6 +1437,7 @@ out_err: } return err; } +EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 609965f0e298..fc3614377413 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -49,7 +49,6 @@ MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wma struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ - u32 loss_cwnd; /* congestion window at last loss */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 epoch_start; /* beginning of an epoch */ @@ -72,7 +71,6 @@ static void bictcp_init(struct sock *sk) struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); - ca->loss_cwnd = 0; if (initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; @@ -172,22 +170,12 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk) else ca->last_max_cwnd = tp->snd_cwnd; - ca->loss_cwnd = tp->snd_cwnd; - if (tp->snd_cwnd <= low_window) return max(tp->snd_cwnd >> 1U, 2U); else return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U); } -static u32 bictcp_undo_cwnd(struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - const struct bictcp *ca = inet_csk_ca(sk); - - return max(tp->snd_cwnd, ca->loss_cwnd); -} - static void bictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) @@ -214,7 +202,7 @@ static struct tcp_congestion_ops bictcp __read_mostly = { .ssthresh = bictcp_recalc_ssthresh, .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, - .undo_cwnd = bictcp_undo_cwnd, + .undo_cwnd = tcp_reno_undo_cwnd, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "bic", diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 50a0f3e51d5b..66ac69f7bd19 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -85,7 +85,6 @@ struct cdg { u8 state; u8 delack; u32 rtt_seq; - u32 undo_cwnd; u32 shadow_wnd; u16 backoff_cnt; u16 sample_cnt; @@ -330,8 +329,6 @@ static u32 tcp_cdg_ssthresh(struct sock *sk) struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - ca->undo_cwnd = tp->snd_cwnd; - if (ca->state == CDG_BACKOFF) return max(2U, (tp->snd_cwnd * min(1024U, backoff_beta)) >> 10); @@ -344,13 +341,6 @@ static u32 tcp_cdg_ssthresh(struct sock *sk) return max(2U, tp->snd_cwnd >> 1); } -static u32 tcp_cdg_undo_cwnd(struct sock *sk) -{ - struct cdg *ca = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, ca->undo_cwnd); -} - static void tcp_cdg_cwnd_event(struct sock *sk, const enum tcp_ca_event ev) { struct cdg *ca = inet_csk_ca(sk); @@ -403,7 +393,7 @@ struct tcp_congestion_ops tcp_cdg __read_mostly = { .cong_avoid = tcp_cdg_cong_avoid, .cwnd_event = tcp_cdg_cwnd_event, .pkts_acked = tcp_cdg_acked, - .undo_cwnd = tcp_cdg_undo_cwnd, + .undo_cwnd = tcp_reno_undo_cwnd, .ssthresh = tcp_cdg_ssthresh, .release = tcp_cdg_release, .init = tcp_cdg_init, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index fde983f6376b..c2b174469645 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -456,7 +456,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - return max(tp->snd_cwnd, tp->snd_ssthresh << 1); + return max(tp->snd_cwnd, tp->prior_cwnd); } EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 57ae5b5ae643..78bfadfcf342 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -83,7 +83,6 @@ MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (mse struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ - u32 loss_cwnd; /* congestion window at last loss */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 bic_origin_point;/* origin point of bic function */ @@ -142,7 +141,6 @@ static void bictcp_init(struct sock *sk) struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); - ca->loss_cwnd = 0; if (hystart) bictcp_hystart_reset(sk); @@ -366,18 +364,9 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk) else ca->last_max_cwnd = tp->snd_cwnd; - ca->loss_cwnd = tp->snd_cwnd; - return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U); } -static u32 bictcp_undo_cwnd(struct sock *sk) -{ - struct bictcp *ca = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); -} - static void bictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) { @@ -470,7 +459,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .ssthresh = bictcp_recalc_ssthresh, .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, - .undo_cwnd = bictcp_undo_cwnd, + .undo_cwnd = tcp_reno_undo_cwnd, .cwnd_event = bictcp_cwnd_event, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 6d9879e93648..d1c33c91eadc 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -94,7 +94,6 @@ static const struct hstcp_aimd_val { struct hstcp { u32 ai; - u32 loss_cwnd; }; static void hstcp_init(struct sock *sk) @@ -153,22 +152,14 @@ static u32 hstcp_ssthresh(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); struct hstcp *ca = inet_csk_ca(sk); - ca->loss_cwnd = tp->snd_cwnd; /* Do multiplicative decrease */ return max(tp->snd_cwnd - ((tp->snd_cwnd * hstcp_aimd_vals[ca->ai].md) >> 8), 2U); } -static u32 hstcp_cwnd_undo(struct sock *sk) -{ - const struct hstcp *ca = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); -} - static struct tcp_congestion_ops tcp_highspeed __read_mostly = { .init = hstcp_init, .ssthresh = hstcp_ssthresh, - .undo_cwnd = hstcp_cwnd_undo, + .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = hstcp_cong_avoid, .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 3eb78cde6ff0..082d479462fa 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -66,7 +66,6 @@ static inline void htcp_reset(struct htcp *ca) static u32 htcp_cwnd_undo(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); if (ca->undo_last_cong) { @@ -76,7 +75,7 @@ static u32 htcp_cwnd_undo(struct sock *sk) ca->undo_last_cong = 0; } - return max(tp->snd_cwnd, (tp->snd_ssthresh << 7) / ca->beta); + return tcp_reno_undo_cwnd(sk); } static inline void measure_rtt(struct sock *sk, u32 srtt) diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 60352ff4f5a8..7c843578f233 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -48,7 +48,6 @@ struct illinois { u32 end_seq; /* right edge of current RTT */ u32 alpha; /* Additive increase */ u32 beta; /* Muliplicative decrease */ - u32 loss_cwnd; /* cwnd on loss */ u16 acked; /* # packets acked by current ACK */ u8 rtt_above; /* average rtt has gone above threshold */ u8 rtt_low; /* # of rtts measurements below threshold */ @@ -297,18 +296,10 @@ static u32 tcp_illinois_ssthresh(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); - ca->loss_cwnd = tp->snd_cwnd; /* Multiplicative decrease */ return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->beta) >> BETA_SHIFT), 2U); } -static u32 tcp_illinois_cwnd_undo(struct sock *sk) -{ - const struct illinois *ca = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); -} - /* Extract info for Tcp socket info provided via netlink. */ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) @@ -336,7 +327,7 @@ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, static struct tcp_congestion_ops tcp_illinois __read_mostly = { .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, - .undo_cwnd = tcp_illinois_cwnd_undo, + .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index af0a98d54b62..d73903fe8c83 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -106,6 +106,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ +#define FLAG_SET_XMIT_TIMER 0x1000 /* Set TLP or RTO timer */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ @@ -1950,6 +1951,7 @@ void tcp_enter_loss(struct sock *sk) !after(tp->high_seq, tp->snd_una) || (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) { tp->prior_ssthresh = tcp_current_ssthresh(sk); + tp->prior_cwnd = tp->snd_cwnd; tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); tcp_ca_event(sk, CA_EVENT_LOSS); tcp_init_undo(tp); @@ -2519,8 +2521,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) return; /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || - (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { + if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && + (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) { tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_jiffies32; } @@ -3003,10 +3005,7 @@ void tcp_rearm_rto(struct sock *sk) /* Offset the time elapsed after installing regular RTO */ if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { - struct sk_buff *skb = tcp_write_queue_head(sk); - u64 rto_time_stamp = skb->skb_mstamp + - jiffies_to_usecs(rto); - s64 delta_us = rto_time_stamp - tp->tcp_mstamp; + s64 delta_us = tcp_rto_delta_us(sk); /* delta_us may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ @@ -3018,6 +3017,13 @@ void tcp_rearm_rto(struct sock *sk) } } +/* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */ +static void tcp_set_xmit_timer(struct sock *sk) +{ + if (!tcp_schedule_loss_probe(sk)) + tcp_rearm_rto(sk); +} + /* If we get here, the whole TSO packet has not been acked. */ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) { @@ -3179,7 +3185,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_rtt_us, sack->rate); if (flag & FLAG_ACKED) { - tcp_rearm_rto(sk); + flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */ if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); @@ -3207,7 +3213,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. */ - tcp_rearm_rto(sk); + flag |= FLAG_SET_XMIT_TIMER; /* set TLP or RTO timer */ } if (icsk->icsk_ca_ops->pkts_acked) { @@ -3574,9 +3580,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, tp->snd_nxt)) goto invalid_ack; - if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) - tcp_rearm_rto(sk); - if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; icsk->icsk_retransmits = 0; @@ -3625,18 +3628,20 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, &sack_state); + if (tp->tlp_high_seq) + tcp_process_tlp_ack(sk, ack, flag); + /* If needed, reset TLP/RTO timer; RACK may later override this. */ + if (flag & FLAG_SET_XMIT_TIMER) + tcp_set_xmit_timer(sk); + if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); } - if (tp->tlp_high_seq) - tcp_process_tlp_ack(sk, ack, flag); if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); - if (icsk->icsk_pending == ICSK_TIME_RETRANS) - tcp_schedule_loss_probe(sk); delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ lost = tp->lost - lost; /* freshly marked lost */ tcp_rate_gen(sk, delivered, lost, sack_state.rate); @@ -4564,8 +4569,8 @@ err: static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - bool fragstolen = false; - int eaten = -1; + bool fragstolen; + int eaten; if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); @@ -4588,12 +4593,11 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) /* Ok. In sequence. In window. */ queue_and_out: - if (eaten < 0) { - if (skb_queue_len(&sk->sk_receive_queue) == 0) - sk_forced_mem_schedule(sk, skb->truesize); - else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) - goto drop; - } + if (skb_queue_len(&sk->sk_receive_queue) == 0) + sk_forced_mem_schedule(sk, skb->truesize); + else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) + goto drop; + eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (skb->len) @@ -5343,11 +5347,6 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) if (sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); - - if (!sock_flag(sk, SOCK_DEAD)) { - sk->sk_state_change(sk); - sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); - } } static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9b51663cd5a4..5af8b809dfbc 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -383,7 +383,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), - inet_iif(icmp_skb)); + inet_iif(icmp_skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return; @@ -659,7 +659,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, - ntohs(th->source), inet_iif(skb)); + ntohs(th->source), inet_iif(skb), + tcp_v4_sdif(skb)); /* don't send rst if it can't find key */ if (!sk1) goto out; @@ -1267,7 +1268,7 @@ static void tcp_v4_init_req(struct request_sock *req, sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); - ireq->opt = tcp_v4_save_options(skb); + ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, @@ -1523,7 +1524,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), - skb->skb_iif); + skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; @@ -1588,6 +1589,7 @@ EXPORT_SYMBOL(tcp_filter); int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + int sdif = inet_sdif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; @@ -1638,7 +1640,7 @@ int tcp_v4_rcv(struct sk_buff *skb) lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, - th->dest, &refcounted); + th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; @@ -1665,6 +1667,8 @@ process: */ sock_hold(sk); refcounted = true; + if (tcp_filter(sk, skb)) + goto discard_and_relse; nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); @@ -1672,8 +1676,6 @@ process: } if (nsk == sk) { reqsk_put(req); - } else if (tcp_filter(sk, skb)) { - goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; @@ -1766,7 +1768,8 @@ do_time_wait: __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, - inet_iif(skb)); + inet_iif(skb), + sdif); if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 6d650ed3cb59..1ff73982e28c 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -86,7 +86,6 @@ struct tcpnv { * < 0 => less than 1 packet/RTT */ u8 available8; u16 available16; - u32 loss_cwnd; /* cwnd at last loss */ u8 nv_allow_cwnd_growth:1, /* whether cwnd can grow */ nv_reset:1, /* whether to reset values */ nv_catchup:1; /* whether we are growing because @@ -121,7 +120,6 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); ca->nv_reset = 0; - ca->loss_cwnd = 0; ca->nv_no_cong_cnt = 0; ca->nv_rtt_cnt = 0; ca->nv_last_rtt = 0; @@ -177,19 +175,10 @@ static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked) static u32 tcpnv_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - struct tcpnv *ca = inet_csk_ca(sk); - ca->loss_cwnd = tp->snd_cwnd; return max((tp->snd_cwnd * nv_loss_dec_factor) >> 10, 2U); } -static u32 tcpnv_undo_cwnd(struct sock *sk) -{ - struct tcpnv *ca = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); -} - static void tcpnv_state(struct sock *sk, u8 new_state) { struct tcpnv *ca = inet_csk_ca(sk); @@ -446,7 +435,7 @@ static struct tcp_congestion_ops tcpnv __read_mostly = { .ssthresh = tcpnv_recalc_ssthresh, .cong_avoid = tcpnv_cong_avoid, .set_state = tcpnv_state, - .undo_cwnd = tcpnv_undo_cwnd, + .undo_cwnd = tcp_reno_undo_cwnd, .pkts_acked = tcpnv_acked, .get_info = tcpnv_get_info, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d49bff51bdb7..3e0d19631534 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2375,23 +2375,14 @@ bool tcp_schedule_loss_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, tlp_time_stamp, rto_time_stamp; + u32 timeout, rto_delta_us; - /* No consecutive loss probes. */ - if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) { - tcp_rearm_rto(sk); - return false; - } /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (tp->fastopen_rsk) return false; - /* TLP is only scheduled when next timer event is RTO. */ - if (icsk->icsk_pending != ICSK_TIME_RETRANS) - return false; - /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ @@ -2418,14 +2409,10 @@ bool tcp_schedule_loss_probe(struct sock *sk) timeout = TCP_TIMEOUT_INIT; } - /* If RTO is shorter, just schedule TLP in its place. */ - tlp_time_stamp = tcp_jiffies32 + timeout; - rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; - if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { - s32 delta = rto_time_stamp - tcp_jiffies32; - if (delta > 0) - timeout = delta; - } + /* If the RTO formula yields an earlier time, then use that time. */ + rto_delta_us = tcp_rto_delta_us(sk); /* How far in future is RTO? */ + if (rto_delta_us > 0) + timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); @@ -3450,6 +3437,10 @@ int tcp_connect(struct sock *sk) int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); + + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) + return -EHOSTUNREACH; /* Routing failure or similar. */ + tcp_connect_init(sk); if (unlikely(tp->repair)) { diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index f2123075ce6e..addc122f8818 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -15,10 +15,6 @@ #define TCP_SCALABLE_AI_CNT 50U #define TCP_SCALABLE_MD_SCALE 3 -struct scalable { - u32 loss_cwnd; -}; - static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); @@ -36,23 +32,13 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) static u32 tcp_scalable_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - struct scalable *ca = inet_csk_ca(sk); - - ca->loss_cwnd = tp->snd_cwnd; return max(tp->snd_cwnd - (tp->snd_cwnd>>TCP_SCALABLE_MD_SCALE), 2U); } -static u32 tcp_scalable_cwnd_undo(struct sock *sk) -{ - const struct scalable *ca = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); -} - static struct tcp_congestion_ops tcp_scalable __read_mostly = { .ssthresh = tcp_scalable_ssthresh, - .undo_cwnd = tcp_scalable_cwnd_undo, + .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_scalable_cong_avoid, .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f753f9d2fee3..655dd8d7f064 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -640,7 +640,8 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) + if (!sock_flag(sk, SOCK_KEEPOPEN) || + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 2417f55374c5..6bb9e14c710a 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -122,14 +122,14 @@ int tcp_set_ulp(struct sock *sk, const char *name) ulp_ops = __tcp_ulp_find_autoload(name); if (!ulp_ops) - err = -ENOENT; - else - err = ulp_ops->init(sk); + return -ENOENT; - if (err) - goto out; + err = ulp_ops->init(sk); + if (err) { + module_put(ulp_ops->owner); + return err; + } icsk->icsk_ulp_ops = ulp_ops; - out: - return err; + return 0; } diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 76005d4b8dfc..6fcf482d611b 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -30,7 +30,6 @@ struct veno { u32 basertt; /* the min of all Veno rtt measurements seen (in usec) */ u32 inc; /* decide whether to increase cwnd */ u32 diff; /* calculate the diff rate */ - u32 loss_cwnd; /* cwnd when loss occured */ }; /* There are several situations when we must "re-start" Veno: @@ -194,7 +193,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); struct veno *veno = inet_csk_ca(sk); - veno->loss_cwnd = tp->snd_cwnd; if (veno->diff < beta) /* in "non-congestive state", cut cwnd by 1/5 */ return max(tp->snd_cwnd * 4 / 5, 2U); @@ -203,17 +201,10 @@ static u32 tcp_veno_ssthresh(struct sock *sk) return max(tp->snd_cwnd >> 1U, 2U); } -static u32 tcp_veno_cwnd_undo(struct sock *sk) -{ - const struct veno *veno = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, veno->loss_cwnd); -} - static struct tcp_congestion_ops tcp_veno __read_mostly = { .init = tcp_veno_init, .ssthresh = tcp_veno_ssthresh, - .undo_cwnd = tcp_veno_cwnd_undo, + .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_veno_cong_avoid, .pkts_acked = tcp_veno_pkts_acked, .set_state = tcp_veno_state, diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index e6ff99c4bd3b..96e829b2e2fc 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -37,7 +37,6 @@ struct yeah { u32 fast_count; u32 pkts_acked; - u32 loss_cwnd; }; static void tcp_yeah_init(struct sock *sk) @@ -220,22 +219,14 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) yeah->fast_count = 0; yeah->reno_count = max(yeah->reno_count>>1, 2U); - yeah->loss_cwnd = tp->snd_cwnd; return max_t(int, tp->snd_cwnd - reduction, 2); } -static u32 tcp_yeah_cwnd_undo(struct sock *sk) -{ - const struct yeah *yeah = inet_csk_ca(sk); - - return max(tcp_sk(sk)->snd_cwnd, yeah->loss_cwnd); -} - static struct tcp_congestion_ops tcp_yeah __read_mostly = { .init = tcp_yeah_init, .ssthresh = tcp_yeah_ssthresh, - .undo_cwnd = tcp_yeah_cwnd_undo, + .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_yeah_cong_avoid, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e6276fa3750b..cb633884e825 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -380,8 +380,8 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) static int compute_score(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum, int dif, - bool exact_dif) + __be32 daddr, unsigned short hnum, + int dif, int sdif, bool exact_dif) { int score; struct inet_sock *inet; @@ -413,10 +413,15 @@ static int compute_score(struct sock *sk, struct net *net, } if (sk->sk_bound_dev_if || exact_dif) { - if (sk->sk_bound_dev_if != dif) + bool dev_match = (sk->sk_bound_dev_if == dif || + sk->sk_bound_dev_if == sdif); + + if (exact_dif && !dev_match) return -1; - score += 4; + if (sk->sk_bound_dev_if && dev_match) + score += 4; } + if (sk->sk_incoming_cpu == raw_smp_processor_id()) score++; return score; @@ -436,10 +441,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, - __be32 saddr, __be16 sport, - __be32 daddr, unsigned int hnum, int dif, bool exact_dif, - struct udp_hslot *hslot2, - struct sk_buff *skb) + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, bool exact_dif, + struct udp_hslot *hslot2, + struct sk_buff *skb) { struct sock *sk, *result; int score, badness, matches = 0, reuseport = 0; @@ -449,7 +455,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, exact_dif); + daddr, hnum, dif, sdif, exact_dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -477,8 +483,8 @@ static struct sock *udp4_lib_lookup2(struct net *net, * harder than this. -DaveM */ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, - __be16 sport, __be32 daddr, __be16 dport, - int dif, struct udp_table *udptable, struct sk_buff *skb) + __be16 sport, __be32 daddr, __be16 dport, int dif, + int sdif, struct udp_table *udptable, struct sk_buff *skb) { struct sock *sk, *result; unsigned short hnum = ntohs(dport); @@ -496,7 +502,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, goto begin; result = udp4_lib_lookup2(net, saddr, sport, - daddr, hnum, dif, + daddr, hnum, dif, sdif, exact_dif, hslot2, skb); if (!result) { unsigned int old_slot2 = slot2; @@ -511,7 +517,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, goto begin; result = udp4_lib_lookup2(net, saddr, sport, - daddr, hnum, dif, + daddr, hnum, dif, sdif, exact_dif, hslot2, skb); } return result; @@ -521,7 +527,7 @@ begin: badness = 0; sk_for_each_rcu(sk, &hslot->head) { score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, exact_dif); + daddr, hnum, dif, sdif, exact_dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -554,7 +560,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - udptable, skb); + inet_sdif(skb), udptable, skb); } struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, @@ -576,7 +582,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, struct sock *sk; sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, - dif, &udp_table, NULL); + dif, 0, &udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -587,7 +593,7 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup); static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, - int dif, unsigned short hnum) + int dif, int sdif, unsigned short hnum) { struct inet_sock *inet = inet_sk(sk); @@ -597,9 +603,10 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, (inet->inet_dport != rmt_port && inet->inet_dport) || (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) || ipv6_only_sock(sk) || - (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && + sk->sk_bound_dev_if != sdif)) return false; - if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif)) + if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif)) return false; return true; } @@ -628,8 +635,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) struct net *net = dev_net(skb->dev); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, - iph->saddr, uh->source, skb->dev->ifindex, udptable, - NULL); + iph->saddr, uh->source, skb->dev->ifindex, 0, + udptable, NULL); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return; /* No socket for error */ @@ -802,7 +809,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); - else if (sk->sk_no_check_tx) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx && !skb_is_gso(skb)) { /* UDP csum off */ skb->ip_summed = CHECKSUM_NONE; goto send; @@ -1176,7 +1183,11 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif - if (likely(!skb->_skb_refdst)) + /* all head states execept sp (dst, sk, nf) are always cleared by + * udp_rcv() and we need to preserve secpath, if present, to eventually + * process IP_CMSG_PASSSEC at recvmsg() time + */ + if (likely(!skb_sec_path(skb))) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } @@ -1782,13 +1793,6 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id_once(sk, skb); } - /* At recvmsg() time we may access skb->dst or skb->sp depending on - * the IP options and the cmsg flags, elsewhere can we clear all - * pending head states while they are hot in the cache - */ - if (likely(IPCB(skb)->opt.optlen == 0 && !skb_sec_path(skb))) - skb_release_head_state(skb); - rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1956,6 +1960,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); unsigned int offset = offsetof(typeof(*sk), sk_node); int dif = skb->dev->ifindex; + int sdif = inet_sdif(skb); struct hlist_node *node; struct sk_buff *nskb; @@ -1970,7 +1975,7 @@ start_lookup: sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr, - uh->source, saddr, dif, hnum)) + uh->source, saddr, dif, sdif, hnum)) continue; if (!first) { @@ -2160,7 +2165,7 @@ drop: static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, - int dif) + int dif, int sdif) { struct sock *sk, *result; unsigned short hnum = ntohs(loc_port); @@ -2174,7 +2179,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, result = NULL; sk_for_each_rcu(sk, &hslot->head) { if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr, - rmt_port, rmt_addr, dif, hnum)) { + rmt_port, rmt_addr, dif, sdif, hnum)) { if (result) return NULL; result = sk; @@ -2191,7 +2196,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, static struct sock *__udp4_lib_demux_lookup(struct net *net, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, - int dif) + int dif, int sdif) { unsigned short hnum = ntohs(loc_port); unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum); @@ -2203,7 +2208,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (INET_MATCH(sk, net, acookie, rmt_addr, - loc_addr, ports, dif)) + loc_addr, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; @@ -2219,6 +2224,7 @@ void udp_v4_early_demux(struct sk_buff *skb) struct sock *sk = NULL; struct dst_entry *dst; int dif = skb->dev->ifindex; + int sdif = inet_sdif(skb); int ours; /* validate the packet */ @@ -2244,10 +2250,11 @@ void udp_v4_early_demux(struct sk_buff *skb) } sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, - uh->source, iph->saddr, dif); + uh->source, iph->saddr, + dif, sdif); } else if (skb->pkt_type == PACKET_HOST) { sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, - uh->source, iph->saddr, dif); + uh->source, iph->saddr, dif, sdif); } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 4515836d2a3a..d0390d844ac8 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -45,7 +45,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, - req->id.idiag_if, tbl, NULL); + req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) sk = __udp6_lib_lookup(net, @@ -53,7 +53,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, - req->id.idiag_if, tbl, NULL); + req->id.idiag_if, 0, tbl, NULL); #endif if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; @@ -182,7 +182,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, sk = __udp4_lib_lookup(net, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, - req->id.idiag_if, tbl, NULL); + req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && @@ -190,7 +190,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, sk = __udp4_lib_lookup(net, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, - req->id.idiag_if, tbl, NULL); + req->id.idiag_if, 0, tbl, NULL); else sk = __udp6_lib_lookup(net, @@ -198,7 +198,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, - req->id.idiag_if, tbl, NULL); + req->id.idiag_if, 0, tbl, NULL); } #endif else { diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 48c452959d2c..0d722396dce6 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -311,19 +311,8 @@ config IPV6_SEG6_LWTUNNEL ---help--- Support for encapsulation of packets within an outer IPv6 header and a Segment Routing Header using the lightweight - tunnels mechanism. - - If unsure, say N. - -config IPV6_SEG6_INLINE - bool "IPv6: direct Segment Routing Header insertion " - depends on IPV6_SEG6_LWTUNNEL - ---help--- - Support for direct insertion of the Segment Routing Header, - also known as inline mode. Be aware that direct insertion of - extension headers (as opposed to encapsulation) may break - multiple mechanisms such as PMTUD or IPSec AH. Use this feature - only if you know exactly what you are doing. + tunnels mechanism. Also enable support for advanced local + processing of SRv6 packets based on their active segment. If unsure, say N. diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 217e9ff0e24b..10e342363793 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -9,7 +9,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ - udp_offload.o seg6.o + udp_offload.o seg6.o fib6_notifier.o ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o @@ -23,7 +23,7 @@ ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o ipv6-$(CONFIG_PROC_FS) += proc.o ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o ipv6-$(CONFIG_NETLABEL) += calipso.o -ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o +ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o seg6_local.o ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o ipv6-objs += $(ipv6-y) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3c46e9513a31..640792e1ecb7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3066,7 +3066,7 @@ static void init_loopback(struct net_device *dev) * lo device down, release this obsolete dst and * reallocate a new router for ifa. */ - if (!atomic_read(&sp_ifa->rt->rt6i_ref)) { + if (!sp_ifa->rt->rt6i_node) { ip6_rt_put(sp_ifa->rt); sp_ifa->rt = NULL; } else { @@ -3321,11 +3321,11 @@ static void addrconf_gre_config(struct net_device *dev) static int fixup_permanent_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - /* rt6i_ref == 0 means the host route was removed from the + /* !rt6i_node means the host route was removed from the * FIB, for example, if 'lo' device is taken down. In that * case regenerate the host route. */ - if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) { + if (!ifp->rt || !ifp->rt->rt6i_node) { struct rt6_info *rt, *prev; rt = addrconf_dst_alloc(idev, &ifp->addr, false); @@ -6605,21 +6605,21 @@ int __init addrconf_init(void) rtnl_af_register(&inet6_ops); err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo, - NULL); + 0); if (err < 0) goto errout; /* Only the first call to __rtnl_register can fail */ - __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, NULL); - __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0); + __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0); __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, - inet6_dump_ifaddr, NULL); + inet6_dump_ifaddr, 0); __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, - inet6_dump_ifmcaddr, NULL); + inet6_dump_ifmcaddr, 0); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, - inet6_dump_ifacaddr, NULL); + inet6_dump_ifacaddr, 0); __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, - inet6_netconf_dump_devconf, NULL); + inet6_netconf_dump_devconf, 0); ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 7a428f65c7ec..cea5eb488013 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -593,10 +593,10 @@ out: void __init ipv6_addr_label_rtnl_register(void) { __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, - NULL, NULL); + NULL, 0); __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, - NULL, NULL); + NULL, 0); __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, - ip6addrlbl_dump, NULL); + ip6addrlbl_dump, 0); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0a7c74049a0c..3b58ee709f33 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -554,6 +554,8 @@ const struct proto_ops inet6_stream_ops = { .recvmsg = inet_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = inet_sendpage, + .sendmsg_locked = tcp_sendmsg_locked, + .sendpage_locked = tcp_sendpage_locked, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, .peek_len = tcp_peek_len, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 3cec529c6113..95516138e861 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -882,7 +882,7 @@ static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto, (hops - 1) * sizeof(struct in6_addr)); sr_phdr->segments[0] = **addr_p; - *addr_p = &sr_ihdr->segments[hops - 1]; + *addr_p = &sr_ihdr->segments[sr_ihdr->segments_left]; #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(sr_phdr)) { @@ -1174,7 +1174,7 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, { struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt; - fl6->daddr = srh->segments[srh->first_segment]; + fl6->daddr = srh->segments[srh->segments_left]; break; } default: diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c new file mode 100644 index 000000000000..66a103ef7e86 --- /dev/null +++ b/net/ipv6/fib6_notifier.c @@ -0,0 +1,61 @@ +#include <linux/notifier.h> +#include <linux/socket.h> +#include <linux/kernel.h> +#include <net/net_namespace.h> +#include <net/fib_notifier.h> +#include <net/netns/ipv6.h> +#include <net/ip6_fib.h> + +int call_fib6_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->family = AF_INET6; + return call_fib_notifier(nb, net, event_type, info); +} + +int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info) +{ + info->family = AF_INET6; + return call_fib_notifiers(net, event_type, info); +} + +static unsigned int fib6_seq_read(struct net *net) +{ + return fib6_tables_seq_read(net) + fib6_rules_seq_read(net); +} + +static int fib6_dump(struct net *net, struct notifier_block *nb) +{ + int err; + + err = fib6_rules_dump(net, nb); + if (err) + return err; + + return fib6_tables_dump(net, nb); +} + +static const struct fib_notifier_ops fib6_notifier_ops_template = { + .family = AF_INET6, + .fib_seq_read = fib6_seq_read, + .fib_dump = fib6_dump, +}; + +int __net_init fib6_notifier_init(struct net *net) +{ + struct fib_notifier_ops *ops; + + ops = fib_notifier_ops_register(&fib6_notifier_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv6.notifier_ops = ops; + + return 0; +} + +void __net_exit fib6_notifier_exit(struct net *net) +{ + fib_notifier_ops_unregister(net->ipv6.notifier_ops); +} diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index ec849d88a662..b240f24a6e52 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -14,6 +14,7 @@ */ #include <linux/netdevice.h> +#include <linux/notifier.h> #include <linux/export.h> #include <net/fib_rules.h> @@ -29,22 +30,65 @@ struct fib6_rule { u8 tclass; }; -struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, - int flags, pol_lookup_t lookup) +static bool fib6_rule_matchall(const struct fib_rule *rule) +{ + struct fib6_rule *r = container_of(rule, struct fib6_rule, common); + + if (r->dst.plen || r->src.plen || r->tclass) + return false; + return fib_rule_matchall(rule); +} + +bool fib6_rule_default(const struct fib_rule *rule) { - struct fib_lookup_arg arg = { - .lookup_ptr = lookup, - .flags = FIB_LOOKUP_NOREF, - }; + if (!fib6_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || + rule->l3mdev) + return false; + if (rule->table != RT6_TABLE_LOCAL && rule->table != RT6_TABLE_MAIN) + return false; + return true; +} +EXPORT_SYMBOL_GPL(fib6_rule_default); - /* update flow if oif or iif point to device enslaved to l3mdev */ - l3mdev_update_flow(net, flowi6_to_flowi(fl6)); +int fib6_rules_dump(struct net *net, struct notifier_block *nb) +{ + return fib_rules_dump(net, nb, AF_INET6); +} - fib_rules_lookup(net->ipv6.fib6_rules_ops, - flowi6_to_flowi(fl6), flags, &arg); +unsigned int fib6_rules_seq_read(struct net *net) +{ + return fib_rules_seq_read(net, AF_INET6); +} - if (arg.result) - return arg.result; +struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, + int flags, pol_lookup_t lookup) +{ + if (net->ipv6.fib6_has_custom_rules) { + struct fib_lookup_arg arg = { + .lookup_ptr = lookup, + .flags = FIB_LOOKUP_NOREF, + }; + + /* update flow if oif or iif point to device enslaved to l3mdev */ + l3mdev_update_flow(net, flowi6_to_flowi(fl6)); + + fib_rules_lookup(net->ipv6.fib6_rules_ops, + flowi6_to_flowi(fl6), flags, &arg); + + if (arg.result) + return arg.result; + } else { + struct rt6_info *rt; + + rt = lookup(net, net->ipv6.fib6_local_tbl, fl6, flags); + if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN) + return &rt->dst; + ip6_rt_put(rt); + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + if (rt->dst.error != -EAGAIN) + return &rt->dst; + ip6_rt_put(rt); + } dst_hold(&net->ipv6.ip6_null_entry->dst); return &net->ipv6.ip6_null_entry->dst; @@ -214,6 +258,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule6->dst.plen = frh->dst_len; rule6->tclass = frh->tos; + net->ipv6.fib6_has_custom_rules = true; err = 0; errout: return err; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b13b8f93079d..b01858f5deb1 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -56,7 +56,7 @@ struct sock *__inet6_lookup_established(struct net *net, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, - const int dif) + const int dif, const int sdif) { struct sock *sk; const struct hlist_nulls_node *node; @@ -73,12 +73,12 @@ begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; - if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) + if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; - if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { + if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))) { sock_gen_put(sk); goto begin; } @@ -96,7 +96,7 @@ EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, - const int dif, bool exact_dif) + const int dif, const int sdif, bool exact_dif) { int score = -1; @@ -110,9 +110,13 @@ static inline int compute_score(struct sock *sk, struct net *net, score++; } if (sk->sk_bound_dev_if || exact_dif) { - if (sk->sk_bound_dev_if != dif) + bool dev_match = (sk->sk_bound_dev_if == dif || + sk->sk_bound_dev_if == sdif); + + if (exact_dif && !dev_match) return -1; - score++; + if (sk->sk_bound_dev_if && dev_match) + score++; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) score++; @@ -126,7 +130,7 @@ struct sock *inet6_lookup_listener(struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, - const unsigned short hnum, const int dif) + const unsigned short hnum, const int dif, const int sdif) { unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; @@ -136,7 +140,7 @@ struct sock *inet6_lookup_listener(struct net *net, u32 phash = 0; sk_for_each(sk, &ilb->head) { - score = compute_score(sk, net, hnum, daddr, dif, exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif); if (score > hiscore) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -171,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, bool refcounted; sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, - ntohs(dport), dif, &refcounted); + ntohs(dport), dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -187,8 +191,9 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; - const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); + const int sdif = l3mdev_master_ifindex_by_index(net, dif); + const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); @@ -203,7 +208,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, if (sk2->sk_hash != hash) continue; - if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) { + if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, + dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ebb299cf72b7..8c58c7558de0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -33,6 +33,7 @@ #include <net/ndisc.h> #include <net/addrconf.h> #include <net/lwtunnel.h> +#include <net/fib_notifier.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -153,7 +154,7 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } -static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) +void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -176,15 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) free_percpu(non_pcpu_rt->rt6i_pcpu); non_pcpu_rt->rt6i_pcpu = NULL; } - -static void rt6_release(struct rt6_info *rt) -{ - if (atomic_dec_and_test(&rt->rt6i_ref)) { - rt6_free_pcpu(rt); - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - } -} +EXPORT_SYMBOL_GPL(rt6_free_pcpu); static void fib6_link_table(struct net *net, struct fib6_table *tb) { @@ -302,6 +295,109 @@ static void __net_init fib6_tables_init(struct net *net) #endif +unsigned int fib6_tables_seq_read(struct net *net) +{ + unsigned int h, fib_seq = 0; + + rcu_read_lock(); + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + struct hlist_head *head = &net->ipv6.fib_table_hash[h]; + struct fib6_table *tb; + + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { + read_lock_bh(&tb->tb6_lock); + fib_seq += tb->fib_seq; + read_unlock_bh(&tb->tb6_lock); + } + } + rcu_read_unlock(); + + return fib_seq; +} + +static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct rt6_info *rt) +{ + struct fib6_entry_notifier_info info = { + .rt = rt, + }; + + return call_fib6_notifier(nb, net, event_type, &info.info); +} + +static int call_fib6_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct rt6_info *rt) +{ + struct fib6_entry_notifier_info info = { + .rt = rt, + }; + + rt->rt6i_table->fib_seq++; + return call_fib6_notifiers(net, event_type, &info.info); +} + +struct fib6_dump_arg { + struct net *net; + struct notifier_block *nb; +}; + +static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg) +{ + if (rt == arg->net->ipv6.ip6_null_entry) + return; + call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt); +} + +static int fib6_node_dump(struct fib6_walker *w) +{ + struct rt6_info *rt; + + for (rt = w->leaf; rt; rt = rt->dst.rt6_next) + fib6_rt_dump(rt, w->args); + w->leaf = NULL; + return 0; +} + +static void fib6_table_dump(struct net *net, struct fib6_table *tb, + struct fib6_walker *w) +{ + w->root = &tb->tb6_root; + read_lock_bh(&tb->tb6_lock); + fib6_walk(net, w); + read_unlock_bh(&tb->tb6_lock); +} + +/* Called with rcu_read_lock() */ +int fib6_tables_dump(struct net *net, struct notifier_block *nb) +{ + struct fib6_dump_arg arg; + struct fib6_walker *w; + unsigned int h; + + w = kzalloc(sizeof(*w), GFP_ATOMIC); + if (!w) + return -ENOMEM; + + w->func = fib6_node_dump; + arg.net = net; + arg.nb = nb; + w->args = &arg; + + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + struct hlist_head *head = &net->ipv6.fib_table_hash[h]; + struct fib6_table *tb; + + hlist_for_each_entry_rcu(tb, head, tb6_hlist) + fib6_table_dump(net, tb, w); + } + + kfree(w); + + return 0; +} + static int fib6_dump_node(struct fib6_walker *w) { int res; @@ -733,8 +829,6 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, } fn = fn->parent; } - /* No more references are possible at this point. */ - BUG_ON(atomic_read(&rt->rt6i_ref) != 1); } } @@ -879,6 +973,8 @@ add: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); + call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, + rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; @@ -906,6 +1002,8 @@ add: rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); + call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, + rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { @@ -913,6 +1011,7 @@ add: fn->fn_flags |= RTN_RTINFO; } nsiblings = iter->rt6i_nsiblings; + iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); rt6_release(iter); @@ -925,6 +1024,7 @@ add: break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->dst.rt6_next; + iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); rt6_release(iter); nsiblings--; @@ -1459,6 +1559,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fib6_purge_rt(rt, fn, net); + call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt); if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); @@ -1839,6 +1940,11 @@ static void fib6_gc_timer_cb(unsigned long arg) static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; + int err; + + err = fib6_notifier_init(net); + if (err) + return err; spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); @@ -1891,6 +1997,7 @@ out_fib_table_hash: out_rt6_stats: kfree(net->ipv6.rt6_stats); out_timer: + fib6_notifier_exit(net); return -ENOMEM; } @@ -1907,6 +2014,7 @@ static void fib6_net_exit(struct net *net) kfree(net->ipv6.fib6_main_tbl); kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); + fib6_notifier_exit(net); } static struct pernet_operations fib6_net_ops = { @@ -1930,7 +2038,7 @@ int __init fib6_init(void) goto out_kmem_cache_create; ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib, - NULL); + 0); if (ret) goto out_unregister_subsys; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 7454850f2098..f5500f5444e9 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1427,7 +1427,7 @@ int __init ip6_mr_init(void) } #endif rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, - ip6mr_rtm_dumproute, NULL); + ip6mr_rtm_dumproute, 0); return 0; #ifdef CONFIG_IPV6_PIMSM_V2 add_proto_fail: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0327c1f2e6fc..5e338eb89509 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1779,6 +1779,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, + .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 60be012fe708..e4462b0ff801 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -72,7 +72,7 @@ EXPORT_SYMBOL_GPL(raw_v6_hashinfo); struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, - const struct in6_addr *rmt_addr, int dif) + const struct in6_addr *rmt_addr, int dif, int sdif) { bool is_multicast = ipv6_addr_is_multicast(loc_addr); @@ -86,7 +86,9 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; - if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) + if (sk->sk_bound_dev_if && + sk->sk_bound_dev_if != dif && + sk->sk_bound_dev_if != sdif) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { @@ -178,7 +180,8 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) goto out; net = dev_net(skb->dev); - sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb)); + sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, + inet6_iif(skb), inet6_sdif(skb)); while (sk) { int filtered; @@ -222,7 +225,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, - inet6_iif(skb)); + inet6_iif(skb), inet6_sdif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); @@ -378,7 +381,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, - inet6_iif(skb)))) { + inet6_iif(skb), inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4d30c96a819d..bec12ae3e6b7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -417,14 +417,11 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, struct net_device *loopback_dev = dev_net(dev)->loopback_dev; - if (dev != loopback_dev) { - if (idev && idev->dev == dev) { - struct inet6_dev *loopback_idev = - in6_dev_get(loopback_dev); - if (loopback_idev) { - rt->rt6i_idev = loopback_idev; - in6_dev_put(idev); - } + if (idev && idev->dev != loopback_dev) { + struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev); + if (loopback_idev) { + rt->rt6i_idev = loopback_idev; + in6_dev_put(idev); } } } @@ -2351,6 +2348,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; + nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; if (ip6_ins_rt(nrt)) @@ -2461,6 +2459,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), + .fc_protocol = RTPROT_RA, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, @@ -2513,6 +2512,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + .fc_protocol = RTPROT_RA, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = dev_net(dev), @@ -3327,6 +3327,9 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, goto nla_put_failure; } + if (rt->rt6i_nh_flags & RTNH_F_OFFLOAD) + *flags |= RTNH_F_OFFLOAD; + /* not needed for multipath encoding b/c it has a rtnexthop struct */ if (!skip_oif && rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) @@ -3424,14 +3427,6 @@ static int rt6_fill_node(struct net *net, rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->rt6i_protocol; - if (rt->rt6i_flags & RTF_DYNAMIC) - rtm->rtm_protocol = RTPROT_REDIRECT; - else if (rt->rt6i_flags & RTF_ADDRCONF) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO)) - rtm->rtm_protocol = RTPROT_RA; - else - rtm->rtm_protocol = RTPROT_KERNEL; - } if (rt->rt6i_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; @@ -3613,8 +3608,11 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct net_device *dev; int flags = 0; - dev = __dev_get_by_index(net, iif); + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, iif); if (!dev) { + rcu_read_unlock(); err = -ENODEV; goto errout; } @@ -3626,15 +3624,19 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!fibmatch) dst = ip6_route_input_lookup(net, dev, &fl6, flags); + else + dst = ip6_route_lookup(net, &fl6, 0); + + rcu_read_unlock(); } else { fl6.flowi6_oif = oif; if (!fibmatch) dst = ip6_route_output(net, NULL, &fl6); + else + dst = ip6_route_lookup(net, &fl6, 0); } - if (fibmatch) - dst = ip6_route_lookup(net, &fl6, 0); rt = container_of(dst, struct rt6_info, dst); if (rt->dst.error) { @@ -3729,10 +3731,10 @@ static int ip6_route_dev_notify(struct notifier_block *this, /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ - in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); + in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES - in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); - in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev); + in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); + in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } @@ -3926,6 +3928,7 @@ static int __net_init ip6_route_net_init(struct net *net) ip6_template_metrics, true); #ifdef CONFIG_IPV6_MULTIPLE_TABLES + net->ipv6.fib6_has_custom_rules = false; net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, sizeof(*net->ipv6.ip6_prohibit_entry), GFP_KERNEL); @@ -4101,9 +4104,10 @@ int __init ip6_route_init(void) goto fib6_rules_init; ret = -ENOBUFS; - if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) || - __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) || - __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL)) + if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, 0) || + __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, 0) || + __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, + RTNL_FLAG_DOIT_UNLOCKED)) goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 15fba55e3da8..c81407770956 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -40,7 +40,7 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) if (((srh->hdrlen + 1) << 3) != len) return false; - if (srh->segments_left != srh->first_segment) + if (srh->segments_left > srh->first_segment) return false; tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); @@ -456,6 +456,10 @@ int __init seg6_init(void) err = seg6_iptunnel_init(); if (err) goto out_unregister_pernet; + + err = seg6_local_init(); + if (err) + goto out_unregister_pernet; #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -471,6 +475,7 @@ out: #ifdef CONFIG_IPV6_SEG6_HMAC out_unregister_iptun: #ifdef CONFIG_IPV6_SEG6_LWTUNNEL + seg6_local_exit(); seg6_iptunnel_exit(); #endif #endif diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 264d772d3c7d..501233040570 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -91,7 +91,7 @@ static void set_tun_src(struct net *net, struct net_device *dev, } /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ -static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) +int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) { struct net *net = dev_net(skb_dst(skb)->dev); struct ipv6hdr *hdr, *inner_hdr; @@ -141,10 +141,10 @@ static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) return 0; } +EXPORT_SYMBOL_GPL(seg6_do_srh_encap); /* insert an SRH within an IPv6 packet, just after the IPv6 header */ -#ifdef CONFIG_IPV6_SEG6_INLINE -static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) +int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) { struct ipv6hdr *hdr, *oldhdr; struct ipv6_sr_hdr *isrh; @@ -193,7 +193,7 @@ static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) return 0; } -#endif +EXPORT_SYMBOL_GPL(seg6_do_srh_inline); static int seg6_do_srh(struct sk_buff *skb) { @@ -209,12 +209,10 @@ static int seg6_do_srh(struct sk_buff *skb) } switch (tinfo->mode) { -#ifdef CONFIG_IPV6_SEG6_INLINE case SEG6_IPTUN_MODE_INLINE: err = seg6_do_srh_inline(skb, tinfo->srh); skb_reset_inner_headers(skb); break; -#endif case SEG6_IPTUN_MODE_ENCAP: err = seg6_do_srh_encap(skb, tinfo->srh); break; @@ -357,10 +355,8 @@ static int seg6_build_state(struct nlattr *nla, return -EINVAL; switch (tuninfo->mode) { -#ifdef CONFIG_IPV6_SEG6_INLINE case SEG6_IPTUN_MODE_INLINE: break; -#endif case SEG6_IPTUN_MODE_ENCAP: break; default: diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c new file mode 100644 index 000000000000..147680e7a00c --- /dev/null +++ b/net/ipv6/seg6_local.c @@ -0,0 +1,766 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/net.h> +#include <linux/module.h> +#include <net/ip.h> +#include <net/lwtunnel.h> +#include <net/netevent.h> +#include <net/netns/generic.h> +#include <net/ip6_fib.h> +#include <net/route.h> +#include <net/seg6.h> +#include <linux/seg6.h> +#include <linux/seg6_local.h> +#include <net/addrconf.h> +#include <net/ip6_route.h> +#include <net/dst_cache.h> +#ifdef CONFIG_IPV6_SEG6_HMAC +#include <net/seg6_hmac.h> +#endif + +struct seg6_local_lwt; + +struct seg6_action_desc { + int action; + unsigned long attrs; + int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt); + int static_headroom; +}; + +struct seg6_local_lwt { + int action; + struct ipv6_sr_hdr *srh; + int table; + struct in_addr nh4; + struct in6_addr nh6; + int iif; + int oif; + + int headroom; + struct seg6_action_desc *desc; +}; + +static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt) +{ + return (struct seg6_local_lwt *)lwt->data; +} + +static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb) +{ + struct ipv6_sr_hdr *srh; + struct ipv6hdr *hdr; + int len; + + hdr = ipv6_hdr(skb); + if (hdr->nexthdr != IPPROTO_ROUTING) + return NULL; + + srh = (struct ipv6_sr_hdr *)(hdr + 1); + len = (srh->hdrlen + 1) << 3; + + if (!pskb_may_pull(skb, sizeof(*hdr) + len)) + return NULL; + + if (!seg6_validate_srh(srh, len)) + return NULL; + + return srh; +} + +static struct ipv6_sr_hdr *get_and_validate_srh(struct sk_buff *skb) +{ + struct ipv6_sr_hdr *srh; + + srh = get_srh(skb); + if (!srh) + return NULL; + + if (srh->segments_left == 0) + return NULL; + +#ifdef CONFIG_IPV6_SEG6_HMAC + if (!seg6_hmac_validate_skb(skb)) + return NULL; +#endif + + return srh; +} + +/* regular endpoint function */ +static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct ipv6_sr_hdr *srh; + struct in6_addr *addr; + + srh = get_and_validate_srh(skb); + if (!srh) + goto drop; + + srh->segments_left--; + addr = srh->segments + srh->segments_left; + + ipv6_hdr(skb)->daddr = *addr; + + skb_dst_drop(skb); + ip6_route_input(skb); + + return dst_input(skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +/* regular endpoint, and forward to specified nexthop */ +static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct net *net = dev_net(skb->dev); + struct ipv6_sr_hdr *srh; + struct dst_entry *dst; + struct in6_addr *addr; + struct ipv6hdr *hdr; + struct flowi6 fl6; + int flags; + + srh = get_and_validate_srh(skb); + if (!srh) + goto drop; + + srh->segments_left--; + addr = srh->segments + srh->segments_left; + + hdr = ipv6_hdr(skb); + hdr->daddr = *addr; + + skb_dst_drop(skb); + + fl6.flowi6_iif = skb->dev->ifindex; + fl6.daddr = slwt->nh6; + fl6.saddr = hdr->saddr; + fl6.flowlabel = ip6_flowinfo(hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = hdr->nexthdr; + + flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE | + RT6_LOOKUP_F_REACHABLE; + + dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags); + if (dst->dev->flags & IFF_LOOPBACK) + goto drop; + + skb_dst_set(skb, dst); + + return dst_input(skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +/* decapsulate and forward to specified nexthop */ +static int input_action_end_dx6(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct net *net = dev_net(skb->dev); + struct ipv6hdr *inner_hdr; + struct ipv6_sr_hdr *srh; + struct dst_entry *dst; + unsigned int off = 0; + struct flowi6 fl6; + bool use_nh; + int flags; + + /* this function accepts IPv6 encapsulated packets, with either + * an SRH with SL=0, or no SRH. + */ + + srh = get_srh(skb); + if (srh && srh->segments_left > 0) + goto drop; + +#ifdef CONFIG_IPV6_SEG6_HMAC + if (srh && !seg6_hmac_validate_skb(skb)) + goto drop; +#endif + + if (ipv6_find_hdr(skb, &off, IPPROTO_IPV6, NULL, NULL) < 0) + goto drop; + + if (!pskb_pull(skb, off)) + goto drop; + + skb_postpull_rcsum(skb, skb_network_header(skb), off); + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb->encapsulation = 0; + + inner_hdr = ipv6_hdr(skb); + + /* The inner packet is not associated to any local interface, + * so we do not call netif_rx(). + * + * If slwt->nh6 is set to ::, then lookup the nexthop for the + * inner packet's DA. Otherwise, use the specified nexthop. + */ + + use_nh = !ipv6_addr_any(&slwt->nh6); + + skb_dst_drop(skb); + + fl6.flowi6_iif = skb->dev->ifindex; + fl6.daddr = use_nh ? slwt->nh6 : inner_hdr->daddr; + fl6.saddr = inner_hdr->saddr; + fl6.flowlabel = ip6_flowinfo(inner_hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = inner_hdr->nexthdr; + + flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_REACHABLE; + if (use_nh) + flags |= RT6_LOOKUP_F_IFACE; + + dst = ip6_route_input_lookup(net, skb->dev, &fl6, flags); + if (dst->dev->flags & IFF_LOOPBACK) + goto drop; + + skb_dst_set(skb, dst); + + return dst_input(skb); +drop: + kfree_skb(skb); + return -EINVAL; +} + +/* push an SRH on top of the current one */ +static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct ipv6_sr_hdr *srh; + int err = -EINVAL; + + srh = get_and_validate_srh(skb); + if (!srh) + goto drop; + + err = seg6_do_srh_inline(skb, slwt->srh); + if (err) + goto drop; + + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + skb_dst_drop(skb); + ip6_route_input(skb); + + return dst_input(skb); + +drop: + kfree_skb(skb); + return err; +} + +/* encapsulate within an outer IPv6 header and a specified SRH */ +static int input_action_end_b6_encap(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct ipv6_sr_hdr *srh; + struct in6_addr *addr; + int err = -EINVAL; + + srh = get_and_validate_srh(skb); + if (!srh) + goto drop; + + srh->segments_left--; + addr = srh->segments + srh->segments_left; + ipv6_hdr(skb)->daddr = *addr; + + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + + err = seg6_do_srh_encap(skb, slwt->srh); + if (err) + goto drop; + + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + skb_dst_drop(skb); + ip6_route_input(skb); + + return dst_input(skb); + +drop: + kfree_skb(skb); + return err; +} + +static struct seg6_action_desc seg6_action_table[] = { + { + .action = SEG6_LOCAL_ACTION_END, + .attrs = 0, + .input = input_action_end, + }, + { + .action = SEG6_LOCAL_ACTION_END_X, + .attrs = (1 << SEG6_LOCAL_NH6), + .input = input_action_end_x, + }, + { + .action = SEG6_LOCAL_ACTION_END_DX6, + .attrs = (1 << SEG6_LOCAL_NH6), + .input = input_action_end_dx6, + }, + { + .action = SEG6_LOCAL_ACTION_END_B6, + .attrs = (1 << SEG6_LOCAL_SRH), + .input = input_action_end_b6, + }, + { + .action = SEG6_LOCAL_ACTION_END_B6_ENCAP, + .attrs = (1 << SEG6_LOCAL_SRH), + .input = input_action_end_b6_encap, + .static_headroom = sizeof(struct ipv6hdr), + } +}; + +static struct seg6_action_desc *__get_action_desc(int action) +{ + struct seg6_action_desc *desc; + int i, count; + + count = sizeof(seg6_action_table) / sizeof(struct seg6_action_desc); + for (i = 0; i < count; i++) { + desc = &seg6_action_table[i]; + if (desc->action == action) + return desc; + } + + return NULL; +} + +static int seg6_local_input(struct sk_buff *skb) +{ + struct dst_entry *orig_dst = skb_dst(skb); + struct seg6_action_desc *desc; + struct seg6_local_lwt *slwt; + + slwt = seg6_local_lwtunnel(orig_dst->lwtstate); + desc = slwt->desc; + + return desc->input(skb, slwt); +} + +static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { + [SEG6_LOCAL_ACTION] = { .type = NLA_U32 }, + [SEG6_LOCAL_SRH] = { .type = NLA_BINARY }, + [SEG6_LOCAL_TABLE] = { .type = NLA_U32 }, + [SEG6_LOCAL_NH4] = { .type = NLA_BINARY, + .len = sizeof(struct in_addr) }, + [SEG6_LOCAL_NH6] = { .type = NLA_BINARY, + .len = sizeof(struct in6_addr) }, + [SEG6_LOCAL_IIF] = { .type = NLA_U32 }, + [SEG6_LOCAL_OIF] = { .type = NLA_U32 }, +}; + +static int parse_nla_srh(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + struct ipv6_sr_hdr *srh; + int len; + + srh = nla_data(attrs[SEG6_LOCAL_SRH]); + len = nla_len(attrs[SEG6_LOCAL_SRH]); + + /* SRH must contain at least one segment */ + if (len < sizeof(*srh) + sizeof(struct in6_addr)) + return -EINVAL; + + if (!seg6_validate_srh(srh, len)) + return -EINVAL; + + slwt->srh = kmalloc(len, GFP_KERNEL); + if (!slwt->srh) + return -ENOMEM; + + memcpy(slwt->srh, srh, len); + + slwt->headroom += len; + + return 0; +} + +static int put_nla_srh(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct ipv6_sr_hdr *srh; + struct nlattr *nla; + int len; + + srh = slwt->srh; + len = (srh->hdrlen + 1) << 3; + + nla = nla_reserve(skb, SEG6_LOCAL_SRH, len); + if (!nla) + return -EMSGSIZE; + + memcpy(nla_data(nla), srh, len); + + return 0; +} + +static int cmp_nla_srh(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + int len = (a->srh->hdrlen + 1) << 3; + + if (len != ((b->srh->hdrlen + 1) << 3)) + return 1; + + return memcmp(a->srh, b->srh, len); +} + +static int parse_nla_table(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + slwt->table = nla_get_u32(attrs[SEG6_LOCAL_TABLE]); + + return 0; +} + +static int put_nla_table(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + if (nla_put_u32(skb, SEG6_LOCAL_TABLE, slwt->table)) + return -EMSGSIZE; + + return 0; +} + +static int cmp_nla_table(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + if (a->table != b->table) + return 1; + + return 0; +} + +static int parse_nla_nh4(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + memcpy(&slwt->nh4, nla_data(attrs[SEG6_LOCAL_NH4]), + sizeof(struct in_addr)); + + return 0; +} + +static int put_nla_nh4(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct nlattr *nla; + + nla = nla_reserve(skb, SEG6_LOCAL_NH4, sizeof(struct in_addr)); + if (!nla) + return -EMSGSIZE; + + memcpy(nla_data(nla), &slwt->nh4, sizeof(struct in_addr)); + + return 0; +} + +static int cmp_nla_nh4(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + return memcmp(&a->nh4, &b->nh4, sizeof(struct in_addr)); +} + +static int parse_nla_nh6(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + memcpy(&slwt->nh6, nla_data(attrs[SEG6_LOCAL_NH6]), + sizeof(struct in6_addr)); + + return 0; +} + +static int put_nla_nh6(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct nlattr *nla; + + nla = nla_reserve(skb, SEG6_LOCAL_NH6, sizeof(struct in6_addr)); + if (!nla) + return -EMSGSIZE; + + memcpy(nla_data(nla), &slwt->nh6, sizeof(struct in6_addr)); + + return 0; +} + +static int cmp_nla_nh6(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + return memcmp(&a->nh6, &b->nh6, sizeof(struct in6_addr)); +} + +static int parse_nla_iif(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + slwt->iif = nla_get_u32(attrs[SEG6_LOCAL_IIF]); + + return 0; +} + +static int put_nla_iif(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + if (nla_put_u32(skb, SEG6_LOCAL_IIF, slwt->iif)) + return -EMSGSIZE; + + return 0; +} + +static int cmp_nla_iif(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + if (a->iif != b->iif) + return 1; + + return 0; +} + +static int parse_nla_oif(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + slwt->oif = nla_get_u32(attrs[SEG6_LOCAL_OIF]); + + return 0; +} + +static int put_nla_oif(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + if (nla_put_u32(skb, SEG6_LOCAL_OIF, slwt->oif)) + return -EMSGSIZE; + + return 0; +} + +static int cmp_nla_oif(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + if (a->oif != b->oif) + return 1; + + return 0; +} + +struct seg6_action_param { + int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt); + int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt); + int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b); +}; + +static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = { + [SEG6_LOCAL_SRH] = { .parse = parse_nla_srh, + .put = put_nla_srh, + .cmp = cmp_nla_srh }, + + [SEG6_LOCAL_TABLE] = { .parse = parse_nla_table, + .put = put_nla_table, + .cmp = cmp_nla_table }, + + [SEG6_LOCAL_NH4] = { .parse = parse_nla_nh4, + .put = put_nla_nh4, + .cmp = cmp_nla_nh4 }, + + [SEG6_LOCAL_NH6] = { .parse = parse_nla_nh6, + .put = put_nla_nh6, + .cmp = cmp_nla_nh6 }, + + [SEG6_LOCAL_IIF] = { .parse = parse_nla_iif, + .put = put_nla_iif, + .cmp = cmp_nla_iif }, + + [SEG6_LOCAL_OIF] = { .parse = parse_nla_oif, + .put = put_nla_oif, + .cmp = cmp_nla_oif }, +}; + +static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + struct seg6_action_param *param; + struct seg6_action_desc *desc; + int i, err; + + desc = __get_action_desc(slwt->action); + if (!desc) + return -EINVAL; + + if (!desc->input) + return -EOPNOTSUPP; + + slwt->desc = desc; + slwt->headroom += desc->static_headroom; + + for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { + if (desc->attrs & (1 << i)) { + if (!attrs[i]) + return -EINVAL; + + param = &seg6_action_params[i]; + + err = param->parse(attrs, slwt); + if (err < 0) + return err; + } + } + + return 0; +} + +static int seg6_local_build_state(struct nlattr *nla, unsigned int family, + const void *cfg, struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[SEG6_LOCAL_MAX + 1]; + struct lwtunnel_state *newts; + struct seg6_local_lwt *slwt; + int err; + + err = nla_parse_nested(tb, SEG6_LOCAL_MAX, nla, seg6_local_policy, + extack); + + if (err < 0) + return err; + + if (!tb[SEG6_LOCAL_ACTION]) + return -EINVAL; + + newts = lwtunnel_state_alloc(sizeof(*slwt)); + if (!newts) + return -ENOMEM; + + slwt = seg6_local_lwtunnel(newts); + slwt->action = nla_get_u32(tb[SEG6_LOCAL_ACTION]); + + err = parse_nla_action(tb, slwt); + if (err < 0) + goto out_free; + + newts->type = LWTUNNEL_ENCAP_SEG6_LOCAL; + newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT; + newts->headroom = slwt->headroom; + + *ts = newts; + + return 0; + +out_free: + kfree(slwt->srh); + kfree(newts); + return err; +} + +static void seg6_local_destroy_state(struct lwtunnel_state *lwt) +{ + struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); + + kfree(slwt->srh); +} + +static int seg6_local_fill_encap(struct sk_buff *skb, + struct lwtunnel_state *lwt) +{ + struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); + struct seg6_action_param *param; + int i, err; + + if (nla_put_u32(skb, SEG6_LOCAL_ACTION, slwt->action)) + return -EMSGSIZE; + + for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { + if (slwt->desc->attrs & (1 << i)) { + param = &seg6_action_params[i]; + err = param->put(skb, slwt); + if (err < 0) + return err; + } + } + + return 0; +} + +static int seg6_local_get_encap_size(struct lwtunnel_state *lwt) +{ + struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); + unsigned long attrs; + int nlsize; + + nlsize = nla_total_size(4); /* action */ + + attrs = slwt->desc->attrs; + + if (attrs & (1 << SEG6_LOCAL_SRH)) + nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3); + + if (attrs & (1 << SEG6_LOCAL_TABLE)) + nlsize += nla_total_size(4); + + if (attrs & (1 << SEG6_LOCAL_NH4)) + nlsize += nla_total_size(4); + + if (attrs & (1 << SEG6_LOCAL_NH6)) + nlsize += nla_total_size(16); + + if (attrs & (1 << SEG6_LOCAL_IIF)) + nlsize += nla_total_size(4); + + if (attrs & (1 << SEG6_LOCAL_OIF)) + nlsize += nla_total_size(4); + + return nlsize; +} + +static int seg6_local_cmp_encap(struct lwtunnel_state *a, + struct lwtunnel_state *b) +{ + struct seg6_local_lwt *slwt_a, *slwt_b; + struct seg6_action_param *param; + int i; + + slwt_a = seg6_local_lwtunnel(a); + slwt_b = seg6_local_lwtunnel(b); + + if (slwt_a->action != slwt_b->action) + return 1; + + if (slwt_a->desc->attrs != slwt_b->desc->attrs) + return 1; + + for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { + if (slwt_a->desc->attrs & (1 << i)) { + param = &seg6_action_params[i]; + if (param->cmp(slwt_a, slwt_b)) + return 1; + } + } + + return 0; +} + +static const struct lwtunnel_encap_ops seg6_local_ops = { + .build_state = seg6_local_build_state, + .destroy_state = seg6_local_destroy_state, + .input = seg6_local_input, + .fill_encap = seg6_local_fill_encap, + .get_encap_size = seg6_local_get_encap_size, + .cmp_encap = seg6_local_cmp_encap, + .owner = THIS_MODULE, +}; + +int __init seg6_local_init(void) +{ + return lwtunnel_encap_add_ops(&seg6_local_ops, + LWTUNNEL_ENCAP_SEG6_LOCAL); +} + +void seg6_local_exit(void) +{ + lwtunnel_encap_del_ops(&seg6_local_ops, LWTUNNEL_ENCAP_SEG6_LOCAL); +} diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ced5dcf37465..d79a1af3252e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -350,7 +350,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __inet6_lookup_established(net, &tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr, ntohs(th->source), - skb->dev->ifindex); + skb->dev->ifindex, inet6_sdif(skb)); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), @@ -918,7 +918,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), tcp_v6_iif(skb)); + ntohs(th->source), tcp_v6_iif(skb), + tcp_v6_sdif(skb)); if (!sk1) goto out; @@ -1397,6 +1398,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, static int tcp_v6_rcv(struct sk_buff *skb) { + int sdif = inet6_sdif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; bool refcounted; @@ -1430,7 +1432,7 @@ static int tcp_v6_rcv(struct sk_buff *skb) lookup: sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), - th->source, th->dest, inet6_iif(skb), + th->source, th->dest, inet6_iif(skb), sdif, &refcounted); if (!sk) goto no_tcp_socket; @@ -1456,6 +1458,8 @@ process: } sock_hold(sk); refcounted = true; + if (tcp_filter(sk, skb)) + goto discard_and_relse; nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); @@ -1464,8 +1468,6 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); - } else if (tcp_filter(sk, skb)) { - goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); goto discard_and_relse; @@ -1563,7 +1565,8 @@ do_time_wait: skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), tcp_v6_iif(skb)); + ntohs(th->dest), tcp_v6_iif(skb), + sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); inet_twsk_deschedule_put(tw); @@ -1610,7 +1613,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), - inet6_iif(skb)); + inet6_iif(skb), inet6_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 578142b7ca3e..19afcaf4a22e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -129,7 +129,7 @@ static void udp_v6_rehash(struct sock *sk) static int compute_score(struct sock *sk, struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, - int dif, bool exact_dif) + int dif, int sdif, bool exact_dif) { int score; struct inet_sock *inet; @@ -161,9 +161,13 @@ static int compute_score(struct sock *sk, struct net *net, } if (sk->sk_bound_dev_if || exact_dif) { - if (sk->sk_bound_dev_if != dif) + bool dev_match = (sk->sk_bound_dev_if == dif || + sk->sk_bound_dev_if == sdif); + + if (exact_dif && !dev_match) return -1; - score++; + if (sk->sk_bound_dev_if && dev_match) + score++; } if (sk->sk_incoming_cpu == raw_smp_processor_id()) @@ -175,9 +179,9 @@ static int compute_score(struct sock *sk, struct net *net, /* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, unsigned int hnum, int dif, - bool exact_dif, struct udp_hslot *hslot2, - struct sk_buff *skb) + const struct in6_addr *daddr, unsigned int hnum, + int dif, int sdif, bool exact_dif, + struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; int score, badness, matches = 0, reuseport = 0; @@ -187,7 +191,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, badness = -1; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, exact_dif); + daddr, hnum, dif, sdif, exact_dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -214,10 +218,10 @@ static struct sock *udp6_lib_lookup2(struct net *net, /* rcu_read_lock() must be held */ struct sock *__udp6_lib_lookup(struct net *net, - const struct in6_addr *saddr, __be16 sport, - const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *udptable, - struct sk_buff *skb) + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, __be16 dport, + int dif, int sdif, struct udp_table *udptable, + struct sk_buff *skb) { struct sock *sk, *result; unsigned short hnum = ntohs(dport); @@ -235,7 +239,7 @@ struct sock *__udp6_lib_lookup(struct net *net, goto begin; result = udp6_lib_lookup2(net, saddr, sport, - daddr, hnum, dif, exact_dif, + daddr, hnum, dif, sdif, exact_dif, hslot2, skb); if (!result) { unsigned int old_slot2 = slot2; @@ -250,7 +254,7 @@ struct sock *__udp6_lib_lookup(struct net *net, goto begin; result = udp6_lib_lookup2(net, saddr, sport, - daddr, hnum, dif, + daddr, hnum, dif, sdif, exact_dif, hslot2, skb); } @@ -261,7 +265,7 @@ begin: badness = -1; sk_for_each_rcu(sk, &hslot->head) { score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, - exact_dif); + sdif, exact_dif); if (score > badness) { reuseport = sk->sk_reuseport; if (reuseport) { @@ -294,7 +298,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - udptable, skb); + inet6_sdif(skb), udptable, skb); } struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, @@ -304,7 +308,7 @@ struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - &udp_table, skb); + inet6_sdif(skb), &udp_table, skb); } EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb); @@ -320,7 +324,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be struct sock *sk; sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, - dif, &udp_table, NULL); + dif, 0, &udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -501,7 +505,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct net *net = dev_net(skb->dev); sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, - inet6_iif(skb), udptable, skb); + inet6_iif(skb), 0, udptable, skb); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); @@ -893,7 +897,7 @@ discard: static struct sock *__udp6_lib_demux_lookup(struct net *net, __be16 loc_port, const struct in6_addr *loc_addr, __be16 rmt_port, const struct in6_addr *rmt_addr, - int dif) + int dif, int sdif) { unsigned short hnum = ntohs(loc_port); unsigned int hash2 = udp6_portaddr_hash(net, loc_addr, hnum); @@ -904,7 +908,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (sk->sk_state == TCP_ESTABLISHED && - INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif)) + INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; @@ -919,6 +923,7 @@ static void udp_v6_early_demux(struct sk_buff *skb) struct sock *sk; struct dst_entry *dst; int dif = skb->dev->ifindex; + int sdif = inet6_sdif(skb); if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) @@ -930,7 +935,7 @@ static void udp_v6_early_demux(struct sk_buff *skb) sk = __udp6_lib_demux_lookup(net, uh->dest, &ipv6_hdr(skb)->daddr, uh->source, &ipv6_hdr(skb)->saddr, - dif); + dif, sdif); else return; diff --git a/net/key/af_key.c b/net/key/af_key.c index 10d7133e4fe9..a00d607e7224 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -228,7 +228,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, #define BROADCAST_ONE 1 #define BROADCAST_REGISTERED 2 #define BROADCAST_PROMISC_ONLY 4 -static int pfkey_broadcast(struct sk_buff *skb, +static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, int broadcast_flags, struct sock *one_sk, struct net *net) { @@ -278,7 +278,7 @@ static int pfkey_broadcast(struct sk_buff *skb, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk); + err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); kfree_skb(skb2); kfree_skb(skb); @@ -311,7 +311,7 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; hdr->sadb_msg_errno = rc; - pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = NULL; } @@ -355,7 +355,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk)); + pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk)); return 0; } @@ -1389,7 +1389,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ xfrm_state_put(x); - pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net); + pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net); return 0; } @@ -1476,7 +1476,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; - pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x)); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); return 0; } @@ -1589,7 +1589,7 @@ static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); return 0; } @@ -1694,8 +1694,8 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad return -ENOBUFS; } - pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk)); - + pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk, + sock_net(sk)); return 0; } @@ -1712,7 +1712,8 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk)); + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, + sock_net(sk)); } static int key_notify_sa_flush(const struct km_event *c) @@ -1733,7 +1734,7 @@ static int key_notify_sa_flush(const struct km_event *c) hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; - pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } @@ -1790,7 +1791,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr) out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) - pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; @@ -1878,7 +1879,7 @@ static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb new_hdr->sadb_msg_errno = 0; } - pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk)); + pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk)); return 0; } @@ -2206,7 +2207,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; out_hdr->sadb_msg_pid = c->portid; - pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); return 0; } @@ -2424,7 +2425,7 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp)); err = 0; out: @@ -2678,7 +2679,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) - pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; @@ -2735,7 +2736,7 @@ static int key_notify_policy_flush(const struct km_event *c) hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; - pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net); + pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } @@ -2797,7 +2798,7 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), + pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); @@ -3018,7 +3019,8 @@ static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) out_hdr->sadb_msg_seq = 0; out_hdr->sadb_msg_pid = 0; - pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, + xs_net(x)); return 0; } @@ -3206,7 +3208,8 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_ctx->ctx_len); } - return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x)); + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, + xs_net(x)); } static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, @@ -3402,7 +3405,8 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, n_port->sadb_x_nat_t_port_port = sport; n_port->sadb_x_nat_t_port_reserved = 0; - return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x)); + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, + xs_net(x)); } #ifdef CONFIG_NET_KEY_MIGRATE @@ -3593,7 +3597,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* broadcast migrate message to sockets */ - pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); return 0; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 8708cbe8af5b..2b36eff5d97e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -7,7 +7,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation - * Copyright(c) 2015 Intel Deutschland GmbH + * Copyright(c) 2015-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -466,3 +466,23 @@ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_manage_rx_ba_offl); + +void ieee80211_rx_ba_timer_expired(struct ieee80211_vif *vif, + const u8 *addr, unsigned int tid) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + rcu_read_lock(); + sta = sta_info_get_bss(sdata, addr); + if (!sta) + goto unlock; + + set_bit(tid, sta->ampdu_mlme.tid_rx_timer_expired); + ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); + + unlock: + rcu_read_unlock(); +} +EXPORT_SYMBOL(ieee80211_rx_ba_timer_expired); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index ea4f481839dd..c5b9ce41d66f 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -2479,12 +2479,12 @@ static int __init mpls_init(void) rtnl_af_register(&mpls_af_ops); - rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL); - rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL); + rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, 0); + rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, 0); rtnl_register(PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, - NULL); + 0); rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, - mpls_netconf_dump_devconf, NULL); + mpls_netconf_dump_devconf, 0); err = 0; out: return err; diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index d767e35fff6b..ade4c10c28c6 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -125,7 +125,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, __tcp_hdrlen(tcph), saddr, sport, daddr, dport, - in->ifindex); + in->ifindex, 0); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; @@ -195,7 +195,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, thoff + __tcp_hdrlen(tcph), saddr, sport, daddr, ntohs(dport), - in->ifindex); + in->ifindex, 0); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; @@ -208,7 +208,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, case NFT_LOOKUP_ESTABLISHED: sk = __inet6_lookup_established(net, &tcp_hashinfo, saddr, sport, daddr, ntohs(dport), - in->ifindex); + in->ifindex, 0); break; default: BUG(); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 03859e386b47..30d632509f82 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1180,15 +1180,13 @@ static int parse_nat(const struct nlattr *attr, int type = nla_type(a); if (type > OVS_NAT_ATTR_MAX) { - OVS_NLERR(log, - "Unknown NAT attribute (type=%d, max=%d).\n", + OVS_NLERR(log, "Unknown NAT attribute (type=%d, max=%d)", type, OVS_NAT_ATTR_MAX); return -EINVAL; } if (nla_len(a) != ovs_nat_attr_lens[type][ip_vers]) { - OVS_NLERR(log, - "NAT attribute type %d has unexpected length (%d != %d).\n", + OVS_NLERR(log, "NAT attribute type %d has unexpected length (%d != %d)", type, nla_len(a), ovs_nat_attr_lens[type][ip_vers]); return -EINVAL; @@ -1198,9 +1196,7 @@ static int parse_nat(const struct nlattr *attr, case OVS_NAT_ATTR_SRC: case OVS_NAT_ATTR_DST: if (info->nat) { - OVS_NLERR(log, - "Only one type of NAT may be specified.\n" - ); + OVS_NLERR(log, "Only one type of NAT may be specified"); return -ERANGE; } info->nat |= OVS_CT_NAT; @@ -1245,13 +1241,13 @@ static int parse_nat(const struct nlattr *attr, break; default: - OVS_NLERR(log, "Unknown nat attribute (%d).\n", type); + OVS_NLERR(log, "Unknown nat attribute (%d)", type); return -EINVAL; } } if (rem > 0) { - OVS_NLERR(log, "NAT attribute has %d unknown bytes.\n", rem); + OVS_NLERR(log, "NAT attribute has %d unknown bytes", rem); return -EINVAL; } if (!info->nat) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index f07d10ac35d8..e8eb427ce6d1 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1255,7 +1255,7 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, } if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) { - OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x).\n", + OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x)", ntohl(ipv6_key->ipv6_label), (1 << 20) - 1); return -EINVAL; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5a178047a7ce..f31cb71172e0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3698,14 +3698,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; - po->tp_reserve = val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_reserve = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_LOSS: { diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 45b3af3080d8..da754fc926e7 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -300,15 +300,15 @@ out: int __init phonet_netlink_register(void) { int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit, - NULL, NULL); + NULL, 0); if (err) return err; /* Further __rtnl_register() cannot fail */ - __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL, NULL); - __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit, NULL); - __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL, NULL); - __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL, NULL); - __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit, NULL); + __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL, 0); + __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit, 0); + __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL, 0); + __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL, 0); + __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit, 0); return 0; } diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 5586609afa27..c2f5c13550c0 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -1081,7 +1081,7 @@ static int __init qrtr_proto_init(void) return rc; } - rtnl_register(PF_QIPCRTR, RTM_NEWADDR, qrtr_addr_doit, NULL, NULL); + rtnl_register(PF_QIPCRTR, RTM_NEWADDR, qrtr_addr_doit, NULL, 0); return 0; } diff --git a/net/rds/connection.c b/net/rds/connection.c index 005bca68aa94..7ee2d5d68b78 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -151,6 +151,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, struct rds_transport *loop_trans; unsigned long flags; int ret, i; + int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rcu_read_lock(); conn = rds_conn_lookup(net, head, laddr, faddr, trans); @@ -172,6 +173,12 @@ static struct rds_connection *__rds_conn_create(struct net *net, conn = ERR_PTR(-ENOMEM); goto out; } + conn->c_path = kcalloc(npaths, sizeof(struct rds_conn_path), gfp); + if (!conn->c_path) { + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-ENOMEM); + goto out; + } INIT_HLIST_NODE(&conn->c_hash_node); conn->c_laddr = laddr; @@ -181,6 +188,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, ret = rds_cong_get_maps(conn); if (ret) { + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(ret); goto out; @@ -207,13 +215,14 @@ static struct rds_connection *__rds_conn_create(struct net *net, conn->c_trans = trans; init_waitqueue_head(&conn->c_hs_waitq); - for (i = 0; i < RDS_MPATH_WORKERS; i++) { + for (i = 0; i < npaths; i++) { __rds_conn_path_init(conn, &conn->c_path[i], is_outgoing); conn->c_path[i].cp_index = i; } ret = trans->conn_alloc(conn, gfp); if (ret) { + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(ret); goto out; @@ -236,6 +245,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, /* Creating passive conn */ if (parent->c_passive) { trans->conn_free(conn->c_path[0].cp_transport_data); + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = parent->c_passive; } else { @@ -252,7 +262,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, struct rds_conn_path *cp; int i; - for (i = 0; i < RDS_MPATH_WORKERS; i++) { + for (i = 0; i < npaths; i++) { cp = &conn->c_path[i]; /* The ->conn_alloc invocation may have * allocated resource for all paths, so all @@ -261,6 +271,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (cp->cp_transport_data) trans->conn_free(cp->cp_transport_data); } + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = found; } else { @@ -407,6 +418,7 @@ void rds_conn_destroy(struct rds_connection *conn) unsigned long flags; int i; struct rds_conn_path *cp; + int npaths = (conn->c_trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rdsdebug("freeing conn %p for %pI4 -> " "%pI4\n", conn, &conn->c_laddr, @@ -420,7 +432,7 @@ void rds_conn_destroy(struct rds_connection *conn) synchronize_rcu(); /* shut the connection down */ - for (i = 0; i < RDS_MPATH_WORKERS; i++) { + for (i = 0; i < npaths; i++) { cp = &conn->c_path[i]; rds_conn_path_destroy(cp); BUG_ON(!list_empty(&cp->cp_retrans)); @@ -434,6 +446,7 @@ void rds_conn_destroy(struct rds_connection *conn) rds_cong_remove_conn(conn); put_net(conn->c_net); + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); spin_lock_irqsave(&rds_conn_lock, flags); @@ -464,8 +477,12 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, i++, head++) { hlist_for_each_entry_rcu(conn, head, c_hash_node) { struct rds_conn_path *cp; + int npaths; + + npaths = (conn->c_trans->t_mp_capable ? + RDS_MPATH_WORKERS : 1); - for (j = 0; j < RDS_MPATH_WORKERS; j++) { + for (j = 0; j < npaths; j++) { cp = &conn->c_path[j]; if (want_send) list = &cp->cp_send_queue; @@ -486,8 +503,6 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, } spin_unlock_irqrestore(&cp->cp_lock, flags); - if (!conn->c_trans->t_mp_capable) - break; } } } @@ -571,15 +586,16 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len, i++, head++) { hlist_for_each_entry_rcu(conn, head, c_hash_node) { struct rds_conn_path *cp; + int npaths; - for (j = 0; j < RDS_MPATH_WORKERS; j++) { + npaths = (conn->c_trans->t_mp_capable ? + RDS_MPATH_WORKERS : 1); + for (j = 0; j < npaths; j++) { cp = &conn->c_path[j]; /* XXX no cp_lock usage.. */ if (!visitor(cp, buffer)) continue; - if (!conn->c_trans->t_mp_capable) - break; } /* We copy as much as we can fit in the buffer, diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index e10624aa6959..9722bf839d9d 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -1015,8 +1015,10 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, if (rds_ib_ring_empty(&ic->i_recv_ring)) rds_ib_stats_inc(s_ib_rx_ring_empty); - if (rds_ib_ring_low(&ic->i_recv_ring)) + if (rds_ib_ring_low(&ic->i_recv_ring)) { rds_ib_recv_refill(conn, 0, GFP_NOWAIT); + rds_ib_stats_inc(s_ib_rx_refill_from_cq); + } } int rds_ib_recv_path(struct rds_conn_path *cp) @@ -1029,6 +1031,7 @@ int rds_ib_recv_path(struct rds_conn_path *cp) if (rds_conn_up(conn)) { rds_ib_attempt_ack(ic); rds_ib_recv_refill(conn, 0, GFP_KERNEL); + rds_ib_stats_inc(s_ib_rx_refill_from_thread); } return ret; diff --git a/net/rds/rds.h b/net/rds/rds.h index 3382695bf46c..2e0315b159cb 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -154,7 +154,7 @@ struct rds_connection { struct list_head c_map_item; unsigned long c_map_queued; - struct rds_conn_path c_path[RDS_MPATH_WORKERS]; + struct rds_conn_path *c_path; wait_queue_head_t c_hs_waitq; /* handshake waitq */ u32 c_my_gen_num; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f19b118df414..02fcb0c78a28 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -473,9 +473,10 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res) { - int ret = -1, i; u32 jmp_prgcnt = 0; u32 jmp_ttl = TCA_ACT_MAX_PRIO; /*matches actions per filter */ + int i; + int ret = TC_ACT_OK; if (skb_skip_tc_classify(skb)) return TC_ACT_OK; @@ -1254,10 +1255,10 @@ out_module_put: static int __init tc_action_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, - NULL); + 0); return 0; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 36f0ced9e60c..d516ba8178b8 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -36,8 +36,8 @@ static struct tc_action_ops act_ipt_ops; static unsigned int xt_net_id; static struct tc_action_ops act_xt_ops; -static int ipt_init_target(struct xt_entry_target *t, char *table, - unsigned int hook) +static int ipt_init_target(struct net *net, struct xt_entry_target *t, + char *table, unsigned int hook) { struct xt_tgchk_param par; struct xt_target *target; @@ -49,8 +49,9 @@ static int ipt_init_target(struct xt_entry_target *t, char *table, return PTR_ERR(target); t->u.kernel.target = target; + memset(&par, 0, sizeof(par)); + par.net = net; par.table = table; - par.entryinfo = NULL; par.target = target; par.targinfo = t->data; par.hook_mask = hook; @@ -91,10 +92,11 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; -static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, +static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int ovr, int bind) { + struct tc_action_net *tn = net_generic(net, id); struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; struct xt_entry_target *td, *t; @@ -159,7 +161,7 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla, if (unlikely(!t)) goto err2; - err = ipt_init_target(t, tname, hook); + err = ipt_init_target(net, t, tname, hook); if (err < 0) goto err3; @@ -193,18 +195,16 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_ipt_ops, ovr, bind); + return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, + bind); } static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return __tcf_ipt_init(tn, nla, est, a, &act_xt_ops, ovr, bind); + return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, + bind); } static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 39da0c5801c9..ebeeb87e6d44 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -100,21 +100,6 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) } EXPORT_SYMBOL(unregister_tcf_proto_ops); -static int tfilter_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, struct tcf_proto *tp, - unsigned long fh, int event, bool unicast); - -static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, - struct tcf_chain *chain, int event) -{ - struct tcf_proto *tp; - - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, 0, event, false); -} - /* Select new prio value from the range, managed by kernel. */ static inline u32 tcf_auto_prio(struct tcf_proto *tp) @@ -407,6 +392,109 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, return tp; } +static int tcf_fill_node(struct net *net, struct sk_buff *skb, + struct tcf_proto *tp, void *fh, u32 portid, + u32 seq, u16 flags, int event) +{ + struct tcmsg *tcm; + struct nlmsghdr *nlh; + unsigned char *b = skb_tail_pointer(skb); + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); + if (!nlh) + goto out_nlmsg_trim; + tcm = nlmsg_data(nlh); + tcm->tcm_family = AF_UNSPEC; + tcm->tcm__pad1 = 0; + tcm->tcm__pad2 = 0; + tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; + tcm->tcm_parent = tp->classid; + tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); + if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) + goto nla_put_failure; + if (!fh) { + tcm->tcm_handle = 0; + } else { + if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) + goto nla_put_failure; + } + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; + +out_nlmsg_trim: +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static int tfilter_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, struct tcf_proto *tp, + void *fh, int event, bool unicast) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + n->nlmsg_flags, event) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + if (unicast) + return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); +} + +static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, struct tcf_proto *tp, + void *fh, bool unicast, bool *last) +{ + struct sk_buff *skb; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + int err; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + n->nlmsg_flags, RTM_DELTFILTER) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + err = tp->ops->delete(tp, fh, last); + if (err) { + kfree_skb(skb); + return err; + } + + if (unicast) + return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); +} + +static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, + struct nlmsghdr *n, + struct tcf_chain *chain, int event) +{ + struct tcf_proto *tp; + + for (tp = rtnl_dereference(chain->filter_chain); + tp; tp = rtnl_dereference(tp->next)) + tfilter_notify(net, oskb, n, tp, 0, event, false); +} + /* Add/change/delete/get a filter node */ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -428,7 +516,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct tcf_proto *tp; const struct Qdisc_class_ops *cops; unsigned long cl; - unsigned long fh; + void *fh; int err; int tp_created; @@ -567,7 +655,7 @@ replay: fh = tp->ops->get(tp, t->tcm_handle); - if (fh == 0) { + if (!fh) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { tcf_chain_tp_remove(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, @@ -595,11 +683,10 @@ replay: } break; case RTM_DELTFILTER: - err = tp->ops->delete(tp, fh, &last); + err = tfilter_del_notify(net, skb, n, tp, fh, false, + &last); if (err) goto errout; - tfilter_notify(net, skb, n, tp, t->tcm_handle, - RTM_DELTFILTER, false); if (last) { tcf_chain_tp_remove(chain, &chain_info, tp); tcf_proto_destroy(tp); @@ -637,75 +724,13 @@ errout: return err; } -static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, unsigned long fh, u32 portid, - u32 seq, u16 flags, int event) -{ - struct tcmsg *tcm; - struct nlmsghdr *nlh; - unsigned char *b = skb_tail_pointer(skb); - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); - if (!nlh) - goto out_nlmsg_trim; - tcm = nlmsg_data(nlh); - tcm->tcm_family = AF_UNSPEC; - tcm->tcm__pad1 = 0; - tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; - tcm->tcm_parent = tp->classid; - tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); - if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) - goto nla_put_failure; - if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) - goto nla_put_failure; - tcm->tcm_handle = fh; - if (RTM_DELTFILTER != event) { - tcm->tcm_handle = 0; - if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) - goto nla_put_failure; - } - nlh->nlmsg_len = skb_tail_pointer(skb) - b; - return skb->len; - -out_nlmsg_trim: -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int tfilter_notify(struct net *net, struct sk_buff *oskb, - struct nlmsghdr *n, struct tcf_proto *tp, - unsigned long fh, int event, bool unicast) -{ - struct sk_buff *skb; - u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; - - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; - - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, - n->nlmsg_flags, event) <= 0) { - kfree_skb(skb); - return -EINVAL; - } - - if (unicast) - return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); - - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); -} - struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; }; -static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, - struct tcf_walker *arg) +static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) { struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); @@ -883,18 +908,12 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, } EXPORT_SYMBOL(tcf_exts_validate); -void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, - struct tcf_exts *src) +void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT struct tcf_exts old = *dst; - tcf_tree_lock(tp); - dst->nr_actions = src->nr_actions; - dst->actions = src->actions; - dst->type = src->type; - tcf_tree_unlock(tp); - + *dst = *src; tcf_exts_destroy(&old); #endif } @@ -915,7 +934,7 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) #ifdef CONFIG_NET_CLS_ACT struct nlattr *nest; - if (exts->action && exts->nr_actions) { + if (exts->action && tcf_exts_has_actions(exts)) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering @@ -972,7 +991,7 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, const struct tc_action *a; LIST_HEAD(actions); - if (tc_no_actions(exts)) + if (!tcf_exts_has_actions(exts)) return -EINVAL; tcf_exts_to_list(exts, &actions); @@ -991,10 +1010,10 @@ EXPORT_SYMBOL(tcf_exts_get_dev); static int __init tc_filter_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, - tc_dump_tfilter, NULL); + tc_dump_tfilter, 0); return 0; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index c4fd63a068f9..73cc7f167a38 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -56,20 +56,18 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static unsigned long basic_get(struct tcf_proto *tp, u32 handle) +static void *basic_get(struct tcf_proto *tp, u32 handle) { - unsigned long l = 0UL; struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; list_for_each_entry(f, &head->flist, link) { if (f->handle == handle) { - l = (unsigned long) f; - break; + return f; } } - return l; + return NULL; } static int basic_init(struct tcf_proto *tp) @@ -106,10 +104,10 @@ static void basic_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int basic_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int basic_delete(struct tcf_proto *tp, void *arg, bool *last) { struct basic_head *head = rtnl_dereference(tp->root); - struct basic_filter *f = (struct basic_filter *) arg; + struct basic_filter *f = arg; list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); @@ -129,38 +127,27 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, struct nlattr *est, bool ovr) { int err; - struct tcf_exts e; - struct tcf_ematch_tree t; - err = tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - err = tcf_em_tree_validate(tp, tb[TCA_BASIC_EMATCHES], &t); + err = tcf_em_tree_validate(tp, tb[TCA_BASIC_EMATCHES], &f->ematches); if (err < 0) - goto errout; + return err; if (tb[TCA_BASIC_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_BASIC_CLASSID]); tcf_bind_filter(tp, &f->res, base); } - tcf_exts_change(tp, &f->exts, &e); - tcf_em_tree_change(tp, &f->ematches, &t); f->tp = tp; - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr) { int err; struct basic_head *head = rtnl_dereference(tp->root); @@ -213,7 +200,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - *arg = (unsigned long)fnew; + *arg = fnew; if (fold) { list_replace_rcu(&fold->link, &fnew->link); @@ -239,7 +226,7 @@ static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) f, arg) < 0) { + if (arg->fn(tp, f, arg) < 0) { arg->stop = 1; break; } @@ -248,10 +235,10 @@ skip: } } -static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct basic_filter *f = (struct basic_filter *) fh; + struct basic_filter *f = fh; struct nlattr *nest; if (f == NULL) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index f57bd531ba98..6f2dffe30f25 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -147,24 +147,18 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, enum tc_clsbpf_command cmd) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_bpf_offload bpf_offload = {}; - struct tc_to_netdev offload; + struct tc_cls_bpf_offload cls_bpf = {}; int err; - offload.type = TC_SETUP_CLSBPF; - offload.cls_bpf = &bpf_offload; - - bpf_offload.command = cmd; - bpf_offload.exts = &prog->exts; - bpf_offload.prog = prog->filter; - bpf_offload.name = prog->bpf_name; - bpf_offload.exts_integrated = prog->exts_integrated; - bpf_offload.gen_flags = prog->gen_flags; - - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, - tp->protocol, &offload); + tc_cls_common_offload_init(&cls_bpf.common, tp); + cls_bpf.command = cmd; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; + cls_bpf.gen_flags = prog->gen_flags; + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSBPF, &cls_bpf); if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE)) prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; @@ -184,7 +178,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, (oldprog && tc_skip_sw(oldprog->gen_flags)); if (oldprog && oldprog->offloaded) { - if (tc_should_offload(dev, tp, prog->gen_flags)) { + if (tc_should_offload(dev, prog->gen_flags)) { cmd = TC_CLSBPF_REPLACE; } else if (!tc_skip_sw(prog->gen_flags)) { obj = oldprog; @@ -193,7 +187,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, return -EINVAL; } } else { - if (!tc_should_offload(dev, tp, prog->gen_flags)) + if (!tc_should_offload(dev, prog->gen_flags)) return skip_sw ? -EINVAL : 0; cmd = TC_CLSBPF_ADD; } @@ -276,11 +270,11 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) call_rcu(&prog->rcu, cls_bpf_delete_prog_rcu); } -static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last) { struct cls_bpf_head *head = rtnl_dereference(tp->root); - __cls_bpf_delete(tp, (struct cls_bpf_prog *) arg); + __cls_bpf_delete(tp, arg); *last = list_empty(&head->plist); return 0; } @@ -296,20 +290,17 @@ static void cls_bpf_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) +static void *cls_bpf_get(struct tcf_proto *tp, u32 handle) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; - unsigned long ret = 0UL; list_for_each_entry(prog, &head->plist, link) { - if (prog->handle == handle) { - ret = (unsigned long) prog; - break; - } + if (prog->handle == handle) + return prog; } - return ret; + return NULL; } static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) @@ -382,13 +373,11 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, - unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) +static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, + struct cls_bpf_prog *prog, unsigned long base, + struct nlattr **tb, struct nlattr *est, bool ovr) { bool is_bpf, is_ebpf, have_exts = false; - struct tcf_exts exts; u32 gen_flags = 0; int ret; @@ -397,30 +386,23 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; - ret = tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); + ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr); if (ret < 0) return ret; - ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); - if (ret < 0) - goto errout; if (tb[TCA_BPF_FLAGS]) { u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); - if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { - ret = -EINVAL; - goto errout; - } + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) + return -EINVAL; have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; } if (tb[TCA_BPF_FLAGS_GEN]) { gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || - !tc_flags_valid(gen_flags)) { - ret = -EINVAL; - goto errout; - } + !tc_flags_valid(gen_flags)) + return -EINVAL; } prog->exts_integrated = have_exts; @@ -429,19 +411,14 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : cls_bpf_prog_from_efd(tb, prog, tp); if (ret < 0) - goto errout; + return ret; if (tb[TCA_BPF_CLASSID]) { prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); tcf_bind_filter(tp, &prog->res, base); } - tcf_exts_change(tp, &prog->exts, &exts); return 0; - -errout: - tcf_exts_destroy(&exts); - return ret; } static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, @@ -468,10 +445,10 @@ static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, bool ovr) { struct cls_bpf_head *head = rtnl_dereference(tp->root); - struct cls_bpf_prog *oldprog = (struct cls_bpf_prog *) *arg; + struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; struct cls_bpf_prog *prog; int ret; @@ -508,8 +485,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; } - ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], - ovr); + ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr); if (ret < 0) goto errout; @@ -530,7 +506,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, list_add_rcu(&prog->link, &head->plist); } - *arg = (unsigned long) prog; + *arg = prog; return 0; errout: @@ -578,10 +554,10 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *tm) { - struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; + struct cls_bpf_prog *prog = fh; struct nlattr *nest; u32 bpf_flags = 0; int ret; @@ -639,7 +615,7 @@ static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg) list_for_each_entry(prog, &head->plist, link) { if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) prog, arg) < 0) { + if (arg->fn(tp, prog, arg) < 0) { arg->stop = 1; break; } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 12ce547eea04..d48452f87975 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -43,9 +43,9 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, return tcf_exts_exec(skb, &head->exts, res); } -static unsigned long cls_cgroup_get(struct tcf_proto *tp, u32 handle) +static void *cls_cgroup_get(struct tcf_proto *tp, u32 handle) { - return 0UL; + return NULL; } static int cls_cgroup_init(struct tcf_proto *tp) @@ -71,13 +71,11 @@ static void cls_cgroup_destroy_rcu(struct rcu_head *root) static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, bool ovr) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; struct cls_cgroup_head *head = rtnl_dereference(tp->root); struct cls_cgroup_head *new; - struct tcf_ematch_tree t; - struct tcf_exts e; int err; if (!tca[TCA_OPTIONS]) @@ -103,23 +101,13 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - err = tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr); if (err < 0) goto errout; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) { - tcf_exts_destroy(&e); - goto errout; - } - err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t); - if (err < 0) { - tcf_exts_destroy(&e); + err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &new->ematches); + if (err < 0) goto errout; - } - - tcf_exts_change(tp, &new->exts, &e); - tcf_em_tree_change(tp, &new->ematches, &t); rcu_assign_pointer(tp->root, new); if (head) @@ -140,7 +128,7 @@ static void cls_cgroup_destroy(struct tcf_proto *tp) call_rcu(&head->rcu, cls_cgroup_destroy_rcu); } -static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last) { return -EOPNOTSUPP; } @@ -152,7 +140,7 @@ static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg) if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) head, arg) < 0) { + if (arg->fn(tp, head, arg) < 0) { arg->stop = 1; return; } @@ -160,7 +148,7 @@ skip: arg->count++; } -static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 3065752b9cda..2a3a60ec5b86 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -382,14 +382,12 @@ static void flow_destroy_filter(struct rcu_head *head) static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, bool ovr) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *fold, *fnew; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FLOW_MAX + 1]; - struct tcf_exts e; - struct tcf_ematch_tree t; unsigned int nkeys = 0; unsigned int perturb_period = 0; u32 baseclass = 0; @@ -425,31 +423,27 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, return -EOPNOTSUPP; } - err = tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE); - if (err < 0) - goto err1; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) - goto err1; + fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); + if (!fnew) + return -ENOBUFS; - err = tcf_em_tree_validate(tp, tb[TCA_FLOW_EMATCHES], &t); + err = tcf_em_tree_validate(tp, tb[TCA_FLOW_EMATCHES], &fnew->ematches); if (err < 0) goto err1; - err = -ENOBUFS; - fnew = kzalloc(sizeof(*fnew), GFP_KERNEL); - if (!fnew) + err = tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); + if (err < 0) goto err2; - err = tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr); if (err < 0) - goto err3; + goto err2; - fold = (struct flow_filter *)*arg; + fold = *arg; if (fold) { err = -EINVAL; if (fold->handle != handle && handle) - goto err3; + goto err2; /* Copy fold into fnew */ fnew->tp = fold->tp; @@ -469,31 +463,31 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) - goto err3; + goto err2; if (mode == FLOW_MODE_HASH) perturb_period = fold->perturb_period; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) - goto err3; + goto err2; perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } } else { err = -EINVAL; if (!handle) - goto err3; + goto err2; if (!tb[TCA_FLOW_KEYS]) - goto err3; + goto err2; mode = FLOW_MODE_MAP; if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) - goto err3; + goto err2; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) - goto err3; + goto err2; perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } @@ -511,9 +505,6 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, (unsigned long)fnew); - tcf_exts_change(tp, &fnew->exts, &e); - tcf_em_tree_change(tp, &fnew->ematches, &t); - netif_keep_dst(qdisc_dev(tp->q)); if (tb[TCA_FLOW_KEYS]) { @@ -541,31 +532,29 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (perturb_period) mod_timer(&fnew->perturb_timer, jiffies + perturb_period); - if (*arg == 0) + if (!*arg) list_add_tail_rcu(&fnew->list, &head->filters); else list_replace_rcu(&fold->list, &fnew->list); - *arg = (unsigned long)fnew; + *arg = fnew; if (fold) call_rcu(&fold->rcu, flow_destroy_filter); return 0; -err3: - tcf_exts_destroy(&fnew->exts); err2: - tcf_em_tree_destroy(&t); - kfree(fnew); + tcf_exts_destroy(&fnew->exts); + tcf_em_tree_destroy(&fnew->ematches); err1: - tcf_exts_destroy(&e); + kfree(fnew); return err; } -static int flow_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int flow_delete(struct tcf_proto *tp, void *arg, bool *last) { struct flow_head *head = rtnl_dereference(tp->root); - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = arg; list_del_rcu(&f->list); call_rcu(&f->rcu, flow_destroy_filter); @@ -597,21 +586,21 @@ static void flow_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static unsigned long flow_get(struct tcf_proto *tp, u32 handle) +static void *flow_get(struct tcf_proto *tp, u32 handle) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; list_for_each_entry(f, &head->filters, list) if (f->handle == handle) - return (unsigned long)f; - return 0; + return f; + return NULL; } -static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct flow_filter *f = (struct flow_filter *)fh; + struct flow_filter *f = fh; struct nlattr *nest; if (f == NULL) @@ -677,7 +666,7 @@ static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg) list_for_each_entry(f, &head->filters, list) { if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long)f, arg) < 0) { + if (arg->fn(tp, f, arg) < 0) { arg->stop = 1; break; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7832eb93379b..bd9dab41f8af 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -88,7 +88,6 @@ struct cls_fl_filter { u32 handle; u32 flags; struct rcu_head rcu; - struct tc_to_netdev tc; struct net_device *hw_dev; }; @@ -225,22 +224,17 @@ static void fl_destroy_filter(struct rcu_head *head) static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) { - struct tc_cls_flower_offload offload = {0}; + struct tc_cls_flower_offload cls_flower = {}; struct net_device *dev = f->hw_dev; - struct tc_to_netdev *tc = &f->tc; - if (!tc_can_offload(dev, tp)) + if (!tc_can_offload(dev)) return; - offload.command = TC_CLSFLOWER_DESTROY; - offload.prio = tp->prio; - offload.cookie = (unsigned long)f; + tc_cls_common_offload_init(&cls_flower.common, tp); + cls_flower.command = TC_CLSFLOWER_DESTROY; + cls_flower.cookie = (unsigned long) f; - tc->type = TC_SETUP_CLSFLOWER; - tc->cls_flower = &offload; - - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->chain->index, - tp->protocol, tc); + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower); } static int fl_hw_replace_filter(struct tcf_proto *tp, @@ -249,35 +243,31 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, struct cls_fl_filter *f) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_flower_offload offload = {0}; - struct tc_to_netdev *tc = &f->tc; + struct tc_cls_flower_offload cls_flower = {}; int err; - if (!tc_can_offload(dev, tp)) { + if (!tc_can_offload(dev)) { if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) || - (f->hw_dev && !tc_can_offload(f->hw_dev, tp))) { + (f->hw_dev && !tc_can_offload(f->hw_dev))) { f->hw_dev = dev; return tc_skip_sw(f->flags) ? -EINVAL : 0; } dev = f->hw_dev; - tc->egress_dev = true; + cls_flower.egress_dev = true; } else { f->hw_dev = dev; } - offload.command = TC_CLSFLOWER_REPLACE; - offload.prio = tp->prio; - offload.cookie = (unsigned long)f; - offload.dissector = dissector; - offload.mask = mask; - offload.key = &f->mkey; - offload.exts = &f->exts; - - tc->type = TC_SETUP_CLSFLOWER; - tc->cls_flower = &offload; + tc_cls_common_offload_init(&cls_flower.common, tp); + cls_flower.command = TC_CLSFLOWER_REPLACE; + cls_flower.cookie = (unsigned long) f; + cls_flower.dissector = dissector; + cls_flower.mask = mask; + cls_flower.key = &f->mkey; + cls_flower.exts = &f->exts; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, tc); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); if (!err) f->flags |= TCA_CLS_FLAGS_IN_HW; @@ -288,23 +278,19 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) { - struct tc_cls_flower_offload offload = {0}; + struct tc_cls_flower_offload cls_flower = {}; struct net_device *dev = f->hw_dev; - struct tc_to_netdev *tc = &f->tc; - if (!tc_can_offload(dev, tp)) + if (!tc_can_offload(dev)) return; - offload.command = TC_CLSFLOWER_STATS; - offload.prio = tp->prio; - offload.cookie = (unsigned long)f; - offload.exts = &f->exts; - - tc->type = TC_SETUP_CLSFLOWER; - tc->cls_flower = &offload; + tc_cls_common_offload_init(&cls_flower.common, tp); + cls_flower.command = TC_CLSFLOWER_STATS; + cls_flower.cookie = (unsigned long) f; + cls_flower.exts = &f->exts; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, tc); + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); } static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) @@ -346,15 +332,15 @@ static void fl_destroy(struct tcf_proto *tp) call_rcu(&head->rcu, fl_destroy_rcu); } -static unsigned long fl_get(struct tcf_proto *tp, u32 handle) +static void *fl_get(struct tcf_proto *tp, u32 handle) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; list_for_each_entry(f, &head->filters, list) if (f->handle == handle) - return (unsigned long) f; - return 0; + return f; + return NULL; } static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { @@ -852,15 +838,11 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr **tb, struct nlattr *est, bool ovr) { - struct tcf_exts e; int err; - err = tcf_exts_init(&e, TCA_FLOWER_ACT, 0); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; if (tb[TCA_FLOWER_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); @@ -869,17 +851,12 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, err = fl_set_key(net, tb, &f->key, &mask->key); if (err) - goto errout; + return err; fl_mask_update_range(mask); fl_set_masked_key(&f->mkey, &f->key, mask); - tcf_exts_change(tp, &f->exts, &e); - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static u32 fl_grab_new_handle(struct tcf_proto *tp, @@ -906,10 +883,10 @@ static u32 fl_grab_new_handle(struct tcf_proto *tp, static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, bool ovr) { struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *fold = (struct cls_fl_filter *) *arg; + struct cls_fl_filter *fold = *arg; struct cls_fl_filter *fnew; struct nlattr **tb; struct fl_flow_mask mask = {}; @@ -1000,7 +977,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, fl_hw_destroy_filter(tp, fold); } - *arg = (unsigned long) fnew; + *arg = fnew; if (fold) { list_replace_rcu(&fold->list, &fnew->list); @@ -1021,10 +998,10 @@ errout_tb: return err; } -static int fl_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int fl_delete(struct tcf_proto *tp, void *arg, bool *last) { struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *f = (struct cls_fl_filter *) arg; + struct cls_fl_filter *f = arg; if (!tc_skip_sw(f->flags)) rhashtable_remove_fast(&head->ht, &f->ht_node, @@ -1042,7 +1019,7 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) list_for_each_entry_rcu(f, &head->filters, list) { if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) f, arg) < 0) { + if (arg->fn(tp, f, arg) < 0) { arg->stop = 1; break; } @@ -1177,11 +1154,11 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask); } -static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { struct cls_fl_head *head = rtnl_dereference(tp->root); - struct cls_fl_filter *f = (struct cls_fl_filter *) fh; + struct cls_fl_filter *f = fh; struct nlattr *nest; struct fl_flow_key *key, *mask; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index d3885362e017..192255ec50bd 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -95,20 +95,20 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static unsigned long fw_get(struct tcf_proto *tp, u32 handle) +static void *fw_get(struct tcf_proto *tp, u32 handle) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; if (head == NULL) - return 0; + return NULL; f = rtnl_dereference(head->ht[fw_hash(handle)]); for (; f; f = rtnl_dereference(f->next)) { if (f->id == handle) - return (unsigned long)f; + return f; } - return 0; + return NULL; } static int fw_init(struct tcf_proto *tp) @@ -147,10 +147,10 @@ static void fw_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int fw_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int fw_delete(struct tcf_proto *tp, void *arg, bool *last) { struct fw_head *head = rtnl_dereference(tp->root); - struct fw_filter *f = (struct fw_filter *)arg; + struct fw_filter *f = arg; struct fw_filter __rcu **fp; struct fw_filter *pfp; int ret = -EINVAL; @@ -190,22 +190,17 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { [TCA_FW_MASK] = { .type = NLA_U32 }, }; -static int -fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, - struct nlattr **tb, struct nlattr **tca, unsigned long base, - bool ovr) +static int fw_set_parms(struct net *net, struct tcf_proto *tp, + struct fw_filter *f, struct nlattr **tb, + struct nlattr **tca, unsigned long base, bool ovr) { struct fw_head *head = rtnl_dereference(tp->root); - struct tcf_exts e; u32 mask; int err; - err = tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); - if (err < 0) - goto errout; if (tb[TCA_FW_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); @@ -216,10 +211,8 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, if (tb[TCA_FW_INDEV]) { int ret; ret = tcf_change_indev(net, tb[TCA_FW_INDEV]); - if (ret < 0) { - err = ret; - goto errout; - } + if (ret < 0) + return ret; f->ifindex = ret; } #endif /* CONFIG_NET_CLS_IND */ @@ -228,25 +221,20 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, if (tb[TCA_FW_MASK]) { mask = nla_get_u32(tb[TCA_FW_MASK]); if (mask != head->mask) - goto errout; + return err; } else if (head->mask != 0xFFFFFFFF) - goto errout; - - tcf_exts_change(tp, &f->exts, &e); + return err; return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, - u32 handle, struct nlattr **tca, unsigned long *arg, + u32 handle, struct nlattr **tca, void **arg, bool ovr) { struct fw_head *head = rtnl_dereference(tp->root); - struct fw_filter *f = (struct fw_filter *) *arg; + struct fw_filter *f = *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; int err; @@ -282,7 +270,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return err; } - err = fw_change_attrs(net, tp, fnew, tb, tca, base, ovr); + err = fw_set_parms(net, tp, fnew, tb, tca, base, ovr); if (err < 0) { tcf_exts_destroy(&fnew->exts); kfree(fnew); @@ -300,7 +288,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, fw_delete_filter); - *arg = (unsigned long)fnew; + *arg = fnew; return err; } @@ -330,14 +318,14 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, f->id = handle; f->tp = tp; - err = fw_change_attrs(net, tp, f, tb, tca, base, ovr); + err = fw_set_parms(net, tp, f, tb, tca, base, ovr); if (err < 0) goto errout; RCU_INIT_POINTER(f->next, head->ht[fw_hash(handle)]); rcu_assign_pointer(head->ht[fw_hash(handle)], f); - *arg = (unsigned long)f; + *arg = f; return 0; errout: @@ -366,7 +354,7 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) arg->count++; continue; } - if (arg->fn(tp, (unsigned long)f, arg) < 0) { + if (arg->fn(tp, f, arg) < 0) { arg->stop = 1; return; } @@ -375,11 +363,11 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { struct fw_head *head = rtnl_dereference(tp->root); - struct fw_filter *f = (struct fw_filter *)fh; + struct fw_filter *f = fh; struct nlattr *nest; if (f == NULL) @@ -387,7 +375,7 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, t->tcm_handle = f->id; - if (!f->res.classid && !tcf_exts_is_available(&f->exts)) + if (!f->res.classid && !tcf_exts_has_actions(&f->exts)) return skb->len; nest = nla_nest_start(skb, TCA_OPTIONS); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 9dc26c32cf32..d4dc387f7a56 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -54,19 +54,16 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, unsigned long cookie) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_to_netdev offload; - struct tc_cls_matchall_offload mall_offload = {0}; + struct tc_cls_matchall_offload cls_mall = {}; int err; - offload.type = TC_SETUP_MATCHALL; - offload.cls_mall = &mall_offload; - offload.cls_mall->command = TC_CLSMATCHALL_REPLACE; - offload.cls_mall->exts = &head->exts; - offload.cls_mall->cookie = cookie; + tc_cls_common_offload_init(&cls_mall.common, tp); + cls_mall.command = TC_CLSMATCHALL_REPLACE; + cls_mall.exts = &head->exts; + cls_mall.cookie = cookie; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, - tp->protocol, &offload); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, + &cls_mall); if (!err) head->flags |= TCA_CLS_FLAGS_IN_HW; @@ -78,17 +75,13 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp, unsigned long cookie) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_to_netdev offload; - struct tc_cls_matchall_offload mall_offload = {0}; + struct tc_cls_matchall_offload cls_mall = {}; - offload.type = TC_SETUP_MATCHALL; - offload.cls_mall = &mall_offload; - offload.cls_mall->command = TC_CLSMATCHALL_DESTROY; - offload.cls_mall->exts = NULL; - offload.cls_mall->cookie = cookie; + tc_cls_common_offload_init(&cls_mall.common, tp); + cls_mall.command = TC_CLSMATCHALL_DESTROY; + cls_mall.cookie = cookie; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->chain->index, - tp->protocol, &offload); + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, &cls_mall); } static void mall_destroy(struct tcf_proto *tp) @@ -99,15 +92,15 @@ static void mall_destroy(struct tcf_proto *tp) if (!head) return; - if (tc_should_offload(dev, tp, head->flags)) + if (tc_should_offload(dev, head->flags)) mall_destroy_hw_filter(tp, head, (unsigned long) head); call_rcu(&head->rcu, mall_destroy_rcu); } -static unsigned long mall_get(struct tcf_proto *tp, u32 handle) +static void *mall_get(struct tcf_proto *tp, u32 handle) { - return 0UL; + return NULL; } static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { @@ -120,33 +113,23 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr **tb, struct nlattr *est, bool ovr) { - struct tcf_exts e; int err; - err = tcf_exts_init(&e, TCA_MATCHALL_ACT, 0); - if (err) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr); if (err < 0) - goto errout; + return err; if (tb[TCA_MATCHALL_CLASSID]) { head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); tcf_bind_filter(tp, &head->res, base); } - - tcf_exts_change(tp, &head->exts, &e); - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, bool ovr) { struct cls_mall_head *head = rtnl_dereference(tp->root); struct net_device *dev = tp->q->dev_queue->dev; @@ -189,7 +172,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (err) goto err_set_parms; - if (tc_should_offload(dev, tp, flags)) { + if (tc_should_offload(dev, flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long) new); if (err) { if (tc_skip_sw(flags)) @@ -202,7 +185,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (!tc_in_hw(new->flags)) new->flags |= TCA_CLS_FLAGS_NOT_IN_HW; - *arg = (unsigned long) head; + *arg = head; rcu_assign_pointer(tp->root, new); return 0; @@ -214,7 +197,7 @@ err_exts_init: return err; } -static int mall_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int mall_delete(struct tcf_proto *tp, void *arg, bool *last) { return -EOPNOTSUPP; } @@ -225,16 +208,16 @@ static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg) if (arg->count < arg->skip) goto skip; - if (arg->fn(tp, (unsigned long) head, arg) < 0) + if (arg->fn(tp, head, arg) < 0) arg->stop = 1; skip: arg->count++; } -static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct cls_mall_head *head = (struct cls_mall_head *) fh; + struct cls_mall_head *head = fh; struct nlattr *nest; if (!head) diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index d63d5502ee02..3b70982394ce 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -113,7 +113,7 @@ static inline int route4_hash_wild(void) #define ROUTE4_APPLY_RESULT() \ { \ *res = f->res; \ - if (tcf_exts_is_available(&f->exts)) { \ + if (tcf_exts_has_actions(&f->exts)) { \ int r = tcf_exts_exec(skb, &f->exts, res); \ if (r < 0) { \ dont_cache = 1; \ @@ -216,7 +216,7 @@ static inline u32 from_hash(u32 id) return 16 + (id & 0xF); } -static unsigned long route4_get(struct tcf_proto *tp, u32 handle) +static void *route4_get(struct tcf_proto *tp, u32 handle) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_bucket *b; @@ -225,11 +225,11 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) h1 = to_hash(handle); if (h1 > 256) - return 0; + return NULL; h2 = from_hash(handle >> 16); if (h2 > 32) - return 0; + return NULL; b = rtnl_dereference(head->table[h1]); if (b) { @@ -237,9 +237,9 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) f; f = rtnl_dereference(f->next)) if (f->handle == handle) - return (unsigned long)f; + return f; } - return 0; + return NULL; } static int route4_init(struct tcf_proto *tp) @@ -294,10 +294,10 @@ static void route4_destroy(struct tcf_proto *tp) kfree_rcu(head, rcu); } -static int route4_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int route4_delete(struct tcf_proto *tp, void *arg, bool *last) { struct route4_head *head = rtnl_dereference(tp->root); - struct route4_filter *f = (struct route4_filter *)arg; + struct route4_filter *f = arg; struct route4_filter __rcu **fp; struct route4_filter *nf; struct route4_bucket *b; @@ -372,37 +372,32 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct route4_filter *fp; unsigned int h1; struct route4_bucket *b; - struct tcf_exts e; int err; - err = tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - err = -EINVAL; if (tb[TCA_ROUTE4_TO]) { if (new && handle & 0x8000) - goto errout; + return -EINVAL; to = nla_get_u32(tb[TCA_ROUTE4_TO]); if (to > 0xFF) - goto errout; + return -EINVAL; nhandle = to; } if (tb[TCA_ROUTE4_FROM]) { if (tb[TCA_ROUTE4_IIF]) - goto errout; + return -EINVAL; id = nla_get_u32(tb[TCA_ROUTE4_FROM]); if (id > 0xFF) - goto errout; + return -EINVAL; nhandle |= id << 16; } else if (tb[TCA_ROUTE4_IIF]) { id = nla_get_u32(tb[TCA_ROUTE4_IIF]); if (id > 0x7FFF) - goto errout; + return -EINVAL; nhandle |= (id | 0x8000) << 16; } else nhandle |= 0xFFFF << 16; @@ -410,27 +405,25 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, if (handle && new) { nhandle |= handle & 0x7F00; if (nhandle != handle) - goto errout; + return -EINVAL; } h1 = to_hash(nhandle); b = rtnl_dereference(head->table[h1]); if (!b) { - err = -ENOBUFS; b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) - goto errout; + return -ENOBUFS; rcu_assign_pointer(head->table[h1], b); } else { unsigned int h2 = from_hash(nhandle >> 16); - err = -EEXIST; for (fp = rtnl_dereference(b->ht[h2]); fp; fp = rtnl_dereference(fp->next)) if (fp->handle == f->handle) - goto errout; + return -EEXIST; } if (tb[TCA_ROUTE4_TO]) @@ -450,17 +443,12 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, tcf_bind_filter(tp, &f->res, base); } - tcf_exts_change(tp, &f->exts, &e); - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; @@ -479,7 +467,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - fold = (struct route4_filter *)*arg; + fold = *arg; if (fold && handle && fold->handle != handle) return -EINVAL; @@ -537,7 +525,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } route4_reset_fastmap(head); - *arg = (unsigned long)f; + *arg = f; if (fold) { tcf_unbind_filter(tp, &fold->res); call_rcu(&fold->rcu, route4_delete_filter); @@ -576,7 +564,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) arg->count++; continue; } - if (arg->fn(tp, (unsigned long)f, arg) < 0) { + if (arg->fn(tp, f, arg) < 0) { arg->stop = 1; return; } @@ -587,10 +575,10 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct route4_filter *f = (struct route4_filter *)fh; + struct route4_filter *f = fh; struct nlattr *nest; u32 id; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 0d9d07798699..26203ff817f3 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -248,7 +248,7 @@ static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) BUG_ON(1); } -static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) +static void *rsvp_get(struct tcf_proto *tp, u32 handle) { struct rsvp_head *head = rtnl_dereference(tp->root); struct rsvp_session *s; @@ -257,17 +257,17 @@ static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) unsigned int h2 = (handle >> 8) & 0xFF; if (h2 > 16) - return 0; + return NULL; for (s = rtnl_dereference(head->ht[h1]); s; s = rtnl_dereference(s->next)) { for (f = rtnl_dereference(s->ht[h2]); f; f = rtnl_dereference(f->next)) { if (f->handle == handle) - return (unsigned long)f; + return f; } } - return 0; + return NULL; } static int rsvp_init(struct tcf_proto *tp) @@ -328,10 +328,10 @@ static void rsvp_destroy(struct tcf_proto *tp) kfree_rcu(data, rcu); } -static int rsvp_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last) { struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = (struct rsvp_filter *)arg; + struct rsvp_filter *nfp, *f = arg; struct rsvp_filter __rcu **fp; unsigned int h = f->handle; struct rsvp_session __rcu **sp; @@ -464,7 +464,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - unsigned long *arg, bool ovr) + void **arg, bool ovr) { struct rsvp_head *data = rtnl_dereference(tp->root); struct rsvp_filter *f, *nfp; @@ -493,7 +493,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout2; - f = (struct rsvp_filter *)*arg; + f = *arg; if (f) { /* Node exists: adjust only classid */ struct rsvp_filter *n; @@ -518,7 +518,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, tcf_bind_filter(tp, &n->res, base); } - tcf_exts_change(tp, &n->exts, &e); + tcf_exts_change(&n->exts, &e); rsvp_replace(tp, n, handle); return 0; } @@ -591,7 +591,7 @@ insert: if (f->tunnelhdr == 0) tcf_bind_filter(tp, &f->res, base); - tcf_exts_change(tp, &f->exts, &e); + tcf_exts_change(&f->exts, &e); fp = &s->ht[h2]; for (nfp = rtnl_dereference(*fp); nfp; @@ -604,7 +604,7 @@ insert: RCU_INIT_POINTER(f->next, nfp); rcu_assign_pointer(*fp, f); - *arg = (unsigned long)f; + *arg = f; return 0; } } @@ -663,7 +663,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) arg->count++; continue; } - if (arg->fn(tp, (unsigned long)f, arg) < 0) { + if (arg->fn(tp, f, arg) < 0) { arg->stop = 1; return; } @@ -674,10 +674,10 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct rsvp_filter *f = (struct rsvp_filter *)fh; + struct rsvp_filter *f = fh; struct rsvp_session *s; struct nlattr *nest; struct tc_rsvp_pinfo pinfo; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 8a8a58357c39..fb281b9b2c52 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -52,7 +52,7 @@ struct tcindex_data { static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) { - return tcf_exts_is_predicative(&r->exts) || r->res.classid; + return tcf_exts_has_actions(&r->exts) || r->res.classid; } static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, @@ -104,16 +104,16 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, } -static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle) +static void *tcindex_get(struct tcf_proto *tp, u32 handle) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r; pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); if (p->perfect && handle >= p->alloc_hash) - return 0; + return NULL; r = tcindex_lookup(p, handle); - return r && tcindex_filter_is_set(r) ? (unsigned long) r : 0UL; + return r && tcindex_filter_is_set(r) ? r : NULL; } static int tcindex_init(struct tcf_proto *tp) @@ -150,14 +150,14 @@ static void tcindex_destroy_fexts(struct rcu_head *head) kfree(f); } -static int tcindex_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last) { struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; + struct tcindex_filter_result *r = arg; struct tcindex_filter __rcu **walk; struct tcindex_filter *f = NULL; - pr_debug("tcindex_delete(tp %p,arg 0x%lx),p %p\n", tp, arg, p); + pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p); if (p->perfect) { if (!r->res.class) return -ENOENT; @@ -192,8 +192,7 @@ found: } static int tcindex_destroy_element(struct tcf_proto *tp, - unsigned long arg, - struct tcf_walker *walker) + void *arg, struct tcf_walker *walker) { bool last; @@ -419,9 +418,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (old_r) - tcf_exts_change(tp, &r->exts, &e); + tcf_exts_change(&r->exts, &e); else - tcf_exts_change(tp, &cr.exts, &e); + tcf_exts_change(&cr.exts, &e); if (old_r && old_r != r) { err = tcindex_filter_result_init(old_r); @@ -439,7 +438,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tcindex_filter *nfp; struct tcindex_filter __rcu **fp; - tcf_exts_change(tp, &f->result.exts, &r->exts); + tcf_exts_change(&f->result.exts, &r->exts); fp = cp->h + (handle % cp->hash); for (nfp = rtnl_dereference(*fp); @@ -471,17 +470,17 @@ errout: static int tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr) { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg; + struct tcindex_filter_result *r = *arg; int err; pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," - "p %p,r %p,*arg 0x%lx\n", - tp, handle, tca, arg, opt, p, r, arg ? *arg : 0L); + "p %p,r %p,*arg %p\n", + tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL); if (!opt) return 0; @@ -506,9 +505,7 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) if (!p->perfect[i].res.class) continue; if (walker->count >= walker->skip) { - if (walker->fn(tp, - (unsigned long) (p->perfect+i), walker) - < 0) { + if (walker->fn(tp, p->perfect + i, walker) < 0) { walker->stop = 1; return; } @@ -522,8 +519,7 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) for (f = rtnl_dereference(p->h[i]); f; f = next) { next = rtnl_dereference(f->next); if (walker->count >= walker->skip) { - if (walker->fn(tp, (unsigned long) &f->result, - walker) < 0) { + if (walker->fn(tp, &f->result, walker) < 0) { walker->stop = 1; return; } @@ -548,14 +544,14 @@ static void tcindex_destroy(struct tcf_proto *tp) } -static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh; + struct tcindex_filter_result *r = fh; struct nlattr *nest; - pr_debug("tcindex_dump(tp %p,fh 0x%lx,skb %p,t %p),p %p,r %p\n", + pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n", tp, fh, skb, t, p, r); pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 2d01195153e6..af22742d2847 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -289,7 +289,7 @@ out: } -static unsigned long u32_get(struct tcf_proto *tp, u32 handle) +static void *u32_get(struct tcf_proto *tp, u32 handle) { struct tc_u_hnode *ht; struct tc_u_common *tp_c = tp->data; @@ -300,12 +300,12 @@ static unsigned long u32_get(struct tcf_proto *tp, u32 handle) ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle)); if (!ht) - return 0; + return NULL; if (TC_U32_KEY(handle) == 0) - return (unsigned long)ht; + return ht; - return (unsigned long)u32_lookup_key(ht, handle); + return u32_lookup_key(ht, handle); } static u32 gen_new_htid(struct tc_u_common *tp_c) @@ -431,43 +431,35 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; - - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; - - if (tc_should_offload(dev, tp, 0)) { - offload.cls_u32->command = TC_CLSU32_DELETE_KNODE; - offload.cls_u32->knode.handle = handle; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); - } + struct tc_cls_u32_offload cls_u32 = {}; + + if (!tc_should_offload(dev, 0)) + return; + + tc_cls_common_offload_init(&cls_u32.common, tp); + cls_u32.command = TC_CLSU32_DELETE_KNODE; + cls_u32.knode.handle = handle; + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; + struct tc_cls_u32_offload cls_u32 = {}; int err; - if (!tc_should_offload(dev, tp, flags)) + if (!tc_should_offload(dev, flags)) return tc_skip_sw(flags) ? -EINVAL : 0; - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; - - offload.cls_u32->command = TC_CLSU32_NEW_HNODE; - offload.cls_u32->hnode.divisor = h->divisor; - offload.cls_u32->hnode.handle = h->handle; - offload.cls_u32->hnode.prio = h->prio; + tc_cls_common_offload_init(&cls_u32.common, tp); + cls_u32.command = TC_CLSU32_NEW_HNODE; + cls_u32.hnode.divisor = h->divisor; + cls_u32.hnode.handle = h->handle; + cls_u32.hnode.prio = h->prio; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); if (tc_skip_sw(flags)) return err; @@ -477,56 +469,47 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; + struct tc_cls_u32_offload cls_u32 = {}; - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; + if (!tc_should_offload(dev, 0)) + return; - if (tc_should_offload(dev, tp, 0)) { - offload.cls_u32->command = TC_CLSU32_DELETE_HNODE; - offload.cls_u32->hnode.divisor = h->divisor; - offload.cls_u32->hnode.handle = h->handle; - offload.cls_u32->hnode.prio = h->prio; + tc_cls_common_offload_init(&cls_u32.common, tp); + cls_u32.command = TC_CLSU32_DELETE_HNODE; + cls_u32.hnode.divisor = h->divisor; + cls_u32.hnode.handle = h->handle; + cls_u32.hnode.prio = h->prio; - dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); - } + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32 flags) { struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_u32_offload u32_offload = {0}; - struct tc_to_netdev offload; + struct tc_cls_u32_offload cls_u32 = {}; int err; - offload.type = TC_SETUP_CLSU32; - offload.cls_u32 = &u32_offload; - - if (!tc_should_offload(dev, tp, flags)) + if (!tc_should_offload(dev, flags)) return tc_skip_sw(flags) ? -EINVAL : 0; - offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE; - offload.cls_u32->knode.handle = n->handle; - offload.cls_u32->knode.fshift = n->fshift; + tc_cls_common_offload_init(&cls_u32.common, tp); + cls_u32.command = TC_CLSU32_REPLACE_KNODE; + cls_u32.knode.handle = n->handle; + cls_u32.knode.fshift = n->fshift; #ifdef CONFIG_CLS_U32_MARK - offload.cls_u32->knode.val = n->val; - offload.cls_u32->knode.mask = n->mask; + cls_u32.knode.val = n->val; + cls_u32.knode.mask = n->mask; #else - offload.cls_u32->knode.val = 0; - offload.cls_u32->knode.mask = 0; + cls_u32.knode.val = 0; + cls_u32.knode.mask = 0; #endif - offload.cls_u32->knode.sel = &n->sel; - offload.cls_u32->knode.exts = &n->exts; + cls_u32.knode.sel = &n->sel; + cls_u32.knode.exts = &n->exts; if (n->ht_down) - offload.cls_u32->knode.link_handle = n->ht_down->handle; + cls_u32.knode.link_handle = n->ht_down->handle; - err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, - tp->chain->index, tp->protocol, - &offload); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); if (!err) n->flags |= TCA_CLS_FLAGS_IN_HW; @@ -622,9 +605,9 @@ static void u32_destroy(struct tcf_proto *tp) tp->data = NULL; } -static int u32_delete(struct tcf_proto *tp, unsigned long arg, bool *last) +static int u32_delete(struct tcf_proto *tp, void *arg, bool *last) { - struct tc_u_hnode *ht = (struct tc_u_hnode *)arg; + struct tc_u_hnode *ht = arg; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); struct tc_u_common *tp_c = tp->data; int ret = 0; @@ -723,29 +706,24 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, bool ovr) { - struct tcf_exts e; int err; - err = tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE); + err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); - if (err < 0) - goto errout; - err = -EINVAL; if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; if (TC_U32_KEY(handle)) - goto errout; + return -EINVAL; if (handle) { ht_down = u32_lookup_ht(ht->tp_c, handle); if (ht_down == NULL) - goto errout; + return -EINVAL; ht_down->refcnt++; } @@ -765,16 +743,11 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, int ret; ret = tcf_change_indev(net, tb[TCA_U32_INDEV]); if (ret < 0) - goto errout; + return -EINVAL; n->ifindex = ret; } #endif - tcf_exts_change(tp, &n->exts, &e); - return 0; -errout: - tcf_exts_destroy(&e); - return err; } static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, @@ -858,7 +831,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, unsigned long *arg, bool ovr) + struct nlattr **tca, void **arg, bool ovr) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -885,7 +858,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } - n = (struct tc_u_knode *)*arg; + n = *arg; if (n) { struct tc_u_knode *new; @@ -952,7 +925,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(ht->next, tp_c->hlist); rcu_assign_pointer(tp_c->hlist, ht); - *arg = (unsigned long)ht; + *arg = ht; return 0; } @@ -1047,7 +1020,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->next, pins); rcu_assign_pointer(*ins, n); - *arg = (unsigned long)n; + *arg = n; return 0; } @@ -1081,7 +1054,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) if (ht->prio != tp->prio) continue; if (arg->count >= arg->skip) { - if (arg->fn(tp, (unsigned long)ht, arg) < 0) { + if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; return; } @@ -1095,7 +1068,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) arg->count++; continue; } - if (arg->fn(tp, (unsigned long)n, arg) < 0) { + if (arg->fn(tp, n, arg) < 0) { arg->stop = 1; return; } @@ -1105,10 +1078,10 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) } } -static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, +static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct tc_u_knode *n = (struct tc_u_knode *)fh; + struct tc_u_knode *n = fh; struct tc_u_hnode *ht_up, *ht_down; struct nlattr *nest; @@ -1122,7 +1095,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; if (TC_U32_KEY(n->handle) == 0) { - struct tc_u_hnode *ht = (struct tc_u_hnode *)fh; + struct tc_u_hnode *ht = fh; u32 divisor = ht->divisor + 1; if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor)) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bd24a550e0f9..0fea0c50b763 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -286,9 +286,6 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { - struct Qdisc *root = qdisc_dev(q)->qdisc; - - WARN_ON_ONCE(root == &noop_qdisc); ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); if (invisible) @@ -752,6 +749,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; + bool notify; int drops; if (n == 0 && len == 0) @@ -764,6 +762,13 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, if (sch->flags & TCQ_F_NOPARENT) break; + /* Notify parent qdisc only if child qdisc becomes empty. + * + * If child was empty even before update then backlog + * counter is screwed and we skip notification because + * parent class is already passive. + */ + notify = !sch->q.qlen && !WARN_ON_ONCE(!n); /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { @@ -771,7 +776,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, break; } cops = sch->ops->cl_ops; - if (cops->qlen_notify) { + if (notify && cops->qlen_notify) { cl = cops->get(sch, parentid); cops->qlen_notify(sch, cl); cops->put(sch, cl); @@ -1952,14 +1957,14 @@ static int __init pktsched_init(void) register_qdisc(&mq_qdisc_ops); register_qdisc(&noqueue_qdisc_ops); - rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, - NULL); - rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL); + 0); + rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, - NULL); + 0); return 0; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 572fe2584e48..2732950766a9 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -41,6 +41,7 @@ #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; @@ -49,7 +50,6 @@ struct atm_flow_data { struct sk_buff *skb); /* chaining */ struct atm_qdisc_data *parent; /* parent qdisc */ struct socket *sock; /* for closing */ - u32 classid; /* x:y type ID */ int ref; /* reference count */ struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; @@ -75,7 +75,7 @@ static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) struct atm_flow_data *flow; list_for_each_entry(flow, &p->flows, list) { - if (flow->classid == classid) + if (flow->common.classid == classid) return flow; } return NULL; @@ -293,7 +293,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, flow->old_pop = flow->vcc->pop; flow->parent = p; flow->vcc->pop = sch_atm_pop; - flow->classid = classid; + flow->common.classid = classid; flow->ref = 1; flow->excess = excess; list_add(&flow->list, &p->link.list); @@ -549,7 +549,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) p->link.vcc = NULL; p->link.sock = NULL; - p->link.classid = sch->handle; + p->link.common.classid = sch->handle; p->link.ref = 1; tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; @@ -572,8 +572,10 @@ static void atm_tc_destroy(struct Qdisc *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) + 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) @@ -594,7 +596,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, sch, p, flow, skb, tcm); if (list_empty(&flow->list)) return -EINVAL; - tcm->tcm_handle = flow->classid; + tcm->tcm_handle = flow->common.classid; tcm->tcm_info = flow->q->handle; nest = nla_nest_start(skb, TCA_OPTIONS); @@ -619,7 +621,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, goto nla_put_failure; } if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->classid)) + 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)) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 481036f6b54e..1bdb0106f342 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1385,8 +1385,7 @@ static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct cbq_class *cl = (struct cbq_class *)arg; - if (cl->q->q.qlen == 0) - cbq_deactivate_class(cl); + cbq_deactivate_class(cl); } static unsigned long cbq_get(struct Qdisc *sch, u32 classid) @@ -1431,8 +1430,10 @@ static void cbq_destroy(struct Qdisc *sch) * 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) + 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], diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index a413dc1c2098..1d2f6235dfcf 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -246,8 +246,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg) { struct drr_class *cl = (struct drr_class *)arg; - if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); + list_del(&cl->alist); } static int drr_dump_class(struct Qdisc *sch, unsigned long arg, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 57ba406f1437..c6b89a34e8d2 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -29,6 +29,7 @@ #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <trace/events/qdisc.h> /* Qdisc to use by default */ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; @@ -126,7 +127,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, q->q.qlen--; } else skb = NULL; - return skb; + goto trace; } *validate = true; skb = q->skb_bad_txq; @@ -139,7 +140,8 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, q->q.qlen--; goto bulk; } - return NULL; + skb = NULL; + goto trace; } if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) @@ -151,6 +153,8 @@ bulk: else try_bulk_dequeue_skb_slow(q, skb, packets); } +trace: + trace_qdisc_dequeue(q, txq, *packets, skb); return skb; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b52f74610dc7..15f09cb9f1ff 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -829,28 +829,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time) } } -static void -set_active(struct hfsc_class *cl, unsigned int len) -{ - if (cl->cl_flags & HFSC_RSC) - init_ed(cl, len); - if (cl->cl_flags & HFSC_FSC) - init_vf(cl, len); - -} - -static void -set_passive(struct hfsc_class *cl) -{ - if (cl->cl_flags & HFSC_RSC) - eltree_remove(cl); - - /* - * vttree is now handled in update_vf() so that update_vf(cl, 0, 0) - * needs to be called explicitly to remove a class from vttree. - */ -} - static unsigned int qdisc_peek_len(struct Qdisc *sch) { @@ -1221,10 +1199,12 @@ hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct hfsc_class *cl = (struct hfsc_class *)arg; - if (cl->qdisc->q.qlen == 0) { - update_vf(cl, 0, 0); - set_passive(cl); - } + /* vttree is now handled in update_vf() so that update_vf(cl, 0, 0) + * needs to be called explicitly to remove a class from vttree. + */ + update_vf(cl, 0, 0); + if (cl->cl_flags & HFSC_RSC) + eltree_remove(cl); } static unsigned long @@ -1428,6 +1408,10 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; + err = tcf_block_get(&q->root.block, &q->root.filter_list); + if (err) + goto err_tcf; + q->root.cl_common.classid = sch->handle; q->root.refcnt = 1; q->root.sched = q; @@ -1447,6 +1431,10 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); return 0; + +err_tcf: + qdisc_class_hash_destroy(&q->clhash); + return err; } static int @@ -1522,8 +1510,10 @@ hfsc_destroy_qdisc(struct Qdisc *sch) unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1575,7 +1565,12 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } if (cl->qdisc->q.qlen == 1) { - set_active(cl, qdisc_pkt_len(skb)); + unsigned int len = qdisc_pkt_len(skb); + + if (cl->cl_flags & HFSC_RSC) + init_ed(cl, len); + if (cl->cl_flags & HFSC_FSC) + init_vf(cl, len); /* * If this is the first packet, isolate the head so an eventual * head drop before the first dequeue operation has no chance @@ -1639,18 +1634,18 @@ hfsc_dequeue(struct Qdisc *sch) if (realtime) cl->cl_cumul += qdisc_pkt_len(skb); - if (cl->qdisc->q.qlen != 0) { - if (cl->cl_flags & HFSC_RSC) { + if (cl->cl_flags & HFSC_RSC) { + if (cl->qdisc->q.qlen != 0) { /* update ed */ next_len = qdisc_peek_len(cl->qdisc); if (realtime) update_ed(cl, next_len); else update_d(cl, next_len); + } else { + /* the class becomes passive */ + eltree_remove(cl); } - } else { - /* the class becomes passive */ - set_passive(cl); } qdisc_bstats_update(sch, skb); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 203286ab4427..dcf3c85e1f4f 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1186,8 +1186,7 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - if (cl->un.leaf.q->q.qlen == 0) - htb_deactivate(qdisc_priv(sch), cl); + htb_deactivate(qdisc_priv(sch), cl); } static unsigned long htb_get(struct Qdisc *sch, u32 classid) @@ -1258,8 +1257,10 @@ static void htb_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index d8a9bebcab90..a15c543c3569 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -32,11 +32,6 @@ static unsigned long ingress_get(struct Qdisc *sch, u32 classid) return TC_H_MIN(classid) + 1; } -static bool ingress_cl_offload(u32 classid) -{ - return true; -} - static unsigned long ingress_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { @@ -103,7 +98,6 @@ static const struct Qdisc_class_ops ingress_class_ops = { .put = ingress_put, .walk = ingress_walk, .tcf_block = ingress_tcf_block, - .tcf_cl_offload = ingress_cl_offload, .bind_tcf = ingress_bind_filter, .unbind_tcf = ingress_put, }; @@ -134,11 +128,6 @@ static unsigned long clsact_get(struct Qdisc *sch, u32 classid) } } -static bool clsact_cl_offload(u32 classid) -{ - return TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS); -} - static unsigned long clsact_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { @@ -198,7 +187,6 @@ static const struct Qdisc_class_ops clsact_class_ops = { .put = ingress_put, .walk = ingress_walk, .tcf_block = clsact_tcf_block, - .tcf_cl_offload = clsact_cl_offload, .bind_tcf = clsact_bind_filter, .unbind_tcf = ingress_put, }; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index e0c02725cd48..2165a05994b7 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -39,11 +39,9 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt offload = { 0 }; - struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, - { .mqprio = &offload } }; + struct tc_mqprio_qopt mqprio = {}; - dev->netdev_ops->ndo_setup_tc(dev, sch->handle, 0, 0, &tc); + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio); } else { netdev_set_num_tc(dev, 0); } @@ -148,16 +146,14 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt offload = *qopt; - struct tc_to_netdev tc = { .type = TC_SETUP_MQPRIO, - { .mqprio = &offload } }; + struct tc_mqprio_qopt mqprio = *qopt; - err = dev->netdev_ops->ndo_setup_tc(dev, sch->handle, - 0, 0, &tc); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + &mqprio); if (err) return err; - priv->hw_offload = offload.hw; + priv->hw_offload = mqprio.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 0e16dfda0bd7..9caa959f91e1 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1428,8 +1428,7 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; - if (cl->qdisc->q.qlen == 0) - qfq_deactivate_class(q, cl); + qfq_deactivate_class(q, cl); } static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index f80ea2cc5f1f..82469ef9655e 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -437,6 +437,7 @@ congestion_drop: qdisc_drop(head, sch, to_free); slot_queue_add(slot, skb); + qdisc_tree_reduce_backlog(sch, 0, delta); return NET_XMIT_CN; } @@ -468,8 +469,10 @@ enqueue: /* Return Congestion Notification only if we dropped a packet * from this flow. */ - if (qlen != slot->qlen) + if (qlen != slot->qlen) { + qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb)); return NET_XMIT_CN; + } /* As we dropped a packet, better let upper stack know this */ qdisc_tree_reduce_backlog(sch, 1, dropped); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 40ec83679d6e..dfb9651e818b 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -63,11 +63,11 @@ static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc); /* 1st Level Abstractions. */ /* Initialize a new association from provided memory. */ -static struct sctp_association *sctp_association_init(struct sctp_association *asoc, - const struct sctp_endpoint *ep, - const struct sock *sk, - sctp_scope_t scope, - gfp_t gfp) +static struct sctp_association *sctp_association_init( + struct sctp_association *asoc, + const struct sctp_endpoint *ep, + const struct sock *sk, + enum sctp_scope scope, gfp_t gfp) { struct net *net = sock_net(sk); struct sctp_sock *sp; @@ -301,9 +301,8 @@ fail_init: /* Allocate and initialize a new association */ struct sctp_association *sctp_association_new(const struct sctp_endpoint *ep, - const struct sock *sk, - sctp_scope_t scope, - gfp_t gfp) + const struct sock *sk, + enum sctp_scope scope, gfp_t gfp) { struct sctp_association *asoc; @@ -797,7 +796,7 @@ void sctp_assoc_del_nonprimary_peers(struct sctp_association *asoc, */ void sctp_assoc_control_transport(struct sctp_association *asoc, struct sctp_transport *transport, - sctp_transport_cmd_t command, + enum sctp_transport_cmd command, sctp_sn_error_t error) { struct sctp_ulpevent *event; @@ -1022,11 +1021,11 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) container_of(work, struct sctp_association, base.inqueue.immediate); struct net *net = sock_net(asoc->base.sk); + union sctp_subtype subtype; struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; int state; - sctp_subtype_t subtype; int error = 0; /* The association should be held so we should be safe. */ @@ -1564,7 +1563,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) * local endpoint and the remote peer. */ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, - sctp_scope_t scope, gfp_t gfp) + enum sctp_scope scope, gfp_t gfp) { int flags; diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 1ebc184a0e23..7df3704982f5 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -45,9 +45,9 @@ #include <net/sctp/sm.h> /* Forward declarations for internal helpers. */ -static int sctp_copy_one_addr(struct net *, struct sctp_bind_addr *, - union sctp_addr *, sctp_scope_t scope, gfp_t gfp, - int flags); +static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, + union sctp_addr *addr, enum sctp_scope scope, + gfp_t gfp, int flags); static void sctp_bind_addr_clean(struct sctp_bind_addr *); /* First Level Abstractions. */ @@ -57,7 +57,7 @@ static void sctp_bind_addr_clean(struct sctp_bind_addr *); */ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, - sctp_scope_t scope, gfp_t gfp, + enum sctp_scope scope, gfp_t gfp, int flags) { struct sctp_sockaddr_entry *addr; @@ -440,9 +440,8 @@ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, /* Copy out addresses from the global local address list. */ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, - union sctp_addr *addr, - sctp_scope_t scope, gfp_t gfp, - int flags) + union sctp_addr *addr, enum sctp_scope scope, + gfp_t gfp, int flags) { int error = 0; @@ -485,9 +484,10 @@ int sctp_is_any(struct sock *sk, const union sctp_addr *addr) } /* Is 'addr' valid for 'scope'? */ -int sctp_in_scope(struct net *net, const union sctp_addr *addr, sctp_scope_t scope) +int sctp_in_scope(struct net *net, const union sctp_addr *addr, + enum sctp_scope scope) { - sctp_scope_t addr_scope = sctp_scope(addr); + enum sctp_scope addr_scope = sctp_scope(addr); /* The unusable SCTP addresses will not be considered with * any defined scopes. @@ -545,7 +545,7 @@ int sctp_is_ep_boundall(struct sock *sk) ********************************************************************/ /* What is the scope of 'addr'? */ -sctp_scope_t sctp_scope(const union sctp_addr *addr) +enum sctp_scope sctp_scope(const union sctp_addr *addr) { struct sctp_af *af; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 681b181e7ae3..3afac275ee82 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -201,7 +201,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) - max_data -= SCTP_PAD4(sizeof(sctp_auth_chunk_t) + + max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) + hmac_desc->hmac_len); } diff --git a/net/sctp/debug.c b/net/sctp/debug.c index 2e47eb2f05cb..3f619fdcbf0a 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -60,7 +60,7 @@ static const char *const sctp_cid_tbl[SCTP_NUM_BASE_CHUNK_TYPES] = { }; /* Lookup "chunk type" debug name. */ -const char *sctp_cname(const sctp_subtype_t cid) +const char *sctp_cname(const union sctp_subtype cid) { if (cid.chunk <= SCTP_CID_BASE_MAX) return sctp_cid_tbl[cid.chunk]; @@ -130,7 +130,7 @@ static const char *const sctp_primitive_tbl[SCTP_NUM_PRIMITIVE_TYPES] = { }; /* Lookup primitive debug name. */ -const char *sctp_pname(const sctp_subtype_t id) +const char *sctp_pname(const union sctp_subtype id) { if (id.primitive <= SCTP_EVENT_PRIMITIVE_MAX) return sctp_primitive_tbl[id.primitive]; @@ -143,7 +143,7 @@ static const char *const sctp_other_tbl[] = { }; /* Lookup "other" debug name. */ -const char *sctp_oname(const sctp_subtype_t id) +const char *sctp_oname(const union sctp_subtype id) { if (id.other <= SCTP_EVENT_OTHER_MAX) return sctp_other_tbl[id.other]; @@ -165,7 +165,7 @@ static const char *const sctp_timer_tbl[] = { }; /* Lookup timer debug name. */ -const char *sctp_tname(const sctp_subtype_t id) +const char *sctp_tname(const union sctp_subtype id) { BUILD_BUG_ON(SCTP_EVENT_TIMEOUT_MAX + 1 != ARRAY_SIZE(sctp_timer_tbl)); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 3d506b2f6193..ee1e601a0b11 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -382,8 +382,8 @@ static void sctp_endpoint_bh_rcv(struct work_struct *work) struct sctp_transport *transport; struct sctp_chunk *chunk; struct sctp_inq *inqueue; - sctp_subtype_t subtype; - sctp_state_t state; + union sctp_subtype subtype; + enum sctp_state state; int error = 0; int first_time = 1; /* is this the first time through the loop */ diff --git a/net/sctp/input.c b/net/sctp/input.c index 41eb2ec10460..92a07141fd07 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1111,7 +1111,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( __be16 peer_port, struct sctp_transport **transportp) { - sctp_addip_chunk_t *asconf = (struct sctp_addip_chunk *)ch; + struct sctp_addip_chunk *asconf = (struct sctp_addip_chunk *)ch; struct sctp_af *af; union sctp_addr_param *param; union sctp_addr paddr; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 107d7c912922..a2a1c1d08d51 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -243,8 +243,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; struct in6_addr *final_p, final; + enum sctp_scope scope; __u8 matchlen = 0; - sctp_scope_t scope; memset(fl6, 0, sizeof(struct flowi6)); fl6->daddr = daddr->v6.sin6_addr; @@ -624,10 +624,10 @@ static int sctp_v6_addr_valid(union sctp_addr *addr, } /* What is the scope of 'addr'? */ -static sctp_scope_t sctp_v6_scope(union sctp_addr *addr) +static enum sctp_scope sctp_v6_scope(union sctp_addr *addr) { + enum sctp_scope retval; int v6scope; - sctp_scope_t retval; /* The IPv6 scope is really a set of bit fields. * See IFA_* in <net/if_inet6.h>. Map to a generic SCTP scope. diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c index 105ac3327b28..aeea6da81441 100644 --- a/net/sctp/objcnt.c +++ b/net/sctp/objcnt.c @@ -57,7 +57,7 @@ SCTP_DBG_OBJCNT(keys); /* An array to make it easy to pretty print the debug information * to the proc fs. */ -static sctp_dbg_objcnt_entry_t sctp_dbg_objcnt[] = { +static struct sctp_dbg_objcnt_entry sctp_dbg_objcnt[] = { SCTP_DBG_OBJCNT_ENTRY(sock), SCTP_DBG_OBJCNT_ENTRY(ep), SCTP_DBG_OBJCNT_ENTRY(assoc), diff --git a/net/sctp/output.c b/net/sctp/output.c index 9d8504985744..4a865cd06d76 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -57,15 +57,15 @@ #include <net/sctp/checksum.h> /* Forward declarations for private helpers. */ -static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, - struct sctp_chunk *chunk); -static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, - struct sctp_chunk *chunk); +static enum sctp_xmit __sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk); +static enum sctp_xmit sctp_packet_can_append_data(struct sctp_packet *packet, + struct sctp_chunk *chunk); static void sctp_packet_append_data(struct sctp_packet *packet, - struct sctp_chunk *chunk); -static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, - struct sctp_chunk *chunk, - u16 chunk_len); + struct sctp_chunk *chunk); +static enum sctp_xmit sctp_packet_will_fit(struct sctp_packet *packet, + struct sctp_chunk *chunk, + u16 chunk_len); static void sctp_packet_reset(struct sctp_packet *packet) { @@ -181,11 +181,11 @@ void sctp_packet_free(struct sctp_packet *packet) * as it can fit in the packet, but any more data that does not fit in this * packet can be sent only after receiving the COOKIE_ACK. */ -sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, - struct sctp_chunk *chunk, - int one_packet, gfp_t gfp) +enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk, + int one_packet, gfp_t gfp) { - sctp_xmit_t retval; + enum sctp_xmit retval; pr_debug("%s: packet:%p size:%zu chunk:%p size:%d\n", __func__, packet, packet->size, chunk, chunk->skb ? chunk->skb->len : -1); @@ -218,12 +218,12 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, } /* Try to bundle an auth chunk into the packet. */ -static sctp_xmit_t sctp_packet_bundle_auth(struct sctp_packet *pkt, - struct sctp_chunk *chunk) +static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt, + struct sctp_chunk *chunk) { struct sctp_association *asoc = pkt->transport->asoc; + enum sctp_xmit retval = SCTP_XMIT_OK; struct sctp_chunk *auth; - sctp_xmit_t retval = SCTP_XMIT_OK; /* if we don't have an association, we can't do authentication */ if (!asoc) @@ -254,10 +254,10 @@ static sctp_xmit_t sctp_packet_bundle_auth(struct sctp_packet *pkt, } /* Try to bundle a SACK with the packet. */ -static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt, - struct sctp_chunk *chunk) +static enum sctp_xmit sctp_packet_bundle_sack(struct sctp_packet *pkt, + struct sctp_chunk *chunk) { - sctp_xmit_t retval = SCTP_XMIT_OK; + enum sctp_xmit retval = SCTP_XMIT_OK; /* If sending DATA and haven't aleady bundled a SACK, try to * bundle one in to the packet. @@ -299,11 +299,11 @@ out: /* Append a chunk to the offered packet reporting back any inability to do * so. */ -static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet, - struct sctp_chunk *chunk) +static enum sctp_xmit __sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk) { - sctp_xmit_t retval = SCTP_XMIT_OK; __u16 chunk_len = SCTP_PAD4(ntohs(chunk->chunk_hdr->length)); + enum sctp_xmit retval = SCTP_XMIT_OK; /* Check to see if this chunk will fit into the packet */ retval = sctp_packet_will_fit(packet, chunk, chunk_len); @@ -353,10 +353,10 @@ finish: /* Append a chunk to the offered packet reporting back any inability to do * so. */ -sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *packet, - struct sctp_chunk *chunk) +enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk) { - sctp_xmit_t retval = SCTP_XMIT_OK; + enum sctp_xmit retval = SCTP_XMIT_OK; pr_debug("%s: packet:%p chunk:%p\n", __func__, packet, chunk); @@ -653,8 +653,8 @@ out: ********************************************************************/ /* This private function check to see if a chunk can be added */ -static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, - struct sctp_chunk *chunk) +static enum sctp_xmit sctp_packet_can_append_data(struct sctp_packet *packet, + struct sctp_chunk *chunk) { size_t datasize, rwnd, inflight, flight_size; struct sctp_transport *transport = packet->transport; @@ -762,12 +762,12 @@ static void sctp_packet_append_data(struct sctp_packet *packet, sctp_chunk_assign_ssn(chunk); } -static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, - struct sctp_chunk *chunk, - u16 chunk_len) +static enum sctp_xmit sctp_packet_will_fit(struct sctp_packet *packet, + struct sctp_chunk *chunk, + u16 chunk_len) { + enum sctp_xmit retval = SCTP_XMIT_OK; size_t psize, pmtu, maxsize; - sctp_xmit_t retval = SCTP_XMIT_OK; psize = packet->size; if (packet->transport->asoc) diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index d2a8adfd4a6f..2966ff400755 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -534,7 +534,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * one packet out. */ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, - sctp_retransmit_reason_t reason) + enum sctp_retransmit_reason reason) { struct net *net = sock_net(q->asoc->base.sk); @@ -594,14 +594,14 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer) { - struct list_head *lqueue; struct sctp_transport *transport = pkt->transport; - sctp_xmit_t status; struct sctp_chunk *chunk, *chunk1; - int fast_rtx; + struct list_head *lqueue; + enum sctp_xmit status; int error = 0; int timer = 0; int done = 0; + int fast_rtx; lqueue = &q->retransmit; fast_rtx = q->fast_rtx; @@ -781,7 +781,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) struct sctp_transport *transport = NULL; struct sctp_transport *new_transport; struct sctp_chunk *chunk, *tmp; - sctp_xmit_t status; + enum sctp_xmit status; int error = 0; int start_timer = 0; int one_packet = 0; diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c index f0553a022859..c0817f7a8964 100644 --- a/net/sctp/primitive.c +++ b/net/sctp/primitive.c @@ -53,8 +53,8 @@ int sctp_primitive_ ## name(struct net *net, struct sctp_association *asoc, \ void *arg) { \ int error = 0; \ - sctp_event_t event_type; sctp_subtype_t subtype; \ - sctp_state_t state; \ + enum sctp_event event_type; union sctp_subtype subtype; \ + enum sctp_state state; \ struct sctp_endpoint *ep; \ \ event_type = SCTP_EVENT_T_PRIMITIVE; \ diff --git a/net/sctp/probe.c b/net/sctp/probe.c index 6cc2152e0740..1280f85a598d 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -127,12 +127,13 @@ static const struct file_operations sctpprobe_fops = { .llseek = noop_llseek, }; -static sctp_disposition_t jsctp_sf_eat_sack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition jsctp_sf_eat_sack( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sk_buff *skb = chunk->skb; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 852556d67ae3..fcd80feb293f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -196,7 +196,7 @@ static void sctp_free_local_addr_list(struct net *net) /* Copy the local addresses which are valid for 'scope' into 'bp'. */ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, - sctp_scope_t scope, gfp_t gfp, int copy_flags) + enum sctp_scope scope, gfp_t gfp, int copy_flags) { struct sctp_sockaddr_entry *addr; union sctp_addr laddr; @@ -400,9 +400,9 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) * IPv4 scoping can be controlled through sysctl option * net.sctp.addr_scope_policy */ -static sctp_scope_t sctp_v4_scope(union sctp_addr *addr) +static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) { - sctp_scope_t retval; + enum sctp_scope retval; /* Check for unusable SCTP addresses. */ if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 163004e7047c..ca8f196b6c6c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -132,17 +132,17 @@ static const struct sctp_paramhdr prsctp_param = { * provided chunk, as most cause codes will be embedded inside an * abort chunk. */ -void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, - size_t paylen) +void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, + size_t paylen) { - sctp_errhdr_t err; + struct sctp_errhdr err; __u16 len; /* Cause code constants are now defined in network order. */ err.cause = cause_code; - len = sizeof(sctp_errhdr_t) + paylen; + len = sizeof(err) + paylen; err.length = htons(len); - chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(sctp_errhdr_t), &err); + chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); } /* A helper to initialize an op error inside a @@ -151,21 +151,21 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, * if there isn't enough space in the op error chunk */ static int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, - size_t paylen) + size_t paylen) { - sctp_errhdr_t err; + struct sctp_errhdr err; __u16 len; /* Cause code constants are now defined in network order. */ err.cause = cause_code; - len = sizeof(sctp_errhdr_t) + paylen; + len = sizeof(err) + paylen; err.length = htons(len); if (skb_tailroom(chunk->skb) < len) return -ENOSPC; - chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk, - sizeof(sctp_errhdr_t), - &err); + + chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk, sizeof(err), &err); + return 0; } /* 3.3.2 Initiation (INIT) (1) @@ -213,32 +213,31 @@ static int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, * Supported Address Types (Note 4) Optional 12 */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, - const struct sctp_bind_addr *bp, - gfp_t gfp, int vparam_len) + const struct sctp_bind_addr *bp, + gfp_t gfp, int vparam_len) { struct net *net = sock_net(asoc->base.sk); + struct sctp_supported_ext_param ext_param; + struct sctp_adaptation_ind_param aiparam; + struct sctp_paramhdr *auth_chunks = NULL; + struct sctp_paramhdr *auth_hmacs = NULL; + struct sctp_supported_addrs_param sat; struct sctp_endpoint *ep = asoc->ep; - struct sctp_inithdr init; - union sctp_params addrs; - size_t chunksize; struct sctp_chunk *retval = NULL; int num_types, addrs_len = 0; + struct sctp_inithdr init; + union sctp_params addrs; struct sctp_sock *sp; - struct sctp_supported_addrs_param sat; + __u8 extensions[4]; + size_t chunksize; __be16 types[2]; - struct sctp_adaptation_ind_param aiparam; - struct sctp_supported_ext_param ext_param; int num_ext = 0; - __u8 extensions[4]; - struct sctp_paramhdr *auth_chunks = NULL, - *auth_hmacs = NULL; /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 1: The INIT chunks can contain multiple addresses that * can be IPv4 and/or IPv6 in any combination. */ - retval = NULL; /* Convert the provided bind address list to raw format. */ addrs = sctp_bind_addrs_to_raw(bp, &addrs_len, gfp); @@ -380,26 +379,24 @@ nodata: } struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - gfp_t gfp, int unkparam_len) + const struct sctp_chunk *chunk, + gfp_t gfp, int unkparam_len) { + struct sctp_supported_ext_param ext_param; + struct sctp_adaptation_ind_param aiparam; + struct sctp_paramhdr *auth_chunks = NULL; + struct sctp_paramhdr *auth_random = NULL; + struct sctp_paramhdr *auth_hmacs = NULL; + struct sctp_chunk *retval = NULL; + struct sctp_cookie_param *cookie; struct sctp_inithdr initack; - struct sctp_chunk *retval; union sctp_params addrs; struct sctp_sock *sp; - int addrs_len; - struct sctp_cookie_param *cookie; - int cookie_len; + __u8 extensions[4]; size_t chunksize; - struct sctp_adaptation_ind_param aiparam; - struct sctp_supported_ext_param ext_param; int num_ext = 0; - __u8 extensions[4]; - struct sctp_paramhdr *auth_chunks = NULL, - *auth_hmacs = NULL, - *auth_random = NULL; - - retval = NULL; + int cookie_len; + int addrs_len; /* Note: there may be no addresses to embed. */ addrs = sctp_bind_addrs_to_raw(&asoc->base.bind_addr, &addrs_len, gfp); @@ -562,11 +559,11 @@ nomem_cookie: * to insure interoperability. */ struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, - const struct sctp_chunk *chunk) + const struct sctp_chunk *chunk) { struct sctp_chunk *retval; - void *cookie; int cookie_len; + void *cookie; cookie = asoc->peer.cookie; cookie_len = asoc->peer.cookie_len; @@ -614,7 +611,7 @@ nodata: * Set to zero on transmit and ignored on receipt. */ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, - const struct sctp_chunk *chunk) + const struct sctp_chunk *chunk) { struct sctp_chunk *retval; @@ -659,15 +656,15 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, * Note: The CWR is considered a Control chunk. */ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, - const __u32 lowest_tsn, - const struct sctp_chunk *chunk) + const __u32 lowest_tsn, + const struct sctp_chunk *chunk) { struct sctp_chunk *retval; - sctp_cwrhdr_t cwr; + struct sctp_cwrhdr cwr; cwr.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_CWR, 0, - sizeof(sctp_cwrhdr_t), GFP_ATOMIC); + sizeof(cwr), GFP_ATOMIC); if (!retval) goto nodata; @@ -694,14 +691,14 @@ nodata: /* Make an ECNE chunk. This is a congestion experienced report. */ struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, - const __u32 lowest_tsn) + const __u32 lowest_tsn) { struct sctp_chunk *retval; - sctp_ecnehdr_t ecne; + struct sctp_ecnehdr ecne; ecne.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_ECNE, 0, - sizeof(sctp_ecnehdr_t), GFP_ATOMIC); + sizeof(ecne), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.ecne_hdr = @@ -715,9 +712,9 @@ nodata: * parameters. However, do not populate the data payload. */ struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc, - const struct sctp_sndrcvinfo *sinfo, - int data_len, __u8 flags, __u16 ssn, - gfp_t gfp) + const struct sctp_sndrcvinfo *sinfo, + int data_len, __u8 flags, __u16 ssn, + gfp_t gfp) { struct sctp_chunk *retval; struct sctp_datahdr dp; @@ -755,15 +752,15 @@ nodata: */ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) { - struct sctp_chunk *retval; - struct sctp_sackhdr sack; - int len; - __u32 ctsn; - __u16 num_gabs, num_dup_tsns; - struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; + struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; + __u16 num_gabs, num_dup_tsns; struct sctp_transport *trans; + struct sctp_chunk *retval; + struct sctp_sackhdr sack; + __u32 ctsn; + int len; memset(gabs, 0, sizeof(gabs)); ctsn = sctp_tsnmap_get_ctsn(map); @@ -857,15 +854,15 @@ nodata: struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { + struct sctp_shutdownhdr shut; struct sctp_chunk *retval; - sctp_shutdownhdr_t shut; __u32 ctsn; ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); shut.cum_tsn_ack = htonl(ctsn); retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0, - sizeof(sctp_shutdownhdr_t), GFP_ATOMIC); + sizeof(shut), GFP_ATOMIC); if (!retval) goto nodata; @@ -879,7 +876,7 @@ nodata: } struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, - const struct sctp_chunk *chunk) + const struct sctp_chunk *chunk) { struct sctp_chunk *retval; @@ -902,8 +899,8 @@ struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, } struct sctp_chunk *sctp_make_shutdown_complete( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk) { struct sctp_chunk *retval; __u8 flags = 0; @@ -936,8 +933,8 @@ struct sctp_chunk *sctp_make_shutdown_complete( * association, except when responding to an INIT (sctpimpguide 2.41). */ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - const size_t hint) + const struct sctp_chunk *chunk, + const size_t hint) { struct sctp_chunk *retval; __u8 flags = 0; @@ -973,14 +970,15 @@ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, /* Helper to create ABORT with a NO_USER_DATA error. */ struct sctp_chunk *sctp_make_abort_no_data( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk, __u32 tsn) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + __u32 tsn) { struct sctp_chunk *retval; __be32 payload; - retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) - + sizeof(tsn)); + retval = sctp_make_abort(asoc, chunk, + sizeof(struct sctp_errhdr) + sizeof(tsn)); if (!retval) goto no_mem; @@ -1015,7 +1013,8 @@ struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, void *payload = NULL; int err; - retval = sctp_make_abort(asoc, NULL, sizeof(sctp_errhdr_t) + paylen); + retval = sctp_make_abort(asoc, NULL, + sizeof(struct sctp_errhdr) + paylen); if (!retval) goto err_chunk; @@ -1053,8 +1052,8 @@ err_chunk: static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data) { - void *target; int chunklen = ntohs(chunk->chunk_hdr->length); + void *target; target = skb_put(chunk->skb, len); @@ -1072,16 +1071,16 @@ static void *sctp_addto_param(struct sctp_chunk *chunk, int len, /* Make an ABORT chunk with a PROTOCOL VIOLATION cause code. */ struct sctp_chunk *sctp_make_abort_violation( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - const __u8 *payload, - const size_t paylen) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + const __u8 *payload, + const size_t paylen) { struct sctp_chunk *retval; struct sctp_paramhdr phdr; - retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) + paylen + - sizeof(phdr)); + retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + + paylen + sizeof(phdr)); if (!retval) goto end; @@ -1098,14 +1097,14 @@ end: } struct sctp_chunk *sctp_make_violation_paramlen( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - struct sctp_paramhdr *param) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + struct sctp_paramhdr *param) { - struct sctp_chunk *retval; static const char error[] = "The following parameter had invalid length:"; - size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t) + + size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr) + sizeof(*param); + struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) @@ -1121,12 +1120,12 @@ nodata: } struct sctp_chunk *sctp_make_violation_max_retrans( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk) { - struct sctp_chunk *retval; static const char error[] = "Association exceeded its max_retans count"; - size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t); + size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr); + struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) @@ -1141,10 +1140,10 @@ nodata: /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport) + const struct sctp_transport *transport) { + struct sctp_sender_hb_info hbinfo; struct sctp_chunk *retval; - sctp_sender_hb_info_t hbinfo; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, sizeof(hbinfo), GFP_ATOMIC); @@ -1153,7 +1152,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, goto nodata; hbinfo.param_hdr.type = SCTP_PARAM_HEARTBEAT_INFO; - hbinfo.param_hdr.length = htons(sizeof(sctp_sender_hb_info_t)); + hbinfo.param_hdr.length = htons(sizeof(hbinfo)); hbinfo.daddr = transport->ipaddr; hbinfo.sent_at = jiffies; hbinfo.hb_nonce = transport->hb_nonce; @@ -1170,8 +1169,9 @@ nodata: } struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - const void *payload, const size_t paylen) + const struct sctp_chunk *chunk, + const void *payload, + const size_t paylen) { struct sctp_chunk *retval; @@ -1202,14 +1202,15 @@ nodata: * This routine can be used for containing multiple causes in the chunk. */ static struct sctp_chunk *sctp_make_op_error_space( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - size_t size) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + size_t size) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_ERROR, 0, - sizeof(sctp_errhdr_t) + size, GFP_ATOMIC); + sizeof(struct sctp_errhdr) + size, + GFP_ATOMIC); if (!retval) goto nodata; @@ -1235,8 +1236,8 @@ nodata: * to report all the errors, if the incoming chunk is large */ static inline struct sctp_chunk *sctp_make_op_error_fixed( - const struct sctp_association *asoc, - const struct sctp_chunk *chunk) + const struct sctp_association *asoc, + const struct sctp_chunk *chunk) { size_t size = asoc ? asoc->pathmtu : 0; @@ -1248,9 +1249,9 @@ static inline struct sctp_chunk *sctp_make_op_error_fixed( /* Create an Operation Error chunk. */ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, - const struct sctp_chunk *chunk, - __be16 cause_code, const void *payload, - size_t paylen, size_t reserve_tail) + const struct sctp_chunk *chunk, + __be16 cause_code, const void *payload, + size_t paylen, size_t reserve_tail) { struct sctp_chunk *retval; @@ -1269,9 +1270,9 @@ nodata: struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) { - struct sctp_chunk *retval; - struct sctp_hmac *hmac_desc; struct sctp_authhdr auth_hdr; + struct sctp_hmac *hmac_desc; + struct sctp_chunk *retval; __u8 *hmac; /* Get the first hmac that the peer told us to use */ @@ -1280,16 +1281,16 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) return NULL; retval = sctp_make_control(asoc, SCTP_CID_AUTH, 0, - hmac_desc->hmac_len + sizeof(sctp_authhdr_t), - GFP_ATOMIC); + hmac_desc->hmac_len + sizeof(auth_hdr), + GFP_ATOMIC); if (!retval) return NULL; auth_hdr.hmac_id = htons(hmac_desc->hmac_id); auth_hdr.shkey_id = htons(asoc->active_key_id); - retval->subh.auth_hdr = sctp_addto_chunk(retval, sizeof(sctp_authhdr_t), - &auth_hdr); + retval->subh.auth_hdr = sctp_addto_chunk(retval, sizeof(auth_hdr), + &auth_hdr); hmac = skb_put_zero(retval->skb, hmac_desc->hmac_len); @@ -1317,8 +1318,8 @@ struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc) * */ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, - const struct sctp_association *asoc, - struct sock *sk, gfp_t gfp) + const struct sctp_association *asoc, + struct sock *sk, gfp_t gfp) { struct sctp_chunk *retval; @@ -1370,11 +1371,11 @@ const union sctp_addr *sctp_source(const struct sctp_chunk *chunk) * arguments, reserving enough space for a 'paylen' byte payload. */ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, - __u8 type, __u8 flags, int paylen, - gfp_t gfp) + __u8 type, __u8 flags, int paylen, + gfp_t gfp) { - struct sctp_chunk *retval; struct sctp_chunkhdr *chunk_hdr; + struct sctp_chunk *retval; struct sk_buff *skb; struct sock *sk; @@ -1468,9 +1469,9 @@ void sctp_chunk_put(struct sctp_chunk *ch) */ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) { - void *target; int chunklen = ntohs(chunk->chunk_hdr->length); int padlen = SCTP_PAD4(chunklen) - chunklen; + void *target; skb_put_zero(chunk->skb, padlen); target = skb_put_data(chunk->skb, data, len); @@ -1523,11 +1524,10 @@ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len, */ void sctp_chunk_assign_ssn(struct sctp_chunk *chunk) { - struct sctp_datamsg *msg; - struct sctp_chunk *lchunk; struct sctp_stream *stream; - __u16 ssn; - __u16 sid; + struct sctp_chunk *lchunk; + struct sctp_datamsg *msg; + __u16 ssn, sid; if (chunk->has_ssn) return; @@ -1572,12 +1572,12 @@ void sctp_chunk_assign_tsn(struct sctp_chunk *chunk) /* Create a CLOSED association to use with an incoming packet. */ struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *ep, - struct sctp_chunk *chunk, - gfp_t gfp) + struct sctp_chunk *chunk, + gfp_t gfp) { struct sctp_association *asoc; + enum sctp_scope scope; struct sk_buff *skb; - sctp_scope_t scope; /* Create the bare association. */ scope = sctp_scope(sctp_source(chunk)); @@ -1600,8 +1600,8 @@ static struct sctp_cookie_param *sctp_pack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *init_chunk, - int *cookie_len, - const __u8 *raw_addrs, int addrs_len) + int *cookie_len, const __u8 *raw_addrs, + int addrs_len) { struct sctp_signed_cookie *cookie; struct sctp_cookie_param *retval; @@ -1688,19 +1688,19 @@ nodata: /* Unpack the cookie from COOKIE ECHO chunk, recreating the association. */ struct sctp_association *sctp_unpack_cookie( - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - struct sctp_chunk *chunk, gfp_t gfp, - int *error, struct sctp_chunk **errp) + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + struct sctp_chunk *chunk, gfp_t gfp, + int *error, struct sctp_chunk **errp) { struct sctp_association *retval = NULL; + int headersize, bodysize, fixed_size; struct sctp_signed_cookie *cookie; + struct sk_buff *skb = chunk->skb; struct sctp_cookie *bear_cookie; - int headersize, bodysize, fixed_size; __u8 *digest = ep->digest; + enum sctp_scope scope; unsigned int len; - sctp_scope_t scope; - struct sk_buff *skb = chunk->skb; ktime_t kt; /* Header size is static data prior to the actual cookie, including @@ -1972,8 +1972,8 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, static int sctp_verify_ext_param(struct net *net, union sctp_params param) { __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); - int have_auth = 0; int have_asconf = 0; + int have_auth = 0; int i; for (i = 0; i < num_ext; i++) { @@ -2003,10 +2003,10 @@ static int sctp_verify_ext_param(struct net *net, union sctp_params param) } static void sctp_process_ext_param(struct sctp_association *asoc, - union sctp_params param) + union sctp_params param) { - struct net *net = sock_net(asoc->base.sk); __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); + struct net *net = sock_net(asoc->base.sk); int i; for (i = 0; i < num_ext; i++) { @@ -2063,10 +2063,11 @@ static void sctp_process_ext_param(struct sctp_association *asoc, * SCTP_IERROR_ERROR - stop and report an error. * SCTP_IERROR_NOMEME - out of memory. */ -static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, - union sctp_params param, - struct sctp_chunk *chunk, - struct sctp_chunk **errp) +static enum sctp_ierror sctp_process_unk_param( + const struct sctp_association *asoc, + union sctp_params param, + struct sctp_chunk *chunk, + struct sctp_chunk **errp) { int retval = SCTP_IERROR_NO_ERROR; @@ -2115,13 +2116,13 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, * SCTP_IERROR_ERROR - stop processing, trigger an ERROR * SCTP_IERROR_NO_ERROR - continue with the chunk */ -static sctp_ierror_t sctp_verify_param(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - union sctp_params param, - enum sctp_cid cid, - struct sctp_chunk *chunk, - struct sctp_chunk **err_chunk) +static enum sctp_ierror sctp_verify_param(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + union sctp_params param, + enum sctp_cid cid, + struct sctp_chunk *chunk, + struct sctp_chunk **err_chunk) { struct sctp_hmac_algo_param *hmacs; int retval = SCTP_IERROR_NO_ERROR; @@ -2306,13 +2307,13 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_init_chunk *peer_init, gfp_t gfp) { struct net *net = sock_net(asoc->base.sk); - union sctp_params param; struct sctp_transport *transport; struct list_head *pos, *temp; - struct sctp_af *af; + union sctp_params param; union sctp_addr addr; - char *cookie; + struct sctp_af *af; int src_match = 0; + char *cookie; /* We must include the address that the INIT packet came from. * This is the only address that matters for an INIT packet. @@ -2496,16 +2497,15 @@ static int sctp_process_param(struct sctp_association *asoc, gfp_t gfp) { struct net *net = sock_net(asoc->base.sk); - union sctp_addr addr; - int i; - __u16 sat; - int retval = 1; - sctp_scope_t scope; - u32 stale; - struct sctp_af *af; + struct sctp_endpoint *ep = asoc->ep; union sctp_addr_param *addr_param; struct sctp_transport *t; - struct sctp_endpoint *ep = asoc->ep; + enum sctp_scope scope; + union sctp_addr addr; + struct sctp_af *af; + int retval = 1, i; + u32 stale; + __u16 sat; /* We maintain all INIT parameters in network byte order all the * time. This allows us to not worry about whether the parameters @@ -2613,7 +2613,7 @@ do_addr_param: if (!net->sctp.addip_enable) goto fall_through; - addr_param = param.v + sizeof(sctp_addip_param_t); + addr_param = param.v + sizeof(struct sctp_addip_param); af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (af == NULL) @@ -2750,7 +2750,7 @@ static struct sctp_chunk *sctp_make_asconf(struct sctp_association *asoc, union sctp_addr *addr, int vparam_len) { - sctp_addiphdr_t asconf; + struct sctp_addiphdr asconf; struct sctp_chunk *retval; int length = sizeof(asconf) + vparam_len; union sctp_addr_param addrparam; @@ -2803,22 +2803,20 @@ static struct sctp_chunk *sctp_make_asconf(struct sctp_association *asoc, * */ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, - union sctp_addr *laddr, - struct sockaddr *addrs, - int addrcnt, - __be16 flags) -{ - sctp_addip_param_t param; - struct sctp_chunk *retval; - union sctp_addr_param addr_param; - union sctp_addr *addr; - void *addr_buf; - struct sctp_af *af; - int paramlen = sizeof(param); - int addr_param_len = 0; - int totallen = 0; - int i; - int del_pickup = 0; + union sctp_addr *laddr, + struct sockaddr *addrs, + int addrcnt, __be16 flags) +{ + union sctp_addr_param addr_param; + struct sctp_addip_param param; + int paramlen = sizeof(param); + struct sctp_chunk *retval; + int addr_param_len = 0; + union sctp_addr *addr; + int totallen = 0, i; + int del_pickup = 0; + struct sctp_af *af; + void *addr_buf; /* Get total length of all the address parameters. */ addr_buf = addrs; @@ -2894,12 +2892,12 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr) { - sctp_addip_param_t param; - struct sctp_chunk *retval; - int len = sizeof(param); - union sctp_addr_param addrparam; - int addrlen; - struct sctp_af *af = sctp_get_af_specific(addr->v4.sin_family); + struct sctp_af *af = sctp_get_af_specific(addr->v4.sin_family); + union sctp_addr_param addrparam; + struct sctp_addip_param param; + struct sctp_chunk *retval; + int len = sizeof(param); + int addrlen; addrlen = af->to_addr_param(addr, &addrparam); if (!addrlen) @@ -2943,9 +2941,9 @@ struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, static struct sctp_chunk *sctp_make_asconf_ack(const struct sctp_association *asoc, __u32 serial, int vparam_len) { - sctp_addiphdr_t asconf; - struct sctp_chunk *retval; - int length = sizeof(asconf) + vparam_len; + struct sctp_addiphdr asconf; + struct sctp_chunk *retval; + int length = sizeof(asconf) + vparam_len; /* Create the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_ASCONF_ACK, 0, length, @@ -2963,13 +2961,14 @@ static struct sctp_chunk *sctp_make_asconf_ack(const struct sctp_association *as /* Add response parameters to an ASCONF_ACK chunk. */ static void sctp_add_asconf_response(struct sctp_chunk *chunk, __be32 crr_id, - __be16 err_code, sctp_addip_param_t *asconf_param) + __be16 err_code, + struct sctp_addip_param *asconf_param) { - sctp_addip_param_t ack_param; - sctp_errhdr_t err_param; - int asconf_param_len = 0; - int err_param_len = 0; - __be16 response_type; + struct sctp_addip_param ack_param; + struct sctp_errhdr err_param; + int asconf_param_len = 0; + int err_param_len = 0; + __be16 response_type; if (SCTP_ERROR_NO_ERROR == err_code) { response_type = SCTP_PARAM_SUCCESS_REPORT; @@ -3004,15 +3003,15 @@ static void sctp_add_asconf_response(struct sctp_chunk *chunk, __be32 crr_id, /* Process a asconf parameter. */ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, - struct sctp_chunk *asconf, - sctp_addip_param_t *asconf_param) + struct sctp_chunk *asconf, + struct sctp_addip_param *asconf_param) { + union sctp_addr_param *addr_param; struct sctp_transport *peer; - struct sctp_af *af; union sctp_addr addr; - union sctp_addr_param *addr_param; + struct sctp_af *af; - addr_param = (void *)asconf_param + sizeof(sctp_addip_param_t); + addr_param = (void *)asconf_param + sizeof(*asconf_param); if (asconf_param->param_hdr.type != SCTP_PARAM_ADD_IP && asconf_param->param_hdr.type != SCTP_PARAM_DEL_IP && @@ -3137,10 +3136,11 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, bool addr_param_needed, struct sctp_paramhdr **errp) { - sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr; - union sctp_params param; + struct sctp_addip_chunk *addip; bool addr_param_seen = false; + union sctp_params param; + addip = (struct sctp_addip_chunk *)chunk->chunk_hdr; sctp_walk_params(param, addip, addip_hdr.params) { size_t length = ntohs(param.p->length); @@ -3172,13 +3172,13 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, if (addr_param_needed && !addr_param_seen) return false; length = ntohs(param.addip->param_hdr.length); - if (length < sizeof(sctp_addip_param_t) + + if (length < sizeof(struct sctp_addip_param) + sizeof(**errp)) return false; break; case SCTP_PARAM_SUCCESS_REPORT: case SCTP_PARAM_ADAPTATION_LAYER_IND: - if (length != sizeof(sctp_addip_param_t)) + if (length != sizeof(struct sctp_addip_param)) return false; break; default: @@ -3204,24 +3204,24 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf) { - sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr; + union sctp_addr_param *addr_param; + struct sctp_addip_chunk *addip; + struct sctp_chunk *asconf_ack; bool all_param_pass = true; + struct sctp_addiphdr *hdr; + int length = 0, chunk_len; union sctp_params param; - sctp_addiphdr_t *hdr; - union sctp_addr_param *addr_param; - struct sctp_chunk *asconf_ack; - __be16 err_code; - int length = 0; - int chunk_len; - __u32 serial; + __be16 err_code; + __u32 serial; + addip = (struct sctp_addip_chunk *)asconf->chunk_hdr; chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); - hdr = (sctp_addiphdr_t *)asconf->skb->data; + hdr = (struct sctp_addiphdr *)asconf->skb->data; serial = ntohl(hdr->serial); /* Skip the addiphdr and store a pointer to address parameter. */ - length = sizeof(sctp_addiphdr_t); + length = sizeof(*hdr); addr_param = (union sctp_addr_param *)(asconf->skb->data + length); chunk_len -= length; @@ -3287,16 +3287,16 @@ done: /* Process a asconf parameter that is successfully acked. */ static void sctp_asconf_param_success(struct sctp_association *asoc, - sctp_addip_param_t *asconf_param) + struct sctp_addip_param *asconf_param) { - struct sctp_af *af; - union sctp_addr addr; struct sctp_bind_addr *bp = &asoc->base.bind_addr; union sctp_addr_param *addr_param; - struct sctp_transport *transport; struct sctp_sockaddr_entry *saddr; + struct sctp_transport *transport; + union sctp_addr addr; + struct sctp_af *af; - addr_param = (void *)asconf_param + sizeof(sctp_addip_param_t); + addr_param = (void *)asconf_param + sizeof(*asconf_param); /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); @@ -3347,14 +3347,14 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, * specific success indication is present for the parameter. */ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, - sctp_addip_param_t *asconf_param, - int no_err) + struct sctp_addip_param *asconf_param, + int no_err) { - sctp_addip_param_t *asconf_ack_param; - sctp_errhdr_t *err_param; - int length; - int asconf_ack_len; - __be16 err_code; + struct sctp_addip_param *asconf_ack_param; + struct sctp_errhdr *err_param; + int asconf_ack_len; + __be16 err_code; + int length; if (no_err) err_code = SCTP_ERROR_NO_ERROR; @@ -3367,9 +3367,9 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, /* Skip the addiphdr from the asconf_ack chunk and store a pointer to * the first asconf_ack parameter. */ - length = sizeof(sctp_addiphdr_t); - asconf_ack_param = (sctp_addip_param_t *)(asconf_ack->skb->data + - length); + length = sizeof(struct sctp_addiphdr); + asconf_ack_param = (struct sctp_addip_param *)(asconf_ack->skb->data + + length); asconf_ack_len -= length; while (asconf_ack_len > 0) { @@ -3378,7 +3378,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, case SCTP_PARAM_SUCCESS_REPORT: return SCTP_ERROR_NO_ERROR; case SCTP_PARAM_ERR_CAUSE: - length = sizeof(sctp_addip_param_t); + length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; asconf_ack_len -= length; if (asconf_ack_len > 0) @@ -3403,20 +3403,20 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, int sctp_process_asconf_ack(struct sctp_association *asoc, struct sctp_chunk *asconf_ack) { - struct sctp_chunk *asconf = asoc->addip_last_asconf; - union sctp_addr_param *addr_param; - sctp_addip_param_t *asconf_param; - int length = 0; - int asconf_len = asconf->skb->len; - int all_param_pass = 0; - int no_err = 1; - int retval = 0; - __be16 err_code = SCTP_ERROR_NO_ERROR; + struct sctp_chunk *asconf = asoc->addip_last_asconf; + struct sctp_addip_param *asconf_param; + __be16 err_code = SCTP_ERROR_NO_ERROR; + union sctp_addr_param *addr_param; + int asconf_len = asconf->skb->len; + int all_param_pass = 0; + int length = 0; + int no_err = 1; + int retval = 0; /* Skip the chunkhdr and addiphdr from the last asconf sent and store * a pointer to address parameter. */ - length = sizeof(sctp_addip_chunk_t); + length = sizeof(struct sctp_addip_chunk); addr_param = (union sctp_addr_param *)(asconf->skb->data + length); asconf_len -= length; @@ -3432,7 +3432,7 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, * failures are indicated, then all request(s) are considered * successful. */ - if (asconf_ack->skb->len == sizeof(sctp_addiphdr_t)) + if (asconf_ack->skb->len == sizeof(struct sctp_addiphdr)) all_param_pass = 1; /* Process the TLVs contained in the last sent ASCONF chunk. */ @@ -3538,9 +3538,8 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ -static struct sctp_chunk *sctp_make_reconf( - const struct sctp_association *asoc, - int length) +static struct sctp_chunk *sctp_make_reconf(const struct sctp_association *asoc, + int length) { struct sctp_reconf_chunk *reconf; struct sctp_chunk *retval; @@ -3591,9 +3590,9 @@ static struct sctp_chunk *sctp_make_reconf( * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_req( - const struct sctp_association *asoc, - __u16 stream_num, __u16 *stream_list, - bool out, bool in) + const struct sctp_association *asoc, + __u16 stream_num, __u16 *stream_list, + bool out, bool in) { struct sctp_strreset_outreq outreq; __u16 stream_len = stream_num * 2; @@ -3645,7 +3644,7 @@ struct sctp_chunk *sctp_make_strreset_req( * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_tsnreq( - const struct sctp_association *asoc) + const struct sctp_association *asoc) { struct sctp_strreset_tsnreq tsnreq; __u16 length = sizeof(tsnreq); @@ -3676,8 +3675,8 @@ struct sctp_chunk *sctp_make_strreset_tsnreq( * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_strreset_addstrm( - const struct sctp_association *asoc, - __u16 out, __u16 in) + const struct sctp_association *asoc, + __u16 out, __u16 in) { struct sctp_strreset_addstrm addstrm; __u16 size = sizeof(addstrm); @@ -3721,9 +3720,8 @@ struct sctp_chunk *sctp_make_strreset_addstrm( * | Result | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ -struct sctp_chunk *sctp_make_strreset_resp( - const struct sctp_association *asoc, - __u32 result, __u32 sn) +struct sctp_chunk *sctp_make_strreset_resp(const struct sctp_association *asoc, + __u32 result, __u32 sn) { struct sctp_strreset_resp resp; __u16 length = sizeof(resp); @@ -3758,10 +3756,10 @@ struct sctp_chunk *sctp_make_strreset_resp( * | Receiver's Next TSN (optional) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ -struct sctp_chunk *sctp_make_strreset_tsnresp( - struct sctp_association *asoc, - __u32 result, __u32 sn, - __u32 sender_tsn, __u32 receiver_tsn) +struct sctp_chunk *sctp_make_strreset_tsnresp(struct sctp_association *asoc, + __u32 result, __u32 sn, + __u32 sender_tsn, + __u32 receiver_tsn) { struct sctp_strreset_resptsn tsnresp; __u16 length = sizeof(tsnresp); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index d6e5e9e0fd6d..e6a2974e020e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -51,22 +51,23 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> -static int sctp_cmd_interpreter(sctp_event_t event_type, - sctp_subtype_t subtype, - sctp_state_t state, +static int sctp_cmd_interpreter(enum sctp_event event_type, + union sctp_subtype subtype, + enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, - sctp_disposition_t status, - sctp_cmd_seq_t *commands, + enum sctp_disposition status, + struct sctp_cmd_seq *commands, gfp_t gfp); -static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, - sctp_state_t state, +static int sctp_side_effects(enum sctp_event event_type, + union sctp_subtype subtype, + enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association **asoc, void *event_arg, - sctp_disposition_t status, - sctp_cmd_seq_t *commands, + enum sctp_disposition status, + struct sctp_cmd_seq *commands, gfp_t gfp); /******************************************************************** @@ -96,8 +97,8 @@ static void sctp_do_ecn_ce_work(struct sctp_association *asoc, * that was originally marked with the CE bit. */ static struct sctp_chunk *sctp_do_ecn_ecne_work(struct sctp_association *asoc, - __u32 lowest_tsn, - struct sctp_chunk *chunk) + __u32 lowest_tsn, + struct sctp_chunk *chunk) { struct sctp_chunk *repl; @@ -149,11 +150,11 @@ static void sctp_do_ecn_cwr_work(struct sctp_association *asoc, /* Generate SACK if necessary. We call this at the end of a packet. */ static int sctp_gen_sack(struct sctp_association *asoc, int force, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { + struct sctp_transport *trans = asoc->peer.last_data_from; __u32 ctsn, max_tsn_seen; struct sctp_chunk *sack; - struct sctp_transport *trans = asoc->peer.last_data_from; int error = 0; if (force || @@ -243,11 +244,11 @@ nomem: */ void sctp_generate_t3_rtx_event(unsigned long peer) { - int error; struct sctp_transport *transport = (struct sctp_transport *) peer; struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); + int error; /* Check whether a task is in the sock. */ @@ -280,7 +281,7 @@ out_unlock: * for timeouts which use the association as their parameter. */ static void sctp_generate_timeout_event(struct sctp_association *asoc, - sctp_event_timeout_t timeout_type) + enum sctp_event_timeout timeout_type) { struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -360,12 +361,12 @@ static void sctp_generate_autoclose_event(unsigned long data) */ void sctp_generate_heartbeat_event(unsigned long data) { - int error = 0; struct sctp_transport *transport = (struct sctp_transport *) data; struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); u32 elapsed, timeout; + int error = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { @@ -405,7 +406,7 @@ out_unlock: */ void sctp_generate_proto_unreach_event(unsigned long data) { - struct sctp_transport *transport = (struct sctp_transport *) data; + struct sctp_transport *transport = (struct sctp_transport *)data; struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -471,7 +472,7 @@ out_unlock: /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(unsigned long data) { - struct sctp_association *asoc = (struct sctp_association *) data; + struct sctp_association *asoc = (struct sctp_association *)data; sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_SACK); } @@ -505,7 +506,7 @@ sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = { * notification SHOULD be sent to the upper layer. * */ -static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, +static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands, struct sctp_association *asoc, struct sctp_transport *transport, int is_hb) @@ -577,7 +578,7 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, } /* Worker routine to handle INIT command failure. */ -static void sctp_cmd_init_failed(sctp_cmd_seq_t *commands, +static void sctp_cmd_init_failed(struct sctp_cmd_seq *commands, struct sctp_association *asoc, unsigned int error) { @@ -600,15 +601,16 @@ static void sctp_cmd_init_failed(sctp_cmd_seq_t *commands, } /* Worker routine to handle SCTP_CMD_ASSOC_FAILED. */ -static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, +static void sctp_cmd_assoc_failed(struct sctp_cmd_seq *commands, struct sctp_association *asoc, - sctp_event_t event_type, - sctp_subtype_t subtype, + enum sctp_event event_type, + union sctp_subtype subtype, struct sctp_chunk *chunk, unsigned int error) { struct sctp_ulpevent *event; struct sctp_chunk *abort; + /* Cancel any partial delivery in progress. */ sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); @@ -644,7 +646,7 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, * since all other cases use "temporary" associations and can do all * their work in statefuns directly. */ -static int sctp_cmd_process_init(sctp_cmd_seq_t *commands, +static int sctp_cmd_process_init(struct sctp_cmd_seq *commands, struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_init_chunk *peer_init, @@ -666,7 +668,7 @@ static int sctp_cmd_process_init(sctp_cmd_seq_t *commands, } /* Helper function to break out starting up of heartbeat timers. */ -static void sctp_cmd_hb_timers_start(sctp_cmd_seq_t *cmds, +static void sctp_cmd_hb_timers_start(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sctp_transport *t; @@ -679,7 +681,7 @@ static void sctp_cmd_hb_timers_start(sctp_cmd_seq_t *cmds, sctp_transport_reset_hb_timer(t); } -static void sctp_cmd_hb_timers_stop(sctp_cmd_seq_t *cmds, +static void sctp_cmd_hb_timers_stop(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sctp_transport *t; @@ -694,7 +696,7 @@ static void sctp_cmd_hb_timers_stop(sctp_cmd_seq_t *cmds, } /* Helper function to stop any pending T3-RTX timers */ -static void sctp_cmd_t3_rtx_timers_stop(sctp_cmd_seq_t *cmds, +static void sctp_cmd_t3_rtx_timers_stop(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sctp_transport *t; @@ -708,12 +710,12 @@ static void sctp_cmd_t3_rtx_timers_stop(sctp_cmd_seq_t *cmds, /* Helper function to handle the reception of an HEARTBEAT ACK. */ -static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, +static void sctp_cmd_transport_on(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_transport *t, struct sctp_chunk *chunk) { - sctp_sender_hb_info_t *hbinfo; + struct sctp_sender_hb_info *hbinfo; int was_unconfirmed = 0; /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the @@ -767,7 +769,7 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, if (t->rto_pending == 0) t->rto_pending = 1; - hbinfo = (sctp_sender_hb_info_t *) chunk->skb->data; + hbinfo = (struct sctp_sender_hb_info *)chunk->skb->data; sctp_transport_update_rto(t, (jiffies - hbinfo->sent_at)); /* Update the heartbeat timer. */ @@ -779,7 +781,7 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, /* Helper function to process the process SACK command. */ -static int sctp_cmd_process_sack(sctp_cmd_seq_t *cmds, +static int sctp_cmd_process_sack(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { @@ -801,7 +803,7 @@ static int sctp_cmd_process_sack(sctp_cmd_seq_t *cmds, /* Helper function to set the timeout value for T2-SHUTDOWN timer and to set * the transport for a shutdown chunk. */ -static void sctp_cmd_setup_t2(sctp_cmd_seq_t *cmds, +static void sctp_cmd_setup_t2(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { @@ -818,7 +820,7 @@ static void sctp_cmd_setup_t2(sctp_cmd_seq_t *cmds, asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = t->rto; } -static void sctp_cmd_assoc_update(sctp_cmd_seq_t *cmds, +static void sctp_cmd_assoc_update(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_association *new) { @@ -828,7 +830,7 @@ static void sctp_cmd_assoc_update(sctp_cmd_seq_t *cmds, if (!sctp_assoc_update(asoc, new)) return; - abort = sctp_make_abort(asoc, NULL, sizeof(sctp_errhdr_t)); + abort = sctp_make_abort(asoc, NULL, sizeof(struct sctp_errhdr)); if (abort) { sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); sctp_add_cmd_sf(cmds, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); @@ -841,9 +843,9 @@ static void sctp_cmd_assoc_update(sctp_cmd_seq_t *cmds, } /* Helper function to change the state of an association. */ -static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds, +static void sctp_cmd_new_state(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, - sctp_state_t state) + enum sctp_state state) { struct sock *sk = asoc->base.sk; @@ -901,7 +903,7 @@ static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds, } /* Helper function to delete an association. */ -static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, +static void sctp_cmd_delete_tcb(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; @@ -923,9 +925,9 @@ static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, * destination address (we use active path instead of primary path just * because primary path may be inactive. */ -static void sctp_cmd_setup_t4(sctp_cmd_seq_t *cmds, - struct sctp_association *asoc, - struct sctp_chunk *chunk) +static void sctp_cmd_setup_t4(struct sctp_cmd_seq *cmds, + struct sctp_association *asoc, + struct sctp_chunk *chunk) { struct sctp_transport *t; @@ -935,7 +937,7 @@ static void sctp_cmd_setup_t4(sctp_cmd_seq_t *cmds, } /* Process an incoming Operation Error Chunk. */ -static void sctp_cmd_process_operr(sctp_cmd_seq_t *cmds, +static void sctp_cmd_process_operr(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { @@ -990,6 +992,7 @@ static void sctp_cmd_process_fwdtsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) { struct sctp_fwdtsn_skip *skip; + /* Walk through all the skipped SSNs */ sctp_walk_fwdtsn(skip, chunk) { sctp_ulpq_skip(ulpq, ntohs(skip->stream), ntohs(skip->ssn)); @@ -1002,8 +1005,8 @@ static void sctp_cmd_process_fwdtsn(struct sctp_ulpq *ulpq, static void sctp_cmd_del_non_primary(struct sctp_association *asoc) { struct sctp_transport *t; - struct list_head *pos; struct list_head *temp; + struct list_head *pos; list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { t = list_entry(pos, struct sctp_transport, transports); @@ -1024,9 +1027,9 @@ static void sctp_cmd_set_sk_err(struct sctp_association *asoc, int error) } /* Helper function to generate an association change event */ -static void sctp_cmd_assoc_change(sctp_cmd_seq_t *commands, - struct sctp_association *asoc, - u8 state) +static void sctp_cmd_assoc_change(struct sctp_cmd_seq *commands, + struct sctp_association *asoc, + u8 state) { struct sctp_ulpevent *ev; @@ -1039,7 +1042,7 @@ static void sctp_cmd_assoc_change(sctp_cmd_seq_t *commands, } /* Helper function to generate an adaptation indication event */ -static void sctp_cmd_adaptation_ind(sctp_cmd_seq_t *commands, +static void sctp_cmd_adaptation_ind(struct sctp_cmd_seq *commands, struct sctp_association *asoc) { struct sctp_ulpevent *ev; @@ -1052,8 +1055,8 @@ static void sctp_cmd_adaptation_ind(sctp_cmd_seq_t *commands, static void sctp_cmd_t1_timer_update(struct sctp_association *asoc, - sctp_event_timeout_t timer, - char *name) + enum sctp_event_timeout timer, + char *name) { struct sctp_transport *t; @@ -1139,22 +1142,20 @@ static void sctp_cmd_send_asconf(struct sctp_association *asoc) * If you want to understand all of lksctp, this is a * good place to start. */ -int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype, - sctp_state_t state, - struct sctp_endpoint *ep, - struct sctp_association *asoc, - void *event_arg, - gfp_t gfp) +int sctp_do_sm(struct net *net, enum sctp_event event_type, + union sctp_subtype subtype, enum sctp_state state, + struct sctp_endpoint *ep, struct sctp_association *asoc, + void *event_arg, gfp_t gfp) { - sctp_cmd_seq_t commands; - const sctp_sm_table_entry_t *state_fn; - sctp_disposition_t status; - int error = 0; - typedef const char *(printfn_t)(sctp_subtype_t); + typedef const char *(printfn_t)(union sctp_subtype); static printfn_t *table[] = { NULL, sctp_cname, sctp_tname, sctp_oname, sctp_pname, }; printfn_t *debug_fn __attribute__ ((unused)) = table[event_type]; + const struct sctp_sm_table_entry *state_fn; + struct sctp_cmd_seq commands; + enum sctp_disposition status; + int error = 0; /* Look up the state function, run it, and then process the * side effects. These three steps are the heart of lksctp. @@ -1178,13 +1179,14 @@ int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype, /***************************************************************** * This the master state function side effect processing function. *****************************************************************/ -static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, - sctp_state_t state, +static int sctp_side_effects(enum sctp_event event_type, + union sctp_subtype subtype, + enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association **asoc, void *event_arg, - sctp_disposition_t status, - sctp_cmd_seq_t *commands, + enum sctp_disposition status, + struct sctp_cmd_seq *commands, gfp_t gfp) { int error; @@ -1263,29 +1265,27 @@ bail: ********************************************************************/ /* This is the side-effect interpreter. */ -static int sctp_cmd_interpreter(sctp_event_t event_type, - sctp_subtype_t subtype, - sctp_state_t state, +static int sctp_cmd_interpreter(enum sctp_event event_type, + union sctp_subtype subtype, + enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, - sctp_disposition_t status, - sctp_cmd_seq_t *commands, + enum sctp_disposition status, + struct sctp_cmd_seq *commands, gfp_t gfp) { - struct sock *sk = ep->base.sk; - struct sctp_sock *sp = sctp_sk(sk); - int error = 0; - int force; - sctp_cmd_t *cmd; - struct sctp_chunk *new_obj; - struct sctp_chunk *chunk = NULL; + struct sctp_sock *sp = sctp_sk(ep->base.sk); + struct sctp_chunk *chunk = NULL, *new_obj; struct sctp_packet *packet; + struct sctp_sackhdr sackh; struct timer_list *timer; - unsigned long timeout; struct sctp_transport *t; - struct sctp_sackhdr sackh; + unsigned long timeout; + struct sctp_cmd *cmd; int local_cork = 0; + int error = 0; + int force; if (SCTP_EVENT_T_TIMEOUT != event_type) chunk = event_arg; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index dc0c2c4188d8..8f8ccded13e4 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -59,103 +59,110 @@ #include <net/sctp/sm.h> #include <net/sctp/structs.h> -static struct sctp_packet *sctp_abort_pkt_new(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - struct sctp_chunk *chunk, - const void *payload, - size_t paylen); +static struct sctp_packet *sctp_abort_pkt_new( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + struct sctp_chunk *chunk, + const void *payload, size_t paylen); static int sctp_eat_data(const struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands); -static struct sctp_packet *sctp_ootb_pkt_new(struct net *net, - const struct sctp_association *asoc, - const struct sctp_chunk *chunk); + struct sctp_cmd_seq *commands); +static struct sctp_packet *sctp_ootb_pkt_new( + struct net *net, + const struct sctp_association *asoc, + const struct sctp_chunk *chunk); static void sctp_send_stale_cookie_err(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands, + struct sctp_cmd_seq *commands, struct sctp_chunk *err_chunk); -static sctp_disposition_t sctp_sf_do_5_2_6_stale(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands); -static sctp_disposition_t sctp_sf_shut_8_4_5(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands); -static sctp_disposition_t sctp_sf_tabort_8_4_8(struct net *net, +static enum sctp_disposition sctp_sf_do_5_2_6_stale( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); +static enum sctp_disposition sctp_sf_shut_8_4_5( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); +static enum sctp_disposition sctp_sf_tabort_8_4_8( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands); + struct sctp_cmd_seq *commands); static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk); -static sctp_disposition_t sctp_stop_t1_and_abort(struct net *net, - sctp_cmd_seq_t *commands, - __be16 error, int sk_err, - const struct sctp_association *asoc, - struct sctp_transport *transport); +static enum sctp_disposition sctp_stop_t1_and_abort( + struct net *net, + struct sctp_cmd_seq *commands, + __be16 error, int sk_err, + const struct sctp_association *asoc, + struct sctp_transport *transport); -static sctp_disposition_t sctp_sf_abort_violation( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - void *arg, - sctp_cmd_seq_t *commands, - const __u8 *payload, - const size_t paylen); +static enum sctp_disposition sctp_sf_abort_violation( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + void *arg, + struct sctp_cmd_seq *commands, + const __u8 *payload, + const size_t paylen); -static sctp_disposition_t sctp_sf_violation_chunklen( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands); +static enum sctp_disposition sctp_sf_violation_chunklen( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); -static sctp_disposition_t sctp_sf_violation_paramlen( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, void *ext, - sctp_cmd_seq_t *commands); +static enum sctp_disposition sctp_sf_violation_paramlen( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, void *ext, + struct sctp_cmd_seq *commands); -static sctp_disposition_t sctp_sf_violation_ctsn( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands); +static enum sctp_disposition sctp_sf_violation_ctsn( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); -static sctp_disposition_t sctp_sf_violation_chunk( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands); +static enum sctp_disposition sctp_sf_violation_chunk( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); -static sctp_ierror_t sctp_sf_authenticate(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - struct sctp_chunk *chunk); +static enum sctp_ierror sctp_sf_authenticate( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + struct sctp_chunk *chunk); -static sctp_disposition_t __sctp_sf_do_9_1_abort(struct net *net, +static enum sctp_disposition __sctp_sf_do_9_1_abort( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands); + struct sctp_cmd_seq *commands); /* Small helper function that checks if the chunk length * is of the appropriate length. The 'required_length' argument @@ -164,8 +171,8 @@ static sctp_disposition_t __sctp_sf_do_9_1_abort(struct net *net, * false = Invalid length * */ -static inline bool -sctp_chunk_length_valid(struct sctp_chunk *chunk, __u16 required_length) +static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, + __u16 required_length) { __u16 chunk_length = ntohs(chunk->chunk_hdr->length); @@ -213,12 +220,11 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, __u16 required_length) * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_4_C(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_4_C(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_ulpevent *ev; @@ -299,12 +305,12 @@ sctp_disposition_t sctp_sf_do_4_C(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg, *repl, *err_chunk; struct sctp_unrecognized_param *unk_param; @@ -493,15 +499,15 @@ nomem: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = arg; struct sctp_init_chunk *initchunk; + struct sctp_chunk *chunk = arg; struct sctp_chunk *err_chunk; struct sctp_packet *packet; @@ -528,7 +534,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { - sctp_error_t error = SCTP_ERROR_NO_RESOURCE; + enum sctp_error error = SCTP_ERROR_NO_RESOURCE; /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes. If there are no causes, @@ -643,20 +649,21 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = arg; + struct sctp_ulpevent *ev, *ai_ev = NULL; struct sctp_association *new_asoc; struct sctp_init_chunk *peer_init; - struct sctp_chunk *repl; - struct sctp_ulpevent *ev, *ai_ev = NULL; - int error = 0; + struct sctp_chunk *chunk = arg; struct sctp_chunk *err_chk_p; + struct sctp_chunk *repl; struct sock *sk; + int error = 0; /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. @@ -756,7 +763,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, */ if (chunk->auth_chunk) { struct sctp_chunk auth; - sctp_ierror_t ret; + enum sctp_ierror ret; /* Make sure that we and the peer are AUTH capable */ if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { @@ -870,11 +877,12 @@ nomem: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_1E_ca(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_ulpevent *ev; @@ -948,11 +956,12 @@ nomem: } /* Generate and sendout a heartbeat packet. */ -static sctp_disposition_t sctp_sf_heartbeat(const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_heartbeat( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_transport *transport = (struct sctp_transport *) arg; struct sctp_chunk *reply; @@ -973,12 +982,12 @@ static sctp_disposition_t sctp_sf_heartbeat(const struct sctp_endpoint *ep, } /* Generate a HEARTBEAT packet on the given transport. */ -sctp_disposition_t sctp_sf_sendbeat_8_3(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_sendbeat_8_3(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_transport *transport = (struct sctp_transport *) arg; @@ -1021,11 +1030,12 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(struct net *net, } /* resend asoc strreset_chunk. */ -sctp_disposition_t sctp_sf_send_reconf(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_send_reconf(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_transport *transport = arg; @@ -1072,12 +1082,11 @@ sctp_disposition_t sctp_sf_send_reconf(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_beat_8_3(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_beat_8_3(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { struct sctp_paramhdr *param_hdr; struct sctp_chunk *chunk = arg; @@ -1147,34 +1156,32 @@ nomem: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_backbeat_8_3(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { + struct sctp_sender_hb_info *hbinfo; struct sctp_chunk *chunk = arg; - union sctp_addr from_addr; struct sctp_transport *link; - sctp_sender_hb_info_t *hbinfo; unsigned long max_interval; + union sctp_addr from_addr; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the HEARTBEAT-ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr) + - sizeof(sctp_sender_hb_info_t))) + sizeof(*hbinfo))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - hbinfo = (sctp_sender_hb_info_t *) chunk->skb->data; + hbinfo = (struct sctp_sender_hb_info *)chunk->skb->data; /* Make sure that the length of the parameter is what we expect */ - if (ntohs(hbinfo->param_hdr.length) != - sizeof(sctp_sender_hb_info_t)) { + if (ntohs(hbinfo->param_hdr.length) != sizeof(*hbinfo)) return SCTP_DISPOSITION_DISCARD; - } from_addr = hbinfo->daddr; link = sctp_assoc_lookup_paddr(asoc, &from_addr); @@ -1226,15 +1233,15 @@ sctp_disposition_t sctp_sf_backbeat_8_3(struct net *net, */ static int sctp_sf_send_restart_abort(struct net *net, union sctp_addr *ssa, struct sctp_chunk *init, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { - int len; - struct sctp_packet *pkt; + struct sctp_af *af = sctp_get_af_specific(ssa->v4.sin_family); union sctp_addr_param *addrparm; struct sctp_errhdr *errhdr; + char buffer[sizeof(*errhdr) + sizeof(*addrparm)]; struct sctp_endpoint *ep; - char buffer[sizeof(struct sctp_errhdr)+sizeof(union sctp_addr_param)]; - struct sctp_af *af = sctp_get_af_specific(ssa->v4.sin_family); + struct sctp_packet *pkt; + int len; /* Build the error on the stack. We are way to malloc crazy * throughout the code today. @@ -1244,7 +1251,7 @@ static int sctp_sf_send_restart_abort(struct net *net, union sctp_addr *ssa, /* Copy into a parm format. */ len = af->to_addr_param(ssa, addrparm); - len += sizeof(sctp_errhdr_t); + len += sizeof(*errhdr); errhdr->cause = SCTP_ERROR_RESTART; errhdr->length = htons(len); @@ -1291,7 +1298,7 @@ static bool list_has_sctp_addr(const struct list_head *list, static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, const struct sctp_association *asoc, struct sctp_chunk *init, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { struct net *net = sock_net(new_asoc->base.sk); struct sctp_transport *new_addr; @@ -1411,18 +1418,19 @@ static char sctp_tietags_compare(struct sctp_association *new_asoc, /* Common helper routine for both duplicate and simulataneous INIT * chunk handling. */ -static sctp_disposition_t sctp_sf_do_unexpected_init( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_do_unexpected_init( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg, *repl, *err_chunk; struct sctp_unrecognized_param *unk_param; struct sctp_association *new_asoc; + enum sctp_disposition retval; struct sctp_packet *packet; - sctp_disposition_t retval; int len; /* 6.10 Bundling @@ -1623,12 +1631,13 @@ cleanup: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_2_1_siminit(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_5_2_1_siminit( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* Call helper to do the real work for both simulataneous and * duplicate INIT chunk handling. @@ -1677,12 +1686,13 @@ sctp_disposition_t sctp_sf_do_5_2_1_siminit(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_2_2_dupinit(struct net *net, +enum sctp_disposition sctp_sf_do_5_2_2_dupinit( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { /* Call helper to do the real work for both simulataneous and * duplicate INIT chunk handling. @@ -1700,11 +1710,13 @@ sctp_disposition_t sctp_sf_do_5_2_2_dupinit(struct net *net, * An unexpected INIT ACK usually indicates the processing of an old or * duplicated INIT chunk. */ -sctp_disposition_t sctp_sf_do_5_2_3_initack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_5_2_3_initack( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* Per the above section, we'll discard the chunk if we have an * endpoint. If this is an OOTB INIT-ACK, treat it as such. @@ -1720,18 +1732,19 @@ sctp_disposition_t sctp_sf_do_5_2_3_initack(struct net *net, * Section 5.2.4 * A) In this case, the peer may have restarted. */ -static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, +static enum sctp_disposition sctp_sf_do_dupcook_a( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands, + struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { struct sctp_init_chunk *peer_init; + enum sctp_disposition disposition; struct sctp_ulpevent *ev; struct sctp_chunk *repl; struct sctp_chunk *err; - sctp_disposition_t disposition; /* new_asoc is a brand-new association, so these are not yet * side effects--it is safe to run them here. @@ -1835,11 +1848,12 @@ nomem: * after responding to the local endpoint's INIT */ /* This case represents an initialization collision. */ -static sctp_disposition_t sctp_sf_do_dupcook_b(struct net *net, +static enum sctp_disposition sctp_sf_do_dupcook_b( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands, + struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { struct sctp_init_chunk *peer_init; @@ -1906,11 +1920,12 @@ nomem: * but a new tag of its own. */ /* This case represents an initialization collision. */ -static sctp_disposition_t sctp_sf_do_dupcook_c(struct net *net, +static enum sctp_disposition sctp_sf_do_dupcook_c( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands, + struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { /* The cookie should be silently discarded. @@ -1928,11 +1943,12 @@ static sctp_disposition_t sctp_sf_do_dupcook_c(struct net *net, * enter the ESTABLISHED state, if it has not already done so. */ /* This case represents an initialization collision. */ -static sctp_disposition_t sctp_sf_do_dupcook_d(struct net *net, +static enum sctp_disposition sctp_sf_do_dupcook_d( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands, + struct sctp_cmd_seq *commands, struct sctp_association *new_asoc) { struct sctp_ulpevent *ev = NULL, *ai_ev = NULL; @@ -2023,19 +2039,20 @@ nomem: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_5_2_4_dupcook(struct net *net, +enum sctp_disposition sctp_sf_do_5_2_4_dupcook( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { - sctp_disposition_t retval; - struct sctp_chunk *chunk = arg; struct sctp_association *new_asoc; + struct sctp_chunk *chunk = arg; + enum sctp_disposition retval; + struct sctp_chunk *err_chk_p; int error = 0; char action; - struct sctp_chunk *err_chk_p; /* Make sure that the chunk has a valid length from the protocol * perspective. In this case check to make sure we have at least @@ -2141,13 +2158,13 @@ nomem: * * See sctp_sf_do_9_1_abort(). */ -sctp_disposition_t sctp_sf_shutdown_pending_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_shutdown_pending_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -2184,12 +2201,13 @@ sctp_disposition_t sctp_sf_shutdown_pending_abort( * * See sctp_sf_do_9_1_abort(). */ -sctp_disposition_t sctp_sf_shutdown_sent_abort(struct net *net, +enum sctp_disposition sctp_sf_shutdown_sent_abort( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -2234,13 +2252,13 @@ sctp_disposition_t sctp_sf_shutdown_sent_abort(struct net *net, * * See sctp_sf_do_9_1_abort(). */ -sctp_disposition_t sctp_sf_shutdown_ack_sent_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_shutdown_ack_sent_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* The same T2 timer, so we should be able to use * common function with the SHUTDOWN-SENT state. @@ -2262,15 +2280,16 @@ sctp_disposition_t sctp_sf_shutdown_ack_sent_abort( * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_cookie_echoed_err(struct net *net, +enum sctp_disposition sctp_sf_cookie_echoed_err( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; - sctp_errhdr_t *err; + struct sctp_errhdr *err; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2278,7 +2297,7 @@ sctp_disposition_t sctp_sf_cookie_echoed_err(struct net *net, /* Make sure that the ERROR chunk has a valid length. * The parameter walking depends on this as well. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_operr_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_operr_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -2326,18 +2345,19 @@ sctp_disposition_t sctp_sf_cookie_echoed_err(struct net *net, * * The return value is the disposition of the chunk. */ -static sctp_disposition_t sctp_sf_do_5_2_6_stale(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_do_5_2_6_stale( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { int attempts = asoc->init_err_counter + 1; struct sctp_chunk *chunk = arg, *reply; struct sctp_cookie_preserve_param bht; struct sctp_bind_addr *bp; - sctp_errhdr_t *err; + struct sctp_errhdr *err; u32 stale; if (attempts > asoc->max_init_attempts) { @@ -2348,7 +2368,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(struct net *net, return SCTP_DISPOSITION_DELETE_TCB; } - err = (sctp_errhdr_t *)(chunk->skb->data); + err = (struct sctp_errhdr *)(chunk->skb->data); /* When calculating the time extension, an implementation * SHOULD use the RTT information measured based on the @@ -2364,7 +2384,7 @@ static sctp_disposition_t sctp_sf_do_5_2_6_stale(struct net *net, * to give ample time to retransmit the new cookie and thus * yield a higher probability of success on the reattempt. */ - stale = ntohl(*(__be32 *)((u8 *)err + sizeof(sctp_errhdr_t))); + stale = ntohl(*(__be32 *)((u8 *)err + sizeof(*err))); stale = (stale * 2) / 1000; bht.param_hdr.type = SCTP_PARAM_COOKIE_PRESERVATIVE; @@ -2448,12 +2468,13 @@ nomem: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_9_1_abort(struct net *net, +enum sctp_disposition sctp_sf_do_9_1_abort( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -2485,27 +2506,29 @@ sctp_disposition_t sctp_sf_do_9_1_abort(struct net *net, return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } -static sctp_disposition_t __sctp_sf_do_9_1_abort(struct net *net, +static enum sctp_disposition __sctp_sf_do_9_1_abort( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { + __be16 error = SCTP_ERROR_NO_ERROR; struct sctp_chunk *chunk = arg; unsigned int len; - __be16 error = SCTP_ERROR_NO_ERROR; /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { + struct sctp_errhdr *err; - sctp_errhdr_t *err; sctp_walk_errors(err, chunk->chunk_hdr); if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, + commands); - error = ((sctp_errhdr_t *)chunk->skb->data)->cause; + error = ((struct sctp_errhdr *)chunk->skb->data)->cause; } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); @@ -2522,16 +2545,17 @@ static sctp_disposition_t __sctp_sf_do_9_1_abort(struct net *net, * * See sctp_sf_do_9_1_abort() above. */ -sctp_disposition_t sctp_sf_cookie_wait_abort(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_cookie_wait_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { + __be16 error = SCTP_ERROR_NO_ERROR; struct sctp_chunk *chunk = arg; unsigned int len; - __be16 error = SCTP_ERROR_NO_ERROR; if (!sctp_vtag_verify_either(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2552,7 +2576,7 @@ sctp_disposition_t sctp_sf_cookie_wait_abort(struct net *net, /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) - error = ((sctp_errhdr_t *)chunk->skb->data)->cause; + error = ((struct sctp_errhdr *)chunk->skb->data)->cause; return sctp_stop_t1_and_abort(net, commands, error, ECONNREFUSED, asoc, chunk->transport); @@ -2561,12 +2585,13 @@ sctp_disposition_t sctp_sf_cookie_wait_abort(struct net *net, /* * Process an incoming ICMP as an ABORT. (COOKIE-WAIT state) */ -sctp_disposition_t sctp_sf_cookie_wait_icmp_abort(struct net *net, +enum sctp_disposition sctp_sf_cookie_wait_icmp_abort( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { return sctp_stop_t1_and_abort(net, commands, SCTP_ERROR_NO_ERROR, ENOPROTOOPT, asoc, @@ -2576,12 +2601,13 @@ sctp_disposition_t sctp_sf_cookie_wait_icmp_abort(struct net *net, /* * Process an ABORT. (COOKIE-ECHOED state) */ -sctp_disposition_t sctp_sf_cookie_echoed_abort(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_cookie_echoed_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* There is a single T1 timer, so we should be able to use * common function with the COOKIE-WAIT state. @@ -2594,11 +2620,12 @@ sctp_disposition_t sctp_sf_cookie_echoed_abort(struct net *net, * * This is common code called by several sctp_sf_*_abort() functions above. */ -static sctp_disposition_t sctp_stop_t1_and_abort(struct net *net, - sctp_cmd_seq_t *commands, - __be16 error, int sk_err, - const struct sctp_association *asoc, - struct sctp_transport *transport) +static enum sctp_disposition sctp_stop_t1_and_abort( + struct net *net, + struct sctp_cmd_seq *commands, + __be16 error, int sk_err, + const struct sctp_association *asoc, + struct sctp_transport *transport) { pr_debug("%s: ABORT received (INIT)\n", __func__); @@ -2648,16 +2675,17 @@ static sctp_disposition_t sctp_stop_t1_and_abort(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_9_2_shutdown(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_shutdown( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { + enum sctp_disposition disposition; struct sctp_chunk *chunk = arg; - sctp_shutdownhdr_t *sdh; - sctp_disposition_t disposition; + struct sctp_shutdownhdr *sdh; struct sctp_ulpevent *ev; __u32 ctsn; @@ -2665,14 +2693,13 @@ sctp_disposition_t sctp_sf_do_9_2_shutdown(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, - sizeof(struct sctp_shutdown_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_shutdown_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Convert the elaborate header. */ - sdh = (sctp_shutdownhdr_t *)chunk->skb->data; - skb_pull(chunk->skb, sizeof(sctp_shutdownhdr_t)); + sdh = (struct sctp_shutdownhdr *)chunk->skb->data; + skb_pull(chunk->skb, sizeof(*sdh)); chunk->subh.shutdown_hdr = sdh; ctsn = ntohl(sdh->cum_tsn_ack); @@ -2738,27 +2765,27 @@ out: * The Cumulative TSN Ack of the received SHUTDOWN chunk * MUST be processed. */ -sctp_disposition_t sctp_sf_do_9_2_shut_ctsn(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_shut_ctsn( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; - sctp_shutdownhdr_t *sdh; + struct sctp_shutdownhdr *sdh; __u32 ctsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, - sizeof(struct sctp_shutdown_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_shutdown_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - sdh = (sctp_shutdownhdr_t *)chunk->skb->data; + sdh = (struct sctp_shutdownhdr *)chunk->skb->data; ctsn = ntohl(sdh->cum_tsn_ack); if (TSN_lt(ctsn, asoc->ctsn_ack_point)) { @@ -2792,14 +2819,15 @@ sctp_disposition_t sctp_sf_do_9_2_shut_ctsn(struct net *net, * that belong to this association, it should discard the INIT chunk and * retransmit the SHUTDOWN ACK chunk. */ -sctp_disposition_t sctp_sf_do_9_2_reshutack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_reshutack( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = (struct sctp_chunk *) arg; + struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; /* Make sure that the chunk has a valid length */ @@ -2856,26 +2884,26 @@ nomem: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_ecn_cwr(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_ecn_cwr(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - sctp_cwrhdr_t *cwr; struct sctp_chunk *chunk = arg; + struct sctp_cwrhdr *cwr; u32 lowest_tsn; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_ecne_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_ecne_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - cwr = (sctp_cwrhdr_t *) chunk->skb->data; - skb_pull(chunk->skb, sizeof(sctp_cwrhdr_t)); + cwr = (struct sctp_cwrhdr *)chunk->skb->data; + skb_pull(chunk->skb, sizeof(*cwr)); lowest_tsn = ntohl(cwr->lowest_tsn); @@ -2912,25 +2940,24 @@ sctp_disposition_t sctp_sf_do_ecn_cwr(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_ecne(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_ecne(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { - sctp_ecnehdr_t *ecne; struct sctp_chunk *chunk = arg; + struct sctp_ecnehdr *ecne; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_ecne_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_ecne_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - ecne = (sctp_ecnehdr_t *) chunk->skb->data; - skb_pull(chunk->skb, sizeof(sctp_ecnehdr_t)); + ecne = (struct sctp_ecnehdr *)chunk->skb->data; + skb_pull(chunk->skb, sizeof(*ecne)); /* If this is a newer ECNE than the last CWR packet we sent out */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_ECNE, @@ -2969,15 +2996,15 @@ sctp_disposition_t sctp_sf_do_ecne(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_eat_data_6_2(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { + union sctp_arg force = SCTP_NOFORCE(); struct sctp_chunk *chunk = arg; - sctp_arg_t force = SCTP_NOFORCE(); int error; if (!sctp_vtag_verify(chunk, asoc)) { @@ -3089,12 +3116,13 @@ discard_noforce: * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_eat_data_fast_4_4( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; int error; @@ -3180,12 +3208,12 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_eat_sack_6_2(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_eat_sack_6_2(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_sackhdr *sackh; @@ -3254,12 +3282,13 @@ sctp_disposition_t sctp_sf_eat_sack_6_2(struct net *net, * * The return value is the disposition of the chunk. */ -static sctp_disposition_t sctp_sf_tabort_8_4_8(struct net *net, +static enum sctp_disposition sctp_sf_tabort_8_4_8( + struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; @@ -3304,21 +3333,21 @@ static sctp_disposition_t sctp_sf_tabort_8_4_8(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_operr_notify(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_operr_notify(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; - sctp_errhdr_t *err; + struct sctp_errhdr *err; if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the ERROR chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_operr_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_operr_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); sctp_walk_errors(err, chunk->chunk_hdr); @@ -3342,12 +3371,12 @@ sctp_disposition_t sctp_sf_operr_notify(struct net *net, * * The return value is the disposition. */ -sctp_disposition_t sctp_sf_do_9_2_final(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_final(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; @@ -3425,20 +3454,19 @@ nomem: * receiver of the OOTB packet shall discard the OOTB packet and take * no further action. */ -sctp_disposition_t sctp_sf_ootb(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_ootb(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sk_buff *skb = chunk->skb; struct sctp_chunkhdr *ch; - sctp_errhdr_t *err; - __u8 *ch_end; - int ootb_shut_ack = 0; + struct sctp_errhdr *err; int ootb_cookie_ack = 0; + int ootb_shut_ack = 0; + __u8 *ch_end; SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); @@ -3514,16 +3542,17 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, * (endpoint, asoc, type, arg, commands) * * Outputs - * (sctp_disposition_t) + * (enum sctp_disposition) * * The return value is the disposition of the chunk. */ -static sctp_disposition_t sctp_sf_shut_8_4_5(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_shut_8_4_5( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; @@ -3580,12 +3609,12 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(struct net *net, * chunks. --piggy ] * */ -sctp_disposition_t sctp_sf_do_8_5_1_E_sa(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -3605,17 +3634,18 @@ sctp_disposition_t sctp_sf_do_8_5_1_E_sa(struct net *net, } /* ADDIP Section 4.2 Upon reception of an ASCONF Chunk. */ -sctp_disposition_t sctp_sf_do_asconf(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_asconf(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = arg; - struct sctp_chunk *asconf_ack = NULL; - struct sctp_paramhdr *err_param = NULL; - sctp_addiphdr_t *hdr; - __u32 serial; + struct sctp_paramhdr *err_param = NULL; + struct sctp_chunk *asconf_ack = NULL; + struct sctp_chunk *chunk = arg; + struct sctp_addiphdr *hdr; + __u32 serial; if (!sctp_vtag_verify(chunk, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3630,14 +3660,15 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, * described in [I-D.ietf-tsvwg-sctp-auth]. */ if (!net->sctp.addip_noauth && !chunk->auth) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_discard_chunk(net, ep, asoc, type, arg, + commands); /* Make sure that the ASCONF ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_addip_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - hdr = (sctp_addiphdr_t *)chunk->skb->data; + hdr = (struct sctp_addiphdr *)chunk->skb->data; serial = ntohl(hdr->serial); /* Verify the ASCONF chunk before processing it. */ @@ -3721,18 +3752,19 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net, * When building TLV parameters for the ASCONF Chunk that will add or * delete IP addresses the D0 to D13 rules should be applied: */ -sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *asconf_ack = arg; - struct sctp_chunk *last_asconf = asoc->addip_last_asconf; - struct sctp_chunk *abort; - struct sctp_paramhdr *err_param = NULL; - sctp_addiphdr_t *addip_hdr; - __u32 sent_serial, rcvd_serial; + struct sctp_chunk *last_asconf = asoc->addip_last_asconf; + struct sctp_paramhdr *err_param = NULL; + struct sctp_chunk *asconf_ack = arg; + struct sctp_addiphdr *addip_hdr; + __u32 sent_serial, rcvd_serial; + struct sctp_chunk *abort; if (!sctp_vtag_verify(asconf_ack, asoc)) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG, @@ -3747,14 +3779,16 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, * described in [I-D.ietf-tsvwg-sctp-auth]. */ if (!net->sctp.addip_noauth && !asconf_ack->auth) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_discard_chunk(net, ep, asoc, type, arg, + commands); /* Make sure that the ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(asconf_ack, sizeof(sctp_addip_chunk_t))) + if (!sctp_chunk_length_valid(asconf_ack, + sizeof(struct sctp_addip_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); - addip_hdr = (sctp_addiphdr_t *)asconf_ack->skb->data; + addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data; rcvd_serial = ntohl(addip_hdr->serial); /* Verify the ASCONF-ACK chunk before processing it. */ @@ -3763,7 +3797,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, (void *)err_param, commands); if (last_asconf) { - addip_hdr = (sctp_addiphdr_t *)last_asconf->subh.addip_hdr; + addip_hdr = (struct sctp_addiphdr *)last_asconf->subh.addip_hdr; sent_serial = ntohl(addip_hdr->serial); } else { sent_serial = asoc->addip_serial - 1; @@ -3778,7 +3812,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, if (ADDIP_SERIAL_gte(rcvd_serial, sent_serial + 1) && !(asoc->addip_last_asconf)) { abort = sctp_make_abort(asoc, asconf_ack, - sizeof(sctp_errhdr_t)); + sizeof(struct sctp_errhdr)); if (abort) { sctp_init_cause(abort, SCTP_ERROR_ASCONF_ACK, 0); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, @@ -3814,7 +3848,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, } abort = sctp_make_abort(asoc, asconf_ack, - sizeof(sctp_errhdr_t)); + sizeof(struct sctp_errhdr)); if (abort) { sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, @@ -3837,11 +3871,12 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net, } /* RE-CONFIG Section 5.2 Upon reception of an RECONF Chunk. */ -sctp_disposition_t sctp_sf_do_reconf(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_reconf(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_paramhdr *err_param = NULL; struct sctp_chunk *chunk = arg; @@ -3913,15 +3948,15 @@ sctp_disposition_t sctp_sf_do_reconf(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_eat_fwd_tsn(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = arg; struct sctp_fwdtsn_hdr *fwdtsn_hdr; + struct sctp_chunk *chunk = arg; struct sctp_fwdtsn_skip *skip; __u16 len; __u32 tsn; @@ -3983,16 +4018,16 @@ discard_noforce: return SCTP_DISPOSITION_DISCARD; } -sctp_disposition_t sctp_sf_eat_fwd_tsn_fast( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_eat_fwd_tsn_fast( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = arg; struct sctp_fwdtsn_hdr *fwdtsn_hdr; + struct sctp_chunk *chunk = arg; struct sctp_fwdtsn_skip *skip; __u16 len; __u32 tsn; @@ -4075,23 +4110,23 @@ gen_shutdown: * * The return value is the disposition of the chunk. */ -static sctp_ierror_t sctp_sf_authenticate(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - struct sctp_chunk *chunk) +static enum sctp_ierror sctp_sf_authenticate( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + struct sctp_chunk *chunk) { struct sctp_authhdr *auth_hdr; + __u8 *save_digest, *digest; struct sctp_hmac *hmac; unsigned int sig_len; __u16 key_id; - __u8 *save_digest; - __u8 *digest; /* Pull in the auth header, so we can do some more verification */ auth_hdr = (struct sctp_authhdr *)chunk->skb->data; chunk->subh.auth_hdr = auth_hdr; - skb_pull(chunk->skb, sizeof(struct sctp_authhdr)); + skb_pull(chunk->skb, sizeof(*auth_hdr)); /* Make sure that we support the HMAC algorithm from the auth * chunk. @@ -4110,7 +4145,8 @@ static sctp_ierror_t sctp_sf_authenticate(struct net *net, /* Make sure that the length of the signature matches what * we expect. */ - sig_len = ntohs(chunk->chunk_hdr->length) - sizeof(sctp_auth_chunk_t); + sig_len = ntohs(chunk->chunk_hdr->length) - + sizeof(struct sctp_auth_chunk); hmac = sctp_auth_get_hmac(ntohs(auth_hdr->hmac_id)); if (sig_len != hmac->hmac_len) return SCTP_IERROR_PROTO_VIOLATION; @@ -4132,8 +4168,8 @@ static sctp_ierror_t sctp_sf_authenticate(struct net *net, memset(digest, 0, sig_len); sctp_auth_calculate_hmac(asoc, chunk->skb, - (struct sctp_auth_chunk *)chunk->chunk_hdr, - GFP_ATOMIC); + (struct sctp_auth_chunk *)chunk->chunk_hdr, + GFP_ATOMIC); /* Discard the packet if the digests do not match */ if (memcmp(save_digest, digest, sig_len)) { @@ -4149,17 +4185,16 @@ nomem: return SCTP_IERROR_NOMEM; } -sctp_disposition_t sctp_sf_eat_auth(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_eat_auth(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { - struct sctp_authhdr *auth_hdr; struct sctp_chunk *chunk = arg; + struct sctp_authhdr *auth_hdr; struct sctp_chunk *err_chunk; - sctp_ierror_t error; + enum sctp_ierror error; /* Make sure that the peer has AUTH capable */ if (!asoc->peer.auth_capable) @@ -4246,12 +4281,12 @@ sctp_disposition_t sctp_sf_eat_auth(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_unk_chunk(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_unk_chunk(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *unk_chunk = arg; struct sctp_chunk *err_chunk; @@ -4326,12 +4361,12 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_discard_chunk(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_discard_chunk(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -4366,12 +4401,11 @@ sctp_disposition_t sctp_sf_discard_chunk(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_pdiscard(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_pdiscard(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_DISCARDS); sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); @@ -4394,12 +4428,12 @@ sctp_disposition_t sctp_sf_pdiscard(struct net *net, * We simply tag the chunk as a violation. The state machine will log * the violation and continue. */ -sctp_disposition_t sctp_sf_violation(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_violation(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -4414,14 +4448,14 @@ sctp_disposition_t sctp_sf_violation(struct net *net, /* * Common function to handle a protocol violation. */ -static sctp_disposition_t sctp_sf_abort_violation( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - void *arg, - sctp_cmd_seq_t *commands, - const __u8 *payload, - const size_t paylen) +static enum sctp_disposition sctp_sf_abort_violation( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + void *arg, + struct sctp_cmd_seq *commands, + const __u8 *payload, + const size_t paylen) { struct sctp_packet *packet = NULL; struct sctp_chunk *chunk = arg; @@ -4531,18 +4565,18 @@ nomem: * * Generate an ABORT chunk and terminate the association. */ -static sctp_disposition_t sctp_sf_violation_chunklen( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_violation_chunklen( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { static const char err_str[] = "The following chunk had invalid length:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, - sizeof(err_str)); + sizeof(err_str)); } /* @@ -4551,17 +4585,17 @@ static sctp_disposition_t sctp_sf_violation_chunklen( * or accumulated length in multi parameters exceeds the end of the chunk, * the length is considered as invalid. */ -static sctp_disposition_t sctp_sf_violation_paramlen( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, void *ext, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_violation_paramlen( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, void *ext, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = arg; struct sctp_paramhdr *param = ext; struct sctp_chunk *abort = NULL; + struct sctp_chunk *chunk = arg; if (sctp_auth_recv_cid(SCTP_CID_ABORT, asoc)) goto discard; @@ -4594,18 +4628,18 @@ nomem: * We inform the other end by sending an ABORT with a Protocol Violation * error code. */ -static sctp_disposition_t sctp_sf_violation_ctsn( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_violation_ctsn( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { static const char err_str[] = "The cumulative tsn ack beyond the max tsn currently sent:"; return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, - sizeof(err_str)); + sizeof(err_str)); } /* Handle protocol violation of an invalid chunk bundling. For example, @@ -4614,13 +4648,13 @@ static sctp_disposition_t sctp_sf_violation_ctsn( * statement from the specs. Additionally, there might be an attacker * on the path and we may not want to continue this communication. */ -static sctp_disposition_t sctp_sf_violation_chunk( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static enum sctp_disposition sctp_sf_violation_chunk( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { static const char err_str[] = "The following chunk violates protocol:"; @@ -4628,7 +4662,7 @@ static sctp_disposition_t sctp_sf_violation_chunk( return sctp_sf_violation(net, ep, asoc, type, arg, commands); return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str, - sizeof(err_str)); + sizeof(err_str)); } /*************************************************************************** * These are the state functions for handling primitive (Section 10) events. @@ -4690,15 +4724,15 @@ static sctp_disposition_t sctp_sf_violation_chunk( * * The return value is a disposition. */ -sctp_disposition_t sctp_sf_do_prm_asoc(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_prm_asoc(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *repl; struct sctp_association *my_asoc; + struct sctp_chunk *repl; /* The comment below says that we enter COOKIE-WAIT AFTER * sending the INIT, but that doesn't actually work in our @@ -4802,12 +4836,12 @@ nomem: * * The return value is the disposition. */ -sctp_disposition_t sctp_sf_do_prm_send(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_prm_send(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_datamsg *msg = arg; @@ -4841,15 +4875,15 @@ sctp_disposition_t sctp_sf_do_prm_send(struct net *net, * * The return value is the disposition. */ -sctp_disposition_t sctp_sf_do_9_2_prm_shutdown( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_prm_shutdown( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - int disposition; + enum sctp_disposition disposition; /* From 9.2 Shutdown of an Association * Upon receipt of the SHUTDOWN primitive from its upper @@ -4867,6 +4901,7 @@ sctp_disposition_t sctp_sf_do_9_2_prm_shutdown( disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, arg, commands); } + return disposition; } @@ -4897,13 +4932,13 @@ sctp_disposition_t sctp_sf_do_9_2_prm_shutdown( * * The return value is the disposition. */ -sctp_disposition_t sctp_sf_do_9_1_prm_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_1_prm_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* From 9.1 Abort of an Association * Upon receipt of the ABORT primitive from its upper @@ -4935,12 +4970,12 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort( } /* We tried an illegal operation on an association which is closed. */ -sctp_disposition_t sctp_sf_error_closed(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_error_closed(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_ERROR, SCTP_ERROR(-EINVAL)); return SCTP_DISPOSITION_CONSUME; @@ -4949,12 +4984,13 @@ sctp_disposition_t sctp_sf_error_closed(struct net *net, /* We tried an illegal operation on an association which is shutting * down. */ -sctp_disposition_t sctp_sf_error_shutdown(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_error_shutdown( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_ERROR, SCTP_ERROR(-ESHUTDOWN)); @@ -4975,13 +5011,13 @@ sctp_disposition_t sctp_sf_error_shutdown(struct net *net, * Outputs * (timers) */ -sctp_disposition_t sctp_sf_cookie_wait_prm_shutdown( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_cookie_wait_prm_shutdown( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); @@ -5010,12 +5046,13 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_shutdown( * Outputs * (timers) */ -sctp_disposition_t sctp_sf_cookie_echoed_prm_shutdown( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_cookie_echoed_prm_shutdown( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* There is a single T1 timer, so we should be able to use * common function with the COOKIE-WAIT state. @@ -5037,13 +5074,13 @@ sctp_disposition_t sctp_sf_cookie_echoed_prm_shutdown( * Outputs * (timers) */ -sctp_disposition_t sctp_sf_cookie_wait_prm_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_cookie_wait_prm_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *abort = arg; @@ -5086,13 +5123,13 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort( * Outputs * (timers) */ -sctp_disposition_t sctp_sf_cookie_echoed_prm_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_cookie_echoed_prm_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* There is a single T1 timer, so we should be able to use * common function with the COOKIE-WAIT state. @@ -5112,13 +5149,13 @@ sctp_disposition_t sctp_sf_cookie_echoed_prm_abort( * Outputs * (timers) */ -sctp_disposition_t sctp_sf_shutdown_pending_prm_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_shutdown_pending_prm_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* Stop the T5-shutdown guard timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -5139,13 +5176,13 @@ sctp_disposition_t sctp_sf_shutdown_pending_prm_abort( * Outputs * (timers) */ -sctp_disposition_t sctp_sf_shutdown_sent_prm_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_shutdown_sent_prm_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -5170,13 +5207,13 @@ sctp_disposition_t sctp_sf_shutdown_sent_prm_abort( * Outputs * (timers) */ -sctp_disposition_t sctp_sf_shutdown_ack_sent_prm_abort( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_shutdown_ack_sent_prm_abort( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { /* The same T2 timer, so we should be able to use * common function with the SHUTDOWN-SENT state. @@ -5206,13 +5243,13 @@ sctp_disposition_t sctp_sf_shutdown_ack_sent_prm_abort( * o destination transport address - the transport address of the * association on which a heartbeat should be issued. */ -sctp_disposition_t sctp_sf_do_prm_requestheartbeat( +enum sctp_disposition sctp_sf_do_prm_requestheartbeat( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const sctp_subtype_t type, + const union sctp_subtype type, void *arg, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { if (SCTP_DISPOSITION_NOMEM == sctp_sf_heartbeat(ep, asoc, type, (struct sctp_transport *)arg, commands)) @@ -5239,12 +5276,12 @@ sctp_disposition_t sctp_sf_do_prm_requestheartbeat( * When an endpoint has an ASCONF signaled change to be sent to the * remote endpoint it should do A1 to A9 */ -sctp_disposition_t sctp_sf_do_prm_asconf(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_prm_asconf(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -5256,11 +5293,12 @@ sctp_disposition_t sctp_sf_do_prm_asconf(struct net *net, } /* RE-CONFIG Section 5.1 RECONF Chunk Procedures */ -sctp_disposition_t sctp_sf_do_prm_reconf(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_prm_reconf(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; @@ -5273,13 +5311,13 @@ sctp_disposition_t sctp_sf_do_prm_reconf(struct net *net, * * The return value is the disposition of the primitive. */ -sctp_disposition_t sctp_sf_ignore_primitive( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_ignore_primitive( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { pr_debug("%s: primitive type:%d is ignored\n", __func__, type.primitive); @@ -5297,13 +5335,13 @@ sctp_disposition_t sctp_sf_ignore_primitive( * subscribes to this event, if there is no data to be sent or * retransmit, the stack will immediately send up this notification. */ -sctp_disposition_t sctp_sf_do_no_pending_tsn( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_no_pending_tsn( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_ulpevent *event; @@ -5329,13 +5367,13 @@ sctp_disposition_t sctp_sf_do_no_pending_tsn( * * The return value is the disposition. */ -sctp_disposition_t sctp_sf_do_9_2_start_shutdown( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_start_shutdown( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *reply; @@ -5399,15 +5437,15 @@ nomem: * * The return value is the disposition. */ -sctp_disposition_t sctp_sf_do_9_2_shutdown_ack( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_9_2_shutdown_ack( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *chunk = (struct sctp_chunk *) arg; + struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; /* There are 2 ways of getting here: @@ -5419,12 +5457,14 @@ sctp_disposition_t sctp_sf_do_9_2_shutdown_ack( */ if (chunk) { if (!sctp_vtag_verify(chunk, asoc)) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, + commands); /* Make sure that the SHUTDOWN chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_shutdown_chunk_t))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + if (!sctp_chunk_length_valid( + chunk, sizeof(struct sctp_shutdown_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, + arg, commands); } /* If it has no more outstanding DATA chunks, the SHUTDOWN receiver @@ -5471,12 +5511,12 @@ nomem: * * The return value is the disposition of the event. */ -sctp_disposition_t sctp_sf_ignore_other(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_ignore_other(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { pr_debug("%s: the event other type:%d is ignored\n", __func__, type.other); @@ -5499,12 +5539,12 @@ sctp_disposition_t sctp_sf_ignore_other(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_do_6_3_3_rtx(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_6_3_3_rtx(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_transport *transport = arg; @@ -5587,12 +5627,12 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(struct net *net, * allow. However, an SCTP transmitter MUST NOT be more aggressive than * the following algorithms allow. */ -sctp_disposition_t sctp_sf_do_6_2_sack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_do_6_2_sack(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { SCTP_INC_STATS(net, SCTP_MIB_DELAY_SACK_EXPIREDS); sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_FORCE()); @@ -5618,16 +5658,17 @@ sctp_disposition_t sctp_sf_do_6_2_sack(struct net *net, * (timers, events) * */ -sctp_disposition_t sctp_sf_t1_init_timer_expire(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_t1_init_timer_expire( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { + int attempts = asoc->init_err_counter + 1; struct sctp_chunk *repl = NULL; struct sctp_bind_addr *bp; - int attempts = asoc->init_err_counter + 1; pr_debug("%s: timer T1 expired (INIT)\n", __func__); @@ -5682,15 +5723,16 @@ sctp_disposition_t sctp_sf_t1_init_timer_expire(struct net *net, * (timers, events) * */ -sctp_disposition_t sctp_sf_t1_cookie_timer_expire(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_t1_cookie_timer_expire( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - struct sctp_chunk *repl = NULL; int attempts = asoc->init_err_counter + 1; + struct sctp_chunk *repl = NULL; pr_debug("%s: timer T1 expired (COOKIE-ECHO)\n", __func__); @@ -5732,12 +5774,13 @@ sctp_disposition_t sctp_sf_t1_cookie_timer_expire(struct net *net, * the T2-Shutdown timer, giving its peer ample opportunity to transmit * all of its queued DATA chunks that have not yet been sent. */ -sctp_disposition_t sctp_sf_t2_timer_expire(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_t2_timer_expire( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *reply = NULL; @@ -5802,13 +5845,13 @@ nomem: * ADDIP Section 4.1 ASCONF CHunk Procedures * If the T4 RTO timer expires the endpoint should do B1 to B5 */ -sctp_disposition_t sctp_sf_t4_timer_expire( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_t4_timer_expire( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = asoc->addip_last_asconf; struct sctp_transport *transport = chunk->transport; @@ -5874,12 +5917,13 @@ sctp_disposition_t sctp_sf_t4_timer_expire( * At the expiration of this timer the sender SHOULD abort the association * by sending an ABORT chunk. */ -sctp_disposition_t sctp_sf_t5_timer_expire(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_t5_timer_expire( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *reply = NULL; @@ -5910,15 +5954,15 @@ nomem: * The work that needs to be done is same as when SHUTDOWN is initiated by * the user. So this routine looks same as sctp_sf_do_9_2_prm_shutdown(). */ -sctp_disposition_t sctp_sf_autoclose_timer_expire( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_autoclose_timer_expire( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { - int disposition; + enum sctp_disposition disposition; SCTP_INC_STATS(net, SCTP_MIB_AUTOCLOSE_EXPIREDS); @@ -5938,6 +5982,7 @@ sctp_disposition_t sctp_sf_autoclose_timer_expire( disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, arg, commands); } + return disposition; } @@ -5953,12 +5998,11 @@ sctp_disposition_t sctp_sf_autoclose_timer_expire( * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_not_impl(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_not_impl(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { return SCTP_DISPOSITION_NOT_IMPL; } @@ -5971,12 +6015,11 @@ sctp_disposition_t sctp_sf_not_impl(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_bug(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_bug(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, struct sctp_cmd_seq *commands) { return SCTP_DISPOSITION_BUG; } @@ -5992,12 +6035,12 @@ sctp_disposition_t sctp_sf_bug(struct net *net, * * The return value is the disposition of the chunk. */ -sctp_disposition_t sctp_sf_timer_ignore(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +enum sctp_disposition sctp_sf_timer_ignore(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) { pr_debug("%s: timer %d ignored\n", __func__, type.chunk); @@ -6012,9 +6055,9 @@ sctp_disposition_t sctp_sf_timer_ignore(struct net *net, static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk) { struct sctp_sackhdr *sack; + __u16 num_dup_tsns; unsigned int len; __u16 num_blocks; - __u16 num_dup_tsns; /* Protect ourselves from reading too far into * the skb from a bogus sender. @@ -6036,12 +6079,12 @@ static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk) /* Create an ABORT packet to be sent as a response, with the specified * error causes. */ -static struct sctp_packet *sctp_abort_pkt_new(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - struct sctp_chunk *chunk, - const void *payload, - size_t paylen) +static struct sctp_packet *sctp_abort_pkt_new( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + struct sctp_chunk *chunk, + const void *payload, size_t paylen) { struct sctp_packet *packet; struct sctp_chunk *abort; @@ -6078,14 +6121,14 @@ static struct sctp_packet *sctp_abort_pkt_new(struct net *net, } /* Allocate a packet for responding in the OOTB conditions. */ -static struct sctp_packet *sctp_ootb_pkt_new(struct net *net, - const struct sctp_association *asoc, - const struct sctp_chunk *chunk) +static struct sctp_packet *sctp_ootb_pkt_new( + struct net *net, + const struct sctp_association *asoc, + const struct sctp_chunk *chunk) { - struct sctp_packet *packet; struct sctp_transport *transport; - __u16 sport; - __u16 dport; + struct sctp_packet *packet; + __u16 sport, dport; __u32 vtag; /* Get the source and destination port from the inbound packet. */ @@ -6163,7 +6206,7 @@ static void sctp_send_stale_cookie_err(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands, + struct sctp_cmd_seq *commands, struct sctp_chunk *err_chunk) { struct sctp_packet *packet; @@ -6192,20 +6235,19 @@ static void sctp_send_stale_cookie_err(struct net *net, /* Process a data chunk */ static int sctp_eat_data(const struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_cmd_seq_t *commands) + struct sctp_cmd_seq *commands) { - struct sctp_datahdr *data_hdr; - struct sctp_chunk *err; - size_t datalen; - sctp_verb_t deliver; - int tmp; - __u32 tsn; struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); - u16 ssn; - u16 sid; + struct sctp_datahdr *data_hdr; + struct sctp_chunk *err; + enum sctp_verb deliver; + size_t datalen; u8 ordered = 0; + u16 ssn, sid; + __u32 tsn; + int tmp; data_hdr = (struct sctp_datahdr *)chunk->skb->data; chunk->subh.data_hdr = data_hdr; diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 3e958c1c4b95..79b6bee5b768 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -45,26 +45,27 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> -static const sctp_sm_table_entry_t +static const struct sctp_sm_table_entry primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES]; -static const sctp_sm_table_entry_t +static const struct sctp_sm_table_entry other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES]; -static const sctp_sm_table_entry_t +static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES]; -static const sctp_sm_table_entry_t *sctp_chunk_event_lookup(struct net *net, - enum sctp_cid cid, - sctp_state_t state); +static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( + struct net *net, + enum sctp_cid cid, + enum sctp_state state); -static const sctp_sm_table_entry_t bug = { +static const struct sctp_sm_table_entry bug = { .fn = sctp_sf_bug, .name = "sctp_sf_bug" }; #define DO_LOOKUP(_max, _type, _table) \ ({ \ - const sctp_sm_table_entry_t *rtn; \ + const struct sctp_sm_table_entry *rtn; \ \ if ((event_subtype._type > (_max))) { \ pr_warn("table %p possible attack: event %d exceeds max %d\n", \ @@ -76,10 +77,11 @@ static const sctp_sm_table_entry_t bug = { rtn; \ }) -const sctp_sm_table_entry_t *sctp_sm_lookup_event(struct net *net, - sctp_event_t event_type, - sctp_state_t state, - sctp_subtype_t event_subtype) +const struct sctp_sm_table_entry *sctp_sm_lookup_event( + struct net *net, + enum sctp_event event_type, + enum sctp_state state, + union sctp_subtype event_subtype) { switch (event_type) { case SCTP_EVENT_T_CHUNK: @@ -392,7 +394,8 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(struct net *net, * * For base protocol (RFC 2960). */ -static const sctp_sm_table_entry_t chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_DATA, TYPE_SCTP_INIT, TYPE_SCTP_INIT_ACK, @@ -451,7 +454,8 @@ static const sctp_sm_table_entry_t chunk_event_table[SCTP_NUM_BASE_CHUNK_TYPES][ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ -static const sctp_sm_table_entry_t addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_ASCONF, TYPE_SCTP_ASCONF_ACK, }; /*state_fn_t addip_chunk_event_table[][] */ @@ -478,7 +482,8 @@ static const sctp_sm_table_entry_t addip_chunk_event_table[SCTP_NUM_ADDIP_CHUNK_ /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ -static const sctp_sm_table_entry_t prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FWD_TSN, }; /*state_fn_t prsctp_chunk_event_table[][] */ @@ -504,7 +509,8 @@ static const sctp_sm_table_entry_t prsctp_chunk_event_table[SCTP_NUM_PRSCTP_CHUN /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ -static const sctp_sm_table_entry_t reconf_chunk_event_table[SCTP_NUM_RECONF_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +reconf_chunk_event_table[SCTP_NUM_RECONF_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_RECONF, }; /*state_fn_t reconf_chunk_event_table[][] */ @@ -530,11 +536,12 @@ static const sctp_sm_table_entry_t reconf_chunk_event_table[SCTP_NUM_RECONF_CHUN /* The primary index for this table is the chunk type. * The secondary index for this table is the state. */ -static const sctp_sm_table_entry_t auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_AUTH, }; /*state_fn_t auth_chunk_event_table[][] */ -static const sctp_sm_table_entry_t +static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), @@ -691,7 +698,8 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* The primary index for this table is the primitive type. * The secondary index for this table is the state. */ -static const sctp_sm_table_entry_t primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +primitive_event_table[SCTP_NUM_PRIMITIVE_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_PRIMITIVE_ASSOCIATE, TYPE_SCTP_PRIMITIVE_SHUTDOWN, TYPE_SCTP_PRIMITIVE_ABORT, @@ -739,7 +747,8 @@ static const sctp_sm_table_entry_t primitive_event_table[SCTP_NUM_PRIMITIVE_TYPE TYPE_SCTP_FUNC(sctp_sf_ignore_other), \ } -static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_OTHER_NO_PENDING_TSN, TYPE_SCTP_OTHER_ICMP_PROTO_UNREACH, }; @@ -953,7 +962,8 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } -static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { +static const struct sctp_sm_table_entry +timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE, TYPE_SCTP_EVENT_TIMEOUT_T1_INIT, @@ -967,9 +977,10 @@ static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][S TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; -static const sctp_sm_table_entry_t *sctp_chunk_event_lookup(struct net *net, - enum sctp_cid cid, - sctp_state_t state) +static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( + struct net *net, + enum sctp_cid cid, + enum sctp_state state) { if (state > SCTP_STATE_MAX) return &bug; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1db478e34520..c01af72cc603 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -100,8 +100,9 @@ static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk); static int sctp_do_bind(struct sock *, union sctp_addr *, int); static int sctp_autobind(struct sock *sk); -static void sctp_sock_migrate(struct sock *, struct sock *, - struct sctp_association *, sctp_socket_type_t); +static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, + struct sctp_association *assoc, + enum sctp_socket_type type); static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; @@ -1055,7 +1056,7 @@ static int __sctp_connect(struct sock *sk, struct sctp_association *asoc2; struct sctp_transport *transport; union sctp_addr to; - sctp_scope_t scope; + enum sctp_scope scope; long timeo; int err = 0; int addrcnt = 0; @@ -1593,7 +1594,8 @@ static int sctp_error(struct sock *sk, int flags, int err) */ /* BUG: We do not implement the equivalent of sk_stream_wait_memory(). */ -static int sctp_msghdr_parse(const struct msghdr *, sctp_cmsgs_t *); +static int sctp_msghdr_parse(const struct msghdr *msg, + struct sctp_cmsgs *cmsgs); static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) { @@ -1609,8 +1611,8 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_sndrcvinfo *sinfo; struct sctp_initmsg *sinit; sctp_assoc_t associd = 0; - sctp_cmsgs_t cmsgs = { NULL }; - sctp_scope_t scope; + struct sctp_cmsgs cmsgs = { NULL }; + enum sctp_scope scope; bool fill_sinfo_ttl = false, wait_connect = false; struct sctp_datamsg *datamsg; int msg_flags = msg->msg_flags; @@ -7445,10 +7447,10 @@ static int sctp_autobind(struct sock *sk) * msg_control * points here */ -static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) +static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs) { - struct cmsghdr *cmsg; struct msghdr *my_msg = (struct msghdr *)msg; + struct cmsghdr *cmsg; for_each_cmsghdr(cmsg, my_msg) { if (!CMSG_OK(my_msg, cmsg)) @@ -8085,7 +8087,7 @@ static inline void sctp_copy_descendant(struct sock *sk_to, */ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_association *assoc, - sctp_socket_type_t type) + enum sctp_socket_type type) { struct sctp_sock *oldsp = sctp_sk(oldsk); struct sctp_sock *newsp = sctp_sk(newsk); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 0e732f68c2bf..ef7ca44d6e6a 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -46,7 +46,7 @@ static int timer_max = 86400000; /* ms in one day */ static int int_max = INT_MAX; static int sack_timer_min = 1; static int sack_timer_max = 500; -static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ +static int addr_scope_max = SCTP_SCOPE_POLICY_MAX; static int rwnd_scale_max = 16; static int rto_alpha_min = 0; static int rto_beta_min = 0; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 80a97c8501a7..2d9bd3776bc8 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -490,7 +490,7 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, * detected. */ void sctp_transport_lower_cwnd(struct sctp_transport *transport, - sctp_lower_cwnd_t reason) + enum sctp_lower_cwnd reason) { struct sctp_association *asoc = transport->asoc; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 5f86c5062a98..67abc0194f30 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -371,19 +371,19 @@ sctp_ulpevent_make_remote_error(const struct sctp_association *asoc, struct sctp_chunk *chunk, __u16 flags, gfp_t gfp) { - struct sctp_ulpevent *event; struct sctp_remote_error *sre; + struct sctp_ulpevent *event; + struct sctp_errhdr *ch; struct sk_buff *skb; - sctp_errhdr_t *ch; __be16 cause; int elen; - ch = (sctp_errhdr_t *)(chunk->skb->data); + ch = (struct sctp_errhdr *)(chunk->skb->data); cause = ch->cause; - elen = SCTP_PAD4(ntohs(ch->length)) - sizeof(sctp_errhdr_t); + elen = SCTP_PAD4(ntohs(ch->length)) - sizeof(*ch); /* Pull off the ERROR header. */ - skb_pull(chunk->skb, sizeof(sctp_errhdr_t)); + skb_pull(chunk->skb, sizeof(*ch)); /* Copy the skb to a new skb with room for us to prepend * notification with. diff --git a/net/socket.c b/net/socket.c index b332d1e8e4e4..c729625eb5d3 100644 --- a/net/socket.c +++ b/net/socket.c @@ -658,7 +658,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct socket *sock = sk->sk_socket; if (!sock->ops->sendmsg_locked) - sock_no_sendmsg_locked(sk, msg, size); + return sock_no_sendmsg_locked(sk, msg, size); iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 0d18fbc6f870..434aa6637a52 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -373,6 +373,9 @@ static int strp_read_sock(struct strparser *strp) struct socket *sock = strp->sk->sk_socket; read_descriptor_t desc; + if (unlikely(!sock || !sock->ops || !sock->ops->read_sock)) + return -EBUSY; + desc.arg.data = strp; desc.error = 0; desc.count = 1; /* give more than one skb per call */ @@ -486,12 +489,7 @@ int strp_init(struct strparser *strp, struct sock *sk, * The upper layer calls strp_process for each skb to be parsed. */ - if (sk) { - struct socket *sock = sk->sk_socket; - - if (!sock->ops->read_sock || !sock->ops->peek_len) - return -EAFNOSUPPORT; - } else { + if (!sk) { if (!cb->lock || !cb->unlock) return -EINVAL; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 25dc67ef9d37..0531b41d1f2d 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -343,8 +343,6 @@ static size_t switchdev_obj_size(const struct switchdev_obj *obj) switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: return sizeof(struct switchdev_obj_port_vlan); - case SWITCHDEV_OBJ_ID_PORT_FDB: - return sizeof(struct switchdev_obj_port_fdb); case SWITCHDEV_OBJ_ID_PORT_MDB: return sizeof(struct switchdev_obj_port_mdb); default: @@ -534,43 +532,6 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); -/** - * switchdev_port_obj_dump - Dump port objects - * - * @dev: port device - * @id: object ID - * @obj: object to dump - * @cb: function to call with a filled object - * - * rtnl_lock must be held. - */ -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, - switchdev_obj_dump_cb_t *cb) -{ - const struct switchdev_ops *ops = dev->switchdev_ops; - struct net_device *lower_dev; - struct list_head *iter; - int err = -EOPNOTSUPP; - - ASSERT_RTNL(); - - if (ops && ops->switchdev_port_obj_dump) - return ops->switchdev_port_obj_dump(dev, obj, cb); - - /* Switch device port(s) may be stacked under - * bond/team/vlan dev, so recurse down to dump objects on - * first port at bottom of stack. - */ - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_dump(lower_dev, obj, cb); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); - static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); /** @@ -613,486 +574,6 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); -struct switchdev_vlan_dump { - struct switchdev_obj_port_vlan vlan; - struct sk_buff *skb; - u32 filter_mask; - u16 flags; - u16 begin; - u16 end; -}; - -static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump) -{ - struct bridge_vlan_info vinfo; - - vinfo.flags = dump->flags; - - if (dump->begin == 0 && dump->end == 0) { - return 0; - } else if (dump->begin == dump->end) { - vinfo.vid = dump->begin; - if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO, - sizeof(vinfo), &vinfo)) - return -EMSGSIZE; - } else { - vinfo.vid = dump->begin; - vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; - if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO, - sizeof(vinfo), &vinfo)) - return -EMSGSIZE; - vinfo.vid = dump->end; - vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN; - vinfo.flags |= BRIDGE_VLAN_INFO_RANGE_END; - if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO, - sizeof(vinfo), &vinfo)) - return -EMSGSIZE; - } - - return 0; -} - -static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj) -{ - struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); - struct switchdev_vlan_dump *dump = - container_of(vlan, struct switchdev_vlan_dump, vlan); - int err = 0; - - if (vlan->vid_begin > vlan->vid_end) - return -EINVAL; - - if (dump->filter_mask & RTEXT_FILTER_BRVLAN) { - dump->flags = vlan->flags; - for (dump->begin = dump->end = vlan->vid_begin; - dump->begin <= vlan->vid_end; - dump->begin++, dump->end++) { - err = switchdev_port_vlan_dump_put(dump); - if (err) - return err; - } - } else if (dump->filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) { - if (dump->begin > vlan->vid_begin && - dump->begin >= vlan->vid_end) { - if ((dump->begin - 1) == vlan->vid_end && - dump->flags == vlan->flags) { - /* prepend */ - dump->begin = vlan->vid_begin; - } else { - err = switchdev_port_vlan_dump_put(dump); - dump->flags = vlan->flags; - dump->begin = vlan->vid_begin; - dump->end = vlan->vid_end; - } - } else if (dump->end <= vlan->vid_begin && - dump->end < vlan->vid_end) { - if ((dump->end + 1) == vlan->vid_begin && - dump->flags == vlan->flags) { - /* append */ - dump->end = vlan->vid_end; - } else { - err = switchdev_port_vlan_dump_put(dump); - dump->flags = vlan->flags; - dump->begin = vlan->vid_begin; - dump->end = vlan->vid_end; - } - } else { - err = -EINVAL; - } - } - - return err; -} - -static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, - u32 filter_mask) -{ - struct switchdev_vlan_dump dump = { - .vlan.obj.orig_dev = dev, - .vlan.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .skb = skb, - .filter_mask = filter_mask, - }; - int err = 0; - - if ((filter_mask & RTEXT_FILTER_BRVLAN) || - (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - err = switchdev_port_obj_dump(dev, &dump.vlan.obj, - switchdev_port_vlan_dump_cb); - if (err) - goto err_out; - if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) - /* last one */ - err = switchdev_port_vlan_dump_put(&dump); - } - -err_out: - return err == -EOPNOTSUPP ? 0 : err; -} - -/** - * switchdev_port_bridge_getlink - Get bridge port attributes - * - * @dev: port device - * - * Called for SELF on rtnl_bridge_getlink to get bridge port - * attributes. - */ -int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask, - int nlflags) -{ - struct switchdev_attr attr = { - .orig_dev = dev, - .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, - }; - u16 mode = BRIDGE_MODE_UNDEF; - u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD; - int err; - - if (!netif_is_bridge_port(dev)) - return -EOPNOTSUPP; - - err = switchdev_port_attr_get(dev, &attr); - if (err && err != -EOPNOTSUPP) - return err; - - return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, - attr.u.brport_flags, mask, nlflags, - filter_mask, switchdev_port_vlan_fill); -} -EXPORT_SYMBOL_GPL(switchdev_port_bridge_getlink); - -static int switchdev_port_br_setflag(struct net_device *dev, - struct nlattr *nlattr, - unsigned long brport_flag) -{ - struct switchdev_attr attr = { - .orig_dev = dev, - .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, - }; - u8 flag = nla_get_u8(nlattr); - int err; - - err = switchdev_port_attr_get(dev, &attr); - if (err) - return err; - - if (flag) - attr.u.brport_flags |= brport_flag; - else - attr.u.brport_flags &= ~brport_flag; - - return switchdev_port_attr_set(dev, &attr); -} - -static const struct nla_policy -switchdev_port_bridge_policy[IFLA_BRPORT_MAX + 1] = { - [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, - [IFLA_BRPORT_COST] = { .type = NLA_U32 }, - [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, - [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, - [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, - [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, - [IFLA_BRPORT_FAST_LEAVE] = { .type = NLA_U8 }, - [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, - [IFLA_BRPORT_LEARNING_SYNC] = { .type = NLA_U8 }, - [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, -}; - -static int switchdev_port_br_setlink_protinfo(struct net_device *dev, - struct nlattr *protinfo) -{ - struct nlattr *attr; - int rem; - int err; - - err = nla_validate_nested(protinfo, IFLA_BRPORT_MAX, - switchdev_port_bridge_policy, NULL); - if (err) - return err; - - nla_for_each_nested(attr, protinfo, rem) { - switch (nla_type(attr)) { - case IFLA_BRPORT_LEARNING: - err = switchdev_port_br_setflag(dev, attr, - BR_LEARNING); - break; - case IFLA_BRPORT_LEARNING_SYNC: - err = switchdev_port_br_setflag(dev, attr, - BR_LEARNING_SYNC); - break; - case IFLA_BRPORT_UNICAST_FLOOD: - err = switchdev_port_br_setflag(dev, attr, BR_FLOOD); - break; - default: - err = -EOPNOTSUPP; - break; - } - if (err) - return err; - } - - return 0; -} - -static int switchdev_port_br_afspec(struct net_device *dev, - struct nlattr *afspec, - int (*f)(struct net_device *dev, - const struct switchdev_obj *obj)) -{ - struct nlattr *attr; - struct bridge_vlan_info *vinfo; - struct switchdev_obj_port_vlan vlan = { - .obj.orig_dev = dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - }; - int rem; - int err; - - nla_for_each_nested(attr, afspec, rem) { - if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO) - continue; - if (nla_len(attr) != sizeof(struct bridge_vlan_info)) - return -EINVAL; - vinfo = nla_data(attr); - if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) - return -EINVAL; - vlan.flags = vinfo->flags; - if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { - if (vlan.vid_begin) - return -EINVAL; - vlan.vid_begin = vinfo->vid; - /* don't allow range of pvids */ - if (vlan.flags & BRIDGE_VLAN_INFO_PVID) - return -EINVAL; - } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { - if (!vlan.vid_begin) - return -EINVAL; - vlan.vid_end = vinfo->vid; - if (vlan.vid_end <= vlan.vid_begin) - return -EINVAL; - err = f(dev, &vlan.obj); - if (err) - return err; - vlan.vid_begin = 0; - } else { - if (vlan.vid_begin) - return -EINVAL; - vlan.vid_begin = vinfo->vid; - vlan.vid_end = vinfo->vid; - err = f(dev, &vlan.obj); - if (err) - return err; - vlan.vid_begin = 0; - } - } - - return 0; -} - -/** - * switchdev_port_bridge_setlink - Set bridge port attributes - * - * @dev: port device - * @nlh: netlink header - * @flags: netlink flags - * - * Called for SELF on rtnl_bridge_setlink to set bridge port - * attributes. - */ -int switchdev_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) -{ - struct nlattr *protinfo; - struct nlattr *afspec; - int err = 0; - - if (!netif_is_bridge_port(dev)) - return -EOPNOTSUPP; - - protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), - IFLA_PROTINFO); - if (protinfo) { - err = switchdev_port_br_setlink_protinfo(dev, protinfo); - if (err) - return err; - } - - afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), - IFLA_AF_SPEC); - if (afspec) - err = switchdev_port_br_afspec(dev, afspec, - switchdev_port_obj_add); - - return err; -} -EXPORT_SYMBOL_GPL(switchdev_port_bridge_setlink); - -/** - * switchdev_port_bridge_dellink - Set bridge port attributes - * - * @dev: port device - * @nlh: netlink header - * @flags: netlink flags - * - * Called for SELF on rtnl_bridge_dellink to set bridge port - * attributes. - */ -int switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) -{ - struct nlattr *afspec; - - if (!netif_is_bridge_port(dev)) - return -EOPNOTSUPP; - - afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), - IFLA_AF_SPEC); - if (afspec) - return switchdev_port_br_afspec(dev, afspec, - switchdev_port_obj_del); - - return 0; -} -EXPORT_SYMBOL_GPL(switchdev_port_bridge_dellink); - -/** - * switchdev_port_fdb_add - Add FDB (MAC/VLAN) entry to port - * - * @ndmsg: netlink hdr - * @nlattr: netlink attributes - * @dev: port device - * @addr: MAC address to add - * @vid: VLAN to add - * - * Add FDB entry to switch device. - */ -int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, const unsigned char *addr, - u16 vid, u16 nlm_flags) -{ - struct switchdev_obj_port_fdb fdb = { - .obj.orig_dev = dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .vid = vid, - }; - - ether_addr_copy(fdb.addr, addr); - return switchdev_port_obj_add(dev, &fdb.obj); -} -EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); - -/** - * switchdev_port_fdb_del - Delete FDB (MAC/VLAN) entry from port - * - * @ndmsg: netlink hdr - * @nlattr: netlink attributes - * @dev: port device - * @addr: MAC address to delete - * @vid: VLAN to delete - * - * Delete FDB entry from switch device. - */ -int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, const unsigned char *addr, - u16 vid) -{ - struct switchdev_obj_port_fdb fdb = { - .obj.orig_dev = dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .vid = vid, - }; - - ether_addr_copy(fdb.addr, addr); - return switchdev_port_obj_del(dev, &fdb.obj); -} -EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); - -struct switchdev_fdb_dump { - struct switchdev_obj_port_fdb fdb; - struct net_device *dev; - struct sk_buff *skb; - struct netlink_callback *cb; - int idx; -}; - -static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj) -{ - struct switchdev_obj_port_fdb *fdb = SWITCHDEV_OBJ_PORT_FDB(obj); - struct switchdev_fdb_dump *dump = - container_of(fdb, struct switchdev_fdb_dump, fdb); - u32 portid = NETLINK_CB(dump->cb->skb).portid; - u32 seq = dump->cb->nlh->nlmsg_seq; - struct nlmsghdr *nlh; - struct ndmsg *ndm; - - if (dump->idx < dump->cb->args[2]) - goto skip; - - nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, - sizeof(*ndm), NLM_F_MULTI); - if (!nlh) - return -EMSGSIZE; - - ndm = nlmsg_data(nlh); - ndm->ndm_family = AF_BRIDGE; - ndm->ndm_pad1 = 0; - ndm->ndm_pad2 = 0; - ndm->ndm_flags = NTF_SELF; - ndm->ndm_type = 0; - ndm->ndm_ifindex = dump->dev->ifindex; - ndm->ndm_state = fdb->ndm_state; - - if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, fdb->addr)) - goto nla_put_failure; - - if (fdb->vid && nla_put_u16(dump->skb, NDA_VLAN, fdb->vid)) - goto nla_put_failure; - - nlmsg_end(dump->skb, nlh); - -skip: - dump->idx++; - return 0; - -nla_put_failure: - nlmsg_cancel(dump->skb, nlh); - return -EMSGSIZE; -} - -/** - * switchdev_port_fdb_dump - Dump port FDB (MAC/VLAN) entries - * - * @skb: netlink skb - * @cb: netlink callback - * @dev: port device - * @filter_dev: filter device - * @idx: - * - * Dump FDB entries from switch device. - */ -int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, - struct net_device *filter_dev, int *idx) -{ - struct switchdev_fdb_dump dump = { - .fdb.obj.orig_dev = dev, - .fdb.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB, - .dev = dev, - .skb = skb, - .cb = cb, - .idx = *idx, - }; - int err; - - err = switchdev_port_obj_dump(dev, &dump.fdb.obj, - switchdev_port_fdb_dump_cb); - *idx = dump.idx; - return err; -} -EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); - bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index d174ee3254ee..767e0537dde5 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -596,7 +596,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, rcu_read_lock(); b = rcu_dereference_rtnl(dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && - (skb->pkt_type <= PACKET_BROADCAST))) { + (skb->pkt_type <= PACKET_MULTICAST))) { skb->next = NULL; tipc_rcv(dev_net(dev), skb, b); rcu_read_unlock(); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index ab3087687a32..dcd90e6fa7c3 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -513,6 +513,7 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) /* Now reverse the concerned fields */ msg_set_errcode(hdr, err); + msg_set_non_seq(hdr, 0); msg_set_origport(hdr, msg_destport(&ohdr)); msg_set_destport(hdr, msg_origport(&ohdr)); msg_set_destnode(hdr, msg_prevnode(&ohdr)); diff --git a/net/tipc/node.c b/net/tipc/node.c index aeef8011ac7d..9b4dcb6a16b5 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1455,10 +1455,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, /* Initiate synch mode if applicable */ if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { syncpt = iseqno + exp_pkts - 1; - if (!tipc_link_is_up(l)) { - tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!tipc_link_is_up(l)) __tipc_node_link_up(n, bearer_id, xmitq); - } if (n->state == SELF_UP_PEER_UP) { n->sync_point = syncpt; tipc_link_fsm_evt(l, LINK_SYNCH_BEGIN_EVT); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5a1a98df3499..ac095936552d 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -74,7 +74,7 @@ DEFINE_RWLOCK(x25_list_lock); static const struct proto_ops x25_proto_ops; -static struct x25_address null_x25_address = {" "}; +static const struct x25_address null_x25_address = {" "}; #ifdef CONFIG_COMPAT struct compat_x25_subscrip_struct { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1de52f36caf5..cc0d783ccbad 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1819,7 +1819,8 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, xdst->num_pols == num_pols && !xfrm_pol_dead(xdst) && memcmp(xdst->pols, pols, - sizeof(struct xfrm_policy *) * num_pols) == 0) { + sizeof(struct xfrm_policy *) * num_pols) == 0 && + xfrm_bundle_ok(xdst)) { dst_hold(&xdst->u.dst); return xdst; } |