diff options
Diffstat (limited to 'net')
289 files changed, 4492 insertions, 2800 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 546af0e73ac3..fce3b7eebffb 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -368,10 +368,12 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ifrr.ifr_ifru = ifr->ifr_ifru; switch (cmd) { + case SIOCSHWTSTAMP: + if (!net_eq(dev_net(dev), &init_net)) + break; case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - case SIOCSHWTSTAMP: case SIOCGHWTSTAMP: if (netif_device_present(real_dev) && ops->ndo_do_ioctl) err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); diff --git a/net/9p/client.c b/net/9p/client.c index deae53a7dffc..23ec6187dc07 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -181,6 +181,12 @@ static int parse_opts(char *opts, struct p9_client *clnt) ret = r; continue; } + if (option < 4096) { + p9_debug(P9_DEBUG_ERROR, + "msize should be at least 4k\n"); + ret = -EINVAL; + continue; + } clnt->msize = option; break; case Opt_trans: @@ -993,10 +999,18 @@ static int p9_client_version(struct p9_client *c) else if (!strncmp(version, "9P2000", 6)) c->proto_version = p9_proto_legacy; else { + p9_debug(P9_DEBUG_ERROR, + "server returned an unknown version: %s\n", version); err = -EREMOTEIO; goto error; } + if (msize < 4096) { + p9_debug(P9_DEBUG_ERROR, + "server returned a msize < 4096: %d\n", msize); + err = -EREMOTEIO; + goto error; + } if (msize < c->msize) c->msize = msize; @@ -1055,6 +1069,13 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) if (clnt->msize > clnt->trans_mod->maxsize) clnt->msize = clnt->trans_mod->maxsize; + if (clnt->msize < 4096) { + p9_debug(P9_DEBUG_ERROR, + "Please specify a msize of at least 4k\n"); + err = -EINVAL; + goto close_trans; + } + err = p9_client_version(clnt); if (err) goto close_trans; diff --git a/net/9p/protocol.c b/net/9p/protocol.c index ee32bbf12675..b4d80c533f89 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -571,9 +571,10 @@ int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st) if (ret) { p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret); trace_9p_protocol_dump(clnt, &fake_pdu); + return ret; } - return ret; + return fake_pdu.offset; } EXPORT_SYMBOL(p9stat_read); diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index 8006295f8bd7..dda73991bb54 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -255,7 +255,7 @@ out_interface: goto out; } -void __exit atalk_proc_exit(void) +void atalk_proc_exit(void) { remove_proc_entry("interface", atalk_proc_dir); remove_proc_entry("route", atalk_proc_dir); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 9b6bc5abe946..795fbc6c06aa 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1910,12 +1910,16 @@ static const char atalk_err_snap[] __initconst = /* Called by proto.c on kernel start up */ static int __init atalk_init(void) { - int rc = proto_register(&ddp_proto, 0); + int rc; - if (rc != 0) + rc = proto_register(&ddp_proto, 0); + if (rc) goto out; - (void)sock_register(&atalk_family_ops); + rc = sock_register(&atalk_family_ops); + if (rc) + goto out_proto; + ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv); if (!ddp_dl) printk(atalk_err_snap); @@ -1923,12 +1927,33 @@ static int __init atalk_init(void) dev_add_pack(<alk_packet_type); dev_add_pack(&ppptalk_packet_type); - register_netdevice_notifier(&ddp_notifier); + rc = register_netdevice_notifier(&ddp_notifier); + if (rc) + goto out_sock; + aarp_proto_init(); - atalk_proc_init(); - atalk_register_sysctl(); + rc = atalk_proc_init(); + if (rc) + goto out_aarp; + + rc = atalk_register_sysctl(); + if (rc) + goto out_proc; out: return rc; +out_proc: + atalk_proc_exit(); +out_aarp: + aarp_cleanup_module(); + unregister_netdevice_notifier(&ddp_notifier); +out_sock: + dev_remove_pack(&ppptalk_packet_type); + dev_remove_pack(<alk_packet_type); + unregister_snap_client(ddp_dl); + sock_unregister(PF_APPLETALK); +out_proto: + proto_unregister(&ddp_proto); + goto out; } module_init(atalk_init); diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c index c744a853fa5f..d945b7c0176d 100644 --- a/net/appletalk/sysctl_net_atalk.c +++ b/net/appletalk/sysctl_net_atalk.c @@ -45,9 +45,12 @@ static struct ctl_table atalk_table[] = { static struct ctl_table_header *atalk_table_header; -void atalk_register_sysctl(void) +int __init atalk_register_sysctl(void) { atalk_table_header = register_net_sysctl(&init_net, "net/appletalk", atalk_table); + if (!atalk_table_header) + return -ENOMEM; + return 0; } void atalk_unregister_sysctl(void) diff --git a/net/atm/lec.c b/net/atm/lec.c index d7f5cf5b7594..ad4f829193f0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) static int lec_mcast_attach(struct atm_vcc *vcc, int arg) { - if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) + if (arg < 0 || arg >= MAX_LEC_ITF) + return -EINVAL; + arg = array_index_nospec(arg, MAX_LEC_ITF); + if (!dev_lec[arg]) return -EINVAL; vcc->proto_data = dev_lec[arg]; return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc); @@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) i = arg; if (arg >= MAX_LEC_ITF) return -EINVAL; + i = array_index_nospec(arg, MAX_LEC_ITF); if (!dev_lec[i]) { int size; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index c603d33d5410..5d01edf8d819 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -653,15 +653,22 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, break; } - dev = dev_get_by_name(&init_net, devname); + rtnl_lock(); + dev = __dev_get_by_name(&init_net, devname); if (!dev) { + rtnl_unlock(); res = -ENODEV; break; } ax25->ax25_dev = ax25_dev_ax25dev(dev); + if (!ax25->ax25_dev) { + rtnl_unlock(); + res = -ENODEV; + break; + } ax25_fillin_cb(ax25, ax25->ax25_dev); - dev_put(dev); + rtnl_unlock(); break; default: diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 9a3a301e1e2f..d92195cd7834 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -116,6 +116,7 @@ void ax25_dev_device_down(struct net_device *dev) if ((s = ax25_dev_list) == ax25_dev) { ax25_dev_list = s->next; spin_unlock_bh(&ax25_dev_lock); + dev->ax25_ptr = NULL; dev_put(dev); kfree(ax25_dev); return; @@ -125,6 +126,7 @@ void ax25_dev_device_down(struct net_device *dev) if (s->next == ax25_dev) { s->next = ax25_dev->next; spin_unlock_bh(&ax25_dev_lock); + dev->ax25_ptr = NULL; dev_put(dev); kfree(ax25_dev); return; diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index 70417e9b932d..314bbc8010fb 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -114,6 +114,7 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) dst = (ax25_address *)(bp + 1); src = (ax25_address *)(bp + 8); + ax25_route_lock_use(); route = ax25_get_route(dst, NULL); if (route) { digipeat = route->digipeat; @@ -206,9 +207,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) ax25_queue_xmit(skb, dev); put: - if (route) - ax25_put_route(route); + ax25_route_lock_unuse(); return NETDEV_TX_OK; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index a0eff323af12..66f74c85cf6b 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -40,7 +40,7 @@ #include <linux/export.h> static ax25_route *ax25_route_list; -static DEFINE_RWLOCK(ax25_route_lock); +DEFINE_RWLOCK(ax25_route_lock); void ax25_rt_device_down(struct net_device *dev) { @@ -335,6 +335,7 @@ const struct seq_operations ax25_rt_seqops = { * Find AX.25 route * * Only routes with a reference count of zero can be destroyed. + * Must be called with ax25_route_lock read locked. */ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) { @@ -342,7 +343,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) ax25_route *ax25_def_rt = NULL; ax25_route *ax25_rt; - read_lock(&ax25_route_lock); /* * Bind to the physical interface we heard them on, or the default * route if none is found; @@ -365,11 +365,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) if (ax25_spe_rt != NULL) ax25_rt = ax25_spe_rt; - if (ax25_rt != NULL) - ax25_hold_route(ax25_rt); - - read_unlock(&ax25_route_lock); - return ax25_rt; } @@ -400,9 +395,12 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) ax25_route *ax25_rt; int err = 0; - if ((ax25_rt = ax25_get_route(addr, NULL)) == NULL) + ax25_route_lock_use(); + ax25_rt = ax25_get_route(addr, NULL); + if (!ax25_rt) { + ax25_route_lock_unuse(); return -EHOSTUNREACH; - + } if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) { err = -EHOSTUNREACH; goto put; @@ -437,8 +435,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) } put: - ax25_put_route(ax25_rt); - + ax25_route_lock_unuse(); return err; } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..5da183b2f4c9 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -104,6 +104,11 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); + if (!ret) { + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + } + dev_put(real_netdev); if (ret == -ENOENT) { /* Node is not associated anymore! It would be diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5f1aeeded0e3..85faf25c2912 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -803,6 +803,8 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; + struct batadv_bla_claim *claim_removed_entry; + struct hlist_node *claim_removed_node; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; @@ -813,10 +815,18 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, mac, batadv_print_vid(vid)); - batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, - batadv_choose_claim, claim); - batadv_claim_put(claim); /* reference from the hash is gone */ + claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash, + batadv_compare_claim, + batadv_choose_claim, claim); + if (!claim_removed_node) + goto free_claim; + /* reference from the hash is gone */ + claim_removed_entry = hlist_entry(claim_removed_node, + struct batadv_bla_claim, hash_entry); + batadv_claim_put(claim_removed_entry); + +free_claim: /* don't need the reference from hash_find() anymore */ batadv_claim_put(claim); } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index a60bacf7120b..2895e3b26e93 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1394,7 +1394,6 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, hw_src, &ip_src, hw_dst, &ip_dst, dat_entry->mac_addr, &dat_entry->ip); dropped = true; - goto out; } /* Update our internal cache with both the IP addresses the node got @@ -1403,6 +1402,9 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid); + if (dropped) + goto out; + /* If BLA is enabled, only forward ARP replies if we have claimed the * source of the ARP reply or if no one else of the same backbone has * already claimed that client. This prevents that different gateways diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 2f0d42f2f913..08690d06b7be 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -20,7 +20,6 @@ #include "main.h" #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/gfp.h> @@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) parent_dev = __dev_get_by_index((struct net *)parent_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ - if (WARN(!parent_dev, "Cannot find parent device")) + if (!parent_dev) { + pr_err("Cannot find parent device\n"); return false; + } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 69c0d85bceb3..79b8a2d8793e 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -160,6 +160,7 @@ int batadv_mesh_init(struct net_device *soft_iface) spin_lock_init(&bat_priv->tt.commit_lock); spin_lock_init(&bat_priv->gw.list_lock); #ifdef CONFIG_BATMAN_ADV_MCAST + spin_lock_init(&bat_priv->mcast.mla_lock); spin_lock_init(&bat_priv->mcast.want_lists_lock); #endif spin_lock_init(&bat_priv->tvlv.container_list_lock); diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 86725d792e15..b90fe25d6b0b 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -325,8 +325,6 @@ static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list) * translation table except the ones listed in the given mcast_list. * * If mcast_list is NULL then all are retracted. - * - * Do not call outside of the mcast worker! (or cancel mcast worker first) */ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) @@ -334,8 +332,6 @@ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; - WARN_ON(delayed_work_pending(&bat_priv->mcast.work)); - hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list, list) { if (mcast_list && @@ -359,8 +355,6 @@ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, * * Adds multicast listener announcements from the given mcast_list to the * translation table if they have not been added yet. - * - * Do not call outside of the mcast worker! (or cancel mcast worker first) */ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, struct hlist_head *mcast_list) @@ -368,8 +362,6 @@ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; - WARN_ON(delayed_work_pending(&bat_priv->mcast.work)); - if (!mcast_list) return; @@ -658,7 +650,10 @@ static void batadv_mcast_mla_update(struct work_struct *work) priv_mcast = container_of(delayed_work, struct batadv_priv_mcast, work); bat_priv = container_of(priv_mcast, struct batadv_priv, mcast); + spin_lock(&bat_priv->mcast.mla_lock); __batadv_mcast_mla_update(bat_priv); + spin_unlock(&bat_priv->mcast.mla_lock); + batadv_mcast_start_timer(bat_priv); } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 626ddca332db..a2976adeeedc 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -221,10 +221,14 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, netif_trans_update(soft_iface); vid = batadv_get_vid(skb, 0); + + skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, sizeof(*vhdr))) + goto dropped; vhdr = vlan_eth_hdr(skb); /* drop batman-in-batman packets to prevent loops */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index d21624c44665..359ec1a6e822 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -616,14 +616,26 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global, const char *message) { + struct batadv_tt_global_entry *tt_removed_entry; + struct hlist_node *tt_removed_node; + batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM (vid: %d): %s\n", tt_global->common.addr, batadv_print_vid(tt_global->common.vid), message); - batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, - batadv_choose_tt, &tt_global->common); - batadv_tt_global_entry_put(tt_global); + tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash, + batadv_compare_tt, + batadv_choose_tt, + &tt_global->common); + if (!tt_removed_node) + return; + + /* drop reference of remove hash entry */ + tt_removed_entry = hlist_entry(tt_removed_node, + struct batadv_tt_global_entry, + common.hash_entry); + batadv_tt_global_entry_put(tt_removed_entry); } /** @@ -1332,9 +1344,10 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid, const char *message, bool roaming) { + struct batadv_tt_local_entry *tt_removed_entry; struct batadv_tt_local_entry *tt_local_entry; u16 flags, curr_flags = BATADV_NO_FLAGS; - void *tt_entry_exists; + struct hlist_node *tt_removed_node; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) @@ -1363,15 +1376,18 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, */ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); - tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash, + tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_tt, &tt_local_entry->common); - if (!tt_entry_exists) + if (!tt_removed_node) goto out; - /* extra call to free the local tt entry */ - batadv_tt_local_entry_put(tt_local_entry); + /* drop reference of remove hash entry */ + tt_removed_entry = hlist_entry(tt_removed_node, + struct batadv_tt_local_entry, + common.hash_entry); + batadv_tt_local_entry_put(tt_removed_entry); out: if (tt_local_entry) diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 343d304851a5..eeee3e61c625 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1216,6 +1216,11 @@ struct batadv_priv_mcast { unsigned char bridged:1; /** + * @mla_lock: a lock protecting mla_list and mla_flags + */ + spinlock_t mla_lock; + + /** * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP * traffic */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index deacc52d7ff1..8d12198eaa94 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -154,15 +154,25 @@ void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) } EXPORT_SYMBOL(bt_sock_unlink); -void bt_accept_enqueue(struct sock *parent, struct sock *sk) +void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + + if (bh) + bh_lock_sock_nested(sk); + else + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; - release_sock(sk); + + if (bh) + bh_unlock_sock(sk); + else + release_sock(sk); + parent->sk_ack_backlog++; } EXPORT_SYMBOL(bt_accept_enqueue); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index bd4978ce8c45..3cf0764d5793 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1276,6 +1276,14 @@ int hci_conn_check_link_mode(struct hci_conn *conn) !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; + /* The minimum encryption key size needs to be enforced by the + * host stack before establishing any L2CAP connections. The + * specification in theory allows a minimum of 1, but to align + * BR/EDR and LE transports, a minimum of 7 is chosen. + */ + if (conn->enc_key_size < HCI_MIN_ENC_KEY_SIZE) + return 0; + return 1; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 74b29c7d841c..5afd67ef797a 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3084,6 +3084,8 @@ struct hci_dev *hci_alloc_dev(void) hdev->le_max_tx_time = 0x0148; hdev->le_max_rx_len = 0x001b; hdev->le_max_rx_time = 0x0148; + hdev->le_max_key_size = SMP_MAX_ENC_KEY_SIZE; + hdev->le_min_key_size = SMP_MIN_ENC_KEY_SIZE; hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; @@ -4272,6 +4274,9 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, return; } + /* If we reach this point this event matches the last command sent */ + hci_dev_clear_flag(hdev, HCI_CMD_PENDING); + /* If the command succeeded and there's still more commands in * this request the request is not yet complete. */ @@ -4382,6 +4387,8 @@ static void hci_cmd_work(struct work_struct *work) hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); if (hdev->sent_cmd) { + if (hci_req_status_pend(hdev)) + hci_dev_set_flag(hdev, HCI_CMD_PENDING); atomic_dec(&hdev->cmd_cnt); hci_send_frame(hdev, skb); if (test_bit(HCI_RESET, &hdev->flags)) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f12555f23a49..3e7badb3ac2d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3357,6 +3357,12 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_req_cmd_complete(hdev, *opcode, *status, req_complete, req_complete_skb); + if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { + bt_dev_err(hdev, + "unexpected event for opcode 0x%4.4x", *opcode); + return; + } + if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); } @@ -3464,6 +3470,12 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb); + if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { + bt_dev_err(hdev, + "unexpected event for opcode 0x%4.4x", *opcode); + return; + } + if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); } @@ -5668,6 +5680,12 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, return true; } + /* Check if request ended in Command Status - no way to retreive + * any extra parameters in this case. + */ + if (hdr->evt == HCI_EV_CMD_STATUS) + return false; + if (hdr->evt != HCI_EV_CMD_COMPLETE) { bt_dev_err(hdev, "last event is not cmd complete (0x%2.2x)", hdr->evt); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index e8c9ef1e1922..9448ebd3780a 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -46,6 +46,11 @@ void hci_req_purge(struct hci_request *req) skb_queue_purge(&req->cmd_q); } +bool hci_req_status_pend(struct hci_dev *hdev) +{ + return hdev->req_status == HCI_REQ_PEND; +} + static int req_run(struct hci_request *req, hci_req_complete_t complete, hci_req_complete_skb_t complete_skb) { diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 692cc8b13368..55b2050cc9ff 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -37,6 +37,7 @@ struct hci_request { void hci_req_init(struct hci_request *req, struct hci_dev *hdev); void hci_req_purge(struct hci_request *req); +bool hci_req_status_pend(struct hci_dev *hdev); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1506e1632394..d4e2a166ae17 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -831,8 +831,6 @@ static int hci_sock_release(struct socket *sock) if (!sk) return 0; - hdev = hci_pi(sk)->hdev; - switch (hci_pi(sk)->channel) { case HCI_CHANNEL_MONITOR: atomic_dec(&monitor_promisc); @@ -854,6 +852,7 @@ static int hci_sock_release(struct socket *sock) bt_sock_unlink(&hci_sk_list, sk); + hdev = hci_pi(sk)->hdev; if (hdev) { if (hci_pi(sk)->channel == HCI_CHANNEL_USER) { /* When releasing a user channel exclusive access, diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 1eaac01f85de..7f36fa73ffee 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -76,6 +76,7 @@ static int hidp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long sockfd_put(csock); return err; } + ca.name[sizeof(ca.name)-1] = 0; err = hidp_connection_add(&ca, csock, isock); if (!err && copy_to_user(argp, &ca, sizeof(ca))) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index d17a4736e47c..2c6eabf294b3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3336,16 +3336,22 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data while (len >= L2CAP_CONF_OPT_SIZE) { len -= l2cap_get_conf_opt(&req, &type, &olen, &val); + if (len < 0) + break; hint = type & L2CAP_CONF_HINT; type &= L2CAP_CONF_MASK; switch (type) { case L2CAP_CONF_MTU: + if (olen != 2) + break; mtu = val; break; case L2CAP_CONF_FLUSH_TO: + if (olen != 2) + break; chan->flush_to = val; break; @@ -3353,26 +3359,30 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data break; case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *) val, olen); + if (olen != sizeof(rfc)) + break; + memcpy(&rfc, (void *) val, olen); break; case L2CAP_CONF_FCS: + if (olen != 1) + break; if (val == L2CAP_FCS_NONE) set_bit(CONF_RECV_NO_FCS, &chan->conf_state); break; case L2CAP_CONF_EFS: - if (olen == sizeof(efs)) { - remote_efs = 1; - memcpy(&efs, (void *) val, olen); - } + if (olen != sizeof(efs)) + break; + remote_efs = 1; + memcpy(&efs, (void *) val, olen); break; case L2CAP_CONF_EWS: + if (olen != 2) + break; if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP)) return -ECONNREFUSED; - set_bit(FLAG_EXT_CTRL, &chan->flags); set_bit(CONF_EWS_RECV, &chan->conf_state); chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW; @@ -3382,7 +3392,6 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data default: if (hint) break; - result = L2CAP_CONF_UNKNOWN; *((u8 *) ptr++) = type; break; @@ -3547,58 +3556,65 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, while (len >= L2CAP_CONF_OPT_SIZE) { len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); + if (len < 0) + break; switch (type) { case L2CAP_CONF_MTU: + if (olen != 2) + break; if (val < L2CAP_DEFAULT_MIN_MTU) { *result = L2CAP_CONF_UNACCEPT; chan->imtu = L2CAP_DEFAULT_MIN_MTU; } else chan->imtu = val; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, + endptr - ptr); break; case L2CAP_CONF_FLUSH_TO: + if (olen != 2) + break; chan->flush_to = val; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO, - 2, chan->flush_to, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_FLUSH_TO, 2, + chan->flush_to, endptr - ptr); break; case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *)val, olen); - + if (olen != sizeof(rfc)) + break; + memcpy(&rfc, (void *)val, olen); if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state) && rfc.mode != chan->mode) return -ECONNREFUSED; - chan->fcs = 0; - - l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, - sizeof(rfc), (unsigned long) &rfc, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), + (unsigned long) &rfc, endptr - ptr); break; case L2CAP_CONF_EWS: + if (olen != 2) + break; chan->ack_win = min_t(u16, val, chan->ack_win); l2cap_add_conf_opt(&ptr, L2CAP_CONF_EWS, 2, chan->tx_win, endptr - ptr); break; case L2CAP_CONF_EFS: - if (olen == sizeof(efs)) { - memcpy(&efs, (void *)val, olen); - - if (chan->local_stype != L2CAP_SERV_NOTRAFIC && - efs.stype != L2CAP_SERV_NOTRAFIC && - efs.stype != chan->local_stype) - return -ECONNREFUSED; - - l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), - (unsigned long) &efs, endptr - ptr); - } + if (olen != sizeof(efs)) + break; + memcpy(&efs, (void *)val, olen); + if (chan->local_stype != L2CAP_SERV_NOTRAFIC && + efs.stype != L2CAP_SERV_NOTRAFIC && + efs.stype != chan->local_stype) + return -ECONNREFUSED; + l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), + (unsigned long) &efs, endptr - ptr); break; case L2CAP_CONF_FCS: + if (olen != 1) + break; if (*result == L2CAP_CONF_PENDING) if (val == L2CAP_FCS_NONE) set_bit(CONF_RECV_NO_FCS, @@ -3727,13 +3743,18 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) while (len >= L2CAP_CONF_OPT_SIZE) { len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); + if (len < 0) + break; switch (type) { case L2CAP_CONF_RFC: - if (olen == sizeof(rfc)) - memcpy(&rfc, (void *)val, olen); + if (olen != sizeof(rfc)) + break; + memcpy(&rfc, (void *)val, olen); break; case L2CAP_CONF_EWS: + if (olen != 2) + break; txwin_ext = val; break; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 686bdc6b35b0..a3a2cd55e23a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1252,7 +1252,7 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) l2cap_sock_init(sk, parent); - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, false); release_sock(parent); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index d606e9212291..c044ff2f73e6 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -988,7 +988,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * rfcomm_pi(sk)->channel = channel; sk->sk_state = BT_CONFIG; - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, true); /* Accept connection and return socket DLC */ *d = rfcomm_pi(sk)->dlc; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8f0f9279eac9..a4ca55df7390 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -193,7 +193,7 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, conn->sk = sk; if (parent) - bt_accept_enqueue(parent, sk); + bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 73f7211d0431..a1c1b7e8a45c 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -88,9 +88,6 @@ struct smp_dev { u8 local_rand[16]; bool debug_key; - u8 min_key_size; - u8 max_key_size; - struct crypto_cipher *tfm_aes; struct crypto_shash *tfm_cmac; struct crypto_kpp *tfm_ecdh; @@ -720,7 +717,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, if (rsp == NULL) { req->io_capability = conn->hcon->io_capability; req->oob_flag = oob_flag; - req->max_key_size = SMP_DEV(hdev)->max_key_size; + req->max_key_size = hdev->le_max_key_size; req->init_key_dist = local_dist; req->resp_key_dist = remote_dist; req->auth_req = (authreq & AUTH_REQ_MASK(hdev)); @@ -731,7 +728,7 @@ static void build_pairing_cmd(struct l2cap_conn *conn, rsp->io_capability = conn->hcon->io_capability; rsp->oob_flag = oob_flag; - rsp->max_key_size = SMP_DEV(hdev)->max_key_size; + rsp->max_key_size = hdev->le_max_key_size; rsp->init_key_dist = req->init_key_dist & remote_dist; rsp->resp_key_dist = req->resp_key_dist & local_dist; rsp->auth_req = (authreq & AUTH_REQ_MASK(hdev)); @@ -745,7 +742,7 @@ static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) struct hci_dev *hdev = conn->hcon->hdev; struct smp_chan *smp = chan->data; - if (max_key_size > SMP_DEV(hdev)->max_key_size || + if (max_key_size > hdev->le_max_key_size || max_key_size < SMP_MIN_ENC_KEY_SIZE) return SMP_ENC_KEY_SIZE; @@ -3264,8 +3261,6 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; smp->tfm_ecdh = tfm_ecdh; - smp->min_key_size = SMP_MIN_ENC_KEY_SIZE; - smp->max_key_size = SMP_MAX_ENC_KEY_SIZE; create_chan: chan = l2cap_chan_create(); @@ -3391,7 +3386,7 @@ static ssize_t le_min_key_size_read(struct file *file, struct hci_dev *hdev = file->private_data; char buf[4]; - snprintf(buf, sizeof(buf), "%2u\n", SMP_DEV(hdev)->min_key_size); + snprintf(buf, sizeof(buf), "%2u\n", hdev->le_min_key_size); return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf)); } @@ -3412,11 +3407,11 @@ static ssize_t le_min_key_size_write(struct file *file, sscanf(buf, "%hhu", &key_size); - if (key_size > SMP_DEV(hdev)->max_key_size || + if (key_size > hdev->le_max_key_size || key_size < SMP_MIN_ENC_KEY_SIZE) return -EINVAL; - SMP_DEV(hdev)->min_key_size = key_size; + hdev->le_min_key_size = key_size; return count; } @@ -3435,7 +3430,7 @@ static ssize_t le_max_key_size_read(struct file *file, struct hci_dev *hdev = file->private_data; char buf[4]; - snprintf(buf, sizeof(buf), "%2u\n", SMP_DEV(hdev)->max_key_size); + snprintf(buf, sizeof(buf), "%2u\n", hdev->le_max_key_size); return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf)); } @@ -3457,10 +3452,10 @@ static ssize_t le_max_key_size_write(struct file *file, sscanf(buf, "%hhu", &key_size); if (key_size > SMP_MAX_ENC_KEY_SIZE || - key_size < SMP_DEV(hdev)->min_key_size) + key_size < hdev->le_min_key_size) return -EINVAL; - SMP_DEV(hdev)->max_key_size = key_size; + hdev->le_max_key_size = key_size; return count; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 502f66349530..4d4b9b5ea1c1 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1088,6 +1088,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, err = -ENOMEM; goto err_unlock; } + if (swdev_notify) + fdb->added_by_user = 1; fdb->added_by_external_learn = 1; fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { @@ -1107,6 +1109,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } + if (swdev_notify) + fdb->added_by_user = 1; + if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 5372e2042adf..48ddc60b4fbd 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -36,10 +36,10 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { + skb_push(skb, ETH_HLEN); if (!is_skb_forwardable(skb->dev, skb)) goto drop; - skb_push(skb, ETH_HLEN); br_drop_fake_rtable(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && @@ -65,6 +65,7 @@ EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + skb->tstamp = 0; return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, net, sk, skb, NULL, skb->dev, br_dev_queue_push_xmit); @@ -97,12 +98,11 @@ static void __br_forward(const struct net_bridge_port *to, net = dev_net(indev); } else { if (unlikely(netpoll_tx_running(to->br->dev))) { - if (!is_skb_forwardable(skb->dev, skb)) { + skb_push(skb, ETH_HLEN); + if (!is_skb_forwardable(skb->dev, skb)) kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); + else br_netpoll_send_skb(to, skb); - } return; } br_hook = NF_BR_LOCAL_OUT; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 0363f1bdc401..ed2b6002ae53 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -603,13 +603,15 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, call_netdevice_notifiers(NETDEV_JOIN, dev); err = dev_set_allmulti(dev, 1); - if (err) - goto put_back; + if (err) { + kfree(p); /* kobject not yet init'd, manually free */ + goto err1; + } err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj), SYSFS_BRIDGE_PORT_ATTR); if (err) - goto err1; + goto err2; err = br_sysfs_addif(p); if (err) @@ -692,12 +694,9 @@ err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: kobject_put(&p->kobj); - p = NULL; /* kobject_put frees */ -err1: dev_set_allmulti(dev, -1); -put_back: +err1: dev_put(dev); - kfree(p); return err; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 72074276c088..fed0ff446abb 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -195,13 +195,10 @@ static void __br_handle_local_finish(struct sk_buff *skb) /* note: already called with rcu_read_lock */ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_bridge_port *p = br_port_get_rcu(skb->dev); - __br_handle_local_finish(skb); - BR_INPUT_SKB_CB(skb)->brdev = p->br->dev; - br_pass_frame_up(skb); - return 0; + /* return 1 to signal the okfn() was called so it's ok to use the skb */ + return 1; } /* @@ -278,10 +275,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } - /* Deliver packet to local host only */ - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev), - NULL, skb, skb->dev, NULL, br_handle_local_finish); - return RX_HANDLER_CONSUMED; + /* The else clause should be hit when nf_hook(): + * - returns < 0 (drop/error) + * - returns = 0 (stolen/nf_queue) + * Thus return 1 from the okfn() to signal the skb is ok to pass + */ + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, + br_handle_local_finish) == 1) { + return RX_HANDLER_PASS; + } else { + return RX_HANDLER_CONSUMED; + } } forward: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 6dec8e9b3451..75901c4641b1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1420,14 +1420,7 @@ static void br_multicast_query_received(struct net_bridge *br, return; br_multicast_update_query_timer(br, query, max_delay); - - /* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules, - * the arrival port for IGMP Queries where the source address - * is 0.0.0.0 should not be added to router port list. - */ - if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) || - saddr->proto == htons(ETH_P_IPV6)) - br_multicast_mark_router(br, port); + br_multicast_mark_router(br, port); } static void br_ip4_multicast_query(struct net_bridge *br, @@ -2159,7 +2152,8 @@ static void br_multicast_start_querier(struct net_bridge *br, __br_multicast_open(br, query); - list_for_each_entry(port, &br->port_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(port, &br->port_list, list) { if (port->state == BR_STATE_DISABLED || port->state == BR_STATE_BLOCKING) continue; @@ -2171,6 +2165,7 @@ static void br_multicast_start_querier(struct net_bridge *br, br_multicast_enable(&port->ip6_own_query); #endif } + rcu_read_unlock(); } int br_multicast_toggle(struct net_bridge *br, unsigned long val) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 37278dc280eb..212c184c1eee 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -278,7 +278,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; - if (neigh->hh.hh_len) { + if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; ret = br_handle_frame_finish(net, sk, skb); @@ -515,6 +515,7 @@ static unsigned int br_nf_pre_routing(void *priv, nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; skb->protocol = htons(ETH_P_IP); + skb->transport_header = skb->network_header + ip_hdr(skb)->ihl * 4; NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, @@ -884,11 +885,6 @@ static const struct nf_br_ops br_ops = { .br_dev_xmit_hook = br_nf_dev_xmit, }; -void br_netfilter_enable(void) -{ -} -EXPORT_SYMBOL_GPL(br_netfilter_enable); - /* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because * br_dev_queue_push_xmit is called afterwards */ static const struct nf_hook_ops br_nf_ops[] = { diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 96c072e71ea2..09d5e0c7b3ba 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -131,6 +131,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb) IPSTATS_MIB_INDISCARDS); goto drop; } + hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb)) goto drop; @@ -234,6 +235,8 @@ unsigned int br_nf_pre_routing_ipv6(void *priv, nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; skb->protocol = htons(ETH_P_IPV6); + skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 491828713e0b..0bb4d712b80c 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -31,10 +31,6 @@ /* needed for logical [in,out]-dev filtering */ #include "../br_private.h" -#define BUGPRINT(format, args...) printk("kernel msg: ebtables bug: please "\ - "report to author: "format, ## args) -/* #define BUGPRINT(format, args...) */ - /* Each cpu has its own set of counters, so there is no need for write_lock in * the softirq * For reading or updating the counters, the user context needs to @@ -466,8 +462,6 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, /* we make userspace set this right, * so there is no misunderstanding */ - BUGPRINT("EBT_ENTRY_OR_ENTRIES shouldn't be set " - "in distinguisher\n"); return -EINVAL; } if (i != NF_BR_NUMHOOKS) @@ -485,18 +479,14 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, offset += e->next_offset; } } - if (offset != limit) { - BUGPRINT("entries_size too small\n"); + if (offset != limit) return -EINVAL; - } /* check if all valid hooks have a chain */ for (i = 0; i < NF_BR_NUMHOOKS; i++) { if (!newinfo->hook_entry[i] && - (valid_hooks & (1 << i))) { - BUGPRINT("Valid hook without chain\n"); + (valid_hooks & (1 << i))) return -EINVAL; - } } return 0; } @@ -523,26 +513,20 @@ ebt_check_entry_size_and_hooks(const struct ebt_entry *e, /* this checks if the previous chain has as many entries * as it said it has */ - if (*n != *cnt) { - BUGPRINT("nentries does not equal the nr of entries " - "in the chain\n"); + if (*n != *cnt) return -EINVAL; - } + if (((struct ebt_entries *)e)->policy != EBT_DROP && ((struct ebt_entries *)e)->policy != EBT_ACCEPT) { /* only RETURN from udc */ if (i != NF_BR_NUMHOOKS || - ((struct ebt_entries *)e)->policy != EBT_RETURN) { - BUGPRINT("bad policy\n"); + ((struct ebt_entries *)e)->policy != EBT_RETURN) return -EINVAL; - } } if (i == NF_BR_NUMHOOKS) /* it's a user defined chain */ (*udc_cnt)++; - if (((struct ebt_entries *)e)->counter_offset != *totalcnt) { - BUGPRINT("counter_offset != totalcnt"); + if (((struct ebt_entries *)e)->counter_offset != *totalcnt) return -EINVAL; - } *n = ((struct ebt_entries *)e)->nentries; *cnt = 0; return 0; @@ -550,15 +534,13 @@ ebt_check_entry_size_and_hooks(const struct ebt_entry *e, /* a plain old entry, heh */ if (sizeof(struct ebt_entry) > e->watchers_offset || e->watchers_offset > e->target_offset || - e->target_offset >= e->next_offset) { - BUGPRINT("entry offsets not in right order\n"); + e->target_offset >= e->next_offset) return -EINVAL; - } + /* this is not checked anywhere else */ - if (e->next_offset - e->target_offset < sizeof(struct ebt_entry_target)) { - BUGPRINT("target size too small\n"); + if (e->next_offset - e->target_offset < sizeof(struct ebt_entry_target)) return -EINVAL; - } + (*cnt)++; (*totalcnt)++; return 0; @@ -678,18 +660,15 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, if (e->bitmask == 0) return 0; - if (e->bitmask & ~EBT_F_MASK) { - BUGPRINT("Unknown flag for bitmask\n"); + if (e->bitmask & ~EBT_F_MASK) return -EINVAL; - } - if (e->invflags & ~EBT_INV_MASK) { - BUGPRINT("Unknown flag for inv bitmask\n"); + + if (e->invflags & ~EBT_INV_MASK) return -EINVAL; - } - if ((e->bitmask & EBT_NOPROTO) && (e->bitmask & EBT_802_3)) { - BUGPRINT("NOPROTO & 802_3 not allowed\n"); + + if ((e->bitmask & EBT_NOPROTO) && (e->bitmask & EBT_802_3)) return -EINVAL; - } + /* what hook do we belong to? */ for (i = 0; i < NF_BR_NUMHOOKS; i++) { if (!newinfo->hook_entry[i]) @@ -748,13 +727,11 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, t->u.target = target; if (t->u.target == &ebt_standard_target) { if (gap < sizeof(struct ebt_standard_target)) { - BUGPRINT("Standard target size too big\n"); ret = -EFAULT; goto cleanup_watchers; } if (((struct ebt_standard_target *)t)->verdict < -NUM_STANDARD_TARGETS) { - BUGPRINT("Invalid standard target\n"); ret = -EFAULT; goto cleanup_watchers; } @@ -813,10 +790,9 @@ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack if (strcmp(t->u.name, EBT_STANDARD_TARGET)) goto letscontinue; if (e->target_offset + sizeof(struct ebt_standard_target) > - e->next_offset) { - BUGPRINT("Standard target size too big\n"); + e->next_offset) return -1; - } + verdict = ((struct ebt_standard_target *)t)->verdict; if (verdict >= 0) { /* jump to another chain */ struct ebt_entries *hlp2 = @@ -825,14 +801,12 @@ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack if (hlp2 == cl_s[i].cs.chaininfo) break; /* bad destination or loop */ - if (i == udc_cnt) { - BUGPRINT("bad destination\n"); + if (i == udc_cnt) return -1; - } - if (cl_s[i].cs.n) { - BUGPRINT("loop\n"); + + if (cl_s[i].cs.n) return -1; - } + if (cl_s[i].hookmask & (1 << hooknr)) goto letscontinue; /* this can't be 0, so the loop test is correct */ @@ -865,24 +839,21 @@ static int translate_table(struct net *net, const char *name, i = 0; while (i < NF_BR_NUMHOOKS && !newinfo->hook_entry[i]) i++; - if (i == NF_BR_NUMHOOKS) { - BUGPRINT("No valid hooks specified\n"); + if (i == NF_BR_NUMHOOKS) return -EINVAL; - } - if (newinfo->hook_entry[i] != (struct ebt_entries *)newinfo->entries) { - BUGPRINT("Chains don't start at beginning\n"); + + if (newinfo->hook_entry[i] != (struct ebt_entries *)newinfo->entries) return -EINVAL; - } + /* make sure chains are ordered after each other in same order * as their corresponding hooks */ for (j = i + 1; j < NF_BR_NUMHOOKS; j++) { if (!newinfo->hook_entry[j]) continue; - if (newinfo->hook_entry[j] <= newinfo->hook_entry[i]) { - BUGPRINT("Hook order must be followed\n"); + if (newinfo->hook_entry[j] <= newinfo->hook_entry[i]) return -EINVAL; - } + i = j; } @@ -900,15 +871,11 @@ static int translate_table(struct net *net, const char *name, if (ret != 0) return ret; - if (i != j) { - BUGPRINT("nentries does not equal the nr of entries in the " - "(last) chain\n"); + if (i != j) return -EINVAL; - } - if (k != newinfo->nentries) { - BUGPRINT("Total nentries is wrong\n"); + + if (k != newinfo->nentries) return -EINVAL; - } /* get the location of the udc, put them in an array * while we're at it, allocate the chainstack @@ -942,7 +909,6 @@ static int translate_table(struct net *net, const char *name, ebt_get_udc_positions, newinfo, &i, cl_s); /* sanity check */ if (i != udc_cnt) { - BUGPRINT("i != udc_cnt\n"); vfree(cl_s); return -EFAULT; } @@ -1042,7 +1008,6 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_unlock; if (repl->num_counters && repl->num_counters != t->private->nentries) { - BUGPRINT("Wrong nr. of counters requested\n"); ret = -EINVAL; goto free_unlock; } @@ -1118,15 +1083,12 @@ static int do_replace(struct net *net, const void __user *user, if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.entries_size) { - BUGPRINT("Wrong len argument\n"); + if (len != sizeof(tmp) + tmp.entries_size) return -EINVAL; - } - if (tmp.entries_size == 0) { - BUGPRINT("Entries_size never zero\n"); + if (tmp.entries_size == 0) return -EINVAL; - } + /* overflow check */ if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / NR_CPUS - SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) @@ -1137,21 +1099,22 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof(tmp.name) - 1] = 0; countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = vmalloc(sizeof(*newinfo) + countersize); + newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo) return -ENOMEM; if (countersize) memset(newinfo->counters, 0, countersize); - newinfo->entries = vmalloc(tmp.entries_size); + newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo->entries) { ret = -ENOMEM; goto free_newinfo; } if (copy_from_user( newinfo->entries, tmp.entries, tmp.entries_size) != 0) { - BUGPRINT("Couldn't copy entries from userspace\n"); ret = -EFAULT; goto free_entries; } @@ -1192,10 +1155,8 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, if (input_table == NULL || (repl = input_table->table) == NULL || repl->entries == NULL || repl->entries_size == 0 || - repl->counters != NULL || input_table->private != NULL) { - BUGPRINT("Bad table data for ebt_register_table!!!\n"); + repl->counters != NULL || input_table->private != NULL) return -EINVAL; - } /* Don't add one table to multiple lists. */ table = kmemdup(input_table, sizeof(struct ebt_table), GFP_KERNEL); @@ -1233,13 +1194,10 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, ((char *)repl->hook_entry[i] - repl->entries); } ret = translate_table(net, repl->name, newinfo); - if (ret != 0) { - BUGPRINT("Translate_table failed\n"); + if (ret != 0) goto free_chainstack; - } if (table->check && table->check(newinfo, table->valid_hooks)) { - BUGPRINT("The table doesn't like its own initial data, lol\n"); ret = -EINVAL; goto free_chainstack; } @@ -1250,7 +1208,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, list_for_each_entry(t, &net->xt.tables[NFPROTO_BRIDGE], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; - BUGPRINT("Table name already exists\n"); goto free_unlock; } } @@ -1318,7 +1275,6 @@ static int do_update_counters(struct net *net, const char *name, goto free_tmp; if (num_counters != t->private->nentries) { - BUGPRINT("Wrong nr of counters\n"); ret = -EINVAL; goto unlock_mutex; } @@ -1445,10 +1401,8 @@ static int copy_counters_to_user(struct ebt_table *t, if (num_counters == 0) return 0; - if (num_counters != nentries) { - BUGPRINT("Num_counters wrong\n"); + if (num_counters != nentries) return -EINVAL; - } counterstmp = vmalloc(array_size(nentries, sizeof(*counterstmp))); if (!counterstmp) @@ -1494,15 +1448,11 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user, (tmp.num_counters ? nentries * sizeof(struct ebt_counter) : 0)) return -EINVAL; - if (tmp.nentries != nentries) { - BUGPRINT("Nentries wrong\n"); + if (tmp.nentries != nentries) return -EINVAL; - } - if (tmp.entries_size != entries_size) { - BUGPRINT("Wrong size\n"); + if (tmp.entries_size != entries_size) return -EINVAL; - } ret = copy_counters_to_user(t, oldcounters, tmp.counters, tmp.num_counters, nentries); @@ -1574,7 +1524,6 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } mutex_unlock(&ebt_mutex); if (copy_to_user(user, &tmp, *len) != 0) { - BUGPRINT("c2u Didn't work\n"); ret = -EFAULT; break; } @@ -2083,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + /* rule should have no remaining data after target */ + if (type == EBT_COMPAT_TARGET && size_left) return -EINVAL; match32 = (struct compat_ebt_entry_mwt *) buf; @@ -2291,9 +2241,12 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; + if (tmp.nentries) { + ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); + if (ret < 0) + goto out_unlock; + } + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 08cbed7d940e..419e8edf23ba 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -229,6 +229,7 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) return false; + ip6h = ipv6_hdr(skb); thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) return false; diff --git a/net/can/bcm.c b/net/can/bcm.c index 0af8f0db892a..79bb8afa9c0c 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -67,6 +67,9 @@ */ #define MAX_NFRAMES 256 +/* limit timers to 400 days for sending/timeouts */ +#define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60) + /* use of last_frames[index].flags */ #define RX_RECV 0x40 /* received data for this element */ #define RX_THR 0x80 /* element not been sent due to throttle feature */ @@ -140,6 +143,22 @@ static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv) return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); } +/* check limitations for timeval provided by user */ +static bool bcm_is_invalid_tv(struct bcm_msg_head *msg_head) +{ + if ((msg_head->ival1.tv_sec < 0) || + (msg_head->ival1.tv_sec > BCM_TIMER_SEC_MAX) || + (msg_head->ival1.tv_usec < 0) || + (msg_head->ival1.tv_usec >= USEC_PER_SEC) || + (msg_head->ival2.tv_sec < 0) || + (msg_head->ival2.tv_sec > BCM_TIMER_SEC_MAX) || + (msg_head->ival2.tv_usec < 0) || + (msg_head->ival2.tv_usec >= USEC_PER_SEC)) + return true; + + return false; +} + #define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU) #define OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) @@ -873,6 +892,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES) return -EINVAL; + /* check timeval limitations */ + if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) + return -EINVAL; + /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { @@ -1053,6 +1076,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, (!(msg_head->can_id & CAN_RTR_FLAG)))) return -EINVAL; + /* check timeval limitations */ + if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) + return -EINVAL; + /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { diff --git a/net/can/gw.c b/net/can/gw.c index faa3da88a127..53859346dc9a 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -416,13 +416,29 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); - /* check for checksum updates when the CAN frame has been modified */ + /* Has the CAN frame been modified? */ if (modidx) { - if (gwj->mod.csumfunc.crc8) + /* get available space for the processed CAN frame type */ + int max_len = nskb->len - offsetof(struct can_frame, data); + + /* dlc may have changed, make sure it fits to the CAN frame */ + if (cf->can_dlc > max_len) + goto out_delete; + + /* check for checksum updates in classic CAN length only */ + if (gwj->mod.csumfunc.crc8) { + if (cf->can_dlc > 8) + goto out_delete; + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + } + + if (gwj->mod.csumfunc.xor) { + if (cf->can_dlc > 8) + goto out_delete; - if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + } } /* clear the skb timestamp if not configured the other way */ @@ -434,6 +450,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) gwj->dropped_frames++; else gwj->handled_frames++; + + return; + + out_delete: + /* delete frame due to misconfiguration */ + gwj->deleted_frames++; + kfree_skb(nskb); + return; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 87afb9ec4c68..20f0c3d7ed50 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -729,7 +729,6 @@ int __ceph_open_session(struct ceph_client *client, unsigned long started) } EXPORT_SYMBOL(__ceph_open_session); - int ceph_open_session(struct ceph_client *client) { int ret; @@ -745,6 +744,23 @@ int ceph_open_session(struct ceph_client *client) } EXPORT_SYMBOL(ceph_open_session); +int ceph_wait_for_latest_osdmap(struct ceph_client *client, + unsigned long timeout) +{ + u64 newest_epoch; + int ret; + + ret = ceph_monc_get_version(&client->monc, "osdmap", &newest_epoch); + if (ret) + return ret; + + if (client->osdc.osdmap->epoch >= newest_epoch) + return 0; + + ceph_osdc_maybe_request_map(&client->osdc); + return ceph_monc_wait_osdmap(&client->monc, newest_epoch, timeout); +} +EXPORT_SYMBOL(ceph_wait_for_latest_osdmap); static int __init init_ceph_lib(void) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9a1c27c61de8..f7d7f32ac673 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2091,6 +2091,8 @@ static int process_connect(struct ceph_connection *con) dout("process_connect on %p tag %d\n", con, (int)con->in_tag); if (con->auth) { + int len = le32_to_cpu(con->in_reply.authorizer_len); + /* * Any connection that defines ->get_authorizer() * should also define ->add_authorizer_challenge() and @@ -2100,8 +2102,7 @@ static int process_connect(struct ceph_connection *con) */ if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) { ret = con->ops->add_authorizer_challenge( - con, con->auth->authorizer_reply_buf, - le32_to_cpu(con->in_reply.authorizer_len)); + con, con->auth->authorizer_reply_buf, len); if (ret < 0) return ret; @@ -2111,10 +2112,12 @@ static int process_connect(struct ceph_connection *con) return 0; } - ret = con->ops->verify_authorizer_reply(con); - if (ret < 0) { - con->error_msg = "bad authorize reply"; - return ret; + if (len) { + ret = con->ops->verify_authorizer_reply(con); + if (ret < 0) { + con->error_msg = "bad authorize reply"; + return ret; + } } } @@ -3240,9 +3243,10 @@ void ceph_con_keepalive(struct ceph_connection *con) dout("con_keepalive %p\n", con); mutex_lock(&con->mutex); clear_standby(con); + con_flag_set(con, CON_FLAG_KEEPALIVE_PENDING); mutex_unlock(&con->mutex); - if (con_flag_test_and_set(con, CON_FLAG_KEEPALIVE_PENDING) == 0 && - con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) + + if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 18deb3d889c4..a53e4fbb6319 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -922,6 +922,15 @@ int ceph_monc_blacklist_add(struct ceph_mon_client *monc, mutex_unlock(&monc->mutex); ret = wait_generic_request(req); + if (!ret) + /* + * Make sure we have the osdmap that includes the blacklist + * entry. This is needed to ensure that the OSDs pick up the + * new blacklist before processing any future requests from + * this client. + */ + ret = ceph_wait_for_latest_osdmap(monc->client, 0); + out: put_generic_request(req); return ret; diff --git a/net/compat.c b/net/compat.c index 3b2105f6549d..3c4b0283b29a 100644 --- a/net/compat.c +++ b/net/compat.c @@ -467,12 +467,14 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) ctv = (struct compat_timeval __user *) userstamp; err = -ENOENT; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sk->sk_stamp); + tv = ktime_to_timeval(sock_read_timestamp(sk)); + if (tv.tv_sec == -1) return err; if (tv.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - tv = ktime_to_timeval(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + tv = ktime_to_timeval(kt); } err = 0; if (put_user(tv.tv_sec, &ctv->tv_sec) || @@ -494,12 +496,13 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta ctv = (struct compat_timespec __user *) userstamp; err = -ENOENT; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sk->sk_stamp); + ts = ktime_to_timespec(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return err; if (ts.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - ts = ktime_to_timespec(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + ts = ktime_to_timespec(kt); } err = 0; if (put_user(ts.tv_sec, &ctv->tv_sec) || diff --git a/net/core/datagram.c b/net/core/datagram.c index 57f3a6fcfc1e..a487df53a453 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -279,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (!skb_queue_empty(&sk->sk_receive_queue)); + } while (sk->sk_receive_queue.prev != *last); error = -EAGAIN; diff --git a/net/core/dev.c b/net/core/dev.c index 6c0b8b894aa4..63b3058dd172 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1182,7 +1182,21 @@ int dev_change_name(struct net_device *dev, const char *newname) BUG_ON(!dev_net(dev)); net = dev_net(dev); - if (dev->flags & IFF_UP) + + /* Some auto-enslaved devices e.g. failover slaves are + * special, as userspace might rename the device after + * the interface had been brought up and running since + * the point kernel initiated auto-enslavement. Allow + * live name change even when these slave devices are + * up and running. + * + * Typically, users of these auto-enslaving devices + * don't actually care about slave name change, as + * they are supposed to operate on master interface + * directly. + */ + if (dev->flags & IFF_UP && + likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; mutex_lock(&devnet_rename_mutex); @@ -1813,7 +1827,7 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) @@ -1832,7 +1846,7 @@ static DECLARE_WORK(netstamp_work, netstamp_clear); void net_enable_timestamp(void) { -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL int wanted; while (1) { @@ -1852,7 +1866,7 @@ EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL int wanted; while (1) { @@ -4975,8 +4989,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, if (pt_prev->list_func != NULL) pt_prev->list_func(head, pt_prev, orig_dev); else - list_for_each_entry_safe(skb, next, head, list) + list_for_each_entry_safe(skb, next, head, list) { + skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) @@ -5728,7 +5744,6 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) skb_reset_mac_header(skb); skb_gro_reset_offset(skb); - eth = skb_gro_header_fast(skb, 0); if (unlikely(skb_gro_header_hard(skb, hlen))) { eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { @@ -5738,6 +5753,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) return NULL; } } else { + eth = (const struct ethhdr *)skb->data; gro_pull_from_frag0(skb, hlen); NAPI_GRO_CB(skb)->frag0 += hlen; NAPI_GRO_CB(skb)->frag0_len -= hlen; @@ -8073,7 +8089,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { @@ -8093,7 +8109,7 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", @@ -8633,6 +8649,9 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* napi_busy_loop stats accounting wants this */ + dev_net_set(dev, &init_net); + /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. @@ -8731,7 +8750,7 @@ static void netdev_wait_allrefs(struct net_device *dev) refcnt = netdev_refcnt_read(dev); - if (time_after(jiffies, warning_time + 10 * HZ)) { + if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, refcnt); warning_time = jiffies; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index aeabc4831fca..996813f345d5 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -880,8 +880,13 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops->get_regs_len) - info.regdump_len = ops->get_regs_len(dev); + if (ops->get_regs_len) { + int ret = ops->get_regs_len(dev); + + if (ret > 0) + info.regdump_len = ret; + } + if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); @@ -1424,6 +1429,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) return -EFAULT; reglen = ops->get_regs_len(dev); + if (reglen <= 0) + return reglen; + if (regs.len > reglen) regs.len = reglen; @@ -1434,13 +1442,16 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) return -ENOMEM; } + if (regs.len < reglen) + reglen = regs.len; + ops->get_regs(dev, ®s, regbuf); ret = -EFAULT; if (copy_to_user(useraddr, ®s, sizeof(regs))) goto out; useraddr += offsetof(struct ethtool_regs, data); - if (regbuf && copy_to_user(useraddr, regbuf, regs.len)) + if (copy_to_user(useraddr, regbuf, reglen)) goto out; ret = 0; @@ -1863,11 +1874,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) WARN_ON_ONCE(!ret); gstrings.len = ret; - data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); - if (gstrings.len && !data) - return -ENOMEM; - __ethtool_get_strings(dev, gstrings.string_set, data); + if (gstrings.len) { + data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); + if (!data) + return -ENOMEM; + + __ethtool_get_strings(dev, gstrings.string_set, data); + } else { + data = NULL; + } ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) @@ -1963,11 +1979,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) return -EFAULT; stats.n_stats = n_stats; - data = vzalloc(array_size(n_stats, sizeof(u64))); - if (n_stats && !data) - return -ENOMEM; - ops->get_ethtool_stats(dev, &stats, data); + if (n_stats) { + data = vzalloc(array_size(n_stats, sizeof(u64))); + if (!data) + return -ENOMEM; + ops->get_ethtool_stats(dev, &stats, data); + } else { + data = NULL; + } ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) @@ -2007,16 +2027,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) return -EFAULT; stats.n_stats = n_stats; - data = vzalloc(array_size(n_stats, sizeof(u64))); - if (n_stats && !data) - return -ENOMEM; - if (dev->phydev && !ops->get_ethtool_phy_stats) { - ret = phy_ethtool_get_stats(dev->phydev, &stats, data); - if (ret < 0) - return ret; + if (n_stats) { + data = vzalloc(array_size(n_stats, sizeof(u64))); + if (!data) + return -ENOMEM; + + if (dev->phydev && !ops->get_ethtool_phy_stats) { + ret = phy_ethtool_get_stats(dev->phydev, &stats, data); + if (ret < 0) + goto out; + } else { + ops->get_ethtool_phy_stats(dev, &stats, data); + } } else { - ops->get_ethtool_phy_stats(dev, &stats, data); + data = NULL; } ret = -EFAULT; diff --git a/net/core/failover.c b/net/core/failover.c index 4a92a98ccce9..b5cd3c727285 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) diff --git a/net/core/filter.c b/net/core/filter.c index 86e2739dad96..2dd1f2eef4fa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2018,18 +2018,19 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { - /* skb->mac_len is not set on normal egress */ - unsigned int mlen = skb->network_header - skb->mac_header; + unsigned int mlen = skb_network_offset(skb); - __skb_pull(skb, mlen); + if (mlen) { + __skb_pull(skb, mlen); - /* At ingress, the mac header has already been pulled once. - * At egress, skb_pospull_rcsum has to be done in case that - * the skb is originated from ingress (i.e. a forwarded skb) - * to ensure that rcsum starts at net header. - */ - if (!skb_at_tc_ingress(skb)) - skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + /* At ingress, the mac header has already been pulled once. + * At egress, skb_pospull_rcsum has to be done in case that + * the skb is originated from ingress (i.e. a forwarded skb) + * to ensure that rcsum starts at net header. + */ + if (!skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? @@ -2613,8 +2614,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2655,8 +2655,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2781,8 +2780,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2811,8 +2809,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -3908,10 +3905,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; @@ -3929,7 +3928,10 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, sk->sk_rcvlowat = val ? : 1; break; case SO_MARK: - sk->sk_mark = val; + if (sk->sk_mark != val) { + sk->sk_mark = val; + sk_dst_reset(sk); + } break; default: ret = -EINVAL; @@ -4000,7 +4002,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: - if (val <= 0 || tp->data_segs_out > 0) + if (val <= 0 || tp->data_segs_out > tp->syn_data) ret = -EINVAL; else tp->snd_cwnd = val; diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index c48e46759e23..8bab88738691 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -256,7 +256,6 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats, for_each_possible_cpu(i) { const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i); - qstats->qlen = 0; qstats->backlog += qcpu->backlog; qstats->drops += qcpu->drops; qstats->requeues += qcpu->requeues; @@ -272,7 +271,6 @@ void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, if (cpu) { __gnet_stats_copy_queue_cpu(qstats, cpu); } else { - qstats->qlen = q->qlen; qstats->backlog = q->backlog; qstats->drops = q->drops; qstats->requeues = q->requeues; diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 4b54e5f107c6..e095fb871d91 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -13,22 +13,36 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct gro_cell *cell; + int res; - if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) - return netif_rx(skb); + rcu_read_lock(); + if (unlikely(!(dev->flags & IFF_UP))) + goto drop; + + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { + res = netif_rx(skb); + goto unlock; + } cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { +drop: atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); - return NET_RX_DROP; + res = NET_RX_DROP; + goto unlock; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); - return NET_RX_SUCCESS; + + res = NET_RX_SUCCESS; + +unlock: + rcu_read_unlock(); + return res; } EXPORT_SYMBOL(gro_cells_receive); @@ -84,6 +98,7 @@ void gro_cells_destroy(struct gro_cells *gcells) for_each_possible_cpu(i) { struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); + napi_disable(&cell->napi); netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 3e85437f7106..a648568c5e8f 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -63,6 +63,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, lwt->name ? : "<unknown>"); ret = BPF_OK; } else { + skb_reset_mac_header(skb); ret = skb_do_redirect(skb); if (ret == 0) ret = BPF_REDIRECT; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 4e07824eec5e..4e4ac77c6816 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -30,6 +30,7 @@ #include <linux/times.h> #include <net/net_namespace.h> #include <net/neighbour.h> +#include <net/arp.h> #include <net/dst.h> #include <net/sock.h> #include <net/netevent.h> @@ -2536,7 +2537,13 @@ int neigh_xmit(int index, struct net_device *dev, if (!tbl) goto out; rcu_read_lock_bh(); - neigh = __neigh_lookup_noref(tbl, addr, dev); + if (index == NEIGH_ARP_TABLE) { + u32 key = *((u32 *)addr); + + neigh = __ipv4_neigh_lookup_noref(dev, key); + } else { + neigh = __neigh_lookup_noref(tbl, addr, dev); + } if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index bd67c4d0fcfd..bf9a3b6ac885 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -934,6 +934,8 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) if (error) return error; + dev_hold(queue->dev); + if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) { @@ -943,7 +945,6 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) } kobject_uevent(kobj, KOBJ_ADD); - dev_hold(queue->dev); return error; } @@ -1472,6 +1473,8 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) if (error) return error; + dev_hold(queue->dev); + #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); if (error) { @@ -1481,7 +1484,6 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) #endif kobject_uevent(kobj, KOBJ_ADD); - dev_hold(queue->dev); return 0; } @@ -1547,6 +1549,9 @@ static int register_queue_kobjects(struct net_device *dev) error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); +#ifdef CONFIG_SYSFS + kset_unregister(dev->queues_kset); +#endif return error; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 670c84b1bfc2..7320f0844a50 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->count, 1); refcount_set(&net->passive, 1); + get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b71d9eef334e..9d472d626aaa 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3065,7 +3065,13 @@ static int pktgen_wait_thread_run(struct pktgen_thread *t) { while (thread_is_running(t)) { + /* note: 't' will still be around even after the unlock/lock + * cycle because pktgen_thread threads are only cleared at + * net exit + */ + mutex_unlock(&pktgen_thread_lock); msleep_interruptible(100); + mutex_lock(&pktgen_thread_lock); if (signal_pending(current)) goto signal; @@ -3080,6 +3086,10 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn) struct pktgen_thread *t; int sig = 1; + /* prevent from racing with rmmod */ + if (!try_module_get(THIS_MODULE)) + return sig; + mutex_lock(&pktgen_thread_lock); list_for_each_entry(t, &pn->pktgen_threads, th_list) { @@ -3093,6 +3103,7 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn) t->control |= (T_STOP); mutex_unlock(&pktgen_thread_lock); + module_put(THIS_MODULE); return sig; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ebde98b565e9..3932eed379a4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1496,14 +1496,15 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev) return ret; } -static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev) +static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev, + bool force) { int ifindex = dev_get_iflink(dev); - if (dev->ifindex == ifindex) - return 0; + if (force || dev->ifindex != ifindex) + return nla_put_u32(skb, IFLA_LINK, ifindex); - return nla_put_u32(skb, IFLA_LINK, ifindex); + return 0; } static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, @@ -1520,6 +1521,8 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, const struct net_device *dev, struct net *src_net) { + bool put_iflink = false; + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) { struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); @@ -1528,10 +1531,12 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) return -EMSGSIZE; + + put_iflink = true; } } - return 0; + return nla_put_iflink(skb, dev, put_iflink); } static int rtnl_fill_link_af(struct sk_buff *skb, @@ -1617,7 +1622,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif - nla_put_iflink(skb, dev) || put_master_ifindex(skb, dev) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 001de1882f36..e20b1f25a273 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -356,6 +356,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) */ void *netdev_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __netdev_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(netdev_alloc_frag); @@ -373,6 +375,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) void *napi_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); @@ -3843,7 +3847,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int delta_truesize; struct sk_buff *lp; - if (unlikely(p->len + len >= 65536)) + if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) return -E2BIG; lp = NAPI_GRO_CB(p)->last; @@ -5082,7 +5086,8 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { - int mac_len; + int mac_len, meta_len; + void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); @@ -5094,6 +5099,13 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } + + meta_len = skb_metadata_len(skb); + if (meta_len) { + meta = skb_metadata_end(skb) - meta_len; + memmove(meta + VLAN_HLEN, meta, meta_len); + } + skb->mac_header += VLAN_HLEN; return skb; } @@ -5273,7 +5285,6 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long chunk; struct sk_buff *skb; struct page *page; - gfp_t gfp_head; int i; *errcode = -EMSGSIZE; @@ -5283,12 +5294,8 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, if (npages > MAX_SKB_FRAGS) return NULL; - gfp_head = gfp_mask; - if (gfp_head & __GFP_DIRECT_RECLAIM) - gfp_head |= __GFP_RETRY_MAYFAIL; - *errcode = -ENOBUFS; - skb = alloc_skb(header_len, gfp_head); + skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; diff --git a/net/core/sock.c b/net/core/sock.c index 748765e35423..c9668dcb5eb9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -698,6 +698,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); + sk_dst_reset(sk); break; case SO_BROADCAST: sock_valbool_flag(sk, SOCK_BROADCAST, valbool); @@ -2803,6 +2804,9 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; +#if BITS_PER_LONG==32 + seqlock_init(&sk->sk_stamp_seq); +#endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL @@ -2902,12 +2906,13 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) struct timeval tv; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sk->sk_stamp); + tv = ktime_to_timeval(sock_read_timestamp(sk)); if (tv.tv_sec == -1) return -ENOENT; if (tv.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - tv = ktime_to_timeval(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + tv = ktime_to_timeval(kt); } return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0; } @@ -2918,11 +2923,12 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) struct timespec ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sk->sk_stamp); + ts = ktime_to_timespec(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); ts = ktime_to_timespec(sk->sk_stamp); } return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b1a2c5e38530..37b4667128a3 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -279,7 +279,6 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } -# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -290,7 +289,6 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } -# endif #endif static struct ctl_table net_core_table[] = { @@ -397,6 +395,14 @@ static struct ctl_table net_core_table[] = { .extra2 = &one, }, # endif + { + .procname = "bpf_jit_limit", + .data = &bpf_jit_limit, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax_bpf_restricted, + .extra1 = &one, + }, #endif { .procname = "netdev_tstamp_prequeue", diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6eb837a47b5c..baaaeb2b2c42 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } @@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6344f1b18a6a..58a401e9cf09 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -433,8 +433,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; - newnp->mcast_oif = inet6_iif(skb); - newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->mcast_oif = inet_iif(skb); + newnp->mcast_hops = ip_hdr(skb)->ttl; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 9f3209ff7ffd..601534a5bfe8 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -293,15 +293,22 @@ static int __init dsa_init_module(void) rc = dsa_slave_register_notifier(); if (rc) - return rc; + goto register_notifier_fail; rc = dsa_legacy_register(); if (rc) - return rc; + goto legacy_register_fail; dev_add_pack(&dsa_pack_type); return 0; + +legacy_register_fail: + dsa_slave_unregister_notifier(); +register_notifier_fail: + destroy_workqueue(dsa_owq); + + return rc; } module_init(dsa_init_module); diff --git a/net/dsa/master.c b/net/dsa/master.c index c90ee3227dea..aae478d61101 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -158,6 +158,8 @@ static void dsa_master_ethtool_teardown(struct net_device *dev) cpu_dp->orig_ethtool_ops = NULL; } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { /* If we use a tagging format that doesn't have an ethertype @@ -167,6 +169,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); return dsa_master_ethtool_setup(dev); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1c45c1d6d241..b39720d0995d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct net_device *master = dsa_slave_to_master(dev); - - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(master, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(master, + dev->flags & IFF_PROMISC ? 1 : -1); + } } static void dsa_slave_set_rx_mode(struct net_device *dev) @@ -639,7 +642,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +662,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index b8cd43c9ed5b..a97bf326b231 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -94,9 +94,8 @@ static void hsr_check_announce(struct net_device *hsr_dev, && (old_operstate != IF_OPER_UP)) { /* Went up */ hsr->announce_count = 0; - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); - add_timer(&hsr->announce_timer); + mod_timer(&hsr->announce_timer, + jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP)) @@ -332,6 +331,7 @@ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; + unsigned long interval; hsr = from_timer(hsr, t, announce_timer); @@ -343,18 +343,16 @@ static void hsr_announce(struct timer_list *t) hsr->protVersion); hsr->announce_count++; - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); + interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); } else { send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK, hsr->protVersion); - hsr->announce_timer.expires = jiffies + - msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); + interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); } if (is_admin_up(master->dev)) - add_timer(&hsr->announce_timer); + mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } @@ -486,7 +484,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - return res; + goto err_add_port; res = register_netdevice(hsr_dev); if (res) @@ -506,6 +504,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], fail: hsr_for_each_port(hsr, port) hsr_del_port(port); +err_add_port: + hsr_del_node(&hsr->self_node_db); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 286ceb41ac0c..9af16cb68f76 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -124,6 +124,18 @@ int hsr_create_self_node(struct list_head *self_node_db, return 0; } +void hsr_del_node(struct list_head *self_node_db) +{ + struct hsr_node *node; + + rcu_read_lock(); + node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); + rcu_read_unlock(); + if (node) { + list_del_rcu(&node->mac_list); + kfree(node); + } +} /* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA; * seq_out is used to initialize filtering of outgoing duplicate frames diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 370b45998121..531fd3dfcac1 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -16,6 +16,7 @@ struct hsr_node; +void hsr_del_node(struct list_head *self_node_db); struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index ca53efa17be1..8bec827081cd 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -48,6 +48,9 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev, const struct ipv6hdr *hdr = ipv6_hdr(skb); struct neighbour *n; + if (!daddr) + return -EINVAL; + /* TODO: * if this package isn't ipv6 one, where should it be routed? */ diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 777fa3b7fb13..f0165c5f376b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level) case CIPSO_V4_MAP_PASS: return 0; case CIPSO_V4_MAP_TRANS: - if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL) + if ((level < doi_def->map.std->lvl.cipso_size) && + (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)) return 0; break; } @@ -1735,13 +1736,26 @@ validate_return: */ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { + unsigned char optbuf[sizeof(struct ip_options) + 40]; + struct ip_options *opt = (struct ip_options *)optbuf; + if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; + /* + * We might be called above the IP layer, + * so we can not use icmp_send and IPCB here. + */ + + memset(opt, 0, sizeof(struct ip_options)); + opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + return; + if (gateway) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt); else - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt); } /** diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 97689012b357..114f9def1ec5 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -223,7 +223,7 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto) tail[plen - 1] = proto; } -static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) +static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { int encap_type; struct udphdr *uh; @@ -231,6 +231,7 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru __be16 sport, dport; struct xfrm_encap_tmpl *encap = x->encap; struct ip_esp_hdr *esph = esp->esph; + unsigned int len; spin_lock_bh(&x->lock); sport = encap->encap_sport; @@ -238,11 +239,14 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru encap_type = encap->encap_type; spin_unlock_bh(&x->lock); + len = skb->len + esp->tailen - skb_transport_offset(skb); + if (len + sizeof(struct iphdr) >= IP_MAX_MTU) + return -EMSGSIZE; + uh = (struct udphdr *)esph; uh->source = sport; uh->dest = dport; - uh->len = htons(skb->len + esp->tailen - - skb_transport_offset(skb)); + uh->len = htons(len); uh->check = 0; switch (encap_type) { @@ -259,6 +263,8 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru *skb_mac_header(skb) = IPPROTO_UDP; esp->esph = esph; + + return 0; } int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) @@ -272,8 +278,12 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * int tailen = esp->tailen; /* this is non-NULL only with UDP Encapsulation */ - if (x->encap) - esp_output_udp_encap(x, skb, esp); + if (x->encap) { + int err = esp_output_udp_encap(x, skb, esp); + + if (err < 0) + return err; + } if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { @@ -325,7 +335,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0113993e9b2c..dae743b649c1 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -203,7 +203,7 @@ static void fib_flush(struct net *net) struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) - flushed += fib_table_flush(net, tb); + flushed += fib_table_flush(net, tb, false); } if (flushed) @@ -700,6 +700,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_GATEWAY: cfg->fc_gw = nla_get_be32(attr); break; + case RTA_VIA: + NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute"); + err = -EINVAL; + goto errout; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; @@ -1357,7 +1361,7 @@ static void ip_fib_net_exit(struct net *net) hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); - fib_table_flush(net, tb); + fib_table_flush(net, tb, true); fib_free_table(tb); } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5bc0c89e81e4..3955a6d7ea66 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1856,7 +1856,7 @@ void fib_table_flush_external(struct fib_table *tb) } /* Caller must hold RTNL. */ -int fib_table_flush(struct net *net, struct fib_table *tb) +int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; @@ -1904,8 +1904,17 @@ int fib_table_flush(struct net *net, struct fib_table *tb) hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; - if (!fi || !(fi->fib_flags & RTNH_F_DEAD) || - tb->tb_id != fa->tb_id) { + if (!fi || tb->tb_id != fa->tb_id || + (!(fi->fib_flags & RTNH_F_DEAD) && + !fib_props[fa->fa_type].error)) { + slen = fa->fa_slen; + continue; + } + + /* Do not flush error routes if network namespace is + * not being dismantled + */ + if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 500a59906b87..854ff1e4c41f 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -120,6 +120,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) struct guehdr *guehdr; void *data; u16 doffset = 0; + u8 proto_ctype; if (!fou) return 1; @@ -211,13 +212,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr); + proto_ctype = guehdr->proto_ctype; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); if (iptunnel_pull_offloads(skb)) goto drop; - return -guehdr->proto_ctype; + return -proto_ctype; drop: kfree_skb(skb); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index b798862b6be5..f21ea6125fc2 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -25,6 +25,7 @@ #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> +#include <net/erspan.h> #include <net/icmp.h> #include <net/route.h> @@ -118,6 +119,22 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, hdr_len += 4; } tpi->hdr_len = hdr_len; + + /* ERSPAN ver 1 and 2 protocol sets GRE key field + * to 0 and sets the configured key in the + * inner erspan header field + */ + if (greh->protocol == htons(ETH_P_ERSPAN) || + greh->protocol == htons(ETH_P_ERSPAN2)) { + struct erspan_base_hdr *ershdr; + + if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) + return -EINVAL; + + ershdr = (struct erspan_base_hdr *)options; + tpi->key = cpu_to_be32(get_session_id(ershdr)); + } + return hdr_len; } EXPORT_SYMBOL(gre_parse_header); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4fe69e685569..1770ff1638bc 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -578,7 +578,8 @@ relookup_failed: * MUST reply to only the first fragment. */ -void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) +void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, + const struct ip_options *opt) { struct iphdr *iph; int room; @@ -699,7 +700,7 @@ 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(net, &icmp_param.replyopts.opt.opt, skb_in)) + if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) goto out_unlock; @@ -750,7 +751,7 @@ out_bh_enable: local_bh_enable(); out:; } -EXPORT_SYMBOL(icmp_send); +EXPORT_SYMBOL(__icmp_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 4da39446da2d..d187ee8156a1 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -190,6 +190,17 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +static void ip_sf_list_clear_all(struct ip_sf_list *psf) +{ + struct ip_sf_list *next; + + while (psf) { + next = psf->sf_next; + kfree(psf); + psf = next; + } +} + #ifdef CONFIG_IP_MULTICAST /* @@ -635,6 +646,13 @@ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) } } +static void kfree_pmc(struct ip_mc_list *pmc) +{ + ip_sf_list_clear_all(pmc->sources); + ip_sf_list_clear_all(pmc->tomb); + kfree(pmc); +} + static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; @@ -671,7 +689,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); - kfree(pmc); + kfree_pmc(pmc); } else pmc_prev = pmc; } @@ -1201,14 +1219,18 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; + pmc->tomb = NULL; + im->sources = pmc->sources; + pmc->sources = NULL; + for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; } else { im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; } in_dev_put(pmc->interface); - kfree(pmc); + kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } @@ -1229,21 +1251,18 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); - kfree(pmc); + kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { - struct ip_sf_list *psf, *psf_next; + struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); - for (; psf; psf = psf_next) { - psf_next = psf->sf_next; - kfree(psf); - } + ip_sf_list_clear_all(psf); } rcu_read_unlock(); } @@ -2114,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, static void ip_mc_clear_src(struct ip_mc_list *pmc) { - struct ip_sf_list *psf, *nextpsf, *tomb, *sources; + struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; @@ -2126,14 +2145,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); - for (psf = tomb; psf; psf = nextpsf) { - nextpsf = psf->sf_next; - kfree(psf); - } - for (psf = sources; psf; psf = nextpsf) { - nextpsf = psf->sf_next; - kfree(psf); - } + ip_sf_list_clear_all(tomb); + ip_sf_list_clear_all(sources); } /* Join a multicast group diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 4e5bc4b2f14e..5731670c560b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk, + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; #ifdef CONFIG_SOCK_CGROUP_DATA classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; @@ -998,7 +1006,9 @@ next_chunk: if (!inet_diag_bc_sk(bc, sk)) goto next_normal; - sock_hold(sk); + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + goto next_normal; + num_arr[accum] = num; sk_arr[accum] = sk; if (++accum == SKARR_SZ) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 760a9e52e02b..9f69411251d0 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -25,6 +25,62 @@ #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> +#include <net/ip.h> +#include <net/ipv6.h> + +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + }; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void fragcb_clear(struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void fragrun_append_to_last(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + fragcb_clear(skb); + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + fragcb_clear(skb); + + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + q->fragments_tail = skb; + q->last_run_head = skb; +} /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. @@ -123,6 +179,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } +unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -224,3 +302,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) return fq; } EXPORT_SYMBOL(inet_frag_find); + +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end) +{ + struct sk_buff *last = q->fragments_tail; + + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * Duplicates, however, should be ignored (i.e. skb dropped, but the + * queue/fragments kept for later reassembly). + */ + if (!last) + fragrun_create(q, skb); /* First fragment. */ + else if (last->ip_defrag_offset + last->len < end) { + /* This is the common case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < last->ip_defrag_offset + last->len) + return IPFRAG_OVERLAP; + if (offset == last->ip_defrag_offset + last->len) + fragrun_append_to_last(q, skb); + else + fragrun_create(q, skb); + } else { + /* Binary search. Note that skb can become the first fragment, + * but not the last (covered above). + */ + struct rb_node **rbn, *parent; + + rbn = &q->rb_fragments.rb_node; + do { + struct sk_buff *curr; + int curr_run_end; + + parent = *rbn; + curr = rb_to_skb(parent); + curr_run_end = curr->ip_defrag_offset + + FRAG_CB(curr)->frag_run_len; + if (end <= curr->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= curr_run_end) + rbn = &parent->rb_right; + else if (offset >= curr->ip_defrag_offset && + end <= curr_run_end) + return IPFRAG_DUP; + else + return IPFRAG_OVERLAP; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. + */ + fragcb_clear(skb); + rb_link_node(&skb->rbnode, parent, rbn); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + } + + skb->ip_defrag_offset = offset; + + return IPFRAG_OK; +} +EXPORT_SYMBOL(inet_frag_queue_insert); + +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent) +{ + struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); + struct sk_buff **nextp; + int delta; + + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); + if (!fp) + return NULL; + FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; + if (RB_EMPTY_NODE(&skb->rbnode)) + FRAG_CB(parent)->next_frag = fp; + else + rb_replace_node(&skb->rbnode, &fp->rbnode, + &q->rb_fragments); + if (q->fragments_tail == skb) + q->fragments_tail = fp; + skb_morph(skb, head); + FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + consume_skb(head); + head = skb; + } + WARN_ON(head->ip_defrag_offset != 0); + + delta = -head->truesize; + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + return NULL; + + delta += head->truesize; + if (delta) + add_frag_mem_limit(q->net, delta); + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + return NULL; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->data_len = head->data_len - plen; + clone->len = clone->data_len; + head->truesize += clone->truesize; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + add_frag_mem_limit(q->net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; + } + + return nextp; +} +EXPORT_SYMBOL(inet_frag_reasm_prepare); + +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data) +{ + struct sk_buff **nextp = (struct sk_buff **)reasm_data; + struct rb_node *rbn; + struct sk_buff *fp; + + skb_push(head, head->data - skb_network_header(head)); + + /* Traverse the tree in order, to build frag_list. */ + fp = FRAG_CB(head)->next_frag; + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &q->rb_fragments); + while (rbn || fp) { + /* fp points to the next sk_buff in the current run; + * rbn points to the next run. + */ + /* Go through the current run. */ + while (fp) { + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + fp = FRAG_CB(fp)->next_frag; + } + /* Move to the next run. */ + if (rbn) { + struct rb_node *rbnext = rb_next(rbn); + + fp = rb_to_skb(rbn); + rb_erase(rbn, &q->rb_fragments); + rbn = rbnext; + } + } + sub_frag_mem_limit(q->net, head->truesize); + + *nextp = NULL; + skb_mark_not_on_list(head); + head->prev = NULL; + head->tstamp = q->stamp; +} +EXPORT_SYMBOL(inet_frag_reasm_finish); + +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) +{ + struct sk_buff *head; + + if (q->fragments) { + head = q->fragments; + q->fragments = head->next; + } else { + struct sk_buff *skb; + + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == q->fragments_tail) + q->fragments_tail = NULL; + + sub_frag_mem_limit(q->net, head->truesize); + + return head; +} +EXPORT_SYMBOL(inet_frag_pull_head); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d757b9642d0d..be778599bfed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; + p->n_redirects = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first * calculation of tokens is at its maximum. */ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 32662e9e5d21..d5984d31ab93 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -72,6 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s if (unlikely(opt->optlen)) ip_forward_options(skb); + skb->tstamp = 0; return dst_output(net, sk, skb); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index f686d7761acb..5a1d39e32196 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,57 +57,6 @@ */ static const char ip_frag_cache_name[] = "ip4-frags"; -/* Use skb->cb to track consecutive/adjacent fragments coming at - * the end of the queue. Nodes in the rb-tree queue will - * contain "runs" of one or more adjacent fragments. - * - * Invariants: - * - next_frag is NULL at the tail of a "run"; - * - the head of a "run" has the sum of all fragment lengths in frag_run_len. - */ -struct ipfrag_skb_cb { - struct inet_skb_parm h; - struct sk_buff *next_frag; - int frag_run_len; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - -static void ip4_frag_init_run(struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); - - FRAG_CB(skb)->next_frag = NULL; - FRAG_CB(skb)->frag_run_len = skb->len; -} - -/* Append skb to the last "run". */ -static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, - struct sk_buff *skb) -{ - RB_CLEAR_NODE(&skb->rbnode); - FRAG_CB(skb)->next_frag = NULL; - - FRAG_CB(q->last_run_head)->frag_run_len += skb->len; - FRAG_CB(q->fragments_tail)->next_frag = skb; - q->fragments_tail = skb; -} - -/* Create a new "run" with the skb. */ -static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) -{ - if (q->last_run_head) - rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, - &q->last_run_head->rbnode.rb_right); - else - rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); - rb_insert_color(&skb->rbnode, &q->rb_fragments); - - ip4_frag_init_run(skb); - q->fragments_tail = skb; - q->last_run_head = skb; -} - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -212,27 +161,9 @@ static void ip_expire(struct timer_list *t) * pull the head out of the tree in order to be able to * deal with head->dev. */ - if (qp->q.fragments) { - head = qp->q.fragments; - qp->q.fragments = head->next; - } else { - head = skb_rb_first(&qp->q.rb_fragments); - if (!head) - goto out; - if (FRAG_CB(head)->next_frag) - rb_replace_node(&head->rbnode, - &FRAG_CB(head)->next_frag->rbnode, - &qp->q.rb_fragments); - else - rb_erase(&head->rbnode, &qp->q.rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } - if (head == qp->q.fragments_tail) - qp->q.fragments_tail = NULL; - - sub_frag_mem_limit(qp->q.net, head->truesize); - + head = inet_frag_pull_head(&qp->q); + if (!head) + goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -345,12 +276,10 @@ static int ip_frag_reinit(struct ipq *qp) static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct rb_node **rbn, *parent; - struct sk_buff *skb1, *prev_tail; + int ihl, end, flags, offset; + struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; - int flags, offset; - int ihl, end; int err = -ENOENT; u8 ecn; @@ -382,7 +311,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) - goto err; + goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { @@ -394,75 +323,33 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_qp; qp->q.len = end; } } if (end == offset) - goto err; + goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) - goto err; + goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) - goto err; + goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - * - * We do the same here for IPv4 (and increment an snmp counter). - */ - - /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; - if (!prev_tail) - ip4_frag_create_run(&qp->q, skb); /* First fragment. */ - else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { - /* This is the common case: skb goes to the end. */ - /* Detect and discard overlaps. */ - if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto discard_qp; - if (offset == prev_tail->ip_defrag_offset + prev_tail->len) - ip4_frag_append_to_last_run(&qp->q, skb); - else - ip4_frag_create_run(&qp->q, skb); - } else { - /* Binary search. Note that skb can become the first fragment, - * but not the last (covered above). - */ - rbn = &qp->q.rb_fragments.rb_node; - do { - parent = *rbn; - skb1 = rb_to_skb(parent); - if (end <= skb1->ip_defrag_offset) - rbn = &parent->rb_left; - else if (offset >= skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len) - rbn = &parent->rb_right; - else /* Found an overlap with skb1. */ - goto discard_qp; - } while (*rbn); - /* Here we have parent properly set, and rbn pointing to - * one of its NULL left/right children. Insert skb. - */ - ip4_frag_init_run(skb); - rb_link_node(&skb->rbnode, parent, rbn); - rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - } + err = inet_frag_queue_insert(&qp->q, skb, offset, end); + if (err) + goto insert_error; if (dev) qp->iif = dev->ifindex; - skb->ip_defrag_offset = offset; qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; @@ -487,16 +374,24 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; + if (err) + inet_frag_kill(&qp->q); return err; } skb_dst_drop(skb); return -EINPROGRESS; -discard_qp: - inet_frag_kill(&qp->q); +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); +discard_qp: + inet_frag_kill(&qp->q); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -508,13 +403,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); - struct sk_buff **nextp; /* To build frag_list. */ - struct rb_node *rbn; - int len; - int ihlen; - int delta; - int err; + void *reasm_data; + int len, err; u8 ecn; ipq_kill(qp); @@ -524,117 +414,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, err = -EINVAL; goto out_fail; } - /* Make the one we just received the head. */ - if (head != skb) { - fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - goto out_nomem; - FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; - if (RB_EMPTY_NODE(&skb->rbnode)) - FRAG_CB(prev_tail)->next_frag = fp; - else - rb_replace_node(&skb->rbnode, &fp->rbnode, - &qp->q.rb_fragments); - if (qp->q.fragments_tail == skb) - qp->q.fragments_tail = fp; - skb_morph(skb, head); - FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; - rb_replace_node(&head->rbnode, &skb->rbnode, - &qp->q.rb_fragments); - consume_skb(head); - head = skb; - } - - WARN_ON(head->ip_defrag_offset != 0); - /* Allocate a new buffer for the datagram. */ - ihlen = ip_hdrlen(head); - len = ihlen + qp->q.len; + /* Make the one we just received the head. */ + reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); + if (!reasm_data) + goto out_nomem; + len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(qp->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_nomem; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->truesize += clone->truesize; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(qp->q.net, clone->truesize); - skb_shinfo(head)->frag_list = clone; - nextp = &clone->next; - } else { - nextp = &skb_shinfo(head)->frag_list; - } - - skb_push(head, head->data - skb_network_header(head)); + inet_frag_reasm_finish(&qp->q, skb, reasm_data); - /* Traverse the tree in order, to build frag_list. */ - fp = FRAG_CB(head)->next_frag; - rbn = rb_next(&head->rbnode); - rb_erase(&head->rbnode, &qp->q.rb_fragments); - while (rbn || fp) { - /* fp points to the next sk_buff in the current run; - * rbn points to the next run. - */ - /* Go through the current run. */ - while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; - } - /* Move to the next run. */ - if (rbn) { - struct rb_node *rbnext = rb_next(rbn); + skb->dev = dev; + IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - fp = rb_to_skb(rbn); - rb_erase(rbn, &qp->q.rb_fragments); - rbn = rbnext; - } - } - sub_frag_mem_limit(qp->q.net, head->truesize); - - *nextp = NULL; - head->next = NULL; - head->prev = NULL; - head->dev = dev; - head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - - iph = ip_hdr(head); + iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; @@ -647,7 +443,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { - IPCB(head)->flags |= IPSKB_FRAG_PMTU; + IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; @@ -745,28 +541,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_check_defrag); -unsigned int inet_frag_rbtree_purge(struct rb_root *root) -{ - struct rb_node *p = rb_first(root); - unsigned int sum = 0; - - while (p) { - struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - - p = rb_next(p); - rb_erase(&skb->rbnode, root); - while (skb) { - struct sk_buff *next = FRAG_CB(skb)->next_frag; - - sum += skb->truesize; - kfree_skb(skb); - skb = next; - } - } - return sum; -} -EXPORT_SYMBOL(inet_frag_rbtree_purge); - #ifdef CONFIG_SYSCTL static int dist_min; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8cce0e9ea08c..3c734832bb7c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -260,7 +260,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; - struct erspan_metadata *pkt_md; struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -269,20 +268,11 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int len; itn = net_generic(net, erspan_net_id); - len = gre_hdr_len + sizeof(*ershdr); - - /* Check based hdr len */ - if (unlikely(!pskb_may_pull(skb, len))) - return PACKET_REJECT; iph = ip_hdr(skb); ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; - /* The original GRE header does not have key field, - * Use ERSPAN 10-bit session ID as key. - */ - tpi->key = cpu_to_be32(get_session_id(ershdr)); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); @@ -292,9 +282,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; - ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); - pkt_md = (struct erspan_metadata *)(ershdr + 1); - if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), @@ -302,8 +289,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, goto drop; if (tunnel->collect_md) { + struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; - struct erspan_metadata *md; + unsigned char *gh; __be64 tun_id; __be16 flags; @@ -316,6 +304,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!tun_dst) return PACKET_REJECT; + /* skb can be uncloned in __iptunnel_pull_header, so + * old pkt_md is no longer valid and we need to reset + * it + */ + gh = skb_network_header(skb) + + skb_network_header_len(skb); + pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; @@ -570,8 +566,7 @@ err_free_skb: dev->stats.tx_dropped++; } -static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, - __be16 proto) +static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; @@ -579,10 +574,10 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, struct erspan_metadata *md; struct rtable *rt = NULL; bool truncate = false; + __be16 df, proto; struct flowi4 fl; int tunnel_hlen; int version; - __be16 df; int nhoff; int thoff; @@ -627,18 +622,20 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); + proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); + proto = htons(ETH_P_ERSPAN2); } else { goto err_free_rt; } gre_build_header(skb, 8, TUNNEL_SEQ, - htons(ETH_P_ERSPAN), 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(tunnel->o_seqno++)); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -677,6 +674,9 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; + if (!pskb_inet_may_pull(skb)) + goto free_skb; + if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; @@ -719,9 +719,13 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; + __be16 proto; + + if (!pskb_inet_may_pull(skb)) + goto free_skb; if (tunnel->collect_md) { - erspan_fb_xmit(skb, dev, skb->protocol); + erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } @@ -737,19 +741,22 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, } /* Push ERSPAN header */ - if (tunnel->erspan_ver == 1) + if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); - else if (tunnel->erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto free_skb; + } tunnel->parms.o_flags &= ~TUNNEL_KEY; - __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN)); + __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: @@ -763,6 +770,9 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); + if (!pskb_inet_may_pull(skb)) + goto free_skb; + if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; @@ -1457,12 +1467,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((t->erspan_ver == 1 || t->erspan_ver == 2) && + !t->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 27c863f6dd83..c3a0683e83df 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -258,11 +258,10 @@ int ip_local_deliver(struct sk_buff *skb) ip_local_deliver_finish); } -static inline bool ip_rcv_options(struct sk_buff *skb) +static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt; const struct iphdr *iph; - struct net_device *dev = skb->dev; /* It looks as overkill, because not all IP options require packet mangling. @@ -298,7 +297,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb) } } - if (ip_options_rcv_srr(skb)) + if (ip_options_rcv_srr(skb, dev)) goto drop; } @@ -308,11 +307,10 @@ drop: } static int ip_rcv_finish_core(struct net *net, struct sock *sk, - struct sk_buff *skb) + struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); - struct net_device *dev = skb->dev; struct rtable *rt; int err; @@ -355,7 +353,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, } #endif - if (iph->ihl > 5 && ip_rcv_options(skb)) + if (iph->ihl > 5 && ip_rcv_options(skb, dev)) goto drop; rt = skb_rtable(skb); @@ -401,6 +399,7 @@ drop_error: static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + struct net_device *dev = skb->dev; int ret; /* if ingress device is enslaved to an L3 master device pass the @@ -410,7 +409,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) if (!skb) return NET_RX_SUCCESS; - ret = ip_rcv_finish_core(net, sk, skb); + ret = ip_rcv_finish_core(net, sk, skb, dev); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; @@ -489,6 +488,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) goto drop; } + iph = ip_hdr(skb); skb->transport_header = skb->network_header + iph->ihl*4; /* Remove any debris in the socket control block */ @@ -549,6 +549,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { + struct net_device *dev = skb->dev; struct dst_entry *dst; skb_list_del_init(skb); @@ -558,7 +559,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, skb = l3mdev_ip_rcv(skb); if (!skb) continue; - if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP) + if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP) continue; dst = skb_dst(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ed194d46c00e..3db31bb9df50 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb) * If opt == NULL, then skb->data should point to IP header. */ -int ip_options_compile(struct net *net, - struct ip_options *opt, struct sk_buff *skb) +int __ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb, + __be32 *info) { __be32 spec_dst = htonl(INADDR_ANY); unsigned char *pp_ptr = NULL; @@ -468,11 +469,22 @@ eol: return 0; error: - if (skb) { - icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24)); - } + if (info) + *info = htonl((pp_ptr-iph)<<24); return -EINVAL; } + +int ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb) +{ + int ret; + __be32 info; + + ret = __ip_options_compile(net, opt, skb, &info); + if (ret != 0 && skb) + icmp_send(skb, ICMP_PARAMETERPROB, 0, info); + return ret; +} EXPORT_SYMBOL(ip_options_compile); /* @@ -600,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb) } } -int ip_options_rcv_srr(struct sk_buff *skb) +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; @@ -635,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); - err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); + err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9c4e72e9c60a..73894ed12a70 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; + to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..b7a26120d552 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -148,19 +148,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { + __be16 _ports[2], *ports; struct sockaddr_in sin; - __be16 *ports; - int end; - - end = skb_transport_offset(skb) + 4; - if (end > 0 && !pskb_may_pull(skb, end)) - return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ - ports = (__be16 *)skb_transport_header(skb); + ports = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_ports), &_ports); + if (!ports) + return; sin.sin_family = AF_INET; sin.sin_addr.s_addr = ip_hdr(skb)->daddr; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 284a22154b4e..c4f5602308ed 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -627,7 +627,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); - unsigned int inner_nhdr_len = 0; const struct iphdr *inner_iph; struct flowi4 fl4; u8 tos, ttl; @@ -637,14 +636,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, __be32 dst; bool connected; - /* ensure we can access the inner net header, for several users below */ - if (skb->protocol == htons(ETH_P_IP)) - inner_nhdr_len = sizeof(struct iphdr); - else if (skb->protocol == htons(ETH_P_IPV6)) - inner_nhdr_len = sizeof(struct ipv6hdr); - if (unlikely(!pskb_may_pull(skb, inner_nhdr_len))) - goto tx_error; - inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index f38cb21d773d..808f8d15c519 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -74,6 +74,33 @@ drop: return 0; } +static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + + skb->dev = tunnel->dev; + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + static int vti_rcv(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; @@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb) return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); } +static int vti_rcv_ipip(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0); +} + static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; @@ -241,6 +276,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); struct flowi fl; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { @@ -253,15 +291,18 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); break; default: - dev->stats.tx_errors++; - dev_kfree_skb(skb); - return NETDEV_TX_OK; + goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); return vti_xmit(skb, dev, &fl); + +tx_err: + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; } static int vti4_err(struct sk_buff *skb, u32 info) @@ -429,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .priority = 100, }; +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = vti_rcv_ipip, + .err_handler = vti4_err, + .priority = 0, +}; + static int __net_init vti_init_net(struct net *net) { int err; @@ -597,6 +644,13 @@ static int __init vti_init(void) if (err < 0) goto xfrm_proto_comp_failed; + msg = "ipip tunnel"; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: cant't register tunnel\n",__func__); + goto xfrm_tunnel_failed; + } + msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) @@ -605,6 +659,8 @@ static int __init vti_init(void) return err; rtnl_link_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel_failed: xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); @@ -620,6 +676,7 @@ pernet_dev_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5660adcf7a04..f6275aa19b6a 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -69,6 +69,8 @@ #include <net/nexthop.h> #include <net/switchdev.h> +#include <linux/nospec.h> + struct ipmr_rule { struct fib_rule common; }; @@ -1612,6 +1614,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; + vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { @@ -1686,6 +1689,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; + vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 2c8d313ae216..2fa196325988 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -56,18 +56,15 @@ struct clusterip_config { #endif enum clusterip_hashmode hash_mode; /* which hashing mode */ u_int32_t hash_initval; /* hash initialization */ - struct rcu_head rcu; - + struct rcu_head rcu; /* for call_rcu_bh */ + struct net *net; /* netns for pernet list */ char ifname[IFNAMSIZ]; /* device ifname */ - struct notifier_block notifier; /* refresh c->ifindex in it */ }; #ifdef CONFIG_PROC_FS static const struct file_operations clusterip_proc_fops; #endif -static unsigned int clusterip_net_id __read_mostly; - struct clusterip_net { struct list_head configs; /* lock protects the configs list */ @@ -75,19 +72,35 @@ struct clusterip_net { #ifdef CONFIG_PROC_FS struct proc_dir_entry *procdir; + /* mutex protects the config->pde*/ + struct mutex mutex; #endif }; +static unsigned int clusterip_net_id __read_mostly; +static inline struct clusterip_net *clusterip_pernet(struct net *net) +{ + return net_generic(net, clusterip_net_id); +} + static inline void clusterip_config_get(struct clusterip_config *c) { refcount_inc(&c->refcount); } - static void clusterip_config_rcu_free(struct rcu_head *head) { - kfree(container_of(head, struct clusterip_config, rcu)); + struct clusterip_config *config; + struct net_device *dev; + + config = container_of(head, struct clusterip_config, rcu); + dev = dev_get_by_name(config->net, config->ifname); + if (dev) { + dev_mc_del(dev, config->clustermac); + dev_put(dev); + } + kfree(config); } static inline void @@ -101,25 +114,24 @@ clusterip_config_put(struct clusterip_config *c) * entry(rule) is removed, remove the config from lists, but don't free it * yet, since proc-files could still be holding references */ static inline void -clusterip_config_entry_put(struct net *net, struct clusterip_config *c) +clusterip_config_entry_put(struct clusterip_config *c) { - struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_net *cn = clusterip_pernet(c->net); local_bh_disable(); if (refcount_dec_and_lock(&c->entries, &cn->lock)) { + list_del_rcu(&c->list); + spin_unlock(&cn->lock); + local_bh_enable(); /* In case anyone still accesses the file, the open/close * functions are also incrementing the refcount on their own, * so it's safe to remove the entry even if it's in use. */ #ifdef CONFIG_PROC_FS + mutex_lock(&cn->mutex); if (cn->procdir) proc_remove(c->pde); + mutex_unlock(&cn->mutex); #endif - list_del_rcu(&c->list); - spin_unlock(&cn->lock); - local_bh_enable(); - - unregister_netdevice_notifier(&c->notifier); - return; } local_bh_enable(); @@ -129,7 +141,7 @@ static struct clusterip_config * __clusterip_config_find(struct net *net, __be32 clusterip) { struct clusterip_config *c; - struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_net *cn = clusterip_pernet(net); list_for_each_entry_rcu(c, &cn->configs, list) { if (c->clusterip == clusterip) @@ -181,32 +193,37 @@ clusterip_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + struct clusterip_net *cn = clusterip_pernet(net); struct clusterip_config *c; - c = container_of(this, struct clusterip_config, notifier); - switch (event) { - case NETDEV_REGISTER: - if (!strcmp(dev->name, c->ifname)) { - c->ifindex = dev->ifindex; - dev_mc_add(dev, c->clustermac); - } - break; - case NETDEV_UNREGISTER: - if (dev->ifindex == c->ifindex) { - dev_mc_del(dev, c->clustermac); - c->ifindex = -1; - } - break; - case NETDEV_CHANGENAME: - if (!strcmp(dev->name, c->ifname)) { - c->ifindex = dev->ifindex; - dev_mc_add(dev, c->clustermac); - } else if (dev->ifindex == c->ifindex) { - dev_mc_del(dev, c->clustermac); - c->ifindex = -1; + spin_lock_bh(&cn->lock); + list_for_each_entry_rcu(c, &cn->configs, list) { + switch (event) { + case NETDEV_REGISTER: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } + break; + case NETDEV_UNREGISTER: + if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + case NETDEV_CHANGENAME: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } else if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; } - break; } + spin_unlock_bh(&cn->lock); return NOTIFY_DONE; } @@ -215,30 +232,44 @@ static struct clusterip_config * clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, __be32 ip, const char *iniface) { - struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_net *cn = clusterip_pernet(net); struct clusterip_config *c; + struct net_device *dev; int err; + if (iniface[0] == '\0') { + pr_info("Please specify an interface name\n"); + return ERR_PTR(-EINVAL); + } + c = kzalloc(sizeof(*c), GFP_ATOMIC); if (!c) return ERR_PTR(-ENOMEM); - strcpy(c->ifname, iniface); - c->ifindex = -1; - c->clusterip = ip; + dev = dev_get_by_name(net, iniface); + if (!dev) { + pr_info("no such interface %s\n", iniface); + kfree(c); + return ERR_PTR(-ENOENT); + } + c->ifindex = dev->ifindex; + strcpy(c->ifname, dev->name); memcpy(&c->clustermac, &i->clustermac, ETH_ALEN); + dev_mc_add(dev, c->clustermac); + dev_put(dev); + + c->clusterip = ip; c->num_total_nodes = i->num_total_nodes; clusterip_config_init_nodelist(c, i); c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; + c->net = net; refcount_set(&c->refcount, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { - spin_unlock_bh(&cn->lock); - kfree(c); - - return ERR_PTR(-EBUSY); + err = -EBUSY; + goto out_config_put; } list_add_rcu(&c->list, &cn->configs); @@ -250,9 +281,11 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, /* create proc dir entry */ sprintf(buffer, "%pI4", &ip); + mutex_lock(&cn->mutex); c->pde = proc_create_data(buffer, 0600, cn->procdir, &clusterip_proc_fops, c); + mutex_unlock(&cn->mutex); if (!c->pde) { err = -ENOMEM; goto err; @@ -260,22 +293,17 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, } #endif - c->notifier.notifier_call = clusterip_netdev_event; - err = register_netdevice_notifier(&c->notifier); - if (!err) { - refcount_set(&c->entries, 1); - return c; - } + refcount_set(&c->entries, 1); + return c; #ifdef CONFIG_PROC_FS - proc_remove(c->pde); err: #endif spin_lock_bh(&cn->lock); list_del_rcu(&c->list); +out_config_put: spin_unlock_bh(&cn->lock); clusterip_config_put(c); - return ERR_PTR(err); } @@ -475,34 +503,20 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) &e->ip.dst.s_addr); return -EINVAL; } else { - struct net_device *dev; - - if (e->ip.iniface[0] == '\0') { - pr_info("Please specify an interface name\n"); - return -EINVAL; - } - - dev = dev_get_by_name(par->net, e->ip.iniface); - if (!dev) { - pr_info("no such interface %s\n", - e->ip.iniface); - return -ENOENT; - } - dev_put(dev); - config = clusterip_config_init(par->net, cipinfo, e->ip.dst.s_addr, e->ip.iniface); if (IS_ERR(config)) return PTR_ERR(config); } - } + } else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN)) + return -EINVAL; ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); - clusterip_config_entry_put(par->net, config); + clusterip_config_entry_put(config); clusterip_config_put(config); return ret; } @@ -524,7 +538,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) /* if no more entries are referencing the config, remove it * from the list and destroy the proc entry */ - clusterip_config_entry_put(par->net, cipinfo->config); + clusterip_config_entry_put(cipinfo->config); clusterip_config_put(cipinfo->config); @@ -806,7 +820,7 @@ static const struct file_operations clusterip_proc_fops = { static int clusterip_net_init(struct net *net) { - struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_net *cn = clusterip_pernet(net); int ret; INIT_LIST_HEAD(&cn->configs); @@ -824,6 +838,7 @@ static int clusterip_net_init(struct net *net) pr_err("Unable to proc dir entry\n"); return -ENOMEM; } + mutex_init(&cn->mutex); #endif /* CONFIG_PROC_FS */ return 0; @@ -831,13 +846,15 @@ static int clusterip_net_init(struct net *net) static void clusterip_net_exit(struct net *net) { - struct clusterip_net *cn = net_generic(net, clusterip_net_id); #ifdef CONFIG_PROC_FS + struct clusterip_net *cn = clusterip_pernet(net); + + mutex_lock(&cn->mutex); proc_remove(cn->procdir); cn->procdir = NULL; + mutex_unlock(&cn->mutex); #endif nf_unregister_net_hook(net, &cip_arp_ops); - WARN_ON_ONCE(!list_empty(&cn->configs)); } static struct pernet_operations clusterip_net_ops = { @@ -847,6 +864,10 @@ static struct pernet_operations clusterip_net_ops = { .size = sizeof(struct clusterip_net), }; +struct notifier_block cip_netdev_notifier = { + .notifier_call = clusterip_netdev_event +}; + static int __init clusterip_tg_init(void) { int ret; @@ -859,11 +880,17 @@ static int __init clusterip_tg_init(void) if (ret < 0) goto cleanup_subsys; + ret = register_netdevice_notifier(&cip_netdev_notifier); + if (ret < 0) + goto unregister_target; + pr_info("ClusterIP Version %s loaded successfully\n", CLUSTERIP_VERSION); return 0; +unregister_target: + xt_unregister_target(&clusterip_tg_reg); cleanup_subsys: unregister_pernet_subsys(&clusterip_net_ops); return ret; @@ -873,6 +900,7 @@ static void __exit clusterip_tg_exit(void) { pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION); + unregister_netdevice_notifier(&cip_netdev_notifier); xt_unregister_target(&clusterip_tg_reg); unregister_pernet_subsys(&clusterip_net_ops); diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index ac110c1d55b5..481437fc1eb2 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -104,6 +104,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset) int snmp_version(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { + if (datalen != 1) + return -EINVAL; if (*(unsigned char *)data > 1) return -ENOTSUPP; return 1; @@ -113,8 +115,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { struct snmp_ctx *ctx = (struct snmp_ctx *)context; - __be32 *pdata = (__be32 *)data; + __be32 *pdata; + if (datalen != 4) + return -EINVAL; + pdata = (__be32 *)data; if (*pdata == ctx->from) { pr_debug("%s: %pI4 to %pI4\n", __func__, (void *)&ctx->from, (void *)&ctx->to); diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c index f86bb4f06609..d8e3a1fb8e82 100644 --- a/net/ipv4/netlink.c +++ b/net/ipv4/netlink.c @@ -3,9 +3,10 @@ #include <linux/types.h> #include <net/net_namespace.h> #include <net/netlink.h> +#include <linux/in6.h> #include <net/ip.h> -int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, +int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack) { *ip_proto = nla_get_u8(attr); @@ -13,11 +14,19 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, switch (*ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: + return 0; case IPPROTO_ICMP: + if (family != AF_INET) + break; + return 0; +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: + if (family != AF_INET6) + break; return 0; - default: - NL_SET_ERR_MSG(extack, "Unsupported ip proto"); - return -EOPNOTSUPP; +#endif } + NL_SET_ERR_MSG(extack, "Unsupported ip proto"); + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 33df4d76db2d..711a5c75bd4b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -174,6 +174,7 @@ 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); + int dif = inet_iif(skb); struct sock *sk; struct hlist_head *head; int delivered = 0; @@ -186,8 +187,7 @@ 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, sdif); + iph->saddr, iph->daddr, dif, sdif); while (sk) { delivered = 1; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8501554e96a4..232581c140a0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -500,15 +500,17 @@ EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { - static u32 ip_idents_hashrnd __read_mostly; u32 hash, id; - net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); + /* Note the following code is not safe, but this is okay. */ + if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) + get_random_bytes(&net->ipv4.ip_id_key, + sizeof(net->ipv4.ip_id_key)); - hash = jhash_3words((__force u32)iph->daddr, + hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, - iph->protocol ^ net_hash_mix(net), - ip_idents_hashrnd); + iph->protocol, + &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } @@ -887,13 +889,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; + peer->n_redirects = 0; + } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (peer->rate_tokens >= ip_rt_redirect_number) { + if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } @@ -910,6 +914,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; + ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && peer->rate_tokens == ip_rt_redirect_number) @@ -1182,11 +1187,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return dst; } +static void ipv4_send_dest_unreach(struct sk_buff *skb) +{ + struct ip_options opt; + int res; + + /* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. + */ + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) + return; + + memset(&opt, 0, sizeof(opt)); + if (ip_hdr(skb)->ihl > 5) { + if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) + return; + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); + + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) + return; + } + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); +} + static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) @@ -1305,6 +1338,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + /* set fnhe_daddr to 0 to ensure it won't bind with + * new dsts in rt_bind_exception(). + */ + fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; @@ -1923,7 +1960,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, u32 itag = 0; struct rtable *rth; struct flowi4 fl4; - bool do_cache; + bool do_cache = true; /* IP on this device is disabled. */ @@ -2000,6 +2037,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res->type == RTN_BROADCAST) { if (IN_DEV_BFORWARD(in_dev)) goto make_route; + /* not do cache if bc_forwarding is enabled */ + if (IPV4_DEVCONF_ALL(net, BC_FORWARDING)) + do_cache = false; goto brd_input; } @@ -2037,16 +2077,13 @@ brd_input: RT_CACHE_STAT_INC(in_brd); local_input: - do_cache = false; - if (res->fi) { - if (!itag) { - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - if (rt_cache_valid(rth)) { - skb_dst_set_noref(skb, &rth->dst); - err = 0; - goto out; - } - do_cache = true; + do_cache &= res->fi && !itag; + if (do_cache) { + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rt_cache_valid(rth)) { + skb_dst_set_noref(skb, &rth->dst); + err = 0; + goto out; } } @@ -2152,12 +2189,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, int our = 0; int err = -EINVAL; - if (in_dev) - our = ip_check_mc_rcu(in_dev, daddr, saddr, - ip_hdr(skb)->protocol); + if (!in_dev) + return err; + our = ip_check_mc_rcu(in_dev, daddr, saddr, + ip_hdr(skb)->protocol); /* check l3 master if no match yet */ - if ((!in_dev || !our) && netif_is_l3_slave(dev)) { + if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); @@ -2811,7 +2849,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], - &ip_proto, extack); + &ip_proto, AF_INET, extack); if (err) return err; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index c3387dfd725b..f66b2e6d97a7 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); - inet_csk_reqsk_queue_add(sk, req, child); + if (!inet_csk_reqsk_queue_add(sk, req, child)) { + bh_unlock_sock(child); + sock_put(child); + child = NULL; + reqsk_put(req); + } } else { reqsk_free(req); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 891ed2f91467..ce64453d337d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static int comp_sack_nr_max = 255; static u32 u32_max_div_HZ = UINT_MAX / HZ; +static int one_day_secs = 24 * 3600; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -1140,7 +1141,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_day_secs }, { .procname = "tcp_autocorking", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a32a0f4cc138..30c6e94b06c4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1186,7 +1186,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { - if (sk->sk_state != TCP_ESTABLISHED) { + if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { err = -EINVAL; goto out_err; } @@ -1901,6 +1901,11 @@ static int tcp_inq_hint(struct sock *sk) inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } + /* After receiving a FIN, tell the user-space to continue reading + * by returning a non-zero inq. + */ + if (inq == 0 && sock_flag(sk, SOCK_DONE)) + inq = 1; return inq; } @@ -2519,6 +2524,7 @@ void tcp_write_queue_purge(struct sock *sk) sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; + inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) @@ -2567,7 +2573,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; - icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index ca61e2a659e7..5205c5a5d8d5 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -66,11 +66,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; module_param(dctcp_alpha_on_init, uint, 0644); MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value"); -static unsigned int dctcp_clamp_alpha_on_loss __read_mostly; -module_param(dctcp_clamp_alpha_on_loss, uint, 0644); -MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss, - "parameter for clamping alpha on loss"); - static struct tcp_congestion_ops dctcp_reno; static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) @@ -211,21 +206,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) } } -static void dctcp_state(struct sock *sk, u8 new_state) +static void dctcp_react_to_loss(struct sock *sk) { - if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) { - struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); - /* If this extension is enabled, we clamp dctcp_alpha to - * max on packet loss; the motivation is that dctcp_alpha - * is an indicator to the extend of congestion and packet - * loss is an indicator of extreme congestion; setting - * this in practice turned out to be beneficial, and - * effectively assumes total congestion which reduces the - * window by half. - */ - ca->dctcp_alpha = DCTCP_MAX_ALPHA; - } + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +static void dctcp_state(struct sock *sk, u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != inet_csk(sk)->icsk_ca_state) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ } static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) @@ -237,6 +234,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ce_state_1_to_0(sk); break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 664fa7d8f7d9..cfdd70e32755 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + int room; + + room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh; /* Check #1 */ - if (tp->rcv_ssthresh < tp->window_clamp && - (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_under_memory_pressure(sk)) { + if (room > 0 && !tcp_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) if (incr) { incr = max_t(int, incr, 2 * skb->len); - tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, - tp->window_clamp); + tp->rcv_ssthresh += min(room, incr); inet_csk(sk)->icsk_ack.quick |= 1; } } @@ -6514,7 +6514,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->send_synack(fastopen_sk, dst, &fl, req, &foc, TCP_SYNACK_FASTOPEN); /* Add the child socket directly into the accept queue */ - inet_csk_reqsk_queue_add(sk, req, fastopen_sk); + if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { + reqsk_fastopen_remove(fastopen_sk, req, false); + bh_unlock_sock(fastopen_sk); + sock_put(fastopen_sk); + reqsk_put(req); + goto drop; + } sk->sk_data_ready(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c78c22ea0be1..2b7205ad261a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -536,14 +536,15 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (sock_owned_by_user(sk)) break; + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + break; + icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_rtx_queue_head(sk); - BUG_ON(!skb); - tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp); remaining = icsk->icsk_rto - @@ -1651,15 +1652,8 @@ EXPORT_SYMBOL(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = (struct tcphdr *)skb->data; - unsigned int eaten = skb->len; - int err; - err = sk_filter_trim_cap(sk, skb, th->doff * 4); - if (!err) { - eaten -= skb->len; - TCP_SKB_CB(skb)->end_seq -= eaten; - } - return err; + return sk_filter_trim_cap(sk, skb, th->doff * 4); } EXPORT_SYMBOL(tcp_filter); @@ -2502,7 +2496,8 @@ static void __net_exit tcp_sk_exit(struct net *net) { int cpu; - module_put(net->ipv4.tcp_congestion_control->owner); + if (net->ipv4.tcp_congestion_control) + module_put(net->ipv4.tcp_congestion_control->owner); for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 57eae8d70ba1..b1b5a648def6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -224,7 +224,7 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) { dst_negative_advice(sk); - } else if (!tp->syn_data && !tp->syn_fastopen) { + } else { sk_rethink_txhash(sk); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f8183fdce5b2..e45a5e19e509 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -785,15 +785,23 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) + if (hlen + cork->gso_size > cork->fragsize) { + kfree_skb(skb); return -EINVAL; - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + } + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + kfree_skb(skb); return -EINVAL; - if (sk->sk_no_check_tx) + } + if (sk->sk_no_check_tx) { + kfree_skb(skb); return -EINVAL; + } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) + dst_xfrm(skb_dst(skb))) { + kfree_skb(skb); return -EIO; + } skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index d73a6d6652f6..2b144b92ae46 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -111,7 +111,8 @@ static void _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) { const struct iphdr *iph = ip_hdr(skb); - u8 *xprth = skb_network_header(skb) + iph->ihl * 4; + int ihl = iph->ihl; + u8 *xprth = skb_network_header(skb) + ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; @@ -122,6 +123,11 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) fl4->flowi4_mark = skb->mark; fl4->flowi4_oif = reverse ? skb->skb_iif : oif; + fl4->flowi4_proto = iph->protocol; + fl4->daddr = reverse ? iph->saddr : iph->daddr; + fl4->saddr = reverse ? iph->daddr : iph->saddr; + fl4->flowi4_tos = iph->tos; + if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: @@ -133,7 +139,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ports = (__be16 *)xprth; fl4->fl4_sport = ports[!!reverse]; @@ -146,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 2 - skb->data)) { u8 *icmp; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; icmp = xprth; fl4->fl4_icmp_type = icmp[0]; @@ -159,7 +165,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be32 *ehdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ehdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ehdr[0]; @@ -171,7 +177,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 8 - skb->data)) { __be32 *ah_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ah_hdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ah_hdr[1]; @@ -183,7 +189,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ipcomp_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ipcomp_hdr = (__be16 *)xprth; fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1])); @@ -196,7 +202,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) __be16 *greflags; __be32 *gre_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; greflags = (__be16 *)xprth; gre_hdr = (__be32 *)xprth; @@ -213,10 +219,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) break; } } - fl4->flowi4_proto = iph->protocol; - fl4->daddr = reverse ? iph->saddr : iph->daddr; - fl4->saddr = reverse ? iph->daddr : iph->saddr; - fl4->flowi4_tos = iph->tos; } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4e81ff2f4588..c57efd5c5b38 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1148,7 +1148,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; - if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + if (ifa->prefix_len != ifp->prefix_len || + !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) @@ -4711,8 +4712,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; idev = ipv6_find_idev(dev); - if (IS_ERR(idev)) - return PTR_ERR(idev); + if (!idev) + return -ENOBUFS; if (!ipv6_allow_optimistic_dad(net, idev)) cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9a4261e50272..79fcd9550fd2 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -309,6 +309,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { + struct net_device *dev = NULL; int chk_addr_ret; /* Binding to v4-mapped address on a v6-only socket @@ -319,9 +320,20 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, goto out; } + rcu_read_lock(); + if (sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + err = -ENODEV; + goto out_unlock; + } + } + /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; - chk_addr_ret = inet_addr_type(net, v4addr); + chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr); + rcu_read_unlock(); + if (!inet_can_nonlocal_bind(net, inet) && v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && @@ -349,6 +361,9 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = -EINVAL; goto out_unlock; } + } + + if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 1ede7a16a0be..cb24850d2c7f 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -341,6 +341,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; + ip6_flow_hdr(iph, 0, 0); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; @@ -700,17 +701,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports; - int end; + __be16 _ports[2], *ports; - end = skb_transport_offset(skb) + 4; - if (end <= 0 || pskb_may_pull(skb, end)) { + ports = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_ports), &_ports); + if (ports) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ - ports = (__be16 *)skb_transport_header(skb); - sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 88a7579c23bd..a7d996148eed 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -293,7 +293,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index c9c53ade55c3..6d14cbe443f8 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -421,10 +421,10 @@ static int icmp6_iif(const struct sk_buff *skb) static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr) { - struct net *net = dev_net(skb->dev); struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; + struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct dst_entry *dst; @@ -435,12 +435,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - u32 mark = IP6_REPLY_MARK(net, skb->mark); + u32 mark; if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; + if (!skb->dev) + return; + net = dev_net(skb->dev); + mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules * i.e. RFC 1885 2.4(e) diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 17c455ff69ff..7858fa9ea103 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -420,6 +420,7 @@ int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info) done: rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); return ret; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index cbe46175bb59..a6c0479c1d55 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -877,6 +877,12 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i, { int cpu; + /* Make sure rt6_make_pcpu_route() wont add other percpu routes + * while we are cleaning them here. + */ + f6i->fib6_destroying = 1; + mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ + /* release the reference to this fib entry from * all of its cached pcpu routes */ @@ -889,9 +895,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i, if (pcpu_rt) { struct fib6_info *from; - from = rcu_dereference_protected(pcpu_rt->from, - lockdep_is_held(&table->tb6_lock)); - rcu_assign_pointer(pcpu_rt->from, NULL); + from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); fib6_info_release(from); } } @@ -902,6 +906,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, { struct fib6_table *table = rt->fib6_table; + if (rt->rt6i_pcpu) + fib6_drop_pcpu_from(rt, table); + if (atomic_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, @@ -923,9 +930,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } - - if (rt->rt6i_pcpu) - fib6_drop_pcpu_from(rt, table); } } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index cb54a8a3c273..be5f3d7ceb96 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) return fl; } +static void fl_free_rcu(struct rcu_head *head) +{ + struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu); + + if (fl->share == IPV6_FL_S_PROCESS) + put_pid(fl->owner.pid); + kfree(fl->opt); + kfree(fl); +} + static void fl_free(struct ip6_flowlabel *fl) { - if (fl) { - if (fl->share == IPV6_FL_S_PROCESS) - put_pid(fl->owner.pid); - kfree(fl->opt); - kfree_rcu(fl, rcu); - } + if (fl) + call_rcu(&fl->rcu, fl_free_rcu); } static void fl_release(struct ip6_flowlabel *fl) @@ -633,9 +639,9 @@ recheck: if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || ((fl1->share == IPV6_FL_S_PROCESS) && - (fl1->owner.pid == fl->owner.pid)) || + (fl1->owner.pid != fl->owner.pid)) || ((fl1->share == IPV6_FL_S_USER) && - uid_eq(fl1->owner.uid, fl->owner.uid))) + !uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -ENOMEM; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e493b041d4ac..01ecd510014f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -540,23 +540,18 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) return PACKET_REJECT; } -static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, - struct tnl_ptk_info *tpi) +static int ip6erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, + int gre_hdr_len) { struct erspan_base_hdr *ershdr; - struct erspan_metadata *pkt_md; const struct ipv6hdr *ipv6h; struct erspan_md2 *md2; struct ip6_tnl *tunnel; u8 ver; - if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) - return PACKET_REJECT; - ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; - tpi->key = cpu_to_be32(get_session_id(ershdr)); tunnel = ip6gre_tunnel_lookup(skb->dev, &ipv6h->saddr, &ipv6h->daddr, tpi->key, @@ -567,18 +562,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; - ershdr = (struct erspan_base_hdr *)skb->data; - pkt_md = (struct erspan_metadata *)(ershdr + 1); - if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) return PACKET_REJECT; if (tunnel->parms.collect_md) { + struct erspan_metadata *pkt_md, *md; struct metadata_dst *tun_dst; struct ip_tunnel_info *info; - struct erspan_metadata *md; + unsigned char *gh; __be64 tun_id; __be16 flags; @@ -591,6 +584,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, if (!tun_dst) return PACKET_REJECT; + /* skb can be uncloned in __iptunnel_pull_header, so + * old pkt_md is no longer valid and we need to reset + * it + */ + gh = skb_network_header(skb) + + skb_network_header_len(skb); + pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + + sizeof(*ershdr)); info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); md->version = ver; @@ -627,7 +628,7 @@ static int gre_rcv(struct sk_buff *skb) if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { - if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD) + if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } @@ -897,6 +898,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device_stats *stats = &t->dev->stats; int ret; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; @@ -935,10 +939,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, __u8 dsfield = false; struct flowi6 fl6; int err = -EINVAL; + __be16 proto; __u32 mtu; int nhoff; int thoff; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; @@ -1011,8 +1019,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; } } else { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); - switch (skb->protocol) { case htons(ETH_P_IP): memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1020,7 +1026,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, &dsfield, &encap_limit); break; case htons(ETH_P_IPV6): - if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr)) + if (ipv6_addr_equal(&t->parms.raddr, &ipv6_hdr(skb)->saddr)) goto tx_err; if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) @@ -1047,8 +1053,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, } /* Push GRE header. */ - gre_build_header(skb, 8, TUNNEL_SEQ, - htons(ETH_P_ERSPAN), 0, htonl(t->o_seqno++)); + proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) + : htons(ETH_P_ERSPAN2); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) @@ -1181,6 +1188,10 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, t->parms.i_flags = p->i_flags; t->parms.o_flags = p->o_flags; t->parms.fwmark = p->fwmark; + t->parms.erspan_ver = p->erspan_ver; + t->parms.index = p->index; + t->parms.dir = p->dir; + t->parms.hwid = p->hwid; dst_cache_reset(&t->dst_cache); } @@ -1729,6 +1740,27 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static void ip6erspan_set_version(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + if (!data) + return; + + parms->erspan_ver = 1; + if (data[IFLA_GRE_ERSPAN_VER]) + parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); + + if (parms->erspan_ver == 1) { + if (data[IFLA_GRE_ERSPAN_INDEX]) + parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + } else if (parms->erspan_ver == 2) { + if (data[IFLA_GRE_ERSPAN_DIR]) + parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); + if (data[IFLA_GRE_ERSPAN_HWID]) + parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); + } +} + static void ip6gre_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { @@ -1777,20 +1809,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; - - parms->erspan_ver = 1; - if (data[IFLA_GRE_ERSPAN_VER]) - parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); - - if (parms->erspan_ver == 1) { - if (data[IFLA_GRE_ERSPAN_INDEX]) - parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); - } else if (parms->erspan_ver == 2) { - if (data[IFLA_GRE_ERSPAN_DIR]) - parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); - if (data[IFLA_GRE_ERSPAN_HWID]) - parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); - } } static int ip6gre_tap_init(struct net_device *dev) @@ -2043,9 +2061,9 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id); + struct ip6_tnl *t = netdev_priv(dev); + struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); struct __ip6_tnl_parm p; - struct ip6_tnl *t; t = ip6gre_changelink_common(dev, tb, data, &p, extack); if (IS_ERR(t)) @@ -2114,12 +2132,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((p->erspan_ver == 1 || p->erspan_ver == 2) && + !p->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || @@ -2214,6 +2237,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, int err; ip6gre_netlink_parms(data, &nt->parms); + ip6erspan_set_version(data, &nt->parms); ign = net_generic(net, ip6gre_net_id); if (nt->parms.collect_md) { @@ -2259,6 +2283,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (IS_ERR(t)) return PTR_ERR(t); + ip6erspan_set_version(data, &p); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2694def1e72c..eed9231c90ad 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -378,6 +378,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); __IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); + skb->tstamp = 0; return dst_output(net, sk, skb); } @@ -586,7 +587,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; - unsigned int mtu, hlen, left, len; + unsigned int mtu, hlen, left, len, nexthdr_offset; int hroom, troom; __be32 frag_id; int ptr, offset = 0, err = 0; @@ -597,6 +598,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, goto fail; hlen = err; nexthdr = *prevhdr; + nexthdr_offset = prevhdr - skb_network_header(skb); mtu = ip6_skb_dst_mtu(skb); @@ -631,6 +633,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, (err = skb_checksum_help(skb))) goto fail; + prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a9d06d4dd057..ade1390c6348 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -627,7 +627,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); - if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; @@ -636,7 +636,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) goto out; } @@ -901,6 +901,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; + ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) goto drop; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) @@ -1242,10 +1243,6 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - /* ensure we can access the full inner ip header */ - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return -1; - iph = ip_hdr(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1320,9 +1317,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - return -1; - ipv6h = ipv6_hdr(skb); tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || @@ -1404,6 +1398,9 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) struct net_device_stats *stats = &t->dev->stats; int ret; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + switch (skb->protocol) { case htons(ETH_P_IP): ret = ip4ip6_tnl_xmit(skb, dev); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index b283f293ee4a..caad40d6e74d 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -15,7 +15,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { - struct sockaddr_in6 udp6_addr; + struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; @@ -42,6 +42,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, goto error; if (cfg->peer_udp_port) { + memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index eeaf7455d51e..8b6eefff2f7e 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -318,6 +318,7 @@ static int vti6_rcv(struct sk_buff *skb) return 0; } + ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); @@ -521,18 +522,18 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; - struct ipv6hdr *ipv6h; struct flowi fl; int ret; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): - ipv6h = ipv6_hdr(skb); - if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || - vti6_addr_conflict(t, ipv6h)) + vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; xfrm_decode_session(skb, &fl, AF_INET6); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index d0b7e0249c13..35e7092eceb3 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -51,6 +51,9 @@ #include <linux/export.h> #include <net/ip6_checksum.h> #include <linux/netconf.h> +#include <net/ip_tunnels.h> + +#include <linux/nospec.h> struct ip6mr_rule { struct fib_rule common; @@ -591,13 +594,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; - int err; - err = ip6mr_fib_lookup(net, &fl6, &mrt); - if (err < 0) { - kfree_skb(skb); - return err; - } + if (!pskb_inet_may_pull(skb)) + goto tx_err; + + if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) + goto tx_err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; @@ -606,6 +608,11 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; + +tx_err: + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) @@ -1499,6 +1506,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, + (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } @@ -1507,10 +1517,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), - FIB_EVENT_ENTRY_DEL, - (struct mfc6_cache *)c, - mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); @@ -1831,6 +1837,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; + vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { @@ -1905,6 +1912,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; + vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { @@ -1946,10 +1954,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTFORWDATAGRAMS); - __IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTOCTETS, skb->len); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTOCTETS, skb->len); return dst_output(net, sk, skb); } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 8b075f0bc351..6d0b1f3e927b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; + int strict = (ipv6_addr_type(&iph->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, + strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c index 1059894a6f4c..4cb83fb69844 100644 --- a/net/ipv6/netfilter/ip6t_srh.c +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -210,6 +210,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) psidoff = srhoff + sizeof(struct ipv6_sr_hdr) + ((srh->segments_left + 1) * sizeof(struct in6_addr)); psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid); + if (!psid) + return false; if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID, ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk, &srhinfo->psid_addr))) @@ -223,6 +225,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) + ((srh->segments_left - 1) * sizeof(struct in6_addr)); nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid); + if (!nsid) + return false; if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID, ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk, &srhinfo->nsid_addr))) @@ -233,6 +237,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) if (srhinfo->mt_flags & IP6T_SRH_LSID) { lsidoff = srhoff + sizeof(struct ipv6_sr_hdr); lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid); + if (!lsid) + return false; if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID, ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk, &srhinfo->lsid_addr))) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 043ed8eb0ab9..cb1b4772dac0 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -136,6 +136,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #endif +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); + static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); @@ -177,9 +180,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { - struct sk_buff *prev, *next; unsigned int payload_len; - int offset, end; + struct net_device *dev; + struct sk_buff *prev; + int offset, end, err; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) { @@ -254,55 +258,18 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, goto err; } - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4: - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments, including those not yet received) MUST be silently - * discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (prev->ip_defrag_offset + prev->len) > offset) - goto discard_fq; - - /* Look for overlap with succeeding segment. */ - if (next && next->ip_defrag_offset < end) - goto discard_fq; - - /* Note : skb->ip_defrag_offset and skb->dev share the same location */ - if (skb->dev) - fq->iif = skb->dev->ifindex; + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); - skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error; + + if (dev) + fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; @@ -319,11 +286,25 @@ found: fq->q.flags |= INET_FRAG_FIRST_IN; } - return 0; + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + err = nf_ct_frag6_reasm(fq, skb, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + + skb_dst_drop(skb); + return -EINPROGRESS; -discard_fq: +insert_error: + if (err == IPFRAG_DUP) + goto err; inet_frag_kill(&fq->q); err: + skb_dst_drop(skb); return -EINVAL; } @@ -333,147 +314,67 @@ err: * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. - * - * returns true if *prev skb has been transformed into the reassembled - * skb, false otherwise. */ -static bool -nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; + void *reasm_data; + int payload_len; u8 ecn; inet_frag_kill(&fq->q); - WARN_ON(head == NULL); - WARN_ON(head->ip_defrag_offset != 0); - ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) - return false; + goto err; + + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto err; - /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); - return false; - } - - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - return false; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (clone == NULL) - return false; - - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - - add_frag_mem_limit(fq->q.net, clone->truesize); - } - - /* morph head into last received skb: prev. - * - * This allows callers of ipv6 conntrack defrag to continue - * to use the last skb(frag) passed into the reasm engine. - * The last skb frag 'silently' turns into the full reassembled skb. - * - * Since prev is also part of q->fragments we have to clone it first. - */ - if (head != prev) { - struct sk_buff *iter; - - fp = skb_clone(prev, GFP_ATOMIC); - if (!fp) - return false; - - fp->next = prev->next; - - iter = head; - while (iter) { - if (iter->next == prev) { - iter->next = fp; - break; - } - iter = iter->next; - } - - skb_morph(prev, head); - prev->next = head->next; - consume_skb(head); - head = prev; + goto err; } /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ - skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_shinfo(head)->frag_list = head->next; - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - for (fp = head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp->sk = NULL; - } - sub_frag_mem_limit(fq->q.net, head->truesize); + skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data); - head->ignore_df = 1; - head->next = NULL; - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; + skb->ignore_df = 1; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_partial(skb_network_header(head), - skb_network_header_len(head), - head->csum); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_partial(skb_network_header(skb), + skb_network_header_len(skb), + skb->csum); fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; - return true; + return 0; + +err: + inet_frag_kill(&fq->q); + return -EINVAL; } /* @@ -542,7 +443,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; - struct net_device *dev = skb->dev; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; @@ -565,10 +465,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - return -EINVAL; - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); @@ -580,31 +476,17 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) spin_lock_bh(&fq->q.lock); ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); - if (ret < 0) { - if (ret == -EPROTO) { - skb->transport_header = savethdr; - ret = 0; - } - goto out_unlock; + if (ret == -EPROTO) { + skb->transport_header = savethdr; + ret = 0; } /* after queue has assumed skb ownership, only 0 or -EINPROGRESS * must be returned. */ - ret = -EINPROGRESS; - if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) { - unsigned long orefdst = skb->_skb_refdst; - - skb->_skb_refdst = 0UL; - if (nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - skb->_skb_refdst = orefdst; - } else { - skb_dst_drop(skb); - } + if (ret) + ret = -EINPROGRESS; -out_unlock: spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q); return ret; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 4fe7c90962dd..868ae23dbae1 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -10,15 +10,25 @@ #include <net/secure_seq.h> #include <linux/netfilter.h> -static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, +static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { + const struct { + struct in6_addr dst; + struct in6_addr src; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .dst = *dst, + .src = *src, + }; u32 hash, id; - hash = __ipv6_addr_jhash(dst, hashrnd); - hash = __ipv6_addr_jhash(src, hash); - hash ^= net_hash_mix(net); + /* Note the following code is not safe, but this is okay. */ + if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) + get_random_bytes(&net->ipv4.ip_id_key, + sizeof(net->ipv4.ip_id_key)); + + hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key); /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, * set the hight order instead thus minimizing possible future @@ -41,7 +51,6 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, */ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { - static u32 ip6_proxy_idents_hashrnd __read_mostly; struct in6_addr buf[2]; struct in6_addr *addrs; u32 id; @@ -53,11 +62,7 @@ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) if (!addrs) return 0; - net_get_random_once(&ip6_proxy_idents_hashrnd, - sizeof(ip6_proxy_idents_hashrnd)); - - id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, - &addrs[1], &addrs[0]); + id = __ipv6_select_ident(net, &addrs[1], &addrs[0]); return htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); @@ -66,12 +71,9 @@ __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) { - static u32 ip6_idents_hashrnd __read_mostly; u32 id; - net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); - - id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr); + id = __ipv6_select_ident(net, daddr, saddr); return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5e0efd3954e9..4856d9320b28 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -288,7 +288,9 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; + } + if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); @@ -780,6 +782,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; + int hdrincl; u16 proto; int err; @@ -793,6 +796,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; + /* hdrincl should be READ_ONCE(inet->hdrincl) + * but READ_ONCE() doesn't work with bit fields. + * Doing this indirectly yields the same result. + */ + hdrincl = inet->hdrincl; + hdrincl = READ_ONCE(hdrincl); + /* * Get and verify the address. */ @@ -884,11 +894,14 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; - rfv.msg = msg; - rfv.hlen = 0; - err = rawv6_probe_proto_opt(&rfv, &fl6); - if (err) - goto out; + + if (!hdrincl) { + rfv.msg = msg; + rfv.hlen = 0; + err = rawv6_probe_proto_opt(&rfv, &fl6); + if (err) + goto out; + } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; @@ -905,7 +918,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (inet->hdrincl) + if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) @@ -928,7 +941,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto do_confirm; back_from_confirm: - if (inet->hdrincl) + if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index d3fd2d7e5aa4..095825f964e2 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -69,8 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) static struct inet_frags ip6_frags; -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev); +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); static void ip6_frag_expire(struct timer_list *t) { @@ -111,21 +111,26 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff, u32 *prob_offset) { - struct sk_buff *prev, *next; - struct net_device *dev; - int offset, end, fragsize; struct net *net = dev_net(skb_dst(skb)->dev); + int offset, end, fragsize; + struct sk_buff *prev_tail; + struct net_device *dev; + int err = -ENOENT; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) goto err; + err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); + /* note that if prob_offset is set, the skb is freed elsewhere, + * we do not free it here. + */ return -1; } @@ -145,7 +150,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) - goto err; + goto discard_fq; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { @@ -162,70 +167,35 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_fq; fq->q.len = end; } } if (end == offset) - goto err; + goto discard_fq; + err = -ENOMEM; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) - goto err; - - if (pskb_trim_rcsum(skb, end - offset)) - goto err; - - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (prev->ip_defrag_offset + prev->len) > offset) goto discard_fq; - /* Look for overlap with succeeding segment. */ - if (next && next->ip_defrag_offset < end) + err = pskb_trim_rcsum(skb, end - offset); + if (err) goto discard_fq; - /* Note : skb->ip_defrag_offset and skb->dev share the same location */ + /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; - if (dev) - fq->iif = dev->ifindex; /* Makes sure compiler wont do silly aliasing games */ barrier(); - skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev_tail = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error; + + if (dev) + fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; @@ -246,44 +216,48 @@ found: if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { - int res; unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - res = ip6_frag_reasm(fq, prev, dev); + err = ip6_frag_reasm(fq, skb, prev_tail, dev); skb->_skb_refdst = orefdst; - return res; + return err; } skb_dst_drop(skb); - return -1; + return -EINPROGRESS; +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASM_OVERLAPS); discard_fq: inet_frag_kill(&fq->q); -err: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); +err: kfree_skb(skb); - return -1; + return err; } /* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev) +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; unsigned int nhoff; - int sum_truesize; + void *reasm_data; + int payload_len; u8 ecn; inet_frag_kill(&fq->q); @@ -292,120 +266,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, if (unlikely(ecn == 0xff)) goto out_fail; - /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); - - if (!fp) - goto out_oom; - - fp->next = head->next; - if (!fp->next) - fq->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, fq->q.fragments); - head->next = fq->q.fragments->next; - - consume_skb(fq->q.fragments); - fq->q.fragments = head; - } - - WARN_ON(head == NULL); - WARN_ON(head->ip_defrag_offset != 0); + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto out_oom; - /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) goto out_oversize; - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_oom; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_oom; - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(fq->q.net, clone->truesize); - } - /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ nhoff = fq->nhoffset; - skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - if (skb_mac_header_was_set(head)) - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; - } - sub_frag_mem_limit(fq->q.net, sum_truesize); + skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data); - head->next = NULL; - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->nhoff = nhoff; - IP6CB(head)->flags |= IP6SKB_FRAGMENTED; - IP6CB(head)->frag_max_size = fq->q.max_size; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->nhoff = nhoff; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = fq->q.max_size; /* Yes, and fold redundant checksum back. 8) */ - skb_postpush_rcsum(head, skb_network_header(head), - skb_network_header_len(head)); + skb_postpush_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); @@ -413,6 +307,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; return 1; out_oversize: @@ -424,6 +319,7 @@ out_fail: rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); + inet_frag_kill(&fq->q); return -1; } @@ -462,10 +358,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - goto fail_hdr; - iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { @@ -483,6 +375,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) if (prob_offset) { __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); + /* icmpv6_param_prob() calls kfree_skb(skb) */ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); } return ret; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a33681dc4796..24f7b2cf504b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -110,8 +110,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags); static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt, - struct in6_addr *daddr, - struct in6_addr *saddr); + const struct in6_addr *daddr, + const struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_add_route_info(struct net *net, @@ -210,7 +210,9 @@ struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; - return neigh_create(&nd_tbl, daddr, dev); + + n = neigh_create(&nd_tbl, daddr, dev); + return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, @@ -380,11 +382,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } - rcu_read_lock(); - from = rcu_dereference(rt->from); - rcu_assign_pointer(rt->from, NULL); + from = xchg((__force struct fib6_info **)&rt->from, NULL); fib6_info_release(from); - rcu_read_unlock(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -1046,14 +1045,20 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct rt6_info *nrt; if (!fib6_info_hold_safe(rt)) - return NULL; + goto fallback; nrt = ip6_dst_alloc(dev_net(dev), dev, flags); - if (nrt) - ip6_rt_copy_init(nrt, rt); - else + if (!nrt) { fib6_info_release(rt); + goto fallback; + } + + ip6_rt_copy_init(nrt, rt); + return nrt; +fallback: + nrt = dev_net(dev)->ipv6.ip6_null_entry; + dst_hold(&nrt->dst); return nrt; } @@ -1102,10 +1107,6 @@ restart: dst_hold(&rt->dst); } else { rt = ip6_create_rt_rcu(f6i); - if (!rt) { - rt = net->ipv6.ip6_null_entry; - dst_hold(&rt->dst); - } } rcu_read_unlock(); @@ -1267,6 +1268,13 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net, prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); + if (rt->fib6_destroying) { + struct fib6_info *from; + + from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); + fib6_info_release(from); + } + return pcpu_rt; } @@ -1280,18 +1288,27 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { + struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); + net->ipv6.rt6_stats->fib_rt_cache--; + + /* purge completely the exception to allow releasing the held resources: + * some [sk] cache may keep the dst around for unlimited time + */ + from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL); + fib6_info_release(from); + dst_dev_put(&rt6_ex->rt6i->dst); + hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; - net->ipv6.rt6_stats->fib_rt_cache--; } /* Remove oldest rt6_ex in bucket and free the memory @@ -1532,31 +1549,44 @@ out: * Caller has to hold rcu_read_lock() */ static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt, - struct in6_addr *daddr, - struct in6_addr *saddr) + const struct in6_addr *daddr, + const struct in6_addr *saddr) { + const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; - struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct rt6_info *res = NULL; - bucket = rcu_dereference(rt->rt6i_exception_bucket); - #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates rt is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. - * Otherwise, the exception table is indexed by - * a hash of only rt6i_dst. + * However, the src addr used to create the hash + * might not be exactly the passed in saddr which + * is a /128 addr from the flow. + * So we need to use f6i->fib6_src to redo lookup + * if the passed in saddr does not find anything. + * (See the logic in ip6_rt_cache_alloc() on how + * rt->rt6i_src is updated.) */ if (rt->fib6_src.plen) src_key = saddr; +find_ex: #endif + bucket = rcu_dereference(rt->rt6i_exception_bucket); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) res = rt6_ex->rt6i; +#ifdef CONFIG_IPV6_SUBTREES + /* Use fib6_src as src_key and redo lookup */ + if (!res && src_key && src_key != &rt->fib6_src.addr) { + src_key = &rt->fib6_src.addr; + goto find_ex; + } +#endif + return res; } @@ -1610,15 +1640,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - - if (!from || - !(rt->rt6i_flags & RTF_CACHE)) - return; + struct fib6_info *from; rcu_read_lock(); + from = rcu_dereference(rt->from); + if (!from || !(rt->rt6i_flags & RTF_CACHE)) + goto unlock; + bucket = rcu_dereference(from->rt6i_exception_bucket); #ifdef CONFIG_IPV6_SUBTREES @@ -1637,6 +1667,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) if (rt6_ex) rt6_ex->stamp = jiffies; +unlock: rcu_read_unlock(); } @@ -2351,6 +2382,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_lock(); from = rcu_dereference(rt6->from); + if (!from) { + rcu_read_unlock(); + return; + } nrt6 = ip6_rt_cache_alloc(from, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); @@ -2445,6 +2480,12 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_info *rt; struct fib6_node *fn; + /* l3mdev_update_flow overrides oif if the device is enslaved; in + * this case we must match on the real ingress device, so reset it + */ + if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) + fl6->flowi6_oif = skb->dev->ifindex; + /* Get the "current" route for this destination and * check if the redirect has come from appropriate router. * @@ -2635,10 +2676,8 @@ out: u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, struct in6_addr *saddr) { - struct rt6_exception_bucket *bucket; - struct rt6_exception *rt6_ex; - struct in6_addr *src_key; struct inet6_dev *idev; + struct rt6_info *rt; u32 mtu = 0; if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { @@ -2647,18 +2686,10 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, goto out; } - src_key = NULL; -#ifdef CONFIG_IPV6_SUBTREES - if (f6i->fib6_src.plen) - src_key = saddr; -#endif - - bucket = rcu_dereference(f6i->rt6i_exception_bucket); - rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); - if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) - mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU); - - if (likely(!mtu)) { + rt = rt6_find_cached_rt(f6i, daddr, saddr); + if (unlikely(rt)) { + mtu = dst_metric_raw(&rt->dst, RTAX_MTU); + } else { struct net_device *dev = fib6_info_nh_dev(f6i); mtu = IPV6_MIN_MTU; @@ -2794,20 +2825,24 @@ static int ip6_route_check_nh_onlink(struct net *net, u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT; + struct fib6_info *from; struct rt6_info *grt; int err; err = 0; grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { + rcu_read_lock(); + from = rcu_dereference(grt->from); if (!grt->dst.error && /* ignore match if it is the default route */ - grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) && + from && !ipv6_addr_any(&from->fib6_dst.addr) && (grt->rt6i_flags & flags || dev != grt->dst.dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } + rcu_read_unlock(); ip6_rt_put(grt); } @@ -3430,11 +3465,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); - /* This fib6_info_hold() is safe here because we hold reference to rt - * and rt already holds reference to fib6_info. - */ - fib6_info_hold(from); - rcu_read_unlock(); + if (!from) + goto out; nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL); if (!nrt) @@ -3446,10 +3478,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - /* No need to remove rt from the exception table if rt is - * a cached route because rt6_insert_exception() will - * takes care of it - */ + /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, from)) { dst_release_immediate(&nrt->dst); goto out; @@ -3462,7 +3491,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: - fib6_info_release(from); + rcu_read_unlock(); neigh_release(neigh); } @@ -4211,6 +4240,10 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } + if (tb[RTA_VIA]) { + NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); + goto errout; + } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; @@ -4704,7 +4737,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; - rtm->rtm_table = table; + rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; @@ -4905,7 +4938,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], - &fl6.flowi6_proto, extack); + &fl6.flowi6_proto, AF_INET6, + extack); if (err) goto errout; } @@ -4962,16 +4996,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, rcu_read_lock(); from = rcu_dereference(rt->from); - - if (fibmatch) - err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); - else - err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, - &fl6.saddr, iif, RTM_NEWROUTE, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - 0); + if (from) { + if (fibmatch) + err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, + iif, RTM_NEWROUTE, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + else + err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, + &fl6.saddr, iif, RTM_NEWROUTE, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + } else { + err = -ENETUNREACH; + } rcu_read_unlock(); if (err < 0) { diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 8d0ba757a46c..9b2f272ca164 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(msg, hdr); - genlmsg_reply(msg, info); - - return 0; + return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8181ee7e1e27..ee5403cbe655 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e9400ffa7875..41b3fe8ac3bc 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) } err = 0; - if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) + if (__in6_dev_get(skb->dev) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) @@ -668,6 +669,10 @@ static int ipip6_rcv(struct sk_buff *skb) !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; + /* skb can be uncloned in iptunnel_pull_header, so + * old iph is no longer valid + */ + iph = (const struct iphdr *)skb_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -777,8 +782,9 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, pbw0 = tunnel->ip6rd.prefixlen >> 5; pbi0 = tunnel->ip6rd.prefixlen & 0x1f; - d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> - tunnel->ip6rd.relay_prefixlen; + d = tunnel->ip6rd.relay_prefixlen < 32 ? + (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen : 0; pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; if (pbi1 > 0) @@ -1021,6 +1027,9 @@ tx_error: static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + if (!pskb_inet_may_pull(skb)) + goto tx_err; + switch (skb->protocol) { case htons(ETH_P_IP): sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP); @@ -1075,7 +1084,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); - if (tdev) { + if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); @@ -1869,6 +1878,7 @@ static int __net_init sit_init_net(struct net *net) err_reg_dev: ipip6_dev_free(sitn->fb_tunnel_dev); + free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 03e6b7a2bc53..e7cdfa92c382 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1108,11 +1108,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; - newnp->mcast_oif = tcp_v6_iif(skb); - newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + newnp->mcast_oif = inet_iif(skb); + newnp->mcast_hops = ip_hdr(skb)->ttl; + newnp->rcv_flowinfo = 0; if (np->repflow) - newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); + newnp->flow_label = 0; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b36694b6716e..cab8b2b647f9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1056,15 +1056,23 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) + if (hlen + cork->gso_size > cork->fragsize) { + kfree_skb(skb); return -EINVAL; - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + } + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + kfree_skb(skb); return -EINVAL; - if (udp_sk(sk)->no_check6_tx) + } + if (udp_sk(sk)->no_check6_tx) { + kfree_skb(skb); return -EINVAL; + } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) + dst_xfrm(skb_dst(skb))) { + kfree_skb(skb); return -EIO; + } skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; @@ -1314,10 +1322,7 @@ do_udp_sendmsg: ipc6.opt = opt; fl6.flowi6_proto = sk->sk_protocol; - if (!ipv6_addr_any(daddr)) - fl6.daddr = *daddr; - else - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + fl6.daddr = *daddr; if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; @@ -1345,6 +1350,9 @@ do_udp_sendmsg: } } + if (ipv6_addr_any(&fl6.daddr)) + fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 4a46df8441c9..d9e5f6808811 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -144,6 +144,9 @@ static u32 __xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr) index = __xfrm6_tunnel_spi_check(net, spi); if (index >= 0) goto alloc_spi; + + if (spi == XFRM6_TUNNEL_SPI_MAX) + break; } for (spi = XFRM6_TUNNEL_SPI_MIN; spi < xfrm6_tn->spi; spi++) { index = __xfrm6_tunnel_spi_check(net, spi); @@ -341,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); + xfrm_state_flush(net, 0, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); @@ -399,6 +402,10 @@ static void __exit xfrm6_tunnel_fini(void) xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); unregister_pernet_subsys(&xfrm6_tunnel_net_ops); + /* Someone maybe has gotten the xfrm6_tunnel_spi. + * So need to wait it. + */ + rcu_barrier(); kmem_cache_destroy(xfrm6_tunnel_spi_kmem); } diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 571d824e4e24..b919db02c7f9 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -2054,14 +2054,14 @@ static int __init kcm_init(void) if (err) goto fail; - err = sock_register(&kcm_family_ops); - if (err) - goto sock_register_fail; - err = register_pernet_device(&kcm_net_ops); if (err) goto net_ops_fail; + err = sock_register(&kcm_family_ops); + if (err) + goto sock_register_fail; + err = kcm_proc_init(); if (err) goto proc_init_fail; @@ -2069,12 +2069,12 @@ static int __init kcm_init(void) return 0; proc_init_fail: - unregister_pernet_device(&kcm_net_ops); - -net_ops_fail: sock_unregister(PF_KCM); sock_register_fail: + unregister_pernet_device(&kcm_net_ops); + +net_ops_fail: proto_unregister(&kcm_proto); fail: @@ -2090,8 +2090,8 @@ fail: static void __exit kcm_exit(void) { kcm_proc_exit(); - unregister_pernet_device(&kcm_net_ops); sock_unregister(PF_KCM); + unregister_pernet_device(&kcm_net_ops); proto_unregister(&kcm_proto); destroy_workqueue(kcm_wq); diff --git a/net/key/af_key.c b/net/key/af_key.c index 9d61266526e7..0b79c9aa8eb1 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock) return 0; } -static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, - gfp_t allocation, struct sock *sk) +static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, + struct sock *sk) { int err = -ENOBUFS; - sock_hold(sk); - if (*skb2 == NULL) { - if (refcount_read(&skb->users) != 1) { - *skb2 = skb_clone(skb, allocation); - } else { - *skb2 = skb; - refcount_inc(&skb->users); - } - } - if (*skb2 != NULL) { - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_set_owner_r(*skb2, sk); - skb_queue_tail(&sk->sk_receive_queue, *skb2); - sk->sk_data_ready(sk); - *skb2 = NULL; - err = 0; - } + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return err; + + skb = skb_clone(skb, allocation); + + if (skb) { + skb_set_owner_r(skb, sk); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk); + err = 0; } - sock_put(sk); return err; } @@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct sk_buff *skb2 = NULL; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think @@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, * socket. */ if (pfk->promisc) - pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) @@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, continue; } - err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ @@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); + err = pfkey_broadcast_one(skb, allocation, one_sk); - kfree_skb(skb2); kfree_skb(skb); return err; } @@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true); + err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ @@ -1961,8 +1951,10 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if (rq->sadb_x_ipsecrequest_mode == 0) return -EINVAL; + if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto)) + return -EINVAL; - t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */ + t->id.proto = rq->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 26f1d435696a..52b5a2797c0c 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -83,8 +83,7 @@ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff -#define L2TP_HDR_SIZE_SEQ 10 -#define L2TP_HDR_SIZE_NOSEQ 6 +#define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 @@ -170,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) rcu_read_lock_bh(); list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (tunnel->tunnel_id == tunnel_id) { - l2tp_tunnel_inc_refcount(tunnel); + if (tunnel->tunnel_id == tunnel_id && + refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; @@ -191,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) rcu_read_lock_bh(); list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (++count > nth) { - l2tp_tunnel_inc_refcount(tunnel); + if (++count > nth && + refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } @@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { l2tp_info(tunnel, L2TP_MSG_DATA, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); @@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) goto error; } + if (tunnel->version == L2TP_HDR_VER_3 && + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto error; + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); @@ -906,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - tunnel = l2tp_tunnel(sk); + tunnel = rcu_dereference_sk_user_data(sk); if (tunnel == NULL) goto pass_up; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9c9afe94d389..b2ce90260c35 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) } #endif +static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, + unsigned char **ptr, unsigned char **optr) +{ + int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); + + if (opt_len > 0) { + int off = *ptr - *optr; + + if (!pskb_may_pull(skb, off + opt_len)) + return -1; + + if (skb->data != *optr) { + *optr = skb->data; + *ptr = skb->data + off; + } + } + + return 0; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 35f6f86d4dcc..d4c60523c549 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 237f1a4a0b0c..37a69df17cab 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); @@ -671,9 +674,6 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*lsa); - if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); @@ -703,6 +703,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, lsa->l2tp_conn_id = 0; if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = inet6_iif(skb); + *addr_len = sizeof(*lsa); } if (np->rxopt.all) diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index 94425e421213..9e4b6bcf6920 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -72,6 +72,8 @@ int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, rc = llc_mac_hdr_init(skb, skb->dev->dev_addr, dmac); if (likely(!rc)) rc = dev_queue_xmit(skb); + else + kfree_skb(skb); return rc; } diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 69e831bc317b..54821fb1a960 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018 - 2019 Intel Corporation * * 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 @@ -366,6 +366,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + ieee80211_agg_stop_txq(sta, tid); + spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 5d22eda8a6b1..40c510223467 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -887,6 +887,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER; int err; + int prev_beacon_int; old = sdata_dereference(sdata->u.ap.beacon, sdata); if (old) @@ -909,6 +910,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->needed_rx_chains = sdata->local->rx_chains; + prev_beacon_int = sdata->vif.bss_conf.beacon_int; sdata->vif.bss_conf.beacon_int = params->beacon_interval; mutex_lock(&local->mtx); @@ -917,8 +919,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (!err) ieee80211_vif_copy_chanctx_to_vlans(sdata, false); mutex_unlock(&local->mtx); - if (err) + if (err) { + sdata->vif.bss_conf.beacon_int = prev_beacon_int; return err; + } /* * Apply control port protocol, this allows us to @@ -1474,6 +1478,10 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) sta->sta.tdls = true; + if (sta->sta.tdls && sdata->vif.type == NL80211_IFTYPE_STATION && + !sdata->u.mgd.associated) + return -EINVAL; + err = sta_apply_parameters(local, sta, params); if (err) { sta_info_free(local, sta); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index c813207bb123..d37d4acafebf 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -838,7 +838,7 @@ void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) dir = sdata->vif.debugfs_dir; - if (!dir) + if (IS_ERR_OR_NULL(dir)) return; sprintf(buf, "netdev:%s", sdata->name); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 8f6998091d26..2123f6e90fc0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1166,6 +1166,9 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif); + if (local->in_reconfig) + return; + if (!check_sdata_in_driver(sdata)) return; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5f3c81e705c7..152d4365f961 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -7,6 +7,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * 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 @@ -1909,6 +1910,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata) list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); + if (sdata->vif.txq) + ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq)); + synchronize_rcu(); if (sdata->dev) { @@ -1951,6 +1955,8 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) WARN(local->open_count, "%s: open count remains %d\n", wiphy_name(local->hw.wiphy), local->open_count); + ieee80211_txq_teardown_flows(local); + mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index c054ac85793c..f20bb39f492d 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -167,8 +167,10 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) * The driver doesn't know anything about VLAN interfaces. * Hence, don't send GTKs for VLAN interfaces to the driver. */ - if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) + if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { + ret = 1; goto out_unsupported; + } } ret = drv_set_key(key->local, SET_KEY, sdata, @@ -213,11 +215,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) /* all of these we can do in software - if driver can */ if (ret == 1) return 0; - if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - return 0; + if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) return -EINVAL; - } return 0; default: return -EINVAL; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 513627896204..68db2a356443 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1198,7 +1198,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) rtnl_unlock(); ieee80211_led_exit(local); ieee80211_wep_free(local); - ieee80211_txq_teardown_flows(local); fail_flows: destroy_workqueue(local->workqueue); fail_workqueue: @@ -1224,7 +1223,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&local->ifa6_notifier); #endif - ieee80211_txq_teardown_flows(local); rtnl_lock(); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 21526630bf65..e84103b40534 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -70,6 +70,7 @@ enum mesh_deferred_task_flags { * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer + * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be @@ -105,6 +106,7 @@ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; + struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; @@ -133,12 +135,16 @@ struct mesh_path { * gate's mpath may or may not be resolved and active. * @gates_lock: protects updates to known_gates * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containging all mesh_path objects + * @walk_lock: lock protecting walk_head * @entries: number of entries in the table */ struct mesh_table { struct hlist_head known_gates; spinlock_t gates_lock; struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ }; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index a5125624a76d..49a90217622b 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -23,7 +23,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath); static u32 mesh_table_hash(const void *addr, u32 len, u32 seed) { /* Use last four bytes of hw addr as hash index */ - return jhash_1word(*(u32 *)(addr+2), seed); + return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed); } static const struct rhashtable_params mesh_rht_params = { @@ -59,8 +59,10 @@ static struct mesh_table *mesh_table_alloc(void) return NULL; INIT_HLIST_HEAD(&newtbl->known_gates); + INIT_HLIST_HEAD(&newtbl->walk_head); atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); + spin_lock_init(&newtbl->walk_lock); return newtbl; } @@ -249,28 +251,15 @@ mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) static struct mesh_path * __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) { - int i = 0, ret; - struct mesh_path *mpath = NULL; - struct rhashtable_iter iter; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return NULL; - - rhashtable_walk_start(&iter); + int i = 0; + struct mesh_path *mpath; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (i++ == idx) break; } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); - if (IS_ERR(mpath) || !mpath) + if (!mpath) return NULL; if (mpath_expired(mpath)) { @@ -432,6 +421,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, return ERR_PTR(-ENOMEM); tbl = sdata->u.mesh.mesh_paths; + spin_lock_bh(&tbl->walk_lock); do { ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, @@ -441,20 +431,20 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, mpath = rhashtable_lookup_fast(&tbl->rhead, dst, mesh_rht_params); - + else if (!ret) + hlist_add_head(&new_mpath->walk_list, &tbl->walk_head); } while (unlikely(ret == -EEXIST && !mpath)); + spin_unlock_bh(&tbl->walk_lock); - if (ret && ret != -EEXIST) - return ERR_PTR(ret); - - /* At this point either new_mpath was added, or we found a - * matching entry already in the table; in the latter case - * free the unnecessary new entry. - */ - if (ret == -EEXIST) { + if (ret) { kfree(new_mpath); + + if (ret != -EEXIST) + return ERR_PTR(ret); + new_mpath = mpath; } + sdata->u.mesh.mesh_paths_generation++; return new_mpath; } @@ -480,9 +470,17 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, memcpy(new_mpath->mpp, mpp, ETH_ALEN); tbl = sdata->u.mesh.mpp_paths; + + spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, mesh_rht_params); + if (!ret) + hlist_add_head_rcu(&new_mpath->walk_list, &tbl->walk_head); + spin_unlock_bh(&tbl->walk_lock); + + if (ret) + kfree(new_mpath); sdata->u.mesh.mpp_paths_generation++; return ret; @@ -503,20 +501,9 @@ void mesh_plink_broken(struct sta_info *sta) struct mesh_table *tbl = sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + rcu_read_lock(); + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && !(mpath->flags & MESH_PATH_FIXED)) { @@ -530,8 +517,7 @@ void mesh_plink_broken(struct sta_info *sta) WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast); } } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + rcu_read_unlock(); } static void mesh_path_free_rcu(struct mesh_table *tbl, @@ -551,6 +537,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) { + hlist_del_rcu(&mpath->walk_list); rhashtable_remove_fast(&tbl->rhead, &mpath->rhash, mesh_rht_params); mesh_path_free_rcu(tbl, mpath); } @@ -571,27 +558,14 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; struct mesh_table *tbl = sdata->u.mesh.mesh_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, @@ -599,51 +573,26 @@ static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, { struct mesh_table *tbl = sdata->u.mesh.mpp_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (ether_addr_equal(mpath->mpp, proxy)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void table_flush_by_iface(struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); + struct hlist_node *n; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } /** @@ -675,7 +624,7 @@ static int table_path_del(struct mesh_table *tbl, { struct mesh_path *mpath; - rcu_read_lock(); + spin_lock_bh(&tbl->walk_lock); mpath = rhashtable_lookup_fast(&tbl->rhead, addr, mesh_rht_params); if (!mpath) { rcu_read_unlock(); @@ -683,7 +632,7 @@ static int table_path_del(struct mesh_table *tbl, } __mesh_path_del(tbl, mpath); - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return 0; } @@ -854,28 +803,16 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; + struct hlist_node *n; - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_KERNEL); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if ((!(mpath->flags & MESH_PATH_RESOLVING)) && (!(mpath->flags & MESH_PATH_FIXED)) && time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } void mesh_path_expire(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3dbecae4be73..2ac749c4a6b2 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1156,9 +1156,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; } - /* XXX: shouldn't really modify cfg80211-owned data! */ - ifmgd->associated->channel = sdata->csa_chandef.chan; - ifmgd->csa_waiting_bcn = true; ieee80211_sta_reset_beacon_monitor(sdata); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5e2b4a41acf1..e946ee4f335b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -142,6 +142,9 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, /* allocate extra bitmaps */ if (status->chains) len += 4 * hweight8(status->chains); + /* vendor presence bitmap */ + if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) + len += 4; if (ieee80211_have_rx_timestamp(status)) { len = ALIGN(len, 8); @@ -197,8 +200,6 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) { struct ieee80211_vendor_radiotap *rtap = (void *)skb->data; - /* vendor presence bitmap */ - len += 4; /* alignment for fixed 6-byte vendor data header */ len = ALIGN(len, 2); /* vendor data header */ @@ -220,7 +221,7 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr_3addr hdr; u8 category; u8 action_code; - } __packed action; + } __packed __aligned(2) action; if (!sdata) return; @@ -2597,6 +2598,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u16 ac, q, hdrlen; + int tailroom = 0; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2676,15 +2678,21 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) skb_set_queue_mapping(skb, q); if (!--mesh_hdr->ttl) { - IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); + if (!is_multicast_ether_addr(hdr->addr1)) + IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, + dropped_frames_ttl); goto out; } if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; + if (sdata->crypto_tx_tailroom_needed_cnt) + tailroom = IEEE80211_ENCRYPT_TAILROOM; + fwd_skb = skb_copy_expand(skb, local->tx_headroom + - sdata->encrypt_headroom, 0, GFP_ATOMIC); + sdata->encrypt_headroom, + tailroom, GFP_ATOMIC); if (!fwd_skb) goto out; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 7fa10d06cc51..534a604b75c2 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -556,6 +556,11 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, } ieee80211_led_tx(local); + + if (skb_has_frag_list(skb)) { + kfree_skb_list(skb_shinfo(skb)->frag_list); + skb_shinfo(skb)->frag_list = NULL; + } } /* diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h index 366b9e6f043e..40141df09f25 100644 --- a/net/mac80211/trace_msg.h +++ b/net/mac80211/trace_msg.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions of this file + * Copyright (C) 2019 Intel Corporation + */ + #ifdef CONFIG_MAC80211_MESSAGE_TRACING #if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) @@ -11,7 +16,7 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM mac80211_msg -#define MAX_MSG_LEN 100 +#define MAX_MSG_LEN 120 DECLARE_EVENT_CLASS(mac80211_msg_event, TP_PROTO(struct va_format *vaf), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 995a491f73a9..2f726cde9998 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1913,9 +1913,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, int head_need, bool may_encrypt) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr; + bool enc_tailroom; int tail_need = 0; - if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { + hdr = (struct ieee80211_hdr *) skb->data; + enc_tailroom = may_encrypt && + (sdata->crypto_tx_tailroom_needed_cnt || + ieee80211_is_mgmt(hdr->frame_control)); + + if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1923,8 +1930,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) || - !skb_clone_writable(skb, ETH_HLEN) || - (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) + !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); @@ -3179,6 +3185,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, u8 max_subframes = sta->sta.max_amsdu_subframes; int max_frags = local->hw.max_tx_fragments; int max_amsdu_len = sta->sta.max_amsdu_len; + int orig_truesize; __be16 len; void *data; bool ret = false; @@ -3212,6 +3219,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!head) goto out; + orig_truesize = head->truesize; orig_len = head->len; if (skb->len + head->len > max_amsdu_len) @@ -3266,6 +3274,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, *frag_tail = skb; out_recalc: + fq->memory_usage += head->truesize - orig_truesize; if (head->len != orig_len) { flow->backlog += head->len - orig_len; tin->backlog_bytes += head->len - orig_len; @@ -3608,10 +3617,10 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, /* We need a bit of data queued to build aggregates properly, so * instruct the TCP stack to allow more than a single ms of data * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP + * second, so 7 is ~8ms of queued data. Only affects local TCP * sockets. */ - sk_pacing_shift_update(skb->sk, 8); + sk_pacing_shift_update(skb->sk, 7); fast_tx = rcu_dereference(sta->fast_tx); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 716cd6442d86..3deaa01ebee4 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation * * 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 @@ -2020,6 +2020,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: break; + case NL80211_IFTYPE_ADHOC: + if (sdata->vif.bss_conf.ibss_joined) + WARN_ON(drv_join_ibss(local, sdata)); + /* fall through */ default: ieee80211_reconfig_stations(sdata); /* fall through */ diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 8fbe6cdbe255..d5a4db5b3fe7 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1822,6 +1822,9 @@ static int rtm_to_route_config(struct sk_buff *skb, goto errout; break; } + case RTA_GATEWAY: + NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); + goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f61c306de1d0..e0fb56d67d42 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1003,6 +1003,7 @@ config NETFILTER_XT_TARGET_TEE depends on NETFILTER_ADVANCED depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK + depends on IP6_NF_IPTABLES || !IP6_NF_IPTABLES select NF_DUP_IPV4 select NF_DUP_IPV6 if IP6_NF_IPTABLES ---help--- diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 9bd8f062ebc1..b364cf8e5776 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -39,7 +39,7 @@ EXPORT_SYMBOL_GPL(nf_ipv6_ops); DEFINE_PER_CPU(bool, nf_skb_duplicated); EXPORT_SYMBOL_GPL(nf_skb_duplicated); -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif @@ -353,7 +353,7 @@ static int __nf_register_net_hook(struct net *net, int pf, if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) net_inc_ingress_queue(); #endif -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL static_key_slow_inc(&nf_hooks_needed[pf][reg->hooknum]); #endif BUG_ON(p == new_hooks); @@ -411,7 +411,7 @@ static void __nf_unregister_net_hook(struct net *net, int pf, if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) net_dec_ingress_queue(); #endif -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[pf][reg->hooknum]); #endif } else { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index c00b6a2e8e3c..13ade5782847 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -219,10 +219,6 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); u32 ip; - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC)); if (ip < map->first_ip || ip > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; @@ -233,7 +229,11 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, return -EINVAL; e.id = ip_to_id(map, ip); - memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN); + + if (opt->flags & IPSET_DIM_ONE_SRC) + ether_addr_copy(e.ether, eth_hdr(skb)->h_source); + else + ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 1ab5ed2f6839..fd87de3ed55b 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -103,7 +103,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN); + if (opt->flags & IPSET_DIM_ONE_SRC) + ether_addr_copy(e.ether, eth_hdr(skb)->h_source); + else + ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); + if (ether_addr_equal(e.ether, invalid_ether)) return -EINVAL; @@ -211,15 +215,15 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN); + if (opt->flags & IPSET_DIM_ONE_SRC) + ether_addr_copy(e.ether, eth_hdr(skb)->h_source); + else + ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); + if (ether_addr_equal(e.ether, invalid_ether)) return -EINVAL; diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c index f9d5a2a1e3d0..4fe5f243d0a3 100644 --- a/net/netfilter/ipset/ip_set_hash_mac.c +++ b/net/netfilter/ipset/ip_set_hash_mac.c @@ -81,15 +81,15 @@ hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_ONE_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - ether_addr_copy(e.ether, eth_hdr(skb)->h_source); + if (opt->flags & IPSET_DIM_ONE_SRC) + ether_addr_copy(e.ether, eth_hdr(skb)->h_source); + else + ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); + if (is_zero_ether_addr(e.ether)) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 4eef55da0878..8da228da53ae 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -531,8 +531,8 @@ nla_put_failure: ret = -EMSGSIZE; } else { cb->args[IPSET_CB_ARG0] = i; + ipset_nest_end(skb, atd); } - ipset_nest_end(skb, atd); out: rcu_read_unlock(); return ret; diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index cad48d07c818..8401cefd9f65 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,6 +29,7 @@ config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 select IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 ---help--- Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 7ca926a03b81..a42c1bc7c698 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1536,14 +1536,12 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); - if (iph->fragoffs) { - /* Fragment that couldn't be mapped to a conn entry - * is missing module nf_defrag_ipv6 - */ - IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + + /* Fragment couldn't be mapped to a conn entry */ + if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); - } + *verdict = NF_ACCEPT; return 0; } @@ -1649,7 +1647,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!cp) { int v; - if (!sysctl_schedule_icmp(ipvs)) + if (ipip || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 518364f4abcc..2d4e048762f6 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -43,6 +43,7 @@ #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/route.h> #include <net/sock.h> @@ -900,11 +901,17 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { + int ret; + atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; + + ret = nf_defrag_ipv6_enable(svc->ipvs->net); + if (ret) + return ret; } else #endif { @@ -1228,6 +1235,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ret = -EINVAL; goto out_err; } + + ret = nf_defrag_ipv6_enable(ipvs->net); + if (ret) + goto out_err; } #endif @@ -2221,6 +2232,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user u->udp_timeout); #ifdef CONFIG_IP_VS_PROTO_TCP + if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) || + u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) { + return -EINVAL; + } +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP + if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ)) + return -EINVAL; +#endif + +#ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index b6d0f6deea86..7554c56b2e63 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -33,12 +33,6 @@ #define CONNCOUNT_SLOTS 256U -#ifdef CONFIG_LOCKDEP -#define CONNCOUNT_LOCK_SLOTS 8U -#else -#define CONNCOUNT_LOCK_SLOTS 256U -#endif - #define CONNCOUNT_GC_MAX_NODES 8 #define MAX_KEYLEN 5 @@ -49,8 +43,6 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; - bool dead; - struct rcu_head rcu_head; }; struct nf_conncount_rb { @@ -60,7 +52,7 @@ struct nf_conncount_rb { struct rcu_head rcu_head; }; -static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp; +static spinlock_t nf_conncount_locks[CONNCOUNT_SLOTS] __cacheline_aligned_in_smp; struct nf_conncount_data { unsigned int keylen; @@ -89,79 +81,25 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -enum nf_conncount_list_add -nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) -{ - struct nf_conncount_tuple *conn; - - if (WARN_ON_ONCE(list->count > INT_MAX)) - return NF_CONNCOUNT_ERR; - - conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); - if (conn == NULL) - return NF_CONNCOUNT_ERR; - - conn->tuple = *tuple; - conn->zone = *zone; - conn->cpu = raw_smp_processor_id(); - conn->jiffies32 = (u32)jiffies; - conn->dead = false; - spin_lock_bh(&list->list_lock); - if (list->dead == true) { - kmem_cache_free(conncount_conn_cachep, conn); - spin_unlock_bh(&list->list_lock); - return NF_CONNCOUNT_SKIP; - } - list_add_tail(&conn->node, &list->head); - list->count++; - spin_unlock_bh(&list->list_lock); - return NF_CONNCOUNT_ADDED; -} -EXPORT_SYMBOL_GPL(nf_conncount_add); - -static void __conn_free(struct rcu_head *h) -{ - struct nf_conncount_tuple *conn; - - conn = container_of(h, struct nf_conncount_tuple, rcu_head); - kmem_cache_free(conncount_conn_cachep, conn); -} - -static bool conn_free(struct nf_conncount_list *list, +static void conn_free(struct nf_conncount_list *list, struct nf_conncount_tuple *conn) { - bool free_entry = false; - - spin_lock_bh(&list->list_lock); - - if (conn->dead) { - spin_unlock_bh(&list->list_lock); - return free_entry; - } + lockdep_assert_held(&list->list_lock); list->count--; - conn->dead = true; - list_del_rcu(&conn->node); - if (list->count == 0) { - list->dead = true; - free_entry = true; - } + list_del(&conn->node); - spin_unlock_bh(&list->list_lock); - call_rcu(&conn->rcu_head, __conn_free); - return free_entry; + kmem_cache_free(conncount_conn_cachep, conn); } static const struct nf_conntrack_tuple_hash * find_or_evict(struct net *net, struct nf_conncount_list *list, - struct nf_conncount_tuple *conn, bool *free_entry) + struct nf_conncount_tuple *conn) { const struct nf_conntrack_tuple_hash *found; unsigned long a, b; int cpu = raw_smp_processor_id(); - __s32 age; + u32 age; found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); if (found) @@ -176,52 +114,45 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, */ age = a - b; if (conn->cpu == cpu || age >= 2) { - *free_entry = conn_free(list, conn); + conn_free(list, conn); return ERR_PTR(-ENOENT); } return ERR_PTR(-EAGAIN); } -void nf_conncount_lookup(struct net *net, - struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit) +static int __nf_conncount_add(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collect = 0; - bool free_entry = false; - - /* best effort only */ - *addit = tuple ? true : false; /* check the saved connections */ list_for_each_entry_safe(conn, conn_n, &list->head, node) { if (collect > CONNCOUNT_GC_MAX_NODES) break; - found = find_or_evict(net, list, conn, &free_entry); + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { - if (!tuple) - continue; - if (nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_id(&conn->zone, conn->zone.dir) == nf_ct_zone_id(zone, zone->dir)) - *addit = false; - } else if (PTR_ERR(found) == -ENOENT) + return 0; /* already exists */ + } else { collect++; + } continue; } found_ct = nf_ct_tuplehash_to_ctrack(found); - if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) && + if (nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_equal(found_ct, zone, zone->dir)) { /* * We should not see tuples twice unless someone hooks @@ -229,7 +160,8 @@ void nf_conncount_lookup(struct net *net, * * Attempt to avoid a re-add in this case. */ - *addit = false; + nf_ct_put(found_ct); + return 0; } else if (already_closed(found_ct)) { /* * we do not care about connections which are @@ -243,19 +175,48 @@ void nf_conncount_lookup(struct net *net, nf_ct_put(found_ct); } + + if (WARN_ON_ONCE(list->count > INT_MAX)) + return -EOVERFLOW; + + conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); + if (conn == NULL) + return -ENOMEM; + + conn->tuple = *tuple; + conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; + list_add_tail(&conn->node, &list->head); + list->count++; + return 0; } -EXPORT_SYMBOL_GPL(nf_conncount_lookup); + +int nf_conncount_add(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) +{ + int ret; + + /* check the saved connections */ + spin_lock_bh(&list->list_lock); + ret = __nf_conncount_add(net, list, tuple, zone); + spin_unlock_bh(&list->list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(nf_conncount_add); void nf_conncount_list_init(struct nf_conncount_list *list) { spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); list->count = 0; - list->dead = false; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); -/* Return true if the list is empty */ +/* Return true if the list is empty. Must be called with BH disabled. */ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list) { @@ -263,17 +224,17 @@ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collected = 0; - bool free_entry = false; bool ret = false; + /* don't bother if other cpu is already doing GC */ + if (!spin_trylock(&list->list_lock)) + return false; + list_for_each_entry_safe(conn, conn_n, &list->head, node) { - found = find_or_evict(net, list, conn, &free_entry); + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { - if (PTR_ERR(found) == -ENOENT) { - if (free_entry) - return true; + if (PTR_ERR(found) == -ENOENT) collected++; - } continue; } @@ -284,23 +245,19 @@ bool nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - if (conn_free(list, conn)) - return true; + conn_free(list, conn); collected++; continue; } nf_ct_put(found_ct); if (collected > CONNCOUNT_GC_MAX_NODES) - return false; + break; } - spin_lock_bh(&list->list_lock); - if (!list->count) { - list->dead = true; + if (!list->count) ret = true; - } - spin_unlock_bh(&list->list_lock); + spin_unlock(&list->list_lock); return ret; } @@ -314,6 +271,7 @@ static void __tree_nodes_free(struct rcu_head *h) kmem_cache_free(conncount_rb_cachep, rbconn); } +/* caller must hold tree nf_conncount_locks[] lock */ static void tree_nodes_free(struct rb_root *root, struct nf_conncount_rb *gc_nodes[], unsigned int gc_count) @@ -323,8 +281,10 @@ static void tree_nodes_free(struct rb_root *root, while (gc_count) { rbconn = gc_nodes[--gc_count]; spin_lock(&rbconn->list.list_lock); - rb_erase(&rbconn->node, root); - call_rcu(&rbconn->rcu_head, __tree_nodes_free); + if (!rbconn->list.count) { + rb_erase(&rbconn->node, root); + call_rcu(&rbconn->rcu_head, __tree_nodes_free); + } spin_unlock(&rbconn->list.list_lock); } } @@ -341,20 +301,19 @@ insert_tree(struct net *net, struct rb_root *root, unsigned int hash, const u32 *key, - u8 keylen, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - enum nf_conncount_list_add ret; struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES]; struct rb_node **rbnode, *parent; struct nf_conncount_rb *rbconn; struct nf_conncount_tuple *conn; unsigned int count = 0, gc_count = 0; - bool node_found = false; - - spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); + u8 keylen = data->keylen; + bool do_gc = true; + spin_lock_bh(&nf_conncount_locks[hash]); +restart: parent = NULL; rbnode = &(root->rb_node); while (*rbnode) { @@ -368,45 +327,32 @@ insert_tree(struct net *net, } else if (diff > 0) { rbnode = &((*rbnode)->rb_right); } else { - /* unlikely: other cpu added node already */ - node_found = true; - ret = nf_conncount_add(&rbconn->list, tuple, zone); - if (ret == NF_CONNCOUNT_ERR) { + int ret; + + ret = nf_conncount_add(net, &rbconn->list, tuple, zone); + if (ret) count = 0; /* hotdrop */ - } else if (ret == NF_CONNCOUNT_ADDED) { + else count = rbconn->list.count; - } else { - /* NF_CONNCOUNT_SKIP, rbconn is already - * reclaimed by gc, insert a new tree node - */ - node_found = false; - } - break; + tree_nodes_free(root, gc_nodes, gc_count); + goto out_unlock; } if (gc_count >= ARRAY_SIZE(gc_nodes)) continue; - if (nf_conncount_gc_list(net, &rbconn->list)) + if (do_gc && nf_conncount_gc_list(net, &rbconn->list)) gc_nodes[gc_count++] = rbconn; } if (gc_count) { tree_nodes_free(root, gc_nodes, gc_count); - /* tree_node_free before new allocation permits - * allocator to re-use newly free'd object. - * - * This is a rare event; in most cases we will find - * existing node to re-use. (or gc_count is 0). - */ - - if (gc_count >= ARRAY_SIZE(gc_nodes)) - schedule_gc_worker(data, hash); + schedule_gc_worker(data, hash); + gc_count = 0; + do_gc = false; + goto restart; } - if (node_found) - goto out_unlock; - /* expected case: match, insert new node */ rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC); if (rbconn == NULL) @@ -427,10 +373,10 @@ insert_tree(struct net *net, count = 1; rbconn->list.count = count; - rb_link_node(&rbconn->node, parent, rbnode); + rb_link_node_rcu(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); out_unlock: - spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); + spin_unlock_bh(&nf_conncount_locks[hash]); return count; } @@ -441,7 +387,6 @@ count_tree(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - enum nf_conncount_list_add ret; struct rb_root *root; struct rb_node *parent; struct nf_conncount_rb *rbconn; @@ -454,7 +399,6 @@ count_tree(struct net *net, parent = rcu_dereference_raw(root->rb_node); while (parent) { int diff; - bool addit; rbconn = rb_entry(parent, struct nf_conncount_rb, node); @@ -464,31 +408,36 @@ count_tree(struct net *net, } else if (diff > 0) { parent = rcu_dereference_raw(parent->rb_right); } else { - /* same source network -> be counted! */ - nf_conncount_lookup(net, &rbconn->list, tuple, zone, - &addit); + int ret; - if (!addit) + if (!tuple) { + nf_conncount_gc_list(net, &rbconn->list); return rbconn->list.count; + } - ret = nf_conncount_add(&rbconn->list, tuple, zone); - if (ret == NF_CONNCOUNT_ERR) { - return 0; /* hotdrop */ - } else if (ret == NF_CONNCOUNT_ADDED) { - return rbconn->list.count; - } else { - /* NF_CONNCOUNT_SKIP, rbconn is already - * reclaimed by gc, insert a new tree node - */ + spin_lock_bh(&rbconn->list.list_lock); + /* Node might be about to be free'd. + * We need to defer to insert_tree() in this case. + */ + if (rbconn->list.count == 0) { + spin_unlock_bh(&rbconn->list.list_lock); break; } + + /* same source network -> be counted! */ + ret = __nf_conncount_add(net, &rbconn->list, tuple, zone); + spin_unlock_bh(&rbconn->list.list_lock); + if (ret) + return 0; /* hotdrop */ + else + return rbconn->list.count; } } if (!tuple) return 0; - return insert_tree(net, data, root, hash, key, keylen, tuple, zone); + return insert_tree(net, data, root, hash, key, tuple, zone); } static void tree_gc_worker(struct work_struct *work) @@ -499,27 +448,47 @@ static void tree_gc_worker(struct work_struct *work) struct rb_node *node; unsigned int tree, next_tree, gc_count = 0; - tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS; + tree = data->gc_tree % CONNCOUNT_SLOTS; root = &data->root[tree]; + local_bh_disable(); rcu_read_lock(); for (node = rb_first(root); node != NULL; node = rb_next(node)) { rbconn = rb_entry(node, struct nf_conncount_rb, node); if (nf_conncount_gc_list(data->net, &rbconn->list)) - gc_nodes[gc_count++] = rbconn; + gc_count++; } rcu_read_unlock(); + local_bh_enable(); + + cond_resched(); spin_lock_bh(&nf_conncount_locks[tree]); + if (gc_count < ARRAY_SIZE(gc_nodes)) + goto next; /* do not bother */ - if (gc_count) { - tree_nodes_free(root, gc_nodes, gc_count); + gc_count = 0; + node = rb_first(root); + while (node != NULL) { + rbconn = rb_entry(node, struct nf_conncount_rb, node); + node = rb_next(node); + + if (rbconn->list.count > 0) + continue; + + gc_nodes[gc_count++] = rbconn; + if (gc_count >= ARRAY_SIZE(gc_nodes)) { + tree_nodes_free(root, gc_nodes, gc_count); + gc_count = 0; + } } + tree_nodes_free(root, gc_nodes, gc_count); +next: clear_bit(tree, data->pending_trees); next_tree = (tree + 1) % CONNCOUNT_SLOTS; - next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS); + next_tree = find_next_bit(data->pending_trees, CONNCOUNT_SLOTS, next_tree); if (next_tree < CONNCOUNT_SLOTS) { data->gc_tree = next_tree; @@ -621,10 +590,7 @@ static int __init nf_conncount_modinit(void) { int i; - BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS); - BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0); - - for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i) + for (i = 0; i < CONNCOUNT_SLOTS; ++i) spin_lock_init(&nf_conncount_locks[i]); conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple", diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 277d02a8cac8..27eff89fad01 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -25,6 +25,7 @@ #include <linux/slab.h> #include <linux/random.h> #include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/err.h> #include <linux/percpu.h> #include <linux/moduleparam.h> @@ -424,6 +425,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, } EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); +/* Generate a almost-unique pseudo-id for a given conntrack. + * + * intentionally doesn't re-use any of the seeds used for hash + * table location, we assume id gets exposed to userspace. + * + * Following nf_conn items do not change throughout lifetime + * of the nf_conn after it has been committed to main hash table: + * + * 1. nf_conn address + * 2. nf_conn->ext address + * 3. nf_conn->master address (normally NULL) + * 4. tuple + * 5. the associated net namespace + */ +u32 nf_ct_get_id(const struct nf_conn *ct) +{ + static __read_mostly siphash_key_t ct_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&ct_id_seed, sizeof(ct_id_seed)); + + a = (unsigned long)ct; + b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct)); + c = (unsigned long)ct->ext; + d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash), + &ct_id_seed); +#ifdef CONFIG_64BIT + return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed); +#else + return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed); +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_get_id); + static void clean_from_lists(struct nf_conn *ct) { @@ -901,10 +936,18 @@ __nf_conntrack_confirm(struct sk_buff *skb) * REJECT will give spurious warnings here. */ - /* No external references means no one else could have - * confirmed us. + /* Another skb with the same unconfirmed conntrack may + * win the race. This may happen for bridge(br_flood) + * or broadcast/multicast packets do skb_clone with + * unconfirmed conntrack. */ - WARN_ON(nf_ct_is_confirmed(ct)); + if (unlikely(nf_ct_is_confirmed(ct))) { + WARN_ON_ONCE(1); + nf_conntrack_double_unlock(hash, reply_hash); + local_bh_enable(); + return NF_DROP; + } + pr_debug("Confirming conntrack %p\n", ct); /* We have to check the DYING flag after unlink to prevent * a race against nf_ct_get_next_corpse() possibly called from @@ -1007,6 +1050,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 036207ecaf16..47e5a076522d 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -29,6 +29,7 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> +#include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> @@ -487,7 +488,9 @@ nla_put_failure: static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct))) + __be32 id = (__force __be32)nf_ct_get_id(ct); + + if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; @@ -1275,8 +1278,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, } if (cda[CTA_ID]) { - u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID])); - if (id != (u32)(unsigned long)ct) { + __be32 id = nla_get_be32(cda[CTA_ID]); + + if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } @@ -2675,6 +2679,25 @@ nla_put_failure: static const union nf_inet_addr any_addr; +static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) +{ + static __read_mostly siphash_key_t exp_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); + + a = (unsigned long)exp; + b = (unsigned long)exp->helper; + c = (unsigned long)exp->master; + d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); + +#ifdef CONFIG_64BIT + return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); +#else + return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); +#endif +} + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2722,7 +2745,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || - nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) || + nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; @@ -3027,7 +3050,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 51c5d7eec0a3..e903ef9b96cf 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -86,7 +86,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb, struct va_format vaf; va_list args; - if (net->ct.sysctl_log_invalid != protonum || + if (net->ct.sysctl_log_invalid != protonum && net->ct.sysctl_log_invalid != IPPROTO_RAW) return; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 650eb4fba2c5..841c472aae1c 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -43,24 +43,12 @@ #include <linux/netfilter/nf_conntrack_proto_gre.h> #include <linux/netfilter/nf_conntrack_pptp.h> -enum grep_conntrack { - GRE_CT_UNREPLIED, - GRE_CT_REPLIED, - GRE_CT_MAX -}; - static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_UNREPLIED] = 30*HZ, [GRE_CT_REPLIED] = 180*HZ, }; static unsigned int proto_gre_net_id __read_mostly; -struct netns_proto_gre { - struct nf_proto_net nf; - rwlock_t keymap_lock; - struct list_head keymap_list; - unsigned int gre_timeouts[GRE_CT_MAX]; -}; static inline struct netns_proto_gre *gre_pernet(struct net *net) { @@ -408,6 +396,8 @@ static int __init nf_ct_proto_gre_init(void) { int ret; + BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0); + ret = register_pernet_subsys(&proto_gre_net_ops); if (ret < 0) goto out_pernet; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 247b89784a6f..842f3f86fb2e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -769,6 +769,12 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +static bool nf_conntrack_tcp_established(const struct nf_conn *ct) +{ + return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED && + test_bit(IPS_ASSURED_BIT, &ct->status); +} + /* Returns verdict for packet, or -1 for invalid. */ static int tcp_packet(struct nf_conn *ct, const struct sk_buff *skb, @@ -963,16 +969,38 @@ static int tcp_packet(struct nf_conn *ct, new_state = TCP_CONNTRACK_ESTABLISHED; break; case TCP_CONNTRACK_CLOSE: - if (index == TCP_RST_SET - && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) - && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { - /* Invalid RST */ - spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); - return -NF_ACCEPT; + if (index != TCP_RST_SET) + break; + + if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) { + u32 seq = ntohl(th->seq); + + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { + /* Invalid RST */ + spin_unlock_bh(&ct->lock); + nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); + return -NF_ACCEPT; + } + + if (!nf_conntrack_tcp_established(ct) || + seq == ct->proto.tcp.seen[!dir].td_maxack) + break; + + /* Check if rst is part of train, such as + * foo:80 > bar:4379: P, 235946583:235946602(19) ack 42 + * foo:80 > bar:4379: R, 235946602:235946602(0) ack 42 + */ + if (ct->proto.tcp.last_index == TCP_ACK_SET && + ct->proto.tcp.last_dir == dir && + seq == ct->proto.tcp.last_end) + break; + + /* ... RST sequence number doesn't match exactly, keep + * established state to allow a possible challenge ACK. + */ + new_state = old_state; } - if (index == TCP_RST_SET - && ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) + if (((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_SYN_SET) || (!test_bit(IPS_ASSURED_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_ACK_SET)) @@ -988,7 +1016,7 @@ static int tcp_packet(struct nf_conn *ct, * segments we ignored. */ goto in_window; } - /* Just fall through */ + break; default: /* Keep compilers happy. */ break; @@ -1023,6 +1051,8 @@ static int tcp_packet(struct nf_conn *ct, if (ct->proto.tcp.retrans >= tn->tcp_max_retrans && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; + else if (unlikely(index == TCP_RST_SET)) + timeout = timeouts[TCP_CONNTRACK_CLOSE]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index a975efd6b8c3..9da303461069 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -115,12 +115,12 @@ static void nf_ct_sack_block_adjust(struct sk_buff *skb, /* TCP SACK sequence number adjustment */ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, unsigned int protoff, - struct tcphdr *tcph, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - unsigned int dir, optoff, optend; + struct tcphdr *tcph = (void *)skb->data + protoff; struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + unsigned int dir, optoff, optend; optoff = protoff + sizeof(struct tcphdr); optend = protoff + tcph->doff * 4; @@ -128,6 +128,7 @@ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, if (!skb_make_writable(skb, optend)) return 0; + tcph = (void *)skb->data + protoff; dir = CTINFO2DIR(ctinfo); while (optoff < optend) { @@ -207,7 +208,7 @@ int nf_ct_seq_adjust(struct sk_buff *skb, ntohl(newack)); tcph->ack_seq = newack; - res = nf_ct_sack_adjust(skb, protoff, tcph, ct, ctinfo); + res = nf_ct_sack_adjust(skb, protoff, ct, ctinfo); out: spin_unlock_bh(&ct->lock); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index d8125616edc7..e1537ace2b90 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -28,6 +28,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, { struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple; struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple; + struct dst_entry *other_dst = route->tuple[!dir].dst; struct dst_entry *dst = route->tuple[dir].dst; ft->dir = dir; @@ -50,8 +51,8 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, ft->src_port = ctt->src.u.tcp.port; ft->dst_port = ctt->dst.u.tcp.port; - ft->iifidx = route->tuple[dir].ifindex; - ft->oifidx = route->tuple[!dir].ifindex; + ft->iifidx = other_dst->dev->ifindex; + ft->oifidx = dst->dev->ifindex; ft->dst_cache = dst; } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index e2b196054dfc..2268b10a9dcf 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -117,7 +117,8 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; - dst_hold(dst); + if (!dst_hold_safe(dst)) + return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fe0558b15fd3..ebfcfe1dcbdb 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -112,6 +112,23 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_set_is_anonymous(set)) + return; + + list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + nft_trans_set(trans) == set) { + set->bound = true; + break; + } + } +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -222,14 +239,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule) + struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { if (expr->ops->deactivate) - expr->ops->deactivate(ctx, expr); + expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } @@ -280,7 +298,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } @@ -291,6 +309,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) int err; list_for_each_entry(rule, &ctx->chain->rules, list) { + if (!nft_is_active_next(ctx->net, rule)) + continue; + err = nft_delrule(ctx, rule); if (err < 0) return err; @@ -298,7 +319,7 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) return 0; } -static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type, +static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, struct nft_set *set) { struct nft_trans *trans; @@ -318,7 +339,7 @@ static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type, return 0; } -static int nft_delset(struct nft_ctx *ctx, struct nft_set *set) +static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -1199,7 +1220,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; - if (basechain->stats && nft_dump_stats(skb, basechain->stats)) + if (rcu_access_pointer(basechain->stats) && + nft_dump_stats(skb, rcu_dereference(basechain->stats))) goto nla_put_failure; } @@ -1375,7 +1397,8 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) return newstats; } -static void nft_chain_stats_replace(struct nft_base_chain *chain, +static void nft_chain_stats_replace(struct net *net, + struct nft_base_chain *chain, struct nft_stats __percpu *newstats) { struct nft_stats __percpu *oldstats; @@ -1383,8 +1406,9 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain, if (newstats == NULL) return; - if (chain->stats) { - oldstats = nfnl_dereference(chain->stats, NFNL_SUBSYS_NFTABLES); + if (rcu_access_pointer(chain->stats)) { + oldstats = rcu_dereference_protected(chain->stats, + lockdep_commit_lock_is_held(net)); rcu_assign_pointer(chain->stats, newstats); synchronize_rcu(); free_percpu(oldstats); @@ -1421,9 +1445,10 @@ static void nf_tables_chain_destroy(struct nft_ctx *ctx) struct nft_base_chain *basechain = nft_base_chain(chain); module_put(basechain->type->owner); - free_percpu(basechain->stats); - if (basechain->stats) + if (rcu_access_pointer(basechain->stats)) { static_branch_dec(&nft_counters_enabled); + free_percpu(rcu_dereference_raw(basechain->stats)); + } kfree(chain->name); kfree(basechain); } else { @@ -1471,7 +1496,7 @@ static int nft_chain_parse_hook(struct net *net, if (IS_ERR(type)) return PTR_ERR(type); } - if (!(type->hook_mask & (1 << hook->num))) + if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && @@ -1572,7 +1597,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, kfree(basechain); return PTR_ERR(stats); } - basechain->stats = stats; + rcu_assign_pointer(basechain->stats, stats); static_branch_inc(&nft_counters_enabled); } @@ -2088,9 +2113,11 @@ err1: static void nf_tables_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) { + const struct nft_expr_type *type = expr->ops->type; + if (expr->ops->destroy) expr->ops->destroy(ctx, expr); - module_put(expr->ops->type->owner); + module_put(type->owner); } struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, @@ -2098,6 +2125,7 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, { struct nft_expr_info info; struct nft_expr *expr; + struct module *owner; int err; err = nf_tables_expr_parse(ctx, nla, &info); @@ -2117,7 +2145,11 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err3: kfree(expr); err2: - module_put(info.ops->type->owner); + owner = info.ops->type->owner; + if (info.ops->type->release_ops) + info.ops->type->release_ops(info.ops); + + module_put(owner); err1: return ERR_PTR(err); } @@ -2451,7 +2483,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -2687,8 +2719,11 @@ err2: nf_tables_rule_release(&ctx, rule); err1: for (i = 0; i < n; i++) { - if (info[i].ops != NULL) + if (info[i].ops) { module_put(info[i].ops->type->owner); + if (info[i].ops->type->release_ops) + info[i].ops->type->release_ops(info[i].ops); + } } kvfree(info); return err; @@ -3555,19 +3590,15 @@ err1: static void nft_set_destroy(struct nft_set *set) { + if (WARN_ON(set->use > 0)) + return; + set->ops->destroy(set); module_put(to_set_type(set->ops)->owner); kfree(set->name); kvfree(set); } -static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) -{ - list_del_rcu(&set->list); - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); - nft_set_destroy(set); -} - static int nf_tables_delset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -3602,7 +3633,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(set); } - if (!list_empty(&set->bindings) || + if (set->use || (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; @@ -3632,6 +3663,9 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; + if (set->use == UINT_MAX) + return -EOVERFLOW; + if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -3658,21 +3692,53 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, bind: binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); + nft_set_trans_bind(ctx, set); + set->use++; + return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) - nf_tables_set_destroy(ctx, set); + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { + list_del_rcu(&set->list); + if (event) + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, + GFP_KERNEL); + } } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); +void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_binding *binding, + enum nft_trans_phase phase) +{ + switch (phase) { + case NFT_TRANS_PREPARE: + set->use--; + return; + case NFT_TRANS_ABORT: + case NFT_TRANS_RELEASE: + set->use--; + /* fall through */ + default: + nf_tables_unbind_set(ctx, set, binding, + phase == NFT_TRANS_COMMIT); + } +} +EXPORT_SYMBOL_GPL(nf_tables_deactivate_set); + +void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) +{ + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) + nft_set_destroy(set); +} +EXPORT_SYMBOL_GPL(nf_tables_destroy_set); + const struct nft_set_ext_type nft_set_ext_types[] = { [NFT_SET_EXT_KEY] = { .align = __alignof__(u32), @@ -4435,6 +4501,8 @@ err6: err5: kfree(trans); err4: + if (obj) + obj->use--; kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) @@ -6145,7 +6213,8 @@ static void nft_chain_commit_update(struct nft_trans *trans) return; basechain = nft_base_chain(trans->ctx.chain); - nft_chain_stats_replace(basechain, nft_trans_chain_stats(trans)); + nft_chain_stats_replace(trans->ctx.net, basechain, + nft_trans_chain_stats(trans)); switch (nft_trans_chain_policy(trans)) { case NF_DROP: @@ -6419,6 +6488,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_DELRULE); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_COMMIT); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -6567,7 +6639,9 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; @@ -6577,6 +6651,10 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; + if (nft_trans_set(trans)->bound) { + nft_trans_destroy(trans); + break; + } list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: @@ -6585,8 +6663,11 @@ static int __nf_tables_abort(struct net *net) nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: + if (nft_trans_elem_set(trans)->bound) { + nft_trans_destroy(trans); + break; + } te = (struct nft_trans_elem *)trans->data; - te->set->ops->remove(net, te->set, &te->elem); atomic_dec(&te->set->nelems); break; @@ -7193,9 +7274,6 @@ static void __nft_release_tables(struct net *net) list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); - list_for_each_entry(flowtable, &table->flowtables, list) - nf_unregister_net_hooks(net, flowtable->ops, - flowtable->ops_len); /* No packets are walking on these chains anymore. */ ctx.table = table; list_for_each_entry(chain, &table->chains, list) { diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index ffd5c0f9412b..a3850414dba2 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -98,21 +98,23 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, const struct nft_pktinfo *pkt) { struct nft_base_chain *base_chain; + struct nft_stats __percpu *pstats; struct nft_stats *stats; base_chain = nft_base_chain(chain); - if (!base_chain->stats) - return; - local_bh_disable(); - stats = this_cpu_ptr(rcu_dereference(base_chain->stats)); - if (stats) { + rcu_read_lock(); + pstats = READ_ONCE(base_chain->stats); + if (pstats) { + local_bh_disable(); + stats = this_cpu_ptr(pstats); u64_stats_update_begin(&stats->syncp); stats->pkts++; stats->bytes += pkt->skb->len; u64_stats_update_end(&stats->syncp); + local_bh_enable(); } - local_bh_enable(); + rcu_read_unlock(); } struct nft_jumpstack { diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index a30f8ba4b89a..70a7382b9787 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -392,7 +392,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -421,7 +422,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; @@ -444,6 +445,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -456,12 +458,55 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l3num, l4num); - /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &net->ct.nf_ct_proto.icmp.timeout; + break; + case IPPROTO_TCP: + timeouts = net->ct.nf_ct_proto.tcp.timeouts; + break; + case IPPROTO_UDP: /* fallthrough */ + case IPPROTO_UDPLITE: + timeouts = net->ct.nf_ct_proto.udp.timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = net->ct.nf_ct_proto.dccp.dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &net->ct.nf_ct_proto.icmpv6.timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = net->ct.nf_ct_proto.sctp.timeouts; +#endif + break; + case IPPROTO_GRE: +#ifdef CONFIG_NF_CT_PROTO_GRE + if (l4proto->net_id) { + struct netns_proto_gre *net_gre; + + net_gre = net_generic(net, *l4proto->net_id); + timeouts = net_gre->gre_timeouts; + } +#endif + break; + case 255: + timeouts = &net->ct.nf_ct_proto.generic.timeout; + break; + default: + WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto); + break; } + if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -472,7 +517,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l4proto); + l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM; diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 00db27dfd2ff..b0bc130947c9 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -71,6 +71,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb, int ttl_check, struct nf_osf_hdr_ctx *ctx) { + const __u8 *optpinit = ctx->optp; unsigned int check_WSS = 0; int fmatch = FMATCH_WRONG; int foptsize, optnum; @@ -160,6 +161,9 @@ static bool nf_osf_match_one(const struct sk_buff *skb, } } + if (fmatch != FMATCH_OK) + ctx->optp = optpinit; + return fmatch == FMATCH_OK; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 29d6fc73caf9..1245e02239d9 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -23,19 +23,6 @@ #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> -struct nft_xt { - struct list_head head; - struct nft_expr_ops ops; - unsigned int refcnt; - - /* Unlike other expressions, ops doesn't have static storage duration. - * nft core assumes they do. We use kfree_rcu so that nft core can - * can check expr->ops->size even after nft_compat->destroy() frees - * the nft_xt struct that holds the ops structure. - */ - struct rcu_head rcu_head; -}; - /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -43,17 +30,6 @@ struct nft_xt_match_priv { void *info; }; -static bool nft_xt_put(struct nft_xt *xt) -{ - if (--xt->refcnt == 0) { - list_del(&xt->head); - kfree_rcu(xt, rcu_head); - return true; - } - - return false; -} - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -248,7 +224,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_target *target = expr->ops->data; struct xt_tgchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO])); - struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -272,8 +247,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (!target->target) return -EINVAL; - nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; return 0; } @@ -282,6 +255,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); + struct module *me = target->me; struct xt_tgdtor_param par; par.net = ctx->net; @@ -291,8 +265,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.target->destroy != NULL) par.target->destroy(&par); - if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(target->me); + module_put(me); + kfree(expr->ops); } static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -446,7 +420,6 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_match *match = expr->ops->data; struct xt_mtchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO])); - struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -462,13 +435,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); - ret = xt_check_match(&par, size, proto, inv); - if (ret < 0) - return ret; - - nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; - return 0; + return xt_check_match(&par, size, proto, inv); } static int @@ -511,8 +478,8 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, if (par.match->destroy != NULL) par.match->destroy(&par); - if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(me); + module_put(me); + kfree(expr->ops); } static void @@ -714,22 +681,13 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { .cb = nfnl_nft_compat_cb, }; -static LIST_HEAD(nft_match_list); - static struct nft_expr_type nft_match_type; -static bool nft_match_cmp(const struct xt_match *match, - const char *name, u32 rev, u32 family) -{ - return strcmp(match->name, name) == 0 && match->revision == rev && - (match->family == NFPROTO_UNSPEC || match->family == family); -} - static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { - struct nft_xt *nft_match; + struct nft_expr_ops *ops; struct xt_match *match; unsigned int matchsize; char *mt_name; @@ -745,14 +703,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family; - /* Re-use the existing match if it's already loaded. */ - list_for_each_entry(nft_match, &nft_match_list, head) { - struct xt_match *match = nft_match->ops.data; - - if (nft_match_cmp(match, mt_name, rev, family)) - return &nft_match->ops; - } - match = xt_request_find_match(family, mt_name, rev); if (IS_ERR(match)) return ERR_PTR(-ENOENT); @@ -762,66 +712,62 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - /* This is the first time we use this match, allocate operations */ - nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_match == NULL) { + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + if (!ops) { err = -ENOMEM; goto err; } - nft_match->refcnt = 0; - nft_match->ops.type = &nft_match_type; - nft_match->ops.eval = nft_match_eval; - nft_match->ops.init = nft_match_init; - nft_match->ops.destroy = nft_match_destroy; - nft_match->ops.dump = nft_match_dump; - nft_match->ops.validate = nft_match_validate; - nft_match->ops.data = match; + ops->type = &nft_match_type; + ops->eval = nft_match_eval; + ops->init = nft_match_init; + ops->destroy = nft_match_destroy; + ops->dump = nft_match_dump; + ops->validate = nft_match_validate; + ops->data = match; matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); if (matchsize > NFT_MATCH_LARGE_THRESH) { matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv)); - nft_match->ops.eval = nft_match_large_eval; - nft_match->ops.init = nft_match_large_init; - nft_match->ops.destroy = nft_match_large_destroy; - nft_match->ops.dump = nft_match_large_dump; + ops->eval = nft_match_large_eval; + ops->init = nft_match_large_init; + ops->destroy = nft_match_large_destroy; + ops->dump = nft_match_large_dump; } - nft_match->ops.size = matchsize; - - list_add(&nft_match->head, &nft_match_list); + ops->size = matchsize; - return &nft_match->ops; + return ops; err: module_put(match->me); return ERR_PTR(err); } +static void nft_match_release_ops(const struct nft_expr_ops *ops) +{ + struct xt_match *match = ops->data; + + module_put(match->me); + kfree(ops); +} + static struct nft_expr_type nft_match_type __read_mostly = { .name = "match", .select_ops = nft_match_select_ops, + .release_ops = nft_match_release_ops, .policy = nft_match_policy, .maxattr = NFTA_MATCH_MAX, .owner = THIS_MODULE, }; -static LIST_HEAD(nft_target_list); - static struct nft_expr_type nft_target_type; -static bool nft_target_cmp(const struct xt_target *tg, - const char *name, u32 rev, u32 family) -{ - return strcmp(tg->name, name) == 0 && tg->revision == rev && - (tg->family == NFPROTO_UNSPEC || tg->family == family); -} - static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { - struct nft_xt *nft_target; + struct nft_expr_ops *ops; struct xt_target *target; char *tg_name; u32 rev, family; @@ -841,17 +787,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL); - /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_target_list, head) { - struct xt_target *target = nft_target->ops.data; - - if (!target->target) - continue; - - if (nft_target_cmp(target, tg_name, rev, family)) - return &nft_target->ops; - } - target = xt_request_find_target(family, tg_name, rev); if (IS_ERR(target)) return ERR_PTR(-ENOENT); @@ -866,38 +801,43 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - /* This is the first time we use this target, allocate operations */ - nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_target == NULL) { + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + if (!ops) { err = -ENOMEM; goto err; } - nft_target->refcnt = 0; - nft_target->ops.type = &nft_target_type; - nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); - nft_target->ops.init = nft_target_init; - nft_target->ops.destroy = nft_target_destroy; - nft_target->ops.dump = nft_target_dump; - nft_target->ops.validate = nft_target_validate; - nft_target->ops.data = target; + ops->type = &nft_target_type; + ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); + ops->init = nft_target_init; + ops->destroy = nft_target_destroy; + ops->dump = nft_target_dump; + ops->validate = nft_target_validate; + ops->data = target; if (family == NFPROTO_BRIDGE) - nft_target->ops.eval = nft_target_eval_bridge; + ops->eval = nft_target_eval_bridge; else - nft_target->ops.eval = nft_target_eval_xt; - - list_add(&nft_target->head, &nft_target_list); + ops->eval = nft_target_eval_xt; - return &nft_target->ops; + return ops; err: module_put(target->me); return ERR_PTR(err); } +static void nft_target_release_ops(const struct nft_expr_ops *ops) +{ + struct xt_target *target = ops->data; + + module_put(target->me); + kfree(ops); +} + static struct nft_expr_type nft_target_type __read_mostly = { .name = "target", .select_ops = nft_target_select_ops, + .release_ops = nft_target_release_ops, .policy = nft_target_policy, .maxattr = NFTA_TARGET_MAX, .owner = THIS_MODULE, @@ -922,7 +862,6 @@ static int __init nft_compat_module_init(void) } return ret; - err_target: nft_unregister_expr(&nft_target_type); err_match: @@ -932,32 +871,6 @@ err_match: static void __exit nft_compat_module_exit(void) { - struct nft_xt *xt, *next; - - /* list should be empty here, it can be non-empty only in case there - * was an error that caused nft_xt expr to not be initialized fully - * and noone else requested the same expression later. - * - * In this case, the lists contain 0-refcount entries that still - * hold module reference. - */ - list_for_each_entry_safe(xt, next, &nft_target_list, head) { - struct xt_target *target = xt->ops.data; - - if (WARN_ON_ONCE(xt->refcnt)) - continue; - module_put(target->me); - kfree(xt); - } - - list_for_each_entry_safe(xt, next, &nft_match_list, head) { - struct xt_match *match = xt->ops.data; - - if (WARN_ON_ONCE(xt->refcnt)) - continue; - module_put(match->me); - kfree(xt); - } nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index b90d96ba4a12..af1497ab9464 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -30,7 +30,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int count; - bool addit; tuple_ptr = &tuple; @@ -44,19 +43,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, return; } - nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, - &addit); - count = priv->list.count; - - if (!addit) - goto out; - - if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) { + if (nf_conncount_add(nft_net(pkt), &priv->list, tuple_ptr, zone)) { regs->verdict.code = NF_DROP; return; } - count++; -out: + + count = priv->list.count; if ((count > priv->limit) ^ priv->invert) { regs->verdict.code = NFT_BREAK; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 6e91a37d57f2..eb7f9a5f2aeb 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -235,14 +235,32 @@ err1: return err; } +static void nft_dynset_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) +{ + struct nft_dynset *priv = nft_expr_priv(expr); + + nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase); +} + +static void nft_dynset_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_dynset *priv = nft_expr_priv(expr); + + priv->set->use++; +} + static void nft_dynset_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_dynset *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); if (priv->expr != NULL) nft_expr_destroy(ctx, priv->expr); + + nf_tables_destroy_set(ctx, priv->set); } static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -279,6 +297,8 @@ static const struct nft_expr_ops nft_dynset_ops = { .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, + .activate = nft_dynset_activate, + .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, }; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 5fd4c57c79cc..436cc14cfc59 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -12,6 +12,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <linux/netfilter/nf_conntrack_common.h> #include <net/netfilter/nf_flow_table.h> +#include <net/netfilter/nf_conntrack_helper.h> struct nft_flow_offload { struct nft_flowtable *flowtable; @@ -29,10 +30,12 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: - fl.u.ip4.daddr = ct->tuplehash[!dir].tuple.dst.u3.ip; + fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; + fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; break; case NFPROTO_IPV6: - fl.u.ip6.daddr = ct->tuplehash[!dir].tuple.dst.u3.in6; + fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; + fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; break; } @@ -41,9 +44,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, return -ENOENT; route->tuple[dir].dst = this_dst; - route->tuple[dir].ifindex = nft_in(pkt)->ifindex; route->tuple[!dir].dst = other_dst; - route->tuple[!dir].ifindex = nft_out(pkt)->ifindex; return 0; } @@ -66,6 +67,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; + const struct nf_conn_help *help; enum ip_conntrack_info ctinfo; struct nf_flow_route route; struct flow_offload *flow; @@ -88,7 +90,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, goto out; } - if (test_bit(IPS_HELPER_BIT, &ct->status)) + help = nfct_help(ct); + if (help) goto out; if (ctinfo == IP_CT_NEW || diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 0777a93211e2..3f6d1d2a6281 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, } static void nft_immediate_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index ad13e8643599..161c3451a747 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -121,12 +121,29 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } +static void nft_lookup_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) +{ + struct nft_lookup *priv = nft_expr_priv(expr); + + nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase); +} + +static void nft_lookup_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_lookup *priv = nft_expr_priv(expr); + + priv->set->use++; +} + static void nft_lookup_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + nf_tables_destroy_set(ctx, priv->set); } static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -209,6 +226,8 @@ static const struct nft_expr_ops nft_lookup_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, + .activate = nft_lookup_activate, + .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, .validate = nft_lookup_validate, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index cdf348f751ec..bf92a40dd1b2 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -64,21 +64,34 @@ nla_put_failure: return -1; } -static void nft_objref_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_objref_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_object *obj = nft_objref_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + obj->use--; } +static void nft_objref_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_object *obj = nft_objref_priv(expr); + + obj->use++; +} + static struct nft_expr_type nft_objref_type; static const struct nft_expr_ops nft_objref_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_object *)), .eval = nft_objref_eval, .init = nft_objref_init, - .destroy = nft_objref_destroy, + .activate = nft_objref_activate, + .deactivate = nft_objref_deactivate, .dump = nft_objref_dump, }; @@ -155,12 +168,29 @@ nla_put_failure: return -1; } +static void nft_objref_map_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) +{ + struct nft_objref_map *priv = nft_expr_priv(expr); + + nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase); +} + +static void nft_objref_map_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_objref_map *priv = nft_expr_priv(expr); + + priv->set->use++; +} + static void nft_objref_map_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_objref_map *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + nf_tables_destroy_set(ctx, priv->set); } static struct nft_expr_type nft_objref_type; @@ -169,6 +199,8 @@ static const struct nft_expr_ops nft_objref_map_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, + .activate = nft_objref_map_activate, + .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, }; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 0e5ec126f6ad..b3e75f9cb686 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -302,10 +302,6 @@ static void *nft_rbtree_deactivate(const struct net *net, else if (d > 0) parent = parent->rb_right; else { - if (!nft_set_elem_active(&rbe->ext, genmask)) { - parent = parent->rb_left; - continue; - } if (nft_rbtree_interval_end(rbe) && !nft_rbtree_interval_end(this)) { parent = parent->rb_left; @@ -314,6 +310,9 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; + } else if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; } nft_rbtree_flush(net, set, rbe); return rbe; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index aecadd471e1d..13e1ac333fa4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1899,7 +1899,7 @@ static int __init xt_init(void) seqcount_init(&per_cpu(xt_recseq, i)); } - xt = kmalloc_array(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); + xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 0d0d68c989df..1dae02a97ee3 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -14,6 +14,8 @@ #include <linux/skbuff.h> #include <linux/route.h> #include <linux/netfilter/x_tables.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include <net/route.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #include <net/netfilter/ipv6/nf_dup_ipv6.h> @@ -25,8 +27,15 @@ struct xt_tee_priv { int oif; }; +static unsigned int tee_net_id __read_mostly; static const union nf_inet_addr tee_zero_address; +struct tee_net { + struct list_head priv_list; + /* lock protects the priv_list */ + struct mutex lock; +}; + static unsigned int tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { @@ -51,17 +60,16 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) } #endif -static DEFINE_MUTEX(priv_list_mutex); -static LIST_HEAD(priv_list); - static int tee_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + struct tee_net *tn = net_generic(net, tee_net_id); struct xt_tee_priv *priv; - mutex_lock(&priv_list_mutex); - list_for_each_entry(priv, &priv_list, list) { + mutex_lock(&tn->lock); + list_for_each_entry(priv, &tn->priv_list, list) { switch (event) { case NETDEV_REGISTER: if (!strcmp(dev->name, priv->tginfo->oif)) @@ -79,13 +87,14 @@ static int tee_netdev_event(struct notifier_block *this, unsigned long event, break; } } - mutex_unlock(&priv_list_mutex); + mutex_unlock(&tn->lock); return NOTIFY_DONE; } static int tee_tg_check(const struct xt_tgchk_param *par) { + struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; struct xt_tee_priv *priv; @@ -95,6 +104,8 @@ static int tee_tg_check(const struct xt_tgchk_param *par) return -EINVAL; if (info->oif[0]) { + struct net_device *dev; + if (info->oif[sizeof(info->oif)-1] != '\0') return -EINVAL; @@ -106,9 +117,14 @@ static int tee_tg_check(const struct xt_tgchk_param *par) priv->oif = -1; info->priv = priv; - mutex_lock(&priv_list_mutex); - list_add(&priv->list, &priv_list); - mutex_unlock(&priv_list_mutex); + dev = dev_get_by_name(par->net, info->oif); + if (dev) { + priv->oif = dev->ifindex; + dev_put(dev); + } + mutex_lock(&tn->lock); + list_add(&priv->list, &tn->priv_list); + mutex_unlock(&tn->lock); } else info->priv = NULL; @@ -118,12 +134,13 @@ static int tee_tg_check(const struct xt_tgchk_param *par) static void tee_tg_destroy(const struct xt_tgdtor_param *par) { + struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; if (info->priv) { - mutex_lock(&priv_list_mutex); + mutex_lock(&tn->lock); list_del(&info->priv->list); - mutex_unlock(&priv_list_mutex); + mutex_unlock(&tn->lock); kfree(info->priv); } static_key_slow_dec(&xt_tee_enabled); @@ -156,6 +173,21 @@ static struct xt_target tee_tg_reg[] __read_mostly = { #endif }; +static int __net_init tee_net_init(struct net *net) +{ + struct tee_net *tn = net_generic(net, tee_net_id); + + INIT_LIST_HEAD(&tn->priv_list); + mutex_init(&tn->lock); + return 0; +} + +static struct pernet_operations tee_net_ops = { + .init = tee_net_init, + .id = &tee_net_id, + .size = sizeof(struct tee_net), +}; + static struct notifier_block tee_netdev_notifier = { .notifier_call = tee_netdev_event, }; @@ -164,22 +196,32 @@ static int __init tee_tg_init(void) { int ret; - ret = xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); - if (ret) + ret = register_pernet_subsys(&tee_net_ops); + if (ret < 0) return ret; + + ret = xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); + if (ret < 0) + goto cleanup_subsys; + ret = register_netdevice_notifier(&tee_netdev_notifier); - if (ret) { - xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); - return ret; - } + if (ret < 0) + goto unregister_targets; return 0; + +unregister_targets: + xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); +cleanup_subsys: + unregister_pernet_subsys(&tee_net_ops); + return ret; } static void __exit tee_tg_exit(void) { unregister_netdevice_notifier(&tee_netdev_notifier); xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); + unregister_pernet_subsys(&tee_net_ops); } module_init(tee_tg_init); diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 5d92e1781980..5cb1ecb29ea4 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -68,6 +68,38 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) return 0; } +static int cgroup_mt_check_v2(const struct xt_mtchk_param *par) +{ + struct xt_cgroup_info_v2 *info = par->matchinfo; + struct cgroup *cgrp; + + if ((info->invert_path & ~1) || (info->invert_classid & ~1)) + return -EINVAL; + + if (!info->has_path && !info->has_classid) { + pr_info("xt_cgroup: no path or classid specified\n"); + return -EINVAL; + } + + if (info->has_path && info->has_classid) { + pr_info_ratelimited("path and classid specified\n"); + return -EINVAL; + } + + info->priv = NULL; + if (info->has_path) { + cgrp = cgroup_get_from_path(info->path); + if (IS_ERR(cgrp)) { + pr_info_ratelimited("invalid path, errno=%ld\n", + PTR_ERR(cgrp)); + return -EINVAL; + } + info->priv = cgrp; + } + + return 0; +} + static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { @@ -99,6 +131,24 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) info->invert_classid; } +static bool cgroup_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_cgroup_info_v2 *info = par->matchinfo; + struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; + struct cgroup *ancestor = info->priv; + struct sock *sk = skb->sk; + + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) + return false; + + if (ancestor) + return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ + info->invert_path; + else + return (info->classid == sock_cgroup_classid(skcd)) ^ + info->invert_classid; +} + static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) { struct xt_cgroup_info_v1 *info = par->matchinfo; @@ -107,6 +157,14 @@ static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) cgroup_put(info->priv); } +static void cgroup_mt_destroy_v2(const struct xt_mtdtor_param *par) +{ + struct xt_cgroup_info_v2 *info = par->matchinfo; + + if (info->priv) + cgroup_put(info->priv); +} + static struct xt_match cgroup_mt_reg[] __read_mostly = { { .name = "cgroup", @@ -134,6 +192,20 @@ static struct xt_match cgroup_mt_reg[] __read_mostly = { (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, + { + .name = "cgroup", + .revision = 2, + .family = NFPROTO_UNSPEC, + .checkentry = cgroup_mt_check_v2, + .match = cgroup_mt_v2, + .matchsize = sizeof(struct xt_cgroup_info_v2), + .usersize = offsetof(struct xt_cgroup_info_v2, priv), + .destroy = cgroup_mt_destroy_v2, + .me = THIS_MODULE, + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + }, }; static int __init cgroup_mt_init(void) diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 9d6d67b953ac..05f00fb20b04 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -96,8 +96,7 @@ match_outdev: static int physdev_mt_check(const struct xt_mtchk_param *par) { const struct xt_physdev_info *info = par->matchinfo; - - br_netfilter_enable(); + static bool brnf_probed __read_mostly; if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) @@ -111,6 +110,12 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) return -EINVAL; } + + if (!brnf_probed) { + brnf_probed = true; + request_module("br_netfilter"); + } + return 0; } diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index ea7c67050792..ee3e5b6471a6 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -903,7 +903,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, (state == 0 && (byte & bitmask) == 0)) return bit_spot; - bit_spot++; + if (++bit_spot >= bitmap_len) + return -1; bitmask >>= 1; if (bitmask == 0) { byte = bitmap[++byte_offset]; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 25eeb6d2a75a..f0ec068e1d02 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -366,7 +366,7 @@ int genl_register_family(struct genl_family *family) start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; - goto errout_locked; + goto errout_free; } err = genl_validate_assign_mc_groups(family); @@ -385,6 +385,7 @@ int genl_register_family(struct genl_family *family) errout_remove: idr_remove(&genl_fam_idr, family->id); +errout_free: kfree(family->attrbuf); errout_locked: genl_unlock_all(); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 03f37c4e64fe..71ffd1a6dc7c 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -153,7 +153,7 @@ static struct sock *nr_find_listener(ax25_address *addr) sk_for_each(s, &nr_list) if (!ax25cmp(&nr_sk(s)->source_addr, addr) && s->sk_state == TCP_LISTEN) { - bh_lock_sock(s); + sock_hold(s); goto found; } s = NULL; @@ -174,7 +174,7 @@ static struct sock *nr_find_socket(unsigned char index, unsigned char id) struct nr_sock *nr = nr_sk(s); if (nr->my_index == index && nr->my_id == id) { - bh_lock_sock(s); + sock_hold(s); goto found; } } @@ -198,7 +198,7 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id, if (nr->your_index == index && nr->your_id == id && !ax25cmp(&nr->dest_addr, dest)) { - bh_lock_sock(s); + sock_hold(s); goto found; } } @@ -224,7 +224,7 @@ static unsigned short nr_find_next_circuit(void) if (i != 0 && j != 0) { if ((sk=nr_find_socket(i, j)) == NULL) break; - bh_unlock_sock(sk); + sock_put(sk); } id++; @@ -920,6 +920,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) } if (sk != NULL) { + bh_lock_sock(sk); skb_reset_transport_header(skb); if (frametype == NR_CONNACK && skb->len == 22) @@ -929,6 +930,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) ret = nr_process_rx_frame(sk, skb); bh_unlock_sock(sk); + sock_put(sk); return ret; } @@ -960,10 +962,12 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) (make = nr_make_new(sk)) == NULL) { nr_transmit_refusal(skb, 0); if (sk) - bh_unlock_sock(sk); + sock_put(sk); return 0; } + bh_lock_sock(sk); + window = skb->data[20]; skb->sk = make; @@ -1016,6 +1020,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) sk->sk_data_ready(sk); bh_unlock_sock(sk); + sock_put(sk); nr_insert_socket(make); @@ -1387,18 +1392,22 @@ static int __init nr_proto_init(void) int i; int rc = proto_register(&nr_proto, 0); - if (rc != 0) - goto out; + if (rc) + return rc; if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n"); - return -1; + pr_err("NET/ROM: %s - nr_ndevs parameter too large\n", + __func__); + rc = -EINVAL; + goto unregister_proto; } dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL); - if (dev_nr == NULL) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n"); - return -1; + if (!dev_nr) { + pr_err("NET/ROM: %s - unable to allocate device array\n", + __func__); + rc = -ENOMEM; + goto unregister_proto; } for (i = 0; i < nr_ndevs; i++) { @@ -1408,13 +1417,13 @@ static int __init nr_proto_init(void) sprintf(name, "nr%d", i); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup); if (!dev) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n"); + rc = -ENOMEM; goto fail; } dev->base_addr = i; - if (register_netdev(dev)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n"); + rc = register_netdev(dev); + if (rc) { free_netdev(dev); goto fail; } @@ -1422,36 +1431,64 @@ static int __init nr_proto_init(void) dev_nr[i] = dev; } - if (sock_register(&nr_family_ops)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n"); + rc = sock_register(&nr_family_ops); + if (rc) goto fail; - } - register_netdevice_notifier(&nr_dev_notifier); + rc = register_netdevice_notifier(&nr_dev_notifier); + if (rc) + goto out_sock; ax25_register_pid(&nr_pid); ax25_linkfail_register(&nr_linkfail_notifier); #ifdef CONFIG_SYSCTL - nr_register_sysctl(); + rc = nr_register_sysctl(); + if (rc) + goto out_sysctl; #endif nr_loopback_init(); - proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops); - proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops); - proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops); -out: - return rc; + rc = -ENOMEM; + if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops)) + goto proc_remove1; + if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net, + &nr_neigh_seqops)) + goto proc_remove2; + if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net, + &nr_node_seqops)) + goto proc_remove3; + + return 0; + +proc_remove3: + remove_proc_entry("nr_neigh", init_net.proc_net); +proc_remove2: + remove_proc_entry("nr", init_net.proc_net); +proc_remove1: + + nr_loopback_clear(); + nr_rt_free(); + +#ifdef CONFIG_SYSCTL + nr_unregister_sysctl(); +out_sysctl: +#endif + ax25_linkfail_release(&nr_linkfail_notifier); + ax25_protocol_release(AX25_P_NETROM); + unregister_netdevice_notifier(&nr_dev_notifier); +out_sock: + sock_unregister(PF_NETROM); fail: while (--i >= 0) { unregister_netdev(dev_nr[i]); free_netdev(dev_nr[i]); } kfree(dev_nr); +unregister_proto: proto_unregister(&nr_proto); - rc = -1; - goto out; + return rc; } module_init(nr_proto_init); diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c index 215ad22a9647..93d13f019981 100644 --- a/net/netrom/nr_loopback.c +++ b/net/netrom/nr_loopback.c @@ -70,7 +70,7 @@ static void nr_loopback_timer(struct timer_list *unused) } } -void __exit nr_loopback_clear(void) +void nr_loopback_clear(void) { del_timer_sync(&loopback_timer); skb_queue_purge(&loopback_queue); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 6485f593e2f0..b76aa668a94b 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -953,7 +953,7 @@ const struct seq_operations nr_neigh_seqops = { /* * Free all memory associated with the nodes and routes lists. */ -void __exit nr_rt_free(void) +void nr_rt_free(void) { struct nr_neigh *s = NULL; struct nr_node *t = NULL; diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index cbd51ed5a2d7..908e53ab47a4 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t1timer, jiffies + nr->t1); + sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1); } void nr_start_t2timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t2timer, jiffies + nr->t2); + sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2); } void nr_start_t4timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t4timer, jiffies + nr->t4); + sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4); } void nr_start_idletimer(struct sock *sk) @@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk) struct nr_sock *nr = nr_sk(sk); if (nr->idle > 0) - mod_timer(&nr->idletimer, jiffies + nr->idle); + sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle); } void nr_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void nr_stop_t1timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t1timer); + sk_stop_timer(sk, &nr_sk(sk)->t1timer); } void nr_stop_t2timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t2timer); + sk_stop_timer(sk, &nr_sk(sk)->t2timer); } void nr_stop_t4timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t4timer); + sk_stop_timer(sk, &nr_sk(sk)->t4timer); } void nr_stop_idletimer(struct sock *sk) { - del_timer(&nr_sk(sk)->idletimer); + sk_stop_timer(sk, &nr_sk(sk)->idletimer); } void nr_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } int nr_t1timer_running(struct sock *sk) diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index ba1c368b3f18..771011b84270 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -146,9 +146,12 @@ static struct ctl_table nr_table[] = { { } }; -void __init nr_register_sysctl(void) +int __init nr_register_sysctl(void) { nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table); + if (!nr_table_header) + return -ENOMEM; + return 0; } void nr_unregister_sysctl(void) diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 6a196e438b6c..d1fc019e932e 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -419,6 +419,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) sock->service_name, sock->service_name_len, &service_name_tlv_length); + if (!service_name_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += service_name_tlv_length; } @@ -429,9 +433,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); @@ -484,9 +496,17 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index ef4026a23e80..4fa015208aab 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -532,10 +532,10 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { - u8 *gb_cur, *version_tlv, version, version_length; - u8 *lto_tlv, lto_length; - u8 *wks_tlv, wks_length; - u8 *miux_tlv, miux_length; + u8 *gb_cur, version, version_length; + u8 lto_length, wks_length, miux_length; + u8 *version_tlv = NULL, *lto_tlv = NULL, + *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; int ret = 0; @@ -543,17 +543,33 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) version = LLCP_VERSION_11; version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version, 1, &version_length); + if (!version_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += version_length; lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, <o_length); + if (!lto_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length); + if (!wks_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += wks_length; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_length); + if (!miux_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += miux_length; gb_len += ARRAY_SIZE(llcp_magic); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index ddfc52ac1f9b..c0d323b58e73 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -312,6 +312,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, create_info = (struct nci_hci_create_pipe_resp *)skb->data; dest_gate = create_info->dest_gate; new_pipe = create_info->pipe; + if (new_pipe >= NCI_HCI_MAX_PIPES) { + status = NCI_HCI_ANY_E_NOK; + goto exit; + } /* Save the new created pipe and bind with local gate, * the description for skb->data[3] is destination gate id @@ -336,6 +340,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, goto exit; } delete_info = (struct nci_hci_delete_pipe_noti *)skb->data; + if (delete_info->pipe >= NCI_HCI_MAX_PIPES) { + status = NCI_HCI_ANY_E_NOK; + goto exit; + } ndev->hci_dev->pipes[delete_info->pipe].gate = NCI_HCI_INVALID_GATE; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 865ecef68196..eab5e8eaddaa 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -500,7 +500,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, return -EINVAL; } - if (!nz || !is_all_zero(nla_data(nla), expected_len)) { + if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) { attrs |= 1 << type; a[type] = nla; } @@ -2306,14 +2306,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, struct sw_flow_actions *acts; int new_acts_size; - int req_size = NLA_ALIGN(attr_len); + size_t req_size = NLA_ALIGN(attr_len); int next_offset = offsetof(struct sw_flow_actions, actions) + (*sfa)->actions_len; if (req_size <= (ksize(*sfa) - next_offset)) goto out; - new_acts_size = ksize(*sfa) * 2; + new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0c6e031a38b6..e99b69846aeb 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2604,8 +2604,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); + unsigned char *addr = NULL; int tp_len, size_max; - unsigned char *addr; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; @@ -2616,7 +2616,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; - addr = NULL; } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2626,8 +2625,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) sll_addr))) goto out; proto = saddr->sll_protocol; - addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); + if (po->sk.sk_socket->type == SOCK_DGRAM) { + if (dev && msg->msg_namelen < dev->addr_len + + offsetof(struct sockaddr_ll, sll_addr)) + goto out_put; + addr = saddr->sll_addr; + } } err = -ENXIO; @@ -2799,7 +2803,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) struct sk_buff *skb; struct net_device *dev; __be16 proto; - unsigned char *addr; + unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; @@ -2816,7 +2820,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; - addr = NULL; } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2824,8 +2827,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; - addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); + if (sock->type == SOCK_DGRAM) { + if (dev && msg->msg_namelen < dev->addr_len + + offsetof(struct sockaddr_ll, sll_addr)) + goto out_unlock; + addr = saddr->sll_addr; + } } err = -ENXIO; @@ -2884,7 +2892,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); - if (len < reserve) + if (len < reserve + sizeof(struct ipv6hdr) && + dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } @@ -3009,8 +3018,8 @@ static int packet_release(struct socket *sock) synchronize_net(); + kfree(po->rollover); if (f) { - kfree(po->rollover); fanout_release_data(f); kfree(f); } @@ -3241,7 +3250,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, } mutex_lock(&net->packet.sklist_lock); - sk_add_node_rcu(sk, &net->packet.sklist); + sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); preempt_disable(); @@ -4190,7 +4199,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) struct pgv *pg_vec; int i; - pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL); + pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; @@ -4271,7 +4280,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; - if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) @@ -4570,14 +4579,29 @@ static void __exit packet_exit(void) static int __init packet_init(void) { - int rc = proto_register(&packet_proto, 0); + int rc; - if (rc != 0) + rc = proto_register(&packet_proto, 0); + if (rc) goto out; + rc = sock_register(&packet_family_ops); + if (rc) + goto out_proto; + rc = register_pernet_subsys(&packet_net_ops); + if (rc) + goto out_sock; + rc = register_netdevice_notifier(&packet_netdev_notifier); + if (rc) + goto out_pernet; + + return 0; - sock_register(&packet_family_ops); - register_pernet_subsys(&packet_net_ops); - register_netdevice_notifier(&packet_netdev_notifier); +out_pernet: + unregister_pernet_subsys(&packet_net_ops); +out_sock: + sock_unregister(PF_PACKET); +out_proto: + proto_unregister(&packet_proto); out: return rc; } diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9fc76b19cd3c..db3473540303 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code, ph->utid = 0; ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code, ph->utid = id; /* whatever */ ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, struct pnpipehdr *ph; struct sockaddr_pn dst; u8 data[4] = { - oph->data[0], /* PEP type */ + oph->pep_type, /* PEP type */ code, /* error code, at an unusual offset */ PAD, PAD, }; @@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, ph->utid = oph->utid; ph->message_id = PNS_PEP_CTRL_RESP; ph->pipe_handle = oph->pipe_handle; - ph->data[0] = oph->data[1]; /* CTRL id */ + ph->data0 = oph->data[0]; /* CTRL id */ pn_skb_get_src_sockaddr(oskb, &dst); return pn_skb_send(sk, skb, &dst); @@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) return -EINVAL; hdr = pnp_hdr(skb); - if (hdr->data[0] != PN_PEP_TYPE_COMMON) { + if (hdr->pep_type != PN_PEP_TYPE_COMMON) { net_dbg_ratelimited("Phonet unknown PEP type: %u\n", - (unsigned int)hdr->data[0]); + (unsigned int)hdr->pep_type); return -EOPNOTSUPP; } - switch (hdr->data[1]) { + switch (hdr->data[0]) { case PN_PEP_IND_FLOW_CONTROL: switch (pn->tx_fc) { case PN_LEGACY_FLOW_CONTROL: - switch (hdr->data[4]) { + switch (hdr->data[3]) { case PEP_IND_BUSY: atomic_set(&pn->tx_credits, 0); break; @@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) } break; case PN_ONE_CREDIT_FLOW_CONTROL: - if (hdr->data[4] == PEP_IND_READY) + if (hdr->data[3] == PEP_IND_READY) atomic_set(&pn->tx_credits, wake = 1); break; } @@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) case PN_PEP_IND_ID_MCFC_GRANT_CREDITS: if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL) break; - atomic_add(wake = hdr->data[4], &pn->tx_credits); + atomic_add(wake = hdr->data[3], &pn->tx_credits); break; default: net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", - (unsigned int)hdr->data[1]); + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } if (wake) @@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); - u8 n_sb = hdr->data[0]; + u8 n_sb = hdr->data0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; __skb_pull(skb, sizeof(*hdr)); @@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) return -ECONNREFUSED; /* Parse sub-blocks */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[6], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk) ph->utid = 0; ph->message_id = PNS_PIPE_REMOVE_REQ; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = PAD; + ph->data0 = PAD; return pn_skb_send(sk, skb, NULL); } @@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, peer_type = hdr->other_pep_type << 8; /* Parse sub-blocks (options) */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[1], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) ph->utid = 0; if (pn->aligned) { ph->message_id = PNS_PIPE_ALIGNED_DATA; - ph->data[0] = 0; /* padding */ + ph->data0 = 0; /* padding */ } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 65387e1e6964..cd7e01ea8144 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -506,6 +506,9 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, struct rds_sock *rs = rds_sk_to_rs(sk); int ret = 0; + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + lock_sock(sk); switch (uaddr->sa_family) { diff --git a/net/rds/bind.c b/net/rds/bind.c index 762d2c6788a3..0f4398e7f2a7 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); - if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) - rds_sock_addref(rs); - else + if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || + !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, @@ -173,6 +173,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index e0f70c4051b6..01e764f8f224 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) else pool = rds_ibdev->mr_1m_pool; + if (atomic_read(&pool->dirty_count) >= pool->max_items / 10) + queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); + + /* Switch pools if one of the pool is reaching upper limit */ + if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) { + if (pool->pool_type == RDS_IB_MR_8K_POOL) + pool = rds_ibdev->mr_1m_pool; + else + pool = rds_ibdev->mr_8k_pool; + } + ibmr = rds_ib_try_reuse_ibmr(pool); if (ibmr) return ibmr; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 671f8ad38864..f395f06031bc 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -429,12 +429,14 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, wait_clean_list_grace(); list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail); - if (ibmr_ret) + if (ibmr_ret) { *ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode); - + clean_nodes = clean_nodes->next; + } /* more than one entry in llist nodes */ - if (clean_nodes->next) - llist_add_batch(clean_nodes->next, clean_tail, &pool->clean_list); + if (clean_nodes) + llist_add_batch(clean_nodes, clean_tail, + &pool->clean_list); } @@ -455,9 +457,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) struct rds_ib_mr *ibmr = NULL; int iter = 0; - if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10) - queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); - while (1) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 98237feb607a..e1965d9cbcf8 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -517,9 +517,10 @@ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) return tot_pages; } -int rds_rdma_extra_size(struct rds_rdma_args *args) +int rds_rdma_extra_size(struct rds_rdma_args *args, + struct rds_iov_vector *iov) { - struct rds_iovec vec; + struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; @@ -530,13 +531,23 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) if (args->nr_local == 0) return -EINVAL; + iov->iov = kcalloc(args->nr_local, + sizeof(struct rds_iovec), + GFP_KERNEL); + if (!iov->iov) + return -ENOMEM; + + vec = &iov->iov[0]; + + if (copy_from_user(vec, local_vec, args->nr_local * + sizeof(struct rds_iovec))) + return -EFAULT; + iov->len = args->nr_local; + /* figure out the number of pages in the vector */ - for (i = 0; i < args->nr_local; i++) { - if (copy_from_user(&vec, &local_vec[i], - sizeof(struct rds_iovec))) - return -EFAULT; + for (i = 0; i < args->nr_local; i++, vec++) { - nr_pages = rds_pages_in_vec(&vec); + nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; @@ -558,15 +569,15 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg) + struct cmsghdr *cmsg, + struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; - struct rds_iovec iovstack[UIO_FASTIOV], *iovs = iovstack; - int iov_size; + struct rds_iovec *iovs; unsigned int i, j; int ret = 0; @@ -586,31 +597,23 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_ret; } - /* Check whether to allocate the iovec area */ - iov_size = args->nr_local * sizeof(struct rds_iovec); - if (args->nr_local > UIO_FASTIOV) { - iovs = sock_kmalloc(rds_rs_to_sk(rs), iov_size, GFP_KERNEL); - if (!iovs) { - ret = -ENOMEM; - goto out_ret; - } + if (vec->len != args->nr_local) { + ret = -EINVAL; + goto out_ret; } - if (copy_from_user(iovs, (struct rds_iovec __user *)(unsigned long) args->local_vec_addr, iov_size)) { - ret = -EFAULT; - goto out; - } + iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; - goto out; + goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; - goto out; + goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); @@ -623,7 +626,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_sg = rds_message_alloc_sgs(rm, nr_pages); if (!op->op_sg) { ret = -ENOMEM; - goto out; + goto out_pages; } if (op->op_notify || op->op_recverr) { @@ -635,7 +638,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; - goto out; + goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; @@ -681,7 +684,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if (ret < 0) - goto out; + goto out_pages; else ret = 0; @@ -714,13 +717,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; - goto out; + goto out_pages; } op->op_bytes = nr_bytes; -out: - if (iovs != iovstack) - sock_kfree_s(rds_rs_to_sk(rs), iovs, iov_size); +out_pages: kfree(pages); out_ret: if (ret) diff --git a/net/rds/rds.h b/net/rds/rds.h index c4dcf654d8fe..4234ab81b5af 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -386,6 +386,18 @@ static inline void rds_message_zcopy_queue_init(struct rds_msg_zcopy_queue *q) INIT_LIST_HEAD(&q->zcookie_head); } +struct rds_iov_vector { + struct rds_iovec *iov; + int len; +}; + +struct rds_iov_vector_arr { + struct rds_iov_vector *vec; + int len; + int indx; + int incr; +}; + struct rds_message { refcount_t m_refcount; struct list_head m_sock_item; @@ -904,13 +916,13 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen); int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen); int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen); void rds_rdma_drop_keys(struct rds_sock *rs); -int rds_rdma_extra_size(struct rds_rdma_args *args); -int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg); +int rds_rdma_extra_size(struct rds_rdma_args *args, + struct rds_iov_vector *iov); int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg); + struct cmsghdr *cmsg, + struct rds_iov_vector *vec); int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); void rds_rdma_free_op(struct rm_rdma_op *ro); diff --git a/net/rds/send.c b/net/rds/send.c index fe785ee819dd..ec2267cbf85f 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -876,13 +876,15 @@ out: * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ -static int rds_rm_size(struct msghdr *msg, int num_sgs) +static int rds_rm_size(struct msghdr *msg, int num_sgs, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; bool zcopy_cookie = false; + struct rds_iov_vector *iov, *tmp_iov; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -893,8 +895,24 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs) switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: + if (vct->indx >= vct->len) { + vct->len += vct->incr; + tmp_iov = + krealloc(vct->vec, + vct->len * + sizeof(struct rds_iov_vector), + GFP_KERNEL); + if (!tmp_iov) { + vct->len -= vct->incr; + return -ENOMEM; + } + vct->vec = tmp_iov; + } + iov = &vct->vec[vct->indx]; + memset(iov, 0, sizeof(struct rds_iov_vector)); + vct->indx++; cmsg_groups |= 1; - retval = rds_rdma_extra_size(CMSG_DATA(cmsg)); + retval = rds_rdma_extra_size(CMSG_DATA(cmsg), iov); if (retval < 0) return retval; size += retval; @@ -951,10 +969,11 @@ static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, } static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, - struct msghdr *msg, int *allocated_mr) + struct msghdr *msg, int *allocated_mr, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; - int ret = 0; + int ret = 0, ind = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -968,7 +987,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, */ switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: - ret = rds_cmsg_rdma_args(rs, rm, cmsg); + if (ind >= vct->indx) + return -ENOMEM; + ret = rds_cmsg_rdma_args(rs, rm, cmsg, &vct->vec[ind]); + ind++; break; case RDS_CMSG_RDMA_DEST: @@ -1084,6 +1106,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = ceil(payload_len, PAGE_SIZE); int namelen; + struct rds_iov_vector_arr vct = {0}; + int ind; + + /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ + vct.incr = 1; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ @@ -1220,7 +1247,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); } /* size of rm including all sgs */ - ret = rds_rm_size(msg, num_sgs); + ret = rds_rm_size(msg, num_sgs, &vct); if (ret < 0) goto out; @@ -1270,7 +1297,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rm->m_conn_path = cpath; /* Parse any control messages the user may have included. */ - ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); + ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); if (ret) { /* Trigger connection so that its ready for the next retry */ if (ret == -EAGAIN) @@ -1348,9 +1375,18 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret) goto out; rds_message_put(rm); + + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + return payload_len; out: + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + /* If the user included a RDMA_MAP cmsg, we allocated a MR on the fly. * If the sendmsg goes through, we keep the MR. If it fails with EAGAIN * or in any other way, we need to destroy the MR again */ diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b9bbcf3d6c63..18bb522df282 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -600,7 +600,7 @@ static void rds_tcp_kill_sock(struct net *net) list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net); - if (net != c_net || !tc->t_sock) + if (net != c_net) continue; if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) { list_move_tail(&tc->t_tcp_node, &tmp_list); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7af4f99c4a93..094a6621f8e8 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -16,6 +16,7 @@ #include <linux/init.h> static struct sk_buff_head loopback_queue; +#define ROSE_LOOPBACK_LIMIT 1000 static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); @@ -35,29 +36,27 @@ static int rose_loopback_running(void) int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) { - struct sk_buff *skbn; + struct sk_buff *skbn = NULL; - skbn = skb_clone(skb, GFP_ATOMIC); + if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT) + skbn = skb_clone(skb, GFP_ATOMIC); - kfree_skb(skb); - - if (skbn != NULL) { + if (skbn) { + consume_skb(skb); skb_queue_tail(&loopback_queue, skbn); if (!rose_loopback_running()) rose_set_loopback_timer(); + } else { + kfree_skb(skb); } return 1; } - static void rose_set_loopback_timer(void) { - del_timer(&loopback_timer); - - loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); + mod_timer(&loopback_timer, jiffies + 10); } static void rose_loopback_timer(struct timer_list *unused) @@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused) struct sock *sk; unsigned short frametype; unsigned int lci_i, lci_o; + int count; - while ((skb = skb_dequeue(&loopback_queue)) != NULL) { + for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) { + skb = skb_dequeue(&loopback_queue); + if (!skb) + return; if (skb->len < ROSE_MIN_LEN) { kfree_skb(skb); continue; @@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused) kfree_skb(skb); } } + if (!skb_queue_empty(&loopback_queue)) + mod_timer(&loopback_timer, jiffies + 1); } void __exit rose_loopback_clear(void) diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 77e9f85a2c92..f2ff21d7df08 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev) /* * Route a frame to an appropriate AX.25 connection. + * A NULL ax25_cb indicates an internally generated frame. */ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) { @@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (skb->len < ROSE_MIN_LEN) return res; + + if (!ax25) + return rose_loopback_queue(skb, NULL); + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); if (frametype == ROSE_CALL_REQUEST && diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c index 7ca57741b2fb..7849f286bb93 100644 --- a/net/rose/rose_subr.c +++ b/net/rose/rose_subr.c @@ -105,16 +105,17 @@ void rose_write_internal(struct sock *sk, int frametype) struct sk_buff *skb; unsigned char *dptr; unsigned char lci1, lci2; - char buffer[100]; - int len, faclen = 0; + int maxfaclen = 0; + int len, faclen; + int reserve; - len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 1; + reserve = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1; + len = ROSE_MIN_LEN; switch (frametype) { case ROSE_CALL_REQUEST: len += 1 + ROSE_ADDR_LEN + ROSE_ADDR_LEN; - faclen = rose_create_facilities(buffer, rose); - len += faclen; + maxfaclen = 256; break; case ROSE_CALL_ACCEPTED: case ROSE_CLEAR_REQUEST: @@ -123,15 +124,16 @@ void rose_write_internal(struct sock *sk, int frametype) break; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(reserve + len + maxfaclen, GFP_ATOMIC); + if (!skb) return; /* * Space for AX.25 header and PID. */ - skb_reserve(skb, AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1); + skb_reserve(skb, reserve); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); lci1 = (rose->lci >> 8) & 0x0F; lci2 = (rose->lci >> 0) & 0xFF; @@ -146,7 +148,8 @@ void rose_write_internal(struct sock *sk, int frametype) dptr += ROSE_ADDR_LEN; memcpy(dptr, &rose->source_addr, ROSE_ADDR_LEN); dptr += ROSE_ADDR_LEN; - memcpy(dptr, buffer, faclen); + faclen = rose_create_facilities(dptr, rose); + skb_put(skb, faclen); dptr += faclen; break; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8f1a8f85b1f9..215f4d98baa0 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -701,30 +701,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) _enter(""); - if (list_empty(&rxnet->calls)) - return; + if (!list_empty(&rxnet->calls)) { + write_lock(&rxnet->call_lock); - write_lock(&rxnet->call_lock); + while (!list_empty(&rxnet->calls)) { + call = list_entry(rxnet->calls.next, + struct rxrpc_call, link); + _debug("Zapping call %p", call); - while (!list_empty(&rxnet->calls)) { - call = list_entry(rxnet->calls.next, struct rxrpc_call, link); - _debug("Zapping call %p", call); + rxrpc_see_call(call); + list_del_init(&call->link); - rxrpc_see_call(call); - list_del_init(&call->link); + pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", + call, atomic_read(&call->usage), + rxrpc_call_states[call->state], + call->flags, call->events); - pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", - call, atomic_read(&call->usage), - rxrpc_call_states[call->state], - call->flags, call->events); + write_unlock(&rxnet->call_lock); + cond_resched(); + write_lock(&rxnet->call_lock); + } write_unlock(&rxnet->call_lock); - cond_resched(); - write_lock(&rxnet->call_lock); } - write_unlock(&rxnet->call_lock); - atomic_dec(&rxnet->nr_calls); wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls)); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 521189f4b666..c979a56faaef 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -353,7 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, * normally have to take channel_lock but we do this before anyone else * can see the connection. */ - list_add_tail(&call->chan_wait_link, &candidate->waiting_calls); + list_add(&call->chan_wait_link, &candidate->waiting_calls); if (cp->exclusive) { call->conn = candidate; @@ -432,7 +432,7 @@ found_extant_conn: call->conn = conn; call->security_ix = conn->security_ix; call->service_id = conn->service_id; - list_add(&call->chan_wait_link, &conn->waiting_calls); + list_add_tail(&call->chan_wait_link, &conn->waiting_calls); spin_unlock(&conn->channel_lock); _leave(" = 0 [extant %d]", conn->debug_id); return 0; @@ -707,6 +707,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, ret = rxrpc_wait_for_channel(call, gfp); if (ret < 0) { + trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); rxrpc_disconnect_client_call(call); goto out; } @@ -777,16 +778,22 @@ static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet) */ void rxrpc_disconnect_client_call(struct rxrpc_call *call) { - unsigned int channel = call->cid & RXRPC_CHANNELMASK; struct rxrpc_connection *conn = call->conn; - struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_channel *chan = NULL; struct rxrpc_net *rxnet = conn->params.local->rxnet; + unsigned int channel = -1; + u32 cid; + spin_lock(&conn->channel_lock); + + cid = call->cid; + if (cid) { + channel = cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; + } trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); call->conn = NULL; - spin_lock(&conn->channel_lock); - /* Calls that have never actually been assigned a channel can simply be * discarded. If the conn didn't get used either, it will follow * immediately unless someone else grabs it in the meantime. @@ -810,7 +817,10 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) goto out; } - ASSERTCMP(rcu_access_pointer(chan->call), ==, call); + if (rcu_access_pointer(chan->call) != call) { + spin_unlock(&conn->channel_lock); + BUG(); + } /* If a client call was exposed to the world, we save the result for * retransmission. diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 570b49d2da42..d591f54cb91f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1155,19 +1155,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * handle data received on the local endpoint * - may be called in interrupt context * - * The socket is locked by the caller and this prevents the socket from being - * shut down and the local endpoint from going away, thus sk_user_data will not - * be cleared until this function returns. + * [!] Note that as this is called from the encap_rcv hook, the socket is not + * held locked by the caller and nothing prevents sk_user_data on the UDP from + * being cleared in the middle of processing this function. * * Called with the RCU read lock held from the IP layer via UDP. */ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) { + struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk); struct rxrpc_connection *conn; struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; - struct rxrpc_local *local = udp_sk->sk_user_data; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; @@ -1175,6 +1175,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) _enter("%p", udp_sk); + if (unlikely(!local)) { + kfree_skb(skb); + return 0; + } if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 0906e51d3cfb..10317dbdab5f 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -304,7 +304,8 @@ nomem: ret = -ENOMEM; sock_error: mutex_unlock(&rxnet->local_mutex); - kfree(local); + if (local) + call_rcu(&local->rcu, rxrpc_local_rcu); _leave(" = %d", ret); return ERR_PTR(ret); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 816b19a78809..0374b0623c8b 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -596,6 +596,7 @@ error_requeue_call: } error_no_call: release_sock(&rx->sk); +error_trace: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; @@ -604,7 +605,7 @@ wait_interrupted: wait_error: finish_wait(sk_sleep(&rx->sk), &wait); call = NULL; - goto error_no_call; + goto error_trace; } /** diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e12f8ef7baa4..7c4a4b874248 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -744,7 +744,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { a = actions[i]; - nest = nla_nest_start(skb, a->order); + nest = nla_nest_start(skb, i + 1); if (nest == NULL) goto nla_put_failure; err = tcf_action_dump_1(skb, a, bind, ref); @@ -1257,7 +1257,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, ret = PTR_ERR(act); goto err; } - act->order = i; attr_size += tcf_action_fill_size(act); actions[i - 1] = act; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8525de811616..334f3a057671 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -199,8 +199,7 @@ err3: err2: kfree(tname); err1: - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 8bf66d0a6800..f767e78e38c9 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -159,6 +159,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } m = to_mirred(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&m->tcfm_list); + spin_lock_bh(&m->tcf_lock); m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 6b67aa13d2dd..c7f5d630d97c 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -43,8 +43,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate; struct tc_sample *parm; - u32 psample_group_num; struct tcf_sample *s; bool exists = false; int ret, err; @@ -80,6 +80,12 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return -EEXIST; } + rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + if (!rate) { + NL_SET_ERR_MSG(extack, "invalid sample rate"); + tcf_idr_release(*a, bind); + return -EINVAL; + } psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { @@ -91,7 +97,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, spin_lock_bh(&s->tcf_lock); s->tcf_action = parm->action; - s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + s->rate = rate; s->psample_group_num = psample_group_num; RCU_INIT_POINTER(s->psample_group, psample_group); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 73e44ce2a883..86d90fc5e97e 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -191,8 +191,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); + tcf_idr_release(*a, bind); return -ENOMEM; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 681f6f04e7da..72d9c432e8b4 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -197,6 +197,15 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; +static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) +{ + if (!p) + return; + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(&p->tcft_enc_metadata->dst); + kfree_rcu(p, rcu); +} + static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, @@ -360,8 +369,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, rcu_swap_protected(t->params, params_new, lockdep_is_held(&t->tcf_lock)); spin_unlock_bh(&t->tcf_lock); - if (params_new) - kfree_rcu(params_new, rcu); + tunnel_key_release_params(params_new); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -369,7 +377,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; release_tun_meta: - dst_release(&metadata->dst); + if (metadata) + dst_release(&metadata->dst); err_out: if (exists) @@ -385,12 +394,7 @@ static void tunnel_key_release(struct tc_action *a) struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); - if (params) { - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(¶ms->tcft_enc_metadata->dst); - - kfree_rcu(params, rcu); - } + tunnel_key_release_params(params); } static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 70f144ac5e1d..2167c6ca55e3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -960,7 +960,6 @@ static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type, int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { - __be16 protocol = tc_skb_protocol(skb); #ifdef CONFIG_NET_CLS_ACT const int max_reclassify_loop = 4; const struct tcf_proto *orig_tp = tp; @@ -970,6 +969,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { + __be16 protocol = tc_skb_protocol(skb); int err; if (tp->protocol != protocol && @@ -1002,7 +1002,6 @@ reset: } tp = first_tp; - protocol = tc_skb_protocol(skb); goto reclassify; #endif } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7fade7107f95..09b359784629 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1176,17 +1176,23 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *fold = *arg; struct cls_fl_filter *fnew; + struct fl_flow_mask *mask; struct nlattr **tb; - struct fl_flow_mask mask = {}; int err; if (!tca[TCA_OPTIONS]) return -EINVAL; - tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); - if (!tb) + mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL); + if (!mask) return -ENOBUFS; + tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); + if (!tb) { + err = -ENOBUFS; + goto errout_mask_alloc; + } + err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy, NULL); if (err < 0) @@ -1207,47 +1213,47 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - if (!handle) { - handle = 1; - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, - INT_MAX, GFP_KERNEL); - } else if (!fold) { - /* user specifies a handle and it doesn't exist */ - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, - handle, GFP_KERNEL); - } - if (err) - goto errout; - fnew->handle = handle; - if (tb[TCA_FLOWER_FLAGS]) { fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); if (!tc_flags_valid(fnew->flags)) { err = -EINVAL; - goto errout_idr; + goto errout; } } - err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr, + err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, tp->chain->tmplt_priv, extack); if (err) - goto errout_idr; + goto errout; + + err = fl_check_assign_mask(head, fnew, fold, mask); + if (err) + goto errout; - err = fl_check_assign_mask(head, fnew, fold, &mask); + if (!handle) { + handle = 1; + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + INT_MAX, GFP_KERNEL); + } else if (!fold) { + /* user specifies a handle and it doesn't exist */ + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + handle, GFP_KERNEL); + } if (err) - goto errout_idr; + goto errout_mask; + fnew->handle = handle; if (!tc_skip_sw(fnew->flags)) { if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) { err = -EEXIST; - goto errout_mask; + goto errout_idr; } err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, fnew->mask->filter_ht_params); if (err) - goto errout_mask; + goto errout_idr; } if (!tc_skip_hw(fnew->flags)) { @@ -1281,19 +1287,23 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } kfree(tb); + kfree(mask); return 0; -errout_mask: - fl_mask_put(head, fnew->mask, false); - errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); + +errout_mask: + fl_mask_put(head, fnew->mask, false); + errout: tcf_exts_destroy(&fnew->exts); kfree(fnew); errout_tb: kfree(tb); +errout_mask_alloc: + kfree(mask); return err; } diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 856fa79d4ffd..621bc1d5b057 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -126,6 +126,11 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) static void *mall_get(struct tcf_proto *tp, u32 handle) { + struct cls_mall_head *head = rtnl_dereference(tp->root); + + if (head && head->handle == handle) + return head; + return NULL; } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 9ccc93f257db..38bb882bb958 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -48,7 +48,7 @@ struct tcindex_data { u32 hash; /* hash table size; 0 if undefined */ u32 alloc_hash; /* allocated size */ u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_head rcu; + struct rcu_work rwork; }; static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) @@ -221,17 +221,11 @@ found: return 0; } -static int tcindex_destroy_element(struct tcf_proto *tp, - void *arg, struct tcf_walker *walker) -{ - bool last; - - return tcindex_delete(tp, arg, &last, NULL); -} - -static void __tcindex_destroy(struct rcu_head *head) +static void tcindex_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p->h); @@ -258,9 +252,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r) return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } -static void __tcindex_partial_destroy(struct rcu_head *head) +static void tcindex_partial_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p); @@ -275,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp) kfree(cp->perfect); } -static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) +static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) { int i, err = 0; @@ -289,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) goto errout; +#ifdef CONFIG_NET_CLS_ACT + cp->perfect[i].exts.net = net; +#endif } return 0; @@ -305,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_filter_result cr; struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ + struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; @@ -337,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (p->perfect) { int i; - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; for (i = 0; i < cp->hash; i++) cp->perfect[i].res = p->perfect[i].res; @@ -348,11 +347,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result); if (err < 0) goto errout1; - err = tcindex_filter_result_init(&cr); - if (err < 0) - goto errout1; if (old_r) - cr.res = r->res; + cr = r->res; if (tb[TCA_TCINDEX_HASH]) cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -406,7 +402,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp->perfect && !cp->h) { if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout_alloc; balloc = 1; } else { @@ -443,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (tb[TCA_TCINDEX_CLASSID]) { - cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr.res, base); + cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); + tcf_bind_filter(tp, &cr, base); } if (old_r && old_r != r) { @@ -456,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } oldp = p; - r->res = cr.res; + r->res = cr; tcf_exts_change(&r->exts, &e); rcu_assign_pointer(tp->root, cp); @@ -475,10 +471,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, ; /* nothing */ rcu_assign_pointer(*fp, f); + } else { + tcf_exts_destroy(&new_filter_result.exts); } if (oldp) - call_rcu(&oldp->rcu, __tcindex_partial_destroy); + tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); return 0; errout_alloc: @@ -487,7 +485,6 @@ errout_alloc: else if (balloc == 2) kfree(cp->h); errout1: - tcf_exts_destroy(&cr.exts); tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -562,15 +559,34 @@ static void tcindex_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcf_walker walker; + int i; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - walker.count = 0; - walker.skip = 0; - walker.fn = tcindex_destroy_element; - tcindex_walk(tp, &walker); - call_rcu(&p->rcu, __tcindex_destroy); + if (p->perfect) { + for (i = 0; i < p->hash; i++) { + struct tcindex_filter_result *r = p->perfect + i; + + tcf_unbind_filter(tp, &r->res); + if (tcf_exts_get_net(&r->exts)) + tcf_queue_work(&r->rwork, + tcindex_destroy_rexts_work); + else + __tcindex_destroy_rexts(r); + } + } + + for (i = 0; p->h && i < p->hash; i++) { + struct tcindex_filter *f, *next; + bool last; + + for (f = rtnl_dereference(p->h[i]); f; f = next) { + next = rtnl_dereference(f->next); + tcindex_delete(tp, &f->result, &last, NULL); + } + } + + tcf_queue_work(&p->rwork, tcindex_destroy_work); } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 793016d722ec..9fd37d91b5ed 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1508,32 +1508,29 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) return idx + (tin << 16); } -static void cake_wash_diffserv(struct sk_buff *skb) -{ - switch (skb->protocol) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); - break; - default: - break; - } -} - static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) { + int wlen = skb_network_offset(skb); u8 dscp; - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; if (wash && dscp) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); return dscp; case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; if (wash && dscp) ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); @@ -1553,25 +1550,27 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); u32 tin; + u8 dscp; + + /* Tin selection: Default to diffserv-based selection, allow overriding + * using firewall marks or skb->priority. + */ + dscp = cake_handle_diffserv(skb, + q->rate_flags & CAKE_FLAG_WASH); - if (TC_H_MAJ(skb->priority) == sch->handle && - TC_H_MIN(skb->priority) > 0 && - TC_H_MIN(skb->priority) <= q->tin_cnt) { + if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) + tin = 0; + + else if (TC_H_MAJ(skb->priority) == sch->handle && + TC_H_MIN(skb->priority) > 0 && + TC_H_MIN(skb->priority) <= q->tin_cnt) tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; - if (q->rate_flags & CAKE_FLAG_WASH) - cake_wash_diffserv(skb); - } else if (q->tin_mode != CAKE_DIFFSERV_BESTEFFORT) { - /* extract the Diffserv Precedence field, if it exists */ - /* and clear DSCP bits if washing */ - tin = q->tin_index[cake_handle_diffserv(skb, - q->rate_flags & CAKE_FLAG_WASH)]; + else { + tin = q->tin_index[dscp]; + if (unlikely(tin >= q->tin_cnt)) tin = 0; - } else { - tin = 0; - if (q->rate_flags & CAKE_FLAG_WASH) - cake_wash_diffserv(skb); } return &q->tins[tin]; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index cfa761f2d041..b0cc57ff96e3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) skb = __skb_dequeue(&q->skb_bad_txq); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); - qdisc_qstats_cpu_qlen_dec(q); + qdisc_qstats_atomic_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; @@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_inc(q, skb); - qdisc_qstats_cpu_qlen_inc(q); + qdisc_qstats_atomic_qlen_inc(q); } else { qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; @@ -147,7 +147,7 @@ static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q) qdisc_qstats_cpu_requeues_inc(q); qdisc_qstats_cpu_backlog_inc(q, skb); - qdisc_qstats_cpu_qlen_inc(q); + qdisc_qstats_atomic_qlen_inc(q); skb = next; } @@ -252,7 +252,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, skb = __skb_dequeue(&q->gso_skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); - qdisc_qstats_cpu_qlen_dec(q); + qdisc_qstats_atomic_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; @@ -637,7 +637,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, if (unlikely(err)) return qdisc_drop_cpu(skb, qdisc, to_free); - qdisc_qstats_cpu_qlen_inc(qdisc); + qdisc_qstats_atomic_qlen_inc(qdisc); /* Note: skb can not be used after skb_array_produce(), * so we better not use qdisc_qstats_cpu_backlog_inc() */ @@ -662,7 +662,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) if (likely(skb)) { qdisc_qstats_cpu_backlog_dec(qdisc, skb); qdisc_bstats_cpu_update(qdisc, skb); - qdisc_qstats_cpu_qlen_dec(qdisc); + qdisc_qstats_atomic_qlen_dec(qdisc); } return skb; @@ -706,7 +706,6 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); q->backlog = 0; - q->qlen = 0; } } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 74c0f656f28c..4dfe10b9f96c 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -440,6 +440,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, int nb = 0; int count = 1; int rc = NET_XMIT_SUCCESS; + int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -479,6 +480,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->duplicate = 0; rootq->enqueue(skb2, rootq, to_free); q->duplicate = dupsave; + rc_drop = NET_XMIT_SUCCESS; } /* @@ -491,7 +493,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { segs = netem_segment(skb, sch, to_free); if (!segs) - return NET_XMIT_DROP; + return rc_drop; } else { segs = skb; } @@ -514,8 +516,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<<(prandom_u32() % 8); } - if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop_all(skb, sch, to_free); + if (unlikely(sch->q.qlen >= sch->limit)) { + qdisc_drop_all(skb, sch, to_free); + return rc_drop; + } qdisc_qstats_backlog_inc(sch, skb); diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 078f01a8d582..435847d98b51 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index fc6c5e4bffa5..4fede55b9010 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -97,10 +97,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, switch (ev) { case NETDEV_UP: - addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; - addr->a.v6.sin6_port = 0; addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; @@ -278,7 +277,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (saddr) { fl6->saddr = saddr->v6.sin6_addr; - fl6->fl6_sport = saddr->v6.sin6_port; + if (!fl6->fl6_sport) + fl6->fl6_sport = saddr->v6.sin6_port; pr_debug("src=%pI6 - ", &fl6->saddr); } @@ -430,7 +430,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; - addr->a.v6.sin6_port = 0; addr->a.v6.sin6_addr = ifp->addr; addr->a.v6.sin6_scope_id = dev->ifindex; addr->valid = 1; diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 123e9f2dc226..edfcf16e704c 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; + gso_reset_checksum(skb, ~0); return sctp_compute_cksum(skb, skb_transport_offset(skb)); } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e948db29ab53..d97b2b4b7a8b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -101,7 +101,6 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; - addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; INIT_LIST_HEAD(&addr->list); @@ -441,7 +440,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } if (saddr) { fl4->saddr = saddr->v4.sin_addr.s_addr; - fl4->fl4_sport = saddr->v4.sin_port; + if (!fl4->fl4_sport) + fl4->fl4_sport = saddr->v4.sin_port; } pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr, @@ -600,6 +600,7 @@ out: static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); } @@ -776,10 +777,9 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, switch (ev) { case NETDEV_UP: - addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; - addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; spin_lock_bh(&net->sctp.local_addr_lock); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index f4ac6c592e13..ae65a1cfa596 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -495,7 +495,10 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, * * [INIT ACK back to where the INIT came from.] */ - retval->transport = chunk->transport; + if (chunk->transport) + retval->transport = + sctp_assoc_lookup_paddr(asoc, + &chunk->transport->ipaddr); retval->subh.init_hdr = sctp_addto_chunk(retval, sizeof(initack), &initack); @@ -642,8 +645,10 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, * * [COOKIE ACK back to where the COOKIE ECHO came from.] */ - if (retval && chunk) - retval->transport = chunk->transport; + if (retval && chunk && chunk->transport) + retval->transport = + sctp_assoc_lookup_paddr(asoc, + &chunk->transport->ipaddr); return retval; } @@ -2324,7 +2329,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, union sctp_addr addr; 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. @@ -2428,14 +2432,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* Peer Rwnd : Current calculated value of the peer's rwnd. */ asoc->peer.rwnd = asoc->peer.i.a_rwnd; - /* Copy cookie in case we need to resend COOKIE-ECHO. */ - cookie = asoc->peer.cookie; - if (cookie) { - asoc->peer.cookie = kmemdup(cookie, asoc->peer.cookie_len, gfp); - if (!asoc->peer.cookie) - goto clean_up; - } - /* RFC 2960 7.2.1 The initial value of ssthresh MAY be arbitrarily * high (for example, implementations MAY use the size of the receiver * advertised window). @@ -2604,7 +2600,9 @@ do_addr_param: case SCTP_PARAM_STATE_COOKIE: asoc->peer.cookie_len = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); - asoc->peer.cookie = param.cookie->body; + asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp); + if (!asoc->peer.cookie) + retval = 0; break; case SCTP_PARAM_HEARTBEAT_INFO: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 85d393090238..3131b4154c74 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -898,6 +898,11 @@ static void sctp_cmd_new_state(struct sctp_cmd_seq *cmds, asoc->rto_initial; } + if (sctp_state(asoc, ESTABLISHED)) { + kfree(asoc->peer.cookie); + asoc->peer.cookie = NULL; + } + if (sctp_state(asoc, ESTABLISHED) || sctp_state(asoc, CLOSED) || sctp_state(asoc, SHUTDOWN_RECEIVED)) { @@ -1112,32 +1117,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc, } -/* Sent the next ASCONF packet currently stored in the association. - * This happens after the ASCONF_ACK was succeffully processed. - */ -static void sctp_cmd_send_asconf(struct sctp_association *asoc) -{ - struct net *net = sock_net(asoc->base.sk); - - /* Send the next asconf chunk from the addip chunk - * queue. - */ - if (!list_empty(&asoc->addip_chunk_list)) { - struct list_head *entry = asoc->addip_chunk_list.next; - struct sctp_chunk *asconf = list_entry(entry, - struct sctp_chunk, list); - list_del_init(entry); - - /* Hold the chunk until an ASCONF_ACK is received. */ - sctp_chunk_hold(asconf); - if (sctp_primitive_ASCONF(net, asoc, asconf)) - sctp_chunk_free(asconf); - else - asoc->addip_last_asconf = asconf; - } -} - - /* These three macros allow us to pull the debugging code out of the * main flow of sctp_do_sm() to keep attention focused on the real * functionality there. @@ -1783,9 +1762,6 @@ static int sctp_cmd_interpreter(enum sctp_event event_type, } sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp); break; - case SCTP_CMD_SEND_NEXT_ASCONF: - sctp_cmd_send_asconf(asoc); - break; case SCTP_CMD_PURGE_ASCONF_QUEUE: sctp_asconf_queue_teardown(asoc); break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index c9ae3404b1bb..713a669d2058 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, return SCTP_DISPOSITION_CONSUME; } +static enum sctp_disposition sctp_send_next_asconf( + struct net *net, + const struct sctp_endpoint *ep, + struct sctp_association *asoc, + const union sctp_subtype type, + struct sctp_cmd_seq *commands) +{ + struct sctp_chunk *asconf; + struct list_head *entry; + + if (list_empty(&asoc->addip_chunk_list)) + return SCTP_DISPOSITION_CONSUME; + + entry = asoc->addip_chunk_list.next; + asconf = list_entry(entry, struct sctp_chunk, list); + + list_del_init(entry); + sctp_chunk_hold(asconf); + asoc->addip_last_asconf = asconf; + + return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands); +} + /* * ADDIP Section 4.3 General rules for address manipulation * When building TLV parameters for the ASCONF Chunk that will add or @@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); if (!sctp_process_asconf_ack((struct sctp_association *)asoc, - asconf_ack)) { - /* Successfully processed ASCONF_ACK. We can - * release the next asconf if we have one. - */ - sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF, - SCTP_NULL()); - return SCTP_DISPOSITION_CONSUME; - } + asconf_ack)) + return sctp_send_next_asconf(net, ep, + (struct sctp_association *)asoc, + type, commands); abort = sctp_make_abort(asoc, asconf_ack, sizeof(struct sctp_errhdr)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 876393cf5ed6..8c00a7ef1bcd 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1017,7 +1017,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, if (unlikely(addrs_size <= 0)) return -EINVAL; - kaddrs = vmemdup_user(addrs, addrs_size); + kaddrs = memdup_user(addrs, addrs_size); if (unlikely(IS_ERR(kaddrs))) return PTR_ERR(kaddrs); @@ -1025,7 +1025,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, addr_buf = kaddrs; while (walk_size < addrs_size) { if (walk_size + sizeof(sa_family_t) > addrs_size) { - kvfree(kaddrs); + kfree(kaddrs); return -EINVAL; } @@ -1036,7 +1036,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, * causes the address buffer to overflow return EINVAL. */ if (!af || (walk_size + af->sockaddr_len) > addrs_size) { - kvfree(kaddrs); + kfree(kaddrs); return -EINVAL; } addrcnt++; @@ -1072,7 +1072,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, } out: - kvfree(kaddrs); + kfree(kaddrs); return err; } @@ -1347,7 +1347,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, if (unlikely(addrs_size <= 0)) return -EINVAL; - kaddrs = vmemdup_user(addrs, addrs_size); + kaddrs = memdup_user(addrs, addrs_size); if (unlikely(IS_ERR(kaddrs))) return PTR_ERR(kaddrs); @@ -1367,7 +1367,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id); out_free: - kvfree(kaddrs); + kfree(kaddrs); return err; } @@ -1884,6 +1884,7 @@ static int sctp_sendmsg_check_sflags(struct sctp_association *asoc, pr_debug("%s: aborting association:%p\n", __func__, asoc); sctp_primitive_ABORT(net, asoc, chunk); + iov_iter_revert(&msg->msg_iter, msg_len); return 0; } @@ -2045,7 +2046,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; - struct sctp_association *asoc; + struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; @@ -2071,7 +2072,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { - list_for_each_entry(asoc, &ep->asocs, asocs) { + list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 3892e7630f3a..3b47457862cc 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count) } } +static size_t fa_index(struct flex_array *fa, void *elem, size_t count) +{ + size_t index = 0; + + while (count--) { + if (elem == flex_array_get(fa, index)) + break; + index++; + } + + return index; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -131,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, } } - for (i = outcnt; i < stream->outcnt; i++) + for (i = outcnt; i < stream->outcnt; i++) { kfree(SCTP_SO(stream, i)->ext); + SCTP_SO(stream, i)->ext = NULL; + } } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, @@ -147,6 +162,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, if (stream->out) { fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + if (stream->out_curr) { + size_t index = fa_index(stream->out, stream->out_curr, + stream->outcnt); + + BUG_ON(index == stream->outcnt); + stream->out_curr = flex_array_get(out, index); + } fa_free(stream->out); } @@ -208,8 +230,6 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - sched->init(stream); - in: sctp_stream_interleave_init(stream); if (!incnt) @@ -585,9 +605,9 @@ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_strreset_outreq *outreq = param.v; struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; - __u16 i, nums, flags = 0; __be16 *str_p = NULL; __u32 request_seq; + __u16 i, nums; request_seq = ntohl(outreq->request_seq); @@ -615,6 +635,15 @@ struct sctp_chunk *sctp_process_strreset_outreq( if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ)) goto out; + nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16); + str_p = outreq->list_of_streams; + for (i = 0; i < nums; i++) { + if (ntohs(str_p[i]) >= stream->incnt) { + result = SCTP_STRRESET_ERR_WRONG_SSN; + goto out; + } + } + if (asoc->strreset_chunk) { if (!sctp_chunk_lookup_strreset_param( asoc, outreq->response_seq, @@ -637,32 +666,19 @@ struct sctp_chunk *sctp_process_strreset_outreq( sctp_chunk_put(asoc->strreset_chunk); asoc->strreset_chunk = NULL; } - - flags = SCTP_STREAM_RESET_INCOMING_SSN; } - nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16); - if (nums) { - str_p = outreq->list_of_streams; - for (i = 0; i < nums; i++) { - if (ntohs(str_p[i]) >= stream->incnt) { - result = SCTP_STRRESET_ERR_WRONG_SSN; - goto out; - } - } - + if (nums) for (i = 0; i < nums; i++) SCTP_SI(stream, ntohs(str_p[i]))->mid = 0; - } else { + else for (i = 0; i < stream->incnt; i++) SCTP_SI(stream, i)->mid = 0; - } result = SCTP_STRRESET_PERFORMED; *evp = sctp_ulpevent_make_stream_reset_event(asoc, - flags | SCTP_STREAM_RESET_OUTGOING_SSN, nums, str_p, - GFP_ATOMIC); + SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC); out: sctp_update_strreset_result(asoc, result); @@ -738,9 +754,6 @@ struct sctp_chunk *sctp_process_strreset_inreq( result = SCTP_STRRESET_PERFORMED; - *evp = sctp_ulpevent_make_stream_reset_event(asoc, - SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC); - out: sctp_update_strreset_result(asoc, result); err: @@ -873,6 +886,14 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) goto out; + in = ntohs(addstrm->number_of_streams); + incnt = stream->incnt + in; + if (!in || incnt > SCTP_MAX_STREAM) + goto out; + + if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC)) + goto out; + if (asoc->strreset_chunk) { if (!sctp_chunk_lookup_strreset_param( asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { @@ -896,14 +917,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( } } - in = ntohs(addstrm->number_of_streams); - incnt = stream->incnt + in; - if (!in || incnt > SCTP_MAX_STREAM) - goto out; - - if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC)) - goto out; - stream->incnt = incnt; result = SCTP_STRRESET_PERFORMED; @@ -973,9 +986,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( result = SCTP_STRRESET_PERFORMED; - *evp = sctp_ulpevent_make_stream_change_event(asoc, - 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC); - out: sctp_update_strreset_result(asoc, result); err: @@ -1036,10 +1046,10 @@ struct sctp_chunk *sctp_process_strreset_resp( sout->mid_uo = 0; } } - - flags = SCTP_STREAM_RESET_OUTGOING_SSN; } + flags |= SCTP_STREAM_RESET_OUTGOING_SSN; + for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; @@ -1058,6 +1068,8 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / sizeof(__u16); + flags |= SCTP_STREAM_RESET_INCOMING_SSN; + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, nums, str_p, GFP_ATOMIC); } else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 80e2119f1c70..e6e506b2db99 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -144,9 +144,18 @@ static int smc_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } + + sk->sk_prot->unhash(sk); + if (smc->clcsock) { + if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + /* wake up clcsock accept */ + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + } + mutex_lock(&smc->clcsock_release_lock); sock_release(smc->clcsock); smc->clcsock = NULL; + mutex_unlock(&smc->clcsock_release_lock); } if (smc->use_fallback) { if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) @@ -162,7 +171,6 @@ static int smc_release(struct socket *sock) smc_conn_free(&smc->conn); release_sock(sk); - sk->sk_prot->unhash(sk); sock_put(sk); /* final sock_put */ out: return rc; @@ -203,6 +211,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, spin_lock_init(&smc->conn.send_lock); sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); + mutex_init(&smc->clcsock_release_lock); return sk; } @@ -818,7 +827,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) struct socket *new_clcsock = NULL; struct sock *lsk = &lsmc->sk; struct sock *new_sk; - int rc; + int rc = -EINVAL; release_sock(lsk); new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol); @@ -831,7 +840,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) } *new_smc = smc_sk(new_sk); - rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_lock(&lsmc->clcsock_release_lock); + if (lsmc->clcsock) + rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); if (rc < 0) lsk->sk_err = -rc; diff --git a/net/smc/smc.h b/net/smc/smc.h index 08786ace6010..adbdf195eb08 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -113,9 +113,9 @@ struct smc_host_cdc_msg { /* Connection Data Control message */ } __aligned(8); enum smc_urg_state { - SMC_URG_VALID, /* data present */ - SMC_URG_NOTYET, /* data pending */ - SMC_URG_READ /* data was already read */ + SMC_URG_VALID = 1, /* data present */ + SMC_URG_NOTYET = 2, /* data pending */ + SMC_URG_READ = 3, /* data was already read */ }; struct smc_connection { @@ -219,6 +219,10 @@ struct smc_sock { /* smc sock container */ * started, waiting for unsent * data to be sent */ + struct mutex clcsock_release_lock; + /* protects clcsock of a listen + * socket + * */ }; static inline struct smc_sock *smc_sk(const struct sock *sk) diff --git a/net/socket.c b/net/socket.c index 390a8ecef4bf..18d27b8c2511 100644 --- a/net/socket.c +++ b/net/socket.c @@ -577,6 +577,7 @@ static void __sock_release(struct socket *sock, struct inode *inode) if (inode) inode_lock(inode); sock->ops->release(sock); + sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; @@ -941,8 +942,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg, - unsigned int ifreq_size) + unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; @@ -968,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, ifreq_size)) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, ifreq_size)) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } return err; @@ -1071,8 +1071,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct ifreq)); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -2752,8 +2751,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2769,8 +2767,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -2966,6 +2963,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, &ifreq, NULL); } +static int compat_ifreq_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + /* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCGIFNAME: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { @@ -3081,8 +3126,7 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, - sizeof(struct compat_ifreq)); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: @@ -3182,21 +3226,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - case SIOCSARP: - case SIOCGARP: - case SIOCDARP: - case SIOCATMARK: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct compat_ifreq)); + return compat_ifreq_ioctl(net, sock, cmd, argp); + + case SIOCSARP: + case SIOCGARP: + case SIOCDARP: + case SIOCATMARK: + return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index da1a676860ca..0f4e42792878 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -140,13 +140,11 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* We are going to append to the frags_list of head. * Need to unshare the frag_list. */ - if (skb_has_frag_list(head)) { - err = skb_unclone(head, GFP_ATOMIC); - if (err) { - STRP_STATS_INCR(strp->stats.mem_fail); - desc->error = err; - return 0; - } + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.mem_fail); + desc->error = err; + return 0; } if (unlikely(skb_shinfo(head)->frag_list)) { diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index c8b9082f4a9d..2d2ed6772fe4 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -44,7 +44,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, unsigned char *cksum, unsigned char *buf) { struct crypto_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -53,6 +53,10 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, if (IS_ERR(cipher)) return PTR_ERR(cipher); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) ((seqnum >> 24) & 0xff); plain[1] = (unsigned char) ((seqnum >> 16) & 0xff); plain[2] = (unsigned char) ((seqnum >> 8) & 0xff); @@ -69,6 +73,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, code = krb5_encrypt(cipher, cksum, plain, buf, 8); out: crypto_free_skcipher(cipher); + kfree(plain); return code; } s32 @@ -78,12 +83,17 @@ krb5_make_seq_num(struct krb5_ctx *kctx, u32 seqnum, unsigned char *cksum, unsigned char *buf) { - unsigned char plain[8]; + unsigned char *plain; + s32 code; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_make_rc4_seq_num(kctx, direction, seqnum, cksum, buf); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) (seqnum & 0xff); plain[1] = (unsigned char) ((seqnum >> 8) & 0xff); plain[2] = (unsigned char) ((seqnum >> 16) & 0xff); @@ -94,7 +104,9 @@ krb5_make_seq_num(struct krb5_ctx *kctx, plain[6] = direction; plain[7] = direction; - return krb5_encrypt(key, cksum, plain, buf, 8); + code = krb5_encrypt(key, cksum, plain, buf, 8); + kfree(plain); + return code; } static s32 @@ -102,7 +114,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, unsigned char *buf, int *direction, s32 *seqnum) { struct crypto_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -115,20 +127,28 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, if (code) goto out; + plain = kmalloc(8, GFP_NOFS); + if (!plain) { + code = -ENOMEM; + goto out; + } + code = krb5_decrypt(cipher, cksum, buf, plain, 8); if (code) - goto out; + goto out_plain; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || (plain[4] != plain[7])) { code = (s32)KG_BAD_SEQ; - goto out; + goto out_plain; } *direction = plain[4]; *seqnum = ((plain[0] << 24) | (plain[1] << 16) | (plain[2] << 8) | (plain[3])); +out_plain: + kfree(plain); out: crypto_free_skcipher(cipher); return code; @@ -141,26 +161,33 @@ krb5_get_seq_num(struct krb5_ctx *kctx, int *direction, u32 *seqnum) { s32 code; - unsigned char plain[8]; struct crypto_skcipher *key = kctx->seq; + unsigned char *plain; dprintk("RPC: krb5_get_seq_num:\n"); if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_get_rc4_seq_num(kctx, cksum, buf, direction, seqnum); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; if ((code = krb5_decrypt(key, cksum, buf, plain, 8))) - return code; + goto out; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || - (plain[4] != plain[7])) - return (s32)KG_BAD_SEQ; + (plain[4] != plain[7])) { + code = (s32)KG_BAD_SEQ; + goto out; + } *direction = plain[4]; *seqnum = ((plain[0]) | (plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24)); - return 0; +out: + kfree(plain); + return code; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 860f2a1bbb67..1a65f88d021a 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1122,7 +1122,7 @@ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, struct kvec *resv = &rqstp->rq_res.head[0]; struct rsi *rsip, rsikey; int ret; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); memset(&rsikey, 0, sizeof(rsikey)); ret = gss_read_verf(gc, argv, authp, @@ -1233,7 +1233,7 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, uint64_t handle; int status; int ret; - struct net *net = rqstp->rq_xprt->xpt_net; + struct net *net = SVC_NET(rqstp); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); memset(&ud, 0, sizeof(ud)); @@ -1424,7 +1424,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) __be32 *rpcstart; __be32 *reject_stat = resv->iov_base + resv->iov_len; int ret; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); dprintk("RPC: svcauth_gss: argv->iov_len = %zd\n", argv->iov_len); @@ -1714,7 +1714,7 @@ svcauth_gss_release(struct svc_rqst *rqstp) struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *resbuf = &rqstp->rq_res; int stat = -EINVAL; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 109fbe591e7b..214440c5b14e 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -54,6 +54,12 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } +static inline int cache_is_valid(struct cache_head *h); +static void cache_fresh_locked(struct cache_head *head, time_t expiry, + struct cache_detail *detail); +static void cache_fresh_unlocked(struct cache_head *head, + struct cache_detail *detail); + struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash) { @@ -95,6 +101,9 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init(&tmp->cache_list); detail->entries --; + if (cache_is_valid(tmp) == -EAGAIN) + set_bit(CACHE_NEGATIVE, &tmp->flags); + cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; } @@ -110,8 +119,10 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, cache_get(new); write_unlock(&detail->hash_lock); - if (freeme) + if (freeme) { + cache_fresh_unlocked(freeme, detail); cache_put(freeme, detail); + } return new; } EXPORT_SYMBOL_GPL(sunrpc_cache_lookup); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8ea2f5fadd96..1fc812ba9871 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1992,13 +1992,15 @@ call_transmit(struct rpc_task *task) static void call_transmit_status(struct rpc_task *task) { + struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; task->tk_action = call_status; /* * Common case: success. Force the compiler to put this - * test first. + * test first. Or, if any error and xprt_close_wait, + * release the xprt lock so the socket can close. */ - if (task->tk_status == 0) { + if (task->tk_status == 0 || xprt_close_wait(xprt)) { xprt_end_transmit(task); rpc_task_force_reencode(task); return; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c7872bc13860..08b5fa4a2852 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -771,6 +771,12 @@ void rpcb_getport_async(struct rpc_task *task) case RPCBVERS_3: map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID]; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_ATOMIC); + if (!map->r_addr) { + status = -ENOMEM; + dprintk("RPC: %5u %s: no memory available\n", + task->tk_pid, __func__); + goto bailout_free_args; + } map->r_owner = ""; break; case RPCBVERS_2: @@ -793,6 +799,8 @@ void rpcb_getport_async(struct rpc_task *task) rpc_put_task(child); return; +bailout_free_args: + kfree(map); bailout_release_client: rpc_release_client(rpcb_clnt); bailout_nofree: diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d13e05f1a990..d65f8d35de87 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1144,6 +1144,8 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif +extern void svc_tcp_prep_reply_hdr(struct svc_rqst *); + /* * Common routine for processing the RPC request. */ @@ -1172,7 +1174,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) clear_bit(RQ_DROPME, &rqstp->rq_flags); /* Setup reply header */ - rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); + if (rqstp->rq_prot == IPPROTO_TCP) + svc_tcp_prep_reply_hdr(rqstp); svc_putu32(resv, rqstp->rq_xid); @@ -1244,7 +1247,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) * for lower versions. RPC_PROG_MISMATCH seems to be the closest * fit. */ - if (versp->vs_need_cong_ctrl && + if (versp->vs_need_cong_ctrl && rqstp->rq_xprt && !test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags)) goto err_bad_vers; @@ -1336,7 +1339,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) return 0; close: - if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) + if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_close_xprt(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); return 0; @@ -1459,10 +1462,10 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, dprintk("svc: %s(%p)\n", __func__, req); /* Build the svc_rqst used by the common processing routine */ - rqstp->rq_xprt = serv->sv_bc_xprt; rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_server = serv; + rqstp->rq_bc_net = req->rq_xprt->xprt_net; rqstp->rq_addrlen = sizeof(req->rq_xprt->addr); memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b7b9cf3b375a..48c0a0b90946 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -469,10 +469,11 @@ out: */ void svc_reserve(struct svc_rqst *rqstp, int space) { + struct svc_xprt *xprt = rqstp->rq_xprt; + space += rqstp->rq_res.head[0].iov_len; - if (space < rqstp->rq_reserved) { - struct svc_xprt *xprt = rqstp->rq_xprt; + if (xprt && space < rqstp->rq_reserved) { atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved); rqstp->rq_reserved = space; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5445145e639c..8566531c2f10 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -381,12 +381,16 @@ static int svc_partial_recvfrom(struct svc_rqst *rqstp, /* * Set socket snd and rcv buffer lengths */ -static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, - unsigned int rcv) +static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs) { + unsigned int max_mesg = svsk->sk_xprt.xpt_server->sv_max_mesg; + struct socket *sock = svsk->sk_sock; + + nreqs = min(nreqs, INT_MAX / 2 / max_mesg); + lock_sock(sock->sk); - sock->sk->sk_sndbuf = snd * 2; - sock->sk->sk_rcvbuf = rcv * 2; + sock->sk->sk_sndbuf = nreqs * max_mesg * 2; + sock->sk->sk_rcvbuf = nreqs * max_mesg * 2; sock->sk->sk_write_space(sock->sk); release_sock(sock->sk); } @@ -548,9 +552,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) * provides an upper bound on the number of threads * which will access the socket. */ - svc_sock_setbufsize(svsk->sk_sock, - (serv->sv_nrthreads+3) * serv->sv_max_mesg, - (serv->sv_nrthreads+3) * serv->sv_max_mesg); + svc_sock_setbufsize(svsk, serv->sv_nrthreads + 3); clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); skb = NULL; @@ -574,7 +576,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) /* Don't enable netstamp, sunrpc doesn't need that much accuracy */ } - svsk->sk_sk->sk_stamp = skb->tstamp; + sock_write_timestamp(svsk->sk_sk, skb->tstamp); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */ len = skb->len; @@ -718,9 +720,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) * receive and respond to one request. * svc_udp_recvfrom will re-adjust if necessary */ - svc_sock_setbufsize(svsk->sk_sock, - 3 * svsk->sk_xprt.xpt_server->sv_max_mesg, - 3 * svsk->sk_xprt.xpt_server->sv_max_mesg); + svc_sock_setbufsize(svsk, 3); /* data might have come in before data_ready set up */ set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); @@ -1198,7 +1198,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) /* * Setup response header. TCP has a 4B record length field. */ -static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) +void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) { struct kvec *resv = &rqstp->rq_res.head[0]; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index a8db2e3f8904..d066aae3cb6d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -781,8 +781,15 @@ void xprt_connect(struct rpc_task *task) return; if (xprt_test_and_set_connecting(xprt)) return; - xprt->stat.connect_start = jiffies; - xprt->ops->connect(xprt, task); + /* Race breaker */ + if (!xprt_connected(xprt)) { + xprt->stat.connect_start = jiffies; + xprt->ops->connect(xprt, task); + } else { + xprt_clear_connecting(xprt); + task->tk_status = 0; + rpc_wake_up_queued_task(&xprt->pending, task); + } } xprt_release_write(xprt, task); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 8602a5f1b515..e8ad7ddf347a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -563,6 +563,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, DMA_TO_DEVICE); } +/* If the xdr_buf has more elements than the device can + * transmit in a single RDMA Send, then the reply will + * have to be copied into a bounce buffer. + */ +static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma, + struct xdr_buf *xdr, + __be32 *wr_lst) +{ + int elements; + + /* xdr->head */ + elements = 1; + + /* xdr->pages */ + if (!wr_lst) { + unsigned int remaining; + unsigned long pageoff; + + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + ++elements; + remaining -= min_t(u32, PAGE_SIZE - pageoff, + remaining); + pageoff = 0; + } + } + + /* xdr->tail */ + if (xdr->tail[0].iov_len) + ++elements; + + /* assume 1 SGE is needed for the transport header */ + return elements >= rdma->sc_max_send_sges; +} + +/* The device is not capable of sending the reply directly. + * Assemble the elements of @xdr into the transport header + * buffer. + */ +static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + struct xdr_buf *xdr, __be32 *wr_lst) +{ + unsigned char *dst, *tailbase; + unsigned int taillen; + + dst = ctxt->sc_xprt_buf; + dst += ctxt->sc_sges[0].length; + + memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len); + dst += xdr->head[0].iov_len; + + tailbase = xdr->tail[0].iov_base; + taillen = xdr->tail[0].iov_len; + if (wr_lst) { + u32 xdrpad; + + xdrpad = xdr_padsize(xdr->page_len); + if (taillen && xdrpad) { + tailbase += xdrpad; + taillen -= xdrpad; + } + } else { + unsigned int len, remaining; + unsigned long pageoff; + struct page **ppages; + + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + len = min_t(u32, PAGE_SIZE - pageoff, remaining); + + memcpy(dst, page_address(*ppages), len); + remaining -= len; + dst += len; + pageoff = 0; + } + } + + if (taillen) + memcpy(dst, tailbase, taillen); + + ctxt->sc_sges[0].length += xdr->len; + ib_dma_sync_single_for_device(rdma->sc_pd->device, + ctxt->sc_sges[0].addr, + ctxt->sc_sges[0].length, + DMA_TO_DEVICE); + + return 0; +} + /* svc_rdma_map_reply_msg - Map the buffer holding RPC message * @rdma: controlling transport * @ctxt: send_ctxt for the Send WR @@ -585,8 +678,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, u32 xdr_pad; int ret; - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst)) + return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst); + + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, xdr->head[0].iov_base, xdr->head[0].iov_len); @@ -617,8 +712,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - page_off, remaining); - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++, page_off, len); if (ret < 0) @@ -632,8 +726,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, len = xdr->tail[0].iov_len; tail: if (len) { - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 2848cafd4a17..ce5c610b49c7 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -475,13 +475,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Qualify the transport resource defaults with the * capabilities of this particular device */ - newxprt->sc_max_send_sges = dev->attrs.max_send_sge; - /* transport hdr, head iovec, one page list entry, tail iovec */ - if (newxprt->sc_max_send_sges < 4) { - pr_err("svcrdma: too few Send SGEs available (%d)\n", - newxprt->sc_max_send_sges); - goto errout; - } + /* Transport header, head iovec, tail iovec */ + newxprt->sc_max_send_sges = 3; + /* Add one SGE per page list entry */ + newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; + if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 956a5ea47b58..5ddbf227e7c6 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -546,7 +546,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, - 1, IB_POLL_WORKQUEUE); + ia->ri_device->num_comp_vectors > 1 ? 1 : 0, + IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); dprintk("RPC: %s: failed to create send CQ: %i\n", @@ -872,7 +873,7 @@ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt) for (i = 0; i <= buf->rb_sc_last; i++) { sc = rpcrdma_sendctx_create(&r_xprt->rx_ia); if (!sc) - goto out_destroy; + return -ENOMEM; sc->sc_xprt = r_xprt; buf->rb_sc_ctxs[i] = sc; @@ -880,10 +881,6 @@ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt) buf->rb_flags = 0; return 0; - -out_destroy: - rpcrdma_sendctxs_destroy(buf); - return -ENOMEM; } /* The sendctx queue is not guaranteed to have a size that is a diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 6b7539c0466e..7d8cce1dfcad 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2244,8 +2244,8 @@ static void xs_udp_setup_socket(struct work_struct *work) trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: - xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); + xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); } @@ -2480,8 +2480,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) } status = -EAGAIN; out: - xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); + xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 645c16052052..2649a0a0d45e 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -317,7 +317,6 @@ static int tipc_enable_bearer(struct net *net, const char *name, res = tipc_disc_create(net, b, &b->bcast_addr, &skb); if (res) { bearer_disable(net, b); - kfree(b); errstr = "failed to create discoverer"; goto rejected; } diff --git a/net/tipc/core.c b/net/tipc/core.c index 5b38f5164281..3ecca3b88bf8 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -75,9 +75,6 @@ static int __net_init tipc_init_net(struct net *net) goto out_nametbl; INIT_LIST_HEAD(&tn->dist_queue); - err = tipc_topsrv_start(net); - if (err) - goto out_subscr; err = tipc_bcast_init(net); if (err) @@ -86,8 +83,6 @@ static int __net_init tipc_init_net(struct net *net) return 0; out_bclink: - tipc_bcast_stop(net); -out_subscr: tipc_nametbl_stop(net); out_nametbl: tipc_sk_rht_destroy(net); @@ -97,7 +92,6 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { - tipc_topsrv_stop(net); tipc_net_stop(net); tipc_bcast_stop(net); tipc_nametbl_stop(net); @@ -111,6 +105,11 @@ static struct pernet_operations tipc_net_ops = { .size = sizeof(struct tipc_net), }; +static struct pernet_operations tipc_topsrv_net_ops = { + .init = tipc_topsrv_init_net, + .exit = tipc_topsrv_exit_net, +}; + static int __init tipc_init(void) { int err; @@ -129,10 +128,6 @@ static int __init tipc_init(void) if (err) goto out_netlink_compat; - err = tipc_socket_init(); - if (err) - goto out_socket; - err = tipc_register_sysctl(); if (err) goto out_sysctl; @@ -141,6 +136,14 @@ static int __init tipc_init(void) if (err) goto out_pernet; + err = tipc_socket_init(); + if (err) + goto out_socket; + + err = register_pernet_subsys(&tipc_topsrv_net_ops); + if (err) + goto out_pernet_topsrv; + err = tipc_bearer_setup(); if (err) goto out_bearer; @@ -148,12 +151,14 @@ static int __init tipc_init(void) pr_info("Started in single node mode\n"); return 0; out_bearer: + unregister_pernet_subsys(&tipc_topsrv_net_ops); +out_pernet_topsrv: + tipc_socket_stop(); +out_socket: unregister_pernet_subsys(&tipc_net_ops); out_pernet: tipc_unregister_sysctl(); out_sysctl: - tipc_socket_stop(); -out_socket: tipc_netlink_compat_stop(); out_netlink_compat: tipc_netlink_stop(); @@ -165,10 +170,11 @@ out_netlink: static void __exit tipc_exit(void) { tipc_bearer_cleanup(); + unregister_pernet_subsys(&tipc_topsrv_net_ops); + tipc_socket_stop(); unregister_pernet_subsys(&tipc_net_ops); tipc_netlink_stop(); tipc_netlink_compat_stop(); - tipc_socket_stop(); tipc_unregister_sysctl(); pr_info("Deactivated\n"); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 66d5b2c5987a..d72985ca1d55 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -908,7 +908,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, for (; i < TIPC_NAMETBL_SIZE; i++) { head = &tn->nametbl->services[i]; - if (*last_type) { + if (*last_type || + (!i && *last_key && (*last_lower == *last_key))) { service = tipc_service_find(net, *last_type); if (!service) return -EPIPE; diff --git a/net/tipc/net.c b/net/tipc/net.c index f076edb74338..7ce1e86b024f 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -163,12 +163,9 @@ void tipc_sched_net_finalize(struct net *net, u32 addr) void tipc_net_stop(struct net *net) { - u32 self = tipc_own_addr(net); - - if (!self) + if (!tipc_own_id(net)) return; - tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self); rtnl_lock(); tipc_bearer_stop(net); tipc_node_stop(net); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 6376467e78f8..588d5aa14c41 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -87,6 +87,11 @@ static int tipc_skb_tailroom(struct sk_buff *skb) return limit; } +static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv) +{ + return TLV_GET_LEN(tlv) - TLV_SPACE(0); +} + static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) { struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb); @@ -166,6 +171,11 @@ static struct sk_buff *tipc_get_err_tlv(char *str) return buf; } +static inline bool string_is_valid(char *s, int len) +{ + return memchr(s, '\0', len) ? true : false; +} + static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -257,8 +267,14 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, if (msg->rep_type) tipc_tlv_init(msg->rep, msg->rep_type); - if (cmd->header) - (*cmd->header)(msg); + if (cmd->header) { + err = (*cmd->header)(msg); + if (err) { + kfree_skb(msg->rep); + msg->rep = NULL; + return err; + } + } arg = nlmsg_new(0, GFP_KERNEL); if (!arg) { @@ -379,6 +395,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, struct nlattr *prop; struct nlattr *bearer; struct tipc_bearer_config *b; + int len; b = (struct tipc_bearer_config *)TLV_DATA(msg->req); @@ -386,6 +403,15 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; + len = TLV_GET_DATA_LEN(msg->req); + len -= offsetof(struct tipc_bearer_config, name); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); + if (!string_is_valid(b->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name)) return -EMSGSIZE; @@ -411,6 +437,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, { char *name; struct nlattr *bearer; + int len; name = (char *)TLV_DATA(msg->req); @@ -418,6 +445,10 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name)) return -EMSGSIZE; @@ -478,6 +509,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, struct nlattr *prop[TIPC_NLA_PROP_MAX + 1]; struct nlattr *stats[TIPC_NLA_STATS_MAX + 1]; int err; + int len; if (!attrs[TIPC_NLA_LINK]) return -EINVAL; @@ -504,6 +536,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return err; name = (char *)TLV_DATA(msg->req); + + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) return 0; @@ -644,6 +681,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, struct nlattr *prop; struct nlattr *media; struct tipc_link_config *lc; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -651,6 +689,10 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, if (!media) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name)) return -EMSGSIZE; @@ -671,6 +713,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, struct nlattr *prop; struct nlattr *bearer; struct tipc_link_config *lc; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -678,6 +721,10 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name)) return -EMSGSIZE; @@ -726,9 +773,19 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, struct tipc_link_config *lc; struct tipc_bearer *bearer; struct tipc_media *media; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); + len = TLV_GET_DATA_LEN(msg->req); + len -= offsetof(struct tipc_link_config, name); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_LINK_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + media = tipc_media_find(lc->name); if (media) { cmd->doit = &__tipc_nl_media_set; @@ -750,6 +807,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, { char *name; struct nlattr *link; + int len; name = (char *)TLV_DATA(msg->req); @@ -757,6 +815,10 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (!link) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) return -EMSGSIZE; @@ -778,6 +840,8 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); + if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + return -EINVAL; depth = ntohl(ntq->depth); @@ -1201,7 +1265,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) } len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (len && !TLV_OK(msg.req, len)) { + if (!len || !TLV_OK(msg.req, len)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; diff --git a/net/tipc/node.c b/net/tipc/node.c index 488019766433..32556f480a60 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -624,6 +624,12 @@ static void tipc_node_timeout(struct timer_list *t) __skb_queue_head_init(&xmitq); + /* Initial node interval to value larger (10 seconds), then it will be + * recalculated with link lowest tolerance + */ + tipc_node_read_lock(n); + n->keepalive_intv = 10000; + tipc_node_read_unlock(n); for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) { tipc_node_read_lock(n); le = &n->links[bearer_id]; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 366ce0bf2658..6c91f1217dcf 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -377,11 +377,13 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) #define tipc_wait_for_cond(sock_, timeo_, condition_) \ ({ \ + DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ struct sock *sk_; \ int rc_; \ \ while ((rc_ = !(condition_))) { \ - DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ + /* coupled with smp_wmb() in tipc_sk_proto_rcv() */ \ + smp_rmb(); \ sk_ = (sock_)->sk; \ rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ @@ -724,11 +726,11 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, switch (sk->sk_state) { case TIPC_ESTABLISHED: - case TIPC_CONNECTING: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) revents |= EPOLLOUT; /* fall thru' */ case TIPC_LISTEN: + case TIPC_CONNECTING: if (!skb_queue_empty(&sk->sk_receive_queue)) revents |= EPOLLIN | EPOLLRDNORM; break; @@ -878,7 +880,6 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int blks = tsk_blocks(GROUP_H_SIZE + dlen); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_group *grp = tsk->group; struct net *net = sock_net(sk); struct tipc_member *mb = NULL; u32 node, port; @@ -892,7 +893,9 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, /* Block or return if destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tipc_dest_find(&tsk->cong_links, node, 0) && - !tipc_group_cong(grp, node, port, blks, &mb)); + tsk->group && + !tipc_group_cong(tsk->group, node, port, blks, + &mb)); if (unlikely(rc)) return rc; @@ -922,7 +925,6 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, struct tipc_sock *tsk = tipc_sk(sk); struct list_head *cong_links = &tsk->cong_links; int blks = tsk_blocks(GROUP_H_SIZE + dlen); - struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct tipc_member *first = NULL; struct tipc_member *mbr = NULL; @@ -939,9 +941,10 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, type = msg_nametype(hdr); inst = dest->addr.name.name.instance; scope = msg_lookup_scope(hdr); - exclude = tipc_group_exclude(grp); while (++lookups < 4) { + exclude = tipc_group_exclude(tsk->group); + first = NULL; /* Look for a non-congested destination member, if any */ @@ -950,7 +953,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, &dstcnt, exclude, false)) return -EHOSTUNREACH; tipc_dest_pop(&dsts, &node, &port); - cong = tipc_group_cong(grp, node, port, blks, &mbr); + cong = tipc_group_cong(tsk->group, node, port, blks, + &mbr); if (!cong) break; if (mbr == first) @@ -969,7 +973,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, /* Block or return if destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tipc_dest_find(cong_links, node, 0) && - !tipc_group_cong(grp, node, port, + tsk->group && + !tipc_group_cong(tsk->group, node, port, blks, &mbr)); if (unlikely(rc)) return rc; @@ -1004,8 +1009,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_group *grp = tsk->group; - struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_nlist *dsts; struct tipc_mc_method *method = &tsk->mc_method; bool ack = method->mandatory && method->rcast; int blks = tsk_blocks(MCAST_H_SIZE + dlen); @@ -1014,15 +1018,17 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sk_buff_head pkts; int rc = -EHOSTUNREACH; - if (!dsts->local && !dsts->remote) - return -EHOSTUNREACH; - /* Block or return if any destination link or member is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && - !tipc_group_bc_cong(grp, blks)); + rc = tipc_wait_for_cond(sock, &timeout, + !tsk->cong_link_cnt && tsk->group && + !tipc_group_bc_cong(tsk->group, blks)); if (unlikely(rc)) return rc; + dsts = tipc_group_dests(tsk->group); + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + /* Complete message header */ if (dest) { msg_set_type(hdr, TIPC_GRP_MCAST_MSG); @@ -1034,7 +1040,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, msg_set_hdr_sz(hdr, GROUP_H_SIZE); msg_set_destport(hdr, 0); msg_set_destnode(hdr, 0); - msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(tsk->group)); /* Avoid getting stuck with repeated forced replicasts */ msg_set_grp_bc_ack_req(hdr, ack); @@ -1314,7 +1320,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(!dest)) { dest = &tsk->peer; - if (!syn || dest->family != AF_TIPC) + if (!syn && dest->family != AF_TIPC) return -EDESTADDRREQ; } @@ -1957,6 +1963,8 @@ static void tipc_sk_proto_rcv(struct sock *sk, return; case SOCK_WAKEUP: tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); + /* coupled with smp_rmb() in tipc_wait_for_cond() */ + smp_wmb(); tsk->cong_link_cnt--; wakeup = true; break; @@ -2031,7 +2039,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) return true; /* If empty 'ACK-' message, wake up sleeping connect() */ - sk->sk_data_ready(sk); + sk->sk_state_change(sk); /* 'ACK-' message is neither accepted nor rejected: */ msg_set_dest_droppable(hdr, 1); @@ -2302,6 +2310,16 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) return 0; } +static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr) +{ + if (addr->family != AF_TIPC) + return false; + if (addr->addrtype == TIPC_SERVICE_RANGE) + return (addr->addr.nameseq.lower <= addr->addr.nameseq.upper); + return (addr->addrtype == TIPC_SERVICE_ADDR || + addr->addrtype == TIPC_SOCKET_ADDR); +} + /** * tipc_connect - establish a connection to another TIPC port * @sock: socket structure @@ -2337,18 +2355,18 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, if (!tipc_sk_type_connectionless(sk)) res = -EINVAL; goto exit; - } else if (dst->family != AF_TIPC) { - res = -EINVAL; } - if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME) + if (!tipc_sockaddr_is_sane(dst)) { res = -EINVAL; - if (res) goto exit; - + } /* DGRAM/RDM connect(), just save the destaddr */ if (tipc_sk_type_connectionless(sk)) { memcpy(&tsk->peer, dest, destlen); goto exit; + } else if (dst->addrtype == TIPC_SERVICE_RANGE) { + res = -EINVAL; + goto exit; } previous = sk->sk_state; @@ -2683,11 +2701,15 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_start(&iter); while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) { - spin_lock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(&iter); + lock_sock(&tsk->sk); msg = &tsk->phdr; msg_set_prevnode(msg, tipc_own_addr(net)); msg_set_orignode(msg, tipc_own_addr(net)); - spin_unlock_bh(&tsk->sk.sk_lock.slock); + release_sock(&tsk->sk); + rhashtable_walk_start(&iter); + sock_put(&tsk->sk); } rhashtable_walk_stop(&iter); diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index d793b4343885..aa015c233898 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -77,8 +77,9 @@ void tipc_sub_report_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, u32 event, u32 port, u32 node, u32 scope, int must); -int tipc_topsrv_start(struct net *net); -void tipc_topsrv_stop(struct net *net); + +int __net_init tipc_topsrv_init_net(struct net *net); +void __net_exit tipc_topsrv_exit_net(struct net *net); void tipc_sub_put(struct tipc_subscription *subscription); void tipc_sub_get(struct tipc_subscription *subscription); diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index b84c0059214f..35558656fe02 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -371,6 +371,7 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, struct tipc_subscription *sub; if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { + s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL); tipc_conn_delete_sub(con, s); return 0; } @@ -404,7 +405,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; - if (ret > 0) { + if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); @@ -642,7 +643,7 @@ static void tipc_topsrv_work_stop(struct tipc_topsrv *s) destroy_workqueue(s->send_wq); } -int tipc_topsrv_start(struct net *net) +static int tipc_topsrv_start(struct net *net) { struct tipc_net *tn = tipc_net(net); const char name[] = "topology_server"; @@ -676,7 +677,7 @@ int tipc_topsrv_start(struct net *net) return ret; } -void tipc_topsrv_stop(struct net *net) +static void tipc_topsrv_stop(struct net *net) { struct tipc_topsrv *srv = tipc_topsrv(net); struct socket *lsock = srv->listener; @@ -701,3 +702,13 @@ void tipc_topsrv_stop(struct net *net) idr_destroy(&srv->conn_idr); kfree(srv); } + +int __net_init tipc_topsrv_init_net(struct net *net) +{ + return tipc_topsrv_start(net); +} + +void __net_exit tipc_topsrv_exit_net(struct net *net) +{ + tipc_topsrv_stop(net); +} diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 9783101bc4a9..da2d311476ab 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -245,10 +245,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, } err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr); - if (err) { - kfree_skb(_skb); + if (err) goto out; - } } err = 0; out: @@ -680,6 +678,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (err) goto err; + if (remote.proto != local.proto) { + err = -EINVAL; + goto err; + } + /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net)) { memcpy(node_id, local.ipv6.in6_u.u6_addr8, 16); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 961b07d4d41c..ead29c2aefa7 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,8 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock); static void tls_device_free_ctx(struct tls_context *ctx) { - if (ctx->tx_conf == TLS_HW) + if (ctx->tx_conf == TLS_HW) { kfree(tls_offload_ctx_tx(ctx)); + kfree(ctx->tx.rec_seq); + kfree(ctx->tx.iv); + } if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx)); @@ -542,10 +545,22 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); } +static void tls_device_resync_rx(struct tls_context *tls_ctx, + struct sock *sk, u32 seq, u64 rcd_sn) +{ + struct net_device *netdev; + + if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags))) + return; + netdev = READ_ONCE(tls_ctx->netdev); + if (netdev) + netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk, seq, rcd_sn); + clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags); +} + void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct net_device *netdev = tls_ctx->netdev; struct tls_offload_context_rx *rx_ctx; u32 is_req_pending; s64 resync_req; @@ -560,16 +575,16 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn) is_req_pending = resync_req; if (unlikely(is_req_pending) && req_seq == seq && - atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) - netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk, - seq + TLS_HEADER_SIZE - 1, - rcd_sn); + atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) { + seq += TLS_HEADER_SIZE - 1; + tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn); + } } static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) { struct strp_msg *rxm = strp_msg(skb); - int err = 0, offset = rxm->offset, copy, nsg; + int err = 0, offset = rxm->offset, copy, nsg, data_len, pos; struct sk_buff *skb_iter, *unused; struct scatterlist sg[1]; char *orig_buf, *buf; @@ -600,25 +615,42 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) else err = 0; - copy = min_t(int, skb_pagelen(skb) - offset, - rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE); + data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE; + + if (skb_pagelen(skb) > offset) { + copy = min_t(int, skb_pagelen(skb) - offset, data_len); - if (skb->decrypted) - skb_store_bits(skb, offset, buf, copy); + if (skb->decrypted) + skb_store_bits(skb, offset, buf, copy); - offset += copy; - buf += copy; + offset += copy; + buf += copy; + } + pos = skb_pagelen(skb); skb_walk_frags(skb, skb_iter) { - copy = min_t(int, skb_iter->len, - rxm->full_len - offset + rxm->offset - - TLS_CIPHER_AES_GCM_128_TAG_SIZE); + int frag_pos; + + /* Practically all frags must belong to msg if reencrypt + * is needed with current strparser and coalescing logic, + * but strparser may "get optimized", so let's be safe. + */ + if (pos + skb_iter->len <= offset) + goto done_with_frag; + if (pos >= data_len + rxm->offset) + break; + + frag_pos = offset - pos; + copy = min_t(int, skb_iter->len - frag_pos, + data_len + rxm->offset - offset); if (skb_iter->decrypted) - skb_store_bits(skb_iter, offset, buf, copy); + skb_store_bits(skb_iter, frag_pos, buf, copy); offset += copy; buf += copy; +done_with_frag: + pos += skb_iter->len; } free_buf: @@ -874,7 +906,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_netdev; free_sw_resources: + up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); + down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_netdev: @@ -894,12 +928,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk) if (!netdev) goto out; - if (!(netdev->features & NETIF_F_HW_TLS_RX)) { - pr_err_ratelimited("%s: device is missing NETIF_F_HW_TLS_RX cap\n", - __func__); - goto out; - } - netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx, TLS_OFFLOAD_CTX_DIR_RX); @@ -909,8 +937,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk) } out: up_read(&device_offload_lock); - kfree(tls_ctx->rx.rec_seq); - kfree(tls_ctx->rx.iv); tls_sw_release_resources_rx(sk); } @@ -940,7 +966,10 @@ static int tls_device_down(struct net_device *netdev) if (ctx->rx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); - ctx->netdev = NULL; + WRITE_ONCE(ctx->netdev, NULL); + smp_mb__before_atomic(); /* pairs with test_and_set_bit() */ + while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags)) + usleep_range(10, 200); dev_put(netdev); list_del_init(&ctx->list); @@ -960,7 +989,8 @@ static int tls_dev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - if (!(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX))) + if (!dev->tlsdev_ops && + !(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX))) return NOTIFY_DONE; switch (event) { diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 450a6dbc5a88..426dd97725e4 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -193,18 +193,26 @@ static void update_chksum(struct sk_buff *skb, int headln) static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) { + struct sock *sk = skb->sk; + int delta; + skb_copy_header(nskb, skb); skb_put(nskb, skb->len); memcpy(nskb->data, skb->data, headln); - update_chksum(nskb, headln); nskb->destructor = skb->destructor; - nskb->sk = skb->sk; + nskb->sk = sk; skb->destructor = NULL; skb->sk = NULL; - refcount_add(nskb->truesize - skb->truesize, - &nskb->sk->sk_wmem_alloc); + + update_chksum(nskb, headln); + + delta = nskb->truesize - skb->truesize; + if (likely(delta < 0)) + WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); + else if (delta) + refcount_add(delta, &sk->sk_wmem_alloc); } /* This function may be called after the user socket is already diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 523622dc74f8..25b3fb585777 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -290,11 +290,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_sw_free_resources_tx(sk); } - if (ctx->rx_conf == TLS_SW) { - kfree(ctx->rx.rec_seq); - kfree(ctx->rx.iv); + if (ctx->rx_conf == TLS_SW) tls_sw_free_resources_rx(sk); - } #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) @@ -550,11 +547,14 @@ static struct tls_context *create_ctx(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) return NULL; icsk->icsk_ulp_data = ctx; + ctx->setsockopt = sk->sk_prot->setsockopt; + ctx->getsockopt = sk->sk_prot->getsockopt; + ctx->sk_proto_close = sk->sk_prot->close; return ctx; } @@ -685,9 +685,6 @@ static int tls_init(struct sock *sk) rc = -ENOMEM; goto out; } - ctx->setsockopt = sk->sk_prot->setsockopt; - ctx->getsockopt = sk->sk_prot->getsockopt; - ctx->sk_proto_close = sk->sk_prot->close; /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ if (ip_ver == TLSV6 && diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b9c6ecfbcfea..6848a8196711 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1118,6 +1118,9 @@ void tls_sw_release_resources_rx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + kfree(tls_ctx->rx.rec_seq); + kfree(tls_ctx->rx.iv); + if (ctx->aead_recv) { kfree_skb(ctx->recv_pkt); ctx->recv_pkt = NULL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c754f3a90a2e..f601933ad728 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -888,7 +888,7 @@ retry: addr->hash ^= sk->sk_type; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(&unix_socket_table[addr->hash], sk); spin_unlock(&unix_table_lock); err = 0; @@ -1058,7 +1058,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(list, sk); out_unlock: @@ -1329,15 +1329,29 @@ restart: RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); - /* copy address information from listening to new sock*/ - if (otheru->addr) { - refcount_inc(&otheru->addr->refcnt); - newu->addr = otheru->addr; - } + /* copy address information from listening to new sock + * + * The contents of *(otheru->addr) and otheru->path + * are seen fully set up here, since we have found + * otheru in hash under unix_table_lock. Insertion + * into the hash chain we'd found it in had been done + * in an earlier critical area protected by unix_table_lock, + * the same one where we'd set *(otheru->addr) contents, + * as well as otheru->path and otheru->addr itself. + * + * Using smp_store_release() here to set newu->addr + * is enough to make those stores, as well as stores + * to newu->path visible to anyone who gets newu->addr + * by smp_load_acquire(). IOW, the same warranties + * as for unix_sock instances bound in unix_bind() or + * in unix_autobind(). + */ if (otheru->path.dentry) { path_get(&otheru->path); newu->path = otheru->path; } + refcount_inc(&otheru->addr->refcnt); + smp_store_release(&newu->addr, otheru->addr); /* Set credentials */ copy_peercred(sk, other); @@ -1451,7 +1465,7 @@ out: static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; - struct unix_sock *u; + struct unix_address *addr; DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr); int err = 0; @@ -1466,19 +1480,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) sock_hold(sk); } - u = unix_sk(sk); - unix_state_lock(sk); - if (!u->addr) { + addr = smp_load_acquire(&unix_sk(sk)->addr); + if (!addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; err = sizeof(short); } else { - struct unix_address *addr = u->addr; - err = addr->len; memcpy(sunaddr, addr->name, addr->len); } - unix_state_unlock(sk); sock_put(sk); out: return err; @@ -2071,11 +2081,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); - if (u->addr) { - msg->msg_namelen = u->addr->len; - memcpy(msg->msg_name, u->addr->name, u->addr->len); + if (addr) { + msg->msg_namelen = addr->len; + memcpy(msg->msg_name, addr->name, addr->len); } } @@ -2579,15 +2589,14 @@ static int unix_open_file(struct sock *sk) if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; - unix_state_lock(sk); + if (!smp_load_acquire(&unix_sk(sk)->addr)) + return -ENOENT; + path = unix_sk(sk)->path; - if (!path.dentry) { - unix_state_unlock(sk); + if (!path.dentry) return -ENOENT; - } path_get(&path); - unix_state_unlock(sk); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) @@ -2828,7 +2837,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { + if (u->addr) { // under unix_table_lock here int i, len; seq_putc(seq, ' '); diff --git a/net/unix/diag.c b/net/unix/diag.c index 384c84e83462..3183d9b8ab33 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,7 +10,8 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { - struct unix_address *addr = unix_sk(sk)->addr; + /* might or might not have unix_table_lock */ + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); if (!addr) return 0; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 5d3cce9e8744..96ab344f17bb 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); @@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,15 +701,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_wq; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_vci; + + return 0; + +out_vci: + vsock_core_exit(); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; } static void __exit virtio_vsock_exit(void) { unregister_virtio_driver(&virtio_vsock_driver); + vsock_core_exit(); destroy_workqueue(virtio_vsock_workqueue); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 3ae3a33da70b..f3f3d06cb6d8 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -662,6 +662,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk, */ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) { + const struct virtio_transport *t; + struct virtio_vsock_pkt *reply; struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, .type = le16_to_cpu(pkt->hdr.type), @@ -672,15 +674,21 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) return 0; - pkt = virtio_transport_alloc_pkt(&info, 0, - le64_to_cpu(pkt->hdr.dst_cid), - le32_to_cpu(pkt->hdr.dst_port), - le64_to_cpu(pkt->hdr.src_cid), - le32_to_cpu(pkt->hdr.src_port)); - if (!pkt) + reply = virtio_transport_alloc_pkt(&info, 0, + le64_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port), + le64_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + if (!reply) return -ENOMEM; - return virtio_transport_get_ops()->send_pkt(pkt); + t = virtio_transport_get_ops(); + if (!t) { + virtio_transport_free_pkt(reply); + return -ENOTCONN; + } + + return t->send_pkt(reply); } static void virtio_transport_wait_close(struct sock *sk, long timeout) @@ -778,12 +786,19 @@ static bool virtio_transport_close(struct vsock_sock *vsk) void virtio_transport_release(struct vsock_sock *vsk) { + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt, *tmp; struct sock *sk = &vsk->sk; bool remove_sock = true; lock_sock(sk); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); + + list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) { + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } release_sock(sk); if (remove_sock) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index cb332adb84cd..c3d5ab01fba7 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -264,6 +264,31 @@ vmci_transport_send_control_pkt_bh(struct sockaddr_vm *src, } static int +vmci_transport_alloc_send_control_pkt(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle) +{ + struct vmci_transport_packet *pkt; + int err; + + pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + err = __vmci_transport_send_control_pkt(pkt, src, dst, type, size, + mode, wait, proto, handle, + true); + kfree(pkt); + + return err; +} + +static int vmci_transport_send_control_pkt(struct sock *sk, enum vmci_transport_packet_type type, u64 size, @@ -272,9 +297,7 @@ vmci_transport_send_control_pkt(struct sock *sk, u16 proto, struct vmci_handle handle) { - struct vmci_transport_packet *pkt; struct vsock_sock *vsk; - int err; vsk = vsock_sk(sk); @@ -284,17 +307,10 @@ vmci_transport_send_control_pkt(struct sock *sk, if (!vsock_addr_bound(&vsk->remote_addr)) return -EINVAL; - pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - - err = __vmci_transport_send_control_pkt(pkt, &vsk->local_addr, - &vsk->remote_addr, type, size, - mode, wait, proto, handle, - true); - kfree(pkt); - - return err; + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, + &vsk->remote_addr, + type, size, mode, + wait, proto, handle); } static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, @@ -312,12 +328,29 @@ static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, static int vmci_transport_send_reset(struct sock *sk, struct vmci_transport_packet *pkt) { + struct sockaddr_vm *dst_ptr; + struct sockaddr_vm dst; + struct vsock_sock *vsk; + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) return 0; - return vmci_transport_send_control_pkt(sk, - VMCI_TRANSPORT_PACKET_TYPE_RST, - 0, 0, NULL, VSOCK_PROTO_INVALID, - VMCI_INVALID_HANDLE); + + vsk = vsock_sk(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) + return -EINVAL; + + if (vsock_addr_bound(&vsk->remote_addr)) { + dst_ptr = &vsk->remote_addr; + } else { + vsock_addr_init(&dst, pkt->dg.src.context, + pkt->src_port); + dst_ptr = &dst; + } + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, dst_ptr, + VMCI_TRANSPORT_PACKET_TYPE_RST, + 0, 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); } static int vmci_transport_send_negotiate(struct sock *sk, size_t size) @@ -1618,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work) static void vmci_transport_destruct(struct vsock_sock *vsk) { + /* transport can be NULL if we hit a failure at init() time */ + if (!vmci_trans(vsk)) + return; + /* Ensure that the detach callback doesn't use the sk/vsk * we are about to destruct. */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 176edfefcbaa..c6711ead5e59 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8993,8 +8993,10 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_CONTROL_PORT_OVER_NL80211]) { int r = validate_pae_over_nl80211(rdev, info); - if (r < 0) + if (r < 0) { + kzfree(connkeys); return r; + } ibss.control_port_over_nl80211 = true; } @@ -13390,7 +13392,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEAUTHENTICATE, @@ -13441,7 +13444,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS, @@ -13449,7 +13453,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DISCONNECT, @@ -13478,7 +13483,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEL_PMKSA, @@ -13830,7 +13836,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_SET_QOS_MAP, @@ -13885,7 +13892,8 @@ static const struct genl_ops nl80211_ops[] = { .doit = nl80211_set_pmk, .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEL_PMK, @@ -15433,6 +15441,11 @@ void cfg80211_ch_switch_notify(struct net_device *dev, wdev->chandef = *chandef; wdev->preset_chandef = *chandef; + + if (wdev->iftype == NL80211_IFTYPE_STATION && + !WARN_ON(!wdev->current_bss)) + wdev->current_bss->pub.channel = chandef->chan; + nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL, NL80211_CMD_CH_SWITCH_NOTIFY, 0); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 24cfa2776f50..8a47297ff206 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1249,7 +1249,7 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd) * definitions (the "2.4 GHz band", the "5 GHz band" and the "60GHz band"), * however it is safe for now to assume that a frequency rule should not be * part of a frequency's band if the start freq or end freq are off by more - * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 10 GHz for the + * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 20 GHz for the * 60 GHz band. * This resolution can be lowered and should be considered as we add * regulatory rule support for other "bands". @@ -1264,7 +1264,7 @@ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, * with the Channel starting frequency above 45 GHz. */ u32 limit = freq_khz > 45 * ONE_GHZ_IN_KHZ ? - 10 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; + 20 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; if (abs(freq_khz - freq_range->start_freq_khz) <= limit) return true; if (abs(freq_khz - freq_range->end_freq_khz) <= limit) @@ -1287,6 +1287,16 @@ reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1, return dfs_region1; } +static void reg_wmm_rules_intersect(const struct ieee80211_wmm_ac *wmm_ac1, + const struct ieee80211_wmm_ac *wmm_ac2, + struct ieee80211_wmm_ac *intersect) +{ + intersect->cw_min = max_t(u16, wmm_ac1->cw_min, wmm_ac2->cw_min); + intersect->cw_max = max_t(u16, wmm_ac1->cw_max, wmm_ac2->cw_max); + intersect->cot = min_t(u16, wmm_ac1->cot, wmm_ac2->cot); + intersect->aifsn = max_t(u8, wmm_ac1->aifsn, wmm_ac2->aifsn); +} + /* * Helper for regdom_intersect(), this does the real * mathematical intersection fun @@ -1301,6 +1311,8 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, struct ieee80211_freq_range *freq_range; const struct ieee80211_power_rule *power_rule1, *power_rule2; struct ieee80211_power_rule *power_rule; + const struct ieee80211_wmm_rule *wmm_rule1, *wmm_rule2; + struct ieee80211_wmm_rule *wmm_rule; u32 freq_diff, max_bandwidth1, max_bandwidth2; freq_range1 = &rule1->freq_range; @@ -1311,6 +1323,10 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, power_rule2 = &rule2->power_rule; power_rule = &intersected_rule->power_rule; + wmm_rule1 = &rule1->wmm_rule; + wmm_rule2 = &rule2->wmm_rule; + wmm_rule = &intersected_rule->wmm_rule; + freq_range->start_freq_khz = max(freq_range1->start_freq_khz, freq_range2->start_freq_khz); freq_range->end_freq_khz = min(freq_range1->end_freq_khz, @@ -1354,6 +1370,29 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms, rule2->dfs_cac_ms); + if (rule1->has_wmm && rule2->has_wmm) { + u8 ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + reg_wmm_rules_intersect(&wmm_rule1->client[ac], + &wmm_rule2->client[ac], + &wmm_rule->client[ac]); + reg_wmm_rules_intersect(&wmm_rule1->ap[ac], + &wmm_rule2->ap[ac], + &wmm_rule->ap[ac]); + } + + intersected_rule->has_wmm = true; + } else if (rule1->has_wmm) { + *wmm_rule = *wmm_rule1; + intersected_rule->has_wmm = true; + } else if (rule2->has_wmm) { + *wmm_rule = *wmm_rule2; + intersected_rule->has_wmm = true; + } else { + intersected_rule->has_wmm = false; + } + if (!is_valid_reg_rule(intersected_rule)) return -EINVAL; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d49aa79b7997..f7f53f9ae7ef 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x25_neigh *nb) unsigned int lci = 1; struct sock *sk; - read_lock_bh(&x25_list_lock); - - while ((sk = __x25_find_socket(lci, nb)) != NULL) { + while ((sk = x25_find_socket(lci, nb)) != NULL) { sock_put(sk); if (++lci == 4096) { lci = 0; break; } + cond_resched(); } - read_unlock_bh(&x25_list_lock); return lci; } @@ -681,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; int len, i, rc = 0; - if (!sock_flag(sk, SOCK_ZAPPED) || - addr_len != sizeof(struct sockaddr_x25) || + if (addr_len != sizeof(struct sockaddr_x25) || addr->sx25_family != AF_X25) { rc = -EINVAL; goto out; @@ -697,9 +694,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } lock_sock(sk); - x25_sk(sk)->source_addr = addr->sx25_addr; - x25_insert_socket(sk); - sock_reset_flag(sk, SOCK_ZAPPED); + if (sock_flag(sk, SOCK_ZAPPED)) { + x25_sk(sk)->source_addr = addr->sx25_addr; + x25_insert_socket(sk); + sock_reset_flag(sk, SOCK_ZAPPED); + } else { + rc = -EINVAL; + } release_sock(sk); SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); out: @@ -815,8 +816,13 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) + if (rc) { + read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + x25->state = X25_STATE_0; + } out_put_route: x25_route_put(rt); out: diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index bfe2dbea480b..a3b037fbfecd 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -152,9 +152,6 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) static void xdp_umem_release(struct xdp_umem *umem) { - struct task_struct *task; - struct mm_struct *mm; - xdp_umem_clear_dev(umem); if (umem->fq) { @@ -169,21 +166,10 @@ static void xdp_umem_release(struct xdp_umem *umem) xdp_umem_unpin_pages(umem); - task = get_pid_task(umem->pid, PIDTYPE_PID); - put_pid(umem->pid); - if (!task) - goto out; - mm = get_task_mm(task); - put_task_struct(task); - if (!mm) - goto out; - - mmput(mm); kfree(umem->pages); umem->pages = NULL; xdp_umem_unaccount_pages(umem); -out: kfree(umem); } @@ -312,7 +298,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (size_chk < 0) return -EINVAL; - umem->pid = get_task_pid(current, PIDTYPE_PID); umem->address = (unsigned long)addr; umem->props.chunk_mask = ~((u64)chunk_size - 1); umem->props.size = size; @@ -328,7 +313,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) err = xdp_umem_account_pages(umem); if (err) - goto out; + return err; err = xdp_umem_pin_pages(umem); if (err) @@ -347,8 +332,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) out_account: xdp_umem_unaccount_pages(umem); -out: - put_pid(umem->pid); return err; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index be3520e429c9..790b514f86b6 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -346,6 +346,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; + skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); + goto drop; + } + lock: spin_lock(&x->lock); @@ -385,7 +391,6 @@ lock: XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; - skb_dst_force(skb); dev_hold(skb->dev); if (crypto_done) diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 6f05e831a73e..555ee2aca6c0 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -70,17 +70,28 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) return NULL; } -static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) +static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb, + unsigned short family) { struct xfrmi_net *xfrmn; - int ifindex; struct xfrm_if *xi; + int ifindex = 0; - if (!skb->dev) + if (!secpath_exists(skb) || !skb->dev) return NULL; - xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); - ifindex = skb->dev->ifindex; + switch (family) { + case AF_INET6: + ifindex = inet6_sdif(skb); + break; + case AF_INET: + ifindex = inet_sdif(skb); + break; + } + if (!ifindex) + ifindex = skb->dev->ifindex; + + xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { if (ifindex == xi->dev->ifindex && diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 261995d37ced..6d20fbcde000 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -102,6 +102,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + err = -EHOSTUNREACH; goto error_nolock; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 119a427d9b2b..ce1b262ce964 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1628,7 +1628,10 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { - __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + __u32 mark = 0; + + if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) + mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, @@ -2336,9 +2339,11 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, ifcb = xfrm_if_get_cb(); if (ifcb) { - xi = ifcb->decode_session(skb); - if (xi) + xi = ifcb->decode_session(skb, family); + if (xi) { if_id = xi->p.if_id; + net = xi->net; + } } rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index b669262682c9..11e09eb138d6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -426,7 +426,13 @@ static void xfrm_put_mode(struct xfrm_mode *mode) module_put(mode->owner); } -static void xfrm_state_gc_destroy(struct xfrm_state *x) +void xfrm_state_free(struct xfrm_state *x) +{ + kmem_cache_free(xfrm_state_cache, x); +} +EXPORT_SYMBOL(xfrm_state_free); + +static void ___xfrm_state_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); @@ -452,7 +458,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) } xfrm_dev_state_free(x); security_xfrm_state_free(x); - kmem_cache_free(xfrm_state_cache, x); + xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) @@ -468,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - xfrm_state_gc_destroy(x); + ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -592,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); -void __xfrm_state_destroy(struct xfrm_state *x) +void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + if (sync) { + synchronize_rcu(); + ___xfrm_state_destroy(x); + } else { + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); + } } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -702,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; @@ -724,7 +735,10 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - xfrm_state_put(x); + if (sync) + xfrm_state_put_sync(x); + else + xfrm_state_put(x); if (!err) cnt++; @@ -788,7 +802,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; - si->sadhcnt = net->xfrm.state_hmask; + si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } @@ -2211,7 +2225,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); - xfrm_state_put(t); + xfrm_state_put_sync(t); x->tunnel = NULL; } } @@ -2371,8 +2385,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); + xfrm_state_flush(net, 0, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index df7ca2dabc48..2122f89f6155 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1424,7 +1424,7 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) ret = verify_policy_dir(p->dir); if (ret) return ret; - if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir)) + if (p->index && (xfrm_policy_id2dir(p->index) != p->dir)) return -EINVAL; return 0; @@ -1488,10 +1488,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) if (!ut[i].family) ut[i].family = family; - if ((ut[i].mode == XFRM_MODE_TRANSPORT) && - (ut[i].family != prev_family)) - return -EINVAL; - + switch (ut[i].mode) { + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + break; + default: + if (ut[i].family != prev_family) + return -EINVAL; + break; + } if (ut[i].mode >= XFRM_MODE_MAX) return -EINVAL; @@ -1508,20 +1513,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) return -EINVAL; } - switch (ut[i].id.proto) { - case IPPROTO_AH: - case IPPROTO_ESP: - case IPPROTO_COMP: -#if IS_ENABLED(CONFIG_IPV6) - case IPPROTO_ROUTING: - case IPPROTO_DSTOPTS: -#endif - case IPSEC_PROTO_ANY: - break; - default: + if (!xfrm_id_proto_valid(ut[i].id.proto)) return -EINVAL; - } - } return 0; @@ -1927,7 +1920,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true); + err = xfrm_state_flush(net, p->proto, true, false); if (err) { if (err == -ESRCH) /* empty table */ return 0; @@ -2288,13 +2281,13 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } - kfree(x); + xfrm_state_free(x); kfree(xp); return 0; free_state: - kfree(x); + xfrm_state_free(x); nomem: return err; } |