diff options
Diffstat (limited to 'net')
105 files changed, 906 insertions, 562 deletions
diff --git a/net/atm/svc.c b/net/atm/svc.c index db9794ec61d8..5589de7086af 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -318,7 +318,8 @@ out: return error; } -static int svc_accept(struct socket *sock, struct socket *newsock, int flags) +static int svc_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; @@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk); - error = svc_create(sock_net(sk), newsock, 0, 0); + error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index a8e42cedf1db..b7c486752b3a 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1320,7 +1320,8 @@ out_release: return err; } -static int ax25_accept(struct socket *sock, struct socket *newsock, int flags) +static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 7c3d994e90d8..71343d0fec94 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -2477,6 +2477,16 @@ static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface) batadv_iv_ogm_schedule(hard_iface); } +/** + * batadv_iv_init_sel_class - initialize GW selection class + * @bat_priv: the bat priv with all the soft interface information + */ +static void batadv_iv_init_sel_class(struct batadv_priv *bat_priv) +{ + /* set default TQ difference threshold to 20 */ + atomic_set(&bat_priv->gw.sel_class, 20); +} + static struct batadv_gw_node * batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) { @@ -2823,6 +2833,7 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .del_if = batadv_iv_ogm_orig_del_if, }, .gw = { + .init_sel_class = batadv_iv_init_sel_class, .get_best_gw_node = batadv_iv_gw_get_best_gw_node, .is_eligible = batadv_iv_gw_is_eligible, #ifdef CONFIG_BATMAN_ADV_DEBUGFS diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 0acd081dd286..a36c8e7291d6 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -668,6 +668,16 @@ err_ifinfo1: return ret; } +/** + * batadv_v_init_sel_class - initialize GW selection class + * @bat_priv: the bat priv with all the soft interface information + */ +static void batadv_v_init_sel_class(struct batadv_priv *bat_priv) +{ + /* set default throughput difference threshold to 5Mbps */ + atomic_set(&bat_priv->gw.sel_class, 50); +} + static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv, char *buff, size_t count) { @@ -1052,6 +1062,7 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = { .dump = batadv_v_orig_dump, }, .gw = { + .init_sel_class = batadv_v_init_sel_class, .store_sel_class = batadv_v_store_sel_class, .show_sel_class = batadv_v_show_sel_class, .get_best_gw_node = batadv_v_gw_get_best_gw_node, @@ -1092,9 +1103,6 @@ int batadv_v_mesh_init(struct batadv_priv *bat_priv) if (ret < 0) return ret; - /* set default throughput difference threshold to 5Mbps */ - atomic_set(&bat_priv->gw.sel_class, 50); - return 0; } diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 11a23fd6e1a0..8f964beaac28 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -404,7 +404,7 @@ out: * batadv_frag_create - create a fragment from skb * @skb: skb to create fragment from * @frag_head: header to use in new fragment - * @mtu: size of new fragment + * @fragment_size: size of new fragment * * Split the passed skb into two fragments: A new one with size matching the * passed mtu and the old one with the rest. The new skb contains data from the @@ -414,11 +414,11 @@ out: */ static struct sk_buff *batadv_frag_create(struct sk_buff *skb, struct batadv_frag_packet *frag_head, - unsigned int mtu) + unsigned int fragment_size) { struct sk_buff *skb_fragment; unsigned int header_size = sizeof(*frag_head); - unsigned int fragment_size = mtu - header_size; + unsigned int mtu = fragment_size + header_size; skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN); if (!skb_fragment) @@ -456,7 +456,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, struct sk_buff *skb_fragment; unsigned int mtu = neigh_node->if_incoming->net_dev->mtu; unsigned int header_size = sizeof(frag_header); - unsigned int max_fragment_size, max_packet_size; + unsigned int max_fragment_size, num_fragments; int ret; /* To avoid merge and refragmentation at next-hops we never send @@ -464,10 +464,15 @@ int batadv_frag_send_packet(struct sk_buff *skb, */ mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE); max_fragment_size = mtu - header_size; - max_packet_size = max_fragment_size * BATADV_FRAG_MAX_FRAGMENTS; + + if (skb->len == 0 || max_fragment_size == 0) + return -EINVAL; + + num_fragments = (skb->len - 1) / max_fragment_size + 1; + max_fragment_size = (skb->len - 1) / num_fragments + 1; /* Don't even try to fragment, if we need more than 16 fragments */ - if (skb->len > max_packet_size) { + if (num_fragments > BATADV_FRAG_MAX_FRAGMENTS) { ret = -EAGAIN; goto free_skb; } @@ -507,7 +512,8 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto put_primary_if; } - skb_fragment = batadv_frag_create(skb, &frag_header, mtu); + skb_fragment = batadv_frag_create(skb, &frag_header, + max_fragment_size); if (!skb_fragment) { ret = -ENOMEM; goto put_primary_if; diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 5db2e43e3775..33940c5c74a8 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -253,6 +253,11 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, */ void batadv_gw_init(struct batadv_priv *bat_priv) { + if (bat_priv->algo_ops->gw.init_sel_class) + bat_priv->algo_ops->gw.init_sel_class(bat_priv); + else + atomic_set(&bat_priv->gw.sel_class, 1); + batadv_tvlv_handler_register(bat_priv, batadv_gw_tvlv_ogm_handler_v1, NULL, BATADV_TVLV_GW, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5d099b2e6cfc..d042c99af028 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -819,7 +819,6 @@ static int batadv_softif_init_late(struct net_device *dev) atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0); #endif atomic_set(&bat_priv->gw.mode, BATADV_GW_MODE_OFF); - atomic_set(&bat_priv->gw.sel_class, 20); atomic_set(&bat_priv->gw.bandwidth_down, 100); atomic_set(&bat_priv->gw.bandwidth_up, 20); atomic_set(&bat_priv->orig_interval, 1000); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 66b25e410a41..246f21b4973b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1489,6 +1489,7 @@ struct batadv_algo_orig_ops { /** * struct batadv_algo_gw_ops - mesh algorithm callbacks (GW specific) + * @init_sel_class: initialize GW selection class (optional) * @store_sel_class: parse and stores a new GW selection class (optional) * @show_sel_class: prints the current GW selection class (optional) * @get_best_gw_node: select the best GW from the list of available nodes @@ -1499,6 +1500,7 @@ struct batadv_algo_orig_ops { * @dump: dump gateways to a netlink socket (optional) */ struct batadv_algo_gw_ops { + void (*init_sel_class)(struct batadv_priv *bat_priv); ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff, size_t count); ssize_t (*show_sel_class)(struct batadv_priv *bat_priv, char *buff); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f307b145ea54..507b80d59dec 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -301,7 +301,7 @@ done: } static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index aa1a814ceddc..ac3c650cb234 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -471,7 +471,8 @@ done: return err; } -static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags) +static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e4e9a2da1e7e..728e0c8dc8e7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -627,7 +627,7 @@ done: } static int sco_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 4f598dc2d916..6e08b7199dd7 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -106,7 +106,7 @@ static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br, struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; - WARN_ON_ONCE(!br_hash_lock_held(br)); + lockdep_assert_held_once(&br->hash_lock); rcu_read_lock(); fdb = fdb_find_rcu(head, addr, vid); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 236f34244dbe..013f2290bfa5 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,6 +30,7 @@ EXPORT_SYMBOL(br_should_route_hook); static int br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { + br_drop_fake_rtable(skb); return netif_receive_skb(skb); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 95087e6e8258..1f1e62095464 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv, } -/* PF_BRIDGE/LOCAL_IN ************************************************/ -/* The packet is locally destined, which requires a real - * dst_entry, so detach the fake one. On the way up, the - * packet would pass through PRE_ROUTING again (which already - * took place when the packet entered the bridge), but we - * register an IPv4 PRE_ROUTING 'sabotage' hook that will - * prevent this from happening. */ -static unsigned int br_nf_local_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - br_drop_fake_rtable(skb); - return NF_ACCEPT; -} - /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -721,18 +706,20 @@ static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct nf_bridge_info *nf_bridge; - unsigned int mtu_reserved; + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + unsigned int mtu, mtu_reserved; mtu_reserved = nf_bridge_mtu_reduction(skb); + mtu = skb->dev->mtu; - if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) { + if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) + mtu = nf_bridge->frag_max_size; + + if (skb_is_gso(skb) || skb->len + mtu_reserved <= mtu) { nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); } - nf_bridge = nf_bridge_info_get(skb); - /* This is wrong! We should preserve the original fragment * boundaries by preserving frag_list rather than refragmenting. */ @@ -908,12 +895,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = { .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_local_in, - .pf = NFPROTO_BRIDGE, - .hooknum = NF_BR_LOCAL_IN, - .priority = NF_BR_PRI_BRNF, - }, - { .hook = br_nf_forward_ip, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2288fca7756c..61368186edea 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -531,15 +531,6 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); -static inline bool br_hash_lock_held(struct net_bridge *br) -{ -#ifdef CONFIG_LOCKDEP - return lockdep_is_held(&br->hash_lock); -#else - return true; -#endif -} - /* br_forward.c */ enum br_pkt_type { BR_PKT_UNICAST, diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 464e88599b9d..108533859a53 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -230,6 +230,7 @@ enum { Opt_osdkeepalivetimeout, Opt_mount_timeout, Opt_osd_idle_ttl, + Opt_osd_request_timeout, Opt_last_int, /* int args above */ Opt_fsid, @@ -256,6 +257,7 @@ static match_table_t opt_tokens = { {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, {Opt_mount_timeout, "mount_timeout=%d"}, {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, + {Opt_osd_request_timeout, "osd_request_timeout=%d"}, /* int args above */ {Opt_fsid, "fsid=%s"}, {Opt_name, "name=%s"}, @@ -361,6 +363,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ @@ -473,6 +476,15 @@ ceph_parse_options(char *options, const char *dev_name, } opt->mount_timeout = msecs_to_jiffies(intval * 1000); break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (intval < 0 || intval > INT_MAX / 1000) { + pr_err("osd_request_timeout out of range\n"); + err = -EINVAL; + goto out; + } + opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); + break; case Opt_share: opt->flags &= ~CEPH_OPT_NOSHARE; @@ -557,6 +569,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) seq_printf(m, "osdkeepalivetimeout=%d,", jiffies_to_msecs(opt->osd_keepalive_timeout) / 1000); + if (opt->osd_request_timeout != CEPH_OSD_REQUEST_TIMEOUT_DEFAULT) + seq_printf(m, "osd_request_timeout=%d,", + jiffies_to_msecs(opt->osd_request_timeout) / 1000); /* drop redundant comma */ if (m->count != pos) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 38dcf1eb427d..f76bb3332613 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -7,6 +7,7 @@ #include <linux/kthread.h> #include <linux/net.h> #include <linux/nsproxy.h> +#include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/string.h> @@ -469,11 +470,16 @@ static int ceph_tcp_connect(struct ceph_connection *con) { struct sockaddr_storage *paddr = &con->peer_addr.in_addr; struct socket *sock; + unsigned int noio_flag; int ret; BUG_ON(con->sock); + + /* sock_create_kern() allocates with GFP_KERNEL */ + noio_flag = memalloc_noio_save(); ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); + memalloc_noio_restore(noio_flag); if (ret) return ret; sock->sk->sk_allocation = GFP_NOFS; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b65bbf9f45eb..e15ea9e4c495 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1709,6 +1709,8 @@ static void account_request(struct ceph_osd_request *req) req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); + + req->r_start_stamp = jiffies; } static void submit_request(struct ceph_osd_request *req, bool wrlocked) @@ -1789,6 +1791,14 @@ static void cancel_request(struct ceph_osd_request *req) ceph_osdc_put_request(req); } +static void abort_request(struct ceph_osd_request *req, int err) +{ + dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); + + cancel_map_check(req); + complete_request(req, err); +} + static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; @@ -2487,6 +2497,7 @@ static void handle_timeout(struct work_struct *work) container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; + unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; @@ -2502,15 +2513,23 @@ static void handle_timeout(struct work_struct *work) struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; - for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { + for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); + p = rb_next(p); /* abort_request() */ + if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } + if (opts->osd_request_timeout && + time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osd->o_osd); + abort_request(req, -ETIMEDOUT); + } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = @@ -2530,6 +2549,21 @@ static void handle_timeout(struct work_struct *work) list_move_tail(&osd->o_keepalive_item, &slow_osds); } + if (opts->osd_request_timeout) { + for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { + struct ceph_osd_request *req = + rb_entry(p, struct ceph_osd_request, r_node); + + p = rb_next(p); /* abort_request() */ + + if (time_before(req->r_start_stamp, expiry_cutoff)) { + pr_err_ratelimited("tid %llu on osd%d timeout\n", + req->r_tid, osdc->homeless_osd.o_osd); + abort_request(req, -ETIMEDOUT); + } + } + } + if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 6824c0ec8373..ffe9e904d4d1 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -390,9 +390,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable chooseleaf_stable = %d\n", c->chooseleaf_stable); - crush_finalize(c); - done: + crush_finalize(c); dout("crush_decode success\n"); return c; @@ -1380,7 +1379,6 @@ static int decode_new_up_state_weight(void **p, void *end, if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && (xorstate & CEPH_OSD_EXISTS)) { pr_info("osd%d does not exist\n", osd); - map->osd_weight[osd] = CEPH_OSD_IN; ret = set_primary_affinity(map, osd, CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); if (ret) diff --git a/net/core/dev.c b/net/core/dev.c index 8637b2b71f3d..7869ae3837ca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1304,6 +1304,7 @@ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 3945821e9c1f..65ea0ff4017c 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -953,7 +953,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; - if (!list_empty(&dev_net(dev)->exit_list)) + if (!atomic_read(&dev_net(dev)->count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); @@ -1371,7 +1371,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; - if (!list_empty(&dev_net(dev)->exit_list)) + if (!atomic_read(&dev_net(dev)->count)) queue->kobj.uevent_suppress = 1; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); @@ -1558,7 +1558,7 @@ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &(ndev->dev); - if (!list_empty(&dev_net(ndev)->exit_list)) + if (!atomic_read(&dev_net(ndev)->count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 6ae56037bb13..029a61ac6cdd 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -71,27 +71,17 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n) return 0; } -static void update_classid(struct cgroup_subsys_state *css, void *v) +static void cgrp_attach(struct cgroup_taskset *tset) { - struct css_task_iter it; + struct cgroup_subsys_state *css; struct task_struct *p; - css_task_iter_start(css, &it); - while ((p = css_task_iter_next(&it))) { + cgroup_taskset_for_each(p, css, tset) { task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, v); + iterate_fd(p->files, 0, update_classid_sock, + (void *)(unsigned long)css_cls_state(css)->classid); task_unlock(p); } - css_task_iter_end(&it); -} - -static void cgrp_attach(struct cgroup_taskset *tset) -{ - struct cgroup_subsys_state *css; - - cgroup_taskset_first(tset, &css); - update_classid(css, - (void *)(unsigned long)css_cls_state(css)->classid); } static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) @@ -103,12 +93,22 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, u64 value) { struct cgroup_cls_state *cs = css_cls_state(css); + struct css_task_iter it; + struct task_struct *p; cgroup_sk_alloc_disable(); cs->classid = (u32)value; - update_classid(css, (void *)(unsigned long)cs->classid); + css_task_iter_start(css, &it); + while ((p = css_task_iter_next(&it))) { + task_lock(p); + iterate_fd(p->files, 0, update_classid_sock, + (void *)(unsigned long)cs->classid); + task_unlock(p); + } + css_task_iter_end(&it); + return 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f3557958e9bf..9f781092fda9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3694,6 +3694,15 @@ static void sock_rmem_free(struct sk_buff *skb) atomic_sub(skb->truesize, &sk->sk_rmem_alloc); } +static void skb_set_err_queue(struct sk_buff *skb) +{ + /* pkt_type of skbs received on local sockets is never PACKET_OUTGOING. + * So, it is safe to (mis)use it to mark skbs on the error queue. + */ + skb->pkt_type = PACKET_OUTGOING; + BUILD_BUG_ON(PACKET_OUTGOING == 0); +} + /* * Note: We dont mem charge error packets (no sk_forward_alloc changes) */ @@ -3707,6 +3716,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); + skb_set_err_queue(skb); /* before exiting rcu section, make sure dst is refcounted */ skb_dst_force(skb); @@ -3783,16 +3793,20 @@ EXPORT_SYMBOL(skb_clone_sk); static void __skb_complete_tx_timestamp(struct sk_buff *skb, struct sock *sk, - int tstype) + int tstype, + bool opt_stats) { struct sock_exterr_skb *serr; int err; + BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb)); + serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = tstype; + serr->opt_stats = opt_stats; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk->sk_protocol == IPPROTO_TCP && @@ -3828,13 +3842,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, if (!skb_may_tx_timestamp(sk, false)) return; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - *skb_hwtstamps(skb) = *hwtstamps; - __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND); - - sock_put(sk); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + *skb_hwtstamps(skb) = *hwtstamps; + __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); + sock_put(sk); + } } EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); @@ -3843,7 +3858,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, struct sock *sk, int tstype) { struct sk_buff *skb; - bool tsonly; + bool tsonly, opt_stats = false; if (!sk) return; @@ -3856,9 +3871,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, #ifdef CONFIG_INET if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) + sk->sk_type == SOCK_STREAM) { skb = tcp_get_timestamping_opt_stats(sk); - else + opt_stats = true; + } else #endif skb = alloc_skb(0, GFP_ATOMIC); } else { @@ -3877,7 +3893,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, else skb->tstamp = ktime_get_real(); - __skb_complete_tx_timestamp(skb, sk, tstype); + __skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } EXPORT_SYMBOL_GPL(__skb_tstamp_tx); @@ -3893,7 +3909,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) { struct sock *sk = skb->sk; struct sock_exterr_skb *serr; - int err; + int err = 1; skb->wifi_acked_valid = 1; skb->wifi_acked = acked; @@ -3903,14 +3919,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; - /* take a reference to prevent skb_orphan() from freeing the socket */ - sock_hold(sk); - - err = sock_queue_err_skb(sk, skb); + /* Take a reference to prevent skb_orphan() from freeing the socket, + * but only if the socket refcount is not zero. + */ + if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + err = sock_queue_err_skb(sk, skb); + sock_put(sk); + } if (err) kfree_skb(skb); - - sock_put(sk); } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); diff --git a/net/core/sock.c b/net/core/sock.c index f6fd79f33097..2c4f574168fb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -197,66 +197,55 @@ EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have - * one slock key per address family: + * one slock key per address family and separate keys for internal and + * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; +static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ + +#define _sock_locks(x) \ + x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ + x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ + x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ + x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ + x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ + x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ + x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ + x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ + x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ + x "27" , x "28" , x "AF_CAN" , \ + x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ + x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ + x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ + x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ + x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + static const char *const af_family_key_strings[AF_MAX+1] = { - "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , - "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", - "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , - "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" , - "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , - "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , - "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , - "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , - "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , - "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , - "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , - "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , - "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , - "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX" + _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { - "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , - "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", - "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , - "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" , - "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , - "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , - "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , - "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" , - "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , - "slock-27" , "slock-28" , "slock-AF_CAN" , - "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , - "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , - "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , - "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX" + _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { - "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , - "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", - "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , - "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" , - "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" , - "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" , - "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , - "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , - "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , - "clock-27" , "clock-28" , "clock-AF_CAN" , - "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , - "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , - "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , - "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX" + _sock_locks("clock-") +}; + +static const char *const af_family_kern_key_strings[AF_MAX+1] = { + _sock_locks("k-sk_lock-") +}; +static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { + _sock_locks("k-slock-") +}; +static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { + _sock_locks("k-clock-") }; /* @@ -264,6 +253,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; +static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across @@ -1293,7 +1283,16 @@ lenout: */ static inline void sock_lock_init(struct sock *sk) { - sock_lock_init_class_and_name(sk, + if (sk->sk_kern_sock) + sock_lock_init_class_and_name( + sk, + af_family_kern_slock_key_strings[sk->sk_family], + af_family_kern_slock_keys + sk->sk_family, + af_family_kern_key_strings[sk->sk_family], + af_family_kern_keys + sk->sk_family); + else + sock_lock_init_class_and_name( + sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], @@ -1399,6 +1398,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; + sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) @@ -1442,6 +1442,11 @@ static void __sk_destruct(struct rcu_head *head) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + if (sk->sk_peer_cred) put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); @@ -1539,6 +1544,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) is_charged = sk_filter_charge(newsk, filter); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { + /* We need to make sure that we don't uncharge the new + * socket if we couldn't charge it in the first place + * as otherwise we uncharge the parent's filter. + */ + if (!is_charged) + RCU_INIT_POINTER(newsk->sk_filter, NULL); sk_free_unlock_clone(newsk); newsk = NULL; goto out; @@ -2277,7 +2288,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2) } EXPORT_SYMBOL(sock_no_socketpair); -int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) +int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { return -EOPNOTSUPP; } @@ -2481,7 +2493,14 @@ void sock_init_data(struct socket *sock, struct sock *sk) } rwlock_init(&sk->sk_callback_lock); - lockdep_set_class_and_name(&sk->sk_callback_lock, + if (sk->sk_kern_sock) + lockdep_set_class_and_name( + &sk->sk_callback_lock, + af_kern_callback_keys + sk->sk_family, + af_family_kern_clock_key_strings[sk->sk_family]); + else + lockdep_set_class_and_name( + &sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); @@ -2779,11 +2798,6 @@ void sk_common_release(struct sock *sk) sk_refcnt_debug_release(sk); - if (sk->sk_frag.page) { - put_page(sk->sk_frag.page); - sk->sk_frag.page = NULL; - } - sock_put(sk); } EXPORT_SYMBOL(sk_common_release); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index f053198e730c..5e3a7302f774 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk) for (i = 0; i < hc->tx_seqbufc; i++) kfree(hc->tx_seqbuf[i]); hc->tx_seqbufc = 0; + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 409d0cfd3447..b99168b0fabf 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) switch (type) { case ICMP_REDIRECT: - dccp_do_redirect(skb, sk); + if (!sock_owned_by_user(sk)) + dccp_do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 233b57367758..d9b6a4e403e7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index e267e6f4c9a5..abd07a443219 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -142,6 +142,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, struct dccp_request_sock *dreq = dccp_rsk(req); bool own_req; + /* TCP/DCCP listeners became lockless. + * DCCP stores complex state in its request_sock, so we need + * a protection for them, now this code runs without being protected + * by the parent (listener) lock. + */ + spin_lock_bh(&dreq->dreq_lock); + /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { @@ -156,7 +163,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ - return NULL; + goto out; } DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR; @@ -182,20 +189,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, req, &own_req); - if (!child) - goto listen_overflow; - - return inet_csk_complete_hashdance(sk, child, req, own_req); + if (child) { + child = inet_csk_complete_hashdance(sk, child, req, own_req); + goto out; + } -listen_overflow: - dccp_pr_debug("listen_overflow!\n"); DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); inet_csk_reqsk_queue_drop(sk, req); - return NULL; +out: + spin_unlock_bh(&dreq->dreq_lock); + return child; } EXPORT_SYMBOL_GPL(dccp_check_req); @@ -246,6 +253,7 @@ int dccp_reqsk_init(struct request_sock *req, { struct dccp_request_sock *dreq = dccp_rsk(req); + spin_lock_init(&dreq->dreq_lock); inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport; inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport); inet_rsk(req)->acked = 0; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e6e79eda9763..7de5b40a5d0d 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1070,7 +1070,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) return skb == NULL ? ERR_PTR(err) : skb; } -static int dn_accept(struct socket *sock, struct socket *newsock, int flags) +static int dn_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct sk_buff *skb = NULL; @@ -1099,7 +1100,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) cb = DN_SKB_CB(skb); sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0); + newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern); if (newsk == NULL) { release_sock(sk); kfree_skb(skb); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 602d40f43687..6b1fc6e4278e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect); * Accept a pending connection. The TCP layer now gives BSD semantics. */ -int inet_accept(struct socket *sock, struct socket *newsock, int flags) +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk1 = sock->sk; int err = -EINVAL; - struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err); + struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern); if (!sk2) goto do_err; @@ -1487,8 +1488,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff) int proto = iph->protocol; int err = -ENOSYS; - if (skb->encapsulation) + if (skb->encapsulation) { + skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); + } csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 42bfd08109dd..8f2133ffc2ff 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1083,7 +1083,8 @@ static void nl_fib_input(struct sk_buff *skb) net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); - if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len || + if (skb->len < nlmsg_total_size(sizeof(*frn)) || + skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b4d5980ade3b..5e313c1ac94f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) /* * This will accept the next outstanding connection. */ -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index bbe7f72db9c1..b3cdeec85f1f 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -198,6 +198,7 @@ static void ip_expire(unsigned long arg) qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); + rcu_read_lock(); spin_lock(&qp->q.lock); if (qp->q.flags & INET_FRAG_COMPLETE) @@ -207,7 +208,7 @@ static void ip_expire(unsigned long arg) __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); if (!inet_frag_evicting(&qp->q)) { - struct sk_buff *head = qp->q.fragments; + struct sk_buff *clone, *head = qp->q.fragments; const struct iphdr *iph; int err; @@ -216,32 +217,40 @@ static void ip_expire(unsigned long arg) if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments) goto out; - rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) - goto out_rcu_unlock; + goto out; + /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); if (err) - goto out_rcu_unlock; + goto out; /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ if (frag_expire_skip_icmp(qp->user) && (skb_rtable(head)->rt_type != RTN_LOCAL)) - goto out_rcu_unlock; + goto out; + + clone = skb_clone(head, GFP_ATOMIC); /* Send an ICMP "Fragment Reassembly Timeout" message. */ - icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); -out_rcu_unlock: - rcu_read_unlock(); + if (clone) { + spin_unlock(&qp->q.lock); + icmp_send(clone, ICMP_TIME_EXCEEDED, + ICMP_EXC_FRAGTIME, 0); + consume_skb(clone); + goto out_rcu_unlock; + } } out: spin_unlock(&qp->q.lock); +out_rcu_unlock: + rcu_read_unlock(); ipq_put(qp); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 737ce826d7ec..7a3fd25e8913 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index bc1486f2c064..2e14ed11a35c 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -165,6 +165,10 @@ static unsigned int ipv4_conntrack_local(void *priv, if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; + + if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */ + return NF_ACCEPT; + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); } diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index f8aad03d674b..6f5e8d01b876 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -255,11 +255,6 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, /* maniptype == SRC for postrouting. */ enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); - /* We never see fragments: conntrack defrags on pre-routing - * and local-out, and nf_nat_out protects post-routing. - */ - NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb))); - ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index a0ea8aad1bf1..f18677277119 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -26,10 +26,10 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); } regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt), &range, nft_out(pkt)); diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c index 1650ed23c15d..5120be1d3118 100644 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ b/net/ipv4/netfilter/nft_redir_ipv4.c @@ -26,10 +26,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr, memset(&mr, 0, sizeof(mr)); if (priv->sreg_proto_min) { - mr.range[0].min.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - mr.range[0].max.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + mr.range[0].min.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + mr.range[0].max.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cf4555581282..1e319a525d51 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2770,7 +2770,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); - u32 now = tcp_time_stamp, intv; + u32 now, intv; u64 rate64; bool slow; u32 rate; @@ -2839,6 +2839,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_retrans = tp->retrans_out; info->tcpi_fackets = tp->fackets_out; + now = tcp_time_stamp; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 39c393cc0fd3..c43119726a62 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5541,6 +5541,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); + icsk->icsk_ack.lrcvtime = tcp_time_stamp; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -5759,7 +5760,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * to stand against the temptation 8) --ANK */ inet_csk_schedule_ack(sk); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; tcp_enter_quickack_mode(sk); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9a89b8deafae..575e19dcc017 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -279,10 +279,13 @@ EXPORT_SYMBOL(tcp_v4_connect); */ void tcp_v4_mtu_reduced(struct sock *sk) { - struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); - u32 mtu = tcp_sk(sk)->mtu_info; + struct dst_entry *dst; + u32 mtu; + if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + return; + mtu = tcp_sk(sk)->mtu_info; dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -428,7 +431,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) switch (type) { case ICMP_REDIRECT: - do_redirect(icmp_skb, sk); + if (!sock_owned_by_user(sk)) + do_redirect(icmp_skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7e16243cdb58..65c0f3d13eca 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -460,6 +460,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; + newicsk->icsk_ack.lrcvtime = tcp_time_stamp; newtp->packets_out = 0; newtp->retrans_out = 0; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 40d893556e67..b2ab411c6d37 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk) sk_mem_reclaim_partial(sk); - if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); int event; - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 04db40620ea6..a9a9553ee63d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -920,12 +920,12 @@ static int __init inet6_init(void) err = register_pernet_subsys(&inet6_net_ops); if (err) goto register_pernet_fail; - err = icmpv6_init(); - if (err) - goto icmp_fail; err = ip6_mr_init(); if (err) goto ipmr_fail; + err = icmpv6_init(); + if (err) + goto icmp_fail; err = ndisc_init(); if (err) goto ndisc_fail; @@ -1061,10 +1061,10 @@ igmp_fail: ndisc_cleanup(); ndisc_fail: ip6_mr_cleanup(); -ipmr_fail: - icmpv6_cleanup(); icmp_fail: unregister_pernet_subsys(&inet6_net_ops); +ipmr_fail: + icmpv6_cleanup(); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e4266746e4a2..d4bf2c68a545 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -923,6 +923,8 @@ add: ins = &rt->dst.rt6_next; iter = *ins; while (iter) { + if (iter->rt6i_metric > rt->rt6i_metric) + break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->dst.rt6_next; fib6_purge_rt(iter, fn, info->nl_net); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 0838e6d01d2e..93e58a5e1837 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff) struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff); int err = -ENOSYS; - if (skb->encapsulation) + if (skb->encapsulation) { + skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6)); skb_set_inner_network_header(skb, nhoff); + } iph->payload_len = htons(skb->len - nhoff - sizeof(*iph)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 528b3c1f3fde..58f6288e9ba5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -768,13 +768,14 @@ slow_path: * Fragment the datagram. */ - *prevhdr = NEXTHDR_FRAGMENT; troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while (left > 0) { + u8 *fragnexthdr_offset; + len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) @@ -819,6 +820,10 @@ slow_path: */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); + fragnexthdr_offset = skb_network_header(frag); + fragnexthdr_offset += prevhdr - skb_network_header(skb); + *fragnexthdr_offset = NEXTHDR_FRAGMENT; + /* * Build fragment header. */ @@ -1385,7 +1390,7 @@ emsgsize: if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && + (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 644ba59fbd9d..3d8a3b63b4fd 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -485,11 +485,15 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (!skb->ignore_df && skb->len > mtu) { skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu); - if (skb->protocol == htons(ETH_P_IPV6)) + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - else + } else { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + } return -EMSGSIZE; } diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index 6c5b5b1830a7..4146536e9c15 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -27,10 +27,10 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); } regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, nft_out(pkt)); diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index f5ac080fc084..a27e424f690d 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -26,10 +26,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min], - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max], + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 229bfcc451ef..9db1418993f2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3299,7 +3299,6 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt) nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16) /* RTA_GATEWAY */ - + nla_total_size(4) /* RTA_OIF */ + lwtunnel_get_encap_size(rt->dst.lwtstate); nexthop_len *= rt->rt6i_nsiblings; @@ -3323,7 +3322,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt) } static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, - unsigned int *flags) + unsigned int *flags, bool skip_oif) { if (!netif_running(rt->dst.dev) || !netif_carrier_ok(rt->dst.dev)) { *flags |= RTNH_F_LINKDOWN; @@ -3336,7 +3335,8 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, goto nla_put_failure; } - if (rt->dst.dev && + /* not needed for multipath encoding b/c it has a rtnexthop struct */ + if (!skip_oif && rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; @@ -3350,6 +3350,7 @@ nla_put_failure: return -EMSGSIZE; } +/* add multipath next hop */ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) { struct rtnexthop *rtnh; @@ -3362,7 +3363,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) rtnh->rtnh_hops = 0; rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0; - if (rt6_nexthop_info(skb, rt, &flags) < 0) + if (rt6_nexthop_info(skb, rt, &flags, true) < 0) goto nla_put_failure; rtnh->rtnh_flags = flags; @@ -3422,6 +3423,8 @@ static int rt6_fill_node(struct net *net, } else if (rt->rt6i_flags & RTF_LOCAL) rtm->rtm_type = RTN_LOCAL; + else if (rt->rt6i_flags & RTF_ANYCAST) + rtm->rtm_type = RTN_ANYCAST; else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) rtm->rtm_type = RTN_LOCAL; else @@ -3515,7 +3518,7 @@ static int rt6_fill_node(struct net *net, nla_nest_end(skb, mp); } else { - if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags) < 0) + if (rt6_nexthop_info(skb, rt, &rtm->rtm_flags, false) < 0) goto nla_put_failure; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 60a5295a7de6..49fa2e8c3fa9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -391,10 +391,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, np = inet6_sk(sk); if (type == NDISC_REDIRECT) { - struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + if (!sock_owned_by_user(sk)) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); - if (dst) - dst->ops->redirect(dst, sk, skb); + if (dst) + dst->ops->redirect(dst, sk, skb); + } goto out; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4e4c401e3bc6..e28082f0a307 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1035,6 +1035,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.hlimit = -1; ipc6.tclass = -1; ipc6.dontfrag = -1; + sockc.tsflags = sk->sk_tsflags; /* destination address check */ if (sin6) { @@ -1159,7 +1160,6 @@ do_udp_sendmsg: fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; - sockc.tsflags = sk->sk_tsflags; if (msg->msg_controllen) { opt = &opt_space; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 81adc29a448d..8d77ad5cadaf 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -828,7 +828,8 @@ out: * Wait for incoming connection * */ -static int irda_accept(struct socket *sock, struct socket *newsock, int flags) +static int irda_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct irda_sock *new, *self = irda_sk(sk); @@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) struct sk_buff *skb = NULL; int err; - err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0); + err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern); if (err) return err; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 89bbde1081ce..84de7b6326dc 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -938,7 +938,7 @@ done: /* Accept a pending connection */ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *nsk; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 06186d608a27..cb4fff785cbf 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @flags: User specified operational flags. + * @kern: If the socket is kernel internal * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ -static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags) +static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 3818686182b2..6414079aa729 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1269,6 +1269,8 @@ static void mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); + unsigned int nh_flags = RTNH_F_DEAD | RTNH_F_LINKDOWN; + unsigned int alive; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); @@ -1278,9 +1280,11 @@ static void mpls_ifdown(struct net_device *dev, int event) if (!rt) continue; + alive = 0; change_nexthops(rt) { if (rtnl_dereference(nh->nh_dev) != dev) - continue; + goto next; + switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: @@ -1288,12 +1292,16 @@ static void mpls_ifdown(struct net_device *dev, int event) /* fall through */ case NETDEV_CHANGE: nh->nh_flags |= RTNH_F_LINKDOWN; - ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1; break; } if (event == NETDEV_UNREGISTER) RCU_INIT_POINTER(nh->nh_dev, NULL); +next: + if (!(nh->nh_flags & nh_flags)) + alive++; } endfor_nexthops(rt); + + WRITE_ONCE(rt->rt_nhn_alive, alive); } } @@ -2028,6 +2036,7 @@ static void mpls_net_exit(struct net *net) for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); + mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 071b97fcbefb..ffb78e5f7b70 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -181,7 +181,11 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; seqcount_t nf_conntrack_generation __read_mostly; -DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked); +/* nf_conn must be 8 bytes aligned, as the 3 LSB bits are used + * for the nfctinfo. We cheat by (ab)using the PER CPU cache line + * alignment to enforce this. + */ +DEFINE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked); EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); static unsigned int nf_conntrack_hash_rnd __read_mostly; diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 31d358691af0..804e8a0ab36e 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -33,8 +33,16 @@ sctp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { sctp_sctphdr_t *hdr; + int hdrsize = 8; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + /* This could be an inner header returned in imcp packet; in such + * cases we cannot update the checksum field since it is outside + * of the 8 bytes of transport layer headers we are guaranteed. + */ + if (skb->len >= hdroff + sizeof(*hdr)) + hdrsize = sizeof(*hdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); @@ -47,6 +55,9 @@ sctp_manip_pkt(struct sk_buff *skb, hdr->dest = tuple->dst.u.sctp.port; } + if (hdrsize < sizeof(*hdr)) + return true; + if (skb->ip_summed != CHECKSUM_PARTIAL) { hdr->checksum = sctp_compute_cksum(skb, hdroff); skb->ip_summed = CHECKSUM_NONE; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5e0ccfd5bb37..434c739dfeca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3145,7 +3145,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, iter.count = 0; iter.err = 0; iter.fn = nf_tables_bind_check_setelem; - iter.flush = false; set->ops->walk(ctx, set, &iter); if (iter.err < 0) @@ -3399,7 +3398,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.iter.count = 0; args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; - args.iter.flush = false; set->ops->walk(&ctx, set, &args.iter); nla_nest_end(skb, nest); @@ -3963,7 +3961,6 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct nft_set_iter iter = { .genmask = genmask, .fn = nft_flush_set, - .flush = true, }; set->ops->walk(&ctx, set, &iter); @@ -5114,7 +5111,6 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, iter.count = 0; iter.err = 0; iter.fn = nf_tables_loop_check_setelem; - iter.flush = false; set->ops->walk(ctx, set, &iter); if (iter.err < 0) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bf548a7a71ec..0264258c46fe 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -83,7 +83,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_CT_DIRECTION: - *dest = CTINFO2DIR(ctinfo); + nft_reg_store8(dest, CTINFO2DIR(ctinfo)); return; case NFT_CT_STATUS: *dest = ct->status; @@ -151,20 +151,22 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; } case NFT_CT_L3PROTOCOL: - *dest = nf_ct_l3num(ct); + nft_reg_store8(dest, nf_ct_l3num(ct)); return; case NFT_CT_PROTOCOL: - *dest = nf_ct_protonum(ct); + nft_reg_store8(dest, nf_ct_protonum(ct)); return; #ifdef CONFIG_NF_CONNTRACK_ZONES case NFT_CT_ZONE: { const struct nf_conntrack_zone *zone = nf_ct_zone(ct); + u16 zoneid; if (priv->dir < IP_CT_DIR_MAX) - *dest = nf_ct_zone_id(zone, priv->dir); + zoneid = nf_ct_zone_id(zone, priv->dir); else - *dest = zone->id; + zoneid = zone->id; + nft_reg_store16(dest, zoneid); return; } #endif @@ -183,10 +185,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr, nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); return; case NFT_CT_PROTO_SRC: - *dest = (__force __u16)tuple->src.u.all; + nft_reg_store16(dest, (__force u16)tuple->src.u.all); return; case NFT_CT_PROTO_DST: - *dest = (__force __u16)tuple->dst.u.all; + nft_reg_store16(dest, (__force u16)tuple->dst.u.all); return; default: break; @@ -205,7 +207,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, const struct nft_ct *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; enum ip_conntrack_info ctinfo; - u16 value = regs->data[priv->sreg]; + u16 value = nft_reg_load16(®s->data[priv->sreg]); struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); @@ -542,7 +544,8 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, case IP_CT_DIR_REPLY: break; default: - return -EINVAL; + err = -EINVAL; + goto err1; } } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e1f5ca9b423b..7b60e01f38ff 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -45,16 +45,15 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->len; break; case NFT_META_PROTOCOL: - *dest = 0; - *(__be16 *)dest = skb->protocol; + nft_reg_store16(dest, (__force u16)skb->protocol); break; case NFT_META_NFPROTO: - *dest = nft_pf(pkt); + nft_reg_store8(dest, nft_pf(pkt)); break; case NFT_META_L4PROTO: if (!pkt->tprot_set) goto err; - *dest = pkt->tprot; + nft_reg_store8(dest, pkt->tprot); break; case NFT_META_PRIORITY: *dest = skb->priority; @@ -85,14 +84,12 @@ void nft_meta_get_eval(const struct nft_expr *expr, case NFT_META_IIFTYPE: if (in == NULL) goto err; - *dest = 0; - *(u16 *)dest = in->type; + nft_reg_store16(dest, in->type); break; case NFT_META_OIFTYPE: if (out == NULL) goto err; - *dest = 0; - *(u16 *)dest = out->type; + nft_reg_store16(dest, out->type); break; case NFT_META_SKUID: sk = skb_to_full_sk(skb); @@ -142,19 +139,19 @@ void nft_meta_get_eval(const struct nft_expr *expr, #endif case NFT_META_PKTTYPE: if (skb->pkt_type != PACKET_LOOPBACK) { - *dest = skb->pkt_type; + nft_reg_store8(dest, skb->pkt_type); break; } switch (nft_pf(pkt)) { case NFPROTO_IPV4: if (ipv4_is_multicast(ip_hdr(skb)->daddr)) - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); else - *dest = PACKET_BROADCAST; + nft_reg_store8(dest, PACKET_BROADCAST); break; case NFPROTO_IPV6: - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); break; case NFPROTO_NETDEV: switch (skb->protocol) { @@ -168,14 +165,14 @@ void nft_meta_get_eval(const struct nft_expr *expr, goto err; if (ipv4_is_multicast(iph->daddr)) - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); else - *dest = PACKET_BROADCAST; + nft_reg_store8(dest, PACKET_BROADCAST); break; } case htons(ETH_P_IPV6): - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); break; default: WARN_ON_ONCE(1); @@ -230,7 +227,9 @@ void nft_meta_set_eval(const struct nft_expr *expr, { const struct nft_meta *meta = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; - u32 value = regs->data[meta->sreg]; + u32 *sreg = ®s->data[meta->sreg]; + u32 value = *sreg; + u8 pkt_type; switch (meta->key) { case NFT_META_MARK: @@ -240,9 +239,12 @@ void nft_meta_set_eval(const struct nft_expr *expr, skb->priority = value; break; case NFT_META_PKTTYPE: - if (skb->pkt_type != value && - skb_pkt_type_ok(value) && skb_pkt_type_ok(skb->pkt_type)) - skb->pkt_type = value; + pkt_type = nft_reg_load8(sreg); + + if (skb->pkt_type != pkt_type && + skb_pkt_type_ok(pkt_type) && + skb_pkt_type_ok(skb->pkt_type)) + skb->pkt_type = pkt_type; break; case NFT_META_NFTRACE: skb->nf_trace = !!value; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 19a7bf3236f9..439e0bd152a0 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr, } if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 152d226552c1..8ebbc2940f4c 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -15,6 +15,11 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +struct nft_bitmap_elem { + struct list_head head; + struct nft_set_ext ext; +}; + /* This bitmap uses two bits to represent one element. These two bits determine * the element state in the current and the future generation. * @@ -41,13 +46,22 @@ * restore its previous state. */ struct nft_bitmap { - u16 bitmap_size; - u8 bitmap[]; + struct list_head list; + u16 bitmap_size; + u8 bitmap[]; }; -static inline void nft_bitmap_location(u32 key, u32 *idx, u32 *off) +static inline void nft_bitmap_location(const struct nft_set *set, + const void *key, + u32 *idx, u32 *off) { - u32 k = (key << 1); + u32 k; + + if (set->klen == 2) + k = *(u16 *)key; + else + k = *(u8 *)key; + k <<= 1; *idx = k / BITS_PER_BYTE; *off = k % BITS_PER_BYTE; @@ -69,26 +83,48 @@ static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, u8 genmask = nft_genmask_cur(net); u32 idx, off; - nft_bitmap_location(*key, &idx, &off); + nft_bitmap_location(set, key, &idx, &off); return nft_bitmap_active(priv->bitmap, idx, off, genmask); } +static struct nft_bitmap_elem * +nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this, + u8 genmask) +{ + const struct nft_bitmap *priv = nft_set_priv(set); + struct nft_bitmap_elem *be; + + list_for_each_entry_rcu(be, &priv->list, head) { + if (memcmp(nft_set_ext_key(&be->ext), + nft_set_ext_key(&this->ext), set->klen) || + !nft_set_elem_active(&be->ext, genmask)) + continue; + + return be; + } + return NULL; +} + static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **_ext) + struct nft_set_ext **ext) { struct nft_bitmap *priv = nft_set_priv(set); - struct nft_set_ext *ext = elem->priv; + struct nft_bitmap_elem *new = elem->priv, *be; u8 genmask = nft_genmask_next(net); u32 idx, off; - nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); - if (nft_bitmap_active(priv->bitmap, idx, off, genmask)) + be = nft_bitmap_elem_find(set, new, genmask); + if (be) { + *ext = &be->ext; return -EEXIST; + } + nft_bitmap_location(set, nft_set_ext_key(&new->ext), &idx, &off); /* Enter 01 state. */ priv->bitmap[idx] |= (genmask << off); + list_add_tail_rcu(&new->head, &priv->list); return 0; } @@ -98,13 +134,14 @@ static void nft_bitmap_remove(const struct net *net, const struct nft_set_elem *elem) { struct nft_bitmap *priv = nft_set_priv(set); - struct nft_set_ext *ext = elem->priv; + struct nft_bitmap_elem *be = elem->priv; u8 genmask = nft_genmask_next(net); u32 idx, off; - nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 00 state. */ priv->bitmap[idx] &= ~(genmask << off); + list_del_rcu(&be->head); } static void nft_bitmap_activate(const struct net *net, @@ -112,74 +149,52 @@ static void nft_bitmap_activate(const struct net *net, const struct nft_set_elem *elem) { struct nft_bitmap *priv = nft_set_priv(set); - struct nft_set_ext *ext = elem->priv; + struct nft_bitmap_elem *be = elem->priv; u8 genmask = nft_genmask_next(net); u32 idx, off; - nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 11 state. */ priv->bitmap[idx] |= (genmask << off); + nft_set_elem_change_active(net, set, &be->ext); } static bool nft_bitmap_flush(const struct net *net, - const struct nft_set *set, void *ext) + const struct nft_set *set, void *_be) { struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); + struct nft_bitmap_elem *be = _be; u32 idx, off; - nft_bitmap_location(nft_set_ext_key(ext)->data[0], &idx, &off); + nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 10 state, similar to deactivation. */ priv->bitmap[idx] &= ~(genmask << off); + nft_set_elem_change_active(net, set, &be->ext); return true; } -static struct nft_set_ext *nft_bitmap_ext_alloc(const struct nft_set *set, - const struct nft_set_elem *elem) -{ - struct nft_set_ext_tmpl tmpl; - struct nft_set_ext *ext; - - nft_set_ext_prepare(&tmpl); - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); - - ext = kzalloc(tmpl.len, GFP_KERNEL); - if (!ext) - return NULL; - - nft_set_ext_init(ext, &tmpl); - memcpy(nft_set_ext_key(ext), elem->key.val.data, set->klen); - - return ext; -} - static void *nft_bitmap_deactivate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_bitmap *priv = nft_set_priv(set); + struct nft_bitmap_elem *this = elem->priv, *be; u8 genmask = nft_genmask_next(net); - struct nft_set_ext *ext; - u32 idx, off, key = 0; - - memcpy(&key, elem->key.val.data, set->klen); - nft_bitmap_location(key, &idx, &off); + u32 idx, off; - if (!nft_bitmap_active(priv->bitmap, idx, off, genmask)) - return NULL; + nft_bitmap_location(set, elem->key.val.data, &idx, &off); - /* We have no real set extension since this is a bitmap, allocate this - * dummy object that is released from the commit/abort path. - */ - ext = nft_bitmap_ext_alloc(set, elem); - if (!ext) + be = nft_bitmap_elem_find(set, this, genmask); + if (!be) return NULL; /* Enter 10 state. */ priv->bitmap[idx] &= ~(genmask << off); + nft_set_elem_change_active(net, set, &be->ext); - return ext; + return be; } static void nft_bitmap_walk(const struct nft_ctx *ctx, @@ -187,47 +202,23 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, struct nft_set_iter *iter) { const struct nft_bitmap *priv = nft_set_priv(set); - struct nft_set_ext_tmpl tmpl; + struct nft_bitmap_elem *be; struct nft_set_elem elem; - struct nft_set_ext *ext; - int idx, off; - u16 key; - - nft_set_ext_prepare(&tmpl); - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); - - for (idx = 0; idx < priv->bitmap_size; idx++) { - for (off = 0; off < BITS_PER_BYTE; off += 2) { - if (iter->count < iter->skip) - goto cont; - - if (!nft_bitmap_active(priv->bitmap, idx, off, - iter->genmask)) - goto cont; - - ext = kzalloc(tmpl.len, GFP_KERNEL); - if (!ext) { - iter->err = -ENOMEM; - return; - } - nft_set_ext_init(ext, &tmpl); - key = ((idx * BITS_PER_BYTE) + off) >> 1; - memcpy(nft_set_ext_key(ext), &key, set->klen); - - elem.priv = ext; - iter->err = iter->fn(ctx, set, iter, &elem); - - /* On set flush, this dummy extension object is released - * from the commit/abort path. - */ - if (!iter->flush) - kfree(ext); - - if (iter->err < 0) - return; + + list_for_each_entry_rcu(be, &priv->list, head) { + if (iter->count < iter->skip) + goto cont; + if (!nft_set_elem_active(&be->ext, iter->genmask)) + goto cont; + + elem.priv = be; + + iter->err = iter->fn(ctx, set, iter, &elem); + + if (iter->err < 0) + return; cont: - iter->count++; - } + iter->count++; } } @@ -258,6 +249,7 @@ static int nft_bitmap_init(const struct nft_set *set, { struct nft_bitmap *priv = nft_set_priv(set); + INIT_LIST_HEAD(&priv->list); priv->bitmap_size = nft_bitmap_size(set->klen); return 0; @@ -283,6 +275,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, static struct nft_set_ops nft_bitmap_ops __read_mostly = { .privsize = nft_bitmap_privsize, + .elemsize = offsetof(struct nft_bitmap_elem, ext), .estimate = nft_bitmap_estimate, .init = nft_bitmap_init, .destroy = nft_bitmap_destroy, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7b73c7c161a9..596eaff66649 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -96,6 +96,44 @@ EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); +static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; + +static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { + "nlk_cb_mutex-ROUTE", + "nlk_cb_mutex-1", + "nlk_cb_mutex-USERSOCK", + "nlk_cb_mutex-FIREWALL", + "nlk_cb_mutex-SOCK_DIAG", + "nlk_cb_mutex-NFLOG", + "nlk_cb_mutex-XFRM", + "nlk_cb_mutex-SELINUX", + "nlk_cb_mutex-ISCSI", + "nlk_cb_mutex-AUDIT", + "nlk_cb_mutex-FIB_LOOKUP", + "nlk_cb_mutex-CONNECTOR", + "nlk_cb_mutex-NETFILTER", + "nlk_cb_mutex-IP6_FW", + "nlk_cb_mutex-DNRTMSG", + "nlk_cb_mutex-KOBJECT_UEVENT", + "nlk_cb_mutex-GENERIC", + "nlk_cb_mutex-17", + "nlk_cb_mutex-SCSITRANSPORT", + "nlk_cb_mutex-ECRYPTFS", + "nlk_cb_mutex-RDMA", + "nlk_cb_mutex-CRYPTO", + "nlk_cb_mutex-SMC", + "nlk_cb_mutex-23", + "nlk_cb_mutex-24", + "nlk_cb_mutex-25", + "nlk_cb_mutex-26", + "nlk_cb_mutex-27", + "nlk_cb_mutex-28", + "nlk_cb_mutex-29", + "nlk_cb_mutex-30", + "nlk_cb_mutex-31", + "nlk_cb_mutex-MAX_LINKS" +}; + static int netlink_dump(struct sock *sk); static void netlink_skb_destructor(struct sk_buff *skb); @@ -585,6 +623,9 @@ static int __netlink_create(struct net *net, struct socket *sock, } else { nlk->cb_mutex = &nlk->cb_def_mutex; mutex_init(nlk->cb_mutex); + lockdep_set_class_and_name(nlk->cb_mutex, + nlk_cb_mutex_keys + protocol, + nlk_cb_mutex_key_strings[protocol]); } init_waitqueue_head(&nlk->wait); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index fb6e10fdb217..92e0981f7404 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -783,8 +783,10 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - skb, CTRL_CMD_NEWFAMILY) < 0) + skb, CTRL_CMD_NEWFAMILY) < 0) { + n--; break; + } } cb->args[0] = n; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 4bbf4526b885..ebf16f7f9089 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -765,7 +765,8 @@ out_release: return err; } -static int nr_accept(struct socket *sock, struct socket *newsock, int flags) +static int nr_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 879885b31cce..2ffb18e73df6 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, } static int llcp_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *new_sk; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 6f5fa50f716d..1105a838bab8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -604,7 +604,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV6_SRC: - SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src, nla_get_in6_addr(a), is_mask); ipv6 = true; break; @@ -665,6 +665,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, tun_flags |= TUNNEL_VXLAN_OPT; opts_type = type; break; + case OVS_TUNNEL_KEY_ATTR_PAD: + break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 222bedcd9575..e81537991ddf 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout) sock_put(sk); } -static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) +static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, + bool kern) { struct pep_sock *pn = pep_sk(sk), *newpn; struct sock *newsk = NULL; @@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) } /* Create a new to-be-accepted sock */ - newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, + kern); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index a6c8da3ee893..64634e3ec2fc 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -305,7 +305,7 @@ out: } static int pn_socket_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk; struct sock *newsk; @@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock, if (unlikely(sk->sk_state != TCP_LISTEN)) return -EINVAL; - newsk = sk->sk_prot->accept(sk, flags, &err); + newsk = sk->sk_prot->accept(sk, flags, &err, kern); if (!newsk) return err; diff --git a/net/rds/connection.c b/net/rds/connection.c index 0e04dcceb1d4..1fa75ab7b733 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -429,6 +429,7 @@ void rds_conn_destroy(struct rds_connection *conn) */ rds_cong_remove_conn(conn); + put_net(conn->c_net); kmem_cache_free(rds_conn_slab, conn); spin_lock_irqsave(&rds_conn_lock, flags); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index ce3775abc6e7..1c38d2c7caa8 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -442,7 +442,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ic->i_send_cq = NULL; ibdev_put_vector(rds_ibdev, ic->i_scq_vector); rdsdebug("ib_create_cq send failed: %d\n", ret); - goto out; + goto rds_ibdev_out; } ic->i_rcq_vector = ibdev_get_unused_vector(rds_ibdev); @@ -456,19 +456,19 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ic->i_recv_cq = NULL; ibdev_put_vector(rds_ibdev, ic->i_rcq_vector); rdsdebug("ib_create_cq recv failed: %d\n", ret); - goto out; + goto send_cq_out; } ret = ib_req_notify_cq(ic->i_send_cq, IB_CQ_NEXT_COMP); if (ret) { rdsdebug("ib_req_notify_cq send failed: %d\n", ret); - goto out; + goto recv_cq_out; } ret = ib_req_notify_cq(ic->i_recv_cq, IB_CQ_SOLICITED); if (ret) { rdsdebug("ib_req_notify_cq recv failed: %d\n", ret); - goto out; + goto recv_cq_out; } /* XXX negotiate max send/recv with remote? */ @@ -494,7 +494,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ret = rdma_create_qp(ic->i_cm_id, ic->i_pd, &attr); if (ret) { rdsdebug("rdma_create_qp failed: %d\n", ret); - goto out; + goto recv_cq_out; } ic->i_send_hdrs = ib_dma_alloc_coherent(dev, @@ -504,7 +504,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_send_hdrs) { ret = -ENOMEM; rdsdebug("ib_dma_alloc_coherent send failed\n"); - goto out; + goto qp_out; } ic->i_recv_hdrs = ib_dma_alloc_coherent(dev, @@ -514,7 +514,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_recv_hdrs) { ret = -ENOMEM; rdsdebug("ib_dma_alloc_coherent recv failed\n"); - goto out; + goto send_hdrs_dma_out; } ic->i_ack = ib_dma_alloc_coherent(dev, sizeof(struct rds_header), @@ -522,7 +522,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_ack) { ret = -ENOMEM; rdsdebug("ib_dma_alloc_coherent ack failed\n"); - goto out; + goto recv_hdrs_dma_out; } ic->i_sends = vzalloc_node(ic->i_send_ring.w_nr * sizeof(struct rds_ib_send_work), @@ -530,7 +530,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_sends) { ret = -ENOMEM; rdsdebug("send allocation failed\n"); - goto out; + goto ack_dma_out; } ic->i_recvs = vzalloc_node(ic->i_recv_ring.w_nr * sizeof(struct rds_ib_recv_work), @@ -538,7 +538,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) if (!ic->i_recvs) { ret = -ENOMEM; rdsdebug("recv allocation failed\n"); - goto out; + goto sends_out; } rds_ib_recv_init_ack(ic); @@ -546,8 +546,33 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd, ic->i_send_cq, ic->i_recv_cq); -out: + return ret; + +sends_out: + vfree(ic->i_sends); +ack_dma_out: + ib_dma_free_coherent(dev, sizeof(struct rds_header), + ic->i_ack, ic->i_ack_dma); +recv_hdrs_dma_out: + ib_dma_free_coherent(dev, ic->i_recv_ring.w_nr * + sizeof(struct rds_header), + ic->i_recv_hdrs, ic->i_recv_hdrs_dma); +send_hdrs_dma_out: + ib_dma_free_coherent(dev, ic->i_send_ring.w_nr * + sizeof(struct rds_header), + ic->i_send_hdrs, ic->i_send_hdrs_dma); +qp_out: + rdma_destroy_qp(ic->i_cm_id); +recv_cq_out: + if (!ib_destroy_cq(ic->i_recv_cq)) + ic->i_recv_cq = NULL; +send_cq_out: + if (!ib_destroy_cq(ic->i_send_cq)) + ic->i_send_cq = NULL; +rds_ibdev_out: + rds_ib_remove_conn(rds_ibdev, conn); rds_ib_dev_put(rds_ibdev); + return ret; } diff --git a/net/rds/rds.h b/net/rds/rds.h index 39518ef7af4d..82d38ccf5e8b 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -147,7 +147,7 @@ struct rds_connection { /* Protocol version */ unsigned int c_version; - possible_net_t c_net; + struct net *c_net; struct list_head c_map_item; unsigned long c_map_queued; @@ -162,13 +162,13 @@ struct rds_connection { static inline struct net *rds_conn_net(struct rds_connection *conn) { - return read_pnet(&conn->c_net); + return conn->c_net; } static inline void rds_conn_net_set(struct rds_connection *conn, struct net *net) { - write_pnet(&conn->c_net, net); + conn->c_net = get_net(net); } #define RDS_FLAG_CONG_BITMAP 0x01 diff --git a/net/rds/tcp.c b/net/rds/tcp.c index a973d3b4dff0..431404dbdad1 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -84,13 +84,10 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* doing it this way avoids calling tcp_sk() */ void rds_tcp_nonagle(struct socket *sock) { - mm_segment_t oldfs = get_fs(); int val = 1; - set_fs(KERNEL_DS); - sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY, (char __user *)&val, + kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (void *)&val, sizeof(val)); - set_fs(oldfs); } u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc) @@ -484,9 +481,10 @@ static void __net_exit rds_tcp_exit_net(struct net *net) * we do need to clean up the listen socket here. */ if (rtn->rds_tcp_listen_sock) { - rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); + struct socket *lsock = rtn->rds_tcp_listen_sock; + rtn->rds_tcp_listen_sock = NULL; - flush_work(&rtn->rds_tcp_accept_w); + rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w); } } @@ -523,13 +521,13 @@ static void rds_tcp_kill_sock(struct net *net) struct rds_tcp_connection *tc, *_tc; LIST_HEAD(tmp_list); struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct socket *lsock = rtn->rds_tcp_listen_sock; - rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); rtn->rds_tcp_listen_sock = NULL; - flush_work(&rtn->rds_tcp_accept_w); + rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w); spin_lock_irq(&rds_tcp_conn_lock); 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); + struct net *c_net = tc->t_cpath->cp_conn->c_net; if (net != c_net || !tc->t_sock) continue; @@ -546,8 +544,12 @@ static void rds_tcp_kill_sock(struct net *net) void *rds_tcp_listen_sock_def_readable(struct net *net) { struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + struct socket *lsock = rtn->rds_tcp_listen_sock; + + if (!lsock) + return NULL; - return rtn->rds_tcp_listen_sock->sk->sk_user_data; + return lsock->sk->sk_user_data; } static int rds_tcp_dev_event(struct notifier_block *this, @@ -584,7 +586,7 @@ static void rds_tcp_sysctl_reset(struct net *net) spin_lock_irq(&rds_tcp_conn_lock); 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); + struct net *c_net = tc->t_cpath->cp_conn->c_net; if (net != c_net || !tc->t_sock) continue; @@ -638,19 +640,19 @@ static int rds_tcp_init(void) goto out; } - ret = register_netdevice_notifier(&rds_tcp_dev_notifier); - if (ret) { - pr_warn("could not register rds_tcp_dev_notifier\n"); + ret = rds_tcp_recv_init(); + if (ret) goto out_slab; - } ret = register_pernet_subsys(&rds_tcp_net_ops); if (ret) - goto out_notifier; + goto out_recv; - ret = rds_tcp_recv_init(); - if (ret) + ret = register_netdevice_notifier(&rds_tcp_dev_notifier); + if (ret) { + pr_warn("could not register rds_tcp_dev_notifier\n"); goto out_pernet; + } rds_trans_register(&rds_tcp_transport); @@ -660,9 +662,8 @@ static int rds_tcp_init(void) out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); -out_notifier: - if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) - pr_warn("could not unregister rds_tcp_dev_notifier\n"); +out_recv: + rds_tcp_recv_exit(); out_slab: kmem_cache_destroy(rds_tcp_conn_slab); out: diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 9a1cc8906576..56ea6620fcf9 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -66,7 +66,7 @@ void rds_tcp_state_change(struct sock *sk); /* tcp_listen.c */ struct socket *rds_tcp_listen_init(struct net *); -void rds_tcp_listen_stop(struct socket *); +void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor); void rds_tcp_listen_data_ready(struct sock *sk); int rds_tcp_accept_one(struct socket *sock); int rds_tcp_keepalive(struct socket *sock); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 67d0929c7d3d..507678853e6c 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; @@ -223,6 +223,9 @@ void rds_tcp_listen_data_ready(struct sock *sk) * before it has been accepted and the accepter has set up their * data_ready.. we only want to queue listen work for our listening * socket + * + * (*ready)() may be null if we are racing with netns delete, and + * the listen socket is being torn down. */ if (sk->sk_state == TCP_LISTEN) rds_tcp_accept_work(sk); @@ -231,7 +234,8 @@ void rds_tcp_listen_data_ready(struct sock *sk) out: read_unlock_bh(&sk->sk_callback_lock); - ready(sk); + if (ready) + ready(sk); } struct socket *rds_tcp_listen_init(struct net *net) @@ -271,7 +275,7 @@ out: return NULL; } -void rds_tcp_listen_stop(struct socket *sock) +void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor) { struct sock *sk; @@ -292,5 +296,6 @@ void rds_tcp_listen_stop(struct socket *sock) /* wait for accepts to stop and close the socket */ flush_workqueue(rds_wq); + flush_work(acceptor); sock_release(sock); } diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index dcf4742083ea..52d11d7725c8 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -40,13 +40,7 @@ static void rds_tcp_cork(struct socket *sock, int val) { - mm_segment_t oldfs; - - oldfs = get_fs(); - set_fs(KERNEL_DS); - sock->ops->setsockopt(sock, SOL_TCP, TCP_CORK, (char __user *)&val, - sizeof(val)); - set_fs(oldfs); + kernel_setsockopt(sock, SOL_TCP, TCP_CORK, (void *)&val, sizeof(val)); } void rds_tcp_xmit_path_prepare(struct rds_conn_path *cp) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index b8a1df2c9785..4a9729257023 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -871,7 +871,8 @@ out_release: return err; } -static int rose_accept(struct socket *sock, struct socket *newsock, int flags) +static int rose_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 3f9d8d7ec632..b099b64366f3 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -275,6 +275,10 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, rxrpc_conn_retransmit_call(conn, skb); return 0; + case RXRPC_PACKET_TYPE_BUSY: + /* Just ignore BUSY packets for now. */ + return 0; + case RXRPC_PACKET_TYPE_ABORT: if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &wtmp, sizeof(wtmp)) < 0) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9f4cfa25af7c..18b2ad8be8e2 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -420,6 +420,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, u16 skew) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + enum rxrpc_call_state state; unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int ix; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0; @@ -434,14 +435,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, _proto("Rx DATA %%%u { #%u f=%02x }", sp->hdr.serial, seq, sp->hdr.flags); - if (call->state >= RXRPC_CALL_COMPLETE) + state = READ_ONCE(call->state); + if (state >= RXRPC_CALL_COMPLETE) return; /* Received data implicitly ACKs all of the request packets we sent * when we're acting as a client. */ - if ((call->state == RXRPC_CALL_CLIENT_SEND_REQUEST || - call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && + if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || + state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) return; @@ -650,6 +652,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; unsigned int mtu; + bool wake = false; u32 rwind = ntohl(ackinfo->rwind); _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", @@ -657,9 +660,14 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; - call->tx_winsize = rwind; + if (call->tx_winsize != rwind) { + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; + if (rwind > call->tx_winsize) + wake = true; + call->tx_winsize = rwind; + } + if (call->cong_ssthresh > rwind) call->cong_ssthresh = rwind; @@ -673,6 +681,9 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, spin_unlock_bh(&peer->lock); _net("Net MTU %u (maxdata %u)", peer->mtu, peer->maxdata); } + + if (wake) + wake_up(&call->waitq); } /* @@ -799,7 +810,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, return rxrpc_proto_abort("AK0", call, 0); /* Ignore ACKs unless we are or have just been transmitting. */ - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: case RXRPC_CALL_SERVER_SEND_REPLY: @@ -940,7 +951,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, struct rxrpc_call *call) { - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); break; diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 6491ca46a03f..3e2f1a8e9c5b 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -527,7 +527,7 @@ try_again: msg->msg_namelen = len; } - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_ACCEPTING: ret = rxrpc_recvmsg_new_call(rx, call, msg, flags); break; @@ -640,7 +640,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, mutex_lock(&call->user_mutex); - switch (call->state) { + switch (READ_ONCE(call->state)) { case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index bc2d3dcff9de..97ab214ca411 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -488,6 +488,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { + enum rxrpc_call_state state; enum rxrpc_command cmd; struct rxrpc_call *call; unsigned long user_call_ID = 0; @@ -526,13 +527,17 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return PTR_ERR(call); /* ... and we have the call lock. */ } else { - ret = -EBUSY; - if (call->state == RXRPC_CALL_UNINITIALISED || - call->state == RXRPC_CALL_CLIENT_AWAIT_CONN || - call->state == RXRPC_CALL_SERVER_PREALLOC || - call->state == RXRPC_CALL_SERVER_SECURING || - call->state == RXRPC_CALL_SERVER_ACCEPTING) + switch (READ_ONCE(call->state)) { + case RXRPC_CALL_UNINITIALISED: + case RXRPC_CALL_CLIENT_AWAIT_CONN: + case RXRPC_CALL_SERVER_PREALLOC: + case RXRPC_CALL_SERVER_SECURING: + case RXRPC_CALL_SERVER_ACCEPTING: + ret = -EBUSY; goto error_release_sock; + default: + break; + } ret = mutex_lock_interruptible(&call->user_mutex); release_sock(&rx->sk); @@ -542,10 +547,11 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } } + state = READ_ONCE(call->state); _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, call->state, call->conn); + call->debug_id, call->user_call_ID, state, call->conn); - if (call->state >= RXRPC_CALL_COMPLETE) { + if (state >= RXRPC_CALL_COMPLETE) { /* it's too late for this call */ ret = -ESHUTDOWN; } else if (cmd == RXRPC_CMD_SEND_ABORT) { @@ -555,12 +561,12 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else if (rxrpc_is_client_call(call) && - call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { + state != RXRPC_CALL_CLIENT_SEND_REQUEST) { /* request phase complete for this client call */ ret = -EPROTO; } else if (rxrpc_is_service_call(call) && - call->state != RXRPC_CALL_SERVER_ACK_REQUEST && - call->state != RXRPC_CALL_SERVER_SEND_REPLY) { + state != RXRPC_CALL_SERVER_ACK_REQUEST && + state != RXRPC_CALL_SERVER_SEND_REPLY) { /* Reply phase not begun or not complete for service call. */ ret = -EPROTO; } else { @@ -605,14 +611,21 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); - if (call->state >= RXRPC_CALL_COMPLETE) { - ret = -ESHUTDOWN; /* it's too late for this call */ - } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && - call->state != RXRPC_CALL_SERVER_ACK_REQUEST && - call->state != RXRPC_CALL_SERVER_SEND_REPLY) { - ret = -EPROTO; /* request phase complete for this client call */ - } else { + switch (READ_ONCE(call->state)) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_SERVER_ACK_REQUEST: + case RXRPC_CALL_SERVER_SEND_REPLY: ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len); + break; + case RXRPC_CALL_COMPLETE: + read_lock_bh(&call->state_lock); + ret = -call->error; + read_unlock_bh(&call->state_lock); + break; + default: + /* Request phase complete for this client call */ + ret = -EPROTO; + break; } mutex_unlock(&call->user_mutex); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ab8062909962..f9bb43c25697 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, if (ret < 0) return ret; + if (!tb[TCA_CONNMARK_PARMS]) + return -EINVAL; + parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(tn, parm->index, a, bind)) { diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 3b7074e23024..c736627f8f4a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, return skb->len; nla_put_failure: - rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 802ac7c2e5e8..5334e309f17f 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -201,9 +201,13 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); if (p->set_tc_index) { + int wlen = skb_network_offset(skb); + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): - if (skb_cow_head(skb, sizeof(struct iphdr))) + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) goto drop; skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) @@ -211,7 +215,9 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; case htons(ETH_P_IPV6): - if (skb_cow_head(skb, sizeof(struct ipv6hdr))) + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) goto drop; skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 2a6835b4562b..0439a1a68367 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -71,9 +71,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a { struct net *net = sock_net(sk); struct sctp_sock *sp; - int i; sctp_paramhdr_t *p; - int err; + int i; /* Retrieve the SCTP per socket area. */ sp = sctp_sk((struct sock *)sk); @@ -264,8 +263,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); - err = sctp_auth_asoc_copy_shkeys(ep, asoc, gfp); - if (err) + if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp)) goto fail_init; asoc->active_key_id = ep->active_key_id; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 063baac5b9fe..961ee59f696a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr) /* Create and initialize a new sk for the socket to be returned by accept(). */ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; struct ipv6_txoptions *opt; - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); if (!newsk) goto out; diff --git a/net/sctp/output.c b/net/sctp/output.c index 71ce6b945dcb..1224421036b3 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -546,7 +546,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) struct sctp_association *asoc = tp->asoc; struct sctp_chunk *chunk, *tmp; int pkt_count, gso = 0; - int confirm; struct dst_entry *dst; struct sk_buff *head; struct sctphdr *sh; @@ -625,13 +624,13 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) asoc->peer.last_sent_to = tp; } head->ignore_df = packet->ipfragok; - confirm = tp->dst_pending_confirm; - if (confirm) + if (tp->dst_pending_confirm) skb_set_dst_pending_confirm(head, 1); /* neighbour should be confirmed on successful transmission or * positive error */ - if (tp->af_specific->sctp_xmit(head, tp) >= 0 && confirm) + if (tp->af_specific->sctp_xmit(head, tp) >= 0 && + tp->dst_pending_confirm) tp->dst_pending_confirm = 0; out: diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index db352e5d61f8..025ccff67072 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -382,17 +382,18 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, } static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, - struct sctp_sndrcvinfo *sinfo, - struct list_head *queue, int msg_len) + struct sctp_sndrcvinfo *sinfo, int msg_len) { + struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; - list_for_each_entry_safe(chk, temp, queue, list) { + list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) continue; list_del_init(&chk->list); + q->out_qlen -= chk->skb->len; asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; @@ -431,9 +432,7 @@ void sctp_prsctp_prune(struct sctp_association *asoc, return; } - sctp_prsctp_prune_unsent(asoc, sinfo, - &asoc->outqueue.out_chunk_list, - msg_len); + sctp_prsctp_prune_unsent(asoc, sinfo, msg_len); } /* Mark all the eligible packets on a transport for retransmission. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1b6d4574d2b0..989a900383b5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb) /* Create and initialize a new sk for the socket returned by accept(). */ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot, 0); + sk->sk_prot, kern); struct inet_sock *newinet; if (!newsk) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6f0a9be50f50..0f378ea2ae38 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4116,7 +4116,7 @@ static int sctp_disconnect(struct sock *sk, int flags) * descriptor will be returned from accept() to represent the newly * formed association. */ -static struct sock *sctp_accept(struct sock *sk, int flags, int *err) +static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -4151,7 +4151,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err) */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc); + newsk = sp->pf->create_accept_sk(sk, asoc, kern); if (!newsk) { error = -ENOMEM; goto out; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 85837ab90e89..093803786eac 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -944,7 +944,7 @@ out: } static int smc_accept(struct socket *sock, struct socket *new_sock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); diff --git a/net/socket.c b/net/socket.c index 2c1e8677ff2d..985ef06792d6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -652,6 +652,16 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_sendmsg); +static bool skb_is_err_queue(const struct sk_buff *skb) +{ + /* pkt_type of skbs enqueued on the error queue are set to + * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do + * in recvmsg, since skbs received on a local socket will never + * have a pkt_type of PACKET_OUTGOING. + */ + return skb->pkt_type == PACKET_OUTGOING; +} + /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ @@ -695,7 +705,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING, sizeof(tss), &tss); - if (skb->len && (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS)) + if (skb_is_err_queue(skb) && skb->len && + SKB_EXT_ERR(skb)->opt_stats) put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, skb->len, skb->data); } @@ -1506,7 +1517,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags); + err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); if (err < 0) goto out_fd; @@ -1731,6 +1742,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; msg.msg_iocb = NULL; + msg.msg_flags = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); @@ -3238,7 +3250,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = sock->ops->accept(sock, *newsock, flags); + err = sock->ops->accept(sock, *newsock, flags, true); if (err < 0) { sock_release(*newsock); *newsock = NULL; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 81cd31acf690..3b332b395045 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -503,7 +503,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, struct ib_cq *sendcq, *recvcq; int rc; - max_sge = min(ia->ri_device->attrs.max_sge, RPCRDMA_MAX_SEND_SGES); + max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge, + RPCRDMA_MAX_SEND_SGES); if (max_sge < RPCRDMA_MIN_SEND_SGES) { pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge); return -ENOMEM; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 43e4045e72bc..7130e73bd42c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); static int tipc_release(struct socket *sock); -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern); static void tipc_sk_timeout(unsigned long data); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); @@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * * Returns 0 on success, errno otherwise */ -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; @@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) buf = skb_peek(&sk->sk_receive_queue); - res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0); + res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern); if (res) goto exit; security_sk_clone(sock->sk, new_sock->sk); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 9d94e65d0894..271cd66e4b3b 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -141,6 +141,11 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, static void tipc_subscrp_timeout(unsigned long data) { struct tipc_subscription *sub = (struct tipc_subscription *)data; + struct tipc_subscriber *subscriber = sub->subscriber; + + spin_lock_bh(&subscriber->lock); + tipc_nametbl_unsubscribe(sub); + spin_unlock_bh(&subscriber->lock); /* Notify subscriber of timeout */ tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper, @@ -173,7 +178,6 @@ static void tipc_subscrp_kref_release(struct kref *kref) struct tipc_subscriber *subscriber = sub->subscriber; spin_lock_bh(&subscriber->lock); - tipc_nametbl_unsubscribe(sub); list_del(&sub->subscrp_list); atomic_dec(&tn->subscription_count); spin_unlock_bh(&subscriber->lock); @@ -205,6 +209,7 @@ static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber, if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) continue; + tipc_nametbl_unsubscribe(sub); tipc_subscrp_get(sub); spin_unlock_bh(&subscriber->lock); tipc_subscrp_delete(sub); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ee37b390260a..928691c43408 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int); static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); -static int unix_accept(struct socket *, struct socket *, int); +static int unix_accept(struct socket *, struct socket *, int, bool); static int unix_getname(struct socket *, struct sockaddr *, int *, int); static unsigned int unix_poll(struct file *, struct socket *, poll_table *); static unsigned int unix_dgram_poll(struct file *, struct socket *, @@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old, set_bit(SOCK_PASSSEC, &new->flags); } -static int unix_accept(struct socket *sock, struct socket *newsock, int flags) +static int unix_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *tsk; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 6a0d48525fcf..c36757e72844 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); + BUG_ON(!atomic_long_read(&u->inflight)); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) @@ -341,6 +342,14 @@ void unix_gc(void) } list_del(&cursor); + /* Now gc_candidates contains only garbage. Restore original + * inflight counters for these as well, and remove the skbuffs + * which are creating the cycle(s). + */ + skb_queue_head_init(&hitlist); + list_for_each_entry(u, &gc_candidates, link) + scan_children(&u->sk, inc_inflight, &hitlist); + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ @@ -350,14 +359,6 @@ void unix_gc(void) list_move_tail(&u->link, &gc_inflight_list); } - /* Now gc_candidates contains only garbage. Restore original - * inflight counters for these as well, and remove the skbuffs - * which are creating the cycle(s). - */ - skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) - scan_children(&u->sk, inc_inflight, &hitlist); - spin_unlock(&unix_gc_lock); /* Here we are. Hitlist is filled. Die. */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9192ead66751..6f7f6757ceef 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1102,10 +1102,19 @@ static const struct proto_ops vsock_dgram_ops = { .sendpage = sock_no_sendpage, }; +static int vsock_transport_cancel_pkt(struct vsock_sock *vsk) +{ + if (!transport->cancel_pkt) + return -EOPNOTSUPP; + + return transport->cancel_pkt(vsk); +} + static void vsock_connect_timeout(struct work_struct *work) { struct sock *sk; struct vsock_sock *vsk; + int cancel = 0; vsk = container_of(work, struct vsock_sock, dwork.work); sk = sk_vsock(vsk); @@ -1116,8 +1125,11 @@ static void vsock_connect_timeout(struct work_struct *work) sk->sk_state = SS_UNCONNECTED; sk->sk_err = ETIMEDOUT; sk->sk_error_report(sk); + cancel = 1; } release_sock(sk); + if (cancel) + vsock_transport_cancel_pkt(vsk); sock_put(sk); } @@ -1224,11 +1236,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, err = sock_intr_errno(timeout); sk->sk_state = SS_UNCONNECTED; sock->state = SS_UNCONNECTED; + vsock_transport_cancel_pkt(vsk); goto out_wait; } else if (timeout == 0) { err = -ETIMEDOUT; sk->sk_state = SS_UNCONNECTED; sock->state = SS_UNCONNECTED; + vsock_transport_cancel_pkt(vsk); goto out_wait; } @@ -1250,7 +1264,8 @@ out: return err; } -static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) +static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *listener; int err; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 9d24c0e958b1..68675a151f22 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -213,6 +213,47 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) return len; } +static int +virtio_transport_cancel_pkt(struct vsock_sock *vsk) +{ + struct virtio_vsock *vsock; + struct virtio_vsock_pkt *pkt, *n; + int cnt = 0; + LIST_HEAD(freeme); + + vsock = virtio_vsock_get(); + if (!vsock) { + return -ENODEV; + } + + spin_lock_bh(&vsock->send_pkt_list_lock); + list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) { + if (pkt->vsk != vsk) + continue; + list_move(&pkt->list, &freeme); + } + spin_unlock_bh(&vsock->send_pkt_list_lock); + + list_for_each_entry_safe(pkt, n, &freeme, list) { + if (pkt->reply) + cnt++; + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + if (cnt) { + struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; + int new_cnt; + + new_cnt = atomic_sub_return(cnt, &vsock->queued_replies); + if (new_cnt + cnt >= virtqueue_get_vring_size(rx_vq) && + new_cnt < virtqueue_get_vring_size(rx_vq)) + queue_work(virtio_vsock_workqueue, &vsock->rx_work); + } + + return 0; +} + static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) { int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; @@ -462,6 +503,7 @@ static struct virtio_transport virtio_transport = { .release = virtio_transport_release, .connect = virtio_transport_connect, .shutdown = virtio_transport_shutdown, + .cancel_pkt = virtio_transport_cancel_pkt, .dgram_bind = virtio_transport_dgram_bind, .dgram_dequeue = virtio_transport_dgram_dequeue, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 8d592a45b597..af087b44ceea 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -58,6 +58,7 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->len = len; pkt->hdr.len = cpu_to_le32(len); pkt->reply = info->reply; + pkt->vsk = info->vsk; if (info->msg && len > 0) { pkt->buf = kmalloc(len, GFP_KERNEL); @@ -180,6 +181,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk, struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, .type = type, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -519,6 +521,7 @@ int virtio_transport_connect(struct vsock_sock *vsk) struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, .type = VIRTIO_VSOCK_TYPE_STREAM, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -534,6 +537,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_SEND : 0), + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -560,6 +564,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, .type = VIRTIO_VSOCK_TYPE_STREAM, .msg = msg, .pkt_len = len, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); @@ -581,6 +586,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk, .op = VIRTIO_VSOCK_OP_RST, .type = VIRTIO_VSOCK_TYPE_STREAM, .reply = !!pkt, + .vsk = vsk, }; /* Send RST only if the original pkt is not a RST pkt */ @@ -826,6 +832,7 @@ virtio_transport_send_response(struct vsock_sock *vsk, .remote_cid = le64_to_cpu(pkt->hdr.src_cid), .remote_port = le32_to_cpu(pkt->hdr.src_port), .reply = true, + .vsk = vsk, }; return virtio_transport_send_pkt_info(vsk, &info); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d7f8be4e321a..2312dc2ffdb9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -545,22 +545,18 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, { int err; - rtnl_lock(); - if (!cb->args[0]) { err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, genl_family_attrbuf(&nl80211_fam), nl80211_fam.maxattr, nl80211_policy); if (err) - goto out_unlock; + return err; *wdev = __cfg80211_wdev_from_attrs( sock_net(skb->sk), genl_family_attrbuf(&nl80211_fam)); - if (IS_ERR(*wdev)) { - err = PTR_ERR(*wdev); - goto out_unlock; - } + if (IS_ERR(*wdev)) + return PTR_ERR(*wdev); *rdev = wiphy_to_rdev((*wdev)->wiphy); /* 0 is the first index - add 1 to parse only once */ cb->args[0] = (*rdev)->wiphy_idx + 1; @@ -570,10 +566,8 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); struct wireless_dev *tmp; - if (!wiphy) { - err = -ENODEV; - goto out_unlock; - } + if (!wiphy) + return -ENODEV; *rdev = wiphy_to_rdev(wiphy); *wdev = NULL; @@ -584,21 +578,11 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb, } } - if (!*wdev) { - err = -ENODEV; - goto out_unlock; - } + if (!*wdev) + return -ENODEV; } return 0; - out_unlock: - rtnl_unlock(); - return err; -} - -static void nl80211_finish_wdev_dump(struct cfg80211_registered_device *rdev) -{ - rtnl_unlock(); } /* IE validation */ @@ -2608,17 +2592,17 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * int filter_wiphy = -1; struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; + int ret; rtnl_lock(); if (!cb->args[2]) { struct nl80211_dump_wiphy_state state = { .filter_wiphy = -1, }; - int ret; ret = nl80211_dump_wiphy_parse(skb, cb, &state); if (ret) - return ret; + goto out_unlock; filter_wiphy = state.filter_wiphy; @@ -2663,12 +2647,14 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * wp_idx++; } out: - rtnl_unlock(); - cb->args[0] = wp_idx; cb->args[1] = if_idx; - return skb->len; + ret = skb->len; + out_unlock: + rtnl_unlock(); + + return ret; } static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) @@ -4452,9 +4438,10 @@ static int nl80211_dump_station(struct sk_buff *skb, int sta_idx = cb->args[2]; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out_err; if (!wdev->netdev) { err = -EINVAL; @@ -4489,7 +4476,7 @@ static int nl80211_dump_station(struct sk_buff *skb, cb->args[2] = sta_idx; err = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return err; } @@ -5275,9 +5262,10 @@ static int nl80211_dump_mpath(struct sk_buff *skb, int path_idx = cb->args[2]; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out_err; if (!rdev->ops->dump_mpath) { err = -EOPNOTSUPP; @@ -5310,7 +5298,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, cb->args[2] = path_idx; err = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return err; } @@ -5470,9 +5458,10 @@ static int nl80211_dump_mpp(struct sk_buff *skb, int path_idx = cb->args[2]; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out_err; if (!rdev->ops->dump_mpp) { err = -EOPNOTSUPP; @@ -5505,7 +5494,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb, cb->args[2] = path_idx; err = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return err; } @@ -7674,9 +7663,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) int start = cb->args[2], idx = 0; int err; + rtnl_lock(); err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); - if (err) + if (err) { + rtnl_unlock(); return err; + } wdev_lock(wdev); spin_lock_bh(&rdev->bss_lock); @@ -7699,7 +7691,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) wdev_unlock(wdev); cb->args[2] = idx; - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return skb->len; } @@ -7784,9 +7776,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) int res; bool radio_stats; + rtnl_lock(); res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev); if (res) - return res; + goto out_err; /* prepare_wdev_dump parsed the attributes */ radio_stats = attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS]; @@ -7827,7 +7820,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) cb->args[2] = survey_idx; res = skb->len; out_err: - nl80211_finish_wdev_dump(rdev); + rtnl_unlock(); return res; } @@ -11508,17 +11501,13 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, void *data = NULL; unsigned int data_len = 0; - rtnl_lock(); - if (cb->args[0]) { /* subtract the 1 again here */ struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); struct wireless_dev *tmp; - if (!wiphy) { - err = -ENODEV; - goto out_unlock; - } + if (!wiphy) + return -ENODEV; *rdev = wiphy_to_rdev(wiphy); *wdev = NULL; @@ -11538,23 +11527,19 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf, nl80211_fam.maxattr, nl80211_policy); if (err) - goto out_unlock; + return err; if (!attrbuf[NL80211_ATTR_VENDOR_ID] || - !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) { - err = -EINVAL; - goto out_unlock; - } + !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) + return -EINVAL; *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), attrbuf); if (IS_ERR(*wdev)) *wdev = NULL; *rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), attrbuf); - if (IS_ERR(*rdev)) { - err = PTR_ERR(*rdev); - goto out_unlock; - } + if (IS_ERR(*rdev)) + return PTR_ERR(*rdev); vid = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_ID]); subcmd = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_SUBCMD]); @@ -11567,19 +11552,15 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd) continue; - if (!vcmd->dumpit) { - err = -EOPNOTSUPP; - goto out_unlock; - } + if (!vcmd->dumpit) + return -EOPNOTSUPP; vcmd_idx = i; break; } - if (vcmd_idx < 0) { - err = -EOPNOTSUPP; - goto out_unlock; - } + if (vcmd_idx < 0) + return -EOPNOTSUPP; if (attrbuf[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(attrbuf[NL80211_ATTR_VENDOR_DATA]); @@ -11596,9 +11577,6 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, /* keep rtnl locked in successful case */ return 0; - out_unlock: - rtnl_unlock(); - return err; } static int nl80211_vendor_cmd_dump(struct sk_buff *skb, @@ -11613,9 +11591,10 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb, int err; struct nlattr *vendor_data; + rtnl_lock(); err = nl80211_prepare_vendor_dump(skb, cb, &rdev, &wdev); if (err) - return err; + goto out; vcmd_idx = cb->args[2]; data = (void *)cb->args[3]; @@ -11624,15 +11603,21 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb, if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_NETDEV)) { - if (!wdev) - return -EINVAL; + if (!wdev) { + err = -EINVAL; + goto out; + } if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV && - !wdev->netdev) - return -EINVAL; + !wdev->netdev) { + err = -EINVAL; + goto out; + } if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) { - if (!wdev_running(wdev)) - return -ENETDOWN; + if (!wdev_running(wdev)) { + err = -ENETDOWN; + goto out; + } } } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index fd28a49dbe8f..8b911c29860e 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout) return rc; } -static int x25_accept(struct socket *sock, struct socket *newsock, int flags) +static int x25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *newsk; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 0806dccdf507..236cbbc0ab9c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1243,7 +1243,7 @@ static inline int policy_to_flow_dir(int dir) } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, - const struct flowi *fl) + const struct flowi *fl, u16 family) { struct xfrm_policy *pol; @@ -1251,8 +1251,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { - bool match = xfrm_selector_match(&pol->selector, fl, - sk->sk_family); + bool match = xfrm_selector_match(&pol->selector, fl, family); int err = 0; if (match) { @@ -2239,7 +2238,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; - pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2518,7 +2517,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { - pol = xfrm_sk_policy_lookup(sk, dir, &fl); + pol = xfrm_sk_policy_lookup(sk, dir, &fl, family); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; @@ -3069,6 +3068,11 @@ static int __net_init xfrm_net_init(struct net *net) { int rv; + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + spin_lock_init(&net->xfrm.xfrm_policy_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; @@ -3085,11 +3089,6 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out; - /* Initialize the per-net locks here */ - spin_lock_init(&net->xfrm.xfrm_state_lock); - spin_lock_init(&net->xfrm.xfrm_policy_lock); - mutex_init(&net->xfrm.xfrm_cfg_mutex); - return 0; out: |