diff options
Diffstat (limited to 'net')
153 files changed, 1654 insertions, 1065 deletions
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 9f481cfdf77d..e8090f099eb8 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -352,19 +352,21 @@ out: */ int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface) { + static const size_t tvlv_padding = sizeof(__be32); struct batadv_elp_packet *elp_packet; unsigned char *elp_buff; u32 random_seqno; size_t size; int res = -ENOMEM; - size = ETH_HLEN + NET_IP_ALIGN + BATADV_ELP_HLEN; + size = ETH_HLEN + NET_IP_ALIGN + BATADV_ELP_HLEN + tvlv_padding; hard_iface->bat_v.elp_skb = dev_alloc_skb(size); if (!hard_iface->bat_v.elp_skb) goto out; skb_reserve(hard_iface->bat_v.elp_skb, ETH_HLEN + NET_IP_ALIGN); - elp_buff = skb_put_zero(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN); + elp_buff = skb_put_zero(hard_iface->bat_v.elp_skb, + BATADV_ELP_HLEN + tvlv_padding); elp_packet = (struct batadv_elp_packet *)elp_buff; elp_packet->packet_type = BATADV_ELP; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 0fddc17106bd..5b71a289d04f 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -275,7 +275,7 @@ batadv_frag_merge_packets(struct hlist_head *chain) kfree(entry); packet = (struct batadv_frag_packet *)skb_out->data; - size = ntohs(packet->total_size); + size = ntohs(packet->total_size) + hdr_size; /* Make room for the rest of the fragments. */ if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index c89c22c49015..25001913d03b 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -28,12 +28,13 @@ static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx, return ret; } -static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time) +static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, + u32 *time) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 }; enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; - u32 ret = 0, i; + u32 i; for_each_cgroup_storage_type(stype) { storage[stype] = bpf_cgroup_storage_alloc(prog, stype); @@ -49,7 +50,7 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time) repeat = 1; time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - ret = bpf_test_run_one(prog, ctx, storage); + *ret = bpf_test_run_one(prog, ctx, storage); if (need_resched()) { if (signal_pending(current)) break; @@ -65,7 +66,7 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time) for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); - return ret; + return 0; } static int bpf_test_finish(const union bpf_attr *kattr, @@ -165,7 +166,12 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); - retval = bpf_test_run(prog, skb, repeat, &duration); + ret = bpf_test_run(prog, skb, repeat, &retval, &duration); + if (ret) { + kfree_skb(skb); + kfree(sk); + return ret; + } if (!is_l2) { if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); @@ -212,11 +218,14 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); xdp.rxq = &rxqueue->xdp_rxq; - retval = bpf_test_run(prog, &xdp, repeat, &duration); + ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration); + if (ret) + goto out; if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN || xdp.data_end != xdp.data + size) size = xdp.data_end - xdp.data; ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); +out: kfree(data); return ret; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2920e06a5403..04c19a37e500 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -102,12 +102,18 @@ struct br_tunnel_info { struct metadata_dst *tunnel_dst; }; +/* private vlan flags */ +enum { + BR_VLFLAG_PER_PORT_STATS = BIT(0), +}; + /** * struct net_bridge_vlan - per-vlan entry * * @vnode: rhashtable member * @vid: VLAN id * @flags: bridge vlan flags + * @priv_flags: private (in-kernel) bridge vlan flags * @stats: per-cpu VLAN statistics * @br: if MASTER flag set, this points to a bridge struct * @port: if MASTER flag unset, this points to a port struct @@ -127,6 +133,7 @@ struct net_bridge_vlan { struct rhash_head tnode; u16 vid; u16 flags; + u16 priv_flags; struct br_vlan_stats __percpu *stats; union { struct net_bridge *br; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 8c9297a01947..e84be08b8285 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -197,7 +197,7 @@ static void nbp_vlan_rcu_free(struct rcu_head *rcu) v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(br_vlan_is_master(v)); /* if we had per-port stats configured then free them here */ - if (v->brvlan->stats != v->stats) + if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS) free_percpu(v->stats); v->stats = NULL; kfree(v); @@ -264,6 +264,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags) err = -ENOMEM; goto out_filt; } + v->priv_flags |= BR_VLFLAG_PER_PORT_STATS; } else { v->stats = masterv->stats; } diff --git a/net/can/raw.c b/net/can/raw.c index 1051eee82581..c70207537488 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -745,18 +745,19 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } else ifindex = ro->ifindex; - if (ro->fd_frames) { + dev = dev_get_by_index(sock_net(sk), ifindex); + if (!dev) + return -ENXIO; + + err = -EINVAL; + if (ro->fd_frames && dev->mtu == CANFD_MTU) { if (unlikely(size != CANFD_MTU && size != CAN_MTU)) - return -EINVAL; + goto put_dev; } else { if (unlikely(size != CAN_MTU)) - return -EINVAL; + goto put_dev; } - dev = dev_get_by_index(sock_net(sk), ifindex); - if (!dev) - return -ENXIO; - skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) @@ -770,7 +771,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err < 0) goto free_skb; - sock_tx_timestamp(sk, sk->sk_tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sk->sk_tsflags); skb->dev = dev; skb->sk = sk; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 57fcc6b4bf6e..2f126eff275d 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -580,9 +580,15 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, struct bio_vec bvec; int ret; - /* sendpage cannot properly handle pages with page_count == 0, - * we need to fallback to sendmsg if that's the case */ - if (page_count(page) >= 1) + /* + * sendpage cannot properly handle pages with page_count == 0, + * we need to fall back to sendmsg if that's the case. + * + * Same goes for slab pages: skb_can_coalesce() allows + * coalescing neighboring slab objects into a single frag which + * triggers one of hardened usercopy checks. + */ + if (page_count(page) >= 1 && !PageSlab(page)) return __ceph_tcp_sendpage(sock, page, offset, size, more); bvec.bv_page = page; diff --git a/net/core/dev.c b/net/core/dev.c index 77d43ae2a7bb..722d50dbf8a4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2175,6 +2175,20 @@ static bool remove_xps_queue_cpu(struct net_device *dev, return active; } +static void reset_xps_maps(struct net_device *dev, + struct xps_dev_maps *dev_maps, + bool is_rxqs_map) +{ + if (is_rxqs_map) { + static_key_slow_dec_cpuslocked(&xps_rxqs_needed); + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + } else { + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); + } + static_key_slow_dec_cpuslocked(&xps_needed); + kfree_rcu(dev_maps, rcu); +} + static void clean_xps_maps(struct net_device *dev, const unsigned long *mask, struct xps_dev_maps *dev_maps, unsigned int nr_ids, u16 offset, u16 count, bool is_rxqs_map) @@ -2186,18 +2200,15 @@ static void clean_xps_maps(struct net_device *dev, const unsigned long *mask, j < nr_ids;) active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); - if (!active) { - if (is_rxqs_map) { - RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); - } else { - RCU_INIT_POINTER(dev->xps_cpus_map, NULL); + if (!active) + reset_xps_maps(dev, dev_maps, is_rxqs_map); - for (i = offset + (count - 1); count--; i--) - netdev_queue_numa_node_write( - netdev_get_tx_queue(dev, i), - NUMA_NO_NODE); + if (!is_rxqs_map) { + for (i = offset + (count - 1); count--; i--) { + netdev_queue_numa_node_write( + netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); } - kfree_rcu(dev_maps, rcu); } } @@ -2234,10 +2245,6 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset, false); out_no_maps: - if (static_key_enabled(&xps_rxqs_needed)) - static_key_slow_dec_cpuslocked(&xps_rxqs_needed); - - static_key_slow_dec_cpuslocked(&xps_needed); mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } @@ -2355,9 +2362,12 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, if (!new_dev_maps) goto out_no_new_maps; - static_key_slow_inc_cpuslocked(&xps_needed); - if (is_rxqs_map) - static_key_slow_inc_cpuslocked(&xps_rxqs_needed); + if (!dev_maps) { + /* Increment static keys at most once per type */ + static_key_slow_inc_cpuslocked(&xps_needed); + if (is_rxqs_map) + static_key_slow_inc_cpuslocked(&xps_rxqs_needed); + } for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), j < nr_ids;) { @@ -2455,13 +2465,8 @@ out_no_new_maps: } /* free map if not active */ - if (!active) { - if (is_rxqs_map) - RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); - else - RCU_INIT_POINTER(dev->xps_cpus_map, NULL); - kfree_rcu(dev_maps, rcu); - } + if (!active) + reset_xps_maps(dev, dev_maps, is_rxqs_map); out_no_maps: mutex_unlock(&xps_map_mutex); @@ -3272,7 +3277,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de } skb = next; - if (netif_xmit_stopped(txq) && skb) { + if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } @@ -5009,7 +5014,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; - list_del(&skb->list); + skb_list_del_init(skb); __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; @@ -5165,7 +5170,7 @@ static void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(netdev_tstamp_prequeue, skb); - list_del(&skb->list); + skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); } @@ -5176,7 +5181,7 @@ static void netif_receive_skb_list_internal(struct list_head *head) rcu_read_lock(); list_for_each_entry_safe(skb, next, head, list) { xdp_prog = rcu_dereference(skb->dev->xdp_prog); - list_del(&skb->list); + skb_list_del_init(skb); if (do_xdp_generic(xdp_prog, skb) == XDP_PASS) list_add_tail(&skb->list, &sublist); } @@ -5195,7 +5200,7 @@ static void netif_receive_skb_list_internal(struct list_head *head) if (cpu >= 0) { /* Will be handled, remove from list */ - list_del(&skb->list); + skb_list_del_init(skb); enqueue_to_backlog(skb, cpu, &rflow->last_qtail); } } @@ -5655,6 +5660,10 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->vlan_tci = 0; skb->dev = napi->dev; skb->skb_iif = 0; + + /* eth_type_trans() assumes pkt_type is PACKET_HOST */ + skb->pkt_type = PACKET_HOST; + skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); @@ -5966,11 +5975,14 @@ bool napi_complete_done(struct napi_struct *n, int work_done) if (work_done) timeout = n->dev->gro_flush_timeout; + /* When the NAPI instance uses a timeout and keeps postponing + * it, we need to bound somehow the time packets are kept in + * the GRO layer + */ + napi_gro_flush(n, !!timeout); if (timeout) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); - else - napi_gro_flush(n, false); } if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ @@ -6197,8 +6209,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) - pr_err_once("netif_napi_add() called with weight %d on device %s\n", - weight, dev->name); + netdev_err_once(dev, "%s() called with weight %d\n", __func__, + weight); napi->weight = weight; list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; diff --git a/net/core/filter.c b/net/core/filter.c index e521c5ebc7d1..8d2c629501e2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; - u16 hnum = ntohs(tuple->ipv6.dport); int sdif = inet6_sdif(skb); if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0, src6, tuple->ipv6.sport, - dst6, hnum, + dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, - dst6, hnum, + dst6, tuple->ipv6.dport, dif, sdif, &udp_table, skb); #endif @@ -4891,22 +4890,23 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *net; family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6; - if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags)) + if (unlikely(family == AF_UNSPEC || flags || + !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (skb->dev) caller_net = dev_net(skb->dev); else caller_net = sock_net(skb->sk); - if (netns_id) { + if ((s32)netns_id < 0) { + net = caller_net; + sk = sk_lookup(net, tuple, skb, family, proto); + } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, skb, family, proto); put_net(net); - } else { - net = caller_net; - sk = sk_lookup(net, tuple, skb, family, proto); } if (sk) @@ -5436,8 +5436,8 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (size != size_default) return false; break; - case bpf_ctx_range(struct __sk_buff, flow_keys): - if (size != sizeof(struct bpf_flow_keys *)) + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): + if (size != sizeof(__u64)) return false; break; default: @@ -5465,7 +5465,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5490,7 +5490,7 @@ static bool cg_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): @@ -5531,7 +5531,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; } @@ -5757,7 +5757,7 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5959,7 +5959,7 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; } @@ -6040,7 +6040,7 @@ static bool flow_dissector_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): info->reg_type = PTR_TO_FLOW_KEYS; break; case bpf_ctx_range(struct __sk_buff, tc_classid): diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 676f3ad629f9..af68207ee56c 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -783,6 +783,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, /* Pass parameters to the BPF program */ cb->qdisc_cb.flow_keys = &flow_keys; flow_keys.nhoff = nhoff; + flow_keys.thoff = nhoff; bpf_compute_data_pointers((struct sk_buff *)skb); result = BPF_PROG_RUN(attached, skb); @@ -790,9 +791,12 @@ bool __skb_flow_dissect(const struct sk_buff *skb, /* Restore state */ memcpy(cb, &cb_saved, sizeof(cb_saved)); + flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len); + flow_keys.thoff = clamp_t(u16, flow_keys.thoff, + flow_keys.nhoff, skb->len); + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); - key_control->thoff = min_t(u16, key_control->thoff, skb->len); rcu_read_unlock(); return result == BPF_OK; } @@ -1166,8 +1170,8 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && + !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 4b54e5f107c6..acf45ddbe924 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -84,6 +84,7 @@ void gro_cells_destroy(struct gro_cells *gcells) for_each_possible_cpu(i) { struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); + napi_disable(&cell->napi); netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 41954e42a2de..5fa32c064baf 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2494,11 +2494,16 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_ifindex || - ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) { + ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request"); return -EINVAL; } + if (ndm->ndm_flags & ~NTF_PROXY) { + NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor dump request"); + return -EINVAL; + } + err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, extack); } else { diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5da9552b186b..2b9fdbc43205 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np) read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != + !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; err = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e01274bd5e3e..7819f7804eeb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = 0; } ret = dumpit(skb, cb); - if (ret < 0) + if (ret) break; } cb->family = idx; @@ -3800,6 +3800,9 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, { int err; + if (dev->type != ARPHRD_ETHER) + return -EINVAL; + netif_addr_lock_bh(dev); err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->uc); if (err) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 946de0e24c87..a8217e221e19 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4854,6 +4854,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) nf_reset(skb); nf_reset_trace(skb); +#ifdef CONFIG_NET_SWITCHDEV + skb->offload_fwd_mark = 0; + skb->offload_mr_fwd_mark = 0; +#endif + if (!xnet) return; @@ -4944,6 +4949,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * + * @skb: GSO skb + * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 56a99d0c9aa0..b7dbb3c976cd 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -94,6 +94,9 @@ int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, } while (len) { + if (sk_msg_full(dst)) + return -ENOSPC; + sge_len = sge->length - off; sge_off = sge->offset + off; if (sge_len > len) diff --git a/net/core/sock.c b/net/core/sock.c index 6fcc4bc07d19..080a880a1761 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && + protocol != IPPROTO_RAW && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 37b4667128a3..d67ec17f2cc8 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -28,6 +28,8 @@ static int two __maybe_unused = 2; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static long long_one __maybe_unused = 1; +static long long_max __maybe_unused = LONG_MAX; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -289,6 +291,17 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } + +static int +proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); +} #endif static struct ctl_table net_core_table[] = { @@ -398,10 +411,11 @@ static struct ctl_table net_core_table[] = { { .procname = "bpf_jit_limit", .data = &bpf_jit_limit, - .maxlen = sizeof(int), + .maxlen = sizeof(long), .mode = 0600, - .proc_handler = proc_dointvec_minmax_bpf_restricted, - .extra1 = &one, + .proc_handler = proc_dolongvec_minmax_bpf_restricted, + .extra1 = &long_one, + .extra2 = &long_max, }, #endif { diff --git a/net/dsa/master.c b/net/dsa/master.c index c90ee3227dea..5e8c9bef78bd 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -158,8 +158,31 @@ static void dsa_master_ethtool_teardown(struct net_device *dev) cpu_dp->orig_ethtool_ops = NULL; } +static ssize_t tagging_show(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_device *dev = to_net_dev(d); + struct dsa_port *cpu_dp = dev->dsa_ptr; + + return sprintf(buf, "%s\n", + dsa_tag_protocol_to_str(cpu_dp->tag_ops)); +} +static DEVICE_ATTR_RO(tagging); + +static struct attribute *dsa_slave_attrs[] = { + &dev_attr_tagging.attr, + NULL +}; + +static const struct attribute_group dsa_group = { + .name = "dsa", + .attrs = dsa_slave_attrs, +}; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { + int ret; + /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -168,11 +191,20 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) dev->dsa_ptr = cpu_dp; - return dsa_master_ethtool_setup(dev); + ret = dsa_master_ethtool_setup(dev); + if (ret) + return ret; + + ret = sysfs_create_group(&dev->dev.kobj, &dsa_group); + if (ret) + dsa_master_ethtool_teardown(dev); + + return ret; } void dsa_master_teardown(struct net_device *dev) { + sysfs_remove_group(&dev->dev.kobj, &dsa_group); dsa_master_ethtool_teardown(dev); dev->dsa_ptr = NULL; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7d0c19e7edcf..aec78f5aca72 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1058,27 +1058,6 @@ static struct device_type dsa_type = { .name = "dsa", }; -static ssize_t tagging_show(struct device *d, struct device_attribute *attr, - char *buf) -{ - struct net_device *dev = to_net_dev(d); - struct dsa_port *dp = dsa_slave_to_port(dev); - - return sprintf(buf, "%s\n", - dsa_tag_protocol_to_str(dp->cpu_dp->tag_ops)); -} -static DEVICE_ATTR_RO(tagging); - -static struct attribute *dsa_slave_attrs[] = { - &dev_attr_tagging.attr, - NULL -}; - -static const struct attribute_group dsa_group = { - .name = "dsa", - .attrs = dsa_slave_attrs, -}; - static void dsa_slave_phylink_validate(struct net_device *dev, unsigned long *supported, struct phylink_link_state *state) @@ -1374,14 +1353,8 @@ int dsa_slave_create(struct dsa_port *port) goto out_phy; } - ret = sysfs_create_group(&slave_dev->dev.kobj, &dsa_group); - if (ret) - goto out_unreg; - return 0; -out_unreg: - unregister_netdev(slave_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -1405,7 +1378,6 @@ void dsa_slave_destroy(struct net_device *slave_dev) rtnl_unlock(); dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); - sysfs_remove_group(&slave_dev->dev.kobj, &dsa_group); unregister_netdev(slave_dev); phylink_destroy(dp->pl); free_percpu(p->stats64); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a34602ae27de..608a6f4223fb 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -952,17 +952,18 @@ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ - if (ipv4_is_zeronet(addr)) + if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); - if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; + else if (IN_CLASSE(haddr)) + rc = 32; } return rc; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 4e5bc4b2f14e..1a4e9ff02762 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -998,7 +998,9 @@ next_chunk: if (!inet_diag_bc_sk(bc, sk)) goto next_normal; - sock_hold(sk); + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + goto next_normal; + num_arr[accum] = num; sk_arr[accum] = sk; if (++accum == SKARR_SZ) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bcb11f3a27c0..760a9e52e02b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - void *arg) + void *arg, + struct inet_frag_queue **prev) { struct inet_frags *f = nf->f; struct inet_frag_queue *q; - int err; q = inet_frag_alloc(nf, f, arg); - if (!q) + if (!q) { + *prev = ERR_PTR(-ENOMEM); return NULL; - + } mod_timer(&q->timer, jiffies + nf->timeout); - err = rhashtable_insert_fast(&nf->rhashtable, &q->node, - f->rhash_params); - if (err < 0) { + *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + &q->node, f->rhash_params); + if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); @@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_queue *fq; + struct inet_frag_queue *fq = NULL, *prev; if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) return NULL; rcu_read_lock(); - fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); - if (fq) { + prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (!prev) + fq = inet_frag_create(nf, key, &prev); + if (prev && !IS_ERR(prev)) { + fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; - rcu_read_unlock(); - return fq; } rcu_read_unlock(); - - return inet_frag_create(nf, key); + return fq; } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 32662e9e5d21..d5984d31ab93 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -72,6 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s if (unlikely(opt->optlen)) ip_forward_options(skb); + skb->tstamp = 0; return dst_output(net, sk, skb); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9b0158fa431f..867be8f7f1fa 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -346,10 +346,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct rb_node **rbn, *parent; struct sk_buff *skb1, *prev_tail; + int ihl, end, skb1_run_end; struct net_device *dev; unsigned int fragsize; int flags, offset; - int ihl, end; int err = -ENOENT; u8 ecn; @@ -419,7 +419,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * - * We do the same here for IPv4 (and increment an snmp counter). + * We do the same here for IPv4 (and increment an snmp counter) but + * we do not want to drop the whole queue in response to a duplicate + * fragment. */ err = -EINVAL; @@ -444,13 +446,17 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) do { parent = *rbn; skb1 = rb_to_skb(parent); + skb1_run_end = skb1->ip_defrag_offset + + FRAG_CB(skb1)->frag_run_len; if (end <= skb1->ip_defrag_offset) rbn = &parent->rb_left; - else if (offset >= skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len) + else if (offset >= skb1_run_end) rbn = &parent->rb_right; - else /* Found an overlap with skb1. */ - goto overlap; + else if (offset >= skb1->ip_defrag_offset && + end <= skb1_run_end) + goto err; /* No new data, potential duplicate */ + else + goto overlap; /* Found an overlap */ } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. @@ -515,6 +521,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct rb_node *rbn; int len; int ihlen; + int delta; int err; u8 ecn; @@ -556,10 +563,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, if (len > 65535) goto out_oversize; + delta = - head->truesize; + /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) goto out_nomem; + delta += head->truesize; + if (delta) + add_frag_mem_limit(qp->q.net, delta); + /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ @@ -722,10 +735,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) - return skb; - if (pskb_trim_rcsum(skb, netoff + len)) - return skb; + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { + kfree_skb(skb); + return NULL; + } + if (pskb_trim_rcsum(skb, netoff + len)) { + kfree_skb(skb); + return NULL; + } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 35a786c0aaa0..e609b08c9df4 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -547,7 +547,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, list_for_each_entry_safe(skb, next, head, list) { struct dst_entry *dst; - list_del(&skb->list); + skb_list_del_init(skb); /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ @@ -594,7 +594,7 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *dev = skb->dev; struct net *net = dev_net(dev); - list_del(&skb->list); + skb_list_del_init(skb); skb = ip_rcv_core(skb, net); if (skb == NULL) continue; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c09219e7f230..5dbec21856f4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -939,7 +939,7 @@ static int __ip_append_data(struct sock *sk, unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; - unsigned int pagedlen = 0; + unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; @@ -956,6 +956,7 @@ alloc_new_skb: if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; + pagedlen = 0; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..fffcc130900e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); @@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); @@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index dde671e97829..c248e0dccbe1 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; - iph->frag_off = df; + iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df; iph->protocol = proto; iph->tos = tos; iph->daddr = dst; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 88212615bf4c..2393e5c106bf 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -429,6 +429,8 @@ static int __init ic_defaults(void) ic_netmask = htonl(IN_CLASSB_NET); else if (IN_CLASSC(ntohl(ic_myaddr))) ic_netmask = htonl(IN_CLASSC_NET); + else if (IN_CLASSE(ntohl(ic_myaddr))) + ic_netmask = htonl(IN_CLASSE_NET); else { pr_err("IP-Config: Unable to guess netmask for address %pI4\n", &ic_myaddr); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a6defbec4f1b..e7a3879cedd0 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -69,6 +69,8 @@ #include <net/nexthop.h> #include <net/switchdev.h> +#include <linux/nospec.h> + struct ipmr_rule { struct fib_rule common; }; @@ -1612,6 +1614,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; + vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { @@ -1686,6 +1689,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; + vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index ce1512b02cb2..fd3f9e8a74da 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -81,9 +81,12 @@ static int __init masquerade_tg_init(void) int ret; ret = xt_register_target(&masquerade_tg_reg); + if (ret) + return ret; - if (ret == 0) - nf_nat_masquerade_ipv4_register_notifier(); + ret = nf_nat_masquerade_ipv4_register_notifier(); + if (ret) + xt_unregister_target(&masquerade_tg_reg); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index a9d5e013e555..41327bb99093 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -147,28 +147,50 @@ static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; -static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0); +static int masq_refcnt; +static DEFINE_MUTEX(masq_mutex); -void nf_nat_masquerade_ipv4_register_notifier(void) +int nf_nat_masquerade_ipv4_register_notifier(void) { + int ret = 0; + + mutex_lock(&masq_mutex); /* check if the notifier was already set */ - if (atomic_inc_return(&masquerade_notifier_refcount) > 1) - return; + if (++masq_refcnt > 1) + goto out_unlock; /* Register for device down reports */ - register_netdevice_notifier(&masq_dev_notifier); + ret = register_netdevice_notifier(&masq_dev_notifier); + if (ret) + goto err_dec; /* Register IP address change reports */ - register_inetaddr_notifier(&masq_inet_notifier); + ret = register_inetaddr_notifier(&masq_inet_notifier); + if (ret) + goto err_unregister; + + mutex_unlock(&masq_mutex); + return ret; + +err_unregister: + unregister_netdevice_notifier(&masq_dev_notifier); +err_dec: + masq_refcnt--; +out_unlock: + mutex_unlock(&masq_mutex); + return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier); void nf_nat_masquerade_ipv4_unregister_notifier(void) { + mutex_lock(&masq_mutex); /* check if the notifier still has clients */ - if (atomic_dec_return(&masquerade_notifier_refcount) > 0) - return; + if (--masq_refcnt > 0) + goto out_unlock; unregister_netdevice_notifier(&masq_dev_notifier); unregister_inetaddr_notifier(&masq_inet_notifier); +out_unlock: + mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier); diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index f1193e1e928a..6847de1d1db8 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -69,7 +69,9 @@ static int __init nft_masq_ipv4_module_init(void) if (ret < 0) return ret; - nf_nat_masquerade_ipv4_register_notifier(); + ret = nf_nat_masquerade_ipv4_register_notifier(); + if (ret) + nft_unregister_expr(&nft_masq_ipv4_type); return ret; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8ca3eb06ba04..169a652b3dd1 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -391,7 +391,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2868ef28ce52..a9d9555a973f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; u32 delta_us; - if (!delta) - delta = 1; - delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - tcp_rcv_rtt_update(tp, delta_us, 0); + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + tcp_rcv_rtt_update(tp, delta_us, 0); + } } } @@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - seq_rtt_us = ca_rtt_us = delta_us; + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + ca_rtt_us = seq_rtt_us; + } } rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) @@ -4268,7 +4272,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) * If the sack array is full, forget about the last one. */ if (this_sack >= TCP_NUM_SACKS) { - if (tp->compressed_ack) + if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) tcp_send_ack(sk); this_sack--; tp->rx_opt.num_sacks--; @@ -4363,6 +4367,7 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->has_rxtstamp) { TCP_SKB_CB(to)->has_rxtstamp = true; to->tstamp = from->tstamp; + skb_hwtstamps(to)->hwtstamp = skb_hwtstamps(from)->hwtstamp; } return true; @@ -5188,7 +5193,17 @@ send_now: if (!tcp_is_sack(tp) || tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr) goto send_now; - tp->compressed_ack++; + + if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { + tp->compressed_ack_rcv_nxt = tp->rcv_nxt; + if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, + tp->compressed_ack - TCP_FASTRETRANS_THRESH); + tp->compressed_ack = 0; + } + + if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH) + goto send_now; if (hrtimer_is_queued(&tp->compressed_ack_timer)) return; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9c34b97d365d..d1676d8a6ed7 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -180,10 +180,10 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, { struct tcp_sock *tp = tcp_sk(sk); - if (unlikely(tp->compressed_ack)) { + if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, - tp->compressed_ack); - tp->compressed_ack = 0; + tp->compressed_ack - TCP_FASTRETRANS_THRESH); + tp->compressed_ack = TCP_FASTRETRANS_THRESH; if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } @@ -1904,7 +1904,9 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, * This algorithm is from John Heffner. */ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, - bool *is_cwnd_limited, u32 max_segs) + bool *is_cwnd_limited, + bool *is_rwnd_limited, + u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 age, send_win, cong_win, limit, in_flight; @@ -1912,9 +1914,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, struct sk_buff *head; int win_divisor; - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) - goto send_now; - if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; @@ -1973,10 +1972,27 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if (age < (tp->srtt_us >> 4)) goto send_now; - /* Ok, it looks like it is advisable to defer. */ + /* Ok, it looks like it is advisable to defer. + * Three cases are tracked : + * 1) We are cwnd-limited + * 2) We are rwnd-limited + * 3) We are application limited. + */ + if (cong_win < send_win) { + if (cong_win <= skb->len) { + *is_cwnd_limited = true; + return true; + } + } else { + if (send_win <= skb->len) { + *is_rwnd_limited = true; + return true; + } + } - if (cong_win < send_win && cong_win <= skb->len) - *is_cwnd_limited = true; + /* If this packet won't get more data, do not wait. */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + goto send_now; return true; @@ -2356,7 +2372,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } else { if (!push_one && tcp_tso_should_defer(sk, skb, &is_cwnd_limited, - max_segs)) + &is_rwnd_limited, max_segs)) break; } @@ -2494,15 +2510,18 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; } skb = skb_rb_last(&sk->tcp_rtx_queue); + if (unlikely(!skb)) { + WARN_ONCE(tp->packets_out, + "invalid inflight: %u state %u cwnd %u mss %d\n", + tp->packets_out, sk->sk_state, tp->snd_cwnd, mss); + inet_csk(sk)->icsk_pending = 0; + return; + } /* At most one outstanding TLP retransmission. */ if (tp->tlp_high_seq) goto rearm_timer; - /* Retransmit last segment. */ - if (WARN_ON(!skb)) - goto rearm_timer; - if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; @@ -2920,7 +2939,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } return err; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 676020663ce8..f87dbc78b6bc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; + s32 remaining; start_ts = tcp_retransmit_stamp(sk); if (!icsk->icsk_user_timeout || !start_ts) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; - if (elapsed >= icsk->icsk_user_timeout) + remaining = icsk->icsk_user_timeout - elapsed; + if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ - else - return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed)); + + return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } /** @@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk, (boundary - linear_backoff_thresh) * TCP_RTO_MAX; timeout = jiffies_to_msecs(timeout); } - return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout; + return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ @@ -376,7 +378,7 @@ static void tcp_probe_timer(struct sock *sk) return; } - if (icsk->icsk_probes_out > max_probes) { + if (icsk->icsk_probes_out >= max_probes) { abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ @@ -482,11 +484,12 @@ void tcp_retransmit_timer(struct sock *sk) goto out_reset_timer; } + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { - int mib_idx; + int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) @@ -501,10 +504,9 @@ void tcp_retransmit_timer(struct sock *sk) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; - } else { - mib_idx = LINUX_MIB_TCPTIMEOUTS; } - __NET_INC_STATS(sock_net(sk), mib_idx); + if (mib_idx) + __NET_INC_STATS(sock_net(sk), mib_idx); } tcp_enter_loss(sk); @@ -740,7 +742,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - if (tp->compressed_ack) + if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) tcp_send_ack(sk); } else { if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 63a808d5af15..045597b9a7c0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -179,7 +179,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_work(struct work_struct *w); static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, bool send_na); -static void addrconf_dad_run(struct inet6_dev *idev); +static void addrconf_dad_run(struct inet6_dev *idev, bool restart); static void addrconf_rs_timer(struct timer_list *t); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); @@ -3439,6 +3439,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_change_info *change_info; struct netdev_notifier_changeupper_info *info; struct inet6_dev *idev = __in6_dev_get(dev); struct net *net = dev_net(dev); @@ -3513,7 +3514,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; } - if (idev) { + if (!IS_ERR_OR_NULL(idev)) { if (idev->if_flags & IF_READY) { /* device is already configured - * but resend MLD reports, we might @@ -3521,6 +3522,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, * multicast snooping switches */ ipv6_mc_up(idev); + change_info = ptr; + if (change_info->flags_changed & IFF_NOARP) + addrconf_dad_run(idev, true); rt6_sync_up(dev, RTNH_F_LINKDOWN); break; } @@ -3555,7 +3559,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!IS_ERR_OR_NULL(idev)) { if (run_pending) - addrconf_dad_run(idev); + addrconf_dad_run(idev, false); /* Device has an address by now */ rt6_sync_up(dev, RTNH_F_DEAD); @@ -4173,16 +4177,19 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, addrconf_verify_rtnl(); } -static void addrconf_dad_run(struct inet6_dev *idev) +static void addrconf_dad_run(struct inet6_dev *idev, bool restart) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); - if (ifp->flags & IFA_F_TENTATIVE && - ifp->state == INET6_IFADDR_STATE_DAD) + if ((ifp->flags & IFA_F_TENTATIVE && + ifp->state == INET6_IFADDR_STATE_DAD) || restart) { + if (restart) + ifp->state = INET6_IFADDR_STATE_PREDAD; addrconf_dad_kick(ifp); + } spin_unlock(&ifp->lock); } read_unlock_bh(&idev->lock); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3f4d61017a69..f0cd291034f0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1001,6 +1001,9 @@ static int __init inet6_init(void) err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; + err = ipv6_anycast_init(); + if (err) + goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; @@ -1091,6 +1094,8 @@ ipv6_frag_fail: ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: + ipv6_anycast_cleanup(); +ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 4e0ff7031edd..94999058e110 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -44,8 +44,22 @@ #include <net/checksum.h> +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT) +/* anycast address hash table + */ +static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(acaddr_hash_lock); + static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); +static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr) +{ + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + /* * socket join an anycast group */ @@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk) rtnl_unlock(); } +static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) +{ + unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); + + spin_lock(&acaddr_hash_lock); + hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); + spin_unlock(&acaddr_hash_lock); +} + +static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) +{ + spin_lock(&acaddr_hash_lock); + hlist_del_init_rcu(&aca->aca_addr_lst); + spin_unlock(&acaddr_hash_lock); +} + static void aca_get(struct ifacaddr6 *aca) { refcount_inc(&aca->aca_refcnt); } +static void aca_free_rcu(struct rcu_head *h) +{ + struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu); + + fib6_info_release(aca->aca_rt); + kfree(aca); +} + static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - fib6_info_release(ac->aca_rt); - kfree(ac); + call_rcu(&ac->rcu, aca_free_rcu); } } @@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, aca->aca_addr = *addr; fib6_info_hold(f6i); aca->aca_rt = f6i; + INIT_HLIST_NODE(&aca->aca_addr_lst); aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); + ipv6_add_acaddr_hash(net, aca); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) else idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); + addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -390,17 +433,25 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr) { + unsigned int hash = inet6_acaddr_hash(net, addr); + struct net_device *nh_dev; + struct ifacaddr6 *aca; bool found = false; rcu_read_lock(); if (dev) found = ipv6_chk_acast_dev(dev, addr); else - for_each_netdev_rcu(net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { + hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash], + aca_addr_lst) { + nh_dev = fib6_info_nh_dev(aca->aca_rt); + if (!nh_dev || !net_eq(dev_net(nh_dev), net)) + continue; + if (ipv6_addr_equal(&aca->aca_addr, addr)) { found = true; break; } + } rcu_read_unlock(); return found; } @@ -540,3 +591,24 @@ void ac6_proc_exit(struct net *net) remove_proc_entry("anycast6", net->proc_net); } #endif + +/* Init / cleanup code + */ +int __init ipv6_anycast_init(void) +{ + int i; + + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_acaddr_lst[i]); + return 0; +} + +void ipv6_anycast_cleanup(void) +{ + int i; + + spin_lock(&acaddr_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); + spin_unlock(&acaddr_hash_lock); +} diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1b8bc008b53b..ae3786132c23 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* fib entries are never clones */ if (arg.filter.flags & RTM_F_CLONED) - return skb->len; + goto out; w = (void *)cb->args[2]; if (!w) { @@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (arg.filter.dump_all_families) - return skb->len; + goto out; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); return -ENOENT; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 96577e742afd..c1d85830c906 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -95,7 +95,7 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk, list_for_each_entry_safe(skb, next, head, list) { struct dst_entry *dst; - list_del(&skb->list); + skb_list_del_init(skb); /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing */ @@ -296,7 +296,7 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *dev = skb->dev; struct net *net = dev_net(dev); - list_del(&skb->list); + skb_list_del_init(skb); skb = ip6_rcv_core(skb, dev, net); if (skb == NULL) continue; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 89e0d5118afe..4591ca4bdbe8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -195,37 +195,37 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); + unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu; - if (opt) { - unsigned int head_room; + head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); + if (opt) + head_room += opt->opt_nflen + opt->opt_flen; - /* First: exthdrs may take lots of space (~8K for now) - MAX_HEADER is not enough. - */ - head_room = opt->opt_nflen + opt->opt_flen; - seg_len += head_room; - head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); - - if (skb_headroom(skb) < head_room) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); - if (!skb2) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -ENOBUFS; - } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; + if (unlikely(skb_headroom(skb) < head_room)) { + struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); + if (!skb2) { + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + if (opt) { + seg_len += opt->opt_nflen + opt->opt_flen; + if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); + if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop, &fl6->saddr); @@ -378,6 +378,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); __IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); + skb->tstamp = 0; return dst_output(net, sk, skb); } @@ -1354,7 +1355,7 @@ emsgsize: unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; - unsigned int pagedlen = 0; + unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ if (skb) @@ -1378,6 +1379,7 @@ alloc_new_skb: if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; + pagedlen = 0; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a9d06d4dd057..99179b9c8384 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -901,6 +901,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; + ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) goto drop; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index b283f293ee4a..caad40d6e74d 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -15,7 +15,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { - struct sockaddr_in6 udp6_addr; + struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; @@ -42,6 +42,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, goto error; if (cfg->peer_udp_port) { + memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index eeaf7455d51e..706fe42e4928 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -318,6 +318,7 @@ static int vti6_rcv(struct sk_buff *skb) return 0; } + ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e2ea691e42c6..377a2ee5d9ad 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -52,6 +52,8 @@ #include <net/ip6_checksum.h> #include <linux/netconf.h> +#include <linux/nospec.h> + struct ip6mr_rule { struct fib_rule common; }; @@ -1841,6 +1843,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; + vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { @@ -1915,6 +1918,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; + vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); read_lock(&mrt_lock); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 5ae8e1c51079..8b075f0bc351 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, + .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : + rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 491f808e356a..29c7f1915a96 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void) int err; err = xt_register_target(&masquerade_tg6_reg); - if (err == 0) - nf_nat_masquerade_ipv6_register_notifier(); + if (err) + return err; + + err = nf_nat_masquerade_ipv6_register_notifier(); + if (err) + xt_unregister_target(&masquerade_tg6_reg); return err; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b8ac369f98ad..181da2c40f9a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -341,7 +341,7 @@ static bool nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) { struct sk_buff *fp, *head = fq->q.fragments; - int payload_len; + int payload_len, delta; u8 ecn; inet_frag_kill(&fq->q); @@ -363,10 +363,16 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic return false; } + delta = - head->truesize; + /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) return false; + delta += head->truesize; + if (delta) + add_frag_mem_limit(fq->q.net, delta); + /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ @@ -587,11 +593,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) */ ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len && - nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - else + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + if (nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; + skb->_skb_refdst = orefdst; + } else { skb_dst_drop(skb); + } out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 3e4bf2286abe..0ad0da5a2600 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work) * of ipv6 addresses being deleted), we also need to add an upper * limit to the number of queued work items. */ -static int masq_inet_event(struct notifier_block *this, - unsigned long event, void *ptr) +static int masq_inet6_event(struct notifier_block *this, + unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; @@ -171,30 +171,53 @@ static int masq_inet_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct notifier_block masq_inet_notifier = { - .notifier_call = masq_inet_event, +static struct notifier_block masq_inet6_notifier = { + .notifier_call = masq_inet6_event, }; -static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0); +static int masq_refcnt; +static DEFINE_MUTEX(masq_mutex); -void nf_nat_masquerade_ipv6_register_notifier(void) +int nf_nat_masquerade_ipv6_register_notifier(void) { + int ret = 0; + + mutex_lock(&masq_mutex); /* check if the notifier is already set */ - if (atomic_inc_return(&masquerade_notifier_refcount) > 1) - return; + if (++masq_refcnt > 1) + goto out_unlock; + + ret = register_netdevice_notifier(&masq_dev_notifier); + if (ret) + goto err_dec; + + ret = register_inet6addr_notifier(&masq_inet6_notifier); + if (ret) + goto err_unregister; - register_netdevice_notifier(&masq_dev_notifier); - register_inet6addr_notifier(&masq_inet_notifier); + mutex_unlock(&masq_mutex); + return ret; + +err_unregister: + unregister_netdevice_notifier(&masq_dev_notifier); +err_dec: + masq_refcnt--; +out_unlock: + mutex_unlock(&masq_mutex); + return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier); void nf_nat_masquerade_ipv6_unregister_notifier(void) { + mutex_lock(&masq_mutex); /* check if the notifier still has clients */ - if (atomic_dec_return(&masquerade_notifier_refcount) > 0) - return; + if (--masq_refcnt > 0) + goto out_unlock; - unregister_inet6addr_notifier(&masq_inet_notifier); + unregister_inet6addr_notifier(&masq_inet6_notifier); unregister_netdevice_notifier(&masq_dev_notifier); +out_unlock: + mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier); diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index dd0122f3cffe..e06c82e9dfcd 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void) if (ret < 0) return ret; - nf_nat_masquerade_ipv6_register_notifier(); + ret = nf_nat_masquerade_ipv6_register_notifier(); + if (ret) + nft_unregister_expr(&nft_masq_ipv6_type); return ret; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5e0efd3954e9..fc2b5e845fdf 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -658,6 +658,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->ip_summed = CHECKSUM_NONE; + skb_setup_tx_timestamp(skb, sockc->tsflags); + if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5c3c92713096..a5bb59ee50ac 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -281,7 +281,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); struct sk_buff *fp, *head = fq->q.fragments; - int payload_len; + int payload_len, delta; unsigned int nhoff; int sum_truesize; u8 ecn; @@ -322,10 +322,16 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, if (payload_len > IPV6_MAXPLEN) goto out_oversize; + delta = - head->truesize; + /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) goto out_oom; + delta += head->truesize; + if (delta) + add_frag_mem_limit(fq->q.net, delta); + /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ @@ -378,6 +384,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, if (skb_try_coalesce(head, fp, &headstolen, &delta)) { kfree_skb_partial(fp, headstolen); } else { + fp->sk = NULL; if (!skb_shinfo(head)->frag_list) skb_shinfo(head)->frag_list = fp; head->data_len += fp->len; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2a7423c39456..059f0531f7c1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2232,8 +2232,7 @@ static void ip6_link_failure(struct sk_buff *skb) if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { - if (dst_hold_safe(&rt->dst)) - rt6_remove_exception_rt(rt); + rt6_remove_exception_rt(rt); } else { struct fib6_info *from; struct fib6_node *fn; @@ -2360,10 +2359,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) { + int oif = sk->sk_bound_dev_if; struct dst_entry *dst; - ip6_update_pmtu(skb, sock_net(sk), mtu, - sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid); + if (!oif && skb->dev) + oif = l3mdev_master_ifindex(skb->dev); + + ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || @@ -3214,8 +3216,8 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) goto out; - if (dst_hold_safe(&rt->dst)) - rc = rt6_remove_exception_rt(rt); + + rc = rt6_remove_exception_rt(rt); out: return rc; } diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index a8854dd3e9c5..8181ee7e1e27 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -347,6 +347,7 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct ipv6hdr *hdr = ipv6_hdr(skb); struct flowi6 fl6; + memset(&fl6, 0, sizeof(fl6)); fl6.daddr = hdr->daddr; fl6.saddr = hdr->saddr; fl6.flowlabel = ip6_flowinfo(hdr); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 82cdf9020b53..26f1d435696a 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1490,12 +1490,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, goto err_sock; } - sk = sock->sk; - - sock_hold(sk); - tunnel->sock = sk; tunnel->l2tp_net = net; - pn = l2tp_pernet(net); spin_lock_bh(&pn->l2tp_tunnel_list_lock); @@ -1510,6 +1505,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + sk = sock->sk; + sock_hold(sk); + tunnel->sock = sk; + if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .sk_user_data = tunnel, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 51622333d460..818aa0060349 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2891,7 +2891,7 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) len = beacon->head_len + beacon->tail_len + beacon->beacon_ies_len + beacon->proberesp_ies_len + beacon->assocresp_ies_len + - beacon->probe_resp_len; + beacon->probe_resp_len + beacon->lci_len + beacon->civicloc_len; new_beacon = kzalloc(sizeof(*new_beacon) + len, GFP_KERNEL); if (!new_beacon) @@ -2934,8 +2934,9 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) memcpy(pos, beacon->probe_resp, beacon->probe_resp_len); pos += beacon->probe_resp_len; } - if (beacon->ftm_responder) - new_beacon->ftm_responder = beacon->ftm_responder; + + /* might copy -1, meaning no changes requested */ + new_beacon->ftm_responder = beacon->ftm_responder; if (beacon->lci) { new_beacon->lci_len = beacon->lci_len; new_beacon->lci = pos; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 5836ddeac9e3..3a0171a65db3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -7,6 +7,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1015,6 +1016,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, if (local->open_count == 0) ieee80211_clear_tx_pending(local); + sdata->vif.bss_conf.beacon_int = 0; + /* * If the interface goes down while suspended, presumably because * the device was unplugged and that happens before our resume, @@ -1949,6 +1952,8 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) WARN(local->open_count, "%s: open count remains %d\n", wiphy_name(local->hw.wiphy), local->open_count); + ieee80211_txq_teardown_flows(local); + mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 83e71e6b2ebe..7b8320d4a8e4 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1262,7 +1262,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) rtnl_unlock(); ieee80211_led_exit(local); ieee80211_wep_free(local); - ieee80211_txq_teardown_flows(local); fail_flows: destroy_workqueue(local->workqueue); fail_workqueue: @@ -1288,7 +1287,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&local->ifa6_notifier); #endif - ieee80211_txq_teardown_flows(local); rtnl_lock(); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index d2bc8d57c87e..bcf5ffc1567a 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2766,6 +2766,7 @@ static bool ieee80211_mark_sta_auth(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct sta_info *sta; + bool result = true; sdata_info(sdata, "authenticated\n"); ifmgd->auth_data->done = true; @@ -2778,15 +2779,18 @@ static bool ieee80211_mark_sta_auth(struct ieee80211_sub_if_data *sdata, sta = sta_info_get(sdata, bssid); if (!sta) { WARN_ONCE(1, "%s: STA %pM not found", sdata->name, bssid); - return false; + result = false; + goto out; } if (sta_info_move_state(sta, IEEE80211_STA_AUTH)) { sdata_info(sdata, "failed moving %pM to auth\n", bssid); - return false; + result = false; + goto out; } - mutex_unlock(&sdata->local->sta_mtx); - return true; +out: + mutex_unlock(&sdata->local->sta_mtx); + return result; } static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3bd3b5769797..428f7ad5f9b5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1403,6 +1403,7 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) return RX_CONTINUE; if (ieee80211_is_ctl(hdr->frame_control) || + ieee80211_is_nullfunc(hdr->frame_control) || ieee80211_is_qos_nullfunc(hdr->frame_control) || is_multicast_ether_addr(hdr->addr1)) return RX_CONTINUE; @@ -3063,7 +3064,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) cfg80211_sta_opmode_change_notify(sdata->dev, rx->sta->addr, &sta_opmode, - GFP_KERNEL); + GFP_ATOMIC); goto handled; } case WLAN_HT_ACTION_NOTIFY_CHANWIDTH: { @@ -3100,7 +3101,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) cfg80211_sta_opmode_change_notify(sdata->dev, rx->sta->addr, &sta_opmode, - GFP_KERNEL); + GFP_ATOMIC); goto handled; } default: diff --git a/net/mac80211/status.c b/net/mac80211/status.c index aa4afbf0abaf..3f0b96e1e02f 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -556,6 +556,11 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, } ieee80211_led_tx(local); + + if (skb_has_frag_list(skb)) { + kfree_skb_list(skb_shinfo(skb)->frag_list); + skb_shinfo(skb)->frag_list = NULL; + } } /* @@ -964,6 +969,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, /* Track when last TDLS packet was ACKed */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) sta->status_stats.last_tdls_pkt_time = jiffies; + } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + return; } else { ieee80211_lost_packet(sta, info); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e0ccee23fbcd..1f536ba573b4 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -439,8 +439,8 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (ieee80211_hw_check(&tx->local->hw, QUEUE_CONTROL)) info->hw_queue = tx->sdata->vif.cab_queue; - /* no stations in PS mode */ - if (!atomic_read(&ps->num_sta_ps)) + /* no stations in PS mode and no buffered packets */ + if (!atomic_read(&ps->num_sta_ps) && skb_queue_empty(&ps->bc_buf)) return TX_CONTINUE; info->flags |= IEEE80211_TX_CTL_SEND_AFTER_DTIM; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bc4bd247bb7d..1577f2f76060 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -55,11 +55,15 @@ MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); -/* When the nfnl mutex is held: */ +/* When the nfnl mutex or ip_set_ref_lock is held: */ #define ip_set_dereference(p) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&ip_set_ref_lock)) #define ip_set(inst, id) \ ip_set_dereference((inst)->ip_set_list)[id] +#define ip_set_ref_netlink(inst,id) \ + rcu_dereference_raw((inst)->ip_set_list)[id] /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -693,21 +697,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index) EXPORT_SYMBOL_GPL(ip_set_put_byindex); /* Get the name of a set behind a set index. - * We assume the set is referenced, so it does exist and - * can't be destroyed. The set cannot be renamed due to - * the referencing either. - * + * Set itself is protected by RCU, but its name isn't: to protect against + * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the + * name. */ -const char * -ip_set_name_byindex(struct net *net, ip_set_id_t index) +void +ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name) { - const struct ip_set *set = ip_set_rcu_get(net, index); + struct ip_set *set = ip_set_rcu_get(net, index); BUG_ON(!set); - BUG_ON(set->ref == 0); - /* Referenced, so it's safe */ - return set->name; + read_lock_bh(&ip_set_ref_lock); + strncpy(name, set->name, IPSET_MAXNAMELEN); + read_unlock_bh(&ip_set_ref_lock); } EXPORT_SYMBOL_GPL(ip_set_name_byindex); @@ -961,7 +964,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Wraparound */ goto cleanup; - list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ @@ -973,7 +976,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Use new list */ index = inst->ip_set_max; inst->ip_set_max = i; - kfree(tmp); + kvfree(tmp); ret = 0; } else if (ret) { goto cleanup; @@ -1153,7 +1156,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, if (!set) return -ENOENT; - read_lock_bh(&ip_set_ref_lock); + write_lock_bh(&ip_set_ref_lock); if (set->ref != 0) { ret = -IPSET_ERR_REFERENCED; goto out; @@ -1170,7 +1173,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, strncpy(set->name, name2, IPSET_MAXNAMELEN); out: - read_unlock_bh(&ip_set_ref_lock); + write_unlock_bh(&ip_set_ref_lock); return ret; } @@ -1252,7 +1255,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; ip_set_id_t index = (ip_set_id_t)cb->args[IPSET_CB_INDEX]; - struct ip_set *set = ip_set(inst, index); + struct ip_set *set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); @@ -1441,7 +1444,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - set = ip_set(inst, index); + set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); @@ -2059,7 +2062,7 @@ ip_set_net_init(struct net *net) if (inst->ip_set_max >= IPSET_INVALID_ID) inst->ip_set_max = IPSET_INVALID_ID - 1; - list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); if (!list) return -ENOMEM; inst->is_deleted = false; @@ -2087,7 +2090,7 @@ ip_set_net_exit(struct net *net) } } nfnl_unlock(NFNL_SUBSYS_IPSET); - kfree(rcu_dereference_protected(inst->ip_set_list, 1)); + kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index d391485a6acd..613e18e720a4 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -493,13 +493,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 072a658fde04..8da228da53ae 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; - struct list_set *map = set->data; - ip_set_put_byindex(map->net, e->id); ip_set_ext_destroy(set, e); kfree(e); } @@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu) static inline void list_set_del(struct ip_set *set, struct set_elem *e) { + struct list_set *map = set->data; + set->elements--; list_del_rcu(&e->list); + ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static inline void -list_set_replace(struct set_elem *e, struct set_elem *old) +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { + struct list_set *map = set->data; + list_replace_rcu(&old->list, &e->list); + ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } @@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) - list_set_replace(e, n); + list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) @@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set, const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; @@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set, nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_string(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(map->net, e->id))) + ip_set_name_byindex(map->net, e->id, name); + if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; @@ -526,8 +531,8 @@ nla_put_failure: ret = -EMSGSIZE; } else { cb->args[IPSET_CB_ARG0] = i; + ipset_nest_end(skb, atd); } - ipset_nest_end(skb, atd); out: rcu_read_unlock(); return ret; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 83395bf6dc35..432141f04af3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3980,6 +3980,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) static struct notifier_block ip_vs_dst_notifier = { .notifier_call = ip_vs_dst_event, +#ifdef CONFIG_IP_VS_IPV6 + .priority = ADDRCONF_NOTIFY_PRIORITY + 5, +#endif }; int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 02ca7df793f5..9cd180bda092 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -49,6 +49,7 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; + bool dead; struct rcu_head rcu_head; }; @@ -106,15 +107,16 @@ nf_conncount_add(struct nf_conncount_list *list, conn->zone = *zone; conn->cpu = raw_smp_processor_id(); conn->jiffies32 = (u32)jiffies; - spin_lock(&list->list_lock); + conn->dead = false; + spin_lock_bh(&list->list_lock); if (list->dead == true) { kmem_cache_free(conncount_conn_cachep, conn); - spin_unlock(&list->list_lock); + spin_unlock_bh(&list->list_lock); return NF_CONNCOUNT_SKIP; } list_add_tail(&conn->node, &list->head); list->count++; - spin_unlock(&list->list_lock); + spin_unlock_bh(&list->list_lock); return NF_CONNCOUNT_ADDED; } EXPORT_SYMBOL_GPL(nf_conncount_add); @@ -132,19 +134,22 @@ static bool conn_free(struct nf_conncount_list *list, { bool free_entry = false; - spin_lock(&list->list_lock); + spin_lock_bh(&list->list_lock); - if (list->count == 0) { - spin_unlock(&list->list_lock); - return free_entry; + if (conn->dead) { + spin_unlock_bh(&list->list_lock); + return free_entry; } list->count--; + conn->dead = true; list_del_rcu(&conn->node); - if (list->count == 0) + if (list->count == 0) { + list->dead = true; free_entry = true; + } - spin_unlock(&list->list_lock); + spin_unlock_bh(&list->list_lock); call_rcu(&conn->rcu_head, __conn_free); return free_entry; } @@ -245,7 +250,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list) { spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); - list->count = 1; + list->count = 0; list->dead = false; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); @@ -259,6 +264,7 @@ bool nf_conncount_gc_list(struct net *net, struct nf_conn *found_ct; unsigned int collected = 0; bool free_entry = false; + bool ret = false; list_for_each_entry_safe(conn, conn_n, &list->head, node) { found = find_or_evict(net, list, conn, &free_entry); @@ -288,7 +294,15 @@ bool nf_conncount_gc_list(struct net *net, if (collected > CONNCOUNT_GC_MAX_NODES) return false; } - return false; + + spin_lock_bh(&list->list_lock); + if (!list->count) { + list->dead = true; + ret = true; + } + spin_unlock_bh(&list->list_lock); + + return ret; } EXPORT_SYMBOL_GPL(nf_conncount_gc_list); @@ -309,11 +323,8 @@ static void tree_nodes_free(struct rb_root *root, while (gc_count) { rbconn = gc_nodes[--gc_count]; spin_lock(&rbconn->list.list_lock); - if (rbconn->list.count == 0 && rbconn->list.dead == false) { - rbconn->list.dead = true; - rb_erase(&rbconn->node, root); - call_rcu(&rbconn->rcu_head, __tree_nodes_free); - } + rb_erase(&rbconn->node, root); + call_rcu(&rbconn->rcu_head, __tree_nodes_free); spin_unlock(&rbconn->list.list_lock); } } @@ -414,8 +425,9 @@ insert_tree(struct net *net, nf_conncount_list_init(&rbconn->list); list_add(&conn->node, &rbconn->list.head); count = 1; + rbconn->list.count = count; - rb_link_node(&rbconn->node, parent, rbnode); + rb_link_node_rcu(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); out_unlock: spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ca1168d67fac..e92e749aff53 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1073,19 +1073,22 @@ static unsigned int early_drop_list(struct net *net, return drops; } -static noinline int early_drop(struct net *net, unsigned int _hash) +static noinline int early_drop(struct net *net, unsigned int hash) { - unsigned int i; + unsigned int i, bucket; for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned int hash, hsize, drops; + unsigned int hsize, drops; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hsize); - hash = reciprocal_scale(_hash++, hsize); + if (!i) + bucket = reciprocal_scale(hash, hsize); + else + bucket = (bucket + 1) % hsize; - drops = early_drop_list(net, &ct_hash[hash]); + drops = early_drop_list(net, &ct_hash[bucket]); rcu_read_unlock(); if (drops) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 171e9e122e5f..023c1445bc39 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -384,11 +384,6 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = }, }; -static inline struct nf_dccp_net *dccp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp; -} - static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh) @@ -401,7 +396,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: - dn = dccp_pernet(net); + dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; @@ -568,7 +563,7 @@ static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout; + timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; @@ -681,7 +676,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; @@ -814,7 +809,7 @@ static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, static int dccp_init_net(struct net *net) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); struct nf_proto_net *pn = &dn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e10e867e0b55..5da19d5fbc76 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -27,11 +27,6 @@ static bool nf_generic_should_process(u8 proto) } } -static inline struct nf_generic_net *generic_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.generic; -} - static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) @@ -58,7 +53,7 @@ static int generic_packet(struct nf_conn *ct, } if (!timeout) - timeout = &generic_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -72,7 +67,7 @@ static int generic_packet(struct nf_conn *ct, static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); unsigned int *timeout = data; if (!timeout) @@ -138,7 +133,7 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, static int generic_init_net(struct net *net) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 9b48dc8b4b88..2a5e56c6d8d9 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -43,24 +43,12 @@ #include <linux/netfilter/nf_conntrack_proto_gre.h> #include <linux/netfilter/nf_conntrack_pptp.h> -enum grep_conntrack { - GRE_CT_UNREPLIED, - GRE_CT_REPLIED, - GRE_CT_MAX -}; - static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_UNREPLIED] = 30*HZ, [GRE_CT_REPLIED] = 180*HZ, }; static unsigned int proto_gre_net_id __read_mostly; -struct netns_proto_gre { - struct nf_proto_net nf; - rwlock_t keymap_lock; - struct list_head keymap_list; - unsigned int gre_timeouts[GRE_CT_MAX]; -}; static inline struct netns_proto_gre *gre_pernet(struct net *net) { @@ -402,6 +390,8 @@ static int __init nf_ct_proto_gre_init(void) { int ret; + BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0); + ret = register_pernet_subsys(&proto_gre_net_ops); if (ret < 0) goto out_pernet; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 3598520bd19b..de64d8a5fdfd 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,11 +25,6 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static inline struct nf_icmp_net *icmp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp; -} - static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { @@ -103,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct, } if (!timeout) - timeout = &icmp_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -275,7 +270,7 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) @@ -337,7 +332,7 @@ static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmp_init_net(struct net *net) { - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmp_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 378618feed5d..a15eefb8e317 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,11 +30,6 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6; -} - static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, @@ -87,7 +82,7 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &icmpv6_pernet(net)->timeout; + return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -286,7 +281,7 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); @@ -348,7 +343,7 @@ static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmpv6_init_net(struct net *net) { - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmpv6_timeout; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 3d719d3eb9a3..d53e3e78f605 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -146,11 +146,6 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { } }; -static inline struct nf_sctp_net *sctp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -480,7 +475,7 @@ static int sctp_packet(struct nf_conn *ct, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = sctp_pernet(nf_ct_net(ct))->timeouts; + timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); @@ -599,7 +594,7 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; /* set default SCTP timeouts. */ @@ -736,7 +731,7 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int sctp_init_net(struct net *net) { - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); struct nf_proto_net *pn = &sn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1bcf9984d45e..4dcbd51a8e97 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -272,11 +272,6 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { } }; -static inline struct nf_tcp_net *tcp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -475,7 +470,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct tcphdr *tcph) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; @@ -767,7 +762,7 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); - const struct nf_tcp_net *tn = tcp_pernet(net); + const struct nf_tcp_net *tn = nf_tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; @@ -841,7 +836,7 @@ static int tcp_packet(struct nf_conn *ct, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; @@ -1283,7 +1278,7 @@ static unsigned int tcp_nlattr_tuple_size(void) static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; @@ -1508,7 +1503,7 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int tcp_init_net(struct net *net) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_proto_net *pn = &tn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index a7aa70370913..c879d8d78cfd 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -32,14 +32,9 @@ static const unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_REPLIED] = 180*HZ, }; -static inline struct nf_udp_net *udp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.udp; -} - static unsigned int *udp_get_timeouts(struct net *net) { - return udp_pernet(net)->timeouts; + return nf_udp_pernet(net)->timeouts; } static void udp_error_log(const struct sk_buff *skb, @@ -212,7 +207,7 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); if (!timeouts) timeouts = un->timeouts; @@ -292,7 +287,7 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int udp_init_net(struct net *net) { - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); struct nf_proto_net *pn = &un->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index a975efd6b8c3..9da303461069 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -115,12 +115,12 @@ static void nf_ct_sack_block_adjust(struct sk_buff *skb, /* TCP SACK sequence number adjustment */ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, unsigned int protoff, - struct tcphdr *tcph, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - unsigned int dir, optoff, optend; + struct tcphdr *tcph = (void *)skb->data + protoff; struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); + unsigned int dir, optoff, optend; optoff = protoff + sizeof(struct tcphdr); optend = protoff + tcph->doff * 4; @@ -128,6 +128,7 @@ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, if (!skb_make_writable(skb, optend)) return 0; + tcph = (void *)skb->data + protoff; dir = CTINFO2DIR(ctinfo); while (optoff < optend) { @@ -207,7 +208,7 @@ int nf_ct_seq_adjust(struct sk_buff *skb, ntohl(newack)); tcph->ack_seq = newack; - res = nf_ct_sack_adjust(skb, protoff, tcph, ct, ctinfo); + res = nf_ct_sack_adjust(skb, protoff, ct, ctinfo); out: spin_unlock_bh(&ct->lock); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index e2b196054dfc..2268b10a9dcf 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -117,7 +117,8 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; - dst_hold(dst); + if (!dst_hold_safe(dst)) + return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 42487d01a3ed..6e548d7c9f67 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1216,7 +1216,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; - if (basechain->stats && nft_dump_stats(skb, basechain->stats)) + if (rcu_access_pointer(basechain->stats) && + nft_dump_stats(skb, rcu_dereference(basechain->stats))) goto nla_put_failure; } @@ -1392,7 +1393,8 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) return newstats; } -static void nft_chain_stats_replace(struct nft_base_chain *chain, +static void nft_chain_stats_replace(struct net *net, + struct nft_base_chain *chain, struct nft_stats __percpu *newstats) { struct nft_stats __percpu *oldstats; @@ -1400,8 +1402,9 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain, if (newstats == NULL) return; - if (chain->stats) { - oldstats = nfnl_dereference(chain->stats, NFNL_SUBSYS_NFTABLES); + if (rcu_access_pointer(chain->stats)) { + oldstats = rcu_dereference_protected(chain->stats, + lockdep_commit_lock_is_held(net)); rcu_assign_pointer(chain->stats, newstats); synchronize_rcu(); free_percpu(oldstats); @@ -1439,9 +1442,10 @@ static void nf_tables_chain_destroy(struct nft_ctx *ctx) struct nft_base_chain *basechain = nft_base_chain(chain); module_put(basechain->type->owner); - free_percpu(basechain->stats); - if (basechain->stats) + if (rcu_access_pointer(basechain->stats)) { static_branch_dec(&nft_counters_enabled); + free_percpu(rcu_dereference_raw(basechain->stats)); + } kfree(chain->name); kfree(basechain); } else { @@ -1590,7 +1594,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, kfree(basechain); return PTR_ERR(stats); } - basechain->stats = stats; + rcu_assign_pointer(basechain->stats, stats); static_branch_inc(&nft_counters_enabled); } @@ -2457,7 +2461,7 @@ err: static void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { - struct nft_expr *expr; + struct nft_expr *expr, *next; /* * Careful: some expressions might not be initialized in case this @@ -2465,8 +2469,9 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, */ expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { + next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); - expr = nft_expr_next(expr); + expr = next; } kfree(rule); } @@ -2589,17 +2594,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, if (chain->use == UINT_MAX) return -EOVERFLOW; - } - - if (nla[NFTA_RULE_POSITION]) { - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) - return -EOPNOTSUPP; - pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); - old_rule = __nft_rule_lookup(chain, pos_handle); - if (IS_ERR(old_rule)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); - return PTR_ERR(old_rule); + if (nla[NFTA_RULE_POSITION]) { + pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); + old_rule = __nft_rule_lookup(chain, pos_handle); + if (IS_ERR(old_rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); + return PTR_ERR(old_rule); + } } } @@ -2669,21 +2671,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (!nft_is_active_next(net, old_rule)) { - err = -ENOENT; - goto err2; - } - trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, - old_rule); + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; goto err2; } - nft_deactivate_next(net, old_rule); - chain->use--; - - if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { - err = -ENOMEM; + err = nft_delrule(&ctx, old_rule); + if (err < 0) { + nft_trans_destroy(trans); goto err2; } @@ -6189,7 +6184,8 @@ static void nft_chain_commit_update(struct nft_trans *trans) return; basechain = nft_base_chain(trans->ctx.chain); - nft_chain_stats_replace(basechain, nft_trans_chain_stats(trans)); + nft_chain_stats_replace(trans->ctx.net, basechain, + nft_trans_chain_stats(trans)); switch (nft_trans_chain_policy(trans)) { case NF_DROP: @@ -6324,7 +6320,7 @@ static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules) call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old); } -static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *chain) +static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) { struct nft_rule **g0, **g1; bool next_genbit; @@ -6441,11 +6437,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) /* step 2. Make rules_gen_X visible to packet path */ list_for_each_entry(table, &net->nft.tables, list) { - list_for_each_entry(chain, &table->chains, list) { - if (!nft_is_active_next(net, chain)) - continue; - nf_tables_commit_chain_active(net, chain); - } + list_for_each_entry(chain, &table->chains, list) + nf_tables_commit_chain(net, chain); } /* diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 3fbce3b9c5ec..a50500232b0a 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -101,7 +101,7 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, struct nft_stats *stats; base_chain = nft_base_chain(chain); - if (!base_chain->stats) + if (!rcu_access_pointer(base_chain->stats)) return; local_bh_disable(); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index e7a50af1b3d6..109b0d27345a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -382,7 +382,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 l3num, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -408,7 +409,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; @@ -430,6 +431,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -442,12 +444,55 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l4num); - /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &nf_icmp_pernet(net)->timeout; + break; + case IPPROTO_TCP: + timeouts = nf_tcp_pernet(net)->timeouts; + break; + case IPPROTO_UDP: /* fallthrough */ + case IPPROTO_UDPLITE: + timeouts = nf_udp_pernet(net)->timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = nf_dccp_pernet(net)->dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &nf_icmpv6_pernet(net)->timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = nf_sctp_pernet(net)->timeouts; +#endif + break; + case IPPROTO_GRE: +#ifdef CONFIG_NF_CT_PROTO_GRE + if (l4proto->net_id) { + struct netns_proto_gre *net_gre; + + net_gre = net_generic(net, *l4proto->net_id); + timeouts = net_gre->gre_timeouts; + } +#endif + break; + case 255: + timeouts = &nf_generic_pernet(net)->timeout; + break; + default: + WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto); + break; } + if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -458,8 +503,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l3num, - l4proto); + l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 768292eac2a4..7334e0b80a5e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -54,9 +54,11 @@ static bool nft_xt_put(struct nft_xt *xt) return false; } -static int nft_compat_chain_validate_dependency(const char *tablename, - const struct nft_chain *chain) +static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, + const char *tablename) { + enum nft_chain_types type = NFT_CHAIN_T_DEFAULT; + const struct nft_chain *chain = ctx->chain; const struct nft_base_chain *basechain; if (!tablename || @@ -64,9 +66,12 @@ static int nft_compat_chain_validate_dependency(const char *tablename, return 0; basechain = nft_base_chain(chain); - if (strcmp(tablename, "nat") == 0 && - basechain->type->type != NFT_CHAIN_T_NAT) - return -EINVAL; + if (strcmp(tablename, "nat") == 0) { + if (ctx->family != NFPROTO_BRIDGE) + type = NFT_CHAIN_T_NAT; + if (basechain->type->type != type) + return -EINVAL; + } return 0; } @@ -342,8 +347,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(target->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; } @@ -516,6 +520,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, void *info) { struct xt_match *match = expr->ops->data; + struct module *me = match->me; struct xt_mtdtor_param par; par.net = ctx->net; @@ -526,7 +531,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, par.match->destroy(&par); if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(match->me); + module_put(me); } static void @@ -590,8 +595,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(match->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; } diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index e82d9a966c45..974525eb92df 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -214,7 +214,9 @@ static int __init nft_flow_offload_module_init(void) { int err; - register_netdevice_notifier(&flow_offload_netdev_notifier); + err = register_netdevice_notifier(&flow_offload_netdev_notifier); + if (err) + goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) @@ -224,6 +226,7 @@ static int __init nft_flow_offload_module_init(void) register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); +err: return err; } diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 649d1700ec5b..3cc1b3dc3c3c 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,7 +24,6 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; - struct nft_set *map; }; static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) @@ -48,34 +47,11 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_inc_gen(priv); } -static void nft_ng_inc_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_inc_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, - [NFTA_NG_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -101,22 +77,6 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_inc_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_inc_init(ctx, expr, tb); - - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -143,27 +103,10 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_inc_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_inc *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_INCREMENTAL, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static u32 nft_ng_random_gen(struct nft_ng_random *priv) @@ -183,25 +126,6 @@ static void nft_ng_random_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_random_gen(priv); } -static void nft_ng_random_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_random_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static int nft_ng_random_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -226,21 +150,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_random_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); @@ -249,22 +158,6 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_random_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_random *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_RANDOM, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - static struct nft_expr_type nft_ng_type; static const struct nft_expr_ops nft_ng_inc_ops = { .type = &nft_ng_type, @@ -274,14 +167,6 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; -static const struct nft_expr_ops nft_ng_inc_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), - .eval = nft_ng_inc_map_eval, - .init = nft_ng_inc_map_init, - .dump = nft_ng_inc_map_dump, -}; - static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -290,14 +175,6 @@ static const struct nft_expr_ops nft_ng_random_ops = { .dump = nft_ng_random_dump, }; -static const struct nft_expr_ops nft_ng_random_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), - .eval = nft_ng_random_map_eval, - .init = nft_ng_random_map_init, - .dump = nft_ng_random_map_dump, -}; - static const struct nft_expr_ops * nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { @@ -312,12 +189,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_random_map_ops; return &nft_ng_random_ops; } diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ca5e5d8c5ef8..b13618c764ec 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -50,7 +50,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; - if (nla_get_u8(tb[NFTA_OSF_TTL])) { + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) return -EINVAL; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index c6acfc2d9c84..eb4cbd244c3d 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -114,6 +114,22 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } +static int idletimer_check_sysfs_name(const char *name, unsigned int size) +{ + int ret; + + ret = xt_check_proc_name(name, size); + if (ret < 0) + return ret; + + if (!strcmp(name, "power") || + !strcmp(name, "subsystem") || + !strcmp(name, "uevent")) + return -EINVAL; + + return 0; +} + static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; @@ -124,6 +140,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); + if (ret < 0) + goto out_free_timer; + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index dec843cadf46..9e05c86ba5c4 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -201,18 +201,8 @@ static __net_init int xt_rateest_net_init(struct net *net) return 0; } -static void __net_exit xt_rateest_net_exit(struct net *net) -{ - struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); - int i; - - for (i = 0; i < ARRAY_SIZE(xn->hash); i++) - WARN_ON_ONCE(!hlist_empty(&xn->hash[i])); -} - static struct pernet_operations xt_rateest_net_ops = { .init = xt_rateest_net_init, - .exit = xt_rateest_net_exit, .id = &xt_rateest_id, .size = sizeof(struct xt_rateest_net), }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 3e7d259e5d8d..1ad4017f9b73 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -295,9 +295,10 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, /* copy match config into hashtable config */ ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3); - - if (ret) + if (ret) { + vfree(hinfo); return ret; + } hinfo->cfg.size = size; if (hinfo->cfg.max == 0) @@ -814,7 +815,6 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); - if (ret) return ret; @@ -830,7 +830,6 @@ hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); - if (ret) return ret; @@ -921,7 +920,6 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); - if (ret) return ret; @@ -940,7 +938,6 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); - if (ret) return ret; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6bb9f3cde0b0..3c023d6120f6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1706,7 +1706,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, nlk->flags &= ~NETLINK_F_EXT_ACK; err = 0; break; - case NETLINK_DUMP_STRICT_CHK: + case NETLINK_GET_STRICT_CHK: if (val) nlk->flags |= NETLINK_F_STRICT_CHK; else @@ -1806,7 +1806,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, return -EFAULT; err = 0; break; - case NETLINK_DUMP_STRICT_CHK: + case NETLINK_GET_STRICT_CHK: if (len < sizeof(int)) return -EINVAL; len = sizeof(int); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 6bec37ab4472..cd94f925495a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1166,7 +1166,7 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); if (err) { net_warn_ratelimited("openvswitch: zone: %u " - "execeeds conntrack limit\n", + "exceeds conntrack limit\n", info->zone.id); return err; } @@ -1203,7 +1203,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; - } else if (labels_nonzero(&info->labels.mask)) { + } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ec3095f13aae..5dda263b4a0a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1965,7 +1965,7 @@ retry: skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -2394,7 +2394,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb) void *ph; __u32 ts; - ph = skb_shinfo(skb)->destructor_arg; + ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); @@ -2460,8 +2460,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = po->sk.sk_priority; skb->mark = po->sk.sk_mark; skb->tstamp = sockc->transmit_time; - sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); - skb_shinfo(skb)->destructor_arg = ph.raw; + skb_setup_tx_timestamp(skb, sockc->tsflags); + skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); @@ -2627,6 +2627,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); + if (addr && dev && saddr->sll_halen < dev->addr_len) + goto out; } err = -ENXIO; @@ -2825,6 +2827,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) proto = saddr->sll_protocol; addr = saddr->sll_addr; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); + if (addr && dev && saddr->sll_halen < dev->addr_len) + goto out; } err = -ENXIO; @@ -2898,7 +2902,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { diff --git a/net/rds/message.c b/net/rds/message.c index 4b00b1152a5f..f139420ba1f6 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -308,16 +308,27 @@ out: /* * RDS ops use this to grab SG entries from the rm's sg pool. */ -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, + int *ret) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; - WARN_ON(rm->m_used_sgs + nents > rm->m_total_sgs); - WARN_ON(!nents); + if (WARN_ON(!ret)) + return NULL; - if (rm->m_used_sgs + nents > rm->m_total_sgs) + if (nents <= 0) { + pr_warn("rds: alloc sgs failed! nents <= 0\n"); + *ret = -EINVAL; return NULL; + } + + if (rm->m_used_sgs + nents > rm->m_total_sgs) { + pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", + rm->m_total_sgs, rm->m_used_sgs, nents); + *ret = -ENOMEM; + return NULL; + } sg_ret = &sg_first[rm->m_used_sgs]; sg_init_table(sg_ret, nents); @@ -332,6 +343,7 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in unsigned int i; int num_sgs = ceil(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); + int ret; rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) @@ -340,10 +352,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = ceil(total_len, PAGE_SIZE); - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); if (!rm->data.op_sg) { rds_message_put(rm); - return ERR_PTR(-ENOMEM); + return ERR_PTR(ret); } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 98237feb607a..182ab8430594 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -517,9 +517,10 @@ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) return tot_pages; } -int rds_rdma_extra_size(struct rds_rdma_args *args) +int rds_rdma_extra_size(struct rds_rdma_args *args, + struct rds_iov_vector *iov) { - struct rds_iovec vec; + struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; @@ -530,13 +531,23 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) if (args->nr_local == 0) return -EINVAL; + iov->iov = kcalloc(args->nr_local, + sizeof(struct rds_iovec), + GFP_KERNEL); + if (!iov->iov) + return -ENOMEM; + + vec = &iov->iov[0]; + + if (copy_from_user(vec, local_vec, args->nr_local * + sizeof(struct rds_iovec))) + return -EFAULT; + iov->len = args->nr_local; + /* figure out the number of pages in the vector */ - for (i = 0; i < args->nr_local; i++) { - if (copy_from_user(&vec, &local_vec[i], - sizeof(struct rds_iovec))) - return -EFAULT; + for (i = 0; i < args->nr_local; i++, vec++) { - nr_pages = rds_pages_in_vec(&vec); + nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; @@ -558,15 +569,15 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg) + struct cmsghdr *cmsg, + struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; - struct rds_iovec iovstack[UIO_FASTIOV], *iovs = iovstack; - int iov_size; + struct rds_iovec *iovs; unsigned int i, j; int ret = 0; @@ -586,31 +597,23 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_ret; } - /* Check whether to allocate the iovec area */ - iov_size = args->nr_local * sizeof(struct rds_iovec); - if (args->nr_local > UIO_FASTIOV) { - iovs = sock_kmalloc(rds_rs_to_sk(rs), iov_size, GFP_KERNEL); - if (!iovs) { - ret = -ENOMEM; - goto out_ret; - } + if (vec->len != args->nr_local) { + ret = -EINVAL; + goto out_ret; } - if (copy_from_user(iovs, (struct rds_iovec __user *)(unsigned long) args->local_vec_addr, iov_size)) { - ret = -EFAULT; - goto out; - } + iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; - goto out; + goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; - goto out; + goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); @@ -620,11 +623,9 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_active = 1; op->op_recverr = rs->rs_recverr; WARN_ON(!nr_pages); - op->op_sg = rds_message_alloc_sgs(rm, nr_pages); - if (!op->op_sg) { - ret = -ENOMEM; - goto out; - } + op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); + if (!op->op_sg) + goto out_pages; if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -635,7 +636,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; - goto out; + goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; @@ -681,7 +682,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if (ret < 0) - goto out; + goto out_pages; else ret = 0; @@ -714,13 +715,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; - goto out; + goto out_pages; } op->op_bytes = nr_bytes; -out: - if (iovs != iovstack) - sock_kfree_s(rds_rs_to_sk(rs), iovs, iov_size); +out_pages: kfree(pages); out_ret: if (ret) @@ -838,11 +837,9 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; - rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); - if (!rm->atomic.op_sg) { - ret = -ENOMEM; + rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret); + if (!rm->atomic.op_sg) goto err; - } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/rds.h b/net/rds/rds.h index 6bfaf05b63b2..02ec4a3b2799 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -386,6 +386,18 @@ static inline void rds_message_zcopy_queue_init(struct rds_msg_zcopy_queue *q) INIT_LIST_HEAD(&q->zcookie_head); } +struct rds_iov_vector { + struct rds_iovec *iov; + int len; +}; + +struct rds_iov_vector_arr { + struct rds_iov_vector *vec; + int len; + int indx; + int incr; +}; + struct rds_message { refcount_t m_refcount; struct list_head m_sock_item; @@ -827,7 +839,8 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, + int *ret); int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); @@ -904,13 +917,13 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen); int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen); int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen); void rds_rdma_drop_keys(struct rds_sock *rs); -int rds_rdma_extra_size(struct rds_rdma_args *args); -int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg); +int rds_rdma_extra_size(struct rds_rdma_args *args, + struct rds_iov_vector *iov); int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, - struct cmsghdr *cmsg); + struct cmsghdr *cmsg, + struct rds_iov_vector *vec); int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); void rds_rdma_free_op(struct rm_rdma_op *ro); diff --git a/net/rds/send.c b/net/rds/send.c index fe785ee819dd..3d822bad7de9 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -876,13 +876,18 @@ out: * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ -static int rds_rm_size(struct msghdr *msg, int num_sgs) +static int rds_rm_size(struct msghdr *msg, int num_sgs, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; bool zcopy_cookie = false; + struct rds_iov_vector *iov, *tmp_iov; + + if (num_sgs < 0) + return -EINVAL; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -893,8 +898,24 @@ static int rds_rm_size(struct msghdr *msg, int num_sgs) switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: + if (vct->indx >= vct->len) { + vct->len += vct->incr; + tmp_iov = + krealloc(vct->vec, + vct->len * + sizeof(struct rds_iov_vector), + GFP_KERNEL); + if (!tmp_iov) { + vct->len -= vct->incr; + return -ENOMEM; + } + vct->vec = tmp_iov; + } + iov = &vct->vec[vct->indx]; + memset(iov, 0, sizeof(struct rds_iov_vector)); + vct->indx++; cmsg_groups |= 1; - retval = rds_rdma_extra_size(CMSG_DATA(cmsg)); + retval = rds_rdma_extra_size(CMSG_DATA(cmsg), iov); if (retval < 0) return retval; size += retval; @@ -951,10 +972,11 @@ static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, } static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, - struct msghdr *msg, int *allocated_mr) + struct msghdr *msg, int *allocated_mr, + struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; - int ret = 0; + int ret = 0, ind = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) @@ -968,7 +990,10 @@ static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, */ switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: - ret = rds_cmsg_rdma_args(rs, rm, cmsg); + if (ind >= vct->indx) + return -ENOMEM; + ret = rds_cmsg_rdma_args(rs, rm, cmsg, &vct->vec[ind]); + ind++; break; case RDS_CMSG_RDMA_DEST: @@ -1084,6 +1109,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = ceil(payload_len, PAGE_SIZE); int namelen; + struct rds_iov_vector_arr vct; + int ind; + + memset(&vct, 0, sizeof(vct)); + + /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ + vct.incr = 1; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ @@ -1220,7 +1252,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); } /* size of rm including all sgs */ - ret = rds_rm_size(msg, num_sgs); + ret = rds_rm_size(msg, num_sgs, &vct); if (ret < 0) goto out; @@ -1232,11 +1264,9 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); - if (!rm->data.op_sg) { - ret = -ENOMEM; + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); + if (!rm->data.op_sg) goto out; - } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; @@ -1270,7 +1300,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rm->m_conn_path = cpath; /* Parse any control messages the user may have included. */ - ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); + ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); if (ret) { /* Trigger connection so that its ready for the next retry */ if (ret == -EAGAIN) @@ -1348,9 +1378,18 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret) goto out; rds_message_put(rm); + + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + return payload_len; out: + for (ind = 0; ind < vct.indx; ind++) + kfree(vct.vec[ind].iov); + kfree(vct.vec); + /* If the user included a RDMA_MAP cmsg, we allocated a MR on the fly. * If the sendmsg goes through, we keep the MR. If it fails with EAGAIN * or in any other way, we need to destroy the MR again */ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 64362d078da8..a2522f9d71e2 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -375,17 +375,36 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * getting ACKs from the server. Returns a number representing the life state * which can be compared to that returned by a previous call. * - * If this is a client call, ping ACKs will be sent to the server to find out - * whether it's still responsive and whether the call is still alive on the - * server. + * If the life state stalls, rxrpc_kernel_probe_life() should be called and + * then 2RTT waited. */ -u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call) +u32 rxrpc_kernel_check_life(const struct socket *sock, + const struct rxrpc_call *call) { return call->acks_latest; } EXPORT_SYMBOL(rxrpc_kernel_check_life); /** + * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive + * @sock: The socket the call is on + * @call: The call to check + * + * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to + * find out whether a call is still alive by pinging it. This should cause the + * life state to be bumped in about 2*RTT. + * + * The must be called in TASK_RUNNING state on pain of might_sleep() objecting. + */ +void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call) +{ + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ack_ping_for_check_life); + rxrpc_send_ack_packet(call, true, NULL); +} +EXPORT_SYMBOL(rxrpc_kernel_probe_life); + +/** * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call. * @sock: The socket the call is on * @call: The call to query diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 382196e57a26..bc628acf4f4f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -611,6 +611,7 @@ struct rxrpc_call { * not hard-ACK'd packet follows this. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + u16 tx_backoff; /* Delay to insert due to Tx failure */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 8e7434e92097..468efc3660c0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; + ack_at += READ_ONCE(call->tx_backoff); ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); @@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work) container_of(work, struct rxrpc_call, processor); rxrpc_serial_t *send_ack; unsigned long now, next, t; + unsigned int iterations = 0; rxrpc_see_call(call); @@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + /* Limit the number of times we do this before returning to the manager */ + iterations++; + if (iterations > 5) + goto requeue; + if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; @@ -447,13 +454,16 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) { - __rxrpc_queue_call(call); - goto out; - } + if (call->events && call->state < RXRPC_CALL_COMPLETE) + goto requeue; out_put: rxrpc_put_call(call, rxrpc_call_put); out: _leave(""); + return; + +requeue: + __rxrpc_queue_call(call); + goto out; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 189418888839..736aa9281100 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -35,6 +35,21 @@ struct rxrpc_abort_buffer { static const char rxrpc_keepalive_string[] = ""; /* + * Increase Tx backoff on transmission failure and clear it on success. + */ +static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) +{ + if (ret < 0) { + u16 tx_backoff = READ_ONCE(call->tx_backoff); + + if (tx_backoff < HZ) + WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + } else { + WRITE_ONCE(call->tx_backoff, 0); + } +} + +/* * Arrange for a keepalive ping a certain time after we last transmitted. This * lets the far side know we're still interested in this call and helps keep * the route through any intervening firewall open. @@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, else trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, rxrpc_tx_point_call_ack); + rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), - true, true, + false, true, rxrpc_propose_ack_retry_tx); } else { spin_lock_bh(&call->lock); @@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) else trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, rxrpc_tx_point_call_abort); - + rxrpc_tx_backoff(call, ret); rxrpc_put_connection(conn); return ret; @@ -413,6 +429,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -445,9 +462,18 @@ done: rxrpc_reduce_call_timer(call, expect_rx_by, nowj, rxrpc_timer_set_for_normal); } - } - rxrpc_set_keepalive(call); + rxrpc_set_keepalive(call); + } else { + /* Cancel the call if the initial transmission fails, + * particularly if that's due to network routing issues that + * aren't going away anytime soon. The layer above can arrange + * the retransmission. + */ + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_USER_ABORT, ret); + } _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; @@ -506,6 +532,7 @@ send_fragmentable: else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); goto done; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1dae5f2b358f..c8cf4d10c435 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; - + if (skb2->tc_from_ingress) + skb2->tstamp = 0; /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index da3dd0f68cc2..2b372a06b432 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -201,7 +201,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, goto out_release; } } else { - return err; + ret = err; + goto out_free; } p = to_pedit(*a); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 052855d47354..ec8ec55e0fe8 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -27,10 +27,7 @@ struct tcf_police_params { u32 tcfp_ewma_rate; s64 tcfp_burst; u32 tcfp_mtu; - s64 tcfp_toks; - s64 tcfp_ptoks; s64 tcfp_mtu_ptoks; - s64 tcfp_t_c; struct psched_ratecfg rate; bool rate_present; struct psched_ratecfg peak; @@ -41,6 +38,11 @@ struct tcf_police_params { struct tcf_police { struct tc_action common; struct tcf_police_params __rcu *params; + + spinlock_t tcfp_lock ____cacheline_aligned_in_smp; + s64 tcfp_toks; + s64 tcfp_ptoks; + s64 tcfp_t_c; }; #define to_police(pc) ((struct tcf_police *)pc) @@ -83,7 +85,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, int ovr, int bind, bool rtnl_held, struct netlink_ext_ack *extack) { - int ret = 0, err; + int ret = 0, tcfp_result = TC_ACT_OK, err, size; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tc_police *parm; struct tcf_police *police; @@ -91,7 +93,6 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, police_net_id); struct tcf_police_params *new; bool exists = false; - int size; if (nla == NULL) return -EINVAL; @@ -122,6 +123,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return ret; } ret = ACT_P_CREATED; + spin_lock_init(&(to_police(*a)->tcfp_lock)); } else if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; @@ -157,6 +159,16 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, goto failure; } + if (tb[TCA_POLICE_RESULT]) { + tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { + NL_SET_ERR_MSG(extack, + "goto chain not allowed on fallback"); + err = -EINVAL; + goto failure; + } + } + new = kzalloc(sizeof(*new), GFP_KERNEL); if (unlikely(!new)) { err = -ENOMEM; @@ -164,6 +176,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } /* No failure allowed after this point */ + new->tcfp_result = tcfp_result; new->tcfp_mtu = parm->mtu; if (!new->tcfp_mtu) { new->tcfp_mtu = ~0; @@ -186,28 +199,20 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); - new->tcfp_toks = new->tcfp_burst; - if (new->peak_present) { + if (new->peak_present) new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, new->tcfp_mtu); - new->tcfp_ptoks = new->tcfp_mtu_ptoks; - } if (tb[TCA_POLICE_AVRATE]) new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); - if (tb[TCA_POLICE_RESULT]) { - new->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - if (TC_ACT_EXT_CMP(new->tcfp_result, TC_ACT_GOTO_CHAIN)) { - NL_SET_ERR_MSG(extack, - "goto chain not allowed on fallback"); - err = -EINVAL; - goto failure; - } - } - spin_lock_bh(&police->tcf_lock); - new->tcfp_t_c = ktime_get_ns(); + spin_lock_bh(&police->tcfp_lock); + police->tcfp_t_c = ktime_get_ns(); + police->tcfp_toks = new->tcfp_burst; + if (new->peak_present) + police->tcfp_ptoks = new->tcfp_mtu_ptoks; + spin_unlock_bh(&police->tcfp_lock); police->tcf_action = parm->action; rcu_swap_protected(police->params, new, @@ -257,25 +262,28 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, } now = ktime_get_ns(); - toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst); + spin_lock_bh(&police->tcfp_lock); + toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst); if (p->peak_present) { - ptoks = toks + p->tcfp_ptoks; + ptoks = toks + police->tcfp_ptoks; if (ptoks > p->tcfp_mtu_ptoks) ptoks = p->tcfp_mtu_ptoks; ptoks -= (s64)psched_l2t_ns(&p->peak, qdisc_pkt_len(skb)); } - toks += p->tcfp_toks; + toks += police->tcfp_toks; if (toks > p->tcfp_burst) toks = p->tcfp_burst; toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); if ((toks|ptoks) >= 0) { - p->tcfp_t_c = now; - p->tcfp_toks = toks; - p->tcfp_ptoks = ptoks; + police->tcfp_t_c = now; + police->tcfp_toks = toks; + police->tcfp_ptoks = ptoks; + spin_unlock_bh(&police->tcfp_lock); ret = p->tcfp_result; goto inc_drops; } + spin_unlock_bh(&police->tcfp_lock); } inc_overlimits: diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9aada2d0ef06..208d940464d7 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct netlink_ext_ack *extack) { const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; - int option_len, key_depth, msk_depth = 0; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); } @@ -1226,18 +1238,16 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout_idr; - if (!tc_skip_sw(fnew->flags)) { - if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) { - err = -EEXIST; - goto errout_mask; - } - - err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, - fnew->mask->filter_ht_params); - if (err) - goto errout_mask; + if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) { + err = -EEXIST; + goto errout_mask; } + err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + if (err) + goto errout_mask; + if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) @@ -1248,10 +1258,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (fold) { - if (!tc_skip_sw(fold->flags)) - rhashtable_remove_fast(&fold->mask->ht, - &fold->ht_node, - fold->mask->filter_ht_params); + rhashtable_remove_fast(&fold->mask->ht, + &fold->ht_node, + fold->mask->filter_ht_params); if (!tc_skip_hw(fold->flags)) fl_hw_destroy_filter(tp, fold, NULL); } @@ -1291,9 +1300,8 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = arg; - if (!tc_skip_sw(f->flags)) - rhashtable_remove_fast(&f->mask->ht, &f->ht_node, - f->mask->filter_ht_params); + rhashtable_remove_fast(&f->mask->ht, &f->ht_node, + f->mask->filter_ht_params); __fl_delete(tp, f, extack); *last = list_empty(&head->masks); return 0; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4b1af706896c..25a7cf6d380f 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -469,22 +469,29 @@ begin: goto begin; } prefetch(&skb->end); - f->credit -= qdisc_pkt_len(skb); + plen = qdisc_pkt_len(skb); + f->credit -= plen; - if (ktime_to_ns(skb->tstamp) || !q->rate_enable) + if (!q->rate_enable) goto out; rate = q->flow_max_rate; - if (skb->sk) - rate = min(skb->sk->sk_pacing_rate, rate); - - if (rate <= q->low_rate_threshold) { - f->credit = 0; - plen = qdisc_pkt_len(skb); - } else { - plen = max(qdisc_pkt_len(skb), q->quantum); - if (f->credit > 0) - goto out; + + /* If EDT time was provided for this skb, we need to + * update f->time_next_packet only if this qdisc enforces + * a flow max rate. + */ + if (!skb->tstamp) { + if (skb->sk) + rate = min(skb->sk->sk_pacing_rate, rate); + + if (rate <= q->low_rate_threshold) { + f->credit = 0; + } else { + plen = max(plen, q->quantum); + if (f->credit > 0) + goto out; + } } if (rate != ~0UL) { u64 len = (u64)plen * NSEC_PER_SEC; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 57b3ad9394ad..22cd46a60057 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -431,6 +431,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, int count = 1; int rc = NET_XMIT_SUCCESS; + /* Do not fool qdisc_drop_all() */ + skb->prev = NULL; + /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) ++count; @@ -648,15 +651,6 @@ deliver: */ skb->dev = qdisc_dev(sch); -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). - */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif - if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 6a28b96e779e..914750b819b2 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -118,9 +118,6 @@ static struct sctp_association *sctp_association_init( asoc->flowlabel = sp->flowlabel; asoc->dscp = sp->dscp; - /* Initialize default path MTU. */ - asoc->pathmtu = sp->pathmtu; - /* Set association default SACK delay */ asoc->sackdelay = msecs_to_jiffies(sp->sackdelay); asoc->sackfreq = sp->sackfreq; @@ -252,6 +249,10 @@ static struct sctp_association *sctp_association_init( 0, gfp)) goto fail_init; + /* Initialize default path MTU. */ + asoc->pathmtu = sp->pathmtu; + sctp_assoc_update_frag_point(asoc); + /* Assume that peer would support both address types unless we are * told otherwise. */ @@ -434,7 +435,7 @@ static void sctp_association_destroy(struct sctp_association *asoc) WARN_ON(atomic_read(&asoc->rmem_alloc)); - kfree(asoc); + kfree_rcu(asoc, rcu); SCTP_DBG_OBJCNT_DEC(assoc); } diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index ce8087846f05..d2048de86e7c 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -191,6 +191,12 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, * the packet */ max_data = asoc->frag_point; + if (unlikely(!max_data)) { + max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk), + sctp_datachk_len(&asoc->stream)); + pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%Zu)", + __func__, asoc, max_data); + } /* If the the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index fc6c5e4bffa5..7f0539db5604 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -101,6 +101,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, if (addr) { addr->a.v6.sin6_family = AF_INET6; addr->a.v6.sin6_port = 0; + addr->a.v6.sin6_flowinfo = 0; addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; diff --git a/net/sctp/output.c b/net/sctp/output.c index 67939ad99c01..025f48e14a91 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -118,6 +118,9 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, sctp_transport_route(tp, NULL, sp); if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); + } else if (!sctp_transport_pmtu_check(tp)) { + if (asoc->param_flags & SPP_PMTUD_ENABLE) + sctp_assoc_sync_pmtu(asoc); } if (asoc->pmtu_pending) { @@ -396,25 +399,6 @@ finish: return retval; } -static void sctp_packet_release_owner(struct sk_buff *skb) -{ - sk_free(skb->sk); -} - -static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk) -{ - skb_orphan(skb); - skb->sk = sk; - skb->destructor = sctp_packet_release_owner; - - /* - * The data chunks have already been accounted for in sctp_sendmsg(), - * therefore only reserve a single byte to keep socket around until - * the packet has been transmitted. - */ - refcount_inc(&sk->sk_wmem_alloc); -} - static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb) { if (SCTP_OUTPUT_CB(head)->last == head) @@ -426,6 +410,7 @@ static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb) head->truesize += skb->truesize; head->data_len += skb->len; head->len += skb->len; + refcount_add(skb->truesize, &head->sk->sk_wmem_alloc); __skb_header_release(skb); } @@ -601,7 +586,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) if (!head) goto out; skb_reserve(head, packet->overhead + MAX_HEADER); - sctp_packet_set_owner_w(head, sk); + skb_set_owner_w(head, sk); /* set sctp header */ sh = skb_push(head, sizeof(struct sctphdr)); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9cb854b05342..c37e1c2dec9d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_FCFS); + sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 4a4fd1971255..f4ac6c592e13 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2462,6 +2462,9 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, asoc->c.sinit_max_instreams, gfp)) goto clean_up; + /* Update frag_point when stream_interleave may get changed. */ + sctp_assoc_update_frag_point(asoc); + if (!asoc->temp && sctp_assoc_set_id(asoc, gfp)) goto clean_up; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 739f3e50120d..b8cebd5a87e5 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3324,8 +3324,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned __u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) : sizeof(struct sctp_data_chunk); - min_len = sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, - datasize); + min_len = sctp_min_frag_point(sp, datasize); max_len = SCTP_MAX_CHUNK_LEN - datasize; if (val < min_len || val > max_len) @@ -3940,32 +3939,16 @@ static int sctp_setsockopt_pr_supported(struct sock *sk, unsigned int optlen) { struct sctp_assoc_value params; - struct sctp_association *asoc; - int retval = -EINVAL; if (optlen != sizeof(params)) - goto out; - - if (copy_from_user(¶ms, optval, optlen)) { - retval = -EFAULT; - goto out; - } - - asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - asoc->prsctp_enable = !!params.assoc_value; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); + return -EINVAL; - sp->ep->prsctp_enable = !!params.assoc_value; - } else { - goto out; - } + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; - retval = 0; + sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value; -out: - return retval; + return 0; } static int sctp_setsockopt_default_prinfo(struct sock *sk, diff --git a/net/sctp/stream.c b/net/sctp/stream.c index ffb940d3b57c..3892e7630f3a 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -535,7 +535,6 @@ int sctp_send_add_streams(struct sctp_association *asoc, goto out; } - stream->incnt = incnt; stream->outcnt = outcnt; asoc->strreset_outstanding = !!out + !!in; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 80e2119f1c70..82cb0e5634bc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -127,6 +127,8 @@ static int smc_release(struct socket *sock) smc = smc_sk(sk); /* cleanup for a dangling non-blocking connect */ + if (smc->connect_info && sk->sk_state == SMC_INIT) + tcp_abort(smc->clcsock->sk, ECONNABORTED); flush_work(&smc->connect_work); kfree(smc->connect_info); smc->connect_info = NULL; @@ -145,8 +147,14 @@ static int smc_release(struct socket *sock) sk->sk_shutdown |= SHUTDOWN_MASK; } if (smc->clcsock) { + if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + /* wake up clcsock accept */ + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + } + mutex_lock(&smc->clcsock_release_lock); sock_release(smc->clcsock); smc->clcsock = NULL; + mutex_unlock(&smc->clcsock_release_lock); } if (smc->use_fallback) { if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) @@ -203,6 +211,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, spin_lock_init(&smc->conn.send_lock); sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); + mutex_init(&smc->clcsock_release_lock); return sk; } @@ -547,7 +556,8 @@ static int smc_connect_rdma(struct smc_sock *smc, mutex_lock(&smc_create_lgr_pending); local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev, - ibport, &aclc->lcl, NULL, 0); + ibport, ntoh24(aclc->qpn), &aclc->lcl, + NULL, 0); if (local_contact < 0) { if (local_contact == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ @@ -618,7 +628,7 @@ static int smc_connect_ism(struct smc_sock *smc, int rc = 0; mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, + local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0, NULL, ismdev, aclc->gid); if (local_contact < 0) return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0); @@ -818,7 +828,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) struct socket *new_clcsock = NULL; struct sock *lsk = &lsmc->sk; struct sock *new_sk; - int rc; + int rc = -EINVAL; release_sock(lsk); new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol); @@ -831,7 +841,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) } *new_smc = smc_sk(new_sk); - rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_lock(&lsmc->clcsock_release_lock); + if (lsmc->clcsock) + rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); if (rc < 0) lsk->sk_err = -rc; @@ -1083,7 +1096,7 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, int *local_contact) { /* allocate connection / link group */ - *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, + *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, 0, &pclc->lcl, NULL, 0); if (*local_contact < 0) { if (*local_contact == -ENOMEM) @@ -1107,7 +1120,7 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, struct smc_clc_msg_smcd *pclc_smcd; pclc_smcd = smc_get_clc_msg_smcd(pclc); - *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL, + *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, 0, NULL, ismdev, pclc_smcd->gid); if (*local_contact < 0) { if (*local_contact == -ENOMEM) diff --git a/net/smc/smc.h b/net/smc/smc.h index 08786ace6010..5721416d0605 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -219,6 +219,10 @@ struct smc_sock { /* smc sock container */ * started, waiting for unsent * data to be sent */ + struct mutex clcsock_release_lock; + /* protects clcsock of a listen + * socket + * */ }; static inline struct smc_sock *smc_sk(const struct sock *sk) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index ed5dcf03fe0b..db83332ac1c8 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -81,7 +81,7 @@ static inline void smc_cdc_add_pending_send(struct smc_connection *conn, sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE, "must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)"); BUILD_BUG_ON_MSG( - sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE, + offsetofend(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE, "must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()"); BUILD_BUG_ON_MSG( sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE, @@ -177,23 +177,24 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn) int smcd_cdc_msg_send(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + union smc_host_cursor curs; struct smcd_cdc_msg cdc; int rc, diff; memset(&cdc, 0, sizeof(cdc)); cdc.common.type = SMC_CDC_MSG_TYPE; - cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap; - cdc.prod_count = conn->local_tx_ctrl.prod.count; - - cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap; - cdc.cons_count = conn->local_tx_ctrl.cons.count; - cdc.prod_flags = conn->local_tx_ctrl.prod_flags; - cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags; + curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.prod.acurs); + cdc.prod.wrap = curs.wrap; + cdc.prod.count = curs.count; + curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.cons.acurs); + cdc.cons.wrap = curs.wrap; + cdc.cons.count = curs.count; + cdc.cons.prod_flags = conn->local_tx_ctrl.prod_flags; + cdc.cons.conn_state_flags = conn->local_tx_ctrl.conn_state_flags; rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1); if (rc) return rc; - smc_curs_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons, - conn); + smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn); /* Calculate transmitted data and increment free send buffer space */ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin, &conn->tx_curs_sent); @@ -331,13 +332,16 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc) static void smcd_cdc_rx_tsklet(unsigned long data) { struct smc_connection *conn = (struct smc_connection *)data; + struct smcd_cdc_msg *data_cdc; struct smcd_cdc_msg cdc; struct smc_sock *smc; if (!conn) return; - memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc)); + data_cdc = (struct smcd_cdc_msg *)conn->rmb_desc->cpu_addr; + smcd_curs_copy(&cdc.prod, &data_cdc->prod, conn); + smcd_curs_copy(&cdc.cons, &data_cdc->cons, conn); smc = container_of(conn, struct smc_sock, conn); smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc); } diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index 934df4473a7c..b5bfe38c7f9b 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -48,21 +48,31 @@ struct smc_cdc_msg { struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; u8 reserved[18]; -} __packed; /* format defined in RFC7609 */ +}; + +/* SMC-D cursor format */ +union smcd_cdc_cursor { + struct { + u16 wrap; + u32 count; + struct smc_cdc_producer_flags prod_flags; + struct smc_cdc_conn_state_flags conn_state_flags; + } __packed; +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_t acurs; /* for atomic processing */ +#else + u64 acurs; /* for atomic processing */ +#endif +} __aligned(8); /* CDC message for SMC-D */ struct smcd_cdc_msg { struct smc_wr_rx_hdr common; /* Type = 0xFE */ u8 res1[7]; - u16 prod_wrap; - u32 prod_count; - u8 res2[2]; - u16 cons_wrap; - u32 cons_count; - struct smc_cdc_producer_flags prod_flags; - struct smc_cdc_conn_state_flags conn_state_flags; + union smcd_cdc_cursor prod; + union smcd_cdc_cursor cons; u8 res3[8]; -} __packed; +} __aligned(8); static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { @@ -135,6 +145,21 @@ static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt, #endif } +static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, + union smcd_cdc_cursor *src, + struct smc_connection *conn) +{ +#ifndef KERNEL_HAS_ATOMIC64 + unsigned long flags; + + spin_lock_irqsave(&conn->acurs_lock, flags); + tgt->acurs = src->acurs; + spin_unlock_irqrestore(&conn->acurs_lock, flags); +#else + atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); +#endif +} + /* calculate cursor difference between old and new, where old <= new */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, @@ -222,12 +247,17 @@ static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smcd_cdc_msg *peer) { - local->prod.wrap = peer->prod_wrap; - local->prod.count = peer->prod_count; - local->cons.wrap = peer->cons_wrap; - local->cons.count = peer->cons_count; - local->prod_flags = peer->prod_flags; - local->conn_state_flags = peer->conn_state_flags; + union smc_host_cursor temp; + + temp.wrap = peer->prod.wrap; + temp.count = peer->prod.count; + atomic64_set(&local->prod.acurs, atomic64_read(&temp.acurs)); + + temp.wrap = peer->cons.wrap; + temp.count = peer->cons.count; + atomic64_set(&local->cons.acurs, atomic64_read(&temp.acurs)); + local->prod_flags = peer->cons.prod_flags; + local->conn_state_flags = peer->cons.conn_state_flags; } static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 18daebcef181..1c9fa7f0261a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -184,6 +184,8 @@ free: if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE) smc_llc_link_inactive(lnk); + if (lgr->is_smcd) + smc_ism_signal_shutdown(lgr); smc_lgr_free(lgr); } } @@ -485,7 +487,7 @@ void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport) } /* Called when SMC-D device is terminated or peer is lost */ -void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan) { struct smc_link_group *lgr, *l; LIST_HEAD(lgr_free_list); @@ -495,7 +497,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { if (lgr->is_smcd && lgr->smcd == dev && (!peer_gid || lgr->peer_gid == peer_gid) && - !list_empty(&lgr->list)) { + (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { __smc_lgr_terminate(lgr); list_move(&lgr->list, &lgr_free_list); } @@ -506,6 +508,8 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { list_del_init(&lgr->list); cancel_delayed_work_sync(&lgr->free_work); + if (!peer_gid && vlan == VLAN_VID_MASK) /* dev terminated? */ + smc_ism_signal_shutdown(lgr); smc_lgr_free(lgr); } } @@ -559,7 +563,7 @@ out: static bool smcr_lgr_match(struct smc_link_group *lgr, struct smc_clc_msg_local *lcl, - enum smc_lgr_role role) + enum smc_lgr_role role, u32 clcqpn) { return !memcmp(lgr->peer_systemid, lcl->id_for_peer, SMC_SYSTEMID_LEN) && @@ -567,7 +571,9 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, SMC_GID_SIZE) && !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac, sizeof(lcl->mac)) && - lgr->role == role; + lgr->role == role && + (lgr->role == SMC_SERV || + lgr->lnk[SMC_SINGLE_LINK].peer_qpn == clcqpn); } static bool smcd_lgr_match(struct smc_link_group *lgr, @@ -578,7 +584,7 @@ static bool smcd_lgr_match(struct smc_link_group *lgr, /* create a new SMC connection (and a new link group if necessary) */ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, - struct smc_ib_device *smcibdev, u8 ibport, + struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn, struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, u64 peer_gid) { @@ -603,7 +609,7 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, list_for_each_entry(lgr, &smc_lgr_list.list, list) { write_lock_bh(&lgr->conns_lock); if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) : - smcr_lgr_match(lgr, lcl, role)) && + smcr_lgr_match(lgr, lcl, role, clcqpn)) && !lgr->sync_err && lgr->vlan_id == vlan_id && (role == SMC_CLNT || @@ -1024,6 +1030,8 @@ void smc_core_exit(void) smc_llc_link_inactive(lnk); } cancel_delayed_work_sync(&lgr->free_work); + if (lgr->is_smcd) + smc_ism_signal_shutdown(lgr); smc_lgr_free(lgr); /* free link group */ } } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c156674733c9..cf98f4d6093e 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -247,7 +247,8 @@ void smc_lgr_free(struct smc_link_group *lgr); void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_terminate(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); -void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid); +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, + unsigned short vlan); int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, @@ -262,7 +263,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, - struct smc_ib_device *smcibdev, u8 ibport, + struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn, struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, u64 peer_gid); void smcd_conn_free(struct smc_connection *conn); diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index e36f21ce7252..2fff79db1a59 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -187,22 +187,28 @@ struct smc_ism_event_work { #define ISM_EVENT_REQUEST 0x0001 #define ISM_EVENT_RESPONSE 0x0002 #define ISM_EVENT_REQUEST_IR 0x00000001 +#define ISM_EVENT_CODE_SHUTDOWN 0x80 #define ISM_EVENT_CODE_TESTLINK 0x83 +union smcd_sw_event_info { + u64 info; + struct { + u8 uid[SMC_LGR_ID_SIZE]; + unsigned short vlan_id; + u16 code; + }; +}; + static void smcd_handle_sw_event(struct smc_ism_event_work *wrk) { - union { - u64 info; - struct { - u32 uid; - unsigned short vlanid; - u16 code; - }; - } ev_info; + union smcd_sw_event_info ev_info; + ev_info.info = wrk->event.info; switch (wrk->event.code) { + case ISM_EVENT_CODE_SHUTDOWN: /* Peer shut down DMBs */ + smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id); + break; case ISM_EVENT_CODE_TESTLINK: /* Activity timer */ - ev_info.info = wrk->event.info; if (ev_info.code == ISM_EVENT_REQUEST) { ev_info.code = ISM_EVENT_RESPONSE; wrk->smcd->ops->signal_event(wrk->smcd, @@ -215,6 +221,21 @@ static void smcd_handle_sw_event(struct smc_ism_event_work *wrk) } } +int smc_ism_signal_shutdown(struct smc_link_group *lgr) +{ + int rc; + union smcd_sw_event_info ev_info; + + memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE); + ev_info.vlan_id = lgr->vlan_id; + ev_info.code = ISM_EVENT_REQUEST; + rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid, + ISM_EVENT_REQUEST_IR, + ISM_EVENT_CODE_SHUTDOWN, + ev_info.info); + return rc; +} + /* worker for SMC-D events */ static void smc_ism_event_work(struct work_struct *work) { @@ -223,7 +244,7 @@ static void smc_ism_event_work(struct work_struct *work) switch (wrk->event.type) { case ISM_EVENT_GID: /* GID event, token is peer GID */ - smc_smcd_terminate(wrk->smcd, wrk->event.tok); + smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK); break; case ISM_EVENT_DMB: break; @@ -289,7 +310,7 @@ void smcd_unregister_dev(struct smcd_dev *smcd) spin_unlock(&smcd_dev_list.lock); flush_workqueue(smcd->event_wq); destroy_workqueue(smcd->event_wq); - smc_smcd_terminate(smcd, 0); + smc_smcd_terminate(smcd, 0, VLAN_VID_MASK); device_del(&smcd->dev); } diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index aee45b860b79..4da946cbfa29 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -45,4 +45,5 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size, int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos, void *data, size_t len); +int smc_ism_signal_shutdown(struct smc_link_group *lgr); #endif diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 3c458d279855..c2694750a6a8 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -215,12 +215,14 @@ int smc_wr_tx_put_slot(struct smc_link *link, pend = container_of(wr_pend_priv, struct smc_wr_tx_pend, priv); if (pend->idx < link->wr_tx_cnt) { + u32 idx = pend->idx; + /* clear the full struct smc_wr_tx_pend including .priv */ memset(&link->wr_tx_pends[pend->idx], 0, sizeof(link->wr_tx_pends[pend->idx])); memset(&link->wr_tx_bufs[pend->idx], 0, sizeof(link->wr_tx_bufs[pend->idx])); - test_and_clear_bit(pend->idx, link->wr_tx_mask); + test_and_clear_bit(idx, link->wr_tx_mask); return 1; } diff --git a/net/socket.c b/net/socket.c index 593826e11a53..334fcc617ef2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -853,7 +853,7 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct socket *sock = file->private_data; if (unlikely(!sock->ops->splice_read)) - return -EINVAL; + return generic_file_splice_read(file, ppos, pipe, len, flags); return sock->ops->splice_read(sock, ppos, pipe, len, flags); } diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index d8831b988b1e..ab4a3be1542a 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -281,13 +281,7 @@ static bool generic_key_to_expire(struct rpc_cred *cred) { struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred; - bool ret; - - get_rpccred(cred); - ret = test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); - put_rpccred(cred); - - return ret; + return test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); } static const struct rpc_credops generic_credops = { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 30f970cdc7f6..ba765473d1f0 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1239,36 +1239,59 @@ gss_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) return &gss_auth->rpc_auth; } +static struct gss_cred * +gss_dup_cred(struct gss_auth *gss_auth, struct gss_cred *gss_cred) +{ + struct gss_cred *new; + + /* Make a copy of the cred so that we can reference count it */ + new = kzalloc(sizeof(*gss_cred), GFP_NOIO); + if (new) { + struct auth_cred acred = { + .uid = gss_cred->gc_base.cr_uid, + }; + struct gss_cl_ctx *ctx = + rcu_dereference_protected(gss_cred->gc_ctx, 1); + + rpcauth_init_cred(&new->gc_base, &acred, + &gss_auth->rpc_auth, + &gss_nullops); + new->gc_base.cr_flags = 1UL << RPCAUTH_CRED_UPTODATE; + new->gc_service = gss_cred->gc_service; + new->gc_principal = gss_cred->gc_principal; + kref_get(&gss_auth->kref); + rcu_assign_pointer(new->gc_ctx, ctx); + gss_get_ctx(ctx); + } + return new; +} + /* - * gss_destroying_context will cause the RPCSEC_GSS to send a NULL RPC call + * gss_send_destroy_context will cause the RPCSEC_GSS to send a NULL RPC call * to the server with the GSS control procedure field set to * RPC_GSS_PROC_DESTROY. This should normally cause the server to release * all RPCSEC_GSS state associated with that context. */ -static int -gss_destroying_context(struct rpc_cred *cred) +static void +gss_send_destroy_context(struct rpc_cred *cred) { struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_auth *gss_auth = container_of(cred->cr_auth, struct gss_auth, rpc_auth); struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1); + struct gss_cred *new; struct rpc_task *task; - if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0) - return 0; + new = gss_dup_cred(gss_auth, gss_cred); + if (new) { + ctx->gc_proc = RPC_GSS_PROC_DESTROY; - ctx->gc_proc = RPC_GSS_PROC_DESTROY; - cred->cr_ops = &gss_nullops; + task = rpc_call_null(gss_auth->client, &new->gc_base, + RPC_TASK_ASYNC|RPC_TASK_SOFT); + if (!IS_ERR(task)) + rpc_put_task(task); - /* Take a reference to ensure the cred will be destroyed either - * by the RPC call or by the put_rpccred() below */ - get_rpccred(cred); - - task = rpc_call_null(gss_auth->client, cred, RPC_TASK_ASYNC|RPC_TASK_SOFT); - if (!IS_ERR(task)) - rpc_put_task(task); - - put_rpccred(cred); - return 1; + put_rpccred(&new->gc_base); + } } /* gss_destroy_cred (and gss_free_ctx) are used to clean up after failure @@ -1330,8 +1353,8 @@ static void gss_destroy_cred(struct rpc_cred *cred) { - if (gss_destroying_context(cred)) - return; + if (test_and_clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) + gss_send_destroy_context(cred); gss_destroy_nullcred(cred); } @@ -1768,6 +1791,7 @@ priv_release_snd_buf(struct rpc_rqst *rqstp) for (i=0; i < rqstp->rq_enc_pages_num; i++) __free_page(rqstp->rq_enc_pages[i]); kfree(rqstp->rq_enc_pages); + rqstp->rq_release_snd_buf = NULL; } static int @@ -1776,6 +1800,9 @@ alloc_enc_pages(struct rpc_rqst *rqstp) struct xdr_buf *snd_buf = &rqstp->rq_snd_buf; int first, last, i; + if (rqstp->rq_release_snd_buf) + rqstp->rq_release_snd_buf(rqstp); + if (snd_buf->page_len == 0) { rqstp->rq_enc_pages_num = 0; return 0; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index ae3b8145da35..24cbddc44c88 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1915,6 +1915,13 @@ call_connect_status(struct rpc_task *task) struct rpc_clnt *clnt = task->tk_client; int status = task->tk_status; + /* Check if the task was already transmitted */ + if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) { + xprt_end_transmit(task); + task->tk_action = call_transmit_status; + return; + } + dprint_status(task); trace_rpc_connect_status(task); @@ -1945,6 +1952,7 @@ call_connect_status(struct rpc_task *task) /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); /* fall through */ + case -ENOTCONN: case -EAGAIN: /* Check for timeouts before looping back to call_bind */ case -ETIMEDOUT: @@ -2302,6 +2310,7 @@ out_retry: task->tk_status = 0; /* Note: rpc_verify_header() may have freed the RPC slot */ if (task->tk_rqstp == req) { + xdr_free_bvec(&req->rq_rcv_buf); req->rq_reply_bytes_recvd = req->rq_rcv_buf.len = 0; if (task->tk_client->cl_discrtry) xprt_conditional_disconnect(req->rq_xprt, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 2bbb8d38d2bf..f302c6eb8779 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(xdr_commit_encode); static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, size_t nbytes) { - static __be32 *p; + __be32 *p; int space_left; int frag1bytes, frag2bytes; @@ -673,11 +673,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) WARN_ON_ONCE(xdr->iov); return; } - if (fraglen) { + if (fraglen) xdr->end = head->iov_base + head->iov_len; - xdr->page_ptr--; - } /* (otherwise assume xdr->end is already set) */ + xdr->page_ptr--; head->iov_len = len; buf->len = len; xdr->p = head->iov_base + head->iov_len; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 86bea4520c4d..73547d17d3c6 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -67,7 +67,6 @@ */ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_connect_status(struct rpc_task *task); static void xprt_destroy(struct rpc_xprt *xprt); static DEFINE_SPINLOCK(xprt_list_lock); @@ -680,7 +679,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(xprtiod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -EAGAIN); + else if (xprt->snd_task) + rpc_wake_up_queued_task_set_status(&xprt->pending, + xprt->snd_task, -ENOTCONN); spin_unlock_bh(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_force_disconnect); @@ -820,46 +821,25 @@ void xprt_connect(struct rpc_task *task) if (!xprt_connected(xprt)) { task->tk_timeout = task->tk_rqstp->rq_timeout; task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; - rpc_sleep_on(&xprt->pending, task, xprt_connect_status); + rpc_sleep_on(&xprt->pending, task, NULL); if (test_bit(XPRT_CLOSING, &xprt->state)) return; if (xprt_test_and_set_connecting(xprt)) return; - xprt->stat.connect_start = jiffies; - xprt->ops->connect(xprt, task); + /* Race breaker */ + if (!xprt_connected(xprt)) { + xprt->stat.connect_start = jiffies; + xprt->ops->connect(xprt, task); + } else { + xprt_clear_connecting(xprt); + task->tk_status = 0; + rpc_wake_up_queued_task(&xprt->pending, task); + } } xprt_release_write(xprt, task); } -static void xprt_connect_status(struct rpc_task *task) -{ - switch (task->tk_status) { - case 0: - dprintk("RPC: %5u xprt_connect_status: connection established\n", - task->tk_pid); - break; - case -ECONNREFUSED: - case -ECONNRESET: - case -ECONNABORTED: - case -ENETUNREACH: - case -EHOSTUNREACH: - case -EPIPE: - case -EAGAIN: - dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); - break; - case -ETIMEDOUT: - dprintk("RPC: %5u xprt_connect_status: connect attempt timed " - "out\n", task->tk_pid); - break; - default: - dprintk("RPC: %5u xprt_connect_status: error %d connecting to " - "server %s\n", task->tk_pid, -task->tk_status, - task->tk_rqstp->rq_xprt->servername); - task->tk_status = -EIO; - } -} - enum xprt_xid_rb_cmp { XID_RB_EQUAL, XID_RB_LEFT, @@ -1623,6 +1603,8 @@ xprt_request_init(struct rpc_task *task) req->rq_snd_buf.buflen = 0; req->rq_rcv_buf.len = 0; req->rq_rcv_buf.buflen = 0; + req->rq_snd_buf.bvec = NULL; + req->rq_rcv_buf.bvec = NULL; req->rq_release_snd_buf = NULL; xprt_reset_majortimeo(req); dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ae77c71c1f64..f0b3700cec95 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -330,18 +330,16 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp) { size_t i,n; - if (!(buf->flags & XDRBUF_SPARSE_PAGES)) + if (!want || !(buf->flags & XDRBUF_SPARSE_PAGES)) return want; - if (want > buf->page_len) - want = buf->page_len; n = (buf->page_base + want + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < n; i++) { if (buf->pages[i]) continue; buf->bvec[i].bv_page = buf->pages[i] = alloc_page(gfp); if (!buf->pages[i]) { - buf->page_len = (i * PAGE_SIZE) - buf->page_base; - return buf->page_len; + i *= PAGE_SIZE; + return i > buf->page_base ? i - buf->page_base : 0; } } return want; @@ -378,8 +376,8 @@ static ssize_t xs_read_discard(struct socket *sock, struct msghdr *msg, int flags, size_t count) { - struct kvec kvec = { 0 }; - return xs_read_kvec(sock, msg, flags | MSG_TRUNC, &kvec, count, 0); + iov_iter_discard(&msg->msg_iter, READ, count); + return sock_recvmsg(sock, msg, flags); } static ssize_t @@ -398,16 +396,17 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) goto out; if (ret != want) - goto eagain; + goto out; seek = 0; } else { seek -= buf->head[0].iov_len; offset += buf->head[0].iov_len; } - if (seek < buf->page_len) { - want = xs_alloc_sparse_pages(buf, - min_t(size_t, count - offset, buf->page_len), - GFP_NOWAIT); + + want = xs_alloc_sparse_pages(buf, + min_t(size_t, count - offset, buf->page_len), + GFP_NOWAIT); + if (seek < want) { ret = xs_read_bvec(sock, msg, flags, buf->bvec, xdr_buf_pagecount(buf), want + buf->page_base, @@ -418,12 +417,13 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) goto out; if (ret != want) - goto eagain; + goto out; seek = 0; } else { - seek -= buf->page_len; - offset += buf->page_len; + seek -= want; + offset += want; } + if (seek < buf->tail[0].iov_len) { want = min_t(size_t, count - offset, buf->tail[0].iov_len); ret = xs_read_kvec(sock, msg, flags, &buf->tail[0], want, seek); @@ -433,17 +433,13 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) goto out; if (ret != want) - goto eagain; + goto out; } else offset += buf->tail[0].iov_len; ret = -EMSGSIZE; - msg->msg_flags |= MSG_TRUNC; out: *read = offset - seek_init; return ret; -eagain: - ret = -EAGAIN; - goto out; sock_err: offset += seek; goto out; @@ -486,19 +482,20 @@ xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg, if (transport->recv.offset == transport->recv.len) { if (xs_read_stream_request_done(transport)) msg->msg_flags |= MSG_EOR; - return transport->recv.copied; + return read; } switch (ret) { + default: + break; + case -EFAULT: case -EMSGSIZE: - return transport->recv.copied; + msg->msg_flags |= MSG_TRUNC; + return read; case 0: return -ESHUTDOWN; - default: - if (ret < 0) - return ret; } - return -EAGAIN; + return ret < 0 ? ret : read; } static size_t @@ -537,7 +534,7 @@ xs_read_stream_call(struct sock_xprt *transport, struct msghdr *msg, int flags) ret = xs_read_stream_request(transport, msg, flags, req); if (msg->msg_flags & (MSG_EOR|MSG_TRUNC)) - xprt_complete_bc_request(req, ret); + xprt_complete_bc_request(req, transport->recv.copied); return ret; } @@ -570,7 +567,7 @@ xs_read_stream_reply(struct sock_xprt *transport, struct msghdr *msg, int flags) spin_lock(&xprt->queue_lock); if (msg->msg_flags & (MSG_EOR|MSG_TRUNC)) - xprt_complete_rqst(req->rq_task, ret); + xprt_complete_rqst(req->rq_task, transport->recv.copied); xprt_unpin_rqst(req); out: spin_unlock(&xprt->queue_lock); @@ -591,10 +588,8 @@ xs_read_stream(struct sock_xprt *transport, int flags) if (ret <= 0) goto out_err; transport->recv.offset = ret; - if (ret != want) { - ret = -EAGAIN; - goto out_err; - } + if (transport->recv.offset != want) + return transport->recv.offset; transport->recv.len = be32_to_cpu(transport->recv.fraghdr) & RPC_FRAGMENT_SIZE_MASK; transport->recv.offset -= sizeof(transport->recv.fraghdr); @@ -602,6 +597,9 @@ xs_read_stream(struct sock_xprt *transport, int flags) } switch (be32_to_cpu(transport->recv.calldir)) { + default: + msg.msg_flags |= MSG_TRUNC; + break; case RPC_CALL: ret = xs_read_stream_call(transport, &msg, flags); break; @@ -616,6 +614,9 @@ xs_read_stream(struct sock_xprt *transport, int flags) goto out_err; read += ret; if (transport->recv.offset < transport->recv.len) { + if (!(msg.msg_flags & MSG_TRUNC)) + return read; + msg.msg_flags = 0; ret = xs_read_discard(transport->sock, &msg, flags, transport->recv.len - transport->recv.offset); if (ret <= 0) @@ -623,7 +624,7 @@ xs_read_stream(struct sock_xprt *transport, int flags) transport->recv.offset += ret; read += ret; if (transport->recv.offset != transport->recv.len) - return -EAGAIN; + return read; } if (xs_read_stream_request_done(transport)) { trace_xs_stream_read_request(transport); @@ -633,13 +634,7 @@ xs_read_stream(struct sock_xprt *transport, int flags) transport->recv.len = 0; return read; out_err: - switch (ret) { - case 0: - case -ESHUTDOWN: - xprt_force_disconnect(&transport->xprt); - return -ESHUTDOWN; - } - return ret; + return ret != 0 ? ret : -ESHUTDOWN; } static void xs_stream_data_receive(struct sock_xprt *transport) @@ -648,12 +643,12 @@ static void xs_stream_data_receive(struct sock_xprt *transport) ssize_t ret = 0; mutex_lock(&transport->recv_mutex); + clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); if (transport->sock == NULL) goto out; - clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); for (;;) { ret = xs_read_stream(transport, MSG_DONTWAIT); - if (ret <= 0) + if (ret < 0) break; read += ret; cond_resched(); @@ -1222,6 +1217,8 @@ static void xs_reset_transport(struct sock_xprt *transport) trace_rpc_socket_close(xprt, sock); sock_release(sock); + + xprt_disconnect_done(xprt); } /** @@ -1242,8 +1239,6 @@ static void xs_close(struct rpc_xprt *xprt) xs_reset_transport(transport); xprt->reestablish_timeout = 0; - - xprt_disconnect_done(xprt); } static void xs_inject_disconnect(struct rpc_xprt *xprt) @@ -1345,10 +1340,10 @@ static void xs_udp_data_receive(struct sock_xprt *transport) int err; mutex_lock(&transport->recv_mutex); + clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); sk = transport->inet; if (sk == NULL) goto out; - clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); for (;;) { skb = skb_recv_udp(sk, 0, 1, &err); if (skb == NULL) @@ -1494,8 +1489,6 @@ static void xs_tcp_state_change(struct sock *sk) &transport->sock_state)) xprt_clear_connecting(xprt); clear_bit(XPRT_CLOSING, &xprt->state); - if (sk->sk_err) - xprt_wake_pending_tasks(xprt, -sk->sk_err); /* Trigger the socket release */ xs_tcp_force_close(xprt); } @@ -2097,8 +2090,8 @@ static void xs_udp_setup_socket(struct work_struct *work) trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: - xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); + xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); } @@ -2334,8 +2327,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) } status = -EAGAIN; out: - xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); + xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); } diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 2830709957bd..c138d68e8a69 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -166,7 +166,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, /* Apply trial address if we just left trial period */ if (!trial && !self) { - tipc_net_finalize(net, tn->trial_addr); + tipc_sched_net_finalize(net, tn->trial_addr); + msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } @@ -300,14 +301,12 @@ static void tipc_disc_timeout(struct timer_list *t) goto exit; } - /* Trial period over ? */ - if (!time_before(jiffies, tn->addr_trial_end)) { - /* Did we just leave it ? */ - if (!tipc_own_addr(net)) - tipc_net_finalize(net, tn->trial_addr); - - msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); - msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net)); + /* Did we just leave trial period ? */ + if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { + mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); + spin_unlock_bh(&d->lock); + tipc_sched_net_finalize(net, tn->trial_addr); + return; } /* Adjust timeout interval according to discovery phase */ @@ -319,6 +318,8 @@ static void tipc_disc_timeout(struct timer_list *t) d->timer_intv = TIPC_DISC_SLOW; else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST) d->timer_intv = TIPC_DISC_FAST; + msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); + msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); } mod_timer(&d->timer, jiffies + d->timer_intv); diff --git a/net/tipc/link.c b/net/tipc/link.c index 201c3b5bc96b..836727e363c4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; - /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (msg_peer_stopping(hdr)) + /* If peer is going down we want full re-establish cycle */ + if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - else if ((mtyp == RESET_MSG) || !link_is_up(l)) + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ + if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ - if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING)) + if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); diff --git a/net/tipc/net.c b/net/tipc/net.c index 62199cf5a56c..f076edb74338 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -104,6 +104,14 @@ * - A local spin_lock protecting the queue of subscriber events. */ +struct tipc_net_work { + struct work_struct work; + struct net *net; + u32 addr; +}; + +static void tipc_net_finalize(struct net *net, u32 addr); + int tipc_net_init(struct net *net, u8 *node_id, u32 addr) { if (tipc_own_id(net)) { @@ -119,17 +127,38 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr) return 0; } -void tipc_net_finalize(struct net *net, u32 addr) +static void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); - if (!cmpxchg(&tn->node_addr, 0, addr)) { - tipc_set_node_addr(net, addr); - tipc_named_reinit(net); - tipc_sk_reinit(net); - tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, - TIPC_CLUSTER_SCOPE, 0, addr); - } + if (cmpxchg(&tn->node_addr, 0, addr)) + return; + tipc_set_node_addr(net, addr); + tipc_named_reinit(net); + tipc_sk_reinit(net); + tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, + TIPC_CLUSTER_SCOPE, 0, addr); +} + +static void tipc_net_finalize_work(struct work_struct *work) +{ + struct tipc_net_work *fwork; + + fwork = container_of(work, struct tipc_net_work, work); + tipc_net_finalize(fwork->net, fwork->addr); + kfree(fwork); +} + +void tipc_sched_net_finalize(struct net *net, u32 addr) +{ + struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC); + + if (!fwork) + return; + INIT_WORK(&fwork->work, tipc_net_finalize_work); + fwork->net = net; + fwork->addr = addr; + schedule_work(&fwork->work); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/net.h b/net/tipc/net.h index 09ad02b50bb1..b7f2e364eb99 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -42,7 +42,7 @@ extern const struct nla_policy tipc_nl_net_policy[]; int tipc_net_init(struct net *net, u8 *node_id, u32 addr); -void tipc_net_finalize(struct net *net, u32 addr); +void tipc_sched_net_finalize(struct net *net, u32 addr); void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); diff --git a/net/tipc/node.c b/net/tipc/node.c index 2afc4f8c37a7..488019766433 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -584,12 +584,15 @@ static void tipc_node_clear_links(struct tipc_node *node) /* tipc_node_cleanup - delete nodes that does not * have active links for NODE_CLEANUP_AFTER time */ -static int tipc_node_cleanup(struct tipc_node *peer) +static bool tipc_node_cleanup(struct tipc_node *peer) { struct tipc_net *tn = tipc_net(peer->net); bool deleted = false; - spin_lock_bh(&tn->node_list_lock); + /* If lock held by tipc_node_stop() the node will be deleted anyway */ + if (!spin_trylock_bh(&tn->node_list_lock)) + return false; + tipc_node_write_lock(peer); if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 636e6131769d..8f34db2a9785 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -880,7 +880,6 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int blks = tsk_blocks(GROUP_H_SIZE + dlen); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_group *grp = tsk->group; struct net *net = sock_net(sk); struct tipc_member *mb = NULL; u32 node, port; @@ -894,7 +893,9 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, /* Block or return if destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tipc_dest_find(&tsk->cong_links, node, 0) && - !tipc_group_cong(grp, node, port, blks, &mb)); + tsk->group && + !tipc_group_cong(tsk->group, node, port, blks, + &mb)); if (unlikely(rc)) return rc; @@ -924,7 +925,6 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, struct tipc_sock *tsk = tipc_sk(sk); struct list_head *cong_links = &tsk->cong_links; int blks = tsk_blocks(GROUP_H_SIZE + dlen); - struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct tipc_member *first = NULL; struct tipc_member *mbr = NULL; @@ -941,9 +941,10 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, type = msg_nametype(hdr); inst = dest->addr.name.name.instance; scope = msg_lookup_scope(hdr); - exclude = tipc_group_exclude(grp); while (++lookups < 4) { + exclude = tipc_group_exclude(tsk->group); + first = NULL; /* Look for a non-congested destination member, if any */ @@ -952,7 +953,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, &dstcnt, exclude, false)) return -EHOSTUNREACH; tipc_dest_pop(&dsts, &node, &port); - cong = tipc_group_cong(grp, node, port, blks, &mbr); + cong = tipc_group_cong(tsk->group, node, port, blks, + &mbr); if (!cong) break; if (mbr == first) @@ -971,7 +973,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, /* Block or return if destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tipc_dest_find(cong_links, node, 0) && - !tipc_group_cong(grp, node, port, + tsk->group && + !tipc_group_cong(tsk->group, node, port, blks, &mbr)); if (unlikely(rc)) return rc; @@ -1006,8 +1009,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_group *grp = tsk->group; - struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_nlist *dsts; struct tipc_mc_method *method = &tsk->mc_method; bool ack = method->mandatory && method->rcast; int blks = tsk_blocks(MCAST_H_SIZE + dlen); @@ -1016,15 +1018,17 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sk_buff_head pkts; int rc = -EHOSTUNREACH; - if (!dsts->local && !dsts->remote) - return -EHOSTUNREACH; - /* Block or return if any destination link or member is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && - !tipc_group_bc_cong(grp, blks)); + rc = tipc_wait_for_cond(sock, &timeout, + !tsk->cong_link_cnt && tsk->group && + !tipc_group_bc_cong(tsk->group, blks)); if (unlikely(rc)) return rc; + dsts = tipc_group_dests(tsk->group); + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + /* Complete message header */ if (dest) { msg_set_type(hdr, TIPC_GRP_MCAST_MSG); @@ -1036,7 +1040,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, msg_set_hdr_sz(hdr, GROUP_H_SIZE); msg_set_destport(hdr, 0); msg_set_destnode(hdr, 0); - msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(tsk->group)); /* Avoid getting stuck with repeated forced replicasts */ msg_set_grp_bc_ack_req(hdr, ack); @@ -1555,16 +1559,17 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) /** * tipc_sk_anc_data_recv - optionally capture ancillary data for received message * @m: descriptor for message info - * @msg: received message header + * @skb: received message buffer * @tsk: TIPC port associated with message * * Note: Ancillary data is not captured if not requested by receiver. * * Returns 0 if successful, otherwise errno */ -static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg, +static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb, struct tipc_sock *tsk) { + struct tipc_msg *msg; u32 anc_data[3]; u32 err; u32 dest_type; @@ -1573,6 +1578,7 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg, if (likely(m->msg_controllen == 0)) return 0; + msg = buf_msg(skb); /* Optionally capture errored message object(s) */ err = msg ? msg_errcode(msg) : 0; @@ -1583,6 +1589,9 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg, if (res) return res; if (anc_data[1]) { + if (skb_linearize(skb)) + return -ENOMEM; + msg = buf_msg(skb); res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1], msg_data(msg)); if (res) @@ -1744,9 +1753,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, /* Collect msg meta data, including error code and rejected data */ tipc_sk_set_orig_addr(m, skb); - rc = tipc_sk_anc_data_recv(m, hdr, tsk); + rc = tipc_sk_anc_data_recv(m, skb, tsk); if (unlikely(rc)) goto exit; + hdr = buf_msg(skb); /* Capture data if non-error msg, otherwise just set return value */ if (likely(!err)) { @@ -1856,9 +1866,10 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Collect msg meta data, incl. error code and rejected data */ if (!copied) { tipc_sk_set_orig_addr(m, skb); - rc = tipc_sk_anc_data_recv(m, hdr, tsk); + rc = tipc_sk_anc_data_recv(m, skb, tsk); if (rc) break; + hdr = buf_msg(skb); } /* Copy data if msg ok, otherwise return error/partial data */ @@ -2717,11 +2728,15 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_start(&iter); while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) { - spin_lock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(&iter); + lock_sock(&tsk->sk); msg = &tsk->phdr; msg_set_prevnode(msg, tipc_own_addr(net)); msg_set_orignode(msg, tipc_own_addr(net)); - spin_unlock_bh(&tsk->sk.sk_lock.slock); + release_sock(&tsk->sk); + rhashtable_walk_start(&iter); + sock_put(&tsk->sk); } rhashtable_walk_stop(&iter); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 10dc59ce9c82..4d85d71f16e2 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -245,10 +245,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, } err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr); - if (err) { - kfree_skb(_skb); + if (err) goto out; - } } err = 0; out: @@ -681,6 +679,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, if (err) goto err; + if (remote.proto != local.proto) { + err = -EINVAL; + goto err; + } + /* Checking remote ip address */ rmcast = tipc_udp_is_mcast_addr(&remote); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 311cec8e533d..28887cf628b8 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -56,7 +56,7 @@ enum { static struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); static LIST_HEAD(device_list); -static DEFINE_MUTEX(device_mutex); +static DEFINE_SPINLOCK(device_spinlock); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_sw_proto_ops; @@ -538,11 +538,14 @@ static struct tls_context *create_ctx(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) return NULL; icsk->icsk_ulp_data = ctx; + ctx->setsockopt = sk->sk_prot->setsockopt; + ctx->getsockopt = sk->sk_prot->getsockopt; + ctx->sk_proto_close = sk->sk_prot->close; return ctx; } @@ -552,7 +555,7 @@ static int tls_hw_prot(struct sock *sk) struct tls_device *dev; int rc = 0; - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->feature && dev->feature(dev)) { ctx = create_ctx(sk); @@ -570,7 +573,7 @@ static int tls_hw_prot(struct sock *sk) } } out: - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); return rc; } @@ -579,12 +582,17 @@ static void tls_hw_unhash(struct sock *sk) struct tls_context *ctx = tls_get_ctx(sk); struct tls_device *dev; - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { - if (dev->unhash) + if (dev->unhash) { + kref_get(&dev->kref); + spin_unlock_bh(&device_spinlock); dev->unhash(dev, sk); + kref_put(&dev->kref, dev->release); + spin_lock_bh(&device_spinlock); + } } - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); ctx->unhash(sk); } @@ -595,12 +603,17 @@ static int tls_hw_hash(struct sock *sk) int err; err = ctx->hash(sk); - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { - if (dev->hash) + if (dev->hash) { + kref_get(&dev->kref); + spin_unlock_bh(&device_spinlock); err |= dev->hash(dev, sk); + kref_put(&dev->kref, dev->release); + spin_lock_bh(&device_spinlock); + } } - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); if (err) tls_hw_unhash(sk); @@ -675,9 +688,6 @@ static int tls_init(struct sock *sk) rc = -ENOMEM; goto out; } - ctx->setsockopt = sk->sk_prot->setsockopt; - ctx->getsockopt = sk->sk_prot->getsockopt; - ctx->sk_proto_close = sk->sk_prot->close; /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ if (ip_ver == TLSV6 && @@ -699,17 +709,17 @@ out: void tls_register_device(struct tls_device *device) { - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_add_tail(&device->dev_list, &device_list); - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_register_device); void tls_unregister_device(struct tls_device *device) { - mutex_lock(&device_mutex); + spin_lock_bh(&device_spinlock); list_del(&device->dev_list); - mutex_unlock(&device_mutex); + spin_unlock_bh(&device_spinlock); } EXPORT_SYMBOL(tls_unregister_device); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 7b1af8b59cd2..29b27858fff1 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -935,10 +935,12 @@ fallback_to_reg_send: tls_ctx->tx.overhead_size); } - ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_pl, - try_to_copy); - if (ret < 0) - goto trim_sgl; + if (try_to_copy) { + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, + msg_pl, try_to_copy); + if (ret < 0) + goto trim_sgl; + } /* Open records defined only if successfully copied, otherwise * we would trim the sg but not reset the open record frags. diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ab27a2872935..43a1dec08825 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -107,6 +107,7 @@ #include <linux/mutex.h> #include <linux/net.h> #include <linux/poll.h> +#include <linux/random.h> #include <linux/skbuff.h> #include <linux/smp.h> #include <linux/socket.h> @@ -504,9 +505,13 @@ out: static int __vsock_bind_stream(struct vsock_sock *vsk, struct sockaddr_vm *addr) { - static u32 port = LAST_RESERVED_PORT + 1; + static u32 port = 0; struct sockaddr_vm new_addr; + if (!port) + port = LAST_RESERVED_PORT + 1 + + prandom_u32_max(U32_MAX - LAST_RESERVED_PORT); + vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); if (addr->svm_port == VMADDR_PORT_ANY) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index cb332adb84cd..c361ce782412 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -264,6 +264,31 @@ vmci_transport_send_control_pkt_bh(struct sockaddr_vm *src, } static int +vmci_transport_alloc_send_control_pkt(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle) +{ + struct vmci_transport_packet *pkt; + int err; + + pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + err = __vmci_transport_send_control_pkt(pkt, src, dst, type, size, + mode, wait, proto, handle, + true); + kfree(pkt); + + return err; +} + +static int vmci_transport_send_control_pkt(struct sock *sk, enum vmci_transport_packet_type type, u64 size, @@ -272,9 +297,7 @@ vmci_transport_send_control_pkt(struct sock *sk, u16 proto, struct vmci_handle handle) { - struct vmci_transport_packet *pkt; struct vsock_sock *vsk; - int err; vsk = vsock_sk(sk); @@ -284,17 +307,10 @@ vmci_transport_send_control_pkt(struct sock *sk, if (!vsock_addr_bound(&vsk->remote_addr)) return -EINVAL; - pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - - err = __vmci_transport_send_control_pkt(pkt, &vsk->local_addr, - &vsk->remote_addr, type, size, - mode, wait, proto, handle, - true); - kfree(pkt); - - return err; + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, + &vsk->remote_addr, + type, size, mode, + wait, proto, handle); } static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, @@ -312,12 +328,29 @@ static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, static int vmci_transport_send_reset(struct sock *sk, struct vmci_transport_packet *pkt) { + struct sockaddr_vm *dst_ptr; + struct sockaddr_vm dst; + struct vsock_sock *vsk; + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) return 0; - return vmci_transport_send_control_pkt(sk, - VMCI_TRANSPORT_PACKET_TYPE_RST, - 0, 0, NULL, VSOCK_PROTO_INVALID, - VMCI_INVALID_HANDLE); + + vsk = vsock_sk(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) + return -EINVAL; + + if (vsock_addr_bound(&vsk->remote_addr)) { + dst_ptr = &vsk->remote_addr; + } else { + vsock_addr_init(&dst, pkt->dg.src.context, + pkt->src_port); + dst_ptr = &dst; + } + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, dst_ptr, + VMCI_TRANSPORT_PACKET_TYPE_RST, + 0, 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); } static int vmci_transport_send_negotiate(struct sock *sk, size_t size) diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 12b3edf70a7b..1615e503f8e3 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -272,11 +272,11 @@ void cfg80211_oper_and_ht_capa(struct ieee80211_ht_cap *ht_capa, p1 = (u8*)(ht_capa); p2 = (u8*)(ht_capa_mask); - for (i = 0; i<sizeof(*ht_capa); i++) + for (i = 0; i < sizeof(*ht_capa); i++) p1[i] &= p2[i]; } -/* Do a logical ht_capa &= ht_capa_mask. */ +/* Do a logical vht_capa &= vht_capa_mask. */ void cfg80211_oper_and_vht_capa(struct ieee80211_vht_cap *vht_capa, const struct ieee80211_vht_cap *vht_capa_mask) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 744b5851bbf9..2317727d6413 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7870,6 +7870,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) } memset(¶ms, 0, sizeof(params)); + params.beacon_csa.ftm_responder = -1; if (!info->attrs[NL80211_ATTR_WIPHY_FREQ] || !info->attrs[NL80211_ATTR_CH_SWITCH_COUNT]) @@ -8929,8 +8930,10 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_CONTROL_PORT_OVER_NL80211]) { int r = validate_pae_over_nl80211(rdev, info); - if (r < 0) + if (r < 0) { + kzfree(connkeys); return r; + } ibss.control_port_over_nl80211 = true; } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d536b07582f8..f741d8376a46 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -642,11 +642,15 @@ static bool cfg80211_is_all_idle(void) * All devices must be idle as otherwise if you are actively * scanning some new beacon hints could be learned and would * count as new regulatory hints. + * Also if there is any other active beaconing interface we + * need not issue a disconnect hint and reset any info such + * as chan dfs state, etc. */ list_for_each_entry(rdev, &cfg80211_rdev_list, list) { list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { wdev_lock(wdev); - if (wdev->conn || wdev->current_bss) + if (wdev->conn || wdev->current_bss || + cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; wdev_unlock(wdev); } @@ -1171,6 +1175,8 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, cfg80211_oper_and_ht_capa(&connect->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); + cfg80211_oper_and_vht_capa(&connect->vht_capa_mask, + rdev->wiphy.vht_capa_mod_mask); if (connkeys && connkeys->def >= 0) { int idx; diff --git a/net/wireless/util.c b/net/wireless/util.c index ef14d80ca03e..d473bd135da8 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1421,6 +1421,8 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, ies[pos + ext], ext == 2)) pos = skip_ie(ies, ielen, pos); + else + break; } } else { pos = skip_ie(ies, ielen, pos); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d49aa79b7997..5121729b8b63 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -100,7 +100,7 @@ int x25_parse_address_block(struct sk_buff *skb, } len = *skb->data; - needed = 1 + (len >> 4) + (len & 0x0f); + needed = 1 + ((len >> 4) + (len & 0x0f) + 1) / 2; if (!pskb_may_pull(skb, needed)) { /* packet is too short to hold the addresses it claims @@ -288,7 +288,7 @@ static struct sock *x25_find_listener(struct x25_address *addr, sk_for_each(s, &x25_list) if ((!strcmp(addr->x25_addr, x25_sk(s)->source_addr.x25_addr) || - !strcmp(addr->x25_addr, + !strcmp(x25_sk(s)->source_addr.x25_addr, null_x25_address.x25_addr)) && s->sk_state == TCP_LISTEN) { /* @@ -688,11 +688,15 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - len = strlen(addr->sx25_addr.x25_addr); - for (i = 0; i < len; i++) { - if (!isdigit(addr->sx25_addr.x25_addr[i])) { - rc = -EINVAL; - goto out; + /* check for the null_x25_address */ + if (strcmp(addr->sx25_addr.x25_addr, null_x25_address.x25_addr)) { + + len = strlen(addr->sx25_addr.x25_addr); + for (i = 0; i < len; i++) { + if (!isdigit(addr->sx25_addr.x25_addr[i])) { + rc = -EINVAL; + goto out; + } } } diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 3c12cae32001..afb26221d8a8 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -142,6 +142,15 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp sk->sk_state_change(sk); break; } + case X25_CALL_REQUEST: + /* call collision */ + x25->causediag.cause = 0x01; + x25->causediag.diagnostic = 0x48; + + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_disconnect(sk, EISCONN, 0x01, 0x48); + break; + case X25_CLEAR_REQUEST: if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) goto out_clear; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 684c0bc01e2c..d5635908587f 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -346,6 +346,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; + skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); + goto drop; + } + lock: spin_lock(&x->lock); @@ -385,7 +391,6 @@ lock: XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; - skb_dst_force(skb); dev_hold(skb->dev); if (crypto_done) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 4ae87c5ce2e3..fef6b2da3c5d 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -102,6 +102,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + err = -EHOSTUNREACH; goto error_nolock; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index dc4a9f1fb941..23c92891758a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -426,6 +426,12 @@ static void xfrm_put_mode(struct xfrm_mode *mode) module_put(mode->owner); } +void xfrm_state_free(struct xfrm_state *x) +{ + kmem_cache_free(xfrm_state_cache, x); +} +EXPORT_SYMBOL(xfrm_state_free); + static void xfrm_state_gc_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); @@ -452,7 +458,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) } xfrm_dev_state_free(x); security_xfrm_state_free(x); - kmem_cache_free(xfrm_state_cache, x); + xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) @@ -788,7 +794,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; - si->sadhcnt = net->xfrm.state_hmask; + si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c9a84e22f5d5..277c1c46fe94 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2288,13 +2288,13 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } - kfree(x); + xfrm_state_free(x); kfree(xp); return 0; free_state: - kfree(x); + xfrm_state_free(x); nomem: return err; } |