diff options
Diffstat (limited to 'net')
72 files changed, 710 insertions, 316 deletions
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e034afbd1bb0..08ce36147c4c 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -652,6 +652,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_softif_destroy_sysfs(hard_iface->soft_iface); } + hard_iface->soft_iface = NULL; batadv_hardif_put(hard_iface); out: diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 2333777f919d..8af1611b8ab2 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -837,6 +837,7 @@ static int batadv_tp_send(void *arg) primary_if = batadv_primary_if_get_selected(bat_priv); if (unlikely(!primary_if)) { err = BATADV_TP_REASON_DST_UNREACHABLE; + tp_vars->reason = err; goto out; } diff --git a/net/can/bcm.c b/net/can/bcm.c index 8e999ffdf28b..8af9d25ff988 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1549,24 +1549,31 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); + int ret = 0; if (len < sizeof(*addr)) return -EINVAL; - if (bo->bound) - return -EISCONN; + lock_sock(sk); + + if (bo->bound) { + ret = -EISCONN; + goto fail; + } /* bind a device to this socket */ if (addr->can_ifindex) { struct net_device *dev; dev = dev_get_by_index(&init_net, addr->can_ifindex); - if (!dev) - return -ENODEV; - + if (!dev) { + ret = -ENODEV; + goto fail; + } if (dev->type != ARPHRD_CAN) { dev_put(dev); - return -ENODEV; + ret = -ENODEV; + goto fail; } bo->ifindex = dev->ifindex; @@ -1577,17 +1584,24 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, bo->ifindex = 0; } - bo->bound = 1; - if (proc_dir) { /* unique socket address as filename */ sprintf(bo->procname, "%lu", sock_i_ino(sk)); bo->bcm_proc_read = proc_create_data(bo->procname, 0644, proc_dir, &bcm_proc_fops, sk); + if (!bo->bcm_proc_read) { + ret = -ENOMEM; + goto fail; + } } - return 0; + bo->bound = 1; + +fail: + release_sock(sk); + + return ret; } static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c index 7d54e944de5e..dcbe67ff3e2b 100644 --- a/net/ceph/ceph_fs.c +++ b/net/ceph/ceph_fs.c @@ -34,7 +34,8 @@ void ceph_file_layout_from_legacy(struct ceph_file_layout *fl, fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count); fl->object_size = le32_to_cpu(legacy->fl_object_size); fl->pool_id = le32_to_cpu(legacy->fl_pg_pool); - if (fl->pool_id == 0) + if (fl->pool_id == 0 && fl->stripe_unit == 0 && + fl->stripe_count == 0 && fl->object_size == 0) fl->pool_id = -1; } EXPORT_SYMBOL(ceph_file_layout_from_legacy); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index d9bf7a1d0a58..e6ae15bc41b7 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -4094,6 +4094,7 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) osd_init(&osdc->homeless_osd); osdc->homeless_osd.o_osdc = osdc; osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD; + osdc->last_linger_id = CEPH_LINGER_ID_START; osdc->linger_requests = RB_ROOT; osdc->map_checks = RB_ROOT; osdc->linger_map_checks = RB_ROOT; diff --git a/net/core/dev.c b/net/core/dev.c index 820bac239738..6666b28b6815 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1766,19 +1766,14 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } + int ret = ____dev_forward_skb(dev, skb); - skb_scrub_packet(skb, true); - skb->priority = 0; - skb->protocol = eth_type_trans(skb, dev); - skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + if (likely(!ret)) { + skb->protocol = eth_type_trans(skb, dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + } - return 0; + return ret; } EXPORT_SYMBOL_GPL(__dev_forward_skb); @@ -2484,7 +2479,7 @@ int skb_checksum_help(struct sk_buff *skb) goto out; } - *(__sum16 *)(skb->data + offset) = csum_fold(csum); + *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: diff --git a/net/core/filter.c b/net/core/filter.c index 00351cdf7d0c..b391209838ef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1628,6 +1628,19 @@ static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) return dev_forward_skb(dev, skb); } +static inline int __bpf_rx_skb_no_mac(struct net_device *dev, + struct sk_buff *skb) +{ + int ret = ____dev_forward_skb(dev, skb); + + if (likely(!ret)) { + skb->dev = dev; + ret = netif_rx(skb); + } + + return ret; +} + static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; @@ -1647,6 +1660,51 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) return ret; } +static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, + u32 flags) +{ + /* skb->mac_len is not set on normal egress */ + unsigned int mlen = skb->network_header - skb->mac_header; + + __skb_pull(skb, mlen); + + /* At ingress, the mac header has already been pulled once. + * At egress, skb_pospull_rcsum has to be done in case that + * the skb is originated from ingress (i.e. a forwarded skb) + * to ensure that rcsum starts at net header. + */ + if (!skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + skb_pop_mac_header(skb); + skb_reset_mac_len(skb); + return flags & BPF_F_INGRESS ? + __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); +} + +static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, + u32 flags) +{ + bpf_push_mac_rcsum(skb); + return flags & BPF_F_INGRESS ? + __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); +} + +static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, + u32 flags) +{ + switch (dev->type) { + case ARPHRD_TUNNEL: + case ARPHRD_TUNNEL6: + case ARPHRD_SIT: + case ARPHRD_IPGRE: + case ARPHRD_VOID: + case ARPHRD_NONE: + return __bpf_redirect_no_mac(skb, dev, flags); + default: + return __bpf_redirect_common(skb, dev, flags); + } +} + BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; @@ -1675,10 +1733,7 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) return -ENOMEM; } - bpf_push_mac_rcsum(clone); - - return flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone); + return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { @@ -1722,10 +1777,7 @@ int skb_do_redirect(struct sk_buff *skb) return -EINVAL; } - bpf_push_mac_rcsum(skb); - - return ri->flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); + return __bpf_redirect(skb, dev, ri->flags); } static const struct bpf_func_proto bpf_redirect_proto = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ab193e5def07..69e4463a4b1b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -122,7 +122,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_keyid *key_keyid; bool skip_vlan = false; u8 ip_proto = 0; - bool ret = false; + bool ret; if (!data) { data = skb->data; @@ -549,12 +549,17 @@ ip_proto_again: out_good: ret = true; -out_bad: + key_control->thoff = (u16)nhoff; +out: key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; - key_control->thoff = (u16)nhoff; return ret; + +out_bad: + ret = false; + key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); + goto out; } EXPORT_SYMBOL(__skb_flow_dissect); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f61c0e02a413..7001da910c6b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -219,6 +219,8 @@ int peernet2id_alloc(struct net *net, struct net *peer) bool alloc; int id; + if (atomic_read(&net->count) == 0) + return NETNSA_NSID_NOT_ASSIGNED; spin_lock_irqsave(&net->nsid_lock, flags); alloc = atomic_read(&peer->count) == 0 ? false : true; id = __peernet2id_alloc(net, peer, &alloc); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index fb7348f13501..a99917b5de33 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -275,6 +275,7 @@ int rtnl_unregister(int protocol, int msgtype) rtnl_msg_handlers[protocol][msgindex].doit = NULL; rtnl_msg_handlers[protocol][msgindex].dumpit = NULL; + rtnl_msg_handlers[protocol][msgindex].calcit = NULL; return 0; } @@ -839,18 +840,20 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, if (dev->dev.parent && dev_is_pci(dev->dev.parent) && (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); - size_t size = nla_total_size(sizeof(struct nlattr)); - size += nla_total_size(num_vfs * sizeof(struct nlattr)); + size_t size = nla_total_size(0); size += num_vfs * - (nla_total_size(sizeof(struct ifla_vf_mac)) + - nla_total_size(MAX_VLAN_LIST_LEN * - sizeof(struct nlattr)) + + (nla_total_size(0) + + nla_total_size(sizeof(struct ifla_vf_mac)) + + nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(0) + /* nest IFLA_VF_VLAN_LIST */ nla_total_size(MAX_VLAN_LIST_LEN * sizeof(struct ifla_vf_vlan_info)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + nla_total_size(sizeof(struct ifla_vf_rate)) + nla_total_size(sizeof(struct ifla_vf_link_state)) + nla_total_size(sizeof(struct ifla_vf_rss_query_en)) + + nla_total_size(0) + /* nest IFLA_VF_STATS */ /* IFLA_VF_STATS_RX_PACKETS */ nla_total_size_64bit(sizeof(__u64)) + /* IFLA_VF_STATS_TX_PACKETS */ @@ -898,7 +901,8 @@ static size_t rtnl_port_size(const struct net_device *dev, static size_t rtnl_xdp_size(const struct net_device *dev) { - size_t xdp_size = nla_total_size(1); /* XDP_ATTACHED */ + size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */ + nla_total_size(1); /* XDP_ATTACHED */ if (!dev->netdev_ops->ndo_xdp) return 0; @@ -1605,7 +1609,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) head = &net->dev_index_head[h]; hlist_for_each_entry(dev, head, index_hlist) { if (link_dump_filtered(dev, master_idx, kind_ops)) - continue; + goto cont; if (idx < s_idx) goto cont; err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -2848,7 +2852,10 @@ nla_put_failure: static inline size_t rtnl_fdb_nlmsg_size(void) { - return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(sizeof(u16)) + /* NDA_VLAN */ + 0; } static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, diff --git a/net/core/sock.c b/net/core/sock.c index c73e28fc9c2a..5e3ca414357e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) EXPORT_SYMBOL(sock_queue_rcv_skb); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, - const int nested, unsigned int trim_cap) + const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; @@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, bh_unlock_sock(sk); out: - sock_put(sk); + if (refcounted) + sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); @@ -1543,6 +1544,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); newsk->sk_err = 0; + newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 345a3aeb8c7e..b567c8725aea 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + const struct dccp_hdr *dh; struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; @@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - if (skb->len < offset + sizeof(*dh) || - skb->len < offset + __dccp_basic_hdr_len(dh)) { - __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); - return; - } + /* Only need dccph_dport & dccph_sport which are the first + * 4 bytes in dccp header. + * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. + */ + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet_lookup_established(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, @@ -868,7 +870,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3828f94b234c..715e5d1dc107 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; @@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - if (skb->len < offset + sizeof(*dh) || - skb->len < offset + __dccp_basic_hdr_len(dh)) { - __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), - ICMP6_MIB_INERRORS); - return; - } + /* Only need dccph_dport & dccph_sport which are the first + * 4 bytes in dccp header. + * Our caller (icmpv6_notify()) already pulled 8 bytes for us. + */ + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, @@ -738,7 +739,8 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, + refcounted) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -956,6 +958,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), + .bind_conflict = inet6_csk_bind_conflict, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 41e65804ddf5..9fe25bf63296 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout) __kfree_skb(skb); } + /* If socket has been already reset kill it. */ + if (sk->sk_state == DCCP_CLOSED) + goto adjudge_to_death; + if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9648c97e541f..5ddf5cda07f4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -533,9 +533,9 @@ EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ @@ -545,13 +545,12 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) */ while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); if (signal_pending(current) || !timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; return timeo; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c3b80478226e..161fc0f0d752 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -151,7 +151,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old, int fib_unmerge(struct net *net) { - struct fib_table *old, *new; + struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); @@ -162,11 +162,21 @@ int fib_unmerge(struct net *net) if (!new) return -ENOMEM; + /* table is already unmerged */ + if (new == old) + return 0; + /* replace merged table with clean table */ - if (new != old) { - fib_replace_table(net, old, new); - fib_free_table(old); - } + fib_replace_table(net, old, new); + fib_free_table(old); + + /* attempt to fetch main table if it has been allocated */ + main_table = fib_get_table(net, RT_TABLE_MAIN); + if (!main_table) + return 0; + + /* flush local entries from main table */ + fib_table_flush_external(main_table); return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 31cef3602585..026f309c51e9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1743,8 +1743,10 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, - NULL, l->key)) + NULL, l->key)) { + kmem_cache_free(fn_alias_kmem, new_fa); goto out; + } } /* stop loop if key wrapped back to 0 */ @@ -1760,6 +1762,71 @@ out: return NULL; } +/* Caller must hold RTNL */ +void fib_table_flush_external(struct fib_table *tb) +{ + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct hlist_node *tmp; + struct fib_alias *fa; + + /* walk trie in reverse order */ + for (;;) { + unsigned char slen = 0; + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; + + /* cannot resize the trie vector */ + if (IS_TRIE(pn)) + break; + + /* resize completed node */ + pn = resize(t, pn); + cindex = get_index(pkey, pn); + + continue; + } + + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; + + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; + + continue; + } + + hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { + /* if alias was cloned to local then we just + * need to remove the local copy from main + */ + if (tb->tb_id != fa->tb_id) { + hlist_del_rcu(&fa->fa_list); + alias_free_mem_rcu(fa); + continue; + } + + /* record local slen */ + slen = fa->fa_slen; + } + + /* update leaf slen */ + n->slen = slen; + + if (hlist_empty(&n->leaf)) { + put_child_root(pn, n->key, NULL); + node_free(n); + } + } +} + /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb) { @@ -2413,22 +2480,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, struct key_vector *l, **tp = &iter->tnode; t_key key; - /* use cache location of next-to-find key */ + /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { - pos -= iter->pos; key = iter->key; } else { - iter->pos = 0; + iter->pos = 1; key = 0; } - while ((l = leaf_walk_rcu(tp, key)) != NULL) { + pos -= iter->pos; + + while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; - - if (--pos <= 0) - break; - l = NULL; /* handle unlikely case of a key wrap */ @@ -2437,7 +2501,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, } if (l) - iter->key = key; /* remember it */ + iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ @@ -2465,7 +2529,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return fib_route_get_idx(iter, *pos); iter->pos = 0; - iter->key = 0; + iter->key = KEY_MAX; return SEQ_START_TOKEN; } @@ -2474,7 +2538,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; - t_key key = iter->key; + t_key key = iter->key + 1; ++*pos; @@ -2483,7 +2547,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) l = leaf_walk_rcu(&iter->tnode, key); if (l) { - iter->key = l->key + 1; + iter->key = l->key; iter->pos++; } else { iter->pos = 0; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 38abe70e595f..48734ee6293f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -477,7 +477,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); + fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key_hash(net, fl4, @@ -502,7 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type_dev_table(net, skb_in->dev, + if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 606cc3e85d2b..15db786d50ed 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -162,7 +162,7 @@ static int unsolicited_report_interval(struct in_device *in_dev) } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); -static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr); +static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); @@ -1130,10 +1130,15 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_unlock_bh(&in_dev->mc_tomb_lock); } -static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) +/* + * restore ip_mc_list deleted records + */ +static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; - struct ip_sf_list *psf, *psf_next; + struct ip_sf_list *psf; + struct net *net = dev_net(in_dev->dev); + __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; @@ -1149,16 +1154,26 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr) in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); + + spin_lock_bh(&im->lock); if (pmc) { - for (psf = pmc->tomb; psf; psf = psf_next) { - psf_next = psf->sf_next; - kfree(psf); + im->interface = pmc->interface; + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->sfmode = pmc->sfmode; + if (pmc->sfmode == MCAST_INCLUDE) { + im->tomb = pmc->tomb; + im->sources = pmc->sources; + for (psf = im->sources; psf; psf = psf->sf_next) + psf->sf_crcount = im->crcount; } in_dev_put(pmc->interface); - kfree(pmc); } + spin_unlock_bh(&im->lock); } +/* + * flush ip_mc_list deleted records + */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; @@ -1366,7 +1381,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST - igmpv3_del_delrec(in_dev, im->multiaddr); + igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) @@ -1626,8 +1641,12 @@ void ip_mc_remap(struct in_device *in_dev) ASSERT_RTNL(); - for_each_pmc_rtnl(in_dev, pmc) + for_each_pmc_rtnl(in_dev, pmc) { +#ifdef CONFIG_IP_MULTICAST + igmpv3_del_delrec(in_dev, pmc); +#endif igmp_group_added(pmc); + } } /* Device going down */ @@ -1648,7 +1667,6 @@ void ip_mc_down(struct in_device *in_dev) in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); - igmpv3_clear_delrec(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); @@ -1688,8 +1706,12 @@ void ip_mc_up(struct in_device *in_dev) #endif ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for_each_pmc_rtnl(in_dev, pmc) + for_each_pmc_rtnl(in_dev, pmc) { +#ifdef CONFIG_IP_MULTICAST + igmpv3_del_delrec(in_dev, pmc); +#endif igmp_group_added(pmc); + } } /* @@ -1704,13 +1726,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); +#ifdef CONFIG_IP_MULTICAST + igmpv3_clear_delrec(in_dev); +#endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - - /* We've dropped the groups in ip_mc_down already */ - ip_mc_clear_src(i); ip_ma_put(i); } } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 8b4ffd216839..9f0a7b96646f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 03e7f7310423..105908d841a3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -239,19 +239,23 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *segs; int ret = 0; - /* common case: fragmentation of segments is not allowed, - * or seglen is <= mtu + /* common case: seglen is <= mtu */ - if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) || - skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_mtu(skb, mtu)) return ip_finish_output2(net, sk, skb); - /* Slowpath - GSO segment length is exceeding the dst MTU. + /* Slowpath - GSO segment length exceeds the egress MTU. * - * This can happen in two cases: - * 1) TCP GRO packet, DF bit not set - * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly - * from host network stack. + * This can happen in several cases: + * - Forwarding of a TCP GRO skb, when DF flag is not set. + * - Forwarding of an skb that arrived on a virtualization interface + * (virtio-net/vhost/tap) with TSO/GSO size set by other network + * stack. + * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an + * interface with a smaller MTU. + * - Arriving GRO skb (or GSO skb in a virtualized environment) that is + * bridged to a NETIF_F_TSO tunnel stacked over an interface with an + * insufficent MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); @@ -1579,7 +1583,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, } oif = arg->bound_dev_if; - oif = oif ? : skb->skb_iif; + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) + oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 777bc1883870..fed3d29f9eb3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; - int skb_iif = skb->skb_iif; struct iphdr *iph; int err; @@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && !(df & htons(IP_DF))) { - /* Arrived from an ingress interface, got encapsulated, with - * fragmentation of encapulating frames allowed. - * If skb is gso, the resulting encapsulated network segments - * may exceed dst mtu. - * Allow IP Fragmentation of segments. - */ - IPCB(skb)->flags |= IPSKB_FRAG_SEGS; - } - /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5f006e13de56..27089f5ebbb1 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->dev->stats.tx_bytes += skb->len; } - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index bf855e64fc45..0c01a270bf9f 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -28,7 +28,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr, struct in_addr gw = { .s_addr = (__force __be32)regs->data[priv->sreg_addr], }; - int oif = regs->data[priv->sreg_dev]; + int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif); } @@ -59,7 +59,9 @@ static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); - if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) + goto nla_put_failure; + if (priv->sreg_dev && nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 62d4d90c1389..2a57566e6e91 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -753,7 +753,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + if (!n) + n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3251fe71f39f..814af89c1bd3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1164,7 +1164,7 @@ restart: err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) - goto out_err; + goto do_error; sg = !!(sk->sk_route_caps & NETIF_F_SG); @@ -1241,7 +1241,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1294af4e0127..f9038d6b109e 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -200,8 +200,10 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; - if (sk->sk_state != TCP_CLOSE) + if (sk->sk_state != TCP_CLOSE) { + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_init_congestion_control(sk); + } } /* Manage refcounts on socket close. */ diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 10d728b6804c..ab37c6775630 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -56,6 +56,7 @@ struct dctcp { u32 next_seq; u32 ce_state; u32 delayed_ack_reserved; + u32 loss_cwnd; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ @@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); ca->delayed_ack_reserved = 0; + ca->loss_cwnd = 0; ca->ce_state = 0; dctcp_reset(tp, ca); @@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk) static u32 dctcp_ssthresh(struct sock *sk) { - const struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); + ca->loss_cwnd = tp->snd_cwnd; return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); } @@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, return 0; } +static u32 dctcp_cwnd_undo(struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + static struct tcp_congestion_ops dctcp __read_mostly = { .init = dctcp_init, .in_ack_event = dctcp_update_alpha, .cwnd_event = dctcp_cwnd_event, .ssthresh = dctcp_ssthresh, .cong_avoid = tcp_reno_cong_avoid, + .undo_cwnd = dctcp_cwnd_undo, .set_state = dctcp_state, .get_info = dctcp_get_info, .flags = TCP_CONG_NEEDS_ECN, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 61b7be303eec..2259114c7242 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1564,6 +1564,21 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_add_backlog); +int tcp_filter(struct sock *sk, struct sk_buff *skb) +{ + struct tcphdr *th = (struct tcphdr *)skb->data; + unsigned int eaten = skb->len; + int err; + + err = sk_filter_trim_cap(sk, skb, th->doff * 4); + if (!err) { + eaten -= skb->len; + TCP_SKB_CB(skb)->end_seq -= eaten; + } + return err; +} +EXPORT_SYMBOL(tcp_filter); + /* * From tcp_input.c */ @@ -1676,8 +1691,10 @@ process: nf_reset(skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); skb->dev = NULL; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d123d68f4d1d..0de9d5d2b9ae 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1652,10 +1652,10 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (use_hash2) { hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & - udp_table.mask; - hash2 = udp4_portaddr_hash(net, daddr, hnum) & udp_table.mask; + udptable->mask; + hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udp_table.hash2[hash2]; + hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index bd59c343d35f..7370ad2e693a 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -448,7 +448,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; else - iif = l3mdev_master_ifindex(skb->dev); + iif = l3mdev_master_ifindex(skb_dst(skb)->dev); /* * Must not send error if the source does not uniquely diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 6001e781164e..59eb4ed99ce8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1366,7 +1366,7 @@ emsgsize: if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 87784560dc46..0a4759b89da2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1034,6 +1034,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, int mtu; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; + bool use_cache = false; u8 hop_limit; int err = -1; @@ -1066,7 +1067,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); - } else if (!fl6->flowi6_mark) + } else if (!(t->parms.flags & + (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { + /* enable the cache only only if the routing decision does + * not depend on the current inner header value + */ + use_cache = true; + } + + if (use_cache) dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) @@ -1150,7 +1159,7 @@ route_lookup: if (t->encap.type != TUNNEL_ENCAP_NONE) goto tx_err_dst_release; } else { - if (!fl6->flowi6_mark && ndst) + if (use_cache && ndst) dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); } skb_dst_set(skb, dst); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index a7520528ecd2..b283f293ee4a 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -88,9 +88,6 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, uh->len = htons(skb->len); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED - | IPSKB_REROUTED); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 8bfd470cbe72..831f86e1ec08 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -26,7 +26,7 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr, { struct nft_dup_ipv6 *priv = nft_expr_priv(expr); struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; - int oif = regs->data[priv->sreg_dev]; + int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif); } @@ -57,7 +57,9 @@ static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_dup_ipv6 *priv = nft_expr_priv(expr); - if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) + goto nla_put_failure; + if (priv->sreg_dev && nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 947ed1ded026..1b57e11e6e0d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1364,6 +1364,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6->rt6i_flags & RTF_LOCAL) return; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + dst_confirm(dst); mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) @@ -2758,6 +2761,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) PMTU discouvery. */ if (rt->dst.dev == arg->dev && + dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { if (rt->rt6i_flags & RTF_CACHE) { /* For RTF_CACHE with rt6i_pmtu == 0 diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5a27ab4eab39..b9f1fee9a886 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -818,8 +818,12 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); - else - fl6.flowi6_oif = oif ? : skb->skb_iif; + else { + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) + oif = skb->skb_iif; + + fl6.flowi6_oif = oif; + } fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); fl6.fl6_dport = t1->dest; @@ -1225,7 +1229,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard; /* @@ -1453,8 +1457,10 @@ process: if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard_and_relse; - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + hdr = ipv6_hdr(skb); skb->dev = NULL; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b2ef061e6836..e5056d4873d1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -706,10 +706,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (use_hash2) { hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) & - udp_table.mask; - hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask; + udptable->mask; + hash2 = udp6_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: - hslot = &udp_table.hash2[hash2]; + hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 965f7e344cef..3dc97b4f982b 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -97,7 +97,7 @@ static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int len = skb->len; int ret = l2tp_xmit_skb(session, skb, session->hdr_len); - if (likely(ret == NET_XMIT_SUCCESS)) { + if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { atomic_long_add(len, &priv->tx_bytes); atomic_long_inc(&priv->tx_packets); } else { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index fce25afb652a..982f6c44ea01 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -251,8 +251,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret; int chk_addr_ret; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) @@ -267,6 +265,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) read_unlock_bh(&l2tp_ip_lock); lock_sock(sk); + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out; + if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip)) goto out; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index ad3468c32b53..9978d01ba0ba 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -269,8 +269,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int addr_type; int err; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -296,6 +294,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) lock_sock(sk); err = -EINVAL; + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out_unlock; + if (sk->sk_state != TCP_CLOSE) goto out_unlock; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 78e9ecbc96e6..8e05032689f0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -688,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) } /* No need to do anything if the driver does all */ - if (!local->ops->set_tim) + if (ieee80211_hw_check(&local->hw, AP_LINK_PS)) return; if (sta->dead) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1c56abc49627..bd5f4be89435 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1501,7 +1501,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, struct sta_info *sta, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct fq *fq = &local->fq; struct ieee80211_vif *vif; struct txq_info *txqi; @@ -1526,8 +1525,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, if (!txqi) return false; - info->control.vif = vif; - spin_lock_bh(&fq->lock); ieee80211_txq_enqueue(local, txqi, skb); spin_unlock_bh(&fq->lock); @@ -3213,7 +3210,6 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - *ieee80211_get_qos_ctl(hdr) = tid; hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid); } else { info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; @@ -3338,6 +3334,11 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, (tid_tx ? IEEE80211_TX_CTL_AMPDU : 0); info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT; + if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + *ieee80211_get_qos_ctl(hdr) = tid; + } + __skb_queue_head_init(&tx.skbs); tx.flags = IEEE80211_TX_UNICAST; @@ -3426,6 +3427,11 @@ begin: goto begin; } + if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags)) + info->flags |= IEEE80211_TX_CTL_AMPDU; + else + info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, sta); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ee715764a828..6832bf6ab69f 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -270,6 +270,22 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, vht_cap->vht_mcs.tx_mcs_map |= cpu_to_le16(peer_tx << i * 2); } + /* + * This is a workaround for VHT-enabled STAs which break the spec + * and have the VHT-MCS Rx map filled in with value 3 for all eight + * spacial streams, an example is AR9462. + * + * As per spec, in section 22.1.1 Introduction to the VHT PHY + * A VHT STA shall support at least single spactial stream VHT-MCSs + * 0 to 7 (transmit and receive) in all supported channel widths. + */ + if (vht_cap->vht_mcs.rx_mcs_map == cpu_to_le16(0xFFFF)) { + vht_cap->vht_supported = false; + sdata_info(sdata, "Ignoring VHT IE from %pM due to invalid rx_mcs_map\n", + sta->addr); + return; + } + /* finally set up the bandwidth */ switch (vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c3c809b2e712..a6e44ef2ec9a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2845,7 +2845,7 @@ static struct genl_family ip_vs_genl_family = { .hdrsize = 0, .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, - .maxattr = IPVS_CMD_MAX, + .maxattr = IPVS_CMD_ATTR_MAX, .netnsok = true, /* Make ipvsadm to work on netns */ }; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 1b07578bedf3..9350530c16c1 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -283,6 +283,7 @@ struct ip_vs_sync_buff { */ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) { + memset(ho, 0, sizeof(*ho)); ho->init_seq = get_unaligned_be32(&no->init_seq); ho->delta = get_unaligned_be32(&no->delta); ho->previous_delta = get_unaligned_be32(&no->previous_delta); @@ -917,8 +918,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa kfree(param->pe_data); } - if (opt) - memcpy(&cp->in_seq, opt, sizeof(*opt)); + if (opt) { + cp->in_seq = opt->in_seq; + cp->out_seq = opt->out_seq; + } atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs)); cp->state = state; cp->old_state = cp->state; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index df2f5a3901df..0f87e5d21be7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -76,6 +76,7 @@ struct conntrack_gc_work { struct delayed_work dwork; u32 last_bucket; bool exiting; + long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; @@ -83,9 +84,11 @@ static __read_mostly spinlock_t nf_conntrack_locks_all_lock; static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ #define GC_MAX_BUCKETS_DIV 64u -#define GC_MAX_BUCKETS 8192u -#define GC_INTERVAL (5 * HZ) +/* upper bound of scan intervals */ +#define GC_INTERVAL_MAX (2 * HZ) +/* maximum conntracks to evict per gc run */ #define GC_MAX_EVICTS 256u static struct conntrack_gc_work conntrack_gc_work; @@ -936,13 +939,13 @@ static noinline int early_drop(struct net *net, unsigned int _hash) static void gc_worker(struct work_struct *work) { unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned long next_run = GC_INTERVAL; - unsigned int ratio, scanned = 0; struct conntrack_gc_work *gc_work; + unsigned int ratio, scanned = 0; + unsigned long next_run; gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = min(nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV, GC_MAX_BUCKETS); + goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; i = gc_work->last_bucket; do { @@ -982,17 +985,47 @@ static void gc_worker(struct work_struct *work) if (gc_work->exiting) return; + /* + * Eviction will normally happen from the packet path, and not + * from this gc worker. + * + * This worker is only here to reap expired entries when system went + * idle after a busy period. + * + * The heuristics below are supposed to balance conflicting goals: + * + * 1. Minimize time until we notice a stale entry + * 2. Maximize scan intervals to not waste cycles + * + * Normally, expired_count will be 0, this increases the next_run time + * to priorize 2) above. + * + * As soon as a timed-out entry is found, move towards 1) and increase + * the scan frequency. + * In case we have lots of evictions next scan is done immediately. + */ ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio >= 90 || expired_count == GC_MAX_EVICTS) + if (ratio >= 90 || expired_count == GC_MAX_EVICTS) { + gc_work->next_gc_run = 0; next_run = 0; + } else if (expired_count) { + gc_work->next_gc_run /= 2U; + next_run = msecs_to_jiffies(1); + } else { + if (gc_work->next_gc_run < GC_INTERVAL_MAX) + gc_work->next_gc_run += msecs_to_jiffies(1); + + next_run = gc_work->next_gc_run; + } gc_work->last_bucket = i; - schedule_delayed_work(&gc_work->dwork, next_run); + queue_delayed_work(system_long_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DELAYED_WORK(&gc_work->dwork, gc_worker); + gc_work->next_gc_run = GC_INTERVAL_MAX; gc_work->exiting = false; } @@ -1885,7 +1918,7 @@ int nf_conntrack_init_start(void) nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); conntrack_gc_work_init(&conntrack_gc_work); - schedule_delayed_work(&conntrack_gc_work.dwork, GC_INTERVAL); + queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX); return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 336e21559e01..7341adf7059d 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -138,9 +138,14 @@ __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { - if (!strcmp(h->name, name) && - h->tuple.src.l3num == l3num && - h->tuple.dst.protonum == protonum) + if (strcmp(h->name, name)) + continue; + + if (h->tuple.src.l3num != NFPROTO_UNSPEC && + h->tuple.src.l3num != l3num) + continue; + + if (h->tuple.dst.protonum == protonum) return h; } } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 621b81c7bddc..c3fc14e021ec 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1436,9 +1436,12 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, handler = &sip_handlers[i]; if (handler->request == NULL) continue; - if (*datalen < handler->len || + if (*datalen < handler->len + 2 || strncasecmp(*dptr, handler->method, handler->len)) continue; + if ((*dptr)[handler->len] != ' ' || + !isalpha((*dptr)[handler->len+1])) + continue; if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ, &matchoff, &matchlen) <= 0) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 24db22257586..026581b04ea8 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2956,12 +2956,14 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; +err3: + ops->destroy(set); err2: kfree(set); err1: @@ -3452,14 +3454,15 @@ void *nft_set_elem_init(const struct nft_set *set, return elem; } -void nft_set_elem_destroy(const struct nft_set *set, void *elem) +void nft_set_elem_destroy(const struct nft_set *set, void *elem, + bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_uninit(nft_set_ext_data(ext), set->dtype); - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) + if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); kfree(elem); @@ -3565,6 +3568,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { + .net = ctx->net, .afi = ctx->afi, .table = ctx->table, .chain = (struct nft_chain *)binding->chain, @@ -3812,7 +3816,7 @@ void nft_set_gc_batch_release(struct rcu_head *rcu) gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i]); + nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); kfree(gcb); } EXPORT_SYMBOL_GPL(nft_set_gc_batch_release); @@ -4030,7 +4034,7 @@ static void nf_tables_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem(trans).priv, true); break; } kfree(trans); @@ -4171,7 +4175,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem(trans).priv, true); break; } kfree(trans); @@ -4421,7 +4425,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, * Otherwise a 0 is returned and the attribute value is stored in the * destination variable. */ -unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) +int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) { u32 val; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 517f08767a3c..31ca94793aa9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -44,18 +44,22 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, ®s->data[priv->sreg_key], ®s->data[priv->sreg_data], timeout, GFP_ATOMIC); - if (elem == NULL) { - if (set->size) - atomic_dec(&set->nelems); - return NULL; - } + if (elem == NULL) + goto err1; ext = nft_set_elem_ext(set, elem); if (priv->expr != NULL && nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0) - return NULL; + goto err2; return elem; + +err2: + nft_set_elem_destroy(set, elem, false); +err1: + if (set->size) + atomic_dec(&set->nelems); + return NULL; } static void nft_dynset_eval(const struct nft_expr *expr, @@ -139,6 +143,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return PTR_ERR(set); } + if (set->ops->update == NULL) + return -EOPNOTSUPP; + if (set->flags & NFT_SET_CONSTANT) return -EBUSY; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3794cb2fc788..a3dface3e6e6 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -98,7 +98,7 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; + struct nft_hash_elem *he, *prev; struct nft_hash_cmp_arg arg = { .genmask = NFT_GENMASK_ANY, .set = set, @@ -112,15 +112,24 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key, he = new(set, expr, regs); if (he == NULL) goto err1; - if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params)) + + prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); + if (IS_ERR(prev)) goto err2; + + /* Another cpu may race to insert the element with the same key */ + if (prev) { + nft_set_elem_destroy(set, he, true); + he = prev; + } + out: *ext = &he->ext; return true; err2: - nft_set_elem_destroy(set, he); + nft_set_elem_destroy(set, he, true); err1: return false; } @@ -332,7 +341,7 @@ static int nft_hash_init(const struct nft_set *set, static void nft_hash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy((const struct nft_set *)arg, ptr); + nft_set_elem_destroy((const struct nft_set *)arg, ptr, true); } static void nft_hash_destroy(const struct nft_set *set) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 38b5bda242f8..36493a7cae88 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -266,7 +266,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe); + nft_set_elem_destroy(set, rbe, true); } } diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 69f78e96fdb4..b83e158e116a 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -44,7 +44,7 @@ connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) u_int32_t newmark; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_untracked(ct)) return XT_CONTINUE; switch (info->mode) { @@ -97,7 +97,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_untracked(ct)) return false; return ((ct->mark & info->mask) == info->mark) ^ info->invert; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index b2f0e986a6f4..a5546249fb10 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -178,11 +178,8 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) } cb->args[1] = i; } else { - if (req->sdiag_protocol >= MAX_LINKS) { - read_unlock(&nl_table_lock); - rcu_read_unlock(); + if (req->sdiag_protocol >= MAX_LINKS) return -ENOENT; - } err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 23cc12639ba7..49c28e8ef01b 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -404,7 +404,7 @@ int __genl_register_family(struct genl_family *family) err = genl_validate_assign_mc_groups(family); if (err) - goto errout_locked; + goto errout_free; list_add_tail(&family->family_list, genl_family_chain(family->id)); genl_unlock_all(); @@ -417,6 +417,8 @@ int __genl_register_family(struct genl_family *family) return 0; +errout_free: + kfree(family->attrbuf); errout_locked: genl_unlock_all(); errout: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2b2a7974e4bb..8e93d4afe5ea 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -112,7 +112,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL; it_chain = &tp->next) - tfilter_notify(net, oskb, n, tp, 0, event, false); + tfilter_notify(net, oskb, n, tp, n->nlmsg_flags, event, false); } /* Select new prio value from the range, managed by kernel. */ @@ -430,7 +430,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; } diff --git a/net/sctp/input.c b/net/sctp/input.c index a2ea1d1cc06a..a01a56ec8b8c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -181,9 +181,10 @@ int sctp_rcv(struct sk_buff *skb) * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB */ if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) { - if (asoc) { - sctp_association_put(asoc); + if (transport) { + sctp_transport_put(transport); asoc = NULL; + transport = NULL; } else { sctp_endpoint_put(ep); ep = NULL; @@ -269,8 +270,8 @@ int sctp_rcv(struct sk_buff *skb) bh_unlock_sock(sk); /* Release the asoc/ep ref we took in the lookup calls. */ - if (asoc) - sctp_association_put(asoc); + if (transport) + sctp_transport_put(transport); else sctp_endpoint_put(ep); @@ -283,8 +284,8 @@ discard_it: discard_release: /* Release the asoc/ep ref we took in the lookup calls. */ - if (asoc) - sctp_association_put(asoc); + if (transport) + sctp_transport_put(transport); else sctp_endpoint_put(ep); @@ -300,6 +301,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; struct sctp_inq *inqueue = &chunk->rcvr->inqueue; + struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = NULL; int backloged = 0; @@ -351,7 +353,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) done: /* Release the refs we took in sctp_add_backlog */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) - sctp_association_put(sctp_assoc(rcvr)); + sctp_transport_put(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_put(sctp_ep(rcvr)); else @@ -363,6 +365,7 @@ done: static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; + struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = chunk->rcvr; int ret; @@ -373,7 +376,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) * from us */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) - sctp_association_hold(sctp_assoc(rcvr)); + sctp_transport_hold(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_hold(sctp_ep(rcvr)); else @@ -537,15 +540,15 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, return sk; out: - sctp_association_put(asoc); + sctp_transport_put(transport); return NULL; } /* Common cleanup code for icmp/icmpv6 error handler. */ -void sctp_err_finish(struct sock *sk, struct sctp_association *asoc) +void sctp_err_finish(struct sock *sk, struct sctp_transport *t) { bh_unlock_sock(sk); - sctp_association_put(asoc); + sctp_transport_put(t); } /* @@ -641,7 +644,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) } out_unlock: - sctp_err_finish(sk, asoc); + sctp_err_finish(sk, transport); } /* @@ -952,11 +955,8 @@ static struct sctp_association *__sctp_lookup_association( goto out; asoc = t->asoc; - sctp_association_hold(asoc); *pt = t; - sctp_transport_put(t); - out: return asoc; } @@ -986,7 +986,7 @@ int sctp_has_association(struct net *net, struct sctp_transport *transport; if ((asoc = sctp_lookup_association(net, laddr, paddr, &transport))) { - sctp_association_put(asoc); + sctp_transport_put(transport); return 1; } @@ -1021,7 +1021,6 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, struct sctphdr *sh = sctp_hdr(skb); union sctp_params params; sctp_init_chunk_t *init; - struct sctp_transport *transport; struct sctp_af *af; /* @@ -1052,7 +1051,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, af->from_addr_param(paddr, params.addr, sh->source, 0); - asoc = __sctp_lookup_association(net, laddr, paddr, &transport); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp); if (asoc) return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index f473779e8b1c..176af3080a2b 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -198,7 +198,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } out_unlock: - sctp_err_finish(sk, asoc); + sctp_err_finish(sk, transport); out: if (likely(idev != NULL)) in6_dev_put(idev); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9fbb6feb8c27..f23ad913dc7a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1214,9 +1214,12 @@ static int __sctp_connect(struct sock *sk, timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK); - err = sctp_wait_for_connect(asoc, &timeo); - if ((err == 0 || err == -EINPROGRESS) && assoc_id) + if (assoc_id) *assoc_id = asoc->assoc_id; + err = sctp_wait_for_connect(asoc, &timeo); + /* Note: the asoc may be freed after the return of + * sctp_wait_for_connect. + */ /* Don't free association on exit. */ asoc = NULL; @@ -4282,19 +4285,18 @@ static void sctp_shutdown(struct sock *sk, int how) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; - struct sctp_association *asoc; if (!sctp_style(sk, TCP)) return; - if (how & SEND_SHUTDOWN) { + ep = sctp_sk(sk)->ep; + if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) { + struct sctp_association *asoc; + sk->sk_state = SCTP_SS_CLOSING; - ep = sctp_sk(sk)->ep; - if (!list_empty(&ep->asocs)) { - asoc = list_entry(ep->asocs.next, - struct sctp_association, asocs); - sctp_primitive_SHUTDOWN(net, asoc, NULL); - } + asoc = list_entry(ep->asocs.next, + struct sctp_association, asocs); + sctp_primitive_SHUTDOWN(net, asoc, NULL); } } @@ -4480,12 +4482,9 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), if (!transport || !sctp_transport_hold(transport)) goto out; - sctp_association_hold(transport->asoc); - sctp_transport_put(transport); - rcu_read_unlock(); err = cb(transport, p); - sctp_association_put(transport->asoc); + sctp_transport_put(transport); out: return err; diff --git a/net/socket.c b/net/socket.c index 5a9bf5ee2464..73dc69f9681e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -341,8 +341,23 @@ static const struct xattr_handler sockfs_xattr_handler = { .get = sockfs_xattr_get, }; +static int sockfs_security_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *suffix, const void *value, + size_t size, int flags) +{ + /* Handled by LSM. */ + return -EAGAIN; +} + +static const struct xattr_handler sockfs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .set = sockfs_security_xattr_set, +}; + static const struct xattr_handler *sockfs_xattr_handlers[] = { &sockfs_xattr_handler, + &sockfs_security_xattr_handler, NULL }; @@ -2038,6 +2053,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (err) break; ++datagrams; + if (msg_data_left(&msg_sys)) + break; cond_resched(); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 34dd7b26ee5f..62a482790937 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2753,14 +2753,18 @@ EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout); void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt) { + rcu_read_lock(); xprt_switch_put(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_put); void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { + rcu_read_lock(); rpc_xprt_switch_add_xprt(rcu_dereference(clnt->cl_xpi.xpi_xpswitch), xprt); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_add_xprt); @@ -2770,9 +2774,8 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps; bool ret; - xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); - rcu_read_lock(); + xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); ret = rpc_xprt_switch_has_addr(xps, sap); rcu_read_unlock(); return ret; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c3f652395a80..3bc1d61694cb 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1002,14 +1002,8 @@ static void svc_age_temp_xprts(unsigned long closure) void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) { struct svc_xprt *xprt; - struct svc_sock *svsk; - struct socket *sock; struct list_head *le, *next; LIST_HEAD(to_be_closed); - struct linger no_linger = { - .l_onoff = 1, - .l_linger = 0, - }; spin_lock_bh(&serv->sv_lock); list_for_each_safe(le, next, &serv->sv_tempsocks) { @@ -1027,10 +1021,7 @@ void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) list_del_init(le); xprt = list_entry(le, struct svc_xprt, xpt_list); dprintk("svc_age_temp_xprts_now: closing %p\n", xprt); - svsk = container_of(xprt, struct svc_sock, sk_xprt); - sock = svsk->sk_sock; - kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, - (char *)&no_linger, sizeof(no_linger)); + xprt->xpt_ops->xpo_kill_temp_xprt(xprt); svc_close_xprt(xprt); } } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 57625f64efd5..a4bc98265d88 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -438,6 +438,21 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt) return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); } +static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt) +{ + struct svc_sock *svsk; + struct socket *sock; + struct linger no_linger = { + .l_onoff = 1, + .l_linger = 0, + }; + + svsk = container_of(xprt, struct svc_sock, sk_xprt); + sock = svsk->sk_sock; + kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&no_linger, sizeof(no_linger)); +} + /* * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo */ @@ -648,6 +663,10 @@ static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt) return NULL; } +static void svc_udp_kill_temp_xprt(struct svc_xprt *xprt) +{ +} + static struct svc_xprt *svc_udp_create(struct svc_serv *serv, struct net *net, struct sockaddr *sa, int salen, @@ -667,6 +686,7 @@ static struct svc_xprt_ops svc_udp_ops = { .xpo_has_wspace = svc_udp_has_wspace, .xpo_accept = svc_udp_accept, .xpo_secure_port = svc_sock_secure_port, + .xpo_kill_temp_xprt = svc_udp_kill_temp_xprt, }; static struct svc_xprt_class svc_udp_class = { @@ -1242,6 +1262,7 @@ static struct svc_xprt_ops svc_tcp_ops = { .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, .xpo_secure_port = svc_sock_secure_port, + .xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt, }; static struct svc_xprt_class svc_tcp_class = { diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 210949562786..26b26beef2d4 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -44,18 +44,20 @@ * being done. * * When the underlying transport disconnects, MRs are left in one of - * three states: + * four states: * * INVALID: The MR was not in use before the QP entered ERROR state. - * (Or, the LOCAL_INV WR has not completed or flushed yet). - * - * STALE: The MR was being registered or unregistered when the QP - * entered ERROR state, and the pending WR was flushed. * * VALID: The MR was registered before the QP entered ERROR state. * - * When frwr_op_map encounters STALE and VALID MRs, they are recovered - * with ib_dereg_mr and then are re-initialized. Beause MR recovery + * FLUSHED_FR: The MR was being registered when the QP entered ERROR + * state, and the pending WR was flushed. + * + * FLUSHED_LI: The MR was being invalidated when the QP entered ERROR + * state, and the pending WR was flushed. + * + * When frwr_op_map encounters FLUSHED and VALID MRs, they are recovered + * with ib_dereg_mr and then are re-initialized. Because MR recovery * allocates fresh resources, it is deferred to a workqueue, and the * recovered MRs are placed back on the rb_mws list when recovery is * complete. frwr_op_map allocates another MR for the current RPC while @@ -177,12 +179,15 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) static void frwr_op_recover_mr(struct rpcrdma_mw *mw) { + enum rpcrdma_frmr_state state = mw->frmr.fr_state; struct rpcrdma_xprt *r_xprt = mw->mw_xprt; struct rpcrdma_ia *ia = &r_xprt->rx_ia; int rc; rc = __frwr_reset_mr(ia, mw); - ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); + if (state != FRMR_FLUSHED_LI) + ib_dma_unmap_sg(ia->ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); if (rc) goto out_release; @@ -262,10 +267,8 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) } static void -__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_frmr *frmr, - const char *wr) +__frwr_sendcompletion_flush(struct ib_wc *wc, const char *wr) { - frmr->fr_state = FRMR_IS_STALE; if (wc->status != IB_WC_WR_FLUSH_ERR) pr_err("rpcrdma: %s: %s (%u/0x%x)\n", wr, ib_wc_status_msg(wc->status), @@ -288,7 +291,8 @@ frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) { cqe = wc->wr_cqe; frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); - __frwr_sendcompletion_flush(wc, frmr, "fastreg"); + frmr->fr_state = FRMR_FLUSHED_FR; + __frwr_sendcompletion_flush(wc, "fastreg"); } } @@ -308,7 +312,8 @@ frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) { cqe = wc->wr_cqe; frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); - __frwr_sendcompletion_flush(wc, frmr, "localinv"); + frmr->fr_state = FRMR_FLUSHED_LI; + __frwr_sendcompletion_flush(wc, "localinv"); } } @@ -328,8 +333,10 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) /* WARNING: Only wr_cqe and status are reliable at this point */ cqe = wc->wr_cqe; frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); - if (wc->status != IB_WC_SUCCESS) - __frwr_sendcompletion_flush(wc, frmr, "localinv"); + if (wc->status != IB_WC_SUCCESS) { + frmr->fr_state = FRMR_FLUSHED_LI; + __frwr_sendcompletion_flush(wc, "localinv"); + } complete(&frmr->fr_linv_done); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 6864fb967038..1334de2715c2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -67,6 +67,7 @@ static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); static int svc_rdma_secure_port(struct svc_rqst *); +static void svc_rdma_kill_temp_xprt(struct svc_xprt *); static struct svc_xprt_ops svc_rdma_ops = { .xpo_create = svc_rdma_create, @@ -79,6 +80,7 @@ static struct svc_xprt_ops svc_rdma_ops = { .xpo_has_wspace = svc_rdma_has_wspace, .xpo_accept = svc_rdma_accept, .xpo_secure_port = svc_rdma_secure_port, + .xpo_kill_temp_xprt = svc_rdma_kill_temp_xprt, }; struct svc_xprt_class svc_rdma_class = { @@ -1317,6 +1319,10 @@ static int svc_rdma_secure_port(struct svc_rqst *rqstp) return 1; } +static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt) +{ +} + int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) { struct ib_send_wr *bad_wr, *n_wr; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0d35b761c883..6e1bba358203 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -216,7 +216,8 @@ struct rpcrdma_rep { enum rpcrdma_frmr_state { FRMR_IS_INVALID, /* ready to be used */ FRMR_IS_VALID, /* in use */ - FRMR_IS_STALE, /* failed completion */ + FRMR_FLUSHED_FR, /* flushed FASTREG WR */ + FRMR_FLUSHED_LI, /* flushed LOCALINV WR */ }; struct rpcrdma_frmr { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f9f5f3c3dab5..db32777ab591 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2015, Ericsson AB + * Copyright (c) 2001-2007, 2012-2016, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -129,54 +129,8 @@ static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; static const struct proto_ops msg_ops; static struct proto tipc_proto; - static const struct rhashtable_params tsk_rht_params; -/* - * Revised TIPC socket locking policy: - * - * Most socket operations take the standard socket lock when they start - * and hold it until they finish (or until they need to sleep). Acquiring - * this lock grants the owner exclusive access to the fields of the socket - * data structures, with the exception of the backlog queue. A few socket - * operations can be done without taking the socket lock because they only - * read socket information that never changes during the life of the socket. - * - * Socket operations may acquire the lock for the associated TIPC port if they - * need to perform an operation on the port. If any routine needs to acquire - * both the socket lock and the port lock it must take the socket lock first - * to avoid the risk of deadlock. - * - * The dispatcher handling incoming messages cannot grab the socket lock in - * the standard fashion, since invoked it runs at the BH level and cannot block. - * Instead, it checks to see if the socket lock is currently owned by someone, - * and either handles the message itself or adds it to the socket's backlog - * queue; in the latter case the queued message is processed once the process - * owning the socket lock releases it. - * - * NOTE: Releasing the socket lock while an operation is sleeping overcomes - * the problem of a blocked socket operation preventing any other operations - * from occurring. However, applications must be careful if they have - * multiple threads trying to send (or receive) on the same socket, as these - * operations might interfere with each other. For example, doing a connect - * and a receive at the same time might allow the receive to consume the - * ACK message meant for the connect. While additional work could be done - * to try and overcome this, it doesn't seem to be worthwhile at the present. - * - * NOTE: Releasing the socket lock while an operation is sleeping also ensures - * that another operation that must be performed in a non-blocking manner is - * not delayed for very long because the lock has already been taken. - * - * NOTE: This code assumes that certain fields of a port/socket pair are - * constant over its lifetime; such fields can be examined without taking - * the socket lock and/or port lock, and do not need to be re-read even - * after resuming processing after waiting. These fields include: - * - socket type - * - pointer to socket sk structure (aka tipc_sock structure) - * - pointer to port structure - * - port reference - */ - static u32 tsk_own_node(struct tipc_sock *tsk) { return msg_prevnode(&tsk->phdr); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 145082e2ba36..2358f2690ec5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2199,7 +2199,8 @@ out: * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last, unsigned int last_len) + struct sk_buff *last, unsigned int last_len, + bool freezable) { struct sk_buff *tail; DEFINE_WAIT(wait); @@ -2220,7 +2221,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); - timeo = freezable_schedule_timeout(timeo); + if (freezable) + timeo = freezable_schedule_timeout(timeo); + else + timeo = schedule_timeout(timeo); unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) @@ -2250,7 +2254,8 @@ struct unix_stream_read_state { unsigned int splice_flags; }; -static int unix_stream_read_generic(struct unix_stream_read_state *state) +static int unix_stream_read_generic(struct unix_stream_read_state *state, + bool freezable) { struct scm_cookie scm; struct socket *sock = state->socket; @@ -2330,7 +2335,7 @@ again: mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, - last_len); + last_len, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -2472,7 +2477,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, .flags = flags }; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, true); } static int unix_stream_splice_actor(struct sk_buff *skb, @@ -2503,7 +2508,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, flags & SPLICE_F_NONBLOCK) state.flags = MSG_DONTWAIT; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, false); } static int unix_shutdown(struct socket *sock, int mode) @@ -2812,7 +2817,8 @@ static int unix_seq_show(struct seq_file *seq, void *v) i++; } for ( ; i < len; i++) - seq_putc(seq, u->addr->name->sun_path[i]); + seq_putc(seq, u->addr->name->sun_path[i] ?: + '@'); } unix_state_unlock(s); seq_putc(seq, '\n'); diff --git a/net/wireless/core.h b/net/wireless/core.h index 08d2e948c9ad..f0c0c8a48c92 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -71,6 +71,7 @@ struct cfg80211_registered_device { struct list_head bss_list; struct rb_root bss_tree; u32 bss_generation; + u32 bss_entries; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ struct sk_buff *scan_msg; struct cfg80211_sched_scan_request __rcu *sched_scan_req; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b5bd58d0f731..35ad69fd0838 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -57,6 +57,19 @@ * also linked into the probe response struct. */ +/* + * Limit the number of BSS entries stored in mac80211. Each one is + * a bit over 4k at most, so this limits to roughly 4-5M of memory. + * If somebody wants to really attack this though, they'd likely + * use small beacons, and only one type of frame, limiting each of + * the entries to a much smaller size (in order to generate more + * entries in total, so overhead is bigger.) + */ +static int bss_entries_limit = 1000; +module_param(bss_entries_limit, int, 0644); +MODULE_PARM_DESC(bss_entries_limit, + "limit to number of scan BSS entries (per wiphy, default 1000)"); + #define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) static void bss_free(struct cfg80211_internal_bss *bss) @@ -137,6 +150,10 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev, list_del_init(&bss->list); rb_erase(&bss->rbn, &rdev->bss_tree); + rdev->bss_entries--; + WARN_ONCE((rdev->bss_entries == 0) ^ list_empty(&rdev->bss_list), + "rdev bss entries[%d]/list[empty:%d] corruption\n", + rdev->bss_entries, list_empty(&rdev->bss_list)); bss_ref_put(rdev, bss); return true; } @@ -163,6 +180,40 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev, rdev->bss_generation++; } +static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev) +{ + struct cfg80211_internal_bss *bss, *oldest = NULL; + bool ret; + + lockdep_assert_held(&rdev->bss_lock); + + list_for_each_entry(bss, &rdev->bss_list, list) { + if (atomic_read(&bss->hold)) + continue; + + if (!list_empty(&bss->hidden_list) && + !bss->pub.hidden_beacon_bss) + continue; + + if (oldest && time_before(oldest->ts, bss->ts)) + continue; + oldest = bss; + } + + if (WARN_ON(!oldest)) + return false; + + /* + * The callers make sure to increase rdev->bss_generation if anything + * gets removed (and a new entry added), so there's no need to also do + * it here. + */ + + ret = __cfg80211_unlink_bss(rdev, oldest); + WARN_ON(!ret); + return ret; +} + void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool send_message) { @@ -689,6 +740,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, const u8 *ie; int i, ssidlen; u8 fold = 0; + u32 n_entries = 0; ies = rcu_access_pointer(new->pub.beacon_ies); if (WARN_ON(!ies)) @@ -712,6 +764,12 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, /* This is the bad part ... */ list_for_each_entry(bss, &rdev->bss_list, list) { + /* + * we're iterating all the entries anyway, so take the + * opportunity to validate the list length accounting + */ + n_entries++; + if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid)) continue; if (bss->pub.channel != new->pub.channel) @@ -740,6 +798,10 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, new->pub.beacon_ies); } + WARN_ONCE(n_entries != rdev->bss_entries, + "rdev bss entries[%d]/list[len:%d] corruption\n", + rdev->bss_entries, n_entries); + return true; } @@ -894,7 +956,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, } } + if (rdev->bss_entries >= bss_entries_limit && + !cfg80211_bss_expire_oldest(rdev)) { + kfree(new); + goto drop; + } + list_add_tail(&new->list, &rdev->bss_list); + rdev->bss_entries++; rb_insert_bss(rdev, new); found = new; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 5ea12afc7706..659b507b347d 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1158,7 +1158,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 58500000, 65000000, 78000000, - 0, + /* not in the spec, but some devices use this: */ + 86500000, }, { 13500000, 27000000, |