diff options
Diffstat (limited to 'net')
64 files changed, 770 insertions, 323 deletions
diff --git a/net/atm/common.c b/net/atm/common.c index c7f92405daf0..81195727fa18 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -710,7 +710,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct atm_vcc *vcc; - unsigned long value; + int value; int error; if (__SO_LEVEL_MATCH(optname, level) && optlen != __SO_SIZE(optname)) @@ -722,8 +722,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, { struct atm_qos qos; - if (copy_from_sockptr(&qos, optval, sizeof(qos))) - return -EFAULT; + error = copy_safe_from_sockptr(&qos, sizeof(qos), optval, + optlen); + if (error) + return error; error = check_qos(&qos); if (error) return error; @@ -737,8 +739,10 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, return 0; } case SO_SETCLP: - if (copy_from_sockptr(&value, optval, sizeof(value))) - return -EFAULT; + error = copy_safe_from_sockptr(&value, sizeof(value), optval, + optlen); + if (error) + return error; if (value) vcc->atm_options |= ATM_ATMOPT_CLP; else diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 179d2470b724..ef16d0703924 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -224,11 +224,9 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, sub_opt = skb_put(skb, sizeof(*sub_opt)); memset(sub_opt, 0x0, sizeof(*sub_opt)); - sub_tlv = skb_put(skb, sizeof(*sub_tlv)); - sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; - /* 32 bit alligment shall be ensured therefore add 2 bytes */ - skb_put(skb, MRP_OPT_PADDING); + sub_tlv = skb_put_zero(skb, sizeof(*sub_tlv) + MRP_OPT_PADDING); + sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; } br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index 61bf8f4465ab..426f8adc912c 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -41,11 +41,25 @@ ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int ebt_nflog_tg_check(const struct xt_tgchk_param *par) { struct ebt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~EBT_NFLOG_MASK) return -EINVAL; info->prefix[EBT_NFLOG_PREFIX_SIZE - 1] = '\0'; - return 0; + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; +} + +static void ebt_nflog_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_ULOG); } static struct xt_target ebt_nflog_tg_reg __read_mostly = { @@ -54,6 +68,7 @@ static struct xt_target ebt_nflog_tg_reg __read_mostly = { .family = NFPROTO_BRIDGE, .target = ebt_nflog_tg, .checkentry = ebt_nflog_tg_check, + .destroy = ebt_nflog_tg_destroy, .targetsize = sizeof(struct ebt_nflog_info), .me = THIS_MODULE, }; diff --git a/net/core/datagram.c b/net/core/datagram.c index c285c6465923..173b5d97bd40 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -712,6 +712,9 @@ zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from, size_t virt_addr, size, off; struct net_iov *niov; + if (i && skb_frags_readable(skb)) + return -EFAULT; + /* Devmem filling works by taking an IOVEC from the user where the * iov_addrs are interpreted as an offset in bytes into the dma-buf to * send from. We do not support other iter types. diff --git a/net/core/dev.c b/net/core/dev.c index 5933c5dab09e..af260ff5462a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -11494,6 +11494,7 @@ int register_netdevice(struct net_device *dev) * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ + netdev_uevent_add(dev); if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing)) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); @@ -12435,6 +12436,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); dev_memory_provider_uninstall(dev); + netdev_work_cancel_all(dev); netdev_unlock_ops(dev); bpf_dev_bound_netdev_unregister(dev); diff --git a/net/core/dev.h b/net/core/dev.h index 5d0b0305d3ba..b757faead4d1 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -179,6 +179,7 @@ enum netdev_work_core { void __netdev_work_core_sched(struct net_device *dev, unsigned long event); unsigned long __netdev_work_core_cancel(struct net_device *dev, unsigned long mask); +void netdev_work_cancel_all(struct net_device *dev); void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges, u32 portid, diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 0e71c9ed41e8..25546deacec8 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -2334,6 +2334,9 @@ int netdev_register_kobject(struct net_device *ndev) *groups++ = &wireless_group; #endif /* CONFIG_SYSFS */ + /* Hold back the KOBJ_ADD uevent until the device is listed. */ + dev_set_uevent_suppress(dev, 1); + error = device_add(dev); if (error) return error; @@ -2349,6 +2352,17 @@ int netdev_register_kobject(struct net_device *ndev) return error; } +/* Announce a fully registered device to userspace. This pairs with the uevent + * suppression from netdev_register_kobject(). + */ +void netdev_uevent_add(struct net_device *ndev) +{ + struct device *dev = &ndev->dev; + + dev_set_uevent_suppress(dev, 0); + kobject_uevent(&dev->kobj, KOBJ_ADD); +} + /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 38e2e3ffd0bd..2f41a4dee866 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -4,6 +4,7 @@ int __init netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); +void netdev_uevent_add(struct net_device *dev); void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); int netdev_queue_update_kobjects(struct net_device *net, diff --git a/net/core/netdev_work.c b/net/core/netdev_work.c index 3109fae132ad..e721a06d58df 100644 --- a/net/core/netdev_work.c +++ b/net/core/netdev_work.c @@ -31,6 +31,10 @@ static void netdev_work_enqueue(struct net_device *dev, unsigned long events, return; spin_lock_bh(&netdev_work_lock); + if (!dev_isalive(dev)) { + spin_unlock_bh(&netdev_work_lock); + return; + } if (list_empty(&dev->work_node)) { list_add_tail(&dev->work_node, &netdev_work_list); netdev_hold(dev, &dev->work_tracker, GFP_ATOMIC); @@ -61,6 +65,18 @@ netdev_work_dequeue(struct net_device *dev, unsigned long *pending, return events; } +void netdev_work_cancel_all(struct net_device *dev) +{ + spin_lock_bh(&netdev_work_lock); + dev->work_pending = 0; + dev->work_core_pending = 0; + if (!list_empty(&dev->work_node)) { + list_del_init(&dev->work_node); + netdev_put(dev, &dev->work_tracker); + } + spin_unlock_bh(&netdev_work_lock); +} + void netdev_work_sched(struct net_device *dev, unsigned long events) { netdev_work_enqueue(dev, events, 0); diff --git a/net/core/sock.c b/net/core/sock.c index ffa73594c13c..1ad41904db25 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -779,7 +779,6 @@ bool sk_mc_loop(const struct sock *sk) return inet6_test_bit(MC6_LOOP, sk); #endif } - WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); diff --git a/net/core/xdp.c b/net/core/xdp.c index 9890a30584ba..0194e69da339 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -871,7 +871,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) headroom = xdpf->headroom + sizeof(*xdpf); totalsize = headroom + xdpf->len; - if (unlikely(totalsize > PAGE_SIZE)) + if (unlikely(totalsize > SKB_WITH_OVERHEAD(PAGE_SIZE))) return NULL; page = dev_alloc_page(); if (!page) diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 57b2b8f03543..fd5633fa88ec 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -578,6 +578,7 @@ int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) action != DEVLINK_RELOAD_ACTION_DRIVER_REINIT) { NL_SET_ERR_MSG_MOD(info->extack, "Changing namespace is only supported for reinit action"); + put_net(dest_net); return -EOPNOTSUPP; } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4f3c0740dde9..78f84ae3ee12 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -490,6 +490,34 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) return -1; } +static size_t fib_nexthop_nlmsg_size(const struct fib_nh_common *nhc, + bool skip_oif) +{ + size_t nhsize = 0; + + switch (nhc->nhc_gw_family) { + case AF_INET: + nhsize += nla_total_size(4); /* RTA_GATEWAY */ + break; + case AF_INET6: + nhsize += nla_total_size(sizeof(struct rtvia) + + sizeof(struct in6_addr)); + break; + } + + if (!skip_oif && nhc->nhc_dev) + nhsize += nla_total_size(4); /* RTA_OIF */ + + if (nhc->nhc_lwtstate) { + /* RTA_ENCAP */ + nhsize += lwtunnel_get_encap_size(nhc->nhc_lwtstate); + /* RTA_ENCAP_TYPE */ + nhsize += nla_total_size(2); + } + + return nhsize; +} + size_t fib_nlmsg_size(struct fib_info *fi) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) @@ -507,32 +535,35 @@ size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size(4); /* RTA_NH_ID */ if (nhs) { - size_t nh_encapsize = 0; - /* Also handles the special case nhs == 1 */ - - /* each nexthop is packed in an attribute */ - size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); + size_t mpsize = 0; unsigned int i; - /* may contain flow and gateway attribute */ - nhsize += 2 * nla_total_size(4); - - /* grab encap info */ for (i = 0; i < fib_info_num_path(fi); i++) { struct fib_nh_common *nhc = fib_info_nhc(fi, i); + size_t nhsize; + + nhsize = fib_nexthop_nlmsg_size(nhc, nhs != 1); - if (nhc->nhc_lwtstate) { - /* RTA_ENCAP_TYPE */ - nh_encapsize += lwtunnel_get_encap_size( - nhc->nhc_lwtstate); - /* RTA_ENCAP */ - nh_encapsize += nla_total_size(2); + if (nhs != 1) + nhsize += NLA_ALIGN(sizeof(struct rtnexthop)); + +#ifdef CONFIG_IP_ROUTE_CLASSID + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + if (nh->nh_tclassid) + nhsize += nla_total_size(4); } +#endif + if (nhs == 1) + payload += nhsize; + else + mpsize += nhsize; } - /* all nexthops are packed in a nested attribute */ - payload += nla_total_size((nhs * nhsize) + nh_encapsize); - + if (nhs != 1) + payload += nla_total_size(mpsize); } return payload; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 56902bba5483..6257459bcee2 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -943,11 +943,23 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, nreq->rsk_listener = sk; - /* We need not acquire fastopenq->lock - * because the child socket is locked in inet_csk_listen_stop(). - */ - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) { + struct fastopen_queue *fastopenq; + + /* reqsk_fastopen_remove() will uncharge nreq->rsk_listener, + * that is @sk, so charge it here. Unlike the listener + * being closed, @sk is live and needs its lock. + */ + fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen++; + spin_unlock_bh(&fastopenq->lock); + + /* We need not acquire fastopenq->lock + * because the child socket is locked in inet_csk_listen_stop(). + */ rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); + } return nreq; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 848c0f0c2ed9..fc0cb993959f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -393,8 +393,8 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, *prev = ERR_PTR(-ENOMEM); return NULL; } - mod_timer(&q->timer, jiffies + fqdir->timeout); + spin_lock_bh(&q->lock); *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { @@ -402,13 +402,13 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, * we need to cancel what inet_frag_alloc() * anticipated. */ - int refs = 1; - q->flags |= INET_FRAG_COMPLETE; - inet_frag_kill(q, &refs); - inet_frag_putn(q, refs); + spin_unlock_bh(&q->lock); + inet_frag_putn(q, 2); return NULL; } + mod_timer(&q->timer, jiffies + fqdir->timeout); + spin_unlock_bh(&q->lock); return q; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index daff93d51342..5b6378b94701 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -252,7 +252,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); val = tcp_win_from_space(sk, sk->sk_rcvbuf); - tcp_set_window_clamp(sk, val); + WRITE_ONCE(tp->window_clamp, val); if (tp->window_clamp < tp->rcvq_space.space) tp->rcvq_space.space = tp->window_clamp; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 29651b1a0bc7..abcd3cc2d9a3 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -178,17 +178,19 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); - struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; + struct udphdr *uh; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; + uh = udp_hdr(skb); + /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index bf8e40af60b0..ebf83f090376 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -684,6 +684,9 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!skb2) return 0; + /* Remove debris left by outer IPv6 stack. */ + memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2))); + skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fc42d67e5822..5968ce5ad150 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -988,13 +988,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { - if (rinfo->length < 2) { + /* RFC 4191: Length MUST be 3 when Prefix Length > 64 */ + if (rinfo->length < 3) return -EINVAL; - } } else if (rinfo->prefix_len > 0) { - if (rinfo->length < 1) { + /* RFC 4191: Length MUST be 2 or 3 when Prefix Length > 0 */ + if (rinfo->length < 2) return -EINVAL; - } } pref = rinfo->route_pref; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 65089826ff59..005338f89b75 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -415,6 +415,7 @@ void mac802154_beacon_worker(struct work_struct *work) container_of(work, struct ieee802154_local, beacon_work.work); struct cfg802154_beacon_request *beacon_req; struct ieee802154_sub_if_data *sdata; + netdevice_tracker dev_tracker; struct wpan_dev *wpan_dev; u8 interval; int ret; @@ -427,12 +428,14 @@ void mac802154_beacon_worker(struct work_struct *work) } sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(beacon_req->wpan_dev); + netdev_hold(sdata->dev, &dev_tracker, GFP_ATOMIC); /* Wait an arbitrary amount of time in case we cannot use the device */ if (local->suspended || !ieee802154_sdata_running(sdata)) { rcu_read_unlock(); queue_delayed_work(local->mac_wq, &local->beacon_work, msecs_to_jiffies(1000)); + netdev_put(sdata->dev, &dev_tracker); return; } @@ -450,6 +453,7 @@ void mac802154_beacon_worker(struct work_struct *work) if (interval < IEEE802154_ACTIVE_SCAN_DURATION) queue_delayed_work(local->mac_wq, &local->beacon_work, local->beacon_interval); + netdev_put(sdata->dev, &dev_tracker); } int mac802154_stop_beacons_locked(struct ieee802154_local *local, diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 082c46c0f50e..f717750906ff 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -24,12 +24,13 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf sk = subflow->conn; tp = tcp_sk(ssk); - subflow->is_mptfo = 1; - + /* A valid TFO cookie does not guarantee SYN data. */ skb = skb_peek(&ssk->sk_receive_queue); - if (WARN_ON_ONCE(!skb)) + if (!skb) return; + subflow->is_mptfo = 1; + /* dequeue the skb from sk receive queue */ __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c664023d37ba..1057d500577b 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -50,6 +50,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } + /* Only the MPC + ACK can be used with a RM_ADDR */ + if (subopt == OPTION_MPTCP_MPC_ACK) { + if ((mp_opt->suboptions & ~OPTION_MPTCP_RM_ADDR) != 0) + break; + } else if (mp_opt->suboptions != 0) { + break; + } + /* Cfr RFC 8684 Section 3.3.0: * If a checksum is present but its use had * not been negotiated in the MP_CAPABLE handshake, the receiver MUST @@ -122,6 +130,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; @@ -153,6 +166,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_DSS: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO | + OPTION_MPTCP_FASTCLOSE | + OPTION_MPTCP_FAIL)) != 0) + break; + pr_debug("DSS\n"); ptr++; @@ -188,8 +209,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && - opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) + opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { + mp_opt->dsn64 = 0; + mp_opt->use_map = 0; + mp_opt->ack64 = 0; + mp_opt->use_ack = 0; + mp_opt->data_fin = 0; break; + } mp_opt->suboptions |= OPTION_MPTCP_DSS; if (mp_opt->use_ack) { @@ -234,6 +261,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_ADD_ADDR: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO; if (!mp_opt->echo) { if (opsize == TCPOLEN_MPTCP_ADD_ADDR || @@ -293,6 +326,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RM_ADDR: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_MPC_ACK | + OPTIONS_MPTCP_MPJ | + OPTIONS_MPTCP_DSS | + OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 || opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX) break; @@ -307,6 +348,13 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_PRIO: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_MPJ | + OPTIONS_MPTCP_DSS | + OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_RM_ADDR)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_PRIO) break; @@ -316,6 +364,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_FASTCLOSE: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RST)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_FASTCLOSE) break; @@ -327,6 +380,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RST: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_FAIL | + OPTION_MPTCP_FASTCLOSE)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_RST) break; @@ -342,6 +400,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_FAIL: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RST)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_FAIL) break; @@ -1400,7 +1463,7 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, * RM | C | C | C | P |------|------|------|------| * PRIO | X | C | C | C | C |------|------|------| * FAIL | X | X | C | X | X | X |------|------| - * FC | X | X | X | X | X | X | X |------| + * FC | X | X | P | X | X | X | X |------| * RST | X | X | X | X | X | X | O | O | * ------|------|------|------|------|------|------|------|------| * diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 6afd39aea110..64a1236aabee 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -380,6 +380,7 @@ static void mptcp_pm_add_addr_timer(struct timer_list *timer) struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; unsigned int timeout = 0; + bool retransmit; pr_debug("msk=%p\n", msk); @@ -412,14 +413,15 @@ static void mptcp_pm_add_addr_timer(struct timer_list *timer) entry->retrans_times++; } - if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) + retransmit = entry->retrans_times < ADD_ADDR_RETRANS_MAX; + if (retransmit) timeout <<= entry->retrans_times; else timeout = 0; spin_unlock_bh(&msk->pm.lock); - if (entry->retrans_times == ADD_ADDR_RETRANS_MAX) + if (!retransmit) mptcp_pm_subflow_established(msk); out: @@ -441,6 +443,9 @@ bool mptcp_pm_announced_alloc(struct mptcp_sock *msk, lockdep_assert_held(&msk->pm.lock); + if (msk->pm.status & BIT(MPTCP_PM_DESTROYING)) + return false; + add_entry = mptcp_pm_announced_lookup(msk, addr); if (add_entry) { if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) @@ -1143,10 +1148,16 @@ void mptcp_pm_worker(struct mptcp_sock *msk) void mptcp_pm_destroy(struct mptcp_sock *msk) { + spin_lock_bh(&msk->pm.lock); + msk->pm.status |= BIT(MPTCP_PM_DESTROYING); + spin_unlock_bh(&msk->pm.lock); + mptcp_pm_free_announced_list(msk); - if (mptcp_pm_is_userspace(msk)) - mptcp_userspace_pm_free_local_addr_list(msk); + /* Free the userspace local address list unconditionally: the socket + * can be reused (mptcp_disconnect()) and re-selected to a different PM + */ + mptcp_userspace_pm_free_local_addr_list(msk); } void mptcp_pm_data_reset(struct mptcp_sock *msk) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 945aa5afc2dd..2203cc2d2748 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -54,6 +54,10 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, bitmap_zero(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_lock_bh(&msk->pm.lock); + if (msk->pm.status & BIT(MPTCP_PM_DESTROYING)) { + ret = -EINVAL; + goto append_err; + } mptcp_for_each_userspace_pm_addr(msk, e) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); if (addr_match && entry->addr.id == 0 && needs_id) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index ca644ec53eed..7c8180d8d5ef 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -149,6 +149,12 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) static void mptcp_drop(struct sock *sk, struct sk_buff *skb) { + /* The skb forward memory was already transferred to sk by + * mptcp_borrow_fwdmem(), even before setting the destructor. + */ + if (!skb->destructor) + sk_mem_reclaim(sk); + sk_drops_skbadd(sk, skb); __kfree_skb(skb); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4a2d40cd7b13..1b80f2d6ec5a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -37,6 +37,7 @@ OPTION_MPTCP_MPC_ACK) #define OPTIONS_MPTCP_MPJ (OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \ OPTION_MPTCP_MPJ_ACK) +#define OPTIONS_MPTCP_DSS (OPTION_MPTCP_DSS | OPTION_MPTCP_CSUMREQD) /* MPTCP option subtypes */ #define MPTCPOPT_MP_CAPABLE 0 @@ -189,9 +190,10 @@ enum mptcp_pm_status { MPTCP_PM_ESTABLISHED, MPTCP_PM_SUBFLOW_ESTABLISHED, MPTCP_PM_ALREADY_ESTABLISHED, /* persistent status, set after ESTABLISHED event */ - MPTCP_PM_MPC_ENDPOINT_ACCOUNTED /* persistent status, set after MPC local address is - * accounted int id_avail_bitmap - */ + MPTCP_PM_MPC_ENDPOINT_ACCOUNTED, /* persistent status, set after MPC local address is + * accounted int id_avail_bitmap + */ + MPTCP_PM_DESTROYING, /* To fence out PM list allocs */ }; enum mptcp_pm_type { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8e386899ceb9..e1f20ff8fdb4 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -174,8 +174,6 @@ static int subflow_check_req(struct request_sock *req, if (unlikely(listener->pm_listener)) return subflow_reset_req_endp(req, skb); - if (opt_mp_join) - return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); @@ -277,9 +275,6 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); - if (opt_mp_capable && opt_mp_join) - return -EINVAL; - if (opt_mp_capable && listener->request_mptcp) { if (mp_opt.sndr_key == 0) return -EINVAL; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 2f872d064396..8cc538358f6a 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -461,6 +461,10 @@ static int ncsi_send_cmd_nl(struct sk_buff *msg, struct genl_info *info) nca.req_flags = NCSI_REQ_FLAG_NETLINK_DRIVEN; nca.info = info; nca.payload = ntohs(hdr->length); + if (nca.payload > len - sizeof(*hdr)) { + ret = -EINVAL; + goto out_netlink; + } nca.data = data + sizeof(*hdr); ret = ncsi_xmit_cmd(&nca); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index bb9b5bed10e1..226fdf17b683 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -77,7 +77,7 @@ mtype_flush(struct ip_set *set) mtype_ext_cleanup(set); bitmap_zero(map->members, map->elements); set->elements = 0; - set->ext_size = 0; + atomic64_set(&set->ext_size, 0); } /* Calculate the actual memory size of the set data */ @@ -93,7 +93,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) { const struct mtype *map = set->data; struct nlattr *nested; - size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size; + size_t memsize = mtype_memsize(map, set->dsize) + atomic64_read(&set->ext_size); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 6cfad152d7d1..543851a923d0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -25,6 +25,7 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */ static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */ static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */ +static struct workqueue_struct *ipset_destroy_wq; struct ip_set_net { struct ip_set * __rcu *ip_set_list; /* all individual sets */ @@ -350,7 +351,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, size_t len = ext->comment ? strlen(ext->comment) : 0; if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, NULL); kfree_rcu(c, rcu); } @@ -362,7 +363,7 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, if (unlikely(!c)) return; strscpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; + atomic64_add(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, c); } EXPORT_SYMBOL_GPL(ip_set_init_comment); @@ -392,7 +393,7 @@ ip_set_comment_free(struct ip_set *set, void *ptr) c = rcu_dereference_protected(comment->c, 1); if (unlikely(!c)) return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + atomic64_sub(sizeof(*c) + strlen(c->str) + 1, &set->ext_size); rcu_assign_pointer(comment->c, NULL); kfree_rcu(c, rcu); } @@ -1178,22 +1179,26 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { .len = IPSET_MAXNAMELEN - 1 }, }; -/* In order to return quickly when destroying a single set, it is split - * into two stages: - * - Cancel garbage collector - * - Destroy the set itself via call_rcu() - */ - static void -ip_set_destroy_set_rcu(struct rcu_head *head) +destroy_and_free_set(struct ip_set *set) { - struct ip_set *set = container_of(head, struct ip_set, rcu); - set->variant->destroy(set); module_put(set->type->me); kfree(set); } +/* In order to return quickly when destroying a single set, + * destruction is done asynchronously via work queues. + */ +static void +ip_set_destroy_set_work(struct work_struct *work) +{ + struct ip_set *set = container_of(to_rcu_work(work), + struct ip_set, rwork); + + destroy_and_free_set(set); +} + static void _destroy_all_sets(struct ip_set_net *inst) { @@ -1283,7 +1288,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, /* Must wait for flush to be really finished */ rcu_barrier(); } - call_rcu(&s->rcu, ip_set_destroy_set_rcu); + INIT_RCU_WORK(&s->rwork, ip_set_destroy_set_work); + queue_rcu_work(ipset_destroy_wq, &s->rwork); } return 0; out: @@ -2421,18 +2427,23 @@ static struct pernet_operations ip_set_net_ops = { static int __init ip_set_init(void) { - int ret = register_pernet_subsys(&ip_set_net_ops); + int ret; + + ipset_destroy_wq = alloc_ordered_workqueue("ipset_destroy_wq", 0); + if (!ipset_destroy_wq) + return -ENOMEM; + ret = register_pernet_subsys(&ip_set_net_ops); if (ret) { pr_err("ip_set: cannot register pernet_subsys.\n"); - return ret; + goto out_wq; } ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); if (ret != 0) { pr_err("ip_set: cannot register with nfnetlink.\n"); unregister_pernet_subsys(&ip_set_net_ops); - return ret; + goto out_wq; } ret = nf_register_sockopt(&so_set); @@ -2440,10 +2451,13 @@ ip_set_init(void) pr_err("SO_SET registry failed: %d\n", ret); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); unregister_pernet_subsys(&ip_set_net_ops); - return ret; + goto out_wq; } return 0; +out_wq: + destroy_workqueue(ipset_destroy_wq); + return ret; } static void __exit @@ -2453,9 +2467,7 @@ ip_set_fini(void) nfnetlink_subsys_unregister(&ip_set_netlink_subsys); unregister_pernet_subsys(&ip_set_net_ops); - /* Wait for call_rcu() in destroy */ - rcu_barrier(); - + destroy_workqueue(ipset_destroy_wq); pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index b2d77973272d..f00c82acd7f0 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -99,9 +99,15 @@ struct htable { #endif /* Book-keeping of the prefixes added to the set */ +struct net_prefix { + u8 cidr; /* the cidr value */ + u32 count; /* number of elements of this cidr */ +}; + struct net_prefixes { - u32 nets[IPSET_NET_COUNT]; /* number of elements for this cidr */ - u8 cidr[IPSET_NET_COUNT]; /* the cidr value */ + struct rcu_head rcu; + u8 len; + struct net_prefix nets[] __counted_by(len); }; /* Compute the hash table size */ @@ -127,11 +133,6 @@ htable_size(u8 hbits) #else #define __CIDR(cidr, i) (cidr) #endif - -/* cidr + 1 is stored in net_prefixes to support /0 */ -#define NCIDR_PUT(cidr) ((cidr) + 1) -#define NCIDR_GET(cidr) ((cidr) - 1) - #ifdef IP_SET_HASH_WITH_NETS_PACKED /* When cidr is packed with nomatch, cidr - 1 is stored in the data entry */ #define DCIDR_PUT(cidr) ((cidr) - 1) @@ -141,21 +142,11 @@ htable_size(u8 hbits) #define DCIDR_GET(cidr, i) __CIDR(cidr, i) #endif -#define INIT_CIDR(cidr, host_mask) \ - DCIDR_PUT(((cidr) ? NCIDR_GET(cidr) : host_mask)) - -#ifdef IP_SET_HASH_WITH_NET0 -/* cidr from 0 to HOST_MASK value and c = cidr + 1 */ -#define NLEN (HOST_MASK + 1) -#define CIDR_POS(c) ((c) - 1) -#else -/* cidr from 1 to HOST_MASK value and c = cidr + 1 */ -#define NLEN HOST_MASK -#define CIDR_POS(c) ((c) - 2) -#endif +#define INIT_CIDR(n, host_mask) ({ \ + const struct net_prefixes *__n = rcu_dereference(n); \ + DCIDR_PUT((__n)->len ? (__n)->nets[0].cidr : host_mask);\ +}) -#else -#define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ #define SET_ELEM_EXPIRED(set, d) \ @@ -204,12 +195,15 @@ static const union nf_inet_addr zeromask = {}; #undef mtype_ext_cleanup #undef mtype_add_cidr #undef mtype_del_cidr +#undef mtype_del_cidr_all #undef mtype_ahash_memsize #undef mtype_flush #undef mtype_destroy #undef mtype_same_set #undef mtype_kadt #undef mtype_uadt +#undef mtype_bucket_size +#undef mtype_hash_size #undef mtype_add #undef mtype_del @@ -249,12 +243,15 @@ static const union nf_inet_addr zeromask = {}; #define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup) #define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr) #define mtype_del_cidr IPSET_TOKEN(MTYPE, _del_cidr) +#define mtype_del_cidr_all IPSET_TOKEN(MTYPE, _del_cidr_all) #define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize) #define mtype_flush IPSET_TOKEN(MTYPE, _flush) #define mtype_destroy IPSET_TOKEN(MTYPE, _destroy) #define mtype_same_set IPSET_TOKEN(MTYPE, _same_set) #define mtype_kadt IPSET_TOKEN(MTYPE, _kadt) #define mtype_uadt IPSET_TOKEN(MTYPE, _uadt) +#define mtype_bucket_size IPSET_TOKEN(MTYPE, _bucket_size) +#define mtype_hash_size IPSET_TOKEN(MTYPE, _hash_size) #define mtype_add IPSET_TOKEN(MTYPE, _add) #define mtype_del IPSET_TOKEN(MTYPE, _del) @@ -292,6 +289,7 @@ static const union nf_inet_addr zeromask = {}; /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ + struct net_prefixes __rcu *rnets[IPSET_NET_COUNT]; /* cidr prefixes */ struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ @@ -303,9 +301,6 @@ struct htype { u8 netmask; /* netmask value for subnets to store */ union nf_inet_addr bitmask; /* stores bitmask */ #endif -#ifdef IP_SET_HASH_WITH_NETS - struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ -#endif /* Because 'next' is IPv4/IPv6 dependent, no elements of this * structure and referred in create() may come after 'next'. */ @@ -326,55 +321,108 @@ struct mtype_resize_ad { /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ -static void +static int mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { - int i, j; + struct net_prefixes *nets, *tmp; + int i, j, found, len = 0, ret = 0; spin_lock_bh(&set->lock); + nets = __ipset_dereference(h->rnets[n]); /* Add in increasing prefix order, so larger cidr first */ - for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { - if (j != -1) { + for (i = 0, found = -1; i < nets->len; i++) { + if (nets->nets[i].count) + len++; + if (found != -1) { continue; - } else if (h->nets[i].cidr[n] < cidr) { - j = i; - } else if (h->nets[i].cidr[n] == cidr) { - h->nets[CIDR_POS(cidr)].nets[n]++; + } else if (nets->nets[i].cidr < cidr) { + found = i; + } else if (nets->nets[i].cidr == cidr) { + nets->nets[i].count++; goto unlock; } } - if (j != -1) { - for (; i > j; i--) - h->nets[i].cidr[n] = h->nets[i - 1].cidr[n]; + len++; + tmp = kzalloc_flex(*tmp, nets, len, GFP_ATOMIC); + if (!tmp) { + ret = -ENOMEM; + goto unlock; + } + + tmp->len = len; + for (i = 0, j = 0; i < nets->len; i++) { + if (i == found) { + tmp->nets[j].cidr = cidr; + tmp->nets[j++].count = 1; + } + if (!nets->nets[i].count) + continue; + tmp->nets[j].cidr = nets->nets[i].cidr; + tmp->nets[j++].count = nets->nets[i].count; } - h->nets[i].cidr[n] = cidr; - h->nets[CIDR_POS(cidr)].nets[n] = 1; + if (found == -1) { + tmp->nets[j].cidr = cidr; + tmp->nets[j].count = 1; + } + rcu_assign_pointer(h->rnets[n], tmp); + kfree_rcu(nets, rcu); unlock: spin_unlock_bh(&set->lock); + return ret; } static void mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { - u8 i, j, net_end = NLEN - 1; + struct net_prefixes *nets, *tmp; + u8 i, j, len = 0; + int found; spin_lock_bh(&set->lock); - for (i = 0; i < NLEN; i++) { - if (h->nets[i].cidr[n] != cidr) - continue; - h->nets[CIDR_POS(cidr)].nets[n]--; - if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - goto unlock; - for (j = i; j < net_end && h->nets[j].cidr[n]; j++) - h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; - h->nets[j].cidr[n] = 0; + nets = __ipset_dereference(h->rnets[n]); + for (i = 0, found = -1; i < nets->len; i++) { + if (nets->nets[i].count) + len++; + if (nets->nets[i].cidr == cidr) + found = i; + } + if (unlikely(found == -1)) + goto unlock; + + nets->nets[found].count--; + if (nets->nets[found].count) + goto unlock; + len--; + tmp = kzalloc_flex(*tmp, nets, len, GFP_ATOMIC); + if (!tmp) + /* Leave a hole */ goto unlock; + + tmp->len = len; + for (i = 0, j = 0; i < nets->len; i++) { + if (!nets->nets[i].count || i == found) + continue; + tmp->nets[j].cidr = nets->nets[i].cidr; + tmp->nets[j++].count = nets->nets[i].count; } + rcu_assign_pointer(h->rnets[n], tmp); + kfree_rcu(nets, rcu); unlock: spin_unlock_bh(&set->lock); } #endif +static void +mtype_del_cidr_all(struct ip_set *set, struct htype *h, const struct mtype_elem *data) +{ +#ifdef IP_SET_HASH_WITH_NETS + int k; + + for (k = 0; k < IPSET_NET_COUNT; k++) + mtype_del_cidr(set, h, DCIDR_GET(data->cidr, k), k); +#endif +} + /* Calculate the actual memory size of the set data */ static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) @@ -402,6 +450,9 @@ static void mtype_flush(struct ip_set *set) { struct htype *h = set->data; +#ifdef IP_SET_HASH_WITH_NETS + struct net_prefixes *nets, *tmp; +#endif struct htable *t; struct hbucket *n; u32 r, i; @@ -425,7 +476,19 @@ mtype_flush(struct ip_set *set) spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS - memset(h->nets, 0, sizeof(h->nets)); + for (i = 0; i < IPSET_NET_COUNT; i++) { + nets = ipset_dereference_nfnl(h->rnets[i]); + tmp = kzalloc_obj(*tmp, GFP_ATOMIC); + if (!tmp) { + u8 j; + + for (j = 0; j < nets->len; j++) + nets->nets[j].count = 0; + } else { + rcu_assign_pointer(h->rnets[i], tmp); + kfree_rcu(nets, rcu); + } + } #endif } @@ -433,6 +496,9 @@ mtype_flush(struct ip_set *set) static void mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) { +#ifdef IP_SET_HASH_WITH_NETS + struct htype *h = set->data; +#endif struct hbucket *n; u32 i; @@ -446,6 +512,11 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } +#ifdef IP_SET_HASH_WITH_NETS + if (ext_destroy) + for (i = 0; i < IPSET_NET_COUNT; i++) + kfree(rcu_dereference_raw(h->rnets[i])); +#endif ip_set_free(t->hregion); ip_set_free(t); } @@ -493,9 +564,6 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) struct mtype_elem *data; u32 i, j, d; size_t dsize = set->dsize; -#ifdef IP_SET_HASH_WITH_NETS - u8 k; -#endif u8 pos, htable_bits = t->htable_bits; spin_lock_bh(&t->hregion[r].lock); @@ -516,12 +584,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) pr_debug("expired %u/%u\n", i, j); clear_bit(j, n->used); smp_mb__after_atomic(); -#ifdef IP_SET_HASH_WITH_NETS - for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(set, h, - NCIDR_PUT(DCIDR_GET(data->cidr, k)), - k); -#endif + mtype_del_cidr_all(set, h, data); t->hregion[r].elements--; ip_set_ext_destroy(set, data); d++; @@ -947,12 +1010,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { -#ifdef IP_SET_HASH_WITH_NETS - for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(set, h, - NCIDR_PUT(DCIDR_GET(data->cidr, i)), - i); -#endif + mtype_del_cidr_all(set, h, data); ip_set_ext_destroy(set, data); t->hregion[r].elements--; } @@ -996,7 +1054,7 @@ copy_data: t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, DCIDR_GET(d->cidr, i), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -1107,11 +1165,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (i + 1 == pos) smp_store_release(&n->pos, --pos); t->hregion[r].elements--; -#ifdef IP_SET_HASH_WITH_NETS - for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(set, h, - NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); -#endif + mtype_del_cidr_all(set, h, d); ip_set_ext_destroy(set, data); if (t->resizing && ext && ext->target) { @@ -1193,28 +1247,37 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, { struct htype *h = set->data; struct htable *t = rcu_dereference_bh(h->table); + struct net_prefixes *nets0; struct hbucket *n; struct mtype_elem *data; #if IPSET_NET_COUNT == 2 + struct net_prefixes *nets1; struct mtype_elem orig = *d; - int ret, i, j = 0, k; + int ret, i, j, k; #else - int ret, i, j = 0; + int ret, i, j; #endif u32 key, multi = 0; u8 pos; pr_debug("test by nets\n"); - for (; j < NLEN && h->nets[j].cidr[0] && !multi; j++) { + rcu_read_lock_bh(); + nets0 = rcu_dereference_bh(h->rnets[0]); +#if IPSET_NET_COUNT == 2 + nets1 = rcu_dereference_bh(h->rnets[1]); +#endif + for (j = 0; j < nets0->len && !multi; j++) { + if (!nets0->nets[j].count) + continue; #if IPSET_NET_COUNT == 2 mtype_data_reset_elem(d, &orig); - mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0]), false); - for (k = 0; k < NLEN && h->nets[k].cidr[1] && !multi; - k++) { - mtype_data_netmask(d, NCIDR_GET(h->nets[k].cidr[1]), - true); + mtype_data_netmask(d, nets0->nets[j].cidr, false); + for (k = 0; k < nets1->len && !multi; k++) { + if (!nets1->nets[k].count) + continue; + mtype_data_netmask(d, nets1->nets[k].cidr, true); #else - mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0])); + mtype_data_netmask(d, nets0->nets[j].cidr); #endif key = HKEY(d, h->initval, t->htable_bits); n = rcu_dereference_bh(hbucket(t, key)); @@ -1229,7 +1292,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, continue; ret = mtype_data_match(data, ext, mext, set, flags); if (ret != 0) - return ret; + goto unlock; #ifdef IP_SET_HASH_WITH_MULTI /* No match, reset multiple match flag */ multi = 0; @@ -1239,7 +1302,10 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, } #endif } - return 0; + ret = 0; +unlock: + rcu_read_unlock_bh(); + return ret; } #endif @@ -1294,6 +1360,24 @@ out: return ret; } +static u32 mtype_hash_size(const struct htype *h) +{ + const struct htable *t; + u8 htable_bits; + + rcu_read_lock(); + t = rcu_dereference(h->table); + htable_bits = t->htable_bits; + rcu_read_unlock(); + + return jhash_size(htable_bits); +} + +static u32 mtype_bucket_size(const struct htype *h) +{ + return h->bucketsize; +} + /* Reply a HEADER request: fill out the header part of the set */ static int mtype_head(struct ip_set *set, struct sk_buff *skb) @@ -1304,21 +1388,20 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) size_t memsize; u32 elements = 0; size_t ext_size = 0; - u8 htable_bits; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); mtype_ext_size(set, &elements, &ext_size); - memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; - htable_bits = t->htable_bits; + memsize = mtype_ahash_memsize(h, t) + ext_size + atomic64_read(&set->ext_size); rcu_read_unlock_bh(); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, - htonl(jhash_size(htable_bits))) || - nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) + + if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, htonl(mtype_hash_size(h)))) + goto nla_put_failure; + if (nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) goto nla_put_failure; #ifdef IP_SET_HASH_WITH_BITMASK /* if netmask is set to anything other than HOST_MASK we know that the user supplied netmask @@ -1342,8 +1425,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) goto nla_put_failure; #endif if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) { - if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) || - nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) + if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, mtype_bucket_size(h))) + goto nla_put_failure; + if (nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) goto nla_put_failure; } if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || @@ -1505,6 +1589,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, u8 netmask = set->family == NFPROTO_IPV4 ? 32 : 128; union nf_inet_addr bitmask = onesmask; #endif +#ifdef IP_SET_HASH_WITH_NETS + struct net_prefixes *nets; +#endif size_t hsize; struct htype *h; struct htable *t; @@ -1604,21 +1691,25 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, */ hbits = fls(hashsize - 1); hsize = htable_size(hbits); - if (hsize == 0) { - kfree(h); - return -ENOMEM; - } + if (hsize == 0) + goto free_h; t = ip_set_alloc(hsize); - if (!t) { - kfree(h); - return -ENOMEM; - } + if (!t) + goto free_h; t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); - if (!t->hregion) { - ip_set_free(t); - kfree(h); - return -ENOMEM; + if (!t->hregion) + goto free_t; +#ifdef IP_SET_HASH_WITH_NETS + for (i = 0; i < IPSET_NET_COUNT; i++) { + nets = kzalloc_obj(*nets); + if (!nets) { + while (i > 0) + kfree(rcu_dereference_raw(h->rnets[--i])); + goto free_hregion; + } + RCU_INIT_POINTER(h->rnets[i], nets); } +#endif h->gc.set = set; spin_lock_init(&h->gc.lock); for (i = 0; i < ahash_numof_locks(hbits); i++) @@ -1650,6 +1741,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, INIT_LIST_HEAD(&t->ad); RCU_INIT_POINTER(h->table, t); set->data = h; + #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { #endif @@ -1678,10 +1770,20 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", - set->name, jhash_size(t->htable_bits), + set->name, mtype_hash_size(h), t->htable_bits, h->maxelem, set->data, t); return 0; + +#ifdef IP_SET_HASH_WITH_NETS +free_hregion: + ip_set_free(t->hregion); +#endif +free_t: + ip_set_free(t); +free_h: + kfree(h); + return -ENOMEM; } #endif /* IP_SET_EMIT_CREATE */ diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 2d6652d43199..195853a25b06 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -138,7 +138,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_ipportnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -398,7 +398,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_ipportnet6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index ce0a9ce5a91f..092f3c9281b8 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -117,7 +117,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_net4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -291,7 +291,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_net6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 30a655e5c4fd..b44b95f766b7 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -161,7 +161,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netiface4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), .elem = 1, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -382,7 +382,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netiface6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), .elem = 1, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 8fbe649c9dd3..f7c8a1cc30fc 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -149,8 +149,10 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; @@ -388,8 +390,10 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index d1a0628df4ef..5de4b511de76 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -133,7 +133,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); @@ -353,7 +353,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { - .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), + .cidr = INIT_CIDR(h->rnets[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index bf4f91b78e1d..6291532be7a5 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -157,8 +157,10 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; @@ -452,8 +454,10 @@ hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); - e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); + rcu_read_lock_bh(); + e.cidr[0] = INIT_CIDR(h->rnets[0], HOST_MASK); + e.cidr[1] = INIT_CIDR(h->rnets[1], HOST_MASK); + rcu_read_unlock_bh(); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 1cef84f15e8c..ca3ef9479e83 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -421,7 +421,7 @@ list_set_flush(struct ip_set *set) list_for_each_entry_safe(e, n, &map->members, list) list_set_del(set, e); set->elements = 0; - set->ext_size = 0; + atomic64_set(&set->ext_size, 0); } static void @@ -455,7 +455,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) { const struct list_set *map = set->data; struct nlattr *nested; - size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size; + size_t memsize = list_set_memsize(map, set->dsize) + atomic64_read(&set->ext_size); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 6b79e0c4d9e2..0bdaeb4ed61e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -925,28 +925,27 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, - bool has_ports) + bool has_ports, struct ip_vs_iphdr *ciph) { struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); - struct iphdr *ciph = (struct iphdr *)(icmph + 1); - unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); + struct iphdr *cih = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); - ciph->daddr = cp->vaddr.ip; - ip_send_check(ciph); + cih->daddr = cp->vaddr.ip; + ip_send_check(cih); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); - ciph->saddr = cp->daddr.ip; - ip_send_check(ciph); + cih->saddr = cp->daddr.ip; + ip_send_check(cih); } /* the TCP/UDP/SCTP port */ if (has_ports) { - __be16 *ports = (void *)ciph + ciph->ihl*4; + __be16 *ports = (void *)(skb->data + ciph->len); if (inout) ports[1] = cp->vport; @@ -960,10 +959,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered incoming ICMP"); } @@ -1056,7 +1055,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -1092,7 +1091,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; - unsigned int offset, ihl; + unsigned int offset; union nf_inet_addr snet; *related = 1; @@ -1105,7 +1104,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; } - ihl = ipvsh->len; offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) @@ -1131,11 +1129,15 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph)) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->protocol); + pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; @@ -1146,8 +1148,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); - /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); @@ -1155,8 +1155,8 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.ip = ipvsh->saddr.ip; - return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, - hooknum); + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -1803,10 +1803,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!cih) return NF_ACCEPT; /* The packet looks wrong, ignore */ - raddr = (union nf_inet_addr *)&cih->daddr; hlen_ipip = cih->ihl * 4; + if (!(cih->version == 4 && hlen_ipip >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1823,9 +1825,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += hlen_ipip; - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) - return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ @@ -1850,21 +1849,25 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ - cih = skb_header_pointer(skb, offset, sizeof(_ciph), - &_ciph); - if (cih && cih->version == 4 && cih->ihl >= 5 && - iproto == IPPROTO_IPIP) + if (iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } - pd = ip_vs_proto_data_get(ipvs, cih->protocol); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph)) + return NF_ACCEPT; + pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; @@ -1872,9 +1875,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); - offset2 = offset; - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ @@ -1904,11 +1904,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { - unsigned int hlen_orig = cih->ihl * 4; + unsigned int hlen_orig = ciph.len - ciph.off; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; + offset2 = offset; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ab09f5182951..05a216a47b45 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -191,8 +191,11 @@ static int ip_vs_estimation_kthread(void *data) } /* kthread 0 will handle the calc phase */ - if (ipvs->est_calc_phase) + if (ipvs->est_calc_phase) { ip_vs_est_calc_phase(ipvs); + if (kthread_should_stop() || !READ_ONCE(ipvs->enable)) + return 0; + } } while (1) { @@ -270,6 +273,7 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, kd->task = NULL; goto out; } + get_task_struct(kd->task); set_user_nice(kd->task, sysctl_est_nice(ipvs)); if (sysctl_est_preferred_cpulist(ipvs)) @@ -286,7 +290,7 @@ void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd) { if (kd->task) { pr_info("stopping estimator thread %d...\n", kd->id); - kthread_stop(kd->task); + kthread_stop_put(kd->task); kd->task = NULL; } } @@ -526,7 +530,7 @@ static void ip_vs_est_kthread_destroy(struct ip_vs_est_kt_data *kd) if (kd) { if (kd->task) { pr_info("stop unused estimator thread %d...\n", kd->id); - kthread_stop(kd->task); + kthread_stop_put(kd->task); } ip_vs_stats_free(kd->calc_stats); kfree(kd); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3dbd3096e163..c80567c73469 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -193,7 +193,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, struct sctphdr *sh; __le32 cmp, val; - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 0b0c5304993a..c4508f3f43dd 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1580,7 +1580,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 0b78decce8a9..c9e332fafcb5 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -310,6 +310,7 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, struct dst_entry *dst) { skb_orphan(skb); + skb_dst_drop(skb); skb_dst_set_noref(skb, dst); dst_output(state->net, state->sk, skb); return NF_STOLEN; @@ -861,6 +862,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return NF_DROP; } xmit.dest = neigh->ha; + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); break; case FLOW_OFFLOAD_XMIT_DIRECT: @@ -1178,6 +1180,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return NF_DROP; } xmit.dest = neigh->ha; + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); break; case FLOW_OFFLOAD_XMIT_DIRECT: diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index eaf332b156d7..ae69b2cabab9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1113,9 +1113,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = -EEXIST; goto err_unlock_ovs; } - /* The flow identifier has to be the same for flow updates. - * Look for any overlapping flow. - */ + + /* Look for any overlapping flow. */ if (unlikely(!ovs_flow_cmp(flow, &match))) { if (ovs_identifier_is_key(&flow->id)) flow = ovs_flow_tbl_lookup_exact(&dp->table, @@ -1127,6 +1126,30 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; } } + + if (unlikely(reply)) { + size_t cur, req; + + cur = ovs_flow_cmd_msg_size(acts, &new_flow->id, + ufid_flags); + req = ovs_flow_cmd_msg_size(acts, &flow->id, + ufid_flags); + if (cur < req) { + struct sk_buff *resized; + + resized = ovs_flow_cmd_alloc_info(acts, + &flow->id, + info, false, + ufid_flags); + if (IS_ERR(resized)) { + error = PTR_ERR(resized); + goto err_unlock_ovs; + } + kfree_skb(reply); + reply = resized; + } + } + /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 66366982f604..46c1d66aad8c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -889,8 +889,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * Ethernet header * @key: output flow key * - * The caller must ensure that skb->len >= ETH_HLEN. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -910,8 +908,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { - struct ethhdr *eth; - /* Flags are always used as part of stats */ key->tp.flags = 0; @@ -926,6 +922,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) skb_reset_network_header(skb); key->eth.type = skb->protocol; } else { + struct ethhdr *eth; + int err; + + err = check_header(skb, ETH_HLEN); + if (unlikely(err)) + return err; + eth = eth_hdr(skb); ether_addr_copy(key->eth.src, eth->h_source); ether_addr_copy(key->eth.dst, eth->h_dest); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e75d2932475a..435756877aba 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1315,13 +1315,25 @@ static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) return ret; } -static void packet_rcv_try_clear_pressure(struct packet_sock *po) +static void __packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } +static void packet_rcv_try_clear_pressure(struct packet_sock *po) +{ + struct sock *sk = &po->sk; + + if (!packet_sock_flag(po, PACKET_SOCK_PRESSURE)) + return; + + spin_lock_bh(&sk->sk_receive_queue.lock); + __packet_rcv_try_clear_pressure(po); + spin_unlock_bh(&sk->sk_receive_queue.lock); +} + static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -1924,11 +1936,12 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; + /* On TX skb->data is the L2 header; anchor it for all socket types. */ + skb_reset_mac_header(skb); + if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && - sock->type == SOCK_RAW) { - skb_reset_mac_header(skb); + sock->type == SOCK_RAW) skb->protocol = dev_parse_header_protocol(skb); - } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && @@ -1953,8 +1966,9 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; - int err; + int hard_header_len; int extra_len = 0; + int err; /* * Get and verify the address. @@ -1997,14 +2011,18 @@ retry: extra_len = 4; /* We're doing our own CRC */ } + /* Keep the allocation-time header length across retry. */ + if (!skb) + hard_header_len = READ_ONCE(dev->hard_header_len); + err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) + if (len > dev->mtu + hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { - size_t reserved = LL_RESERVED_SPACE(dev); + size_t reserved = LL_RESERVED_SPACE_EX(dev, hard_header_len); int tlen = dev->needed_tailroom; - unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; + unsigned int hhlen = dev->header_ops ? hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); @@ -2034,7 +2052,7 @@ retry: err = -EINVAL; goto out_unlock; } - if (len > (dev->mtu + dev->hard_header_len + extra_len) && + if (len > (dev->mtu + hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; @@ -2569,6 +2587,7 @@ static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, + int hard_header_len, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; @@ -2600,8 +2619,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); - skb_push(skb, dev->hard_header_len); - skb_put(skb, copylen - dev->hard_header_len); + skb_push(skb, hard_header_len); + skb_put(skb, copylen - hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; @@ -2732,7 +2751,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; - int hlen, tlen, copylen = 0; + int hard_header_len, hlen, tlen, copylen = 0; long timeo; mutex_lock(&po->pg_vec_lock); @@ -2779,8 +2798,9 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_put; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (po->sk.sk_socket->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2817,7 +2837,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { data += vnet_hdr_sz; @@ -2835,10 +2855,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) vnet_hdr.hdr_len); has_vnet_hdr = true; } - copylen = max_t(int, copylen, dev->hard_header_len); + copylen = max_t(int, copylen, hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + - (copylen - dev->hard_header_len), + (copylen - hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { @@ -2848,7 +2868,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, - addr, hlen, copylen, &sockc); + addr, hlen, copylen, hard_header_len, + &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && @@ -2956,7 +2977,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); - int hlen, tlen, linear; + int hard_header_len, hlen, tlen, linear; int extra_len = 0; /* @@ -2996,8 +3017,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; } + hard_header_len = READ_ONCE(dev->hard_header_len); if (sock->type == SOCK_RAW) - reserve = dev->hard_header_len; + reserve = hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) @@ -3018,10 +3040,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; err = -ENOBUFS; - hlen = LL_RESERVED_SPACE(dev); + hlen = LL_RESERVED_SPACE_EX(dev, hard_header_len); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); - linear = max(linear, min_t(int, len, dev->hard_header_len)); + linear = max(linear, min_t(int, len, hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) @@ -3037,7 +3059,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && - dev->min_header_len != dev->hard_header_len) + dev->min_header_len != hard_header_len) skb_reset_network_header(skb); } @@ -4304,7 +4326,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } - packet_rcv_try_clear_pressure(po); + __packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { @@ -4544,14 +4566,14 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; + po->prot_hook.func = (po->rx_ring.pg_vec) ? + tpacket_rcv : packet_rcv; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; - po->prot_hook.func = (po->rx_ring.pg_vec) ? - tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index e5b2adb161d9..c5e7e01db249 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -78,7 +78,7 @@ struct qrtr_node { */ #define QRTR_NS_MAX_NODES 512 #define QRTR_NS_MAX_SERVERS 256 -#define QRTR_NS_MAX_LOOKUPS 64 +#define QRTR_NS_MAX_LOOKUPS 128 static u16 node_count; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index fee4524adc98..4e6a2812a4f3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -443,7 +443,22 @@ static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, bool sig_destroy, struct netlink_ext_ack *extack) { - tp->ops->destroy(tp, rtnl_held, extack); + /* A locked classifier's destroy callback (e.g. u32_destroy) uses + * rtnl_dereference() and mutates shared structures (e.g. the + * tc_u_common hash list) that are only safe under rtnl_lock. When an + * unlocked classifier's request (e.g. flower on ingress) loses the + * tcf_chain_tp_insert_unique() race and ends up dropping the last + * reference on a locked classifier's proto, destroy() would run + * without rtnl held. Take it here in that case. + */ + bool not_lockless = !rtnl_held && + !(tp->ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + + if (not_lockless) + rtnl_lock(); + tp->ops->destroy(tp, rtnl_held || not_lockless, extack); + if (not_lockless) + rtnl_unlock(); tcf_proto_count_usesw(tp, false); if (sig_destroy) tcf_proto_signal_destroyed(tp->chain, tp); diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index bd6f945bd388..eded7aacd3f7 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -52,6 +52,7 @@ struct route4_filter { struct tcf_result res; struct tcf_exts exts; u32 handle; + bool dying; struct route4_bucket *bkt; struct tcf_proto *tp; struct rcu_work rwork; @@ -66,9 +67,11 @@ static inline int route4_fastmap_hash(u32 id, int iif) static DEFINE_SPINLOCK(fastmap_lock); static void -route4_reset_fastmap(struct route4_head *head) +route4_reset_fastmap(struct route4_head *head, struct route4_filter *f) { spin_lock_bh(&fastmap_lock); + if (f) + f->dying = true; memset(head->fastmap, 0, sizeof(head->fastmap)); spin_unlock_bh(&fastmap_lock); } @@ -81,9 +84,11 @@ route4_set_fastmap(struct route4_head *head, u32 id, int iif, /* fastmap updates must look atomic to aling id, iff, filter */ spin_lock_bh(&fastmap_lock); - head->fastmap[h].id = id; - head->fastmap[h].iif = iif; - head->fastmap[h].filter = f; + if (f == ROUTE4_FAILURE || !f->dying) { + head->fastmap[h].id = id; + head->fastmap[h].iif = iif; + head->fastmap[h].filter = f; + } spin_unlock_bh(&fastmap_lock); } @@ -297,6 +302,13 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, next = rtnl_dereference(f->next); RCU_INIT_POINTER(b->ht[h2], next); tcf_unbind_filter(tp, &f->res); + /* Mark the filter dying under fastmap_lock so + * any in-flight reader that still holds it + * will skip the republish in route4_set_fastmap(). + */ + spin_lock_bh(&fastmap_lock); + f->dying = true; + spin_unlock_bh(&fastmap_lock); if (tcf_exts_get_net(&f->exts)) route4_queue_work(f); else @@ -307,6 +319,11 @@ static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, kfree_rcu(b, rcu); } } + + /* All filters are unlinked and marked dying, so no in-flight + * reader can republish a stale entry after this reset. + */ + route4_reset_fastmap(head, NULL); kfree_rcu(head, rcu); } @@ -334,11 +351,11 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, /* unlink it */ RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); - /* Remove any fastmap lookups that might ref filter - * notice we unlink'd the filter so we can't get it - * back in the fastmap. + /* Clear any fastmap entries that may ref this filter and + * mark it dying so in-flight readers can't republish it + * after the reset. */ - route4_reset_fastmap(head); + route4_reset_fastmap(head, f); /* Delete it */ tcf_unbind_filter(tp, &f->res); @@ -558,7 +575,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } } - route4_reset_fastmap(head); + route4_reset_fastmap(head, fold); *arg = f; if (fold) { tcf_unbind_filter(tp, &fold->res); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 668bcd60d183..65b35528d125 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1114,6 +1114,9 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, unsigned int i, num_q, ingress; struct netdev_queue *dev_queue; + if (new) + new->depth = 0; + ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || @@ -1211,9 +1214,15 @@ skip: NL_SET_ERR_MSG(extack, "STAB not supported on a non root"); return -EINVAL; } + if (new && parent->depth >= 7) { + NL_SET_ERR_MSG(extack, "Qdisc hierarchy is too deep"); + return -E2BIG; + } err = cops->graft(parent, cl, new, &old, extack); if (err) return err; + if (new) + new->depth = parent->depth + 1; notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index f64be54ead49..f25f60978631 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1287,7 +1287,6 @@ static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, seglen = ipv6_payload_len(skb, ipv6h_check); } else { - WARN_ON(1); /* shouldn't happen */ continue; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b6ac0966420a..5b0ae616e1ff 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -573,6 +573,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, if (ch->transport == peer) ch->transport = NULL; + list_for_each_entry(ch, &asoc->outqueue.control_chunk_list, list) + if (ch->transport == peer) + ch->transport = NULL; + asoc->peer.transport_count--; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f6b8c13dafa4..e92fb9da4647 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -650,6 +650,7 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); + chunk->transport = transport; continue; } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 0ae30c3c8913..e25612e9d082 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3336,12 +3336,11 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, goto done; } done: - asoc->peer.addip_serial++; - /* If we are sending a new ASCONF_ACK hold a reference to it in assoc * after freeing the reference to old asconf ack if any. */ if (asconf_ack) { + asoc->peer.addip_serial++; sctp_chunk_hold(asconf_ack); list_add_tail(&asconf_ack->transmitted_list, &asoc->asconf_ack_list); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b5db69073e20..00403175b740 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1931,11 +1931,12 @@ static void smc_listen_out(struct smc_sock *new_smc) atomic_dec(&lsmc->queued_smc_hs); release_sock(newsmcsk); /* lock in smc_listen_work() */ + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); release_sock(&lsmc->sk); } else { /* no longer listening */ + release_sock(&lsmc->sk); smc_close_non_accepted(newsmcsk); } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 954b2ff1815c..aa6d83af55ed 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -1927,7 +1927,8 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) return; case SMC_LLC_CONFIRM_LINK: case SMC_LLC_ADD_LINK_CONT: - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { + if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE && + !lgr->llc_flow_lcl.qentry) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); wake_up(&lgr->llc_msg_waiter); diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index c1d9b923938d..5c9e4d8b57de 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -150,7 +150,12 @@ static const struct pipe_buf_operations smc_pipe_ops = { static void smc_rx_spd_release(struct splice_pipe_desc *spd, unsigned int i) { + struct smc_spd_priv *priv = (struct smc_spd_priv *)spd->partial[i].private; + struct sock *sk = &priv->smc->sk; + + kfree(priv); put_page(spd->pages[i]); + sock_put(sk); } static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, @@ -209,6 +214,10 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, offset = 0; } } + for (i = 0; i < nr_pages; i++) { + get_page(pages[i]); + sock_hold(&smc->sk); + } spd.nr_pages_max = nr_pages; spd.nr_pages = nr_pages; spd.pages = pages; @@ -217,16 +226,8 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, spd.spd_release = smc_rx_spd_release; bytes = splice_to_pipe(pipe, &spd); - if (bytes > 0) { - sock_hold(&smc->sk); - if (!lgr->is_smcd && smc->conn.rmb_desc->is_vm) { - for (i = 0; i < PAGE_ALIGN(bytes + offset) / PAGE_SIZE; i++) - get_page(pages[i]); - } else { - get_page(smc->conn.rmb_desc->pages); - } + if (bytes > 0) atomic_add(bytes, &smc->conn.splice_pending); - } kfree(priv); kfree(partial); kfree(pages); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d4afc90fd796..62d46736e24b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags) } tx_err: - if (rc < 0 && rc != -EAGAIN) + if (rc < 0 && rc != -EAGAIN && rc != -EINTR && rc != -ERESTARTSYS) tls_err_abort(sk, rc); return rc; @@ -832,6 +832,14 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; + /* open record may be full if we couldn't push it in the last sendmsg call */ + if (sk_msg_full(msg_pl)) { + full_record = true; + sk_msg_trim(sk, msg_en, + msg_pl->sg.size + prot->overhead_size); + goto copied; + } + alloc_encrypted: ret = tls_alloc_encrypted_msg(sk, required_size); if (ret) { @@ -921,6 +929,12 @@ fallback_to_reg_send: msg_pl, try_to_copy); if (ret < 0) goto trim_sgl; + + if (sk_msg_full(msg_pl)) { + full_record = true; + sk_msg_trim(sk, msg_en, + msg_pl->sg.size + prot->overhead_size); + } } /* Open records defined only if successfully copied, otherwise @@ -1442,6 +1456,8 @@ tls_decrypt_sw(struct sock *sk, struct tls_context *tls_ctx, /* If opportunistic TLS 1.3 ZC failed retry without ZC */ if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION && darg->tail != TLS_RECORD_TYPE_DATA)) { + iov_iter_revert(&msg->msg_iter, strp_msg(darg->skb)->full_len - + prot->overhead_size); darg->zc = false; if (!darg->tail) TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXNOPADVIOL); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 57f2d6ec3ffc..96c9fe8d357c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -346,12 +346,13 @@ static void virtio_transport_tx_work(struct work_struct *work) struct virtqueue *vq; bool added = false; - vq = vsock->vqs[VSOCK_VQ_TX]; mutex_lock(&vsock->tx_lock); if (!vsock->tx_run) goto out; + vq = vsock->vqs[VSOCK_VQ_TX]; + do { struct sk_buff *skb; unsigned int len; @@ -451,13 +452,13 @@ static void virtio_transport_event_work(struct work_struct *work) container_of(work, struct virtio_vsock, event_work); struct virtqueue *vq; - vq = vsock->vqs[VSOCK_VQ_EVENT]; - mutex_lock(&vsock->event_lock); if (!vsock->event_run) goto out; + vq = vsock->vqs[VSOCK_VQ_EVENT]; + do { struct virtio_vsock_event *event; unsigned int len; @@ -634,12 +635,12 @@ static void virtio_transport_rx_work(struct work_struct *work) container_of(work, struct virtio_vsock, rx_work); struct virtqueue *vq; - vq = vsock->vqs[VSOCK_VQ_RX]; - mutex_lock(&vsock->rx_lock); if (!vsock->rx_run) - goto out; + goto out_nofill; + + vq = vsock->vqs[VSOCK_VQ_RX]; do { virtqueue_disable_cb(vq); @@ -691,6 +692,7 @@ static void virtio_transport_rx_work(struct work_struct *work) out: if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) virtio_vsock_rx_fill(vsock); +out_nofill: mutex_unlock(&vsock->rx_lock); } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 8aae9273b7c1..033e7d059f58 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -363,6 +363,7 @@ static void x25_destroy_timer(struct timer_list *t) struct sock *sk = timer_container_of(sk, t, sk_timer); x25_destroy_socket_from_timer(sk); + sock_put(sk); } /* @@ -398,9 +399,8 @@ static void __x25_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - sk->sk_timer.expires = jiffies + 10 * HZ; sk->sk_timer.function = x25_destroy_timer; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 10 * HZ); } else { /* drop last reference so sock_put will free */ __sock_put(sk); diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index 2ec63a1f4c6d..7896cd43f1cc 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -36,45 +36,45 @@ void x25_init_timers(struct sock *sk) void x25_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void x25_stop_heartbeat(struct sock *sk) { - timer_delete(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } void x25_start_t2timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t2); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t2); } void x25_start_t21timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t21); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t21); } void x25_start_t22timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t22); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t22); } void x25_start_t23timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - mod_timer(&x25->timer, jiffies + x25->t23); + sk_reset_timer(sk, &x25->timer, jiffies + x25->t23); } void x25_stop_timer(struct sock *sk) { - timer_delete(&x25_sk(sk)->timer); + sk_stop_timer(sk, &x25_sk(sk)->timer); } unsigned long x25_display_timer(struct sock *sk) @@ -108,7 +108,7 @@ static void x25_heartbeat_expiry(struct timer_list *t) sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); x25_destroy_socket_from_timer(sk); - return; + goto out; } break; @@ -120,8 +120,14 @@ static void x25_heartbeat_expiry(struct timer_list *t) break; } restart_heartbeat: - x25_start_heartbeat(sk); + /* Do not rearm once __x25_destroy_socket() has unlinked the socket: + * it is past its cancel point and owns the teardown from there on. + */ + if (sk_hashed(sk)) + x25_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } /* @@ -166,4 +172,5 @@ static void x25_timer_expiry(struct timer_list *t) } else x25_do_timer_expiry(sk); bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 58da2f4f4397..cd8643360eb3 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -210,6 +210,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) return -EINVAL; + if (mr->tx_metadata_len < 16) + return -EINVAL; umem->tx_metadata_len = mr->tx_metadata_len; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index f906d51b6699..7855ee09c4b6 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -967,15 +967,16 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, { struct xsk_tx_metadata *meta = NULL; u16 csum_start, csum_offset; + u64 flags; if (unlikely(pool->tx_metadata_len == 0)) return -EINVAL; meta = buffer - pool->tx_metadata_len; - if (unlikely(!xsk_buff_valid_tx_metadata(meta))) + if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) return -EINVAL; - if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { + if (flags & XDP_TXMD_FLAGS_CHECKSUM) { csum_start = READ_ONCE(meta->request.csum_start); csum_offset = READ_ONCE(meta->request.csum_offset); @@ -996,8 +997,10 @@ static int xsk_skb_metadata(struct sk_buff *skb, void *buffer, } } - if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME) - skb->skb_mstamp_ns = meta->request.launch_time; + if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME) + skb->skb_mstamp_ns = READ_ONCE(meta->request.launch_time); + if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP)) + meta = NULL; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); return 0; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index a4089480b22b..78c14f106395 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -765,11 +765,11 @@ EXPORT_SYMBOL(xp_raw_get_dma); * @addr: desc address (from userspace) * * Helper for getting desc's DMA address and metadata pointer, if present. - * Saves one call on hotpath, double calculation of the actual address, - * and inline checks for metadata presence and sanity. + * Saves one call on hotpath and double calculation of the actual address. + * Metadata is validated later by xsk_tx_metadata_request(). * * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata - * pointer, if it is present and valid (initialized to %NULL otherwise). + * pointer, if it is present (initialized to %NULL otherwise). */ struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr) { |