diff options
Diffstat (limited to 'net')
40 files changed, 329 insertions, 302 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 1225b4b..13f49f8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -99,6 +99,7 @@ #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/pkt_sched.h> #include <net/checksum.h> #include <net/xfrm.h> @@ -682,6 +683,32 @@ int dev_get_iflink(const struct net_device *dev) EXPORT_SYMBOL(dev_get_iflink); /** + * dev_fill_metadata_dst - Retrieve tunnel egress information. + * @dev: targeted interface + * @skb: The packet. + * + * For better visibility of tunnel traffic OVS needs to retrieve + * egress tunnel information for a packet. Following API allows + * user to get this info. + */ +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info; + + if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) + return -EINVAL; + + info = skb_tunnel_info_unclone(skb); + if (!info) + return -ENOMEM; + if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) + return -EINVAL; + + return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); +} +EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); + +/** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index bd0679d..6145214 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -498,10 +498,26 @@ static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } +static struct rtable *gre_get_rt(struct sk_buff *skb, + struct net_device *dev, + struct flowi4 *fl, + const struct ip_tunnel_key *key) +{ + struct net *net = dev_net(dev); + + memset(fl, 0, sizeof(*fl)); + fl->daddr = key->u.ipv4.dst; + fl->saddr = key->u.ipv4.src; + fl->flowi4_tos = RT_TOS(key->tos); + fl->flowi4_mark = skb->mark; + fl->flowi4_proto = IPPROTO_GRE; + + return ip_route_output_key(net, fl); +} + static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel_info *tun_info; - struct net *net = dev_net(dev); const struct ip_tunnel_key *key; struct flowi4 fl; struct rtable *rt; @@ -516,14 +532,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - memset(&fl, 0, sizeof(fl)); - fl.daddr = key->u.ipv4.dst; - fl.saddr = key->u.ipv4.src; - fl.flowi4_tos = RT_TOS(key->tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_GRE; - - rt = ip_route_output_key(net, &fl); + rt = gre_get_rt(skb, dev, &fl, key); if (IS_ERR(rt)) goto err_free_skb; @@ -566,6 +575,24 @@ err_free_skb: dev->stats.tx_dropped++; } +static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct rtable *rt; + struct flowi4 fl4; + + if (ip_tunnel_info_af(info) != AF_INET) + return -EINVAL; + + rt = gre_get_rt(skb, dev, &fl4, &info->key); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = fl4.saddr; + return 0; +} + static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -1023,6 +1050,7 @@ static const struct net_device_ops gre_tap_netdev_ops = { .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 690d27d..a355841 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -75,6 +75,7 @@ endif # NF_TABLES config NF_DUP_IPV4 tristate "Netfilter IPv4 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK help This option enables the nf_dup_ipv4 core, which duplicates an IPv4 packet to be rerouted to another destination. diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 74dd667..78cc64e 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -60,9 +60,7 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, if (FIB_RES_DEV(res) == dev) dev_match = true; #endif - if (dev_match || flags & XT_RPFILTER_LOOSE) - return FIB_RES_NH(res).nh_scope <= RT_SCOPE_HOST; - return dev_match; + return dev_match || flags & XT_RPFILTER_LOOSE; } static bool rpfilter_is_local(const struct sk_buff *skb) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 7092a61..7e538f7 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -209,7 +209,7 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) /* alpha = (1 - g) * alpha + g * F */ - alpha -= alpha >> dctcp_shift_g; + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); if (bytes_ecn) { /* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 Mbytes. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f6f7f9b..f4f9793 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3410,7 +3410,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); skb_mstamp_get(&skb->skb_mstamp); - NET_INC_STATS_BH(sock_net(sk), mib); + NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 9f298d0..7ee6518 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,6 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if (skb->len > mtu) { + skb->protocol = htons(ETH_P_IP); + if (skb->sk) xfrm_local_error(skb, mtu); else diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 9f777ec..ed33abf 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -32,6 +32,7 @@ struct fib6_rule { struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { + struct rt6_info *rt; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .flags = FIB_LOOKUP_NOREF, @@ -40,11 +41,21 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); - if (arg.result) - return arg.result; + rt = arg.result; - dst_hold(&net->ipv6.ip6_null_entry->dst); - return &net->ipv6.ip6_null_entry->dst; + if (!rt) { + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; + } + + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 09fddf7..0c7e276 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -286,7 +286,17 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + struct rt6_info *rt; + + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static void __net_init fib6_tables_init(struct net *net) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0c89671..c265068 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/kernel.h> +#include <linux/overflow-arith.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> @@ -596,7 +597,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (np->frag_size) mtu = np->frag_size; } - mtu -= hlen + sizeof(struct frag_hdr); + + if (overflow_usub(mtu, hlen + sizeof(struct frag_hdr), &mtu) || + mtu <= 7) + goto fail_toobig; frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 96833e4..f6a024e 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -58,6 +58,7 @@ endif # NF_TABLES config NF_DUP_IPV6 tristate "Netfilter IPv6 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK help This option enables the nf_dup_ipv6 core, which duplicates an IPv6 packet to be rerouted to another destination. diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d061963..2701cb3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1171,6 +1171,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, { struct dst_entry *dst; int flags = 0; + bool any_src; dst = l3mdev_rt6_dst_by_oif(net, fl6); if (dst) @@ -1178,11 +1179,12 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, fl6->flowi6_iif = LOOPBACK_IFINDEX; + any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || - fl6->flowi6_oif) + (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; - if (!ipv6_addr_any(&fl6->saddr)) + if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 9db067a..4d09ce6 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,6 +79,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (!skb->ignore_df && skb->len > mtu) { skb->dev = dst->dev; + skb->protocol = htons(ETH_P_IPV6); if (xfrm6_local_dontfrag(skb)) xfrm6_local_rxpmtu(skb, mtu); @@ -143,6 +144,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; int mtu; + bool toobig; #ifdef CONFIG_NETFILTER if (!x) { @@ -151,25 +153,29 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) } #endif + if (x->props.mode != XFRM_MODE_TUNNEL) + goto skip_frag; + if (skb->protocol == htons(ETH_P_IPV6)) mtu = ip6_skb_dst_mtu(skb); else mtu = dst_mtu(skb_dst(skb)); - if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { + toobig = skb->len > mtu && !skb_is_gso(skb); + + if (toobig && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); return -EMSGSIZE; - } else if (!skb->ignore_df && skb->len > mtu && skb->sk) { + } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); return -EMSGSIZE; } - if (x->props.mode == XFRM_MODE_TUNNEL && - ((skb->len > mtu && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb)))) { + if (toobig || dst_allfrag(skb_dst(skb))) return ip6_fragment(net, sk, skb, __xfrm6_output_finish); - } + +skip_frag: return x->outer_mode->afinfo->output_finish(sk, skb); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 08c9c93..2cc5840 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -177,7 +177,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) return; case IPPROTO_ICMPV6: - if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { + if (!onlyproto && (nh + offset + 2 < skb->data || + pskb_may_pull(skb, nh + offset + 2 - skb->data))) { u8 *icmp; nh = skb_network_header(skb); @@ -191,7 +192,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: offset += ipv6_optlen(exthdr); - if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { + if (!onlyproto && (nh + offset + 3 < skb->data || + pskb_may_pull(skb, nh + offset + 3 - skb->data))) { struct ip6_mh *mh; nh = skb_network_header(skb); diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index a26c401..4396459 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -1839,7 +1839,7 @@ static void *irlmp_seq_hb_idx(struct irlmp_iter_state *iter, loff_t *off) for (element = hashbin_get_first(iter->hashbin); element != NULL; element = hashbin_get_next(iter->hashbin)) { - if (!off || *off-- == 0) { + if (!off || (*off)-- == 0) { /* NB: hashbin left locked */ return element; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 83a7068..f9c9ecb 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -261,7 +261,7 @@ static int pfkey_broadcast(struct sk_buff *skb, err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); - /* Error is cleare after succecful sending to at least one + /* Error is cleared after successful sending to at least one * registered KM */ if ((broadcast_flags & BROADCAST_REGISTERED) && err) err = err2; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 09e661c..f39276d 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -152,6 +152,8 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) #endif synchronize_net(); nf_queue_nf_hook_drop(net, &entry->ops); + /* other cpu might still process nfqueue verdict that used reg */ + synchronize_net(); kfree(entry); } EXPORT_SYMBOL(nf_unregister_net_hook); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index a1fe537..5a30ce6 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -297,7 +297,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, ip_set_timeout_expired(ext_timeout(n, set)))) n = NULL; - e = kzalloc(set->dsize, GFP_KERNEL); + e = kzalloc(set->dsize, GFP_ATOMIC); if (!e) return -ENOMEM; e->id = d->id; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0a49a8c..fafe33b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2371,7 +2371,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, int pos, idx, shift; err = 0; - netlink_table_grab(); + netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; @@ -2386,7 +2386,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, } if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) err = -EFAULT; - netlink_table_ungrab(); + netlink_unlock_table(); break; } case NETLINK_CAP_ACK: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index c608723..221fa8b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -769,7 +769,6 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; @@ -797,11 +796,9 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, if (vport) { int err; - upcall.egress_tun_info = &info; - err = ovs_vport_get_egress_tun_info(vport, skb, - &upcall); - if (err) - upcall.egress_tun_info = NULL; + err = dev_fill_metadata_dst(vport->dev, skb); + if (!err) + upcall.egress_tun_info = skb_tunnel_info(skb); } break; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 9ed833e..bd165ee 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -151,6 +151,8 @@ static void ovs_ct_update_key(const struct sk_buff *skb, ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); + if (!nf_ct_is_confirmed(ct)) + state |= OVS_CS_F_NEW; if (ct->master) state |= OVS_CS_F_RELATED; zone = nf_ct_zone(ct); @@ -222,9 +224,6 @@ static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, struct nf_conn *ct; int err; - if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) - return -ENOTSUPP; - /* The connection could be invalid, in which case set_label is no-op.*/ ct = nf_ct_get(skb, &ctinfo); if (!ct) @@ -377,7 +376,7 @@ static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb, return true; } -static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, +static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { @@ -408,6 +407,8 @@ static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, } } + ovs_ct_update_key(skb, key, true); + return 0; } @@ -430,8 +431,6 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, err = __ovs_ct_lookup(net, key, info, skb); if (err) return err; - - ovs_ct_update_key(skb, key, true); } return 0; @@ -460,8 +459,6 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, if (nf_conntrack_confirm(skb) != NF_ACCEPT) return -EINVAL; - ovs_ct_update_key(skb, key, true); - return 0; } @@ -587,6 +584,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_MARK: { struct md_mark *mark = nla_data(a); + if (!mark->mask) { + OVS_NLERR(log, "ct_mark mask cannot be 0"); + return -EINVAL; + } info->mark = *mark; break; } @@ -595,6 +596,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_LABELS: { struct md_labels *labels = nla_data(a); + if (!labels_nonzero(&labels->mask)) { + OVS_NLERR(log, "ct_labels mask cannot be 0"); + return -EINVAL; + } info->labels = *labels; break; } @@ -705,11 +710,12 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) return -EMSGSIZE; - if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask && nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark), &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&ct_info->labels.mask) && nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), &ct_info->labels)) return -EMSGSIZE; diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index da87149..82e0dfc 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -35,12 +35,9 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); -static inline bool ovs_ct_state_supported(u32 state) -{ - return !(state & ~(OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | - OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | - OVS_CS_F_INVALID | OVS_CS_F_TRACKED)); -} +#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \ + OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \ + OVS_CS_F_INVALID | OVS_CS_F_TRACKED) #else #include <linux/errno.h> @@ -53,11 +50,6 @@ static inline bool ovs_ct_verify(struct net *net, int attr) return false; } -static inline bool ovs_ct_state_supported(u32 state) -{ - return false; -} - static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla, const struct sw_flow_key *key, struct sw_flow_actions **acts, bool log) @@ -94,5 +86,7 @@ static inline int ovs_ct_put_key(const struct sw_flow_key *key, } static inline void ovs_ct_free_action(const struct nlattr *a) { } + +#define CT_SUPPORTED_MASK 0 #endif /* CONFIG_NF_CONNTRACK */ #endif /* ovs_conntrack.h */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a758280..5633172 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -489,9 +489,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (upcall_info->egress_tun_info) { nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); - err = ovs_nla_put_egress_tunnel_key(user_skb, - upcall_info->egress_tun_info, - upcall_info->egress_tun_opts); + err = ovs_nla_put_tunnel_info(user_skb, + upcall_info->egress_tun_info); BUG_ON(err); nla_nest_end(user_skb, nla); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index f88038a..67bdecd 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -117,7 +117,6 @@ struct ovs_skb_cb { */ struct dp_upcall_info { struct ip_tunnel_info *egress_tun_info; - const void *egress_tun_opts; const struct nlattr *userdata; const struct nlattr *actions; int actions_len; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 80e1f09..907d6fd 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -764,7 +764,7 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, if ((output->tun_flags & TUNNEL_OAM) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; - if (tun_opts) { + if (swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_GENEVE_OPT && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) @@ -798,14 +798,13 @@ static int ip_tun_to_nlattr(struct sk_buff *skb, return 0; } -int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, - const struct ip_tunnel_info *egress_tun_info, - const void *egress_tun_opts) +int ovs_nla_put_tunnel_info(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) { - return __ip_tun_to_nlattr(skb, &egress_tun_info->key, - egress_tun_opts, - egress_tun_info->options_len, - ip_tunnel_info_af(egress_tun_info)); + return __ip_tun_to_nlattr(skb, &tun_info->key, + ip_tunnel_info_opts(tun_info), + tun_info->options_len, + ip_tunnel_info_af(tun_info)); } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, @@ -866,7 +865,7 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); - if (!is_mask && !ovs_ct_state_supported(ct_state)) { + if (ct_state & ~CT_SUPPORTED_MASK) { OVS_NLERR(log, "ct_state flags %08x unsupported", ct_state); return -EINVAL; @@ -1149,6 +1148,9 @@ static void nlattr_set(struct nlattr *attr, u8 val, } else { memset(nla_data(nla), val, nla_len(nla)); } + + if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) + *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; } } @@ -2432,11 +2434,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ip_tun_to_nlattr(skb, &tun_info->key, - tun_info->options_len ? - ip_tunnel_info_opts(tun_info) : NULL, - tun_info->options_len, - ip_tunnel_info_af(tun_info)); + err = ovs_nla_put_tunnel_info(skb, tun_info); if (err) return err; nla_nest_end(skb, start); diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 6ca3f0b..47dd142 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -55,9 +55,9 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_get_match(struct net *, struct sw_flow_match *, const struct nlattr *key, const struct nlattr *mask, bool log); -int ovs_nla_put_egress_tunnel_key(struct sk_buff *, - const struct ip_tunnel_info *, - const void *egress_tun_opts); + +int ovs_nla_put_tunnel_info(struct sk_buff *skb, + struct ip_tunnel_info *tun_info); bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 7a568ca..efb736b 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -52,18 +52,6 @@ static int geneve_get_options(const struct vport *vport, return 0; } -static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - struct geneve_port *geneve_port = geneve_vport(vport); - struct net *net = ovs_dp_get_net(vport->dp); - __be16 dport = htons(geneve_port->port_no); - __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); - - return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), - skb, IPPROTO_UDP, sport, dport); -} - static struct vport *geneve_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); @@ -130,7 +118,6 @@ static struct vport_ops ovs_geneve_vport_ops = { .get_options = geneve_get_options, .send = dev_queue_xmit, .owner = THIS_MODULE, - .get_egress_tun_info = geneve_get_egress_tun_info, }; static int __init ovs_geneve_tnl_init(void) diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index cdb758a..c3257d7 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -84,18 +84,10 @@ static struct vport *gre_create(const struct vport_parms *parms) return ovs_netdev_link(vport, parms->name); } -static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), - skb, IPPROTO_GRE, 0, 0); -} - static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, .send = dev_queue_xmit, - .get_egress_tun_info = gre_get_egress_tun_info, .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 7f0a8bd..ec76398 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -106,12 +106,45 @@ static void internal_dev_destructor(struct net_device *dev) free_netdev(dev); } +static struct rtnl_link_stats64 * +internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + int i; + + memset(stats, 0, sizeof(*stats)); + stats->rx_errors = dev->stats.rx_errors; + stats->tx_errors = dev->stats.tx_errors; + stats->tx_dropped = dev->stats.tx_dropped; + stats->rx_dropped = dev->stats.rx_dropped; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *percpu_stats; + struct pcpu_sw_netstats local_stats; + unsigned int start; + + percpu_stats = per_cpu_ptr(dev->tstats, i); + + do { + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); + local_stats = *percpu_stats; + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); + + stats->rx_bytes += local_stats.rx_bytes; + stats->rx_packets += local_stats.rx_packets; + stats->tx_bytes += local_stats.tx_bytes; + stats->tx_packets += local_stats.tx_packets; + } + + return stats; +} + static const struct net_device_ops internal_dev_netdev_ops = { .ndo_open = internal_dev_open, .ndo_stop = internal_dev_stop, .ndo_start_xmit = internal_dev_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = internal_dev_change_mtu, + .ndo_get_stats64 = internal_get_stats, }; static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { @@ -161,6 +194,11 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) err = -ENOMEM; goto error_free_vport; } + vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!vport->dev->tstats) { + err = -ENOMEM; + goto error_free_netdev; + } dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); internal_dev = internal_dev_priv(vport->dev); @@ -173,7 +211,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) rtnl_lock(); err = register_netdevice(vport->dev); if (err) - goto error_free_netdev; + goto error_unlock; dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); @@ -181,8 +219,10 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) return vport; -error_free_netdev: +error_unlock: rtnl_unlock(); + free_percpu(vport->dev->tstats); +error_free_netdev: free_netdev(vport->dev); error_free_vport: ovs_vport_free(vport); @@ -198,7 +238,7 @@ static void internal_dev_destroy(struct vport *vport) /* unregister_netdevice() waits for an RCU grace period. */ unregister_netdevice(vport->dev); - + free_percpu(vport->dev->tstats); rtnl_unlock(); } diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 6f70071..1605691 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -146,32 +146,12 @@ static struct vport *vxlan_create(const struct vport_parms *parms) return ovs_netdev_link(vport, parms->name); } -static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - struct vxlan_dev *vxlan = netdev_priv(vport->dev); - struct net *net = ovs_dp_get_net(vport->dp); - unsigned short family = ip_tunnel_info_af(upcall->egress_tun_info); - __be16 dst_port = vxlan_dev_dst_port(vxlan, family); - __be16 src_port; - int port_min; - int port_max; - - inet_get_local_port_range(net, &port_min, &port_max); - src_port = udp_flow_src_port(net, skb, 0, 0, true); - - return ovs_tunnel_get_egress_info(upcall, net, - skb, IPPROTO_UDP, - src_port, dst_port); -} - static struct vport_ops ovs_vxlan_netdev_vport_ops = { .type = OVS_VPORT_TYPE_VXLAN, .create = vxlan_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = vxlan_get_options, .send = dev_queue_xmit, - .get_egress_tun_info = vxlan_get_egress_tun_info, }; static int __init ovs_vxlan_tnl_init(void) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index ef19d0b..0ac0fd0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -480,64 +480,6 @@ void ovs_vport_deferred_free(struct vport *vport) } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); -int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, - struct net *net, - struct sk_buff *skb, - u8 ipproto, - __be16 tp_src, - __be16 tp_dst) -{ - struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info; - const struct ip_tunnel_info *tun_info = skb_tunnel_info(skb); - const struct ip_tunnel_key *tun_key; - u32 skb_mark = skb->mark; - struct rtable *rt; - struct flowi4 fl; - - if (unlikely(!tun_info)) - return -EINVAL; - if (ip_tunnel_info_af(tun_info) != AF_INET) - return -EINVAL; - - tun_key = &tun_info->key; - - /* Route lookup to get srouce IP address. - * The process may need to be changed if the corresponding process - * in vports ops changed. - */ - rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto); - if (IS_ERR(rt)) - return PTR_ERR(rt); - - ip_rt_put(rt); - - /* Generate egress_tun_info based on tun_info, - * saddr, tp_src and tp_dst - */ - ip_tunnel_key_init(&egress_tun_info->key, - fl.saddr, tun_key->u.ipv4.dst, - tun_key->tos, - tun_key->ttl, - tp_src, tp_dst, - tun_key->tun_id, - tun_key->tun_flags); - egress_tun_info->options_len = tun_info->options_len; - egress_tun_info->mode = tun_info->mode; - upcall->egress_tun_opts = ip_tunnel_info_opts(egress_tun_info); - return 0; -} -EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info); - -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - /* get_egress_tun_info() is only implemented on tunnel ports. */ - if (unlikely(!vport->ops->get_egress_tun_info)) - return -EINVAL; - - return vport->ops->get_egress_tun_info(vport, skb, upcall); -} - static unsigned int packet_length(const struct sk_buff *skb) { unsigned int length = skb->len - ETH_HLEN; diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 885607f..bdfd82a 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -27,7 +27,6 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> -#include <net/route.h> #include "datapath.h" @@ -53,16 +52,6 @@ int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids); int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *); u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); -int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, - struct net *net, - struct sk_buff *, - u8 ipproto, - __be16 tp_src, - __be16 tp_dst); - -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall); - /** * struct vport_portids - array of netlink portids of a vport. * must be protected by rcu. @@ -140,8 +129,6 @@ struct vport_parms { * have any configuration. * @send: Send a packet on the device. * zero for dropped packets or negative for error. - * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for - * a packet. */ struct vport_ops { enum ovs_vport_type type; @@ -154,9 +141,6 @@ struct vport_ops { int (*get_options)(const struct vport *, struct sk_buff *); netdev_tx_t (*send) (struct sk_buff *skb); - int (*get_egress_tun_info)(struct vport *, struct sk_buff *, - struct dp_upcall_info *upcall); - struct module *owner; struct list_head list; }; diff --git a/net/sysctl_net.c b/net/sysctl_net.c index e7000be..ed98c1f 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -94,10 +94,14 @@ __init int net_sysctl_init(void) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) - goto out; + goto out1; register_sysctl_root(&net_sysctl_root); out: return ret; +out1: + unregister_sysctl_table(net_header); + net_header = NULL; + goto out; } struct ctl_table_header *register_net_sysctl(struct net *net, diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 41042de..eadba62 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -42,7 +42,8 @@ #include "core.h" #define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ -#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ +#define BCLINK_WIN_DEFAULT 50 /* bcast link window size (default) */ +#define BCLINK_WIN_MIN 32 /* bcast minimum link window size */ const char tipc_bclink_name[] = "broadcast-link"; @@ -908,9 +909,10 @@ int tipc_bclink_set_queue_limits(struct net *net, u32 limit) if (!bcl) return -ENOPROTOOPT; - if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN)) + if (limit < BCLINK_WIN_MIN) + limit = BCLINK_WIN_MIN; + if (limit > TIPC_MAX_LINK_WIN) return -EINVAL; - tipc_bclink_lock(net); tipc_link_set_queue_limits(bcl, limit); tipc_bclink_unlock(net); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 454f5ec..26d38b3 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -121,7 +121,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) { struct sk_buff *head = *headbuf; struct sk_buff *frag = *buf; - struct sk_buff *tail; + struct sk_buff *tail = NULL; struct tipc_msg *msg; u32 fragid; int delta; @@ -141,9 +141,15 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(skb_unclone(frag, GFP_ATOMIC))) goto err; head = *headbuf = frag; - skb_frag_list_init(head); - TIPC_SKB_CB(head)->tail = NULL; *buf = NULL; + TIPC_SKB_CB(head)->tail = NULL; + if (skb_is_nonlinear(head)) { + skb_walk_frags(head, tail) { + TIPC_SKB_CB(head)->tail = tail; + } + } else { + skb_frag_list_init(head); + } return 0; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 9bc0b1e..0021c01 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -52,6 +52,8 @@ /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 +#define UDP_MIN_HEADROOM 28 + static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, [TIPC_NLA_UDP_LOCAL] = {.type = NLA_BINARY, @@ -156,6 +158,9 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, struct sk_buff *clone; struct rtable *rt; + if (skb_headroom(skb) < UDP_MIN_HEADROOM) + pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); + clone = skb_clone(skb, GFP_ATOMIC); skb_set_inner_protocol(clone, htons(ETH_P_TIPC)); ub = rcu_dereference_rtnl(b->media_ptr); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index df5fc6b..00e8a34 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1948,13 +1948,13 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) err = misc_register(&vsock_device); if (err) { pr_err("Failed to register misc device\n"); - return -ENOENT; + goto err_reset_transport; } err = proto_register(&vsock_proto, 1); /* we want our slab */ if (err) { pr_err("Cannot register vsock protocol\n"); - goto err_misc_deregister; + goto err_deregister_misc; } err = sock_register(&vsock_family_ops); @@ -1969,8 +1969,9 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) err_unregister_proto: proto_unregister(&vsock_proto); -err_misc_deregister: +err_deregister_misc: misc_deregister(&vsock_device); +err_reset_transport: transport = NULL; err_busy: mutex_unlock(&vsock_register_mutex); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1f63daf..7555cad 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -40,13 +40,11 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg); static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg); -static void vmci_transport_peer_attach_cb(u32 sub_id, - const struct vmci_event_data *ed, - void *client_data); static void vmci_transport_peer_detach_cb(u32 sub_id, const struct vmci_event_data *ed, void *client_data); static void vmci_transport_recv_pkt_work(struct work_struct *work); +static void vmci_transport_cleanup(struct work_struct *work); static int vmci_transport_recv_listen(struct sock *sk, struct vmci_transport_packet *pkt); static int vmci_transport_recv_connecting_server( @@ -75,6 +73,10 @@ struct vmci_transport_recv_pkt_info { struct vmci_transport_packet pkt; }; +static LIST_HEAD(vmci_transport_cleanup_list); +static DEFINE_SPINLOCK(vmci_transport_cleanup_lock); +static DECLARE_WORK(vmci_transport_cleanup_work, vmci_transport_cleanup); + static struct vmci_handle vmci_transport_stream_handle = { VMCI_INVALID_ID, VMCI_INVALID_ID }; static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; @@ -791,44 +793,6 @@ out: return err; } -static void vmci_transport_peer_attach_cb(u32 sub_id, - const struct vmci_event_data *e_data, - void *client_data) -{ - struct sock *sk = client_data; - const struct vmci_event_payload_qp *e_payload; - struct vsock_sock *vsk; - - e_payload = vmci_event_data_const_payload(e_data); - - vsk = vsock_sk(sk); - - /* We don't ask for delayed CBs when we subscribe to this event (we - * pass 0 as flags to vmci_event_subscribe()). VMCI makes no - * guarantees in that case about what context we might be running in, - * so it could be BH or process, blockable or non-blockable. So we - * need to account for all possible contexts here. - */ - local_bh_disable(); - bh_lock_sock(sk); - - /* XXX This is lame, we should provide a way to lookup sockets by - * qp_handle. - */ - if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, - e_payload->handle)) { - /* XXX This doesn't do anything, but in the future we may want - * to set a flag here to verify the attach really did occur and - * we weren't just sent a datagram claiming it was. - */ - goto out; - } - -out: - bh_unlock_sock(sk); - local_bh_enable(); -} - static void vmci_transport_handle_detach(struct sock *sk) { struct vsock_sock *vsk; @@ -871,28 +835,38 @@ static void vmci_transport_peer_detach_cb(u32 sub_id, const struct vmci_event_data *e_data, void *client_data) { - struct sock *sk = client_data; + struct vmci_transport *trans = client_data; const struct vmci_event_payload_qp *e_payload; - struct vsock_sock *vsk; e_payload = vmci_event_data_const_payload(e_data); - vsk = vsock_sk(sk); - if (vmci_handle_is_invalid(e_payload->handle)) - return; - - /* Same rules for locking as for peer_attach_cb(). */ - local_bh_disable(); - bh_lock_sock(sk); /* XXX This is lame, we should provide a way to lookup sockets by * qp_handle. */ - if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, - e_payload->handle)) - vmci_transport_handle_detach(sk); + if (vmci_handle_is_invalid(e_payload->handle) || + vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) + return; - bh_unlock_sock(sk); - local_bh_enable(); + /* We don't ask for delayed CBs when we subscribe to this event (we + * pass 0 as flags to vmci_event_subscribe()). VMCI makes no + * guarantees in that case about what context we might be running in, + * so it could be BH or process, blockable or non-blockable. So we + * need to account for all possible contexts here. + */ + spin_lock_bh(&trans->lock); + if (!trans->sk) + goto out; + + /* Apart from here, trans->lock is only grabbed as part of sk destruct, + * where trans->sk isn't locked. + */ + bh_lock_sock(trans->sk); + + vmci_transport_handle_detach(trans->sk); + + bh_unlock_sock(trans->sk); + out: + spin_unlock_bh(&trans->lock); } static void vmci_transport_qp_resumed_cb(u32 sub_id, @@ -1181,7 +1155,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, */ err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, vmci_transport_peer_detach_cb, - pending, &detach_sub_id); + vmci_trans(vpending), &detach_sub_id); if (err < VMCI_SUCCESS) { vmci_transport_send_reset(pending, pkt); err = vmci_transport_error_to_vsock_error(err); @@ -1321,7 +1295,6 @@ vmci_transport_recv_connecting_client(struct sock *sk, || vmci_trans(vsk)->qpair || vmci_trans(vsk)->produce_size != 0 || vmci_trans(vsk)->consume_size != 0 - || vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID || vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { skerr = EPROTO; err = -EINVAL; @@ -1389,7 +1362,6 @@ static int vmci_transport_recv_connecting_client_negotiate( struct vsock_sock *vsk; struct vmci_handle handle; struct vmci_qp *qpair; - u32 attach_sub_id; u32 detach_sub_id; bool is_local; u32 flags; @@ -1399,7 +1371,6 @@ static int vmci_transport_recv_connecting_client_negotiate( vsk = vsock_sk(sk); handle = VMCI_INVALID_HANDLE; - attach_sub_id = VMCI_INVALID_ID; detach_sub_id = VMCI_INVALID_ID; /* If we have gotten here then we should be past the point where old @@ -1444,23 +1415,15 @@ static int vmci_transport_recv_connecting_client_negotiate( goto destroy; } - /* Subscribe to attach and detach events first. + /* Subscribe to detach events first. * * XXX We attach once for each queue pair created for now so it is easy * to find the socket (it's provided), but later we should only * subscribe once and add a way to lookup sockets by queue pair handle. */ - err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_ATTACH, - vmci_transport_peer_attach_cb, - sk, &attach_sub_id); - if (err < VMCI_SUCCESS) { - err = vmci_transport_error_to_vsock_error(err); - goto destroy; - } - err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, vmci_transport_peer_detach_cb, - sk, &detach_sub_id); + vmci_trans(vsk), &detach_sub_id); if (err < VMCI_SUCCESS) { err = vmci_transport_error_to_vsock_error(err); goto destroy; @@ -1496,7 +1459,6 @@ static int vmci_transport_recv_connecting_client_negotiate( vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = pkt->u.size; - vmci_trans(vsk)->attach_sub_id = attach_sub_id; vmci_trans(vsk)->detach_sub_id = detach_sub_id; vmci_trans(vsk)->notify_ops->process_negotiate(sk); @@ -1504,9 +1466,6 @@ static int vmci_transport_recv_connecting_client_negotiate( return 0; destroy: - if (attach_sub_id != VMCI_INVALID_ID) - vmci_event_unsubscribe(attach_sub_id); - if (detach_sub_id != VMCI_INVALID_ID) vmci_event_unsubscribe(detach_sub_id); @@ -1607,9 +1566,11 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; vmci_trans(vsk)->qpair = NULL; vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = 0; - vmci_trans(vsk)->attach_sub_id = vmci_trans(vsk)->detach_sub_id = - VMCI_INVALID_ID; + vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; vmci_trans(vsk)->notify_ops = NULL; + INIT_LIST_HEAD(&vmci_trans(vsk)->elem); + vmci_trans(vsk)->sk = &vsk->sk; + spin_lock_init(&vmci_trans(vsk)->lock); if (psk) { vmci_trans(vsk)->queue_pair_size = vmci_trans(psk)->queue_pair_size; @@ -1629,29 +1590,57 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, return 0; } -static void vmci_transport_destruct(struct vsock_sock *vsk) +static void vmci_transport_free_resources(struct list_head *transport_list) { - if (vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID) { - vmci_event_unsubscribe(vmci_trans(vsk)->attach_sub_id); - vmci_trans(vsk)->attach_sub_id = VMCI_INVALID_ID; - } + while (!list_empty(transport_list)) { + struct vmci_transport *transport = + list_first_entry(transport_list, struct vmci_transport, + elem); + list_del(&transport->elem); - if (vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { - vmci_event_unsubscribe(vmci_trans(vsk)->detach_sub_id); - vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; - } + if (transport->detach_sub_id != VMCI_INVALID_ID) { + vmci_event_unsubscribe(transport->detach_sub_id); + transport->detach_sub_id = VMCI_INVALID_ID; + } - if (!vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle)) { - vmci_qpair_detach(&vmci_trans(vsk)->qpair); - vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; - vmci_trans(vsk)->produce_size = 0; - vmci_trans(vsk)->consume_size = 0; + if (!vmci_handle_is_invalid(transport->qp_handle)) { + vmci_qpair_detach(&transport->qpair); + transport->qp_handle = VMCI_INVALID_HANDLE; + transport->produce_size = 0; + transport->consume_size = 0; + } + + kfree(transport); } +} + +static void vmci_transport_cleanup(struct work_struct *work) +{ + LIST_HEAD(pending); + + spin_lock_bh(&vmci_transport_cleanup_lock); + list_replace_init(&vmci_transport_cleanup_list, &pending); + spin_unlock_bh(&vmci_transport_cleanup_lock); + vmci_transport_free_resources(&pending); +} + +static void vmci_transport_destruct(struct vsock_sock *vsk) +{ + /* Ensure that the detach callback doesn't use the sk/vsk + * we are about to destruct. + */ + spin_lock_bh(&vmci_trans(vsk)->lock); + vmci_trans(vsk)->sk = NULL; + spin_unlock_bh(&vmci_trans(vsk)->lock); if (vmci_trans(vsk)->notify_ops) vmci_trans(vsk)->notify_ops->socket_destruct(vsk); - kfree(vsk->trans); + spin_lock_bh(&vmci_transport_cleanup_lock); + list_add(&vmci_trans(vsk)->elem, &vmci_transport_cleanup_list); + spin_unlock_bh(&vmci_transport_cleanup_lock); + schedule_work(&vmci_transport_cleanup_work); + vsk->trans = NULL; } @@ -2146,6 +2135,9 @@ module_init(vmci_transport_init); static void __exit vmci_transport_exit(void) { + cancel_work_sync(&vmci_transport_cleanup_work); + vmci_transport_free_resources(&vmci_transport_cleanup_list); + if (!vmci_handle_is_invalid(vmci_transport_stream_handle)) { if (vmci_datagram_destroy_handle( vmci_transport_stream_handle) != VMCI_SUCCESS) @@ -2164,6 +2156,7 @@ module_exit(vmci_transport_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); +MODULE_VERSION("1.0.2.0-k"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("vmware_vsock"); MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h index ce6c962..2ad46f3 100644 --- a/net/vmw_vsock/vmci_transport.h +++ b/net/vmw_vsock/vmci_transport.h @@ -119,10 +119,12 @@ struct vmci_transport { u64 queue_pair_size; u64 queue_pair_min_size; u64 queue_pair_max_size; - u32 attach_sub_id; u32 detach_sub_id; union vmci_transport_notify notify; struct vmci_transport_notify_ops *notify_ops; + struct list_head elem; + struct sock *sk; + spinlock_t lock; /* protects sk. */ }; int vmci_transport_register(void); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a8de9e3..24e06a2 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1928,8 +1928,10 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr *rp = attrs[XFRMA_REPLAY_VAL]; struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL]; struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; + struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; + struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; - if (!lt && !rp && !re) + if (!lt && !rp && !re && !et && !rt) return err; /* pedantic mode - thou shalt sayeth replaceth */ |
