diff options
author | David S. Miller <davem@davemloft.net> | 2012-02-27 02:55:51 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2012-02-27 02:55:51 (GMT) |
commit | ff4783ce78c08d2990126ce1874250ae8e72bbd2 (patch) | |
tree | 5c95885a4ab768101dd72942b57c238d452a7565 /net | |
parent | 622121719934f60378279eb440d3cec2fc3176d2 (diff) | |
parent | 203738e548cefc3fc3c2f73a9063176c9f3583d5 (diff) | |
download | linux-ff4783ce78c08d2990126ce1874250ae8e72bbd2.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
drivers/net/ethernet/sfc/rx.c
Overlapping changes in drivers/net/ethernet/sfc/rx.c, one to change
the rx_buf->is_page boolean into a set of u16 flags, and another to
adjust how ->ip_summed is initialized.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/atm/clip.c | 10 | ||||
-rw-r--r-- | net/core/neighbour.c | 2 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 78 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 10 | ||||
-rw-r--r-- | net/ipv4/ping.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 5 | ||||
-rw-r--r-- | net/ipv4/xfrm4_mode_beet.c | 5 | ||||
-rw-r--r-- | net/ipv4/xfrm4_mode_tunnel.c | 6 | ||||
-rw-r--r-- | net/ipv6/ip6mr.c | 4 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 5 | ||||
-rw-r--r-- | net/ipv6/xfrm6_mode_beet.c | 6 | ||||
-rw-r--r-- | net/ipv6/xfrm6_mode_tunnel.c | 6 | ||||
-rw-r--r-- | net/netfilter/ipvs/ip_vs_core.c | 2 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 38 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_netlink.c | 46 | ||||
-rw-r--r-- | net/netfilter/nf_queue.c | 40 | ||||
-rw-r--r-- | net/netfilter/xt_TEE.c | 5 | ||||
-rw-r--r-- | net/sched/sch_netem.c | 6 |
18 files changed, 174 insertions, 101 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c index ef95a30..5de42ea 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -46,8 +46,8 @@ static struct net_device *clip_devs; static struct atm_vcc *atmarpd; -static struct neigh_table clip_tbl; static struct timer_list idle_timer; +static const struct neigh_ops clip_neigh_ops; static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) { @@ -123,6 +123,8 @@ static int neigh_check_cb(struct neighbour *n) struct atmarp_entry *entry = neighbour_priv(n); struct clip_vcc *cv; + if (n->ops != &clip_neigh_ops) + return 0; for (cv = entry->vccs; cv; cv = cv->next) { unsigned long exp = cv->last_use + cv->idle_timeout; @@ -154,10 +156,10 @@ static int neigh_check_cb(struct neighbour *n) static void idle_timer_check(unsigned long dummy) { - write_lock(&clip_tbl.lock); - __neigh_for_each_release(&clip_tbl, neigh_check_cb); + write_lock(&arp_tbl.lock); + __neigh_for_each_release(&arp_tbl, neigh_check_cb); mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - write_unlock(&clip_tbl.lock); + write_unlock(&arp_tbl.lock); } static int clip_arp_rcv(struct sk_buff *skb) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f98ec44..0a68045 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -826,6 +826,8 @@ next_elt: write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); } /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7aef62e..5cf39cd 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -60,7 +60,6 @@ struct rtnl_link { }; static DEFINE_MUTEX(rtnl_mutex); -static u16 min_ifinfo_dump_size; void rtnl_lock(void) { @@ -724,10 +723,11 @@ static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) } /* All VF info */ -static inline int rtnl_vfinfo_size(const struct net_device *dev) +static inline int rtnl_vfinfo_size(const struct net_device *dev, + u32 ext_filter_mask) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent)) { - + if (dev->dev.parent && dev_is_pci(dev->dev.parent) && + (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); size_t size = nla_total_size(sizeof(struct nlattr)); size += nla_total_size(num_vfs * sizeof(struct nlattr)); @@ -766,7 +766,8 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } -static noinline size_t if_nlmsg_size(const struct net_device *dev) +static noinline size_t if_nlmsg_size(const struct net_device *dev, + u32 ext_filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -784,8 +785,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ - + nla_total_size(4) /* IFLA_NUM_VF */ - + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + + nla_total_size(ext_filter_mask + & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ @@ -868,7 +870,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags) + unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -941,10 +943,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); - if (dev->dev.parent) + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent + && (ext_filter_mask & RTEXT_FILTER_VF)) { int i; struct nlattr *vfinfo, *vf; @@ -1048,6 +1051,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct hlist_head *head; struct hlist_node *node; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1055,6 +1060,12 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; + nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + ifla_policy); + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -1064,7 +1075,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + NLM_F_MULTI, + ext_filter_mask) <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1100,6 +1112,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, [IFLA_AF_SPEC] = { .type = NLA_NESTED }, + [IFLA_EXT_MASK] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1509,8 +1522,6 @@ errout: if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - min_ifinfo_dump_size = max_t(u16, if_nlmsg_size(dev), - min_ifinfo_dump_size); return err; } @@ -1842,6 +1853,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev = NULL; struct sk_buff *nskb; int err; + u32 ext_filter_mask = 0; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1850,6 +1862,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); @@ -1861,12 +1876,12 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (dev == NULL) return -ENODEV; - nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, - nlh->nlmsg_seq, 0, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -1877,8 +1892,31 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return err; } -static u16 rtnl_calcit(struct sk_buff *skb) +static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + u16 min_ifinfo_dump_size = 0; + + nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, ifla_policy); + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + + if (!ext_filter_mask) + return NLMSG_GOODSIZE; + /* + * traverse the list of net devices and compute the minimum + * buffer size based upon the filter mask. + */ + list_for_each_entry(dev, &net->dev_base_head, dev_list) { + min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, + if_nlmsg_size(dev, + ext_filter_mask)); + } + return min_ifinfo_dump_size; } @@ -1913,13 +1951,11 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) int err = -ENOBUFS; size_t if_info_size; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL); if (skb == NULL) goto errout; - min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size); - - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1977,7 +2013,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; calcit = rtnl_get_calcit(family, type); if (calcit) - min_dump_alloc = calcit(skb); + min_dump_alloc = calcit(skb, nlh); __rtnl_unlock(); rtnl = net->rtnl; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b59414a..6ef66af 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -65,7 +65,7 @@ it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good - solution, but it supposes maintaing new variable in ALL + solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu @@ -91,14 +91,14 @@ One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, - taking into account fragmentation. TO be short, tt is not solution at all. + taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu - fastly degrades to value <68, where looping stops. + rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made @@ -457,8 +457,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info) GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, - what the hell these idiots break standrads established - by themself??? + what the hell these idiots break standards established + by themselves??? */ const struct iphdr *iph = (const struct iphdr *)skb->data; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index cfc82cf..4398a45 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -631,6 +631,7 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); + err = -EOPNOTSUPP; if (flags & MSG_OOB) goto out; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 37755cc..22ef5f9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3240,7 +3240,8 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long limit; - int i, max_share, cnt; + int max_share, cnt; + unsigned int i; unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -3283,7 +3284,7 @@ void __init tcp_init(void) &tcp_hashinfo.bhash_size, NULL, 64 * 1024); - tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size; + tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 6341818..e3db3f9 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); - - memmove(skb->data - skb->mac_len, skb_mac_header(skb), - skb->mac_len); - skb_set_mac_header(skb, -skb->mac_len); + skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 534972e..ed4bf11 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - const unsigned char *old_mac; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c7e95c8..5aa3981 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1926,8 +1926,10 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, }; dst = ip6_route_output(net, NULL, &fl6); - if (!dst) + if (dst->error) { + dst_release(dst); goto out_free; + } skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 8d81701..3dcdb81 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1550,9 +1550,10 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return; - + } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index a81ce94..9949a35 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -80,7 +80,6 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *ip6h; - const unsigned char *old_mac; int size = sizeof(struct ipv6hdr); int err; @@ -90,10 +89,7 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) __skb_push(skb, size); skb_reset_network_header(skb); - - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); + skb_mac_header_rebuild(skb); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 261e6e6..9f2095b 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -63,7 +63,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - const unsigned char *old_mac; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) goto out; @@ -80,10 +79,9 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 611c335..2555816 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -232,6 +232,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; + const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ @@ -267,7 +268,6 @@ ip_vs_sched_persist(struct ip_vs_service *svc, { int protocol = iph.protocol; const union nf_inet_addr *vaddr = &iph.daddr; - const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; __be16 vport = 0; if (dst_port == svc->port) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 76613f5..ed86a3b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -404,19 +404,49 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, &net->ct.hash[repl_hash]); } -void nf_conntrack_hash_insert(struct nf_conn *ct) +int +nf_conntrack_hash_check_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; u16 zone; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + spin_lock_bh(&nf_conntrack_lock); + /* See if there's one in the list already, including reverse */ + hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + + add_timer(&ct->timeout); + nf_conntrack_get(&ct->ct_general); __nf_conntrack_hash_insert(ct, hash, repl_hash); + NF_CT_STAT_INC(net, insert); + spin_unlock_bh(&nf_conntrack_lock); + + return 0; + +out: + NF_CT_STAT_INC(net, insert_failed); + spin_unlock_bh(&nf_conntrack_lock); + return -EEXIST; } -EXPORT_SYMBOL_GPL(nf_conntrack_hash_insert); +EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); /* Confirm a connection given skb; places it in hash table */ int diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 28d0312..04fb409 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1404,15 +1404,12 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); - spin_unlock_bh(&nf_conntrack_lock); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_lock); err = -EOPNOTSUPP; goto err1; } - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), @@ -1505,8 +1502,10 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, if (tstamp) tstamp->start = ktime_to_ns(ktime_get_real()); - add_timer(&ct->timeout); - nf_conntrack_hash_insert(ct); + err = nf_conntrack_hash_check_insert(ct); + if (err < 0) + goto err2; + rcu_read_unlock(); return ct; @@ -1527,6 +1526,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; u16 zone; int err; @@ -1547,27 +1547,22 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } - spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(net, zone, &otuple); + h = nf_conntrack_find_get(net, zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(net, zone, &rtuple); + h = nf_conntrack_find_get(net, zone, &rtuple); if (h == NULL) { err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - struct nf_conn *ct; enum ip_conntrack_events events; ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, &rtuple, u3); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); - goto out_unlock; - } + if (IS_ERR(ct)) + return PTR_ERR(ct); + err = 0; - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = IPCT_RELATED; else @@ -1582,23 +1577,19 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); + } return err; } /* implicit 'else' */ - /* We manipulate the conntrack inside the global conntrack table lock, - * so there's no need to increase the refcount */ err = -EEXIST; + ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); - + spin_lock_bh(&nf_conntrack_lock); err = ctnetlink_change_conntrack(ct, cda); + spin_unlock_bh(&nf_conntrack_lock); if (err == 0) { - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1607,15 +1598,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_MARK), ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); - nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); - - return err; + } } -out_unlock: - spin_unlock_bh(&nf_conntrack_lock); + nf_ct_put(ct); return err; } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index b3a7db6..ce60cf0 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -203,6 +203,27 @@ err: return status; } +#ifdef CONFIG_BRIDGE_NETFILTER +/* When called from bridge netfilter, skb->data must point to MAC header + * before calling skb_gso_segment(). Else, original MAC header is lost + * and segmented skbs will be sent to wrong destination. + */ +static void nf_bridge_adjust_skb_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_push(skb, skb->network_header - skb->mac_header); +} + +static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_pull(skb, skb->network_header - skb->mac_header); +} +#else +#define nf_bridge_adjust_skb_data(s) do {} while (0) +#define nf_bridge_adjust_segmented_data(s) do {} while (0) +#endif + int nf_queue(struct sk_buff *skb, struct list_head *elem, u_int8_t pf, unsigned int hook, @@ -212,7 +233,7 @@ int nf_queue(struct sk_buff *skb, unsigned int queuenum) { struct sk_buff *segs; - int err; + int err = -EINVAL; unsigned int queued; if (!skb_is_gso(skb)) @@ -228,23 +249,25 @@ int nf_queue(struct sk_buff *skb, break; } + nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ECANCELED to mean * 'ignore this hook'. */ if (IS_ERR(segs)) - return -EINVAL; - + goto out_err; queued = 0; err = 0; do { struct sk_buff *nskb = segs->next; segs->next = NULL; - if (err == 0) + if (err == 0) { + nf_bridge_adjust_segmented_data(segs); err = __nf_queue(segs, elem, pf, hook, indev, outdev, okfn, queuenum); + } if (err == 0) queued++; else @@ -252,11 +275,12 @@ int nf_queue(struct sk_buff *skb, segs = nskb; } while (segs); - /* also free orig skb if only some segments were queued */ - if (unlikely(err && queued)) - err = 0; - if (err == 0) + if (queued) { kfree_skb(skb); + return 0; + } + out_err: + nf_bridge_adjust_segmented_data(skb); return err; } diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3aae66f..4d50579 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,9 +152,10 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return false; - + } skb_dst_drop(skb); skb_dst_set(skb, dst); skb->dev = dst->dev; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e83d61c..5da548f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -501,9 +501,8 @@ tfifo_dequeue: /* if more time remaining? */ if (cb->time_to_send <= psched_get_time()) { - skb = qdisc_dequeue_tail(sch); - if (unlikely(!skb)) - goto qdisc_dequeue; + __skb_unlink(skb, &sch->q); + sch->qstats.backlog -= qdisc_pkt_len(skb); #ifdef CONFIG_NET_CLS_ACT /* @@ -539,7 +538,6 @@ deliver: qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send); } -qdisc_dequeue: if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) |