diff options
Diffstat (limited to 'net')
39 files changed, 292 insertions, 182 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c index c12c258..127fe70 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/caif/caif_socket.c b/net/caif/caif_socket.c index a986280..a97d97a 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -539,8 +539,10 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk, pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb); memset(skb->cb, 0, sizeof(struct caif_payload_info)); - if (cf_sk->layer.dn == NULL) + if (cf_sk->layer.dn == NULL) { + kfree_skb(skb); return -EINVAL; + } return cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt); } @@ -683,10 +685,10 @@ static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, } err = transmit_skb(skb, cf_sk, msg->msg_flags&MSG_DONTWAIT, timeo); - if (err < 0) { - kfree_skb(skb); + if (err < 0) + /* skb is already freed */ goto pipe_err; - } + sent += size; } diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index b36f24a..94b0861 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -248,7 +248,6 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, { struct cfmuxl *muxl = container_obj(layr); struct cflayer *layer; - int idx; rcu_read_lock(); list_for_each_entry_rcu(layer, &muxl->srvl_list, node) { @@ -257,14 +256,9 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && - layer->id != 0) { - - idx = layer->id % UP_CACHE_SIZE; - spin_lock_bh(&muxl->receive_lock); - RCU_INIT_POINTER(muxl->up_cache[idx], NULL); - list_del_rcu(&layer->node); - spin_unlock_bh(&muxl->receive_lock); - } + layer->id != 0) + cfmuxl_remove_uplayer(layr, layer->id); + /* NOTE: ctrlcmd is not allowed to block */ layer->ctrlcmd(layer, ctrl, phyid); } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 97f70e5..761ad9d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -85,8 +85,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) } else { pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid); memcpy(&client->fsid, fsid, sizeof(*fsid)); - ceph_debugfs_client_init(client); - client->have_fsid = true; } return 0; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 0b62dea..1845cde 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -8,8 +8,8 @@ #include <linux/ceph/mon_client.h> #include <linux/ceph/libceph.h> +#include <linux/ceph/debugfs.h> #include <linux/ceph/decode.h> - #include <linux/ceph/auth.h> /* @@ -340,8 +340,19 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, client->monc.monmap = monmap; kfree(old); + if (!client->have_fsid) { + client->have_fsid = true; + mutex_unlock(&monc->mutex); + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(client); + goto out_unlocked; + } out: mutex_unlock(&monc->mutex); +out_unlocked: wake_up_all(&client->auth_wq); } diff --git a/net/core/dev.c b/net/core/dev.c index 115dee1..6ca32f6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3500,14 +3500,20 @@ static inline gro_result_t __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; for (p = napi->gro_list; p; p = p->next) { unsigned long diffs; diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; - diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_gro_mac_header(skb), + maclen); NAPI_GRO_CB(p)->same_flow = !diffs; NAPI_GRO_CB(p)->flush = 0; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 369b418..3f79db1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1190,6 +1190,8 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, if (!dev->ethtool_ops->flash_device) return -EOPNOTSUPP; + efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; + return dev->ethtool_ops->flash_device(dev, &efl); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e287346..2a83914 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/netpoll.c b/net/core/netpoll.c index 556b082..ddefc51 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -194,7 +194,7 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); - if (dev->priv_flags & IFF_SLAVE) { + if (dev->flags & IFF_SLAVE) { if (dev->npinfo) { struct net_device *bond_dev = dev->master; struct sk_buff *skb; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 3a9fd48..4dacc44 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -58,11 +58,12 @@ static int get_prioidx(u32 *prio) spin_lock_irqsave(&prioidx_map_lock, flags); prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) { + spin_unlock_irqrestore(&prioidx_map_lock, flags); + return -ENOSPC; + } set_bit(prioidx, prioidx_map); spin_unlock_irqrestore(&prioidx_map_lock, flags); - if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) - return -ENOSPC; - atomic_set(&max_prioidx, prioidx); *prio = prioidx; return 0; @@ -107,7 +108,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) static void update_netdev_tables(void) { struct net_device *dev; - u32 max_len = atomic_read(&max_prioidx); + u32 max_len = atomic_read(&max_prioidx) + 1; struct netprio_map *map; rtnl_lock(); @@ -270,7 +271,6 @@ static int netprio_device_event(struct notifier_block *unused, { struct net_device *dev = ptr; struct netprio_map *old; - u32 max_len = atomic_read(&max_prioidx); /* * Note this is called with rtnl_lock held so we have update side @@ -278,11 +278,6 @@ static int netprio_device_event(struct notifier_block *unused, */ switch (event) { - - case NETDEV_REGISTER: - if (max_len) - extend_netdev_table(dev, max_len); - break; case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 65aebd4..606a6e8 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/core/sock.c b/net/core/sock.c index 3e81fd2..02f8dfe 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1171,13 +1171,10 @@ EXPORT_SYMBOL(sock_update_classid); void sock_update_netprioidx(struct sock *sk) { - struct cgroup_netprio_state *state; if (in_interrupt()) return; - rcu_read_lock(); - state = task_netprio_state(current); - sk->sk_cgrp_prioidx = state ? state->prioidx : 0; - rcu_read_unlock(); + + sk->sk_cgrp_prioidx = task_netprioidx(current); } EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index aa2a2c7..d183262 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -409,7 +409,7 @@ config INET_TCP_DIAG config INET_UDP_DIAG tristate "UDP: socket monitoring interface" - depends on INET_DIAG + depends on INET_DIAG && (IPV6 || IPV6=n) default n ---help--- Support for UDP socket monitoring interface used by the ss tool. diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 59402be..63e4989 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -863,7 +863,8 @@ static int arp_process(struct sk_buff *skb) if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || - pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { + (rt->dst.dev != dev && + pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6b3ca5b..38673d2 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/ip_options.c b/net/ipv4/ip_options.c index 1e60f76..42dd1a9 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -573,8 +573,8 @@ void ip_forward_options(struct sk_buff *skb) } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; - ip_rt_get_source(&optptr[srrptr-1], skb, rt); ip_hdr(skb)->daddr = opt->nexthop; + ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aea5a19..b072386 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -630,6 +630,7 @@ 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/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4cb9cd2..7a7724d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -778,7 +778,6 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; - unsigned long limit; table = ipv4_net_table; if (!net_eq(net, &init_net)) { @@ -815,11 +814,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_rt_cache_rebuild_count = 4; tcp_init_mem(net); - limit = nr_free_buffer_pages() / 8; - limit = max(limit, 128UL); - net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; - net->ipv4.sysctl_tcp_mem[1] = limit; - net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; net->ipv4.ipv4_hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 06373b4..22ef5f9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1876,6 +1876,20 @@ void tcp_shutdown(struct sock *sk, int how) } EXPORT_SYMBOL(tcp_shutdown); +bool tcp_check_oom(struct sock *sk, int shift) +{ + bool too_many_orphans, out_of_socket_memory; + + too_many_orphans = tcp_too_many_orphans(sk, shift); + out_of_socket_memory = tcp_out_of_memory(sk); + + if (too_many_orphans && net_ratelimit()) + pr_info("TCP: too many orphaned sockets\n"); + if (out_of_socket_memory && net_ratelimit()) + pr_info("TCP: out of memory -- consider tuning tcp_mem\n"); + return too_many_orphans || out_of_socket_memory; +} + void tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; @@ -2015,10 +2029,7 @@ adjudge_to_death: } if (sk->sk_state != TCP_CLOSE) { sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, 0)) { - if (net_ratelimit()) - printk(KERN_INFO "TCP: too many of orphaned " - "sockets\n"); + if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); NET_INC_STATS_BH(sock_net(sk), @@ -3218,7 +3229,6 @@ __setup("thash_entries=", set_thash_entries); void tcp_init_mem(struct net *net) { - /* Set per-socket limits to no more than 1/128 the pressure threshold */ unsigned long limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; @@ -3230,7 +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)); @@ -3273,7 +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); @@ -3287,7 +3298,8 @@ void __init tcp_init(void) sysctl_max_syn_backlog = max(128, cnt / 256); tcp_init_mem(&init_net); - limit = nr_free_buffer_pages() / 8; + /* Set per-socket limits to no more than 1/128 the pressure threshold */ + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); limit = max(limit, 128UL); max_share = min(4UL*1024*1024, limit); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 976034f..53c8ce40 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1307,25 +1307,26 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, return in_sack; } -static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, - struct tcp_sacktag_state *state, +/* Mark the given newly-SACKed range as such, adjusting counters and hints. */ +static u8 tcp_sacktag_one(struct sock *sk, + struct tcp_sacktag_state *state, u8 sacked, + u32 start_seq, u32 end_seq, int dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); - u8 sacked = TCP_SKB_CB(skb)->sacked; int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans && - after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) + after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) + if (!after(end_seq, tp->snd_una)) return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { @@ -1344,13 +1345,13 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, /* New sack for not retransmitted frame, * which was in hole. It is reordering. */ - if (before(TCP_SKB_CB(skb)->seq, + if (before(start_seq, tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); /* SACK enhanced F-RTO (RFC4138; Appendix B) */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) + if (!after(end_seq, tp->frto_highmark)) state->flag |= FLAG_ONLY_ORIG_SACKED; } @@ -1368,8 +1369,7 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->lost_skb_hint)->seq)) + before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; if (fack_count > tp->fackets_out) @@ -1388,6 +1388,9 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, return sacked; } +/* Shift newly-SACKed bytes from this skb to the immediately previous + * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. + */ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, @@ -1395,10 +1398,13 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); + u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ + u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ BUG_ON(!pcount); - if (skb == tp->lost_skb_hint) + /* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */ + if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint)) tp->lost_cnt_hint += pcount; TCP_SKB_CB(prev)->end_seq += shifted; @@ -1424,8 +1430,11 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_type = 0; } - /* We discard results */ - tcp_sacktag_one(skb, sk, state, dup_sack, pcount); + /* Adjust counters and hints for the newly sacked sequence range but + * discard the return value since prev is already marked. + */ + tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, + start_seq, end_seq, dup_sack, pcount); /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); @@ -1664,10 +1673,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, break; if (in_sack) { - TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk, - state, - dup_sack, - tcp_skb_pcount(skb)); + TCP_SKB_CB(skb)->sacked = + tcp_sacktag_one(sk, + state, + TCP_SKB_CB(skb)->sacked, + TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + dup_sack, + tcp_skb_pcount(skb)); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 337ba4c..94d683a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -651,6 +651,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. + * routing might fail in this case. using iif for oif to + * make sure we can deliver it + */ + arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb); net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a516d1e..cd2e072 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -77,10 +77,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset) if (sk->sk_err_soft) shift++; - if (tcp_too_many_orphans(sk, shift)) { - if (net_ratelimit()) - printk(KERN_INFO "Out of socket memory\n"); - + if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || 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 d8f02ef..c964958 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1545,9 +1545,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, &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 9307b03..30c9d4c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1367,15 +1367,12 @@ 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), @@ -1468,8 +1465,10 @@ 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; @@ -1490,6 +1489,7 @@ 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; @@ -1510,27 +1510,22 @@ 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 @@ -1545,23 +1540,19 @@ 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) | @@ -1570,15 +1561,10 @@ 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/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 4cba13e..ae3a035 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -232,7 +232,7 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, if (toklen <= (n_parts + 1) * 4) return -EINVAL; - princ->name_parts = kcalloc(sizeof(char *), n_parts, GFP_KERNEL); + princ->name_parts = kcalloc(n_parts, sizeof(char *), GFP_KERNEL); if (!princ->name_parts) return -ENOMEM; @@ -355,7 +355,7 @@ static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, _debug("n_elem %d", n_elem); - td = kcalloc(sizeof(struct krb5_tagged_data), n_elem, + td = kcalloc(n_elem, sizeof(struct krb5_tagged_data), GFP_KERNEL); if (!td) return -ENOMEM; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index e465064..7e267d7 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -148,8 +148,7 @@ struct choke_skb_cb { static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct choke_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb)); return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 2776012..5da548f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -130,8 +130,7 @@ struct netem_skb_cb { static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct netem_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct netem_skb_cb)); return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data; } @@ -502,9 +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 /* @@ -540,7 +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) diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 96e42ca..d7eea99 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -94,8 +94,7 @@ struct sfb_skb_cb { static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct sfb_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct sfb_skb_cb)); return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 67494ae..60d4718 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -166,9 +166,8 @@ struct sfq_skb_cb { static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct sfq_skb_cb)); - return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; + qdisc_cb_private_validate(skb, sizeof(struct sfq_skb_cb)); + return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; } static unsigned int sfq_hash(const struct sfq_sched_data *q, diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 1426ec3..75762f3 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -92,6 +92,7 @@ generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) if (gcred->acred.group_info != NULL) get_group_info(gcred->acred.group_info); gcred->acred.machine_cred = acred->machine_cred; + gcred->acred.principal = acred->principal; dprintk("RPC: allocated %s cred %p for uid %d gid %d\n", gcred->acred.machine_cred ? "machine" : "generic", @@ -123,6 +124,17 @@ generic_destroy_cred(struct rpc_cred *cred) call_rcu(&cred->cr_rcu, generic_free_cred_callback); } +static int +machine_cred_match(struct auth_cred *acred, struct generic_cred *gcred, int flags) +{ + if (!gcred->acred.machine_cred || + gcred->acred.principal != acred->principal || + gcred->acred.uid != acred->uid || + gcred->acred.gid != acred->gid) + return 0; + return 1; +} + /* * Match credentials against current process creds. */ @@ -132,9 +144,12 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base); int i; + if (acred->machine_cred) + return machine_cred_match(acred, gcred, flags); + if (gcred->acred.uid != acred->uid || gcred->acred.gid != acred->gid || - gcred->acred.machine_cred != acred->machine_cred) + gcred->acred.machine_cred != 0) goto out_nomatch; /* Optimisation in the case where pointers are identical... */ |