diff options
Diffstat (limited to 'net')
38 files changed, 520 insertions, 189 deletions
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 06abb66..53086fb 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -85,7 +85,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) goto err_out; err = br_fill_ifinfo(skb, port, current->pid, 0, event, 0); - if (err) + if (err < 0) goto err_kfree; NETLINK_CB(skb).dst_group = RTNLGRP_LINK; diff --git a/net/core/Makefile b/net/core/Makefile index e9bd246..2645ba4 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -7,7 +7,7 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o \ +obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o obj-$(CONFIG_XFRM) += flow.o diff --git a/net/core/dev.c b/net/core/dev.c index 4d2b516..d95e262 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1166,11 +1166,6 @@ int skb_checksum_help(struct sk_buff *skb, int inward) goto out_set_summed; if (unlikely(skb_shinfo(skb)->gso_size)) { - static int warned; - - WARN_ON(!warned); - warned = 1; - /* Let GSO fix up the checksum. */ goto out_set_summed; } @@ -1220,11 +1215,6 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) __skb_pull(skb, skb->mac_len); if (unlikely(skb->ip_summed != CHECKSUM_HW)) { - static int warned; - - WARN_ON(!warned); - warned = 1; - if (skb_header_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) return ERR_PTR(err); @@ -3429,12 +3419,9 @@ static void net_dma_rebalance(void) unsigned int cpu, i, n; struct dma_chan *chan; - lock_cpu_hotplug(); - if (net_dma_count == 0) { for_each_online_cpu(cpu) - rcu_assign_pointer(per_cpu(softnet_data.net_dma, cpu), NULL); - unlock_cpu_hotplug(); + rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL); return; } @@ -3447,15 +3434,13 @@ static void net_dma_rebalance(void) + (i < (num_online_cpus() % net_dma_count) ? 1 : 0)); while(n) { - per_cpu(softnet_data.net_dma, cpu) = chan; + per_cpu(softnet_data, cpu).net_dma = chan; cpu = next_cpu(cpu, cpu_online_map); n--; } i++; } rcu_read_unlock(); - - unlock_cpu_hotplug(); } /** diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7ad681f..5130d2e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -29,6 +29,7 @@ #include <net/neighbour.h> #include <net/dst.h> #include <net/sock.h> +#include <net/netevent.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> @@ -754,6 +755,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_STALE; neigh->updated = jiffies; neigh_suspect(neigh); + notify = 1; } } else if (state & NUD_DELAY) { if (time_before_eq(now, @@ -762,6 +764,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; neigh_connect(neigh); + notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { NEIGH_PRINTK2("neigh %p is probed.\n", neigh); @@ -819,6 +822,8 @@ static void neigh_timer_handler(unsigned long arg) out: write_unlock(&neigh->lock); } + if (notify) + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); #ifdef CONFIG_ARPD if (notify && neigh->parms->app_probes) @@ -926,9 +931,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, { u8 old; int err; -#ifdef CONFIG_ARPD int notify = 0; -#endif struct net_device *dev; int update_isrouter = 0; @@ -948,9 +951,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_suspect(neigh); neigh->nud_state = new; err = 0; -#ifdef CONFIG_ARPD notify = old & NUD_VALID; -#endif goto out; } @@ -1022,9 +1023,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - (neigh->parms->base_reachable_time << 1); -#ifdef CONFIG_ARPD notify = 1; -#endif } if (new == old) goto out; @@ -1056,6 +1055,9 @@ out: (neigh->flags & ~NTF_ROUTER); } write_unlock_bh(&neigh->lock); + + if (notify) + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); #ifdef CONFIG_ARPD if (notify && neigh->parms->app_probes) neigh_app_notify(neigh); diff --git a/net/core/netevent.c b/net/core/netevent.c new file mode 100644 index 0000000..35d02c3 --- /dev/null +++ b/net/core/netevent.c @@ -0,0 +1,69 @@ +/* + * Network event notifiers + * + * Authors: + * Tom Tucker <tom@opengridcomputing.com> + * Steve Wise <swise@opengridcomputing.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Fixes: + */ + +#include <linux/rtnetlink.h> +#include <linux/notifier.h> + +static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); + +/** + * register_netevent_notifier - register a netevent notifier block + * @nb: notifier + * + * Register a notifier to be called when a netevent occurs. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + */ +int register_netevent_notifier(struct notifier_block *nb) +{ + int err; + + err = atomic_notifier_chain_register(&netevent_notif_chain, nb); + return err; +} + +/** + * netevent_unregister_notifier - unregister a netevent notifier block + * @nb: notifier + * + * Unregister a notifier previously registered by + * register_neigh_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. + */ + +int unregister_netevent_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&netevent_notif_chain, nb); +} + +/** + * call_netevent_notifiers - call all netevent notifier blocks + * @val: value passed unmodified to notifier function + * @v: pointer passed unmodified to notifier function + * + * Call all neighbour notifier blocks. Parameters and return value + * are as for notifier_call_chain(). + */ + +int call_netevent_notifiers(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&netevent_notif_chain, val, v); +} + +EXPORT_SYMBOL_GPL(register_netevent_notifier); +EXPORT_SYMBOL_GPL(unregister_netevent_notifier); +EXPORT_SYMBOL_GPL(call_netevent_notifiers); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 476aa39..022d889 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -71,13 +71,6 @@ static kmem_cache_t *skbuff_head_cache __read_mostly; static kmem_cache_t *skbuff_fclone_cache __read_mostly; /* - * lockdep: lock class key used by skb_queue_head_init(): - */ -struct lock_class_key skb_queue_lock_key; - -EXPORT_SYMBOL(skb_queue_lock_key); - -/* * Keep out-of-line to prevent kernel bloat. * __builtin_return_address is not used because it is not always * reliable. @@ -256,6 +249,29 @@ nodata: goto out; } +/** + * __netdev_alloc_skb - allocate an skbuff for rx on a specific device + * @dev: network device to receive on + * @length: length to allocate + * @gfp_mask: get_free_pages mask, passed to alloc_skb + * + * Allocate a new &sk_buff and assign it a usage count of one. The + * buffer has unspecified headroom built in. Users should allocate + * the headroom they think they need without accounting for the + * built in space. The built in space is used for optimisations. + * + * %NULL is returned if there is no free memory. + */ +struct sk_buff *__netdev_alloc_skb(struct net_device *dev, + unsigned int length, gfp_t gfp_mask) +{ + struct sk_buff *skb; + + skb = alloc_skb(length + NET_SKB_PAD, gfp_mask); + if (likely(skb)) + skb_reserve(skb, NET_SKB_PAD); + return skb; +} static void skb_drop_list(struct sk_buff **listp) { @@ -846,7 +862,11 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) return err; - for (i = 0; i < nfrags; i++) { + i = 0; + if (offset >= len) + goto drop_pages; + + for (; i < nfrags; i++) { int end = offset + skb_shinfo(skb)->frags[i].size; if (end < len) { @@ -854,9 +874,9 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) continue; } - if (len > offset) - skb_shinfo(skb)->frags[i++].size = len - offset; + skb_shinfo(skb)->frags[i++].size = len - offset; +drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) @@ -864,7 +884,7 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) if (skb_shinfo(skb)->frag_list) skb_drop_fraglist(skb); - break; + goto done; } for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); @@ -879,6 +899,7 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) return -ENOMEM; nfrag->next = frag->next; + kfree_skb(frag); frag = nfrag; *fragp = frag; } @@ -897,6 +918,7 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) break; } +done: if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; @@ -2042,6 +2064,7 @@ EXPORT_SYMBOL(__kfree_skb); EXPORT_SYMBOL(kfree_skb); EXPORT_SYMBOL(__pskb_pull_tail); EXPORT_SYMBOL(__alloc_skb); +EXPORT_SYMBOL(__netdev_alloc_skb); EXPORT_SYMBOL(pskb_copy); EXPORT_SYMBOL(pskb_expand_head); EXPORT_SYMBOL(skb_checksum); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9f3d4d7..610c722 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -230,7 +230,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&np->saddr, saddr); inet->rcv_saddr = LOOPBACK4_IPV6; - ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt != NULL) @@ -863,7 +863,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * comment in that function for the gory details. -acme */ - ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 1355614..743e9fc 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -925,8 +925,13 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old for(dev_out = dev_base; dev_out; dev_out = dev_out->next) { if (!dev_out->dn_ptr) continue; - if (dn_dev_islocal(dev_out, oldflp->fld_src)) - break; + if (!dn_dev_islocal(dev_out, oldflp->fld_src)) + continue; + if ((dev_out->flags & IFF_LOOPBACK) && + oldflp->fld_dst && + !dn_dev_islocal(dev_out, oldflp->fld_dst)) + continue; + break; } read_unlock(&dev_base_lock); if (dev_out == NULL) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7c9f9a6..9bf307a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -526,6 +526,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) err = output(skb); + if (!err) + IP_INC_STATS(IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; @@ -649,9 +651,6 @@ slow_path: /* * Put this fragment into the sending queue. */ - - IP_INC_STATS(IPSTATS_MIB_FRAGCREATES); - iph->tot_len = htons(len + hlen); ip_send_check(iph); @@ -659,6 +658,8 @@ slow_path: err = output(skb2); if (err) goto fail; + + IP_INC_STATS(IPSTATS_MIB_FRAGCREATES); } kfree_skb(skb); IP_INC_STATS(IPSTATS_MIB_FRAGOKS); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 84f43a3..2d05c41 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -112,14 +112,19 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { char *secdata; - u32 seclen; + u32 seclen, secid; int err; - err = security_socket_getpeersec_dgram(skb, &secdata, &seclen); + err = security_socket_getpeersec_dgram(NULL, skb, &secid); + if (err) + return; + + err = security_secid_to_secctx(secid, &secdata, &seclen); if (err) return; put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); + security_release_secctx(secdata, seclen); } diff --git a/net/ipv4/netfilter/ip_conntrack_sip.c b/net/ipv4/netfilter/ip_conntrack_sip.c index fc87ce0..4f222d6 100644 --- a/net/ipv4/netfilter/ip_conntrack_sip.c +++ b/net/ipv4/netfilter/ip_conntrack_sip.c @@ -442,7 +442,7 @@ static int __init init(void) sip[i].tuple.src.u.udp.port = htons(ports[i]); sip[i].mask.src.u.udp.port = 0xFFFF; sip[i].mask.dst.protonum = 0xFF; - sip[i].max_expected = 1; + sip[i].max_expected = 2; sip[i].timeout = 3 * 60; /* 3 minutes */ sip[i].me = THIS_MODULE; sip[i].help = sip_help; diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 92980ab..6b66244 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -508,6 +508,9 @@ hashlimit_checkentry(const char *tablename, if (!r->cfg.expire) return 0; + if (r->name[sizeof(r->name) - 1] != '\0') + return 0; + /* This is the best we've got: We cannot release and re-grab lock, * since checkentry() is called before ip_tables.c grabs ipt_mutex. * We also cannot grab the hashtable spinlock, since htable_create will diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 2dc6dbb..19bd49d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -104,6 +104,7 @@ #include <net/icmp.h> #include <net/xfrm.h> #include <net/ip_mp_alg.h> +#include <net/netevent.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif @@ -1125,6 +1126,7 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, struct rtable *rth, **rthp; u32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; + struct netevent_redirect netevent; if (!in_dev) return; @@ -1216,6 +1218,11 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw, rt_drop(rt); goto do_next; } + + netevent.old = &rth->u.dst; + netevent.new = &rt->u.dst; + call_netevent_notifiers(NETEVENT_REDIRECT, + &netevent); rt_del(hash, rth); if (!rt_intern_hash(hash, rt, &rt)) @@ -1452,6 +1459,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } dst->metrics[RTAX_MTU-1] = mtu; dst_set_expires(dst, ip_rt_mtu_expires); + call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f6a2d92..934396b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1132,7 +1132,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, tp->ucopy.dma_chan = NULL; preempt_disable(); if ((len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && - !sysctl_tcp_low_latency && __get_cpu_var(softnet_data.net_dma)) { + !sysctl_tcp_low_latency && __get_cpu_var(softnet_data).net_dma) { preempt_enable_no_resched(); tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); } else @@ -1659,7 +1659,8 @@ adjudge_to_death: const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { - inet_csk_reset_keepalive_timer(sk, tcp_fin_time(sk)); + inet_csk_reset_keepalive_timer(sk, + tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 738dad9..104af5d5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3541,7 +3541,8 @@ void tcp_cwnd_application_limited(struct sock *sk) if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { /* Limited by application or receiver window. */ - u32 win_used = max(tp->snd_cwnd_used, 2U); + u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); + u32 win_used = max(tp->snd_cwnd_used, init_win); if (win_used < tp->snd_cwnd) { tp->snd_ssthresh = tcp_current_ssthresh(sk); tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f6f39e8..4b04c3e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -438,7 +438,6 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) It can f.e. if SYNs crossed. */ if (!sock_owned_by_user(sk)) { - TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); @@ -874,7 +873,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) drop_and_free: reqsk_free(req); drop: - TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0ccb7cb..624e2b2 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -589,8 +589,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, /* RFC793: "second check the RST bit" and * "fourth, check the SYN bit" */ - if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) + if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) { + TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); goto embryonic_reset; + } /* ACK sequence verified above, just make sure ACK is * set. If ACK not set, just silently drop the packet. diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index d7d517a..b343532 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -114,7 +114,7 @@ static int tcpprobe_open(struct inode * inode, struct file * file) static ssize_t tcpprobe_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { - int error = 0, cnt; + int error = 0, cnt = 0; unsigned char *tbuf; if (!buf || len < 0) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2316a43..8ea1e36 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1869,15 +1869,21 @@ err_exit: /* * Manual configuration of address on an interface */ -static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen) +static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, + __u32 prefered_lft, __u32 valid_lft) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; + __u8 ifa_flags = 0; int scope; ASSERT_RTNL(); + /* check the lifetime */ + if (!valid_lft || prefered_lft > valid_lft) + return -EINVAL; + if ((dev = __dev_get_by_index(ifindex)) == NULL) return -ENODEV; @@ -1889,10 +1895,29 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen) scope = ipv6_addr_scope(pfx); - ifp = ipv6_add_addr(idev, pfx, plen, scope, IFA_F_PERMANENT); + if (valid_lft == INFINITY_LIFE_TIME) + ifa_flags |= IFA_F_PERMANENT; + else if (valid_lft >= 0x7FFFFFFF/HZ) + valid_lft = 0x7FFFFFFF/HZ; + + if (prefered_lft == 0) + ifa_flags |= IFA_F_DEPRECATED; + else if ((prefered_lft >= 0x7FFFFFFF/HZ) && + (prefered_lft != INFINITY_LIFE_TIME)) + prefered_lft = 0x7FFFFFFF/HZ; + + ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); + if (!IS_ERR(ifp)) { + spin_lock(&ifp->lock); + ifp->valid_lft = valid_lft; + ifp->prefered_lft = prefered_lft; + ifp->tstamp = jiffies; + spin_unlock(&ifp->lock); + addrconf_dad_start(ifp, 0); in6_ifa_put(ifp); + addrconf_verify(0); return 0; } @@ -1945,7 +1970,8 @@ int addrconf_add_ifaddr(void __user *arg) return -EFAULT; rtnl_lock(); - err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen); + err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); rtnl_unlock(); return err; } @@ -2771,12 +2797,16 @@ restart: ifp->idev->nd_parms->retrans_time / HZ; #endif - if (age >= ifp->valid_lft) { + if (ifp->valid_lft != INFINITY_LIFE_TIME && + age >= ifp->valid_lft) { spin_unlock(&ifp->lock); in6_ifa_hold(ifp); read_unlock(&addrconf_hash_lock); ipv6_del_addr(ifp); goto restart; + } else if (ifp->prefered_lft == INFINITY_LIFE_TIME) { + spin_unlock(&ifp->lock); + continue; } else if (age >= ifp->prefered_lft) { /* jiffies - ifp->tsamp > age >= ifp->prefered_lft */ int deprecate = 0; @@ -2853,7 +2883,8 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) pfx = RTA_DATA(rta[IFA_ADDRESS-1]); } if (rta[IFA_LOCAL-1]) { - if (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx))) + if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*pfx) || + (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx)))) return -EINVAL; pfx = RTA_DATA(rta[IFA_LOCAL-1]); } @@ -2864,11 +2895,61 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } static int +inet6_addr_modify(int ifindex, struct in6_addr *pfx, + __u32 prefered_lft, __u32 valid_lft) +{ + struct inet6_ifaddr *ifp = NULL; + struct net_device *dev; + int ifa_flags = 0; + + if ((dev = __dev_get_by_index(ifindex)) == NULL) + return -ENODEV; + + if (!(dev->flags&IFF_UP)) + return -ENETDOWN; + + if (!valid_lft || (prefered_lft > valid_lft)) + return -EINVAL; + + ifp = ipv6_get_ifaddr(pfx, dev, 1); + if (ifp == NULL) + return -ENOENT; + + if (valid_lft == INFINITY_LIFE_TIME) + ifa_flags = IFA_F_PERMANENT; + else if (valid_lft >= 0x7FFFFFFF/HZ) + valid_lft = 0x7FFFFFFF/HZ; + + if (prefered_lft == 0) + ifa_flags = IFA_F_DEPRECATED; + else if ((prefered_lft >= 0x7FFFFFFF/HZ) && + (prefered_lft != INFINITY_LIFE_TIME)) + prefered_lft = 0x7FFFFFFF/HZ; + + spin_lock_bh(&ifp->lock); + ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED|IFA_F_PERMANENT)) | ifa_flags; + + ifp->tstamp = jiffies; + ifp->valid_lft = valid_lft; + ifp->prefered_lft = prefered_lft; + + spin_unlock_bh(&ifp->lock); + if (!(ifp->flags&IFA_F_TENTATIVE)) + ipv6_ifa_notify(0, ifp); + in6_ifa_put(ifp); + + addrconf_verify(0); + + return 0; +} + +static int inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct rtattr **rta = arg; struct ifaddrmsg *ifm = NLMSG_DATA(nlh); struct in6_addr *pfx; + __u32 valid_lft = INFINITY_LIFE_TIME, prefered_lft = INFINITY_LIFE_TIME; pfx = NULL; if (rta[IFA_ADDRESS-1]) { @@ -2877,14 +2958,34 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) pfx = RTA_DATA(rta[IFA_ADDRESS-1]); } if (rta[IFA_LOCAL-1]) { - if (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx))) + if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*pfx) || + (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx)))) return -EINVAL; pfx = RTA_DATA(rta[IFA_LOCAL-1]); } if (pfx == NULL) return -EINVAL; - return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen); + if (rta[IFA_CACHEINFO-1]) { + struct ifa_cacheinfo *ci; + if (RTA_PAYLOAD(rta[IFA_CACHEINFO-1]) < sizeof(*ci)) + return -EINVAL; + ci = RTA_DATA(rta[IFA_CACHEINFO-1]); + valid_lft = ci->ifa_valid; + prefered_lft = ci->ifa_prefered; + } + + if (nlh->nlmsg_flags & NLM_F_REPLACE) { + int ret; + ret = inet6_addr_modify(ifm->ifa_index, pfx, + prefered_lft, valid_lft); + if (ret == 0 || !(nlh->nlmsg_flags & NLM_F_CREATE)) + return ret; + } + + return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen, + prefered_lft, valid_lft); + } /* Maximum length of ifa_cacheinfo attributes */ @@ -3121,6 +3222,62 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) return inet6_dump_addr(skb, cb, type); } +static int inet6_rtm_getaddr(struct sk_buff *in_skb, + struct nlmsghdr* nlh, void *arg) +{ + struct rtattr **rta = arg; + struct ifaddrmsg *ifm = NLMSG_DATA(nlh); + struct in6_addr *addr = NULL; + struct net_device *dev = NULL; + struct inet6_ifaddr *ifa; + struct sk_buff *skb; + int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + INET6_IFADDR_RTA_SPACE); + int err; + + if (rta[IFA_ADDRESS-1]) { + if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*addr)) + return -EINVAL; + addr = RTA_DATA(rta[IFA_ADDRESS-1]); + } + if (rta[IFA_LOCAL-1]) { + if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*addr) || + (addr && memcmp(addr, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*addr)))) + return -EINVAL; + addr = RTA_DATA(rta[IFA_LOCAL-1]); + } + if (addr == NULL) + return -EINVAL; + + if (ifm->ifa_index) + dev = __dev_get_by_index(ifm->ifa_index); + + if ((ifa = ipv6_get_ifaddr(addr, dev, 1)) == NULL) + return -EADDRNOTAVAIL; + + if ((skb = alloc_skb(size, GFP_KERNEL)) == NULL) { + err = -ENOBUFS; + goto out; + } + + NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; + err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid, + nlh->nlmsg_seq, RTM_NEWADDR, 0); + if (err < 0) { + err = -EMSGSIZE; + goto out_free; + } + + err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); + if (err > 0) + err = 0; +out: + in6_ifa_put(ifa); + return err; +out_free: + kfree_skb(skb); + goto out; +} + static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; @@ -3363,7 +3520,8 @@ static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { [RTM_GETLINK - RTM_BASE] = { .dumpit = inet6_dump_ifinfo, }, [RTM_NEWADDR - RTM_BASE] = { .doit = inet6_rtm_newaddr, }, [RTM_DELADDR - RTM_BASE] = { .doit = inet6_rtm_deladdr, }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = inet6_dump_ifaddr, }, + [RTM_GETADDR - RTM_BASE] = { .doit = inet6_rtm_getaddr, + .dumpit = inet6_dump_ifaddr, }, [RTM_GETMULTICAST - RTM_BASE] = { .dumpit = inet6_dump_ifmcaddr, }, [RTM_GETANYCAST - RTM_BASE] = { .dumpit = inet6_dump_ifacaddr, }, [RTM_NEWROUTE - RTM_BASE] = { .doit = inet6_rtm_newroute, }, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5a0ba58..ac85e9c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -658,7 +658,7 @@ int inet6_sk_rebuild_header(struct sock *sk) return err; } - ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL); } return 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 5c950cc..bf49107 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -185,7 +185,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) return err; } - ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL); } skb->dst = dst_clone(dst); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3bc74ce..69451af 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -356,6 +356,7 @@ int ip6_forward(struct sk_buff *skb) skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0, skb->dev); + IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; @@ -595,6 +596,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } err = output(skb); + if(!err) + IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); + if (err || !frag) break; @@ -706,12 +710,11 @@ slow_path: /* * Put this fragment into the sending queue. */ - - IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); - err = output(frag); if (err) goto fail; + + IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES); } kfree_skb(skb); IP6_INC_STATS(IPSTATS_MIB_FRAGOKS); @@ -723,48 +726,51 @@ fail: return err; } -int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) +static struct dst_entry *ip6_sk_dst_check(struct sock *sk, + struct dst_entry *dst, + struct flowi *fl) { - int err = 0; + struct ipv6_pinfo *np = inet6_sk(sk); + struct rt6_info *rt = (struct rt6_info *)dst; - *dst = NULL; - if (sk) { - struct ipv6_pinfo *np = inet6_sk(sk); - - *dst = sk_dst_check(sk, np->dst_cookie); - if (*dst) { - struct rt6_info *rt = (struct rt6_info*)*dst; - - /* Yes, checking route validity in not connected - * case is not very simple. Take into account, - * that we do not support routing by source, TOS, - * and MSG_DONTROUTE --ANK (980726) - * - * 1. If route was host route, check that - * cached destination is current. - * If it is network route, we still may - * check its validity using saved pointer - * to the last used address: daddr_cache. - * We do not want to save whole address now, - * (because main consumer of this service - * is tcp, which has not this problem), - * so that the last trick works only on connected - * sockets. - * 2. oif also should be the same. - */ - if (((rt->rt6i_dst.plen != 128 || - !ipv6_addr_equal(&fl->fl6_dst, - &rt->rt6i_dst.addr)) - && (np->daddr_cache == NULL || - !ipv6_addr_equal(&fl->fl6_dst, - np->daddr_cache))) - || (fl->oif && fl->oif != (*dst)->dev->ifindex)) { - dst_release(*dst); - *dst = NULL; - } - } + if (!dst) + goto out; + + /* Yes, checking route validity in not connected + * case is not very simple. Take into account, + * that we do not support routing by source, TOS, + * and MSG_DONTROUTE --ANK (980726) + * + * 1. If route was host route, check that + * cached destination is current. + * If it is network route, we still may + * check its validity using saved pointer + * to the last used address: daddr_cache. + * We do not want to save whole address now, + * (because main consumer of this service + * is tcp, which has not this problem), + * so that the last trick works only on connected + * sockets. + * 2. oif also should be the same. + */ + if (((rt->rt6i_dst.plen != 128 || + !ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr)) + && (np->daddr_cache == NULL || + !ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache))) + || (fl->oif && fl->oif != dst->dev->ifindex)) { + dst_release(dst); + dst = NULL; } +out: + return dst; +} + +static int ip6_dst_lookup_tail(struct sock *sk, + struct dst_entry **dst, struct flowi *fl) +{ + int err; + if (*dst == NULL) *dst = ip6_route_output(sk, fl); @@ -773,7 +779,6 @@ int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) if (ipv6_addr_any(&fl->fl6_src)) { err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src); - if (err) goto out_err_release; } @@ -786,8 +791,48 @@ out_err_release: return err; } +/** + * ip6_dst_lookup - perform route lookup on flow + * @sk: socket which provides route info + * @dst: pointer to dst_entry * for result + * @fl: flow to lookup + * + * This function performs a route lookup on the given flow. + * + * It returns zero on success, or a standard errno code on error. + */ +int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) +{ + *dst = NULL; + return ip6_dst_lookup_tail(sk, dst, fl); +} EXPORT_SYMBOL_GPL(ip6_dst_lookup); +/** + * ip6_sk_dst_lookup - perform socket cached route lookup on flow + * @sk: socket which provides the dst cache and route info + * @dst: pointer to dst_entry * for result + * @fl: flow to lookup + * + * This function performs a route lookup on the given flow with the + * possibility of using the cached route in the socket if it is valid. + * It will take the socket dst lock when operating on the dst cache. + * As a result, this function can only be used in process context. + * + * It returns zero on success, or a standard errno code on error. + */ +int ip6_sk_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) +{ + *dst = NULL; + if (sk) { + *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); + *dst = ip6_sk_dst_check(sk, *dst, fl); + } + + return ip6_dst_lookup_tail(sk, dst, fl); +} +EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup); + static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 87c39c9..4b16371 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -53,6 +53,7 @@ #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/xfrm.h> +#include <net/netevent.h> #include <asm/uaccess.h> @@ -742,6 +743,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; } dst->metrics[RTAX_MTU-1] = mtu; + call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } } @@ -1155,6 +1157,7 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, struct rt6_info *rt, *nrt = NULL; int strict; struct fib6_node *fn; + struct netevent_redirect netevent; /* * Get the "current" route for this destination and @@ -1252,6 +1255,10 @@ restart: if (ip6_ins_rt(nrt, NULL, NULL, NULL)) goto out; + netevent.old = &rt->u.dst; + netevent.new = &nrt->u.dst; + call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); + if (rt->rt6i_flags&RTF_CACHE) { ip6_del_rt(rt, NULL, NULL, NULL); return; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 923989d..b843a65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -270,7 +270,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; - ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt) @@ -427,7 +427,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case TCP_SYN_RECV: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { - TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ @@ -831,7 +830,6 @@ drop: if (req) reqsk_free(req); - TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); return 0; /* don't send reset */ } @@ -947,7 +945,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ sk->sk_gso_type = SKB_GSO_TCPV6; - ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ccc57f4..3d54f24 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -782,7 +782,7 @@ do_udp_sendmsg: connected = 0; } - err = ip6_dst_lookup(sk, &dst, fl); + err = ip6_sk_dst_lookup(sk, &dst, fl); if (err) goto out; if (final_p) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 0eea60e..c8c8b44 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -125,7 +125,7 @@ static int xfrm6_output_finish(struct sk_buff *skb) if (!skb_is_gso(skb)) return xfrm6_output_finish2(skb); - skb->protocol = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IPV6); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (unlikely(IS_ERR(segs))) diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index d504eed..7e6bc41 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -238,11 +238,13 @@ int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms) goto out_put; if (lapb->state == LAPB_STATE_0) { - if (((parms->mode & LAPB_EXTENDED) && - (parms->window < 1 || parms->window > 127)) || - (parms->window < 1 || parms->window > 7)) - goto out_put; - + if (parms->mode & LAPB_EXTENDED) { + if (parms->window < 1 || parms->window > 127) + goto out_put; + } else { + if (parms->window < 1 || parms->window > 7) + goto out_put; + } lapb->mode = parms->mode; lapb->window = parms->window; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index d6cfe84..2652ead 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -784,24 +784,20 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, copied += used; len -= used; - if (used + offset < skb->len) - continue; - if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, 0); *seq = 0; } + + /* For non stream protcols we get one packet per recvmsg call */ + if (sk->sk_type != SOCK_STREAM) + goto copy_uaddr; + + /* Partial read */ + if (used + offset < skb->len) + continue; } while (len > 0); - /* - * According to UNIX98, msg_name/msg_namelen are ignored - * on connected socket. -ANK - * But... af_llc still doesn't have separate sets of methods for - * SOCK_DGRAM and SOCK_STREAM :-( So we have to do this test, will - * eventually fix this tho :-) -acme - */ - if (sk->sk_type == SOCK_DGRAM) - goto copy_uaddr; out: release_sock(sk); return copied; diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 20c4eb5..42eb0c3 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -51,10 +51,10 @@ void llc_save_primitive(struct sock *sk, struct sk_buff* skb, u8 prim) { struct sockaddr_llc *addr; - if (skb->sk->sk_type == SOCK_STREAM) /* See UNIX98 */ - return; /* save primitive for use by the user. */ addr = llc_ui_skb_cb(skb); + + memset(addr, 0, sizeof(*addr)); addr->sllc_family = sk->sk_family; addr->sllc_arphrd = skb->dev->type; addr->sllc_test = prim == LLC_TEST_PRIM; diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c index c2ce9c4..de9537a 100644 --- a/net/netfilter/xt_SECMARK.c +++ b/net/netfilter/xt_SECMARK.c @@ -57,6 +57,8 @@ static int checkentry_selinux(struct xt_secmark_target_info *info) { int err; struct xt_secmark_target_selinux_info *sel = &info->u.sel; + + sel->selctx[SECMARK_SELCTX_MAX - 1] = '\0'; err = selinux_string_to_sid(sel->selctx, &sel->selsid); if (err) { diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c index 0ebb6ac..d8e3891 100644 --- a/net/netfilter/xt_string.c +++ b/net/netfilter/xt_string.c @@ -55,7 +55,10 @@ static int checkentry(const char *tablename, /* Damn, can't handle this case properly with iptables... */ if (conf->from_offset > conf->to_offset) return 0; - + if (conf->algo[XT_STRING_MAX_ALGO_NAME_SIZE - 1] != '\0') + return 0; + if (conf->patlen > XT_STRING_MAX_PATTERN_SIZE) + return 0; ts_conf = textsearch_prepare(conf->algo, conf->pattern, conf->patlen, GFP_KERNEL, TS_AUTOLOAD); if (IS_ERR(ts_conf)) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c7844ba..a19eff1 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -430,7 +430,7 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp) } #endif - err = -EINVAL; + err = -ENOENT; if (ops == NULL) goto err_out; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 7026b08..00cb388 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -71,7 +71,12 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, new = detail->alloc(); if (!new) return NULL; + /* must fully initialise 'new', else + * we might get lose if we need to + * cache_put it soon. + */ cache_init(new); + detail->init(new, key); write_lock(&detail->hash_lock); @@ -85,7 +90,6 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, return tmp; } } - detail->init(new, key); new->next = *head; *head = new; detail->entries++; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 4ba271f..d6409e7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -921,26 +921,43 @@ call_transmit(struct rpc_task *task) task->tk_status = xprt_prepare_transmit(task); if (task->tk_status != 0) return; + task->tk_action = call_transmit_status; /* Encode here so that rpcsec_gss can use correct sequence number. */ if (rpc_task_need_encode(task)) { - task->tk_rqstp->rq_bytes_sent = 0; + BUG_ON(task->tk_rqstp->rq_bytes_sent != 0); call_encode(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) - goto out_nosend; + return; } - task->tk_action = call_transmit_status; xprt_transmit(task); if (task->tk_status < 0) return; - if (!task->tk_msg.rpc_proc->p_decode) { - task->tk_action = rpc_exit_task; - rpc_wake_up_task(task); - } - return; -out_nosend: - /* release socket write lock before attempting to handle error */ - xprt_abort_transmit(task); + /* + * On success, ensure that we call xprt_end_transmit() before sleeping + * in order to allow access to the socket to other RPC requests. + */ + call_transmit_status(task); + if (task->tk_msg.rpc_proc->p_decode != NULL) + return; + task->tk_action = rpc_exit_task; + rpc_wake_up_task(task); +} + +/* + * 5a. Handle cleanup after a transmission + */ +static void +call_transmit_status(struct rpc_task *task) +{ + task->tk_action = call_status; + /* + * Special case: if we've been waiting on the socket's write_space() + * callback, then don't call xprt_end_transmit(). + */ + if (task->tk_status == -EAGAIN) + return; + xprt_end_transmit(task); rpc_task_force_reencode(task); } @@ -992,18 +1009,7 @@ call_status(struct rpc_task *task) } /* - * 6a. Handle transmission errors. - */ -static void -call_transmit_status(struct rpc_task *task) -{ - if (task->tk_status != -EAGAIN) - rpc_task_force_reencode(task); - call_status(task); -} - -/* - * 6b. Handle RPC timeout + * 6a. Handle RPC timeout * We do not release the request slot, so we keep using the * same XID for all retransmits. */ diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index dc6cb93..a3bd2db 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -667,10 +667,11 @@ rpc_mkdir(char *path, struct rpc_clnt *rpc_client) RPCAUTH_info, RPCAUTH_EOF); if (error) goto err_depopulate; + dget(dentry); out: mutex_unlock(&dir->i_mutex); rpc_release_path(&nd); - return dget(dentry); + return dentry; err_depopulate: rpc_depopulate(dentry); __rpc_rmdir(dir, dentry); @@ -731,10 +732,11 @@ rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags) rpci->flags = flags; rpci->ops = ops; inode_dir_notify(dir, DN_CREATE); + dget(dentry); out: mutex_unlock(&dir->i_mutex); rpc_release_path(&nd); - return dget(dentry); + return dentry; err_dput: dput(dentry); dentry = ERR_PTR(-ENOMEM); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 313b68d..e8c2bc4 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -707,12 +707,9 @@ out_unlock: return err; } -void -xprt_abort_transmit(struct rpc_task *task) +void xprt_end_transmit(struct rpc_task *task) { - struct rpc_xprt *xprt = task->tk_xprt; - - xprt_release_write(xprt, task); + xprt_release_write(task->tk_xprt, task); } /** @@ -761,8 +758,6 @@ void xprt_transmit(struct rpc_task *task) task->tk_status = -ENOTCONN; else if (!req->rq_received) rpc_sleep_on(&xprt->pending, task, NULL, xprt_timer); - - xprt->ops->release_xprt(xprt, task); spin_unlock_bh(&xprt->transport_lock); return; } @@ -772,18 +767,8 @@ void xprt_transmit(struct rpc_task *task) * schedq, and being picked up by a parallel run of rpciod(). */ task->tk_status = status; - - switch (status) { - case -ECONNREFUSED: + if (status == -ECONNREFUSED) rpc_sleep_on(&xprt->sending, task, NULL, NULL); - case -EAGAIN: - case -ENOTCONN: - return; - default: - break; - } - xprt_release_write(xprt, task); - return; } static inline void do_xprt_reserve(struct rpc_task *task) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ee678ed..441bd53 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -414,6 +414,33 @@ static int xs_tcp_send_request(struct rpc_task *task) } /** + * xs_tcp_release_xprt - clean up after a tcp transmission + * @xprt: transport + * @task: rpc task + * + * This cleans up if an error causes us to abort the transmission of a request. + * In this case, the socket may need to be reset in order to avoid confusing + * the server. + */ +static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) +{ + struct rpc_rqst *req; + + if (task != xprt->snd_task) + return; + if (task == NULL) + goto out_release; + req = task->tk_rqstp; + if (req->rq_bytes_sent == 0) + goto out_release; + if (req->rq_bytes_sent == req->rq_snd_buf.len) + goto out_release; + set_bit(XPRT_CLOSE_WAIT, &task->tk_xprt->state); +out_release: + xprt_release_xprt(xprt, task); +} + +/** * xs_close - close a socket * @xprt: transport * @@ -1250,7 +1277,7 @@ static struct rpc_xprt_ops xs_udp_ops = { static struct rpc_xprt_ops xs_tcp_ops = { .reserve_xprt = xprt_reserve_xprt, - .release_xprt = xprt_release_xprt, + .release_xprt = xs_tcp_release_xprt, .set_port = xs_set_port, .connect = xs_connect, .buf_alloc = rpc_malloc, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6f29092..de6ec51 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -128,23 +128,17 @@ static atomic_t unix_nr_socks = ATOMIC_INIT(0); #define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE) #ifdef CONFIG_SECURITY_NETWORK -static void unix_get_peersec_dgram(struct sk_buff *skb) +static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb) { - int err; - - err = security_socket_getpeersec_dgram(skb, UNIXSECDATA(skb), - UNIXSECLEN(skb)); - if (err) - *(UNIXSECDATA(skb)) = NULL; + memcpy(UNIXSID(skb), &scm->secid, sizeof(u32)); } static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) { - scm->secdata = *UNIXSECDATA(skb); - scm->seclen = *UNIXSECLEN(skb); + scm->secid = *UNIXSID(skb); } #else -static inline void unix_get_peersec_dgram(struct sk_buff *skb) +static inline void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb) { } static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) @@ -1322,8 +1316,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); if (siocb->scm->fp) unix_attach_fds(siocb->scm, skb); - - unix_get_peersec_dgram(skb); + unix_get_secdata(siocb->scm, skb); skb->h.raw = skb->data; err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); |
