diff --git a/Makefile b/Makefile index 81ede20061cf..402cbb7c27f1 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 10 -SUBLEVEL = 69 +SUBLEVEL = 70 EXTRAVERSION = NAME = TOSSUG Baby Fish diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 9951e66b8502..7e3f45105f11 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2149,7 +2149,6 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request) rbd_assert(img_request->obj_request_count > 0); rbd_assert(which != BAD_WHICH); rbd_assert(which < img_request->obj_request_count); - rbd_assert(which >= img_request->next_completion); spin_lock_irq(&img_request->completion_lock); if (which != img_request->next_completion) diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c index e4561264e124..a895ed02da86 100644 --- a/drivers/media/rc/ir-lirc-codec.c +++ b/drivers/media/rc/ir-lirc-codec.c @@ -42,11 +42,17 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) return -EINVAL; /* Packet start */ - if (ev.reset) - return 0; + if (ev.reset) { + /* Userspace expects a long space event before the start of + * the signal to use as a sync. This may be done with repeat + * packets and normal samples. But if a reset has been sent + * then we assume that a long time has passed, so we send a + * space with the maximum time value. */ + sample = LIRC_SPACE(LIRC_VALUE_MASK); + IR_dprintk(2, "delivering reset sync space to lirc_dev\n"); /* Carrier reports */ - if (ev.carrier_report) { + } else if (ev.carrier_report) { sample = LIRC_FREQUENCY(ev.carrier); IR_dprintk(2, "carrier report (freq: %d)\n", sample); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index af951f343ff6..50104a7e963f 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -2315,7 +2315,10 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget) work_done = netxen_process_rcv_ring(sds_ring, budget); - if ((work_done < budget) && tx_complete) { + if (!tx_complete) + work_done = budget; + + if (work_done < budget) { napi_complete(&sds_ring->napi); if (test_bit(__NX_DEV_UP, &adapter->state)) netxen_nic_enable_int(sds_ring); diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c index 602c625d95d5..b5edc7f96a39 100644 --- a/drivers/net/ppp/ppp_deflate.c +++ b/drivers/net/ppp/ppp_deflate.c @@ -246,7 +246,7 @@ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf, /* * See if we managed to reduce the size of the packet. */ - if (olen < isize) { + if (olen < isize && olen <= osize) { state->stats.comp_bytes += olen; state->stats.comp_packets++; } else { diff --git a/include/net/ip.h b/include/net/ip.h index 8695359982d1..0a62365149e2 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -37,11 +37,12 @@ struct inet_skb_parm { struct ip_options opt; /* Compiled IP options */ unsigned char flags; -#define IPSKB_FORWARDED 1 -#define IPSKB_XFRM_TUNNEL_SIZE 2 -#define IPSKB_XFRM_TRANSFORMED 4 -#define IPSKB_FRAG_COMPLETE 8 -#define IPSKB_REROUTED 16 +#define IPSKB_FORWARDED BIT(0) +#define IPSKB_XFRM_TUNNEL_SIZE BIT(1) +#define IPSKB_XFRM_TRANSFORMED BIT(2) +#define IPSKB_FRAG_COMPLETE BIT(3) +#define IPSKB_REROUTED BIT(4) +#define IPSKB_DOREDIRECT BIT(5) u16 frag_max_size; }; @@ -162,7 +163,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0; } -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len); diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2ba9de89e8ec..03e6378d5353 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,6 +43,7 @@ struct netns_ipv4 { struct inet_peer_base *peers; struct tcpm_hash_bucket *tcp_metrics_hash; unsigned int tcp_metrics_hash_log; + struct sock * __percpu *tcp_sk; struct netns_frags frags; #ifdef CONFIG_NETFILTER struct xt_table *iptable_filter; diff --git a/net/core/dev.c b/net/core/dev.c index cca7ae0ba915..c310440309bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6015,10 +6015,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } - /* Append NAPI poll list from offline CPU. */ - if (!list_empty(&oldsd->poll_list)) { - list_splice_init(&oldsd->poll_list, &sd->poll_list); - raise_softirq_irqoff(NET_RX_SOFTIRQ); + /* Append NAPI poll list from offline CPU, with one exception : + * process_backlog() must be called by cpu owning percpu backlog. + * We properly handle process_queue & input_pkt_queue later. + */ + while (!list_empty(&oldsd->poll_list)) { + struct napi_struct *napi = list_first_entry(&oldsd->poll_list, + struct napi_struct, + poll_list); + + list_del_init(&napi->poll_list); + if (napi->poll == process_backlog) + napi->state = 0; + else + ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); @@ -6029,7 +6039,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); input_queue_head_incr(oldsd); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 25c4dd563a79..279b5dcf09ae 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2477,12 +2477,16 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) goto errout; } + if (!skb->len) + goto errout; + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; errout: WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + if (err) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return err; } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index bd1c5baf69be..31ee5c6033df 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -175,7 +175,8 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) + if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr && + !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 22fa05e041ea..def18547748e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1454,23 +1454,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. - * - * Use a fake percpu inet socket to avoid false sharing and contention. */ -static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = { - .sk = { - .__sk_common = { - .skc_refcnt = ATOMIC_INIT(1), - }, - .sk_wmem_alloc = ATOMIC_INIT(1), - .sk_allocation = GFP_ATOMIC, - .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE), - }, - .pmtudisc = IP_PMTUDISC_WANT, - .uc_ttl = -1, -}; - -void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, +void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len) { @@ -1478,9 +1463,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); + struct net *net = sock_net(sk); struct sk_buff *nskb; - struct sock *sk; - struct inet_sock *inet; int err; if (ip_options_echo(&replyopts.opt.opt, skb)) @@ -1508,15 +1492,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_cpu_var(unicast_sock); + inet_sk(sk)->tos = arg->tos; - inet->tos = arg->tos; - sk = &inet->sk; sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sock_net_set(sk, net); - __skb_queue_head_init(&sk->sk_write_queue); sk->sk_sndbuf = sysctl_wmem_default; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); @@ -1532,13 +1512,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - skb_orphan(nskb); skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb)); ip_push_pending_frames(sk, &fl4); } out: - put_cpu_var(unicast_sock); - ip_rt_put(rt); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 23e6ab0a2dc0..f6603142cb33 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -410,15 +410,11 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) { - struct inet_sock *inet = inet_sk(sk); - sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; - sin->sin_port = 0; - memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aa857a4a06a8..698f3a2ac5ae 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -720,8 +720,11 @@ void ping_rcv(struct sk_buff *skb) sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk != NULL) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + pr_debug("rcv on socket %p\n", sk); - ping_queue_rcv_skb(sk, skb_get(skb)); + if (skb2) + ping_queue_rcv_skb(sk, skb2); sock_put(sk); return; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d4d162eac4df..e23c5f64286b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1514,11 +1514,10 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && + skb->protocol == htons(ETH_P_IP) && (IN_DEV_SHARED_MEDIA(out_dev) || - inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) { - flags |= RTCF_DOREDIRECT; - do_cache = false; - } + inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) + IPCB(skb)->flags |= IPSKB_DOREDIRECT; if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is @@ -2255,6 +2254,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; + if (IPCB(skb)->flags & IPSKB_DOREDIRECT) + r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_be32(skb, RTA_DST, dst)) goto nla_put_failure; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e025c1c788a1..cce35e5a7ee6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -707,7 +707,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -790,7 +791,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, if (oif) arg.bound_dev_if = oif; arg.tos = tos; - ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr, + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); @@ -2898,14 +2900,39 @@ struct proto tcp_prot = { }; EXPORT_SYMBOL(tcp_prot); +static void __net_exit tcp_sk_exit(struct net *net) +{ + int cpu; + + for_each_possible_cpu(cpu) + inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); + free_percpu(net->ipv4.tcp_sk); +} + static int __net_init tcp_sk_init(struct net *net) { + int res, cpu; + + net->ipv4.tcp_sk = alloc_percpu(struct sock *); + if (!net->ipv4.tcp_sk) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, net); + if (res) + goto fail; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; + } net->ipv4.sysctl_tcp_ecn = 2; return 0; -} -static void __net_exit tcp_sk_exit(struct net *net) -{ +fail: + tcp_sk_exit(net); + + return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 7927db0a9279..4a000f1dd757 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -99,11 +99,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlin s_slot = cb->args[0]; num = s_num = cb->args[1]; - for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) { + for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct sock *sk; struct hlist_nulls_node *node; struct udp_hslot *hslot = &table->hash[slot]; + num = 0; + if (hlist_nulls_empty(&hslot->head)) continue; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 8997340e3742..ce17d3da9b2b 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -374,11 +374,10 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin6_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); + if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; - sin->sin6_flowinfo = 0; - sin->sin6_port = 0; if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) @@ -387,12 +386,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { - struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - sin->sin6_scope_id = 0; - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 009c9620f442..ceeb9458bb60 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -638,6 +638,29 @@ static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) RTF_GATEWAY; } +static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, + struct net *net) +{ + if (atomic_read(&rt->rt6i_ref) != 1) { + /* This route is used as dummy address holder in some split + * nodes. It is not leaked, but it still holds other resources, + * which must be released in time. So, scan ascendant nodes + * and replace dummy references to this route with references + * to still alive ones. + */ + while (fn) { + if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { + fn->leaf = fib6_find_prefix(net, fn); + atomic_inc(&fn->leaf->rt6i_ref); + rt6_release(rt); + } + fn = fn->parent; + } + /* No more references are possible at this point. */ + BUG_ON(atomic_read(&rt->rt6i_ref) != 1); + } +} + /* * Insert routing information in a node. */ @@ -775,11 +798,12 @@ add: rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info); - rt6_release(iter); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); } return 0; @@ -1284,24 +1308,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fn = fib6_repair_tree(net, fn); } - if (atomic_read(&rt->rt6i_ref) != 1) { - /* This route is used as dummy address holder in some split - * nodes. It is not leaked, but it still holds other resources, - * which must be released in time. So, scan ascendant nodes - * and replace dummy references to this route with references - * to still alive ones. - */ - while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); - rt6_release(rt); - } - fn = fn->parent; - } - /* No more references are possible at this point. */ - BUG_ON(atomic_read(&rt->rt6i_ref) != 1); - } + fib6_purge_rt(rt, fn, net); inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b2614b22622b..92274796eb71 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1141,12 +1141,9 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct net *net = dev_net(dst->dev); rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) { - u32 features = dst_metric(dst, RTAX_FEATURES); + if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(dst, RTAX_FEATURES, features); - } + dst_metric_set(dst, RTAX_MTU, mtu); rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index ca4a1a1b8e69..6360a14edeab 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1297,7 +1297,6 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; - sctp_auth_key_put(asoc->asoc_shared_key); sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 29fc16f3633f..beedadf62f6c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2595,7 +2595,7 @@ do_addr_param: addr_param = param.v + sizeof(sctp_addip_param_t); - af = sctp_get_af_specific(param_type2af(param.p->type)); + af = sctp_get_af_specific(param_type2af(addr_param->p.type)); if (af == NULL) break;