diff options
Diffstat (limited to 'net')
54 files changed, 484 insertions, 349 deletions
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 9b58d70..4f52c3d 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -148,11 +148,16 @@ static int br_set_tx_csum(struct net_device *dev, u32 data) } static struct ethtool_ops br_ethtool_ops = { - .get_drvinfo = br_getinfo, - .get_link = ethtool_op_get_link, - .set_sg = br_set_sg, - .set_tx_csum = br_set_tx_csum, - .set_tso = br_set_tso, + .get_drvinfo = br_getinfo, + .get_link = ethtool_op_get_link, + .get_tx_csum = ethtool_op_get_tx_csum, + .set_tx_csum = br_set_tx_csum, + .get_sg = ethtool_op_get_sg, + .set_sg = br_set_sg, + .get_tso = ethtool_op_get_tso, + .set_tso = br_set_tso, + .get_ufo = ethtool_op_get_ufo, + .get_flags = ethtool_op_get_flags, }; void br_dev_setup(struct net_device *dev) diff --git a/net/core/datagram.c b/net/core/datagram.c index dd61dca..52f577a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -339,6 +339,93 @@ fault: return -EFAULT; } +/** + * skb_copy_datagram_from_iovec - Copy a datagram from an iovec. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying to + * @from: io vector to copy to + * @len: amount of data to copy to buffer from iovec + * + * Returns 0 or -EFAULT. + * Note: the iovec is modified during the copy. + */ +int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, + struct iovec *from, int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_fromiovec(skb->data + offset, from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + WARN_ON(start > offset + len); + + end = start + skb_shinfo(skb)->frags[i].size; + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = frag->page; + + if (copy > len) + copy = len; + vaddr = kmap(page); + err = memcpy_fromiovec(vaddr + frag->page_offset + + offset - start, from, copy); + kunmap(page); + if (err) + goto fault; + + if (!(len -= copy)) + return 0; + offset += copy; + } + start = end; + } + + if (skb_shinfo(skb)->frag_list) { + struct sk_buff *list = skb_shinfo(skb)->frag_list; + + for (; list; list = list->next) { + int end; + + WARN_ON(start > offset + len); + + end = start + list->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_from_iovec(list, + offset - start, + from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + start = end; + } + } + if (!len) + return 0; + +fault: + return -EFAULT; +} +EXPORT_SYMBOL(skb_copy_datagram_from_iovec); + static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, u8 __user *to, int len, __wsum *csump) diff --git a/net/core/dev.c b/net/core/dev.c index 600bb23..8d13380 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1339,19 +1339,23 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) } -void __netif_schedule(struct Qdisc *q) +static inline void __netif_reschedule(struct Qdisc *q) { - if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) { - struct softnet_data *sd; - unsigned long flags; + struct softnet_data *sd; + unsigned long flags; - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - q->next_sched = sd->output_queue; - sd->output_queue = q; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); - } + local_irq_save(flags); + sd = &__get_cpu_var(softnet_data); + q->next_sched = sd->output_queue; + sd->output_queue = q; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); +} + +void __netif_schedule(struct Qdisc *q) +{ + if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) + __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); @@ -1800,9 +1804,13 @@ gso: spin_lock(root_lock); - rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); - + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + kfree_skb(skb); + rc = NET_XMIT_DROP; + } else { + rc = qdisc_enqueue_root(skb, q); + qdisc_run(q); + } spin_unlock(root_lock); goto out; @@ -1974,15 +1982,15 @@ static void net_tx_action(struct softirq_action *h) head = head->next_sched; - smp_mb__before_clear_bit(); - clear_bit(__QDISC_STATE_SCHED, &q->state); - root_lock = qdisc_lock(q); if (spin_trylock(root_lock)) { + smp_mb__before_clear_bit(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); qdisc_run(q); spin_unlock(root_lock); } else { - __netif_schedule(q); + __netif_reschedule(q); } } } @@ -2084,7 +2092,8 @@ static int ing_filter(struct sk_buff *skb) q = rxq->qdisc; if (q != &noop_qdisc) { spin_lock(qdisc_lock(q)); - result = qdisc_enqueue_root(skb, q); + if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) + result = qdisc_enqueue_root(skb, q); spin_unlock(qdisc_lock(q)); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 5262364..a756847 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1961,6 +1961,8 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) */ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) { + int ntxq; + if (!pkt_dev->odev) { printk(KERN_ERR "pktgen: ERROR: pkt_dev->odev == NULL in " "setup_inject.\n"); @@ -1969,6 +1971,33 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) return; } + /* make sure that we don't pick a non-existing transmit queue */ + ntxq = pkt_dev->odev->real_num_tx_queues; + if (ntxq <= num_online_cpus() && (pkt_dev->flags & F_QUEUE_MAP_CPU)) { + printk(KERN_WARNING "pktgen: WARNING: QUEUE_MAP_CPU " + "disabled because CPU count (%d) exceeds number ", + num_online_cpus()); + printk(KERN_WARNING "pktgen: WARNING: of tx queues " + "(%d) on %s \n", ntxq, pkt_dev->odev->name); + pkt_dev->flags &= ~F_QUEUE_MAP_CPU; + } + if (ntxq <= pkt_dev->queue_map_min) { + printk(KERN_WARNING "pktgen: WARNING: Requested " + "queue_map_min (%d) exceeds number of tx\n", + pkt_dev->queue_map_min); + printk(KERN_WARNING "pktgen: WARNING: queues (%d) on " + "%s, resetting\n", ntxq, pkt_dev->odev->name); + pkt_dev->queue_map_min = ntxq - 1; + } + if (ntxq <= pkt_dev->queue_map_max) { + printk(KERN_WARNING "pktgen: WARNING: Requested " + "queue_map_max (%d) exceeds number of tx\n", + pkt_dev->queue_map_max); + printk(KERN_WARNING "pktgen: WARNING: queues (%d) on " + "%s, resetting\n", ntxq, pkt_dev->odev->name); + pkt_dev->queue_map_max = ntxq - 1; + } + /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8464017..ca1ccdf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2256,14 +2256,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) segs = nskb; tail = nskb; - nskb->dev = skb->dev; - skb_copy_queue_mapping(nskb, skb); - nskb->priority = skb->priority; - nskb->protocol = skb->protocol; - nskb->vlan_tci = skb->vlan_tci; - nskb->dst = dst_clone(skb->dst); - memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); - nskb->pkt_type = skb->pkt_type; + __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; skb_reserve(nskb, headroom); @@ -2274,6 +2267,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) skb_copy_from_linear_data(skb, skb_put(nskb, doffset), doffset); if (!sg) { + nskb->ip_summed = CHECKSUM_NONE; nskb->csum = skb_copy_and_csum_bits(skb, offset, skb_put(nskb, len), len, 0); @@ -2283,8 +2277,6 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) frag = skb_shinfo(nskb)->frags; k = 0; - nskb->ip_summed = CHECKSUM_PARTIAL; - nskb->csum = skb->csum; skb_copy_from_linear_data_offset(skb, offset, skb_put(nskb, hsize), hsize); diff --git a/net/dccp/input.c b/net/dccp/input.c index df2f110..803933a 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -411,12 +411,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, struct dccp_sock *dp = dccp_sk(sk); long tstamp = dccp_timestamp(); - /* Stop the REQUEST timer */ - inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); - WARN_ON(sk->sk_send_head == NULL); - __kfree_skb(sk->sk_send_head); - sk->sk_send_head = NULL; - if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq, dp->dccps_awl, dp->dccps_awh)) { dccp_pr_debug("invalid ackno: S.AWL=%llu, " @@ -441,6 +435,12 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, DCCP_ACKVEC_STATE_RECEIVED)) goto out_invalid_packet; /* FIXME: change error code */ + /* Stop the REQUEST timer */ + inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); + WARN_ON(sk->sk_send_head == NULL); + kfree_skb(sk->sk_send_head); + sk->sk_send_head = NULL; + dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_update_gsr(sk, dp->dccps_isr); /* diff --git a/net/dccp/proto.c b/net/dccp/proto.c index b622d974..1ca3b26 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -474,6 +474,11 @@ static int dccp_setsockopt_change(struct sock *sk, int type, if (copy_from_user(&opt, optval, sizeof(opt))) return -EFAULT; + /* + * rfc4340: 6.1. Change Options + */ + if (opt.dccpsf_len < 1) + return -EINVAL; val = kmalloc(opt.dccpsf_len, GFP_KERNEL); if (!val) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6203ece..f70fac6 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -289,6 +289,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; + struct net *net = dev_net(dev); skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); if (skb == NULL) @@ -299,7 +300,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) .nl_u = { .ip4_u = { .daddr = IGMPV3_ALL_MCR } }, .proto = IPPROTO_IGMP }; - if (ip_route_output_key(&init_net, &rt, &fl)) { + if (ip_route_output_key(net, &rt, &fl)) { kfree_skb(skb); return NULL; } @@ -629,6 +630,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; + struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; __be32 dst; @@ -643,7 +645,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, struct flowi fl = { .oif = dev->ifindex, .nl_u = { .ip4_u = { .daddr = dst } }, .proto = IPPROTO_IGMP }; - if (ip_route_output_key(&init_net, &rt, &fl)) + if (ip_route_output_key(net, &rt, &fl)) return -1; } if (rt->rt_src == 0) { @@ -1196,9 +1198,6 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - for (im=in_dev->mc_list; im; im=im->next) { if (im->multiaddr == addr) { im->users++; @@ -1278,9 +1277,6 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { if (i->multiaddr==addr) { if (--i->users == 0) { @@ -1308,9 +1304,6 @@ void ip_mc_down(struct in_device *in_dev) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - for (i=in_dev->mc_list; i; i=i->next) igmp_group_dropped(i); @@ -1331,9 +1324,6 @@ void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - in_dev->mc_tomb = NULL; #ifdef CONFIG_IP_MULTICAST in_dev->mr_gq_running = 0; @@ -1357,9 +1347,6 @@ void ip_mc_up(struct in_device *in_dev) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for (i=in_dev->mc_list; i; i=i->next) @@ -1376,9 +1363,6 @@ void ip_mc_destroy_dev(struct in_device *in_dev) ASSERT_RTNL(); - if (!net_eq(dev_net(in_dev->dev), &init_net)) - return; - /* Deactivate timers */ ip_mc_down(in_dev); @@ -1395,7 +1379,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) write_unlock_bh(&in_dev->mc_list_lock); } -static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) +static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct flowi fl = { .nl_u = { .ip4_u = { .daddr = imr->imr_multiaddr.s_addr } } }; @@ -1404,19 +1388,19 @@ static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) struct in_device *idev = NULL; if (imr->imr_ifindex) { - idev = inetdev_by_index(&init_net, imr->imr_ifindex); + idev = inetdev_by_index(net, imr->imr_ifindex); if (idev) __in_dev_put(idev); return idev; } if (imr->imr_address.s_addr) { - dev = ip_dev_find(&init_net, imr->imr_address.s_addr); + dev = ip_dev_find(net, imr->imr_address.s_addr); if (!dev) return NULL; dev_put(dev); } - if (!dev && !ip_route_output_key(&init_net, &rt, &fl)) { + if (!dev && !ip_route_output_key(net, &rt, &fl)) { dev = rt->u.dst.dev; ip_rt_put(rt); } @@ -1754,18 +1738,16 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) struct ip_mc_socklist *iml=NULL, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); int ifindex; int count = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); - in_dev = ip_mc_find_dev(imr); + in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { iml = NULL; @@ -1827,15 +1809,13 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml, **imlp; struct in_device *in_dev; + struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); - in_dev = ip_mc_find_dev(imr); + in_dev = ip_mc_find_dev(net, imr); ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { if (iml->multi.imr_multiaddr.s_addr != group) @@ -1873,21 +1853,19 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; + struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; - in_dev = ip_mc_find_dev(&imr); + in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; @@ -2007,6 +1985,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; + struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) @@ -2015,15 +1994,12 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; - in_dev = ip_mc_find_dev(&imr); + in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; @@ -2094,19 +2070,17 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; + struct net *net = sock_net(sk); if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; - in_dev = ip_mc_find_dev(&imr); + in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; @@ -2163,9 +2137,6 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!ipv4_is_multicast(addr)) return -EINVAL; - if (!net_eq(sock_net(sk), &init_net)) - return -EPROTONOSUPPORT; - rtnl_lock(); err = -EADDRNOTAVAIL; @@ -2246,19 +2217,17 @@ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; + struct net *net = sock_net(sk); if (inet->mc_list == NULL) return; - if (!net_eq(sock_net(sk), &init_net)) - return; - rtnl_lock(); while ((iml = inet->mc_list) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next; - in_dev = inetdev_by_index(&init_net, iml->multi.imr_ifindex); + in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev != NULL) { ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); diff --git a/net/ipv4/ipvs/ip_vs_app.c b/net/ipv4/ipvs/ip_vs_app.c index 1f1897a..201b8ea 100644 --- a/net/ipv4/ipvs/ip_vs_app.c +++ b/net/ipv4/ipvs/ip_vs_app.c @@ -608,7 +608,7 @@ int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri, } -int ip_vs_app_init(void) +int __init ip_vs_app_init(void) { /* we will replace it with proc_net_ipvs_create() soon */ proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops); diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index f8bdae4..44a6872 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -965,7 +965,7 @@ static void ip_vs_conn_flush(void) } -int ip_vs_conn_init(void) +int __init ip_vs_conn_init(void) { int idx; diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 9a5ace0..6379705 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -683,9 +683,22 @@ static void ip_vs_zero_stats(struct ip_vs_stats *stats) { spin_lock_bh(&stats->lock); - memset(stats, 0, (char *)&stats->lock - (char *)stats); - spin_unlock_bh(&stats->lock); + + stats->conns = 0; + stats->inpkts = 0; + stats->outpkts = 0; + stats->inbytes = 0; + stats->outbytes = 0; + + stats->cps = 0; + stats->inpps = 0; + stats->outpps = 0; + stats->inbps = 0; + stats->outbps = 0; + ip_vs_zero_estimator(stats); + + spin_unlock_bh(&stats->lock); } /* @@ -1589,7 +1602,7 @@ static struct ctl_table vs_vars[] = { { .ctl_name = 0 } }; -struct ctl_path net_vs_ctl_path[] = { +const struct ctl_path net_vs_ctl_path[] = { { .procname = "net", .ctl_name = CTL_NET, }, { .procname = "ipv4", .ctl_name = NET_IPV4, }, { .procname = "vs", }, @@ -1784,7 +1797,9 @@ static const struct file_operations ip_vs_info_fops = { #endif -struct ip_vs_stats ip_vs_stats; +struct ip_vs_stats ip_vs_stats = { + .lock = __SPIN_LOCK_UNLOCKED(ip_vs_stats.lock), +}; #ifdef CONFIG_PROC_FS static int ip_vs_stats_show(struct seq_file *seq, void *v) @@ -2306,7 +2321,7 @@ static struct nf_sockopt_ops ip_vs_sockopts = { }; -int ip_vs_control_init(void) +int __init ip_vs_control_init(void) { int ret; int idx; @@ -2333,8 +2348,6 @@ int ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_rtable[idx]); } - memset(&ip_vs_stats, 0, sizeof(ip_vs_stats)); - spin_lock_init(&ip_vs_stats.lock); ip_vs_new_estimator(&ip_vs_stats); /* Hook the defense timer */ diff --git a/net/ipv4/ipvs/ip_vs_dh.c b/net/ipv4/ipvs/ip_vs_dh.c index 8afc150..fa66824 100644 --- a/net/ipv4/ipvs/ip_vs_dh.c +++ b/net/ipv4/ipvs/ip_vs_dh.c @@ -233,6 +233,7 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler = .name = "dh", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_dh_scheduler.n_list), .init_service = ip_vs_dh_init_svc, .done_service = ip_vs_dh_done_svc, .update_service = ip_vs_dh_update_svc, @@ -242,7 +243,6 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler = static int __init ip_vs_dh_init(void) { - INIT_LIST_HEAD(&ip_vs_dh_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_dh_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_est.c b/net/ipv4/ipvs/ip_vs_est.c index bc04eed..5a20f93 100644 --- a/net/ipv4/ipvs/ip_vs_est.c +++ b/net/ipv4/ipvs/ip_vs_est.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/sysctl.h> +#include <linux/list.h> #include <net/ip_vs.h> @@ -44,28 +45,11 @@ */ -struct ip_vs_estimator -{ - struct ip_vs_estimator *next; - struct ip_vs_stats *stats; - - u32 last_conns; - u32 last_inpkts; - u32 last_outpkts; - u64 last_inbytes; - u64 last_outbytes; - - u32 cps; - u32 inpps; - u32 outpps; - u32 inbps; - u32 outbps; -}; - +static void estimation_timer(unsigned long arg); -static struct ip_vs_estimator *est_list = NULL; -static DEFINE_RWLOCK(est_lock); -static struct timer_list est_timer; +static LIST_HEAD(est_list); +static DEFINE_SPINLOCK(est_lock); +static DEFINE_TIMER(est_timer, estimation_timer, 0, 0); static void estimation_timer(unsigned long arg) { @@ -76,9 +60,9 @@ static void estimation_timer(unsigned long arg) u64 n_inbytes, n_outbytes; u32 rate; - read_lock(&est_lock); - for (e = est_list; e; e = e->next) { - s = e->stats; + spin_lock(&est_lock); + list_for_each_entry(e, &est_list, list) { + s = container_of(e, struct ip_vs_stats, est); spin_lock(&s->lock); n_conns = s->conns; @@ -114,19 +98,16 @@ static void estimation_timer(unsigned long arg) s->outbps = (e->outbps+0xF)>>5; spin_unlock(&s->lock); } - read_unlock(&est_lock); + spin_unlock(&est_lock); mod_timer(&est_timer, jiffies + 2*HZ); } -int ip_vs_new_estimator(struct ip_vs_stats *stats) +void ip_vs_new_estimator(struct ip_vs_stats *stats) { - struct ip_vs_estimator *est; + struct ip_vs_estimator *est = &stats->est; - est = kzalloc(sizeof(*est), GFP_KERNEL); - if (est == NULL) - return -ENOMEM; + INIT_LIST_HEAD(&est->list); - est->stats = stats; est->last_conns = stats->conns; est->cps = stats->cps<<10; @@ -142,59 +123,40 @@ int ip_vs_new_estimator(struct ip_vs_stats *stats) est->last_outbytes = stats->outbytes; est->outbps = stats->outbps<<5; - write_lock_bh(&est_lock); - est->next = est_list; - if (est->next == NULL) { - setup_timer(&est_timer, estimation_timer, 0); - est_timer.expires = jiffies + 2*HZ; - add_timer(&est_timer); - } - est_list = est; - write_unlock_bh(&est_lock); - return 0; + spin_lock_bh(&est_lock); + if (list_empty(&est_list)) + mod_timer(&est_timer, jiffies + 2 * HZ); + list_add(&est->list, &est_list); + spin_unlock_bh(&est_lock); } void ip_vs_kill_estimator(struct ip_vs_stats *stats) { - struct ip_vs_estimator *est, **pest; - int killed = 0; - - write_lock_bh(&est_lock); - pest = &est_list; - while ((est=*pest) != NULL) { - if (est->stats != stats) { - pest = &est->next; - continue; - } - *pest = est->next; - kfree(est); - killed++; + struct ip_vs_estimator *est = &stats->est; + + spin_lock_bh(&est_lock); + list_del(&est->list); + while (list_empty(&est_list) && try_to_del_timer_sync(&est_timer) < 0) { + spin_unlock_bh(&est_lock); + cpu_relax(); + spin_lock_bh(&est_lock); } - if (killed && est_list == NULL) - del_timer_sync(&est_timer); - write_unlock_bh(&est_lock); + spin_unlock_bh(&est_lock); } void ip_vs_zero_estimator(struct ip_vs_stats *stats) { - struct ip_vs_estimator *e; - - write_lock_bh(&est_lock); - for (e = est_list; e; e = e->next) { - if (e->stats != stats) - continue; - - /* set counters zero */ - e->last_conns = 0; - e->last_inpkts = 0; - e->last_outpkts = 0; - e->last_inbytes = 0; - e->last_outbytes = 0; - e->cps = 0; - e->inpps = 0; - e->outpps = 0; - e->inbps = 0; - e->outbps = 0; - } - write_unlock_bh(&est_lock); + struct ip_vs_estimator *est = &stats->est; + + /* set counters zero, caller must hold the stats->lock lock */ + est->last_inbytes = 0; + est->last_outbytes = 0; + est->last_conns = 0; + est->last_inpkts = 0; + est->last_outpkts = 0; + est->cps = 0; + est->inpps = 0; + est->outpps = 0; + est->inbps = 0; + est->outbps = 0; } diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c index 0efa3db..7a6a319 100644 --- a/net/ipv4/ipvs/ip_vs_lblc.c +++ b/net/ipv4/ipvs/ip_vs_lblc.c @@ -539,6 +539,7 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = .name = "lblc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_lblc_scheduler.n_list), .init_service = ip_vs_lblc_init_svc, .done_service = ip_vs_lblc_done_svc, .update_service = ip_vs_lblc_update_svc, @@ -550,7 +551,6 @@ static int __init ip_vs_lblc_init(void) { int ret; - INIT_LIST_HEAD(&ip_vs_lblc_scheduler.n_list); sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler); if (ret) diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c index 8e3bbeb..c234e73 100644 --- a/net/ipv4/ipvs/ip_vs_lblcr.c +++ b/net/ipv4/ipvs/ip_vs_lblcr.c @@ -728,6 +728,7 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = .name = "lblcr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_lblcr_scheduler.n_list), .init_service = ip_vs_lblcr_init_svc, .done_service = ip_vs_lblcr_done_svc, .update_service = ip_vs_lblcr_update_svc, @@ -739,7 +740,6 @@ static int __init ip_vs_lblcr_init(void) { int ret; - INIT_LIST_HEAD(&ip_vs_lblcr_scheduler.n_list); sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler); if (ret) diff --git a/net/ipv4/ipvs/ip_vs_lc.c b/net/ipv4/ipvs/ip_vs_lc.c index ac9f08e..ebcdbf7 100644 --- a/net/ipv4/ipvs/ip_vs_lc.c +++ b/net/ipv4/ipvs/ip_vs_lc.c @@ -98,6 +98,7 @@ static struct ip_vs_scheduler ip_vs_lc_scheduler = { .name = "lc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_lc_scheduler.n_list), .init_service = ip_vs_lc_init_svc, .done_service = ip_vs_lc_done_svc, .update_service = ip_vs_lc_update_svc, @@ -107,7 +108,6 @@ static struct ip_vs_scheduler ip_vs_lc_scheduler = { static int __init ip_vs_lc_init(void) { - INIT_LIST_HEAD(&ip_vs_lc_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_lc_scheduler) ; } diff --git a/net/ipv4/ipvs/ip_vs_nq.c b/net/ipv4/ipvs/ip_vs_nq.c index a46bf25..92f3a67 100644 --- a/net/ipv4/ipvs/ip_vs_nq.c +++ b/net/ipv4/ipvs/ip_vs_nq.c @@ -136,6 +136,7 @@ static struct ip_vs_scheduler ip_vs_nq_scheduler = .name = "nq", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_nq_scheduler.n_list), .init_service = ip_vs_nq_init_svc, .done_service = ip_vs_nq_done_svc, .update_service = ip_vs_nq_update_svc, @@ -145,7 +146,6 @@ static struct ip_vs_scheduler ip_vs_nq_scheduler = static int __init ip_vs_nq_init(void) { - INIT_LIST_HEAD(&ip_vs_nq_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_nq_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c index 876714f..6099a88 100644 --- a/net/ipv4/ipvs/ip_vs_proto.c +++ b/net/ipv4/ipvs/ip_vs_proto.c @@ -43,7 +43,7 @@ static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; /* * register an ipvs protocol */ -static int __used register_ip_vs_protocol(struct ip_vs_protocol *pp) +static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) { unsigned hash = IP_VS_PROTO_HASH(pp->protocol); @@ -190,7 +190,7 @@ ip_vs_tcpudp_debug_packet(struct ip_vs_protocol *pp, } -int ip_vs_protocol_init(void) +int __init ip_vs_protocol_init(void) { char protocols[64]; #define REGISTER_PROTOCOL(p) \ diff --git a/net/ipv4/ipvs/ip_vs_rr.c b/net/ipv4/ipvs/ip_vs_rr.c index c8db12d..358110d 100644 --- a/net/ipv4/ipvs/ip_vs_rr.c +++ b/net/ipv4/ipvs/ip_vs_rr.c @@ -94,6 +94,7 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = { .name = "rr", /* name */ .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_rr_scheduler.n_list), .init_service = ip_vs_rr_init_svc, .done_service = ip_vs_rr_done_svc, .update_service = ip_vs_rr_update_svc, @@ -102,7 +103,6 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = { static int __init ip_vs_rr_init(void) { - INIT_LIST_HEAD(&ip_vs_rr_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_rr_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_sched.c b/net/ipv4/ipvs/ip_vs_sched.c index b647673..a46ad9e 100644 --- a/net/ipv4/ipvs/ip_vs_sched.c +++ b/net/ipv4/ipvs/ip_vs_sched.c @@ -184,7 +184,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) write_lock_bh(&__ip_vs_sched_lock); - if (scheduler->n_list.next != &scheduler->n_list) { + if (!list_empty(&scheduler->n_list)) { write_unlock_bh(&__ip_vs_sched_lock); ip_vs_use_count_dec(); IP_VS_ERR("register_ip_vs_scheduler(): [%s] scheduler " @@ -229,7 +229,7 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) } write_lock_bh(&__ip_vs_sched_lock); - if (scheduler->n_list.next == &scheduler->n_list) { + if (list_empty(&scheduler->n_list)) { write_unlock_bh(&__ip_vs_sched_lock); IP_VS_ERR("unregister_ip_vs_scheduler(): [%s] scheduler " "is not in the list. failed\n", scheduler->name); diff --git a/net/ipv4/ipvs/ip_vs_sed.c b/net/ipv4/ipvs/ip_vs_sed.c index 2a7d313..77663d8 100644 --- a/net/ipv4/ipvs/ip_vs_sed.c +++ b/net/ipv4/ipvs/ip_vs_sed.c @@ -138,6 +138,7 @@ static struct ip_vs_scheduler ip_vs_sed_scheduler = .name = "sed", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_sed_scheduler.n_list), .init_service = ip_vs_sed_init_svc, .done_service = ip_vs_sed_done_svc, .update_service = ip_vs_sed_update_svc, @@ -147,7 +148,6 @@ static struct ip_vs_scheduler ip_vs_sed_scheduler = static int __init ip_vs_sed_init(void) { - INIT_LIST_HEAD(&ip_vs_sed_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_sed_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_sh.c b/net/ipv4/ipvs/ip_vs_sh.c index b8fdfac..7b979e2 100644 --- a/net/ipv4/ipvs/ip_vs_sh.c +++ b/net/ipv4/ipvs/ip_vs_sh.c @@ -230,6 +230,7 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler = .name = "sh", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_sh_scheduler.n_list), .init_service = ip_vs_sh_init_svc, .done_service = ip_vs_sh_done_svc, .update_service = ip_vs_sh_update_svc, @@ -239,7 +240,6 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler = static int __init ip_vs_sh_init(void) { - INIT_LIST_HEAD(&ip_vs_sh_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_sh_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c index 45e9bd9..a652da2 100644 --- a/net/ipv4/ipvs/ip_vs_sync.c +++ b/net/ipv4/ipvs/ip_vs_sync.c @@ -904,9 +904,9 @@ int stop_sync_thread(int state) * progress of stopping the master sync daemon. */ - spin_lock(&ip_vs_sync_lock); + spin_lock_bh(&ip_vs_sync_lock); ip_vs_sync_state &= ~IP_VS_STATE_MASTER; - spin_unlock(&ip_vs_sync_lock); + spin_unlock_bh(&ip_vs_sync_lock); kthread_stop(sync_master_thread); sync_master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { diff --git a/net/ipv4/ipvs/ip_vs_wlc.c b/net/ipv4/ipvs/ip_vs_wlc.c index 772c3cb..9b0ef86 100644 --- a/net/ipv4/ipvs/ip_vs_wlc.c +++ b/net/ipv4/ipvs/ip_vs_wlc.c @@ -126,6 +126,7 @@ static struct ip_vs_scheduler ip_vs_wlc_scheduler = .name = "wlc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_wlc_scheduler.n_list), .init_service = ip_vs_wlc_init_svc, .done_service = ip_vs_wlc_done_svc, .update_service = ip_vs_wlc_update_svc, @@ -135,7 +136,6 @@ static struct ip_vs_scheduler ip_vs_wlc_scheduler = static int __init ip_vs_wlc_init(void) { - INIT_LIST_HEAD(&ip_vs_wlc_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_wlc_scheduler); } diff --git a/net/ipv4/ipvs/ip_vs_wrr.c b/net/ipv4/ipvs/ip_vs_wrr.c index 1d6932d..0d86a79 100644 --- a/net/ipv4/ipvs/ip_vs_wrr.c +++ b/net/ipv4/ipvs/ip_vs_wrr.c @@ -212,6 +212,7 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = { .name = "wrr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list), .init_service = ip_vs_wrr_init_svc, .done_service = ip_vs_wrr_done_svc, .update_service = ip_vs_wrr_update_svc, @@ -220,7 +221,6 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = { static int __init ip_vs_wrr_init(void) { - INIT_LIST_HEAD(&ip_vs_wrr_scheduler.n_list); return register_ip_vs_scheduler(&ip_vs_wrr_scheduler) ; } diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 49587a4..462a22c 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -70,7 +70,7 @@ addrtype_mt_v1(const struct sk_buff *skb, const struct net_device *in, (info->flags & IPT_ADDRTYPE_INVERT_SOURCE); if (ret && info->dest) ret &= match_type(dev, iph->daddr, info->dest) ^ - (info->flags & IPT_ADDRTYPE_INVERT_DEST); + !!(info->flags & IPT_ADDRTYPE_INVERT_DEST); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index 91537f1..6c4f11f 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -73,9 +73,13 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.all) - min + 1; } - off = *rover; if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) - off = net_random(); + off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip, + maniptype == IP_NAT_MANIP_SRC + ? tuple->dst.u.all + : tuple->src.u.all); + else + off = *rover; for (i = 0; i < range_size; i++, off++) { *portptr = htons(min + off % range_size); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 16fc6f4..cca921e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2914,6 +2914,68 @@ static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, return 0; } +static void rt_secret_reschedule(int old) +{ + struct net *net; + int new = ip_rt_secret_interval; + int diff = new - old; + + if (!diff) + return; + + rtnl_lock(); + for_each_net(net) { + int deleted = del_timer_sync(&net->ipv4.rt_secret_timer); + + if (!new) + continue; + + if (deleted) { + long time = net->ipv4.rt_secret_timer.expires - jiffies; + + if (time <= 0 || (time += diff) <= 0) + time = 0; + + net->ipv4.rt_secret_timer.expires = time; + } else + net->ipv4.rt_secret_timer.expires = new; + + net->ipv4.rt_secret_timer.expires += jiffies; + add_timer(&net->ipv4.rt_secret_timer); + } + rtnl_unlock(); +} + +static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, + struct file *filp, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int old = ip_rt_secret_interval; + int ret = proc_dointvec_jiffies(ctl, write, filp, buffer, lenp, ppos); + + rt_secret_reschedule(old); + + return ret; +} + +static int ipv4_sysctl_rt_secret_interval_strategy(ctl_table *table, + int __user *name, + int nlen, + void __user *oldval, + size_t __user *oldlenp, + void __user *newval, + size_t newlen) +{ + int old = ip_rt_secret_interval; + int ret = sysctl_jiffies(table, name, nlen, oldval, oldlenp, newval, + newlen); + + rt_secret_reschedule(old); + + return ret; +} + static ctl_table ipv4_route_table[] = { { .ctl_name = NET_IPV4_ROUTE_GC_THRESH, @@ -3048,8 +3110,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_secret_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = &ipv4_sysctl_rt_secret_interval, + .strategy = &ipv4_sysctl_rt_secret_interval_strategy, }, { .ctl_name = 0 } }; @@ -3126,10 +3188,12 @@ static __net_init int rt_secret_timer_init(struct net *net) net->ipv4.rt_secret_timer.data = (unsigned long)net; init_timer_deferrable(&net->ipv4.rt_secret_timer); - net->ipv4.rt_secret_timer.expires = - jiffies + net_random() % ip_rt_secret_interval + - ip_rt_secret_interval; - add_timer(&net->ipv4.rt_secret_timer); + if (ip_rt_secret_interval) { + net->ipv4.rt_secret_timer.expires = + jiffies + net_random() % ip_rt_secret_interval + + ip_rt_secret_interval; + add_timer(&net->ipv4.rt_secret_timer); + } return 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 383d173..8e42fbb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -989,7 +989,9 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) up->encap_rcv != NULL) { int ret; + bh_unlock_sock(sk); ret = (*up->encap_rcv)(sk, skb); + bh_lock_sock(sk); if (ret <= 0) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INDATAGRAMS, @@ -1092,7 +1094,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, if (skb1) { int ret = 0; - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) ret = udp_queue_rcv_skb(sk, skb1); else @@ -1194,7 +1196,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (sk != NULL) { int ret = 0; - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) ret = udp_queue_rcv_skb(sk, skb); else diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a7842c5..e2d3b758 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1106,13 +1106,12 @@ out: return ret; } -int ipv6_dev_get_saddr(struct net_device *dst_dev, +int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { struct ipv6_saddr_score scores[2], *score = &scores[0], *hiscore = &scores[1]; - struct net *net = dev_net(dst_dev); struct ipv6_saddr_dst dst; struct net_device *dev; int dst_type; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8d05527..f5de3f9 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -93,7 +93,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if (flags & RT6_LOOKUP_F_SRCPREF_COA) srcprefs |= IPV6_PREFER_SRC_COA; - if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, + if (ipv6_dev_get_saddr(net, + ip6_dst_idev(&rt->u.dst)->dev, &flp->fl6_dst, srcprefs, &saddr)) goto again; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 52dddc2..29c7c99 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -378,6 +378,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) arg.skb = skb; arg.cb = cb; + arg.net = net; w->args = &arg; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a4402de..0e844c2 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -934,7 +934,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, goto out_err_release; if (ipv6_addr_any(&fl->fl6_src)) { - err = ipv6_dev_get_saddr(ip6_dst_idev(*dst)->dev, + err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev, &fl->fl6_dst, sk ? inet6_sk(sk)->srcprefs : 0, &fl->fl6_src); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 741cfcd..4e5eac3 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -911,7 +911,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } else { if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif; + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if; ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } @@ -921,7 +921,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif; + src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : sk->sk_bound_dev_if; ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr); put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index beb48e3..f1c62ba 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -549,7 +549,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, override = 0; in6_ifa_put(ifp); } else { - if (ipv6_dev_get_saddr(dev, daddr, + if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5a3e87e..9af6115 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2106,7 +2106,8 @@ static inline size_t rt6_nlmsg_size(void) + nla_total_size(sizeof(struct rta_cacheinfo)); } -static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, +static int rt6_fill_node(struct net *net, + struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, int prefix, int nowait, unsigned int flags) @@ -2187,8 +2188,9 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, #endif NLA_PUT_U32(skb, RTA_IIF, iif); } else if (dst) { + struct inet6_dev *idev = ip6_dst_idev(&rt->u.dst); struct in6_addr saddr_buf; - if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, + if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, dst, 0, &saddr_buf) == 0) NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } @@ -2233,7 +2235,8 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) } else prefix = 0; - return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, + return rt6_fill_node(arg->net, + arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, prefix, 0, NLM_F_MULTI); } @@ -2299,7 +2302,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); skb->dst = &rt->u.dst; - err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, + err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { @@ -2326,7 +2329,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) if (skb == NULL) goto errout; - err = rt6_fill_node(skb, rt, NULL, NULL, 0, + err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, event, info->pid, seq, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d1477b3..a6aecf7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -379,7 +379,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, uh->source, saddr, dif))) { struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); if (buff) { - bh_lock_sock_nested(sk2); + bh_lock_sock(sk2); if (!sock_owned_by_user(sk2)) udpv6_queue_rcv_skb(sk2, buff); else @@ -387,7 +387,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, bh_unlock_sock(sk2); } } - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); else @@ -508,7 +508,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], /* deliver */ - bh_lock_sock_nested(sk); + bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); else diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8f1e054..08e4cbb 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -52,12 +52,14 @@ static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr, static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; + struct net_device *dev; dst = xfrm6_dst_lookup(0, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; - ipv6_dev_get_saddr(ip6_dst_idev(dst)->dev, + dev = ip6_dst_idev(dst)->dev; + ipv6_dev_get_saddr(dev_net(dev), dev, (struct in6_addr *)&daddr->a6, 0, (struct in6_addr *)&saddr->a6); dst_release(dst); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e1d11c9..1e97fb9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2103,6 +2103,8 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); return; } + /* update new sta with its last rx activity */ + sta->last_rx = jiffies; } /* diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 105a616..a875203 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -968,7 +968,7 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nlattr *cda[]) /* need to zero data of old helper */ memset(&help->help, 0, sizeof(help->help)); } else { - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) return -ENOMEM; } @@ -1136,16 +1136,33 @@ ctnetlink_create_conntrack(struct nlattr *cda[], ct->timeout.expires = jiffies + ct->timeout.expires * HZ; ct->status |= IPS_CONFIRMED; + rcu_read_lock(); + helper = __nf_ct_helper_find(rtuple); + if (helper) { + help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); + if (help == NULL) { + rcu_read_unlock(); + err = -ENOMEM; + goto err; + } + /* not in hash table yet so not strictly necessary */ + rcu_assign_pointer(help->helper, helper); + } + if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto err; + } } if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto err; + } } nf_ct_acct_ext_add(ct, GFP_KERNEL); @@ -1155,19 +1172,6 @@ ctnetlink_create_conntrack(struct nlattr *cda[], ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); #endif - rcu_read_lock(); - helper = __nf_ct_helper_find(rtuple); - if (helper) { - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (help == NULL) { - rcu_read_unlock(); - err = -ENOMEM; - goto err; - } - /* not in hash table yet so not strictly necessary */ - rcu_assign_pointer(help->helper, helper); - } - /* setup master conntrack: this is a confirmed expectation */ if (master_ct) { __set_bit(IPS_EXPECTED_BIT, &ct->status); diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c index d2d4565..35a9994 100644 --- a/net/rfkill/rfkill.c +++ b/net/rfkill/rfkill.c @@ -150,6 +150,8 @@ static void update_rfkill_state(struct rfkill *rfkill) * calls and handling all the red tape such as issuing notifications * if the call is successful. * + * Suspended devices are not touched at all, and -EAGAIN is returned. + * * Note that the @force parameter cannot override a (possibly cached) * state of RFKILL_STATE_HARD_BLOCKED. Any device making use of * RFKILL_STATE_HARD_BLOCKED implements either get_state() or @@ -168,6 +170,9 @@ static int rfkill_toggle_radio(struct rfkill *rfkill, int retval = 0; enum rfkill_state oldstate, newstate; + if (unlikely(rfkill->dev.power.power_state.event & PM_EVENT_SLEEP)) + return -EBUSY; + oldstate = rfkill->state; if (rfkill->get_state && !force && @@ -214,7 +219,7 @@ static int rfkill_toggle_radio(struct rfkill *rfkill, * * This function toggles the state of all switches of given type, * unless a specific switch is claimed by userspace (in which case, - * that switch is left alone). + * that switch is left alone) or suspended. */ void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state) { @@ -239,8 +244,8 @@ EXPORT_SYMBOL(rfkill_switch_all); /** * rfkill_epo - emergency power off all transmitters * - * This kicks all rfkill devices to RFKILL_STATE_SOFT_BLOCKED, ignoring - * everything in its path but rfkill_mutex and rfkill->mutex. + * This kicks all non-suspended rfkill devices to RFKILL_STATE_SOFT_BLOCKED, + * ignoring everything in its path but rfkill_mutex and rfkill->mutex. */ void rfkill_epo(void) { @@ -458,13 +463,14 @@ static int rfkill_resume(struct device *dev) if (dev->power.power_state.event != PM_EVENT_ON) { mutex_lock(&rfkill->mutex); + dev->power.power_state.event = PM_EVENT_ON; + /* restore radio state AND notify everybody */ rfkill_toggle_radio(rfkill, rfkill->state, 1); mutex_unlock(&rfkill->mutex); } - dev->power.power_state = PMSG_ON; return 0; } #else diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/ar-accept.c index bdfb774..77228f2 100644 --- a/net/rxrpc/ar-accept.c +++ b/net/rxrpc/ar-accept.c @@ -100,7 +100,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, trans = rxrpc_get_transport(local, peer, GFP_NOIO); rxrpc_put_peer(peer); - if (!trans) { + if (IS_ERR(trans)) { _debug("no trans"); ret = -EBUSY; goto error; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 26c7e1f..9974b3f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -751,7 +751,7 @@ static int tca_action_flush(struct nlattr *nla, struct nlmsghdr *n, u32 pid) struct nlattr *tb[TCA_ACT_MAX+1]; struct nlattr *kind; struct tc_action *a = create_a(0); - int err = -EINVAL; + int err = -ENOMEM; if (a == NULL) { printk("tca_action_flush: couldnt create tc_action\n"); @@ -762,7 +762,7 @@ static int tca_action_flush(struct nlattr *nla, struct nlmsghdr *n, u32 pid) if (!skb) { printk("tca_action_flush: failed skb alloc\n"); kfree(a); - return -ENOBUFS; + return err; } b = skb_tail_pointer(skb); @@ -790,6 +790,8 @@ static int tca_action_flush(struct nlattr *nla, struct nlmsghdr *n, u32 pid) err = a->ops->walk(skb, &dcb, RTM_DELACTION, a); if (err < 0) goto nla_put_failure; + if (err == 0) + goto noflush_out; nla_nest_end(skb, nest); @@ -807,6 +809,7 @@ nla_put_failure: nlmsg_failure: module_put(a->ops->owner); err_out: +noflush_out: kfree_skb(skb); kfree(a); return err; @@ -824,8 +827,10 @@ tca_action_gd(struct nlattr *nla, struct nlmsghdr *n, u32 pid, int event) return ret; if (event == RTM_DELACTION && n->nlmsg_flags&NLM_F_ROOT) { - if (tb[0] != NULL && tb[1] == NULL) - return tca_action_flush(tb[0], n, pid); + if (tb[1] != NULL) + return tca_action_flush(tb[1], n, pid); + else + return -EINVAL; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d2b6f54..5cafdd4 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -280,7 +280,7 @@ replay: if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { spin_lock_bh(root_lock); *back = tp->next; - spin_lock_bh(root_lock); + spin_unlock_bh(root_lock); tfilter_notify(skb, n, tp, fh, RTM_DELTFILTER); tcf_destroy(tp); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index ba1d121..ef0efec 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -27,6 +27,7 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> +#include <linux/lockdep.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -183,6 +184,21 @@ EXPORT_SYMBOL(unregister_qdisc); (root qdisc, all its children, children of children etc.) */ +struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) +{ + struct Qdisc *q; + + if (!(root->flags & TCQ_F_BUILTIN) && + root->handle == handle) + return root; + + list_for_each_entry(q, &root->list, list) { + if (q->handle == handle) + return q; + } + return NULL; +} + struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { unsigned int i; @@ -191,16 +207,11 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) struct netdev_queue *txq = netdev_get_tx_queue(dev, i); struct Qdisc *q, *txq_root = txq->qdisc_sleeping; - if (!(txq_root->flags & TCQ_F_BUILTIN) && - txq_root->handle == handle) - return txq_root; - - list_for_each_entry(q, &txq_root->list, list) { - if (q->handle == handle) - return q; - } + q = qdisc_match_from_root(txq_root, handle); + if (q) + return q; } - return NULL; + return qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle); } static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) @@ -416,7 +427,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) wd->qdisc->flags &= ~TCQ_F_THROTTLED; smp_wmb(); - __netif_schedule(wd->qdisc); + __netif_schedule(qdisc_root(wd->qdisc)); return HRTIMER_NORESTART; } @@ -627,11 +638,8 @@ static void notify_and_destroy(struct sk_buff *skb, struct nlmsghdr *n, u32 clid if (new || old) qdisc_notify(skb, n, clid, old, new); - if (old) { - spin_lock_bh(&old->q.lock); + if (old) qdisc_destroy(old); - spin_unlock_bh(&old->q.lock); - } } /* Graft qdisc "new" to class "classid" of qdisc "parent" or @@ -697,6 +705,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, return err; } +/* lockdep annotation is needed for ingress; egress gets it only for name */ +static struct lock_class_key qdisc_tx_lock; +static struct lock_class_key qdisc_rx_lock; + /* Allocate and initialize new qdisc. @@ -757,6 +769,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); + lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); @@ -764,6 +777,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, if (handle == 0) goto err_out3; } + lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); } sch->handle = handle; @@ -908,7 +922,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -ENOENT; q = qdisc_leaf(p, clid); } else { /* ingress */ - q = dev->rx_queue.qdisc; + q = dev->rx_queue.qdisc_sleeping; } } else { struct netdev_queue *dev_queue; @@ -978,7 +992,7 @@ replay: return -ENOENT; q = qdisc_leaf(p, clid); } else { /*ingress */ - q = dev->rx_queue.qdisc; + q = dev->rx_queue.qdisc_sleeping; } } else { struct netdev_queue *dev_queue; @@ -1074,20 +1088,13 @@ create_n_graft: } graft: - if (1) { - spinlock_t *root_lock; - - err = qdisc_graft(dev, p, skb, n, clid, q, NULL); - if (err) { - if (q) { - root_lock = qdisc_root_lock(q); - spin_lock_bh(root_lock); - qdisc_destroy(q); - spin_unlock_bh(root_lock); - } - return err; - } + err = qdisc_graft(dev, p, skb, n, clid, q, NULL); + if (err) { + if (q) + qdisc_destroy(q); + return err; } + return 0; } @@ -1529,11 +1536,11 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) t = 0; dev_queue = netdev_get_tx_queue(dev, 0); - if (tc_dump_tclass_root(dev_queue->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) goto done; dev_queue = &dev->rx_queue; - if (tc_dump_tclass_root(dev_queue->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0) goto done; done: diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 4e261ce..47ef492 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -654,7 +654,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) } sch->flags &= ~TCQ_F_THROTTLED; - __netif_schedule(sch); + __netif_schedule(qdisc_root(sch)); return HRTIMER_NORESTART; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 7cf83b3..c3ed4d4 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -518,14 +518,17 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -/* this is the rcu callback function to clean up a qdisc when there - * are no further references to it */ - -static void __qdisc_destroy(struct rcu_head *head) +void qdisc_destroy(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, q_rcu); const struct Qdisc_ops *ops = qdisc->ops; + if (qdisc->flags & TCQ_F_BUILTIN || + !atomic_dec_and_test(&qdisc->refcnt)) + return; + + if (qdisc->parent) + list_del(&qdisc->list); + #ifdef CONFIG_NET_SCHED qdisc_put_stab(qdisc->stab); #endif @@ -542,20 +545,6 @@ static void __qdisc_destroy(struct rcu_head *head) kfree((char *) qdisc - qdisc->padded); } - -/* Under qdisc_lock(qdisc) and BH! */ - -void qdisc_destroy(struct Qdisc *qdisc) -{ - if (qdisc->flags & TCQ_F_BUILTIN || - !atomic_dec_and_test(&qdisc->refcnt)) - return; - - if (qdisc->parent) - list_del(&qdisc->list); - - call_rcu(&qdisc->q_rcu, __qdisc_destroy); -} EXPORT_SYMBOL(qdisc_destroy); static bool dev_all_qdisc_sleeping_noop(struct net_device *dev) @@ -597,6 +586,9 @@ static void transition_one_qdisc(struct net_device *dev, struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; int *need_watchdog_p = _need_watchdog; + if (!(new_qdisc->flags & TCQ_F_BUILTIN)) + clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); + rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p && new_qdisc != &noqueue_qdisc) *need_watchdog_p = 1; @@ -640,6 +632,9 @@ static void dev_deactivate_queue(struct net_device *dev, if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); + if (!(qdisc->flags & TCQ_F_BUILTIN)) + set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); + dev_queue->qdisc = qdisc_default; qdisc_reset(qdisc); @@ -647,7 +642,7 @@ static void dev_deactivate_queue(struct net_device *dev, } } -static bool some_qdisc_is_running(struct net_device *dev, int lock) +static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -658,16 +653,15 @@ static bool some_qdisc_is_running(struct net_device *dev, int lock) int val; dev_queue = netdev_get_tx_queue(dev, i); - q = dev_queue->qdisc; + q = dev_queue->qdisc_sleeping; root_lock = qdisc_lock(q); - if (lock) - spin_lock_bh(root_lock); + spin_lock_bh(root_lock); - val = test_bit(__QDISC_STATE_RUNNING, &q->state); + val = (test_bit(__QDISC_STATE_RUNNING, &q->state) || + test_bit(__QDISC_STATE_SCHED, &q->state)); - if (lock) - spin_unlock_bh(root_lock); + spin_unlock_bh(root_lock); if (val) return true; @@ -677,8 +671,6 @@ static bool some_qdisc_is_running(struct net_device *dev, int lock) void dev_deactivate(struct net_device *dev) { - bool running; - netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc); @@ -688,25 +680,8 @@ void dev_deactivate(struct net_device *dev) synchronize_rcu(); /* Wait for outstanding qdisc_run calls. */ - do { - while (some_qdisc_is_running(dev, 0)) - yield(); - - /* - * Double-check inside queue lock to ensure that all effects - * of the queue run are visible when we return. - */ - running = some_qdisc_is_running(dev, 1); - - /* - * The running flag should never be set at this point because - * we've already set dev->qdisc to noop_qdisc *inside* the same - * pair of spin locks. That is, if any qdisc_run starts after - * our initial test it should see the noop_qdisc and then - * clear the RUNNING bit before dropping the queue lock. So - * if it is set here then we've found a bug. - */ - } while (WARN_ON_ONCE(running)); + while (some_qdisc_is_busy(dev)) + yield(); } static void dev_init_scheduler_queue(struct net_device *dev, @@ -735,14 +710,10 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { - spinlock_t *root_lock = qdisc_lock(qdisc); - dev_queue->qdisc = qdisc_default; dev_queue->qdisc_sleeping = qdisc_default; - spin_lock_bh(root_lock); qdisc_destroy(qdisc); - spin_unlock_bh(root_lock); } } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index be35422..0df0df2 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -577,7 +577,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.drops++; cl->qstats.drops++; } - return NET_XMIT_DROP; + return ret; } else { cl->bstats.packets += skb_is_gso(skb)?skb_shinfo(skb)->gso_segs:1; @@ -623,7 +623,7 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.drops++; cl->qstats.drops++; } - return NET_XMIT_DROP; + return ret; } else htb_activate(q, cl); @@ -1279,7 +1279,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) /* delete from hash and active; remainder in destroy_class */ qdisc_class_hash_remove(&q->clhash, &cl->common); - cl->parent->children--; + if (cl->parent) + cl->parent->children--; if (cl->prio_activity) htb_deactivate(q, cl); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index eac1976..a6697c6 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -113,11 +113,11 @@ prio_requeue(struct sk_buff *skb, struct Qdisc* sch) if ((ret = qdisc->ops->requeue(skb, qdisc)) == NET_XMIT_SUCCESS) { sch->q.qlen++; sch->qstats.requeues++; - return 0; + return NET_XMIT_SUCCESS; } if (net_xmit_drop_count(ret)) sch->qstats.drops++; - return NET_XMIT_DROP; + return ret; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 7d3b7ff..94c6159 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -123,15 +123,8 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) struct tbf_sched_data *q = qdisc_priv(sch); int ret; - if (qdisc_pkt_len(skb) > q->max_size) { - sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_ACT - if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) -#endif - kfree_skb(skb); - - return NET_XMIT_DROP; - } + if (qdisc_pkt_len(skb) > q->max_size) + return qdisc_reshape_fail(skb, sch); ret = qdisc_enqueue(skb, q->qdisc); if (ret != 0) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 483a01d..47f91af 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -319,7 +319,8 @@ static void sctp_v6_get_saddr(struct sctp_sock *sk, __func__, asoc, dst, NIP6(daddr->v6.sin6_addr)); if (!asoc) { - ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, + ipv6_dev_get_saddr(sock_net(sctp_opt2sk(sk)), + dst ? ip6_dst_idev(dst)->dev : NULL, &daddr->v6.sin6_addr, inet6_sk(&sk->inet.sk)->srcprefs, &saddr->v6.sin6_addr); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0326d30..0747d8a 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -85,7 +85,7 @@ static struct top_srv topsrv = { 0 }; static u32 htohl(u32 in, int swap) { - return swap ? (u32)___constant_swab32(in) : in; + return swap ? swab32(in) : in; } /** diff --git a/net/wireless/wext.c b/net/wireless/wext.c index df5b388..d98ffb7 100644 --- a/net/wireless/wext.c +++ b/net/wireless/wext.c @@ -1277,6 +1277,7 @@ static int rtnetlink_fill_iwinfo(struct sk_buff *skb, struct net_device *dev, r->ifi_flags = dev_get_flags(dev); r->ifi_change = 0; /* Wireless changes don't affect those flags */ + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); /* Add the wireless events in the netlink packet */ NLA_PUT(skb, IFLA_WIRELESS, event_len, event); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 3f964db..ac25b4c 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -112,16 +112,13 @@ error_nolock: int xfrm_output_resume(struct sk_buff *skb, int err) { while (likely((err = xfrm_output_one(skb, err)) == 0)) { - struct xfrm_state *x; - nf_reset(skb); err = skb->dst->ops->local_out(skb); if (unlikely(err != 1)) goto out; - x = skb->dst->xfrm; - if (!x) + if (!skb->dst->xfrm) return dst_output(skb); err = nf_hook(skb->dst->ops->family, |