diff options
author | Rafael J. Wysocki <rjw@sisk.pl> | 2011-12-21 21:59:45 +0100 |
---|---|---|
committer | Rafael J. Wysocki <rjw@sisk.pl> | 2011-12-21 21:59:45 +0100 |
commit | b00f4dc5ff022cb9cbaffd376d9454d7fa1e496f (patch) | |
tree | 40f1b232e2f1e8ac365317a14fdcbcb331722b46 /net | |
parent | 1eac8111e0763853266a171ce11214da3a347a0a (diff) | |
parent | b9e26dfdad5a4f9cbdaacafac6998614cc9c41bc (diff) | |
download | op-kernel-dev-b00f4dc5ff022cb9cbaffd376d9454d7fa1e496f.zip op-kernel-dev-b00f4dc5ff022cb9cbaffd376d9454d7fa1e496f.tar.gz |
Merge branch 'master' into pm-sleep
* master: (848 commits)
SELinux: Fix RCU deref check warning in sel_netport_insert()
binary_sysctl(): fix memory leak
mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
ipmi_watchdog: restore settings when BMC reset
oom: fix integer overflow of points in oom_badness
memcg: keep root group unchanged if creation fails
nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
nilfs2: unbreak compat ioctl
cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
evm: prevent racing during tfm allocation
evm: key must be set once during initialization
mmc: vub300: fix type of firmware_rom_wait_states module parameter
Revert "mmc: enable runtime PM by default"
mmc: sdhci: remove "state" argument from sdhci_suspend_host
x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
IB/qib: Correct sense on freectxts increment and decrement
RDMA/cma: Verify private data length
cgroups: fix a css_set not found bug in cgroup_attach_proc
oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
...
Conflicts:
kernel/cgroup_freezer.c
Diffstat (limited to 'net')
60 files changed, 514 insertions, 324 deletions
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index c7aafc7..5f09a57 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -245,9 +245,11 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (tt_global_entry) { /* This node is probably going to update its tt table */ tt_global_entry->orig_node->tt_poss_change = true; - /* The global entry has to be marked as PENDING and has to be + /* The global entry has to be marked as ROAMING and has to be * kept for consistency purpose */ - tt_global_entry->flags |= TT_CLIENT_PENDING; + tt_global_entry->flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + send_roam_adv(bat_priv, tt_global_entry->addr, tt_global_entry->orig_node); } @@ -694,6 +696,7 @@ void tt_global_del(struct bat_priv *bat_priv, const char *message, bool roaming) { struct tt_global_entry *tt_global_entry = NULL; + struct tt_local_entry *tt_local_entry = NULL; tt_global_entry = tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) @@ -701,15 +704,29 @@ void tt_global_del(struct bat_priv *bat_priv, if (tt_global_entry->orig_node == orig_node) { if (roaming) { - tt_global_entry->flags |= TT_CLIENT_ROAM; - tt_global_entry->roam_at = jiffies; - goto out; + /* if we are deleting a global entry due to a roam + * event, there are two possibilities: + * 1) the client roamed from node A to node B => we mark + * it with TT_CLIENT_ROAM, we start a timer and we + * wait for node B to claim it. In case of timeout + * the entry is purged. + * 2) the client roamed to us => we can directly delete + * the global entry, since it is useless now. */ + tt_local_entry = tt_local_hash_find(bat_priv, + tt_global_entry->addr); + if (!tt_local_entry) { + tt_global_entry->flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + goto out; + } } _tt_global_del(bat_priv, tt_global_entry, message); } out: if (tt_global_entry) tt_global_entry_free_ref(tt_global_entry); + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); } void tt_global_del_orig(struct bat_priv *bat_priv, diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 91bcd3a..1eea820 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -79,17 +79,12 @@ static struct bnep_session *__bnep_get_session(u8 *dst) static void __bnep_link_session(struct bnep_session *s) { - /* It's safe to call __module_get() here because sessions are added - by the socket layer which has to hold the reference to this module. - */ - __module_get(THIS_MODULE); list_add(&s->list, &bnep_session_list); } static void __bnep_unlink_session(struct bnep_session *s) { list_del(&s->list); - module_put(THIS_MODULE); } static int bnep_send(struct bnep_session *s, void *data, size_t len) @@ -530,6 +525,7 @@ static int bnep_session(void *arg) up_write(&bnep_session_sem); free_netdev(dev); + module_put_and_exit(0); return 0; } @@ -616,9 +612,11 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) __bnep_link_session(s); + __module_get(THIS_MODULE); s->task = kthread_run(bnep_session, s, "kbnepd %s", dev->name); if (IS_ERR(s->task)) { /* Session thread start failed, gotta cleanup. */ + module_put(THIS_MODULE); unregister_netdev(dev); __bnep_unlink_session(s); err = PTR_ERR(s->task); diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 7d00ddf..5a6e634 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -67,14 +67,12 @@ static struct cmtp_session *__cmtp_get_session(bdaddr_t *bdaddr) static void __cmtp_link_session(struct cmtp_session *session) { - __module_get(THIS_MODULE); list_add(&session->list, &cmtp_session_list); } static void __cmtp_unlink_session(struct cmtp_session *session) { list_del(&session->list); - module_put(THIS_MODULE); } static void __cmtp_copy_session(struct cmtp_session *session, struct cmtp_conninfo *ci) @@ -327,6 +325,7 @@ static int cmtp_session(void *arg) up_write(&cmtp_session_sem); kfree(session); + module_put_and_exit(0); return 0; } @@ -376,9 +375,11 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) __cmtp_link_session(session); + __module_get(THIS_MODULE); session->task = kthread_run(cmtp_session, session, "kcmtpd_ctr_%d", session->num); if (IS_ERR(session->task)) { + module_put(THIS_MODULE); err = PTR_ERR(session->task); goto unlink; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d7d96b6..643a41b 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -545,7 +545,7 @@ static void hci_setup(struct hci_dev *hdev) { hci_setup_event_mask(hdev); - if (hdev->lmp_ver > 1) + if (hdev->hci_ver > 1) hci_send_cmd(hdev, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL); if (hdev->features[6] & LMP_SIMPLE_PAIR) { diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e5f9ece3..a1daf82 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -18,6 +18,7 @@ #include <net/sock.h> #include "br_private.h" +#include "br_private_stp.h" static inline size_t br_nlmsg_size(void) { @@ -188,6 +189,11 @@ static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) p->state = new_state; br_log_state(p); + + spin_lock_bh(&p->br->lock); + br_port_state_selection(p->br); + spin_unlock_bh(&p->br->lock); + br_ifinfo_notify(RTM_NEWLINK, p); return 0; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index ad0a3f7..dd147d7 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -399,25 +399,24 @@ void br_port_state_selection(struct net_bridge *br) struct net_bridge_port *p; unsigned int liveports = 0; - /* Don't change port states if userspace is handling STP */ - if (br->stp_enabled == BR_USER_STP) - return; - list_for_each_entry(p, &br->port_list, list) { if (p->state == BR_STATE_DISABLED) continue; - if (p->port_no == br->root_port) { - p->config_pending = 0; - p->topology_change_ack = 0; - br_make_forwarding(p); - } else if (br_is_designated_port(p)) { - del_timer(&p->message_age_timer); - br_make_forwarding(p); - } else { - p->config_pending = 0; - p->topology_change_ack = 0; - br_make_blocking(p); + /* Don't change port states if userspace is handling STP */ + if (br->stp_enabled != BR_USER_STP) { + if (p->port_no == br->root_port) { + p->config_pending = 0; + p->topology_change_ack = 0; + br_make_forwarding(p); + } else if (br_is_designated_port(p)) { + del_timer(&p->message_age_timer); + br_make_forwarding(p); + } else { + p->config_pending = 0; + p->topology_change_ack = 0; + br_make_blocking(p); + } } if (p->state == BR_STATE_FORWARDING) diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index f399211..d3ca87b 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -136,20 +136,21 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt) { - int tmp; u16 chks; u16 len; + __le16 data; + struct cffrml *this = container_obj(layr); if (this->dofcs) { chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff); - tmp = cpu_to_le16(chks); - cfpkt_add_trail(pkt, &tmp, 2); + data = cpu_to_le16(chks); + cfpkt_add_trail(pkt, &data, 2); } else { cfpkt_pad_trail(pkt, 2); } len = cfpkt_getlen(pkt); - tmp = cpu_to_le16(len); - cfpkt_add_head(pkt, &tmp, 2); + data = cpu_to_le16(len); + cfpkt_add_head(pkt, &data, 2); cfpkt_info(pkt)->hdr_len += 2; if (cfpkt_erroneous(pkt)) { pr_err("Packet is erroneous!\n"); diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 42599e3..3a94eae 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -477,7 +477,6 @@ int crush_do_rule(struct crush_map *map, int i, j; int numrep; int firstn; - int rc = -1; BUG_ON(ruleno >= map->max_rules); @@ -491,23 +490,18 @@ int crush_do_rule(struct crush_map *map, * that this may or may not correspond to the specific types * referenced by the crush rule. */ - if (force >= 0) { - if (force >= map->max_devices || - map->device_parents[force] == 0) { - /*dprintk("CRUSH: forcefed device dne\n");*/ - rc = -1; /* force fed device dne */ - goto out; - } - if (!is_out(map, weight, force, x)) { - while (1) { - force_context[++force_pos] = force; - if (force >= 0) - force = map->device_parents[force]; - else - force = map->bucket_parents[-1-force]; - if (force == 0) - break; - } + if (force >= 0 && + force < map->max_devices && + map->device_parents[force] != 0 && + !is_out(map, weight, force, x)) { + while (1) { + force_context[++force_pos] = force; + if (force >= 0) + force = map->device_parents[force]; + else + force = map->bucket_parents[-1-force]; + if (force == 0) + break; } } @@ -600,10 +594,7 @@ int crush_do_rule(struct crush_map *map, BUG_ON(1); } } - rc = result_len; - -out: - return rc; + return result_len; } diff --git a/net/core/dev.c b/net/core/dev.c index 6ba50a1..5a13edf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1396,7 +1396,7 @@ rollback: for_each_net(net) { for_each_netdev(net, dev) { if (dev == last) - break; + goto outroll; if (dev->flags & IFF_UP) { nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); @@ -1407,6 +1407,7 @@ rollback: } } +outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -4282,6 +4283,12 @@ static int dev_seq_open(struct inode *inode, struct file *file) sizeof(struct dev_iter_state)); } +int dev_seq_open_ops(struct inode *inode, struct file *file, + const struct seq_operations *ops) +{ + return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state)); +} + static const struct file_operations dev_seq_fops = { .owner = THIS_MODULE, .open = dev_seq_open, diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 277faef..febba51 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -696,8 +696,7 @@ static const struct seq_operations dev_mc_seq_ops = { static int dev_mc_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); + return dev_seq_open_ops(inode, file, &dev_mc_seq_ops); } static const struct file_operations dev_mc_seq_fops = { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 039d51e..5ac07d3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2397,7 +2397,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 182236b..9b570a6 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -26,10 +26,11 @@ * but then some measure against one socket starving all other sockets * would be needed. * - * It was 128 by default. Experiments with real servers show, that + * The minimum value of it is 128. Experiments with real servers show that * it is absolutely not enough even at 100conn/sec. 256 cures most - * of problems. This value is adjusted to 128 for very small machines - * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). + * of problems. + * This value is adjusted to 128 for low memory machines, + * and it will increase in proportion to the memory of machine. * Note : Dont forget somaxconn that may limit backlog too. */ int sysctl_max_syn_backlog = 256; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 025233d..925991a 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -19,6 +19,7 @@ static int __init net_secret_init(void) } late_initcall(net_secret_init); +#ifdef CONFIG_INET static u32 seq_scale(u32 seq) { /* @@ -33,6 +34,7 @@ static u32 seq_scale(u32 seq) */ return seq + (ktime_to_ns(ktime_get_real()) >> 6); } +#endif #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 18a3ceb..3c30ee4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2230,7 +2230,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than - * the length of the skb, from tgt to skb. Returns number bytes shifted. + * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 90a919a..3f4e541 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -111,6 +111,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { + err = PTR_ERR(rt); rt = NULL; goto failure; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index a77d161..94f4ec0 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -112,7 +112,7 @@ static unsigned long dn_rt_deadline; static int dn_dst_gc(struct dst_ops *ops); static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst); +static unsigned int dn_dst_mtu(const struct dst_entry *dst); static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); @@ -135,7 +135,7 @@ static struct dst_ops dn_dst_ops = { .gc = dn_dst_gc, .check = dn_dst_check, .default_advmss = dn_dst_default_advmss, - .default_mtu = dn_dst_default_mtu, + .mtu = dn_dst_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = dn_dst_destroy, .negative_advice = dn_dst_negative_advice, @@ -825,9 +825,11 @@ static unsigned int dn_dst_default_advmss(const struct dst_entry *dst) return dn_mss_from_pmtu(dst->dev, dst_mtu(dst)); } -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst) +static unsigned int dn_dst_mtu(const struct dst_entry *dst) { - return dst->dev->mtu; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c index 67f691b..d9c150c 100644 --- a/net/decnet/dn_timer.c +++ b/net/decnet/dn_timer.c @@ -36,16 +36,13 @@ static void dn_slow_timer(unsigned long arg); void dn_start_slow_timer(struct sock *sk) { - sk->sk_timer.expires = jiffies + SLOW_INTERVAL; - sk->sk_timer.function = dn_slow_timer; - sk->sk_timer.data = (unsigned long)sk; - - add_timer(&sk->sk_timer); + setup_timer(&sk->sk_timer, dn_slow_timer, (unsigned long)sk); + sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); } void dn_stop_slow_timer(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } static void dn_slow_timer(unsigned long arg) @@ -53,12 +50,10 @@ static void dn_slow_timer(unsigned long arg) struct sock *sk = (struct sock *)arg; struct dn_scp *scp = DN_SK(sk); - sock_hold(sk); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - sk->sk_timer.expires = jiffies + HZ / 10; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10); goto out; } @@ -100,9 +95,7 @@ static void dn_slow_timer(unsigned long arg) scp->keepalive_fxn(sk); } - sk->sk_timer.expires = jiffies + SLOW_INTERVAL; - - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); out: bh_unlock_sock(sk); sock_put(sk); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c6b5092..65f01dc 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if ((new_value == 0) && (old_value != 0)) + rt_cache_flush(net, 0); } return ret; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c7472ef..b2ca095 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1716,7 +1716,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (err) { int j; - pmc->sfcount[sfmode]--; + if (!delta) + pmc->sfcount[sfmode]--; for (j=0; j<i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 68e8ac5..ccee270 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,9 +108,6 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops->name); } - if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -125,16 +122,23 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, + * hence this needs to be included regardless of socket family. + */ + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); + if (ext & (1 << (INET_DIAG_TCLASS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); + ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, &np->rcv_saddr); ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, &np->daddr); - if (ext & (1 << (INET_DIAG_TCLASS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); } #endif diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c..29a07b6 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 05d20cc..1e60f76 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,7 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; - iph->daddr = nexthop; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 065effd..0b2e732 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -285,6 +285,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip_tunnel_link(ipn, nt); return nt; @@ -759,7 +761,6 @@ static int ipip_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -825,6 +826,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) static int __net_init ipip_init_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); + struct ip_tunnel *t; int err; ipn->tunnels[0] = ipn->tunnels_wc; @@ -848,6 +850,9 @@ static int __net_init ipip_init_net(struct net *net) if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(ipn->fb_tunnel_dev); + + strcpy(t->parms.name, ipn->fb_tunnel_dev->name); return 0; err_reg_dev: diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 9899619..4f47e06 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -64,7 +64,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && - pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), + 0, GFP_ATOMIC)) return -1; return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1dfc18a..f19f218 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0c74da8..46af623 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,7 +112,7 @@ #include <net/secure_seq.h> #define RT_FL_TOS(oldflp4) \ - ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) + ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) #define IP_MAX_MTU 0xFFF0 @@ -131,6 +131,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; +static int redirect_genid; /* * Interface to generic destination cache. @@ -138,7 +139,7 @@ static int rt_chain_length_max __read_mostly = 20; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_default_mtu(const struct dst_entry *dst); +static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -193,7 +194,7 @@ static struct dst_ops ipv4_dst_ops = { .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, - .default_mtu = ipv4_default_mtu, + .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, @@ -416,9 +417,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) else { struct rtable *r = v; struct neighbour *n; - int len; + int len, HHUptod; + rcu_read_lock(); n = dst_get_neighbour(&r->dst); + HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; + rcu_read_unlock(); + seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->dst.dev ? r->dst.dev->name : "*", @@ -432,7 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, -1, - (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0, + HHUptod, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -837,6 +842,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); + redirect_genid++; } /* @@ -1304,7 +1310,7 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } -static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; @@ -1315,21 +1321,19 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) rt->rt_gateway = peer->redirect_learned.a4; n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); + if (IS_ERR(n)) { + rt->rt_gateway = orig_gw; + return; + } old_n = xchg(&rt->dst._neighbour, n); if (old_n) neigh_release(old_n); - if (!n || !(n->nud_state & NUD_VALID)) { - if (n) - neigh_event_send(n, NULL); - rt->rt_gateway = orig_gw; - return -EAGAIN; + if (!(n->nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); } else { rt->rt_flags |= RTCF_REDIRECTED; call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } - return 0; } /* called in rcu_read_lock() section */ @@ -1391,8 +1395,10 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, peer = rt->peer; if (peer) { - if (peer->redirect_learned.a4 != new_gw) { + if (peer->redirect_learned.a4 != new_gw || + peer->redirect_genid != redirect_genid) { peer->redirect_learned.a4 = new_gw; + peer->redirect_genid = redirect_genid; atomic_inc(&__rt_peer_genid); } check_peer_redir(&rt->dst, peer); @@ -1685,12 +1691,8 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } -static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +static void ipv4_validate_peer(struct rtable *rt) { - struct rtable *rt = (struct rtable *) dst; - - if (rt_is_expired(rt)) - return NULL; if (rt->rt_peer_genid != rt_peer_genid()) { struct inet_peer *peer; @@ -1699,17 +1701,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) peer = rt->peer; if (peer) { - check_peer_pmtu(dst, peer); + check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - if (check_peer_redir(dst, peer)) - return NULL; - } + peer->redirect_learned.a4 != rt->rt_gateway) + check_peer_redir(&rt->dst, peer); } rt->rt_peer_genid = rt_peer_genid(); } +} + +static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +{ + struct rtable *rt = (struct rtable *) dst; + + if (rt_is_expired(rt)) + return NULL; + ipv4_validate_peer(rt); return dst; } @@ -1814,12 +1825,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return advmss; } -static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_mtu(const struct dst_entry *dst) { - unsigned int mtu = dst->dev->mtu; + const struct rtable *rt = (const struct rtable *) dst; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu && rt_is_output_route(rt)) + return mtu; + + mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - const struct rtable *rt = (const struct rtable *) dst; if (rt->rt_gateway != rt->rt_dst && mtu > 576) mtu = 576; @@ -1852,6 +1868,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, dst_init_metrics(&rt->dst, peer->metrics, false); check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; @@ -2357,6 +2375,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + ipv4_validate_peer(rth); if (noref) { dst_use_noref(&rth->dst, jiffies); skb_dst_set_noref(skb, &rth->dst); @@ -2415,11 +2434,11 @@ EXPORT_SYMBOL(ip_route_input_common); static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, __be32 orig_daddr, __be32 orig_saddr, - int orig_oif, struct net_device *dev_out, + int orig_oif, __u8 orig_rtos, + struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; - u32 tos = RT_FL_TOS(fl4); struct in_device *in_dev; u16 type = res->type; struct rtable *rth; @@ -2470,7 +2489,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_genid = rt_genid(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; - rth->rt_key_tos = tos; + rth->rt_key_tos = orig_rtos; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; rth->rt_route_iif = 0; @@ -2520,7 +2539,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) { struct net_device *dev_out = NULL; - u32 tos = RT_FL_TOS(fl4); + __u8 tos = RT_FL_TOS(fl4); unsigned int flags = 0; struct fib_result res; struct rtable *rth; @@ -2696,7 +2715,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) make_route: rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif, - dev_out, flags); + tos, dev_out, flags); if (!IS_ERR(rth)) { unsigned int hash; @@ -2732,6 +2751,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) (IPTOS_RT_MASK | RTO_ONLINK)) && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + ipv4_validate_peer(rth); dst_use(&rth->dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); @@ -2755,9 +2775,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } -static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -2775,7 +2797,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, - .default_mtu = ipv4_blackhole_default_mtu, + .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ab0966d..5a65eea 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1164,7 +1164,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -1186,9 +1186,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; /* @@ -1197,14 +1198,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, len); + msg->msg_iov, copied); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), @@ -1233,7 +1234,7 @@ try_again: if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cf88df8..36806de 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1805,7 +1805,8 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) return ERR_PTR(-EACCES); /* Add default multicast route */ - addrconf_add_mroute(dev); + if (!(dev->flags & IFF_LOOPBACK)) + addrconf_add_mroute(dev); /* Add link local route */ addrconf_add_lroute(dev); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fee46d5..1567fb1 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -85,7 +85,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, * request_sock (formerly open request) hash tables. */ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, - const u32 rnd, const u16 synq_hsize) + const u32 rnd, const u32 synq_hsize) { u32 c; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c99e3ee..26cb08c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -503,7 +503,7 @@ done: goto e_inval; if (val > 255 || val < -1) goto e_inval; - np->mcast_hops = val; + np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val); retv = 0; break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 44e5b7f..0cb78d7 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1571,7 +1571,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, } if (!rt->rt6i_peer) rt6_bind_peer(rt, 1); - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4484648..f792b34 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -186,7 +186,6 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8473016..b582a0a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -77,7 +77,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_default_mtu(const struct dst_entry *dst); +static unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -144,7 +144,7 @@ static struct dst_ops ip6_dst_ops_template = { .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, - .default_mtu = ip6_default_mtu, + .mtu = ip6_mtu, .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, @@ -155,9 +155,11 @@ static struct dst_ops ip6_dst_ops_template = { .neigh_lookup = ip6_neigh_lookup, }; -static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -175,7 +177,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, - .default_mtu = ip6_blackhole_default_mtu, + .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .cow_metrics = ip6_rt_blackhole_cow_metrics, @@ -726,7 +728,7 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, int attempts = !in_softirq(); if (!(rt->rt6i_flags&RTF_GATEWAY)) { - if (rt->rt6i_dst.plen != 128 && + if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; ipv6_addr_copy(&rt->rt6i_gateway, daddr); @@ -1041,10 +1043,15 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_mtu(const struct dst_entry *dst) { - unsigned int mtu = IPV6_MIN_MTU; struct inet6_dev *idev; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu) + return mtu; + + mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index a7a1860..96f3623 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -263,6 +263,8 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip6_tunnel_link(sitn, nt); @@ -1144,7 +1146,6 @@ static int ipip6_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -1207,6 +1208,7 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); + struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; @@ -1231,6 +1233,9 @@ static int __net_init sit_init_net(struct net *net) if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(sitn->fb_tunnel_dev); + + strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 36131d1..2dea4bb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1255,6 +1255,13 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, tcp_hdr(skb)); + treq->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = inet6_iif(skb); + if (!isn) { struct inet_peer *peer = NULL; @@ -1264,12 +1271,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) atomic_inc(&skb->users); treq->pktopts = skb; } - treq->iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); if (want_cookie) { isn = cookie_v6_init_sequence(sk, skb, &req->mss); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 846f4757..8c25419 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -340,7 +340,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -363,9 +363,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); @@ -376,14 +377,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov,len); + msg->msg_iov, copied ); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) @@ -432,7 +433,7 @@ try_again: datagram_recv_ctl(sk, msg, skb); } - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index cf0f308..89ff8c6 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1072,7 +1072,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Get routing info from the tunnel socket */ skb_dst_drop(skb); - skb_dst_set(skb, dst_clone(__sk_dst_get(sk))); + skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); inet = inet_sk(sk); fl = &inet->cork.fl; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index b3f6552..2e4b961 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -161,6 +161,12 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return -ENOENT; } + /* if we're already stopping ignore any new requests to stop */ + if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { + spin_unlock_bh(&sta->lock); + return -EALREADY; + } + if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { /* not even started yet! */ ieee80211_assign_tid_tx(sta, tid, NULL); @@ -169,6 +175,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return 0; } + set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + spin_unlock_bh(&sta->lock); #ifdef CONFIG_MAC80211_HT_DEBUG @@ -176,8 +184,6 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, sta->sta.addr, tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); - del_timer_sync(&tid_tx->addba_resp_timer); /* @@ -187,6 +193,20 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, */ clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); + /* + * There might be a few packets being processed right now (on + * another CPU) that have already gotten past the aggregation + * check when it was still OPERATIONAL and consequently have + * IEEE80211_TX_CTL_AMPDU set. In that case, this code might + * call into the driver at the same time or even before the + * TX paths calls into it, which could confuse the driver. + * + * Wait for all currently running TX paths to finish before + * telling the driver. New packets will not go through since + * the aggregation session is no longer OPERATIONAL. + */ + synchronize_net(); + tid_tx->stop_initiator = initiator; tid_tx->tx_stop = tx; @@ -283,6 +303,38 @@ ieee80211_wake_queue_agg(struct ieee80211_local *local, int tid) __release(agg_queue); } +/* + * splice packets from the STA's pending to the local pending, + * requires a call to ieee80211_agg_splice_finish later + */ +static void __acquires(agg_queue) +ieee80211_agg_splice_packets(struct ieee80211_local *local, + struct tid_ampdu_tx *tid_tx, u16 tid) +{ + int queue = ieee80211_ac_from_tid(tid); + unsigned long flags; + + ieee80211_stop_queue_agg(local, tid); + + if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates" + " from the pending queue\n", tid)) + return; + + if (!skb_queue_empty(&tid_tx->pending)) { + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + /* copy over remaining packets */ + skb_queue_splice_tail_init(&tid_tx->pending, + &local->pending[queue]); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + } +} + +static void __releases(agg_queue) +ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid) +{ + ieee80211_wake_queue_agg(local, tid); +} + void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; @@ -294,19 +346,17 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) tid_tx = rcu_dereference_protected_tid_tx(sta, tid); /* - * While we're asking the driver about the aggregation, - * stop the AC queue so that we don't have to worry - * about frames that came in while we were doing that, - * which would require us to put them to the AC pending - * afterwards which just makes the code more complex. + * Start queuing up packets for this aggregation session. + * We're going to release them once the driver is OK with + * that. */ - ieee80211_stop_queue_agg(local, tid); - clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); /* - * make sure no packets are being processed to get - * valid starting sequence number + * Make sure no packets are being processed. This ensures that + * we have a valid starting sequence number and that in-flight + * packets have been flushed out and no packets for this TID + * will go into the driver during the ampdu_action call. */ synchronize_net(); @@ -320,17 +370,15 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) " tid %d\n", tid); #endif spin_lock_bh(&sta->lock); + ieee80211_agg_splice_packets(local, tid_tx, tid); ieee80211_assign_tid_tx(sta, tid, NULL); + ieee80211_agg_splice_finish(local, tid); spin_unlock_bh(&sta->lock); - ieee80211_wake_queue_agg(local, tid); kfree_rcu(tid_tx, rcu_head); return; } - /* we can take packets again now */ - ieee80211_wake_queue_agg(local, tid); - /* activate the timer for the recipient's addBA response */ mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL); #ifdef CONFIG_MAC80211_HT_DEBUG @@ -446,38 +494,6 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, } EXPORT_SYMBOL(ieee80211_start_tx_ba_session); -/* - * splice packets from the STA's pending to the local pending, - * requires a call to ieee80211_agg_splice_finish later - */ -static void __acquires(agg_queue) -ieee80211_agg_splice_packets(struct ieee80211_local *local, - struct tid_ampdu_tx *tid_tx, u16 tid) -{ - int queue = ieee80211_ac_from_tid(tid); - unsigned long flags; - - ieee80211_stop_queue_agg(local, tid); - - if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates" - " from the pending queue\n", tid)) - return; - - if (!skb_queue_empty(&tid_tx->pending)) { - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - /* copy over remaining packets */ - skb_queue_splice_tail_init(&tid_tx->pending, - &local->pending[queue]); - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - } -} - -static void __releases(agg_queue) -ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid) -{ - ieee80211_wake_queue_agg(local, tid); -} - static void ieee80211_agg_tx_operational(struct ieee80211_local *local, struct sta_info *sta, u16 tid) { @@ -757,11 +773,27 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, goto out; } - del_timer(&tid_tx->addba_resp_timer); + del_timer_sync(&tid_tx->addba_resp_timer); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d\n", tid); #endif + + /* + * addba_resp_timer may have fired before we got here, and + * caused WANT_STOP to be set. If the stop then was already + * processed further, STOPPING might be set. + */ + if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) || + test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { +#ifdef CONFIG_MAC80211_HT_DEBUG + printk(KERN_DEBUG + "got addBA resp for tid %d but we already gave up\n", + tid); +#endif + goto out; + } + /* * IEEE 802.11-2007 7.3.1.14: * In an ADDBA Response frame, when the Status Code field diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index c5f3417..3110cbd 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -274,9 +274,9 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, PRINT_HT_CAP((htc->cap & BIT(10)), "HT Delayed Block Ack"); - PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " - "3839 bytes"); PRINT_HT_CAP(!(htc->cap & BIT(11)), "Max AMSDU length: " + "3839 bytes"); + PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " "7935 bytes"); /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d999bf3..cae4435 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -757,6 +757,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->int_scan_req) return -ENOMEM; + for (band = 0; band < IEEE80211_NUM_BANDS; band++) { + if (!local->hw.wiphy->bands[band]) + continue; + local->int_scan_req->rates[band] = (u32) -1; + } + /* if low-level driver supports AP, we also support VLAN */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_AP)) { hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_AP_VLAN); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 80de436..16518f3 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -260,7 +260,7 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; unsigned char *pos; - __le16 txflags; + u16 txflags; rthdr = (struct ieee80211_radiotap_header *) skb_push(skb, rtap_len); @@ -290,13 +290,13 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band txflags = 0; if (!(info->flags & IEEE80211_TX_STAT_ACK) && !is_multicast_ether_addr(hdr->addr1)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); + txflags |= IEEE80211_RADIOTAP_F_TX_FAIL; if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); + txflags |= IEEE80211_RADIOTAP_F_TX_CTS; else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); + txflags |= IEEE80211_RADIOTAP_F_TX_RTS; put_unaligned_le16(txflags, pos); pos += 2; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index eca0fad..d5230ec 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1039,7 +1039,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct ieee80211_sub_if_data, u.ap); - memset(&sta->sta.drv_priv, 0, hw->sta_data_size); WARN_ON(drv_sta_add(local, sdata, &sta->sta)); } } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8260b13..d5597b7 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -201,7 +201,6 @@ config NF_CONNTRACK_BROADCAST config NF_CONNTRACK_NETBIOS_NS tristate "NetBIOS name service protocol support" - depends on NETFILTER_ADVANCED select NF_CONNTRACK_BROADCAST help NetBIOS name service requests are sent as broadcast messages from an @@ -542,7 +541,6 @@ config NETFILTER_XT_TARGET_NOTRACK tristate '"NOTRACK" target support' depends on IP_NF_RAW || IP6_NF_RAW depends on NF_CONNTRACK - depends on NETFILTER_ADVANCED help The NOTRACK target allows a select rule to specify which packets *not* to enter the conntrack/NAT diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 6ee10f5..37d667e 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -158,7 +158,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem data = { }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index fb90e34..e69e271 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -162,7 +162,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem data = { }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index deb3e3d..64199b4 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -184,7 +184,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 ip2_from = 0, ip2_to, ip2_last, ip2; u32 timeout = h->timeout; bool with_ports = false; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 6b368be..b62c414 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -27,22 +27,17 @@ static DEFINE_MUTEX(nf_ct_ecache_mutex); -struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly; -EXPORT_SYMBOL_GPL(nf_conntrack_event_cb); - -struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly; -EXPORT_SYMBOL_GPL(nf_expect_event_cb); - /* deliver cached events and clear cache entry - must be called with locally * disabled softirqs */ void nf_ct_deliver_cached_events(struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); unsigned long events; struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_conntrack_event_cb); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (notify == NULL) goto out_unlock; @@ -83,19 +78,20 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); -int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new) +int nf_conntrack_register_notifier(struct net *net, + struct nf_ct_event_notifier *new) { int ret = 0; struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_conntrack_event_cb, + notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); if (notify != NULL) { ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(nf_conntrack_event_cb, new); + RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -105,32 +101,34 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); -void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new) +void nf_conntrack_unregister_notifier(struct net *net, + struct nf_ct_event_notifier *new) { struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_conntrack_event_cb, + notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - RCU_INIT_POINTER(nf_conntrack_event_cb, NULL); + RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); -int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new) +int nf_ct_expect_register_notifier(struct net *net, + struct nf_exp_event_notifier *new) { int ret = 0; struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_expect_event_cb, + notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); if (notify != NULL) { ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(nf_expect_event_cb, new); + RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -140,15 +138,16 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier); -void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new) +void nf_ct_expect_unregister_notifier(struct net *net, + struct nf_exp_event_notifier *new) { struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_expect_event_cb, + notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - RCU_INIT_POINTER(nf_expect_event_cb, NULL); + RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e58aa9b..ef21b22 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -4,7 +4,7 @@ * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> - * (C) 2005-2008 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2005-2011 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -2163,6 +2163,54 @@ MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); +static int __net_init ctnetlink_net_init(struct net *net) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + int ret; + + ret = nf_conntrack_register_notifier(net, &ctnl_notifier); + if (ret < 0) { + pr_err("ctnetlink_init: cannot register notifier.\n"); + goto err_out; + } + + ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp); + if (ret < 0) { + pr_err("ctnetlink_init: cannot expect register notifier.\n"); + goto err_unreg_notifier; + } +#endif + return 0; + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +err_unreg_notifier: + nf_conntrack_unregister_notifier(net, &ctnl_notifier); +err_out: + return ret; +#endif +} + +static void ctnetlink_net_exit(struct net *net) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp); + nf_conntrack_unregister_notifier(net, &ctnl_notifier); +#endif +} + +static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) +{ + struct net *net; + + list_for_each_entry(net, net_exit_list, exit_list) + ctnetlink_net_exit(net); +} + +static struct pernet_operations ctnetlink_net_ops = { + .init = ctnetlink_net_init, + .exit_batch = ctnetlink_net_exit_batch, +}; + static int __init ctnetlink_init(void) { int ret; @@ -2180,28 +2228,15 @@ static int __init ctnetlink_init(void) goto err_unreg_subsys; } -#ifdef CONFIG_NF_CONNTRACK_EVENTS - ret = nf_conntrack_register_notifier(&ctnl_notifier); - if (ret < 0) { - pr_err("ctnetlink_init: cannot register notifier.\n"); + if (register_pernet_subsys(&ctnetlink_net_ops)) { + pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } - ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp); - if (ret < 0) { - pr_err("ctnetlink_init: cannot expect register notifier.\n"); - goto err_unreg_notifier; - } -#endif - return 0; -#ifdef CONFIG_NF_CONNTRACK_EVENTS -err_unreg_notifier: - nf_conntrack_unregister_notifier(&ctnl_notifier); err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); -#endif err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: @@ -2213,11 +2248,7 @@ static void __exit ctnetlink_exit(void) pr_info("ctnetlink: unregistering from nfnetlink.\n"); nf_ct_remove_userspace_expectations(); -#ifdef CONFIG_NF_CONNTRACK_EVENTS - nf_ct_expect_unregister_notifier(&ctnl_notifier_exp); - nf_conntrack_unregister_notifier(&ctnl_notifier); -#endif - + unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); } diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 9c24de10..824f184 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -111,8 +111,6 @@ int netlbl_cfg_unlbl_map_add(const char *domain, struct netlbl_domaddr_map *addrmap = NULL; struct netlbl_domaddr4_map *map4 = NULL; struct netlbl_domaddr6_map *map6 = NULL; - const struct in_addr *addr4, *mask4; - const struct in6_addr *addr6, *mask6; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) @@ -133,9 +131,9 @@ int netlbl_cfg_unlbl_map_add(const char *domain, INIT_LIST_HEAD(&addrmap->list6); switch (family) { - case AF_INET: - addr4 = addr; - mask4 = mask; + case AF_INET: { + const struct in_addr *addr4 = addr; + const struct in_addr *mask4 = mask; map4 = kzalloc(sizeof(*map4), GFP_ATOMIC); if (map4 == NULL) goto cfg_unlbl_map_add_failure; @@ -148,9 +146,11 @@ int netlbl_cfg_unlbl_map_add(const char *domain, if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; - case AF_INET6: - addr6 = addr; - mask6 = mask; + } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: { + const struct in6_addr *addr6 = addr; + const struct in6_addr *mask6 = mask; map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); if (map6 == NULL) goto cfg_unlbl_map_add_failure; @@ -162,11 +162,13 @@ int netlbl_cfg_unlbl_map_add(const char *domain, map6->list.addr.s6_addr32[3] &= mask6->s6_addr32[3]; ipv6_addr_copy(&map6->list.mask, mask6); map6->list.valid = 1; - ret_val = netlbl_af4list_add(&map4->list, - &addrmap->list4); + ret_val = netlbl_af6list_add(&map6->list, + &addrmap->list6); if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; + } +#endif /* IPv6 */ default: goto cfg_unlbl_map_add_failure; break; @@ -225,9 +227,11 @@ int netlbl_cfg_unlbl_static_add(struct net *net, case AF_INET: addr_len = sizeof(struct in_addr); break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case AF_INET6: addr_len = sizeof(struct in6_addr); break; +#endif /* IPv6 */ default: return -EPFNOSUPPORT; } @@ -266,9 +270,11 @@ int netlbl_cfg_unlbl_static_del(struct net *net, case AF_INET: addr_len = sizeof(struct in_addr); break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case AF_INET6: addr_len = sizeof(struct in6_addr); break; +#endif /* IPv6 */ default: return -EPFNOSUPPORT; } diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index b9493a0..6cd8ddf 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -385,7 +385,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched_data *q; if (table->tab[dp] == NULL) { - table->tab[dp] = kzalloc(sizeof(*q), GFP_KERNEL); + table->tab[dp] = kzalloc(sizeof(*q), GFP_ATOMIC); if (table->tab[dp] == NULL) return -ENOMEM; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 6649463..d617161 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -209,8 +209,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) ctl->Plog, ctl->Scell_log, nla_data(tb[TCA_RED_STAB])); - if (skb_queue_empty(&sch->q)) - red_end_of_idle_period(&q->parms); + if (!q->qdisc->q.qlen) + red_start_of_idle_period(&q->parms); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index a3b7120..4f4c52c 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -225,11 +225,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) static int -__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev) +__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, + struct net_device *dev, struct netdev_queue *txq, + struct neighbour *mn) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); - struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc); - struct neighbour *mn = dst_get_neighbour(skb_dst(skb)); + struct teql_sched_data *q = qdisc_priv(txq->qdisc); struct neighbour *n = q->ncache; if (mn->tbl == NULL) @@ -262,17 +262,26 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * } static inline int teql_resolve(struct sk_buff *skb, - struct sk_buff *skb_res, struct net_device *dev) + struct sk_buff *skb_res, + struct net_device *dev, + struct netdev_queue *txq) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct dst_entry *dst = skb_dst(skb); + struct neighbour *mn; + int res; + if (txq->qdisc == &noop_qdisc) return -ENODEV; - if (dev->header_ops == NULL || - skb_dst(skb) == NULL || - dst_get_neighbour(skb_dst(skb)) == NULL) + if (!dev->header_ops || !dst) return 0; - return __teql_resolve(skb, skb_res, dev); + + rcu_read_lock(); + mn = dst_get_neighbour(dst); + res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0; + rcu_read_unlock(); + + return res; } static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) @@ -307,7 +316,7 @@ restart: continue; } - switch (teql_resolve(skb, skb_res, slave)) { + switch (teql_resolve(skb, skb_res, slave, slave_txq)) { case 0: if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 865e68f..bf81204 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -82,7 +82,7 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp) struct sctp_auth_bytes *key; /* Verify that we are not going to overflow INT_MAX */ - if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes)) + if (key_len > (INT_MAX - sizeof(struct sctp_auth_bytes))) return NULL; /* Allocate the shared key */ diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 5317b93..3341d89 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -591,6 +591,27 @@ void rpc_prepare_task(struct rpc_task *task) task->tk_ops->rpc_call_prepare(task, task->tk_calldata); } +static void +rpc_init_task_statistics(struct rpc_task *task) +{ + /* Initialize retry counters */ + task->tk_garb_retry = 2; + task->tk_cred_retry = 2; + task->tk_rebind_retry = 2; + + /* starting timestamp */ + task->tk_start = ktime_get(); +} + +static void +rpc_reset_task_statistics(struct rpc_task *task) +{ + task->tk_timeouts = 0; + task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_KILLED|RPC_TASK_SENT); + + rpc_init_task_statistics(task); +} + /* * Helper that calls task->tk_ops->rpc_call_done if it exists */ @@ -603,6 +624,7 @@ void rpc_exit_task(struct rpc_task *task) WARN_ON(RPC_ASSASSINATED(task)); /* Always release the RPC slot and buffer memory */ xprt_release(task); + rpc_reset_task_statistics(task); } } } @@ -805,11 +827,6 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta task->tk_calldata = task_setup_data->callback_data; INIT_LIST_HEAD(&task->tk_task); - /* Initialize retry counters */ - task->tk_garb_retry = 2; - task->tk_cred_retry = 2; - task->tk_rebind_retry = 2; - task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; @@ -819,8 +836,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta if (task->tk_ops->rpc_call_prepare != NULL) task->tk_action = rpc_prepare_task; - /* starting timestamp */ - task->tk_start = ktime_get(); + rpc_init_task_statistics(task); dprintk("RPC: new task initialized, procpid %u\n", task_pid_nr(current)); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f4385e4..c64c0ef 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -995,13 +995,11 @@ out_init_req: static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (xprt_dynamic_free_slot(xprt, req)) - return; - - memset(req, 0, sizeof(*req)); /* mark unused */ - spin_lock(&xprt->reserve_lock); - list_add(&req->rq_list, &xprt->free); + if (!xprt_dynamic_free_slot(xprt, req)) { + memset(req, 0, sizeof(*req)); /* mark unused */ + list_add(&req->rq_list, &xprt->free); + } rpc_wake_up_next(&xprt->backlog); spin_unlock(&xprt->reserve_lock); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2d78d95..55472c4 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -496,7 +496,7 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - int ret = 0; + int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", task->tk_pid, req->rq_slen - req->rq_bytes_sent, @@ -508,7 +508,6 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) { - ret = -EAGAIN; /* * Notify TCP that we're limited by the application * window size diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 466fbcc..b595a3d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1957,6 +1957,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if ((UNIXCB(skb).pid != siocb->scm->pid) || (UNIXCB(skb).cred != siocb->scm->cred)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } else { @@ -1974,6 +1975,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, chunk = min_t(unsigned int, skb->len, size); if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); if (copied == 0) copied = -EFAULT; break; @@ -1991,6 +1993,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put the skb back if we didn't use it up.. */ if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } @@ -2006,6 +2009,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } while (size); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b3a476f..ffafda5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -89,8 +89,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_IFINDEX] = { .type = NLA_U32 }, [NL80211_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, - [NL80211_ATTR_MAC] = { .type = NLA_BINARY, .len = ETH_ALEN }, - [NL80211_ATTR_PREV_BSSID] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [NL80211_ATTR_MAC] = { .len = ETH_ALEN }, + [NL80211_ATTR_PREV_BSSID] = { .len = ETH_ALEN }, [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index e71f5a6..3302c56 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -57,8 +57,17 @@ #define REG_DBG_PRINT(args...) #endif +static struct regulatory_request core_request_world = { + .initiator = NL80211_REGDOM_SET_BY_CORE, + .alpha2[0] = '0', + .alpha2[1] = '0', + .intersect = false, + .processed = true, + .country_ie_env = ENVIRON_ANY, +}; + /* Receipt of information from last regulatory request */ -static struct regulatory_request *last_request; +static struct regulatory_request *last_request = &core_request_world; /* To trigger userspace events */ static struct platform_device *reg_pdev; @@ -150,7 +159,7 @@ static char user_alpha2[2]; module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); -static void reset_regdomains(void) +static void reset_regdomains(bool full_reset) { /* avoid freeing static information or freeing something twice */ if (cfg80211_regdomain == cfg80211_world_regdom) @@ -165,6 +174,13 @@ static void reset_regdomains(void) cfg80211_world_regdom = &world_regdom; cfg80211_regdomain = NULL; + + if (!full_reset) + return; + + if (last_request != &core_request_world) + kfree(last_request); + last_request = &core_request_world; } /* @@ -175,7 +191,7 @@ static void update_world_regdomain(const struct ieee80211_regdomain *rd) { BUG_ON(!last_request); - reset_regdomains(); + reset_regdomains(false); cfg80211_world_regdom = rd; cfg80211_regdomain = rd; @@ -1407,7 +1423,8 @@ static int __regulatory_hint(struct wiphy *wiphy, } new_request: - kfree(last_request); + if (last_request != &core_request_world) + kfree(last_request); last_request = pending_request; last_request->intersect = intersect; @@ -1577,9 +1594,6 @@ static int regulatory_hint_core(const char *alpha2) { struct regulatory_request *request; - kfree(last_request); - last_request = NULL; - request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) @@ -1777,7 +1791,7 @@ static void restore_regulatory_settings(bool reset_user) mutex_lock(&cfg80211_mutex); mutex_lock(®_mutex); - reset_regdomains(); + reset_regdomains(true); restore_alpha2(alpha2, reset_user); /* @@ -2037,12 +2051,18 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) } request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + if (!request_wiphy && + (last_request->initiator == NL80211_REGDOM_SET_BY_DRIVER || + last_request->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE)) { + schedule_delayed_work(®_timeout, 0); + return -ENODEV; + } if (!last_request->intersect) { int r; if (last_request->initiator != NL80211_REGDOM_SET_BY_DRIVER) { - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = rd; return 0; } @@ -2063,7 +2083,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) if (r) return r; - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = rd; return 0; } @@ -2088,7 +2108,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) rd = NULL; - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = intersected_rd; return 0; @@ -2108,7 +2128,7 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) kfree(rd); rd = NULL; - reset_regdomains(); + reset_regdomains(false); cfg80211_regdomain = intersected_rd; return 0; @@ -2261,11 +2281,8 @@ void /* __init_or_exit */ regulatory_exit(void) mutex_lock(&cfg80211_mutex); mutex_lock(®_mutex); - reset_regdomains(); - - kfree(last_request); + reset_regdomains(true); - last_request = NULL; dev_set_uevent_suppress(®_pdev->dev, true); platform_device_unregister(reg_pdev); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 552df27..2118d64 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2382,9 +2382,11 @@ static unsigned int xfrm_default_advmss(const struct dst_entry *dst) return dst_metric_advmss(dst->path); } -static unsigned int xfrm_default_mtu(const struct dst_entry *dst) +static unsigned int xfrm_mtu(const struct dst_entry *dst) { - return dst_mtu(dst->path); + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst_mtu(dst->path); } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr) @@ -2411,8 +2413,8 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; - if (likely(dst_ops->default_mtu == NULL)) - dst_ops->default_mtu = xfrm_default_mtu; + if (likely(dst_ops->mtu == NULL)) + dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) |