diff options
Diffstat (limited to 'net')
55 files changed, 570 insertions, 464 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index a170893d70e0..8260f132b32e 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1548,7 +1548,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, kernel_buf = 1; indata = data; } else - indata = (char *)udata; + indata = (__force char *)udata; /* * response header len is 11 * PDU Header(7) + IO Size (4) diff --git a/net/atm/lec.c b/net/atm/lec.c index a7d172105c99..2e3d942e77f1 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -231,9 +231,11 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb, if (skb_headroom(skb) < 2) { pr_debug("reallocating skb\n"); skb2 = skb_realloc_headroom(skb, LEC_HEADER_LEN); - kfree_skb(skb); - if (skb2 == NULL) + if (unlikely(!skb2)) { + kfree_skb(skb); return NETDEV_TX_OK; + } + consume_skb(skb); skb = skb2; } skb_push(skb, 2); @@ -1602,7 +1604,7 @@ static void lec_arp_expire_vcc(unsigned long data) { unsigned long flags; struct lec_arp_table *to_remove = (struct lec_arp_table *)data; - struct lec_priv *priv = (struct lec_priv *)to_remove->priv; + struct lec_priv *priv = to_remove->priv; del_timer(&to_remove->timer); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index ce1e59fdae7b..226dca989448 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -283,7 +283,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) kfree_skb(n); goto nospace; } - kfree_skb(skb); + consume_skb(skb); skb = n; if (skb == NULL) return DROP_PACKET; diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index be8a25e0db65..be2acab9be9d 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -350,7 +350,7 @@ void ax25_transmit_buffer(ax25_cb *ax25, struct sk_buff *skb, int type) if (skb->sk != NULL) skb_set_owner_w(skbn, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skbn; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index a65588040b9e..d39097737e38 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -474,7 +474,7 @@ struct sk_buff *ax25_rt_build_path(struct sk_buff *skb, ax25_address *src, if (skb->sk != NULL) skb_set_owner_w(skbn, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skbn; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 46e7f86acfc9..3e18af4dadc4 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -210,7 +210,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) } if (sk->sk_state == BT_CONNECTED || !newsock || - test_bit(BT_DEFER_SETUP, &bt_sk(parent)->flags)) { + test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) { bt_accept_unlink(sk); if (newsock) sock_graft(sk, newsock); diff --git a/net/can/af_can.c b/net/can/af_can.c index 0ce2ad0696da..6efcd37b4bd0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -334,8 +334,8 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev) * relevant bits for the filter. * * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can - * filter for error frames (CAN_ERR_FLAG bit set in mask). For error frames - * there is a special filterlist and a special rx path filter handling. + * filter for error messages (CAN_ERR_FLAG bit set in mask). For error msg + * frames there is a special filterlist and a special rx path filter handling. * * Return: * Pointer to optimal filterlist for the given can_id/mask pair. @@ -347,7 +347,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, { canid_t inv = *can_id & CAN_INV_FILTER; /* save flag before masking */ - /* filter for error frames in extra filterlist */ + /* filter for error message frames in extra filterlist */ if (*mask & CAN_ERR_FLAG) { /* clear CAN_ERR_FLAG in filter entry */ *mask &= CAN_ERR_MASK; @@ -408,7 +408,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, * <received_can_id> & mask == can_id & mask * * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can - * filter for error frames (CAN_ERR_FLAG bit set in mask). + * filter for error message frames (CAN_ERR_FLAG bit set in mask). * * The provided pointer to the sk_buff is guaranteed to be valid as long as * the callback function is running. The callback function must *not* free @@ -578,7 +578,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return 0; if (can_id & CAN_ERR_FLAG) { - /* check for error frame entries only */ + /* check for error message frame entries only */ hlist_for_each_entry_rcu(r, n, &d->rx[RX_ERR], list) { if (can_id & r->mask) { deliver(skb, r); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index ea5fb9fcc3f5..d23b6682f4e9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -36,9 +36,6 @@ #define TRACE_ON 1 #define TRACE_OFF 0 -static void send_dm_alert(struct work_struct *unused); - - /* * Globals, our netlink socket pointer * and the work handle that will send up @@ -48,11 +45,10 @@ static int trace_state = TRACE_OFF; static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { - struct work_struct dm_alert_work; - struct sk_buff __rcu *skb; - atomic_t dm_hit_count; - struct timer_list send_timer; - int cpu; + spinlock_t lock; + struct sk_buff *skb; + struct work_struct dm_alert_work; + struct timer_list send_timer; }; struct dm_hw_stat_delta { @@ -78,13 +74,13 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); -static void reset_per_cpu_data(struct per_cpu_dm_data *data) +static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; - struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1); + unsigned long flags; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); @@ -99,65 +95,40 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data) sizeof(struct net_dm_alert_msg)); msg = nla_data(nla); memset(msg, 0, al); - } else - schedule_work_on(data->cpu, &data->dm_alert_work); - - /* - * Don't need to lock this, since we are guaranteed to only - * run this on a single cpu at a time. - * Note also that we only update data->skb if the old and new skb - * pointers don't match. This ensures that we don't continually call - * synchornize_rcu if we repeatedly fail to alloc a new netlink message. - */ - if (skb != oskb) { - rcu_assign_pointer(data->skb, skb); - - synchronize_rcu(); - - atomic_set(&data->dm_hit_count, dm_hit_limit); + } else { + mod_timer(&data->send_timer, jiffies + HZ / 10); } + spin_lock_irqsave(&data->lock, flags); + swap(data->skb, skb); + spin_unlock_irqrestore(&data->lock, flags); + + return skb; } -static void send_dm_alert(struct work_struct *unused) +static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data; - WARN_ON_ONCE(data->cpu != smp_processor_id()); + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - /* - * Grab the skb we're about to send - */ - skb = rcu_dereference_protected(data->skb, 1); - - /* - * Replace it with a new one - */ - reset_per_cpu_data(data); + skb = reset_per_cpu_data(data); - /* - * Ship it! - */ if (skb) genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); - - put_cpu_var(dm_cpu_data); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the - * hysteresis period. Note that it operates under the timer interrupt - * so we don't need to disable preemption here + * hysteresis period. */ -static void sched_send_work(unsigned long unused) +static void sched_send_work(unsigned long _data) { - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); - - schedule_work_on(smp_processor_id(), &data->dm_alert_work); + struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data; - put_cpu_var(dm_cpu_data); + schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) @@ -167,33 +138,28 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlattr *nla; int i; struct sk_buff *dskb; - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); - + struct per_cpu_dm_data *data; + unsigned long flags; - rcu_read_lock(); - dskb = rcu_dereference(data->skb); + local_irq_save(flags); + data = &__get_cpu_var(dm_cpu_data); + spin_lock(&data->lock); + dskb = data->skb; if (!dskb) goto out; - if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { - /* - * we're already at zero, discard this hit - */ - goto out; - } - nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { msg->points[i].count++; - atomic_inc(&data->dm_hit_count); goto out; } } - + if (msg->entries == dm_hit_limit) + goto out; /* * We need to create a new entry */ @@ -205,13 +171,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location) if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; - add_timer_on(&data->send_timer, smp_processor_id()); + add_timer(&data->send_timer); } out: - rcu_read_unlock(); - put_cpu_var(dm_cpu_data); - return; + spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) @@ -418,11 +382,11 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - data->cpu = cpu; INIT_WORK(&data->dm_alert_work, send_dm_alert); init_timer(&data->send_timer); - data->send_timer.data = cpu; + data->send_timer.data = (unsigned long)data; data->send_timer.function = sched_send_work; + spin_lock_init(&data->lock); reset_per_cpu_data(data); } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 9c2afb480270..c73d0a59212c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -729,6 +729,40 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_wol(dev, &wol); } +static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + int rc; + + if (!dev->ethtool_ops->get_eee) + return -EOPNOTSUPP; + + memset(&edata, 0, sizeof(struct ethtool_eee)); + edata.cmd = ETHTOOL_GEEE; + rc = dev->ethtool_ops->get_eee(dev, &edata); + + if (rc) + return rc; + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + + return 0; +} + +static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + + if (!dev->ethtool_ops->set_eee) + return -EOPNOTSUPP; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + return dev->ethtool_ops->set_eee(dev, &edata); +} + static int ethtool_nway_reset(struct net_device *dev) { if (!dev->ethtool_ops->nway_reset) @@ -1471,6 +1505,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); break; + case ETHTOOL_GEEE: + rc = ethtool_get_eee(dev, useraddr); + break; + case ETHTOOL_SEEE: + rc = ethtool_set_eee(dev, useraddr); + break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 016694d62484..1d74cea22aaa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -160,8 +160,8 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a - * tail room of size bytes. The object has a reference count of one. - * The return is the buffer. On a failure the return is %NULL. + * tail room of at least size bytes. The object has a reference count + * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 5fd146720f39..0d934ce1075f 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -46,6 +46,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); + mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; return 0; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index ac90f658586c..8e9a35b17df4 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -240,7 +240,7 @@ static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; net_info_ratelimited("dn_long_output: Increasing headroom\n"); } @@ -283,7 +283,7 @@ static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; net_info_ratelimited("dn_short_output: Increasing headroom\n"); } @@ -322,7 +322,7 @@ static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); return -ENOBUFS; } - kfree_skb(skb); + consume_skb(skb); skb = skb2; net_info_ratelimited("dn_phase3_output: Increasing headroom\n"); } diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 564a6ad13ce7..8a96047c7c94 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -322,7 +322,7 @@ static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned c /* Set "cross subchannel" bit in ackcrs */ ackcrs |= 0x2000; - ptr = (__le16 *)dn_mk_common_header(scp, skb, msgflag, hlen); + ptr = dn_mk_common_header(scp, skb, msgflag, hlen); *ptr++ = cpu_to_le16(acknum); *ptr++ = cpu_to_le16(ackcrs); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c8f7aee587d1..e4e8e00a2c91 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -553,7 +553,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; - return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len); + return sk->sk_prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 30b88d7b4bd6..9b0f25930fbc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1007,9 +1007,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) while (tn != NULL && (tp = node_parent((struct rt_trie_node *)tn)) != NULL) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); wasfull = tnode_full(tp, tnode_get_child(tp, cindex)); - tn = (struct tnode *) resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); - tnode_put_child_reorg((struct tnode *)tp, cindex, + tnode_put_child_reorg(tp, cindex, (struct rt_trie_node *)tn, wasfull); tp = node_parent((struct rt_trie_node *) tn); @@ -1024,7 +1024,7 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) /* Handle last (top) tnode */ if (IS_TNODE(tn)) - tn = (struct tnode *)resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); @@ -1125,7 +1125,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, (struct rt_trie_node *)l); + put_child(t, tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1160,8 +1160,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, - (struct rt_trie_node *)tn); + put_child(t, tp, cindex, (struct rt_trie_node *)tn); } else { rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; @@ -1620,7 +1619,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, NULL); + put_child(t, tp, cindex, NULL); trie_rebalance(t, tp); } else RCU_INIT_POINTER(t->trie, NULL); @@ -1844,6 +1843,8 @@ int fib_table_flush(struct fib_table *tb) if (ll && hlist_empty(&ll->list)) trie_leaf_remove(t, ll); + inetpeer_invalidate_tree(&tb->tb_peers); + pr_debug("trie_flush found=%d\n", found); return found; } @@ -1992,6 +1993,7 @@ struct fib_table *fib_trie_table(u32 id) tb->tb_id = id; tb->tb_default = -1; tb->tb_num_default = 0; + inet_peer_base_init(&tb->tb_peers); t = (struct trie *) tb->tb_data; memset(t, 0, sizeof(*t)); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c75efbdc71cb..e1caa1abe5d1 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -253,9 +253,8 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, /* Limit if icmp type is enabled in ratemask. */ if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) { - if (!rt->peer) - rt_bind_peer(rt, fl4->daddr, 1); - rc = inet_peer_xrlim_allow(rt->peer, + struct inet_peer *peer = rt_get_peer_create(rt, fl4->daddr); + rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); } out: @@ -674,9 +673,7 @@ static void icmp_unreach(struct sk_buff *skb) LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), &iph->daddr); } else { - info = ip_rt_frag_needed(net, iph, - ntohs(icmph->un.frag.mtu), - skb->dev); + info = ntohs(icmph->un.frag.mtu); if (!info) goto out; } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5ff2a51b6d0c..85190e69297b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -243,12 +243,12 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, if (q == NULL) return NULL; + q->net = nf; f->constructor(q, arg); atomic_add(f->qsize, &nf->mem); setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); atomic_set(&q->refcnt, 1); - q->net = nf; return q; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d4d61b694fab..cac02ad1425d 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -82,23 +82,39 @@ static const struct inet_peer peer_fake_node = { .avl_height = 0 }; -struct inet_peer_base { - struct inet_peer __rcu *root; - seqlock_t lock; - int total; -}; +void inet_peer_base_init(struct inet_peer_base *bp) +{ + bp->root = peer_avl_empty_rcu; + seqlock_init(&bp->lock); + bp->flush_seq = ~0U; + bp->total = 0; +} +EXPORT_SYMBOL_GPL(inet_peer_base_init); -static struct inet_peer_base v4_peers = { - .root = peer_avl_empty_rcu, - .lock = __SEQLOCK_UNLOCKED(v4_peers.lock), - .total = 0, -}; +static atomic_t v4_seq = ATOMIC_INIT(0); +static atomic_t v6_seq = ATOMIC_INIT(0); -static struct inet_peer_base v6_peers = { - .root = peer_avl_empty_rcu, - .lock = __SEQLOCK_UNLOCKED(v6_peers.lock), - .total = 0, -}; +static atomic_t *inetpeer_seq_ptr(int family) +{ + return (family == AF_INET ? &v4_seq : &v6_seq); +} + +static inline void flush_check(struct inet_peer_base *base, int family) +{ + atomic_t *fp = inetpeer_seq_ptr(family); + + if (unlikely(base->flush_seq != atomic_read(fp))) { + inetpeer_invalidate_tree(base); + base->flush_seq = atomic_read(fp); + } +} + +void inetpeer_invalidate_family(int family) +{ + atomic_t *fp = inetpeer_seq_ptr(family); + + atomic_inc(fp); +} #define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */ @@ -401,11 +417,6 @@ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base, call_rcu(&p->rcu, inetpeer_free_rcu); } -static struct inet_peer_base *family_to_base(int family) -{ - return family == AF_INET ? &v4_peers : &v6_peers; -} - /* perform garbage collect on all items stacked during a lookup */ static int inet_peer_gc(struct inet_peer_base *base, struct inet_peer __rcu **stack[PEER_MAXDEPTH], @@ -443,14 +454,17 @@ static int inet_peer_gc(struct inet_peer_base *base, return cnt; } -struct inet_peer *inet_getpeer(const struct inetpeer_addr *daddr, int create) +struct inet_peer *inet_getpeer(struct inet_peer_base *base, + const struct inetpeer_addr *daddr, + int create) { struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; - struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; unsigned int sequence; int invalidated, gccnt = 0; + flush_check(base, daddr->family); + /* Attempt a lockless lookup first. * Because of a concurrent writer, we might not find an existing entry. */ @@ -560,10 +574,20 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) } EXPORT_SYMBOL(inet_peer_xrlim_allow); -void inetpeer_invalidate_tree(int family) +static void inetpeer_inval_rcu(struct rcu_head *head) +{ + struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu); + + spin_lock_bh(&gc_lock); + list_add_tail(&p->gc_list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} + +void inetpeer_invalidate_tree(struct inet_peer_base *base) { struct inet_peer *old, *new, *prev; - struct inet_peer_base *base = family_to_base(family); write_seqlock_bh(&base->lock); @@ -576,10 +600,7 @@ void inetpeer_invalidate_tree(int family) prev = cmpxchg(&base->root, old, new); if (prev == old) { base->total = 0; - spin_lock(&gc_lock); - list_add_tail(&prev->gc_list, &gc_list); - spin_unlock(&gc_lock); - schedule_delayed_work(&gc_work, gc_delay); + call_rcu(&prev->gc_rcu, inetpeer_inval_rcu); } out: diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9dbd3dd6022d..8d07c973409c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -171,6 +171,10 @@ static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) static void ip4_frag_init(struct inet_frag_queue *q, void *a) { struct ipq *qp = container_of(q, struct ipq, q); + struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4, + frags); + struct net *net = container_of(ipv4, struct net, ipv4); + struct ip4_create_arg *arg = a; qp->protocol = arg->iph->protocol; @@ -180,7 +184,7 @@ static void ip4_frag_init(struct inet_frag_queue *q, void *a) qp->daddr = arg->iph->daddr; qp->user = arg->user; qp->peer = sysctl_ipfrag_max_dist ? - inet_getpeer_v4(arg->iph->saddr, 1) : NULL; + inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL; } static __inline__ void ip4_frag_free(struct inet_frag_queue *q) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 451f97c42eb4..b99ca4e154b9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -200,7 +200,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) } if (skb->sk) skb_set_owner_w(skb2, skb->sk); - kfree_skb(skb); + consume_skb(skb); skb = skb2; } @@ -709,7 +709,7 @@ slow_path: IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES); } - kfree_skb(skb); + consume_skb(skb); IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS); return err; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 746edec8b86e..bac712293fd6 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -405,7 +405,7 @@ static unsigned char asn1_octets_decode(struct asn1_ctx *ctx, ptr = *octets; while (ctx->pointer < eoc) { - if (!asn1_octet_decode(ctx, (unsigned char *)ptr++)) { + if (!asn1_octet_decode(ctx, ptr++)) { kfree(*octets); *octets = NULL; return 0; @@ -759,7 +759,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, } break; case SNMP_OBJECTID: - if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { + if (!asn1_oid_decode(ctx, end, &lp, &len)) { kfree(id); return 0; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 98b30d08efe9..842510d50453 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -162,10 +162,7 @@ static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) struct inet_peer *peer; u32 *p = NULL; - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - - peer = rt->peer; + peer = rt_get_peer_create(rt, rt->rt_dst); if (peer) { u32 *old_p = __DST_METRICS_PTR(old); unsigned long prev, new; @@ -680,7 +677,7 @@ static inline int rt_fast_clean(struct rtable *rth) static inline int rt_valuable(struct rtable *rth) { return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) || - (rth->peer && rth->peer->pmtu_expires); + (rt_has_peer(rth) && rt_peer_ptr(rth)->pmtu_expires); } static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2) @@ -938,7 +935,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); - inetpeer_invalidate_tree(AF_INET); + inetpeer_invalidate_family(AF_INET); } /* @@ -1328,14 +1325,20 @@ static u32 rt_peer_genid(void) void rt_bind_peer(struct rtable *rt, __be32 daddr, int create) { + struct inet_peer_base *base; struct inet_peer *peer; - peer = inet_getpeer_v4(daddr, create); + base = inetpeer_base_ptr(rt->_peer); + if (!base) + return; - if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) - inet_putpeer(peer); - else - rt->rt_peer_genid = rt_peer_genid(); + peer = inet_getpeer_v4(base, daddr, create); + if (peer) { + if (!rt_set_peer(rt, peer)) + inet_putpeer(peer); + else + rt->rt_peer_genid = rt_peer_genid(); + } } /* @@ -1363,14 +1366,13 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) struct rtable *rt = (struct rtable *) dst; if (rt && !(rt->dst.flags & DST_NOPEER)) { - if (rt->peer == NULL) - rt_bind_peer(rt, rt->rt_dst, 1); + struct inet_peer *peer = rt_get_peer_create(rt, rt->rt_dst); /* If peer is attached to destination, it is never detached, so that we need not to grab a lock to dereference it. */ - if (rt->peer) { - iph->id = htons(inet_getid(rt->peer, more)); + if (peer) { + iph->id = htons(inet_getid(peer, more)); return; } } else if (!rt) @@ -1480,10 +1482,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rt->rt_gateway != old_gw) continue; - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - - peer = rt->peer; + peer = rt_get_peer_create(rt, rt->rt_dst); if (peer) { if (peer->redirect_learned.a4 != new_gw) { peer->redirect_learned.a4 = new_gw; @@ -1539,8 +1538,10 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) rt_genid(dev_net(dst->dev))); rt_del(hash, rt); ret = NULL; - } else if (rt->peer && peer_pmtu_expired(rt->peer)) { - dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig); + } else if (rt_has_peer(rt)) { + struct inet_peer *peer = rt_peer_ptr(rt); + if (peer_pmtu_expired(peer)) + dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig); } } return ret; @@ -1578,9 +1579,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) log_martians = IN_DEV_LOG_MARTIANS(in_dev); rcu_read_unlock(); - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + peer = rt_get_peer_create(rt, rt->rt_dst); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); return; @@ -1645,9 +1644,7 @@ static int ip_error(struct sk_buff *skb) break; } - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + peer = rt_get_peer_create(rt, rt->rt_dst); send = true; if (peer) { @@ -1668,67 +1665,6 @@ out: kfree_skb(skb); return 0; } -/* - * The last two values are not from the RFC but - * are needed for AMPRnet AX.25 paths. - */ - -static const unsigned short mtu_plateau[] = -{32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 }; - -static inline unsigned short guess_mtu(unsigned short old_mtu) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++) - if (old_mtu > mtu_plateau[i]) - return mtu_plateau[i]; - return 68; -} - -unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, - unsigned short new_mtu, - struct net_device *dev) -{ - unsigned short old_mtu = ntohs(iph->tot_len); - unsigned short est_mtu = 0; - struct inet_peer *peer; - - peer = inet_getpeer_v4(iph->daddr, 1); - if (peer) { - unsigned short mtu = new_mtu; - - if (new_mtu < 68 || new_mtu >= old_mtu) { - /* BSD 4.2 derived systems incorrectly adjust - * tot_len by the IP header length, and report - * a zero MTU in the ICMP message. - */ - if (mtu == 0 && - old_mtu >= 68 + (iph->ihl << 2)) - old_mtu -= iph->ihl << 2; - mtu = guess_mtu(old_mtu); - } - - if (mtu < ip_rt_min_pmtu) - mtu = ip_rt_min_pmtu; - if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { - unsigned long pmtu_expires; - - pmtu_expires = jiffies + ip_rt_mtu_expires; - if (!pmtu_expires) - pmtu_expires = 1UL; - - est_mtu = mtu; - peer->pmtu_learned = mtu; - peer->pmtu_expires = pmtu_expires; - atomic_inc(&__rt_peer_genid); - } - - inet_putpeer(peer); - } - return est_mtu ? : new_mtu; -} - static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) { unsigned long expires = ACCESS_ONCE(peer->pmtu_expires); @@ -1753,9 +1689,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) dst_confirm(dst); - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; + peer = rt_get_peer_create(rt, rt->rt_dst); if (peer) { unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires); @@ -1781,12 +1715,8 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) static void ipv4_validate_peer(struct rtable *rt) { if (rt->rt_peer_genid != rt_peer_genid()) { - struct inet_peer *peer; - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 0); + struct inet_peer *peer = rt_get_peer(rt, rt->rt_dst); - peer = rt->peer; if (peer) { check_peer_pmtu(&rt->dst, peer); @@ -1812,14 +1742,13 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; - struct inet_peer *peer = rt->peer; if (rt->fi) { fib_info_put(rt->fi); rt->fi = NULL; } - if (peer) { - rt->peer = NULL; + if (rt_has_peer(rt)) { + struct inet_peer *peer = rt_peer_ptr(rt); inet_putpeer(peer); } } @@ -1832,8 +1761,11 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); rt = skb_rtable(skb); - if (rt && rt->peer && peer_pmtu_cleaned(rt->peer)) - dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); + if (rt && rt_has_peer(rt)) { + struct inet_peer *peer = rt_peer_ptr(rt); + if (peer_pmtu_cleaned(peer)) + dst_metric_set(&rt->dst, RTAX_MTU, peer->pmtu_orig); + } } static int ip_rt_bug(struct sk_buff *skb) @@ -1935,6 +1867,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, struct fib_info *fi) { + struct inet_peer_base *base; struct inet_peer *peer; int create = 0; @@ -1944,8 +1877,12 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS)) create = 1; - rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create); + base = inetpeer_base_ptr(rt->_peer); + BUG_ON(!base); + + peer = inet_getpeer_v4(base, rt->rt_dst, create); if (peer) { + __rt_set_peer(rt, peer); rt->rt_peer_genid = rt_peer_genid(); if (inet_metrics_new(peer)) memcpy(peer->metrics, fi->fib_metrics, @@ -2061,7 +1998,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; rth->rt_peer_genid = 0; - rth->peer = NULL; + rt_init_peer(rth, dev_net(dev)->ipv4.peers); rth->fi = NULL; if (our) { rth->dst.input= ip_local_deliver; @@ -2189,7 +2126,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; rth->rt_peer_genid = 0; - rth->peer = NULL; + rt_init_peer(rth, &res->table->tb_peers); rth->fi = NULL; rth->dst.input = ip_forward; @@ -2372,7 +2309,7 @@ local_input: rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; rth->rt_peer_genid = 0; - rth->peer = NULL; + rt_init_peer(rth, net->ipv4.peers); rth->fi = NULL; if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -2576,7 +2513,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_gateway = fl4->daddr; rth->rt_spec_dst= fl4->saddr; rth->rt_peer_genid = 0; - rth->peer = NULL; + rt_init_peer(rth, (res->table ? + &res->table->tb_peers : + dev_net(dev_out)->ipv4.peers)); rth->fi = NULL; RT_CACHE_STAT_INC(out_slow_tot); @@ -2625,6 +2564,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) int orig_oif; res.fi = NULL; + res.table = NULL; #ifdef CONFIG_IP_MULTIPLE_TABLES res.r = NULL; #endif @@ -2730,6 +2670,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) if (fib_lookup(net, fl4, &res)) { res.fi = NULL; + res.table = NULL; if (fl4->flowi4_oif) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. @@ -2913,9 +2854,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_src = ort->rt_src; rt->rt_gateway = ort->rt_gateway; rt->rt_spec_dst = ort->rt_spec_dst; - rt->peer = ort->peer; - if (rt->peer) - atomic_inc(&rt->peer->refcnt); + rt_transfer_peer(rt, ort); rt->fi = ort->fi; if (rt->fi) atomic_inc(&rt->fi->fib_clntref); @@ -2953,7 +2892,6 @@ static int rt_fill_info(struct net *net, struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; - const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); @@ -3009,8 +2947,9 @@ static int rt_fill_info(struct net *net, goto nla_put_failure; error = rt->dst.error; - if (peer) { - inet_peer_refcheck(rt->peer); + if (rt_has_peer(rt)) { + const struct inet_peer *peer = rt_peer_ptr(rt); + inet_peer_refcheck(peer); id = atomic_read(&peer->ip_id_count) & 0xffff; if (peer->tcp_ts_stamp) { ts = peer->tcp_ts; @@ -3400,6 +3339,30 @@ static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; +static int __net_init ipv4_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); + + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv4.peers = bp; + return 0; +} + +static void __net_exit ipv4_inetpeer_exit(struct net *net) +{ + struct inet_peer_base *bp = net->ipv4.peers; + + net->ipv4.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} + +static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { + .init = ipv4_inetpeer_init, + .exit = ipv4_inetpeer_exit, +}; #ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; @@ -3480,6 +3443,7 @@ int __init ip_rt_init(void) register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&rt_genid_ops); + register_pernet_subsys(&ipv4_inetpeer_ops); return rc; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c8d28c433b2b..fda2ca17135e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -848,7 +848,6 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, err = net_xmit_eval(err); } - dst_release(dst); return err; } @@ -1821,40 +1820,25 @@ do_time_wait: goto discard_it; } -struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) +struct inet_peer *tcp_v4_get_peer(struct sock *sk) { struct rtable *rt = (struct rtable *) __sk_dst_get(sk); struct inet_sock *inet = inet_sk(sk); - struct inet_peer *peer; - if (!rt || - inet->cork.fl.u.ip4.daddr != inet->inet_daddr) { - peer = inet_getpeer_v4(inet->inet_daddr, 1); - *release_it = true; - } else { - if (!rt->peer) - rt_bind_peer(rt, inet->inet_daddr, 1); - peer = rt->peer; - *release_it = false; - } - - return peer; + /* If we don't have a valid cached route, or we're doing IP + * options which make the IPv4 header destination address + * different from our peer's, do not bother with this. + */ + if (!rt || inet->cork.fl.u.ip4.daddr != inet->inet_daddr) + return NULL; + return rt_get_peer_create(rt, inet->inet_daddr); } EXPORT_SYMBOL(tcp_v4_get_peer); -void *tcp_v4_tw_get_peer(struct sock *sk) -{ - const struct inet_timewait_sock *tw = inet_twsk(sk); - - return inet_getpeer_v4(tw->tw_daddr, 1); -} -EXPORT_SYMBOL(tcp_v4_tw_get_peer); - static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, - .twsk_getpeer = tcp_v4_tw_get_peer, }; const struct inet_connection_sock_af_ops ipv4_specific = { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b85d9fe7d663..cb015317c9f7 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -60,9 +60,8 @@ static bool tcp_remember_stamp(struct sock *sk) const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct inet_peer *peer; - bool release_it; - peer = icsk->icsk_af_ops->get_peer(sk, &release_it); + peer = icsk->icsk_af_ops->get_peer(sk); if (peer) { if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && @@ -70,8 +69,6 @@ static bool tcp_remember_stamp(struct sock *sk) peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; peer->tcp_ts = tp->rx_opt.ts_recent; } - if (release_it) - inet_putpeer(peer); return true; } @@ -80,20 +77,19 @@ static bool tcp_remember_stamp(struct sock *sk) static bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw) { + const struct tcp_timewait_sock *tcptw; struct sock *sk = (struct sock *) tw; struct inet_peer *peer; - peer = twsk_getpeer(sk); + tcptw = tcp_twsk(sk); + peer = tcptw->tw_peer; if (peer) { - const struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; peer->tcp_ts = tcptw->tw_ts_recent; } - inet_putpeer(peer); return true; } return false; @@ -317,9 +313,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); bool recycle_ok = false; + bool recycle_on = false; - if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) + if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) { recycle_ok = tcp_remember_stamp(sk); + recycle_on = true; + } if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets) tw = inet_twsk_alloc(sk, state); @@ -327,8 +326,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (tw != NULL) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); + struct inet_sock *inet = inet_sk(sk); + struct inet_peer *peer = NULL; - tw->tw_transparent = inet_sk(sk)->transparent; + tw->tw_transparent = inet->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -350,6 +351,12 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } #endif + if (recycle_on) + peer = icsk->icsk_af_ops->get_peer(sk); + tcptw->tw_peer = peer; + if (peer) + atomic_inc(&peer->refcnt); + #ifdef CONFIG_TCP_MD5SIG /* * The timewait bucket does not have the key DB from the @@ -401,8 +408,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) void tcp_twsk_destructor(struct sock *sk) { -#ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); + + if (twsk->tw_peer) + inet_putpeer(twsk->tw_peer); +#ifdef CONFIG_TCP_MD5SIG if (twsk->tw_md5_key) { tcp_free_md5sig_pool(); kfree_rcu(twsk->tw_md5_key, rcu); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 803cbfe82fbc..c465d3e51e28 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2442,7 +2442,16 @@ int tcp_send_synack(struct sock *sk) return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } -/* Prepare a SYN-ACK. */ +/** + * tcp_make_synack - Prepare a SYN-ACK. + * sk: listener socket + * dst: dst entry attached to the SYNACK + * req: request_sock pointer + * rvp: request_values pointer + * + * Allocate one skb and build a SYNACK packet. + * @dst is consumed : Caller should not use it again. + */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct request_values *rvp) @@ -2461,14 +2470,15 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) s_data_desired = cvp->s_data_desired; - skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1, GFP_ATOMIC); - if (skb == NULL) + skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC); + if (unlikely(!skb)) { + dst_release(dst); return NULL; - + } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); - skb_dst_set(skb, dst_clone(dst)); + skb_dst_set(skb, dst); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 0d3426cb5c4f..8855d8268552 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -90,9 +90,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.dst.dev = dev; dev_hold(dev); - xdst->u.rt.peer = rt->peer; - if (rt->peer) - atomic_inc(&rt->peer->refcnt); + rt_transfer_peer(&xdst->u.rt, rt); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ @@ -212,8 +210,10 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) dst_destroy_metrics_generic(dst); - if (likely(xdst->u.rt.peer)) - inet_putpeer(xdst->u.rt.peer); + if (rt_has_peer(&xdst->u.rt)) { + struct inet_peer *peer = rt_peer_ptr(&xdst->u.rt); + inet_putpeer(peer); + } xfrm_dst_destroy(xdst); } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 6447dc49429f..fa3d9c328092 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -791,14 +791,14 @@ static int ipv6_renew_option(void *ohdr, if (ohdr) { memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*(struct ipv6_opt_hdr **)hdr)); + *p += CMSG_ALIGN(ipv6_optlen(*hdr)); } } else { if (newopt) { if (copy_from_user(*p, newopt, newoptlen)) return -EFAULT; *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*(struct ipv6_opt_hdr **)hdr) > newoptlen) + if (ipv6_optlen(*hdr) > newoptlen) return -EINVAL; *p += CMSG_ALIGN(newoptlen); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 091a2971c7b7..ed89bba745a1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -188,14 +188,14 @@ static inline bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else { struct rt6_info *rt = (struct rt6_info *)dst; int tmo = net->ipv6.sysctl.icmpv6_time; + struct inet_peer *peer; /* Give more bandwidth to wider prefixes. */ if (rt->rt6i_dst.plen < 128) tmo >>= ((128 - rt->rt6i_dst.plen)>>5); - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - res = inet_peer_xrlim_allow(rt->rt6i_peer, tmo); + peer = rt6_get_peer_create(rt); + res = inet_peer_xrlim_allow(peer, tmo); } dst_release(dst); return res; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0c220a416626..7ef0743f06f0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -197,6 +197,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table->tb6_id = id; table->tb6_root.leaf = net->ipv6.ip6_null_entry; table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&table->tb6_peers); } return table; @@ -1633,6 +1634,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), @@ -1643,6 +1645,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); #endif fib6_tables_init(net); @@ -1666,8 +1669,10 @@ static void fib6_net_exit(struct net *net) del_timer_sync(&net->ipv6.ip6_fib_timer); #ifdef CONFIG_IPV6_MULTIPLE_TABLES + inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers); kfree(net->ipv6.fib6_local_tbl); #endif + inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers); kfree(net->ipv6.fib6_main_tbl); kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 17b8c67998bb..62fcf3e48aca 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -463,6 +463,7 @@ int ip6_forward(struct sk_buff *skb) */ if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; + struct inet_peer *peer; struct rt6_info *rt; /* @@ -476,13 +477,12 @@ int ip6_forward(struct sk_buff *skb) else target = &hdr->daddr; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); + peer = rt6_get_peer_create(rt); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); } else { int addrtype = ipv6_addr_type(&hdr->saddr); @@ -602,11 +602,8 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) int old, new; if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; + struct inet_peer *peer = rt6_get_peer_create(rt); - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - peer = rt->rt6i_peer; if (peer) { fhdr->identification = htonl(inet_getid(peer, 0)); return; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 54f62d3b8dd6..69a6330dea91 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1472,6 +1472,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + struct inet_peer *peer; struct sk_buff *buff; struct icmp6hdr *icmph; struct in6_addr saddr_buf; @@ -1518,9 +1519,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) "Redirect: destination is not a neighbour\n"); goto release; } - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + peer = rt6_get_peer_create(rt); + if (!inet_peer_xrlim_allow(peer, 1*HZ)) goto release; if (dev->addr_len) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 999a982ad3fd..58a3ec23da2f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -99,10 +99,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) if (!(rt->dst.flags & DST_HOST)) return NULL; - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - - peer = rt->rt6i_peer; + peer = rt6_get_peer_create(rt); if (peer) { u32 *old_p = __DST_METRICS_PTR(old); unsigned long prev, new; @@ -261,16 +258,19 @@ static struct rt6_info ip6_blk_hole_entry_template = { #endif /* allocate dst with ip6_dst_ops */ -static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, +static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, - int flags) + int flags, + struct fib6_table *table) { - struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags); + struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, + 0, 0, flags); - if (rt) + if (rt) { memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); - + rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); + } return rt; } @@ -278,7 +278,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - struct inet_peer *peer = rt->rt6i_peer; if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -291,8 +290,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) if (!(rt->rt6i_flags & RTF_EXPIRES) && dst->from) dst_release(dst->from); - if (peer) { - rt->rt6i_peer = NULL; + if (rt6_has_peer(rt)) { + struct inet_peer *peer = rt6_peer_ptr(rt); inet_putpeer(peer); } } @@ -306,13 +305,20 @@ static u32 rt6_peer_genid(void) void rt6_bind_peer(struct rt6_info *rt, int create) { + struct inet_peer_base *base; struct inet_peer *peer; - peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); - if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) - inet_putpeer(peer); - else - rt->rt6i_peer_genid = rt6_peer_genid(); + base = inetpeer_base_ptr(rt->_rt6i_peer); + if (!base) + return; + + peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); + if (peer) { + if (!rt6_set_peer(rt, peer)) + inet_putpeer(peer); + else + rt->rt6i_peer_genid = rt6_peer_genid(); + } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -952,6 +958,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0); if (rt) { memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); + rt6_init_peer(rt, net->ipv6.peers); new = &rt->dst; @@ -996,7 +1003,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { if (rt->rt6i_peer_genid != rt6_peer_genid()) { - if (!rt->rt6i_peer) + if (!rt6_has_peer(rt)) rt6_bind_peer(rt, 0); rt->rt6i_peer_genid = rt6_peer_genid(); } @@ -1110,7 +1117,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(!idev)) return ERR_PTR(-ENODEV); - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); + rt = ip6_dst_alloc(net, dev, 0, NULL); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); @@ -1292,7 +1299,7 @@ int ip6_route_add(struct fib6_config *cfg) if (!table) goto out; - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT); + rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table); if (!rt) { err = -ENOMEM; @@ -1814,8 +1821,8 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest) { struct net *net = dev_net(ort->dst.dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - ort->dst.dev, 0); + struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0, + ort->rt6i_table); if (rt) { rt->dst.input = ort->dst.input; @@ -2099,8 +2106,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, bool anycast) { struct net *net = dev_net(idev->dev); - struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - net->loopback_dev, 0); + struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); int err; if (!rt) { @@ -2521,7 +2527,9 @@ static int rt6_fill_node(struct net *net, else expires = INT_MAX; - peer = rt->rt6i_peer; + peer = NULL; + if (rt6_has_peer(rt)) + peer = rt6_peer_ptr(rt); ts = tsage = 0; if (peer && peer->tcp_ts_stamp) { ts = peer->tcp_ts; @@ -2998,6 +3006,31 @@ static struct pernet_operations ip6_route_net_ops = { .exit = ip6_route_net_exit, }; +static int __net_init ipv6_inetpeer_init(struct net *net) +{ + struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); + + if (!bp) + return -ENOMEM; + inet_peer_base_init(bp); + net->ipv6.peers = bp; + return 0; +} + +static void __net_exit ipv6_inetpeer_exit(struct net *net) +{ + struct inet_peer_base *bp = net->ipv6.peers; + + net->ipv6.peers = NULL; + inetpeer_invalidate_tree(bp); + kfree(bp); +} + +static struct pernet_operations ipv6_inetpeer_ops = { + .init = ipv6_inetpeer_init, + .exit = ipv6_inetpeer_exit, +}; + static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = 0, @@ -3022,6 +3055,10 @@ int __init ip6_route_init(void) if (ret) goto out_dst_entries; + ret = register_pernet_subsys(&ipv6_inetpeer_ops); + if (ret) + goto out_register_subsys; + ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; /* Registering of the loopback is done before this portion of code, @@ -3037,7 +3074,7 @@ int __init ip6_route_init(void) #endif ret = fib6_init(); if (ret) - goto out_register_subsys; + goto out_register_inetpeer; ret = xfrm6_init(); if (ret) @@ -3066,6 +3103,8 @@ xfrm6_init: xfrm6_fini(); out_fib6_init: fib6_gc_cleanup(); +out_register_inetpeer: + unregister_pernet_subsys(&ipv6_inetpeer_ops); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); out_dst_entries: @@ -3081,6 +3120,7 @@ void ip6_route_cleanup(void) fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); + unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3a9aec29581a..f91b0bfd12d5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -522,7 +522,6 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, done: if (opt && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return err; } @@ -1733,42 +1732,24 @@ do_time_wait: goto discard_it; } -static struct inet_peer *tcp_v6_get_peer(struct sock *sk, bool *release_it) +static struct inet_peer *tcp_v6_get_peer(struct sock *sk) { struct rt6_info *rt = (struct rt6_info *) __sk_dst_get(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct inet_peer *peer; - - if (!rt || - !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) { - peer = inet_getpeer_v6(&np->daddr, 1); - *release_it = true; - } else { - if (!rt->rt6i_peer) - rt6_bind_peer(rt, 1); - peer = rt->rt6i_peer; - *release_it = false; - } - - return peer; -} -static void *tcp_v6_tw_get_peer(struct sock *sk) -{ - const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - const struct inet_timewait_sock *tw = inet_twsk(sk); - - if (tw->tw_family == AF_INET) - return tcp_v4_tw_get_peer(sk); - - return inet_getpeer_v6(&tw6->tw_v6_daddr, 1); + /* If we don't have a valid cached route, or we're doing IP + * options which make the IPv6 header destination address + * different from our peer's, do not bother with this. + */ + if (!rt || !ipv6_addr_equal(&np->daddr, &rt->rt6i_dst.addr)) + return NULL; + return rt6_get_peer_create(rt); } static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, - .twsk_getpeer = tcp_v6_tw_get_peer, }; static const struct inet_connection_sock_af_ops ipv6_specific = { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8625fba96db9..d7494845efbf 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -99,9 +99,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, if (!xdst->u.rt6.rt6i_idev) return -ENODEV; - xdst->u.rt6.rt6i_peer = rt->rt6i_peer; - if (rt->rt6i_peer) - atomic_inc(&rt->rt6i_peer->refcnt); + rt6_transfer_peer(&xdst->u.rt6, rt); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ @@ -223,8 +221,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); - if (likely(xdst->u.rt6.rt6i_peer)) - inet_putpeer(xdst->u.rt6.rt6i_peer); + if (rt6_has_peer(&xdst->u.rt6)) { + struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6); + inet_putpeer(peer); + } xfrm_dst_destroy(xdst); } diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index f06947c4fa82..7152624ed5f1 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -523,7 +523,7 @@ void *hashbin_remove_first( hashbin_t *hashbin) * Dequeue the entry... */ dequeue_general( (irda_queue_t**) &hashbin->hb_queue[ bin ], - (irda_queue_t*) entry ); + entry); hashbin->hb_size--; entry->q_next = NULL; entry->q_prev = NULL; @@ -615,7 +615,7 @@ void* hashbin_remove( hashbin_t* hashbin, long hashv, const char* name) */ if ( found ) { dequeue_general( (irda_queue_t**) &hashbin->hb_queue[ bin ], - (irda_queue_t*) entry ); + entry); hashbin->hb_size--; /* @@ -685,7 +685,7 @@ void* hashbin_remove_this( hashbin_t* hashbin, irda_queue_t* entry) * Dequeue the entry... */ dequeue_general( (irda_queue_t**) &hashbin->hb_queue[ bin ], - (irda_queue_t*) entry ); + entry); hashbin->hb_size--; entry->q_next = NULL; entry->q_prev = NULL; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8ef6b9416cba..286366ef8930 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1522,8 +1522,8 @@ static int pppol2tp_session_getsockopt(struct sock *sk, * handler, according to whether the PPPoX socket is a for a regular session * or the special tunnel type. */ -static int pppol2tp_getsockopt(struct socket *sock, int level, - int optname, char __user *optval, int __user *optlen) +static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct l2tp_session *session; @@ -1535,7 +1535,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, if (level != SOL_PPPOL2TP) return udp_prot.getsockopt(sk, level, optname, optval, optlen); - if (get_user(len, (int __user *) optlen)) + if (get_user(len, optlen)) return -EFAULT; len = min_t(unsigned int, len, sizeof(int)); @@ -1568,7 +1568,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, err = pppol2tp_session_getsockopt(sk, session, optname, &val); err = -EFAULT; - if (put_user(len, (int __user *) optlen)) + if (put_user(len, optlen)) goto end_put_sess; if (copy_to_user((void __user *) optval, &val, len)) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 26ddb699d693..c649188314cc 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -145,15 +145,20 @@ static void sta_rx_agg_session_timer_expired(unsigned long data) struct tid_ampdu_rx *tid_rx; unsigned long timeout; + rcu_read_lock(); tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[*ptid]); - if (!tid_rx) + if (!tid_rx) { + rcu_read_unlock(); return; + } timeout = tid_rx->last_rx + TU_TO_JIFFIES(tid_rx->timeout); if (time_is_after_jiffies(timeout)) { mod_timer(&tid_rx->session_timer, timeout); + rcu_read_unlock(); return; } + rcu_read_unlock(); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 495831ee48f1..e9cecca5c44d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -533,16 +533,16 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, sinfo.filled = 0; sta_set_sinfo(sta, &sinfo); - if (sinfo.filled | STATION_INFO_TX_BITRATE) + if (sinfo.filled & STATION_INFO_TX_BITRATE) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); i++; - if (sinfo.filled | STATION_INFO_RX_BITRATE) + if (sinfo.filled & STATION_INFO_RX_BITRATE) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; - if (sinfo.filled | STATION_INFO_SIGNAL_AVG) + if (sinfo.filled & STATION_INFO_SIGNAL_AVG) data[i] = (u8)sinfo.signal_avg; i++; } else { diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d4c19a7773db..8664111d0566 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -637,6 +637,18 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_configure_filter(local); break; default: + mutex_lock(&local->mtx); + if (local->hw_roc_dev == sdata->dev && + local->hw_roc_channel) { + /* ignore return value since this is racy */ + drv_cancel_remain_on_channel(local); + ieee80211_queue_work(&local->hw, &local->hw_roc_done); + } + mutex_unlock(&local->mtx); + + flush_work(&local->hw_roc_start); + flush_work(&local->hw_roc_done); + flush_work(&sdata->work); /* * When we get here, the interface is marked down. diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 04c306308987..d94627c2929c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1220,6 +1220,22 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->vif.bss_conf.qos = true; } +static void __ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) +{ + lockdep_assert_held(&sdata->local->mtx); + + sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | + IEEE80211_STA_BEACON_POLL); + ieee80211_run_deferred_scan(sdata->local); +} + +static void ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) +{ + mutex_lock(&sdata->local->mtx); + __ieee80211_stop_poll(sdata); + mutex_unlock(&sdata->local->mtx); +} + static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, u16 capab, bool erp_valid, u8 erp) { @@ -1285,8 +1301,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE; /* just to be sure */ - sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + ieee80211_stop_poll(sdata); ieee80211_led_assoc(local, 1); @@ -1456,8 +1471,7 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) return; } - ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + __ieee80211_stop_poll(sdata); mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); @@ -1477,7 +1491,6 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); out: - ieee80211_run_deferred_scan(local); mutex_unlock(&local->mtx); } @@ -2408,7 +2421,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, net_dbg_ratelimited("%s: cancelling probereq poll due to a received beacon\n", sdata->name); #endif + mutex_lock(&local->mtx); ifmgd->flags &= ~IEEE80211_STA_BEACON_POLL; + ieee80211_run_deferred_scan(local); + mutex_unlock(&local->mtx); + mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); mutex_unlock(&local->iflist_mtx); @@ -2595,8 +2612,7 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[DEAUTH_DISASSOC_LEN]; - ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + ieee80211_stop_poll(sdata); ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, reason, false, frame_buf); @@ -2874,8 +2890,7 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) u32 flags; if (sdata->vif.type == NL80211_IFTYPE_STATION) { - sdata->u.mgd.flags &= ~(IEEE80211_STA_BEACON_POLL | - IEEE80211_STA_CONNECTION_POLL); + __ieee80211_stop_poll(sdata); /* let's probe the connection once */ flags = sdata->local->hw.flags; @@ -2944,7 +2959,10 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running)) add_timer(&ifmgd->chswitch_timer); ieee80211_sta_reset_beacon_monitor(sdata); + + mutex_lock(&sdata->local->mtx); ieee80211_restart_sta_timer(sdata); + mutex_unlock(&sdata->local->mtx); } #endif diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f054e94901a2..935aa4b6deee 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -234,6 +234,22 @@ static void ieee80211_hw_roc_done(struct work_struct *work) return; } + /* was never transmitted */ + if (local->hw_roc_skb) { + u64 cookie; + + cookie = local->hw_roc_cookie ^ 2; + + cfg80211_mgmt_tx_status(local->hw_roc_dev, cookie, + local->hw_roc_skb->data, + local->hw_roc_skb->len, false, + GFP_KERNEL); + + kfree_skb(local->hw_roc_skb); + local->hw_roc_skb = NULL; + local->hw_roc_skb_for_status = NULL; + } + if (!local->hw_roc_for_tx) cfg80211_remain_on_channel_expired(local->hw_roc_dev, local->hw_roc_cookie, diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 169da0742c81..6d90a562669f 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -114,8 +114,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, if (elems->tim && (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_DTIM))) { - struct ieee80211_tim_ie *tim_ie = - (struct ieee80211_tim_ie *)elems->tim; + struct ieee80211_tim_ie *tim_ie = elems->tim; bss->dtim_period = tim_ie->dtim_period; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_DTIM; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f5b1638fbf80..de455f8bbb91 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -378,7 +378,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) /* make the station visible */ sta_info_hash_add(local, sta); - list_add(&sta->list, &local->sta_list); + list_add_rcu(&sta->list, &local->sta_list); set_sta_flag(sta, WLAN_STA_INSERTED); @@ -688,7 +688,7 @@ int __must_check __sta_info_destroy(struct sta_info *sta) if (ret) return ret; - list_del(&sta->list); + list_del_rcu(&sta->list); mutex_lock(&local->key_mtx); for (i = 0; i < NUM_DEFAULT_KEYS; i++) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 847215bb2a6f..e453212fa17f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1737,7 +1737,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, __le16 fc; struct ieee80211_hdr hdr; struct ieee80211s_hdr mesh_hdr __maybe_unused; - struct mesh_path __maybe_unused *mppath = NULL; + struct mesh_path __maybe_unused *mppath = NULL, *mpath = NULL; const u8 *encaps_data; int encaps_len, skip_header_bytes; int nh_pos, h_pos; @@ -1803,8 +1803,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, goto fail; } rcu_read_lock(); - if (!is_multicast_ether_addr(skb->data)) - mppath = mpp_path_lookup(skb->data, sdata); + if (!is_multicast_ether_addr(skb->data)) { + mpath = mesh_path_lookup(skb->data, sdata); + if (!mpath) + mppath = mpp_path_lookup(skb->data, sdata); + } /* * Use address extension if it is a packet from diff --git a/net/mac80211/util.c b/net/mac80211/util.c index a44c6807df01..8dd4712620ff 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1271,7 +1271,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) enum ieee80211_sta_state state; for (state = IEEE80211_STA_NOTEXIST; - state < sta->sta_state - 1; state++) + state < sta->sta_state; state++) WARN_ON(drv_sta_state(local, sta->sdata, sta, state, state + 1)); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 7fd66dec859d..71d6ecb65926 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -823,7 +823,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } - kfree_skb(skb); + consume_skb(skb); skb = new_skb; old_iph = ip_hdr(skb); } @@ -942,7 +942,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } - kfree_skb(skb); + consume_skb(skb); skb = new_skb; old_iph = ipv6_hdr(skb); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 068f2e0ec58e..1ee2082b81b5 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -531,7 +531,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) tstamp = nf_conn_tstamp_find(ct); if (tstamp) { if (skb->tstamp.tv64 == 0) - __net_timestamp((struct sk_buff *)skb); + __net_timestamp(skb); tstamp->start = ktime_to_ns(skb->tstamp); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0f661745df0f..71ac6559e0c6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -592,7 +592,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; - p1->pkblk_start = (char *)pg_vec[0].buffer; + p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; @@ -824,8 +824,7 @@ static void prb_open_block(struct tpacket_kbdq_core *pkc1, h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; - pkc1->nxt_offset = (char *)(pkc1->pkblk_start + - BLK_PLUS_PRIV(pkc1->blk_sizeof_priv)); + pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; @@ -1018,7 +1017,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct tpacket_block_desc *pbd; char *curr, *end; - pkc = GET_PBDQC_FROM_RB(((struct packet_ring_buffer *)&po->rx_ring)); + pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ @@ -1044,7 +1043,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po, smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; - end = (char *) ((char *)pbd + pkc->kblk_size); + end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index 5d6b572a6704..a9206087b4d7 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -81,10 +81,6 @@ void rxrpc_UDP_error_report(struct sock *sk) _net("I/F MTU %u", mtu); } - /* ip_rt_frag_needed() may have eaten the info */ - if (mtu == 0) - mtu = ntohs(icmp_hdr(skb)->un.frag.mtu); - if (mtu == 0) { /* they didn't give us a size, estimate one */ if (mtu > 1500) { diff --git a/net/tipc/port.c b/net/tipc/port.c index 2ad37a4db376..a1e828989d7a 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -909,8 +909,8 @@ int tipc_createport(void *usr_handle, warn("Port creation failed, no memory\n"); return -ENOMEM; } - p_ptr = (struct tipc_port *)tipc_createport_raw(NULL, port_dispatcher, - port_wakeup, importance); + p_ptr = tipc_createport_raw(NULL, port_dispatcher, port_wakeup, + importance); if (!p_ptr) { kfree(up_ptr); return -ENOMEM; @@ -1078,8 +1078,7 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr) if (tp_ptr->connected) { tp_ptr->connected = 0; /* let timer expire on it's own to avoid deadlock! */ - tipc_nodesub_unsubscribe( - &((struct tipc_port *)tp_ptr)->subscription); + tipc_nodesub_unsubscribe(&tp_ptr->subscription); res = 0; } else { res = -ENOTCONN; @@ -1099,7 +1098,7 @@ int tipc_disconnect(u32 ref) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = tipc_disconnect_port((struct tipc_port *)p_ptr); + res = tipc_disconnect_port(p_ptr); tipc_port_unlock(p_ptr); return res; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 5577a447f531..11a863d81421 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -54,7 +54,7 @@ struct tipc_sock { }; #define tipc_sk(sk) ((struct tipc_sock *)(sk)) -#define tipc_sk_port(sk) ((struct tipc_port *)(tipc_sk(sk)->p)) +#define tipc_sk_port(sk) (tipc_sk(sk)->p) #define tipc_rx_ready(sock) (!skb_queue_empty(&sock->sk->sk_receive_queue) || \ (sock->state == SS_DISCONNECTING)) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 641f2e47f165..79981d97bc9c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -115,15 +115,24 @@ #include <net/checksum.h> #include <linux/security.h> -struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; +struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); DEFINE_SPINLOCK(unix_table_lock); EXPORT_SYMBOL_GPL(unix_table_lock); static atomic_long_t unix_nr_socks; -#define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) -#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash != UNIX_HASH_SIZE) +static struct hlist_head *unix_sockets_unbound(void *addr) +{ + unsigned long hash = (unsigned long)addr; + + hash ^= hash >> 16; + hash ^= hash >> 8; + hash %= UNIX_HASH_SIZE; + return &unix_socket_table[UNIX_HASH_SIZE + hash]; +} + +#define UNIX_ABSTRACT(sk) (unix_sk(sk)->addr->hash < UNIX_HASH_SIZE) #ifdef CONFIG_SECURITY_NETWORK static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb) @@ -645,7 +654,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); - unix_insert_socket(unix_sockets_unbound, sk); + unix_insert_socket(unix_sockets_unbound(sk), sk); out: if (sk == NULL) atomic_long_dec(&unix_nr_socks); @@ -2239,47 +2248,54 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, } #ifdef CONFIG_PROC_FS -static struct sock *first_unix_socket(int *i) + +#define BUCKET_SPACE (BITS_PER_LONG - (UNIX_HASH_BITS + 1) - 1) + +#define get_bucket(x) ((x) >> BUCKET_SPACE) +#define get_offset(x) ((x) & ((1L << BUCKET_SPACE) - 1)) +#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) + +static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) { - for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) { - if (!hlist_empty(&unix_socket_table[*i])) - return __sk_head(&unix_socket_table[*i]); + unsigned long offset = get_offset(*pos); + unsigned long bucket = get_bucket(*pos); + struct sock *sk; + unsigned long count = 0; + + for (sk = sk_head(&unix_socket_table[bucket]); sk; sk = sk_next(sk)) { + if (sock_net(sk) != seq_file_net(seq)) + continue; + if (++count == offset) + break; } - return NULL; + + return sk; } -static struct sock *next_unix_socket(int *i, struct sock *s) +static struct sock *unix_next_socket(struct seq_file *seq, + struct sock *sk, + loff_t *pos) { - struct sock *next = sk_next(s); - /* More in this chain? */ - if (next) - return next; - /* Look for next non-empty chain. */ - for ((*i)++; *i <= UNIX_HASH_SIZE; (*i)++) { - if (!hlist_empty(&unix_socket_table[*i])) - return __sk_head(&unix_socket_table[*i]); + unsigned long bucket; + + while (sk > (struct sock *)SEQ_START_TOKEN) { + sk = sk_next(sk); + if (!sk) + goto next_bucket; + if (sock_net(sk) == seq_file_net(seq)) + return sk; } - return NULL; -} -struct unix_iter_state { - struct seq_net_private p; - int i; -}; + do { + sk = unix_from_bucket(seq, pos); + if (sk) + return sk; -static struct sock *unix_seq_idx(struct seq_file *seq, loff_t pos) -{ - struct unix_iter_state *iter = seq->private; - loff_t off = 0; - struct sock *s; +next_bucket: + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); + } while (bucket < ARRAY_SIZE(unix_socket_table)); - for (s = first_unix_socket(&iter->i); s; s = next_unix_socket(&iter->i, s)) { - if (sock_net(s) != seq_file_net(seq)) - continue; - if (off == pos) - return s; - ++off; - } return NULL; } @@ -2287,22 +2303,20 @@ static void *unix_seq_start(struct seq_file *seq, loff_t *pos) __acquires(unix_table_lock) { spin_lock(&unix_table_lock); - return *pos ? unix_seq_idx(seq, *pos - 1) : SEQ_START_TOKEN; + + if (!*pos) + return SEQ_START_TOKEN; + + if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table)) + return NULL; + + return unix_next_socket(seq, NULL, pos); } static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct unix_iter_state *iter = seq->private; - struct sock *sk = v; ++*pos; - - if (v == SEQ_START_TOKEN) - sk = first_unix_socket(&iter->i); - else - sk = next_unix_socket(&iter->i, sk); - while (sk && (sock_net(sk) != seq_file_net(seq))) - sk = next_unix_socket(&iter->i, sk); - return sk; + return unix_next_socket(seq, v, pos); } static void unix_seq_stop(struct seq_file *seq, void *v) @@ -2365,7 +2379,7 @@ static const struct seq_operations unix_seq_ops = { static int unix_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &unix_seq_ops, - sizeof(struct unix_iter_state)); + sizeof(struct seq_net_private)); } static const struct file_operations unix_seq_fops = { diff --git a/net/unix/diag.c b/net/unix/diag.c index 47d3002737f5..7e8a24bff34a 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -195,7 +195,9 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) num = s_num = cb->args[1]; spin_lock(&unix_table_lock); - for (slot = s_slot; slot <= UNIX_HASH_SIZE; s_num = 0, slot++) { + for (slot = s_slot; + slot < ARRAY_SIZE(unix_socket_table); + s_num = 0, slot++) { struct sock *sk; struct hlist_node *node; @@ -228,7 +230,7 @@ static struct sock *unix_lookup_by_ino(int ino) struct sock *sk; spin_lock(&unix_table_lock); - for (i = 0; i <= UNIX_HASH_SIZE; i++) { + for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) { struct hlist_node *node; sk_for_each(sk, node, &unix_socket_table[i]) diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index d2a19b0ff71f..89baa3328411 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -42,6 +42,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) cfg80211_hold_bss(bss_from_pub(bss)); wdev->current_bss = bss_from_pub(bss); + wdev->sme_state = CFG80211_SME_CONNECTED; cfg80211_upload_connect_keys(wdev); nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, @@ -60,7 +61,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) struct cfg80211_event *ev; unsigned long flags; - CFG80211_DEV_WARN_ON(!wdev->ssid_len); + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTING); ev = kzalloc(sizeof(*ev), gfp); if (!ev) @@ -115,9 +116,11 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, #ifdef CONFIG_CFG80211_WEXT wdev->wext.ibss.channel = params->channel; #endif + wdev->sme_state = CFG80211_SME_CONNECTING; err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); if (err) { wdev->connect_keys = NULL; + wdev->sme_state = CFG80211_SME_IDLE; return err; } @@ -169,6 +172,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) } wdev->current_bss = NULL; + wdev->sme_state = CFG80211_SME_IDLE; wdev->ssid_len = 0; #ifdef CONFIG_CFG80211_WEXT if (!nowext) diff --git a/net/wireless/util.c b/net/wireless/util.c index 55d99466babb..8f2d68fc3a44 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -935,6 +935,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { struct wireless_dev *wdev_iter; + u32 used_iftypes = BIT(iftype); int num[NUM_NL80211_IFTYPES]; int total = 1; int i, j; @@ -961,6 +962,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, num[wdev_iter->iftype]++; total++; + used_iftypes |= BIT(wdev_iter->iftype); } mutex_unlock(&rdev->devlist_mtx); @@ -970,6 +972,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) { const struct ieee80211_iface_combination *c; struct ieee80211_iface_limit *limits; + u32 all_iftypes = 0; c = &rdev->wiphy.iface_combinations[i]; @@ -984,6 +987,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, if (rdev->wiphy.software_iftypes & BIT(iftype)) continue; for (j = 0; j < c->n_limits; j++) { + all_iftypes |= limits[j].types; if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < num[iftype]) @@ -991,7 +995,20 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, limits[j].max -= num[iftype]; } } - /* yay, it fits */ + + /* + * Finally check that all iftypes that we're currently + * using are actually part of this combination. If they + * aren't then we can't use this combination and have + * to continue to the next. + */ + if ((all_iftypes & used_iftypes) != used_iftypes) + goto cont; + + /* + * This combination covered all interface types and + * supported the requested numbers, so we're good. + */ kfree(limits); return 0; cont: |